diff options
author | Ingo Molnar <mingo@elte.hu> | 2008-07-18 19:53:16 +0200 |
---|---|---|
committer | Ingo Molnar <mingo@elte.hu> | 2008-07-18 19:53:16 +0200 |
commit | 9b610fda0df5d0f0b0c64242e37441ad1b384aac (patch) | |
tree | 0ea14b15f2e6546f37fe18d8ac3dc83077ec0e55 /arch/x86 | |
parent | nohz: prevent tick stop outside of the idle loop (diff) | |
parent | Merge branch 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/gi... (diff) | |
download | linux-9b610fda0df5d0f0b0c64242e37441ad1b384aac.tar.xz linux-9b610fda0df5d0f0b0c64242e37441ad1b384aac.zip |
Merge branch 'linus' into timers/nohz
Diffstat (limited to 'arch/x86')
246 files changed, 21779 insertions, 14163 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index dcbec34154cf..96e0c2ebc388 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -23,6 +23,8 @@ config X86 select HAVE_OPROFILE select HAVE_KPROBES select HAVE_KRETPROBES + select HAVE_DYNAMIC_FTRACE + select HAVE_FTRACE select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64) select HAVE_ARCH_KGDB if !X86_VOYAGER @@ -121,7 +123,7 @@ config ARCH_HAS_CACHE_LINE_SIZE def_bool y config HAVE_SETUP_PER_CPU_AREA - def_bool X86_64 || (X86_SMP && !X86_VOYAGER) + def_bool X86_64_SMP || (X86_SMP && !X86_VOYAGER) config HAVE_CPUMASK_OF_CPU_MAP def_bool X86_64_SMP @@ -168,6 +170,7 @@ config GENERIC_PENDING_IRQ config X86_SMP bool depends on SMP && ((X86_32 && !X86_VOYAGER) || X86_64) + select USE_GENERIC_SMP_HELPERS default y config X86_32_SMP @@ -181,12 +184,12 @@ config X86_64_SMP config X86_HT bool depends on SMP - depends on (X86_32 && !(X86_VISWS || X86_VOYAGER)) || X86_64 + depends on (X86_32 && !X86_VOYAGER) || X86_64 default y config X86_BIOS_REBOOT bool - depends on !X86_VISWS && !X86_VOYAGER + depends on !X86_VOYAGER default y config X86_TRAMPOLINE @@ -230,6 +233,26 @@ config SMP If you don't know what to do here, say N. +config X86_FIND_SMP_CONFIG + def_bool y + depends on X86_MPPARSE || X86_VOYAGER + +if ACPI +config X86_MPPARSE + def_bool y + bool "Enable MPS table" + depends on X86_LOCAL_APIC + help + For old smp systems that do not have proper acpi support. Newer systems + (esp with 64bit cpus) with acpi support, MADT and DSDT will override it +endif + +if !ACPI +config X86_MPPARSE + def_bool y + depends on X86_LOCAL_APIC +endif + choice prompt "Subarchitecture Type" default X86_PC @@ -251,7 +274,7 @@ config X86_ELAN config X86_VOYAGER bool "Voyager (NCR)" - depends on X86_32 && (SMP || BROKEN) + depends on X86_32 && (SMP || BROKEN) && !PCI help Voyager is an MCA-based 32-way capable SMP architecture proprietary to NCR Corp. Machine classes 345x/35xx/4100/51xx are Voyager-based. @@ -261,16 +284,27 @@ config X86_VOYAGER If you do not specifically know you have a Voyager based machine, say N here, otherwise the kernel you build will not be bootable. +config X86_GENERICARCH + bool "Generic architecture" + depends on X86_32 + help + This option compiles in the NUMAQ, Summit, bigsmp, ES7000, default + subarchitectures. It is intended for a generic binary kernel. + if you select them all, kernel will probe it one by one. and will + fallback to default. + +if X86_GENERICARCH + config X86_NUMAQ bool "NUMAQ (IBM/Sequent)" - depends on SMP && X86_32 + depends on SMP && X86_32 && PCI && X86_MPPARSE select NUMA help - This option is used for getting Linux to run on a (IBM/Sequent) NUMA - multiquad box. This changes the way that processors are bootstrapped, - and uses Clustered Logical APIC addressing mode instead of Flat Logical. - You will need a new lynxer.elf file to flash your firmware with - send - email to <Martin.Bligh@us.ibm.com>. + This option is used for getting Linux to run on a NUMAQ (IBM/Sequent) + NUMA multiquad box. This changes the way that processors are + bootstrapped, and uses Clustered Logical APIC addressing mode instead + of Flat Logical. You will need a new lynxer.elf file to flash your + firmware with - send email to <Martin.Bligh@us.ibm.com>. config X86_SUMMIT bool "Summit/EXA (IBM x440)" @@ -279,46 +313,21 @@ config X86_SUMMIT This option is needed for IBM systems that use the Summit/EXA chipset. In particular, it is needed for the x440. - If you don't have one of these computers, you should say N here. - If you want to build a NUMA kernel, you must select ACPI. +config X86_ES7000 + bool "Support for Unisys ES7000 IA32 series" + depends on X86_32 && SMP + help + Support for Unisys ES7000 systems. Say 'Y' here if this kernel is + supposed to run on an IA32-based Unisys ES7000 system. config X86_BIGSMP - bool "Support for other sub-arch SMP systems with more than 8 CPUs" + bool "Support for big SMP systems with more than 8 CPUs" depends on X86_32 && SMP help This option is needed for the systems that have more than 8 CPUs and if the system is not of any sub-arch type above. - If you don't have such a system, you should say N here. - -config X86_VISWS - bool "SGI 320/540 (Visual Workstation)" - depends on X86_32 - help - The SGI Visual Workstation series is an IA32-based workstation - based on SGI systems chips with some legacy PC hardware attached. - - Say Y here to create a kernel to run on the SGI 320 or 540. - - A kernel compiled for the Visual Workstation will not run on PCs - and vice versa. See <file:Documentation/sgi-visws.txt> for details. - -config X86_GENERICARCH - bool "Generic architecture (Summit, bigsmp, ES7000, default)" - depends on X86_32 - help - This option compiles in the Summit, bigsmp, ES7000, default subarchitectures. - It is intended for a generic binary kernel. - If you want a NUMA kernel, select ACPI. We need SRAT for NUMA. - -config X86_ES7000 - bool "Support for Unisys ES7000 IA32 series" - depends on X86_32 && SMP - help - Support for Unisys ES7000 systems. Say 'Y' here if this kernel is - supposed to run on an IA32-based Unisys ES7000 system. - Only choose this option if you have such a system, otherwise you - should say N here. +endif config X86_RDC321X bool "RDC R-321x SoC" @@ -337,7 +346,7 @@ config X86_RDC321X config X86_VSMP bool "Support for ScaleMP vSMP" select PARAVIRT - depends on X86_64 + depends on X86_64 && PCI help Support for ScaleMP vSMP systems. Say 'Y' here if this kernel is supposed to run on these EM64T-based machines. Only choose this option @@ -345,6 +354,18 @@ config X86_VSMP endchoice +config X86_VISWS + bool "SGI 320/540 (Visual Workstation)" + depends on X86_32 && PCI && !X86_VOYAGER && X86_MPPARSE && PCI_GODIRECT + help + The SGI Visual Workstation series is an IA32-based workstation + based on SGI systems chips with some legacy PC hardware attached. + + Say Y here to create a kernel to run on the SGI 320 or 540. + + A kernel compiled for the Visual Workstation will run on general + PCs as well. See <file:Documentation/sgi-visws.txt> for details. + config SCHED_NO_NO_OMIT_FRAME_POINTER def_bool y prompt "Single-depth WCHAN output" @@ -373,7 +394,7 @@ config VMI bool "VMI Guest support" select PARAVIRT depends on X86_32 - depends on !(X86_VISWS || X86_VOYAGER) + depends on !X86_VOYAGER help VMI provides a paravirtualized interface to the VMware ESX server (it could be used by other hypervisors in theory too, but is not @@ -383,7 +404,8 @@ config VMI config KVM_CLOCK bool "KVM paravirtualized clock" select PARAVIRT - depends on !(X86_VISWS || X86_VOYAGER) + select PARAVIRT_CLOCK + depends on !X86_VOYAGER help Turning on this option will allow you to run a paravirtualized clock when running over the KVM hypervisor. Instead of relying on a PIT @@ -394,7 +416,7 @@ config KVM_CLOCK config KVM_GUEST bool "KVM Guest support" select PARAVIRT - depends on !(X86_VISWS || X86_VOYAGER) + depends on !X86_VOYAGER help This option enables various optimizations for running under the KVM hypervisor. @@ -403,60 +425,45 @@ source "arch/x86/lguest/Kconfig" config PARAVIRT bool "Enable paravirtualization code" - depends on !(X86_VISWS || X86_VOYAGER) + depends on !X86_VOYAGER help This changes the kernel so it can modify itself when it is run under a hypervisor, potentially improving performance significantly over full virtualization. However, when run without a hypervisor the kernel is theoretically slower and slightly larger. +config PARAVIRT_CLOCK + bool + default n + endif -config MEMTEST_BOOTPARAM - bool "Memtest boot parameter" +config PARAVIRT_DEBUG + bool "paravirt-ops debugging" + depends on PARAVIRT && DEBUG_KERNEL + help + Enable to debug paravirt_ops internals. Specifically, BUG if + a paravirt_op is missing when it is called. + +config MEMTEST + bool "Memtest" depends on X86_64 - default y help This option adds a kernel parameter 'memtest', which allows memtest - to be disabled at boot. If this option is selected, memtest - functionality can be disabled with memtest=0 on the kernel - command line. The purpose of this option is to allow a single - kernel image to be distributed with memtest built in, but not - necessarily enabled. - - If you are unsure how to answer this question, answer Y. - -config MEMTEST_BOOTPARAM_VALUE - int "Memtest boot parameter default value (0-4)" - depends on MEMTEST_BOOTPARAM - range 0 4 - default 0 - help - This option sets the default value for the kernel parameter - 'memtest', which allows memtest to be disabled at boot. If this - option is set to 0 (zero), the memtest kernel parameter will - default to 0, disabling memtest at bootup. If this option is - set to 4, the memtest kernel parameter will default to 4, - enabling memtest at bootup, and use that as pattern number. - - If you are unsure how to answer this question, answer 0. - -config ACPI_SRAT - def_bool y - depends on X86_32 && ACPI && NUMA && (X86_SUMMIT || X86_GENERICARCH) - select ACPI_NUMA - -config HAVE_ARCH_PARSE_SRAT - def_bool y - depends on ACPI_SRAT + to be set. + memtest=0, mean disabled; -- default + memtest=1, mean do 1 test pattern; + ... + memtest=4, mean do 4 test patterns. + If you are unsure how to answer this question, answer N. config X86_SUMMIT_NUMA def_bool y - depends on X86_32 && NUMA && (X86_SUMMIT || X86_GENERICARCH) + depends on X86_32 && NUMA && X86_GENERICARCH config X86_CYCLONE_TIMER def_bool y - depends on X86_32 && X86_SUMMIT || X86_GENERICARCH + depends on X86_GENERICARCH config ES7000_CLUSTERED_APIC def_bool y @@ -544,6 +551,21 @@ config CALGARY_IOMMU_ENABLED_BY_DEFAULT Calgary anyway, pass 'iommu=calgary' on the kernel command line. If unsure, say Y. +config AMD_IOMMU + bool "AMD IOMMU support" + select SWIOTLB + depends on X86_64 && PCI && ACPI + help + With this option you can enable support for AMD IOMMU hardware in + your system. An IOMMU is a hardware component which provides + remapping of DMA memory accesses from devices. With an AMD IOMMU you + can isolate the the DMA memory of different devices and protect the + system from misbehaving device drivers or hardware. + + You can find out if your system has an AMD IOMMU if you look into + your BIOS for an option to enable it or if you have an IVRS ACPI + table. + # need this always selected by IOMMU for the VIA workaround config SWIOTLB bool @@ -555,21 +577,36 @@ config SWIOTLB 3 GB of memory. If unsure, say Y. config IOMMU_HELPER - def_bool (CALGARY_IOMMU || GART_IOMMU || SWIOTLB) + def_bool (CALGARY_IOMMU || GART_IOMMU || SWIOTLB || AMD_IOMMU) +config MAXSMP + bool "Configure Maximum number of SMP Processors and NUMA Nodes" + depends on X86_64 && SMP + default n + help + Configure maximum number of CPUS and NUMA Nodes for this architecture. + If unsure, say N. +if MAXSMP config NR_CPUS - int "Maximum number of CPUs (2-255)" - range 2 255 + int + default "4096" +endif + +if !MAXSMP +config NR_CPUS + int "Maximum number of CPUs (2-4096)" + range 2 4096 depends on SMP default "32" if X86_NUMAQ || X86_SUMMIT || X86_BIGSMP || X86_ES7000 default "8" help This allows you to specify the maximum number of CPUs which this - kernel will support. The maximum supported value is 255 and the + kernel will support. The maximum supported value is 4096 and the minimum value which makes sense is 2. This is purely to save memory - each supported CPU adds approximately eight kilobytes to the kernel image. +endif config SCHED_SMT bool "SMT (Hyperthreading) scheduler support" @@ -593,7 +630,7 @@ source "kernel/Kconfig.preempt" config X86_UP_APIC bool "Local APIC support on uniprocessors" - depends on X86_32 && !SMP && !(X86_VISWS || X86_VOYAGER || X86_GENERICARCH) + depends on X86_32 && !SMP && !(X86_VOYAGER || X86_GENERICARCH) help A local APIC (Advanced Programmable Interrupt Controller) is an integrated interrupt controller in the CPU. If you have a single-CPU @@ -618,11 +655,11 @@ config X86_UP_IOAPIC config X86_LOCAL_APIC def_bool y - depends on X86_64 || (X86_32 && (X86_UP_APIC || ((X86_VISWS || SMP) && !X86_VOYAGER) || X86_GENERICARCH)) + depends on X86_64 || (X86_32 && (X86_UP_APIC || (SMP && !X86_VOYAGER) || X86_GENERICARCH)) config X86_IO_APIC def_bool y - depends on X86_64 || (X86_32 && (X86_UP_IOAPIC || (SMP && !(X86_VISWS || X86_VOYAGER)) || X86_GENERICARCH)) + depends on X86_64 || (X86_32 && (X86_UP_IOAPIC || (SMP && !X86_VOYAGER) || X86_GENERICARCH)) config X86_VISWS_APIC def_bool y @@ -676,7 +713,7 @@ config X86_MCE_NONFATAL config X86_MCE_P4THERMAL bool "check for P4 thermal throttling interrupt." - depends on X86_32 && X86_MCE && (X86_UP_APIC || SMP) && !X86_VISWS + depends on X86_32 && X86_MCE && (X86_UP_APIC || SMP) help Enabling this feature will cause a message to be printed when the P4 enters thermal throttling. @@ -906,9 +943,9 @@ config X86_PAE config NUMA bool "Numa Memory Allocation and Scheduler Support (EXPERIMENTAL)" depends on SMP - depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || (X86_SUMMIT || X86_GENERICARCH) && ACPI) && EXPERIMENTAL) + depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || X86_BIGSMP || X86_SUMMIT && ACPI) && EXPERIMENTAL) default n if X86_PC - default y if (X86_NUMAQ || X86_SUMMIT) + default y if (X86_NUMAQ || X86_SUMMIT || X86_BIGSMP) help Enable NUMA (Non Uniform Memory Access) support. The kernel will try to allocate memory used by a CPU on the @@ -960,13 +997,25 @@ config NUMA_EMU into virtual nodes when booted with "numa=fake=N", where N is the number of nodes. This is only useful for debugging. +if MAXSMP + +config NODES_SHIFT + int + default "9" +endif + +if !MAXSMP config NODES_SHIFT - int "Max num nodes shift(1-15)" - range 1 15 if X86_64 + int "Maximum NUMA Nodes (as a power of 2)" + range 1 9 if X86_64 default "6" if X86_64 default "4" if X86_NUMAQ default "3" depends on NEED_MULTIPLE_NODES + help + Specify the maximum number of NUMA Nodes available on the target + system. Increases memory reserved to accomodate various tables. +endif config HAVE_ARCH_BOOTMEM_NODE def_bool y @@ -1085,6 +1134,37 @@ config MTRR See <file:Documentation/mtrr.txt> for more information. +config MTRR_SANITIZER + bool + prompt "MTRR cleanup support" + depends on MTRR + help + Convert MTRR layout from continuous to discrete, so X drivers can + add writeback entries. + + Can be disabled with disable_mtrr_cleanup on the kernel command line. + The largest mtrr entry size for a continous block can be set with + mtrr_chunk_size. + + If unsure, say N. + +config MTRR_SANITIZER_ENABLE_DEFAULT + int "MTRR cleanup enable value (0-1)" + range 0 1 + default "0" + depends on MTRR_SANITIZER + help + Enable mtrr cleanup default value + +config MTRR_SANITIZER_SPARE_REG_NR_DEFAULT + int "MTRR cleanup spare reg num (0-7)" + range 0 7 + default "1" + depends on MTRR_SANITIZER + help + mtrr cleanup spare entries default, it can be changed via + mtrr_spare_reg_nr=N on the kernel command line. + config X86_PAT bool prompt "x86 PAT support" @@ -1185,7 +1265,6 @@ config KEXEC config CRASH_DUMP bool "kernel crash dumps (EXPERIMENTAL)" - depends on EXPERIMENTAL depends on X86_64 || (X86_32 && HIGHMEM) help Generate crash dump after being started by kexec. @@ -1334,7 +1413,7 @@ config X86_APM_BOOT menuconfig APM tristate "APM (Advanced Power Management) BIOS support" - depends on X86_32 && PM_SLEEP && !X86_VISWS + depends on X86_32 && PM_SLEEP ---help--- APM is a BIOS specification for saving power using several different techniques. This is mostly useful for battery powered laptops with @@ -1470,8 +1549,7 @@ endmenu menu "Bus options (PCI etc.)" config PCI - bool "PCI support" if !X86_VISWS && !X86_VSMP - depends on !X86_VOYAGER + bool "PCI support" default y select ARCH_SUPPORTS_MSI if (X86_LOCAL_APIC && X86_IO_APIC) help @@ -1482,7 +1560,7 @@ config PCI choice prompt "PCI access mode" - depends on X86_32 && PCI && !X86_VISWS + depends on X86_32 && PCI default PCI_GOANY ---help--- On PCI systems, the BIOS can be used to detect the PCI devices and @@ -1508,32 +1586,31 @@ config PCI_GOMMCONFIG config PCI_GODIRECT bool "Direct" -config PCI_GOANY - bool "Any" - config PCI_GOOLPC bool "OLPC" depends on OLPC +config PCI_GOANY + bool "Any" + endchoice config PCI_BIOS def_bool y - depends on X86_32 && !X86_VISWS && PCI && (PCI_GOBIOS || PCI_GOANY) + depends on X86_32 && PCI && (PCI_GOBIOS || PCI_GOANY) # x86-64 doesn't support PCI BIOS access from long mode so always go direct. config PCI_DIRECT def_bool y - depends on PCI && (X86_64 || (PCI_GODIRECT || PCI_GOANY || PCI_GOOLPC) || X86_VISWS) + depends on PCI && (X86_64 || (PCI_GODIRECT || PCI_GOANY || PCI_GOOLPC)) config PCI_MMCONFIG def_bool y depends on X86_32 && PCI && ACPI && (PCI_GOMMCONFIG || PCI_GOANY) config PCI_OLPC - bool - depends on PCI && PCI_GOOLPC - default y + def_bool y + depends on PCI && OLPC && (PCI_GOOLPC || PCI_GOANY) config PCI_DOMAINS def_bool y @@ -1585,7 +1662,7 @@ if X86_32 config ISA bool "ISA support" - depends on !(X86_VOYAGER || X86_VISWS) + depends on !X86_VOYAGER help Find out whether you have ISA slots on your motherboard. ISA is the name of a bus system, i.e. the way the CPU talks to the other stuff @@ -1612,7 +1689,7 @@ config EISA source "drivers/eisa/Kconfig" config MCA - bool "MCA support" if !(X86_VISWS || X86_VOYAGER) + bool "MCA support" if !X86_VOYAGER default y if X86_VOYAGER help MicroChannel Architecture is found in some IBM PS/2 machines and diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 2ad6301849a1..abff1b84ed5b 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -344,7 +344,7 @@ config X86_F00F_BUG config X86_WP_WORKS_OK def_bool y - depends on X86_32 && !M386 + depends on !M386 config X86_INVLPG def_bool y @@ -399,6 +399,10 @@ config X86_TSC def_bool y depends on ((MWINCHIP3D || MWINCHIP2 || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2) && !X86_NUMAQ) || X86_64 +config X86_CMPXCHG64 + def_bool y + depends on X86_PAE || X86_64 + # this should be set for all -march=.. options where the compiler # generates cmov. config X86_CMOV diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index ac1e31ba4795..ae36bfa814e5 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -6,15 +6,27 @@ config TRACE_IRQFLAGS_SUPPORT source "lib/Kconfig.debug" config NONPROMISC_DEVMEM - bool "Disable promiscuous /dev/mem" + bool "Filter access to /dev/mem" help - The /dev/mem file by default only allows userspace access to PCI - space and the BIOS code and data regions. This is sufficient for - dosemu and X and all common users of /dev/mem. With this config - option, you allow userspace access to all of memory, including - kernel and userspace memory. Accidental access to this is - obviously disasterous, but specific access can be used by people - debugging the kernel. + If this option is left off, you allow userspace access to all + of memory, including kernel and userspace memory. Accidental + access to this is obviously disastrous, but specific access can + be used by people debugging the kernel. + + If this option is switched on, the /dev/mem file only allows + userspace access to PCI space and the BIOS code and data regions. + This is sufficient for dosemu and X and all common users of + /dev/mem. + + If in doubt, say Y. + +config X86_VERBOSE_BOOTUP + bool "Enable verbose x86 bootup info messages" + default y + help + Enables the informational output from the decompression stage + (e.g. bzImage) of the boot. If you disable this you will still + see errors. Disable this if you want silent bootup. config EARLY_PRINTK bool "Early printk" if EMBEDDED @@ -56,7 +68,7 @@ config DEBUG_PAGEALLOC config DEBUG_PER_CPU_MAPS bool "Debug access to per_cpu maps" depends on DEBUG_KERNEL - depends on X86_64_SMP + depends on X86_SMP default n help Say Y to verify that the per_cpu map being accessed has @@ -125,15 +137,6 @@ config 4KSTACKS on the VM subsystem for higher order allocations. This option will also use IRQ stacks to compensate for the reduced stackspace. -config X86_FIND_SMP_CONFIG - def_bool y - depends on X86_LOCAL_APIC || X86_VOYAGER - depends on X86_32 - -config X86_MPPARSE - def_bool y - depends on (X86_32 && (X86_LOCAL_APIC && !X86_VISWS)) || X86_64 - config DOUBLEFAULT default y bool "Enable doublefault exception handler" if EMBEDDED @@ -168,6 +171,33 @@ config IOMMU_LEAK Add a simple leak tracer to the IOMMU code. This is useful when you are debugging a buggy device driver that leaks IOMMU mappings. +config MMIOTRACE_HOOKS + bool + +config MMIOTRACE + bool "Memory mapped IO tracing" + depends on DEBUG_KERNEL && PCI + select TRACING + select MMIOTRACE_HOOKS + help + Mmiotrace traces Memory Mapped I/O access and is meant for + debugging and reverse engineering. It is called from the ioremap + implementation and works via page faults. Tracing is disabled by + default and can be enabled at run-time. + + See Documentation/tracers/mmiotrace.txt. + If you are not helping to develop drivers, say N. + +config MMIOTRACE_TEST + tristate "Test module for mmiotrace" + depends on MMIOTRACE && m + help + This is a dumb module for testing mmiotrace. It is very dangerous + as it will write garbage to IO memory starting at a given address. + However, it should be safe to use on e.g. unused portion of VRAM. + + Say N, unless you absolutely know what you are doing. + # # IO delay types: # diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 3cff3c894cf3..919ce21ea654 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -113,33 +113,11 @@ mcore-y := arch/x86/mach-default/ mflags-$(CONFIG_X86_VOYAGER) := -Iinclude/asm-x86/mach-voyager mcore-$(CONFIG_X86_VOYAGER) := arch/x86/mach-voyager/ -# VISWS subarch support -mflags-$(CONFIG_X86_VISWS) := -Iinclude/asm-x86/mach-visws -mcore-$(CONFIG_X86_VISWS) := arch/x86/mach-visws/ - -# NUMAQ subarch support -mflags-$(CONFIG_X86_NUMAQ) := -Iinclude/asm-x86/mach-numaq -mcore-$(CONFIG_X86_NUMAQ) := arch/x86/mach-default/ - -# BIGSMP subarch support -mflags-$(CONFIG_X86_BIGSMP) := -Iinclude/asm-x86/mach-bigsmp -mcore-$(CONFIG_X86_BIGSMP) := arch/x86/mach-default/ - -#Summit subarch support -mflags-$(CONFIG_X86_SUMMIT) := -Iinclude/asm-x86/mach-summit -mcore-$(CONFIG_X86_SUMMIT) := arch/x86/mach-default/ - # generic subarchitecture mflags-$(CONFIG_X86_GENERICARCH):= -Iinclude/asm-x86/mach-generic fcore-$(CONFIG_X86_GENERICARCH) += arch/x86/mach-generic/ mcore-$(CONFIG_X86_GENERICARCH) := arch/x86/mach-default/ - -# ES7000 subarch support -mflags-$(CONFIG_X86_ES7000) := -Iinclude/asm-x86/mach-es7000 -fcore-$(CONFIG_X86_ES7000) := arch/x86/mach-es7000/ -mcore-$(CONFIG_X86_ES7000) := arch/x86/mach-default/ - # RDC R-321x subarch support mflags-$(CONFIG_X86_RDC321X) := -Iinclude/asm-x86/mach-rdc321x mcore-$(CONFIG_X86_RDC321X) := arch/x86/mach-default/ @@ -160,6 +138,7 @@ KBUILD_AFLAGS += $(mflags-y) head-y := arch/x86/kernel/head_$(BITS).o head-y += arch/x86/kernel/head$(BITS).o +head-y += arch/x86/kernel/head.o head-y += arch/x86/kernel/init_task.o libs-y += arch/x86/lib/ @@ -210,12 +189,12 @@ all: bzImage # KBUILD_IMAGE specify target image being built KBUILD_IMAGE := $(boot)/bzImage -zImage zlilo zdisk: KBUILD_IMAGE := arch/x86/boot/zImage +zImage zlilo zdisk: KBUILD_IMAGE := $(boot)/zImage zImage bzImage: vmlinux $(Q)$(MAKE) $(build)=$(boot) $(KBUILD_IMAGE) $(Q)mkdir -p $(objtree)/arch/$(UTS_MACHINE)/boot - $(Q)ln -fsn ../../x86/boot/bzImage $(objtree)/arch/$(UTS_MACHINE)/boot/bzImage + $(Q)ln -fsn ../../x86/boot/bzImage $(objtree)/arch/$(UTS_MACHINE)/boot/$@ compressed: zImage diff --git a/arch/x86/boot/a20.c b/arch/x86/boot/a20.c index 90943f83e84d..4063d630deff 100644 --- a/arch/x86/boot/a20.c +++ b/arch/x86/boot/a20.c @@ -1,7 +1,7 @@ /* -*- linux-c -*- ------------------------------------------------------- * * * Copyright (C) 1991, 1992 Linus Torvalds - * Copyright 2007 rPath, Inc. - All Rights Reserved + * Copyright 2007-2008 rPath, Inc. - All Rights Reserved * * This file is part of the Linux kernel, and is made available under * the terms of the GNU General Public License version 2. @@ -95,6 +95,9 @@ static void enable_a20_kbc(void) outb(0xdf, 0x60); /* A20 on */ empty_8042(); + + outb(0xff, 0x64); /* Null command, but UHCI wants it */ + empty_8042(); } static void enable_a20_fast(void) @@ -115,8 +118,6 @@ static void enable_a20_fast(void) int enable_a20(void) { - int loops = A20_ENABLE_LOOPS; - #if defined(CONFIG_X86_ELAN) /* Elan croaks if we try to touch the KBC */ enable_a20_fast(); @@ -128,6 +129,7 @@ int enable_a20(void) enable_a20_kbc(); return 0; #else + int loops = A20_ENABLE_LOOPS; while (loops--) { /* First, check to see if A20 is already enabled (legacy free, etc.) */ diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index d8819efac81d..1d5dff4123e1 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -30,6 +30,7 @@ #include <asm/page.h> #include <asm/boot.h> #include <asm/msr.h> +#include <asm/processor-flags.h> #include <asm/asm-offsets.h> .section ".text.head" @@ -109,7 +110,7 @@ startup_32: /* Enable PAE mode */ xorl %eax, %eax - orl $(1 << 5), %eax + orl $(X86_CR4_PAE), %eax movl %eax, %cr4 /* @@ -170,7 +171,7 @@ startup_32: pushl %eax /* Enter paged protected Mode, activating Long Mode */ - movl $0x80000001, %eax /* Enable Paging and Protected mode */ + movl $(X86_CR0_PG | X86_CR0_PE), %eax /* Enable Paging and Protected mode */ movl %eax, %cr0 /* Jump from 32bit compatibility mode into 64bit mode. */ diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 90456cee47c3..bc5553b496f7 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -30,6 +30,7 @@ #include <asm/io.h> #include <asm/page.h> #include <asm/boot.h> +#include <asm/bootparam.h> /* WARNING!! * This code is compiled with -fPIC and it is relocated dynamically @@ -187,13 +188,8 @@ static void gzip_release(void **); /* * This is set up by the setup-routine at boot-time */ -static unsigned char *real_mode; /* Pointer to real-mode data */ - -#define RM_EXT_MEM_K (*(unsigned short *)(real_mode + 0x2)) -#ifndef STANDARD_MEMORY_BIOS_CALL -#define RM_ALT_MEM_K (*(unsigned long *)(real_mode + 0x1e0)) -#endif -#define RM_SCREEN_INFO (*(struct screen_info *)(real_mode+0)) +static struct boot_params *real_mode; /* Pointer to real-mode data */ +static int quiet; extern unsigned char input_data[]; extern int input_len; @@ -206,7 +202,8 @@ static void free(void *where); static void *memset(void *s, int c, unsigned n); static void *memcpy(void *dest, const void *src, unsigned n); -static void putstr(const char *); +static void __putstr(int, const char *); +#define putstr(__x) __putstr(0, __x) #ifdef CONFIG_X86_64 #define memptr long @@ -221,10 +218,6 @@ static char *vidmem; static int vidport; static int lines, cols; -#ifdef CONFIG_X86_NUMAQ -void *xquad_portio; -#endif - #include "../../../../lib/inflate.c" static void *malloc(int size) @@ -270,18 +263,24 @@ static void scroll(void) vidmem[i] = ' '; } -static void putstr(const char *s) +static void __putstr(int error, const char *s) { int x, y, pos; char c; +#ifndef CONFIG_X86_VERBOSE_BOOTUP + if (!error) + return; +#endif + #ifdef CONFIG_X86_32 - if (RM_SCREEN_INFO.orig_video_mode == 0 && lines == 0 && cols == 0) + if (real_mode->screen_info.orig_video_mode == 0 && + lines == 0 && cols == 0) return; #endif - x = RM_SCREEN_INFO.orig_x; - y = RM_SCREEN_INFO.orig_y; + x = real_mode->screen_info.orig_x; + y = real_mode->screen_info.orig_y; while ((c = *s++) != '\0') { if (c == '\n') { @@ -302,8 +301,8 @@ static void putstr(const char *s) } } - RM_SCREEN_INFO.orig_x = x; - RM_SCREEN_INFO.orig_y = y; + real_mode->screen_info.orig_x = x; + real_mode->screen_info.orig_y = y; pos = (x + cols * y) * 2; /* Update cursor position */ outb(14, vidport); @@ -366,9 +365,9 @@ static void flush_window(void) static void error(char *x) { - putstr("\n\n"); - putstr(x); - putstr("\n\n -- System halted"); + __putstr(1, "\n\n"); + __putstr(1, x); + __putstr(1, "\n\n -- System halted"); while (1) asm("hlt"); @@ -395,7 +394,8 @@ static void parse_elf(void *output) return; } - putstr("Parsing ELF... "); + if (!quiet) + putstr("Parsing ELF... "); phdrs = malloc(sizeof(*phdrs) * ehdr.e_phnum); if (!phdrs) @@ -430,7 +430,10 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap, { real_mode = rmode; - if (RM_SCREEN_INFO.orig_video_mode == 7) { + if (real_mode->hdr.loadflags & QUIET_FLAG) + quiet = 1; + + if (real_mode->screen_info.orig_video_mode == 7) { vidmem = (char *) 0xb0000; vidport = 0x3b4; } else { @@ -438,8 +441,8 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap, vidport = 0x3d4; } - lines = RM_SCREEN_INFO.orig_video_lines; - cols = RM_SCREEN_INFO.orig_video_cols; + lines = real_mode->screen_info.orig_video_lines; + cols = real_mode->screen_info.orig_video_cols; window = output; /* Output buffer (Normally at 1M) */ free_mem_ptr = heap; /* Heap */ @@ -465,9 +468,11 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap, #endif makecrc(); - putstr("\nDecompressing Linux... "); + if (!quiet) + putstr("\nDecompressing Linux... "); gunzip(); parse_elf(output); - putstr("done.\nBooting the kernel.\n"); + if (!quiet) + putstr("done.\nBooting the kernel.\n"); return; } diff --git a/arch/x86/boot/compressed/relocs.c b/arch/x86/boot/compressed/relocs.c index edaadea90aaf..a1310c52fc0c 100644 --- a/arch/x86/boot/compressed/relocs.c +++ b/arch/x86/boot/compressed/relocs.c @@ -10,16 +10,20 @@ #define USE_BSD #include <endian.h> -#define MAX_SHDRS 100 #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) static Elf32_Ehdr ehdr; -static Elf32_Shdr shdr[MAX_SHDRS]; -static Elf32_Sym *symtab[MAX_SHDRS]; -static Elf32_Rel *reltab[MAX_SHDRS]; -static char *strtab[MAX_SHDRS]; static unsigned long reloc_count, reloc_idx; static unsigned long *relocs; +struct section { + Elf32_Shdr shdr; + struct section *link; + Elf32_Sym *symtab; + Elf32_Rel *reltab; + char *strtab; +}; +static struct section *secs; + /* * Following symbols have been audited. There values are constant and do * not change if bzImage is loaded at a different physical address than @@ -35,7 +39,7 @@ static int is_safe_abs_reloc(const char* sym_name) { int i; - for(i = 0; i < ARRAY_SIZE(safe_abs_relocs); i++) { + for (i = 0; i < ARRAY_SIZE(safe_abs_relocs); i++) { if (!strcmp(sym_name, safe_abs_relocs[i])) /* Match found */ return 1; @@ -137,10 +141,10 @@ static const char *sec_name(unsigned shndx) { const char *sec_strtab; const char *name; - sec_strtab = strtab[ehdr.e_shstrndx]; + sec_strtab = secs[ehdr.e_shstrndx].strtab; name = "<noname>"; if (shndx < ehdr.e_shnum) { - name = sec_strtab + shdr[shndx].sh_name; + name = sec_strtab + secs[shndx].shdr.sh_name; } else if (shndx == SHN_ABS) { name = "ABSOLUTE"; @@ -159,7 +163,7 @@ static const char *sym_name(const char *sym_strtab, Elf32_Sym *sym) name = sym_strtab + sym->st_name; } else { - name = sec_name(shdr[sym->st_shndx].sh_name); + name = sec_name(secs[sym->st_shndx].shdr.sh_name); } return name; } @@ -244,29 +248,34 @@ static void read_ehdr(FILE *fp) static void read_shdrs(FILE *fp) { int i; - if (ehdr.e_shnum > MAX_SHDRS) { - die("%d section headers supported: %d\n", - ehdr.e_shnum, MAX_SHDRS); + Elf32_Shdr shdr; + + secs = calloc(ehdr.e_shnum, sizeof(struct section)); + if (!secs) { + die("Unable to allocate %d section headers\n", + ehdr.e_shnum); } if (fseek(fp, ehdr.e_shoff, SEEK_SET) < 0) { die("Seek to %d failed: %s\n", ehdr.e_shoff, strerror(errno)); } - if (fread(&shdr, sizeof(shdr[0]), ehdr.e_shnum, fp) != ehdr.e_shnum) { - die("Cannot read ELF section headers: %s\n", - strerror(errno)); - } - for(i = 0; i < ehdr.e_shnum; i++) { - shdr[i].sh_name = elf32_to_cpu(shdr[i].sh_name); - shdr[i].sh_type = elf32_to_cpu(shdr[i].sh_type); - shdr[i].sh_flags = elf32_to_cpu(shdr[i].sh_flags); - shdr[i].sh_addr = elf32_to_cpu(shdr[i].sh_addr); - shdr[i].sh_offset = elf32_to_cpu(shdr[i].sh_offset); - shdr[i].sh_size = elf32_to_cpu(shdr[i].sh_size); - shdr[i].sh_link = elf32_to_cpu(shdr[i].sh_link); - shdr[i].sh_info = elf32_to_cpu(shdr[i].sh_info); - shdr[i].sh_addralign = elf32_to_cpu(shdr[i].sh_addralign); - shdr[i].sh_entsize = elf32_to_cpu(shdr[i].sh_entsize); + for (i = 0; i < ehdr.e_shnum; i++) { + struct section *sec = &secs[i]; + if (fread(&shdr, sizeof shdr, 1, fp) != 1) + die("Cannot read ELF section headers %d/%d: %s\n", + i, ehdr.e_shnum, strerror(errno)); + sec->shdr.sh_name = elf32_to_cpu(shdr.sh_name); + sec->shdr.sh_type = elf32_to_cpu(shdr.sh_type); + sec->shdr.sh_flags = elf32_to_cpu(shdr.sh_flags); + sec->shdr.sh_addr = elf32_to_cpu(shdr.sh_addr); + sec->shdr.sh_offset = elf32_to_cpu(shdr.sh_offset); + sec->shdr.sh_size = elf32_to_cpu(shdr.sh_size); + sec->shdr.sh_link = elf32_to_cpu(shdr.sh_link); + sec->shdr.sh_info = elf32_to_cpu(shdr.sh_info); + sec->shdr.sh_addralign = elf32_to_cpu(shdr.sh_addralign); + sec->shdr.sh_entsize = elf32_to_cpu(shdr.sh_entsize); + if (sec->shdr.sh_link < ehdr.e_shnum) + sec->link = &secs[sec->shdr.sh_link]; } } @@ -274,20 +283,22 @@ static void read_shdrs(FILE *fp) static void read_strtabs(FILE *fp) { int i; - for(i = 0; i < ehdr.e_shnum; i++) { - if (shdr[i].sh_type != SHT_STRTAB) { + for (i = 0; i < ehdr.e_shnum; i++) { + struct section *sec = &secs[i]; + if (sec->shdr.sh_type != SHT_STRTAB) { continue; } - strtab[i] = malloc(shdr[i].sh_size); - if (!strtab[i]) { + sec->strtab = malloc(sec->shdr.sh_size); + if (!sec->strtab) { die("malloc of %d bytes for strtab failed\n", - shdr[i].sh_size); + sec->shdr.sh_size); } - if (fseek(fp, shdr[i].sh_offset, SEEK_SET) < 0) { + if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) { die("Seek to %d failed: %s\n", - shdr[i].sh_offset, strerror(errno)); + sec->shdr.sh_offset, strerror(errno)); } - if (fread(strtab[i], 1, shdr[i].sh_size, fp) != shdr[i].sh_size) { + if (fread(sec->strtab, 1, sec->shdr.sh_size, fp) + != sec->shdr.sh_size) { die("Cannot read symbol table: %s\n", strerror(errno)); } @@ -297,28 +308,31 @@ static void read_strtabs(FILE *fp) static void read_symtabs(FILE *fp) { int i,j; - for(i = 0; i < ehdr.e_shnum; i++) { - if (shdr[i].sh_type != SHT_SYMTAB) { + for (i = 0; i < ehdr.e_shnum; i++) { + struct section *sec = &secs[i]; + if (sec->shdr.sh_type != SHT_SYMTAB) { continue; } - symtab[i] = malloc(shdr[i].sh_size); - if (!symtab[i]) { + sec->symtab = malloc(sec->shdr.sh_size); + if (!sec->symtab) { die("malloc of %d bytes for symtab failed\n", - shdr[i].sh_size); + sec->shdr.sh_size); } - if (fseek(fp, shdr[i].sh_offset, SEEK_SET) < 0) { + if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) { die("Seek to %d failed: %s\n", - shdr[i].sh_offset, strerror(errno)); + sec->shdr.sh_offset, strerror(errno)); } - if (fread(symtab[i], 1, shdr[i].sh_size, fp) != shdr[i].sh_size) { + if (fread(sec->symtab, 1, sec->shdr.sh_size, fp) + != sec->shdr.sh_size) { die("Cannot read symbol table: %s\n", strerror(errno)); } - for(j = 0; j < shdr[i].sh_size/sizeof(symtab[i][0]); j++) { - symtab[i][j].st_name = elf32_to_cpu(symtab[i][j].st_name); - symtab[i][j].st_value = elf32_to_cpu(symtab[i][j].st_value); - symtab[i][j].st_size = elf32_to_cpu(symtab[i][j].st_size); - symtab[i][j].st_shndx = elf16_to_cpu(symtab[i][j].st_shndx); + for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Sym); j++) { + Elf32_Sym *sym = &sec->symtab[j]; + sym->st_name = elf32_to_cpu(sym->st_name); + sym->st_value = elf32_to_cpu(sym->st_value); + sym->st_size = elf32_to_cpu(sym->st_size); + sym->st_shndx = elf16_to_cpu(sym->st_shndx); } } } @@ -327,26 +341,29 @@ static void read_symtabs(FILE *fp) static void read_relocs(FILE *fp) { int i,j; - for(i = 0; i < ehdr.e_shnum; i++) { - if (shdr[i].sh_type != SHT_REL) { + for (i = 0; i < ehdr.e_shnum; i++) { + struct section *sec = &secs[i]; + if (sec->shdr.sh_type != SHT_REL) { continue; } - reltab[i] = malloc(shdr[i].sh_size); - if (!reltab[i]) { + sec->reltab = malloc(sec->shdr.sh_size); + if (!sec->reltab) { die("malloc of %d bytes for relocs failed\n", - shdr[i].sh_size); + sec->shdr.sh_size); } - if (fseek(fp, shdr[i].sh_offset, SEEK_SET) < 0) { + if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) { die("Seek to %d failed: %s\n", - shdr[i].sh_offset, strerror(errno)); + sec->shdr.sh_offset, strerror(errno)); } - if (fread(reltab[i], 1, shdr[i].sh_size, fp) != shdr[i].sh_size) { + if (fread(sec->reltab, 1, sec->shdr.sh_size, fp) + != sec->shdr.sh_size) { die("Cannot read symbol table: %s\n", strerror(errno)); } - for(j = 0; j < shdr[i].sh_size/sizeof(reltab[0][0]); j++) { - reltab[i][j].r_offset = elf32_to_cpu(reltab[i][j].r_offset); - reltab[i][j].r_info = elf32_to_cpu(reltab[i][j].r_info); + for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Rel); j++) { + Elf32_Rel *rel = &sec->reltab[j]; + rel->r_offset = elf32_to_cpu(rel->r_offset); + rel->r_info = elf32_to_cpu(rel->r_info); } } } @@ -357,19 +374,21 @@ static void print_absolute_symbols(void) int i; printf("Absolute symbols\n"); printf(" Num: Value Size Type Bind Visibility Name\n"); - for(i = 0; i < ehdr.e_shnum; i++) { + for (i = 0; i < ehdr.e_shnum; i++) { + struct section *sec = &secs[i]; char *sym_strtab; Elf32_Sym *sh_symtab; int j; - if (shdr[i].sh_type != SHT_SYMTAB) { + + if (sec->shdr.sh_type != SHT_SYMTAB) { continue; } - sh_symtab = symtab[i]; - sym_strtab = strtab[shdr[i].sh_link]; - for(j = 0; j < shdr[i].sh_size/sizeof(symtab[0][0]); j++) { + sh_symtab = sec->symtab; + sym_strtab = sec->link->strtab; + for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Sym); j++) { Elf32_Sym *sym; const char *name; - sym = &symtab[i][j]; + sym = &sec->symtab[j]; name = sym_name(sym_strtab, sym); if (sym->st_shndx != SHN_ABS) { continue; @@ -389,26 +408,27 @@ static void print_absolute_relocs(void) { int i, printed = 0; - for(i = 0; i < ehdr.e_shnum; i++) { + for (i = 0; i < ehdr.e_shnum; i++) { + struct section *sec = &secs[i]; + struct section *sec_applies, *sec_symtab; char *sym_strtab; Elf32_Sym *sh_symtab; - unsigned sec_applies, sec_symtab; int j; - if (shdr[i].sh_type != SHT_REL) { + if (sec->shdr.sh_type != SHT_REL) { continue; } - sec_symtab = shdr[i].sh_link; - sec_applies = shdr[i].sh_info; - if (!(shdr[sec_applies].sh_flags & SHF_ALLOC)) { + sec_symtab = sec->link; + sec_applies = &secs[sec->shdr.sh_info]; + if (!(sec_applies->shdr.sh_flags & SHF_ALLOC)) { continue; } - sh_symtab = symtab[sec_symtab]; - sym_strtab = strtab[shdr[sec_symtab].sh_link]; - for(j = 0; j < shdr[i].sh_size/sizeof(reltab[0][0]); j++) { + sh_symtab = sec_symtab->symtab; + sym_strtab = sec_symtab->link->strtab; + for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Rel); j++) { Elf32_Rel *rel; Elf32_Sym *sym; const char *name; - rel = &reltab[i][j]; + rel = &sec->reltab[j]; sym = &sh_symtab[ELF32_R_SYM(rel->r_info)]; name = sym_name(sym_strtab, sym); if (sym->st_shndx != SHN_ABS) { @@ -456,26 +476,28 @@ static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym)) { int i; /* Walk through the relocations */ - for(i = 0; i < ehdr.e_shnum; i++) { + for (i = 0; i < ehdr.e_shnum; i++) { char *sym_strtab; Elf32_Sym *sh_symtab; - unsigned sec_applies, sec_symtab; + struct section *sec_applies, *sec_symtab; int j; - if (shdr[i].sh_type != SHT_REL) { + struct section *sec = &secs[i]; + + if (sec->shdr.sh_type != SHT_REL) { continue; } - sec_symtab = shdr[i].sh_link; - sec_applies = shdr[i].sh_info; - if (!(shdr[sec_applies].sh_flags & SHF_ALLOC)) { + sec_symtab = sec->link; + sec_applies = &secs[sec->shdr.sh_info]; + if (!(sec_applies->shdr.sh_flags & SHF_ALLOC)) { continue; } - sh_symtab = symtab[sec_symtab]; - sym_strtab = strtab[shdr[sec_symtab].sh_link]; - for(j = 0; j < shdr[i].sh_size/sizeof(reltab[0][0]); j++) { + sh_symtab = sec_symtab->symtab; + sym_strtab = sec->link->strtab; + for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Rel); j++) { Elf32_Rel *rel; Elf32_Sym *sym; unsigned r_type; - rel = &reltab[i][j]; + rel = &sec->reltab[j]; sym = &sh_symtab[ELF32_R_SYM(rel->r_info)]; r_type = ELF32_R_TYPE(rel->r_info); /* Don't visit relocations to absolute symbols */ @@ -539,7 +561,7 @@ static void emit_relocs(int as_text) */ printf(".section \".data.reloc\",\"a\"\n"); printf(".balign 4\n"); - for(i = 0; i < reloc_count; i++) { + for (i = 0; i < reloc_count; i++) { printf("\t .long 0x%08lx\n", relocs[i]); } printf("\n"); @@ -550,7 +572,7 @@ static void emit_relocs(int as_text) /* Print a stop */ printf("%c%c%c%c", buf[0], buf[1], buf[2], buf[3]); /* Now print each relocation */ - for(i = 0; i < reloc_count; i++) { + for (i = 0; i < reloc_count; i++) { buf[0] = (relocs[i] >> 0) & 0xff; buf[1] = (relocs[i] >> 8) & 0xff; buf[2] = (relocs[i] >> 16) & 0xff; @@ -577,7 +599,7 @@ int main(int argc, char **argv) show_absolute_relocs = 0; as_text = 0; fname = NULL; - for(i = 1; i < argc; i++) { + for (i = 1; i < argc; i++) { char *arg = argv[i]; if (*arg == '-') { if (strcmp(argv[1], "--abs-syms") == 0) { diff --git a/arch/x86/boot/cpu.c b/arch/x86/boot/cpu.c index 00e19edd852c..92d6fd73dc7d 100644 --- a/arch/x86/boot/cpu.c +++ b/arch/x86/boot/cpu.c @@ -28,6 +28,8 @@ static char *cpu_name(int level) if (level == 64) { return "x86-64"; } else { + if (level == 15) + level = 6; sprintf(buf, "i%d86", level); return buf; } diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c index 77569a4a3be1..2296164b54d2 100644 --- a/arch/x86/boot/main.c +++ b/arch/x86/boot/main.c @@ -165,6 +165,10 @@ void main(void) /* Set the video mode */ set_video(); + /* Parse command line for 'quiet' and pass it to decompressor. */ + if (cmdline_find_option_bool("quiet")) + boot_params.hdr.loadflags |= QUIET_FLAG; + /* Do the last things and invoke protected mode */ go_to_protected_mode(); } diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c index acad32eb4290..53165c97336b 100644 --- a/arch/x86/boot/memory.c +++ b/arch/x86/boot/memory.c @@ -13,6 +13,7 @@ */ #include "boot.h" +#include <linux/kernel.h> #define SMAP 0x534d4150 /* ASCII "SMAP" */ @@ -53,7 +54,7 @@ static int detect_memory_e820(void) count++; desc++; - } while (next && count < E820MAX); + } while (next && count < ARRAY_SIZE(boot_params.e820_map)); return boot_params.e820_entries = count; } diff --git a/arch/x86/boot/pmjump.S b/arch/x86/boot/pmjump.S index ab049d40a884..141b6e20ed31 100644 --- a/arch/x86/boot/pmjump.S +++ b/arch/x86/boot/pmjump.S @@ -33,6 +33,8 @@ protected_mode_jump: movw %cs, %bx shll $4, %ebx addl %ebx, 2f + jmp 1f # Short jump to serialize on 386/486 +1: movw $__BOOT_DS, %cx movw $__BOOT_TSS, %di @@ -40,8 +42,6 @@ protected_mode_jump: movl %cr0, %edx orb $X86_CR0_PE, %dl # Protected mode movl %edx, %cr0 - jmp 1f # Short jump to serialize on 386/486 -1: # Transition to 32-bit mode .byte 0x66, 0xea # ljmpl opcode diff --git a/arch/x86/boot/video-vga.c b/arch/x86/boot/video-vga.c index 40ecb8d7688c..b939cb476dec 100644 --- a/arch/x86/boot/video-vga.c +++ b/arch/x86/boot/video-vga.c @@ -259,8 +259,7 @@ static int vga_probe(void) return mode_count[adapter]; } -__videocard video_vga = -{ +__videocard video_vga = { .card_name = "VGA", .probe = vga_probe, .set_mode = vga_set_mode, diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index ad7ddaaff588..9bc34e2033ec 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -1,54 +1,103 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.22-git14 -# Fri Jul 20 09:53:15 2007 +# Linux kernel version: 2.6.26-rc1 +# Sun May 4 19:59:02 2008 # +# CONFIG_64BIT is not set CONFIG_X86_32=y +# CONFIG_X86_64 is not set +CONFIG_X86=y +CONFIG_DEFCONFIG_LIST="arch/x86/configs/i386_defconfig" +# CONFIG_GENERIC_LOCKBREAK is not set CONFIG_GENERIC_TIME=y +CONFIG_GENERIC_CMOS_UPDATE=y CONFIG_CLOCKSOURCE_WATCHDOG=y CONFIG_GENERIC_CLOCKEVENTS=y CONFIG_GENERIC_CLOCKEVENTS_BROADCAST=y CONFIG_LOCKDEP_SUPPORT=y CONFIG_STACKTRACE_SUPPORT=y -CONFIG_SEMAPHORE_SLEEPERS=y -CONFIG_X86=y +CONFIG_HAVE_LATENCYTOP_SUPPORT=y +CONFIG_FAST_CMPXCHG_LOCAL=y CONFIG_MMU=y CONFIG_ZONE_DMA=y -CONFIG_QUICKLIST=y CONFIG_GENERIC_ISA_DMA=y CONFIG_GENERIC_IOMAP=y CONFIG_GENERIC_BUG=y CONFIG_GENERIC_HWEIGHT=y +# CONFIG_GENERIC_GPIO is not set CONFIG_ARCH_MAY_HAVE_PC_FDC=y -CONFIG_DMI=y -CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" +# CONFIG_RWSEM_GENERIC_SPINLOCK is not set +CONFIG_RWSEM_XCHGADD_ALGORITHM=y +# CONFIG_ARCH_HAS_ILOG2_U32 is not set +# CONFIG_ARCH_HAS_ILOG2_U64 is not set +CONFIG_ARCH_HAS_CPU_IDLE_WAIT=y +CONFIG_GENERIC_CALIBRATE_DELAY=y +# CONFIG_GENERIC_TIME_VSYSCALL is not set +CONFIG_ARCH_HAS_CPU_RELAX=y +CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y +CONFIG_HAVE_SETUP_PER_CPU_AREA=y +# CONFIG_HAVE_CPUMASK_OF_CPU_MAP is not set +CONFIG_ARCH_HIBERNATION_POSSIBLE=y +CONFIG_ARCH_SUSPEND_POSSIBLE=y +# CONFIG_ZONE_DMA32 is not set +CONFIG_ARCH_POPULATES_NODE_MAP=y +# CONFIG_AUDIT_ARCH is not set +CONFIG_ARCH_SUPPORTS_AOUT=y +CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING=y +CONFIG_GENERIC_HARDIRQS=y +CONFIG_GENERIC_IRQ_PROBE=y +CONFIG_GENERIC_PENDING_IRQ=y +CONFIG_X86_SMP=y +CONFIG_X86_32_SMP=y +CONFIG_X86_HT=y +CONFIG_X86_BIOS_REBOOT=y +CONFIG_X86_TRAMPOLINE=y +CONFIG_KTIME_SCALAR=y # -# Code maturity level options +# General setup # CONFIG_EXPERIMENTAL=y CONFIG_LOCK_KERNEL=y CONFIG_INIT_ENV_ARG_LIMIT=32 - -# -# General setup -# CONFIG_LOCALVERSION="" -CONFIG_LOCALVERSION_AUTO=y +# CONFIG_LOCALVERSION_AUTO is not set CONFIG_SWAP=y CONFIG_SYSVIPC=y CONFIG_SYSVIPC_SYSCTL=y CONFIG_POSIX_MQUEUE=y -# CONFIG_BSD_PROCESS_ACCT is not set -# CONFIG_TASKSTATS is not set -# CONFIG_USER_NS is not set -# CONFIG_AUDIT is not set -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_LOG_BUF_SHIFT=18 -# CONFIG_CPUSETS is not set -CONFIG_SYSFS_DEPRECATED=y +CONFIG_BSD_PROCESS_ACCT=y +# CONFIG_BSD_PROCESS_ACCT_V3 is not set +CONFIG_TASKSTATS=y +CONFIG_TASK_DELAY_ACCT=y +CONFIG_TASK_XACCT=y +CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_AUDIT=y +CONFIG_AUDITSYSCALL=y +CONFIG_AUDIT_TREE=y +# CONFIG_IKCONFIG is not set +CONFIG_LOG_BUF_SHIFT=17 +CONFIG_CGROUPS=y +# CONFIG_CGROUP_DEBUG is not set +CONFIG_CGROUP_NS=y +# CONFIG_CGROUP_DEVICE is not set +CONFIG_CPUSETS=y +CONFIG_GROUP_SCHED=y +CONFIG_FAIR_GROUP_SCHED=y +# CONFIG_RT_GROUP_SCHED is not set +# CONFIG_USER_SCHED is not set +CONFIG_CGROUP_SCHED=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_RESOURCE_COUNTERS=y +# CONFIG_CGROUP_MEM_RES_CTLR is not set +# CONFIG_SYSFS_DEPRECATED_V2 is not set +CONFIG_PROC_PID_CPUSET=y CONFIG_RELAY=y +CONFIG_NAMESPACES=y +CONFIG_UTS_NS=y +CONFIG_IPC_NS=y +CONFIG_USER_NS=y +CONFIG_PID_NS=y CONFIG_BLK_DEV_INITRD=y CONFIG_INITRAMFS_SOURCE="" CONFIG_CC_OPTIMIZE_FOR_SIZE=y @@ -56,13 +105,15 @@ CONFIG_SYSCTL=y # CONFIG_EMBEDDED is not set CONFIG_UID16=y CONFIG_SYSCTL_SYSCALL=y +CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_KALLSYMS=y CONFIG_KALLSYMS_ALL=y -# CONFIG_KALLSYMS_EXTRA_PASS is not set +CONFIG_KALLSYMS_EXTRA_PASS=y CONFIG_HOTPLUG=y CONFIG_PRINTK=y CONFIG_BUG=y CONFIG_ELF_CORE=y +# CONFIG_COMPAT_BRK is not set CONFIG_BASE_FULL=y CONFIG_FUTEX=y CONFIG_ANON_INODES=y @@ -76,6 +127,17 @@ CONFIG_SLUB_DEBUG=y # CONFIG_SLAB is not set CONFIG_SLUB=y # CONFIG_SLOB is not set +CONFIG_PROFILING=y +CONFIG_MARKERS=y +# CONFIG_OPROFILE is not set +CONFIG_HAVE_OPROFILE=y +CONFIG_KPROBES=y +CONFIG_KRETPROBES=y +CONFIG_HAVE_KPROBES=y +CONFIG_HAVE_KRETPROBES=y +# CONFIG_HAVE_DMA_ATTRS is not set +CONFIG_PROC_PAGE_MONITOR=y +CONFIG_SLABINFO=y CONFIG_RT_MUTEXES=y # CONFIG_TINY_SHMEM is not set CONFIG_BASE_SMALL=0 @@ -87,10 +149,10 @@ CONFIG_MODULE_FORCE_UNLOAD=y # CONFIG_KMOD is not set CONFIG_STOP_MACHINE=y CONFIG_BLOCK=y -CONFIG_LBD=y -# CONFIG_BLK_DEV_IO_TRACE is not set +# CONFIG_LBD is not set +CONFIG_BLK_DEV_IO_TRACE=y # CONFIG_LSF is not set -# CONFIG_BLK_DEV_BSG is not set +CONFIG_BLK_DEV_BSG=y # # IO Schedulers @@ -103,7 +165,8 @@ CONFIG_IOSCHED_CFQ=y # CONFIG_DEFAULT_DEADLINE is not set CONFIG_DEFAULT_CFQ=y # CONFIG_DEFAULT_NOOP is not set -CONFIG_DEFAULT_IOSCHED="anticipatory" +CONFIG_DEFAULT_IOSCHED="cfq" +CONFIG_CLASSIC_RCU=y # # Processor type and features @@ -111,18 +174,21 @@ CONFIG_DEFAULT_IOSCHED="anticipatory" CONFIG_TICK_ONESHOT=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y +CONFIG_GENERIC_CLOCKEVENTS_BUILD=y CONFIG_SMP=y -# CONFIG_X86_PC is not set +CONFIG_X86_PC=y # CONFIG_X86_ELAN is not set # CONFIG_X86_VOYAGER is not set # CONFIG_X86_NUMAQ is not set # CONFIG_X86_SUMMIT is not set # CONFIG_X86_BIGSMP is not set # CONFIG_X86_VISWS is not set -CONFIG_X86_GENERICARCH=y +# CONFIG_X86_GENERICARCH is not set # CONFIG_X86_ES7000 is not set -# CONFIG_PARAVIRT is not set -CONFIG_X86_CYCLONE_TIMER=y +# CONFIG_X86_RDC321X is not set +# CONFIG_X86_VSMP is not set +CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y +# CONFIG_PARAVIRT_GUEST is not set # CONFIG_M386 is not set # CONFIG_M486 is not set # CONFIG_M586 is not set @@ -130,9 +196,8 @@ CONFIG_X86_CYCLONE_TIMER=y # CONFIG_M586MMX is not set # CONFIG_M686 is not set # CONFIG_MPENTIUMII is not set -CONFIG_MPENTIUMIII=y +# CONFIG_MPENTIUMIII is not set # CONFIG_MPENTIUMM is not set -# CONFIG_MCORE2 is not set # CONFIG_MPENTIUM4 is not set # CONFIG_MK6 is not set # CONFIG_MK7 is not set @@ -147,14 +212,14 @@ CONFIG_MPENTIUMIII=y # CONFIG_MCYRIXIII is not set # CONFIG_MVIAC3_2 is not set # CONFIG_MVIAC7 is not set -CONFIG_X86_GENERIC=y +# CONFIG_MPSC is not set +CONFIG_MCORE2=y +# CONFIG_GENERIC_CPU is not set +# CONFIG_X86_GENERIC is not set +CONFIG_X86_CPU=y CONFIG_X86_CMPXCHG=y -CONFIG_X86_L1_CACHE_SHIFT=7 +CONFIG_X86_L1_CACHE_SHIFT=6 CONFIG_X86_XADD=y -CONFIG_RWSEM_XCHGADD_ALGORITHM=y -# CONFIG_ARCH_HAS_ILOG2_U32 is not set -# CONFIG_ARCH_HAS_ILOG2_U64 is not set -CONFIG_GENERIC_CALIBRATE_DELAY=y CONFIG_X86_WP_WORKS_OK=y CONFIG_X86_INVLPG=y CONFIG_X86_BSWAP=y @@ -162,106 +227,120 @@ CONFIG_X86_POPAD_OK=y CONFIG_X86_GOOD_APIC=y CONFIG_X86_INTEL_USERCOPY=y CONFIG_X86_USE_PPRO_CHECKSUM=y +CONFIG_X86_P6_NOP=y CONFIG_X86_TSC=y -CONFIG_X86_CMOV=y -CONFIG_X86_MINIMUM_CPU_FAMILY=4 +CONFIG_X86_MINIMUM_CPU_FAMILY=6 +CONFIG_X86_DEBUGCTLMSR=y CONFIG_HPET_TIMER=y CONFIG_HPET_EMULATE_RTC=y -CONFIG_NR_CPUS=32 -CONFIG_SCHED_SMT=y +CONFIG_DMI=y +# CONFIG_IOMMU_HELPER is not set +CONFIG_NR_CPUS=4 +# CONFIG_SCHED_SMT is not set CONFIG_SCHED_MC=y # CONFIG_PREEMPT_NONE is not set CONFIG_PREEMPT_VOLUNTARY=y # CONFIG_PREEMPT is not set -CONFIG_PREEMPT_BKL=y CONFIG_X86_LOCAL_APIC=y CONFIG_X86_IO_APIC=y -CONFIG_X86_MCE=y -CONFIG_X86_MCE_NONFATAL=y -CONFIG_X86_MCE_P4THERMAL=y +# CONFIG_X86_MCE is not set CONFIG_VM86=y # CONFIG_TOSHIBA is not set # CONFIG_I8K is not set # CONFIG_X86_REBOOTFIXUPS is not set -CONFIG_MICROCODE=y -CONFIG_MICROCODE_OLD_INTERFACE=y +# CONFIG_MICROCODE is not set CONFIG_X86_MSR=y CONFIG_X86_CPUID=y - -# -# Firmware Drivers -# -# CONFIG_EDD is not set -# CONFIG_DELL_RBU is not set -# CONFIG_DCDBAS is not set -CONFIG_DMIID=y # CONFIG_NOHIGHMEM is not set CONFIG_HIGHMEM4G=y # CONFIG_HIGHMEM64G is not set CONFIG_PAGE_OFFSET=0xC0000000 CONFIG_HIGHMEM=y -CONFIG_ARCH_POPULATES_NODE_MAP=y +CONFIG_NEED_NODE_MEMMAP_SIZE=y +CONFIG_ARCH_FLATMEM_ENABLE=y +CONFIG_ARCH_SPARSEMEM_ENABLE=y +CONFIG_ARCH_SELECT_MEMORY_MODEL=y CONFIG_SELECT_MEMORY_MODEL=y -CONFIG_FLATMEM_MANUAL=y +# CONFIG_FLATMEM_MANUAL is not set # CONFIG_DISCONTIGMEM_MANUAL is not set -# CONFIG_SPARSEMEM_MANUAL is not set -CONFIG_FLATMEM=y -CONFIG_FLAT_NODE_MEM_MAP=y -# CONFIG_SPARSEMEM_STATIC is not set +CONFIG_SPARSEMEM_MANUAL=y +CONFIG_SPARSEMEM=y +CONFIG_HAVE_MEMORY_PRESENT=y +CONFIG_SPARSEMEM_STATIC=y +# CONFIG_SPARSEMEM_VMEMMAP_ENABLE is not set + +# +# Memory hotplug is currently incompatible with Software Suspend +# +CONFIG_PAGEFLAGS_EXTENDED=y CONFIG_SPLIT_PTLOCK_CPUS=4 CONFIG_RESOURCES_64BIT=y CONFIG_ZONE_DMA_FLAG=1 CONFIG_BOUNCE=y -CONFIG_NR_QUICK=1 CONFIG_VIRT_TO_BUS=y # CONFIG_HIGHPTE is not set # CONFIG_MATH_EMULATION is not set CONFIG_MTRR=y -# CONFIG_EFI is not set +# CONFIG_X86_PAT is not set +CONFIG_EFI=y # CONFIG_IRQBALANCE is not set CONFIG_SECCOMP=y # CONFIG_HZ_100 is not set -CONFIG_HZ_250=y +# CONFIG_HZ_250 is not set # CONFIG_HZ_300 is not set -# CONFIG_HZ_1000 is not set -CONFIG_HZ=250 -# CONFIG_KEXEC is not set -# CONFIG_CRASH_DUMP is not set -CONFIG_PHYSICAL_START=0x100000 -# CONFIG_RELOCATABLE is not set -CONFIG_PHYSICAL_ALIGN=0x100000 -# CONFIG_HOTPLUG_CPU is not set -CONFIG_COMPAT_VDSO=y +CONFIG_HZ_1000=y +CONFIG_HZ=1000 +CONFIG_SCHED_HRTICK=y +CONFIG_KEXEC=y +CONFIG_CRASH_DUMP=y +CONFIG_PHYSICAL_START=0x1000000 +CONFIG_RELOCATABLE=y +CONFIG_PHYSICAL_ALIGN=0x200000 +CONFIG_HOTPLUG_CPU=y +# CONFIG_COMPAT_VDSO is not set CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y # -# Power management options (ACPI, APM) +# Power management options # CONFIG_PM=y -CONFIG_PM_LEGACY=y -# CONFIG_PM_DEBUG is not set - -# -# ACPI (Advanced Configuration and Power Interface) Support -# +CONFIG_PM_DEBUG=y +# CONFIG_PM_VERBOSE is not set +CONFIG_CAN_PM_TRACE=y +CONFIG_PM_TRACE=y +CONFIG_PM_TRACE_RTC=y +CONFIG_PM_SLEEP_SMP=y +CONFIG_PM_SLEEP=y +CONFIG_SUSPEND=y +CONFIG_SUSPEND_FREEZER=y +CONFIG_HIBERNATION=y +CONFIG_PM_STD_PARTITION="" CONFIG_ACPI=y +CONFIG_ACPI_SLEEP=y CONFIG_ACPI_PROCFS=y +CONFIG_ACPI_PROCFS_POWER=y +CONFIG_ACPI_SYSFS_POWER=y +CONFIG_ACPI_PROC_EVENT=y CONFIG_ACPI_AC=y CONFIG_ACPI_BATTERY=y CONFIG_ACPI_BUTTON=y CONFIG_ACPI_FAN=y -# CONFIG_ACPI_DOCK is not set +CONFIG_ACPI_DOCK=y +# CONFIG_ACPI_BAY is not set CONFIG_ACPI_PROCESSOR=y +CONFIG_ACPI_HOTPLUG_CPU=y CONFIG_ACPI_THERMAL=y +# CONFIG_ACPI_WMI is not set # CONFIG_ACPI_ASUS is not set # CONFIG_ACPI_TOSHIBA is not set -CONFIG_ACPI_BLACKLIST_YEAR=2001 -CONFIG_ACPI_DEBUG=y +# CONFIG_ACPI_CUSTOM_DSDT is not set +CONFIG_ACPI_BLACKLIST_YEAR=0 +# CONFIG_ACPI_DEBUG is not set CONFIG_ACPI_EC=y CONFIG_ACPI_POWER=y CONFIG_ACPI_SYSTEM=y CONFIG_X86_PM_TIMER=y -# CONFIG_ACPI_CONTAINER is not set +CONFIG_ACPI_CONTAINER=y # CONFIG_ACPI_SBS is not set # CONFIG_APM is not set @@ -271,15 +350,17 @@ CONFIG_X86_PM_TIMER=y CONFIG_CPU_FREQ=y CONFIG_CPU_FREQ_TABLE=y CONFIG_CPU_FREQ_DEBUG=y -CONFIG_CPU_FREQ_STAT=y -# CONFIG_CPU_FREQ_STAT_DETAILS is not set -CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y -# CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set +# CONFIG_CPU_FREQ_STAT is not set +# CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE is not set +# CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE is not set +CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y +# CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND is not set +# CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE is not set CONFIG_CPU_FREQ_GOV_PERFORMANCE=y # CONFIG_CPU_FREQ_GOV_POWERSAVE is not set CONFIG_CPU_FREQ_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_ONDEMAND=y -CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y +# CONFIG_CPU_FREQ_GOV_CONSERVATIVE is not set # # CPUFreq processor drivers @@ -287,8 +368,7 @@ CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y CONFIG_X86_ACPI_CPUFREQ=y # CONFIG_X86_POWERNOW_K6 is not set # CONFIG_X86_POWERNOW_K7 is not set -CONFIG_X86_POWERNOW_K8=y -CONFIG_X86_POWERNOW_K8_ACPI=y +# CONFIG_X86_POWERNOW_K8 is not set # CONFIG_X86_GX_SUSPMOD is not set # CONFIG_X86_SPEEDSTEP_CENTRINO is not set # CONFIG_X86_SPEEDSTEP_ICH is not set @@ -302,43 +382,72 @@ CONFIG_X86_POWERNOW_K8_ACPI=y # # shared options # -CONFIG_X86_ACPI_CPUFREQ_PROC_INTF=y +# CONFIG_X86_ACPI_CPUFREQ_PROC_INTF is not set # CONFIG_X86_SPEEDSTEP_LIB is not set +CONFIG_CPU_IDLE=y +CONFIG_CPU_IDLE_GOV_LADDER=y +CONFIG_CPU_IDLE_GOV_MENU=y # -# Bus options (PCI, PCMCIA, EISA, MCA, ISA) +# Bus options (PCI etc.) # CONFIG_PCI=y # CONFIG_PCI_GOBIOS is not set # CONFIG_PCI_GOMMCONFIG is not set # CONFIG_PCI_GODIRECT is not set CONFIG_PCI_GOANY=y +# CONFIG_PCI_GOOLPC is not set CONFIG_PCI_BIOS=y CONFIG_PCI_DIRECT=y CONFIG_PCI_MMCONFIG=y -# CONFIG_PCIEPORTBUS is not set +CONFIG_PCI_DOMAINS=y +CONFIG_PCIEPORTBUS=y +# CONFIG_HOTPLUG_PCI_PCIE is not set +CONFIG_PCIEAER=y +# CONFIG_PCIEASPM is not set CONFIG_ARCH_SUPPORTS_MSI=y CONFIG_PCI_MSI=y +# CONFIG_PCI_LEGACY is not set # CONFIG_PCI_DEBUG is not set -# CONFIG_HT_IRQ is not set +CONFIG_HT_IRQ=y CONFIG_ISA_DMA_API=y # CONFIG_ISA is not set # CONFIG_MCA is not set # CONFIG_SCx200 is not set +# CONFIG_OLPC is not set CONFIG_K8_NB=y - -# -# PCCARD (PCMCIA/CardBus) support -# -# CONFIG_PCCARD is not set -# CONFIG_HOTPLUG_PCI is not set - -# -# Executable file formats +CONFIG_PCCARD=y +# CONFIG_PCMCIA_DEBUG is not set +CONFIG_PCMCIA=y +CONFIG_PCMCIA_LOAD_CIS=y +CONFIG_PCMCIA_IOCTL=y +CONFIG_CARDBUS=y + +# +# PC-card bridges +# +CONFIG_YENTA=y +CONFIG_YENTA_O2=y +CONFIG_YENTA_RICOH=y +CONFIG_YENTA_TI=y +CONFIG_YENTA_ENE_TUNE=y +CONFIG_YENTA_TOSHIBA=y +# CONFIG_PD6729 is not set +# CONFIG_I82092 is not set +CONFIG_PCCARD_NONSTATIC=y +CONFIG_HOTPLUG_PCI=y +# CONFIG_HOTPLUG_PCI_FAKE is not set +# CONFIG_HOTPLUG_PCI_IBM is not set +# CONFIG_HOTPLUG_PCI_ACPI is not set +# CONFIG_HOTPLUG_PCI_CPCI is not set +# CONFIG_HOTPLUG_PCI_SHPC is not set + +# +# Executable file formats / Emulations # CONFIG_BINFMT_ELF=y # CONFIG_BINFMT_AOUT is not set -# CONFIG_BINFMT_MISC is not set +CONFIG_BINFMT_MISC=y # # Networking @@ -349,59 +458,142 @@ CONFIG_NET=y # Networking options # CONFIG_PACKET=y -# CONFIG_PACKET_MMAP is not set +CONFIG_PACKET_MMAP=y CONFIG_UNIX=y CONFIG_XFRM=y -# CONFIG_XFRM_USER is not set +CONFIG_XFRM_USER=y # CONFIG_XFRM_SUB_POLICY is not set # CONFIG_XFRM_MIGRATE is not set +# CONFIG_XFRM_STATISTICS is not set # CONFIG_NET_KEY is not set CONFIG_INET=y CONFIG_IP_MULTICAST=y -# CONFIG_IP_ADVANCED_ROUTER is not set +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_ASK_IP_FIB_HASH=y +# CONFIG_IP_FIB_TRIE is not set CONFIG_IP_FIB_HASH=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -# CONFIG_IP_PNP_BOOTP is not set -# CONFIG_IP_PNP_RARP is not set +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_ROUTE_MULTIPATH=y +CONFIG_IP_ROUTE_VERBOSE=y +# CONFIG_IP_PNP is not set # CONFIG_NET_IPIP is not set # CONFIG_NET_IPGRE is not set -# CONFIG_IP_MROUTE is not set +CONFIG_IP_MROUTE=y +CONFIG_IP_PIMSM_V1=y +CONFIG_IP_PIMSM_V2=y # CONFIG_ARPD is not set -# CONFIG_SYN_COOKIES is not set +CONFIG_SYN_COOKIES=y # CONFIG_INET_AH is not set # CONFIG_INET_ESP is not set # CONFIG_INET_IPCOMP is not set # CONFIG_INET_XFRM_TUNNEL is not set CONFIG_INET_TUNNEL=y -CONFIG_INET_XFRM_MODE_TRANSPORT=y -CONFIG_INET_XFRM_MODE_TUNNEL=y +# CONFIG_INET_XFRM_MODE_TRANSPORT is not set +# CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -CONFIG_INET_DIAG=y -CONFIG_INET_TCP_DIAG=y -# CONFIG_TCP_CONG_ADVANCED is not set +CONFIG_INET_LRO=y +# CONFIG_INET_DIAG is not set +CONFIG_TCP_CONG_ADVANCED=y +# CONFIG_TCP_CONG_BIC is not set CONFIG_TCP_CONG_CUBIC=y +# CONFIG_TCP_CONG_WESTWOOD is not set +# CONFIG_TCP_CONG_HTCP is not set +# CONFIG_TCP_CONG_HSTCP is not set +# CONFIG_TCP_CONG_HYBLA is not set +# CONFIG_TCP_CONG_VEGAS is not set +# CONFIG_TCP_CONG_SCALABLE is not set +# CONFIG_TCP_CONG_LP is not set +# CONFIG_TCP_CONG_VENO is not set +# CONFIG_TCP_CONG_YEAH is not set +# CONFIG_TCP_CONG_ILLINOIS is not set +# CONFIG_DEFAULT_BIC is not set +CONFIG_DEFAULT_CUBIC=y +# CONFIG_DEFAULT_HTCP is not set +# CONFIG_DEFAULT_VEGAS is not set +# CONFIG_DEFAULT_WESTWOOD is not set +# CONFIG_DEFAULT_RENO is not set CONFIG_DEFAULT_TCP_CONG="cubic" -# CONFIG_TCP_MD5SIG is not set +CONFIG_TCP_MD5SIG=y +# CONFIG_IP_VS is not set CONFIG_IPV6=y # CONFIG_IPV6_PRIVACY is not set # CONFIG_IPV6_ROUTER_PREF is not set # CONFIG_IPV6_OPTIMISTIC_DAD is not set -# CONFIG_INET6_AH is not set -# CONFIG_INET6_ESP is not set +CONFIG_INET6_AH=y +CONFIG_INET6_ESP=y # CONFIG_INET6_IPCOMP is not set # CONFIG_IPV6_MIP6 is not set # CONFIG_INET6_XFRM_TUNNEL is not set # CONFIG_INET6_TUNNEL is not set CONFIG_INET6_XFRM_MODE_TRANSPORT=y CONFIG_INET6_XFRM_MODE_TUNNEL=y -# CONFIG_INET6_XFRM_MODE_BEET is not set +CONFIG_INET6_XFRM_MODE_BEET=y # CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION is not set CONFIG_IPV6_SIT=y +CONFIG_IPV6_NDISC_NODETYPE=y # CONFIG_IPV6_TUNNEL is not set # CONFIG_IPV6_MULTIPLE_TABLES is not set -# CONFIG_NETWORK_SECMARK is not set -# CONFIG_NETFILTER is not set +# CONFIG_IPV6_MROUTE is not set +CONFIG_NETLABEL=y +CONFIG_NETWORK_SECMARK=y +CONFIG_NETFILTER=y +# CONFIG_NETFILTER_DEBUG is not set +# CONFIG_NETFILTER_ADVANCED is not set + +# +# Core Netfilter Configuration +# +CONFIG_NETFILTER_NETLINK=y +CONFIG_NETFILTER_NETLINK_LOG=y +CONFIG_NF_CONNTRACK=y +CONFIG_NF_CONNTRACK_SECMARK=y +CONFIG_NF_CONNTRACK_FTP=y +CONFIG_NF_CONNTRACK_IRC=y +CONFIG_NF_CONNTRACK_SIP=y +CONFIG_NF_CT_NETLINK=y +CONFIG_NETFILTER_XTABLES=y +CONFIG_NETFILTER_XT_TARGET_MARK=y +CONFIG_NETFILTER_XT_TARGET_NFLOG=y +CONFIG_NETFILTER_XT_TARGET_SECMARK=y +CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y +CONFIG_NETFILTER_XT_TARGET_TCPMSS=y +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y +CONFIG_NETFILTER_XT_MATCH_MARK=y +CONFIG_NETFILTER_XT_MATCH_POLICY=y +CONFIG_NETFILTER_XT_MATCH_STATE=y + +# +# IP: Netfilter Configuration +# +CONFIG_NF_CONNTRACK_IPV4=y +CONFIG_NF_CONNTRACK_PROC_COMPAT=y +CONFIG_IP_NF_IPTABLES=y +CONFIG_IP_NF_FILTER=y +CONFIG_IP_NF_TARGET_REJECT=y +CONFIG_IP_NF_TARGET_LOG=y +CONFIG_IP_NF_TARGET_ULOG=y +CONFIG_NF_NAT=y +CONFIG_NF_NAT_NEEDED=y +CONFIG_IP_NF_TARGET_MASQUERADE=y +CONFIG_NF_NAT_FTP=y +CONFIG_NF_NAT_IRC=y +# CONFIG_NF_NAT_TFTP is not set +# CONFIG_NF_NAT_AMANDA is not set +# CONFIG_NF_NAT_PPTP is not set +# CONFIG_NF_NAT_H323 is not set +CONFIG_NF_NAT_SIP=y +CONFIG_IP_NF_MANGLE=y + +# +# IPv6: Netfilter Configuration +# +CONFIG_NF_CONNTRACK_IPV6=y +CONFIG_IP6_NF_IPTABLES=y +CONFIG_IP6_NF_MATCH_IPV6HEADER=y +CONFIG_IP6_NF_FILTER=y +CONFIG_IP6_NF_TARGET_LOG=y +CONFIG_IP6_NF_TARGET_REJECT=y +CONFIG_IP6_NF_MANGLE=y # CONFIG_IP_DCCP is not set # CONFIG_IP_SCTP is not set # CONFIG_TIPC is not set @@ -409,6 +601,7 @@ CONFIG_IPV6_SIT=y # CONFIG_BRIDGE is not set # CONFIG_VLAN_8021Q is not set # CONFIG_DECNET is not set +CONFIG_LLC=y # CONFIG_LLC2 is not set # CONFIG_IPX is not set # CONFIG_ATALK is not set @@ -416,28 +609,99 @@ CONFIG_IPV6_SIT=y # CONFIG_LAPB is not set # CONFIG_ECONET is not set # CONFIG_WAN_ROUTER is not set - -# -# QoS and/or fair queueing -# -# CONFIG_NET_SCHED is not set +CONFIG_NET_SCHED=y + +# +# Queueing/Scheduling +# +# CONFIG_NET_SCH_CBQ is not set +# CONFIG_NET_SCH_HTB is not set +# CONFIG_NET_SCH_HFSC is not set +# CONFIG_NET_SCH_PRIO is not set +# CONFIG_NET_SCH_RR is not set +# CONFIG_NET_SCH_RED is not set +# CONFIG_NET_SCH_SFQ is not set +# CONFIG_NET_SCH_TEQL is not set +# CONFIG_NET_SCH_TBF is not set +# CONFIG_NET_SCH_GRED is not set +# CONFIG_NET_SCH_DSMARK is not set +# CONFIG_NET_SCH_NETEM is not set +# CONFIG_NET_SCH_INGRESS is not set + +# +# Classification +# +CONFIG_NET_CLS=y +# CONFIG_NET_CLS_BASIC is not set +# CONFIG_NET_CLS_TCINDEX is not set +# CONFIG_NET_CLS_ROUTE4 is not set +# CONFIG_NET_CLS_FW is not set +# CONFIG_NET_CLS_U32 is not set +# CONFIG_NET_CLS_RSVP is not set +# CONFIG_NET_CLS_RSVP6 is not set +# CONFIG_NET_CLS_FLOW is not set +CONFIG_NET_EMATCH=y +CONFIG_NET_EMATCH_STACK=32 +# CONFIG_NET_EMATCH_CMP is not set +# CONFIG_NET_EMATCH_NBYTE is not set +# CONFIG_NET_EMATCH_U32 is not set +# CONFIG_NET_EMATCH_META is not set +# CONFIG_NET_EMATCH_TEXT is not set +CONFIG_NET_CLS_ACT=y +# CONFIG_NET_ACT_POLICE is not set +# CONFIG_NET_ACT_GACT is not set +# CONFIG_NET_ACT_MIRRED is not set +# CONFIG_NET_ACT_IPT is not set +# CONFIG_NET_ACT_NAT is not set +# CONFIG_NET_ACT_PEDIT is not set +# CONFIG_NET_ACT_SIMP is not set +CONFIG_NET_SCH_FIFO=y # # Network testing # # CONFIG_NET_PKTGEN is not set # CONFIG_NET_TCPPROBE is not set -# CONFIG_HAMRADIO is not set +CONFIG_HAMRADIO=y + +# +# Packet Radio protocols +# +# CONFIG_AX25 is not set +# CONFIG_CAN is not set # CONFIG_IRDA is not set # CONFIG_BT is not set # CONFIG_AF_RXRPC is not set +CONFIG_FIB_RULES=y # # Wireless # -# CONFIG_CFG80211 is not set -# CONFIG_WIRELESS_EXT is not set -# CONFIG_MAC80211 is not set +CONFIG_CFG80211=y +CONFIG_NL80211=y +CONFIG_WIRELESS_EXT=y +CONFIG_MAC80211=y + +# +# Rate control algorithm selection +# +CONFIG_MAC80211_RC_DEFAULT_PID=y +# CONFIG_MAC80211_RC_DEFAULT_NONE is not set + +# +# Selecting 'y' for an algorithm will +# + +# +# build the algorithm into mac80211. +# +CONFIG_MAC80211_RC_DEFAULT="pid" +CONFIG_MAC80211_RC_PID=y +# CONFIG_MAC80211_MESH is not set +CONFIG_MAC80211_LEDS=y +# CONFIG_MAC80211_DEBUGFS is not set +# CONFIG_MAC80211_DEBUG_PACKET_ALIGNMENT is not set +# CONFIG_MAC80211_DEBUG is not set # CONFIG_IEEE80211 is not set # CONFIG_RFKILL is not set # CONFIG_NET_9P is not set @@ -449,13 +713,15 @@ CONFIG_IPV6_SIT=y # # Generic Driver Options # +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_STANDALONE=y CONFIG_PREVENT_FIRMWARE_BUILD=y CONFIG_FW_LOADER=y # CONFIG_DEBUG_DRIVER is not set -# CONFIG_DEBUG_DEVRES is not set +CONFIG_DEBUG_DEVRES=y # CONFIG_SYS_HYPERVISOR is not set -# CONFIG_CONNECTOR is not set +CONFIG_CONNECTOR=y +CONFIG_PROC_EVENTS=y # CONFIG_MTD is not set # CONFIG_PARPORT is not set CONFIG_PNP=y @@ -466,7 +732,7 @@ CONFIG_PNP=y # CONFIG_PNPACPI=y CONFIG_BLK_DEV=y -CONFIG_BLK_DEV_FD=y +# CONFIG_BLK_DEV_FD is not set # CONFIG_BLK_CPQ_DA is not set # CONFIG_BLK_CPQ_CISS_DA is not set # CONFIG_BLK_DEV_DAC960 is not set @@ -479,8 +745,8 @@ CONFIG_BLK_DEV_LOOP=y # CONFIG_BLK_DEV_UB is not set CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_COUNT=16 -CONFIG_BLK_DEV_RAM_SIZE=4096 -CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024 +CONFIG_BLK_DEV_RAM_SIZE=16384 +# CONFIG_BLK_DEV_XIP is not set # CONFIG_CDROM_PKTCDVD is not set # CONFIG_ATA_OVER_ETH is not set CONFIG_MISC_DEVICES=y @@ -489,73 +755,17 @@ CONFIG_MISC_DEVICES=y # CONFIG_EEPROM_93CX6 is not set # CONFIG_SGI_IOC4 is not set # CONFIG_TIFM_CORE is not set +# CONFIG_ACER_WMI is not set +# CONFIG_ASUS_LAPTOP is not set +# CONFIG_FUJITSU_LAPTOP is not set +# CONFIG_TC1100_WMI is not set +# CONFIG_MSI_LAPTOP is not set # CONFIG_SONY_LAPTOP is not set # CONFIG_THINKPAD_ACPI is not set -CONFIG_IDE=y -CONFIG_BLK_DEV_IDE=y - -# -# Please see Documentation/ide.txt for help/info on IDE drives -# -# CONFIG_BLK_DEV_IDE_SATA is not set -# CONFIG_BLK_DEV_HD_IDE is not set -CONFIG_BLK_DEV_IDEDISK=y -CONFIG_IDEDISK_MULTI_MODE=y -CONFIG_BLK_DEV_IDECD=y -# CONFIG_BLK_DEV_IDETAPE is not set -# CONFIG_BLK_DEV_IDEFLOPPY is not set -# CONFIG_BLK_DEV_IDESCSI is not set -CONFIG_BLK_DEV_IDEACPI=y -# CONFIG_IDE_TASK_IOCTL is not set -CONFIG_IDE_PROC_FS=y - -# -# IDE chipset support/bugfixes -# -CONFIG_IDE_GENERIC=y -# CONFIG_BLK_DEV_CMD640 is not set -# CONFIG_BLK_DEV_IDEPNP is not set -CONFIG_BLK_DEV_IDEPCI=y -# CONFIG_IDEPCI_SHARE_IRQ is not set -CONFIG_IDEPCI_PCIBUS_ORDER=y -# CONFIG_BLK_DEV_OFFBOARD is not set -# CONFIG_BLK_DEV_GENERIC is not set -# CONFIG_BLK_DEV_OPTI621 is not set -# CONFIG_BLK_DEV_RZ1000 is not set -CONFIG_BLK_DEV_IDEDMA_PCI=y -# CONFIG_BLK_DEV_IDEDMA_FORCED is not set -# CONFIG_IDEDMA_ONLYDISK is not set -# CONFIG_BLK_DEV_AEC62XX is not set -# CONFIG_BLK_DEV_ALI15X3 is not set -CONFIG_BLK_DEV_AMD74XX=y -# CONFIG_BLK_DEV_ATIIXP is not set -# CONFIG_BLK_DEV_CMD64X is not set -# CONFIG_BLK_DEV_TRIFLEX is not set -# CONFIG_BLK_DEV_CY82C693 is not set -# CONFIG_BLK_DEV_CS5520 is not set -# CONFIG_BLK_DEV_CS5530 is not set -# CONFIG_BLK_DEV_CS5535 is not set -# CONFIG_BLK_DEV_HPT34X is not set -# CONFIG_BLK_DEV_HPT366 is not set -# CONFIG_BLK_DEV_JMICRON is not set -# CONFIG_BLK_DEV_SC1200 is not set -CONFIG_BLK_DEV_PIIX=y -# CONFIG_BLK_DEV_IT8213 is not set -# CONFIG_BLK_DEV_IT821X is not set -# CONFIG_BLK_DEV_NS87415 is not set -# CONFIG_BLK_DEV_PDC202XX_OLD is not set -# CONFIG_BLK_DEV_PDC202XX_NEW is not set -# CONFIG_BLK_DEV_SVWKS is not set -# CONFIG_BLK_DEV_SIIMAGE is not set -# CONFIG_BLK_DEV_SIS5513 is not set -# CONFIG_BLK_DEV_SLC90E66 is not set -# CONFIG_BLK_DEV_TRM290 is not set -# CONFIG_BLK_DEV_VIA82CXXX is not set -# CONFIG_BLK_DEV_TC86C001 is not set -# CONFIG_IDE_ARM is not set -CONFIG_BLK_DEV_IDEDMA=y -# CONFIG_IDEDMA_IVB is not set -# CONFIG_BLK_DEV_HD is not set +# CONFIG_INTEL_MENLOW is not set +# CONFIG_ENCLOSURE_SERVICES is not set +CONFIG_HAVE_IDE=y +# CONFIG_IDE is not set # # SCSI device support @@ -564,8 +774,8 @@ CONFIG_BLK_DEV_IDEDMA=y CONFIG_SCSI=y CONFIG_SCSI_DMA=y # CONFIG_SCSI_TGT is not set -CONFIG_SCSI_NETLINK=y -# CONFIG_SCSI_PROC_FS is not set +# CONFIG_SCSI_NETLINK is not set +CONFIG_SCSI_PROC_FS=y # # SCSI support type (disk, tape, CD-ROM) @@ -574,7 +784,7 @@ CONFIG_BLK_DEV_SD=y # CONFIG_CHR_DEV_ST is not set # CONFIG_CHR_DEV_OSST is not set CONFIG_BLK_DEV_SR=y -# CONFIG_BLK_DEV_SR_VENDOR is not set +CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y # CONFIG_CHR_DEV_SCH is not set @@ -582,7 +792,7 @@ CONFIG_CHR_DEV_SG=y # Some SCSI devices (e.g. CD jukebox) support multiple LUNs # # CONFIG_SCSI_MULTI_LUN is not set -# CONFIG_SCSI_CONSTANTS is not set +CONFIG_SCSI_CONSTANTS=y # CONFIG_SCSI_LOGGING is not set # CONFIG_SCSI_SCAN_ASYNC is not set CONFIG_SCSI_WAIT_SCAN=m @@ -591,81 +801,37 @@ CONFIG_SCSI_WAIT_SCAN=m # SCSI Transports # CONFIG_SCSI_SPI_ATTRS=y -CONFIG_SCSI_FC_ATTRS=y +# CONFIG_SCSI_FC_ATTRS is not set # CONFIG_SCSI_ISCSI_ATTRS is not set # CONFIG_SCSI_SAS_ATTRS is not set # CONFIG_SCSI_SAS_LIBSAS is not set - -# -# SCSI low-level drivers -# -# CONFIG_ISCSI_TCP is not set -CONFIG_BLK_DEV_3W_XXXX_RAID=y -# CONFIG_SCSI_3W_9XXX is not set -# CONFIG_SCSI_ACARD is not set -# CONFIG_SCSI_AACRAID is not set -CONFIG_SCSI_AIC7XXX=y -CONFIG_AIC7XXX_CMDS_PER_DEVICE=32 -CONFIG_AIC7XXX_RESET_DELAY_MS=5000 -CONFIG_AIC7XXX_DEBUG_ENABLE=y -CONFIG_AIC7XXX_DEBUG_MASK=0 -CONFIG_AIC7XXX_REG_PRETTY_PRINT=y -# CONFIG_SCSI_AIC7XXX_OLD is not set -CONFIG_SCSI_AIC79XX=y -CONFIG_AIC79XX_CMDS_PER_DEVICE=32 -CONFIG_AIC79XX_RESET_DELAY_MS=4000 -# CONFIG_AIC79XX_DEBUG_ENABLE is not set -CONFIG_AIC79XX_DEBUG_MASK=0 -# CONFIG_AIC79XX_REG_PRETTY_PRINT is not set -# CONFIG_SCSI_AIC94XX is not set -# CONFIG_SCSI_DPT_I2O is not set -# CONFIG_SCSI_ADVANSYS is not set -# CONFIG_SCSI_ARCMSR is not set -# CONFIG_MEGARAID_NEWGEN is not set -# CONFIG_MEGARAID_LEGACY is not set -# CONFIG_MEGARAID_SAS is not set -# CONFIG_SCSI_HPTIOP is not set -# CONFIG_SCSI_BUSLOGIC is not set -# CONFIG_SCSI_DMX3191D is not set -# CONFIG_SCSI_EATA is not set -# CONFIG_SCSI_FUTURE_DOMAIN is not set -# CONFIG_SCSI_GDTH is not set -# CONFIG_SCSI_IPS is not set -# CONFIG_SCSI_INITIO is not set -# CONFIG_SCSI_INIA100 is not set -# CONFIG_SCSI_STEX is not set -# CONFIG_SCSI_SYM53C8XX_2 is not set -# CONFIG_SCSI_IPR is not set -# CONFIG_SCSI_QLOGIC_1280 is not set -# CONFIG_SCSI_QLA_FC is not set -# CONFIG_SCSI_QLA_ISCSI is not set -# CONFIG_SCSI_LPFC is not set -# CONFIG_SCSI_DC395x is not set -# CONFIG_SCSI_DC390T is not set -# CONFIG_SCSI_NSP32 is not set -# CONFIG_SCSI_DEBUG is not set -# CONFIG_SCSI_SRP is not set +# CONFIG_SCSI_SRP_ATTRS is not set +# CONFIG_SCSI_LOWLEVEL is not set +# CONFIG_SCSI_LOWLEVEL_PCMCIA is not set CONFIG_ATA=y # CONFIG_ATA_NONSTANDARD is not set CONFIG_ATA_ACPI=y +CONFIG_SATA_PMP=y CONFIG_SATA_AHCI=y -CONFIG_SATA_SVW=y +# CONFIG_SATA_SIL24 is not set +CONFIG_ATA_SFF=y +# CONFIG_SATA_SVW is not set CONFIG_ATA_PIIX=y # CONFIG_SATA_MV is not set -CONFIG_SATA_NV=y +# CONFIG_SATA_NV is not set # CONFIG_PDC_ADMA is not set # CONFIG_SATA_QSTOR is not set # CONFIG_SATA_PROMISE is not set # CONFIG_SATA_SX4 is not set -CONFIG_SATA_SIL=y -# CONFIG_SATA_SIL24 is not set +# CONFIG_SATA_SIL is not set # CONFIG_SATA_SIS is not set # CONFIG_SATA_ULI is not set -CONFIG_SATA_VIA=y +# CONFIG_SATA_VIA is not set # CONFIG_SATA_VITESSE is not set # CONFIG_SATA_INIC162X is not set +# CONFIG_PATA_ACPI is not set # CONFIG_PATA_ALI is not set -# CONFIG_PATA_AMD is not set +CONFIG_PATA_AMD=y # CONFIG_PATA_ARTOP is not set # CONFIG_PATA_ATIIXP is not set # CONFIG_PATA_CMD640_PCI is not set @@ -673,6 +839,7 @@ CONFIG_SATA_VIA=y # CONFIG_PATA_CS5520 is not set # CONFIG_PATA_CS5530 is not set # CONFIG_PATA_CS5535 is not set +# CONFIG_PATA_CS5536 is not set # CONFIG_PATA_CYPRESS is not set # CONFIG_PATA_EFAR is not set # CONFIG_ATA_GENERIC is not set @@ -686,11 +853,14 @@ CONFIG_SATA_VIA=y # CONFIG_PATA_TRIFLEX is not set # CONFIG_PATA_MARVELL is not set # CONFIG_PATA_MPIIX is not set -# CONFIG_PATA_OLDPIIX is not set +CONFIG_PATA_OLDPIIX=y # CONFIG_PATA_NETCELL is not set +# CONFIG_PATA_NINJA32 is not set # CONFIG_PATA_NS87410 is not set +# CONFIG_PATA_NS87415 is not set # CONFIG_PATA_OPTI is not set # CONFIG_PATA_OPTIDMA is not set +# CONFIG_PATA_PCMCIA is not set # CONFIG_PATA_PDC_OLD is not set # CONFIG_PATA_RADISYS is not set # CONFIG_PATA_RZ1000 is not set @@ -702,65 +872,42 @@ CONFIG_SATA_VIA=y # CONFIG_PATA_VIA is not set # CONFIG_PATA_WINBOND is not set CONFIG_MD=y -# CONFIG_BLK_DEV_MD is not set +CONFIG_BLK_DEV_MD=y +# CONFIG_MD_LINEAR is not set +# CONFIG_MD_RAID0 is not set +# CONFIG_MD_RAID1 is not set +# CONFIG_MD_RAID10 is not set +# CONFIG_MD_RAID456 is not set +# CONFIG_MD_MULTIPATH is not set +# CONFIG_MD_FAULTY is not set CONFIG_BLK_DEV_DM=y # CONFIG_DM_DEBUG is not set # CONFIG_DM_CRYPT is not set # CONFIG_DM_SNAPSHOT is not set -# CONFIG_DM_MIRROR is not set -# CONFIG_DM_ZERO is not set +CONFIG_DM_MIRROR=y +CONFIG_DM_ZERO=y # CONFIG_DM_MULTIPATH is not set # CONFIG_DM_DELAY is not set - -# -# Fusion MPT device support -# -CONFIG_FUSION=y -CONFIG_FUSION_SPI=y -# CONFIG_FUSION_FC is not set -# CONFIG_FUSION_SAS is not set -CONFIG_FUSION_MAX_SGE=128 -# CONFIG_FUSION_CTL is not set +# CONFIG_DM_UEVENT is not set +# CONFIG_FUSION is not set # # IEEE 1394 (FireWire) support # # CONFIG_FIREWIRE is not set -CONFIG_IEEE1394=y - -# -# Subsystem Options -# -# CONFIG_IEEE1394_VERBOSEDEBUG is not set - -# -# Controllers -# - -# -# Texas Instruments PCILynx requires I2C -# -CONFIG_IEEE1394_OHCI1394=y - -# -# Protocols -# -# CONFIG_IEEE1394_VIDEO1394 is not set -# CONFIG_IEEE1394_SBP2 is not set -# CONFIG_IEEE1394_ETH1394_ROM_ENTRY is not set -# CONFIG_IEEE1394_ETH1394 is not set -# CONFIG_IEEE1394_DV1394 is not set -CONFIG_IEEE1394_RAWIO=y +# CONFIG_IEEE1394 is not set # CONFIG_I2O is not set CONFIG_MACINTOSH_DRIVERS=y -# CONFIG_MAC_EMUMOUSEBTN is not set +CONFIG_MAC_EMUMOUSEBTN=y CONFIG_NETDEVICES=y -CONFIG_NETDEVICES_MULTIQUEUE=y +# CONFIG_NETDEVICES_MULTIQUEUE is not set +# CONFIG_IFB is not set # CONFIG_DUMMY is not set # CONFIG_BONDING is not set # CONFIG_MACVLAN is not set # CONFIG_EQUALIZER is not set # CONFIG_TUN is not set +# CONFIG_VETH is not set # CONFIG_NET_SB1000 is not set # CONFIG_ARCNET is not set # CONFIG_PHYLIB is not set @@ -770,38 +917,40 @@ CONFIG_MII=y # CONFIG_SUNGEM is not set # CONFIG_CASSINI is not set CONFIG_NET_VENDOR_3COM=y -CONFIG_VORTEX=y +# CONFIG_VORTEX is not set # CONFIG_TYPHOON is not set CONFIG_NET_TULIP=y # CONFIG_DE2104X is not set -CONFIG_TULIP=y -# CONFIG_TULIP_MWI is not set -# CONFIG_TULIP_MMIO is not set -# CONFIG_TULIP_NAPI is not set +# CONFIG_TULIP is not set # CONFIG_DE4X5 is not set # CONFIG_WINBOND_840 is not set # CONFIG_DM9102 is not set # CONFIG_ULI526X is not set +# CONFIG_PCMCIA_XIRCOM is not set # CONFIG_HP100 is not set +# CONFIG_IBM_NEW_EMAC_ZMII is not set +# CONFIG_IBM_NEW_EMAC_RGMII is not set +# CONFIG_IBM_NEW_EMAC_TAH is not set +# CONFIG_IBM_NEW_EMAC_EMAC4 is not set CONFIG_NET_PCI=y # CONFIG_PCNET32 is not set # CONFIG_AMD8111_ETH is not set # CONFIG_ADAPTEC_STARFIRE is not set -CONFIG_B44=y +# CONFIG_B44 is not set CONFIG_FORCEDETH=y # CONFIG_FORCEDETH_NAPI is not set -# CONFIG_DGRS is not set # CONFIG_EEPRO100 is not set CONFIG_E100=y # CONFIG_FEALNX is not set # CONFIG_NATSEMI is not set # CONFIG_NE2K_PCI is not set -CONFIG_8139CP=y +# CONFIG_8139CP is not set CONFIG_8139TOO=y -# CONFIG_8139TOO_PIO is not set +CONFIG_8139TOO_PIO=y # CONFIG_8139TOO_TUNE_TWISTER is not set # CONFIG_8139TOO_8129 is not set # CONFIG_8139_OLD_RX_RESET is not set +# CONFIG_R6040 is not set # CONFIG_SIS900 is not set # CONFIG_EPIC100 is not set # CONFIG_SUNDANCE is not set @@ -814,34 +963,75 @@ CONFIG_NETDEV_1000=y CONFIG_E1000=y # CONFIG_E1000_NAPI is not set # CONFIG_E1000_DISABLE_PACKET_SPLIT is not set +# CONFIG_E1000E is not set +# CONFIG_E1000E_ENABLED is not set +# CONFIG_IP1000 is not set +# CONFIG_IGB is not set # CONFIG_NS83820 is not set # CONFIG_HAMACHI is not set # CONFIG_YELLOWFIN is not set -CONFIG_R8169=y -# CONFIG_R8169_NAPI is not set +# CONFIG_R8169 is not set # CONFIG_SIS190 is not set # CONFIG_SKGE is not set CONFIG_SKY2=y +# CONFIG_SKY2_DEBUG is not set # CONFIG_VIA_VELOCITY is not set CONFIG_TIGON3=y -CONFIG_BNX2=y +# CONFIG_BNX2 is not set # CONFIG_QLA3XXX is not set # CONFIG_ATL1 is not set CONFIG_NETDEV_10000=y # CONFIG_CHELSIO_T1 is not set # CONFIG_CHELSIO_T3 is not set +# CONFIG_IXGBE is not set # CONFIG_IXGB is not set # CONFIG_S2IO is not set # CONFIG_MYRI10GE is not set # CONFIG_NETXEN_NIC is not set +# CONFIG_NIU is not set # CONFIG_MLX4_CORE is not set -# CONFIG_TR is not set +# CONFIG_TEHUTI is not set +# CONFIG_BNX2X is not set +# CONFIG_SFC is not set +CONFIG_TR=y +# CONFIG_IBMOL is not set +# CONFIG_IBMLS is not set +# CONFIG_3C359 is not set +# CONFIG_TMS380TR is not set # # Wireless LAN # # CONFIG_WLAN_PRE80211 is not set -# CONFIG_WLAN_80211 is not set +CONFIG_WLAN_80211=y +# CONFIG_PCMCIA_RAYCS is not set +# CONFIG_IPW2100 is not set +# CONFIG_IPW2200 is not set +# CONFIG_LIBERTAS is not set +# CONFIG_AIRO is not set +# CONFIG_HERMES is not set +# CONFIG_ATMEL is not set +# CONFIG_AIRO_CS is not set +# CONFIG_PCMCIA_WL3501 is not set +# CONFIG_PRISM54 is not set +# CONFIG_USB_ZD1201 is not set +# CONFIG_USB_NET_RNDIS_WLAN is not set +# CONFIG_RTL8180 is not set +# CONFIG_RTL8187 is not set +# CONFIG_ADM8211 is not set +# CONFIG_P54_COMMON is not set +CONFIG_ATH5K=y +# CONFIG_ATH5K_DEBUG is not set +# CONFIG_IWLWIFI is not set +# CONFIG_IWLCORE is not set +# CONFIG_IWLWIFI_LEDS is not set +# CONFIG_IWL4965 is not set +# CONFIG_IWL3945 is not set +# CONFIG_HOSTAP is not set +# CONFIG_B43 is not set +# CONFIG_B43LEGACY is not set +# CONFIG_ZD1211RW is not set +# CONFIG_RT2X00 is not set # # USB Network Adapters @@ -850,16 +1040,27 @@ CONFIG_NETDEV_10000=y # CONFIG_USB_KAWETH is not set # CONFIG_USB_PEGASUS is not set # CONFIG_USB_RTL8150 is not set -# CONFIG_USB_USBNET_MII is not set # CONFIG_USB_USBNET is not set +CONFIG_NET_PCMCIA=y +# CONFIG_PCMCIA_3C589 is not set +# CONFIG_PCMCIA_3C574 is not set +# CONFIG_PCMCIA_FMVJ18X is not set +# CONFIG_PCMCIA_PCNET is not set +# CONFIG_PCMCIA_NMCLAN is not set +# CONFIG_PCMCIA_SMC91C92 is not set +# CONFIG_PCMCIA_XIRC2PS is not set +# CONFIG_PCMCIA_AXNET is not set +# CONFIG_PCMCIA_IBMTR is not set # CONFIG_WAN is not set -# CONFIG_FDDI is not set +CONFIG_FDDI=y +# CONFIG_DEFXX is not set +# CONFIG_SKFP is not set # CONFIG_HIPPI is not set # CONFIG_PPP is not set # CONFIG_SLIP is not set # CONFIG_NET_FC is not set -# CONFIG_SHAPER is not set CONFIG_NETCONSOLE=y +# CONFIG_NETCONSOLE_DYNAMIC is not set CONFIG_NETPOLL=y # CONFIG_NETPOLL_TRAP is not set CONFIG_NET_POLL_CONTROLLER=y @@ -870,18 +1071,17 @@ CONFIG_NET_POLL_CONTROLLER=y # Input device support # CONFIG_INPUT=y -# CONFIG_INPUT_FF_MEMLESS is not set -# CONFIG_INPUT_POLLDEV is not set +CONFIG_INPUT_FF_MEMLESS=y +CONFIG_INPUT_POLLDEV=y # # Userland interfaces # CONFIG_INPUT_MOUSEDEV=y -CONFIG_INPUT_MOUSEDEV_PSAUX=y +# CONFIG_INPUT_MOUSEDEV_PSAUX is not set CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024 CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768 # CONFIG_INPUT_JOYDEV is not set -# CONFIG_INPUT_TSDEV is not set CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_EVBUG is not set @@ -906,17 +1106,63 @@ CONFIG_MOUSE_PS2_TRACKPOINT=y # CONFIG_MOUSE_SERIAL is not set # CONFIG_MOUSE_APPLETOUCH is not set # CONFIG_MOUSE_VSXXXAA is not set -# CONFIG_INPUT_JOYSTICK is not set -# CONFIG_INPUT_TABLET is not set -# CONFIG_INPUT_TOUCHSCREEN is not set -# CONFIG_INPUT_MISC is not set +CONFIG_INPUT_JOYSTICK=y +# CONFIG_JOYSTICK_ANALOG is not set +# CONFIG_JOYSTICK_A3D is not set +# CONFIG_JOYSTICK_ADI is not set +# CONFIG_JOYSTICK_COBRA is not set +# CONFIG_JOYSTICK_GF2K is not set +# CONFIG_JOYSTICK_GRIP is not set +# CONFIG_JOYSTICK_GRIP_MP is not set +# CONFIG_JOYSTICK_GUILLEMOT is not set +# CONFIG_JOYSTICK_INTERACT is not set +# CONFIG_JOYSTICK_SIDEWINDER is not set +# CONFIG_JOYSTICK_TMDC is not set +# CONFIG_JOYSTICK_IFORCE is not set +# CONFIG_JOYSTICK_WARRIOR is not set +# CONFIG_JOYSTICK_MAGELLAN is not set +# CONFIG_JOYSTICK_SPACEORB is not set +# CONFIG_JOYSTICK_SPACEBALL is not set +# CONFIG_JOYSTICK_STINGER is not set +# CONFIG_JOYSTICK_TWIDJOY is not set +# CONFIG_JOYSTICK_ZHENHUA is not set +# CONFIG_JOYSTICK_JOYDUMP is not set +# CONFIG_JOYSTICK_XPAD is not set +CONFIG_INPUT_TABLET=y +# CONFIG_TABLET_USB_ACECAD is not set +# CONFIG_TABLET_USB_AIPTEK is not set +# CONFIG_TABLET_USB_GTCO is not set +# CONFIG_TABLET_USB_KBTAB is not set +# CONFIG_TABLET_USB_WACOM is not set +CONFIG_INPUT_TOUCHSCREEN=y +# CONFIG_TOUCHSCREEN_FUJITSU is not set +# CONFIG_TOUCHSCREEN_GUNZE is not set +# CONFIG_TOUCHSCREEN_ELO is not set +# CONFIG_TOUCHSCREEN_MTOUCH is not set +# CONFIG_TOUCHSCREEN_MK712 is not set +# CONFIG_TOUCHSCREEN_PENMOUNT is not set +# CONFIG_TOUCHSCREEN_TOUCHRIGHT is not set +# CONFIG_TOUCHSCREEN_TOUCHWIN is not set +# CONFIG_TOUCHSCREEN_UCB1400 is not set +# CONFIG_TOUCHSCREEN_USB_COMPOSITE is not set +CONFIG_INPUT_MISC=y +# CONFIG_INPUT_PCSPKR is not set +# CONFIG_INPUT_APANEL is not set +# CONFIG_INPUT_WISTRON_BTNS is not set +# CONFIG_INPUT_ATLAS_BTNS is not set +# CONFIG_INPUT_ATI_REMOTE is not set +# CONFIG_INPUT_ATI_REMOTE2 is not set +# CONFIG_INPUT_KEYSPAN_REMOTE is not set +# CONFIG_INPUT_POWERMATE is not set +# CONFIG_INPUT_YEALINK is not set +# CONFIG_INPUT_UINPUT is not set # # Hardware I/O ports # CONFIG_SERIO=y CONFIG_SERIO_I8042=y -# CONFIG_SERIO_SERPORT is not set +CONFIG_SERIO_SERPORT=y # CONFIG_SERIO_CT82C710 is not set # CONFIG_SERIO_PCIPS2 is not set CONFIG_SERIO_LIBPS2=y @@ -929,8 +1175,26 @@ CONFIG_SERIO_LIBPS2=y CONFIG_VT=y CONFIG_VT_CONSOLE=y CONFIG_HW_CONSOLE=y -# CONFIG_VT_HW_CONSOLE_BINDING is not set -# CONFIG_SERIAL_NONSTANDARD is not set +CONFIG_VT_HW_CONSOLE_BINDING=y +CONFIG_DEVKMEM=y +CONFIG_SERIAL_NONSTANDARD=y +# CONFIG_COMPUTONE is not set +# CONFIG_ROCKETPORT is not set +# CONFIG_CYCLADES is not set +# CONFIG_DIGIEPCA is not set +# CONFIG_MOXA_INTELLIO is not set +# CONFIG_MOXA_SMARTIO is not set +# CONFIG_ISI is not set +# CONFIG_SYNCLINK is not set +# CONFIG_SYNCLINKMP is not set +# CONFIG_SYNCLINK_GT is not set +# CONFIG_N_HDLC is not set +# CONFIG_RISCOM8 is not set +# CONFIG_SPECIALIX is not set +# CONFIG_SX is not set +# CONFIG_RIO is not set +# CONFIG_STALDRV is not set +# CONFIG_NOZOMI is not set # # Serial drivers @@ -940,9 +1204,14 @@ CONFIG_SERIAL_8250_CONSOLE=y CONFIG_FIX_EARLYCON_MEM=y CONFIG_SERIAL_8250_PCI=y CONFIG_SERIAL_8250_PNP=y -CONFIG_SERIAL_8250_NR_UARTS=4 +# CONFIG_SERIAL_8250_CS is not set +CONFIG_SERIAL_8250_NR_UARTS=32 CONFIG_SERIAL_8250_RUNTIME_UARTS=4 -# CONFIG_SERIAL_8250_EXTENDED is not set +CONFIG_SERIAL_8250_EXTENDED=y +CONFIG_SERIAL_8250_MANY_PORTS=y +CONFIG_SERIAL_8250_SHARE_IRQ=y +CONFIG_SERIAL_8250_DETECT_IRQ=y +CONFIG_SERIAL_8250_RSA=y # # Non-8250 serial port support @@ -951,89 +1220,275 @@ CONFIG_SERIAL_CORE=y CONFIG_SERIAL_CORE_CONSOLE=y # CONFIG_SERIAL_JSM is not set CONFIG_UNIX98_PTYS=y -CONFIG_LEGACY_PTYS=y -CONFIG_LEGACY_PTY_COUNT=256 +# CONFIG_LEGACY_PTYS is not set # CONFIG_IPMI_HANDLER is not set -# CONFIG_WATCHDOG is not set CONFIG_HW_RANDOM=y -CONFIG_HW_RANDOM_INTEL=y -CONFIG_HW_RANDOM_AMD=y +# CONFIG_HW_RANDOM_INTEL is not set +# CONFIG_HW_RANDOM_AMD is not set CONFIG_HW_RANDOM_GEODE=y CONFIG_HW_RANDOM_VIA=y -# CONFIG_NVRAM is not set -CONFIG_RTC=y +CONFIG_NVRAM=y # CONFIG_R3964 is not set # CONFIG_APPLICOM is not set # CONFIG_SONYPI is not set -CONFIG_AGP=y -# CONFIG_AGP_ALI is not set -# CONFIG_AGP_ATI is not set -# CONFIG_AGP_AMD is not set -CONFIG_AGP_AMD64=y -CONFIG_AGP_INTEL=y -# CONFIG_AGP_NVIDIA is not set -# CONFIG_AGP_SIS is not set -# CONFIG_AGP_SWORKS is not set -# CONFIG_AGP_VIA is not set -# CONFIG_AGP_EFFICEON is not set -# CONFIG_DRM is not set + +# +# PCMCIA character devices +# +# CONFIG_SYNCLINK_CS is not set +# CONFIG_CARDMAN_4000 is not set +# CONFIG_CARDMAN_4040 is not set +# CONFIG_IPWIRELESS is not set # CONFIG_MWAVE is not set # CONFIG_PC8736x_GPIO is not set # CONFIG_NSC_GPIO is not set # CONFIG_CS5535_GPIO is not set -CONFIG_RAW_DRIVER=y -CONFIG_MAX_RAW_DEVS=256 +# CONFIG_RAW_DRIVER is not set CONFIG_HPET=y # CONFIG_HPET_RTC_IRQ is not set -CONFIG_HPET_MMAP=y +# CONFIG_HPET_MMAP is not set # CONFIG_HANGCHECK_TIMER is not set # CONFIG_TCG_TPM is not set # CONFIG_TELCLOCK is not set CONFIG_DEVPORT=y -# CONFIG_I2C is not set - -# -# SPI support -# +CONFIG_I2C=y +CONFIG_I2C_BOARDINFO=y +# CONFIG_I2C_CHARDEV is not set + +# +# I2C Hardware Bus support +# +# CONFIG_I2C_ALI1535 is not set +# CONFIG_I2C_ALI1563 is not set +# CONFIG_I2C_ALI15X3 is not set +# CONFIG_I2C_AMD756 is not set +# CONFIG_I2C_AMD8111 is not set +CONFIG_I2C_I801=y +# CONFIG_I2C_I810 is not set +# CONFIG_I2C_PIIX4 is not set +# CONFIG_I2C_NFORCE2 is not set +# CONFIG_I2C_OCORES is not set +# CONFIG_I2C_PARPORT_LIGHT is not set +# CONFIG_I2C_PROSAVAGE is not set +# CONFIG_I2C_SAVAGE4 is not set +# CONFIG_I2C_SIMTEC is not set +# CONFIG_SCx200_ACB is not set +# CONFIG_I2C_SIS5595 is not set +# CONFIG_I2C_SIS630 is not set +# CONFIG_I2C_SIS96X is not set +# CONFIG_I2C_TAOS_EVM is not set +# CONFIG_I2C_STUB is not set +# CONFIG_I2C_TINY_USB is not set +# CONFIG_I2C_VIA is not set +# CONFIG_I2C_VIAPRO is not set +# CONFIG_I2C_VOODOO3 is not set +# CONFIG_I2C_PCA_PLATFORM is not set + +# +# Miscellaneous I2C Chip support +# +# CONFIG_DS1682 is not set +# CONFIG_SENSORS_EEPROM is not set +# CONFIG_SENSORS_PCF8574 is not set +# CONFIG_PCF8575 is not set +# CONFIG_SENSORS_PCF8591 is not set +# CONFIG_SENSORS_MAX6875 is not set +# CONFIG_SENSORS_TSL2550 is not set +# CONFIG_I2C_DEBUG_CORE is not set +# CONFIG_I2C_DEBUG_ALGO is not set +# CONFIG_I2C_DEBUG_BUS is not set +# CONFIG_I2C_DEBUG_CHIP is not set # CONFIG_SPI is not set -# CONFIG_SPI_MASTER is not set # CONFIG_W1 is not set -# CONFIG_POWER_SUPPLY is not set +CONFIG_POWER_SUPPLY=y +# CONFIG_POWER_SUPPLY_DEBUG is not set +# CONFIG_PDA_POWER is not set +# CONFIG_BATTERY_DS2760 is not set # CONFIG_HWMON is not set +CONFIG_THERMAL=y +CONFIG_WATCHDOG=y +# CONFIG_WATCHDOG_NOWAYOUT is not set + +# +# Watchdog Device Drivers +# +# CONFIG_SOFT_WATCHDOG is not set +# CONFIG_ACQUIRE_WDT is not set +# CONFIG_ADVANTECH_WDT is not set +# CONFIG_ALIM1535_WDT is not set +# CONFIG_ALIM7101_WDT is not set +# CONFIG_SC520_WDT is not set +# CONFIG_EUROTECH_WDT is not set +# CONFIG_IB700_WDT is not set +# CONFIG_IBMASR is not set +# CONFIG_WAFER_WDT is not set +# CONFIG_I6300ESB_WDT is not set +# CONFIG_ITCO_WDT is not set +# CONFIG_IT8712F_WDT is not set +# CONFIG_HP_WATCHDOG is not set +# CONFIG_SC1200_WDT is not set +# CONFIG_PC87413_WDT is not set +# CONFIG_60XX_WDT is not set +# CONFIG_SBC8360_WDT is not set +# CONFIG_SBC7240_WDT is not set +# CONFIG_CPU5_WDT is not set +# CONFIG_SMSC37B787_WDT is not set +# CONFIG_W83627HF_WDT is not set +# CONFIG_W83697HF_WDT is not set +# CONFIG_W83877F_WDT is not set +# CONFIG_W83977F_WDT is not set +# CONFIG_MACHZ_WDT is not set +# CONFIG_SBC_EPX_C3_WATCHDOG is not set + +# +# PCI-based Watchdog Cards +# +# CONFIG_PCIPCWATCHDOG is not set +# CONFIG_WDTPCI is not set + +# +# USB-based Watchdog Cards +# +# CONFIG_USBPCWATCHDOG is not set + +# +# Sonics Silicon Backplane +# +CONFIG_SSB_POSSIBLE=y +# CONFIG_SSB is not set # # Multifunction device drivers # # CONFIG_MFD_SM501 is not set +# CONFIG_HTC_PASIC3 is not set # # Multimedia devices # + +# +# Multimedia core support +# # CONFIG_VIDEO_DEV is not set # CONFIG_DVB_CORE is not set + +# +# Multimedia drivers +# CONFIG_DAB=y # CONFIG_USB_DABUSB is not set # # Graphics support # -# CONFIG_BACKLIGHT_LCD_SUPPORT is not set +CONFIG_AGP=y +# CONFIG_AGP_ALI is not set +# CONFIG_AGP_ATI is not set +# CONFIG_AGP_AMD is not set +CONFIG_AGP_AMD64=y +CONFIG_AGP_INTEL=y +# CONFIG_AGP_NVIDIA is not set +# CONFIG_AGP_SIS is not set +# CONFIG_AGP_SWORKS is not set +# CONFIG_AGP_VIA is not set +# CONFIG_AGP_EFFICEON is not set +CONFIG_DRM=y +# CONFIG_DRM_TDFX is not set +# CONFIG_DRM_R128 is not set +# CONFIG_DRM_RADEON is not set +# CONFIG_DRM_I810 is not set +# CONFIG_DRM_I830 is not set +CONFIG_DRM_I915=y +# CONFIG_DRM_MGA is not set +# CONFIG_DRM_SIS is not set +# CONFIG_DRM_VIA is not set +# CONFIG_DRM_SAVAGE is not set +# CONFIG_VGASTATE is not set +# CONFIG_VIDEO_OUTPUT_CONTROL is not set +CONFIG_FB=y +# CONFIG_FIRMWARE_EDID is not set +# CONFIG_FB_DDC is not set +CONFIG_FB_CFB_FILLRECT=y +CONFIG_FB_CFB_COPYAREA=y +CONFIG_FB_CFB_IMAGEBLIT=y +# CONFIG_FB_CFB_REV_PIXELS_IN_BYTE is not set +# CONFIG_FB_SYS_FILLRECT is not set +# CONFIG_FB_SYS_COPYAREA is not set +# CONFIG_FB_SYS_IMAGEBLIT is not set +# CONFIG_FB_FOREIGN_ENDIAN is not set +# CONFIG_FB_SYS_FOPS is not set +CONFIG_FB_DEFERRED_IO=y +# CONFIG_FB_SVGALIB is not set +# CONFIG_FB_MACMODES is not set +# CONFIG_FB_BACKLIGHT is not set +CONFIG_FB_MODE_HELPERS=y +CONFIG_FB_TILEBLITTING=y + +# +# Frame buffer hardware drivers +# +# CONFIG_FB_CIRRUS is not set +# CONFIG_FB_PM2 is not set +# CONFIG_FB_CYBER2000 is not set +# CONFIG_FB_ARC is not set +# CONFIG_FB_ASILIANT is not set +# CONFIG_FB_IMSTT is not set +# CONFIG_FB_VGA16 is not set +# CONFIG_FB_UVESA is not set +# CONFIG_FB_VESA is not set +CONFIG_FB_EFI=y +# CONFIG_FB_IMAC is not set +# CONFIG_FB_N411 is not set +# CONFIG_FB_HGA is not set +# CONFIG_FB_S1D13XXX is not set +# CONFIG_FB_NVIDIA is not set +# CONFIG_FB_RIVA is not set +# CONFIG_FB_I810 is not set +# CONFIG_FB_LE80578 is not set +# CONFIG_FB_INTEL is not set +# CONFIG_FB_MATROX is not set +# CONFIG_FB_RADEON is not set +# CONFIG_FB_ATY128 is not set +# CONFIG_FB_ATY is not set +# CONFIG_FB_S3 is not set +# CONFIG_FB_SAVAGE is not set +# CONFIG_FB_SIS is not set +# CONFIG_FB_NEOMAGIC is not set +# CONFIG_FB_KYRO is not set +# CONFIG_FB_3DFX is not set +# CONFIG_FB_VOODOO1 is not set +# CONFIG_FB_VT8623 is not set +# CONFIG_FB_CYBLA is not set +# CONFIG_FB_TRIDENT is not set +# CONFIG_FB_ARK is not set +# CONFIG_FB_PM3 is not set +# CONFIG_FB_GEODE is not set +# CONFIG_FB_VIRTUAL is not set +CONFIG_BACKLIGHT_LCD_SUPPORT=y +# CONFIG_LCD_CLASS_DEVICE is not set +CONFIG_BACKLIGHT_CLASS_DEVICE=y +# CONFIG_BACKLIGHT_CORGI is not set +# CONFIG_BACKLIGHT_PROGEAR is not set # # Display device support # # CONFIG_DISPLAY_SUPPORT is not set -# CONFIG_VGASTATE is not set -# CONFIG_FB is not set # # Console display driver support # CONFIG_VGA_CONSOLE=y CONFIG_VGACON_SOFT_SCROLLBACK=y -CONFIG_VGACON_SOFT_SCROLLBACK_SIZE=128 +CONFIG_VGACON_SOFT_SCROLLBACK_SIZE=64 CONFIG_VIDEO_SELECT=y CONFIG_DUMMY_CONSOLE=y +# CONFIG_FRAMEBUFFER_CONSOLE is not set +CONFIG_LOGO=y +# CONFIG_LOGO_LINUX_MONO is not set +# CONFIG_LOGO_LINUX_VGA16 is not set +CONFIG_LOGO_LINUX_CLUT224=y # # Sound @@ -1043,33 +1498,167 @@ CONFIG_SOUND=y # # Advanced Linux Sound Architecture # -# CONFIG_SND is not set +CONFIG_SND=y +CONFIG_SND_TIMER=y +CONFIG_SND_PCM=y +CONFIG_SND_HWDEP=y +CONFIG_SND_SEQUENCER=y +CONFIG_SND_SEQ_DUMMY=y +CONFIG_SND_OSSEMUL=y +CONFIG_SND_MIXER_OSS=y +CONFIG_SND_PCM_OSS=y +CONFIG_SND_PCM_OSS_PLUGINS=y +CONFIG_SND_SEQUENCER_OSS=y +CONFIG_SND_DYNAMIC_MINORS=y +CONFIG_SND_SUPPORT_OLD_API=y +CONFIG_SND_VERBOSE_PROCFS=y +# CONFIG_SND_VERBOSE_PRINTK is not set +# CONFIG_SND_DEBUG is not set +CONFIG_SND_VMASTER=y + +# +# Generic devices +# +# CONFIG_SND_PCSP is not set +# CONFIG_SND_DUMMY is not set +# CONFIG_SND_VIRMIDI is not set +# CONFIG_SND_MTPAV is not set +# CONFIG_SND_SERIAL_U16550 is not set +# CONFIG_SND_MPU401 is not set + +# +# PCI devices +# +# CONFIG_SND_AD1889 is not set +# CONFIG_SND_ALS300 is not set +# CONFIG_SND_ALS4000 is not set +# CONFIG_SND_ALI5451 is not set +# CONFIG_SND_ATIIXP is not set +# CONFIG_SND_ATIIXP_MODEM is not set +# CONFIG_SND_AU8810 is not set +# CONFIG_SND_AU8820 is not set +# CONFIG_SND_AU8830 is not set +# CONFIG_SND_AW2 is not set +# CONFIG_SND_AZT3328 is not set +# CONFIG_SND_BT87X is not set +# CONFIG_SND_CA0106 is not set +# CONFIG_SND_CMIPCI is not set +# CONFIG_SND_OXYGEN is not set +# CONFIG_SND_CS4281 is not set +# CONFIG_SND_CS46XX is not set +# CONFIG_SND_CS5530 is not set +# CONFIG_SND_CS5535AUDIO is not set +# CONFIG_SND_DARLA20 is not set +# CONFIG_SND_GINA20 is not set +# CONFIG_SND_LAYLA20 is not set +# CONFIG_SND_DARLA24 is not set +# CONFIG_SND_GINA24 is not set +# CONFIG_SND_LAYLA24 is not set +# CONFIG_SND_MONA is not set +# CONFIG_SND_MIA is not set +# CONFIG_SND_ECHO3G is not set +# CONFIG_SND_INDIGO is not set +# CONFIG_SND_INDIGOIO is not set +# CONFIG_SND_INDIGODJ is not set +# CONFIG_SND_EMU10K1 is not set +# CONFIG_SND_EMU10K1X is not set +# CONFIG_SND_ENS1370 is not set +# CONFIG_SND_ENS1371 is not set +# CONFIG_SND_ES1938 is not set +# CONFIG_SND_ES1968 is not set +# CONFIG_SND_FM801 is not set +CONFIG_SND_HDA_INTEL=y +CONFIG_SND_HDA_HWDEP=y +CONFIG_SND_HDA_CODEC_REALTEK=y +CONFIG_SND_HDA_CODEC_ANALOG=y +CONFIG_SND_HDA_CODEC_SIGMATEL=y +CONFIG_SND_HDA_CODEC_VIA=y +CONFIG_SND_HDA_CODEC_ATIHDMI=y +CONFIG_SND_HDA_CODEC_CONEXANT=y +CONFIG_SND_HDA_CODEC_CMEDIA=y +CONFIG_SND_HDA_CODEC_SI3054=y +CONFIG_SND_HDA_GENERIC=y +# CONFIG_SND_HDA_POWER_SAVE is not set +# CONFIG_SND_HDSP is not set +# CONFIG_SND_HDSPM is not set +# CONFIG_SND_HIFIER is not set +# CONFIG_SND_ICE1712 is not set +# CONFIG_SND_ICE1724 is not set +# CONFIG_SND_INTEL8X0 is not set +# CONFIG_SND_INTEL8X0M is not set +# CONFIG_SND_KORG1212 is not set +# CONFIG_SND_MAESTRO3 is not set +# CONFIG_SND_MIXART is not set +# CONFIG_SND_NM256 is not set +# CONFIG_SND_PCXHR is not set +# CONFIG_SND_RIPTIDE is not set +# CONFIG_SND_RME32 is not set +# CONFIG_SND_RME96 is not set +# CONFIG_SND_RME9652 is not set +# CONFIG_SND_SIS7019 is not set +# CONFIG_SND_SONICVIBES is not set +# CONFIG_SND_TRIDENT is not set +# CONFIG_SND_VIA82XX is not set +# CONFIG_SND_VIA82XX_MODEM is not set +# CONFIG_SND_VIRTUOSO is not set +# CONFIG_SND_VX222 is not set +# CONFIG_SND_YMFPCI is not set + +# +# USB devices +# +# CONFIG_SND_USB_AUDIO is not set +# CONFIG_SND_USB_USX2Y is not set +# CONFIG_SND_USB_CAIAQ is not set + +# +# PCMCIA devices +# +# CONFIG_SND_VXPOCKET is not set +# CONFIG_SND_PDAUDIOCF is not set + +# +# System on Chip audio support +# +# CONFIG_SND_SOC is not set + +# +# ALSA SoC audio for Freescale SOCs +# + +# +# SoC Audio for the Texas Instruments OMAP +# # # Open Sound System # -CONFIG_SOUND_PRIME=y -# CONFIG_SOUND_TRIDENT is not set -# CONFIG_SOUND_MSNDCLAS is not set -# CONFIG_SOUND_MSNDPIN is not set -# CONFIG_SOUND_OSS is not set +# CONFIG_SOUND_PRIME is not set CONFIG_HID_SUPPORT=y CONFIG_HID=y -# CONFIG_HID_DEBUG is not set +CONFIG_HID_DEBUG=y +CONFIG_HIDRAW=y # # USB Input Devices # CONFIG_USB_HID=y -# CONFIG_USB_HIDINPUT_POWERBOOK is not set -# CONFIG_HID_FF is not set -# CONFIG_USB_HIDDEV is not set +CONFIG_USB_HIDINPUT_POWERBOOK=y +CONFIG_HID_FF=y +CONFIG_HID_PID=y +CONFIG_LOGITECH_FF=y +# CONFIG_LOGIRUMBLEPAD2_FF is not set +CONFIG_PANTHERLORD_FF=y +CONFIG_THRUSTMASTER_FF=y +CONFIG_ZEROPLUS_FF=y +CONFIG_USB_HIDDEV=y CONFIG_USB_SUPPORT=y CONFIG_USB_ARCH_HAS_HCD=y CONFIG_USB_ARCH_HAS_OHCI=y CONFIG_USB_ARCH_HAS_EHCI=y CONFIG_USB=y -# CONFIG_USB_DEBUG is not set +CONFIG_USB_DEBUG=y +CONFIG_USB_ANNOUNCE_NEW_DEVICES=y # # Miscellaneous USB options @@ -1077,18 +1666,18 @@ CONFIG_USB=y CONFIG_USB_DEVICEFS=y # CONFIG_USB_DEVICE_CLASS is not set # CONFIG_USB_DYNAMIC_MINORS is not set -# CONFIG_USB_SUSPEND is not set -# CONFIG_USB_PERSIST is not set +CONFIG_USB_SUSPEND=y # CONFIG_USB_OTG is not set # # USB Host Controller Drivers # +# CONFIG_USB_C67X00_HCD is not set CONFIG_USB_EHCI_HCD=y -# CONFIG_USB_EHCI_SPLIT_ISO is not set # CONFIG_USB_EHCI_ROOT_HUB_TT is not set # CONFIG_USB_EHCI_TT_NEWSCHED is not set # CONFIG_USB_ISP116X_HCD is not set +# CONFIG_USB_ISP1760_HCD is not set CONFIG_USB_OHCI_HCD=y # CONFIG_USB_OHCI_BIG_ENDIAN_DESC is not set # CONFIG_USB_OHCI_BIG_ENDIAN_MMIO is not set @@ -1121,8 +1710,10 @@ CONFIG_USB_STORAGE=y # CONFIG_USB_STORAGE_SDDR55 is not set # CONFIG_USB_STORAGE_JUMPSHOT is not set # CONFIG_USB_STORAGE_ALAUDA is not set +# CONFIG_USB_STORAGE_ONETOUCH is not set # CONFIG_USB_STORAGE_KARMA is not set -# CONFIG_USB_LIBUSUAL is not set +# CONFIG_USB_STORAGE_CYPRESS_ATACB is not set +CONFIG_USB_LIBUSUAL=y # # USB Imaging devices @@ -1134,10 +1725,6 @@ CONFIG_USB_MON=y # # USB port drivers # - -# -# USB Serial Converter support -# # CONFIG_USB_SERIAL is not set # @@ -1163,90 +1750,125 @@ CONFIG_USB_MON=y # CONFIG_USB_TRANCEVIBRATOR is not set # CONFIG_USB_IOWARRIOR is not set # CONFIG_USB_TEST is not set +# CONFIG_USB_GADGET is not set +# CONFIG_MMC is not set +# CONFIG_MEMSTICK is not set +CONFIG_NEW_LEDS=y +CONFIG_LEDS_CLASS=y # -# USB DSL modem support +# LED drivers # +# CONFIG_LEDS_CLEVO_MAIL is not set # -# USB Gadget Support +# LED Triggers # -# CONFIG_USB_GADGET is not set -# CONFIG_MMC is not set +CONFIG_LEDS_TRIGGERS=y +# CONFIG_LEDS_TRIGGER_TIMER is not set +# CONFIG_LEDS_TRIGGER_HEARTBEAT is not set +# CONFIG_LEDS_TRIGGER_DEFAULT_ON is not set +# CONFIG_ACCESSIBILITY is not set +# CONFIG_INFINIBAND is not set +CONFIG_EDAC=y # -# LED devices +# Reporting subsystems # -# CONFIG_NEW_LEDS is not set +# CONFIG_EDAC_DEBUG is not set +# CONFIG_EDAC_MM_EDAC is not set +CONFIG_RTC_LIB=y +CONFIG_RTC_CLASS=y +# CONFIG_RTC_HCTOSYS is not set +# CONFIG_RTC_DEBUG is not set # -# LED drivers +# RTC interfaces # +CONFIG_RTC_INTF_SYSFS=y +CONFIG_RTC_INTF_PROC=y +CONFIG_RTC_INTF_DEV=y +# CONFIG_RTC_INTF_DEV_UIE_EMUL is not set +# CONFIG_RTC_DRV_TEST is not set # -# LED Triggers +# I2C RTC drivers # -# CONFIG_INFINIBAND is not set -# CONFIG_EDAC is not set +# CONFIG_RTC_DRV_DS1307 is not set +# CONFIG_RTC_DRV_DS1374 is not set +# CONFIG_RTC_DRV_DS1672 is not set +# CONFIG_RTC_DRV_MAX6900 is not set +# CONFIG_RTC_DRV_RS5C372 is not set +# CONFIG_RTC_DRV_ISL1208 is not set +# CONFIG_RTC_DRV_X1205 is not set +# CONFIG_RTC_DRV_PCF8563 is not set +# CONFIG_RTC_DRV_PCF8583 is not set +# CONFIG_RTC_DRV_M41T80 is not set +# CONFIG_RTC_DRV_S35390A is not set # -# Real Time Clock +# SPI RTC drivers # -# CONFIG_RTC_CLASS is not set # -# DMA Engine support +# Platform RTC drivers # -# CONFIG_DMA_ENGINE is not set +CONFIG_RTC_DRV_CMOS=y +# CONFIG_RTC_DRV_DS1511 is not set +# CONFIG_RTC_DRV_DS1553 is not set +# CONFIG_RTC_DRV_DS1742 is not set +# CONFIG_RTC_DRV_STK17TA8 is not set +# CONFIG_RTC_DRV_M48T86 is not set +# CONFIG_RTC_DRV_M48T59 is not set +# CONFIG_RTC_DRV_V3020 is not set # -# DMA Clients +# on-CPU RTC drivers # +CONFIG_DMADEVICES=y # # DMA Devices # -CONFIG_VIRTUALIZATION=y -# CONFIG_KVM is not set +# CONFIG_INTEL_IOATDMA is not set +# CONFIG_UIO is not set # -# Userspace I/O +# Firmware Drivers # -# CONFIG_UIO is not set +# CONFIG_EDD is not set +CONFIG_EFI_VARS=y +# CONFIG_DELL_RBU is not set +# CONFIG_DCDBAS is not set +CONFIG_DMIID=y +# CONFIG_ISCSI_IBFT_FIND is not set # # File systems # -CONFIG_EXT2_FS=y -CONFIG_EXT2_FS_XATTR=y -CONFIG_EXT2_FS_POSIX_ACL=y -# CONFIG_EXT2_FS_SECURITY is not set -# CONFIG_EXT2_FS_XIP is not set +# CONFIG_EXT2_FS is not set CONFIG_EXT3_FS=y CONFIG_EXT3_FS_XATTR=y CONFIG_EXT3_FS_POSIX_ACL=y -# CONFIG_EXT3_FS_SECURITY is not set +CONFIG_EXT3_FS_SECURITY=y # CONFIG_EXT4DEV_FS is not set CONFIG_JBD=y # CONFIG_JBD_DEBUG is not set CONFIG_FS_MBCACHE=y -CONFIG_REISERFS_FS=y -# CONFIG_REISERFS_CHECK is not set -# CONFIG_REISERFS_PROC_INFO is not set -CONFIG_REISERFS_FS_XATTR=y -CONFIG_REISERFS_FS_POSIX_ACL=y -# CONFIG_REISERFS_FS_SECURITY is not set +# CONFIG_REISERFS_FS is not set # CONFIG_JFS_FS is not set CONFIG_FS_POSIX_ACL=y # CONFIG_XFS_FS is not set -# CONFIG_GFS2_FS is not set # CONFIG_OCFS2_FS is not set -# CONFIG_MINIX_FS is not set -# CONFIG_ROMFS_FS is not set +CONFIG_DNOTIFY=y CONFIG_INOTIFY=y CONFIG_INOTIFY_USER=y -# CONFIG_QUOTA is not set -CONFIG_DNOTIFY=y +CONFIG_QUOTA=y +CONFIG_QUOTA_NETLINK_INTERFACE=y +# CONFIG_PRINT_QUOTA_WARNING is not set +# CONFIG_QFMT_V1 is not set +CONFIG_QFMT_V2=y +CONFIG_QUOTACTL=y # CONFIG_AUTOFS_FS is not set CONFIG_AUTOFS4_FS=y # CONFIG_FUSE_FS is not set @@ -1256,8 +1878,8 @@ CONFIG_GENERIC_ACL=y # CD-ROM/DVD Filesystems # CONFIG_ISO9660_FS=y -# CONFIG_JOLIET is not set -# CONFIG_ZISOFS is not set +CONFIG_JOLIET=y +CONFIG_ZISOFS=y # CONFIG_UDF_FS is not set # @@ -1275,13 +1897,13 @@ CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1" # CONFIG_PROC_FS=y CONFIG_PROC_KCORE=y +CONFIG_PROC_VMCORE=y CONFIG_PROC_SYSCTL=y CONFIG_SYSFS=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_HUGETLBFS=y CONFIG_HUGETLB_PAGE=y -CONFIG_RAMFS=y # CONFIG_CONFIGFS_FS is not set # @@ -1289,6 +1911,7 @@ CONFIG_RAMFS=y # # CONFIG_ADFS_FS is not set # CONFIG_AFFS_FS is not set +# CONFIG_ECRYPT_FS is not set # CONFIG_HFS_FS is not set # CONFIG_HFSPLUS_FS is not set # CONFIG_BEFS_FS is not set @@ -1296,33 +1919,15 @@ CONFIG_RAMFS=y # CONFIG_EFS_FS is not set # CONFIG_CRAMFS is not set # CONFIG_VXFS_FS is not set +# CONFIG_MINIX_FS is not set # CONFIG_HPFS_FS is not set # CONFIG_QNX4FS_FS is not set +# CONFIG_ROMFS_FS is not set # CONFIG_SYSV_FS is not set # CONFIG_UFS_FS is not set - -# -# Network File Systems -# -CONFIG_NFS_FS=y -CONFIG_NFS_V3=y -# CONFIG_NFS_V3_ACL is not set -# CONFIG_NFS_V4 is not set -# CONFIG_NFS_DIRECTIO is not set -CONFIG_NFSD=y -CONFIG_NFSD_V3=y -# CONFIG_NFSD_V3_ACL is not set -# CONFIG_NFSD_V4 is not set -CONFIG_NFSD_TCP=y -CONFIG_ROOT_NFS=y -CONFIG_LOCKD=y -CONFIG_LOCKD_V4=y -CONFIG_EXPORTFS=y -CONFIG_NFS_COMMON=y -CONFIG_SUNRPC=y -# CONFIG_SUNRPC_BIND34 is not set -# CONFIG_RPCSEC_GSS_KRB5 is not set -# CONFIG_RPCSEC_GSS_SPKM3 is not set +CONFIG_NETWORK_FILESYSTEMS=y +# CONFIG_NFS_FS is not set +# CONFIG_NFSD is not set # CONFIG_SMB_FS is not set # CONFIG_CIFS is not set # CONFIG_NCP_FS is not set @@ -1332,14 +1937,26 @@ CONFIG_SUNRPC=y # # Partition Types # -# CONFIG_PARTITION_ADVANCED is not set +CONFIG_PARTITION_ADVANCED=y +# CONFIG_ACORN_PARTITION is not set +CONFIG_OSF_PARTITION=y +CONFIG_AMIGA_PARTITION=y +# CONFIG_ATARI_PARTITION is not set +CONFIG_MAC_PARTITION=y CONFIG_MSDOS_PARTITION=y - -# -# Native Language Support -# +CONFIG_BSD_DISKLABEL=y +CONFIG_MINIX_SUBPARTITION=y +CONFIG_SOLARIS_X86_PARTITION=y +CONFIG_UNIXWARE_DISKLABEL=y +# CONFIG_LDM_PARTITION is not set +CONFIG_SGI_PARTITION=y +# CONFIG_ULTRIX_PARTITION is not set +CONFIG_SUN_PARTITION=y +CONFIG_KARMA_PARTITION=y +CONFIG_EFI_PARTITION=y +# CONFIG_SYSV68_PARTITION is not set CONFIG_NLS=y -CONFIG_NLS_DEFAULT="iso8859-1" +CONFIG_NLS_DEFAULT="utf8" CONFIG_NLS_CODEPAGE_437=y # CONFIG_NLS_CODEPAGE_737 is not set # CONFIG_NLS_CODEPAGE_775 is not set @@ -1374,37 +1991,33 @@ CONFIG_NLS_ISO8859_1=y # CONFIG_NLS_ISO8859_9 is not set # CONFIG_NLS_ISO8859_13 is not set # CONFIG_NLS_ISO8859_14 is not set -CONFIG_NLS_ISO8859_15=y +# CONFIG_NLS_ISO8859_15 is not set # CONFIG_NLS_KOI8_R is not set # CONFIG_NLS_KOI8_U is not set CONFIG_NLS_UTF8=y - -# -# Distributed Lock Manager -# # CONFIG_DLM is not set -CONFIG_INSTRUMENTATION=y -CONFIG_PROFILING=y -CONFIG_OPROFILE=y -CONFIG_KPROBES=y # # Kernel hacking # CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set +# CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_FRAME_WARN=2048 CONFIG_MAGIC_SYSRQ=y -CONFIG_UNUSED_SYMBOLS=y -# CONFIG_DEBUG_FS is not set +# CONFIG_UNUSED_SYMBOLS is not set +CONFIG_DEBUG_FS=y # CONFIG_HEADERS_CHECK is not set CONFIG_DEBUG_KERNEL=y # CONFIG_DEBUG_SHIRQ is not set -CONFIG_DETECT_SOFTLOCKUP=y +# CONFIG_DETECT_SOFTLOCKUP is not set # CONFIG_SCHED_DEBUG is not set -# CONFIG_SCHEDSTATS is not set +CONFIG_SCHEDSTATS=y CONFIG_TIMER_STATS=y +# CONFIG_DEBUG_OBJECTS is not set # CONFIG_SLUB_DEBUG_ON is not set +# CONFIG_SLUB_STATS is not set # CONFIG_DEBUG_RT_MUTEXES is not set # CONFIG_RT_MUTEX_TESTER is not set # CONFIG_DEBUG_SPINLOCK is not set @@ -1419,48 +2032,174 @@ CONFIG_TIMER_STATS=y CONFIG_DEBUG_BUGVERBOSE=y # CONFIG_DEBUG_INFO is not set # CONFIG_DEBUG_VM is not set +# CONFIG_DEBUG_WRITECOUNT is not set # CONFIG_DEBUG_LIST is not set -# CONFIG_FRAME_POINTER is not set -CONFIG_OPTIMIZE_INLINING=y +# CONFIG_DEBUG_SG is not set +CONFIG_FRAME_POINTER=y +# CONFIG_BOOT_PRINTK_DELAY is not set # CONFIG_RCU_TORTURE_TEST is not set +# CONFIG_KPROBES_SANITY_TEST is not set +# CONFIG_BACKTRACE_SELF_TEST is not set # CONFIG_LKDTM is not set # CONFIG_FAULT_INJECTION is not set +# CONFIG_LATENCYTOP is not set +CONFIG_PROVIDE_OHCI1394_DMA_INIT=y +# CONFIG_SAMPLES is not set +# CONFIG_KGDB is not set +CONFIG_HAVE_ARCH_KGDB=y +# CONFIG_NONPROMISC_DEVMEM is not set CONFIG_EARLY_PRINTK=y CONFIG_DEBUG_STACKOVERFLOW=y -# CONFIG_DEBUG_STACK_USAGE is not set -# CONFIG_DEBUG_RODATA is not set +CONFIG_DEBUG_STACK_USAGE=y +# CONFIG_DEBUG_PAGEALLOC is not set +# CONFIG_X86_PTDUMP is not set +CONFIG_DEBUG_RODATA=y +# CONFIG_DEBUG_RODATA_TEST is not set +CONFIG_DEBUG_NX_TEST=m # CONFIG_4KSTACKS is not set CONFIG_X86_FIND_SMP_CONFIG=y CONFIG_X86_MPPARSE=y CONFIG_DOUBLEFAULT=y +CONFIG_IO_DELAY_TYPE_0X80=0 +CONFIG_IO_DELAY_TYPE_0XED=1 +CONFIG_IO_DELAY_TYPE_UDELAY=2 +CONFIG_IO_DELAY_TYPE_NONE=3 +CONFIG_IO_DELAY_0X80=y +# CONFIG_IO_DELAY_0XED is not set +# CONFIG_IO_DELAY_UDELAY is not set +# CONFIG_IO_DELAY_NONE is not set +CONFIG_DEFAULT_IO_DELAY_TYPE=0 +CONFIG_DEBUG_BOOT_PARAMS=y +# CONFIG_CPA_DEBUG is not set # # Security options # -# CONFIG_KEYS is not set -# CONFIG_SECURITY is not set -# CONFIG_CRYPTO is not set +CONFIG_KEYS=y +CONFIG_KEYS_DEBUG_PROC_KEYS=y +CONFIG_SECURITY=y +CONFIG_SECURITY_NETWORK=y +# CONFIG_SECURITY_NETWORK_XFRM is not set +CONFIG_SECURITY_CAPABILITIES=y +CONFIG_SECURITY_FILE_CAPABILITIES=y +# CONFIG_SECURITY_ROOTPLUG is not set +CONFIG_SECURITY_DEFAULT_MMAP_MIN_ADDR=65536 +CONFIG_SECURITY_SELINUX=y +CONFIG_SECURITY_SELINUX_BOOTPARAM=y +CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=1 +CONFIG_SECURITY_SELINUX_DISABLE=y +CONFIG_SECURITY_SELINUX_DEVELOP=y +CONFIG_SECURITY_SELINUX_AVC_STATS=y +CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=1 +# CONFIG_SECURITY_SELINUX_ENABLE_SECMARK_DEFAULT is not set +# CONFIG_SECURITY_SELINUX_POLICYDB_VERSION_MAX is not set +# CONFIG_SECURITY_SMACK is not set +CONFIG_CRYPTO=y + +# +# Crypto core or helper +# +CONFIG_CRYPTO_ALGAPI=y +CONFIG_CRYPTO_AEAD=y +CONFIG_CRYPTO_BLKCIPHER=y +CONFIG_CRYPTO_HASH=y +CONFIG_CRYPTO_MANAGER=y +# CONFIG_CRYPTO_GF128MUL is not set +# CONFIG_CRYPTO_NULL is not set +# CONFIG_CRYPTO_CRYPTD is not set +CONFIG_CRYPTO_AUTHENC=y +# CONFIG_CRYPTO_TEST is not set + +# +# Authenticated Encryption with Associated Data +# +# CONFIG_CRYPTO_CCM is not set +# CONFIG_CRYPTO_GCM is not set +# CONFIG_CRYPTO_SEQIV is not set + +# +# Block modes +# +CONFIG_CRYPTO_CBC=y +# CONFIG_CRYPTO_CTR is not set +# CONFIG_CRYPTO_CTS is not set +CONFIG_CRYPTO_ECB=y +# CONFIG_CRYPTO_LRW is not set +# CONFIG_CRYPTO_PCBC is not set +# CONFIG_CRYPTO_XTS is not set + +# +# Hash modes +# +CONFIG_CRYPTO_HMAC=y +# CONFIG_CRYPTO_XCBC is not set + +# +# Digest +# +# CONFIG_CRYPTO_CRC32C is not set +# CONFIG_CRYPTO_MD4 is not set +CONFIG_CRYPTO_MD5=y +# CONFIG_CRYPTO_MICHAEL_MIC is not set +CONFIG_CRYPTO_SHA1=y +# CONFIG_CRYPTO_SHA256 is not set +# CONFIG_CRYPTO_SHA512 is not set +# CONFIG_CRYPTO_TGR192 is not set +# CONFIG_CRYPTO_WP512 is not set + +# +# Ciphers +# +CONFIG_CRYPTO_AES=y +# CONFIG_CRYPTO_AES_586 is not set +# CONFIG_CRYPTO_ANUBIS is not set +CONFIG_CRYPTO_ARC4=y +# CONFIG_CRYPTO_BLOWFISH is not set +# CONFIG_CRYPTO_CAMELLIA is not set +# CONFIG_CRYPTO_CAST5 is not set +# CONFIG_CRYPTO_CAST6 is not set +CONFIG_CRYPTO_DES=y +# CONFIG_CRYPTO_FCRYPT is not set +# CONFIG_CRYPTO_KHAZAD is not set +# CONFIG_CRYPTO_SALSA20 is not set +# CONFIG_CRYPTO_SALSA20_586 is not set +# CONFIG_CRYPTO_SEED is not set +# CONFIG_CRYPTO_SERPENT is not set +# CONFIG_CRYPTO_TEA is not set +# CONFIG_CRYPTO_TWOFISH is not set +# CONFIG_CRYPTO_TWOFISH_586 is not set + +# +# Compression +# +# CONFIG_CRYPTO_DEFLATE is not set +# CONFIG_CRYPTO_LZO is not set +CONFIG_CRYPTO_HW=y +# CONFIG_CRYPTO_DEV_PADLOCK is not set +# CONFIG_CRYPTO_DEV_GEODE is not set +# CONFIG_CRYPTO_DEV_HIFN_795X is not set +CONFIG_HAVE_KVM=y +CONFIG_VIRTUALIZATION=y +# CONFIG_KVM is not set +# CONFIG_LGUEST is not set +# CONFIG_VIRTIO_PCI is not set +# CONFIG_VIRTIO_BALLOON is not set # # Library routines # CONFIG_BITREVERSE=y +CONFIG_GENERIC_FIND_FIRST_BIT=y +CONFIG_GENERIC_FIND_NEXT_BIT=y # CONFIG_CRC_CCITT is not set # CONFIG_CRC16 is not set # CONFIG_CRC_ITU_T is not set CONFIG_CRC32=y # CONFIG_CRC7 is not set # CONFIG_LIBCRC32C is not set +CONFIG_AUDIT_GENERIC=y CONFIG_ZLIB_INFLATE=y CONFIG_PLIST=y CONFIG_HAS_IOMEM=y CONFIG_HAS_IOPORT=y CONFIG_HAS_DMA=y -CONFIG_GENERIC_HARDIRQS=y -CONFIG_GENERIC_IRQ_PROBE=y -CONFIG_GENERIC_PENDING_IRQ=y -CONFIG_X86_SMP=y -CONFIG_X86_HT=y -CONFIG_X86_BIOS_REBOOT=y -CONFIG_X86_TRAMPOLINE=y -CONFIG_KTIME_SCALAR=y diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 2d6f5b2809d2..ae5124e064d4 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -1,64 +1,103 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.22-git14 -# Fri Jul 20 09:53:15 2007 +# Linux kernel version: 2.6.26-rc1 +# Sun May 4 19:59:57 2008 # -CONFIG_X86_64=y CONFIG_64BIT=y +# CONFIG_X86_32 is not set +CONFIG_X86_64=y CONFIG_X86=y +CONFIG_DEFCONFIG_LIST="arch/x86/configs/x86_64_defconfig" +# CONFIG_GENERIC_LOCKBREAK is not set CONFIG_GENERIC_TIME=y -CONFIG_GENERIC_TIME_VSYSCALL=y CONFIG_GENERIC_CMOS_UPDATE=y -CONFIG_ZONE_DMA32=y +CONFIG_CLOCKSOURCE_WATCHDOG=y +CONFIG_GENERIC_CLOCKEVENTS=y +CONFIG_GENERIC_CLOCKEVENTS_BROADCAST=y CONFIG_LOCKDEP_SUPPORT=y CONFIG_STACKTRACE_SUPPORT=y -CONFIG_SEMAPHORE_SLEEPERS=y +CONFIG_HAVE_LATENCYTOP_SUPPORT=y +CONFIG_FAST_CMPXCHG_LOCAL=y CONFIG_MMU=y CONFIG_ZONE_DMA=y -CONFIG_QUICKLIST=y -CONFIG_NR_QUICK=2 -CONFIG_RWSEM_GENERIC_SPINLOCK=y -CONFIG_GENERIC_HWEIGHT=y -CONFIG_GENERIC_CALIBRATE_DELAY=y -CONFIG_X86_CMPXCHG=y -CONFIG_EARLY_PRINTK=y CONFIG_GENERIC_ISA_DMA=y CONFIG_GENERIC_IOMAP=y -CONFIG_ARCH_MAY_HAVE_PC_FDC=y -CONFIG_ARCH_POPULATES_NODE_MAP=y -CONFIG_DMI=y -CONFIG_AUDIT_ARCH=y CONFIG_GENERIC_BUG=y +CONFIG_GENERIC_HWEIGHT=y +# CONFIG_GENERIC_GPIO is not set +CONFIG_ARCH_MAY_HAVE_PC_FDC=y +CONFIG_RWSEM_GENERIC_SPINLOCK=y +# CONFIG_RWSEM_XCHGADD_ALGORITHM is not set # CONFIG_ARCH_HAS_ILOG2_U32 is not set # CONFIG_ARCH_HAS_ILOG2_U64 is not set -CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" +CONFIG_ARCH_HAS_CPU_IDLE_WAIT=y +CONFIG_GENERIC_CALIBRATE_DELAY=y +CONFIG_GENERIC_TIME_VSYSCALL=y +CONFIG_ARCH_HAS_CPU_RELAX=y +CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y +CONFIG_HAVE_SETUP_PER_CPU_AREA=y +CONFIG_HAVE_CPUMASK_OF_CPU_MAP=y +CONFIG_ARCH_HIBERNATION_POSSIBLE=y +CONFIG_ARCH_SUSPEND_POSSIBLE=y +CONFIG_ZONE_DMA32=y +CONFIG_ARCH_POPULATES_NODE_MAP=y +CONFIG_AUDIT_ARCH=y +CONFIG_ARCH_SUPPORTS_AOUT=y +CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING=y +CONFIG_GENERIC_HARDIRQS=y +CONFIG_GENERIC_IRQ_PROBE=y +CONFIG_GENERIC_PENDING_IRQ=y +CONFIG_X86_SMP=y +CONFIG_X86_64_SMP=y +CONFIG_X86_HT=y +CONFIG_X86_BIOS_REBOOT=y +CONFIG_X86_TRAMPOLINE=y +# CONFIG_KTIME_SCALAR is not set # -# Code maturity level options +# General setup # CONFIG_EXPERIMENTAL=y CONFIG_LOCK_KERNEL=y CONFIG_INIT_ENV_ARG_LIMIT=32 - -# -# General setup -# CONFIG_LOCALVERSION="" -CONFIG_LOCALVERSION_AUTO=y +# CONFIG_LOCALVERSION_AUTO is not set CONFIG_SWAP=y CONFIG_SYSVIPC=y CONFIG_SYSVIPC_SYSCTL=y CONFIG_POSIX_MQUEUE=y -# CONFIG_BSD_PROCESS_ACCT is not set -# CONFIG_TASKSTATS is not set -# CONFIG_USER_NS is not set -# CONFIG_AUDIT is not set -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_LOG_BUF_SHIFT=18 -# CONFIG_CPUSETS is not set -CONFIG_SYSFS_DEPRECATED=y +CONFIG_BSD_PROCESS_ACCT=y +# CONFIG_BSD_PROCESS_ACCT_V3 is not set +CONFIG_TASKSTATS=y +CONFIG_TASK_DELAY_ACCT=y +CONFIG_TASK_XACCT=y +CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_AUDIT=y +CONFIG_AUDITSYSCALL=y +CONFIG_AUDIT_TREE=y +# CONFIG_IKCONFIG is not set +CONFIG_LOG_BUF_SHIFT=17 +CONFIG_CGROUPS=y +# CONFIG_CGROUP_DEBUG is not set +CONFIG_CGROUP_NS=y +# CONFIG_CGROUP_DEVICE is not set +CONFIG_CPUSETS=y +CONFIG_GROUP_SCHED=y +CONFIG_FAIR_GROUP_SCHED=y +# CONFIG_RT_GROUP_SCHED is not set +# CONFIG_USER_SCHED is not set +CONFIG_CGROUP_SCHED=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_RESOURCE_COUNTERS=y +# CONFIG_CGROUP_MEM_RES_CTLR is not set +# CONFIG_SYSFS_DEPRECATED_V2 is not set +CONFIG_PROC_PID_CPUSET=y CONFIG_RELAY=y +CONFIG_NAMESPACES=y +CONFIG_UTS_NS=y +CONFIG_IPC_NS=y +CONFIG_USER_NS=y +CONFIG_PID_NS=y CONFIG_BLK_DEV_INITRD=y CONFIG_INITRAMFS_SOURCE="" CONFIG_CC_OPTIMIZE_FOR_SIZE=y @@ -66,13 +105,15 @@ CONFIG_SYSCTL=y # CONFIG_EMBEDDED is not set CONFIG_UID16=y CONFIG_SYSCTL_SYSCALL=y +CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_KALLSYMS=y CONFIG_KALLSYMS_ALL=y -# CONFIG_KALLSYMS_EXTRA_PASS is not set +CONFIG_KALLSYMS_EXTRA_PASS=y CONFIG_HOTPLUG=y CONFIG_PRINTK=y CONFIG_BUG=y CONFIG_ELF_CORE=y +# CONFIG_COMPAT_BRK is not set CONFIG_BASE_FULL=y CONFIG_FUTEX=y CONFIG_ANON_INODES=y @@ -82,9 +123,21 @@ CONFIG_TIMERFD=y CONFIG_EVENTFD=y CONFIG_SHMEM=y CONFIG_VM_EVENT_COUNTERS=y -CONFIG_SLAB=y -# CONFIG_SLUB is not set +CONFIG_SLUB_DEBUG=y +# CONFIG_SLAB is not set +CONFIG_SLUB=y # CONFIG_SLOB is not set +CONFIG_PROFILING=y +CONFIG_MARKERS=y +# CONFIG_OPROFILE is not set +CONFIG_HAVE_OPROFILE=y +CONFIG_KPROBES=y +CONFIG_KRETPROBES=y +CONFIG_HAVE_KPROBES=y +CONFIG_HAVE_KRETPROBES=y +# CONFIG_HAVE_DMA_ATTRS is not set +CONFIG_PROC_PAGE_MONITOR=y +CONFIG_SLABINFO=y CONFIG_RT_MUTEXES=y # CONFIG_TINY_SHMEM is not set CONFIG_BASE_SMALL=0 @@ -96,14 +149,15 @@ CONFIG_MODULE_FORCE_UNLOAD=y # CONFIG_KMOD is not set CONFIG_STOP_MACHINE=y CONFIG_BLOCK=y -# CONFIG_BLK_DEV_IO_TRACE is not set -# CONFIG_BLK_DEV_BSG is not set +CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_BLK_DEV_BSG=y +CONFIG_BLOCK_COMPAT=y # # IO Schedulers # CONFIG_IOSCHED_NOOP=y -# CONFIG_IOSCHED_AS is not set +CONFIG_IOSCHED_AS=y CONFIG_IOSCHED_DEADLINE=y CONFIG_IOSCHED_CFQ=y # CONFIG_DEFAULT_AS is not set @@ -111,107 +165,177 @@ CONFIG_IOSCHED_CFQ=y CONFIG_DEFAULT_CFQ=y # CONFIG_DEFAULT_NOOP is not set CONFIG_DEFAULT_IOSCHED="cfq" +CONFIG_CLASSIC_RCU=y # # Processor type and features # +CONFIG_TICK_ONESHOT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_GENERIC_CLOCKEVENTS_BUILD=y +CONFIG_SMP=y CONFIG_X86_PC=y +# CONFIG_X86_ELAN is not set +# CONFIG_X86_VOYAGER is not set +# CONFIG_X86_NUMAQ is not set +# CONFIG_X86_SUMMIT is not set +# CONFIG_X86_BIGSMP is not set +# CONFIG_X86_VISWS is not set +# CONFIG_X86_GENERICARCH is not set +# CONFIG_X86_ES7000 is not set +# CONFIG_X86_RDC321X is not set # CONFIG_X86_VSMP is not set +# CONFIG_PARAVIRT_GUEST is not set +CONFIG_MEMTEST_BOOTPARAM=y +CONFIG_MEMTEST_BOOTPARAM_VALUE=0 +# CONFIG_M386 is not set +# CONFIG_M486 is not set +# CONFIG_M586 is not set +# CONFIG_M586TSC is not set +# CONFIG_M586MMX is not set +# CONFIG_M686 is not set +# CONFIG_MPENTIUMII is not set +# CONFIG_MPENTIUMIII is not set +# CONFIG_MPENTIUMM is not set +# CONFIG_MPENTIUM4 is not set +# CONFIG_MK6 is not set +# CONFIG_MK7 is not set # CONFIG_MK8 is not set +# CONFIG_MCRUSOE is not set +# CONFIG_MEFFICEON is not set +# CONFIG_MWINCHIPC6 is not set +# CONFIG_MWINCHIP2 is not set +# CONFIG_MWINCHIP3D is not set +# CONFIG_MGEODEGX1 is not set +# CONFIG_MGEODE_LX is not set +# CONFIG_MCYRIXIII is not set +# CONFIG_MVIAC3_2 is not set +# CONFIG_MVIAC7 is not set # CONFIG_MPSC is not set -# CONFIG_MCORE2 is not set -CONFIG_GENERIC_CPU=y -CONFIG_X86_L1_CACHE_BYTES=128 -CONFIG_X86_L1_CACHE_SHIFT=7 -CONFIG_X86_INTERNODE_CACHE_BYTES=128 -CONFIG_X86_TSC=y +CONFIG_MCORE2=y +# CONFIG_GENERIC_CPU is not set +CONFIG_X86_CPU=y +CONFIG_X86_L1_CACHE_BYTES=64 +CONFIG_X86_INTERNODE_CACHE_BYTES=64 +CONFIG_X86_CMPXCHG=y +CONFIG_X86_L1_CACHE_SHIFT=6 CONFIG_X86_GOOD_APIC=y -# CONFIG_MICROCODE is not set -CONFIG_X86_MSR=y -CONFIG_X86_CPUID=y -CONFIG_X86_HT=y -CONFIG_X86_IO_APIC=y -CONFIG_X86_LOCAL_APIC=y -CONFIG_MTRR=y -CONFIG_SMP=y -CONFIG_SCHED_SMT=y +CONFIG_X86_INTEL_USERCOPY=y +CONFIG_X86_USE_PPRO_CHECKSUM=y +CONFIG_X86_P6_NOP=y +CONFIG_X86_TSC=y +CONFIG_X86_CMOV=y +CONFIG_X86_MINIMUM_CPU_FAMILY=64 +CONFIG_X86_DEBUGCTLMSR=y +CONFIG_HPET_TIMER=y +CONFIG_HPET_EMULATE_RTC=y +CONFIG_DMI=y +CONFIG_GART_IOMMU=y +CONFIG_CALGARY_IOMMU=y +CONFIG_CALGARY_IOMMU_ENABLED_BY_DEFAULT=y +CONFIG_SWIOTLB=y +CONFIG_IOMMU_HELPER=y +CONFIG_NR_CPUS=4 +# CONFIG_SCHED_SMT is not set CONFIG_SCHED_MC=y # CONFIG_PREEMPT_NONE is not set CONFIG_PREEMPT_VOLUNTARY=y # CONFIG_PREEMPT is not set -CONFIG_PREEMPT_BKL=y +CONFIG_X86_LOCAL_APIC=y +CONFIG_X86_IO_APIC=y +# CONFIG_X86_MCE is not set +# CONFIG_I8K is not set +# CONFIG_MICROCODE is not set +CONFIG_X86_MSR=y +CONFIG_X86_CPUID=y CONFIG_NUMA=y CONFIG_K8_NUMA=y -CONFIG_NODES_SHIFT=6 CONFIG_X86_64_ACPI_NUMA=y -CONFIG_NUMA_EMU=y +CONFIG_NODES_SPAN_OTHER_NODES=y +# CONFIG_NUMA_EMU is not set +CONFIG_NODES_SHIFT=6 +CONFIG_ARCH_SPARSEMEM_DEFAULT=y +CONFIG_ARCH_SPARSEMEM_ENABLE=y +CONFIG_ARCH_SELECT_MEMORY_MODEL=y +CONFIG_SELECT_MEMORY_MODEL=y +# CONFIG_FLATMEM_MANUAL is not set +# CONFIG_DISCONTIGMEM_MANUAL is not set +CONFIG_SPARSEMEM_MANUAL=y +CONFIG_SPARSEMEM=y CONFIG_NEED_MULTIPLE_NODES=y +CONFIG_HAVE_MEMORY_PRESENT=y # CONFIG_SPARSEMEM_STATIC is not set +CONFIG_SPARSEMEM_EXTREME=y +CONFIG_SPARSEMEM_VMEMMAP_ENABLE=y +CONFIG_SPARSEMEM_VMEMMAP=y + +# +# Memory hotplug is currently incompatible with Software Suspend +# +CONFIG_PAGEFLAGS_EXTENDED=y CONFIG_SPLIT_PTLOCK_CPUS=4 CONFIG_MIGRATION=y CONFIG_RESOURCES_64BIT=y CONFIG_ZONE_DMA_FLAG=1 CONFIG_BOUNCE=y CONFIG_VIRT_TO_BUS=y -CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID=y -CONFIG_OUT_OF_LINE_PFN_TO_PAGE=y -CONFIG_NR_CPUS=32 -CONFIG_PHYSICAL_ALIGN=0x200000 -CONFIG_HOTPLUG_CPU=y -CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y -CONFIG_HPET_TIMER=y -CONFIG_HPET_EMULATE_RTC=y -CONFIG_GART_IOMMU=y -# CONFIG_CALGARY_IOMMU is not set -CONFIG_SWIOTLB=y -CONFIG_X86_MCE=y -CONFIG_X86_MCE_INTEL=y -CONFIG_X86_MCE_AMD=y -# CONFIG_KEXEC is not set -# CONFIG_CRASH_DUMP is not set -# CONFIG_RELOCATABLE is not set -CONFIG_PHYSICAL_START=0x200000 +CONFIG_MTRR=y +# CONFIG_X86_PAT is not set +CONFIG_EFI=y CONFIG_SECCOMP=y -# CONFIG_CC_STACKPROTECTOR is not set # CONFIG_HZ_100 is not set -CONFIG_HZ_250=y +# CONFIG_HZ_250 is not set # CONFIG_HZ_300 is not set -# CONFIG_HZ_1000 is not set -CONFIG_HZ=250 -CONFIG_K8_NB=y -CONFIG_GENERIC_HARDIRQS=y -CONFIG_GENERIC_IRQ_PROBE=y -CONFIG_ISA_DMA_API=y -CONFIG_GENERIC_PENDING_IRQ=y +CONFIG_HZ_1000=y +CONFIG_HZ=1000 +CONFIG_SCHED_HRTICK=y +CONFIG_KEXEC=y +CONFIG_CRASH_DUMP=y +CONFIG_PHYSICAL_START=0x1000000 +CONFIG_RELOCATABLE=y +CONFIG_PHYSICAL_ALIGN=0x200000 +CONFIG_HOTPLUG_CPU=y +# CONFIG_COMPAT_VDSO is not set +CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y +CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID=y # # Power management options # +CONFIG_ARCH_HIBERNATION_HEADER=y CONFIG_PM=y -# CONFIG_PM_LEGACY is not set -# CONFIG_PM_DEBUG is not set +CONFIG_PM_DEBUG=y +# CONFIG_PM_VERBOSE is not set +CONFIG_CAN_PM_TRACE=y +CONFIG_PM_TRACE=y +CONFIG_PM_TRACE_RTC=y +CONFIG_PM_SLEEP_SMP=y +CONFIG_PM_SLEEP=y +CONFIG_SUSPEND=y +CONFIG_SUSPEND_FREEZER=y CONFIG_HIBERNATION=y CONFIG_PM_STD_PARTITION="" - -# -# ACPI (Advanced Configuration and Power Interface) Support -# CONFIG_ACPI=y CONFIG_ACPI_SLEEP=y -CONFIG_ACPI_SLEEP_PROC_FS=y -CONFIG_ACPI_SLEEP_PROC_SLEEP=y CONFIG_ACPI_PROCFS=y +CONFIG_ACPI_PROCFS_POWER=y +CONFIG_ACPI_SYSFS_POWER=y +CONFIG_ACPI_PROC_EVENT=y CONFIG_ACPI_AC=y CONFIG_ACPI_BATTERY=y CONFIG_ACPI_BUTTON=y CONFIG_ACPI_FAN=y -# CONFIG_ACPI_DOCK is not set +CONFIG_ACPI_DOCK=y +# CONFIG_ACPI_BAY is not set CONFIG_ACPI_PROCESSOR=y CONFIG_ACPI_HOTPLUG_CPU=y CONFIG_ACPI_THERMAL=y CONFIG_ACPI_NUMA=y +# CONFIG_ACPI_WMI is not set # CONFIG_ACPI_ASUS is not set # CONFIG_ACPI_TOSHIBA is not set +# CONFIG_ACPI_CUSTOM_DSDT is not set CONFIG_ACPI_BLACKLIST_YEAR=0 # CONFIG_ACPI_DEBUG is not set CONFIG_ACPI_EC=y @@ -227,29 +351,34 @@ CONFIG_ACPI_CONTAINER=y CONFIG_CPU_FREQ=y CONFIG_CPU_FREQ_TABLE=y CONFIG_CPU_FREQ_DEBUG=y -CONFIG_CPU_FREQ_STAT=y -# CONFIG_CPU_FREQ_STAT_DETAILS is not set -CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y -# CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set +# CONFIG_CPU_FREQ_STAT is not set +# CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE is not set +# CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE is not set +CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y +# CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND is not set +# CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE is not set CONFIG_CPU_FREQ_GOV_PERFORMANCE=y # CONFIG_CPU_FREQ_GOV_POWERSAVE is not set CONFIG_CPU_FREQ_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_ONDEMAND=y -CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y +# CONFIG_CPU_FREQ_GOV_CONSERVATIVE is not set # # CPUFreq processor drivers # -CONFIG_X86_POWERNOW_K8=y -CONFIG_X86_POWERNOW_K8_ACPI=y -# CONFIG_X86_SPEEDSTEP_CENTRINO is not set CONFIG_X86_ACPI_CPUFREQ=y +# CONFIG_X86_POWERNOW_K8 is not set +# CONFIG_X86_SPEEDSTEP_CENTRINO is not set +# CONFIG_X86_P4_CLOCKMOD is not set # # shared options # -CONFIG_X86_ACPI_CPUFREQ_PROC_INTF=y +# CONFIG_X86_ACPI_CPUFREQ_PROC_INTF is not set # CONFIG_X86_SPEEDSTEP_LIB is not set +CONFIG_CPU_IDLE=y +CONFIG_CPU_IDLE_GOV_LADDER=y +CONFIG_CPU_IDLE_GOV_MENU=y # # Bus options (PCI etc.) @@ -257,27 +386,56 @@ CONFIG_X86_ACPI_CPUFREQ_PROC_INTF=y CONFIG_PCI=y CONFIG_PCI_DIRECT=y CONFIG_PCI_MMCONFIG=y +CONFIG_PCI_DOMAINS=y +CONFIG_DMAR=y +CONFIG_DMAR_GFX_WA=y +CONFIG_DMAR_FLOPPY_WA=y CONFIG_PCIEPORTBUS=y +# CONFIG_HOTPLUG_PCI_PCIE is not set CONFIG_PCIEAER=y +# CONFIG_PCIEASPM is not set CONFIG_ARCH_SUPPORTS_MSI=y CONFIG_PCI_MSI=y +# CONFIG_PCI_LEGACY is not set # CONFIG_PCI_DEBUG is not set -# CONFIG_HT_IRQ is not set - -# -# PCCARD (PCMCIA/CardBus) support -# -# CONFIG_PCCARD is not set -# CONFIG_HOTPLUG_PCI is not set +CONFIG_HT_IRQ=y +CONFIG_ISA_DMA_API=y +CONFIG_K8_NB=y +CONFIG_PCCARD=y +# CONFIG_PCMCIA_DEBUG is not set +CONFIG_PCMCIA=y +CONFIG_PCMCIA_LOAD_CIS=y +CONFIG_PCMCIA_IOCTL=y +CONFIG_CARDBUS=y + +# +# PC-card bridges +# +CONFIG_YENTA=y +CONFIG_YENTA_O2=y +CONFIG_YENTA_RICOH=y +CONFIG_YENTA_TI=y +CONFIG_YENTA_ENE_TUNE=y +CONFIG_YENTA_TOSHIBA=y +# CONFIG_PD6729 is not set +# CONFIG_I82092 is not set +CONFIG_PCCARD_NONSTATIC=y +CONFIG_HOTPLUG_PCI=y +# CONFIG_HOTPLUG_PCI_FAKE is not set +# CONFIG_HOTPLUG_PCI_ACPI is not set +# CONFIG_HOTPLUG_PCI_CPCI is not set +# CONFIG_HOTPLUG_PCI_SHPC is not set # # Executable file formats / Emulations # CONFIG_BINFMT_ELF=y -# CONFIG_BINFMT_MISC is not set +CONFIG_COMPAT_BINFMT_ELF=y +CONFIG_BINFMT_MISC=y CONFIG_IA32_EMULATION=y -CONFIG_IA32_AOUT=y +# CONFIG_IA32_AOUT is not set CONFIG_COMPAT=y +CONFIG_COMPAT_FOR_U64_ALIGNMENT=y CONFIG_SYSVIPC_COMPAT=y # @@ -289,22 +447,31 @@ CONFIG_NET=y # Networking options # CONFIG_PACKET=y -# CONFIG_PACKET_MMAP is not set +CONFIG_PACKET_MMAP=y CONFIG_UNIX=y +CONFIG_XFRM=y +CONFIG_XFRM_USER=y +# CONFIG_XFRM_SUB_POLICY is not set +# CONFIG_XFRM_MIGRATE is not set +# CONFIG_XFRM_STATISTICS is not set # CONFIG_NET_KEY is not set CONFIG_INET=y CONFIG_IP_MULTICAST=y -# CONFIG_IP_ADVANCED_ROUTER is not set +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_ASK_IP_FIB_HASH=y +# CONFIG_IP_FIB_TRIE is not set CONFIG_IP_FIB_HASH=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -# CONFIG_IP_PNP_BOOTP is not set -# CONFIG_IP_PNP_RARP is not set +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_ROUTE_MULTIPATH=y +CONFIG_IP_ROUTE_VERBOSE=y +# CONFIG_IP_PNP is not set # CONFIG_NET_IPIP is not set # CONFIG_NET_IPGRE is not set -# CONFIG_IP_MROUTE is not set +CONFIG_IP_MROUTE=y +CONFIG_IP_PIMSM_V1=y +CONFIG_IP_PIMSM_V2=y # CONFIG_ARPD is not set -# CONFIG_SYN_COOKIES is not set +CONFIG_SYN_COOKIES=y # CONFIG_INET_AH is not set # CONFIG_INET_ESP is not set # CONFIG_INET_IPCOMP is not set @@ -313,31 +480,109 @@ CONFIG_INET_TUNNEL=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -CONFIG_INET_DIAG=y -CONFIG_INET_TCP_DIAG=y -# CONFIG_TCP_CONG_ADVANCED is not set +CONFIG_INET_LRO=y +# CONFIG_INET_DIAG is not set +CONFIG_TCP_CONG_ADVANCED=y +# CONFIG_TCP_CONG_BIC is not set CONFIG_TCP_CONG_CUBIC=y +# CONFIG_TCP_CONG_WESTWOOD is not set +# CONFIG_TCP_CONG_HTCP is not set +# CONFIG_TCP_CONG_HSTCP is not set +# CONFIG_TCP_CONG_HYBLA is not set +# CONFIG_TCP_CONG_VEGAS is not set +# CONFIG_TCP_CONG_SCALABLE is not set +# CONFIG_TCP_CONG_LP is not set +# CONFIG_TCP_CONG_VENO is not set +# CONFIG_TCP_CONG_YEAH is not set +# CONFIG_TCP_CONG_ILLINOIS is not set +# CONFIG_DEFAULT_BIC is not set +CONFIG_DEFAULT_CUBIC=y +# CONFIG_DEFAULT_HTCP is not set +# CONFIG_DEFAULT_VEGAS is not set +# CONFIG_DEFAULT_WESTWOOD is not set +# CONFIG_DEFAULT_RENO is not set CONFIG_DEFAULT_TCP_CONG="cubic" -# CONFIG_TCP_MD5SIG is not set +CONFIG_TCP_MD5SIG=y +# CONFIG_IP_VS is not set CONFIG_IPV6=y # CONFIG_IPV6_PRIVACY is not set # CONFIG_IPV6_ROUTER_PREF is not set # CONFIG_IPV6_OPTIMISTIC_DAD is not set -# CONFIG_INET6_AH is not set -# CONFIG_INET6_ESP is not set +CONFIG_INET6_AH=y +CONFIG_INET6_ESP=y # CONFIG_INET6_IPCOMP is not set # CONFIG_IPV6_MIP6 is not set # CONFIG_INET6_XFRM_TUNNEL is not set # CONFIG_INET6_TUNNEL is not set -# CONFIG_INET6_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET6_XFRM_MODE_TUNNEL is not set -# CONFIG_INET6_XFRM_MODE_BEET is not set +CONFIG_INET6_XFRM_MODE_TRANSPORT=y +CONFIG_INET6_XFRM_MODE_TUNNEL=y +CONFIG_INET6_XFRM_MODE_BEET=y # CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION is not set CONFIG_IPV6_SIT=y +CONFIG_IPV6_NDISC_NODETYPE=y # CONFIG_IPV6_TUNNEL is not set # CONFIG_IPV6_MULTIPLE_TABLES is not set -# CONFIG_NETWORK_SECMARK is not set -# CONFIG_NETFILTER is not set +# CONFIG_IPV6_MROUTE is not set +CONFIG_NETLABEL=y +CONFIG_NETWORK_SECMARK=y +CONFIG_NETFILTER=y +# CONFIG_NETFILTER_DEBUG is not set +# CONFIG_NETFILTER_ADVANCED is not set + +# +# Core Netfilter Configuration +# +CONFIG_NETFILTER_NETLINK=y +CONFIG_NETFILTER_NETLINK_LOG=y +CONFIG_NF_CONNTRACK=y +CONFIG_NF_CONNTRACK_SECMARK=y +CONFIG_NF_CONNTRACK_FTP=y +CONFIG_NF_CONNTRACK_IRC=y +CONFIG_NF_CONNTRACK_SIP=y +CONFIG_NF_CT_NETLINK=y +CONFIG_NETFILTER_XTABLES=y +CONFIG_NETFILTER_XT_TARGET_MARK=y +CONFIG_NETFILTER_XT_TARGET_NFLOG=y +CONFIG_NETFILTER_XT_TARGET_SECMARK=y +CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y +CONFIG_NETFILTER_XT_TARGET_TCPMSS=y +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y +CONFIG_NETFILTER_XT_MATCH_MARK=y +CONFIG_NETFILTER_XT_MATCH_POLICY=y +CONFIG_NETFILTER_XT_MATCH_STATE=y + +# +# IP: Netfilter Configuration +# +CONFIG_NF_CONNTRACK_IPV4=y +CONFIG_NF_CONNTRACK_PROC_COMPAT=y +CONFIG_IP_NF_IPTABLES=y +CONFIG_IP_NF_FILTER=y +CONFIG_IP_NF_TARGET_REJECT=y +CONFIG_IP_NF_TARGET_LOG=y +CONFIG_IP_NF_TARGET_ULOG=y +CONFIG_NF_NAT=y +CONFIG_NF_NAT_NEEDED=y +CONFIG_IP_NF_TARGET_MASQUERADE=y +CONFIG_NF_NAT_FTP=y +CONFIG_NF_NAT_IRC=y +# CONFIG_NF_NAT_TFTP is not set +# CONFIG_NF_NAT_AMANDA is not set +# CONFIG_NF_NAT_PPTP is not set +# CONFIG_NF_NAT_H323 is not set +CONFIG_NF_NAT_SIP=y +CONFIG_IP_NF_MANGLE=y + +# +# IPv6: Netfilter Configuration +# +CONFIG_NF_CONNTRACK_IPV6=y +CONFIG_IP6_NF_IPTABLES=y +CONFIG_IP6_NF_MATCH_IPV6HEADER=y +CONFIG_IP6_NF_FILTER=y +CONFIG_IP6_NF_TARGET_LOG=y +CONFIG_IP6_NF_TARGET_REJECT=y +CONFIG_IP6_NF_MANGLE=y # CONFIG_IP_DCCP is not set # CONFIG_IP_SCTP is not set # CONFIG_TIPC is not set @@ -345,6 +590,7 @@ CONFIG_IPV6_SIT=y # CONFIG_BRIDGE is not set # CONFIG_VLAN_8021Q is not set # CONFIG_DECNET is not set +CONFIG_LLC=y # CONFIG_LLC2 is not set # CONFIG_IPX is not set # CONFIG_ATALK is not set @@ -352,28 +598,99 @@ CONFIG_IPV6_SIT=y # CONFIG_LAPB is not set # CONFIG_ECONET is not set # CONFIG_WAN_ROUTER is not set - -# -# QoS and/or fair queueing -# -# CONFIG_NET_SCHED is not set +CONFIG_NET_SCHED=y + +# +# Queueing/Scheduling +# +# CONFIG_NET_SCH_CBQ is not set +# CONFIG_NET_SCH_HTB is not set +# CONFIG_NET_SCH_HFSC is not set +# CONFIG_NET_SCH_PRIO is not set +# CONFIG_NET_SCH_RR is not set +# CONFIG_NET_SCH_RED is not set +# CONFIG_NET_SCH_SFQ is not set +# CONFIG_NET_SCH_TEQL is not set +# CONFIG_NET_SCH_TBF is not set +# CONFIG_NET_SCH_GRED is not set +# CONFIG_NET_SCH_DSMARK is not set +# CONFIG_NET_SCH_NETEM is not set +# CONFIG_NET_SCH_INGRESS is not set + +# +# Classification +# +CONFIG_NET_CLS=y +# CONFIG_NET_CLS_BASIC is not set +# CONFIG_NET_CLS_TCINDEX is not set +# CONFIG_NET_CLS_ROUTE4 is not set +# CONFIG_NET_CLS_FW is not set +# CONFIG_NET_CLS_U32 is not set +# CONFIG_NET_CLS_RSVP is not set +# CONFIG_NET_CLS_RSVP6 is not set +# CONFIG_NET_CLS_FLOW is not set +CONFIG_NET_EMATCH=y +CONFIG_NET_EMATCH_STACK=32 +# CONFIG_NET_EMATCH_CMP is not set +# CONFIG_NET_EMATCH_NBYTE is not set +# CONFIG_NET_EMATCH_U32 is not set +# CONFIG_NET_EMATCH_META is not set +# CONFIG_NET_EMATCH_TEXT is not set +CONFIG_NET_CLS_ACT=y +# CONFIG_NET_ACT_POLICE is not set +# CONFIG_NET_ACT_GACT is not set +# CONFIG_NET_ACT_MIRRED is not set +# CONFIG_NET_ACT_IPT is not set +# CONFIG_NET_ACT_NAT is not set +# CONFIG_NET_ACT_PEDIT is not set +# CONFIG_NET_ACT_SIMP is not set +CONFIG_NET_SCH_FIFO=y # # Network testing # # CONFIG_NET_PKTGEN is not set # CONFIG_NET_TCPPROBE is not set -# CONFIG_HAMRADIO is not set +CONFIG_HAMRADIO=y + +# +# Packet Radio protocols +# +# CONFIG_AX25 is not set +# CONFIG_CAN is not set # CONFIG_IRDA is not set # CONFIG_BT is not set # CONFIG_AF_RXRPC is not set +CONFIG_FIB_RULES=y # # Wireless # -# CONFIG_CFG80211 is not set -# CONFIG_WIRELESS_EXT is not set -# CONFIG_MAC80211 is not set +CONFIG_CFG80211=y +CONFIG_NL80211=y +CONFIG_WIRELESS_EXT=y +CONFIG_MAC80211=y + +# +# Rate control algorithm selection +# +CONFIG_MAC80211_RC_DEFAULT_PID=y +# CONFIG_MAC80211_RC_DEFAULT_NONE is not set + +# +# Selecting 'y' for an algorithm will +# + +# +# build the algorithm into mac80211. +# +CONFIG_MAC80211_RC_DEFAULT="pid" +CONFIG_MAC80211_RC_PID=y +# CONFIG_MAC80211_MESH is not set +CONFIG_MAC80211_LEDS=y +# CONFIG_MAC80211_DEBUGFS is not set +# CONFIG_MAC80211_DEBUG_PACKET_ALIGNMENT is not set +# CONFIG_MAC80211_DEBUG is not set # CONFIG_IEEE80211 is not set # CONFIG_RFKILL is not set # CONFIG_NET_9P is not set @@ -385,13 +702,15 @@ CONFIG_IPV6_SIT=y # # Generic Driver Options # +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_STANDALONE=y CONFIG_PREVENT_FIRMWARE_BUILD=y CONFIG_FW_LOADER=y # CONFIG_DEBUG_DRIVER is not set -# CONFIG_DEBUG_DEVRES is not set +CONFIG_DEBUG_DEVRES=y # CONFIG_SYS_HYPERVISOR is not set -# CONFIG_CONNECTOR is not set +CONFIG_CONNECTOR=y +CONFIG_PROC_EVENTS=y # CONFIG_MTD is not set # CONFIG_PARPORT is not set CONFIG_PNP=y @@ -402,7 +721,7 @@ CONFIG_PNP=y # CONFIG_PNPACPI=y CONFIG_BLK_DEV=y -CONFIG_BLK_DEV_FD=y +# CONFIG_BLK_DEV_FD is not set # CONFIG_BLK_CPQ_DA is not set # CONFIG_BLK_CPQ_CISS_DA is not set # CONFIG_BLK_DEV_DAC960 is not set @@ -415,8 +734,8 @@ CONFIG_BLK_DEV_LOOP=y # CONFIG_BLK_DEV_UB is not set CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_COUNT=16 -CONFIG_BLK_DEV_RAM_SIZE=4096 -CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024 +CONFIG_BLK_DEV_RAM_SIZE=16384 +# CONFIG_BLK_DEV_XIP is not set # CONFIG_CDROM_PKTCDVD is not set # CONFIG_ATA_OVER_ETH is not set CONFIG_MISC_DEVICES=y @@ -425,72 +744,16 @@ CONFIG_MISC_DEVICES=y # CONFIG_EEPROM_93CX6 is not set # CONFIG_SGI_IOC4 is not set # CONFIG_TIFM_CORE is not set +# CONFIG_ACER_WMI is not set +# CONFIG_ASUS_LAPTOP is not set +# CONFIG_FUJITSU_LAPTOP is not set +# CONFIG_MSI_LAPTOP is not set # CONFIG_SONY_LAPTOP is not set # CONFIG_THINKPAD_ACPI is not set -CONFIG_IDE=y -CONFIG_BLK_DEV_IDE=y - -# -# Please see Documentation/ide.txt for help/info on IDE drives -# -# CONFIG_BLK_DEV_IDE_SATA is not set -# CONFIG_BLK_DEV_HD_IDE is not set -CONFIG_BLK_DEV_IDEDISK=y -CONFIG_IDEDISK_MULTI_MODE=y -CONFIG_BLK_DEV_IDECD=y -# CONFIG_BLK_DEV_IDETAPE is not set -# CONFIG_BLK_DEV_IDEFLOPPY is not set -# CONFIG_BLK_DEV_IDESCSI is not set -CONFIG_BLK_DEV_IDEACPI=y -# CONFIG_IDE_TASK_IOCTL is not set -CONFIG_IDE_PROC_FS=y - -# -# IDE chipset support/bugfixes -# -CONFIG_IDE_GENERIC=y -# CONFIG_BLK_DEV_CMD640 is not set -# CONFIG_BLK_DEV_IDEPNP is not set -CONFIG_BLK_DEV_IDEPCI=y -# CONFIG_IDEPCI_SHARE_IRQ is not set -CONFIG_IDEPCI_PCIBUS_ORDER=y -# CONFIG_BLK_DEV_OFFBOARD is not set -# CONFIG_BLK_DEV_GENERIC is not set -# CONFIG_BLK_DEV_OPTI621 is not set -# CONFIG_BLK_DEV_RZ1000 is not set -CONFIG_BLK_DEV_IDEDMA_PCI=y -# CONFIG_BLK_DEV_IDEDMA_FORCED is not set -# CONFIG_IDEDMA_ONLYDISK is not set -# CONFIG_BLK_DEV_AEC62XX is not set -# CONFIG_BLK_DEV_ALI15X3 is not set -CONFIG_BLK_DEV_AMD74XX=y -CONFIG_BLK_DEV_ATIIXP=y -# CONFIG_BLK_DEV_CMD64X is not set -# CONFIG_BLK_DEV_TRIFLEX is not set -# CONFIG_BLK_DEV_CY82C693 is not set -# CONFIG_BLK_DEV_CS5520 is not set -# CONFIG_BLK_DEV_CS5530 is not set -# CONFIG_BLK_DEV_HPT34X is not set -# CONFIG_BLK_DEV_HPT366 is not set -# CONFIG_BLK_DEV_JMICRON is not set -# CONFIG_BLK_DEV_SC1200 is not set -CONFIG_BLK_DEV_PIIX=y -# CONFIG_BLK_DEV_IT8213 is not set -# CONFIG_BLK_DEV_IT821X is not set -# CONFIG_BLK_DEV_NS87415 is not set -# CONFIG_BLK_DEV_PDC202XX_OLD is not set -CONFIG_BLK_DEV_PDC202XX_NEW=y -# CONFIG_BLK_DEV_SVWKS is not set -# CONFIG_BLK_DEV_SIIMAGE is not set -# CONFIG_BLK_DEV_SIS5513 is not set -# CONFIG_BLK_DEV_SLC90E66 is not set -# CONFIG_BLK_DEV_TRM290 is not set -# CONFIG_BLK_DEV_VIA82CXXX is not set -# CONFIG_BLK_DEV_TC86C001 is not set -# CONFIG_IDE_ARM is not set -CONFIG_BLK_DEV_IDEDMA=y -# CONFIG_IDEDMA_IVB is not set -# CONFIG_BLK_DEV_HD is not set +# CONFIG_INTEL_MENLOW is not set +# CONFIG_ENCLOSURE_SERVICES is not set +CONFIG_HAVE_IDE=y +# CONFIG_IDE is not set # # SCSI device support @@ -499,8 +762,8 @@ CONFIG_BLK_DEV_IDEDMA=y CONFIG_SCSI=y CONFIG_SCSI_DMA=y # CONFIG_SCSI_TGT is not set -CONFIG_SCSI_NETLINK=y -# CONFIG_SCSI_PROC_FS is not set +# CONFIG_SCSI_NETLINK is not set +CONFIG_SCSI_PROC_FS=y # # SCSI support type (disk, tape, CD-ROM) @@ -509,7 +772,7 @@ CONFIG_BLK_DEV_SD=y # CONFIG_CHR_DEV_ST is not set # CONFIG_CHR_DEV_OSST is not set CONFIG_BLK_DEV_SR=y -# CONFIG_BLK_DEV_SR_VENDOR is not set +CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y # CONFIG_CHR_DEV_SCH is not set @@ -526,73 +789,37 @@ CONFIG_SCSI_WAIT_SCAN=m # SCSI Transports # CONFIG_SCSI_SPI_ATTRS=y -CONFIG_SCSI_FC_ATTRS=y +# CONFIG_SCSI_FC_ATTRS is not set # CONFIG_SCSI_ISCSI_ATTRS is not set -CONFIG_SCSI_SAS_ATTRS=y +# CONFIG_SCSI_SAS_ATTRS is not set # CONFIG_SCSI_SAS_LIBSAS is not set - -# -# SCSI low-level drivers -# -# CONFIG_ISCSI_TCP is not set -# CONFIG_BLK_DEV_3W_XXXX_RAID is not set -# CONFIG_SCSI_3W_9XXX is not set -# CONFIG_SCSI_ACARD is not set -# CONFIG_SCSI_AACRAID is not set -# CONFIG_SCSI_AIC7XXX is not set -# CONFIG_SCSI_AIC7XXX_OLD is not set -CONFIG_SCSI_AIC79XX=y -CONFIG_AIC79XX_CMDS_PER_DEVICE=32 -CONFIG_AIC79XX_RESET_DELAY_MS=4000 -# CONFIG_AIC79XX_DEBUG_ENABLE is not set -CONFIG_AIC79XX_DEBUG_MASK=0 -# CONFIG_AIC79XX_REG_PRETTY_PRINT is not set -# CONFIG_SCSI_AIC94XX is not set -# CONFIG_SCSI_ARCMSR is not set -# CONFIG_MEGARAID_NEWGEN is not set -# CONFIG_MEGARAID_LEGACY is not set -# CONFIG_MEGARAID_SAS is not set -# CONFIG_SCSI_HPTIOP is not set -# CONFIG_SCSI_BUSLOGIC is not set -# CONFIG_SCSI_DMX3191D is not set -# CONFIG_SCSI_EATA is not set -# CONFIG_SCSI_FUTURE_DOMAIN is not set -# CONFIG_SCSI_GDTH is not set -# CONFIG_SCSI_IPS is not set -# CONFIG_SCSI_INITIO is not set -# CONFIG_SCSI_INIA100 is not set -# CONFIG_SCSI_STEX is not set -# CONFIG_SCSI_SYM53C8XX_2 is not set -# CONFIG_SCSI_IPR is not set -# CONFIG_SCSI_QLOGIC_1280 is not set -# CONFIG_SCSI_QLA_FC is not set -# CONFIG_SCSI_QLA_ISCSI is not set -# CONFIG_SCSI_LPFC is not set -# CONFIG_SCSI_DC395x is not set -# CONFIG_SCSI_DC390T is not set -# CONFIG_SCSI_DEBUG is not set -# CONFIG_SCSI_SRP is not set +# CONFIG_SCSI_SRP_ATTRS is not set +# CONFIG_SCSI_LOWLEVEL is not set +# CONFIG_SCSI_LOWLEVEL_PCMCIA is not set CONFIG_ATA=y # CONFIG_ATA_NONSTANDARD is not set CONFIG_ATA_ACPI=y +CONFIG_SATA_PMP=y CONFIG_SATA_AHCI=y -CONFIG_SATA_SVW=y +# CONFIG_SATA_SIL24 is not set +CONFIG_ATA_SFF=y +# CONFIG_SATA_SVW is not set CONFIG_ATA_PIIX=y # CONFIG_SATA_MV is not set -CONFIG_SATA_NV=y +# CONFIG_SATA_NV is not set # CONFIG_PDC_ADMA is not set # CONFIG_SATA_QSTOR is not set # CONFIG_SATA_PROMISE is not set # CONFIG_SATA_SX4 is not set -CONFIG_SATA_SIL=y -# CONFIG_SATA_SIL24 is not set +# CONFIG_SATA_SIL is not set # CONFIG_SATA_SIS is not set # CONFIG_SATA_ULI is not set -CONFIG_SATA_VIA=y +# CONFIG_SATA_VIA is not set # CONFIG_SATA_VITESSE is not set # CONFIG_SATA_INIC162X is not set +# CONFIG_PATA_ACPI is not set # CONFIG_PATA_ALI is not set -# CONFIG_PATA_AMD is not set +CONFIG_PATA_AMD=y # CONFIG_PATA_ARTOP is not set # CONFIG_PATA_ATIIXP is not set # CONFIG_PATA_CMD640_PCI is not set @@ -612,11 +839,14 @@ CONFIG_SATA_VIA=y # CONFIG_PATA_TRIFLEX is not set # CONFIG_PATA_MARVELL is not set # CONFIG_PATA_MPIIX is not set -# CONFIG_PATA_OLDPIIX is not set +CONFIG_PATA_OLDPIIX=y # CONFIG_PATA_NETCELL is not set +# CONFIG_PATA_NINJA32 is not set # CONFIG_PATA_NS87410 is not set +# CONFIG_PATA_NS87415 is not set # CONFIG_PATA_OPTI is not set # CONFIG_PATA_OPTIDMA is not set +# CONFIG_PATA_PCMCIA is not set # CONFIG_PATA_PDC_OLD is not set # CONFIG_PATA_RADISYS is not set # CONFIG_PATA_RZ1000 is not set @@ -628,65 +858,42 @@ CONFIG_SATA_VIA=y # CONFIG_PATA_VIA is not set # CONFIG_PATA_WINBOND is not set CONFIG_MD=y -# CONFIG_BLK_DEV_MD is not set +CONFIG_BLK_DEV_MD=y +# CONFIG_MD_LINEAR is not set +# CONFIG_MD_RAID0 is not set +# CONFIG_MD_RAID1 is not set +# CONFIG_MD_RAID10 is not set +# CONFIG_MD_RAID456 is not set +# CONFIG_MD_MULTIPATH is not set +# CONFIG_MD_FAULTY is not set CONFIG_BLK_DEV_DM=y # CONFIG_DM_DEBUG is not set # CONFIG_DM_CRYPT is not set # CONFIG_DM_SNAPSHOT is not set -# CONFIG_DM_MIRROR is not set -# CONFIG_DM_ZERO is not set +CONFIG_DM_MIRROR=y +CONFIG_DM_ZERO=y # CONFIG_DM_MULTIPATH is not set # CONFIG_DM_DELAY is not set - -# -# Fusion MPT device support -# -CONFIG_FUSION=y -CONFIG_FUSION_SPI=y -# CONFIG_FUSION_FC is not set -# CONFIG_FUSION_SAS is not set -CONFIG_FUSION_MAX_SGE=128 -# CONFIG_FUSION_CTL is not set +# CONFIG_DM_UEVENT is not set +# CONFIG_FUSION is not set # # IEEE 1394 (FireWire) support # # CONFIG_FIREWIRE is not set -CONFIG_IEEE1394=y - -# -# Subsystem Options -# -# CONFIG_IEEE1394_VERBOSEDEBUG is not set - -# -# Controllers -# - -# -# Texas Instruments PCILynx requires I2C -# -CONFIG_IEEE1394_OHCI1394=y - -# -# Protocols -# -# CONFIG_IEEE1394_VIDEO1394 is not set -# CONFIG_IEEE1394_SBP2 is not set -# CONFIG_IEEE1394_ETH1394_ROM_ENTRY is not set -# CONFIG_IEEE1394_ETH1394 is not set -# CONFIG_IEEE1394_DV1394 is not set -CONFIG_IEEE1394_RAWIO=y +# CONFIG_IEEE1394 is not set # CONFIG_I2O is not set CONFIG_MACINTOSH_DRIVERS=y -# CONFIG_MAC_EMUMOUSEBTN is not set +CONFIG_MAC_EMUMOUSEBTN=y CONFIG_NETDEVICES=y -CONFIG_NETDEVICES_MULTIQUEUE=y +# CONFIG_NETDEVICES_MULTIQUEUE is not set +# CONFIG_IFB is not set # CONFIG_DUMMY is not set # CONFIG_BONDING is not set # CONFIG_MACVLAN is not set # CONFIG_EQUALIZER is not set -CONFIG_TUN=y +# CONFIG_TUN is not set +# CONFIG_VETH is not set # CONFIG_NET_SB1000 is not set # CONFIG_ARCNET is not set # CONFIG_PHYLIB is not set @@ -696,39 +903,40 @@ CONFIG_MII=y # CONFIG_SUNGEM is not set # CONFIG_CASSINI is not set CONFIG_NET_VENDOR_3COM=y -CONFIG_VORTEX=y +# CONFIG_VORTEX is not set # CONFIG_TYPHOON is not set CONFIG_NET_TULIP=y # CONFIG_DE2104X is not set -CONFIG_TULIP=y -# CONFIG_TULIP_MWI is not set -# CONFIG_TULIP_MMIO is not set -# CONFIG_TULIP_NAPI is not set +# CONFIG_TULIP is not set # CONFIG_DE4X5 is not set # CONFIG_WINBOND_840 is not set # CONFIG_DM9102 is not set # CONFIG_ULI526X is not set +# CONFIG_PCMCIA_XIRCOM is not set # CONFIG_HP100 is not set +# CONFIG_IBM_NEW_EMAC_ZMII is not set +# CONFIG_IBM_NEW_EMAC_RGMII is not set +# CONFIG_IBM_NEW_EMAC_TAH is not set +# CONFIG_IBM_NEW_EMAC_EMAC4 is not set CONFIG_NET_PCI=y # CONFIG_PCNET32 is not set -CONFIG_AMD8111_ETH=y -# CONFIG_AMD8111E_NAPI is not set +# CONFIG_AMD8111_ETH is not set # CONFIG_ADAPTEC_STARFIRE is not set -CONFIG_B44=y +# CONFIG_B44 is not set CONFIG_FORCEDETH=y # CONFIG_FORCEDETH_NAPI is not set -# CONFIG_DGRS is not set # CONFIG_EEPRO100 is not set CONFIG_E100=y # CONFIG_FEALNX is not set # CONFIG_NATSEMI is not set # CONFIG_NE2K_PCI is not set -CONFIG_8139CP=y +# CONFIG_8139CP is not set CONFIG_8139TOO=y -# CONFIG_8139TOO_PIO is not set +CONFIG_8139TOO_PIO=y # CONFIG_8139TOO_TUNE_TWISTER is not set # CONFIG_8139TOO_8129 is not set # CONFIG_8139_OLD_RX_RESET is not set +# CONFIG_R6040 is not set # CONFIG_SIS900 is not set # CONFIG_EPIC100 is not set # CONFIG_SUNDANCE is not set @@ -740,34 +948,74 @@ CONFIG_NETDEV_1000=y CONFIG_E1000=y # CONFIG_E1000_NAPI is not set # CONFIG_E1000_DISABLE_PACKET_SPLIT is not set +# CONFIG_E1000E is not set +# CONFIG_E1000E_ENABLED is not set +# CONFIG_IP1000 is not set +# CONFIG_IGB is not set # CONFIG_NS83820 is not set # CONFIG_HAMACHI is not set # CONFIG_YELLOWFIN is not set # CONFIG_R8169 is not set # CONFIG_SIS190 is not set # CONFIG_SKGE is not set -# CONFIG_SKY2 is not set +CONFIG_SKY2=y +# CONFIG_SKY2_DEBUG is not set # CONFIG_VIA_VELOCITY is not set CONFIG_TIGON3=y -CONFIG_BNX2=y +# CONFIG_BNX2 is not set # CONFIG_QLA3XXX is not set # CONFIG_ATL1 is not set CONFIG_NETDEV_10000=y # CONFIG_CHELSIO_T1 is not set # CONFIG_CHELSIO_T3 is not set +# CONFIG_IXGBE is not set # CONFIG_IXGB is not set -CONFIG_S2IO=m -# CONFIG_S2IO_NAPI is not set +# CONFIG_S2IO is not set # CONFIG_MYRI10GE is not set # CONFIG_NETXEN_NIC is not set +# CONFIG_NIU is not set # CONFIG_MLX4_CORE is not set -# CONFIG_TR is not set +# CONFIG_TEHUTI is not set +# CONFIG_BNX2X is not set +# CONFIG_SFC is not set +CONFIG_TR=y +# CONFIG_IBMOL is not set +# CONFIG_3C359 is not set +# CONFIG_TMS380TR is not set # # Wireless LAN # # CONFIG_WLAN_PRE80211 is not set -# CONFIG_WLAN_80211 is not set +CONFIG_WLAN_80211=y +# CONFIG_PCMCIA_RAYCS is not set +# CONFIG_IPW2100 is not set +# CONFIG_IPW2200 is not set +# CONFIG_LIBERTAS is not set +# CONFIG_AIRO is not set +# CONFIG_HERMES is not set +# CONFIG_ATMEL is not set +# CONFIG_AIRO_CS is not set +# CONFIG_PCMCIA_WL3501 is not set +# CONFIG_PRISM54 is not set +# CONFIG_USB_ZD1201 is not set +# CONFIG_USB_NET_RNDIS_WLAN is not set +# CONFIG_RTL8180 is not set +# CONFIG_RTL8187 is not set +# CONFIG_ADM8211 is not set +# CONFIG_P54_COMMON is not set +CONFIG_ATH5K=y +# CONFIG_ATH5K_DEBUG is not set +# CONFIG_IWLWIFI is not set +# CONFIG_IWLCORE is not set +# CONFIG_IWLWIFI_LEDS is not set +# CONFIG_IWL4965 is not set +# CONFIG_IWL3945 is not set +# CONFIG_HOSTAP is not set +# CONFIG_B43 is not set +# CONFIG_B43LEGACY is not set +# CONFIG_ZD1211RW is not set +# CONFIG_RT2X00 is not set # # USB Network Adapters @@ -776,16 +1024,26 @@ CONFIG_S2IO=m # CONFIG_USB_KAWETH is not set # CONFIG_USB_PEGASUS is not set # CONFIG_USB_RTL8150 is not set -# CONFIG_USB_USBNET_MII is not set # CONFIG_USB_USBNET is not set +CONFIG_NET_PCMCIA=y +# CONFIG_PCMCIA_3C589 is not set +# CONFIG_PCMCIA_3C574 is not set +# CONFIG_PCMCIA_FMVJ18X is not set +# CONFIG_PCMCIA_PCNET is not set +# CONFIG_PCMCIA_NMCLAN is not set +# CONFIG_PCMCIA_SMC91C92 is not set +# CONFIG_PCMCIA_XIRC2PS is not set +# CONFIG_PCMCIA_AXNET is not set # CONFIG_WAN is not set -# CONFIG_FDDI is not set +CONFIG_FDDI=y +# CONFIG_DEFXX is not set +# CONFIG_SKFP is not set # CONFIG_HIPPI is not set # CONFIG_PPP is not set # CONFIG_SLIP is not set # CONFIG_NET_FC is not set -# CONFIG_SHAPER is not set CONFIG_NETCONSOLE=y +# CONFIG_NETCONSOLE_DYNAMIC is not set CONFIG_NETPOLL=y # CONFIG_NETPOLL_TRAP is not set CONFIG_NET_POLL_CONTROLLER=y @@ -796,18 +1054,17 @@ CONFIG_NET_POLL_CONTROLLER=y # Input device support # CONFIG_INPUT=y -# CONFIG_INPUT_FF_MEMLESS is not set -# CONFIG_INPUT_POLLDEV is not set +CONFIG_INPUT_FF_MEMLESS=y +CONFIG_INPUT_POLLDEV=y # # Userland interfaces # CONFIG_INPUT_MOUSEDEV=y -CONFIG_INPUT_MOUSEDEV_PSAUX=y +# CONFIG_INPUT_MOUSEDEV_PSAUX is not set CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024 CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768 # CONFIG_INPUT_JOYDEV is not set -# CONFIG_INPUT_TSDEV is not set CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_EVBUG is not set @@ -832,17 +1089,62 @@ CONFIG_MOUSE_PS2_TRACKPOINT=y # CONFIG_MOUSE_SERIAL is not set # CONFIG_MOUSE_APPLETOUCH is not set # CONFIG_MOUSE_VSXXXAA is not set -# CONFIG_INPUT_JOYSTICK is not set -# CONFIG_INPUT_TABLET is not set -# CONFIG_INPUT_TOUCHSCREEN is not set -# CONFIG_INPUT_MISC is not set +CONFIG_INPUT_JOYSTICK=y +# CONFIG_JOYSTICK_ANALOG is not set +# CONFIG_JOYSTICK_A3D is not set +# CONFIG_JOYSTICK_ADI is not set +# CONFIG_JOYSTICK_COBRA is not set +# CONFIG_JOYSTICK_GF2K is not set +# CONFIG_JOYSTICK_GRIP is not set +# CONFIG_JOYSTICK_GRIP_MP is not set +# CONFIG_JOYSTICK_GUILLEMOT is not set +# CONFIG_JOYSTICK_INTERACT is not set +# CONFIG_JOYSTICK_SIDEWINDER is not set +# CONFIG_JOYSTICK_TMDC is not set +# CONFIG_JOYSTICK_IFORCE is not set +# CONFIG_JOYSTICK_WARRIOR is not set +# CONFIG_JOYSTICK_MAGELLAN is not set +# CONFIG_JOYSTICK_SPACEORB is not set +# CONFIG_JOYSTICK_SPACEBALL is not set +# CONFIG_JOYSTICK_STINGER is not set +# CONFIG_JOYSTICK_TWIDJOY is not set +# CONFIG_JOYSTICK_ZHENHUA is not set +# CONFIG_JOYSTICK_JOYDUMP is not set +# CONFIG_JOYSTICK_XPAD is not set +CONFIG_INPUT_TABLET=y +# CONFIG_TABLET_USB_ACECAD is not set +# CONFIG_TABLET_USB_AIPTEK is not set +# CONFIG_TABLET_USB_GTCO is not set +# CONFIG_TABLET_USB_KBTAB is not set +# CONFIG_TABLET_USB_WACOM is not set +CONFIG_INPUT_TOUCHSCREEN=y +# CONFIG_TOUCHSCREEN_FUJITSU is not set +# CONFIG_TOUCHSCREEN_GUNZE is not set +# CONFIG_TOUCHSCREEN_ELO is not set +# CONFIG_TOUCHSCREEN_MTOUCH is not set +# CONFIG_TOUCHSCREEN_MK712 is not set +# CONFIG_TOUCHSCREEN_PENMOUNT is not set +# CONFIG_TOUCHSCREEN_TOUCHRIGHT is not set +# CONFIG_TOUCHSCREEN_TOUCHWIN is not set +# CONFIG_TOUCHSCREEN_UCB1400 is not set +# CONFIG_TOUCHSCREEN_USB_COMPOSITE is not set +CONFIG_INPUT_MISC=y +# CONFIG_INPUT_PCSPKR is not set +# CONFIG_INPUT_APANEL is not set +# CONFIG_INPUT_ATLAS_BTNS is not set +# CONFIG_INPUT_ATI_REMOTE is not set +# CONFIG_INPUT_ATI_REMOTE2 is not set +# CONFIG_INPUT_KEYSPAN_REMOTE is not set +# CONFIG_INPUT_POWERMATE is not set +# CONFIG_INPUT_YEALINK is not set +# CONFIG_INPUT_UINPUT is not set # # Hardware I/O ports # CONFIG_SERIO=y CONFIG_SERIO_I8042=y -# CONFIG_SERIO_SERPORT is not set +CONFIG_SERIO_SERPORT=y # CONFIG_SERIO_CT82C710 is not set # CONFIG_SERIO_PCIPS2 is not set CONFIG_SERIO_LIBPS2=y @@ -855,8 +1157,26 @@ CONFIG_SERIO_LIBPS2=y CONFIG_VT=y CONFIG_VT_CONSOLE=y CONFIG_HW_CONSOLE=y -# CONFIG_VT_HW_CONSOLE_BINDING is not set -# CONFIG_SERIAL_NONSTANDARD is not set +CONFIG_VT_HW_CONSOLE_BINDING=y +CONFIG_DEVKMEM=y +CONFIG_SERIAL_NONSTANDARD=y +# CONFIG_COMPUTONE is not set +# CONFIG_ROCKETPORT is not set +# CONFIG_CYCLADES is not set +# CONFIG_DIGIEPCA is not set +# CONFIG_MOXA_INTELLIO is not set +# CONFIG_MOXA_SMARTIO is not set +# CONFIG_ISI is not set +# CONFIG_SYNCLINK is not set +# CONFIG_SYNCLINKMP is not set +# CONFIG_SYNCLINK_GT is not set +# CONFIG_N_HDLC is not set +# CONFIG_RISCOM8 is not set +# CONFIG_SPECIALIX is not set +# CONFIG_SX is not set +# CONFIG_RIO is not set +# CONFIG_STALDRV is not set +# CONFIG_NOZOMI is not set # # Serial drivers @@ -866,9 +1186,14 @@ CONFIG_SERIAL_8250_CONSOLE=y CONFIG_FIX_EARLYCON_MEM=y CONFIG_SERIAL_8250_PCI=y CONFIG_SERIAL_8250_PNP=y -CONFIG_SERIAL_8250_NR_UARTS=4 +# CONFIG_SERIAL_8250_CS is not set +CONFIG_SERIAL_8250_NR_UARTS=32 CONFIG_SERIAL_8250_RUNTIME_UARTS=4 -# CONFIG_SERIAL_8250_EXTENDED is not set +CONFIG_SERIAL_8250_EXTENDED=y +CONFIG_SERIAL_8250_MANY_PORTS=y +CONFIG_SERIAL_8250_SHARE_IRQ=y +CONFIG_SERIAL_8250_DETECT_IRQ=y +CONFIG_SERIAL_8250_RSA=y # # Non-8250 serial port support @@ -877,78 +1202,260 @@ CONFIG_SERIAL_CORE=y CONFIG_SERIAL_CORE_CONSOLE=y # CONFIG_SERIAL_JSM is not set CONFIG_UNIX98_PTYS=y -CONFIG_LEGACY_PTYS=y -CONFIG_LEGACY_PTY_COUNT=256 +# CONFIG_LEGACY_PTYS is not set # CONFIG_IPMI_HANDLER is not set -# CONFIG_WATCHDOG is not set CONFIG_HW_RANDOM=y -CONFIG_HW_RANDOM_INTEL=y -CONFIG_HW_RANDOM_AMD=y -# CONFIG_NVRAM is not set -CONFIG_RTC=y +# CONFIG_HW_RANDOM_INTEL is not set +# CONFIG_HW_RANDOM_AMD is not set +CONFIG_NVRAM=y # CONFIG_R3964 is not set # CONFIG_APPLICOM is not set -CONFIG_AGP=y -CONFIG_AGP_AMD64=y -CONFIG_AGP_INTEL=y -# CONFIG_AGP_SIS is not set -# CONFIG_AGP_VIA is not set -# CONFIG_DRM is not set + +# +# PCMCIA character devices +# +# CONFIG_SYNCLINK_CS is not set +# CONFIG_CARDMAN_4000 is not set +# CONFIG_CARDMAN_4040 is not set +# CONFIG_IPWIRELESS is not set # CONFIG_MWAVE is not set # CONFIG_PC8736x_GPIO is not set -CONFIG_RAW_DRIVER=y -CONFIG_MAX_RAW_DEVS=256 +# CONFIG_RAW_DRIVER is not set CONFIG_HPET=y # CONFIG_HPET_RTC_IRQ is not set -CONFIG_HPET_MMAP=y +# CONFIG_HPET_MMAP is not set # CONFIG_HANGCHECK_TIMER is not set # CONFIG_TCG_TPM is not set # CONFIG_TELCLOCK is not set CONFIG_DEVPORT=y -# CONFIG_I2C is not set - -# -# SPI support -# +CONFIG_I2C=y +CONFIG_I2C_BOARDINFO=y +# CONFIG_I2C_CHARDEV is not set + +# +# I2C Hardware Bus support +# +# CONFIG_I2C_ALI1535 is not set +# CONFIG_I2C_ALI1563 is not set +# CONFIG_I2C_ALI15X3 is not set +# CONFIG_I2C_AMD756 is not set +# CONFIG_I2C_AMD8111 is not set +CONFIG_I2C_I801=y +# CONFIG_I2C_I810 is not set +# CONFIG_I2C_PIIX4 is not set +# CONFIG_I2C_NFORCE2 is not set +# CONFIG_I2C_OCORES is not set +# CONFIG_I2C_PARPORT_LIGHT is not set +# CONFIG_I2C_PROSAVAGE is not set +# CONFIG_I2C_SAVAGE4 is not set +# CONFIG_I2C_SIMTEC is not set +# CONFIG_I2C_SIS5595 is not set +# CONFIG_I2C_SIS630 is not set +# CONFIG_I2C_SIS96X is not set +# CONFIG_I2C_TAOS_EVM is not set +# CONFIG_I2C_STUB is not set +# CONFIG_I2C_TINY_USB is not set +# CONFIG_I2C_VIA is not set +# CONFIG_I2C_VIAPRO is not set +# CONFIG_I2C_VOODOO3 is not set +# CONFIG_I2C_PCA_PLATFORM is not set + +# +# Miscellaneous I2C Chip support +# +# CONFIG_DS1682 is not set +# CONFIG_SENSORS_EEPROM is not set +# CONFIG_SENSORS_PCF8574 is not set +# CONFIG_PCF8575 is not set +# CONFIG_SENSORS_PCF8591 is not set +# CONFIG_SENSORS_MAX6875 is not set +# CONFIG_SENSORS_TSL2550 is not set +# CONFIG_I2C_DEBUG_CORE is not set +# CONFIG_I2C_DEBUG_ALGO is not set +# CONFIG_I2C_DEBUG_BUS is not set +# CONFIG_I2C_DEBUG_CHIP is not set # CONFIG_SPI is not set -# CONFIG_SPI_MASTER is not set # CONFIG_W1 is not set -# CONFIG_POWER_SUPPLY is not set +CONFIG_POWER_SUPPLY=y +# CONFIG_POWER_SUPPLY_DEBUG is not set +# CONFIG_PDA_POWER is not set +# CONFIG_BATTERY_DS2760 is not set # CONFIG_HWMON is not set +CONFIG_THERMAL=y +CONFIG_WATCHDOG=y +# CONFIG_WATCHDOG_NOWAYOUT is not set + +# +# Watchdog Device Drivers +# +# CONFIG_SOFT_WATCHDOG is not set +# CONFIG_ACQUIRE_WDT is not set +# CONFIG_ADVANTECH_WDT is not set +# CONFIG_ALIM1535_WDT is not set +# CONFIG_ALIM7101_WDT is not set +# CONFIG_SC520_WDT is not set +# CONFIG_EUROTECH_WDT is not set +# CONFIG_IB700_WDT is not set +# CONFIG_IBMASR is not set +# CONFIG_WAFER_WDT is not set +# CONFIG_I6300ESB_WDT is not set +# CONFIG_ITCO_WDT is not set +# CONFIG_IT8712F_WDT is not set +# CONFIG_HP_WATCHDOG is not set +# CONFIG_SC1200_WDT is not set +# CONFIG_PC87413_WDT is not set +# CONFIG_60XX_WDT is not set +# CONFIG_SBC8360_WDT is not set +# CONFIG_CPU5_WDT is not set +# CONFIG_SMSC37B787_WDT is not set +# CONFIG_W83627HF_WDT is not set +# CONFIG_W83697HF_WDT is not set +# CONFIG_W83877F_WDT is not set +# CONFIG_W83977F_WDT is not set +# CONFIG_MACHZ_WDT is not set +# CONFIG_SBC_EPX_C3_WATCHDOG is not set + +# +# PCI-based Watchdog Cards +# +# CONFIG_PCIPCWATCHDOG is not set +# CONFIG_WDTPCI is not set + +# +# USB-based Watchdog Cards +# +# CONFIG_USBPCWATCHDOG is not set + +# +# Sonics Silicon Backplane +# +CONFIG_SSB_POSSIBLE=y +# CONFIG_SSB is not set # # Multifunction device drivers # # CONFIG_MFD_SM501 is not set +# CONFIG_HTC_PASIC3 is not set # # Multimedia devices # + +# +# Multimedia core support +# # CONFIG_VIDEO_DEV is not set # CONFIG_DVB_CORE is not set + +# +# Multimedia drivers +# CONFIG_DAB=y # CONFIG_USB_DABUSB is not set # # Graphics support # -# CONFIG_BACKLIGHT_LCD_SUPPORT is not set +CONFIG_AGP=y +CONFIG_AGP_AMD64=y +CONFIG_AGP_INTEL=y +# CONFIG_AGP_SIS is not set +# CONFIG_AGP_VIA is not set +CONFIG_DRM=y +# CONFIG_DRM_TDFX is not set +# CONFIG_DRM_R128 is not set +# CONFIG_DRM_RADEON is not set +# CONFIG_DRM_I810 is not set +# CONFIG_DRM_I830 is not set +CONFIG_DRM_I915=y +# CONFIG_DRM_MGA is not set +# CONFIG_DRM_SIS is not set +# CONFIG_DRM_VIA is not set +# CONFIG_DRM_SAVAGE is not set +# CONFIG_VGASTATE is not set +# CONFIG_VIDEO_OUTPUT_CONTROL is not set +CONFIG_FB=y +# CONFIG_FIRMWARE_EDID is not set +# CONFIG_FB_DDC is not set +CONFIG_FB_CFB_FILLRECT=y +CONFIG_FB_CFB_COPYAREA=y +CONFIG_FB_CFB_IMAGEBLIT=y +# CONFIG_FB_CFB_REV_PIXELS_IN_BYTE is not set +# CONFIG_FB_SYS_FILLRECT is not set +# CONFIG_FB_SYS_COPYAREA is not set +# CONFIG_FB_SYS_IMAGEBLIT is not set +# CONFIG_FB_FOREIGN_ENDIAN is not set +# CONFIG_FB_SYS_FOPS is not set +CONFIG_FB_DEFERRED_IO=y +# CONFIG_FB_SVGALIB is not set +# CONFIG_FB_MACMODES is not set +# CONFIG_FB_BACKLIGHT is not set +CONFIG_FB_MODE_HELPERS=y +CONFIG_FB_TILEBLITTING=y + +# +# Frame buffer hardware drivers +# +# CONFIG_FB_CIRRUS is not set +# CONFIG_FB_PM2 is not set +# CONFIG_FB_CYBER2000 is not set +# CONFIG_FB_ARC is not set +# CONFIG_FB_ASILIANT is not set +# CONFIG_FB_IMSTT is not set +# CONFIG_FB_VGA16 is not set +# CONFIG_FB_UVESA is not set +# CONFIG_FB_VESA is not set +CONFIG_FB_EFI=y +# CONFIG_FB_IMAC is not set +# CONFIG_FB_N411 is not set +# CONFIG_FB_HGA is not set +# CONFIG_FB_S1D13XXX is not set +# CONFIG_FB_NVIDIA is not set +# CONFIG_FB_RIVA is not set +# CONFIG_FB_LE80578 is not set +# CONFIG_FB_INTEL is not set +# CONFIG_FB_MATROX is not set +# CONFIG_FB_RADEON is not set +# CONFIG_FB_ATY128 is not set +# CONFIG_FB_ATY is not set +# CONFIG_FB_S3 is not set +# CONFIG_FB_SAVAGE is not set +# CONFIG_FB_SIS is not set +# CONFIG_FB_NEOMAGIC is not set +# CONFIG_FB_KYRO is not set +# CONFIG_FB_3DFX is not set +# CONFIG_FB_VOODOO1 is not set +# CONFIG_FB_VT8623 is not set +# CONFIG_FB_TRIDENT is not set +# CONFIG_FB_ARK is not set +# CONFIG_FB_PM3 is not set +# CONFIG_FB_GEODE is not set +# CONFIG_FB_VIRTUAL is not set +CONFIG_BACKLIGHT_LCD_SUPPORT=y +# CONFIG_LCD_CLASS_DEVICE is not set +CONFIG_BACKLIGHT_CLASS_DEVICE=y +# CONFIG_BACKLIGHT_CORGI is not set +# CONFIG_BACKLIGHT_PROGEAR is not set # # Display device support # # CONFIG_DISPLAY_SUPPORT is not set -# CONFIG_VGASTATE is not set -# CONFIG_FB is not set # # Console display driver support # CONFIG_VGA_CONSOLE=y CONFIG_VGACON_SOFT_SCROLLBACK=y -CONFIG_VGACON_SOFT_SCROLLBACK_SIZE=256 +CONFIG_VGACON_SOFT_SCROLLBACK_SIZE=64 CONFIG_VIDEO_SELECT=y CONFIG_DUMMY_CONSOLE=y +# CONFIG_FRAMEBUFFER_CONSOLE is not set +CONFIG_LOGO=y +# CONFIG_LOGO_LINUX_MONO is not set +# CONFIG_LOGO_LINUX_VGA16 is not set +CONFIG_LOGO_LINUX_CLUT224=y # # Sound @@ -958,33 +1465,165 @@ CONFIG_SOUND=y # # Advanced Linux Sound Architecture # -# CONFIG_SND is not set +CONFIG_SND=y +CONFIG_SND_TIMER=y +CONFIG_SND_PCM=y +CONFIG_SND_HWDEP=y +CONFIG_SND_SEQUENCER=y +CONFIG_SND_SEQ_DUMMY=y +CONFIG_SND_OSSEMUL=y +CONFIG_SND_MIXER_OSS=y +CONFIG_SND_PCM_OSS=y +CONFIG_SND_PCM_OSS_PLUGINS=y +CONFIG_SND_SEQUENCER_OSS=y +CONFIG_SND_DYNAMIC_MINORS=y +CONFIG_SND_SUPPORT_OLD_API=y +CONFIG_SND_VERBOSE_PROCFS=y +# CONFIG_SND_VERBOSE_PRINTK is not set +# CONFIG_SND_DEBUG is not set +CONFIG_SND_VMASTER=y + +# +# Generic devices +# +# CONFIG_SND_PCSP is not set +# CONFIG_SND_DUMMY is not set +# CONFIG_SND_VIRMIDI is not set +# CONFIG_SND_MTPAV is not set +# CONFIG_SND_SERIAL_U16550 is not set +# CONFIG_SND_MPU401 is not set + +# +# PCI devices +# +# CONFIG_SND_AD1889 is not set +# CONFIG_SND_ALS300 is not set +# CONFIG_SND_ALS4000 is not set +# CONFIG_SND_ALI5451 is not set +# CONFIG_SND_ATIIXP is not set +# CONFIG_SND_ATIIXP_MODEM is not set +# CONFIG_SND_AU8810 is not set +# CONFIG_SND_AU8820 is not set +# CONFIG_SND_AU8830 is not set +# CONFIG_SND_AW2 is not set +# CONFIG_SND_AZT3328 is not set +# CONFIG_SND_BT87X is not set +# CONFIG_SND_CA0106 is not set +# CONFIG_SND_CMIPCI is not set +# CONFIG_SND_OXYGEN is not set +# CONFIG_SND_CS4281 is not set +# CONFIG_SND_CS46XX is not set +# CONFIG_SND_CS5530 is not set +# CONFIG_SND_DARLA20 is not set +# CONFIG_SND_GINA20 is not set +# CONFIG_SND_LAYLA20 is not set +# CONFIG_SND_DARLA24 is not set +# CONFIG_SND_GINA24 is not set +# CONFIG_SND_LAYLA24 is not set +# CONFIG_SND_MONA is not set +# CONFIG_SND_MIA is not set +# CONFIG_SND_ECHO3G is not set +# CONFIG_SND_INDIGO is not set +# CONFIG_SND_INDIGOIO is not set +# CONFIG_SND_INDIGODJ is not set +# CONFIG_SND_EMU10K1 is not set +# CONFIG_SND_EMU10K1X is not set +# CONFIG_SND_ENS1370 is not set +# CONFIG_SND_ENS1371 is not set +# CONFIG_SND_ES1938 is not set +# CONFIG_SND_ES1968 is not set +# CONFIG_SND_FM801 is not set +CONFIG_SND_HDA_INTEL=y +CONFIG_SND_HDA_HWDEP=y +CONFIG_SND_HDA_CODEC_REALTEK=y +CONFIG_SND_HDA_CODEC_ANALOG=y +CONFIG_SND_HDA_CODEC_SIGMATEL=y +CONFIG_SND_HDA_CODEC_VIA=y +CONFIG_SND_HDA_CODEC_ATIHDMI=y +CONFIG_SND_HDA_CODEC_CONEXANT=y +CONFIG_SND_HDA_CODEC_CMEDIA=y +CONFIG_SND_HDA_CODEC_SI3054=y +CONFIG_SND_HDA_GENERIC=y +# CONFIG_SND_HDA_POWER_SAVE is not set +# CONFIG_SND_HDSP is not set +# CONFIG_SND_HDSPM is not set +# CONFIG_SND_HIFIER is not set +# CONFIG_SND_ICE1712 is not set +# CONFIG_SND_ICE1724 is not set +# CONFIG_SND_INTEL8X0 is not set +# CONFIG_SND_INTEL8X0M is not set +# CONFIG_SND_KORG1212 is not set +# CONFIG_SND_MAESTRO3 is not set +# CONFIG_SND_MIXART is not set +# CONFIG_SND_NM256 is not set +# CONFIG_SND_PCXHR is not set +# CONFIG_SND_RIPTIDE is not set +# CONFIG_SND_RME32 is not set +# CONFIG_SND_RME96 is not set +# CONFIG_SND_RME9652 is not set +# CONFIG_SND_SONICVIBES is not set +# CONFIG_SND_TRIDENT is not set +# CONFIG_SND_VIA82XX is not set +# CONFIG_SND_VIA82XX_MODEM is not set +# CONFIG_SND_VIRTUOSO is not set +# CONFIG_SND_VX222 is not set +# CONFIG_SND_YMFPCI is not set + +# +# USB devices +# +# CONFIG_SND_USB_AUDIO is not set +# CONFIG_SND_USB_USX2Y is not set +# CONFIG_SND_USB_CAIAQ is not set + +# +# PCMCIA devices +# +# CONFIG_SND_VXPOCKET is not set +# CONFIG_SND_PDAUDIOCF is not set + +# +# System on Chip audio support +# +# CONFIG_SND_SOC is not set + +# +# ALSA SoC audio for Freescale SOCs +# + +# +# SoC Audio for the Texas Instruments OMAP +# # # Open Sound System # -CONFIG_SOUND_PRIME=y -# CONFIG_SOUND_TRIDENT is not set -# CONFIG_SOUND_MSNDCLAS is not set -# CONFIG_SOUND_MSNDPIN is not set -# CONFIG_SOUND_OSS is not set +# CONFIG_SOUND_PRIME is not set CONFIG_HID_SUPPORT=y CONFIG_HID=y -# CONFIG_HID_DEBUG is not set +CONFIG_HID_DEBUG=y +CONFIG_HIDRAW=y # # USB Input Devices # CONFIG_USB_HID=y -# CONFIG_USB_HIDINPUT_POWERBOOK is not set -# CONFIG_HID_FF is not set -# CONFIG_USB_HIDDEV is not set +CONFIG_USB_HIDINPUT_POWERBOOK=y +CONFIG_HID_FF=y +CONFIG_HID_PID=y +CONFIG_LOGITECH_FF=y +# CONFIG_LOGIRUMBLEPAD2_FF is not set +CONFIG_PANTHERLORD_FF=y +CONFIG_THRUSTMASTER_FF=y +CONFIG_ZEROPLUS_FF=y +CONFIG_USB_HIDDEV=y CONFIG_USB_SUPPORT=y CONFIG_USB_ARCH_HAS_HCD=y CONFIG_USB_ARCH_HAS_OHCI=y CONFIG_USB_ARCH_HAS_EHCI=y CONFIG_USB=y -# CONFIG_USB_DEBUG is not set +CONFIG_USB_DEBUG=y +CONFIG_USB_ANNOUNCE_NEW_DEVICES=y # # Miscellaneous USB options @@ -992,18 +1631,18 @@ CONFIG_USB=y CONFIG_USB_DEVICEFS=y # CONFIG_USB_DEVICE_CLASS is not set # CONFIG_USB_DYNAMIC_MINORS is not set -# CONFIG_USB_SUSPEND is not set -# CONFIG_USB_PERSIST is not set +CONFIG_USB_SUSPEND=y # CONFIG_USB_OTG is not set # # USB Host Controller Drivers # +# CONFIG_USB_C67X00_HCD is not set CONFIG_USB_EHCI_HCD=y -# CONFIG_USB_EHCI_SPLIT_ISO is not set # CONFIG_USB_EHCI_ROOT_HUB_TT is not set # CONFIG_USB_EHCI_TT_NEWSCHED is not set # CONFIG_USB_ISP116X_HCD is not set +# CONFIG_USB_ISP1760_HCD is not set CONFIG_USB_OHCI_HCD=y # CONFIG_USB_OHCI_BIG_ENDIAN_DESC is not set # CONFIG_USB_OHCI_BIG_ENDIAN_MMIO is not set @@ -1036,8 +1675,10 @@ CONFIG_USB_STORAGE=y # CONFIG_USB_STORAGE_SDDR55 is not set # CONFIG_USB_STORAGE_JUMPSHOT is not set # CONFIG_USB_STORAGE_ALAUDA is not set +# CONFIG_USB_STORAGE_ONETOUCH is not set # CONFIG_USB_STORAGE_KARMA is not set -# CONFIG_USB_LIBUSUAL is not set +# CONFIG_USB_STORAGE_CYPRESS_ATACB is not set +CONFIG_USB_LIBUSUAL=y # # USB Imaging devices @@ -1049,10 +1690,6 @@ CONFIG_USB_MON=y # # USB port drivers # - -# -# USB Serial Converter support -# # CONFIG_USB_SERIAL is not set # @@ -1078,98 +1715,126 @@ CONFIG_USB_MON=y # CONFIG_USB_TRANCEVIBRATOR is not set # CONFIG_USB_IOWARRIOR is not set # CONFIG_USB_TEST is not set +# CONFIG_USB_GADGET is not set +# CONFIG_MMC is not set +# CONFIG_MEMSTICK is not set +CONFIG_NEW_LEDS=y +CONFIG_LEDS_CLASS=y # -# USB DSL modem support +# LED drivers # +# CONFIG_LEDS_CLEVO_MAIL is not set # -# USB Gadget Support +# LED Triggers # -# CONFIG_USB_GADGET is not set -# CONFIG_MMC is not set +CONFIG_LEDS_TRIGGERS=y +# CONFIG_LEDS_TRIGGER_TIMER is not set +# CONFIG_LEDS_TRIGGER_HEARTBEAT is not set +# CONFIG_LEDS_TRIGGER_DEFAULT_ON is not set +# CONFIG_ACCESSIBILITY is not set +# CONFIG_INFINIBAND is not set +CONFIG_EDAC=y # -# LED devices +# Reporting subsystems # -# CONFIG_NEW_LEDS is not set +# CONFIG_EDAC_DEBUG is not set +# CONFIG_EDAC_MM_EDAC is not set +CONFIG_RTC_LIB=y +CONFIG_RTC_CLASS=y +# CONFIG_RTC_HCTOSYS is not set +# CONFIG_RTC_DEBUG is not set # -# LED drivers +# RTC interfaces # +CONFIG_RTC_INTF_SYSFS=y +CONFIG_RTC_INTF_PROC=y +CONFIG_RTC_INTF_DEV=y +# CONFIG_RTC_INTF_DEV_UIE_EMUL is not set +# CONFIG_RTC_DRV_TEST is not set # -# LED Triggers +# I2C RTC drivers # -# CONFIG_INFINIBAND is not set -# CONFIG_EDAC is not set +# CONFIG_RTC_DRV_DS1307 is not set +# CONFIG_RTC_DRV_DS1374 is not set +# CONFIG_RTC_DRV_DS1672 is not set +# CONFIG_RTC_DRV_MAX6900 is not set +# CONFIG_RTC_DRV_RS5C372 is not set +# CONFIG_RTC_DRV_ISL1208 is not set +# CONFIG_RTC_DRV_X1205 is not set +# CONFIG_RTC_DRV_PCF8563 is not set +# CONFIG_RTC_DRV_PCF8583 is not set +# CONFIG_RTC_DRV_M41T80 is not set +# CONFIG_RTC_DRV_S35390A is not set # -# Real Time Clock +# SPI RTC drivers # -# CONFIG_RTC_CLASS is not set # -# DMA Engine support +# Platform RTC drivers # -# CONFIG_DMA_ENGINE is not set +CONFIG_RTC_DRV_CMOS=y +# CONFIG_RTC_DRV_DS1511 is not set +# CONFIG_RTC_DRV_DS1553 is not set +# CONFIG_RTC_DRV_DS1742 is not set +# CONFIG_RTC_DRV_STK17TA8 is not set +# CONFIG_RTC_DRV_M48T86 is not set +# CONFIG_RTC_DRV_M48T59 is not set +# CONFIG_RTC_DRV_V3020 is not set # -# DMA Clients +# on-CPU RTC drivers # +CONFIG_DMADEVICES=y # # DMA Devices # -CONFIG_VIRTUALIZATION=y -# CONFIG_KVM is not set - -# -# Userspace I/O -# +# CONFIG_INTEL_IOATDMA is not set # CONFIG_UIO is not set # # Firmware Drivers # # CONFIG_EDD is not set +CONFIG_EFI_VARS=y # CONFIG_DELL_RBU is not set # CONFIG_DCDBAS is not set CONFIG_DMIID=y +# CONFIG_ISCSI_IBFT_FIND is not set # # File systems # -CONFIG_EXT2_FS=y -CONFIG_EXT2_FS_XATTR=y -CONFIG_EXT2_FS_POSIX_ACL=y -# CONFIG_EXT2_FS_SECURITY is not set -# CONFIG_EXT2_FS_XIP is not set +# CONFIG_EXT2_FS is not set CONFIG_EXT3_FS=y CONFIG_EXT3_FS_XATTR=y CONFIG_EXT3_FS_POSIX_ACL=y -# CONFIG_EXT3_FS_SECURITY is not set +CONFIG_EXT3_FS_SECURITY=y # CONFIG_EXT4DEV_FS is not set CONFIG_JBD=y # CONFIG_JBD_DEBUG is not set CONFIG_FS_MBCACHE=y -CONFIG_REISERFS_FS=y -# CONFIG_REISERFS_CHECK is not set -# CONFIG_REISERFS_PROC_INFO is not set -CONFIG_REISERFS_FS_XATTR=y -CONFIG_REISERFS_FS_POSIX_ACL=y -# CONFIG_REISERFS_FS_SECURITY is not set +# CONFIG_REISERFS_FS is not set # CONFIG_JFS_FS is not set CONFIG_FS_POSIX_ACL=y # CONFIG_XFS_FS is not set # CONFIG_GFS2_FS is not set # CONFIG_OCFS2_FS is not set -# CONFIG_MINIX_FS is not set -# CONFIG_ROMFS_FS is not set +CONFIG_DNOTIFY=y CONFIG_INOTIFY=y CONFIG_INOTIFY_USER=y -# CONFIG_QUOTA is not set -CONFIG_DNOTIFY=y +CONFIG_QUOTA=y +CONFIG_QUOTA_NETLINK_INTERFACE=y +# CONFIG_PRINT_QUOTA_WARNING is not set +# CONFIG_QFMT_V1 is not set +CONFIG_QFMT_V2=y +CONFIG_QUOTACTL=y # CONFIG_AUTOFS_FS is not set CONFIG_AUTOFS4_FS=y # CONFIG_FUSE_FS is not set @@ -1180,7 +1845,7 @@ CONFIG_GENERIC_ACL=y # CONFIG_ISO9660_FS=y CONFIG_JOLIET=y -# CONFIG_ZISOFS is not set +CONFIG_ZISOFS=y # CONFIG_UDF_FS is not set # @@ -1198,13 +1863,13 @@ CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1" # CONFIG_PROC_FS=y CONFIG_PROC_KCORE=y +CONFIG_PROC_VMCORE=y CONFIG_PROC_SYSCTL=y CONFIG_SYSFS=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_HUGETLBFS=y CONFIG_HUGETLB_PAGE=y -CONFIG_RAMFS=y # CONFIG_CONFIGFS_FS is not set # @@ -1212,6 +1877,7 @@ CONFIG_RAMFS=y # # CONFIG_ADFS_FS is not set # CONFIG_AFFS_FS is not set +# CONFIG_ECRYPT_FS is not set # CONFIG_HFS_FS is not set # CONFIG_HFSPLUS_FS is not set # CONFIG_BEFS_FS is not set @@ -1219,33 +1885,15 @@ CONFIG_RAMFS=y # CONFIG_EFS_FS is not set # CONFIG_CRAMFS is not set # CONFIG_VXFS_FS is not set +# CONFIG_MINIX_FS is not set # CONFIG_HPFS_FS is not set # CONFIG_QNX4FS_FS is not set +# CONFIG_ROMFS_FS is not set # CONFIG_SYSV_FS is not set # CONFIG_UFS_FS is not set - -# -# Network File Systems -# -CONFIG_NFS_FS=y -CONFIG_NFS_V3=y -# CONFIG_NFS_V3_ACL is not set -# CONFIG_NFS_V4 is not set -# CONFIG_NFS_DIRECTIO is not set -CONFIG_NFSD=y -CONFIG_NFSD_V3=y -# CONFIG_NFSD_V3_ACL is not set -# CONFIG_NFSD_V4 is not set -CONFIG_NFSD_TCP=y -CONFIG_ROOT_NFS=y -CONFIG_LOCKD=y -CONFIG_LOCKD_V4=y -CONFIG_EXPORTFS=y -CONFIG_NFS_COMMON=y -CONFIG_SUNRPC=y -# CONFIG_SUNRPC_BIND34 is not set -# CONFIG_RPCSEC_GSS_KRB5 is not set -# CONFIG_RPCSEC_GSS_SPKM3 is not set +CONFIG_NETWORK_FILESYSTEMS=y +# CONFIG_NFS_FS is not set +# CONFIG_NFSD is not set # CONFIG_SMB_FS is not set # CONFIG_CIFS is not set # CONFIG_NCP_FS is not set @@ -1255,14 +1903,26 @@ CONFIG_SUNRPC=y # # Partition Types # -# CONFIG_PARTITION_ADVANCED is not set +CONFIG_PARTITION_ADVANCED=y +# CONFIG_ACORN_PARTITION is not set +CONFIG_OSF_PARTITION=y +CONFIG_AMIGA_PARTITION=y +# CONFIG_ATARI_PARTITION is not set +CONFIG_MAC_PARTITION=y CONFIG_MSDOS_PARTITION=y - -# -# Native Language Support -# +CONFIG_BSD_DISKLABEL=y +CONFIG_MINIX_SUBPARTITION=y +CONFIG_SOLARIS_X86_PARTITION=y +CONFIG_UNIXWARE_DISKLABEL=y +# CONFIG_LDM_PARTITION is not set +CONFIG_SGI_PARTITION=y +# CONFIG_ULTRIX_PARTITION is not set +CONFIG_SUN_PARTITION=y +CONFIG_KARMA_PARTITION=y +CONFIG_EFI_PARTITION=y +# CONFIG_SYSV68_PARTITION is not set CONFIG_NLS=y -CONFIG_NLS_DEFAULT="iso8859-1" +CONFIG_NLS_DEFAULT="utf8" CONFIG_NLS_CODEPAGE_437=y # CONFIG_NLS_CODEPAGE_737 is not set # CONFIG_NLS_CODEPAGE_775 is not set @@ -1297,40 +1957,33 @@ CONFIG_NLS_ISO8859_1=y # CONFIG_NLS_ISO8859_9 is not set # CONFIG_NLS_ISO8859_13 is not set # CONFIG_NLS_ISO8859_14 is not set -CONFIG_NLS_ISO8859_15=y +# CONFIG_NLS_ISO8859_15 is not set # CONFIG_NLS_KOI8_R is not set # CONFIG_NLS_KOI8_U is not set CONFIG_NLS_UTF8=y - -# -# Distributed Lock Manager -# # CONFIG_DLM is not set # -# Instrumentation Support -# -CONFIG_PROFILING=y -CONFIG_OPROFILE=y -CONFIG_KPROBES=y - -# # Kernel hacking # CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set +# CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_FRAME_WARN=2048 CONFIG_MAGIC_SYSRQ=y -CONFIG_UNUSED_SYMBOLS=y +# CONFIG_UNUSED_SYMBOLS is not set CONFIG_DEBUG_FS=y # CONFIG_HEADERS_CHECK is not set CONFIG_DEBUG_KERNEL=y # CONFIG_DEBUG_SHIRQ is not set -CONFIG_DETECT_SOFTLOCKUP=y +# CONFIG_DETECT_SOFTLOCKUP is not set # CONFIG_SCHED_DEBUG is not set -# CONFIG_SCHEDSTATS is not set +CONFIG_SCHEDSTATS=y CONFIG_TIMER_STATS=y -# CONFIG_DEBUG_SLAB is not set +# CONFIG_DEBUG_OBJECTS is not set +# CONFIG_SLUB_DEBUG_ON is not set +# CONFIG_SLUB_STATS is not set # CONFIG_DEBUG_RT_MUTEXES is not set # CONFIG_RT_MUTEX_TESTER is not set # CONFIG_DEBUG_SPINLOCK is not set @@ -1344,28 +1997,162 @@ CONFIG_TIMER_STATS=y CONFIG_DEBUG_BUGVERBOSE=y # CONFIG_DEBUG_INFO is not set # CONFIG_DEBUG_VM is not set +# CONFIG_DEBUG_WRITECOUNT is not set # CONFIG_DEBUG_LIST is not set -# CONFIG_FRAME_POINTER is not set -CONFIG_OPTIMIZE_INLINING=y +# CONFIG_DEBUG_SG is not set +CONFIG_FRAME_POINTER=y +# CONFIG_BOOT_PRINTK_DELAY is not set # CONFIG_RCU_TORTURE_TEST is not set +# CONFIG_KPROBES_SANITY_TEST is not set +# CONFIG_BACKTRACE_SELF_TEST is not set # CONFIG_LKDTM is not set # CONFIG_FAULT_INJECTION is not set -# CONFIG_DEBUG_RODATA is not set -# CONFIG_IOMMU_DEBUG is not set +# CONFIG_LATENCYTOP is not set +CONFIG_PROVIDE_OHCI1394_DMA_INIT=y +# CONFIG_SAMPLES is not set +# CONFIG_KGDB is not set +CONFIG_HAVE_ARCH_KGDB=y +# CONFIG_NONPROMISC_DEVMEM is not set +CONFIG_EARLY_PRINTK=y CONFIG_DEBUG_STACKOVERFLOW=y -# CONFIG_DEBUG_STACK_USAGE is not set +CONFIG_DEBUG_STACK_USAGE=y +# CONFIG_DEBUG_PAGEALLOC is not set +# CONFIG_DEBUG_PER_CPU_MAPS is not set +# CONFIG_X86_PTDUMP is not set +CONFIG_DEBUG_RODATA=y +# CONFIG_DIRECT_GBPAGES is not set +# CONFIG_DEBUG_RODATA_TEST is not set +CONFIG_DEBUG_NX_TEST=m +CONFIG_X86_MPPARSE=y +# CONFIG_IOMMU_DEBUG is not set +CONFIG_IO_DELAY_TYPE_0X80=0 +CONFIG_IO_DELAY_TYPE_0XED=1 +CONFIG_IO_DELAY_TYPE_UDELAY=2 +CONFIG_IO_DELAY_TYPE_NONE=3 +CONFIG_IO_DELAY_0X80=y +# CONFIG_IO_DELAY_0XED is not set +# CONFIG_IO_DELAY_UDELAY is not set +# CONFIG_IO_DELAY_NONE is not set +CONFIG_DEFAULT_IO_DELAY_TYPE=0 +CONFIG_DEBUG_BOOT_PARAMS=y +# CONFIG_CPA_DEBUG is not set # # Security options # -# CONFIG_KEYS is not set -# CONFIG_SECURITY is not set -# CONFIG_CRYPTO is not set +CONFIG_KEYS=y +CONFIG_KEYS_DEBUG_PROC_KEYS=y +CONFIG_SECURITY=y +CONFIG_SECURITY_NETWORK=y +# CONFIG_SECURITY_NETWORK_XFRM is not set +CONFIG_SECURITY_CAPABILITIES=y +CONFIG_SECURITY_FILE_CAPABILITIES=y +# CONFIG_SECURITY_ROOTPLUG is not set +CONFIG_SECURITY_DEFAULT_MMAP_MIN_ADDR=65536 +CONFIG_SECURITY_SELINUX=y +CONFIG_SECURITY_SELINUX_BOOTPARAM=y +CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=1 +CONFIG_SECURITY_SELINUX_DISABLE=y +CONFIG_SECURITY_SELINUX_DEVELOP=y +CONFIG_SECURITY_SELINUX_AVC_STATS=y +CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=1 +# CONFIG_SECURITY_SELINUX_ENABLE_SECMARK_DEFAULT is not set +# CONFIG_SECURITY_SELINUX_POLICYDB_VERSION_MAX is not set +# CONFIG_SECURITY_SMACK is not set +CONFIG_CRYPTO=y + +# +# Crypto core or helper +# +CONFIG_CRYPTO_ALGAPI=y +CONFIG_CRYPTO_AEAD=y +CONFIG_CRYPTO_BLKCIPHER=y +CONFIG_CRYPTO_HASH=y +CONFIG_CRYPTO_MANAGER=y +# CONFIG_CRYPTO_GF128MUL is not set +# CONFIG_CRYPTO_NULL is not set +# CONFIG_CRYPTO_CRYPTD is not set +CONFIG_CRYPTO_AUTHENC=y +# CONFIG_CRYPTO_TEST is not set + +# +# Authenticated Encryption with Associated Data +# +# CONFIG_CRYPTO_CCM is not set +# CONFIG_CRYPTO_GCM is not set +# CONFIG_CRYPTO_SEQIV is not set + +# +# Block modes +# +CONFIG_CRYPTO_CBC=y +# CONFIG_CRYPTO_CTR is not set +# CONFIG_CRYPTO_CTS is not set +CONFIG_CRYPTO_ECB=y +# CONFIG_CRYPTO_LRW is not set +# CONFIG_CRYPTO_PCBC is not set +# CONFIG_CRYPTO_XTS is not set + +# +# Hash modes +# +CONFIG_CRYPTO_HMAC=y +# CONFIG_CRYPTO_XCBC is not set + +# +# Digest +# +# CONFIG_CRYPTO_CRC32C is not set +# CONFIG_CRYPTO_MD4 is not set +CONFIG_CRYPTO_MD5=y +# CONFIG_CRYPTO_MICHAEL_MIC is not set +CONFIG_CRYPTO_SHA1=y +# CONFIG_CRYPTO_SHA256 is not set +# CONFIG_CRYPTO_SHA512 is not set +# CONFIG_CRYPTO_TGR192 is not set +# CONFIG_CRYPTO_WP512 is not set + +# +# Ciphers +# +CONFIG_CRYPTO_AES=y +# CONFIG_CRYPTO_AES_X86_64 is not set +# CONFIG_CRYPTO_ANUBIS is not set +CONFIG_CRYPTO_ARC4=y +# CONFIG_CRYPTO_BLOWFISH is not set +# CONFIG_CRYPTO_CAMELLIA is not set +# CONFIG_CRYPTO_CAST5 is not set +# CONFIG_CRYPTO_CAST6 is not set +CONFIG_CRYPTO_DES=y +# CONFIG_CRYPTO_FCRYPT is not set +# CONFIG_CRYPTO_KHAZAD is not set +# CONFIG_CRYPTO_SALSA20 is not set +# CONFIG_CRYPTO_SALSA20_X86_64 is not set +# CONFIG_CRYPTO_SEED is not set +# CONFIG_CRYPTO_SERPENT is not set +# CONFIG_CRYPTO_TEA is not set +# CONFIG_CRYPTO_TWOFISH is not set +# CONFIG_CRYPTO_TWOFISH_X86_64 is not set + +# +# Compression +# +# CONFIG_CRYPTO_DEFLATE is not set +# CONFIG_CRYPTO_LZO is not set +CONFIG_CRYPTO_HW=y +# CONFIG_CRYPTO_DEV_HIFN_795X is not set +CONFIG_HAVE_KVM=y +CONFIG_VIRTUALIZATION=y +# CONFIG_KVM is not set +# CONFIG_VIRTIO_PCI is not set +# CONFIG_VIRTIO_BALLOON is not set # # Library routines # CONFIG_BITREVERSE=y +CONFIG_GENERIC_FIND_FIRST_BIT=y +CONFIG_GENERIC_FIND_NEXT_BIT=y # CONFIG_CRC_CCITT is not set # CONFIG_CRC16 is not set # CONFIG_CRC_ITU_T is not set diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index b5e329da166c..20371d0635e4 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -61,6 +61,19 @@ CFI_UNDEFINED r15 .endm +#ifdef CONFIG_PARAVIRT +ENTRY(native_usergs_sysret32) + swapgs + sysretl +ENDPROC(native_usergs_sysret32) + +ENTRY(native_irq_enable_sysexit) + swapgs + sti + sysexit +ENDPROC(native_irq_enable_sysexit) +#endif + /* * 32bit SYSENTER instruction entry. * @@ -85,14 +98,14 @@ ENTRY(ia32_sysenter_target) CFI_SIGNAL_FRAME CFI_DEF_CFA rsp,0 CFI_REGISTER rsp,rbp - swapgs + SWAPGS_UNSAFE_STACK movq %gs:pda_kernelstack, %rsp addq $(PDA_STACKOFFSET),%rsp /* * No need to follow this irqs on/off section: the syscall * disabled irqs, here we enable it straight after entry: */ - sti + ENABLE_INTERRUPTS(CLBR_NONE) movl %ebp,%ebp /* zero extension */ pushq $__USER32_DS CFI_ADJUST_CFA_OFFSET 8 @@ -103,7 +116,7 @@ ENTRY(ia32_sysenter_target) pushfq CFI_ADJUST_CFA_OFFSET 8 /*CFI_REL_OFFSET rflags,0*/ - movl 8*3-THREAD_SIZE+threadinfo_sysenter_return(%rsp), %r10d + movl 8*3-THREAD_SIZE+TI_sysenter_return(%rsp), %r10d CFI_REGISTER rip,r10 pushq $__USER32_CS CFI_ADJUST_CFA_OFFSET 8 @@ -123,8 +136,9 @@ ENTRY(ia32_sysenter_target) .quad 1b,ia32_badarg .previous GET_THREAD_INFO(%r10) - orl $TS_COMPAT,threadinfo_status(%r10) - testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10) + orl $TS_COMPAT,TI_status(%r10) + testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP), \ + TI_flags(%r10) CFI_REMEMBER_STATE jnz sysenter_tracesys sysenter_do_call: @@ -134,11 +148,11 @@ sysenter_do_call: call *ia32_sys_call_table(,%rax,8) movq %rax,RAX-ARGOFFSET(%rsp) GET_THREAD_INFO(%r10) - cli + DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - testl $_TIF_ALLWORK_MASK,threadinfo_flags(%r10) + testl $_TIF_ALLWORK_MASK,TI_flags(%r10) jnz int_ret_from_sys_call - andl $~TS_COMPAT,threadinfo_status(%r10) + andl $~TS_COMPAT,TI_status(%r10) /* clear IF, that popfq doesn't enable interrupts early */ andl $~0x200,EFLAGS-R11(%rsp) movl RIP-R11(%rsp),%edx /* User %eip */ @@ -151,10 +165,7 @@ sysenter_do_call: CFI_ADJUST_CFA_OFFSET -8 CFI_REGISTER rsp,rcx TRACE_IRQS_ON - swapgs - sti /* sti only takes effect after the next instruction */ - /* sysexit */ - .byte 0xf, 0x35 + ENABLE_INTERRUPTS_SYSEXIT32 sysenter_tracesys: CFI_RESTORE_STATE @@ -200,7 +211,7 @@ ENTRY(ia32_cstar_target) CFI_DEF_CFA rsp,PDA_STACKOFFSET CFI_REGISTER rip,rcx /*CFI_REGISTER rflags,r11*/ - swapgs + SWAPGS_UNSAFE_STACK movl %esp,%r8d CFI_REGISTER rsp,r8 movq %gs:pda_kernelstack,%rsp @@ -208,7 +219,7 @@ ENTRY(ia32_cstar_target) * No need to follow this irqs on/off section: the syscall * disabled irqs and here we enable it straight after entry: */ - sti + ENABLE_INTERRUPTS(CLBR_NONE) SAVE_ARGS 8,1,1 movl %eax,%eax /* zero extension */ movq %rax,ORIG_RAX-ARGOFFSET(%rsp) @@ -230,8 +241,9 @@ ENTRY(ia32_cstar_target) .quad 1b,ia32_badarg .previous GET_THREAD_INFO(%r10) - orl $TS_COMPAT,threadinfo_status(%r10) - testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10) + orl $TS_COMPAT,TI_status(%r10) + testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP), \ + TI_flags(%r10) CFI_REMEMBER_STATE jnz cstar_tracesys cstar_do_call: @@ -241,11 +253,11 @@ cstar_do_call: call *ia32_sys_call_table(,%rax,8) movq %rax,RAX-ARGOFFSET(%rsp) GET_THREAD_INFO(%r10) - cli + DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - testl $_TIF_ALLWORK_MASK,threadinfo_flags(%r10) + testl $_TIF_ALLWORK_MASK,TI_flags(%r10) jnz int_ret_from_sys_call - andl $~TS_COMPAT,threadinfo_status(%r10) + andl $~TS_COMPAT,TI_status(%r10) RESTORE_ARGS 1,-ARG_SKIP,1,1,1 movl RIP-ARGOFFSET(%rsp),%ecx CFI_REGISTER rip,rcx @@ -254,8 +266,7 @@ cstar_do_call: TRACE_IRQS_ON movl RSP-ARGOFFSET(%rsp),%esp CFI_RESTORE rsp - swapgs - sysretl + USERGS_SYSRET32 cstar_tracesys: CFI_RESTORE_STATE @@ -310,12 +321,12 @@ ENTRY(ia32_syscall) /*CFI_REL_OFFSET rflags,EFLAGS-RIP*/ /*CFI_REL_OFFSET cs,CS-RIP*/ CFI_REL_OFFSET rip,RIP-RIP - swapgs + SWAPGS /* * No need to follow this irqs on/off section: the syscall * disabled irqs and here we enable it straight after entry: */ - sti + ENABLE_INTERRUPTS(CLBR_NONE) movl %eax,%eax pushq %rax CFI_ADJUST_CFA_OFFSET 8 @@ -324,8 +335,9 @@ ENTRY(ia32_syscall) this could be a problem. */ SAVE_ARGS 0,0,1 GET_THREAD_INFO(%r10) - orl $TS_COMPAT,threadinfo_status(%r10) - testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10) + orl $TS_COMPAT,TI_status(%r10) + testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP), \ + TI_flags(%r10) jnz ia32_tracesys ia32_do_syscall: cmpl $(IA32_NR_syscalls-1),%eax @@ -370,13 +382,11 @@ quiet_ni_syscall: PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn, %rdi PTREGSCALL stub32_sigreturn, sys32_sigreturn, %rdi PTREGSCALL stub32_sigaltstack, sys32_sigaltstack, %rdx - PTREGSCALL stub32_sigsuspend, sys32_sigsuspend, %rcx PTREGSCALL stub32_execve, sys32_execve, %rcx PTREGSCALL stub32_fork, sys_fork, %rdi PTREGSCALL stub32_clone, sys32_clone, %rdx PTREGSCALL stub32_vfork, sys_vfork, %rdi PTREGSCALL stub32_iopl, sys_iopl, %rsi - PTREGSCALL stub32_rt_sigsuspend, sys_rt_sigsuspend, %rdx ENTRY(ia32_ptregs_common) popq %r11 @@ -476,7 +486,7 @@ ia32_sys_call_table: .quad sys_ssetmask .quad sys_setreuid16 /* 70 */ .quad sys_setregid16 - .quad stub32_sigsuspend + .quad sys32_sigsuspend .quad compat_sys_sigpending .quad sys_sethostname .quad compat_sys_setrlimit /* 75 */ @@ -583,7 +593,7 @@ ia32_sys_call_table: .quad sys32_rt_sigpending .quad compat_sys_rt_sigtimedwait .quad sys32_rt_sigqueueinfo - .quad stub32_rt_sigsuspend + .quad sys_rt_sigsuspend .quad sys32_pread /* 180 */ .quad sys32_pwrite .quad sys_chown16 diff --git a/arch/x86/kernel/.gitignore b/arch/x86/kernel/.gitignore index 4ea38a39aed4..08f4fd731469 100644 --- a/arch/x86/kernel/.gitignore +++ b/arch/x86/kernel/.gitignore @@ -1,2 +1,3 @@ vsyscall.lds vsyscall_32.lds +vmlinux.lds diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 5e618c3b4720..da140611bb57 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -2,10 +2,16 @@ # Makefile for the linux kernel. # -extra-y := head_$(BITS).o head$(BITS).o init_task.o vmlinux.lds +extra-y := head_$(BITS).o head$(BITS).o head.o init_task.o vmlinux.lds CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE) +ifdef CONFIG_FTRACE +# Do not profile debug utilities +CFLAGS_REMOVE_tsc.o = -pg +CFLAGS_REMOVE_rtc.o = -pg +endif + # # vsyscalls (which work on the user stack) should have # no stack-protector checks: @@ -13,20 +19,21 @@ CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE) nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_vsyscall_64.o := $(PROFILING) -g0 $(nostackp) CFLAGS_hpet.o := $(nostackp) -CFLAGS_tsc_64.o := $(nostackp) +CFLAGS_tsc.o := $(nostackp) obj-y := process_$(BITS).o signal_$(BITS).o entry_$(BITS).o obj-y += traps_$(BITS).o irq_$(BITS).o obj-y += time_$(BITS).o ioport.o ldt.o -obj-y += setup_$(BITS).o i8259_$(BITS).o setup.o +obj-y += setup.o i8259.o irqinit_$(BITS).o setup_percpu.o +obj-$(CONFIG_X86_VISWS) += visws_quirks.o +obj-$(CONFIG_X86_32) += probe_roms_32.o obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o -obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o setup64.o -obj-y += bootflag.o e820_$(BITS).o +obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o +obj-y += bootflag.o e820.o obj-y += pci-dma.o quirks.o i8237.o topology.o kdebugfs.o obj-y += alternative.o i8253.o pci-nommu.o -obj-$(CONFIG_X86_64) += bugs_64.o -obj-y += tsc_$(BITS).o io_delay.o rtc.o +obj-y += tsc.o io_delay.o rtc.o obj-$(CONFIG_X86_TRAMPOLINE) += trampoline.o obj-y += process.o @@ -53,9 +60,10 @@ obj-$(CONFIG_X86_32_SMP) += smpcommon.o obj-$(CONFIG_X86_64_SMP) += tsc_sync.o smpcommon.o obj-$(CONFIG_X86_TRAMPOLINE) += trampoline_$(BITS).o obj-$(CONFIG_X86_MPPARSE) += mpparse.o -obj-$(CONFIG_X86_LOCAL_APIC) += apic_$(BITS).o nmi_$(BITS).o +obj-$(CONFIG_X86_LOCAL_APIC) += apic_$(BITS).o nmi.o obj-$(CONFIG_X86_IO_APIC) += io_apic_$(BITS).o obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o +obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o @@ -64,7 +72,6 @@ obj-$(CONFIG_X86_SUMMIT_NUMA) += summit_32.o obj-y += vsmp_64.o obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_MODULES) += module_$(BITS).o -obj-$(CONFIG_ACPI_SRAT) += srat_32.o obj-$(CONFIG_EFI) += efi.o efi_$(BITS).o efi_stub_$(BITS).o obj-$(CONFIG_DOUBLEFAULT) += doublefault_32.o obj-$(CONFIG_KGDB) += kgdb.o @@ -82,6 +89,7 @@ obj-$(CONFIG_VMI) += vmi_32.o vmiclock_32.o obj-$(CONFIG_KVM_GUEST) += kvm.o obj-$(CONFIG_KVM_CLOCK) += kvmclock.o obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch_$(BITS).o +obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o obj-$(CONFIG_PCSPKR_PLATFORM) += pcspeaker.o @@ -93,12 +101,13 @@ obj-$(CONFIG_OLPC) += olpc.o ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) - obj-y += genapic_64.o genapic_flat_64.o genx2apic_uv_x.o + obj-y += genapic_64.o genapic_flat_64.o genx2apic_uv_x.o tlb_uv.o obj-$(CONFIG_X86_PM_TIMER) += pmtimer_64.o obj-$(CONFIG_AUDIT) += audit_64.o obj-$(CONFIG_GART_IOMMU) += pci-gart_64.o aperture_64.o obj-$(CONFIG_CALGARY_IOMMU) += pci-calgary_64.o tce_64.o + obj-$(CONFIG_AMD_IOMMU) += amd_iommu_init.o amd_iommu.o obj-$(CONFIG_SWIOTLB) += pci-swiotlb_64.o obj-$(CONFIG_PCI_MMCONFIG) += mmconf-fam10h_64.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index c49ebcc6c41e..f489d7a9be92 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -37,6 +37,7 @@ #include <asm/pgtable.h> #include <asm/io_apic.h> #include <asm/apic.h> +#include <asm/genapic.h> #include <asm/io.h> #include <asm/mpspec.h> #include <asm/smp.h> @@ -106,21 +107,6 @@ static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; */ enum acpi_irq_model_id acpi_irq_model = ACPI_IRQ_MODEL_PIC; -#ifdef CONFIG_X86_64 - -/* rely on all ACPI tables being in the direct mapping */ -char *__init __acpi_map_table(unsigned long phys_addr, unsigned long size) -{ - if (!phys_addr || !size) - return NULL; - - if (phys_addr+size <= (max_pfn_mapped << PAGE_SHIFT) + PAGE_SIZE) - return __va(phys_addr); - - return NULL; -} - -#else /* * Temporarily use the virtual area starting from FIX_IO_APIC_BASE_END, @@ -139,11 +125,15 @@ char *__init __acpi_map_table(unsigned long phys, unsigned long size) unsigned long base, offset, mapped_size; int idx; - if (phys + size < 8 * 1024 * 1024) + if (!phys || !size) + return NULL; + + if (phys+size <= (max_low_pfn_mapped << PAGE_SHIFT)) return __va(phys); offset = phys & (PAGE_SIZE - 1); mapped_size = PAGE_SIZE - offset; + clear_fixmap(FIX_ACPI_END); set_fixmap(FIX_ACPI_END, phys); base = fix_to_virt(FIX_ACPI_END); @@ -155,13 +145,13 @@ char *__init __acpi_map_table(unsigned long phys, unsigned long size) if (--idx < FIX_ACPI_BEGIN) return NULL; /* cannot handle this */ phys += PAGE_SIZE; + clear_fixmap(idx); set_fixmap(idx, phys); mapped_size += PAGE_SIZE; } return ((unsigned char *)base + offset); } -#endif #ifdef CONFIG_PCI_MMCONFIG /* The physical address of the MMCONFIG aperture. Set from ACPI tables. */ @@ -242,12 +232,19 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) static void __cpuinit acpi_register_lapic(int id, u8 enabled) { + unsigned int ver = 0; + if (!enabled) { ++disabled_cpus; return; } - generic_processor_info(id, 0); +#ifdef CONFIG_X86_32 + if (boot_cpu_physical_apicid != -1U) + ver = apic_version[boot_cpu_physical_apicid]; +#endif + + generic_processor_info(id, ver); } static int __init @@ -331,8 +328,6 @@ acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long e #ifdef CONFIG_X86_IO_APIC -struct mp_ioapic_routing mp_ioapic_routing[MAX_IO_APICS]; - static int __init acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end) { @@ -507,8 +502,6 @@ int acpi_register_gsi(u32 gsi, int triggering, int polarity) * Make sure all (legacy) PCI IRQs are set as level-triggered. */ if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) { - extern void eisa_set_level_irq(unsigned int irq); - if (triggering == ACPI_LEVEL_SENSITIVE) eisa_set_level_irq(gsi); } @@ -767,8 +760,13 @@ static void __init acpi_register_lapic_address(unsigned long address) mp_lapic_addr = address; set_fixmap_nocache(FIX_APIC_BASE, address); - if (boot_cpu_physical_apicid == -1U) + if (boot_cpu_physical_apicid == -1U) { boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id()); +#ifdef CONFIG_X86_32 + apic_version[boot_cpu_physical_apicid] = + GET_APIC_VERSION(apic_read(APIC_LVR)); +#endif + } } static int __init early_acpi_parse_madt_lapic_addr_ovr(void) @@ -848,6 +846,364 @@ static int __init acpi_parse_madt_lapic_entries(void) #endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_IO_APIC +#define MP_ISA_BUS 0 + +#ifdef CONFIG_X86_ES7000 +extern int es7000_plat; +#endif + +static struct { + int apic_id; + int gsi_base; + int gsi_end; + DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1); +} mp_ioapic_routing[MAX_IO_APICS]; + +static int mp_find_ioapic(int gsi) +{ + int i = 0; + + /* Find the IOAPIC that manages this GSI. */ + for (i = 0; i < nr_ioapics; i++) { + if ((gsi >= mp_ioapic_routing[i].gsi_base) + && (gsi <= mp_ioapic_routing[i].gsi_end)) + return i; + } + + printk(KERN_ERR "ERROR: Unable to locate IOAPIC for GSI %d\n", gsi); + return -1; +} + +static u8 __init uniq_ioapic_id(u8 id) +{ +#ifdef CONFIG_X86_32 + if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && + !APIC_XAPIC(apic_version[boot_cpu_physical_apicid])) + return io_apic_get_unique_id(nr_ioapics, id); + else + return id; +#else + int i; + DECLARE_BITMAP(used, 256); + bitmap_zero(used, 256); + for (i = 0; i < nr_ioapics; i++) { + struct mp_config_ioapic *ia = &mp_ioapics[i]; + __set_bit(ia->mp_apicid, used); + } + if (!test_bit(id, used)) + return id; + return find_first_zero_bit(used, 256); +#endif +} + +static int bad_ioapic(unsigned long address) +{ + if (nr_ioapics >= MAX_IO_APICS) { + printk(KERN_ERR "ERROR: Max # of I/O APICs (%d) exceeded " + "(found %d)\n", MAX_IO_APICS, nr_ioapics); + panic("Recompile kernel with bigger MAX_IO_APICS!\n"); + } + if (!address) { + printk(KERN_ERR "WARNING: Bogus (zero) I/O APIC address" + " found in table, skipping!\n"); + return 1; + } + return 0; +} + +void __init mp_register_ioapic(int id, u32 address, u32 gsi_base) +{ + int idx = 0; + + if (bad_ioapic(address)) + return; + + idx = nr_ioapics; + + mp_ioapics[idx].mp_type = MP_IOAPIC; + mp_ioapics[idx].mp_flags = MPC_APIC_USABLE; + mp_ioapics[idx].mp_apicaddr = address; + + set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address); + mp_ioapics[idx].mp_apicid = uniq_ioapic_id(id); +#ifdef CONFIG_X86_32 + mp_ioapics[idx].mp_apicver = io_apic_get_version(idx); +#else + mp_ioapics[idx].mp_apicver = 0; +#endif + /* + * Build basic GSI lookup table to facilitate gsi->io_apic lookups + * and to prevent reprogramming of IOAPIC pins (PCI GSIs). + */ + mp_ioapic_routing[idx].apic_id = mp_ioapics[idx].mp_apicid; + mp_ioapic_routing[idx].gsi_base = gsi_base; + mp_ioapic_routing[idx].gsi_end = gsi_base + + io_apic_get_redir_entries(idx); + + printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%lx, " + "GSI %d-%d\n", idx, mp_ioapics[idx].mp_apicid, + mp_ioapics[idx].mp_apicver, mp_ioapics[idx].mp_apicaddr, + mp_ioapic_routing[idx].gsi_base, mp_ioapic_routing[idx].gsi_end); + + nr_ioapics++; +} + +static void assign_to_mp_irq(struct mp_config_intsrc *m, + struct mp_config_intsrc *mp_irq) +{ + memcpy(mp_irq, m, sizeof(struct mp_config_intsrc)); +} + +static int mp_irq_cmp(struct mp_config_intsrc *mp_irq, + struct mp_config_intsrc *m) +{ + return memcmp(mp_irq, m, sizeof(struct mp_config_intsrc)); +} + +static void save_mp_irq(struct mp_config_intsrc *m) +{ + int i; + + for (i = 0; i < mp_irq_entries; i++) { + if (!mp_irq_cmp(&mp_irqs[i], m)) + return; + } + + assign_to_mp_irq(m, &mp_irqs[mp_irq_entries]); + if (++mp_irq_entries == MAX_IRQ_SOURCES) + panic("Max # of irq sources exceeded!!\n"); +} + +void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi) +{ + int ioapic; + int pin; + struct mp_config_intsrc mp_irq; + + /* + * Convert 'gsi' to 'ioapic.pin'. + */ + ioapic = mp_find_ioapic(gsi); + if (ioapic < 0) + return; + pin = gsi - mp_ioapic_routing[ioapic].gsi_base; + + /* + * TBD: This check is for faulty timer entries, where the override + * erroneously sets the trigger to level, resulting in a HUGE + * increase of timer interrupts! + */ + if ((bus_irq == 0) && (trigger == 3)) + trigger = 1; + + mp_irq.mp_type = MP_INTSRC; + mp_irq.mp_irqtype = mp_INT; + mp_irq.mp_irqflag = (trigger << 2) | polarity; + mp_irq.mp_srcbus = MP_ISA_BUS; + mp_irq.mp_srcbusirq = bus_irq; /* IRQ */ + mp_irq.mp_dstapic = mp_ioapics[ioapic].mp_apicid; /* APIC ID */ + mp_irq.mp_dstirq = pin; /* INTIN# */ + + save_mp_irq(&mp_irq); +} + +void __init mp_config_acpi_legacy_irqs(void) +{ + int i; + int ioapic; + unsigned int dstapic; + struct mp_config_intsrc mp_irq; + +#if defined (CONFIG_MCA) || defined (CONFIG_EISA) + /* + * Fabricate the legacy ISA bus (bus #31). + */ + mp_bus_id_to_type[MP_ISA_BUS] = MP_BUS_ISA; +#endif + set_bit(MP_ISA_BUS, mp_bus_not_pci); + Dprintk("Bus #%d is ISA\n", MP_ISA_BUS); + +#ifdef CONFIG_X86_ES7000 + /* + * Older generations of ES7000 have no legacy identity mappings + */ + if (es7000_plat == 1) + return; +#endif + + /* + * Locate the IOAPIC that manages the ISA IRQs (0-15). + */ + ioapic = mp_find_ioapic(0); + if (ioapic < 0) + return; + dstapic = mp_ioapics[ioapic].mp_apicid; + + /* + * Use the default configuration for the IRQs 0-15. Unless + * overridden by (MADT) interrupt source override entries. + */ + for (i = 0; i < 16; i++) { + int idx; + + for (idx = 0; idx < mp_irq_entries; idx++) { + struct mp_config_intsrc *irq = mp_irqs + idx; + + /* Do we already have a mapping for this ISA IRQ? */ + if (irq->mp_srcbus == MP_ISA_BUS + && irq->mp_srcbusirq == i) + break; + + /* Do we already have a mapping for this IOAPIC pin */ + if (irq->mp_dstapic == dstapic && + irq->mp_dstirq == i) + break; + } + + if (idx != mp_irq_entries) { + printk(KERN_DEBUG "ACPI: IRQ%d used by override.\n", i); + continue; /* IRQ already used */ + } + + mp_irq.mp_type = MP_INTSRC; + mp_irq.mp_irqflag = 0; /* Conforming */ + mp_irq.mp_srcbus = MP_ISA_BUS; + mp_irq.mp_dstapic = dstapic; + mp_irq.mp_irqtype = mp_INT; + mp_irq.mp_srcbusirq = i; /* Identity mapped */ + mp_irq.mp_dstirq = i; + + save_mp_irq(&mp_irq); + } +} + +int mp_register_gsi(u32 gsi, int triggering, int polarity) +{ + int ioapic; + int ioapic_pin; +#ifdef CONFIG_X86_32 +#define MAX_GSI_NUM 4096 +#define IRQ_COMPRESSION_START 64 + + static int pci_irq = IRQ_COMPRESSION_START; + /* + * Mapping between Global System Interrupts, which + * represent all possible interrupts, and IRQs + * assigned to actual devices. + */ + static int gsi_to_irq[MAX_GSI_NUM]; +#else + + if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC) + return gsi; +#endif + + /* Don't set up the ACPI SCI because it's already set up */ + if (acpi_gbl_FADT.sci_interrupt == gsi) + return gsi; + + ioapic = mp_find_ioapic(gsi); + if (ioapic < 0) { + printk(KERN_WARNING "No IOAPIC for GSI %u\n", gsi); + return gsi; + } + + ioapic_pin = gsi - mp_ioapic_routing[ioapic].gsi_base; + +#ifdef CONFIG_X86_32 + if (ioapic_renumber_irq) + gsi = ioapic_renumber_irq(ioapic, gsi); +#endif + + /* + * Avoid pin reprogramming. PRTs typically include entries + * with redundant pin->gsi mappings (but unique PCI devices); + * we only program the IOAPIC on the first. + */ + if (ioapic_pin > MP_MAX_IOAPIC_PIN) { + printk(KERN_ERR "Invalid reference to IOAPIC pin " + "%d-%d\n", mp_ioapic_routing[ioapic].apic_id, + ioapic_pin); + return gsi; + } + if (test_bit(ioapic_pin, mp_ioapic_routing[ioapic].pin_programmed)) { + Dprintk(KERN_DEBUG "Pin %d-%d already programmed\n", + mp_ioapic_routing[ioapic].apic_id, ioapic_pin); +#ifdef CONFIG_X86_32 + return (gsi < IRQ_COMPRESSION_START ? gsi : gsi_to_irq[gsi]); +#else + return gsi; +#endif + } + + set_bit(ioapic_pin, mp_ioapic_routing[ioapic].pin_programmed); +#ifdef CONFIG_X86_32 + /* + * For GSI >= 64, use IRQ compression + */ + if ((gsi >= IRQ_COMPRESSION_START) + && (triggering == ACPI_LEVEL_SENSITIVE)) { + /* + * For PCI devices assign IRQs in order, avoiding gaps + * due to unused I/O APIC pins. + */ + int irq = gsi; + if (gsi < MAX_GSI_NUM) { + /* + * Retain the VIA chipset work-around (gsi > 15), but + * avoid a problem where the 8254 timer (IRQ0) is setup + * via an override (so it's not on pin 0 of the ioapic), + * and at the same time, the pin 0 interrupt is a PCI + * type. The gsi > 15 test could cause these two pins + * to be shared as IRQ0, and they are not shareable. + * So test for this condition, and if necessary, avoid + * the pin collision. + */ + gsi = pci_irq++; + /* + * Don't assign IRQ used by ACPI SCI + */ + if (gsi == acpi_gbl_FADT.sci_interrupt) + gsi = pci_irq++; + gsi_to_irq[irq] = gsi; + } else { + printk(KERN_ERR "GSI %u is too high\n", gsi); + return gsi; + } + } +#endif + io_apic_set_pci_routing(ioapic, ioapic_pin, gsi, + triggering == ACPI_EDGE_SENSITIVE ? 0 : 1, + polarity == ACPI_ACTIVE_HIGH ? 0 : 1); + return gsi; +} + +int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin, + u32 gsi, int triggering, int polarity) +{ +#ifdef CONFIG_X86_MPPARSE + struct mp_config_intsrc mp_irq; + int ioapic; + + if (!acpi_ioapic) + return 0; + + /* print the entry should happen on mptable identically */ + mp_irq.mp_type = MP_INTSRC; + mp_irq.mp_irqtype = mp_INT; + mp_irq.mp_irqflag = (triggering == ACPI_EDGE_SENSITIVE ? 4 : 0x0c) | + (polarity == ACPI_ACTIVE_HIGH ? 1 : 3); + mp_irq.mp_srcbus = number; + mp_irq.mp_srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3); + ioapic = mp_find_ioapic(gsi); + mp_irq.mp_dstapic = mp_ioapic_routing[ioapic].apic_id; + mp_irq.mp_dstirq = gsi - mp_ioapic_routing[ioapic].gsi_base; + + save_mp_irq(&mp_irq); +#endif + return 0; +} + /* * Parse IOAPIC related entries in MADT * returns 0 on success, < 0 on error @@ -997,8 +1353,6 @@ static void __init acpi_process_madt(void) return; } -#ifdef __i386__ - static int __init disable_acpi_irq(const struct dmi_system_id *d) { if (!acpi_force) { @@ -1049,6 +1403,16 @@ static int __init force_acpi_ht(const struct dmi_system_id *d) } /* + * Force ignoring BIOS IRQ0 pin2 override + */ +static int __init dmi_ignore_irq0_timer_override(const struct dmi_system_id *d) +{ + pr_notice("%s detected: Ignoring BIOS IRQ0 pin2 override\n", d->ident); + acpi_skip_timer_override = 1; + return 0; +} + +/* * If your system is blacklisted here, but you find that acpi=force * works for you, please contact acpi-devel@sourceforge.net */ @@ -1215,11 +1579,35 @@ static struct dmi_system_id __initdata acpi_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 360"), }, }, + /* + * HP laptops which use a DSDT reporting as HP/SB400/10000, + * which includes some code which overrides all temperature + * trip points to 16C if the INTIN2 input of the I/O APIC + * is enabled. This input is incorrectly designated the + * ISA IRQ 0 via an interrupt source override even though + * it is wired to the output of the master 8259A and INTIN0 + * is not connected at all. Force ignoring BIOS IRQ0 pin2 + * override in that cases. + */ + { + .callback = dmi_ignore_irq0_timer_override, + .ident = "HP NX6125 laptop", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq nx6125"), + }, + }, + { + .callback = dmi_ignore_irq0_timer_override, + .ident = "HP NX6325 laptop", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq nx6325"), + }, + }, {} }; -#endif /* __i386__ */ - /* * acpi_boot_table_init() and acpi_boot_init() * called from setup_arch(), always. @@ -1247,9 +1635,7 @@ int __init acpi_boot_table_init(void) { int error; -#ifdef __i386__ dmi_check_system(acpi_dmi_table); -#endif /* * If acpi_disabled, bail out @@ -1374,6 +1760,20 @@ static int __init parse_pci(char *arg) } early_param("pci", parse_pci); +int __init acpi_mps_check(void) +{ +#if defined(CONFIG_X86_LOCAL_APIC) && !defined(CONFIG_X86_MPPARSE) +/* mptable code is not built-in*/ + if (acpi_disabled || acpi_noirq) { + printk(KERN_WARNING "MPS support code is not built-in.\n" + "Using acpi=off or acpi=noirq or pci=noacpi " + "may have problem\n"); + return 1; + } +#endif + return 0; +} + #ifdef CONFIG_X86_IO_APIC static int __init parse_acpi_skip_timer_override(char *arg) { diff --git a/arch/x86/kernel/acpi/processor.c b/arch/x86/kernel/acpi/processor.c index de2d2e4ebad9..7c074eec39fb 100644 --- a/arch/x86/kernel/acpi/processor.c +++ b/arch/x86/kernel/acpi/processor.c @@ -56,6 +56,12 @@ static void init_intel_pdc(struct acpi_processor *pr, struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_ACPI)) buf[2] |= ACPI_PDC_T_FFH; + /* + * If mwait/monitor is unsupported, C2/C3_FFH will be disabled + */ + if (!cpu_has(c, X86_FEATURE_MWAIT)) + buf[2] &= ~(ACPI_PDC_C_C2C3_FFH); + obj->type = ACPI_TYPE_BUFFER; obj->buffer.length = 12; obj->buffer.pointer = (u8 *) buf; diff --git a/arch/x86/kernel/acpi/realmode/wakeup.S b/arch/x86/kernel/acpi/realmode/wakeup.S index f9b77fb37e5b..3355973b12ac 100644 --- a/arch/x86/kernel/acpi/realmode/wakeup.S +++ b/arch/x86/kernel/acpi/realmode/wakeup.S @@ -5,6 +5,7 @@ #include <asm/msr-index.h> #include <asm/page.h> #include <asm/pgtable.h> +#include <asm/processor-flags.h> .code16 .section ".header", "a" @@ -24,6 +25,11 @@ pmode_gdt: .quad 0 realmode_flags: .long 0 real_magic: .long 0 trampoline_segment: .word 0 +_pad1: .byte 0 +wakeup_jmp: .byte 0xea /* ljmpw */ +wakeup_jmp_off: .word 3f +wakeup_jmp_seg: .word 0 +wakeup_gdt: .quad 0, 0, 0 signature: .long 0x51ee1111 .text @@ -34,11 +40,34 @@ _start: cli cld + /* Apparently some dimwit BIOS programmers don't know how to + program a PM to RM transition, and we might end up here with + junk in the data segment descriptor registers. The only way + to repair that is to go into PM and fix it ourselves... */ + movw $16, %cx + lgdtl %cs:wakeup_gdt + movl %cr0, %eax + orb $X86_CR0_PE, %al + movl %eax, %cr0 + jmp 1f +1: ljmpw $8, $2f +2: + movw %cx, %ds + movw %cx, %es + movw %cx, %ss + movw %cx, %fs + movw %cx, %gs + + andb $~X86_CR0_PE, %al + movl %eax, %cr0 + jmp wakeup_jmp +3: /* Set up segments */ movw %cs, %ax movw %ax, %ds movw %ax, %es movw %ax, %ss + lidtl wakeup_idt movl $wakeup_stack_end, %esp @@ -98,7 +127,14 @@ bogus_real_magic: jmp 1b .data - .balign 4 + .balign 8 + + /* This is the standard real-mode IDT */ +wakeup_idt: + .word 0xffff /* limit */ + .long 0 /* address */ + .word 0 + .globl HEAP, heap_end HEAP: .long wakeup_heap diff --git a/arch/x86/kernel/acpi/realmode/wakeup.h b/arch/x86/kernel/acpi/realmode/wakeup.h index ef8166fe8020..69d38d0b2b64 100644 --- a/arch/x86/kernel/acpi/realmode/wakeup.h +++ b/arch/x86/kernel/acpi/realmode/wakeup.h @@ -24,6 +24,11 @@ struct wakeup_header { u32 realmode_flags; u32 real_magic; u16 trampoline_segment; /* segment with trampoline code, 64-bit only */ + u8 _pad1; + u8 wakeup_jmp; + u16 wakeup_jmp_off; + u16 wakeup_jmp_seg; + u64 wakeup_gdt[3]; u32 signature; /* To check we have correct structure */ } __attribute__((__packed__)); diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index afc25ee9964b..868de3d5c39d 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -23,6 +23,15 @@ static unsigned long acpi_realmode; static char temp_stack[10240]; #endif +/* XXX: this macro should move to asm-x86/segment.h and be shared with the + boot code... */ +#define GDT_ENTRY(flags, base, limit) \ + (((u64)(base & 0xff000000) << 32) | \ + ((u64)flags << 40) | \ + ((u64)(limit & 0x00ff0000) << 32) | \ + ((u64)(base & 0x00ffffff) << 16) | \ + ((u64)(limit & 0x0000ffff))) + /** * acpi_save_state_mem - save kernel state * @@ -50,6 +59,29 @@ int acpi_save_state_mem(void) header->video_mode = saved_video_mode; + header->wakeup_jmp_seg = acpi_wakeup_address >> 4; + + /* + * Set up the wakeup GDT. We set these up as Big Real Mode, + * that is, with limits set to 4 GB. At least the Lenovo + * Thinkpad X61 is known to need this for the video BIOS + * initialization quirk to work; this is likely to also + * be the case for other laptops or integrated video devices. + */ + + /* GDT[0]: GDT self-pointer */ + header->wakeup_gdt[0] = + (u64)(sizeof(header->wakeup_gdt) - 1) + + ((u64)(acpi_wakeup_address + + ((char *)&header->wakeup_gdt - (char *)acpi_realmode)) + << 16); + /* GDT[1]: big real mode-like code segment */ + header->wakeup_gdt[1] = + GDT_ENTRY(0x809b, acpi_wakeup_address, 0xfffff); + /* GDT[2]: big real mode-like data segment */ + header->wakeup_gdt[2] = + GDT_ENTRY(0x8093, acpi_wakeup_address, 0xfffff); + #ifndef CONFIG_64BIT store_gdt((struct desc_ptr *)&header->pmode_gdt); @@ -72,7 +104,9 @@ int acpi_save_state_mem(void) saved_magic = 0x12345678; #else /* CONFIG_64BIT */ header->trampoline_segment = setup_trampoline() >> 4; - init_rsp = (unsigned long)temp_stack + 4096; +#ifdef CONFIG_SMP + stack_start.sp = temp_stack + 4096; +#endif initial_code = (unsigned long)wakeup_long64; saved_magic = 0x123456789abcdef0; #endif /* CONFIG_64BIT */ @@ -111,7 +145,7 @@ void __init acpi_reserve_bootmem(void) return; } - acpi_wakeup_address = acpi_realmode; + acpi_wakeup_address = virt_to_phys((void *)acpi_realmode); } @@ -124,6 +158,8 @@ static int __init acpi_sleep_setup(char *str) acpi_realmode_flags |= 2; if (strncmp(str, "s3_beep", 7) == 0) acpi_realmode_flags |= 4; + if (strncmp(str, "old_ordering", 12) == 0) + acpi_old_suspend_ordering(); str = strchr(str, ','); if (str != NULL) str += strspn(str, ", \t"); diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 65c7857a90dd..2763cb37b553 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -1,6 +1,6 @@ #include <linux/module.h> #include <linux/sched.h> -#include <linux/spinlock.h> +#include <linux/mutex.h> #include <linux/list.h> #include <linux/kprobes.h> #include <linux/mm.h> @@ -143,7 +143,7 @@ static const unsigned char *const p6_nops[ASM_NOP_MAX+1] = { #ifdef CONFIG_X86_64 extern char __vsyscall_0; -static inline const unsigned char*const * find_nop_table(void) +const unsigned char *const *find_nop_table(void) { return boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || boot_cpu_data.x86 < 6 ? k8_nops : p6_nops; @@ -162,7 +162,7 @@ static const struct nop { { -1, NULL } }; -static const unsigned char*const * find_nop_table(void) +const unsigned char *const *find_nop_table(void) { const unsigned char *const *noptable = intel_nops; int i; @@ -279,7 +279,7 @@ struct smp_alt_module { struct list_head next; }; static LIST_HEAD(smp_alt_modules); -static DEFINE_SPINLOCK(smp_alt); +static DEFINE_MUTEX(smp_alt); static int smp_mode = 1; /* protected by smp_alt */ void alternatives_smp_module_add(struct module *mod, char *name, @@ -312,12 +312,12 @@ void alternatives_smp_module_add(struct module *mod, char *name, __func__, smp->locks, smp->locks_end, smp->text, smp->text_end, smp->name); - spin_lock(&smp_alt); + mutex_lock(&smp_alt); list_add_tail(&smp->next, &smp_alt_modules); if (boot_cpu_has(X86_FEATURE_UP)) alternatives_smp_unlock(smp->locks, smp->locks_end, smp->text, smp->text_end); - spin_unlock(&smp_alt); + mutex_unlock(&smp_alt); } void alternatives_smp_module_del(struct module *mod) @@ -327,17 +327,17 @@ void alternatives_smp_module_del(struct module *mod) if (smp_alt_once || noreplace_smp) return; - spin_lock(&smp_alt); + mutex_lock(&smp_alt); list_for_each_entry(item, &smp_alt_modules, next) { if (mod != item->mod) continue; list_del(&item->next); - spin_unlock(&smp_alt); + mutex_unlock(&smp_alt); DPRINTK("%s: %s\n", __func__, item->name); kfree(item); return; } - spin_unlock(&smp_alt); + mutex_unlock(&smp_alt); } void alternatives_smp_switch(int smp) @@ -359,7 +359,7 @@ void alternatives_smp_switch(int smp) return; BUG_ON(!smp && (num_online_cpus() > 1)); - spin_lock(&smp_alt); + mutex_lock(&smp_alt); /* * Avoid unnecessary switches because it forces JIT based VMs to @@ -383,7 +383,7 @@ void alternatives_smp_switch(int smp) mod->text, mod->text_end); } smp_mode = smp; - spin_unlock(&smp_alt); + mutex_unlock(&smp_alt); } #endif diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c new file mode 100644 index 000000000000..f2766d84c7a0 --- /dev/null +++ b/arch/x86/kernel/amd_iommu.c @@ -0,0 +1,962 @@ +/* + * Copyright (C) 2007-2008 Advanced Micro Devices, Inc. + * Author: Joerg Roedel <joerg.roedel@amd.com> + * Leo Duran <leo.duran@amd.com> + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include <linux/pci.h> +#include <linux/gfp.h> +#include <linux/bitops.h> +#include <linux/scatterlist.h> +#include <linux/iommu-helper.h> +#include <asm/proto.h> +#include <asm/gart.h> +#include <asm/amd_iommu_types.h> +#include <asm/amd_iommu.h> + +#define CMD_SET_TYPE(cmd, t) ((cmd)->data[1] |= ((t) << 28)) + +#define to_pages(addr, size) \ + (round_up(((addr) & ~PAGE_MASK) + (size), PAGE_SIZE) >> PAGE_SHIFT) + +static DEFINE_RWLOCK(amd_iommu_devtable_lock); + +struct command { + u32 data[4]; +}; + +static int dma_ops_unity_map(struct dma_ops_domain *dma_dom, + struct unity_map_entry *e); + +static int iommu_has_npcache(struct amd_iommu *iommu) +{ + return iommu->cap & IOMMU_CAP_NPCACHE; +} + +static int __iommu_queue_command(struct amd_iommu *iommu, struct command *cmd) +{ + u32 tail, head; + u8 *target; + + tail = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET); + target = (iommu->cmd_buf + tail); + memcpy_toio(target, cmd, sizeof(*cmd)); + tail = (tail + sizeof(*cmd)) % iommu->cmd_buf_size; + head = readl(iommu->mmio_base + MMIO_CMD_HEAD_OFFSET); + if (tail == head) + return -ENOMEM; + writel(tail, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET); + + return 0; +} + +static int iommu_queue_command(struct amd_iommu *iommu, struct command *cmd) +{ + unsigned long flags; + int ret; + + spin_lock_irqsave(&iommu->lock, flags); + ret = __iommu_queue_command(iommu, cmd); + spin_unlock_irqrestore(&iommu->lock, flags); + + return ret; +} + +static int iommu_completion_wait(struct amd_iommu *iommu) +{ + int ret; + struct command cmd; + volatile u64 ready = 0; + unsigned long ready_phys = virt_to_phys(&ready); + + memset(&cmd, 0, sizeof(cmd)); + cmd.data[0] = LOW_U32(ready_phys) | CMD_COMPL_WAIT_STORE_MASK; + cmd.data[1] = HIGH_U32(ready_phys); + cmd.data[2] = 1; /* value written to 'ready' */ + CMD_SET_TYPE(&cmd, CMD_COMPL_WAIT); + + iommu->need_sync = 0; + + ret = iommu_queue_command(iommu, &cmd); + + if (ret) + return ret; + + while (!ready) + cpu_relax(); + + return 0; +} + +static int iommu_queue_inv_dev_entry(struct amd_iommu *iommu, u16 devid) +{ + struct command cmd; + + BUG_ON(iommu == NULL); + + memset(&cmd, 0, sizeof(cmd)); + CMD_SET_TYPE(&cmd, CMD_INV_DEV_ENTRY); + cmd.data[0] = devid; + + iommu->need_sync = 1; + + return iommu_queue_command(iommu, &cmd); +} + +static int iommu_queue_inv_iommu_pages(struct amd_iommu *iommu, + u64 address, u16 domid, int pde, int s) +{ + struct command cmd; + + memset(&cmd, 0, sizeof(cmd)); + address &= PAGE_MASK; + CMD_SET_TYPE(&cmd, CMD_INV_IOMMU_PAGES); + cmd.data[1] |= domid; + cmd.data[2] = LOW_U32(address); + cmd.data[3] = HIGH_U32(address); + if (s) + cmd.data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK; + if (pde) + cmd.data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK; + + iommu->need_sync = 1; + + return iommu_queue_command(iommu, &cmd); +} + +static int iommu_flush_pages(struct amd_iommu *iommu, u16 domid, + u64 address, size_t size) +{ + int s = 0; + unsigned pages = to_pages(address, size); + + address &= PAGE_MASK; + + if (pages > 1) { + /* + * If we have to flush more than one page, flush all + * TLB entries for this domain + */ + address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS; + s = 1; + } + + iommu_queue_inv_iommu_pages(iommu, address, domid, 0, s); + + return 0; +} + +static int iommu_map(struct protection_domain *dom, + unsigned long bus_addr, + unsigned long phys_addr, + int prot) +{ + u64 __pte, *pte, *page; + + bus_addr = PAGE_ALIGN(bus_addr); + phys_addr = PAGE_ALIGN(bus_addr); + + /* only support 512GB address spaces for now */ + if (bus_addr > IOMMU_MAP_SIZE_L3 || !(prot & IOMMU_PROT_MASK)) + return -EINVAL; + + pte = &dom->pt_root[IOMMU_PTE_L2_INDEX(bus_addr)]; + + if (!IOMMU_PTE_PRESENT(*pte)) { + page = (u64 *)get_zeroed_page(GFP_KERNEL); + if (!page) + return -ENOMEM; + *pte = IOMMU_L2_PDE(virt_to_phys(page)); + } + + pte = IOMMU_PTE_PAGE(*pte); + pte = &pte[IOMMU_PTE_L1_INDEX(bus_addr)]; + + if (!IOMMU_PTE_PRESENT(*pte)) { + page = (u64 *)get_zeroed_page(GFP_KERNEL); + if (!page) + return -ENOMEM; + *pte = IOMMU_L1_PDE(virt_to_phys(page)); + } + + pte = IOMMU_PTE_PAGE(*pte); + pte = &pte[IOMMU_PTE_L0_INDEX(bus_addr)]; + + if (IOMMU_PTE_PRESENT(*pte)) + return -EBUSY; + + __pte = phys_addr | IOMMU_PTE_P; + if (prot & IOMMU_PROT_IR) + __pte |= IOMMU_PTE_IR; + if (prot & IOMMU_PROT_IW) + __pte |= IOMMU_PTE_IW; + + *pte = __pte; + + return 0; +} + +static int iommu_for_unity_map(struct amd_iommu *iommu, + struct unity_map_entry *entry) +{ + u16 bdf, i; + + for (i = entry->devid_start; i <= entry->devid_end; ++i) { + bdf = amd_iommu_alias_table[i]; + if (amd_iommu_rlookup_table[bdf] == iommu) + return 1; + } + + return 0; +} + +static int iommu_init_unity_mappings(struct amd_iommu *iommu) +{ + struct unity_map_entry *entry; + int ret; + + list_for_each_entry(entry, &amd_iommu_unity_map, list) { + if (!iommu_for_unity_map(iommu, entry)) + continue; + ret = dma_ops_unity_map(iommu->default_dom, entry); + if (ret) + return ret; + } + + return 0; +} + +static int dma_ops_unity_map(struct dma_ops_domain *dma_dom, + struct unity_map_entry *e) +{ + u64 addr; + int ret; + + for (addr = e->address_start; addr < e->address_end; + addr += PAGE_SIZE) { + ret = iommu_map(&dma_dom->domain, addr, addr, e->prot); + if (ret) + return ret; + /* + * if unity mapping is in aperture range mark the page + * as allocated in the aperture + */ + if (addr < dma_dom->aperture_size) + __set_bit(addr >> PAGE_SHIFT, dma_dom->bitmap); + } + + return 0; +} + +static int init_unity_mappings_for_device(struct dma_ops_domain *dma_dom, + u16 devid) +{ + struct unity_map_entry *e; + int ret; + + list_for_each_entry(e, &amd_iommu_unity_map, list) { + if (!(devid >= e->devid_start && devid <= e->devid_end)) + continue; + ret = dma_ops_unity_map(dma_dom, e); + if (ret) + return ret; + } + + return 0; +} + +static unsigned long dma_mask_to_pages(unsigned long mask) +{ + return (mask >> PAGE_SHIFT) + + (PAGE_ALIGN(mask & ~PAGE_MASK) >> PAGE_SHIFT); +} + +static unsigned long dma_ops_alloc_addresses(struct device *dev, + struct dma_ops_domain *dom, + unsigned int pages) +{ + unsigned long limit = dma_mask_to_pages(*dev->dma_mask); + unsigned long address; + unsigned long size = dom->aperture_size >> PAGE_SHIFT; + unsigned long boundary_size; + + boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1, + PAGE_SIZE) >> PAGE_SHIFT; + limit = limit < size ? limit : size; + + if (dom->next_bit >= limit) + dom->next_bit = 0; + + address = iommu_area_alloc(dom->bitmap, limit, dom->next_bit, pages, + 0 , boundary_size, 0); + if (address == -1) + address = iommu_area_alloc(dom->bitmap, limit, 0, pages, + 0, boundary_size, 0); + + if (likely(address != -1)) { + dom->next_bit = address + pages; + address <<= PAGE_SHIFT; + } else + address = bad_dma_address; + + WARN_ON((address + (PAGE_SIZE*pages)) > dom->aperture_size); + + return address; +} + +static void dma_ops_free_addresses(struct dma_ops_domain *dom, + unsigned long address, + unsigned int pages) +{ + address >>= PAGE_SHIFT; + iommu_area_free(dom->bitmap, address, pages); +} + +static u16 domain_id_alloc(void) +{ + unsigned long flags; + int id; + + write_lock_irqsave(&amd_iommu_devtable_lock, flags); + id = find_first_zero_bit(amd_iommu_pd_alloc_bitmap, MAX_DOMAIN_ID); + BUG_ON(id == 0); + if (id > 0 && id < MAX_DOMAIN_ID) + __set_bit(id, amd_iommu_pd_alloc_bitmap); + else + id = 0; + write_unlock_irqrestore(&amd_iommu_devtable_lock, flags); + + return id; +} + +static void dma_ops_reserve_addresses(struct dma_ops_domain *dom, + unsigned long start_page, + unsigned int pages) +{ + unsigned int last_page = dom->aperture_size >> PAGE_SHIFT; + + if (start_page + pages > last_page) + pages = last_page - start_page; + + set_bit_string(dom->bitmap, start_page, pages); +} + +static void dma_ops_free_pagetable(struct dma_ops_domain *dma_dom) +{ + int i, j; + u64 *p1, *p2, *p3; + + p1 = dma_dom->domain.pt_root; + + if (!p1) + return; + + for (i = 0; i < 512; ++i) { + if (!IOMMU_PTE_PRESENT(p1[i])) + continue; + + p2 = IOMMU_PTE_PAGE(p1[i]); + for (j = 0; j < 512; ++i) { + if (!IOMMU_PTE_PRESENT(p2[j])) + continue; + p3 = IOMMU_PTE_PAGE(p2[j]); + free_page((unsigned long)p3); + } + + free_page((unsigned long)p2); + } + + free_page((unsigned long)p1); +} + +static void dma_ops_domain_free(struct dma_ops_domain *dom) +{ + if (!dom) + return; + + dma_ops_free_pagetable(dom); + + kfree(dom->pte_pages); + + kfree(dom->bitmap); + + kfree(dom); +} + +static struct dma_ops_domain *dma_ops_domain_alloc(struct amd_iommu *iommu, + unsigned order) +{ + struct dma_ops_domain *dma_dom; + unsigned i, num_pte_pages; + u64 *l2_pde; + u64 address; + + /* + * Currently the DMA aperture must be between 32 MB and 1GB in size + */ + if ((order < 25) || (order > 30)) + return NULL; + + dma_dom = kzalloc(sizeof(struct dma_ops_domain), GFP_KERNEL); + if (!dma_dom) + return NULL; + + spin_lock_init(&dma_dom->domain.lock); + + dma_dom->domain.id = domain_id_alloc(); + if (dma_dom->domain.id == 0) + goto free_dma_dom; + dma_dom->domain.mode = PAGE_MODE_3_LEVEL; + dma_dom->domain.pt_root = (void *)get_zeroed_page(GFP_KERNEL); + dma_dom->domain.priv = dma_dom; + if (!dma_dom->domain.pt_root) + goto free_dma_dom; + dma_dom->aperture_size = (1ULL << order); + dma_dom->bitmap = kzalloc(dma_dom->aperture_size / (PAGE_SIZE * 8), + GFP_KERNEL); + if (!dma_dom->bitmap) + goto free_dma_dom; + /* + * mark the first page as allocated so we never return 0 as + * a valid dma-address. So we can use 0 as error value + */ + dma_dom->bitmap[0] = 1; + dma_dom->next_bit = 0; + + if (iommu->exclusion_start && + iommu->exclusion_start < dma_dom->aperture_size) { + unsigned long startpage = iommu->exclusion_start >> PAGE_SHIFT; + int pages = to_pages(iommu->exclusion_start, + iommu->exclusion_length); + dma_ops_reserve_addresses(dma_dom, startpage, pages); + } + + num_pte_pages = dma_dom->aperture_size / (PAGE_SIZE * 512); + dma_dom->pte_pages = kzalloc(num_pte_pages * sizeof(void *), + GFP_KERNEL); + if (!dma_dom->pte_pages) + goto free_dma_dom; + + l2_pde = (u64 *)get_zeroed_page(GFP_KERNEL); + if (l2_pde == NULL) + goto free_dma_dom; + + dma_dom->domain.pt_root[0] = IOMMU_L2_PDE(virt_to_phys(l2_pde)); + + for (i = 0; i < num_pte_pages; ++i) { + dma_dom->pte_pages[i] = (u64 *)get_zeroed_page(GFP_KERNEL); + if (!dma_dom->pte_pages[i]) + goto free_dma_dom; + address = virt_to_phys(dma_dom->pte_pages[i]); + l2_pde[i] = IOMMU_L1_PDE(address); + } + + return dma_dom; + +free_dma_dom: + dma_ops_domain_free(dma_dom); + + return NULL; +} + +static struct protection_domain *domain_for_device(u16 devid) +{ + struct protection_domain *dom; + unsigned long flags; + + read_lock_irqsave(&amd_iommu_devtable_lock, flags); + dom = amd_iommu_pd_table[devid]; + read_unlock_irqrestore(&amd_iommu_devtable_lock, flags); + + return dom; +} + +static void set_device_domain(struct amd_iommu *iommu, + struct protection_domain *domain, + u16 devid) +{ + unsigned long flags; + + u64 pte_root = virt_to_phys(domain->pt_root); + + pte_root |= (domain->mode & 0x07) << 9; + pte_root |= IOMMU_PTE_IR | IOMMU_PTE_IW | IOMMU_PTE_P | 2; + + write_lock_irqsave(&amd_iommu_devtable_lock, flags); + amd_iommu_dev_table[devid].data[0] = pte_root; + amd_iommu_dev_table[devid].data[1] = pte_root >> 32; + amd_iommu_dev_table[devid].data[2] = domain->id; + + amd_iommu_pd_table[devid] = domain; + write_unlock_irqrestore(&amd_iommu_devtable_lock, flags); + + iommu_queue_inv_dev_entry(iommu, devid); + + iommu->need_sync = 1; +} + +static int get_device_resources(struct device *dev, + struct amd_iommu **iommu, + struct protection_domain **domain, + u16 *bdf) +{ + struct dma_ops_domain *dma_dom; + struct pci_dev *pcidev; + u16 _bdf; + + BUG_ON(!dev || dev->bus != &pci_bus_type || !dev->dma_mask); + + pcidev = to_pci_dev(dev); + _bdf = (pcidev->bus->number << 8) | pcidev->devfn; + + if (_bdf >= amd_iommu_last_bdf) { + *iommu = NULL; + *domain = NULL; + *bdf = 0xffff; + return 0; + } + + *bdf = amd_iommu_alias_table[_bdf]; + + *iommu = amd_iommu_rlookup_table[*bdf]; + if (*iommu == NULL) + return 0; + dma_dom = (*iommu)->default_dom; + *domain = domain_for_device(*bdf); + if (*domain == NULL) { + *domain = &dma_dom->domain; + set_device_domain(*iommu, *domain, *bdf); + printk(KERN_INFO "AMD IOMMU: Using protection domain %d for " + "device ", (*domain)->id); + print_devid(_bdf, 1); + } + + return 1; +} + +static dma_addr_t dma_ops_domain_map(struct amd_iommu *iommu, + struct dma_ops_domain *dom, + unsigned long address, + phys_addr_t paddr, + int direction) +{ + u64 *pte, __pte; + + WARN_ON(address > dom->aperture_size); + + paddr &= PAGE_MASK; + + pte = dom->pte_pages[IOMMU_PTE_L1_INDEX(address)]; + pte += IOMMU_PTE_L0_INDEX(address); + + __pte = paddr | IOMMU_PTE_P | IOMMU_PTE_FC; + + if (direction == DMA_TO_DEVICE) + __pte |= IOMMU_PTE_IR; + else if (direction == DMA_FROM_DEVICE) + __pte |= IOMMU_PTE_IW; + else if (direction == DMA_BIDIRECTIONAL) + __pte |= IOMMU_PTE_IR | IOMMU_PTE_IW; + + WARN_ON(*pte); + + *pte = __pte; + + return (dma_addr_t)address; +} + +static void dma_ops_domain_unmap(struct amd_iommu *iommu, + struct dma_ops_domain *dom, + unsigned long address) +{ + u64 *pte; + + if (address >= dom->aperture_size) + return; + + WARN_ON(address & 0xfffULL || address > dom->aperture_size); + + pte = dom->pte_pages[IOMMU_PTE_L1_INDEX(address)]; + pte += IOMMU_PTE_L0_INDEX(address); + + WARN_ON(!*pte); + + *pte = 0ULL; +} + +static dma_addr_t __map_single(struct device *dev, + struct amd_iommu *iommu, + struct dma_ops_domain *dma_dom, + phys_addr_t paddr, + size_t size, + int dir) +{ + dma_addr_t offset = paddr & ~PAGE_MASK; + dma_addr_t address, start; + unsigned int pages; + int i; + + pages = to_pages(paddr, size); + paddr &= PAGE_MASK; + + address = dma_ops_alloc_addresses(dev, dma_dom, pages); + if (unlikely(address == bad_dma_address)) + goto out; + + start = address; + for (i = 0; i < pages; ++i) { + dma_ops_domain_map(iommu, dma_dom, start, paddr, dir); + paddr += PAGE_SIZE; + start += PAGE_SIZE; + } + address += offset; + +out: + return address; +} + +static void __unmap_single(struct amd_iommu *iommu, + struct dma_ops_domain *dma_dom, + dma_addr_t dma_addr, + size_t size, + int dir) +{ + dma_addr_t i, start; + unsigned int pages; + + if ((dma_addr == 0) || (dma_addr + size > dma_dom->aperture_size)) + return; + + pages = to_pages(dma_addr, size); + dma_addr &= PAGE_MASK; + start = dma_addr; + + for (i = 0; i < pages; ++i) { + dma_ops_domain_unmap(iommu, dma_dom, start); + start += PAGE_SIZE; + } + + dma_ops_free_addresses(dma_dom, dma_addr, pages); +} + +static dma_addr_t map_single(struct device *dev, phys_addr_t paddr, + size_t size, int dir) +{ + unsigned long flags; + struct amd_iommu *iommu; + struct protection_domain *domain; + u16 devid; + dma_addr_t addr; + + get_device_resources(dev, &iommu, &domain, &devid); + + if (iommu == NULL || domain == NULL) + return (dma_addr_t)paddr; + + spin_lock_irqsave(&domain->lock, flags); + addr = __map_single(dev, iommu, domain->priv, paddr, size, dir); + if (addr == bad_dma_address) + goto out; + + if (iommu_has_npcache(iommu)) + iommu_flush_pages(iommu, domain->id, addr, size); + + if (iommu->need_sync) + iommu_completion_wait(iommu); + +out: + spin_unlock_irqrestore(&domain->lock, flags); + + return addr; +} + +static void unmap_single(struct device *dev, dma_addr_t dma_addr, + size_t size, int dir) +{ + unsigned long flags; + struct amd_iommu *iommu; + struct protection_domain *domain; + u16 devid; + + if (!get_device_resources(dev, &iommu, &domain, &devid)) + return; + + spin_lock_irqsave(&domain->lock, flags); + + __unmap_single(iommu, domain->priv, dma_addr, size, dir); + + iommu_flush_pages(iommu, domain->id, dma_addr, size); + + if (iommu->need_sync) + iommu_completion_wait(iommu); + + spin_unlock_irqrestore(&domain->lock, flags); +} + +static int map_sg_no_iommu(struct device *dev, struct scatterlist *sglist, + int nelems, int dir) +{ + struct scatterlist *s; + int i; + + for_each_sg(sglist, s, nelems, i) { + s->dma_address = (dma_addr_t)sg_phys(s); + s->dma_length = s->length; + } + + return nelems; +} + +static int map_sg(struct device *dev, struct scatterlist *sglist, + int nelems, int dir) +{ + unsigned long flags; + struct amd_iommu *iommu; + struct protection_domain *domain; + u16 devid; + int i; + struct scatterlist *s; + phys_addr_t paddr; + int mapped_elems = 0; + + get_device_resources(dev, &iommu, &domain, &devid); + + if (!iommu || !domain) + return map_sg_no_iommu(dev, sglist, nelems, dir); + + spin_lock_irqsave(&domain->lock, flags); + + for_each_sg(sglist, s, nelems, i) { + paddr = sg_phys(s); + + s->dma_address = __map_single(dev, iommu, domain->priv, + paddr, s->length, dir); + + if (s->dma_address) { + s->dma_length = s->length; + mapped_elems++; + } else + goto unmap; + if (iommu_has_npcache(iommu)) + iommu_flush_pages(iommu, domain->id, s->dma_address, + s->dma_length); + } + + if (iommu->need_sync) + iommu_completion_wait(iommu); + +out: + spin_unlock_irqrestore(&domain->lock, flags); + + return mapped_elems; +unmap: + for_each_sg(sglist, s, mapped_elems, i) { + if (s->dma_address) + __unmap_single(iommu, domain->priv, s->dma_address, + s->dma_length, dir); + s->dma_address = s->dma_length = 0; + } + + mapped_elems = 0; + + goto out; +} + +static void unmap_sg(struct device *dev, struct scatterlist *sglist, + int nelems, int dir) +{ + unsigned long flags; + struct amd_iommu *iommu; + struct protection_domain *domain; + struct scatterlist *s; + u16 devid; + int i; + + if (!get_device_resources(dev, &iommu, &domain, &devid)) + return; + + spin_lock_irqsave(&domain->lock, flags); + + for_each_sg(sglist, s, nelems, i) { + __unmap_single(iommu, domain->priv, s->dma_address, + s->dma_length, dir); + iommu_flush_pages(iommu, domain->id, s->dma_address, + s->dma_length); + s->dma_address = s->dma_length = 0; + } + + if (iommu->need_sync) + iommu_completion_wait(iommu); + + spin_unlock_irqrestore(&domain->lock, flags); +} + +static void *alloc_coherent(struct device *dev, size_t size, + dma_addr_t *dma_addr, gfp_t flag) +{ + unsigned long flags; + void *virt_addr; + struct amd_iommu *iommu; + struct protection_domain *domain; + u16 devid; + phys_addr_t paddr; + + virt_addr = (void *)__get_free_pages(flag, get_order(size)); + if (!virt_addr) + return 0; + + memset(virt_addr, 0, size); + paddr = virt_to_phys(virt_addr); + + get_device_resources(dev, &iommu, &domain, &devid); + + if (!iommu || !domain) { + *dma_addr = (dma_addr_t)paddr; + return virt_addr; + } + + spin_lock_irqsave(&domain->lock, flags); + + *dma_addr = __map_single(dev, iommu, domain->priv, paddr, + size, DMA_BIDIRECTIONAL); + + if (*dma_addr == bad_dma_address) { + free_pages((unsigned long)virt_addr, get_order(size)); + virt_addr = NULL; + goto out; + } + + if (iommu_has_npcache(iommu)) + iommu_flush_pages(iommu, domain->id, *dma_addr, size); + + if (iommu->need_sync) + iommu_completion_wait(iommu); + +out: + spin_unlock_irqrestore(&domain->lock, flags); + + return virt_addr; +} + +static void free_coherent(struct device *dev, size_t size, + void *virt_addr, dma_addr_t dma_addr) +{ + unsigned long flags; + struct amd_iommu *iommu; + struct protection_domain *domain; + u16 devid; + + get_device_resources(dev, &iommu, &domain, &devid); + + if (!iommu || !domain) + goto free_mem; + + spin_lock_irqsave(&domain->lock, flags); + + __unmap_single(iommu, domain->priv, dma_addr, size, DMA_BIDIRECTIONAL); + iommu_flush_pages(iommu, domain->id, dma_addr, size); + + if (iommu->need_sync) + iommu_completion_wait(iommu); + + spin_unlock_irqrestore(&domain->lock, flags); + +free_mem: + free_pages((unsigned long)virt_addr, get_order(size)); +} + +/* + * If the driver core informs the DMA layer if a driver grabs a device + * we don't need to preallocate the protection domains anymore. + * For now we have to. + */ +void prealloc_protection_domains(void) +{ + struct pci_dev *dev = NULL; + struct dma_ops_domain *dma_dom; + struct amd_iommu *iommu; + int order = amd_iommu_aperture_order; + u16 devid; + + while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { + devid = (dev->bus->number << 8) | dev->devfn; + if (devid >= amd_iommu_last_bdf) + continue; + devid = amd_iommu_alias_table[devid]; + if (domain_for_device(devid)) + continue; + iommu = amd_iommu_rlookup_table[devid]; + if (!iommu) + continue; + dma_dom = dma_ops_domain_alloc(iommu, order); + if (!dma_dom) + continue; + init_unity_mappings_for_device(dma_dom, devid); + set_device_domain(iommu, &dma_dom->domain, devid); + printk(KERN_INFO "AMD IOMMU: Allocated domain %d for device ", + dma_dom->domain.id); + print_devid(devid, 1); + } +} + +static struct dma_mapping_ops amd_iommu_dma_ops = { + .alloc_coherent = alloc_coherent, + .free_coherent = free_coherent, + .map_single = map_single, + .unmap_single = unmap_single, + .map_sg = map_sg, + .unmap_sg = unmap_sg, +}; + +int __init amd_iommu_init_dma_ops(void) +{ + struct amd_iommu *iommu; + int order = amd_iommu_aperture_order; + int ret; + + list_for_each_entry(iommu, &amd_iommu_list, list) { + iommu->default_dom = dma_ops_domain_alloc(iommu, order); + if (iommu->default_dom == NULL) + return -ENOMEM; + ret = iommu_init_unity_mappings(iommu); + if (ret) + goto free_domains; + } + + if (amd_iommu_isolate) + prealloc_protection_domains(); + + iommu_detected = 1; + force_iommu = 1; + bad_dma_address = 0; +#ifdef CONFIG_GART_IOMMU + gart_iommu_aperture_disabled = 1; + gart_iommu_aperture = 0; +#endif + + dma_ops = &amd_iommu_dma_ops; + + return 0; + +free_domains: + + list_for_each_entry(iommu, &amd_iommu_list, list) { + if (iommu->default_dom) + dma_ops_domain_free(iommu->default_dom); + } + + return ret; +} diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c new file mode 100644 index 000000000000..2a13e430437d --- /dev/null +++ b/arch/x86/kernel/amd_iommu_init.c @@ -0,0 +1,875 @@ +/* + * Copyright (C) 2007-2008 Advanced Micro Devices, Inc. + * Author: Joerg Roedel <joerg.roedel@amd.com> + * Leo Duran <leo.duran@amd.com> + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include <linux/pci.h> +#include <linux/acpi.h> +#include <linux/gfp.h> +#include <linux/list.h> +#include <linux/sysdev.h> +#include <asm/pci-direct.h> +#include <asm/amd_iommu_types.h> +#include <asm/amd_iommu.h> +#include <asm/gart.h> + +/* + * definitions for the ACPI scanning code + */ +#define UPDATE_LAST_BDF(x) do {\ + if ((x) > amd_iommu_last_bdf) \ + amd_iommu_last_bdf = (x); \ + } while (0); + +#define DEVID(bus, devfn) (((bus) << 8) | (devfn)) +#define PCI_BUS(x) (((x) >> 8) & 0xff) +#define IVRS_HEADER_LENGTH 48 +#define TBL_SIZE(x) (1 << (PAGE_SHIFT + get_order(amd_iommu_last_bdf * (x)))) + +#define ACPI_IVHD_TYPE 0x10 +#define ACPI_IVMD_TYPE_ALL 0x20 +#define ACPI_IVMD_TYPE 0x21 +#define ACPI_IVMD_TYPE_RANGE 0x22 + +#define IVHD_DEV_ALL 0x01 +#define IVHD_DEV_SELECT 0x02 +#define IVHD_DEV_SELECT_RANGE_START 0x03 +#define IVHD_DEV_RANGE_END 0x04 +#define IVHD_DEV_ALIAS 0x42 +#define IVHD_DEV_ALIAS_RANGE 0x43 +#define IVHD_DEV_EXT_SELECT 0x46 +#define IVHD_DEV_EXT_SELECT_RANGE 0x47 + +#define IVHD_FLAG_HT_TUN_EN 0x00 +#define IVHD_FLAG_PASSPW_EN 0x01 +#define IVHD_FLAG_RESPASSPW_EN 0x02 +#define IVHD_FLAG_ISOC_EN 0x03 + +#define IVMD_FLAG_EXCL_RANGE 0x08 +#define IVMD_FLAG_UNITY_MAP 0x01 + +#define ACPI_DEVFLAG_INITPASS 0x01 +#define ACPI_DEVFLAG_EXTINT 0x02 +#define ACPI_DEVFLAG_NMI 0x04 +#define ACPI_DEVFLAG_SYSMGT1 0x10 +#define ACPI_DEVFLAG_SYSMGT2 0x20 +#define ACPI_DEVFLAG_LINT0 0x40 +#define ACPI_DEVFLAG_LINT1 0x80 +#define ACPI_DEVFLAG_ATSDIS 0x10000000 + +struct ivhd_header { + u8 type; + u8 flags; + u16 length; + u16 devid; + u16 cap_ptr; + u64 mmio_phys; + u16 pci_seg; + u16 info; + u32 reserved; +} __attribute__((packed)); + +struct ivhd_entry { + u8 type; + u16 devid; + u8 flags; + u32 ext; +} __attribute__((packed)); + +struct ivmd_header { + u8 type; + u8 flags; + u16 length; + u16 devid; + u16 aux; + u64 resv; + u64 range_start; + u64 range_length; +} __attribute__((packed)); + +static int __initdata amd_iommu_detected; + +u16 amd_iommu_last_bdf; +struct list_head amd_iommu_unity_map; +unsigned amd_iommu_aperture_order = 26; +int amd_iommu_isolate; + +struct list_head amd_iommu_list; +struct dev_table_entry *amd_iommu_dev_table; +u16 *amd_iommu_alias_table; +struct amd_iommu **amd_iommu_rlookup_table; +struct protection_domain **amd_iommu_pd_table; +unsigned long *amd_iommu_pd_alloc_bitmap; + +static u32 dev_table_size; +static u32 alias_table_size; +static u32 rlookup_table_size; + +static void __init iommu_set_exclusion_range(struct amd_iommu *iommu) +{ + u64 start = iommu->exclusion_start & PAGE_MASK; + u64 limit = (start + iommu->exclusion_length) & PAGE_MASK; + u64 entry; + + if (!iommu->exclusion_start) + return; + + entry = start | MMIO_EXCL_ENABLE_MASK; + memcpy_toio(iommu->mmio_base + MMIO_EXCL_BASE_OFFSET, + &entry, sizeof(entry)); + + entry = limit; + memcpy_toio(iommu->mmio_base + MMIO_EXCL_LIMIT_OFFSET, + &entry, sizeof(entry)); +} + +static void __init iommu_set_device_table(struct amd_iommu *iommu) +{ + u32 entry; + + BUG_ON(iommu->mmio_base == NULL); + + entry = virt_to_phys(amd_iommu_dev_table); + entry |= (dev_table_size >> 12) - 1; + memcpy_toio(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET, + &entry, sizeof(entry)); +} + +static void __init iommu_feature_enable(struct amd_iommu *iommu, u8 bit) +{ + u32 ctrl; + + ctrl = readl(iommu->mmio_base + MMIO_CONTROL_OFFSET); + ctrl |= (1 << bit); + writel(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET); +} + +static void __init iommu_feature_disable(struct amd_iommu *iommu, u8 bit) +{ + u32 ctrl; + + ctrl = (u64)readl(iommu->mmio_base + MMIO_CONTROL_OFFSET); + ctrl &= ~(1 << bit); + writel(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET); +} + +void __init iommu_enable(struct amd_iommu *iommu) +{ + printk(KERN_INFO "AMD IOMMU: Enabling IOMMU at "); + print_devid(iommu->devid, 0); + printk(" cap 0x%hx\n", iommu->cap_ptr); + + iommu_feature_enable(iommu, CONTROL_IOMMU_EN); +} + +static u8 * __init iommu_map_mmio_space(u64 address) +{ + u8 *ret; + + if (!request_mem_region(address, MMIO_REGION_LENGTH, "amd_iommu")) + return NULL; + + ret = ioremap_nocache(address, MMIO_REGION_LENGTH); + if (ret != NULL) + return ret; + + release_mem_region(address, MMIO_REGION_LENGTH); + + return NULL; +} + +static void __init iommu_unmap_mmio_space(struct amd_iommu *iommu) +{ + if (iommu->mmio_base) + iounmap(iommu->mmio_base); + release_mem_region(iommu->mmio_phys, MMIO_REGION_LENGTH); +} + +static int __init find_last_devid_on_pci(int bus, int dev, int fn, int cap_ptr) +{ + u32 cap; + + cap = read_pci_config(bus, dev, fn, cap_ptr+MMIO_RANGE_OFFSET); + UPDATE_LAST_BDF(DEVID(MMIO_GET_BUS(cap), MMIO_GET_LD(cap))); + + return 0; +} + +static int __init find_last_devid_from_ivhd(struct ivhd_header *h) +{ + u8 *p = (void *)h, *end = (void *)h; + struct ivhd_entry *dev; + + p += sizeof(*h); + end += h->length; + + find_last_devid_on_pci(PCI_BUS(h->devid), + PCI_SLOT(h->devid), + PCI_FUNC(h->devid), + h->cap_ptr); + + while (p < end) { + dev = (struct ivhd_entry *)p; + switch (dev->type) { + case IVHD_DEV_SELECT: + case IVHD_DEV_RANGE_END: + case IVHD_DEV_ALIAS: + case IVHD_DEV_EXT_SELECT: + UPDATE_LAST_BDF(dev->devid); + break; + default: + break; + } + p += 0x04 << (*p >> 6); + } + + WARN_ON(p != end); + + return 0; +} + +static int __init find_last_devid_acpi(struct acpi_table_header *table) +{ + int i; + u8 checksum = 0, *p = (u8 *)table, *end = (u8 *)table; + struct ivhd_header *h; + + /* + * Validate checksum here so we don't need to do it when + * we actually parse the table + */ + for (i = 0; i < table->length; ++i) + checksum += p[i]; + if (checksum != 0) + /* ACPI table corrupt */ + return -ENODEV; + + p += IVRS_HEADER_LENGTH; + + end += table->length; + while (p < end) { + h = (struct ivhd_header *)p; + switch (h->type) { + case ACPI_IVHD_TYPE: + find_last_devid_from_ivhd(h); + break; + default: + break; + } + p += h->length; + } + WARN_ON(p != end); + + return 0; +} + +static u8 * __init alloc_command_buffer(struct amd_iommu *iommu) +{ + u8 *cmd_buf = (u8 *)__get_free_pages(GFP_KERNEL, + get_order(CMD_BUFFER_SIZE)); + u64 entry = 0; + + if (cmd_buf == NULL) + return NULL; + + iommu->cmd_buf_size = CMD_BUFFER_SIZE; + + memset(cmd_buf, 0, CMD_BUFFER_SIZE); + + entry = (u64)virt_to_phys(cmd_buf); + entry |= MMIO_CMD_SIZE_512; + memcpy_toio(iommu->mmio_base + MMIO_CMD_BUF_OFFSET, + &entry, sizeof(entry)); + + iommu_feature_enable(iommu, CONTROL_CMDBUF_EN); + + return cmd_buf; +} + +static void __init free_command_buffer(struct amd_iommu *iommu) +{ + if (iommu->cmd_buf) + free_pages((unsigned long)iommu->cmd_buf, + get_order(CMD_BUFFER_SIZE)); +} + +static void set_dev_entry_bit(u16 devid, u8 bit) +{ + int i = (bit >> 5) & 0x07; + int _bit = bit & 0x1f; + + amd_iommu_dev_table[devid].data[i] |= (1 << _bit); +} + +static void __init set_dev_entry_from_acpi(u16 devid, u32 flags, u32 ext_flags) +{ + if (flags & ACPI_DEVFLAG_INITPASS) + set_dev_entry_bit(devid, DEV_ENTRY_INIT_PASS); + if (flags & ACPI_DEVFLAG_EXTINT) + set_dev_entry_bit(devid, DEV_ENTRY_EINT_PASS); + if (flags & ACPI_DEVFLAG_NMI) + set_dev_entry_bit(devid, DEV_ENTRY_NMI_PASS); + if (flags & ACPI_DEVFLAG_SYSMGT1) + set_dev_entry_bit(devid, DEV_ENTRY_SYSMGT1); + if (flags & ACPI_DEVFLAG_SYSMGT2) + set_dev_entry_bit(devid, DEV_ENTRY_SYSMGT2); + if (flags & ACPI_DEVFLAG_LINT0) + set_dev_entry_bit(devid, DEV_ENTRY_LINT0_PASS); + if (flags & ACPI_DEVFLAG_LINT1) + set_dev_entry_bit(devid, DEV_ENTRY_LINT1_PASS); +} + +static void __init set_iommu_for_device(struct amd_iommu *iommu, u16 devid) +{ + amd_iommu_rlookup_table[devid] = iommu; +} + +static void __init set_device_exclusion_range(u16 devid, struct ivmd_header *m) +{ + struct amd_iommu *iommu = amd_iommu_rlookup_table[devid]; + + if (!(m->flags & IVMD_FLAG_EXCL_RANGE)) + return; + + if (iommu) { + set_dev_entry_bit(m->devid, DEV_ENTRY_EX); + iommu->exclusion_start = m->range_start; + iommu->exclusion_length = m->range_length; + } +} + +static void __init init_iommu_from_pci(struct amd_iommu *iommu) +{ + int bus = PCI_BUS(iommu->devid); + int dev = PCI_SLOT(iommu->devid); + int fn = PCI_FUNC(iommu->devid); + int cap_ptr = iommu->cap_ptr; + u32 range; + + iommu->cap = read_pci_config(bus, dev, fn, cap_ptr+MMIO_CAP_HDR_OFFSET); + + range = read_pci_config(bus, dev, fn, cap_ptr+MMIO_RANGE_OFFSET); + iommu->first_device = DEVID(MMIO_GET_BUS(range), MMIO_GET_FD(range)); + iommu->last_device = DEVID(MMIO_GET_BUS(range), MMIO_GET_LD(range)); +} + +static void __init init_iommu_from_acpi(struct amd_iommu *iommu, + struct ivhd_header *h) +{ + u8 *p = (u8 *)h; + u8 *end = p, flags = 0; + u16 dev_i, devid = 0, devid_start = 0, devid_to = 0; + u32 ext_flags = 0; + bool alias = 0; + struct ivhd_entry *e; + + /* + * First set the recommended feature enable bits from ACPI + * into the IOMMU control registers + */ + h->flags & IVHD_FLAG_HT_TUN_EN ? + iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) : + iommu_feature_disable(iommu, CONTROL_HT_TUN_EN); + + h->flags & IVHD_FLAG_PASSPW_EN ? + iommu_feature_enable(iommu, CONTROL_PASSPW_EN) : + iommu_feature_disable(iommu, CONTROL_PASSPW_EN); + + h->flags & IVHD_FLAG_RESPASSPW_EN ? + iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) : + iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN); + + h->flags & IVHD_FLAG_ISOC_EN ? + iommu_feature_enable(iommu, CONTROL_ISOC_EN) : + iommu_feature_disable(iommu, CONTROL_ISOC_EN); + + /* + * make IOMMU memory accesses cache coherent + */ + iommu_feature_enable(iommu, CONTROL_COHERENT_EN); + + /* + * Done. Now parse the device entries + */ + p += sizeof(struct ivhd_header); + end += h->length; + + while (p < end) { + e = (struct ivhd_entry *)p; + switch (e->type) { + case IVHD_DEV_ALL: + for (dev_i = iommu->first_device; + dev_i <= iommu->last_device; ++dev_i) + set_dev_entry_from_acpi(dev_i, e->flags, 0); + break; + case IVHD_DEV_SELECT: + devid = e->devid; + set_dev_entry_from_acpi(devid, e->flags, 0); + break; + case IVHD_DEV_SELECT_RANGE_START: + devid_start = e->devid; + flags = e->flags; + ext_flags = 0; + alias = 0; + break; + case IVHD_DEV_ALIAS: + devid = e->devid; + devid_to = e->ext >> 8; + set_dev_entry_from_acpi(devid, e->flags, 0); + amd_iommu_alias_table[devid] = devid_to; + break; + case IVHD_DEV_ALIAS_RANGE: + devid_start = e->devid; + flags = e->flags; + devid_to = e->ext >> 8; + ext_flags = 0; + alias = 1; + break; + case IVHD_DEV_EXT_SELECT: + devid = e->devid; + set_dev_entry_from_acpi(devid, e->flags, e->ext); + break; + case IVHD_DEV_EXT_SELECT_RANGE: + devid_start = e->devid; + flags = e->flags; + ext_flags = e->ext; + alias = 0; + break; + case IVHD_DEV_RANGE_END: + devid = e->devid; + for (dev_i = devid_start; dev_i <= devid; ++dev_i) { + if (alias) + amd_iommu_alias_table[dev_i] = devid_to; + set_dev_entry_from_acpi( + amd_iommu_alias_table[dev_i], + flags, ext_flags); + } + break; + default: + break; + } + + p += 0x04 << (e->type >> 6); + } +} + +static int __init init_iommu_devices(struct amd_iommu *iommu) +{ + u16 i; + + for (i = iommu->first_device; i <= iommu->last_device; ++i) + set_iommu_for_device(iommu, i); + + return 0; +} + +static void __init free_iommu_one(struct amd_iommu *iommu) +{ + free_command_buffer(iommu); + iommu_unmap_mmio_space(iommu); +} + +static void __init free_iommu_all(void) +{ + struct amd_iommu *iommu, *next; + + list_for_each_entry_safe(iommu, next, &amd_iommu_list, list) { + list_del(&iommu->list); + free_iommu_one(iommu); + kfree(iommu); + } +} + +static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h) +{ + spin_lock_init(&iommu->lock); + list_add_tail(&iommu->list, &amd_iommu_list); + + /* + * Copy data from ACPI table entry to the iommu struct + */ + iommu->devid = h->devid; + iommu->cap_ptr = h->cap_ptr; + iommu->mmio_phys = h->mmio_phys; + iommu->mmio_base = iommu_map_mmio_space(h->mmio_phys); + if (!iommu->mmio_base) + return -ENOMEM; + + iommu_set_device_table(iommu); + iommu->cmd_buf = alloc_command_buffer(iommu); + if (!iommu->cmd_buf) + return -ENOMEM; + + init_iommu_from_pci(iommu); + init_iommu_from_acpi(iommu, h); + init_iommu_devices(iommu); + + return 0; +} + +static int __init init_iommu_all(struct acpi_table_header *table) +{ + u8 *p = (u8 *)table, *end = (u8 *)table; + struct ivhd_header *h; + struct amd_iommu *iommu; + int ret; + + INIT_LIST_HEAD(&amd_iommu_list); + + end += table->length; + p += IVRS_HEADER_LENGTH; + + while (p < end) { + h = (struct ivhd_header *)p; + switch (*p) { + case ACPI_IVHD_TYPE: + iommu = kzalloc(sizeof(struct amd_iommu), GFP_KERNEL); + if (iommu == NULL) + return -ENOMEM; + ret = init_iommu_one(iommu, h); + if (ret) + return ret; + break; + default: + break; + } + p += h->length; + + } + WARN_ON(p != end); + + return 0; +} + +static void __init free_unity_maps(void) +{ + struct unity_map_entry *entry, *next; + + list_for_each_entry_safe(entry, next, &amd_iommu_unity_map, list) { + list_del(&entry->list); + kfree(entry); + } +} + +static int __init init_exclusion_range(struct ivmd_header *m) +{ + int i; + + switch (m->type) { + case ACPI_IVMD_TYPE: + set_device_exclusion_range(m->devid, m); + break; + case ACPI_IVMD_TYPE_ALL: + for (i = 0; i < amd_iommu_last_bdf; ++i) + set_device_exclusion_range(i, m); + break; + case ACPI_IVMD_TYPE_RANGE: + for (i = m->devid; i <= m->aux; ++i) + set_device_exclusion_range(i, m); + break; + default: + break; + } + + return 0; +} + +static int __init init_unity_map_range(struct ivmd_header *m) +{ + struct unity_map_entry *e = 0; + + e = kzalloc(sizeof(*e), GFP_KERNEL); + if (e == NULL) + return -ENOMEM; + + switch (m->type) { + default: + case ACPI_IVMD_TYPE: + e->devid_start = e->devid_end = m->devid; + break; + case ACPI_IVMD_TYPE_ALL: + e->devid_start = 0; + e->devid_end = amd_iommu_last_bdf; + break; + case ACPI_IVMD_TYPE_RANGE: + e->devid_start = m->devid; + e->devid_end = m->aux; + break; + } + e->address_start = PAGE_ALIGN(m->range_start); + e->address_end = e->address_start + PAGE_ALIGN(m->range_length); + e->prot = m->flags >> 1; + + list_add_tail(&e->list, &amd_iommu_unity_map); + + return 0; +} + +static int __init init_memory_definitions(struct acpi_table_header *table) +{ + u8 *p = (u8 *)table, *end = (u8 *)table; + struct ivmd_header *m; + + INIT_LIST_HEAD(&amd_iommu_unity_map); + + end += table->length; + p += IVRS_HEADER_LENGTH; + + while (p < end) { + m = (struct ivmd_header *)p; + if (m->flags & IVMD_FLAG_EXCL_RANGE) + init_exclusion_range(m); + else if (m->flags & IVMD_FLAG_UNITY_MAP) + init_unity_map_range(m); + + p += m->length; + } + + return 0; +} + +static void __init enable_iommus(void) +{ + struct amd_iommu *iommu; + + list_for_each_entry(iommu, &amd_iommu_list, list) { + iommu_set_exclusion_range(iommu); + iommu_enable(iommu); + } +} + +/* + * Suspend/Resume support + * disable suspend until real resume implemented + */ + +static int amd_iommu_resume(struct sys_device *dev) +{ + return 0; +} + +static int amd_iommu_suspend(struct sys_device *dev, pm_message_t state) +{ + return -EINVAL; +} + +static struct sysdev_class amd_iommu_sysdev_class = { + .name = "amd_iommu", + .suspend = amd_iommu_suspend, + .resume = amd_iommu_resume, +}; + +static struct sys_device device_amd_iommu = { + .id = 0, + .cls = &amd_iommu_sysdev_class, +}; + +int __init amd_iommu_init(void) +{ + int i, ret = 0; + + + if (no_iommu) { + printk(KERN_INFO "AMD IOMMU disabled by kernel command line\n"); + return 0; + } + + if (!amd_iommu_detected) + return -ENODEV; + + /* + * First parse ACPI tables to find the largest Bus/Dev/Func + * we need to handle. Upon this information the shared data + * structures for the IOMMUs in the system will be allocated + */ + if (acpi_table_parse("IVRS", find_last_devid_acpi) != 0) + return -ENODEV; + + dev_table_size = TBL_SIZE(DEV_TABLE_ENTRY_SIZE); + alias_table_size = TBL_SIZE(ALIAS_TABLE_ENTRY_SIZE); + rlookup_table_size = TBL_SIZE(RLOOKUP_TABLE_ENTRY_SIZE); + + ret = -ENOMEM; + + /* Device table - directly used by all IOMMUs */ + amd_iommu_dev_table = (void *)__get_free_pages(GFP_KERNEL, + get_order(dev_table_size)); + if (amd_iommu_dev_table == NULL) + goto out; + + /* + * Alias table - map PCI Bus/Dev/Func to Bus/Dev/Func the + * IOMMU see for that device + */ + amd_iommu_alias_table = (void *)__get_free_pages(GFP_KERNEL, + get_order(alias_table_size)); + if (amd_iommu_alias_table == NULL) + goto free; + + /* IOMMU rlookup table - find the IOMMU for a specific device */ + amd_iommu_rlookup_table = (void *)__get_free_pages(GFP_KERNEL, + get_order(rlookup_table_size)); + if (amd_iommu_rlookup_table == NULL) + goto free; + + /* + * Protection Domain table - maps devices to protection domains + * This table has the same size as the rlookup_table + */ + amd_iommu_pd_table = (void *)__get_free_pages(GFP_KERNEL, + get_order(rlookup_table_size)); + if (amd_iommu_pd_table == NULL) + goto free; + + amd_iommu_pd_alloc_bitmap = (void *)__get_free_pages(GFP_KERNEL, + get_order(MAX_DOMAIN_ID/8)); + if (amd_iommu_pd_alloc_bitmap == NULL) + goto free; + + /* + * memory is allocated now; initialize the device table with all zeroes + * and let all alias entries point to itself + */ + memset(amd_iommu_dev_table, 0, dev_table_size); + for (i = 0; i < amd_iommu_last_bdf; ++i) + amd_iommu_alias_table[i] = i; + + memset(amd_iommu_pd_table, 0, rlookup_table_size); + memset(amd_iommu_pd_alloc_bitmap, 0, MAX_DOMAIN_ID / 8); + + /* + * never allocate domain 0 because its used as the non-allocated and + * error value placeholder + */ + amd_iommu_pd_alloc_bitmap[0] = 1; + + /* + * now the data structures are allocated and basically initialized + * start the real acpi table scan + */ + ret = -ENODEV; + if (acpi_table_parse("IVRS", init_iommu_all) != 0) + goto free; + + if (acpi_table_parse("IVRS", init_memory_definitions) != 0) + goto free; + + ret = amd_iommu_init_dma_ops(); + if (ret) + goto free; + + ret = sysdev_class_register(&amd_iommu_sysdev_class); + if (ret) + goto free; + + ret = sysdev_register(&device_amd_iommu); + if (ret) + goto free; + + enable_iommus(); + + printk(KERN_INFO "AMD IOMMU: aperture size is %d MB\n", + (1 << (amd_iommu_aperture_order-20))); + + printk(KERN_INFO "AMD IOMMU: device isolation "); + if (amd_iommu_isolate) + printk("enabled\n"); + else + printk("disabled\n"); + +out: + return ret; + +free: + if (amd_iommu_pd_alloc_bitmap) + free_pages((unsigned long)amd_iommu_pd_alloc_bitmap, 1); + + if (amd_iommu_pd_table) + free_pages((unsigned long)amd_iommu_pd_table, + get_order(rlookup_table_size)); + + if (amd_iommu_rlookup_table) + free_pages((unsigned long)amd_iommu_rlookup_table, + get_order(rlookup_table_size)); + + if (amd_iommu_alias_table) + free_pages((unsigned long)amd_iommu_alias_table, + get_order(alias_table_size)); + + if (amd_iommu_dev_table) + free_pages((unsigned long)amd_iommu_dev_table, + get_order(dev_table_size)); + + free_iommu_all(); + + free_unity_maps(); + + goto out; +} + +static int __init early_amd_iommu_detect(struct acpi_table_header *table) +{ + return 0; +} + +void __init amd_iommu_detect(void) +{ + if (swiotlb || no_iommu || iommu_detected) + return; + + if (acpi_table_parse("IVRS", early_amd_iommu_detect) == 0) { + iommu_detected = 1; + amd_iommu_detected = 1; +#ifdef CONFIG_GART_IOMMU + gart_iommu_aperture_disabled = 1; + gart_iommu_aperture = 0; +#endif + } +} + +static int __init parse_amd_iommu_options(char *str) +{ + for (; *str; ++str) { + if (strcmp(str, "isolate") == 0) + amd_iommu_isolate = 1; + } + + return 1; +} + +static int __init parse_amd_iommu_size_options(char *str) +{ + for (; *str; ++str) { + if (strcmp(str, "32M") == 0) + amd_iommu_aperture_order = 25; + if (strcmp(str, "64M") == 0) + amd_iommu_aperture_order = 26; + if (strcmp(str, "128M") == 0) + amd_iommu_aperture_order = 27; + if (strcmp(str, "256M") == 0) + amd_iommu_aperture_order = 28; + if (strcmp(str, "512M") == 0) + amd_iommu_aperture_order = 29; + if (strcmp(str, "1G") == 0) + amd_iommu_aperture_order = 30; + } + + return 1; +} + +__setup("amd_iommu=", parse_amd_iommu_options); +__setup("amd_iommu_size=", parse_amd_iommu_size_options); diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 479926d9e004..9f907806c1a5 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -35,6 +35,18 @@ int fallback_aper_force __initdata; int fix_aperture __initdata = 1; +struct bus_dev_range { + int bus; + int dev_base; + int dev_limit; +}; + +static struct bus_dev_range bus_dev_ranges[] __initdata = { + { 0x00, 0x18, 0x20}, + { 0xff, 0x00, 0x20}, + { 0xfe, 0x00, 0x20} +}; + static struct resource gart_resource = { .name = "GART", .flags = IORESOURCE_MEM, @@ -55,8 +67,9 @@ static u32 __init allocate_aperture(void) u32 aper_size; void *p; - if (fallback_aper_order > 7) - fallback_aper_order = 7; + /* aper_size should <= 1G */ + if (fallback_aper_order > 5) + fallback_aper_order = 5; aper_size = (32 * 1024 * 1024) << fallback_aper_order; /* @@ -65,7 +78,20 @@ static u32 __init allocate_aperture(void) * memory. Unfortunately we cannot move it up because that would * make the IOMMU useless. */ - p = __alloc_bootmem_nopanic(aper_size, aper_size, 0); + /* + * using 512M as goal, in case kexec will load kernel_big + * that will do the on position decompress, and could overlap with + * that positon with gart that is used. + * sequende: + * kernel_small + * ==> kexec (with kdump trigger path or previous doesn't shutdown gart) + * ==> kernel_small(gart area become e820_reserved) + * ==> kexec (with kdump trigger path or previous doesn't shutdown gart) + * ==> kerne_big (uncompressed size will be big than 64M or 128M) + * so don't use 512M below as gart iommu, leave the space for kernel + * code for safe + */ + p = __alloc_bootmem_nopanic(aper_size, aper_size, 512ULL<<20); if (!p || __pa(p)+aper_size > 0xffffffff) { printk(KERN_ERR "Cannot allocate aperture memory hole (%p,%uK)\n", @@ -83,69 +109,53 @@ static u32 __init allocate_aperture(void) return (u32)__pa(p); } -static int __init aperture_valid(u64 aper_base, u32 aper_size) -{ - if (!aper_base) - return 0; - - if (aper_base + aper_size > 0x100000000UL) { - printk(KERN_ERR "Aperture beyond 4GB. Ignoring.\n"); - return 0; - } - if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) { - printk(KERN_ERR "Aperture pointing to e820 RAM. Ignoring.\n"); - return 0; - } - if (aper_size < 64*1024*1024) { - printk(KERN_ERR "Aperture too small (%d MB)\n", aper_size>>20); - return 0; - } - - return 1; -} /* Find a PCI capability */ -static __u32 __init find_cap(int num, int slot, int func, int cap) +static u32 __init find_cap(int bus, int slot, int func, int cap) { int bytes; u8 pos; - if (!(read_pci_config_16(num, slot, func, PCI_STATUS) & + if (!(read_pci_config_16(bus, slot, func, PCI_STATUS) & PCI_STATUS_CAP_LIST)) return 0; - pos = read_pci_config_byte(num, slot, func, PCI_CAPABILITY_LIST); + pos = read_pci_config_byte(bus, slot, func, PCI_CAPABILITY_LIST); for (bytes = 0; bytes < 48 && pos >= 0x40; bytes++) { u8 id; pos &= ~3; - id = read_pci_config_byte(num, slot, func, pos+PCI_CAP_LIST_ID); + id = read_pci_config_byte(bus, slot, func, pos+PCI_CAP_LIST_ID); if (id == 0xff) break; if (id == cap) return pos; - pos = read_pci_config_byte(num, slot, func, + pos = read_pci_config_byte(bus, slot, func, pos+PCI_CAP_LIST_NEXT); } return 0; } /* Read a standard AGPv3 bridge header */ -static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order) +static u32 __init read_agp(int bus, int slot, int func, int cap, u32 *order) { u32 apsize; u32 apsizereg; int nbits; u32 aper_low, aper_hi; u64 aper; + u32 old_order; - printk(KERN_INFO "AGP bridge at %02x:%02x:%02x\n", num, slot, func); - apsizereg = read_pci_config_16(num, slot, func, cap + 0x14); + printk(KERN_INFO "AGP bridge at %02x:%02x:%02x\n", bus, slot, func); + apsizereg = read_pci_config_16(bus, slot, func, cap + 0x14); if (apsizereg == 0xffffffff) { printk(KERN_ERR "APSIZE in AGP bridge unreadable\n"); return 0; } + /* old_order could be the value from NB gart setting */ + old_order = *order; + apsize = apsizereg & 0xfff; /* Some BIOS use weird encodings not in the AGPv3 table. */ if (apsize & 0xff) @@ -155,14 +165,26 @@ static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order) if ((int)*order < 0) /* < 32MB */ *order = 0; - aper_low = read_pci_config(num, slot, func, 0x10); - aper_hi = read_pci_config(num, slot, func, 0x14); + aper_low = read_pci_config(bus, slot, func, 0x10); + aper_hi = read_pci_config(bus, slot, func, 0x14); aper = (aper_low & ~((1<<22)-1)) | ((u64)aper_hi << 32); + /* + * On some sick chips, APSIZE is 0. It means it wants 4G + * so let double check that order, and lets trust AMD NB settings: + */ + printk(KERN_INFO "Aperture from AGP @ %Lx old size %u MB\n", + aper, 32 << old_order); + if (aper + (32ULL<<(20 + *order)) > 0x100000000ULL) { + printk(KERN_INFO "Aperture size %u MB (APSIZE %x) is not right, using settings from NB\n", + 32 << *order, apsizereg); + *order = old_order; + } + printk(KERN_INFO "Aperture from AGP @ %Lx size %u MB (APSIZE %x)\n", aper, 32 << *order, apsizereg); - if (!aperture_valid(aper, (32*1024*1024) << *order)) + if (!aperture_valid(aper, (32*1024*1024) << *order, 32<<20)) return 0; return (u32)aper; } @@ -180,17 +202,17 @@ static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order) * the AGP bridges should be always an own bus on the HT hierarchy, * but do it here for future safety. */ -static __u32 __init search_agp_bridge(u32 *order, int *valid_agp) +static u32 __init search_agp_bridge(u32 *order, int *valid_agp) { - int num, slot, func; + int bus, slot, func; /* Poor man's PCI discovery */ - for (num = 0; num < 256; num++) { + for (bus = 0; bus < 256; bus++) { for (slot = 0; slot < 32; slot++) { for (func = 0; func < 8; func++) { u32 class, cap; u8 type; - class = read_pci_config(num, slot, func, + class = read_pci_config(bus, slot, func, PCI_CLASS_REVISION); if (class == 0xffffffff) break; @@ -199,17 +221,17 @@ static __u32 __init search_agp_bridge(u32 *order, int *valid_agp) case PCI_CLASS_BRIDGE_HOST: case PCI_CLASS_BRIDGE_OTHER: /* needed? */ /* AGP bridge? */ - cap = find_cap(num, slot, func, + cap = find_cap(bus, slot, func, PCI_CAP_ID_AGP); if (!cap) break; *valid_agp = 1; - return read_agp(num, slot, func, cap, + return read_agp(bus, slot, func, cap, order); } /* No multi-function device? */ - type = read_pci_config_byte(num, slot, func, + type = read_pci_config_byte(bus, slot, func, PCI_HEADER_TYPE); if (!(type & 0x80)) break; @@ -249,36 +271,50 @@ void __init early_gart_iommu_check(void) * or BIOS forget to put that in reserved. * try to update e820 to make that region as reserved. */ - int fix, num; + int i, fix, slot; u32 ctl; u32 aper_size = 0, aper_order = 0, last_aper_order = 0; u64 aper_base = 0, last_aper_base = 0; - int aper_enabled = 0, last_aper_enabled = 0; + int aper_enabled = 0, last_aper_enabled = 0, last_valid = 0; if (!early_pci_allowed()) return; + /* This is mostly duplicate of iommu_hole_init */ fix = 0; - for (num = 24; num < 32; num++) { - if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00))) - continue; - - ctl = read_pci_config(0, num, 3, 0x90); - aper_enabled = ctl & 1; - aper_order = (ctl >> 1) & 7; - aper_size = (32 * 1024 * 1024) << aper_order; - aper_base = read_pci_config(0, num, 3, 0x94) & 0x7fff; - aper_base <<= 25; - - if ((last_aper_order && aper_order != last_aper_order) || - (last_aper_base && aper_base != last_aper_base) || - (last_aper_enabled && aper_enabled != last_aper_enabled)) { - fix = 1; - break; + for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) { + int bus; + int dev_base, dev_limit; + + bus = bus_dev_ranges[i].bus; + dev_base = bus_dev_ranges[i].dev_base; + dev_limit = bus_dev_ranges[i].dev_limit; + + for (slot = dev_base; slot < dev_limit; slot++) { + if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00))) + continue; + + ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL); + aper_enabled = ctl & AMD64_GARTEN; + aper_order = (ctl >> 1) & 7; + aper_size = (32 * 1024 * 1024) << aper_order; + aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 0x7fff; + aper_base <<= 25; + + if (last_valid) { + if ((aper_order != last_aper_order) || + (aper_base != last_aper_base) || + (aper_enabled != last_aper_enabled)) { + fix = 1; + break; + } + } + + last_aper_order = aper_order; + last_aper_base = aper_base; + last_aper_enabled = aper_enabled; + last_valid = 1; } - last_aper_order = aper_order; - last_aper_base = aper_base; - last_aper_enabled = aper_enabled; } if (!fix && !aper_enabled) @@ -290,32 +326,46 @@ void __init early_gart_iommu_check(void) if (gart_fix_e820 && !fix && aper_enabled) { if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) { - /* reserved it, so we can resuse it in second kernel */ + /* reserve it, so we can reuse it in second kernel */ printk(KERN_INFO "update e820 for GART\n"); - add_memory_region(aper_base, aper_size, E820_RESERVED); + e820_add_region(aper_base, aper_size, E820_RESERVED); update_e820(); } - return; } + if (!fix) + return; + /* different nodes have different setting, disable them all at first*/ - for (num = 24; num < 32; num++) { - if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00))) - continue; + for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) { + int bus; + int dev_base, dev_limit; + + bus = bus_dev_ranges[i].bus; + dev_base = bus_dev_ranges[i].dev_base; + dev_limit = bus_dev_ranges[i].dev_limit; + + for (slot = dev_base; slot < dev_limit; slot++) { + if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00))) + continue; - ctl = read_pci_config(0, num, 3, 0x90); - ctl &= ~1; - write_pci_config(0, num, 3, 0x90, ctl); + ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL); + ctl &= ~AMD64_GARTEN; + write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl); + } } } +static int __initdata printed_gart_size_msg; + void __init gart_iommu_hole_init(void) { + u32 agp_aper_base = 0, agp_aper_order = 0; u32 aper_size, aper_alloc = 0, aper_order = 0, last_aper_order = 0; u64 aper_base, last_aper_base = 0; - int fix, num, valid_agp = 0; - int node; + int fix, slot, valid_agp = 0; + int i, node; if (gart_iommu_aperture_disabled || !fix_aperture || !early_pci_allowed()) @@ -323,38 +373,65 @@ void __init gart_iommu_hole_init(void) printk(KERN_INFO "Checking aperture...\n"); + if (!fallback_aper_force) + agp_aper_base = search_agp_bridge(&agp_aper_order, &valid_agp); + fix = 0; node = 0; - for (num = 24; num < 32; num++) { - if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00))) - continue; - - iommu_detected = 1; - gart_iommu_aperture = 1; - - aper_order = (read_pci_config(0, num, 3, 0x90) >> 1) & 7; - aper_size = (32 * 1024 * 1024) << aper_order; - aper_base = read_pci_config(0, num, 3, 0x94) & 0x7fff; - aper_base <<= 25; - - printk(KERN_INFO "Node %d: aperture @ %Lx size %u MB\n", - node, aper_base, aper_size >> 20); - node++; - - if (!aperture_valid(aper_base, aper_size)) { - fix = 1; - break; - } + for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) { + int bus; + int dev_base, dev_limit; + + bus = bus_dev_ranges[i].bus; + dev_base = bus_dev_ranges[i].dev_base; + dev_limit = bus_dev_ranges[i].dev_limit; + + for (slot = dev_base; slot < dev_limit; slot++) { + if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00))) + continue; + + iommu_detected = 1; + gart_iommu_aperture = 1; + + aper_order = (read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL) >> 1) & 7; + aper_size = (32 * 1024 * 1024) << aper_order; + aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 0x7fff; + aper_base <<= 25; + + printk(KERN_INFO "Node %d: aperture @ %Lx size %u MB\n", + node, aper_base, aper_size >> 20); + node++; + + if (!aperture_valid(aper_base, aper_size, 64<<20)) { + if (valid_agp && agp_aper_base && + agp_aper_base == aper_base && + agp_aper_order == aper_order) { + /* the same between two setting from NB and agp */ + if (!no_iommu && + max_pfn > MAX_DMA32_PFN && + !printed_gart_size_msg) { + printk(KERN_ERR "you are using iommu with agp, but GART size is less than 64M\n"); + printk(KERN_ERR "please increase GART size in your BIOS setup\n"); + printk(KERN_ERR "if BIOS doesn't have that option, contact your HW vendor!\n"); + printed_gart_size_msg = 1; + } + } else { + fix = 1; + goto out; + } + } - if ((last_aper_order && aper_order != last_aper_order) || - (last_aper_base && aper_base != last_aper_base)) { - fix = 1; - break; + if ((last_aper_order && aper_order != last_aper_order) || + (last_aper_base && aper_base != last_aper_base)) { + fix = 1; + goto out; + } + last_aper_order = aper_order; + last_aper_base = aper_base; } - last_aper_order = aper_order; - last_aper_base = aper_base; } +out: if (!fix && !fallback_aper_force) { if (last_aper_base) { unsigned long n = (32 * 1024 * 1024) << last_aper_order; @@ -364,14 +441,16 @@ void __init gart_iommu_hole_init(void) return; } - if (!fallback_aper_force) - aper_alloc = search_agp_bridge(&aper_order, &valid_agp); + if (!fallback_aper_force) { + aper_alloc = agp_aper_base; + aper_order = agp_aper_order; + } if (aper_alloc) { /* Got the aperture from the AGP bridge */ } else if (swiotlb && !valid_agp) { /* Do nothing */ - } else if ((!no_iommu && end_pfn > MAX_DMA32_PFN) || + } else if ((!no_iommu && max_pfn > MAX_DMA32_PFN) || force_iommu || valid_agp || fallback_aper_force) { @@ -401,16 +480,24 @@ void __init gart_iommu_hole_init(void) } /* Fix up the north bridges */ - for (num = 24; num < 32; num++) { - if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00))) - continue; - - /* - * Don't enable translation yet. That is done later. - * Assume this BIOS didn't initialise the GART so - * just overwrite all previous bits - */ - write_pci_config(0, num, 3, 0x90, aper_order<<1); - write_pci_config(0, num, 3, 0x94, aper_alloc>>25); + for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) { + int bus; + int dev_base, dev_limit; + + bus = bus_dev_ranges[i].bus; + dev_base = bus_dev_ranges[i].dev_base; + dev_limit = bus_dev_ranges[i].dev_limit; + for (slot = dev_base; slot < dev_limit; slot++) { + if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00))) + continue; + + /* Don't enable translation yet. That is done later. + Assume this BIOS didn't initialise the GART so + just overwrite all previous bits */ + write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, aper_order << 1); + write_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE, aper_alloc >> 25); + } } + + set_up_gart_resume(aper_order, aper_alloc); } diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c index 4b99b1bdeb6c..a437d027f20b 100644 --- a/arch/x86/kernel/apic_32.c +++ b/arch/x86/kernel/apic_32.c @@ -52,30 +52,41 @@ unsigned long mp_lapic_addr; -DEFINE_PER_CPU(u16, x86_bios_cpu_apicid) = BAD_APICID; -EXPORT_PER_CPU_SYMBOL(x86_bios_cpu_apicid); - /* * Knob to control our willingness to enable the local APIC. * - * -1=force-disable, +1=force-enable + * +1=force-enable */ -static int enable_local_apic __initdata; +static int force_enable_local_apic; +int disable_apic; /* Local APIC timer verification ok */ static int local_apic_timer_verify_ok; -/* Disable local APIC timer from the kernel commandline or via dmi quirk - or using CPU MSR check */ -int local_apic_timer_disabled; +/* Disable local APIC timer from the kernel commandline or via dmi quirk */ +static int local_apic_timer_disabled; /* Local APIC timer works in C2 */ int local_apic_timer_c2_ok; EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok); +int first_system_vector = 0xfe; + +char system_vectors[NR_VECTORS] = { [0 ... NR_VECTORS-1] = SYS_VECTOR_FREE}; + /* * Debug level, exported for io_apic.c */ int apic_verbosity; +int pic_mode; + +/* Have we found an MP table */ +int smp_found_config; + +static struct resource lapic_resource = { + .name = "Local APIC", + .flags = IORESOURCE_MEM | IORESOURCE_BUSY, +}; + static unsigned int calibration_result; static int lapic_next_event(unsigned long delta, @@ -545,7 +556,7 @@ void __init setup_boot_APIC_clock(void) lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY; else printk(KERN_WARNING "APIC timer registered as dummy," - " due to nmi_watchdog=1!\n"); + " due to nmi_watchdog=%d!\n", nmi_watchdog); } /* Setup the lapic or request the broadcast */ @@ -963,7 +974,7 @@ void __cpuinit setup_local_APIC(void) * Double-check whether this APIC is really registered. */ if (!apic_id_registered()) - BUG(); + WARN_ON_ONCE(1); /* * Intel recommends to set DFR, LDR and TPR before enabling @@ -1094,7 +1105,7 @@ static int __init detect_init_APIC(void) u32 h, l, features; /* Disabled by kernel option? */ - if (enable_local_apic < 0) + if (disable_apic) return -1; switch (boot_cpu_data.x86_vendor) { @@ -1117,7 +1128,7 @@ static int __init detect_init_APIC(void) * Over-ride BIOS and try to enable the local APIC only if * "lapic" specified. */ - if (enable_local_apic <= 0) { + if (!force_enable_local_apic) { printk(KERN_INFO "Local APIC disabled by BIOS -- " "you can enable it with \"lapic\"\n"); return -1; @@ -1154,9 +1165,6 @@ static int __init detect_init_APIC(void) if (l & MSR_IA32_APICBASE_ENABLE) mp_lapic_addr = l & MSR_IA32_APICBASE_BASE; - if (nmi_watchdog != NMI_NONE && nmi_watchdog != NMI_DISABLED) - nmi_watchdog = NMI_LOCAL_APIC; - printk(KERN_INFO "Found and enabled local APIC!\n"); apic_pm_activate(); @@ -1195,36 +1203,6 @@ void __init init_apic_mappings(void) if (boot_cpu_physical_apicid == -1U) boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id()); -#ifdef CONFIG_X86_IO_APIC - { - unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0; - int i; - - for (i = 0; i < nr_ioapics; i++) { - if (smp_found_config) { - ioapic_phys = mp_ioapics[i].mpc_apicaddr; - if (!ioapic_phys) { - printk(KERN_ERR - "WARNING: bogus zero IO-APIC " - "address found in MPTABLE, " - "disabling IO/APIC support!\n"); - smp_found_config = 0; - skip_ioapic_setup = 1; - goto fake_ioapic_page; - } - } else { -fake_ioapic_page: - ioapic_phys = (unsigned long) - alloc_bootmem_pages(PAGE_SIZE); - ioapic_phys = __pa(ioapic_phys); - } - set_fixmap_nocache(idx, ioapic_phys); - printk(KERN_DEBUG "mapped IOAPIC to %08lx (%08lx)\n", - __fix_to_virt(idx), ioapic_phys); - idx++; - } - } -#endif } /* @@ -1236,7 +1214,7 @@ int apic_version[MAX_APICS]; int __init APIC_init_uniprocessor(void) { - if (enable_local_apic < 0) + if (disable_apic) clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC); if (!smp_found_config && !cpu_has_apic) @@ -1265,10 +1243,14 @@ int __init APIC_init_uniprocessor(void) #ifdef CONFIG_CRASH_DUMP boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id()); #endif - phys_cpu_present_map = physid_mask_of_physid(boot_cpu_physical_apicid); + physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map); setup_local_APIC(); +#ifdef CONFIG_X86_IO_APIC + if (!smp_found_config || skip_ioapic_setup || !nr_ioapics) +#endif + localise_nmi_watchdog(); end_local_APIC_setup(); #ifdef CONFIG_X86_IO_APIC if (smp_found_config) @@ -1351,13 +1333,17 @@ void __init smp_intr_init(void) * The reschedule interrupt is a CPU-to-CPU reschedule-helper * IPI, driven by wakeup. */ - set_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt); + alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt); /* IPI for invalidation */ - set_intr_gate(INVALIDATE_TLB_VECTOR, invalidate_interrupt); + alloc_intr_gate(INVALIDATE_TLB_VECTOR, invalidate_interrupt); /* IPI for generic function call */ - set_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt); + alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt); + + /* IPI for single call function */ + set_intr_gate(CALL_FUNCTION_SINGLE_VECTOR, + call_function_single_interrupt); } #endif @@ -1370,15 +1356,15 @@ void __init apic_intr_init(void) smp_intr_init(); #endif /* self generated IPI for local APIC timer */ - set_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt); + alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt); /* IPI vectors for APIC spurious and error interrupts */ - set_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt); - set_intr_gate(ERROR_APIC_VECTOR, error_interrupt); + alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt); + alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt); /* thermal monitor LVT interrupt */ #ifdef CONFIG_X86_MCE_P4THERMAL - set_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt); + alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt); #endif } @@ -1513,6 +1499,9 @@ void __cpuinit generic_processor_info(int apicid, int version) */ cpu = 0; + if (apicid > max_physical_apicid) + max_physical_apicid = apicid; + /* * Would be preferable to switch to bigsmp when CONFIG_HOTPLUG_CPU=y * but we need to work other dependencies like SMP_SUSPEND etc @@ -1520,7 +1509,7 @@ void __cpuinit generic_processor_info(int apicid, int version) * if (CPU_HOTPLUG_ENABLED || num_processors > 8) * - Ashok Raj <ashok.raj@intel.com> */ - if (num_processors > 8) { + if (max_physical_apicid >= 8) { switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_INTEL: if (!APIC_XAPIC(version)) { @@ -1534,9 +1523,9 @@ void __cpuinit generic_processor_info(int apicid, int version) } #ifdef CONFIG_SMP /* are we being called early in kernel startup? */ - if (x86_cpu_to_apicid_early_ptr) { - u16 *cpu_to_apicid = x86_cpu_to_apicid_early_ptr; - u16 *bios_cpu_apicid = x86_bios_cpu_apicid_early_ptr; + if (early_per_cpu_ptr(x86_cpu_to_apicid)) { + u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid); + u16 *bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid); cpu_to_apicid[cpu] = apicid; bios_cpu_apicid[cpu] = apicid; @@ -1703,14 +1692,14 @@ static void apic_pm_activate(void) { } */ static int __init parse_lapic(char *arg) { - enable_local_apic = 1; + force_enable_local_apic = 1; return 0; } early_param("lapic", parse_lapic); static int __init parse_nolapic(char *arg) { - enable_local_apic = -1; + disable_apic = 1; clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC); return 0; } @@ -1740,3 +1729,21 @@ static int __init apic_set_verbosity(char *str) } __setup("apic=", apic_set_verbosity); +static int __init lapic_insert_resource(void) +{ + if (!apic_phys) + return -1; + + /* Put local APIC into the resource map. */ + lapic_resource.start = apic_phys; + lapic_resource.end = lapic_resource.start + PAGE_SIZE - 1; + insert_resource(&iomem_resource, &lapic_resource); + + return 0; +} + +/* + * need call insert after e820_reserve_resources() + * that is using request_resource + */ +late_initcall(lapic_insert_resource); diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c index 0633cfd0dc29..1e3d32e27c14 100644 --- a/arch/x86/kernel/apic_64.c +++ b/arch/x86/kernel/apic_64.c @@ -43,7 +43,7 @@ #include <mach_ipi.h> #include <mach_apic.h> -int disable_apic_timer __cpuinitdata; +static int disable_apic_timer __cpuinitdata; static int apic_calibrate_pmtmr __initdata; int disable_apic; @@ -56,6 +56,9 @@ EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok); */ int apic_verbosity; +/* Have we found an MP table */ +int smp_found_config; + static struct resource lapic_resource = { .name = "Local APIC", .flags = IORESOURCE_MEM | IORESOURCE_BUSY, @@ -87,9 +90,6 @@ static unsigned long apic_phys; unsigned long mp_lapic_addr; -DEFINE_PER_CPU(u16, x86_bios_cpu_apicid) = BAD_APICID; -EXPORT_PER_CPU_SYMBOL(x86_bios_cpu_apicid); - unsigned int __cpuinitdata maxcpus = NR_CPUS; /* * Get the LAPIC version @@ -417,37 +417,13 @@ void __init setup_boot_APIC_clock(void) lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY; else printk(KERN_WARNING "APIC timer registered as dummy," - " due to nmi_watchdog=1!\n"); + " due to nmi_watchdog=%d!\n", nmi_watchdog); setup_APIC_timer(); } -/* - * AMD C1E enabled CPUs have a real nasty problem: Some BIOSes set the - * C1E flag only in the secondary CPU, so when we detect the wreckage - * we already have enabled the boot CPU local apic timer. Check, if - * disable_apic_timer is set and the DUMMY flag is cleared. If yes, - * set the DUMMY flag again and force the broadcast mode in the - * clockevents layer. - */ -static void __cpuinit check_boot_apic_timer_broadcast(void) -{ - if (!disable_apic_timer || - (lapic_clockevent.features & CLOCK_EVT_FEAT_DUMMY)) - return; - - printk(KERN_INFO "AMD C1E detected late. Force timer broadcast.\n"); - lapic_clockevent.features |= CLOCK_EVT_FEAT_DUMMY; - - local_irq_enable(); - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE, - &boot_cpu_physical_apicid); - local_irq_disable(); -} - void __cpuinit setup_secondary_APIC_clock(void) { - check_boot_apic_timer_broadcast(); setup_APIC_timer(); } @@ -850,7 +826,6 @@ static void __cpuinit lapic_setup_esr(void) void __cpuinit end_local_APIC_setup(void) { lapic_setup_esr(); - nmi_watchdog_default(); setup_apic_nmi_watchdog(NULL); apic_pm_activate(); } @@ -875,7 +850,7 @@ static int __init detect_init_APIC(void) void __init early_init_lapic_mapping(void) { - unsigned long apic_phys; + unsigned long phys_addr; /* * If no local APIC can be found then go out @@ -884,11 +859,11 @@ void __init early_init_lapic_mapping(void) if (!smp_found_config) return; - apic_phys = mp_lapic_addr; + phys_addr = mp_lapic_addr; - set_fixmap_nocache(FIX_APIC_BASE, apic_phys); + set_fixmap_nocache(FIX_APIC_BASE, phys_addr); apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n", - APIC_BASE, apic_phys); + APIC_BASE, phys_addr); /* * Fetch the APIC ID of the BSP in case we have a @@ -942,7 +917,9 @@ int __init APIC_init_uniprocessor(void) verify_local_APIC(); - phys_cpu_present_map = physid_mask_of_physid(boot_cpu_physical_apicid); + connect_bsp_APIC(); + + physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map); apic_write(APIC_ID, SET_APIC_ID(boot_cpu_physical_apicid)); setup_local_APIC(); @@ -954,6 +931,8 @@ int __init APIC_init_uniprocessor(void) if (!skip_ioapic_setup && nr_ioapics) enable_IO_APIC(); + if (!smp_found_config || skip_ioapic_setup || !nr_ioapics) + localise_nmi_watchdog(); end_local_APIC_setup(); if (smp_found_config && !skip_ioapic_setup && nr_ioapics) @@ -1021,6 +1000,14 @@ asmlinkage void smp_error_interrupt(void) irq_exit(); } +/** + * * connect_bsp_APIC - attach the APIC to the interrupt system + * */ +void __init connect_bsp_APIC(void) +{ + enable_apic_mode(); +} + void disconnect_bsp_APIC(int virt_wire_setup) { /* Go back to Virtual Wire compatibility mode */ @@ -1090,10 +1077,13 @@ void __cpuinit generic_processor_info(int apicid, int version) */ cpu = 0; } + if (apicid > max_physical_apicid) + max_physical_apicid = apicid; + /* are we being called early in kernel startup? */ - if (x86_cpu_to_apicid_early_ptr) { - u16 *cpu_to_apicid = x86_cpu_to_apicid_early_ptr; - u16 *bios_cpu_apicid = x86_bios_cpu_apicid_early_ptr; + if (early_per_cpu_ptr(x86_cpu_to_apicid)) { + u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid); + u16 *bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid); cpu_to_apicid[cpu] = apicid; bios_cpu_apicid[cpu] = apicid; @@ -1269,7 +1259,7 @@ __cpuinit int apic_is_clustered_box(void) if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && !is_vsmp_box()) return 0; - bios_cpu_apicid = x86_bios_cpu_apicid_early_ptr; + bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid); bitmap_zero(clustermap, NUM_APIC_CLUSTERS); for (i = 0; i < NR_CPUS; i++) { diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index bf9290e29013..bf9b441331e9 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -204,6 +204,7 @@ #include <linux/module.h> #include <linux/poll.h> +#include <linux/smp_lock.h> #include <linux/types.h> #include <linux/stddef.h> #include <linux/timer.h> @@ -228,6 +229,7 @@ #include <linux/suspend.h> #include <linux/kthread.h> #include <linux/jiffies.h> +#include <linux/smp_lock.h> #include <asm/system.h> #include <asm/uaccess.h> @@ -1149,7 +1151,7 @@ static void queue_event(apm_event_t event, struct apm_user *sender) as->event_tail = 0; } as->events[as->event_head] = event; - if ((!as->suser) || (!as->writer)) + if (!as->suser || !as->writer) continue; switch (event) { case APM_SYS_SUSPEND: @@ -1211,9 +1213,9 @@ static int suspend(int vetoable) if (err != APM_SUCCESS) apm_error("suspend", err); err = (err == APM_SUCCESS) ? 0 : -EIO; - device_power_up(); + device_power_up(PMSG_RESUME); local_irq_enable(); - device_resume(); + device_resume(PMSG_RESUME); queue_event(APM_NORMAL_RESUME, NULL); spin_lock(&user_list_lock); for (as = user_list; as != NULL; as = as->next) { @@ -1238,7 +1240,7 @@ static void standby(void) apm_error("standby", err); local_irq_disable(); - device_power_up(); + device_power_up(PMSG_RESUME); local_irq_enable(); } @@ -1324,7 +1326,7 @@ static void check_events(void) ignore_bounce = 1; if ((event != APM_NORMAL_RESUME) || (ignore_normal_resume == 0)) { - device_resume(); + device_resume(PMSG_RESUME); queue_event(event, NULL); } ignore_normal_resume = 0; @@ -1396,7 +1398,7 @@ static void apm_mainloop(void) static int check_apm_user(struct apm_user *as, const char *func) { - if ((as == NULL) || (as->magic != APM_BIOS_MAGIC)) { + if (as == NULL || as->magic != APM_BIOS_MAGIC) { printk(KERN_ERR "apm: %s passed bad filp\n", func); return 1; } @@ -1459,18 +1461,19 @@ static unsigned int do_poll(struct file *fp, poll_table *wait) return 0; } -static int do_ioctl(struct inode *inode, struct file *filp, - u_int cmd, u_long arg) +static long do_ioctl(struct file *filp, u_int cmd, u_long arg) { struct apm_user *as; + int ret; as = filp->private_data; if (check_apm_user(as, "ioctl")) return -EIO; - if ((!as->suser) || (!as->writer)) + if (!as->suser || !as->writer) return -EPERM; switch (cmd) { case APM_IOC_STANDBY: + lock_kernel(); if (as->standbys_read > 0) { as->standbys_read--; as->standbys_pending--; @@ -1479,8 +1482,10 @@ static int do_ioctl(struct inode *inode, struct file *filp, queue_event(APM_USER_STANDBY, as); if (standbys_pending <= 0) standby(); + unlock_kernel(); break; case APM_IOC_SUSPEND: + lock_kernel(); if (as->suspends_read > 0) { as->suspends_read--; as->suspends_pending--; @@ -1488,16 +1493,17 @@ static int do_ioctl(struct inode *inode, struct file *filp, } else queue_event(APM_USER_SUSPEND, as); if (suspends_pending <= 0) { - return suspend(1); + ret = suspend(1); } else { as->suspend_wait = 1; wait_event_interruptible(apm_suspend_waitqueue, as->suspend_wait == 0); - return as->suspend_result; + ret = as->suspend_result; } - break; + unlock_kernel(); + return ret; default: - return -EINVAL; + return -ENOTTY; } return 0; } @@ -1544,10 +1550,12 @@ static int do_open(struct inode *inode, struct file *filp) { struct apm_user *as; + lock_kernel(); as = kmalloc(sizeof(*as), GFP_KERNEL); if (as == NULL) { printk(KERN_ERR "apm: cannot allocate struct of size %d bytes\n", sizeof(*as)); + unlock_kernel(); return -ENOMEM; } as->magic = APM_BIOS_MAGIC; @@ -1569,6 +1577,7 @@ static int do_open(struct inode *inode, struct file *filp) user_list = as; spin_unlock(&user_list_lock); filp->private_data = as; + unlock_kernel(); return 0; } @@ -1860,7 +1869,7 @@ static const struct file_operations apm_bios_fops = { .owner = THIS_MODULE, .read = do_read, .poll = do_poll, - .ioctl = do_ioctl, + .unlocked_ioctl = do_ioctl, .open = do_open, .release = do_release, }; diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index 92588083950f..6649d09ad88f 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -111,7 +111,7 @@ void foo(void) OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable); OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable); OFFSET(PV_CPU_iret, pv_cpu_ops, iret); - OFFSET(PV_CPU_irq_enable_syscall_ret, pv_cpu_ops, irq_enable_syscall_ret); + OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit); OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0); #endif diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index f126c05d6170..bacf5deeec2d 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -34,7 +34,7 @@ int main(void) ENTRY(pid); BLANK(); #undef ENTRY -#define ENTRY(entry) DEFINE(threadinfo_ ## entry, offsetof(struct thread_info, entry)) +#define ENTRY(entry) DEFINE(TI_ ## entry, offsetof(struct thread_info, entry)) ENTRY(flags); ENTRY(addr_limit); ENTRY(preempt_count); @@ -61,8 +61,11 @@ int main(void) OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops); OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable); OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable); + OFFSET(PV_IRQ_adjust_exception_frame, pv_irq_ops, adjust_exception_frame); OFFSET(PV_CPU_iret, pv_cpu_ops, iret); - OFFSET(PV_CPU_irq_enable_syscall_ret, pv_cpu_ops, irq_enable_syscall_ret); + OFFSET(PV_CPU_usergs_sysret32, pv_cpu_ops, usergs_sysret32); + OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64); + OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit); OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs); OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2); #endif diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index a0c6f8190887..ee76eaad3001 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -6,11 +6,15 @@ obj-y := intel_cacheinfo.o addon_cpuid_features.o obj-y += proc.o feature_names.o obj-$(CONFIG_X86_32) += common.o bugs.o +obj-$(CONFIG_X86_64) += common_64.o bugs_64.o obj-$(CONFIG_X86_32) += amd.o +obj-$(CONFIG_X86_64) += amd_64.o obj-$(CONFIG_X86_32) += cyrix.o obj-$(CONFIG_X86_32) += centaur.o +obj-$(CONFIG_X86_64) += centaur_64.o obj-$(CONFIG_X86_32) += transmeta.o obj-$(CONFIG_X86_32) += intel.o +obj-$(CONFIG_X86_64) += intel_64.o obj-$(CONFIG_X86_32) += umc.o obj-$(CONFIG_X86_MCE) += mcheck/ diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c index c2e1ce33c7cb..84a8220a6072 100644 --- a/arch/x86/kernel/cpu/addon_cpuid_features.c +++ b/arch/x86/kernel/cpu/addon_cpuid_features.c @@ -1,9 +1,7 @@ - /* * Routines to indentify additional cpu features that are scattered in * cpuid space. */ - #include <linux/cpu.h> #include <asm/pat.h> @@ -53,19 +51,20 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_PAT void __cpuinit validate_pat_support(struct cpuinfo_x86 *c) { + if (!cpu_has_pat) + pat_disable("PAT not supported by CPU."); + switch (c->x86_vendor) { - case X86_VENDOR_AMD: - if (c->x86 >= 0xf && c->x86 <= 0x11) - return; - break; case X86_VENDOR_INTEL: if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15)) return; break; + case X86_VENDOR_AMD: + case X86_VENDOR_CENTAUR: + case X86_VENDOR_TRANSMETA: + return; } - pat_disable(cpu_has_pat ? - "PAT disabled. Not yet verified on this CPU type." : - "PAT not supported by CPU."); + pat_disable("PAT disabled. Not yet verified on this CPU type."); } #endif diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 245866828294..81a07ca65d44 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -24,43 +24,6 @@ extern void vide(void); __asm__(".align 4\nvide: ret"); -#ifdef CONFIG_X86_LOCAL_APIC -#define ENABLE_C1E_MASK 0x18000000 -#define CPUID_PROCESSOR_SIGNATURE 1 -#define CPUID_XFAM 0x0ff00000 -#define CPUID_XFAM_K8 0x00000000 -#define CPUID_XFAM_10H 0x00100000 -#define CPUID_XFAM_11H 0x00200000 -#define CPUID_XMOD 0x000f0000 -#define CPUID_XMOD_REV_F 0x00040000 - -/* AMD systems with C1E don't have a working lAPIC timer. Check for that. */ -static __cpuinit int amd_apic_timer_broken(void) -{ - u32 lo, hi; - u32 eax = cpuid_eax(CPUID_PROCESSOR_SIGNATURE); - switch (eax & CPUID_XFAM) { - case CPUID_XFAM_K8: - if ((eax & CPUID_XMOD) < CPUID_XMOD_REV_F) - break; - case CPUID_XFAM_10H: - case CPUID_XFAM_11H: - rdmsr(MSR_K8_ENABLE_C1E, lo, hi); - if (lo & ENABLE_C1E_MASK) { - if (smp_processor_id() != boot_cpu_physical_apicid) - printk(KERN_INFO "AMD C1E detected late. " - " Force timer broadcast.\n"); - return 1; - } - break; - default: - /* err on the side of caution */ - return 1; - } - return 0; -} -#endif - int force_mwait __cpuinitdata; static void __cpuinit early_init_amd(struct cpuinfo_x86 *c) @@ -297,11 +260,6 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) num_cache_leaves = 3; } -#ifdef CONFIG_X86_LOCAL_APIC - if (amd_apic_timer_broken()) - local_apic_timer_disabled = 1; -#endif - /* K6s reports MCEs but don't actually have all the MSRs */ if (c->x86 < 6) clear_cpu_cap(c, X86_FEATURE_MCE); diff --git a/arch/x86/kernel/cpu/amd_64.c b/arch/x86/kernel/cpu/amd_64.c new file mode 100644 index 000000000000..7c36fb8a28d4 --- /dev/null +++ b/arch/x86/kernel/cpu/amd_64.c @@ -0,0 +1,222 @@ +#include <linux/init.h> +#include <linux/mm.h> + +#include <asm/numa_64.h> +#include <asm/mmconfig.h> +#include <asm/cacheflush.h> + +#include <mach_apic.h> + +#include "cpu.h" + +int force_mwait __cpuinitdata; + +#ifdef CONFIG_NUMA +static int __cpuinit nearby_node(int apicid) +{ + int i, node; + + for (i = apicid - 1; i >= 0; i--) { + node = apicid_to_node[i]; + if (node != NUMA_NO_NODE && node_online(node)) + return node; + } + for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) { + node = apicid_to_node[i]; + if (node != NUMA_NO_NODE && node_online(node)) + return node; + } + return first_node(node_online_map); /* Shouldn't happen */ +} +#endif + +/* + * On a AMD dual core setup the lower bits of the APIC id distingush the cores. + * Assumes number of cores is a power of two. + */ +static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_SMP + unsigned bits; +#ifdef CONFIG_NUMA + int cpu = smp_processor_id(); + int node = 0; + unsigned apicid = hard_smp_processor_id(); +#endif + bits = c->x86_coreid_bits; + + /* Low order bits define the core id (index of core in socket) */ + c->cpu_core_id = c->initial_apicid & ((1 << bits)-1); + /* Convert the initial APIC ID into the socket ID */ + c->phys_proc_id = c->initial_apicid >> bits; + +#ifdef CONFIG_NUMA + node = c->phys_proc_id; + if (apicid_to_node[apicid] != NUMA_NO_NODE) + node = apicid_to_node[apicid]; + if (!node_online(node)) { + /* Two possibilities here: + - The CPU is missing memory and no node was created. + In that case try picking one from a nearby CPU + - The APIC IDs differ from the HyperTransport node IDs + which the K8 northbridge parsing fills in. + Assume they are all increased by a constant offset, + but in the same order as the HT nodeids. + If that doesn't result in a usable node fall back to the + path for the previous case. */ + + int ht_nodeid = c->initial_apicid; + + if (ht_nodeid >= 0 && + apicid_to_node[ht_nodeid] != NUMA_NO_NODE) + node = apicid_to_node[ht_nodeid]; + /* Pick a nearby node */ + if (!node_online(node)) + node = nearby_node(apicid); + } + numa_set_node(cpu, node); + + printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node); +#endif +#endif +} + +static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_SMP + unsigned bits, ecx; + + /* Multi core CPU? */ + if (c->extended_cpuid_level < 0x80000008) + return; + + ecx = cpuid_ecx(0x80000008); + + c->x86_max_cores = (ecx & 0xff) + 1; + + /* CPU telling us the core id bits shift? */ + bits = (ecx >> 12) & 0xF; + + /* Otherwise recompute */ + if (bits == 0) { + while ((1 << bits) < c->x86_max_cores) + bits++; + } + + c->x86_coreid_bits = bits; + +#endif +} + +static void __cpuinit early_init_amd(struct cpuinfo_x86 *c) +{ + early_init_amd_mc(c); + + /* c->x86_power is 8000_0007 edx. Bit 8 is constant TSC */ + if (c->x86_power & (1<<8)) + set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); +} + +static void __cpuinit init_amd(struct cpuinfo_x86 *c) +{ + unsigned level; + +#ifdef CONFIG_SMP + unsigned long value; + + /* + * Disable TLB flush filter by setting HWCR.FFDIS on K8 + * bit 6 of msr C001_0015 + * + * Errata 63 for SH-B3 steppings + * Errata 122 for all steppings (F+ have it disabled by default) + */ + if (c->x86 == 0xf) { + rdmsrl(MSR_K8_HWCR, value); + value |= 1 << 6; + wrmsrl(MSR_K8_HWCR, value); + } +#endif + + /* Bit 31 in normal CPUID used for nonstandard 3DNow ID; + 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */ + clear_cpu_cap(c, 0*32+31); + + /* On C+ stepping K8 rep microcode works well for copy/memset */ + if (c->x86 == 0xf) { + level = cpuid_eax(1); + if((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58) + set_cpu_cap(c, X86_FEATURE_REP_GOOD); + } + if (c->x86 == 0x10 || c->x86 == 0x11) + set_cpu_cap(c, X86_FEATURE_REP_GOOD); + + /* Enable workaround for FXSAVE leak */ + if (c->x86 >= 6) + set_cpu_cap(c, X86_FEATURE_FXSAVE_LEAK); + + level = get_model_name(c); + if (!level) { + switch (c->x86) { + case 0xf: + /* Should distinguish Models here, but this is only + a fallback anyways. */ + strcpy(c->x86_model_id, "Hammer"); + break; + } + } + display_cacheinfo(c); + + /* Multi core CPU? */ + if (c->extended_cpuid_level >= 0x80000008) + amd_detect_cmp(c); + + if (c->extended_cpuid_level >= 0x80000006 && + (cpuid_edx(0x80000006) & 0xf000)) + num_cache_leaves = 4; + else + num_cache_leaves = 3; + + if (c->x86 >= 0xf && c->x86 <= 0x11) + set_cpu_cap(c, X86_FEATURE_K8); + + /* MFENCE stops RDTSC speculation */ + set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); + + if (c->x86 == 0x10) { + /* do this for boot cpu */ + if (c == &boot_cpu_data) + check_enable_amd_mmconf_dmi(); + + fam10h_check_enable_mmcfg(); + } + + if (c == &boot_cpu_data && c->x86 >= 0xf && c->x86 <= 0x11) { + unsigned long long tseg; + + /* + * Split up direct mapping around the TSEG SMM area. + * Don't do it for gbpages because there seems very little + * benefit in doing so. + */ + if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) { + printk(KERN_DEBUG "tseg: %010llx\n", tseg); + if ((tseg>>PMD_SHIFT) < + (max_low_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) || + ((tseg>>PMD_SHIFT) < + (max_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) && + (tseg>>PMD_SHIFT) >= (1ULL<<(32 - PMD_SHIFT)))) + set_memory_4k((unsigned long)__va(tseg), 1); + } + } +} + +static struct cpu_dev amd_cpu_dev __cpuinitdata = { + .c_vendor = "AMD", + .c_ident = { "AuthenticAMD" }, + .c_early_init = early_init_amd, + .c_init = init_amd, +}; + +cpu_vendor_dev_register(X86_VENDOR_AMD, &amd_cpu_dev); + diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 170d2f5523b2..1b1c56bb338f 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -59,8 +59,12 @@ static void __init check_fpu(void) return; } -/* trap_init() enabled FXSR and company _before_ testing for FP problems here. */ - /* Test for the divl bug.. */ + /* + * trap_init() enabled FXSR and company _before_ testing for FP + * problems here. + * + * Test for the divl bug.. + */ __asm__("fninit\n\t" "fldl %1\n\t" "fdivl %2\n\t" @@ -108,10 +112,15 @@ static void __init check_popad(void) "movl $12345678,%%eax; movl $0,%%edi; pusha; popa; movl (%%edx,%%edi),%%ecx " : "=&a" (res) : "d" (inp) - : "ecx", "edi" ); - /* If this fails, it means that any user program may lock the CPU hard. Too bad. */ - if (res != 12345678) printk( "Buggy.\n" ); - else printk( "OK.\n" ); + : "ecx", "edi"); + /* + * If this fails, it means that any user program may lock the + * CPU hard. Too bad. + */ + if (res != 12345678) + printk("Buggy.\n"); + else + printk("OK.\n"); #endif } @@ -137,7 +146,8 @@ static void __init check_config(void) * i486+ only features! (WP works in supervisor mode and the * new "invlpg" and "bswap" instructions) */ -#if defined(CONFIG_X86_WP_WORKS_OK) || defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_BSWAP) +#if defined(CONFIG_X86_WP_WORKS_OK) || defined(CONFIG_X86_INVLPG) || \ + defined(CONFIG_X86_BSWAP) if (boot_cpu_data.x86 == 3) panic("Kernel requires i486+ for 'invlpg' and other features"); #endif @@ -170,6 +180,7 @@ void __init check_bugs(void) check_fpu(); check_hlt(); check_popad(); - init_utsname()->machine[1] = '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); + init_utsname()->machine[1] = + '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); alternative_instructions(); } diff --git a/arch/x86/kernel/bugs_64.c b/arch/x86/kernel/cpu/bugs_64.c index 9a3ed0649d4e..9a3ed0649d4e 100644 --- a/arch/x86/kernel/bugs_64.c +++ b/arch/x86/kernel/cpu/bugs_64.c diff --git a/arch/x86/kernel/cpu/centaur_64.c b/arch/x86/kernel/cpu/centaur_64.c new file mode 100644 index 000000000000..1d181c40e2e1 --- /dev/null +++ b/arch/x86/kernel/cpu/centaur_64.c @@ -0,0 +1,35 @@ +#include <linux/init.h> +#include <linux/smp.h> + +#include <asm/cpufeature.h> +#include <asm/processor.h> + +#include "cpu.h" + +static void __cpuinit early_init_centaur(struct cpuinfo_x86 *c) +{ + if (c->x86 == 0x6 && c->x86_model >= 0xf) + set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); + + set_cpu_cap(c, X86_FEATURE_SYSENTER32); +} + +static void __cpuinit init_centaur(struct cpuinfo_x86 *c) +{ + if (c->x86 == 0x6 && c->x86_model >= 0xf) { + c->x86_cache_alignment = c->x86_clflush_size * 2; + set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); + set_cpu_cap(c, X86_FEATURE_REP_GOOD); + } + set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); +} + +static struct cpu_dev centaur_cpu_dev __cpuinitdata = { + .c_vendor = "Centaur", + .c_ident = { "CentaurHauls" }, + .c_early_init = early_init_centaur, + .c_init = init_centaur, +}; + +cpu_vendor_dev_register(X86_VENDOR_CENTAUR, ¢aur_cpu_dev); + diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index d0463a946247..80ab20d4fa39 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -427,7 +427,7 @@ __setup("serialnumber", x86_serial_nr_setup); /* * This does the hard work of actually picking apart the CPU stuff... */ -void __cpuinit identify_cpu(struct cpuinfo_x86 *c) +static void __cpuinit identify_cpu(struct cpuinfo_x86 *c) { int i; diff --git a/arch/x86/kernel/cpu/common_64.c b/arch/x86/kernel/cpu/common_64.c new file mode 100644 index 000000000000..7b8cc72feb40 --- /dev/null +++ b/arch/x86/kernel/cpu/common_64.c @@ -0,0 +1,681 @@ +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/string.h> +#include <linux/bootmem.h> +#include <linux/bitops.h> +#include <linux/module.h> +#include <linux/kgdb.h> +#include <linux/topology.h> +#include <linux/string.h> +#include <linux/delay.h> +#include <linux/smp.h> +#include <linux/module.h> +#include <linux/percpu.h> +#include <asm/processor.h> +#include <asm/i387.h> +#include <asm/msr.h> +#include <asm/io.h> +#include <asm/mmu_context.h> +#include <asm/mtrr.h> +#include <asm/mce.h> +#include <asm/pat.h> +#include <asm/numa.h> +#ifdef CONFIG_X86_LOCAL_APIC +#include <asm/mpspec.h> +#include <asm/apic.h> +#include <mach_apic.h> +#endif +#include <asm/pda.h> +#include <asm/pgtable.h> +#include <asm/processor.h> +#include <asm/desc.h> +#include <asm/atomic.h> +#include <asm/proto.h> +#include <asm/sections.h> +#include <asm/setup.h> +#include <asm/genapic.h> + +#include "cpu.h" + +/* We need valid kernel segments for data and code in long mode too + * IRET will check the segment types kkeil 2000/10/28 + * Also sysret mandates a special GDT layout + */ +/* The TLS descriptors are currently at a different place compared to i386. + Hopefully nobody expects them at a fixed place (Wine?) */ +DEFINE_PER_CPU(struct gdt_page, gdt_page) = { .gdt = { + [GDT_ENTRY_KERNEL32_CS] = { { { 0x0000ffff, 0x00cf9b00 } } }, + [GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00af9b00 } } }, + [GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9300 } } }, + [GDT_ENTRY_DEFAULT_USER32_CS] = { { { 0x0000ffff, 0x00cffb00 } } }, + [GDT_ENTRY_DEFAULT_USER_DS] = { { { 0x0000ffff, 0x00cff300 } } }, + [GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00affb00 } } }, +} }; +EXPORT_PER_CPU_SYMBOL_GPL(gdt_page); + +__u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata; + +/* Current gdt points %fs at the "master" per-cpu area: after this, + * it's on the real one. */ +void switch_to_new_gdt(void) +{ + struct desc_ptr gdt_descr; + + gdt_descr.address = (long)get_cpu_gdt_table(smp_processor_id()); + gdt_descr.size = GDT_SIZE - 1; + load_gdt(&gdt_descr); +} + +struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {}; + +static void __cpuinit default_init(struct cpuinfo_x86 *c) +{ + display_cacheinfo(c); +} + +static struct cpu_dev __cpuinitdata default_cpu = { + .c_init = default_init, + .c_vendor = "Unknown", +}; +static struct cpu_dev *this_cpu __cpuinitdata = &default_cpu; + +int __cpuinit get_model_name(struct cpuinfo_x86 *c) +{ + unsigned int *v; + + if (c->extended_cpuid_level < 0x80000004) + return 0; + + v = (unsigned int *) c->x86_model_id; + cpuid(0x80000002, &v[0], &v[1], &v[2], &v[3]); + cpuid(0x80000003, &v[4], &v[5], &v[6], &v[7]); + cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]); + c->x86_model_id[48] = 0; + return 1; +} + + +void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c) +{ + unsigned int n, dummy, ebx, ecx, edx; + + n = c->extended_cpuid_level; + + if (n >= 0x80000005) { + cpuid(0x80000005, &dummy, &ebx, &ecx, &edx); + printk(KERN_INFO "CPU: L1 I Cache: %dK (%d bytes/line), " + "D cache %dK (%d bytes/line)\n", + edx>>24, edx&0xFF, ecx>>24, ecx&0xFF); + c->x86_cache_size = (ecx>>24) + (edx>>24); + /* On K8 L1 TLB is inclusive, so don't count it */ + c->x86_tlbsize = 0; + } + + if (n >= 0x80000006) { + cpuid(0x80000006, &dummy, &ebx, &ecx, &edx); + ecx = cpuid_ecx(0x80000006); + c->x86_cache_size = ecx >> 16; + c->x86_tlbsize += ((ebx >> 16) & 0xfff) + (ebx & 0xfff); + + printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n", + c->x86_cache_size, ecx & 0xFF); + } +} + +void __cpuinit detect_ht(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_SMP + u32 eax, ebx, ecx, edx; + int index_msb, core_bits; + + cpuid(1, &eax, &ebx, &ecx, &edx); + + + if (!cpu_has(c, X86_FEATURE_HT)) + return; + if (cpu_has(c, X86_FEATURE_CMP_LEGACY)) + goto out; + + smp_num_siblings = (ebx & 0xff0000) >> 16; + + if (smp_num_siblings == 1) { + printk(KERN_INFO "CPU: Hyper-Threading is disabled\n"); + } else if (smp_num_siblings > 1) { + + if (smp_num_siblings > NR_CPUS) { + printk(KERN_WARNING "CPU: Unsupported number of " + "siblings %d", smp_num_siblings); + smp_num_siblings = 1; + return; + } + + index_msb = get_count_order(smp_num_siblings); + c->phys_proc_id = phys_pkg_id(index_msb); + + smp_num_siblings = smp_num_siblings / c->x86_max_cores; + + index_msb = get_count_order(smp_num_siblings); + + core_bits = get_count_order(c->x86_max_cores); + + c->cpu_core_id = phys_pkg_id(index_msb) & + ((1 << core_bits) - 1); + } +out: + if ((c->x86_max_cores * smp_num_siblings) > 1) { + printk(KERN_INFO "CPU: Physical Processor ID: %d\n", + c->phys_proc_id); + printk(KERN_INFO "CPU: Processor Core ID: %d\n", + c->cpu_core_id); + } + +#endif +} + +static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c) +{ + char *v = c->x86_vendor_id; + int i; + static int printed; + + for (i = 0; i < X86_VENDOR_NUM; i++) { + if (cpu_devs[i]) { + if (!strcmp(v, cpu_devs[i]->c_ident[0]) || + (cpu_devs[i]->c_ident[1] && + !strcmp(v, cpu_devs[i]->c_ident[1]))) { + c->x86_vendor = i; + this_cpu = cpu_devs[i]; + return; + } + } + } + if (!printed) { + printed++; + printk(KERN_ERR "CPU: Vendor unknown, using generic init.\n"); + printk(KERN_ERR "CPU: Your system may be unstable.\n"); + } + c->x86_vendor = X86_VENDOR_UNKNOWN; +} + +static void __init early_cpu_support_print(void) +{ + int i,j; + struct cpu_dev *cpu_devx; + + printk("KERNEL supported cpus:\n"); + for (i = 0; i < X86_VENDOR_NUM; i++) { + cpu_devx = cpu_devs[i]; + if (!cpu_devx) + continue; + for (j = 0; j < 2; j++) { + if (!cpu_devx->c_ident[j]) + continue; + printk(" %s %s\n", cpu_devx->c_vendor, + cpu_devx->c_ident[j]); + } + } +} + +static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c); + +void __init early_cpu_init(void) +{ + struct cpu_vendor_dev *cvdev; + + for (cvdev = __x86cpuvendor_start ; + cvdev < __x86cpuvendor_end ; + cvdev++) + cpu_devs[cvdev->vendor] = cvdev->cpu_dev; + early_cpu_support_print(); + early_identify_cpu(&boot_cpu_data); +} + +/* Do some early cpuid on the boot CPU to get some parameter that are + needed before check_bugs. Everything advanced is in identify_cpu + below. */ +static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c) +{ + u32 tfms, xlvl; + + c->loops_per_jiffy = loops_per_jiffy; + c->x86_cache_size = -1; + c->x86_vendor = X86_VENDOR_UNKNOWN; + c->x86_model = c->x86_mask = 0; /* So far unknown... */ + c->x86_vendor_id[0] = '\0'; /* Unset */ + c->x86_model_id[0] = '\0'; /* Unset */ + c->x86_clflush_size = 64; + c->x86_cache_alignment = c->x86_clflush_size; + c->x86_max_cores = 1; + c->x86_coreid_bits = 0; + c->extended_cpuid_level = 0; + memset(&c->x86_capability, 0, sizeof c->x86_capability); + + /* Get vendor name */ + cpuid(0x00000000, (unsigned int *)&c->cpuid_level, + (unsigned int *)&c->x86_vendor_id[0], + (unsigned int *)&c->x86_vendor_id[8], + (unsigned int *)&c->x86_vendor_id[4]); + + get_cpu_vendor(c); + + /* Initialize the standard set of capabilities */ + /* Note that the vendor-specific code below might override */ + + /* Intel-defined flags: level 0x00000001 */ + if (c->cpuid_level >= 0x00000001) { + __u32 misc; + cpuid(0x00000001, &tfms, &misc, &c->x86_capability[4], + &c->x86_capability[0]); + c->x86 = (tfms >> 8) & 0xf; + c->x86_model = (tfms >> 4) & 0xf; + c->x86_mask = tfms & 0xf; + if (c->x86 == 0xf) + c->x86 += (tfms >> 20) & 0xff; + if (c->x86 >= 0x6) + c->x86_model += ((tfms >> 16) & 0xF) << 4; + if (test_cpu_cap(c, X86_FEATURE_CLFLSH)) + c->x86_clflush_size = ((misc >> 8) & 0xff) * 8; + } else { + /* Have CPUID level 0 only - unheard of */ + c->x86 = 4; + } + + c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xff; +#ifdef CONFIG_SMP + c->phys_proc_id = c->initial_apicid; +#endif + /* AMD-defined flags: level 0x80000001 */ + xlvl = cpuid_eax(0x80000000); + c->extended_cpuid_level = xlvl; + if ((xlvl & 0xffff0000) == 0x80000000) { + if (xlvl >= 0x80000001) { + c->x86_capability[1] = cpuid_edx(0x80000001); + c->x86_capability[6] = cpuid_ecx(0x80000001); + } + if (xlvl >= 0x80000004) + get_model_name(c); /* Default name */ + } + + /* Transmeta-defined flags: level 0x80860001 */ + xlvl = cpuid_eax(0x80860000); + if ((xlvl & 0xffff0000) == 0x80860000) { + /* Don't set x86_cpuid_level here for now to not confuse. */ + if (xlvl >= 0x80860001) + c->x86_capability[2] = cpuid_edx(0x80860001); + } + + c->extended_cpuid_level = cpuid_eax(0x80000000); + if (c->extended_cpuid_level >= 0x80000007) + c->x86_power = cpuid_edx(0x80000007); + + if (c->extended_cpuid_level >= 0x80000008) { + u32 eax = cpuid_eax(0x80000008); + + c->x86_virt_bits = (eax >> 8) & 0xff; + c->x86_phys_bits = eax & 0xff; + } + + /* Assume all 64-bit CPUs support 32-bit syscall */ + set_cpu_cap(c, X86_FEATURE_SYSCALL32); + + if (c->x86_vendor != X86_VENDOR_UNKNOWN && + cpu_devs[c->x86_vendor]->c_early_init) + cpu_devs[c->x86_vendor]->c_early_init(c); + + validate_pat_support(c); + + /* early_param could clear that, but recall get it set again */ + if (disable_apic) + clear_cpu_cap(c, X86_FEATURE_APIC); +} + +/* + * This does the hard work of actually picking apart the CPU stuff... + */ +static void __cpuinit identify_cpu(struct cpuinfo_x86 *c) +{ + int i; + + early_identify_cpu(c); + + init_scattered_cpuid_features(c); + + c->apicid = phys_pkg_id(0); + + /* + * Vendor-specific initialization. In this section we + * canonicalize the feature flags, meaning if there are + * features a certain CPU supports which CPUID doesn't + * tell us, CPUID claiming incorrect flags, or other bugs, + * we handle them here. + * + * At the end of this section, c->x86_capability better + * indicate the features this CPU genuinely supports! + */ + if (this_cpu->c_init) + this_cpu->c_init(c); + + detect_ht(c); + + /* + * On SMP, boot_cpu_data holds the common feature set between + * all CPUs; so make sure that we indicate which features are + * common between the CPUs. The first time this routine gets + * executed, c == &boot_cpu_data. + */ + if (c != &boot_cpu_data) { + /* AND the already accumulated flags with these */ + for (i = 0; i < NCAPINTS; i++) + boot_cpu_data.x86_capability[i] &= c->x86_capability[i]; + } + + /* Clear all flags overriden by options */ + for (i = 0; i < NCAPINTS; i++) + c->x86_capability[i] &= ~cleared_cpu_caps[i]; + +#ifdef CONFIG_X86_MCE + mcheck_init(c); +#endif + select_idle_routine(c); + +#ifdef CONFIG_NUMA + numa_add_cpu(smp_processor_id()); +#endif + +} + +void __cpuinit identify_boot_cpu(void) +{ + identify_cpu(&boot_cpu_data); +} + +void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c) +{ + BUG_ON(c == &boot_cpu_data); + identify_cpu(c); + mtrr_ap_init(); +} + +static __init int setup_noclflush(char *arg) +{ + setup_clear_cpu_cap(X86_FEATURE_CLFLSH); + return 1; +} +__setup("noclflush", setup_noclflush); + +void __cpuinit print_cpu_info(struct cpuinfo_x86 *c) +{ + if (c->x86_model_id[0]) + printk(KERN_CONT "%s", c->x86_model_id); + + if (c->x86_mask || c->cpuid_level >= 0) + printk(KERN_CONT " stepping %02x\n", c->x86_mask); + else + printk(KERN_CONT "\n"); +} + +static __init int setup_disablecpuid(char *arg) +{ + int bit; + if (get_option(&arg, &bit) && bit < NCAPINTS*32) + setup_clear_cpu_cap(bit); + else + return 0; + return 1; +} +__setup("clearcpuid=", setup_disablecpuid); + +cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE; + +struct x8664_pda **_cpu_pda __read_mostly; +EXPORT_SYMBOL(_cpu_pda); + +struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table }; + +char boot_cpu_stack[IRQSTACKSIZE] __page_aligned_bss; + +unsigned long __supported_pte_mask __read_mostly = ~0UL; +EXPORT_SYMBOL_GPL(__supported_pte_mask); + +static int do_not_nx __cpuinitdata; + +/* noexec=on|off +Control non executable mappings for 64bit processes. + +on Enable(default) +off Disable +*/ +static int __init nonx_setup(char *str) +{ + if (!str) + return -EINVAL; + if (!strncmp(str, "on", 2)) { + __supported_pte_mask |= _PAGE_NX; + do_not_nx = 0; + } else if (!strncmp(str, "off", 3)) { + do_not_nx = 1; + __supported_pte_mask &= ~_PAGE_NX; + } + return 0; +} +early_param("noexec", nonx_setup); + +int force_personality32; + +/* noexec32=on|off +Control non executable heap for 32bit processes. +To control the stack too use noexec=off + +on PROT_READ does not imply PROT_EXEC for 32bit processes (default) +off PROT_READ implies PROT_EXEC +*/ +static int __init nonx32_setup(char *str) +{ + if (!strcmp(str, "on")) + force_personality32 &= ~READ_IMPLIES_EXEC; + else if (!strcmp(str, "off")) + force_personality32 |= READ_IMPLIES_EXEC; + return 1; +} +__setup("noexec32=", nonx32_setup); + +void pda_init(int cpu) +{ + struct x8664_pda *pda = cpu_pda(cpu); + + /* Setup up data that may be needed in __get_free_pages early */ + loadsegment(fs, 0); + loadsegment(gs, 0); + /* Memory clobbers used to order PDA accessed */ + mb(); + wrmsrl(MSR_GS_BASE, pda); + mb(); + + pda->cpunumber = cpu; + pda->irqcount = -1; + pda->kernelstack = (unsigned long)stack_thread_info() - + PDA_STACKOFFSET + THREAD_SIZE; + pda->active_mm = &init_mm; + pda->mmu_state = 0; + + if (cpu == 0) { + /* others are initialized in smpboot.c */ + pda->pcurrent = &init_task; + pda->irqstackptr = boot_cpu_stack; + } else { + pda->irqstackptr = (char *) + __get_free_pages(GFP_ATOMIC, IRQSTACK_ORDER); + if (!pda->irqstackptr) + panic("cannot allocate irqstack for cpu %d", cpu); + + if (pda->nodenumber == 0 && cpu_to_node(cpu) != NUMA_NO_NODE) + pda->nodenumber = cpu_to_node(cpu); + } + + pda->irqstackptr += IRQSTACKSIZE-64; +} + +char boot_exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + + DEBUG_STKSZ] +__attribute__((section(".bss.page_aligned"))); + +extern asmlinkage void ignore_sysret(void); + +/* May not be marked __init: used by software suspend */ +void syscall_init(void) +{ + /* + * LSTAR and STAR live in a bit strange symbiosis. + * They both write to the same internal register. STAR allows to + * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip. + */ + wrmsrl(MSR_STAR, ((u64)__USER32_CS)<<48 | ((u64)__KERNEL_CS)<<32); + wrmsrl(MSR_LSTAR, system_call); + wrmsrl(MSR_CSTAR, ignore_sysret); + +#ifdef CONFIG_IA32_EMULATION + syscall32_cpu_init(); +#endif + + /* Flags to clear on syscall */ + wrmsrl(MSR_SYSCALL_MASK, + X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|X86_EFLAGS_IOPL); +} + +void __cpuinit check_efer(void) +{ + unsigned long efer; + + rdmsrl(MSR_EFER, efer); + if (!(efer & EFER_NX) || do_not_nx) + __supported_pte_mask &= ~_PAGE_NX; +} + +unsigned long kernel_eflags; + +/* + * Copies of the original ist values from the tss are only accessed during + * debugging, no special alignment required. + */ +DEFINE_PER_CPU(struct orig_ist, orig_ist); + +/* + * cpu_init() initializes state that is per-CPU. Some data is already + * initialized (naturally) in the bootstrap process, such as the GDT + * and IDT. We reload them nevertheless, this function acts as a + * 'CPU state barrier', nothing should get across. + * A lot of state is already set up in PDA init. + */ +void __cpuinit cpu_init(void) +{ + int cpu = stack_smp_processor_id(); + struct tss_struct *t = &per_cpu(init_tss, cpu); + struct orig_ist *orig_ist = &per_cpu(orig_ist, cpu); + unsigned long v; + char *estacks = NULL; + struct task_struct *me; + int i; + + /* CPU 0 is initialised in head64.c */ + if (cpu != 0) + pda_init(cpu); + else + estacks = boot_exception_stacks; + + me = current; + + if (cpu_test_and_set(cpu, cpu_initialized)) + panic("CPU#%d already initialized!\n", cpu); + + printk(KERN_INFO "Initializing CPU#%d\n", cpu); + + clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); + + /* + * Initialize the per-CPU GDT with the boot GDT, + * and set up the GDT descriptor: + */ + + switch_to_new_gdt(); + load_idt((const struct desc_ptr *)&idt_descr); + + memset(me->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8); + syscall_init(); + + wrmsrl(MSR_FS_BASE, 0); + wrmsrl(MSR_KERNEL_GS_BASE, 0); + barrier(); + + check_efer(); + + /* + * set up and load the per-CPU TSS + */ + for (v = 0; v < N_EXCEPTION_STACKS; v++) { + static const unsigned int order[N_EXCEPTION_STACKS] = { + [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STACK_ORDER, + [DEBUG_STACK - 1] = DEBUG_STACK_ORDER + }; + if (cpu) { + estacks = (char *)__get_free_pages(GFP_ATOMIC, order[v]); + if (!estacks) + panic("Cannot allocate exception stack %ld %d\n", + v, cpu); + } + estacks += PAGE_SIZE << order[v]; + orig_ist->ist[v] = t->x86_tss.ist[v] = (unsigned long)estacks; + } + + t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap); + /* + * <= is required because the CPU will access up to + * 8 bits beyond the end of the IO permission bitmap. + */ + for (i = 0; i <= IO_BITMAP_LONGS; i++) + t->io_bitmap[i] = ~0UL; + + atomic_inc(&init_mm.mm_count); + me->active_mm = &init_mm; + if (me->mm) + BUG(); + enter_lazy_tlb(&init_mm, me); + + load_sp0(t, ¤t->thread); + set_tss_desc(cpu, t); + load_TR_desc(); + load_LDT(&init_mm.context); + +#ifdef CONFIG_KGDB + /* + * If the kgdb is connected no debug regs should be altered. This + * is only applicable when KGDB and a KGDB I/O module are built + * into the kernel and you are using early debugging with + * kgdbwait. KGDB will control the kernel HW breakpoint registers. + */ + if (kgdb_connected && arch_kgdb_ops.correct_hw_break) + arch_kgdb_ops.correct_hw_break(); + else { +#endif + /* + * Clear all 6 debug registers: + */ + + set_debugreg(0UL, 0); + set_debugreg(0UL, 1); + set_debugreg(0UL, 2); + set_debugreg(0UL, 3); + set_debugreg(0UL, 6); + set_debugreg(0UL, 7); +#ifdef CONFIG_KGDB + /* If the kgdb is connected no debug regs should be altered. */ + } +#endif + + fpu_init(); + + raw_local_save_flags(kernel_eflags); + + if (is_uv_system()) + uv_cpu_init(); +} diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 783691b2a738..4d894e8565fe 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -1,3 +1,6 @@ +#ifndef ARCH_X86_CPU_H + +#define ARCH_X86_CPU_H struct cpu_model_info { int vendor; @@ -36,3 +39,5 @@ extern struct cpu_vendor_dev __x86cpuvendor_start[], __x86cpuvendor_end[]; extern int get_model_name(struct cpuinfo_x86 *c); extern void display_cacheinfo(struct cpuinfo_x86 *c); + +#endif diff --git a/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c b/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c index f03e9153618e..965ea52767ac 100644 --- a/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c +++ b/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c @@ -26,9 +26,10 @@ #define NFORCE2_SAFE_DISTANCE 50 /* Delay in ms between FSB changes */ -//#define NFORCE2_DELAY 10 +/* #define NFORCE2_DELAY 10 */ -/* nforce2_chipset: +/* + * nforce2_chipset: * FSB is changed using the chipset */ static struct pci_dev *nforce2_chipset_dev; @@ -36,13 +37,13 @@ static struct pci_dev *nforce2_chipset_dev; /* fid: * multiplier * 10 */ -static int fid = 0; +static int fid; /* min_fsb, max_fsb: * minimum and maximum FSB (= FSB at boot time) */ -static int min_fsb = 0; -static int max_fsb = 0; +static int min_fsb; +static int max_fsb; MODULE_AUTHOR("Sebastian Witt <se.witt@gmx.net>"); MODULE_DESCRIPTION("nForce2 FSB changing cpufreq driver"); @@ -53,7 +54,7 @@ module_param(min_fsb, int, 0444); MODULE_PARM_DESC(fid, "CPU multiplier to use (11.5 = 115)"); MODULE_PARM_DESC(min_fsb, - "Minimum FSB to use, if not defined: current FSB - 50"); + "Minimum FSB to use, if not defined: current FSB - 50"); #define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "cpufreq-nforce2", msg) @@ -139,7 +140,7 @@ static unsigned int nforce2_fsb_read(int bootfsb) /* 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; @@ -147,13 +148,13 @@ static unsigned int nforce2_fsb_read(int bootfsb) 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) + 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; @@ -184,7 +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); @@ -210,7 +211,8 @@ static int nforce2_set_fsb(unsigned int fsb) tfsb--; /* Calculate the PLL reg. value */ - if ((pll = nforce2_calc_pll(tfsb)) == -1) + pll = nforce2_calc_pll(tfsb); + if (pll == -1) return -EINVAL; nforce2_write_pll(pll); @@ -249,7 +251,7 @@ static unsigned int nforce2_get(unsigned int cpu) static int nforce2_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) { -// unsigned long flags; +/* unsigned long flags; */ struct cpufreq_freqs freqs; unsigned int target_fsb; @@ -271,17 +273,17 @@ static int nforce2_target(struct cpufreq_policy *policy, cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); /* Disable IRQs */ - //local_irq_save(flags); + /* local_irq_save(flags); */ if (nforce2_set_fsb(target_fsb) < 0) printk(KERN_ERR "cpufreq: Changing FSB to %d failed\n", - target_fsb); + target_fsb); else dprintk("Changed FSB successfully to %d\n", - target_fsb); + target_fsb); /* Enable IRQs */ - //local_irq_restore(flags); + /* local_irq_restore(flags); */ cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); @@ -302,8 +304,8 @@ static int nforce2_verify(struct cpufreq_policy *policy) policy->max = (fsb_pol_max + 1) * fid * 100; cpufreq_verify_within_limits(policy, - policy->cpuinfo.min_freq, - policy->cpuinfo.max_freq); + policy->cpuinfo.min_freq, + policy->cpuinfo.max_freq); return 0; } @@ -347,7 +349,7 @@ static int nforce2_cpu_init(struct cpufreq_policy *policy) /* Set maximum FSB to FSB at boot time */ max_fsb = nforce2_fsb_read(1); - if(!max_fsb) + if (!max_fsb) return -EIO; if (!min_fsb) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index fe9224c51d37..70609efdf1da 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -226,6 +226,10 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) if (cpu_has_bts) ds_init_intel(c); + +#ifdef CONFIG_X86_NUMAQ + numaq_tsc_disable(); +#endif } static unsigned int __cpuinit intel_size_cache(struct cpuinfo_x86 *c, unsigned int size) diff --git a/arch/x86/kernel/cpu/intel_64.c b/arch/x86/kernel/cpu/intel_64.c new file mode 100644 index 000000000000..1019c58d39f0 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_64.c @@ -0,0 +1,95 @@ +#include <linux/init.h> +#include <linux/smp.h> +#include <asm/processor.h> +#include <asm/ptrace.h> +#include <asm/topology.h> +#include <asm/numa_64.h> + +#include "cpu.h" + +static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) +{ + if ((c->x86 == 0xf && c->x86_model >= 0x03) || + (c->x86 == 0x6 && c->x86_model >= 0x0e)) + set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); + + set_cpu_cap(c, X86_FEATURE_SYSENTER32); +} + +/* + * find out the number of processor cores on the die + */ +static int __cpuinit intel_num_cpu_cores(struct cpuinfo_x86 *c) +{ + unsigned int eax, t; + + if (c->cpuid_level < 4) + return 1; + + cpuid_count(4, 0, &eax, &t, &t, &t); + + if (eax & 0x1f) + return ((eax >> 26) + 1); + else + return 1; +} + +static void __cpuinit srat_detect_node(void) +{ +#ifdef CONFIG_NUMA + unsigned node; + int cpu = smp_processor_id(); + int apicid = hard_smp_processor_id(); + + /* Don't do the funky fallback heuristics the AMD version employs + for now. */ + node = apicid_to_node[apicid]; + if (node == NUMA_NO_NODE || !node_online(node)) + node = first_node(node_online_map); + numa_set_node(cpu, node); + + printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node); +#endif +} + +static void __cpuinit init_intel(struct cpuinfo_x86 *c) +{ + init_intel_cacheinfo(c); + if (c->cpuid_level > 9) { + unsigned eax = cpuid_eax(10); + /* Check for version and the number of counters */ + if ((eax & 0xff) && (((eax>>8) & 0xff) > 1)) + set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON); + } + + if (cpu_has_ds) { + unsigned int l1, l2; + rdmsr(MSR_IA32_MISC_ENABLE, l1, l2); + if (!(l1 & (1<<11))) + set_cpu_cap(c, X86_FEATURE_BTS); + if (!(l1 & (1<<12))) + set_cpu_cap(c, X86_FEATURE_PEBS); + } + + + if (cpu_has_bts) + ds_init_intel(c); + + if (c->x86 == 15) + c->x86_cache_alignment = c->x86_clflush_size * 2; + if (c->x86 == 6) + set_cpu_cap(c, X86_FEATURE_REP_GOOD); + set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); + c->x86_max_cores = intel_num_cpu_cores(c); + + srat_detect_node(); +} + +static struct cpu_dev intel_cpu_dev __cpuinitdata = { + .c_vendor = "Intel", + .c_ident = { "GenuineIntel" }, + .c_early_init = early_init_intel, + .c_init = init_intel, +}; +cpu_vendor_dev_register(X86_VENDOR_INTEL, &intel_cpu_dev); + diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 26d615dcb149..2c8afafa18e8 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -62,6 +62,7 @@ static struct _cache_table cache_table[] __cpuinitdata = { 0x4b, LVL_3, 8192 }, /* 16-way set assoc, 64 byte line size */ { 0x4c, LVL_3, 12288 }, /* 12-way set assoc, 64 byte line size */ { 0x4d, LVL_3, 16384 }, /* 16-way set assoc, 64 byte line size */ + { 0x4e, LVL_2, 6144 }, /* 24-way set assoc, 64 byte line size */ { 0x60, LVL_1_DATA, 16 }, /* 8-way set assoc, sectored cache, 64 byte line size */ { 0x66, LVL_1_DATA, 8 }, /* 4-way set assoc, sectored cache, 64 byte line size */ { 0x67, LVL_1_DATA, 16 }, /* 4-way set assoc, sectored cache, 64 byte line size */ diff --git a/arch/x86/kernel/cpu/mcheck/k7.c b/arch/x86/kernel/cpu/mcheck/k7.c index e633c9c2b764..f390c9f66351 100644 --- a/arch/x86/kernel/cpu/mcheck/k7.c +++ b/arch/x86/kernel/cpu/mcheck/k7.c @@ -9,23 +9,23 @@ #include <linux/interrupt.h> #include <linux/smp.h> -#include <asm/processor.h> +#include <asm/processor.h> #include <asm/system.h> #include <asm/msr.h> #include "mce.h" /* Machine Check Handler For AMD Athlon/Duron */ -static void k7_machine_check(struct pt_regs * regs, long error_code) +static void k7_machine_check(struct pt_regs *regs, long error_code) { - int recover=1; + int recover = 1; u32 alow, ahigh, high, low; u32 mcgstl, mcgsth; int i; - rdmsr (MSR_IA32_MCG_STATUS, mcgstl, mcgsth); + rdmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth); if (mcgstl & (1<<0)) /* Recoverable ? */ - recover=0; + recover = 0; printk(KERN_EMERG "CPU %d: Machine Check Exception: %08x%08x\n", smp_processor_id(), mcgsth, mcgstl); @@ -60,12 +60,12 @@ static void k7_machine_check(struct pt_regs * regs, long error_code) } if (recover&2) - panic ("CPU context corrupt"); + panic("CPU context corrupt"); if (recover&1) - panic ("Unable to continue"); - printk (KERN_EMERG "Attempting to continue.\n"); + panic("Unable to continue"); + printk(KERN_EMERG "Attempting to continue.\n"); mcgstl &= ~(1<<2); - wrmsr (MSR_IA32_MCG_STATUS,mcgstl, mcgsth); + wrmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth); } @@ -81,25 +81,25 @@ void amd_mcheck_init(struct cpuinfo_x86 *c) machine_check_vector = k7_machine_check; wmb(); - printk (KERN_INFO "Intel machine check architecture supported.\n"); - rdmsr (MSR_IA32_MCG_CAP, l, h); + printk(KERN_INFO "Intel machine check architecture supported.\n"); + rdmsr(MSR_IA32_MCG_CAP, l, h); if (l & (1<<8)) /* Control register present ? */ - wrmsr (MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff); + wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff); nr_mce_banks = l & 0xff; /* Clear status for MC index 0 separately, we don't touch CTL, * as some K7 Athlons cause spurious MCEs when its enabled. */ if (boot_cpu_data.x86 == 6) { - wrmsr (MSR_IA32_MC0_STATUS, 0x0, 0x0); + wrmsr(MSR_IA32_MC0_STATUS, 0x0, 0x0); i = 1; } else i = 0; - for (; i<nr_mce_banks; i++) { - wrmsr (MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff); - wrmsr (MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0); + for (; i < nr_mce_banks; i++) { + wrmsr(MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff); + wrmsr(MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0); } - set_in_cr4 (X86_CR4_MCE); - printk (KERN_INFO "Intel machine check reporting enabled on CPU#%d.\n", + set_in_cr4(X86_CR4_MCE); + printk(KERN_INFO "Intel machine check reporting enabled on CPU#%d.\n", smp_processor_id()); } diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c index e07e8c068ae0..c4a7ec31394c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_64.c @@ -9,6 +9,7 @@ #include <linux/types.h> #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/smp_lock.h> #include <linux/string.h> #include <linux/rcupdate.h> #include <linux/kallsyms.h> @@ -31,7 +32,7 @@ #include <asm/idle.h> #define MISC_MCELOG_MINOR 227 -#define NR_BANKS 6 +#define NR_SYSFS_BANKS 6 atomic_t mce_entry; @@ -46,7 +47,7 @@ static int mce_dont_init; */ static int tolerant = 1; static int banks; -static unsigned long bank[NR_BANKS] = { [0 ... NR_BANKS-1] = ~0UL }; +static unsigned long bank[NR_SYSFS_BANKS] = { [0 ... NR_SYSFS_BANKS-1] = ~0UL }; static unsigned long notify_user; static int rip_msr; static int mce_bootlog = -1; @@ -209,7 +210,7 @@ void do_machine_check(struct pt_regs * regs, long error_code) barrier(); for (i = 0; i < banks; i++) { - if (!bank[i]) + if (i < NR_SYSFS_BANKS && !bank[i]) continue; m.misc = 0; @@ -363,7 +364,7 @@ static void mcheck_check_cpu(void *info) static void mcheck_timer(struct work_struct *work) { - on_each_cpu(mcheck_check_cpu, NULL, 1, 1); + on_each_cpu(mcheck_check_cpu, NULL, 1); /* * Alert userspace if needed. If we logged an MCE, reduce the @@ -444,9 +445,10 @@ static void mce_init(void *dummy) rdmsrl(MSR_IA32_MCG_CAP, cap); banks = cap & 0xff; - if (banks > NR_BANKS) { - printk(KERN_INFO "MCE: warning: using only %d banks\n", banks); - banks = NR_BANKS; + if (banks > MCE_EXTENDED_BANK) { + banks = MCE_EXTENDED_BANK; + printk(KERN_INFO "MCE: warning: using only %d banks\n", + MCE_EXTENDED_BANK); } /* Use accurate RIP reporting if available. */ if ((cap & (1<<9)) && ((cap >> 16) & 0xff) >= 9) @@ -462,7 +464,11 @@ static void mce_init(void *dummy) wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff); for (i = 0; i < banks; i++) { - wrmsrl(MSR_IA32_MC0_CTL+4*i, bank[i]); + if (i < NR_SYSFS_BANKS) + wrmsrl(MSR_IA32_MC0_CTL+4*i, bank[i]); + else + wrmsrl(MSR_IA32_MC0_CTL+4*i, ~0UL); + wrmsrl(MSR_IA32_MC0_STATUS+4*i, 0); } } @@ -527,10 +533,12 @@ static int open_exclu; /* already open exclusive? */ static int mce_open(struct inode *inode, struct file *file) { + lock_kernel(); spin_lock(&mce_state_lock); if (open_exclu || (open_count && (file->f_flags & O_EXCL))) { spin_unlock(&mce_state_lock); + unlock_kernel(); return -EBUSY; } @@ -539,6 +547,7 @@ static int mce_open(struct inode *inode, struct file *file) open_count++; spin_unlock(&mce_state_lock); + unlock_kernel(); return nonseekable_open(inode, file); } @@ -612,7 +621,7 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize, * Collect entries that were still getting written before the * synchronize. */ - on_each_cpu(collect_tscs, cpu_tsc, 1, 1); + on_each_cpu(collect_tscs, cpu_tsc, 1); for (i = next; i < MCE_LOG_LEN; i++) { if (mcelog.entry[i].finished && mcelog.entry[i].tsc < cpu_tsc[mcelog.entry[i].cpu]) { @@ -737,7 +746,7 @@ static void mce_restart(void) if (next_interval) cancel_delayed_work(&mcheck_work); /* Timer race is harmless here */ - on_each_cpu(mce_init, NULL, 1, 1); + on_each_cpu(mce_init, NULL, 1); next_interval = check_interval * HZ; if (next_interval) schedule_delayed_work(&mcheck_work, @@ -766,7 +775,10 @@ DEFINE_PER_CPU(struct sys_device, device_mce); } \ static SYSDEV_ATTR(name, 0644, show_ ## name, set_ ## name); -/* TBD should generate these dynamically based on number of available banks */ +/* + * TBD should generate these dynamically based on number of available banks. + * Have only 6 contol banks in /sysfs until then. + */ ACCESSOR(bank0ctl,bank[0],mce_restart()) ACCESSOR(bank1ctl,bank[1],mce_restart()) ACCESSOR(bank2ctl,bank[2],mce_restart()) diff --git a/arch/x86/kernel/cpu/mcheck/non-fatal.c b/arch/x86/kernel/cpu/mcheck/non-fatal.c index 00ccb6c14ec2..cc1fccdd31e0 100644 --- a/arch/x86/kernel/cpu/mcheck/non-fatal.c +++ b/arch/x86/kernel/cpu/mcheck/non-fatal.c @@ -59,7 +59,7 @@ static DECLARE_DELAYED_WORK(mce_work, mce_work_fn); static void mce_work_fn(struct work_struct *work) { - on_each_cpu(mce_checkregs, NULL, 1, 1); + on_each_cpu(mce_checkregs, NULL, 1); schedule_delayed_work(&mce_work, round_jiffies_relative(MCE_RATE)); } diff --git a/arch/x86/kernel/cpu/mcheck/p4.c b/arch/x86/kernel/cpu/mcheck/p4.c index cb03345554a5..eef001ad3bde 100644 --- a/arch/x86/kernel/cpu/mcheck/p4.c +++ b/arch/x86/kernel/cpu/mcheck/p4.c @@ -8,7 +8,7 @@ #include <linux/interrupt.h> #include <linux/smp.h> -#include <asm/processor.h> +#include <asm/processor.h> #include <asm/system.h> #include <asm/msr.h> #include <asm/apic.h> @@ -32,12 +32,12 @@ struct intel_mce_extended_msrs { /* u32 *reserved[]; */ }; -static int mce_num_extended_msrs = 0; +static int mce_num_extended_msrs; #ifdef CONFIG_X86_MCE_P4THERMAL static void unexpected_thermal_interrupt(struct pt_regs *regs) -{ +{ printk(KERN_ERR "CPU%d: Unexpected LVT TMR interrupt!\n", smp_processor_id()); add_taint(TAINT_MACHINE_CHECK); @@ -83,7 +83,7 @@ static void intel_init_thermal(struct cpuinfo_x86 *c) * be some SMM goo which handles it, so we can't even put a handler * since it might be delivered via SMI already -zwanem. */ - rdmsr (MSR_IA32_MISC_ENABLE, l, h); + rdmsr(MSR_IA32_MISC_ENABLE, l, h); h = apic_read(APIC_LVTTHMR); if ((l & (1<<3)) && (h & APIC_DM_SMI)) { printk(KERN_DEBUG "CPU%d: Thermal monitoring handled by SMI\n", @@ -91,7 +91,7 @@ static void intel_init_thermal(struct cpuinfo_x86 *c) return; /* -EBUSY */ } - /* check whether a vector already exists, temporarily masked? */ + /* check whether a vector already exists, temporarily masked? */ if (h & APIC_VECTOR_MASK) { printk(KERN_DEBUG "CPU%d: Thermal LVT vector (%#x) already " "installed\n", @@ -104,18 +104,18 @@ static void intel_init_thermal(struct cpuinfo_x86 *c) h |= (APIC_DM_FIXED | APIC_LVT_MASKED); /* we'll mask till we're ready */ apic_write_around(APIC_LVTTHMR, h); - rdmsr (MSR_IA32_THERM_INTERRUPT, l, h); - wrmsr (MSR_IA32_THERM_INTERRUPT, l | 0x03 , h); + rdmsr(MSR_IA32_THERM_INTERRUPT, l, h); + wrmsr(MSR_IA32_THERM_INTERRUPT, l | 0x03 , h); /* ok we're good to go... */ vendor_thermal_interrupt = intel_thermal_interrupt; - - rdmsr (MSR_IA32_MISC_ENABLE, l, h); - wrmsr (MSR_IA32_MISC_ENABLE, l | (1<<3), h); - l = apic_read (APIC_LVTTHMR); - apic_write_around (APIC_LVTTHMR, l & ~APIC_LVT_MASKED); - printk (KERN_INFO "CPU%d: Thermal monitoring enabled\n", cpu); + rdmsr(MSR_IA32_MISC_ENABLE, l, h); + wrmsr(MSR_IA32_MISC_ENABLE, l | (1<<3), h); + + l = apic_read(APIC_LVTTHMR); + apic_write_around(APIC_LVTTHMR, l & ~APIC_LVT_MASKED); + printk(KERN_INFO "CPU%d: Thermal monitoring enabled\n", cpu); /* enable thermal throttle processing */ atomic_set(&therm_throt_en, 1); @@ -129,28 +129,28 @@ static inline void intel_get_extended_msrs(struct intel_mce_extended_msrs *r) { u32 h; - rdmsr (MSR_IA32_MCG_EAX, r->eax, h); - rdmsr (MSR_IA32_MCG_EBX, r->ebx, h); - rdmsr (MSR_IA32_MCG_ECX, r->ecx, h); - rdmsr (MSR_IA32_MCG_EDX, r->edx, h); - rdmsr (MSR_IA32_MCG_ESI, r->esi, h); - rdmsr (MSR_IA32_MCG_EDI, r->edi, h); - rdmsr (MSR_IA32_MCG_EBP, r->ebp, h); - rdmsr (MSR_IA32_MCG_ESP, r->esp, h); - rdmsr (MSR_IA32_MCG_EFLAGS, r->eflags, h); - rdmsr (MSR_IA32_MCG_EIP, r->eip, h); + rdmsr(MSR_IA32_MCG_EAX, r->eax, h); + rdmsr(MSR_IA32_MCG_EBX, r->ebx, h); + rdmsr(MSR_IA32_MCG_ECX, r->ecx, h); + rdmsr(MSR_IA32_MCG_EDX, r->edx, h); + rdmsr(MSR_IA32_MCG_ESI, r->esi, h); + rdmsr(MSR_IA32_MCG_EDI, r->edi, h); + rdmsr(MSR_IA32_MCG_EBP, r->ebp, h); + rdmsr(MSR_IA32_MCG_ESP, r->esp, h); + rdmsr(MSR_IA32_MCG_EFLAGS, r->eflags, h); + rdmsr(MSR_IA32_MCG_EIP, r->eip, h); } -static void intel_machine_check(struct pt_regs * regs, long error_code) +static void intel_machine_check(struct pt_regs *regs, long error_code) { - int recover=1; + int recover = 1; u32 alow, ahigh, high, low; u32 mcgstl, mcgsth; int i; - rdmsr (MSR_IA32_MCG_STATUS, mcgstl, mcgsth); + rdmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth); if (mcgstl & (1<<0)) /* Recoverable ? */ - recover=0; + recover = 0; printk(KERN_EMERG "CPU %d: Machine Check Exception: %08x%08x\n", smp_processor_id(), mcgsth, mcgstl); @@ -191,20 +191,20 @@ static void intel_machine_check(struct pt_regs * regs, long error_code) } if (recover & 2) - panic ("CPU context corrupt"); + panic("CPU context corrupt"); if (recover & 1) - panic ("Unable to continue"); + panic("Unable to continue"); printk(KERN_EMERG "Attempting to continue.\n"); - /* - * Do not clear the MSR_IA32_MCi_STATUS if the error is not + /* + * Do not clear the MSR_IA32_MCi_STATUS if the error is not * recoverable/continuable.This will allow BIOS to look at the MSRs * for errors if the OS could not log the error. */ - for (i=0; i<nr_mce_banks; i++) { + for (i = 0; i < nr_mce_banks; i++) { u32 msr; msr = MSR_IA32_MC0_STATUS+i*4; - rdmsr (msr, low, high); + rdmsr(msr, low, high); if (high&(1<<31)) { /* Clear it */ wrmsr(msr, 0UL, 0UL); @@ -214,7 +214,7 @@ static void intel_machine_check(struct pt_regs * regs, long error_code) } } mcgstl &= ~(1<<2); - wrmsr (MSR_IA32_MCG_STATUS,mcgstl, mcgsth); + wrmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth); } @@ -222,30 +222,30 @@ void intel_p4_mcheck_init(struct cpuinfo_x86 *c) { u32 l, h; int i; - + machine_check_vector = intel_machine_check; wmb(); - printk (KERN_INFO "Intel machine check architecture supported.\n"); - rdmsr (MSR_IA32_MCG_CAP, l, h); + printk(KERN_INFO "Intel machine check architecture supported.\n"); + rdmsr(MSR_IA32_MCG_CAP, l, h); if (l & (1<<8)) /* Control register present ? */ - wrmsr (MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff); + wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff); nr_mce_banks = l & 0xff; - for (i=0; i<nr_mce_banks; i++) { - wrmsr (MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff); - wrmsr (MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0); + for (i = 0; i < nr_mce_banks; i++) { + wrmsr(MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff); + wrmsr(MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0); } - set_in_cr4 (X86_CR4_MCE); - printk (KERN_INFO "Intel machine check reporting enabled on CPU#%d.\n", + set_in_cr4(X86_CR4_MCE); + printk(KERN_INFO "Intel machine check reporting enabled on CPU#%d.\n", smp_processor_id()); /* Check for P4/Xeon extended MCE MSRs */ - rdmsr (MSR_IA32_MCG_CAP, l, h); + rdmsr(MSR_IA32_MCG_CAP, l, h); if (l & (1<<9)) {/* MCG_EXT_P */ mce_num_extended_msrs = (l >> 16) & 0xff; - printk (KERN_INFO "CPU%d: Intel P4/Xeon Extended MCE MSRs (%d)" + printk(KERN_INFO "CPU%d: Intel P4/Xeon Extended MCE MSRs (%d)" " available\n", smp_processor_id(), mce_num_extended_msrs); diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 5d241ce94a44..509bd3d9eacd 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -37,7 +37,7 @@ static struct fixed_range_block fixed_range_blocks[] = { static unsigned long smp_changes_mask; static struct mtrr_state mtrr_state = {}; static int mtrr_state_set; -static u64 tom2; +u64 mtrr_tom2; #undef MODULE_PARAM_PREFIX #define MODULE_PARAM_PREFIX "mtrr." @@ -139,8 +139,8 @@ u8 mtrr_type_lookup(u64 start, u64 end) } } - if (tom2) { - if (start >= (1ULL<<32) && (end < tom2)) + if (mtrr_tom2) { + if (start >= (1ULL<<32) && (end < mtrr_tom2)) return MTRR_TYPE_WRBACK; } @@ -158,6 +158,20 @@ get_mtrr_var_range(unsigned int index, struct mtrr_var_range *vr) rdmsr(MTRRphysMask_MSR(index), vr->mask_lo, vr->mask_hi); } +/* fill the MSR pair relating to a var range */ +void fill_mtrr_var_range(unsigned int index, + u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi) +{ + struct mtrr_var_range *vr; + + vr = mtrr_state.var_ranges; + + vr[index].base_lo = base_lo; + vr[index].base_hi = base_hi; + vr[index].mask_lo = mask_lo; + vr[index].mask_hi = mask_hi; +} + static void get_fixed_ranges(mtrr_type * frs) { @@ -213,13 +227,13 @@ void __init get_mtrr_state(void) mtrr_state.enabled = (lo & 0xc00) >> 10; if (amd_special_default_mtrr()) { - unsigned lo, hi; + unsigned low, high; /* TOP_MEM2 */ - rdmsr(MSR_K8_TOP_MEM2, lo, hi); - tom2 = hi; - tom2 <<= 32; - tom2 |= lo; - tom2 &= 0xffffff8000000ULL; + rdmsr(MSR_K8_TOP_MEM2, low, high); + mtrr_tom2 = high; + mtrr_tom2 <<= 32; + mtrr_tom2 |= low; + mtrr_tom2 &= 0xffffff800000ULL; } if (mtrr_show) { int high_width; @@ -251,9 +265,9 @@ void __init get_mtrr_state(void) else printk(KERN_INFO "MTRR %u disabled\n", i); } - if (tom2) { + if (mtrr_tom2) { printk(KERN_INFO "TOM2: %016llx aka %lldM\n", - tom2, tom2>>20); + mtrr_tom2, mtrr_tom2>>20); } } mtrr_state_set = 1; @@ -328,7 +342,7 @@ static void set_fixed_range(int msr, bool *changed, unsigned int *msrwords) if (lo != msrwords[0] || hi != msrwords[1]) { if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD && - boot_cpu_data.x86 == 15 && + (boot_cpu_data.x86 >= 0x0f && boot_cpu_data.x86 <= 0x11) && ((msrwords[0] | msrwords[1]) & K8_MTRR_RDMEM_WRMEM_MASK)) k8_enable_fixed_iorrs(); mtrr_wrmsr(msr, msrwords[0], msrwords[1]); diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 6a1e278d9323..6f23969c8faf 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -37,6 +37,7 @@ #include <linux/smp.h> #include <linux/cpu.h> #include <linux/mutex.h> +#include <linux/sort.h> #include <asm/e820.h> #include <asm/mtrr.h> @@ -222,7 +223,7 @@ static void set_mtrr(unsigned int reg, unsigned long base, atomic_set(&data.gate,0); /* Start the ball rolling on other CPUs */ - if (smp_call_function(ipi_handler, &data, 1, 0) != 0) + if (smp_call_function(ipi_handler, &data, 0) != 0) panic("mtrr: timed out waiting for other CPUs\n"); local_irq_save(flags); @@ -609,6 +610,787 @@ static struct sysdev_driver mtrr_sysdev_driver = { .resume = mtrr_restore, }; +/* should be related to MTRR_VAR_RANGES nums */ +#define RANGE_NUM 256 + +struct res_range { + unsigned long start; + unsigned long end; +}; + +static int __init +add_range(struct res_range *range, int nr_range, unsigned long start, + unsigned long end) +{ + /* out of slots */ + if (nr_range >= RANGE_NUM) + return nr_range; + + range[nr_range].start = start; + range[nr_range].end = end; + + nr_range++; + + return nr_range; +} + +static int __init +add_range_with_merge(struct res_range *range, int nr_range, unsigned long start, + unsigned long end) +{ + int i; + + /* try to merge it with old one */ + for (i = 0; i < nr_range; i++) { + unsigned long final_start, final_end; + unsigned long common_start, common_end; + + if (!range[i].end) + continue; + + common_start = max(range[i].start, start); + common_end = min(range[i].end, end); + if (common_start > common_end + 1) + continue; + + final_start = min(range[i].start, start); + final_end = max(range[i].end, end); + + range[i].start = final_start; + range[i].end = final_end; + return nr_range; + } + + /* need to add that */ + return add_range(range, nr_range, start, end); +} + +static void __init +subtract_range(struct res_range *range, unsigned long start, unsigned long end) +{ + int i, j; + + for (j = 0; j < RANGE_NUM; j++) { + if (!range[j].end) + continue; + + if (start <= range[j].start && end >= range[j].end) { + range[j].start = 0; + range[j].end = 0; + continue; + } + + if (start <= range[j].start && end < range[j].end && + range[j].start < end + 1) { + range[j].start = end + 1; + continue; + } + + + if (start > range[j].start && end >= range[j].end && + range[j].end > start - 1) { + range[j].end = start - 1; + continue; + } + + if (start > range[j].start && end < range[j].end) { + /* find the new spare */ + for (i = 0; i < RANGE_NUM; i++) { + if (range[i].end == 0) + break; + } + if (i < RANGE_NUM) { + range[i].end = range[j].end; + range[i].start = end + 1; + } else { + printk(KERN_ERR "run of slot in ranges\n"); + } + range[j].end = start - 1; + continue; + } + } +} + +static int __init cmp_range(const void *x1, const void *x2) +{ + const struct res_range *r1 = x1; + const struct res_range *r2 = x2; + long start1, start2; + + start1 = r1->start; + start2 = r2->start; + + return start1 - start2; +} + +struct var_mtrr_range_state { + unsigned long base_pfn; + unsigned long size_pfn; + mtrr_type type; +}; + +struct var_mtrr_range_state __initdata range_state[RANGE_NUM]; +static int __initdata debug_print; + +static int __init +x86_get_mtrr_mem_range(struct res_range *range, int nr_range, + unsigned long extra_remove_base, + unsigned long extra_remove_size) +{ + unsigned long i, base, size; + mtrr_type type; + + for (i = 0; i < num_var_ranges; i++) { + type = range_state[i].type; + if (type != MTRR_TYPE_WRBACK) + continue; + base = range_state[i].base_pfn; + size = range_state[i].size_pfn; + nr_range = add_range_with_merge(range, nr_range, base, + base + size - 1); + } + if (debug_print) { + printk(KERN_DEBUG "After WB checking\n"); + for (i = 0; i < nr_range; i++) + printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n", + range[i].start, range[i].end + 1); + } + + /* take out UC ranges */ + for (i = 0; i < num_var_ranges; i++) { + type = range_state[i].type; + if (type != MTRR_TYPE_UNCACHABLE) + continue; + size = range_state[i].size_pfn; + if (!size) + continue; + base = range_state[i].base_pfn; + subtract_range(range, base, base + size - 1); + } + if (extra_remove_size) + subtract_range(range, extra_remove_base, + extra_remove_base + extra_remove_size - 1); + + /* get new range num */ + nr_range = 0; + for (i = 0; i < RANGE_NUM; i++) { + if (!range[i].end) + continue; + nr_range++; + } + if (debug_print) { + printk(KERN_DEBUG "After UC checking\n"); + for (i = 0; i < nr_range; i++) + printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n", + range[i].start, range[i].end + 1); + } + + /* sort the ranges */ + sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL); + if (debug_print) { + printk(KERN_DEBUG "After sorting\n"); + for (i = 0; i < nr_range; i++) + printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n", + range[i].start, range[i].end + 1); + } + + /* clear those is not used */ + for (i = nr_range; i < RANGE_NUM; i++) + memset(&range[i], 0, sizeof(range[i])); + + return nr_range; +} + +static struct res_range __initdata range[RANGE_NUM]; + +#ifdef CONFIG_MTRR_SANITIZER + +static unsigned long __init sum_ranges(struct res_range *range, int nr_range) +{ + unsigned long sum; + int i; + + sum = 0; + for (i = 0; i < nr_range; i++) + sum += range[i].end + 1 - range[i].start; + + return sum; +} + +static int enable_mtrr_cleanup __initdata = + CONFIG_MTRR_SANITIZER_ENABLE_DEFAULT; + +static int __init disable_mtrr_cleanup_setup(char *str) +{ + if (enable_mtrr_cleanup != -1) + enable_mtrr_cleanup = 0; + return 0; +} +early_param("disable_mtrr_cleanup", disable_mtrr_cleanup_setup); + +static int __init enable_mtrr_cleanup_setup(char *str) +{ + if (enable_mtrr_cleanup != -1) + enable_mtrr_cleanup = 1; + return 0; +} +early_param("enble_mtrr_cleanup", enable_mtrr_cleanup_setup); + +struct var_mtrr_state { + unsigned long range_startk; + unsigned long range_sizek; + unsigned long chunk_sizek; + unsigned long gran_sizek; + unsigned int reg; +}; + +static void __init +set_var_mtrr(unsigned int reg, unsigned long basek, unsigned long sizek, + unsigned char type, unsigned int address_bits) +{ + u32 base_lo, base_hi, mask_lo, mask_hi; + u64 base, mask; + + if (!sizek) { + fill_mtrr_var_range(reg, 0, 0, 0, 0); + return; + } + + mask = (1ULL << address_bits) - 1; + mask &= ~((((u64)sizek) << 10) - 1); + + base = ((u64)basek) << 10; + + base |= type; + mask |= 0x800; + + base_lo = base & ((1ULL<<32) - 1); + base_hi = base >> 32; + + mask_lo = mask & ((1ULL<<32) - 1); + mask_hi = mask >> 32; + + fill_mtrr_var_range(reg, base_lo, base_hi, mask_lo, mask_hi); +} + +static void __init +save_var_mtrr(unsigned int reg, unsigned long basek, unsigned long sizek, + unsigned char type) +{ + range_state[reg].base_pfn = basek >> (PAGE_SHIFT - 10); + range_state[reg].size_pfn = sizek >> (PAGE_SHIFT - 10); + range_state[reg].type = type; +} + +static void __init +set_var_mtrr_all(unsigned int address_bits) +{ + unsigned long basek, sizek; + unsigned char type; + unsigned int reg; + + for (reg = 0; reg < num_var_ranges; reg++) { + basek = range_state[reg].base_pfn << (PAGE_SHIFT - 10); + sizek = range_state[reg].size_pfn << (PAGE_SHIFT - 10); + type = range_state[reg].type; + + set_var_mtrr(reg, basek, sizek, type, address_bits); + } +} + +static unsigned int __init +range_to_mtrr(unsigned int reg, unsigned long range_startk, + unsigned long range_sizek, unsigned char type) +{ + if (!range_sizek || (reg >= num_var_ranges)) + return reg; + + while (range_sizek) { + unsigned long max_align, align; + unsigned long sizek; + + /* Compute the maximum size I can make a range */ + if (range_startk) + max_align = ffs(range_startk) - 1; + else + max_align = 32; + align = fls(range_sizek) - 1; + if (align > max_align) + align = max_align; + + sizek = 1 << align; + if (debug_print) + printk(KERN_DEBUG "Setting variable MTRR %d, " + "base: %ldMB, range: %ldMB, type %s\n", + reg, range_startk >> 10, sizek >> 10, + (type == MTRR_TYPE_UNCACHABLE)?"UC": + ((type == MTRR_TYPE_WRBACK)?"WB":"Other") + ); + save_var_mtrr(reg++, range_startk, sizek, type); + range_startk += sizek; + range_sizek -= sizek; + if (reg >= num_var_ranges) + break; + } + return reg; +} + +static unsigned __init +range_to_mtrr_with_hole(struct var_mtrr_state *state, unsigned long basek, + unsigned long sizek) +{ + unsigned long hole_basek, hole_sizek; + unsigned long second_basek, second_sizek; + unsigned long range0_basek, range0_sizek; + unsigned long range_basek, range_sizek; + unsigned long chunk_sizek; + unsigned long gran_sizek; + + hole_basek = 0; + hole_sizek = 0; + second_basek = 0; + second_sizek = 0; + chunk_sizek = state->chunk_sizek; + gran_sizek = state->gran_sizek; + + /* align with gran size, prevent small block used up MTRRs */ + range_basek = ALIGN(state->range_startk, gran_sizek); + if ((range_basek > basek) && basek) + return second_sizek; + state->range_sizek -= (range_basek - state->range_startk); + range_sizek = ALIGN(state->range_sizek, gran_sizek); + + while (range_sizek > state->range_sizek) { + range_sizek -= gran_sizek; + if (!range_sizek) + return 0; + } + state->range_sizek = range_sizek; + + /* try to append some small hole */ + range0_basek = state->range_startk; + range0_sizek = ALIGN(state->range_sizek, chunk_sizek); + if (range0_sizek == state->range_sizek) { + if (debug_print) + printk(KERN_DEBUG "rangeX: %016lx - %016lx\n", + range0_basek<<10, + (range0_basek + state->range_sizek)<<10); + state->reg = range_to_mtrr(state->reg, range0_basek, + state->range_sizek, MTRR_TYPE_WRBACK); + return 0; + } + + range0_sizek -= chunk_sizek; + if (range0_sizek && sizek) { + while (range0_basek + range0_sizek > (basek + sizek)) { + range0_sizek -= chunk_sizek; + if (!range0_sizek) + break; + } + } + + if (range0_sizek) { + if (debug_print) + printk(KERN_DEBUG "range0: %016lx - %016lx\n", + range0_basek<<10, + (range0_basek + range0_sizek)<<10); + state->reg = range_to_mtrr(state->reg, range0_basek, + range0_sizek, MTRR_TYPE_WRBACK); + + } + + range_basek = range0_basek + range0_sizek; + range_sizek = chunk_sizek; + + if (range_basek + range_sizek > basek && + range_basek + range_sizek <= (basek + sizek)) { + /* one hole */ + second_basek = basek; + second_sizek = range_basek + range_sizek - basek; + } + + /* if last piece, only could one hole near end */ + if ((second_basek || !basek) && + range_sizek - (state->range_sizek - range0_sizek) - second_sizek < + (chunk_sizek >> 1)) { + /* + * one hole in middle (second_sizek is 0) or at end + * (second_sizek is 0 ) + */ + hole_sizek = range_sizek - (state->range_sizek - range0_sizek) + - second_sizek; + hole_basek = range_basek + range_sizek - hole_sizek + - second_sizek; + } else { + /* fallback for big hole, or several holes */ + range_sizek = state->range_sizek - range0_sizek; + second_basek = 0; + second_sizek = 0; + } + + if (debug_print) + printk(KERN_DEBUG "range: %016lx - %016lx\n", range_basek<<10, + (range_basek + range_sizek)<<10); + state->reg = range_to_mtrr(state->reg, range_basek, range_sizek, + MTRR_TYPE_WRBACK); + if (hole_sizek) { + if (debug_print) + printk(KERN_DEBUG "hole: %016lx - %016lx\n", + hole_basek<<10, (hole_basek + hole_sizek)<<10); + state->reg = range_to_mtrr(state->reg, hole_basek, hole_sizek, + MTRR_TYPE_UNCACHABLE); + + } + + return second_sizek; +} + +static void __init +set_var_mtrr_range(struct var_mtrr_state *state, unsigned long base_pfn, + unsigned long size_pfn) +{ + unsigned long basek, sizek; + unsigned long second_sizek = 0; + + if (state->reg >= num_var_ranges) + return; + + basek = base_pfn << (PAGE_SHIFT - 10); + sizek = size_pfn << (PAGE_SHIFT - 10); + + /* See if I can merge with the last range */ + if ((basek <= 1024) || + (state->range_startk + state->range_sizek == basek)) { + unsigned long endk = basek + sizek; + state->range_sizek = endk - state->range_startk; + return; + } + /* Write the range mtrrs */ + if (state->range_sizek != 0) + second_sizek = range_to_mtrr_with_hole(state, basek, sizek); + + /* Allocate an msr */ + state->range_startk = basek + second_sizek; + state->range_sizek = sizek - second_sizek; +} + +/* mininum size of mtrr block that can take hole */ +static u64 mtrr_chunk_size __initdata = (256ULL<<20); + +static int __init parse_mtrr_chunk_size_opt(char *p) +{ + if (!p) + return -EINVAL; + mtrr_chunk_size = memparse(p, &p); + return 0; +} +early_param("mtrr_chunk_size", parse_mtrr_chunk_size_opt); + +/* granity of mtrr of block */ +static u64 mtrr_gran_size __initdata; + +static int __init parse_mtrr_gran_size_opt(char *p) +{ + if (!p) + return -EINVAL; + mtrr_gran_size = memparse(p, &p); + return 0; +} +early_param("mtrr_gran_size", parse_mtrr_gran_size_opt); + +static int nr_mtrr_spare_reg __initdata = + CONFIG_MTRR_SANITIZER_SPARE_REG_NR_DEFAULT; + +static int __init parse_mtrr_spare_reg(char *arg) +{ + if (arg) + nr_mtrr_spare_reg = simple_strtoul(arg, NULL, 0); + return 0; +} + +early_param("mtrr_spare_reg_nr", parse_mtrr_spare_reg); + +static int __init +x86_setup_var_mtrrs(struct res_range *range, int nr_range, + u64 chunk_size, u64 gran_size) +{ + struct var_mtrr_state var_state; + int i; + int num_reg; + + var_state.range_startk = 0; + var_state.range_sizek = 0; + var_state.reg = 0; + var_state.chunk_sizek = chunk_size >> 10; + var_state.gran_sizek = gran_size >> 10; + + memset(range_state, 0, sizeof(range_state)); + + /* Write the range etc */ + for (i = 0; i < nr_range; i++) + set_var_mtrr_range(&var_state, range[i].start, + range[i].end - range[i].start + 1); + + /* Write the last range */ + if (var_state.range_sizek != 0) + range_to_mtrr_with_hole(&var_state, 0, 0); + + num_reg = var_state.reg; + /* Clear out the extra MTRR's */ + while (var_state.reg < num_var_ranges) { + save_var_mtrr(var_state.reg, 0, 0, 0); + var_state.reg++; + } + + return num_reg; +} + +struct mtrr_cleanup_result { + unsigned long gran_sizek; + unsigned long chunk_sizek; + unsigned long lose_cover_sizek; + unsigned int num_reg; + int bad; +}; + +/* + * gran_size: 1M, 2M, ..., 2G + * chunk size: gran_size, ..., 4G + * so we need (2+13)*6 + */ +#define NUM_RESULT 90 +#define PSHIFT (PAGE_SHIFT - 10) + +static struct mtrr_cleanup_result __initdata result[NUM_RESULT]; +static struct res_range __initdata range_new[RANGE_NUM]; +static unsigned long __initdata min_loss_pfn[RANGE_NUM]; + +static int __init mtrr_cleanup(unsigned address_bits) +{ + unsigned long extra_remove_base, extra_remove_size; + unsigned long i, base, size, def, dummy; + mtrr_type type; + int nr_range, nr_range_new; + u64 chunk_size, gran_size; + unsigned long range_sums, range_sums_new; + int index_good; + int num_reg_good; + + /* extra one for all 0 */ + int num[MTRR_NUM_TYPES + 1]; + + if (!is_cpu(INTEL) || enable_mtrr_cleanup < 1) + return 0; + rdmsr(MTRRdefType_MSR, def, dummy); + def &= 0xff; + if (def != MTRR_TYPE_UNCACHABLE) + return 0; + + /* get it and store it aside */ + memset(range_state, 0, sizeof(range_state)); + for (i = 0; i < num_var_ranges; i++) { + mtrr_if->get(i, &base, &size, &type); + range_state[i].base_pfn = base; + range_state[i].size_pfn = size; + range_state[i].type = type; + } + + /* check entries number */ + memset(num, 0, sizeof(num)); + for (i = 0; i < num_var_ranges; i++) { + type = range_state[i].type; + size = range_state[i].size_pfn; + if (type >= MTRR_NUM_TYPES) + continue; + if (!size) + type = MTRR_NUM_TYPES; + num[type]++; + } + + /* check if we got UC entries */ + if (!num[MTRR_TYPE_UNCACHABLE]) + return 0; + + /* check if we only had WB and UC */ + if (num[MTRR_TYPE_WRBACK] + num[MTRR_TYPE_UNCACHABLE] != + num_var_ranges - num[MTRR_NUM_TYPES]) + return 0; + + memset(range, 0, sizeof(range)); + extra_remove_size = 0; + if (mtrr_tom2) { + extra_remove_base = 1 << (32 - PAGE_SHIFT); + extra_remove_size = + (mtrr_tom2 >> PAGE_SHIFT) - extra_remove_base; + } + nr_range = x86_get_mtrr_mem_range(range, 0, extra_remove_base, + extra_remove_size); + range_sums = sum_ranges(range, nr_range); + printk(KERN_INFO "total RAM coverred: %ldM\n", + range_sums >> (20 - PAGE_SHIFT)); + + if (mtrr_chunk_size && mtrr_gran_size) { + int num_reg; + + debug_print = 1; + /* convert ranges to var ranges state */ + num_reg = x86_setup_var_mtrrs(range, nr_range, mtrr_chunk_size, + mtrr_gran_size); + + /* we got new setting in range_state, check it */ + memset(range_new, 0, sizeof(range_new)); + nr_range_new = x86_get_mtrr_mem_range(range_new, 0, + extra_remove_base, + extra_remove_size); + range_sums_new = sum_ranges(range_new, nr_range_new); + + i = 0; + result[i].chunk_sizek = mtrr_chunk_size >> 10; + result[i].gran_sizek = mtrr_gran_size >> 10; + result[i].num_reg = num_reg; + if (range_sums < range_sums_new) { + result[i].lose_cover_sizek = + (range_sums_new - range_sums) << PSHIFT; + result[i].bad = 1; + } else + result[i].lose_cover_sizek = + (range_sums - range_sums_new) << PSHIFT; + + printk(KERN_INFO "%sgran_size: %ldM \tchunk_size: %ldM \t", + result[i].bad?"*BAD*":" ", result[i].gran_sizek >> 10, + result[i].chunk_sizek >> 10); + printk(KERN_CONT "num_reg: %d \tlose cover RAM: %s%ldM \n", + result[i].num_reg, result[i].bad?"-":"", + result[i].lose_cover_sizek >> 10); + if (!result[i].bad) { + set_var_mtrr_all(address_bits); + return 1; + } + printk(KERN_INFO "invalid mtrr_gran_size or mtrr_chunk_size, " + "will find optimal one\n"); + debug_print = 0; + memset(result, 0, sizeof(result[0])); + } + + i = 0; + memset(min_loss_pfn, 0xff, sizeof(min_loss_pfn)); + memset(result, 0, sizeof(result)); + for (gran_size = (1ULL<<20); gran_size < (1ULL<<32); gran_size <<= 1) { + for (chunk_size = gran_size; chunk_size < (1ULL<<33); + chunk_size <<= 1) { + int num_reg; + + if (debug_print) + printk(KERN_INFO + "\ngran_size: %lldM chunk_size_size: %lldM\n", + gran_size >> 20, chunk_size >> 20); + if (i >= NUM_RESULT) + continue; + + /* convert ranges to var ranges state */ + num_reg = x86_setup_var_mtrrs(range, nr_range, + chunk_size, gran_size); + + /* we got new setting in range_state, check it */ + memset(range_new, 0, sizeof(range_new)); + nr_range_new = x86_get_mtrr_mem_range(range_new, 0, + extra_remove_base, extra_remove_size); + range_sums_new = sum_ranges(range_new, nr_range_new); + + result[i].chunk_sizek = chunk_size >> 10; + result[i].gran_sizek = gran_size >> 10; + result[i].num_reg = num_reg; + if (range_sums < range_sums_new) { + result[i].lose_cover_sizek = + (range_sums_new - range_sums) << PSHIFT; + result[i].bad = 1; + } else + result[i].lose_cover_sizek = + (range_sums - range_sums_new) << PSHIFT; + + /* double check it */ + if (!result[i].bad && !result[i].lose_cover_sizek) { + if (nr_range_new != nr_range || + memcmp(range, range_new, sizeof(range))) + result[i].bad = 1; + } + + if (!result[i].bad && (range_sums - range_sums_new < + min_loss_pfn[num_reg])) { + min_loss_pfn[num_reg] = + range_sums - range_sums_new; + } + i++; + } + } + + /* print out all */ + for (i = 0; i < NUM_RESULT; i++) { + printk(KERN_INFO "%sgran_size: %ldM \tchunk_size: %ldM \t", + result[i].bad?"*BAD* ":" ", result[i].gran_sizek >> 10, + result[i].chunk_sizek >> 10); + printk(KERN_CONT "num_reg: %d \tlose RAM: %s%ldM\n", + result[i].num_reg, result[i].bad?"-":"", + result[i].lose_cover_sizek >> 10); + } + + /* try to find the optimal index */ + if (nr_mtrr_spare_reg >= num_var_ranges) + nr_mtrr_spare_reg = num_var_ranges - 1; + num_reg_good = -1; + for (i = num_var_ranges - nr_mtrr_spare_reg; i > 0; i--) { + if (!min_loss_pfn[i]) { + num_reg_good = i; + break; + } + } + + index_good = -1; + if (num_reg_good != -1) { + for (i = 0; i < NUM_RESULT; i++) { + if (!result[i].bad && + result[i].num_reg == num_reg_good && + !result[i].lose_cover_sizek) { + index_good = i; + break; + } + } + } + + if (index_good != -1) { + printk(KERN_INFO "Found optimal setting for mtrr clean up\n"); + i = index_good; + printk(KERN_INFO "gran_size: %ldM \tchunk_size: %ldM \t", + result[i].gran_sizek >> 10, + result[i].chunk_sizek >> 10); + printk(KERN_CONT "num_reg: %d \tlose RAM: %ldM\n", + result[i].num_reg, + result[i].lose_cover_sizek >> 10); + /* convert ranges to var ranges state */ + chunk_size = result[i].chunk_sizek; + chunk_size <<= 10; + gran_size = result[i].gran_sizek; + gran_size <<= 10; + debug_print = 1; + x86_setup_var_mtrrs(range, nr_range, chunk_size, gran_size); + set_var_mtrr_all(address_bits); + return 1; + } + + printk(KERN_INFO "mtrr_cleanup: can not find optimal value\n"); + printk(KERN_INFO "please specify mtrr_gran_size/mtrr_chunk_size\n"); + + return 0; +} +#else +static int __init mtrr_cleanup(unsigned address_bits) +{ + return 0; +} +#endif + +static int __initdata changed_by_mtrr_cleanup; + static int disable_mtrr_trim; static int __init disable_mtrr_trim_setup(char *str) @@ -648,6 +1430,19 @@ int __init amd_special_default_mtrr(void) return 0; } +static u64 __init real_trim_memory(unsigned long start_pfn, + unsigned long limit_pfn) +{ + u64 trim_start, trim_size; + trim_start = start_pfn; + trim_start <<= PAGE_SHIFT; + trim_size = limit_pfn; + trim_size <<= PAGE_SHIFT; + trim_size -= trim_start; + + return e820_update_range(trim_start, trim_size, E820_RAM, + E820_RESERVED); +} /** * mtrr_trim_uncached_memory - trim RAM not covered by MTRRs * @end_pfn: ending page frame number @@ -663,8 +1458,11 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) { unsigned long i, base, size, highest_pfn = 0, def, dummy; mtrr_type type; - u64 trim_start, trim_size; + int nr_range; + u64 total_trim_size; + /* extra one for all 0 */ + int num[MTRR_NUM_TYPES + 1]; /* * Make sure we only trim uncachable memory on machines that * support the Intel MTRR architecture: @@ -676,14 +1474,22 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) if (def != MTRR_TYPE_UNCACHABLE) return 0; - if (amd_special_default_mtrr()) - return 0; + /* get it and store it aside */ + memset(range_state, 0, sizeof(range_state)); + for (i = 0; i < num_var_ranges; i++) { + mtrr_if->get(i, &base, &size, &type); + range_state[i].base_pfn = base; + range_state[i].size_pfn = size; + range_state[i].type = type; + } /* Find highest cached pfn */ for (i = 0; i < num_var_ranges; i++) { - mtrr_if->get(i, &base, &size, &type); + type = range_state[i].type; if (type != MTRR_TYPE_WRBACK) continue; + base = range_state[i].base_pfn; + size = range_state[i].size_pfn; if (highest_pfn < base + size) highest_pfn = base + size; } @@ -698,22 +1504,65 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) return 0; } - if (highest_pfn < end_pfn) { + /* check entries number */ + memset(num, 0, sizeof(num)); + for (i = 0; i < num_var_ranges; i++) { + type = range_state[i].type; + if (type >= MTRR_NUM_TYPES) + continue; + size = range_state[i].size_pfn; + if (!size) + type = MTRR_NUM_TYPES; + num[type]++; + } + + /* no entry for WB? */ + if (!num[MTRR_TYPE_WRBACK]) + return 0; + + /* check if we only had WB and UC */ + if (num[MTRR_TYPE_WRBACK] + num[MTRR_TYPE_UNCACHABLE] != + num_var_ranges - num[MTRR_NUM_TYPES]) + return 0; + + memset(range, 0, sizeof(range)); + nr_range = 0; + if (mtrr_tom2) { + range[nr_range].start = (1ULL<<(32 - PAGE_SHIFT)); + range[nr_range].end = (mtrr_tom2 >> PAGE_SHIFT) - 1; + if (highest_pfn < range[nr_range].end + 1) + highest_pfn = range[nr_range].end + 1; + nr_range++; + } + nr_range = x86_get_mtrr_mem_range(range, nr_range, 0, 0); + + total_trim_size = 0; + /* check the head */ + if (range[0].start) + total_trim_size += real_trim_memory(0, range[0].start); + /* check the holes */ + for (i = 0; i < nr_range - 1; i++) { + if (range[i].end + 1 < range[i+1].start) + total_trim_size += real_trim_memory(range[i].end + 1, + range[i+1].start); + } + /* check the top */ + i = nr_range - 1; + if (range[i].end + 1 < end_pfn) + total_trim_size += real_trim_memory(range[i].end + 1, + end_pfn); + + if (total_trim_size) { printk(KERN_WARNING "WARNING: BIOS bug: CPU MTRRs don't cover" - " all of memory, losing %luMB of RAM.\n", - (end_pfn - highest_pfn) >> (20 - PAGE_SHIFT)); + " all of memory, losing %lluMB of RAM.\n", + total_trim_size >> 20); - WARN_ON(1); + if (!changed_by_mtrr_cleanup) + WARN_ON(1); printk(KERN_INFO "update e820 for mtrr\n"); - trim_start = highest_pfn; - trim_start <<= PAGE_SHIFT; - trim_size = end_pfn; - trim_size <<= PAGE_SHIFT; - trim_size -= trim_start; - update_memory_range(trim_start, trim_size, E820_RAM, - E820_RESERVED); update_e820(); + return 1; } @@ -729,18 +1578,21 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) */ void __init mtrr_bp_init(void) { + u32 phys_addr; init_ifs(); + phys_addr = 32; + if (cpu_has_mtrr) { mtrr_if = &generic_mtrr_ops; size_or_mask = 0xff000000; /* 36 bits */ size_and_mask = 0x00f00000; + phys_addr = 36; /* This is an AMD specific MSR, but we assume(hope?) that Intel will implement it to when they extend the address bus of the Xeon. */ if (cpuid_eax(0x80000000) >= 0x80000008) { - u32 phys_addr; phys_addr = cpuid_eax(0x80000008) & 0xff; /* CPUID workaround for Intel 0F33/0F34 CPU */ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && @@ -758,6 +1610,7 @@ void __init mtrr_bp_init(void) don't support PAE */ size_or_mask = 0xfff00000; /* 32 bits */ size_and_mask = 0; + phys_addr = 32; } } else { switch (boot_cpu_data.x86_vendor) { @@ -791,8 +1644,15 @@ void __init mtrr_bp_init(void) if (mtrr_if) { set_num_var_ranges(); init_table(); - if (use_intel()) + if (use_intel()) { get_mtrr_state(); + + if (mtrr_cleanup(phys_addr)) { + changed_by_mtrr_cleanup = 1; + mtrr_if->set_all(); + } + + } } } @@ -822,16 +1682,17 @@ void mtrr_ap_init(void) */ void mtrr_save_state(void) { - smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1, 1); + smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1); } static int __init mtrr_init_finialize(void) { if (!mtrr_if) return 0; - if (use_intel()) - mtrr_state_warn(); - else { + if (use_intel()) { + if (!changed_by_mtrr_cleanup) + mtrr_state_warn(); + } else { /* The CPUs haven't MTRR and seem to not support SMP. They have * specific drivers, we use a tricky method to support * suspend/resume for them. diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index 2cc77eb6fea3..2dc4ec656b23 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -81,6 +81,8 @@ void set_mtrr_done(struct set_mtrr_context *ctxt); void set_mtrr_cache_disable(struct set_mtrr_context *ctxt); void set_mtrr_prepare_save(struct set_mtrr_context *ctxt); +void fill_mtrr_var_range(unsigned int index, + u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi); void get_mtrr_state(void); extern void set_mtrr_ops(struct mtrr_ops * ops); @@ -92,6 +94,7 @@ extern struct mtrr_ops * mtrr_if; #define use_intel() (mtrr_if && mtrr_if->use_intel_if == 1) extern unsigned int num_var_ranges; +extern u64 mtrr_tom2; void mtrr_state_warn(void); const char *mtrr_attrib_to_str(int x); diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index f9ae93adffe5..6d4bdc02388a 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -1,11 +1,15 @@ -/* local apic based NMI watchdog for various CPUs. - This file also handles reservation of performance counters for coordination - with other users (like oprofile). - - Note that these events normally don't tick when the CPU idles. This means - the frequency varies with CPU load. - - Original code for K7/P6 written by Keith Owens */ +/* + * local apic based NMI watchdog for various CPUs. + * + * This file also handles reservation of performance counters for coordination + * with other users (like oprofile). + * + * Note that these events normally don't tick when the CPU idles. This means + * the frequency varies with CPU load. + * + * Original code for K7/P6 written by Keith Owens + * + */ #include <linux/percpu.h> #include <linux/module.h> @@ -36,12 +40,16 @@ struct wd_ops { static const struct wd_ops *wd_ops; -/* this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's - * offset from MSR_P4_BSU_ESCR0. It will be the max for all platforms (for now) +/* + * this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's + * offset from MSR_P4_BSU_ESCR0. + * + * It will be the max for all platforms (for now) */ #define NMI_MAX_COUNTER_BITS 66 -/* perfctr_nmi_owner tracks the ownership of the perfctr registers: +/* + * perfctr_nmi_owner tracks the ownership of the perfctr registers: * evtsel_nmi_owner tracks the ownership of the event selection * - different performance counters/ event selection may be reserved for * different subsystems this reservation system just tries to coordinate @@ -73,8 +81,10 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr) return 0; } -/* converts an msr to an appropriate reservation bit */ -/* returns the bit offset of the event selection register */ +/* + * converts an msr to an appropriate reservation bit + * returns the bit offset of the event selection register + */ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr) { /* returns the bit offset of the event selection register */ @@ -114,6 +124,7 @@ int avail_to_resrv_perfctr_nmi(unsigned int msr) return (!test_bit(counter, perfctr_nmi_owner)); } +EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi_bit); int reserve_perfctr_nmi(unsigned int msr) { @@ -128,6 +139,7 @@ int reserve_perfctr_nmi(unsigned int msr) return 1; return 0; } +EXPORT_SYMBOL(reserve_perfctr_nmi); void release_perfctr_nmi(unsigned int msr) { @@ -140,6 +152,7 @@ void release_perfctr_nmi(unsigned int msr) clear_bit(counter, perfctr_nmi_owner); } +EXPORT_SYMBOL(release_perfctr_nmi); int reserve_evntsel_nmi(unsigned int msr) { @@ -154,6 +167,7 @@ int reserve_evntsel_nmi(unsigned int msr) return 1; return 0; } +EXPORT_SYMBOL(reserve_evntsel_nmi); void release_evntsel_nmi(unsigned int msr) { @@ -166,11 +180,6 @@ void release_evntsel_nmi(unsigned int msr) clear_bit(counter, evntsel_nmi_owner); } - -EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi_bit); -EXPORT_SYMBOL(reserve_perfctr_nmi); -EXPORT_SYMBOL(release_perfctr_nmi); -EXPORT_SYMBOL(reserve_evntsel_nmi); EXPORT_SYMBOL(release_evntsel_nmi); void disable_lapic_nmi_watchdog(void) @@ -180,8 +189,10 @@ void disable_lapic_nmi_watchdog(void) if (atomic_read(&nmi_active) <= 0) return; - on_each_cpu(stop_apic_nmi_watchdog, NULL, 0, 1); - wd_ops->unreserve(); + on_each_cpu(stop_apic_nmi_watchdog, NULL, 1); + + if (wd_ops) + wd_ops->unreserve(); BUG_ON(atomic_read(&nmi_active) != 0); } @@ -202,7 +213,7 @@ void enable_lapic_nmi_watchdog(void) return; } - on_each_cpu(setup_apic_nmi_watchdog, NULL, 0, 1); + on_each_cpu(setup_apic_nmi_watchdog, NULL, 1); touch_nmi_watchdog(); } @@ -232,8 +243,8 @@ static unsigned int adjust_for_32bit_ctr(unsigned int hz) return retval; } -static void -write_watchdog_counter(unsigned int perfctr_msr, const char *descr, unsigned nmi_hz) +static void write_watchdog_counter(unsigned int perfctr_msr, + const char *descr, unsigned nmi_hz) { u64 count = (u64)cpu_khz * 1000; @@ -244,7 +255,7 @@ write_watchdog_counter(unsigned int perfctr_msr, const char *descr, unsigned nmi } static void write_watchdog_counter32(unsigned int perfctr_msr, - const char *descr, unsigned nmi_hz) + const char *descr, unsigned nmi_hz) { u64 count = (u64)cpu_khz * 1000; @@ -254,9 +265,10 @@ static void write_watchdog_counter32(unsigned int perfctr_msr, wrmsr(perfctr_msr, (u32)(-count), 0); } -/* AMD K7/K8/Family10h/Family11h support. AMD keeps this interface - nicely stable so there is not much variety */ - +/* + * AMD K7/K8/Family10h/Family11h support. + * AMD keeps this interface nicely stable so there is not much variety + */ #define K7_EVNTSEL_ENABLE (1 << 22) #define K7_EVNTSEL_INT (1 << 20) #define K7_EVNTSEL_OS (1 << 17) @@ -289,7 +301,7 @@ static int setup_k7_watchdog(unsigned nmi_hz) wd->perfctr_msr = perfctr_msr; wd->evntsel_msr = evntsel_msr; - wd->cccr_msr = 0; //unused + wd->cccr_msr = 0; /* unused */ return 1; } @@ -325,18 +337,19 @@ static void single_msr_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz) } static const struct wd_ops k7_wd_ops = { - .reserve = single_msr_reserve, - .unreserve = single_msr_unreserve, - .setup = setup_k7_watchdog, - .rearm = single_msr_rearm, - .stop = single_msr_stop_watchdog, - .perfctr = MSR_K7_PERFCTR0, - .evntsel = MSR_K7_EVNTSEL0, - .checkbit = 1ULL<<47, + .reserve = single_msr_reserve, + .unreserve = single_msr_unreserve, + .setup = setup_k7_watchdog, + .rearm = single_msr_rearm, + .stop = single_msr_stop_watchdog, + .perfctr = MSR_K7_PERFCTR0, + .evntsel = MSR_K7_EVNTSEL0, + .checkbit = 1ULL << 47, }; -/* Intel Model 6 (PPro+,P2,P3,P-M,Core1) */ - +/* + * Intel Model 6 (PPro+,P2,P3,P-M,Core1) + */ #define P6_EVNTSEL0_ENABLE (1 << 22) #define P6_EVNTSEL_INT (1 << 20) #define P6_EVNTSEL_OS (1 << 17) @@ -372,52 +385,58 @@ static int setup_p6_watchdog(unsigned nmi_hz) wd->perfctr_msr = perfctr_msr; wd->evntsel_msr = evntsel_msr; - wd->cccr_msr = 0; //unused + wd->cccr_msr = 0; /* unused */ return 1; } static void p6_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz) { - /* P6 based Pentium M need to re-unmask + /* + * P6 based Pentium M need to re-unmask * the apic vector but it doesn't hurt * other P6 variant. - * ArchPerfom/Core Duo also needs this */ + * ArchPerfom/Core Duo also needs this + */ apic_write(APIC_LVTPC, APIC_DM_NMI); + /* P6/ARCH_PERFMON has 32 bit counter write */ write_watchdog_counter32(wd->perfctr_msr, NULL,nmi_hz); } static const struct wd_ops p6_wd_ops = { - .reserve = single_msr_reserve, - .unreserve = single_msr_unreserve, - .setup = setup_p6_watchdog, - .rearm = p6_rearm, - .stop = single_msr_stop_watchdog, - .perfctr = MSR_P6_PERFCTR0, - .evntsel = MSR_P6_EVNTSEL0, - .checkbit = 1ULL<<39, + .reserve = single_msr_reserve, + .unreserve = single_msr_unreserve, + .setup = setup_p6_watchdog, + .rearm = p6_rearm, + .stop = single_msr_stop_watchdog, + .perfctr = MSR_P6_PERFCTR0, + .evntsel = MSR_P6_EVNTSEL0, + .checkbit = 1ULL << 39, }; -/* Intel P4 performance counters. By far the most complicated of all. */ - -#define MSR_P4_MISC_ENABLE_PERF_AVAIL (1<<7) -#define P4_ESCR_EVENT_SELECT(N) ((N)<<25) -#define P4_ESCR_OS (1<<3) -#define P4_ESCR_USR (1<<2) -#define P4_CCCR_OVF_PMI0 (1<<26) -#define P4_CCCR_OVF_PMI1 (1<<27) -#define P4_CCCR_THRESHOLD(N) ((N)<<20) -#define P4_CCCR_COMPLEMENT (1<<19) -#define P4_CCCR_COMPARE (1<<18) -#define P4_CCCR_REQUIRED (3<<16) -#define P4_CCCR_ESCR_SELECT(N) ((N)<<13) -#define P4_CCCR_ENABLE (1<<12) -#define P4_CCCR_OVF (1<<31) - -/* Set up IQ_COUNTER0 to behave like a clock, by having IQ_CCCR0 filter - CRU_ESCR0 (with any non-null event selector) through a complemented - max threshold. [IA32-Vol3, Section 14.9.9] */ +/* + * Intel P4 performance counters. + * By far the most complicated of all. + */ +#define MSR_P4_MISC_ENABLE_PERF_AVAIL (1 << 7) +#define P4_ESCR_EVENT_SELECT(N) ((N) << 25) +#define P4_ESCR_OS (1 << 3) +#define P4_ESCR_USR (1 << 2) +#define P4_CCCR_OVF_PMI0 (1 << 26) +#define P4_CCCR_OVF_PMI1 (1 << 27) +#define P4_CCCR_THRESHOLD(N) ((N) << 20) +#define P4_CCCR_COMPLEMENT (1 << 19) +#define P4_CCCR_COMPARE (1 << 18) +#define P4_CCCR_REQUIRED (3 << 16) +#define P4_CCCR_ESCR_SELECT(N) ((N) << 13) +#define P4_CCCR_ENABLE (1 << 12) +#define P4_CCCR_OVF (1 << 31) +/* + * Set up IQ_COUNTER0 to behave like a clock, by having IQ_CCCR0 filter + * CRU_ESCR0 (with any non-null event selector) through a complemented + * max threshold. [IA32-Vol3, Section 14.9.9] + */ static int setup_p4_watchdog(unsigned nmi_hz) { unsigned int perfctr_msr, evntsel_msr, cccr_msr; @@ -442,7 +461,8 @@ static int setup_p4_watchdog(unsigned nmi_hz) #endif ht_num = 0; - /* performance counters are shared resources + /* + * performance counters are shared resources * assign each hyperthread its own set * (re-use the ESCR0 register, seems safe * and keeps the cccr_val the same) @@ -540,20 +560,21 @@ static void p4_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz) } static const struct wd_ops p4_wd_ops = { - .reserve = p4_reserve, - .unreserve = p4_unreserve, - .setup = setup_p4_watchdog, - .rearm = p4_rearm, - .stop = stop_p4_watchdog, + .reserve = p4_reserve, + .unreserve = p4_unreserve, + .setup = setup_p4_watchdog, + .rearm = p4_rearm, + .stop = stop_p4_watchdog, /* RED-PEN this is wrong for the other sibling */ - .perfctr = MSR_P4_BPU_PERFCTR0, - .evntsel = MSR_P4_BSU_ESCR0, - .checkbit = 1ULL<<39, + .perfctr = MSR_P4_BPU_PERFCTR0, + .evntsel = MSR_P4_BSU_ESCR0, + .checkbit = 1ULL << 39, }; -/* Watchdog using the Intel architected PerfMon. Used for Core2 and hopefully - all future Intel CPUs. */ - +/* + * Watchdog using the Intel architected PerfMon. + * Used for Core2 and hopefully all future Intel CPUs. + */ #define ARCH_PERFMON_NMI_EVENT_SEL ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL #define ARCH_PERFMON_NMI_EVENT_UMASK ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK @@ -599,19 +620,19 @@ static int setup_intel_arch_watchdog(unsigned nmi_hz) wd->perfctr_msr = perfctr_msr; wd->evntsel_msr = evntsel_msr; - wd->cccr_msr = 0; //unused + wd->cccr_msr = 0; /* unused */ intel_arch_wd_ops.checkbit = 1ULL << (eax.split.bit_width - 1); return 1; } static struct wd_ops intel_arch_wd_ops __read_mostly = { - .reserve = single_msr_reserve, - .unreserve = single_msr_unreserve, - .setup = setup_intel_arch_watchdog, - .rearm = p6_rearm, - .stop = single_msr_stop_watchdog, - .perfctr = MSR_ARCH_PERFMON_PERFCTR1, - .evntsel = MSR_ARCH_PERFMON_EVENTSEL1, + .reserve = single_msr_reserve, + .unreserve = single_msr_unreserve, + .setup = setup_intel_arch_watchdog, + .rearm = p6_rearm, + .stop = single_msr_stop_watchdog, + .perfctr = MSR_ARCH_PERFMON_PERFCTR1, + .evntsel = MSR_ARCH_PERFMON_EVENTSEL1, }; static void probe_nmi_watchdog(void) @@ -624,8 +645,10 @@ static void probe_nmi_watchdog(void) wd_ops = &k7_wd_ops; break; case X86_VENDOR_INTEL: - /* Work around Core Duo (Yonah) errata AE49 where perfctr1 - doesn't have a working enable bit. */ + /* + * Work around Core Duo (Yonah) errata AE49 where perfctr1 + * doesn't have a working enable bit. + */ if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 14) { intel_arch_wd_ops.perfctr = MSR_ARCH_PERFMON_PERFCTR0; intel_arch_wd_ops.evntsel = MSR_ARCH_PERFMON_EVENTSEL0; @@ -636,7 +659,7 @@ static void probe_nmi_watchdog(void) } switch (boot_cpu_data.x86) { case 6: - if (boot_cpu_data.x86_model > 0xd) + if (boot_cpu_data.x86_model > 13) return; wd_ops = &p6_wd_ops; @@ -697,10 +720,11 @@ int lapic_wd_event(unsigned nmi_hz) { struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); u64 ctr; + rdmsrl(wd->perfctr_msr, ctr); - if (ctr & wd_ops->checkbit) { /* perfctr still running? */ + if (ctr & wd_ops->checkbit) /* perfctr still running? */ return 0; - } + wd_ops->rearm(wd, nmi_hz); return 1; } diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index daff52a62248..2de5fa2bbf77 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -33,6 +33,7 @@ #include <linux/init.h> #include <linux/poll.h> #include <linux/smp.h> +#include <linux/smp_lock.h> #include <linux/major.h> #include <linux/fs.h> #include <linux/smp_lock.h> @@ -95,7 +96,7 @@ static ssize_t cpuid_read(struct file *file, char __user *buf, for (; count; count -= 16) { cmd.eax = pos; cmd.ecx = pos >> 32; - smp_call_function_single(cpu, cpuid_smp_cpuid, &cmd, 1, 1); + smp_call_function_single(cpu, cpuid_smp_cpuid, &cmd, 1); if (copy_to_user(tmp, &cmd, 16)) return -EFAULT; tmp += 16; @@ -107,15 +108,23 @@ static ssize_t cpuid_read(struct file *file, char __user *buf, static int cpuid_open(struct inode *inode, struct file *file) { - unsigned int cpu = iminor(file->f_path.dentry->d_inode); - struct cpuinfo_x86 *c = &cpu_data(cpu); - - if (cpu >= NR_CPUS || !cpu_online(cpu)) - return -ENXIO; /* No such CPU */ + unsigned int cpu; + struct cpuinfo_x86 *c; + int ret = 0; + + lock_kernel(); + + cpu = iminor(file->f_path.dentry->d_inode); + if (cpu >= NR_CPUS || !cpu_online(cpu)) { + ret = -ENXIO; /* No such CPU */ + goto out; + } + c = &cpu_data(cpu); if (c->cpuid_level < 0) - return -EIO; /* CPUID not supported */ - - return 0; + ret = -EIO; /* CPUID not supported */ +out: + unlock_kernel(); + return ret; } /* diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c new file mode 100644 index 000000000000..28c29180b380 --- /dev/null +++ b/arch/x86/kernel/e820.c @@ -0,0 +1,1390 @@ +/* + * Handle the memory map. + * The functions here do the job until bootmem takes over. + * + * Getting sanitize_e820_map() in sync with i386 version by applying change: + * - Provisions for empty E820 memory regions (reported by certain BIOSes). + * Alex Achenbach <xela@slit.de>, December 2002. + * Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> + * + */ +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/init.h> +#include <linux/bootmem.h> +#include <linux/ioport.h> +#include <linux/string.h> +#include <linux/kexec.h> +#include <linux/module.h> +#include <linux/mm.h> +#include <linux/pfn.h> +#include <linux/suspend.h> +#include <linux/firmware-map.h> + +#include <asm/pgtable.h> +#include <asm/page.h> +#include <asm/e820.h> +#include <asm/proto.h> +#include <asm/setup.h> +#include <asm/trampoline.h> + +/* + * The e820 map is the map that gets modified e.g. with command line parameters + * and that is also registered with modifications in the kernel resource tree + * with the iomem_resource as parent. + * + * The e820_saved is directly saved after the BIOS-provided memory map is + * copied. It doesn't get modified afterwards. It's registered for the + * /sys/firmware/memmap interface. + * + * That memory map is not modified and is used as base for kexec. The kexec'd + * kernel should get the same memory map as the firmware provides. Then the + * user can e.g. boot the original kernel with mem=1G while still booting the + * next kernel with full memory. + */ +struct e820map e820; +struct e820map e820_saved; + +/* For PCI or other memory-mapped resources */ +unsigned long pci_mem_start = 0xaeedbabe; +#ifdef CONFIG_PCI +EXPORT_SYMBOL(pci_mem_start); +#endif + +/* + * This function checks if any part of the range <start,end> is mapped + * with type. + */ +int +e820_any_mapped(u64 start, u64 end, unsigned type) +{ + int i; + + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + + if (type && ei->type != type) + continue; + if (ei->addr >= end || ei->addr + ei->size <= start) + continue; + return 1; + } + return 0; +} +EXPORT_SYMBOL_GPL(e820_any_mapped); + +/* + * This function checks if the entire range <start,end> is mapped with type. + * + * Note: this function only works correct if the e820 table is sorted and + * not-overlapping, which is the case + */ +int __init e820_all_mapped(u64 start, u64 end, unsigned type) +{ + int i; + + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + + if (type && ei->type != type) + continue; + /* is the region (part) in overlap with the current region ?*/ + if (ei->addr >= end || ei->addr + ei->size <= start) + continue; + + /* if the region is at the beginning of <start,end> we move + * start to the end of the region since it's ok until there + */ + if (ei->addr <= start) + start = ei->addr + ei->size; + /* + * if start is now at or beyond end, we're done, full + * coverage + */ + if (start >= end) + return 1; + } + return 0; +} + +/* + * Add a memory region to the kernel e820 map. + */ +void __init e820_add_region(u64 start, u64 size, int type) +{ + int x = e820.nr_map; + + if (x == ARRAY_SIZE(e820.map)) { + printk(KERN_ERR "Ooops! Too many entries in the memory map!\n"); + return; + } + + e820.map[x].addr = start; + e820.map[x].size = size; + e820.map[x].type = type; + e820.nr_map++; +} + +void __init e820_print_map(char *who) +{ + int i; + + for (i = 0; i < e820.nr_map; i++) { + printk(KERN_INFO " %s: %016Lx - %016Lx ", who, + (unsigned long long) e820.map[i].addr, + (unsigned long long) + (e820.map[i].addr + e820.map[i].size)); + switch (e820.map[i].type) { + case E820_RAM: + case E820_RESERVED_KERN: + printk(KERN_CONT "(usable)\n"); + break; + case E820_RESERVED: + printk(KERN_CONT "(reserved)\n"); + break; + case E820_ACPI: + printk(KERN_CONT "(ACPI data)\n"); + break; + case E820_NVS: + printk(KERN_CONT "(ACPI NVS)\n"); + break; + default: + printk(KERN_CONT "type %u\n", e820.map[i].type); + break; + } + } +} + +/* + * Sanitize the BIOS e820 map. + * + * Some e820 responses include overlapping entries. The following + * replaces the original e820 map with a new one, removing overlaps, + * and resolving conflicting memory types in favor of highest + * numbered type. + * + * The input parameter biosmap points to an array of 'struct + * e820entry' which on entry has elements in the range [0, *pnr_map) + * valid, and which has space for up to max_nr_map entries. + * On return, the resulting sanitized e820 map entries will be in + * overwritten in the same location, starting at biosmap. + * + * The integer pointed to by pnr_map must be valid on entry (the + * current number of valid entries located at biosmap) and will + * be updated on return, with the new number of valid entries + * (something no more than max_nr_map.) + * + * The return value from sanitize_e820_map() is zero if it + * successfully 'sanitized' the map entries passed in, and is -1 + * if it did nothing, which can happen if either of (1) it was + * only passed one map entry, or (2) any of the input map entries + * were invalid (start + size < start, meaning that the size was + * so big the described memory range wrapped around through zero.) + * + * Visually we're performing the following + * (1,2,3,4 = memory types)... + * + * Sample memory map (w/overlaps): + * ____22__________________ + * ______________________4_ + * ____1111________________ + * _44_____________________ + * 11111111________________ + * ____________________33__ + * ___________44___________ + * __________33333_________ + * ______________22________ + * ___________________2222_ + * _________111111111______ + * _____________________11_ + * _________________4______ + * + * Sanitized equivalent (no overlap): + * 1_______________________ + * _44_____________________ + * ___1____________________ + * ____22__________________ + * ______11________________ + * _________1______________ + * __________3_____________ + * ___________44___________ + * _____________33_________ + * _______________2________ + * ________________1_______ + * _________________4______ + * ___________________2____ + * ____________________33__ + * ______________________4_ + */ + +int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, + int *pnr_map) +{ + struct change_member { + struct e820entry *pbios; /* pointer to original bios entry */ + unsigned long long addr; /* address for this change point */ + }; + static struct change_member change_point_list[2*E820_X_MAX] __initdata; + static struct change_member *change_point[2*E820_X_MAX] __initdata; + static struct e820entry *overlap_list[E820_X_MAX] __initdata; + static struct e820entry new_bios[E820_X_MAX] __initdata; + struct change_member *change_tmp; + unsigned long current_type, last_type; + unsigned long long last_addr; + int chgidx, still_changing; + int overlap_entries; + int new_bios_entry; + int old_nr, new_nr, chg_nr; + int i; + + /* if there's only one memory region, don't bother */ + if (*pnr_map < 2) + return -1; + + old_nr = *pnr_map; + BUG_ON(old_nr > max_nr_map); + + /* bail out if we find any unreasonable addresses in bios map */ + for (i = 0; i < old_nr; i++) + if (biosmap[i].addr + biosmap[i].size < biosmap[i].addr) + return -1; + + /* create pointers for initial change-point information (for sorting) */ + for (i = 0; i < 2 * old_nr; i++) + change_point[i] = &change_point_list[i]; + + /* record all known change-points (starting and ending addresses), + omitting those that are for empty memory regions */ + chgidx = 0; + for (i = 0; i < old_nr; i++) { + if (biosmap[i].size != 0) { + change_point[chgidx]->addr = biosmap[i].addr; + change_point[chgidx++]->pbios = &biosmap[i]; + change_point[chgidx]->addr = biosmap[i].addr + + biosmap[i].size; + change_point[chgidx++]->pbios = &biosmap[i]; + } + } + chg_nr = chgidx; + + /* sort change-point list by memory addresses (low -> high) */ + still_changing = 1; + while (still_changing) { + still_changing = 0; + for (i = 1; i < chg_nr; i++) { + unsigned long long curaddr, lastaddr; + unsigned long long curpbaddr, lastpbaddr; + + curaddr = change_point[i]->addr; + lastaddr = change_point[i - 1]->addr; + curpbaddr = change_point[i]->pbios->addr; + lastpbaddr = change_point[i - 1]->pbios->addr; + + /* + * swap entries, when: + * + * curaddr > lastaddr or + * curaddr == lastaddr and curaddr == curpbaddr and + * lastaddr != lastpbaddr + */ + if (curaddr < lastaddr || + (curaddr == lastaddr && curaddr == curpbaddr && + lastaddr != lastpbaddr)) { + change_tmp = change_point[i]; + change_point[i] = change_point[i-1]; + change_point[i-1] = change_tmp; + still_changing = 1; + } + } + } + + /* create a new bios memory map, removing overlaps */ + overlap_entries = 0; /* number of entries in the overlap table */ + new_bios_entry = 0; /* index for creating new bios map entries */ + last_type = 0; /* start with undefined memory type */ + last_addr = 0; /* start with 0 as last starting address */ + + /* loop through change-points, determining affect on the new bios map */ + for (chgidx = 0; chgidx < chg_nr; chgidx++) { + /* keep track of all overlapping bios entries */ + if (change_point[chgidx]->addr == + change_point[chgidx]->pbios->addr) { + /* + * add map entry to overlap list (> 1 entry + * implies an overlap) + */ + overlap_list[overlap_entries++] = + change_point[chgidx]->pbios; + } else { + /* + * remove entry from list (order independent, + * so swap with last) + */ + for (i = 0; i < overlap_entries; i++) { + if (overlap_list[i] == + change_point[chgidx]->pbios) + overlap_list[i] = + overlap_list[overlap_entries-1]; + } + overlap_entries--; + } + /* + * if there are overlapping entries, decide which + * "type" to use (larger value takes precedence -- + * 1=usable, 2,3,4,4+=unusable) + */ + current_type = 0; + for (i = 0; i < overlap_entries; i++) + if (overlap_list[i]->type > current_type) + current_type = overlap_list[i]->type; + /* + * continue building up new bios map based on this + * information + */ + if (current_type != last_type) { + if (last_type != 0) { + new_bios[new_bios_entry].size = + change_point[chgidx]->addr - last_addr; + /* + * move forward only if the new size + * was non-zero + */ + if (new_bios[new_bios_entry].size != 0) + /* + * no more space left for new + * bios entries ? + */ + if (++new_bios_entry >= max_nr_map) + break; + } + if (current_type != 0) { + new_bios[new_bios_entry].addr = + change_point[chgidx]->addr; + new_bios[new_bios_entry].type = current_type; + last_addr = change_point[chgidx]->addr; + } + last_type = current_type; + } + } + /* retain count for new bios entries */ + new_nr = new_bios_entry; + + /* copy new bios mapping into original location */ + memcpy(biosmap, new_bios, new_nr * sizeof(struct e820entry)); + *pnr_map = new_nr; + + return 0; +} + +static int __init __append_e820_map(struct e820entry *biosmap, int nr_map) +{ + while (nr_map) { + u64 start = biosmap->addr; + u64 size = biosmap->size; + u64 end = start + size; + u32 type = biosmap->type; + + /* Overflow in 64 bits? Ignore the memory map. */ + if (start > end) + return -1; + + e820_add_region(start, size, type); + + biosmap++; + nr_map--; + } + return 0; +} + +/* + * Copy the BIOS e820 map into a safe place. + * + * Sanity-check it while we're at it.. + * + * If we're lucky and live on a modern system, the setup code + * will have given us a memory map that we can use to properly + * set up memory. If we aren't, we'll fake a memory map. + */ +static int __init append_e820_map(struct e820entry *biosmap, int nr_map) +{ + /* Only one memory region (or negative)? Ignore it */ + if (nr_map < 2) + return -1; + + return __append_e820_map(biosmap, nr_map); +} + +static u64 __init e820_update_range_map(struct e820map *e820x, u64 start, + u64 size, unsigned old_type, + unsigned new_type) +{ + int i; + u64 real_updated_size = 0; + + BUG_ON(old_type == new_type); + + if (size > (ULLONG_MAX - start)) + size = ULLONG_MAX - start; + + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820x->map[i]; + u64 final_start, final_end; + if (ei->type != old_type) + continue; + /* totally covered? */ + if (ei->addr >= start && + (ei->addr + ei->size) <= (start + size)) { + ei->type = new_type; + real_updated_size += ei->size; + continue; + } + /* partially covered */ + final_start = max(start, ei->addr); + final_end = min(start + size, ei->addr + ei->size); + if (final_start >= final_end) + continue; + e820_add_region(final_start, final_end - final_start, + new_type); + real_updated_size += final_end - final_start; + + ei->size -= final_end - final_start; + if (ei->addr < final_start) + continue; + ei->addr = final_end; + } + return real_updated_size; +} + +u64 __init e820_update_range(u64 start, u64 size, unsigned old_type, + unsigned new_type) +{ + return e820_update_range_map(&e820, start, size, old_type, new_type); +} + +static u64 __init e820_update_range_saved(u64 start, u64 size, + unsigned old_type, unsigned new_type) +{ + return e820_update_range_map(&e820_saved, start, size, old_type, + new_type); +} + +/* make e820 not cover the range */ +u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type, + int checktype) +{ + int i; + u64 real_removed_size = 0; + + if (size > (ULLONG_MAX - start)) + size = ULLONG_MAX - start; + + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + u64 final_start, final_end; + + if (checktype && ei->type != old_type) + continue; + /* totally covered? */ + if (ei->addr >= start && + (ei->addr + ei->size) <= (start + size)) { + real_removed_size += ei->size; + memset(ei, 0, sizeof(struct e820entry)); + continue; + } + /* partially covered */ + final_start = max(start, ei->addr); + final_end = min(start + size, ei->addr + ei->size); + if (final_start >= final_end) + continue; + real_removed_size += final_end - final_start; + + ei->size -= final_end - final_start; + if (ei->addr < final_start) + continue; + ei->addr = final_end; + } + return real_removed_size; +} + +void __init update_e820(void) +{ + int nr_map; + + nr_map = e820.nr_map; + if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr_map)) + return; + e820.nr_map = nr_map; + printk(KERN_INFO "modified physical RAM map:\n"); + e820_print_map("modified"); +} +static void __init update_e820_saved(void) +{ + int nr_map; + + nr_map = e820_saved.nr_map; + if (sanitize_e820_map(e820_saved.map, ARRAY_SIZE(e820_saved.map), &nr_map)) + return; + e820_saved.nr_map = nr_map; +} +#define MAX_GAP_END 0x100000000ull +/* + * Search for a gap in the e820 memory space from start_addr to end_addr. + */ +__init int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize, + unsigned long start_addr, unsigned long long end_addr) +{ + unsigned long long last; + int i = e820.nr_map; + int found = 0; + + last = (end_addr && end_addr < MAX_GAP_END) ? end_addr : MAX_GAP_END; + + while (--i >= 0) { + unsigned long long start = e820.map[i].addr; + unsigned long long end = start + e820.map[i].size; + + if (end < start_addr) + continue; + + /* + * Since "last" is at most 4GB, we know we'll + * fit in 32 bits if this condition is true + */ + if (last > end) { + unsigned long gap = last - end; + + if (gap >= *gapsize) { + *gapsize = gap; + *gapstart = end; + found = 1; + } + } + if (start < last) + last = start; + } + return found; +} + +/* + * Search for the biggest gap in the low 32 bits of the e820 + * memory space. We pass this space to PCI to assign MMIO resources + * for hotplug or unconfigured devices in. + * Hopefully the BIOS let enough space left. + */ +__init void e820_setup_gap(void) +{ + unsigned long gapstart, gapsize, round; + int found; + + gapstart = 0x10000000; + gapsize = 0x400000; + found = e820_search_gap(&gapstart, &gapsize, 0, MAX_GAP_END); + +#ifdef CONFIG_X86_64 + if (!found) { + gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024; + printk(KERN_ERR "PCI: Warning: Cannot find a gap in the 32bit " + "address range\n" + KERN_ERR "PCI: Unassigned devices with 32bit resource " + "registers may break!\n"); + } +#endif + + /* + * See how much we want to round up: start off with + * rounding to the next 1MB area. + */ + round = 0x100000; + while ((gapsize >> 4) > round) + round += round; + /* Fun with two's complement */ + pci_mem_start = (gapstart + round) & -round; + + printk(KERN_INFO + "Allocating PCI resources starting at %lx (gap: %lx:%lx)\n", + pci_mem_start, gapstart, gapsize); +} + +/** + * Because of the size limitation of struct boot_params, only first + * 128 E820 memory entries are passed to kernel via + * boot_params.e820_map, others are passed via SETUP_E820_EXT node of + * linked list of struct setup_data, which is parsed here. + */ +void __init parse_e820_ext(struct setup_data *sdata, unsigned long pa_data) +{ + u32 map_len; + int entries; + struct e820entry *extmap; + + entries = sdata->len / sizeof(struct e820entry); + map_len = sdata->len + sizeof(struct setup_data); + if (map_len > PAGE_SIZE) + sdata = early_ioremap(pa_data, map_len); + extmap = (struct e820entry *)(sdata->data); + __append_e820_map(extmap, entries); + sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); + if (map_len > PAGE_SIZE) + early_iounmap(sdata, map_len); + printk(KERN_INFO "extended physical RAM map:\n"); + e820_print_map("extended"); +} + +#if defined(CONFIG_X86_64) || \ + (defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION)) +/** + * Find the ranges of physical addresses that do not correspond to + * e820 RAM areas and mark the corresponding pages as nosave for + * hibernation (32 bit) or software suspend and suspend to RAM (64 bit). + * + * This function requires the e820 map to be sorted and without any + * overlapping entries and assumes the first e820 area to be RAM. + */ +void __init e820_mark_nosave_regions(unsigned long limit_pfn) +{ + int i; + unsigned long pfn; + + pfn = PFN_DOWN(e820.map[0].addr + e820.map[0].size); + for (i = 1; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + + if (pfn < PFN_UP(ei->addr)) + register_nosave_region(pfn, PFN_UP(ei->addr)); + + pfn = PFN_DOWN(ei->addr + ei->size); + if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN) + register_nosave_region(PFN_UP(ei->addr), pfn); + + if (pfn >= limit_pfn) + break; + } +} +#endif + +/* + * Early reserved memory areas. + */ +#define MAX_EARLY_RES 20 + +struct early_res { + u64 start, end; + char name[16]; + char overlap_ok; +}; +static struct early_res early_res[MAX_EARLY_RES] __initdata = { + { 0, PAGE_SIZE, "BIOS data page" }, /* BIOS data page */ +#if defined(CONFIG_X86_64) && defined(CONFIG_X86_TRAMPOLINE) + { TRAMPOLINE_BASE, TRAMPOLINE_BASE + 2 * PAGE_SIZE, "TRAMPOLINE" }, +#endif +#if defined(CONFIG_X86_32) && defined(CONFIG_SMP) + /* + * But first pinch a few for the stack/trampoline stuff + * FIXME: Don't need the extra page at 4K, but need to fix + * trampoline before removing it. (see the GDT stuff) + */ + { PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE" }, + /* + * Has to be in very low memory so we can execute + * real-mode AP code. + */ + { TRAMPOLINE_BASE, TRAMPOLINE_BASE + PAGE_SIZE, "TRAMPOLINE" }, +#endif + {} +}; + +static int __init find_overlapped_early(u64 start, u64 end) +{ + int i; + struct early_res *r; + + for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) { + r = &early_res[i]; + if (end > r->start && start < r->end) + break; + } + + return i; +} + +/* + * Drop the i-th range from the early reservation map, + * by copying any higher ranges down one over it, and + * clearing what had been the last slot. + */ +static void __init drop_range(int i) +{ + int j; + + for (j = i + 1; j < MAX_EARLY_RES && early_res[j].end; j++) + ; + + memmove(&early_res[i], &early_res[i + 1], + (j - 1 - i) * sizeof(struct early_res)); + + early_res[j - 1].end = 0; +} + +/* + * Split any existing ranges that: + * 1) are marked 'overlap_ok', and + * 2) overlap with the stated range [start, end) + * into whatever portion (if any) of the existing range is entirely + * below or entirely above the stated range. Drop the portion + * of the existing range that overlaps with the stated range, + * which will allow the caller of this routine to then add that + * stated range without conflicting with any existing range. + */ +static void __init drop_overlaps_that_are_ok(u64 start, u64 end) +{ + int i; + struct early_res *r; + u64 lower_start, lower_end; + u64 upper_start, upper_end; + char name[16]; + + for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) { + r = &early_res[i]; + + /* Continue past non-overlapping ranges */ + if (end <= r->start || start >= r->end) + continue; + + /* + * Leave non-ok overlaps as is; let caller + * panic "Overlapping early reservations" + * when it hits this overlap. + */ + if (!r->overlap_ok) + return; + + /* + * We have an ok overlap. We will drop it from the early + * reservation map, and add back in any non-overlapping + * portions (lower or upper) as separate, overlap_ok, + * non-overlapping ranges. + */ + + /* 1. Note any non-overlapping (lower or upper) ranges. */ + strncpy(name, r->name, sizeof(name) - 1); + + lower_start = lower_end = 0; + upper_start = upper_end = 0; + if (r->start < start) { + lower_start = r->start; + lower_end = start; + } + if (r->end > end) { + upper_start = end; + upper_end = r->end; + } + + /* 2. Drop the original ok overlapping range */ + drop_range(i); + + i--; /* resume for-loop on copied down entry */ + + /* 3. Add back in any non-overlapping ranges. */ + if (lower_end) + reserve_early_overlap_ok(lower_start, lower_end, name); + if (upper_end) + reserve_early_overlap_ok(upper_start, upper_end, name); + } +} + +static void __init __reserve_early(u64 start, u64 end, char *name, + int overlap_ok) +{ + int i; + struct early_res *r; + + i = find_overlapped_early(start, end); + if (i >= MAX_EARLY_RES) + panic("Too many early reservations"); + r = &early_res[i]; + if (r->end) + panic("Overlapping early reservations " + "%llx-%llx %s to %llx-%llx %s\n", + start, end - 1, name?name:"", r->start, + r->end - 1, r->name); + r->start = start; + r->end = end; + r->overlap_ok = overlap_ok; + if (name) + strncpy(r->name, name, sizeof(r->name) - 1); +} + +/* + * A few early reservtations come here. + * + * The 'overlap_ok' in the name of this routine does -not- mean it + * is ok for these reservations to overlap an earlier reservation. + * Rather it means that it is ok for subsequent reservations to + * overlap this one. + * + * Use this entry point to reserve early ranges when you are doing + * so out of "Paranoia", reserving perhaps more memory than you need, + * just in case, and don't mind a subsequent overlapping reservation + * that is known to be needed. + * + * The drop_overlaps_that_are_ok() call here isn't really needed. + * It would be needed if we had two colliding 'overlap_ok' + * reservations, so that the second such would not panic on the + * overlap with the first. We don't have any such as of this + * writing, but might as well tolerate such if it happens in + * the future. + */ +void __init reserve_early_overlap_ok(u64 start, u64 end, char *name) +{ + drop_overlaps_that_are_ok(start, end); + __reserve_early(start, end, name, 1); +} + +/* + * Most early reservations come here. + * + * We first have drop_overlaps_that_are_ok() drop any pre-existing + * 'overlap_ok' ranges, so that we can then reserve this memory + * range without risk of panic'ing on an overlapping overlap_ok + * early reservation. + */ +void __init reserve_early(u64 start, u64 end, char *name) +{ + drop_overlaps_that_are_ok(start, end); + __reserve_early(start, end, name, 0); +} + +void __init free_early(u64 start, u64 end) +{ + struct early_res *r; + int i; + + i = find_overlapped_early(start, end); + r = &early_res[i]; + if (i >= MAX_EARLY_RES || r->end != end || r->start != start) + panic("free_early on not reserved area: %llx-%llx!", + start, end - 1); + + drop_range(i); +} + +void __init early_res_to_bootmem(u64 start, u64 end) +{ + int i, count; + u64 final_start, final_end; + + count = 0; + for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) + count++; + + printk(KERN_INFO "(%d early reservations) ==> bootmem\n", count); + for (i = 0; i < count; i++) { + struct early_res *r = &early_res[i]; + printk(KERN_INFO " #%d [%010llx - %010llx] %16s", i, + r->start, r->end, r->name); + final_start = max(start, r->start); + final_end = min(end, r->end); + if (final_start >= final_end) { + printk(KERN_CONT "\n"); + continue; + } + printk(KERN_CONT " ==> [%010llx - %010llx]\n", + final_start, final_end); + reserve_bootmem_generic(final_start, final_end - final_start, + BOOTMEM_DEFAULT); + } +} + +/* Check for already reserved areas */ +static inline int __init bad_addr(u64 *addrp, u64 size, u64 align) +{ + int i; + u64 addr = *addrp; + int changed = 0; + struct early_res *r; +again: + i = find_overlapped_early(addr, addr + size); + r = &early_res[i]; + if (i < MAX_EARLY_RES && r->end) { + *addrp = addr = round_up(r->end, align); + changed = 1; + goto again; + } + return changed; +} + +/* Check for already reserved areas */ +static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align) +{ + int i; + u64 addr = *addrp, last; + u64 size = *sizep; + int changed = 0; +again: + last = addr + size; + for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) { + struct early_res *r = &early_res[i]; + if (last > r->start && addr < r->start) { + size = r->start - addr; + changed = 1; + goto again; + } + if (last > r->end && addr < r->end) { + addr = round_up(r->end, align); + size = last - addr; + changed = 1; + goto again; + } + if (last <= r->end && addr >= r->start) { + (*sizep)++; + return 0; + } + } + if (changed) { + *addrp = addr; + *sizep = size; + } + return changed; +} + +/* + * Find a free area with specified alignment in a specific range. + */ +u64 __init find_e820_area(u64 start, u64 end, u64 size, u64 align) +{ + int i; + + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + u64 addr, last; + u64 ei_last; + + if (ei->type != E820_RAM) + continue; + addr = round_up(ei->addr, align); + ei_last = ei->addr + ei->size; + if (addr < start) + addr = round_up(start, align); + if (addr >= ei_last) + continue; + while (bad_addr(&addr, size, align) && addr+size <= ei_last) + ; + last = addr + size; + if (last > ei_last) + continue; + if (last > end) + continue; + return addr; + } + return -1ULL; +} + +/* + * Find next free range after *start + */ +u64 __init find_e820_area_size(u64 start, u64 *sizep, u64 align) +{ + int i; + + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + u64 addr, last; + u64 ei_last; + + if (ei->type != E820_RAM) + continue; + addr = round_up(ei->addr, align); + ei_last = ei->addr + ei->size; + if (addr < start) + addr = round_up(start, align); + if (addr >= ei_last) + continue; + *sizep = ei_last - addr; + while (bad_addr_size(&addr, sizep, align) && + addr + *sizep <= ei_last) + ; + last = addr + *sizep; + if (last > ei_last) + continue; + return addr; + } + return -1UL; + +} + +/* + * pre allocated 4k and reserved it in e820 + */ +u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align) +{ + u64 size = 0; + u64 addr; + u64 start; + + start = startt; + while (size < sizet) + start = find_e820_area_size(start, &size, align); + + if (size < sizet) + return 0; + + addr = round_down(start + size - sizet, align); + e820_update_range(addr, sizet, E820_RAM, E820_RESERVED); + e820_update_range_saved(addr, sizet, E820_RAM, E820_RESERVED); + printk(KERN_INFO "update e820 for early_reserve_e820\n"); + update_e820(); + update_e820_saved(); + + return addr; +} + +#ifdef CONFIG_X86_32 +# ifdef CONFIG_X86_PAE +# define MAX_ARCH_PFN (1ULL<<(36-PAGE_SHIFT)) +# else +# define MAX_ARCH_PFN (1ULL<<(32-PAGE_SHIFT)) +# endif +#else /* CONFIG_X86_32 */ +# define MAX_ARCH_PFN MAXMEM>>PAGE_SHIFT +#endif + +/* + * Find the highest page frame number we have available + */ +static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type) +{ + int i; + unsigned long last_pfn = 0; + unsigned long max_arch_pfn = MAX_ARCH_PFN; + + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + unsigned long start_pfn; + unsigned long end_pfn; + + if (ei->type != type) + continue; + + start_pfn = ei->addr >> PAGE_SHIFT; + end_pfn = (ei->addr + ei->size) >> PAGE_SHIFT; + + if (start_pfn >= limit_pfn) + continue; + if (end_pfn > limit_pfn) { + last_pfn = limit_pfn; + break; + } + if (end_pfn > last_pfn) + last_pfn = end_pfn; + } + + if (last_pfn > max_arch_pfn) + last_pfn = max_arch_pfn; + + printk(KERN_INFO "last_pfn = %#lx max_arch_pfn = %#lx\n", + last_pfn, max_arch_pfn); + return last_pfn; +} +unsigned long __init e820_end_of_ram_pfn(void) +{ + return e820_end_pfn(MAX_ARCH_PFN, E820_RAM); +} + +unsigned long __init e820_end_of_low_ram_pfn(void) +{ + return e820_end_pfn(1UL<<(32 - PAGE_SHIFT), E820_RAM); +} +/* + * Finds an active region in the address range from start_pfn to last_pfn and + * returns its range in ei_startpfn and ei_endpfn for the e820 entry. + */ +int __init e820_find_active_region(const struct e820entry *ei, + unsigned long start_pfn, + unsigned long last_pfn, + unsigned long *ei_startpfn, + unsigned long *ei_endpfn) +{ + u64 align = PAGE_SIZE; + + *ei_startpfn = round_up(ei->addr, align) >> PAGE_SHIFT; + *ei_endpfn = round_down(ei->addr + ei->size, align) >> PAGE_SHIFT; + + /* Skip map entries smaller than a page */ + if (*ei_startpfn >= *ei_endpfn) + return 0; + + /* Skip if map is outside the node */ + if (ei->type != E820_RAM || *ei_endpfn <= start_pfn || + *ei_startpfn >= last_pfn) + return 0; + + /* Check for overlaps */ + if (*ei_startpfn < start_pfn) + *ei_startpfn = start_pfn; + if (*ei_endpfn > last_pfn) + *ei_endpfn = last_pfn; + + return 1; +} + +/* Walk the e820 map and register active regions within a node */ +void __init e820_register_active_regions(int nid, unsigned long start_pfn, + unsigned long last_pfn) +{ + unsigned long ei_startpfn; + unsigned long ei_endpfn; + int i; + + for (i = 0; i < e820.nr_map; i++) + if (e820_find_active_region(&e820.map[i], + start_pfn, last_pfn, + &ei_startpfn, &ei_endpfn)) + add_active_range(nid, ei_startpfn, ei_endpfn); +} + +/* + * Find the hole size (in bytes) in the memory range. + * @start: starting address of the memory range to scan + * @end: ending address of the memory range to scan + */ +u64 __init e820_hole_size(u64 start, u64 end) +{ + unsigned long start_pfn = start >> PAGE_SHIFT; + unsigned long last_pfn = end >> PAGE_SHIFT; + unsigned long ei_startpfn, ei_endpfn, ram = 0; + int i; + + for (i = 0; i < e820.nr_map; i++) { + if (e820_find_active_region(&e820.map[i], + start_pfn, last_pfn, + &ei_startpfn, &ei_endpfn)) + ram += ei_endpfn - ei_startpfn; + } + return end - start - ((u64)ram << PAGE_SHIFT); +} + +static void early_panic(char *msg) +{ + early_printk(msg); + panic(msg); +} + +static int userdef __initdata; + +/* "mem=nopentium" disables the 4MB page tables. */ +static int __init parse_memopt(char *p) +{ + u64 mem_size; + + if (!p) + return -EINVAL; + +#ifdef CONFIG_X86_32 + if (!strcmp(p, "nopentium")) { + setup_clear_cpu_cap(X86_FEATURE_PSE); + return 0; + } +#endif + + userdef = 1; + mem_size = memparse(p, &p); + e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1); + + return 0; +} +early_param("mem", parse_memopt); + +static int __init parse_memmap_opt(char *p) +{ + char *oldp; + u64 start_at, mem_size; + + if (!p) + return -EINVAL; + + if (!strcmp(p, "exactmap")) { +#ifdef CONFIG_CRASH_DUMP + /* + * If we are doing a crash dump, we still need to know + * the real mem size before original memory map is + * reset. + */ + saved_max_pfn = e820_end_of_ram_pfn(); +#endif + e820.nr_map = 0; + userdef = 1; + return 0; + } + + oldp = p; + mem_size = memparse(p, &p); + if (p == oldp) + return -EINVAL; + + userdef = 1; + if (*p == '@') { + start_at = memparse(p+1, &p); + e820_add_region(start_at, mem_size, E820_RAM); + } else if (*p == '#') { + start_at = memparse(p+1, &p); + e820_add_region(start_at, mem_size, E820_ACPI); + } else if (*p == '$') { + start_at = memparse(p+1, &p); + e820_add_region(start_at, mem_size, E820_RESERVED); + } else + e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1); + + return *p == '\0' ? 0 : -EINVAL; +} +early_param("memmap", parse_memmap_opt); + +void __init finish_e820_parsing(void) +{ + if (userdef) { + int nr = e820.nr_map; + + if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr) < 0) + early_panic("Invalid user supplied memory map"); + e820.nr_map = nr; + + printk(KERN_INFO "user-defined physical RAM map:\n"); + e820_print_map("user"); + } +} + +static inline const char *e820_type_to_string(int e820_type) +{ + switch (e820_type) { + case E820_RESERVED_KERN: + case E820_RAM: return "System RAM"; + case E820_ACPI: return "ACPI Tables"; + case E820_NVS: return "ACPI Non-volatile Storage"; + default: return "reserved"; + } +} + +/* + * Mark e820 reserved areas as busy for the resource manager. + */ +void __init e820_reserve_resources(void) +{ + int i; + struct resource *res; + u64 end; + + res = alloc_bootmem_low(sizeof(struct resource) * e820.nr_map); + for (i = 0; i < e820.nr_map; i++) { + end = e820.map[i].addr + e820.map[i].size - 1; +#ifndef CONFIG_RESOURCES_64BIT + if (end > 0x100000000ULL) { + res++; + continue; + } +#endif + res->name = e820_type_to_string(e820.map[i].type); + res->start = e820.map[i].addr; + res->end = end; + + res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + insert_resource(&iomem_resource, res); + res++; + } + + for (i = 0; i < e820_saved.nr_map; i++) { + struct e820entry *entry = &e820_saved.map[i]; + firmware_map_add_early(entry->addr, + entry->addr + entry->size - 1, + e820_type_to_string(entry->type)); + } +} + +/* + * Non-standard memory setup can be specified via this quirk: + */ +char * (*arch_memory_setup_quirk)(void); + +char *__init default_machine_specific_memory_setup(void) +{ + char *who = "BIOS-e820"; + int new_nr; + /* + * Try to copy the BIOS-supplied E820-map. + * + * Otherwise fake a memory map; one section from 0k->640k, + * the next section from 1mb->appropriate_mem_k + */ + new_nr = boot_params.e820_entries; + sanitize_e820_map(boot_params.e820_map, + ARRAY_SIZE(boot_params.e820_map), + &new_nr); + boot_params.e820_entries = new_nr; + if (append_e820_map(boot_params.e820_map, boot_params.e820_entries) + < 0) { + u64 mem_size; + + /* compare results from other methods and take the greater */ + if (boot_params.alt_mem_k + < boot_params.screen_info.ext_mem_k) { + mem_size = boot_params.screen_info.ext_mem_k; + who = "BIOS-88"; + } else { + mem_size = boot_params.alt_mem_k; + who = "BIOS-e801"; + } + + e820.nr_map = 0; + e820_add_region(0, LOWMEMSIZE(), E820_RAM); + e820_add_region(HIGH_MEMORY, mem_size << 10, E820_RAM); + } + + /* In case someone cares... */ + return who; +} + +char *__init __attribute__((weak)) machine_specific_memory_setup(void) +{ + if (arch_memory_setup_quirk) { + char *who = arch_memory_setup_quirk(); + + if (who) + return who; + } + return default_machine_specific_memory_setup(); +} + +/* Overridden in paravirt.c if CONFIG_PARAVIRT */ +char * __init __attribute__((weak)) memory_setup(void) +{ + return machine_specific_memory_setup(); +} + +void __init setup_memory_map(void) +{ + char *who; + + who = memory_setup(); + memcpy(&e820_saved, &e820, sizeof(struct e820map)); + printk(KERN_INFO "BIOS-provided physical RAM map:\n"); + e820_print_map(who); +} + +#ifdef CONFIG_X86_64 +int __init arch_get_ram_range(int slot, u64 *addr, u64 *size) +{ + int i; + + if (slot < 0 || slot >= e820.nr_map) + return -1; + for (i = slot; i < e820.nr_map; i++) { + if (e820.map[i].type != E820_RAM) + continue; + break; + } + if (i == e820.nr_map || e820.map[i].addr > (max_pfn << PAGE_SHIFT)) + return -1; + *addr = e820.map[i].addr; + *size = min_t(u64, e820.map[i].size + e820.map[i].addr, + max_pfn << PAGE_SHIFT) - *addr; + return i + 1; +} +#endif diff --git a/arch/x86/kernel/e820_32.c b/arch/x86/kernel/e820_32.c deleted file mode 100644 index ed733e7cf4e6..000000000000 --- a/arch/x86/kernel/e820_32.c +++ /dev/null @@ -1,775 +0,0 @@ -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/init.h> -#include <linux/bootmem.h> -#include <linux/ioport.h> -#include <linux/string.h> -#include <linux/kexec.h> -#include <linux/module.h> -#include <linux/mm.h> -#include <linux/pfn.h> -#include <linux/uaccess.h> -#include <linux/suspend.h> - -#include <asm/pgtable.h> -#include <asm/page.h> -#include <asm/e820.h> -#include <asm/setup.h> - -struct e820map e820; -struct change_member { - struct e820entry *pbios; /* pointer to original bios entry */ - unsigned long long addr; /* address for this change point */ -}; -static struct change_member change_point_list[2*E820MAX] __initdata; -static struct change_member *change_point[2*E820MAX] __initdata; -static struct e820entry *overlap_list[E820MAX] __initdata; -static struct e820entry new_bios[E820MAX] __initdata; -/* For PCI or other memory-mapped resources */ -unsigned long pci_mem_start = 0x10000000; -#ifdef CONFIG_PCI -EXPORT_SYMBOL(pci_mem_start); -#endif -extern int user_defined_memmap; - -static struct resource system_rom_resource = { - .name = "System ROM", - .start = 0xf0000, - .end = 0xfffff, - .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM -}; - -static struct resource extension_rom_resource = { - .name = "Extension ROM", - .start = 0xe0000, - .end = 0xeffff, - .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM -}; - -static struct resource adapter_rom_resources[] = { { - .name = "Adapter ROM", - .start = 0xc8000, - .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM -}, { - .name = "Adapter ROM", - .start = 0, - .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM -}, { - .name = "Adapter ROM", - .start = 0, - .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM -}, { - .name = "Adapter ROM", - .start = 0, - .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM -}, { - .name = "Adapter ROM", - .start = 0, - .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM -}, { - .name = "Adapter ROM", - .start = 0, - .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM -} }; - -static struct resource video_rom_resource = { - .name = "Video ROM", - .start = 0xc0000, - .end = 0xc7fff, - .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM -}; - -#define ROMSIGNATURE 0xaa55 - -static int __init romsignature(const unsigned char *rom) -{ - const unsigned short * const ptr = (const unsigned short *)rom; - unsigned short sig; - - return probe_kernel_address(ptr, sig) == 0 && sig == ROMSIGNATURE; -} - -static int __init romchecksum(const unsigned char *rom, unsigned long length) -{ - unsigned char sum, c; - - for (sum = 0; length && probe_kernel_address(rom++, c) == 0; length--) - sum += c; - return !length && !sum; -} - -static void __init probe_roms(void) -{ - const unsigned char *rom; - unsigned long start, length, upper; - unsigned char c; - int i; - - /* video rom */ - upper = adapter_rom_resources[0].start; - for (start = video_rom_resource.start; start < upper; start += 2048) { - rom = isa_bus_to_virt(start); - if (!romsignature(rom)) - continue; - - video_rom_resource.start = start; - - if (probe_kernel_address(rom + 2, c) != 0) - continue; - - /* 0 < length <= 0x7f * 512, historically */ - length = c * 512; - - /* if checksum okay, trust length byte */ - if (length && romchecksum(rom, length)) - video_rom_resource.end = start + length - 1; - - request_resource(&iomem_resource, &video_rom_resource); - break; - } - - start = (video_rom_resource.end + 1 + 2047) & ~2047UL; - if (start < upper) - start = upper; - - /* system rom */ - request_resource(&iomem_resource, &system_rom_resource); - upper = system_rom_resource.start; - - /* check for extension rom (ignore length byte!) */ - rom = isa_bus_to_virt(extension_rom_resource.start); - if (romsignature(rom)) { - length = extension_rom_resource.end - extension_rom_resource.start + 1; - if (romchecksum(rom, length)) { - request_resource(&iomem_resource, &extension_rom_resource); - upper = extension_rom_resource.start; - } - } - - /* check for adapter roms on 2k boundaries */ - for (i = 0; i < ARRAY_SIZE(adapter_rom_resources) && start < upper; start += 2048) { - rom = isa_bus_to_virt(start); - if (!romsignature(rom)) - continue; - - if (probe_kernel_address(rom + 2, c) != 0) - continue; - - /* 0 < length <= 0x7f * 512, historically */ - length = c * 512; - - /* but accept any length that fits if checksum okay */ - if (!length || start + length > upper || !romchecksum(rom, length)) - continue; - - adapter_rom_resources[i].start = start; - adapter_rom_resources[i].end = start + length - 1; - request_resource(&iomem_resource, &adapter_rom_resources[i]); - - start = adapter_rom_resources[i++].end & ~2047UL; - } -} - -/* - * Request address space for all standard RAM and ROM resources - * and also for regions reported as reserved by the e820. - */ -void __init init_iomem_resources(struct resource *code_resource, - struct resource *data_resource, - struct resource *bss_resource) -{ - int i; - - probe_roms(); - for (i = 0; i < e820.nr_map; i++) { - struct resource *res; -#ifndef CONFIG_RESOURCES_64BIT - if (e820.map[i].addr + e820.map[i].size > 0x100000000ULL) - continue; -#endif - res = kzalloc(sizeof(struct resource), GFP_ATOMIC); - switch (e820.map[i].type) { - case E820_RAM: res->name = "System RAM"; break; - case E820_ACPI: res->name = "ACPI Tables"; break; - case E820_NVS: res->name = "ACPI Non-volatile Storage"; break; - default: res->name = "reserved"; - } - res->start = e820.map[i].addr; - res->end = res->start + e820.map[i].size - 1; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; - if (request_resource(&iomem_resource, res)) { - kfree(res); - continue; - } - if (e820.map[i].type == E820_RAM) { - /* - * We don't know which RAM region contains kernel data, - * so we try it repeatedly and let the resource manager - * test it. - */ - request_resource(res, code_resource); - request_resource(res, data_resource); - request_resource(res, bss_resource); -#ifdef CONFIG_KEXEC - if (crashk_res.start != crashk_res.end) - request_resource(res, &crashk_res); -#endif - } - } -} - -#if defined(CONFIG_PM) && defined(CONFIG_HIBERNATION) -/** - * e820_mark_nosave_regions - Find the ranges of physical addresses that do not - * correspond to e820 RAM areas and mark the corresponding pages as nosave for - * hibernation. - * - * This function requires the e820 map to be sorted and without any - * overlapping entries and assumes the first e820 area to be RAM. - */ -void __init e820_mark_nosave_regions(void) -{ - int i; - unsigned long pfn; - - pfn = PFN_DOWN(e820.map[0].addr + e820.map[0].size); - for (i = 1; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; - - if (pfn < PFN_UP(ei->addr)) - register_nosave_region(pfn, PFN_UP(ei->addr)); - - pfn = PFN_DOWN(ei->addr + ei->size); - if (ei->type != E820_RAM) - register_nosave_region(PFN_UP(ei->addr), pfn); - - if (pfn >= max_low_pfn) - break; - } -} -#endif - -void __init add_memory_region(unsigned long long start, - unsigned long long size, int type) -{ - int x; - - x = e820.nr_map; - - if (x == E820MAX) { - printk(KERN_ERR "Ooops! Too many entries in the memory map!\n"); - return; - } - - e820.map[x].addr = start; - e820.map[x].size = size; - e820.map[x].type = type; - e820.nr_map++; -} /* add_memory_region */ - -/* - * Sanitize the BIOS e820 map. - * - * Some e820 responses include overlapping entries. The following - * replaces the original e820 map with a new one, removing overlaps. - * - */ -int __init sanitize_e820_map(struct e820entry * biosmap, char * pnr_map) -{ - struct change_member *change_tmp; - unsigned long current_type, last_type; - unsigned long long last_addr; - int chgidx, still_changing; - int overlap_entries; - int new_bios_entry; - int old_nr, new_nr, chg_nr; - int i; - - /* - Visually we're performing the following (1,2,3,4 = memory types)... - - Sample memory map (w/overlaps): - ____22__________________ - ______________________4_ - ____1111________________ - _44_____________________ - 11111111________________ - ____________________33__ - ___________44___________ - __________33333_________ - ______________22________ - ___________________2222_ - _________111111111______ - _____________________11_ - _________________4______ - - Sanitized equivalent (no overlap): - 1_______________________ - _44_____________________ - ___1____________________ - ____22__________________ - ______11________________ - _________1______________ - __________3_____________ - ___________44___________ - _____________33_________ - _______________2________ - ________________1_______ - _________________4______ - ___________________2____ - ____________________33__ - ______________________4_ - */ - /* if there's only one memory region, don't bother */ - if (*pnr_map < 2) { - return -1; - } - - old_nr = *pnr_map; - - /* bail out if we find any unreasonable addresses in bios map */ - for (i=0; i<old_nr; i++) - if (biosmap[i].addr + biosmap[i].size < biosmap[i].addr) { - return -1; - } - - /* create pointers for initial change-point information (for sorting) */ - for (i=0; i < 2*old_nr; i++) - change_point[i] = &change_point_list[i]; - - /* record all known change-points (starting and ending addresses), - omitting those that are for empty memory regions */ - chgidx = 0; - for (i=0; i < old_nr; i++) { - if (biosmap[i].size != 0) { - change_point[chgidx]->addr = biosmap[i].addr; - change_point[chgidx++]->pbios = &biosmap[i]; - change_point[chgidx]->addr = biosmap[i].addr + biosmap[i].size; - change_point[chgidx++]->pbios = &biosmap[i]; - } - } - chg_nr = chgidx; /* true number of change-points */ - - /* sort change-point list by memory addresses (low -> high) */ - still_changing = 1; - while (still_changing) { - still_changing = 0; - for (i=1; i < chg_nr; i++) { - /* if <current_addr> > <last_addr>, swap */ - /* or, if current=<start_addr> & last=<end_addr>, swap */ - if ((change_point[i]->addr < change_point[i-1]->addr) || - ((change_point[i]->addr == change_point[i-1]->addr) && - (change_point[i]->addr == change_point[i]->pbios->addr) && - (change_point[i-1]->addr != change_point[i-1]->pbios->addr)) - ) - { - change_tmp = change_point[i]; - change_point[i] = change_point[i-1]; - change_point[i-1] = change_tmp; - still_changing=1; - } - } - } - - /* create a new bios memory map, removing overlaps */ - overlap_entries=0; /* number of entries in the overlap table */ - new_bios_entry=0; /* index for creating new bios map entries */ - last_type = 0; /* start with undefined memory type */ - last_addr = 0; /* start with 0 as last starting address */ - /* loop through change-points, determining affect on the new bios map */ - for (chgidx=0; chgidx < chg_nr; chgidx++) - { - /* keep track of all overlapping bios entries */ - if (change_point[chgidx]->addr == change_point[chgidx]->pbios->addr) - { - /* add map entry to overlap list (> 1 entry implies an overlap) */ - overlap_list[overlap_entries++]=change_point[chgidx]->pbios; - } - else - { - /* remove entry from list (order independent, so swap with last) */ - for (i=0; i<overlap_entries; i++) - { - if (overlap_list[i] == change_point[chgidx]->pbios) - overlap_list[i] = overlap_list[overlap_entries-1]; - } - overlap_entries--; - } - /* if there are overlapping entries, decide which "type" to use */ - /* (larger value takes precedence -- 1=usable, 2,3,4,4+=unusable) */ - current_type = 0; - for (i=0; i<overlap_entries; i++) - if (overlap_list[i]->type > current_type) - current_type = overlap_list[i]->type; - /* continue building up new bios map based on this information */ - if (current_type != last_type) { - if (last_type != 0) { - new_bios[new_bios_entry].size = - change_point[chgidx]->addr - last_addr; - /* move forward only if the new size was non-zero */ - if (new_bios[new_bios_entry].size != 0) - if (++new_bios_entry >= E820MAX) - break; /* no more space left for new bios entries */ - } - if (current_type != 0) { - new_bios[new_bios_entry].addr = change_point[chgidx]->addr; - new_bios[new_bios_entry].type = current_type; - last_addr=change_point[chgidx]->addr; - } - last_type = current_type; - } - } - new_nr = new_bios_entry; /* retain count for new bios entries */ - - /* copy new bios mapping into original location */ - memcpy(biosmap, new_bios, new_nr*sizeof(struct e820entry)); - *pnr_map = new_nr; - - return 0; -} - -/* - * Copy the BIOS e820 map into a safe place. - * - * Sanity-check it while we're at it.. - * - * If we're lucky and live on a modern system, the setup code - * will have given us a memory map that we can use to properly - * set up memory. If we aren't, we'll fake a memory map. - * - * We check to see that the memory map contains at least 2 elements - * before we'll use it, because the detection code in setup.S may - * not be perfect and most every PC known to man has two memory - * regions: one from 0 to 640k, and one from 1mb up. (The IBM - * thinkpad 560x, for example, does not cooperate with the memory - * detection code.) - */ -int __init copy_e820_map(struct e820entry *biosmap, int nr_map) -{ - /* Only one memory region (or negative)? Ignore it */ - if (nr_map < 2) - return -1; - - do { - u64 start = biosmap->addr; - u64 size = biosmap->size; - u64 end = start + size; - u32 type = biosmap->type; - - /* Overflow in 64 bits? Ignore the memory map. */ - if (start > end) - return -1; - - add_memory_region(start, size, type); - } while (biosmap++, --nr_map); - - return 0; -} - -/* - * Find the highest page frame number we have available - */ -void __init propagate_e820_map(void) -{ - int i; - - max_pfn = 0; - - for (i = 0; i < e820.nr_map; i++) { - unsigned long start, end; - /* RAM? */ - if (e820.map[i].type != E820_RAM) - continue; - start = PFN_UP(e820.map[i].addr); - end = PFN_DOWN(e820.map[i].addr + e820.map[i].size); - if (start >= end) - continue; - if (end > max_pfn) - max_pfn = end; - memory_present(0, start, end); - } -} - -/* - * Register fully available low RAM pages with the bootmem allocator. - */ -void __init register_bootmem_low_pages(unsigned long max_low_pfn) -{ - int i; - - for (i = 0; i < e820.nr_map; i++) { - unsigned long curr_pfn, last_pfn, size; - /* - * Reserve usable low memory - */ - if (e820.map[i].type != E820_RAM) - continue; - /* - * We are rounding up the start address of usable memory: - */ - curr_pfn = PFN_UP(e820.map[i].addr); - if (curr_pfn >= max_low_pfn) - continue; - /* - * ... and at the end of the usable range downwards: - */ - last_pfn = PFN_DOWN(e820.map[i].addr + e820.map[i].size); - - if (last_pfn > max_low_pfn) - last_pfn = max_low_pfn; - - /* - * .. finally, did all the rounding and playing - * around just make the area go away? - */ - if (last_pfn <= curr_pfn) - continue; - - size = last_pfn - curr_pfn; - free_bootmem(PFN_PHYS(curr_pfn), PFN_PHYS(size)); - } -} - -void __init e820_register_memory(void) -{ - unsigned long gapstart, gapsize, round; - unsigned long long last; - int i; - - /* - * Search for the biggest gap in the low 32 bits of the e820 - * memory space. - */ - last = 0x100000000ull; - gapstart = 0x10000000; - gapsize = 0x400000; - i = e820.nr_map; - while (--i >= 0) { - unsigned long long start = e820.map[i].addr; - unsigned long long end = start + e820.map[i].size; - - /* - * Since "last" is at most 4GB, we know we'll - * fit in 32 bits if this condition is true - */ - if (last > end) { - unsigned long gap = last - end; - - if (gap > gapsize) { - gapsize = gap; - gapstart = end; - } - } - if (start < last) - last = start; - } - - /* - * See how much we want to round up: start off with - * rounding to the next 1MB area. - */ - round = 0x100000; - while ((gapsize >> 4) > round) - round += round; - /* Fun with two's complement */ - pci_mem_start = (gapstart + round) & -round; - - printk("Allocating PCI resources starting at %08lx (gap: %08lx:%08lx)\n", - pci_mem_start, gapstart, gapsize); -} - -void __init print_memory_map(char *who) -{ - int i; - - for (i = 0; i < e820.nr_map; i++) { - printk(" %s: %016Lx - %016Lx ", who, - e820.map[i].addr, - e820.map[i].addr + e820.map[i].size); - switch (e820.map[i].type) { - case E820_RAM: printk("(usable)\n"); - break; - case E820_RESERVED: - printk("(reserved)\n"); - break; - case E820_ACPI: - printk("(ACPI data)\n"); - break; - case E820_NVS: - printk("(ACPI NVS)\n"); - break; - default: printk("type %u\n", e820.map[i].type); - break; - } - } -} - -void __init limit_regions(unsigned long long size) -{ - unsigned long long current_addr; - int i; - - print_memory_map("limit_regions start"); - for (i = 0; i < e820.nr_map; i++) { - current_addr = e820.map[i].addr + e820.map[i].size; - if (current_addr < size) - continue; - - if (e820.map[i].type != E820_RAM) - continue; - - if (e820.map[i].addr >= size) { - /* - * This region starts past the end of the - * requested size, skip it completely. - */ - e820.nr_map = i; - } else { - e820.nr_map = i + 1; - e820.map[i].size -= current_addr - size; - } - print_memory_map("limit_regions endfor"); - return; - } - print_memory_map("limit_regions endfunc"); -} - -/* - * This function checks if any part of the range <start,end> is mapped - * with type. - */ -int -e820_any_mapped(u64 start, u64 end, unsigned type) -{ - int i; - for (i = 0; i < e820.nr_map; i++) { - const struct e820entry *ei = &e820.map[i]; - if (type && ei->type != type) - continue; - if (ei->addr >= end || ei->addr + ei->size <= start) - continue; - return 1; - } - return 0; -} -EXPORT_SYMBOL_GPL(e820_any_mapped); - - /* - * This function checks if the entire range <start,end> is mapped with type. - * - * Note: this function only works correct if the e820 table is sorted and - * not-overlapping, which is the case - */ -int __init -e820_all_mapped(unsigned long s, unsigned long e, unsigned type) -{ - u64 start = s; - u64 end = e; - int i; - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; - if (type && ei->type != type) - continue; - /* is the region (part) in overlap with the current region ?*/ - if (ei->addr >= end || ei->addr + ei->size <= start) - continue; - /* if the region is at the beginning of <start,end> we move - * start to the end of the region since it's ok until there - */ - if (ei->addr <= start) - start = ei->addr + ei->size; - /* if start is now at or beyond end, we're done, full - * coverage */ - if (start >= end) - return 1; /* we're done */ - } - return 0; -} - -static int __init parse_memmap(char *arg) -{ - if (!arg) - return -EINVAL; - - if (strcmp(arg, "exactmap") == 0) { -#ifdef CONFIG_CRASH_DUMP - /* If we are doing a crash dump, we - * still need to know the real mem - * size before original memory map is - * reset. - */ - propagate_e820_map(); - saved_max_pfn = max_pfn; -#endif - e820.nr_map = 0; - user_defined_memmap = 1; - } else { - /* If the user specifies memory size, we - * limit the BIOS-provided memory map to - * that size. exactmap can be used to specify - * the exact map. mem=number can be used to - * trim the existing memory map. - */ - unsigned long long start_at, mem_size; - - mem_size = memparse(arg, &arg); - if (*arg == '@') { - start_at = memparse(arg+1, &arg); - add_memory_region(start_at, mem_size, E820_RAM); - } else if (*arg == '#') { - start_at = memparse(arg+1, &arg); - add_memory_region(start_at, mem_size, E820_ACPI); - } else if (*arg == '$') { - start_at = memparse(arg+1, &arg); - add_memory_region(start_at, mem_size, E820_RESERVED); - } else { - limit_regions(mem_size); - user_defined_memmap = 1; - } - } - return 0; -} -early_param("memmap", parse_memmap); -void __init update_memory_range(u64 start, u64 size, unsigned old_type, - unsigned new_type) -{ - int i; - - BUG_ON(old_type == new_type); - - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; - u64 final_start, final_end; - if (ei->type != old_type) - continue; - /* totally covered? */ - if (ei->addr >= start && ei->size <= size) { - ei->type = new_type; - continue; - } - /* partially covered */ - final_start = max(start, ei->addr); - final_end = min(start + size, ei->addr + ei->size); - if (final_start >= final_end) - continue; - add_memory_region(final_start, final_end - final_start, - new_type); - } -} -void __init update_e820(void) -{ - u8 nr_map; - - nr_map = e820.nr_map; - if (sanitize_e820_map(e820.map, &nr_map)) - return; - e820.nr_map = nr_map; - printk(KERN_INFO "modified physical RAM map:\n"); - print_memory_map("modified"); -} diff --git a/arch/x86/kernel/e820_64.c b/arch/x86/kernel/e820_64.c deleted file mode 100644 index 124480c0008d..000000000000 --- a/arch/x86/kernel/e820_64.c +++ /dev/null @@ -1,952 +0,0 @@ -/* - * Handle the memory map. - * The functions here do the job until bootmem takes over. - * - * Getting sanitize_e820_map() in sync with i386 version by applying change: - * - Provisions for empty E820 memory regions (reported by certain BIOSes). - * Alex Achenbach <xela@slit.de>, December 2002. - * Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> - * - */ -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/init.h> -#include <linux/bootmem.h> -#include <linux/ioport.h> -#include <linux/string.h> -#include <linux/kexec.h> -#include <linux/module.h> -#include <linux/mm.h> -#include <linux/suspend.h> -#include <linux/pfn.h> - -#include <asm/pgtable.h> -#include <asm/page.h> -#include <asm/e820.h> -#include <asm/proto.h> -#include <asm/setup.h> -#include <asm/sections.h> -#include <asm/kdebug.h> -#include <asm/trampoline.h> - -struct e820map e820; - -/* - * PFN of last memory page. - */ -unsigned long end_pfn; - -/* - * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries. - * The direct mapping extends to max_pfn_mapped, so that we can directly access - * apertures, ACPI and other tables without having to play with fixmaps. - */ -unsigned long max_pfn_mapped; - -/* - * Last pfn which the user wants to use. - */ -static unsigned long __initdata end_user_pfn = MAXMEM>>PAGE_SHIFT; - -/* - * Early reserved memory areas. - */ -#define MAX_EARLY_RES 20 - -struct early_res { - unsigned long start, end; - char name[16]; -}; -static struct early_res early_res[MAX_EARLY_RES] __initdata = { - { 0, PAGE_SIZE, "BIOS data page" }, /* BIOS data page */ -#ifdef CONFIG_X86_TRAMPOLINE - { TRAMPOLINE_BASE, TRAMPOLINE_BASE + 2 * PAGE_SIZE, "TRAMPOLINE" }, -#endif - {} -}; - -void __init reserve_early(unsigned long start, unsigned long end, char *name) -{ - int i; - struct early_res *r; - for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) { - r = &early_res[i]; - if (end > r->start && start < r->end) - panic("Overlapping early reservations %lx-%lx %s to %lx-%lx %s\n", - start, end - 1, name?name:"", r->start, r->end - 1, r->name); - } - if (i >= MAX_EARLY_RES) - panic("Too many early reservations"); - r = &early_res[i]; - r->start = start; - r->end = end; - if (name) - strncpy(r->name, name, sizeof(r->name) - 1); -} - -void __init free_early(unsigned long start, unsigned long end) -{ - struct early_res *r; - int i, j; - - for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) { - r = &early_res[i]; - if (start == r->start && end == r->end) - break; - } - if (i >= MAX_EARLY_RES || !early_res[i].end) - panic("free_early on not reserved area: %lx-%lx!", start, end); - - for (j = i + 1; j < MAX_EARLY_RES && early_res[j].end; j++) - ; - - memmove(&early_res[i], &early_res[i + 1], - (j - 1 - i) * sizeof(struct early_res)); - - early_res[j - 1].end = 0; -} - -void __init early_res_to_bootmem(unsigned long start, unsigned long end) -{ - int i; - unsigned long final_start, final_end; - for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) { - struct early_res *r = &early_res[i]; - final_start = max(start, r->start); - final_end = min(end, r->end); - if (final_start >= final_end) - continue; - printk(KERN_INFO " early res: %d [%lx-%lx] %s\n", i, - final_start, final_end - 1, r->name); - reserve_bootmem_generic(final_start, final_end - final_start); - } -} - -/* Check for already reserved areas */ -static inline int __init -bad_addr(unsigned long *addrp, unsigned long size, unsigned long align) -{ - int i; - unsigned long addr = *addrp, last; - int changed = 0; -again: - last = addr + size; - for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) { - struct early_res *r = &early_res[i]; - if (last >= r->start && addr < r->end) { - *addrp = addr = round_up(r->end, align); - changed = 1; - goto again; - } - } - return changed; -} - -/* Check for already reserved areas */ -static inline int __init -bad_addr_size(unsigned long *addrp, unsigned long *sizep, unsigned long align) -{ - int i; - unsigned long addr = *addrp, last; - unsigned long size = *sizep; - int changed = 0; -again: - last = addr + size; - for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) { - struct early_res *r = &early_res[i]; - if (last > r->start && addr < r->start) { - size = r->start - addr; - changed = 1; - goto again; - } - if (last > r->end && addr < r->end) { - addr = round_up(r->end, align); - size = last - addr; - changed = 1; - goto again; - } - if (last <= r->end && addr >= r->start) { - (*sizep)++; - return 0; - } - } - if (changed) { - *addrp = addr; - *sizep = size; - } - return changed; -} -/* - * This function checks if any part of the range <start,end> is mapped - * with type. - */ -int -e820_any_mapped(unsigned long start, unsigned long end, unsigned type) -{ - int i; - - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; - - if (type && ei->type != type) - continue; - if (ei->addr >= end || ei->addr + ei->size <= start) - continue; - return 1; - } - return 0; -} -EXPORT_SYMBOL_GPL(e820_any_mapped); - -/* - * This function checks if the entire range <start,end> is mapped with type. - * - * Note: this function only works correct if the e820 table is sorted and - * not-overlapping, which is the case - */ -int __init e820_all_mapped(unsigned long start, unsigned long end, - unsigned type) -{ - int i; - - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; - - if (type && ei->type != type) - continue; - /* is the region (part) in overlap with the current region ?*/ - if (ei->addr >= end || ei->addr + ei->size <= start) - continue; - - /* if the region is at the beginning of <start,end> we move - * start to the end of the region since it's ok until there - */ - if (ei->addr <= start) - start = ei->addr + ei->size; - /* - * if start is now at or beyond end, we're done, full - * coverage - */ - if (start >= end) - return 1; - } - return 0; -} - -/* - * Find a free area with specified alignment in a specific range. - */ -unsigned long __init find_e820_area(unsigned long start, unsigned long end, - unsigned long size, unsigned long align) -{ - int i; - - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; - unsigned long addr, last; - unsigned long ei_last; - - if (ei->type != E820_RAM) - continue; - addr = round_up(ei->addr, align); - ei_last = ei->addr + ei->size; - if (addr < start) - addr = round_up(start, align); - if (addr >= ei_last) - continue; - while (bad_addr(&addr, size, align) && addr+size <= ei_last) - ; - last = addr + size; - if (last > ei_last) - continue; - if (last > end) - continue; - return addr; - } - return -1UL; -} - -/* - * Find next free range after *start - */ -unsigned long __init find_e820_area_size(unsigned long start, - unsigned long *sizep, - unsigned long align) -{ - int i; - - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; - unsigned long addr, last; - unsigned long ei_last; - - if (ei->type != E820_RAM) - continue; - addr = round_up(ei->addr, align); - ei_last = ei->addr + ei->size; - if (addr < start) - addr = round_up(start, align); - if (addr >= ei_last) - continue; - *sizep = ei_last - addr; - while (bad_addr_size(&addr, sizep, align) && - addr + *sizep <= ei_last) - ; - last = addr + *sizep; - if (last > ei_last) - continue; - return addr; - } - return -1UL; - -} -/* - * Find the highest page frame number we have available - */ -unsigned long __init e820_end_of_ram(void) -{ - unsigned long end_pfn; - - end_pfn = find_max_pfn_with_active_regions(); - - if (end_pfn > max_pfn_mapped) - max_pfn_mapped = end_pfn; - if (max_pfn_mapped > MAXMEM>>PAGE_SHIFT) - max_pfn_mapped = MAXMEM>>PAGE_SHIFT; - if (end_pfn > end_user_pfn) - end_pfn = end_user_pfn; - if (end_pfn > max_pfn_mapped) - end_pfn = max_pfn_mapped; - - printk(KERN_INFO "max_pfn_mapped = %lu\n", max_pfn_mapped); - return end_pfn; -} - -/* - * Mark e820 reserved areas as busy for the resource manager. - */ -void __init e820_reserve_resources(void) -{ - int i; - struct resource *res; - - res = alloc_bootmem_low(sizeof(struct resource) * e820.nr_map); - for (i = 0; i < e820.nr_map; i++) { - switch (e820.map[i].type) { - case E820_RAM: res->name = "System RAM"; break; - case E820_ACPI: res->name = "ACPI Tables"; break; - case E820_NVS: res->name = "ACPI Non-volatile Storage"; break; - default: res->name = "reserved"; - } - res->start = e820.map[i].addr; - res->end = res->start + e820.map[i].size - 1; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; - insert_resource(&iomem_resource, res); - res++; - } -} - -/* - * Find the ranges of physical addresses that do not correspond to - * e820 RAM areas and mark the corresponding pages as nosave for software - * suspend and suspend to RAM. - * - * This function requires the e820 map to be sorted and without any - * overlapping entries and assumes the first e820 area to be RAM. - */ -void __init e820_mark_nosave_regions(void) -{ - int i; - unsigned long paddr; - - paddr = round_down(e820.map[0].addr + e820.map[0].size, PAGE_SIZE); - for (i = 1; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; - - if (paddr < ei->addr) - register_nosave_region(PFN_DOWN(paddr), - PFN_UP(ei->addr)); - - paddr = round_down(ei->addr + ei->size, PAGE_SIZE); - if (ei->type != E820_RAM) - register_nosave_region(PFN_UP(ei->addr), - PFN_DOWN(paddr)); - - if (paddr >= (end_pfn << PAGE_SHIFT)) - break; - } -} - -/* - * Finds an active region in the address range from start_pfn to end_pfn and - * returns its range in ei_startpfn and ei_endpfn for the e820 entry. - */ -static int __init e820_find_active_region(const struct e820entry *ei, - unsigned long start_pfn, - unsigned long end_pfn, - unsigned long *ei_startpfn, - unsigned long *ei_endpfn) -{ - *ei_startpfn = round_up(ei->addr, PAGE_SIZE) >> PAGE_SHIFT; - *ei_endpfn = round_down(ei->addr + ei->size, PAGE_SIZE) >> PAGE_SHIFT; - - /* Skip map entries smaller than a page */ - if (*ei_startpfn >= *ei_endpfn) - return 0; - - /* Check if max_pfn_mapped should be updated */ - if (ei->type != E820_RAM && *ei_endpfn > max_pfn_mapped) - max_pfn_mapped = *ei_endpfn; - - /* Skip if map is outside the node */ - if (ei->type != E820_RAM || *ei_endpfn <= start_pfn || - *ei_startpfn >= end_pfn) - return 0; - - /* Check for overlaps */ - if (*ei_startpfn < start_pfn) - *ei_startpfn = start_pfn; - if (*ei_endpfn > end_pfn) - *ei_endpfn = end_pfn; - - /* Obey end_user_pfn to save on memmap */ - if (*ei_startpfn >= end_user_pfn) - return 0; - if (*ei_endpfn > end_user_pfn) - *ei_endpfn = end_user_pfn; - - return 1; -} - -/* Walk the e820 map and register active regions within a node */ -void __init -e820_register_active_regions(int nid, unsigned long start_pfn, - unsigned long end_pfn) -{ - unsigned long ei_startpfn; - unsigned long ei_endpfn; - int i; - - for (i = 0; i < e820.nr_map; i++) - if (e820_find_active_region(&e820.map[i], - start_pfn, end_pfn, - &ei_startpfn, &ei_endpfn)) - add_active_range(nid, ei_startpfn, ei_endpfn); -} - -/* - * Add a memory region to the kernel e820 map. - */ -void __init add_memory_region(unsigned long start, unsigned long size, int type) -{ - int x = e820.nr_map; - - if (x == E820MAX) { - printk(KERN_ERR "Ooops! Too many entries in the memory map!\n"); - return; - } - - e820.map[x].addr = start; - e820.map[x].size = size; - e820.map[x].type = type; - e820.nr_map++; -} - -/* - * Find the hole size (in bytes) in the memory range. - * @start: starting address of the memory range to scan - * @end: ending address of the memory range to scan - */ -unsigned long __init e820_hole_size(unsigned long start, unsigned long end) -{ - unsigned long start_pfn = start >> PAGE_SHIFT; - unsigned long end_pfn = end >> PAGE_SHIFT; - unsigned long ei_startpfn, ei_endpfn, ram = 0; - int i; - - for (i = 0; i < e820.nr_map; i++) { - if (e820_find_active_region(&e820.map[i], - start_pfn, end_pfn, - &ei_startpfn, &ei_endpfn)) - ram += ei_endpfn - ei_startpfn; - } - return end - start - (ram << PAGE_SHIFT); -} - -static void __init e820_print_map(char *who) -{ - int i; - - for (i = 0; i < e820.nr_map; i++) { - printk(KERN_INFO " %s: %016Lx - %016Lx ", who, - (unsigned long long) e820.map[i].addr, - (unsigned long long) - (e820.map[i].addr + e820.map[i].size)); - switch (e820.map[i].type) { - case E820_RAM: - printk(KERN_CONT "(usable)\n"); - break; - case E820_RESERVED: - printk(KERN_CONT "(reserved)\n"); - break; - case E820_ACPI: - printk(KERN_CONT "(ACPI data)\n"); - break; - case E820_NVS: - printk(KERN_CONT "(ACPI NVS)\n"); - break; - default: - printk(KERN_CONT "type %u\n", e820.map[i].type); - break; - } - } -} - -/* - * Sanitize the BIOS e820 map. - * - * Some e820 responses include overlapping entries. The following - * replaces the original e820 map with a new one, removing overlaps. - * - */ -static int __init sanitize_e820_map(struct e820entry *biosmap, char *pnr_map) -{ - struct change_member { - struct e820entry *pbios; /* pointer to original bios entry */ - unsigned long long addr; /* address for this change point */ - }; - static struct change_member change_point_list[2*E820MAX] __initdata; - static struct change_member *change_point[2*E820MAX] __initdata; - static struct e820entry *overlap_list[E820MAX] __initdata; - static struct e820entry new_bios[E820MAX] __initdata; - struct change_member *change_tmp; - unsigned long current_type, last_type; - unsigned long long last_addr; - int chgidx, still_changing; - int overlap_entries; - int new_bios_entry; - int old_nr, new_nr, chg_nr; - int i; - - /* - Visually we're performing the following - (1,2,3,4 = memory types)... - - Sample memory map (w/overlaps): - ____22__________________ - ______________________4_ - ____1111________________ - _44_____________________ - 11111111________________ - ____________________33__ - ___________44___________ - __________33333_________ - ______________22________ - ___________________2222_ - _________111111111______ - _____________________11_ - _________________4______ - - Sanitized equivalent (no overlap): - 1_______________________ - _44_____________________ - ___1____________________ - ____22__________________ - ______11________________ - _________1______________ - __________3_____________ - ___________44___________ - _____________33_________ - _______________2________ - ________________1_______ - _________________4______ - ___________________2____ - ____________________33__ - ______________________4_ - */ - - /* if there's only one memory region, don't bother */ - if (*pnr_map < 2) - return -1; - - old_nr = *pnr_map; - - /* bail out if we find any unreasonable addresses in bios map */ - for (i = 0; i < old_nr; i++) - if (biosmap[i].addr + biosmap[i].size < biosmap[i].addr) - return -1; - - /* create pointers for initial change-point information (for sorting) */ - for (i = 0; i < 2 * old_nr; i++) - change_point[i] = &change_point_list[i]; - - /* record all known change-points (starting and ending addresses), - omitting those that are for empty memory regions */ - chgidx = 0; - for (i = 0; i < old_nr; i++) { - if (biosmap[i].size != 0) { - change_point[chgidx]->addr = biosmap[i].addr; - change_point[chgidx++]->pbios = &biosmap[i]; - change_point[chgidx]->addr = biosmap[i].addr + - biosmap[i].size; - change_point[chgidx++]->pbios = &biosmap[i]; - } - } - chg_nr = chgidx; - - /* sort change-point list by memory addresses (low -> high) */ - still_changing = 1; - while (still_changing) { - still_changing = 0; - for (i = 1; i < chg_nr; i++) { - unsigned long long curaddr, lastaddr; - unsigned long long curpbaddr, lastpbaddr; - - curaddr = change_point[i]->addr; - lastaddr = change_point[i - 1]->addr; - curpbaddr = change_point[i]->pbios->addr; - lastpbaddr = change_point[i - 1]->pbios->addr; - - /* - * swap entries, when: - * - * curaddr > lastaddr or - * curaddr == lastaddr and curaddr == curpbaddr and - * lastaddr != lastpbaddr - */ - if (curaddr < lastaddr || - (curaddr == lastaddr && curaddr == curpbaddr && - lastaddr != lastpbaddr)) { - change_tmp = change_point[i]; - change_point[i] = change_point[i-1]; - change_point[i-1] = change_tmp; - still_changing = 1; - } - } - } - - /* create a new bios memory map, removing overlaps */ - overlap_entries = 0; /* number of entries in the overlap table */ - new_bios_entry = 0; /* index for creating new bios map entries */ - last_type = 0; /* start with undefined memory type */ - last_addr = 0; /* start with 0 as last starting address */ - - /* loop through change-points, determining affect on the new bios map */ - for (chgidx = 0; chgidx < chg_nr; chgidx++) { - /* keep track of all overlapping bios entries */ - if (change_point[chgidx]->addr == - change_point[chgidx]->pbios->addr) { - /* - * add map entry to overlap list (> 1 entry - * implies an overlap) - */ - overlap_list[overlap_entries++] = - change_point[chgidx]->pbios; - } else { - /* - * remove entry from list (order independent, - * so swap with last) - */ - for (i = 0; i < overlap_entries; i++) { - if (overlap_list[i] == - change_point[chgidx]->pbios) - overlap_list[i] = - overlap_list[overlap_entries-1]; - } - overlap_entries--; - } - /* - * if there are overlapping entries, decide which - * "type" to use (larger value takes precedence -- - * 1=usable, 2,3,4,4+=unusable) - */ - current_type = 0; - for (i = 0; i < overlap_entries; i++) - if (overlap_list[i]->type > current_type) - current_type = overlap_list[i]->type; - /* - * continue building up new bios map based on this - * information - */ - if (current_type != last_type) { - if (last_type != 0) { - new_bios[new_bios_entry].size = - change_point[chgidx]->addr - last_addr; - /* - * move forward only if the new size - * was non-zero - */ - if (new_bios[new_bios_entry].size != 0) - /* - * no more space left for new - * bios entries ? - */ - if (++new_bios_entry >= E820MAX) - break; - } - if (current_type != 0) { - new_bios[new_bios_entry].addr = - change_point[chgidx]->addr; - new_bios[new_bios_entry].type = current_type; - last_addr = change_point[chgidx]->addr; - } - last_type = current_type; - } - } - /* retain count for new bios entries */ - new_nr = new_bios_entry; - - /* copy new bios mapping into original location */ - memcpy(biosmap, new_bios, new_nr * sizeof(struct e820entry)); - *pnr_map = new_nr; - - return 0; -} - -/* - * Copy the BIOS e820 map into a safe place. - * - * Sanity-check it while we're at it.. - * - * If we're lucky and live on a modern system, the setup code - * will have given us a memory map that we can use to properly - * set up memory. If we aren't, we'll fake a memory map. - */ -static int __init copy_e820_map(struct e820entry *biosmap, int nr_map) -{ - /* Only one memory region (or negative)? Ignore it */ - if (nr_map < 2) - return -1; - - do { - u64 start = biosmap->addr; - u64 size = biosmap->size; - u64 end = start + size; - u32 type = biosmap->type; - - /* Overflow in 64 bits? Ignore the memory map. */ - if (start > end) - return -1; - - add_memory_region(start, size, type); - } while (biosmap++, --nr_map); - return 0; -} - -static void early_panic(char *msg) -{ - early_printk(msg); - panic(msg); -} - -/* We're not void only for x86 32-bit compat */ -char * __init machine_specific_memory_setup(void) -{ - char *who = "BIOS-e820"; - /* - * Try to copy the BIOS-supplied E820-map. - * - * Otherwise fake a memory map; one section from 0k->640k, - * the next section from 1mb->appropriate_mem_k - */ - sanitize_e820_map(boot_params.e820_map, &boot_params.e820_entries); - if (copy_e820_map(boot_params.e820_map, boot_params.e820_entries) < 0) - early_panic("Cannot find a valid memory map"); - printk(KERN_INFO "BIOS-provided physical RAM map:\n"); - e820_print_map(who); - - /* In case someone cares... */ - return who; -} - -static int __init parse_memopt(char *p) -{ - if (!p) - return -EINVAL; - end_user_pfn = memparse(p, &p); - end_user_pfn >>= PAGE_SHIFT; - return 0; -} -early_param("mem", parse_memopt); - -static int userdef __initdata; - -static int __init parse_memmap_opt(char *p) -{ - char *oldp; - unsigned long long start_at, mem_size; - - if (!strcmp(p, "exactmap")) { -#ifdef CONFIG_CRASH_DUMP - /* - * If we are doing a crash dump, we still need to know - * the real mem size before original memory map is - * reset. - */ - e820_register_active_regions(0, 0, -1UL); - saved_max_pfn = e820_end_of_ram(); - remove_all_active_ranges(); -#endif - max_pfn_mapped = 0; - e820.nr_map = 0; - userdef = 1; - return 0; - } - - oldp = p; - mem_size = memparse(p, &p); - if (p == oldp) - return -EINVAL; - - userdef = 1; - if (*p == '@') { - start_at = memparse(p+1, &p); - add_memory_region(start_at, mem_size, E820_RAM); - } else if (*p == '#') { - start_at = memparse(p+1, &p); - add_memory_region(start_at, mem_size, E820_ACPI); - } else if (*p == '$') { - start_at = memparse(p+1, &p); - add_memory_region(start_at, mem_size, E820_RESERVED); - } else { - end_user_pfn = (mem_size >> PAGE_SHIFT); - } - return *p == '\0' ? 0 : -EINVAL; -} -early_param("memmap", parse_memmap_opt); - -void __init finish_e820_parsing(void) -{ - if (userdef) { - char nr = e820.nr_map; - - if (sanitize_e820_map(e820.map, &nr) < 0) - early_panic("Invalid user supplied memory map"); - e820.nr_map = nr; - - printk(KERN_INFO "user-defined physical RAM map:\n"); - e820_print_map("user"); - } -} - -void __init update_memory_range(u64 start, u64 size, unsigned old_type, - unsigned new_type) -{ - int i; - - BUG_ON(old_type == new_type); - - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; - u64 final_start, final_end; - if (ei->type != old_type) - continue; - /* totally covered? */ - if (ei->addr >= start && ei->size <= size) { - ei->type = new_type; - continue; - } - /* partially covered */ - final_start = max(start, ei->addr); - final_end = min(start + size, ei->addr + ei->size); - if (final_start >= final_end) - continue; - add_memory_region(final_start, final_end - final_start, - new_type); - } -} - -void __init update_e820(void) -{ - u8 nr_map; - - nr_map = e820.nr_map; - if (sanitize_e820_map(e820.map, &nr_map)) - return; - e820.nr_map = nr_map; - printk(KERN_INFO "modified physical RAM map:\n"); - e820_print_map("modified"); -} - -unsigned long pci_mem_start = 0xaeedbabe; -EXPORT_SYMBOL(pci_mem_start); - -/* - * Search for the biggest gap in the low 32 bits of the e820 - * memory space. We pass this space to PCI to assign MMIO resources - * for hotplug or unconfigured devices in. - * Hopefully the BIOS let enough space left. - */ -__init void e820_setup_gap(void) -{ - unsigned long gapstart, gapsize, round; - unsigned long last; - int i; - int found = 0; - - last = 0x100000000ull; - gapstart = 0x10000000; - gapsize = 0x400000; - i = e820.nr_map; - while (--i >= 0) { - unsigned long long start = e820.map[i].addr; - unsigned long long end = start + e820.map[i].size; - - /* - * Since "last" is at most 4GB, we know we'll - * fit in 32 bits if this condition is true - */ - if (last > end) { - unsigned long gap = last - end; - - if (gap > gapsize) { - gapsize = gap; - gapstart = end; - found = 1; - } - } - if (start < last) - last = start; - } - - if (!found) { - gapstart = (end_pfn << PAGE_SHIFT) + 1024*1024; - printk(KERN_ERR "PCI: Warning: Cannot find a gap in the 32bit " - "address range\n" - KERN_ERR "PCI: Unassigned devices with 32bit resource " - "registers may break!\n"); - } - - /* - * See how much we want to round up: start off with - * rounding to the next 1MB area. - */ - round = 0x100000; - while ((gapsize >> 4) > round) - round += round; - /* Fun with two's complement */ - pci_mem_start = (gapstart + round) & -round; - - printk(KERN_INFO - "Allocating PCI resources starting at %lx (gap: %lx:%lx)\n", - pci_mem_start, gapstart, gapsize); -} - -int __init arch_get_ram_range(int slot, u64 *addr, u64 *size) -{ - int i; - - if (slot < 0 || slot >= e820.nr_map) - return -1; - for (i = slot; i < e820.nr_map; i++) { - if (e820.map[i].type != E820_RAM) - continue; - break; - } - if (i == e820.nr_map || e820.map[i].addr > (max_pfn << PAGE_SHIFT)) - return -1; - *addr = e820.map[i].addr; - *size = min_t(u64, e820.map[i].size + e820.map[i].addr, - max_pfn << PAGE_SHIFT) - *addr; - return i + 1; -} diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 9f51e1ea9e82..a0e11c0cc872 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -50,7 +50,7 @@ static void __init fix_hypertransport_config(int num, int slot, int func) static void __init via_bugs(int num, int slot, int func) { #ifdef CONFIG_GART_IOMMU - if ((end_pfn > MAX_DMA32_PFN || force_iommu) && + if ((max_pfn > MAX_DMA32_PFN || force_iommu) && !gart_iommu_aperture_allowed) { printk(KERN_INFO "Looks like a VIA chipset. Disabling IOMMU." @@ -98,17 +98,6 @@ static void __init nvidia_bugs(int num, int slot, int func) } -static void __init ati_bugs(int num, int slot, int func) -{ -#ifdef CONFIG_X86_IO_APIC - if (timer_over_8254 == 1) { - timer_over_8254 = 0; - printk(KERN_INFO - "ATI board detected. Disabling timer routing over 8254.\n"); - } -#endif -} - #define QFLAG_APPLY_ONCE 0x1 #define QFLAG_APPLIED 0x2 #define QFLAG_DONE (QFLAG_APPLY_ONCE|QFLAG_APPLIED) @@ -126,14 +115,23 @@ static struct chipset early_qrk[] __initdata = { PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, nvidia_bugs }, { PCI_VENDOR_ID_VIA, PCI_ANY_ID, PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, via_bugs }, - { PCI_VENDOR_ID_ATI, PCI_ANY_ID, - PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, ati_bugs }, { PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, fix_hypertransport_config }, {} }; -static void __init check_dev_quirk(int num, int slot, int func) +/** + * check_dev_quirk - apply early quirks to a given PCI device + * @num: bus number + * @slot: slot number + * @func: PCI function + * + * Check the vendor & device ID against the early quirks table. + * + * If the device is single function, let early_quirks() know so we don't + * poke at this device again. + */ +static int __init check_dev_quirk(int num, int slot, int func) { u16 class; u16 vendor; @@ -144,7 +142,7 @@ static void __init check_dev_quirk(int num, int slot, int func) class = read_pci_config_16(num, slot, func, PCI_CLASS_DEVICE); if (class == 0xffff) - return; + return -1; /* no class, treat as single function */ vendor = read_pci_config_16(num, slot, func, PCI_VENDOR_ID); @@ -167,7 +165,9 @@ static void __init check_dev_quirk(int num, int slot, int func) type = read_pci_config_byte(num, slot, func, PCI_HEADER_TYPE); if (!(type & 0x80)) - return; + return -1; + + return 0; } void __init early_quirks(void) @@ -180,6 +180,9 @@ void __init early_quirks(void) /* Poor man's PCI discovery */ for (num = 0; num < 32; num++) for (slot = 0; slot < 32; slot++) - for (func = 0; func < 8; func++) - check_dev_quirk(num, slot, func); + for (func = 0; func < 8; func++) { + /* Only probe function 0 on single fn devices */ + if (check_dev_quirk(num, slot, func)) + break; + } } diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index 643fd861b724..ff9e7350da54 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -196,7 +196,7 @@ static struct console simnow_console = { static struct console *early_console = &early_vga_console; static int early_console_initialized; -void early_printk(const char *fmt, ...) +asmlinkage void early_printk(const char *fmt, ...) { char buf[512]; int n; diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c index 77d424cf68b3..06cc8d4254b1 100644 --- a/arch/x86/kernel/efi.c +++ b/arch/x86/kernel/efi.c @@ -64,6 +64,17 @@ static int __init setup_noefi(char *arg) } early_param("noefi", setup_noefi); +int add_efi_memmap; +EXPORT_SYMBOL(add_efi_memmap); + +static int __init setup_add_efi_memmap(char *arg) +{ + add_efi_memmap = 1; + return 0; +} +early_param("add_efi_memmap", setup_add_efi_memmap); + + static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) { return efi_call_virt2(get_time, tm, tc); @@ -213,6 +224,50 @@ unsigned long efi_get_time(void) eft.minute, eft.second); } +/* + * Tell the kernel about the EFI memory map. This might include + * more than the max 128 entries that can fit in the e820 legacy + * (zeropage) memory map. + */ + +static void __init do_add_efi_memmap(void) +{ + void *p; + + for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { + efi_memory_desc_t *md = p; + unsigned long long start = md->phys_addr; + unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; + int e820_type; + + if (md->attribute & EFI_MEMORY_WB) + e820_type = E820_RAM; + else + e820_type = E820_RESERVED; + e820_add_region(start, size, e820_type); + } + sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); +} + +void __init efi_reserve_early(void) +{ + unsigned long pmap; + +#ifdef CONFIG_X86_32 + pmap = boot_params.efi_info.efi_memmap; +#else + pmap = (boot_params.efi_info.efi_memmap | + ((__u64)boot_params.efi_info.efi_memmap_hi<<32)); +#endif + memmap.phys_map = (void *)pmap; + memmap.nr_map = boot_params.efi_info.efi_memmap_size / + boot_params.efi_info.efi_memdesc_size; + memmap.desc_version = boot_params.efi_info.efi_memdesc_version; + memmap.desc_size = boot_params.efi_info.efi_memdesc_size; + reserve_early(pmap, pmap + memmap.nr_map * memmap.desc_size, + "EFI memmap"); +} + #if EFI_DEBUG static void __init print_efi_memmap(void) { @@ -244,19 +299,11 @@ void __init efi_init(void) #ifdef CONFIG_X86_32 efi_phys.systab = (efi_system_table_t *)boot_params.efi_info.efi_systab; - memmap.phys_map = (void *)boot_params.efi_info.efi_memmap; #else efi_phys.systab = (efi_system_table_t *) (boot_params.efi_info.efi_systab | ((__u64)boot_params.efi_info.efi_systab_hi<<32)); - memmap.phys_map = (void *) - (boot_params.efi_info.efi_memmap | - ((__u64)boot_params.efi_info.efi_memmap_hi<<32)); #endif - memmap.nr_map = boot_params.efi_info.efi_memmap_size / - boot_params.efi_info.efi_memdesc_size; - memmap.desc_version = boot_params.efi_info.efi_memdesc_version; - memmap.desc_size = boot_params.efi_info.efi_memdesc_size; efi.systab = early_ioremap((unsigned long)efi_phys.systab, sizeof(efi_system_table_t)); @@ -370,6 +417,8 @@ void __init efi_init(void) if (memmap.desc_size != sizeof(efi_memory_desc_t)) printk(KERN_WARNING "Kernel-defined memdesc" "doesn't match the one from EFI!\n"); + if (add_efi_memmap) + do_add_efi_memmap(); /* Setup for EFI runtime service */ reboot_type = BOOT_EFI; @@ -424,7 +473,7 @@ void __init efi_enter_virtual_mode(void) size = md->num_pages << EFI_PAGE_SHIFT; end = md->phys_addr + size; - if (PFN_UP(end) <= max_pfn_mapped) + if (PFN_UP(end) <= max_low_pfn_mapped) va = __va(md->phys_addr); else va = efi_ioremap(md->phys_addr, size); diff --git a/arch/x86/kernel/efi_32.c b/arch/x86/kernel/efi_32.c index 5d23d85624d4..4b63c8e1f13b 100644 --- a/arch/x86/kernel/efi_32.c +++ b/arch/x86/kernel/efi_32.c @@ -49,13 +49,13 @@ void efi_call_phys_prelog(void) local_irq_save(efi_rt_eflags); /* - * If I don't have PSE, I should just duplicate two entries in page - * directory. If I have PSE, I just need to duplicate one entry in + * If I don't have PAE, I should just duplicate two entries in page + * directory. If I have PAE, I just need to duplicate one entry in * page directory. */ cr4 = read_cr4(); - if (cr4 & X86_CR4_PSE) { + if (cr4 & X86_CR4_PAE) { efi_bak_pg_dir_pointer[0].pgd = swapper_pg_dir[pgd_index(0)].pgd; swapper_pg_dir[0].pgd = @@ -93,7 +93,7 @@ void efi_call_phys_epilog(void) cr4 = read_cr4(); - if (cr4 & X86_CR4_PSE) { + if (cr4 & X86_CR4_PAE) { swapper_pg_dir[pgd_index(0)].pgd = efi_bak_pg_dir_pointer[0].pgd; } else { diff --git a/arch/x86/kernel/efi_64.c b/arch/x86/kernel/efi_64.c index d0060fdcccac..652c5287215f 100644 --- a/arch/x86/kernel/efi_64.c +++ b/arch/x86/kernel/efi_64.c @@ -97,13 +97,7 @@ void __init efi_call_phys_epilog(void) early_runtime_code_mapping_set_exec(0); } -void __init efi_reserve_bootmem(void) -{ - reserve_bootmem_generic((unsigned long)memmap.phys_map, - memmap.nr_map * memmap.desc_size); -} - -void __iomem * __init efi_ioremap(unsigned long phys_addr, unsigned long size) +void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size) { static unsigned pages_mapped __initdata; unsigned i, pages; diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 2a609dc3271c..6bc07f0f1202 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -51,14 +51,15 @@ #include <asm/percpu.h> #include <asm/dwarf2.h> #include <asm/processor-flags.h> -#include "irq_vectors.h" +#include <asm/ftrace.h> +#include <asm/irq_vectors.h> /* * We use macros for low-level operations which need to be overridden * for paravirtualization. The following will never clobber any registers: * INTERRUPT_RETURN (aka. "iret") * GET_CR0_INTO_EAX (aka. "movl %cr0, %eax") - * ENABLE_INTERRUPTS_SYSCALL_RET (aka "sti; sysexit"). + * ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit"). * * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY). @@ -248,6 +249,7 @@ ENTRY(resume_userspace) DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt # setting need_resched or sigpending # between sampling and the iret + TRACE_IRQS_OFF movl TI_flags(%ebp), %ecx andl $_TIF_WORK_MASK, %ecx # is there any work to be done on # int/exception return? @@ -348,7 +350,7 @@ sysenter_past_esp: xorl %ebp,%ebp TRACE_IRQS_ON 1: mov PT_FS(%esp), %fs - ENABLE_INTERRUPTS_SYSCALL_RET + ENABLE_INTERRUPTS_SYSEXIT CFI_ENDPROC .pushsection .fixup,"ax" 2: movl $0,PT_FS(%esp) @@ -873,10 +875,10 @@ ENTRY(native_iret) .previous END(native_iret) -ENTRY(native_irq_enable_syscall_ret) +ENTRY(native_irq_enable_sysexit) sti sysexit -END(native_irq_enable_syscall_ret) +END(native_irq_enable_sysexit) #endif KPROBE_ENTRY(int3) @@ -1023,6 +1025,7 @@ ENTRY(xen_sysenter_target) RING0_INT_FRAME addl $5*4, %esp /* remove xen-provided frame */ jmp sysenter_past_esp + CFI_ENDPROC ENTRY(xen_hypervisor_callback) CFI_STARTPROC @@ -1109,6 +1112,77 @@ ENDPROC(xen_failsafe_callback) #endif /* CONFIG_XEN */ +#ifdef CONFIG_FTRACE +#ifdef CONFIG_DYNAMIC_FTRACE + +ENTRY(mcount) + pushl %eax + pushl %ecx + pushl %edx + movl 0xc(%esp), %eax + subl $MCOUNT_INSN_SIZE, %eax + +.globl mcount_call +mcount_call: + call ftrace_stub + + popl %edx + popl %ecx + popl %eax + + ret +END(mcount) + +ENTRY(ftrace_caller) + pushl %eax + pushl %ecx + pushl %edx + movl 0xc(%esp), %eax + movl 0x4(%ebp), %edx + subl $MCOUNT_INSN_SIZE, %eax + +.globl ftrace_call +ftrace_call: + call ftrace_stub + + popl %edx + popl %ecx + popl %eax + +.globl ftrace_stub +ftrace_stub: + ret +END(ftrace_caller) + +#else /* ! CONFIG_DYNAMIC_FTRACE */ + +ENTRY(mcount) + cmpl $ftrace_stub, ftrace_trace_function + jnz trace +.globl ftrace_stub +ftrace_stub: + ret + + /* taken from glibc */ +trace: + pushl %eax + pushl %ecx + pushl %edx + movl 0xc(%esp), %eax + movl 0x4(%ebp), %edx + subl $MCOUNT_INSN_SIZE, %eax + + call *ftrace_trace_function + + popl %edx + popl %ecx + popl %eax + + jmp ftrace_stub +END(mcount) +#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_FTRACE */ + .section .rodata,"a" #include "syscall_table_32.S" diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 556a8df522a7..ae63e584c340 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -51,16 +51,121 @@ #include <asm/page.h> #include <asm/irqflags.h> #include <asm/paravirt.h> +#include <asm/ftrace.h> .code64 +#ifdef CONFIG_FTRACE +#ifdef CONFIG_DYNAMIC_FTRACE +ENTRY(mcount) + + subq $0x38, %rsp + movq %rax, (%rsp) + movq %rcx, 8(%rsp) + movq %rdx, 16(%rsp) + movq %rsi, 24(%rsp) + movq %rdi, 32(%rsp) + movq %r8, 40(%rsp) + movq %r9, 48(%rsp) + + movq 0x38(%rsp), %rdi + subq $MCOUNT_INSN_SIZE, %rdi + +.globl mcount_call +mcount_call: + call ftrace_stub + + movq 48(%rsp), %r9 + movq 40(%rsp), %r8 + movq 32(%rsp), %rdi + movq 24(%rsp), %rsi + movq 16(%rsp), %rdx + movq 8(%rsp), %rcx + movq (%rsp), %rax + addq $0x38, %rsp + + retq +END(mcount) + +ENTRY(ftrace_caller) + + /* taken from glibc */ + subq $0x38, %rsp + movq %rax, (%rsp) + movq %rcx, 8(%rsp) + movq %rdx, 16(%rsp) + movq %rsi, 24(%rsp) + movq %rdi, 32(%rsp) + movq %r8, 40(%rsp) + movq %r9, 48(%rsp) + + movq 0x38(%rsp), %rdi + movq 8(%rbp), %rsi + subq $MCOUNT_INSN_SIZE, %rdi + +.globl ftrace_call +ftrace_call: + call ftrace_stub + + movq 48(%rsp), %r9 + movq 40(%rsp), %r8 + movq 32(%rsp), %rdi + movq 24(%rsp), %rsi + movq 16(%rsp), %rdx + movq 8(%rsp), %rcx + movq (%rsp), %rax + addq $0x38, %rsp + +.globl ftrace_stub +ftrace_stub: + retq +END(ftrace_caller) + +#else /* ! CONFIG_DYNAMIC_FTRACE */ +ENTRY(mcount) + cmpq $ftrace_stub, ftrace_trace_function + jnz trace +.globl ftrace_stub +ftrace_stub: + retq + +trace: + /* taken from glibc */ + subq $0x38, %rsp + movq %rax, (%rsp) + movq %rcx, 8(%rsp) + movq %rdx, 16(%rsp) + movq %rsi, 24(%rsp) + movq %rdi, 32(%rsp) + movq %r8, 40(%rsp) + movq %r9, 48(%rsp) + + movq 0x38(%rsp), %rdi + movq 8(%rbp), %rsi + subq $MCOUNT_INSN_SIZE, %rdi + + call *ftrace_trace_function + + movq 48(%rsp), %r9 + movq 40(%rsp), %r8 + movq 32(%rsp), %rdi + movq 24(%rsp), %rsi + movq 16(%rsp), %rdx + movq 8(%rsp), %rcx + movq (%rsp), %rax + addq $0x38, %rsp + + jmp ftrace_stub +END(mcount) +#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_FTRACE */ + #ifndef CONFIG_PREEMPT #define retint_kernel retint_restore_args #endif #ifdef CONFIG_PARAVIRT -ENTRY(native_irq_enable_syscall_ret) - movq %gs:pda_oldrsp,%rsp +ENTRY(native_usergs_sysret64) swapgs sysretq #endif /* CONFIG_PARAVIRT */ @@ -104,7 +209,7 @@ ENTRY(native_irq_enable_syscall_ret) .macro FAKE_STACK_FRAME child_rip /* push in order ss, rsp, eflags, cs, rip */ xorl %eax, %eax - pushq %rax /* ss */ + pushq $__KERNEL_DS /* ss */ CFI_ADJUST_CFA_OFFSET 8 /*CFI_REL_OFFSET ss,0*/ pushq %rax /* rsp */ @@ -169,13 +274,13 @@ ENTRY(ret_from_fork) CFI_ADJUST_CFA_OFFSET -4 call schedule_tail GET_THREAD_INFO(%rcx) - testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),threadinfo_flags(%rcx) + testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),TI_flags(%rcx) jnz rff_trace rff_action: RESTORE_REST testl $3,CS-ARGOFFSET(%rsp) # from kernel_thread? je int_ret_from_sys_call - testl $_TIF_IA32,threadinfo_flags(%rcx) + testl $_TIF_IA32,TI_flags(%rcx) jnz int_ret_from_sys_call RESTORE_TOP_OF_STACK %rdi,ARGOFFSET jmp ret_from_sys_call @@ -244,7 +349,8 @@ ENTRY(system_call_after_swapgs) movq %rcx,RIP-ARGOFFSET(%rsp) CFI_REL_OFFSET rip,RIP-ARGOFFSET GET_THREAD_INFO(%rcx) - testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%rcx) + testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP), \ + TI_flags(%rcx) jnz tracesys cmpq $__NR_syscall_max,%rax ja badsys @@ -263,7 +369,7 @@ sysret_check: GET_THREAD_INFO(%rcx) DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - movl threadinfo_flags(%rcx),%edx + movl TI_flags(%rcx),%edx andl %edi,%edx jnz sysret_careful CFI_REMEMBER_STATE @@ -275,7 +381,8 @@ sysret_check: CFI_REGISTER rip,rcx RESTORE_ARGS 0,-ARG_SKIP,1 /*CFI_REGISTER rflags,r11*/ - ENABLE_INTERRUPTS_SYSCALL_RET + movq %gs:pda_oldrsp, %rsp + USERGS_SYSRET64 CFI_RESTORE_STATE /* Handle reschedules */ @@ -305,7 +412,7 @@ sysret_signal: leaq -ARGOFFSET(%rsp),%rdi # &pt_regs -> arg1 xorl %esi,%esi # oldset -> arg2 call ptregscall_common -1: movl $_TIF_NEED_RESCHED,%edi +1: movl $_TIF_WORK_MASK,%edi /* Use IRET because user could have changed frame. This works because ptregscall_common has called FIXUP_TOP_OF_STACK. */ DISABLE_INTERRUPTS(CLBR_NONE) @@ -347,10 +454,10 @@ int_ret_from_sys_call: int_with_check: LOCKDEP_SYS_EXIT_IRQ GET_THREAD_INFO(%rcx) - movl threadinfo_flags(%rcx),%edx + movl TI_flags(%rcx),%edx andl %edi,%edx jnz int_careful - andl $~TS_COMPAT,threadinfo_status(%rcx) + andl $~TS_COMPAT,TI_status(%rcx) jmp retint_swapgs /* Either reschedule or signal or syscall exit tracking needed. */ @@ -393,7 +500,7 @@ int_signal: movq %rsp,%rdi # &ptregs -> arg1 xorl %esi,%esi # oldset -> arg2 call do_notify_resume -1: movl $_TIF_NEED_RESCHED,%edi +1: movl $_TIF_WORK_MASK,%edi int_restore_rest: RESTORE_REST DISABLE_INTERRUPTS(CLBR_NONE) @@ -420,7 +527,6 @@ END(\label) PTREGSCALL stub_clone, sys_clone, %r8 PTREGSCALL stub_fork, sys_fork, %rdi PTREGSCALL stub_vfork, sys_vfork, %rdi - PTREGSCALL stub_rt_sigsuspend, sys_rt_sigsuspend, %rdx PTREGSCALL stub_sigaltstack, sys_sigaltstack, %rdx PTREGSCALL stub_iopl, sys_iopl, %rsi @@ -559,7 +665,7 @@ retint_with_reschedule: movl $_TIF_WORK_MASK,%edi retint_check: LOCKDEP_SYS_EXIT_IRQ - movl threadinfo_flags(%rcx),%edx + movl TI_flags(%rcx),%edx andl %edi,%edx CFI_REMEMBER_STATE jnz retint_careful @@ -647,17 +753,16 @@ retint_signal: RESTORE_REST DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - movl $_TIF_NEED_RESCHED,%edi GET_THREAD_INFO(%rcx) - jmp retint_check + jmp retint_with_reschedule #ifdef CONFIG_PREEMPT /* Returning to kernel space. Check if we need preemption */ /* rcx: threadinfo. interrupts off. */ ENTRY(retint_kernel) - cmpl $0,threadinfo_preempt_count(%rcx) + cmpl $0,TI_preempt_count(%rcx) jnz retint_restore_args - bt $TIF_NEED_RESCHED,threadinfo_flags(%rcx) + bt $TIF_NEED_RESCHED,TI_flags(%rcx) jnc retint_restore_args bt $9,EFLAGS-ARGOFFSET(%rsp) /* interrupts off? */ jnc retint_restore_args @@ -711,6 +816,9 @@ END(invalidate_interrupt\num) ENTRY(call_function_interrupt) apicinterrupt CALL_FUNCTION_VECTOR,smp_call_function_interrupt END(call_function_interrupt) +ENTRY(call_function_single_interrupt) + apicinterrupt CALL_FUNCTION_SINGLE_VECTOR,smp_call_function_single_interrupt +END(call_function_single_interrupt) ENTRY(irq_move_cleanup_interrupt) apicinterrupt IRQ_MOVE_CLEANUP_VECTOR,smp_irq_move_cleanup_interrupt END(irq_move_cleanup_interrupt) @@ -720,6 +828,10 @@ ENTRY(apic_timer_interrupt) apicinterrupt LOCAL_TIMER_VECTOR,smp_apic_timer_interrupt END(apic_timer_interrupt) +ENTRY(uv_bau_message_intr1) + apicinterrupt 220,uv_bau_message_interrupt +END(uv_bau_message_intr1) + ENTRY(error_interrupt) apicinterrupt ERROR_APIC_VECTOR,smp_error_interrupt END(error_interrupt) @@ -733,6 +845,7 @@ END(spurious_interrupt) */ .macro zeroentry sym INTR_FRAME + PARAVIRT_ADJUST_EXCEPTION_FRAME pushq $0 /* push error code/oldrax */ CFI_ADJUST_CFA_OFFSET 8 pushq %rax /* push real oldrax to the rdi slot */ @@ -745,6 +858,7 @@ END(spurious_interrupt) .macro errorentry sym XCPT_FRAME + PARAVIRT_ADJUST_EXCEPTION_FRAME pushq %rax CFI_ADJUST_CFA_OFFSET 8 CFI_REL_OFFSET rax,0 @@ -814,7 +928,7 @@ paranoid_restore\trace: jmp irq_return paranoid_userspace\trace: GET_THREAD_INFO(%rcx) - movl threadinfo_flags(%rcx),%ebx + movl TI_flags(%rcx),%ebx andl $_TIF_WORK_MASK,%ebx jz paranoid_swapgs\trace movq %rsp,%rdi /* &pt_regs */ @@ -912,7 +1026,7 @@ error_exit: testl %eax,%eax jne retint_kernel LOCKDEP_SYS_EXIT_IRQ - movl threadinfo_flags(%rcx),%edx + movl TI_flags(%rcx),%edx movl $_TIF_WORK_MASK,%edi andl %edi,%edx jnz retint_careful @@ -926,11 +1040,11 @@ error_kernelspace: iret run with kernel gs again, so don't set the user space flag. B stepping K8s sometimes report an truncated RIP for IRET exceptions returning to compat mode. Check for these here too. */ - leaq irq_return(%rip),%rbp - cmpq %rbp,RIP(%rsp) + leaq irq_return(%rip),%rcx + cmpq %rcx,RIP(%rsp) je error_swapgs - movl %ebp,%ebp /* zero extend */ - cmpq %rbp,RIP(%rsp) + movl %ecx,%ecx /* zero extend */ + cmpq %rcx,RIP(%rsp) je error_swapgs cmpq $gs_change,RIP(%rsp) je error_swapgs @@ -939,7 +1053,7 @@ KPROBE_END(error_entry) /* Reload gs selector with exception handling */ /* edi: new selector */ -ENTRY(load_gs_index) +ENTRY(native_load_gs_index) CFI_STARTPROC pushf CFI_ADJUST_CFA_OFFSET 8 @@ -953,7 +1067,7 @@ gs_change: CFI_ADJUST_CFA_OFFSET -8 ret CFI_ENDPROC -ENDPROC(load_gs_index) +ENDPROC(native_load_gs_index) .section __ex_table,"a" .align 8 @@ -1120,10 +1234,6 @@ ENTRY(coprocessor_segment_overrun) zeroentry do_coprocessor_segment_overrun END(coprocessor_segment_overrun) -ENTRY(reserved) - zeroentry do_reserved -END(reserved) - /* runs on exception stack */ ENTRY(double_fault) XCPT_FRAME diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c new file mode 100644 index 000000000000..ab115cd15fdf --- /dev/null +++ b/arch/x86/kernel/ftrace.c @@ -0,0 +1,141 @@ +/* + * Code for replacing ftrace calls with jumps. + * + * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com> + * + * Thanks goes to Ingo Molnar, for suggesting the idea. + * Mathieu Desnoyers, for suggesting postponing the modifications. + * Arjan van de Ven, for keeping me straight, and explaining to me + * the dangers of modifying code on the run. + */ + +#include <linux/spinlock.h> +#include <linux/hardirq.h> +#include <linux/ftrace.h> +#include <linux/percpu.h> +#include <linux/init.h> +#include <linux/list.h> + +#include <asm/alternative.h> +#include <asm/ftrace.h> + + +/* Long is fine, even if it is only 4 bytes ;-) */ +static long *ftrace_nop; + +union ftrace_code_union { + char code[MCOUNT_INSN_SIZE]; + struct { + char e8; + int offset; + } __attribute__((packed)); +}; + + +static int notrace ftrace_calc_offset(long ip, long addr) +{ + return (int)(addr - ip); +} + +notrace unsigned char *ftrace_nop_replace(void) +{ + return (char *)ftrace_nop; +} + +notrace unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) +{ + static union ftrace_code_union calc; + + calc.e8 = 0xe8; + calc.offset = ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr); + + /* + * No locking needed, this must be called via kstop_machine + * which in essence is like running on a uniprocessor machine. + */ + return calc.code; +} + +notrace int +ftrace_modify_code(unsigned long ip, unsigned char *old_code, + unsigned char *new_code) +{ + unsigned replaced; + unsigned old = *(unsigned *)old_code; /* 4 bytes */ + unsigned new = *(unsigned *)new_code; /* 4 bytes */ + unsigned char newch = new_code[4]; + int faulted = 0; + + /* + * Note: Due to modules and __init, code can + * disappear and change, we need to protect against faulting + * as well as code changing. + * + * No real locking needed, this code is run through + * kstop_machine. + */ + asm volatile ( + "1: lock\n" + " cmpxchg %3, (%2)\n" + " jnz 2f\n" + " movb %b4, 4(%2)\n" + "2:\n" + ".section .fixup, \"ax\"\n" + "3: movl $1, %0\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : "=r"(faulted), "=a"(replaced) + : "r"(ip), "r"(new), "c"(newch), + "0"(faulted), "a"(old) + : "memory"); + sync_core(); + + if (replaced != old && replaced != new) + faulted = 2; + + return faulted; +} + +notrace int ftrace_update_ftrace_func(ftrace_func_t func) +{ + unsigned long ip = (unsigned long)(&ftrace_call); + unsigned char old[MCOUNT_INSN_SIZE], *new; + int ret; + + memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE); + new = ftrace_call_replace(ip, (unsigned long)func); + ret = ftrace_modify_code(ip, old, new); + + return ret; +} + +notrace int ftrace_mcount_set(unsigned long *data) +{ + unsigned long ip = (long)(&mcount_call); + unsigned long *addr = data; + unsigned char old[MCOUNT_INSN_SIZE], *new; + + /* + * Replace the mcount stub with a pointer to the + * ip recorder function. + */ + memcpy(old, &mcount_call, MCOUNT_INSN_SIZE); + new = ftrace_call_replace(ip, *addr); + *addr = ftrace_modify_code(ip, old, new); + + return 0; +} + +int __init ftrace_dyn_arch_init(void *data) +{ + const unsigned char *const *noptable = find_nop_table(); + + /* This is running in kstop_machine */ + + ftrace_mcount_set(data); + + ftrace_nop = (unsigned long *)noptable[MCOUNT_INSN_SIZE]; + + return 0; +} diff --git a/arch/x86/kernel/genapic_64.c b/arch/x86/kernel/genapic_64.c index cbaaf69bedb2..1fa8be5bd217 100644 --- a/arch/x86/kernel/genapic_64.c +++ b/arch/x86/kernel/genapic_64.c @@ -51,7 +51,7 @@ void __init setup_apic_routing(void) else #endif - if (num_possible_cpus() <= 8) + if (max_physical_apicid < 8) genapic = &apic_flat; else genapic = &apic_physflat; diff --git a/arch/x86/kernel/genx2apic_uv_x.c b/arch/x86/kernel/genx2apic_uv_x.c index ebf13908a743..711f11c30b06 100644 --- a/arch/x86/kernel/genx2apic_uv_x.c +++ b/arch/x86/kernel/genx2apic_uv_x.c @@ -5,9 +5,10 @@ * * SGI UV APIC functions (note: not an Intel compatible APIC) * - * Copyright (C) 2007 Silicon Graphics, Inc. All rights reserved. + * Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved. */ +#include <linux/kernel.h> #include <linux/threads.h> #include <linux/cpumask.h> #include <linux/string.h> @@ -20,6 +21,7 @@ #include <asm/smp.h> #include <asm/ipi.h> #include <asm/genapic.h> +#include <asm/pgtable.h> #include <asm/uv/uv_mmrs.h> #include <asm/uv/uv_hub.h> @@ -55,37 +57,37 @@ static cpumask_t uv_vector_allocation_domain(int cpu) int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip) { unsigned long val; - int nasid; + int pnode; - nasid = uv_apicid_to_nasid(phys_apicid); + pnode = uv_apicid_to_pnode(phys_apicid); val = (1UL << UVH_IPI_INT_SEND_SHFT) | (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) | (((long)start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) | APIC_DM_INIT; - uv_write_global_mmr64(nasid, UVH_IPI_INT, val); + uv_write_global_mmr64(pnode, UVH_IPI_INT, val); mdelay(10); val = (1UL << UVH_IPI_INT_SEND_SHFT) | (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) | (((long)start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) | APIC_DM_STARTUP; - uv_write_global_mmr64(nasid, UVH_IPI_INT, val); + uv_write_global_mmr64(pnode, UVH_IPI_INT, val); return 0; } static void uv_send_IPI_one(int cpu, int vector) { unsigned long val, apicid, lapicid; - int nasid; + int pnode; apicid = per_cpu(x86_cpu_to_apicid, cpu); /* ZZZ - cache node-local ? */ lapicid = apicid & 0x3f; /* ZZZ macro needed */ - nasid = uv_apicid_to_nasid(apicid); + pnode = uv_apicid_to_pnode(apicid); val = (1UL << UVH_IPI_INT_SEND_SHFT) | (lapicid << UVH_IPI_INT_APIC_ID_SHFT) | (vector << UVH_IPI_INT_VECTOR_SHFT); - uv_write_global_mmr64(nasid, UVH_IPI_INT, val); + uv_write_global_mmr64(pnode, UVH_IPI_INT, val); } static void uv_send_IPI_mask(cpumask_t mask, int vector) @@ -159,39 +161,146 @@ struct genapic apic_x2apic_uv_x = { .phys_pkg_id = phys_pkg_id, /* Fixme ZZZ */ }; -static __cpuinit void set_x2apic_extra_bits(int nasid) +static __cpuinit void set_x2apic_extra_bits(int pnode) { - __get_cpu_var(x2apic_extra_bits) = ((nasid >> 1) << 6); + __get_cpu_var(x2apic_extra_bits) = (pnode << 6); } /* * Called on boot cpu. */ +static __init int boot_pnode_to_blade(int pnode) +{ + int blade; + + for (blade = 0; blade < uv_num_possible_blades(); blade++) + if (pnode == uv_blade_info[blade].pnode) + return blade; + BUG(); +} + +struct redir_addr { + unsigned long redirect; + unsigned long alias; +}; + +#define DEST_SHIFT UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT + +static __initdata struct redir_addr redir_addrs[] = { + {UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR, UVH_SI_ALIAS0_OVERLAY_CONFIG}, + {UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR, UVH_SI_ALIAS1_OVERLAY_CONFIG}, + {UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR, UVH_SI_ALIAS2_OVERLAY_CONFIG}, +}; + +static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size) +{ + union uvh_si_alias0_overlay_config_u alias; + union uvh_rh_gam_alias210_redirect_config_2_mmr_u redirect; + int i; + + for (i = 0; i < ARRAY_SIZE(redir_addrs); i++) { + alias.v = uv_read_local_mmr(redir_addrs[i].alias); + if (alias.s.base == 0) { + *size = (1UL << alias.s.m_alias); + redirect.v = uv_read_local_mmr(redir_addrs[i].redirect); + *base = (unsigned long)redirect.s.dest_base << DEST_SHIFT; + return; + } + } + BUG(); +} + +static __init void map_low_mmrs(void) +{ + init_extra_mapping_uc(UV_GLOBAL_MMR32_BASE, UV_GLOBAL_MMR32_SIZE); + init_extra_mapping_uc(UV_LOCAL_MMR_BASE, UV_LOCAL_MMR_SIZE); +} + +enum map_type {map_wb, map_uc}; + +static void map_high(char *id, unsigned long base, int shift, enum map_type map_type) +{ + unsigned long bytes, paddr; + + paddr = base << shift; + bytes = (1UL << shift); + printk(KERN_INFO "UV: Map %s_HI 0x%lx - 0x%lx\n", id, paddr, + paddr + bytes); + if (map_type == map_uc) + init_extra_mapping_uc(paddr, bytes); + else + init_extra_mapping_wb(paddr, bytes); + +} +static __init void map_gru_high(int max_pnode) +{ + union uvh_rh_gam_gru_overlay_config_mmr_u gru; + int shift = UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT; + + gru.v = uv_read_local_mmr(UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR); + if (gru.s.enable) + map_high("GRU", gru.s.base, shift, map_wb); +} + +static __init void map_config_high(int max_pnode) +{ + union uvh_rh_gam_cfg_overlay_config_mmr_u cfg; + int shift = UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_BASE_SHFT; + + cfg.v = uv_read_local_mmr(UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR); + if (cfg.s.enable) + map_high("CONFIG", cfg.s.base, shift, map_uc); +} + +static __init void map_mmr_high(int max_pnode) +{ + union uvh_rh_gam_mmr_overlay_config_mmr_u mmr; + int shift = UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT; + + mmr.v = uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR); + if (mmr.s.enable) + map_high("MMR", mmr.s.base, shift, map_uc); +} + +static __init void map_mmioh_high(int max_pnode) +{ + union uvh_rh_gam_mmioh_overlay_config_mmr_u mmioh; + int shift = UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT; + + mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR); + if (mmioh.s.enable) + map_high("MMIOH", mmioh.s.base, shift, map_uc); +} + static __init void uv_system_init(void) { union uvh_si_addr_map_config_u m_n_config; - int bytes, nid, cpu, lcpu, nasid, last_nasid, blade; - unsigned long mmr_base; + union uvh_node_id_u node_id; + unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size; + int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val; + int max_pnode = 0; + unsigned long mmr_base, present; + + map_low_mmrs(); m_n_config.v = uv_read_local_mmr(UVH_SI_ADDR_MAP_CONFIG); + m_val = m_n_config.s.m_skt; + n_val = m_n_config.s.n_skt; mmr_base = uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) & ~UV_MMR_ENABLE; printk(KERN_DEBUG "UV: global MMR base 0x%lx\n", mmr_base); - last_nasid = -1; - for_each_possible_cpu(cpu) { - nid = cpu_to_node(cpu); - nasid = uv_apicid_to_nasid(per_cpu(x86_cpu_to_apicid, cpu)); - if (nasid != last_nasid) - uv_possible_blades++; - last_nasid = nasid; - } + for(i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++) + uv_possible_blades += + hweight64(uv_read_local_mmr( UVH_NODE_PRESENT_TABLE + i * 8)); printk(KERN_DEBUG "UV: Found %d blades\n", uv_num_possible_blades()); bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades(); uv_blade_info = alloc_bootmem_pages(bytes); + get_lowmem_redirect(&lowmem_redir_base, &lowmem_redir_size); + bytes = sizeof(uv_node_to_blade[0]) * num_possible_nodes(); uv_node_to_blade = alloc_bootmem_pages(bytes); memset(uv_node_to_blade, 255, bytes); @@ -200,43 +309,62 @@ static __init void uv_system_init(void) uv_cpu_to_blade = alloc_bootmem_pages(bytes); memset(uv_cpu_to_blade, 255, bytes); - last_nasid = -1; - blade = -1; - lcpu = -1; - for_each_possible_cpu(cpu) { - nid = cpu_to_node(cpu); - nasid = uv_apicid_to_nasid(per_cpu(x86_cpu_to_apicid, cpu)); - if (nasid != last_nasid) { - blade++; - lcpu = -1; - uv_blade_info[blade].nr_posible_cpus = 0; + blade = 0; + for (i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++) { + present = uv_read_local_mmr(UVH_NODE_PRESENT_TABLE + i * 8); + for (j = 0; j < 64; j++) { + if (!test_bit(j, &present)) + continue; + uv_blade_info[blade].pnode = (i * 64 + j); + uv_blade_info[blade].nr_possible_cpus = 0; uv_blade_info[blade].nr_online_cpus = 0; + blade++; } - last_nasid = nasid; - lcpu++; + } - uv_cpu_hub_info(cpu)->m_val = m_n_config.s.m_skt; - uv_cpu_hub_info(cpu)->n_val = m_n_config.s.n_skt; + node_id.v = uv_read_local_mmr(UVH_NODE_ID); + gnode_upper = (((unsigned long)node_id.s.node_id) & + ~((1 << n_val) - 1)) << m_val; + + for_each_present_cpu(cpu) { + nid = cpu_to_node(cpu); + pnode = uv_apicid_to_pnode(per_cpu(x86_cpu_to_apicid, cpu)); + blade = boot_pnode_to_blade(pnode); + lcpu = uv_blade_info[blade].nr_possible_cpus; + uv_blade_info[blade].nr_possible_cpus++; + + uv_cpu_hub_info(cpu)->lowmem_remap_base = lowmem_redir_base; + uv_cpu_hub_info(cpu)->lowmem_remap_top = + lowmem_redir_base + lowmem_redir_size; + uv_cpu_hub_info(cpu)->m_val = m_val; + uv_cpu_hub_info(cpu)->n_val = m_val; uv_cpu_hub_info(cpu)->numa_blade_id = blade; uv_cpu_hub_info(cpu)->blade_processor_id = lcpu; - uv_cpu_hub_info(cpu)->local_nasid = nasid; - uv_cpu_hub_info(cpu)->gnode_upper = - nasid & ~((1 << uv_hub_info->n_val) - 1); + uv_cpu_hub_info(cpu)->pnode = pnode; + uv_cpu_hub_info(cpu)->pnode_mask = (1 << n_val) - 1; + uv_cpu_hub_info(cpu)->gpa_mask = (1 << (m_val + n_val)) - 1; + uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper; uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base; uv_cpu_hub_info(cpu)->coherency_domain_number = 0;/* ZZZ */ - uv_blade_info[blade].nasid = nasid; - uv_blade_info[blade].nr_posible_cpus++; uv_node_to_blade[nid] = blade; uv_cpu_to_blade[cpu] = blade; + max_pnode = max(pnode, max_pnode); - printk(KERN_DEBUG "UV cpu %d, apicid 0x%x, nasid %d, nid %d\n", - cpu, per_cpu(x86_cpu_to_apicid, cpu), nasid, nid); - printk(KERN_DEBUG "UV lcpu %d, blade %d\n", lcpu, blade); + printk(KERN_DEBUG "UV: cpu %d, apicid 0x%x, pnode %d, nid %d, " + "lcpu %d, blade %d\n", + cpu, per_cpu(x86_cpu_to_apicid, cpu), pnode, nid, + lcpu, blade); } + + map_gru_high(max_pnode); + map_mmr_high(max_pnode); + map_config_high(max_pnode); + map_mmioh_high(max_pnode); } /* * Called on each cpu to initialize the per_cpu UV data area. + * ZZZ hotplug not supported yet */ void __cpuinit uv_cpu_init(void) { @@ -246,5 +374,5 @@ void __cpuinit uv_cpu_init(void) uv_blade_info[uv_numa_blade_id()].nr_online_cpus++; if (get_uv_system_type() == UV_NON_UNIQUE_APIC) - set_x2apic_extra_bits(uv_hub_info->local_nasid); + set_x2apic_extra_bits(uv_hub_info->pnode); } diff --git a/arch/x86/kernel/geode_32.c b/arch/x86/kernel/geode_32.c index e8edd63ab000..9b08e852fd1a 100644 --- a/arch/x86/kernel/geode_32.c +++ b/arch/x86/kernel/geode_32.c @@ -166,6 +166,8 @@ int geode_has_vsa2(void) static int has_vsa2 = -1; if (has_vsa2 == -1) { + u16 val; + /* * The VSA has virtual registers that we can query for a * signature. @@ -173,7 +175,8 @@ int geode_has_vsa2(void) outw(VSA_VR_UNLOCK, VSA_VRC_INDEX); outw(VSA_VR_SIGNATURE, VSA_VRC_INDEX); - has_vsa2 = (inw(VSA_VRC_DATA) == VSA_SIG); + val = inw(VSA_VRC_DATA); + has_vsa2 = (val == AMD_VSA_SIG || val == GSW_VSA_SIG); } return has_vsa2; diff --git a/arch/x86/kernel/head.c b/arch/x86/kernel/head.c new file mode 100644 index 000000000000..3e66bd364a9d --- /dev/null +++ b/arch/x86/kernel/head.c @@ -0,0 +1,55 @@ +#include <linux/kernel.h> +#include <linux/init.h> + +#include <asm/setup.h> +#include <asm/bios_ebda.h> + +#define BIOS_LOWMEM_KILOBYTES 0x413 + +/* + * The BIOS places the EBDA/XBDA at the top of conventional + * memory, and usually decreases the reported amount of + * conventional memory (int 0x12) too. This also contains a + * workaround for Dell systems that neglect to reserve EBDA. + * The same workaround also avoids a problem with the AMD768MPX + * chipset: reserve a page before VGA to prevent PCI prefetch + * into it (errata #56). Usually the page is reserved anyways, + * unless you have no PS/2 mouse plugged in. + */ +void __init reserve_ebda_region(void) +{ + unsigned int lowmem, ebda_addr; + + /* To determine the position of the EBDA and the */ + /* end of conventional memory, we need to look at */ + /* the BIOS data area. In a paravirtual environment */ + /* that area is absent. We'll just have to assume */ + /* that the paravirt case can handle memory setup */ + /* correctly, without our help. */ + if (paravirt_enabled()) + return; + + /* end of low (conventional) memory */ + lowmem = *(unsigned short *)__va(BIOS_LOWMEM_KILOBYTES); + lowmem <<= 10; + + /* start of EBDA area */ + ebda_addr = get_bios_ebda(); + + /* Fixup: bios puts an EBDA in the top 64K segment */ + /* of conventional memory, but does not adjust lowmem. */ + if ((lowmem - ebda_addr) <= 0x10000) + lowmem = ebda_addr; + + /* Fixup: bios does not report an EBDA at all. */ + /* Some old Dells seem to need 4k anyhow (bugzilla 2990) */ + if ((ebda_addr == 0) && (lowmem >= 0x9f000)) + lowmem = 0x9f000; + + /* Paranoia: should never happen, but... */ + if ((lowmem == 0) || (lowmem >= 0x100000)) + lowmem = 0x9f000; + + /* reserve all memory between lowmem and the 1MB mark */ + reserve_early_overlap_ok(lowmem, 0x100000, "BIOS reserved"); +} diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 3db059058927..fa1d25dd83e3 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -8,7 +8,34 @@ #include <linux/init.h> #include <linux/start_kernel.h> +#include <asm/setup.h> +#include <asm/sections.h> +#include <asm/e820.h> +#include <asm/bios_ebda.h> + void __init i386_start_kernel(void) { + reserve_early(__pa_symbol(&_text), __pa_symbol(&_end), "TEXT DATA BSS"); + +#ifdef CONFIG_BLK_DEV_INITRD + /* Reserve INITRD */ + if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) { + u64 ramdisk_image = boot_params.hdr.ramdisk_image; + u64 ramdisk_size = boot_params.hdr.ramdisk_size; + u64 ramdisk_end = ramdisk_image + ramdisk_size; + reserve_early(ramdisk_image, ramdisk_end, "RAMDISK"); + } +#endif + reserve_early(init_pg_tables_start, init_pg_tables_end, + "INIT_PG_TABLE"); + + reserve_ebda_region(); + + /* + * At this point everything still needed from the boot loader + * or BIOS or kernel text should be early reserved or marked not + * RAM in e820. All other memory is free game. + */ + start_kernel(); } diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index e25c57b8aa84..c97819829146 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -25,6 +25,20 @@ #include <asm/e820.h> #include <asm/bios_ebda.h> +/* boot cpu pda */ +static struct x8664_pda _boot_cpu_pda __read_mostly; + +#ifdef CONFIG_SMP +/* + * We install an empty cpu_pda pointer table to indicate to early users + * (numa_set_node) that the cpu_pda pointer table for cpus other than + * the boot cpu is not yet setup. + */ +static struct x8664_pda *__cpu_pda[NR_CPUS] __initdata; +#else +static struct x8664_pda *__cpu_pda[NR_CPUS] __read_mostly; +#endif + static void __init zap_identity_mappings(void) { pgd_t *pgd = pgd_offset_k(0UL); @@ -51,74 +65,6 @@ static void __init copy_bootdata(char *real_mode_data) } } -#define BIOS_LOWMEM_KILOBYTES 0x413 - -/* - * The BIOS places the EBDA/XBDA at the top of conventional - * memory, and usually decreases the reported amount of - * conventional memory (int 0x12) too. This also contains a - * workaround for Dell systems that neglect to reserve EBDA. - * The same workaround also avoids a problem with the AMD768MPX - * chipset: reserve a page before VGA to prevent PCI prefetch - * into it (errata #56). Usually the page is reserved anyways, - * unless you have no PS/2 mouse plugged in. - */ -static void __init reserve_ebda_region(void) -{ - unsigned int lowmem, ebda_addr; - - /* To determine the position of the EBDA and the */ - /* end of conventional memory, we need to look at */ - /* the BIOS data area. In a paravirtual environment */ - /* that area is absent. We'll just have to assume */ - /* that the paravirt case can handle memory setup */ - /* correctly, without our help. */ - if (paravirt_enabled()) - return; - - /* end of low (conventional) memory */ - lowmem = *(unsigned short *)__va(BIOS_LOWMEM_KILOBYTES); - lowmem <<= 10; - - /* start of EBDA area */ - ebda_addr = get_bios_ebda(); - - /* Fixup: bios puts an EBDA in the top 64K segment */ - /* of conventional memory, but does not adjust lowmem. */ - if ((lowmem - ebda_addr) <= 0x10000) - lowmem = ebda_addr; - - /* Fixup: bios does not report an EBDA at all. */ - /* Some old Dells seem to need 4k anyhow (bugzilla 2990) */ - if ((ebda_addr == 0) && (lowmem >= 0x9f000)) - lowmem = 0x9f000; - - /* Paranoia: should never happen, but... */ - if ((lowmem == 0) || (lowmem >= 0x100000)) - lowmem = 0x9f000; - - /* reserve all memory between lowmem and the 1MB mark */ - reserve_early(lowmem, 0x100000, "BIOS reserved"); -} - -static void __init reserve_setup_data(void) -{ - struct setup_data *data; - unsigned long pa_data; - char buf[32]; - - if (boot_params.hdr.version < 0x0209) - return; - pa_data = boot_params.hdr.setup_data; - while (pa_data) { - data = early_ioremap(pa_data, sizeof(*data)); - sprintf(buf, "setup data %x", data->type); - reserve_early(pa_data, pa_data+sizeof(*data)+data->len, buf); - pa_data = data->next; - early_iounmap(data, sizeof(*data)); - } -} - void __init x86_64_start_kernel(char * real_mode_data) { int i; @@ -156,10 +102,17 @@ void __init x86_64_start_kernel(char * real_mode_data) early_printk("Kernel alive\n"); - for (i = 0; i < NR_CPUS; i++) - cpu_pda(i) = &boot_cpu_pda[i]; - + _cpu_pda = __cpu_pda; + cpu_pda(0) = &_boot_cpu_pda; pda_init(0); + + early_printk("Kernel really alive\n"); + + x86_64_start_reservations(real_mode_data); +} + +void __init x86_64_start_reservations(char *real_mode_data) +{ copy_bootdata(__va(real_mode_data)); reserve_early(__pa_symbol(&_text), __pa_symbol(&_end), "TEXT DATA BSS"); @@ -175,7 +128,6 @@ void __init x86_64_start_kernel(char * real_mode_data) #endif reserve_ebda_region(); - reserve_setup_data(); /* * At this point everything still needed from the boot loader diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index b2cc73768a9d..f67e93441caf 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -189,11 +189,12 @@ default_entry: * this stage. */ -#define KPMDS ((0x100000000-__PAGE_OFFSET) >> 30) /* Number of kernel PMDs */ +#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */ xorl %ebx,%ebx /* %ebx is kept at zero */ movl $pa(pg0), %edi + movl %edi, pa(init_pg_tables_start) movl $pa(swapper_pg_pmd), %edx movl $PTE_ATTR, %eax 10: @@ -219,6 +220,8 @@ default_entry: jb 10b 1: movl %edi,pa(init_pg_tables_end) + shrl $12, %eax + movl %eax, pa(max_pfn_mapped) /* Do early initialization of the fixmap area */ movl $pa(swapper_pg_fixmap)+PDE_ATTR,%eax @@ -228,6 +231,7 @@ default_entry: page_pde_offset = (__PAGE_OFFSET >> 20); movl $pa(pg0), %edi + movl %edi, pa(init_pg_tables_start) movl $pa(swapper_pg_dir), %edx movl $PTE_ATTR, %eax 10: @@ -249,6 +253,8 @@ page_pde_offset = (__PAGE_OFFSET >> 20); cmpl %ebp,%eax jb 10b movl %edi,pa(init_pg_tables_end) + shrl $12, %eax + movl %eax, pa(max_pfn_mapped) /* Do early initialization of the fixmap area */ movl $pa(swapper_pg_fixmap)+PDE_ATTR,%eax @@ -446,10 +452,13 @@ is386: movl $2,%ecx # set MP je 1f movl $(__KERNEL_PERCPU), %eax movl %eax,%fs # set this cpu's percpu - jmp initialize_secondary # all other CPUs call initialize_secondary + movl (stack_start), %esp 1: #endif /* CONFIG_SMP */ - jmp i386_start_kernel + jmp *(initial_code) +.align 4 +ENTRY(initial_code) + .long i386_start_kernel /* * We depend on ET to be correct. This checks for 287/387. diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 10a1955bb1d1..b07ac7b217cb 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -18,6 +18,7 @@ #include <asm/page.h> #include <asm/msr.h> #include <asm/cache.h> +#include <asm/processor-flags.h> #ifdef CONFIG_PARAVIRT #include <asm/asm-offsets.h> @@ -31,6 +32,13 @@ * */ +#define pud_index(x) (((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) + +L4_PAGE_OFFSET = pgd_index(__PAGE_OFFSET) +L3_PAGE_OFFSET = pud_index(__PAGE_OFFSET) +L4_START_KERNEL = pgd_index(__START_KERNEL_map) +L3_START_KERNEL = pud_index(__START_KERNEL_map) + .text .section .text.head .code64 @@ -76,8 +84,8 @@ startup_64: /* Fixup the physical addresses in the page table */ addq %rbp, init_level4_pgt + 0(%rip) - addq %rbp, init_level4_pgt + (258*8)(%rip) - addq %rbp, init_level4_pgt + (511*8)(%rip) + addq %rbp, init_level4_pgt + (L4_PAGE_OFFSET*8)(%rip) + addq %rbp, init_level4_pgt + (L4_START_KERNEL*8)(%rip) addq %rbp, level3_ident_pgt + 0(%rip) @@ -128,7 +136,7 @@ ident_complete: /* Fixup phys_base */ addq %rbp, phys_base(%rip) -#ifdef CONFIG_SMP +#ifdef CONFIG_X86_TRAMPOLINE addq %rbp, trampoline_level4_pgt + 0(%rip) addq %rbp, trampoline_level4_pgt + (511*8)(%rip) #endif @@ -154,9 +162,7 @@ ENTRY(secondary_startup_64) */ /* Enable PAE mode and PGE */ - xorq %rax, %rax - btsq $5, %rax - btsq $7, %rax + movl $(X86_CR4_PAE | X86_CR4_PGE), %eax movq %rax, %cr4 /* Setup early boot stage 4 level pagetables. */ @@ -184,19 +190,15 @@ ENTRY(secondary_startup_64) 1: wrmsr /* Make changes effective */ /* Setup cr0 */ -#define CR0_PM 1 /* protected mode */ -#define CR0_MP (1<<1) -#define CR0_ET (1<<4) -#define CR0_NE (1<<5) -#define CR0_WP (1<<16) -#define CR0_AM (1<<18) -#define CR0_PAGING (1<<31) - movl $CR0_PM|CR0_MP|CR0_ET|CR0_NE|CR0_WP|CR0_AM|CR0_PAGING,%eax +#define CR0_STATE (X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \ + X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \ + X86_CR0_PG) + movl $CR0_STATE, %eax /* Make changes effective */ movq %rax, %cr0 /* Setup a boot time stack */ - movq init_rsp(%rip),%rsp + movq stack_start(%rip),%rsp /* zero EFLAGS after setting rsp */ pushq $0 @@ -208,7 +210,7 @@ ENTRY(secondary_startup_64) * addresses where we're currently running on. We have to do that here * because in 32bit we couldn't load a 64bit linear address. */ - lgdt cpu_gdt_descr(%rip) + lgdt early_gdt_descr(%rip) /* set up data segments. actually 0 would do too */ movl $__KERNEL_DS,%eax @@ -257,8 +259,9 @@ ENTRY(secondary_startup_64) .quad x86_64_start_kernel __FINITDATA - ENTRY(init_rsp) + ENTRY(stack_start) .quad init_thread_union+THREAD_SIZE-8 + .word 0 bad_address: jmp bad_address @@ -327,11 +330,11 @@ early_idt_ripmsg: ENTRY(name) /* Automate the creation of 1 to 1 mapping pmd entries */ -#define PMDS(START, PERM, COUNT) \ - i = 0 ; \ - .rept (COUNT) ; \ - .quad (START) + (i << 21) + (PERM) ; \ - i = i + 1 ; \ +#define PMDS(START, PERM, COUNT) \ + i = 0 ; \ + .rept (COUNT) ; \ + .quad (START) + (i << PMD_SHIFT) + (PERM) ; \ + i = i + 1 ; \ .endr /* @@ -342,9 +345,9 @@ ENTRY(name) */ NEXT_PAGE(init_level4_pgt) .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE - .fill 257,8,0 + .org init_level4_pgt + L4_PAGE_OFFSET*8, 0 .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE - .fill 252,8,0 + .org init_level4_pgt + L4_START_KERNEL*8, 0 /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */ .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE @@ -353,7 +356,7 @@ NEXT_PAGE(level3_ident_pgt) .fill 511,8,0 NEXT_PAGE(level3_kernel_pgt) - .fill 510,8,0 + .fill L3_START_KERNEL,8,0 /* (2^48-(2*1024*1024*1024)-((2^39)*511))/(2^30) = 510 */ .quad level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE .quad level2_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE @@ -384,7 +387,7 @@ NEXT_PAGE(level2_kernel_pgt) * If you want to increase this then increase MODULES_VADDR * too.) */ - PMDS(0, __PAGE_KERNEL_LARGE_EXEC|_PAGE_GLOBAL, + PMDS(0, __PAGE_KERNEL_LARGE_EXEC, KERNEL_IMAGE_SIZE/PMD_SIZE) NEXT_PAGE(level2_spare_pgt) @@ -395,54 +398,16 @@ NEXT_PAGE(level2_spare_pgt) .data .align 16 - .globl cpu_gdt_descr -cpu_gdt_descr: - .word gdt_end-cpu_gdt_table-1 -gdt: - .quad cpu_gdt_table -#ifdef CONFIG_SMP - .rept NR_CPUS-1 - .word 0 - .quad 0 - .endr -#endif + .globl early_gdt_descr +early_gdt_descr: + .word GDT_ENTRIES*8-1 + .quad per_cpu__gdt_page ENTRY(phys_base) /* This must match the first entry in level2_kernel_pgt */ .quad 0x0000000000000000 -/* We need valid kernel segments for data and code in long mode too - * IRET will check the segment types kkeil 2000/10/28 - * Also sysret mandates a special GDT layout - */ - - .section .data.page_aligned, "aw" - .align PAGE_SIZE - -/* The TLS descriptors are currently at a different place compared to i386. - Hopefully nobody expects them at a fixed place (Wine?) */ -ENTRY(cpu_gdt_table) - .quad 0x0000000000000000 /* NULL descriptor */ - .quad 0x00cf9b000000ffff /* __KERNEL32_CS */ - .quad 0x00af9b000000ffff /* __KERNEL_CS */ - .quad 0x00cf93000000ffff /* __KERNEL_DS */ - .quad 0x00cffb000000ffff /* __USER32_CS */ - .quad 0x00cff3000000ffff /* __USER_DS, __USER32_DS */ - .quad 0x00affb000000ffff /* __USER_CS */ - .quad 0x0 /* unused */ - .quad 0,0 /* TSS */ - .quad 0,0 /* LDT */ - .quad 0,0,0 /* three TLS descriptors */ - .quad 0x0000f40000000000 /* node/CPU stored in limit */ -gdt_end: - /* asm/segment.h:GDT_ENTRIES must match this */ - /* This should be a multiple of the cache line size */ - /* GDTs of other CPUs are now dynamically allocated */ - - /* zero the remaining page */ - .fill PAGE_SIZE / 8 - GDT_ENTRIES,8,0 - .section .bss, "aw", @nobits .align L1_CACHE_BYTES ENTRY(idt_table) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 9b5cfcdfc426..0ea6a19bfdfe 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -17,7 +17,7 @@ /* FSEC = 10^-15 NSEC = 10^-9 */ -#define FSEC_PER_NSEC 1000000 +#define FSEC_PER_NSEC 1000000L /* * HPET address is set in acpi/boot.c, when an ACPI entry exists @@ -36,26 +36,15 @@ static inline void hpet_writel(unsigned long d, unsigned long a) } #ifdef CONFIG_X86_64 - #include <asm/pgtable.h> - -static inline void hpet_set_mapping(void) -{ - set_fixmap_nocache(FIX_HPET_BASE, hpet_address); - __set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VSYSCALL_NOCACHE); - hpet_virt_address = (void __iomem *)fix_to_virt(FIX_HPET_BASE); -} - -static inline void hpet_clear_mapping(void) -{ - hpet_virt_address = NULL; -} - -#else +#endif static inline void hpet_set_mapping(void) { hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE); +#ifdef CONFIG_X86_64 + __set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VSYSCALL_NOCACHE); +#endif } static inline void hpet_clear_mapping(void) @@ -63,7 +52,6 @@ static inline void hpet_clear_mapping(void) iounmap(hpet_virt_address); hpet_virt_address = NULL; } -#endif /* * HPET command line enable / disable @@ -206,20 +194,19 @@ static void hpet_enable_legacy_int(void) static void hpet_legacy_clockevent_register(void) { - uint64_t hpet_freq; - /* Start HPET legacy interrupts */ hpet_enable_legacy_int(); /* - * The period is a femto seconds value. We need to calculate the - * scaled math multiplication factor for nanosecond to hpet tick - * conversion. + * The mult factor is defined as (include/linux/clockchips.h) + * mult/2^shift = cyc/ns (in contrast to ns/cyc in clocksource.h) + * hpet_period is in units of femtoseconds (per cycle), so + * mult/2^shift = cyc/ns = 10^6/hpet_period + * mult = (10^6 * 2^shift)/hpet_period + * mult = (FSEC_PER_NSEC << hpet_clockevent.shift)/hpet_period */ - hpet_freq = 1000000000000000ULL; - do_div(hpet_freq, hpet_period); - hpet_clockevent.mult = div_sc((unsigned long) hpet_freq, - NSEC_PER_SEC, hpet_clockevent.shift); + hpet_clockevent.mult = div_sc((unsigned long) FSEC_PER_NSEC, + hpet_period, hpet_clockevent.shift); /* Calculate the min / max delta */ hpet_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF, &hpet_clockevent); @@ -324,7 +311,7 @@ static struct clocksource clocksource_hpet = { static int hpet_clocksource_register(void) { - u64 tmp, start, now; + u64 start, now; cycle_t t1; /* Start the counter */ @@ -351,21 +338,15 @@ static int hpet_clocksource_register(void) return -ENODEV; } - /* Initialize and register HPET clocksource - * - * hpet period is in femto seconds per cycle - * so we need to convert this to ns/cyc units - * approximated by mult/2^shift - * - * fsec/cyc * 1nsec/1000000fsec = nsec/cyc = mult/2^shift - * fsec/cyc * 1ns/1000000fsec * 2^shift = mult - * fsec/cyc * 2^shift * 1nsec/1000000fsec = mult - * (fsec/cyc << shift)/1000000 = mult - * (hpet_period << shift)/FSEC_PER_NSEC = mult + /* + * The definition of mult is (include/linux/clocksource.h) + * mult/2^shift = ns/cyc and hpet_period is in units of fsec/cyc + * so we first need to convert hpet_period to ns/cyc units: + * mult/2^shift = ns/cyc = hpet_period/10^6 + * mult = (hpet_period * 2^shift)/10^6 + * mult = (hpet_period << shift)/FSEC_PER_NSEC */ - tmp = (u64)hpet_period << HPET_SHIFT; - do_div(tmp, FSEC_PER_NSEC); - clocksource_hpet.mult = (u32)tmp; + clocksource_hpet.mult = div_sc(hpet_period, FSEC_PER_NSEC, HPET_SHIFT); clocksource_register(&clocksource_hpet); diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c index deb43785e923..dd7ebee446af 100644 --- a/arch/x86/kernel/i386_ksyms_32.c +++ b/arch/x86/kernel/i386_ksyms_32.c @@ -1,7 +1,14 @@ #include <linux/module.h> + #include <asm/checksum.h> -#include <asm/desc.h> #include <asm/pgtable.h> +#include <asm/desc.h> +#include <asm/ftrace.h> + +#ifdef CONFIG_FTRACE +/* mcount is defined in assembly */ +EXPORT_SYMBOL(mcount); +#endif /* Networking helper routines. */ EXPORT_SYMBOL(csum_partial_copy_generic); diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index e03cc952f233..eb9ddd8efb82 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -56,6 +56,11 @@ void __cpuinit mxcsr_feature_mask_init(void) void __init init_thread_xstate(void) { + if (!HAVE_HWFP) { + xstate_size = sizeof(struct i387_soft_struct); + return; + } + if (cpu_has_fxsr) xstate_size = sizeof(struct i387_fxsave_struct); #ifdef CONFIG_X86_32 @@ -94,7 +99,7 @@ void __cpuinit fpu_init(void) int init_fpu(struct task_struct *tsk) { if (tsk_used_math(tsk)) { - if (tsk == current) + if (HAVE_HWFP && tsk == current) unlazy_fpu(tsk); return 0; } @@ -109,6 +114,15 @@ int init_fpu(struct task_struct *tsk) return -ENOMEM; } +#ifdef CONFIG_X86_32 + if (!HAVE_HWFP) { + memset(tsk->thread.xstate, 0, xstate_size); + finit(); + set_stopped_child_used_math(tsk); + return 0; + } +#endif + if (cpu_has_fxsr) { struct i387_fxsave_struct *fx = &tsk->thread.xstate->fxsave; @@ -330,13 +344,13 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, struct user_i387_ia32_struct env; int ret; - if (!HAVE_HWFP) - return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); - ret = init_fpu(target); if (ret) return ret; + if (!HAVE_HWFP) + return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); + if (!cpu_has_fxsr) { return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.xstate->fsave, 0, @@ -360,15 +374,15 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, struct user_i387_ia32_struct env; int ret; - if (!HAVE_HWFP) - return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); - ret = init_fpu(target); if (ret) return ret; set_stopped_child_used_math(target); + if (!HAVE_HWFP) + return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); + if (!cpu_has_fxsr) { return user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.xstate->fsave, 0, -1); @@ -474,18 +488,18 @@ static int restore_i387_fxsave(struct _fpstate_ia32 __user *buf) int restore_i387_ia32(struct _fpstate_ia32 __user *buf) { int err; + struct task_struct *tsk = current; - if (HAVE_HWFP) { - struct task_struct *tsk = current; - + if (HAVE_HWFP) clear_fpu(tsk); - if (!used_math()) { - err = init_fpu(tsk); - if (err) - return err; - } + if (!used_math()) { + err = init_fpu(tsk); + if (err) + return err; + } + if (HAVE_HWFP) { if (cpu_has_fxsr) err = restore_i387_fxsave(buf); else diff --git a/arch/x86/kernel/i8259_32.c b/arch/x86/kernel/i8259.c index fe631967d625..dc92b49d9204 100644 --- a/arch/x86/kernel/i8259_32.c +++ b/arch/x86/kernel/i8259.c @@ -1,8 +1,10 @@ +#include <linux/linkage.h> #include <linux/errno.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/ioport.h> #include <linux/interrupt.h> +#include <linux/timex.h> #include <linux/slab.h> #include <linux/random.h> #include <linux/init.h> @@ -10,10 +12,12 @@ #include <linux/sysdev.h> #include <linux/bitops.h> +#include <asm/acpi.h> #include <asm/atomic.h> #include <asm/system.h> #include <asm/io.h> #include <asm/timer.h> +#include <asm/hw_irq.h> #include <asm/pgtable.h> #include <asm/delay.h> #include <asm/desc.h> @@ -32,7 +36,7 @@ static int i8259A_auto_eoi; DEFINE_SPINLOCK(i8259A_lock); static void mask_and_ack_8259A(unsigned int); -static struct irq_chip i8259A_chip = { +struct irq_chip i8259A_chip = { .name = "XT-PIC", .mask = disable_8259A_irq, .disable = disable_8259A_irq, @@ -125,14 +129,14 @@ static inline int i8259A_irq_real(unsigned int irq) int irqmask = 1<<irq; if (irq < 8) { - outb(0x0B,PIC_MASTER_CMD); /* ISR register */ + outb(0x0B, PIC_MASTER_CMD); /* ISR register */ value = inb(PIC_MASTER_CMD) & irqmask; - outb(0x0A,PIC_MASTER_CMD); /* back to the IRR register */ + outb(0x0A, PIC_MASTER_CMD); /* back to the IRR register */ return value; } - outb(0x0B,PIC_SLAVE_CMD); /* ISR register */ + outb(0x0B, PIC_SLAVE_CMD); /* ISR register */ value = inb(PIC_SLAVE_CMD) & (irqmask >> 8); - outb(0x0A,PIC_SLAVE_CMD); /* back to the IRR register */ + outb(0x0A, PIC_SLAVE_CMD); /* back to the IRR register */ return value; } @@ -171,12 +175,14 @@ handle_real_irq: if (irq & 8) { inb(PIC_SLAVE_IMR); /* DUMMY - (do we need this?) */ outb(cached_slave_mask, PIC_SLAVE_IMR); - outb(0x60+(irq&7),PIC_SLAVE_CMD);/* 'Specific EOI' to slave */ - outb(0x60+PIC_CASCADE_IR,PIC_MASTER_CMD); /* 'Specific EOI' to master-IRQ2 */ + /* 'Specific EOI' to slave */ + outb(0x60+(irq&7), PIC_SLAVE_CMD); + /* 'Specific EOI' to master-IRQ2 */ + outb(0x60+PIC_CASCADE_IR, PIC_MASTER_CMD); } else { inb(PIC_MASTER_IMR); /* DUMMY - (do we need this?) */ outb(cached_master_mask, PIC_MASTER_IMR); - outb(0x60+irq,PIC_MASTER_CMD); /* 'Specific EOI to master */ + outb(0x60+irq, PIC_MASTER_CMD); /* 'Specific EOI to master */ } spin_unlock_irqrestore(&i8259A_lock, flags); return; @@ -199,7 +205,8 @@ spurious_8259A_irq: * lets ACK and report it. [once per IRQ] */ if (!(spurious_irq_mask & irqmask)) { - printk(KERN_DEBUG "spurious 8259A interrupt: IRQ%d.\n", irq); + printk(KERN_DEBUG + "spurious 8259A interrupt: IRQ%d.\n", irq); spurious_irq_mask |= irqmask; } atomic_inc(&irq_err_count); @@ -290,17 +297,28 @@ void init_8259A(int auto_eoi) * outb_pic - this has to work on a wide range of PC hardware. */ outb_pic(0x11, PIC_MASTER_CMD); /* ICW1: select 8259A-1 init */ - outb_pic(0x20 + 0, PIC_MASTER_IMR); /* ICW2: 8259A-1 IR0-7 mapped to 0x20-0x27 */ - outb_pic(1U << PIC_CASCADE_IR, PIC_MASTER_IMR); /* 8259A-1 (the master) has a slave on IR2 */ + + /* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 on x86-64, + to 0x20-0x27 on i386 */ + outb_pic(IRQ0_VECTOR, PIC_MASTER_IMR); + + /* 8259A-1 (the master) has a slave on IR2 */ + outb_pic(1U << PIC_CASCADE_IR, PIC_MASTER_IMR); + if (auto_eoi) /* master does Auto EOI */ outb_pic(MASTER_ICW4_DEFAULT | PIC_ICW4_AEOI, PIC_MASTER_IMR); else /* master expects normal EOI */ outb_pic(MASTER_ICW4_DEFAULT, PIC_MASTER_IMR); outb_pic(0x11, PIC_SLAVE_CMD); /* ICW1: select 8259A-2 init */ - outb_pic(0x20 + 8, PIC_SLAVE_IMR); /* ICW2: 8259A-2 IR0-7 mapped to 0x28-0x2f */ - outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR); /* 8259A-2 is a slave on master's IR2 */ - outb_pic(SLAVE_ICW4_DEFAULT, PIC_SLAVE_IMR); /* (slave's support for AEOI in flat mode is to be investigated) */ + + /* ICW2: 8259A-2 IR0-7 mapped to IRQ8_VECTOR */ + outb_pic(IRQ8_VECTOR, PIC_SLAVE_IMR); + /* 8259A-2 is a slave on master's IR2 */ + outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR); + /* (slave's support for AEOI in flat mode is to be investigated) */ + outb_pic(SLAVE_ICW4_DEFAULT, PIC_SLAVE_IMR); + if (auto_eoi) /* * In AEOI mode we just have to mask the interrupt @@ -317,93 +335,3 @@ void init_8259A(int auto_eoi) spin_unlock_irqrestore(&i8259A_lock, flags); } - -/* - * Note that on a 486, we don't want to do a SIGFPE on an irq13 - * as the irq is unreliable, and exception 16 works correctly - * (ie as explained in the intel literature). On a 386, you - * can't use exception 16 due to bad IBM design, so we have to - * rely on the less exact irq13. - * - * Careful.. Not only is IRQ13 unreliable, but it is also - * leads to races. IBM designers who came up with it should - * be shot. - */ - - -static irqreturn_t math_error_irq(int cpl, void *dev_id) -{ - extern void math_error(void __user *); - outb(0,0xF0); - if (ignore_fpu_irq || !boot_cpu_data.hard_math) - return IRQ_NONE; - math_error((void __user *)get_irq_regs()->ip); - return IRQ_HANDLED; -} - -/* - * New motherboards sometimes make IRQ 13 be a PCI interrupt, - * so allow interrupt sharing. - */ -static struct irqaction fpu_irq = { - .handler = math_error_irq, - .mask = CPU_MASK_NONE, - .name = "fpu", -}; - -void __init init_ISA_irqs (void) -{ - int i; - -#ifdef CONFIG_X86_LOCAL_APIC - init_bsp_APIC(); -#endif - init_8259A(0); - - /* - * 16 old-style INTA-cycle interrupts: - */ - for (i = 0; i < 16; i++) { - set_irq_chip_and_handler_name(i, &i8259A_chip, - handle_level_irq, "XT"); - } -} - -/* Overridden in paravirt.c */ -void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ"))); - -void __init native_init_IRQ(void) -{ - int i; - - /* all the set up before the call gates are initialised */ - pre_intr_init_hook(); - - /* - * Cover the whole vector space, no vector can escape - * us. (some of these will be overridden and become - * 'special' SMP interrupts) - */ - for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) { - int vector = FIRST_EXTERNAL_VECTOR + i; - if (i >= NR_IRQS) - break; - /* SYSCALL_VECTOR was reserved in trap_init. */ - if (!test_bit(vector, used_vectors)) - set_intr_gate(vector, interrupt[i]); - } - - /* setup after call gates are initialised (usually add in - * the architecture specific gates) - */ - intr_init_hook(); - - /* - * External FPU? Set up irq13 if so, for - * original braindamaged IBM FERR coupling. - */ - if (boot_cpu_data.hard_math && !cpu_has_fpu) - setup_irq(FPU_IRQ, &fpu_irq); - - irq_ctx_init(smp_processor_id()); -} diff --git a/arch/x86/kernel/i8259_64.c b/arch/x86/kernel/i8259_64.c deleted file mode 100644 index fa57a1568508..000000000000 --- a/arch/x86/kernel/i8259_64.c +++ /dev/null @@ -1,512 +0,0 @@ -#include <linux/linkage.h> -#include <linux/errno.h> -#include <linux/signal.h> -#include <linux/sched.h> -#include <linux/ioport.h> -#include <linux/interrupt.h> -#include <linux/timex.h> -#include <linux/slab.h> -#include <linux/random.h> -#include <linux/init.h> -#include <linux/kernel_stat.h> -#include <linux/sysdev.h> -#include <linux/bitops.h> - -#include <asm/acpi.h> -#include <asm/atomic.h> -#include <asm/system.h> -#include <asm/io.h> -#include <asm/hw_irq.h> -#include <asm/pgtable.h> -#include <asm/delay.h> -#include <asm/desc.h> -#include <asm/apic.h> -#include <asm/i8259.h> - -/* - * Common place to define all x86 IRQ vectors - * - * This builds up the IRQ handler stubs using some ugly macros in irq.h - * - * These macros create the low-level assembly IRQ routines that save - * register context and call do_IRQ(). do_IRQ() then does all the - * operations that are needed to keep the AT (or SMP IOAPIC) - * interrupt-controller happy. - */ - -#define BI(x,y) \ - BUILD_IRQ(x##y) - -#define BUILD_16_IRQS(x) \ - BI(x,0) BI(x,1) BI(x,2) BI(x,3) \ - BI(x,4) BI(x,5) BI(x,6) BI(x,7) \ - BI(x,8) BI(x,9) BI(x,a) BI(x,b) \ - BI(x,c) BI(x,d) BI(x,e) BI(x,f) - -/* - * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts: - * (these are usually mapped to vectors 0x30-0x3f) - */ - -/* - * The IO-APIC gives us many more interrupt sources. Most of these - * are unused but an SMP system is supposed to have enough memory ... - * sometimes (mostly wrt. hw bugs) we get corrupted vectors all - * across the spectrum, so we really want to be prepared to get all - * of these. Plus, more powerful systems might have more than 64 - * IO-APIC registers. - * - * (these are usually mapped into the 0x30-0xff vector range) - */ - BUILD_16_IRQS(0x2) BUILD_16_IRQS(0x3) -BUILD_16_IRQS(0x4) BUILD_16_IRQS(0x5) BUILD_16_IRQS(0x6) BUILD_16_IRQS(0x7) -BUILD_16_IRQS(0x8) BUILD_16_IRQS(0x9) BUILD_16_IRQS(0xa) BUILD_16_IRQS(0xb) -BUILD_16_IRQS(0xc) BUILD_16_IRQS(0xd) BUILD_16_IRQS(0xe) BUILD_16_IRQS(0xf) - -#undef BUILD_16_IRQS -#undef BI - - -#define IRQ(x,y) \ - IRQ##x##y##_interrupt - -#define IRQLIST_16(x) \ - IRQ(x,0), IRQ(x,1), IRQ(x,2), IRQ(x,3), \ - IRQ(x,4), IRQ(x,5), IRQ(x,6), IRQ(x,7), \ - IRQ(x,8), IRQ(x,9), IRQ(x,a), IRQ(x,b), \ - IRQ(x,c), IRQ(x,d), IRQ(x,e), IRQ(x,f) - -/* for the irq vectors */ -static void (*__initdata interrupt[NR_VECTORS - FIRST_EXTERNAL_VECTOR])(void) = { - IRQLIST_16(0x2), IRQLIST_16(0x3), - IRQLIST_16(0x4), IRQLIST_16(0x5), IRQLIST_16(0x6), IRQLIST_16(0x7), - IRQLIST_16(0x8), IRQLIST_16(0x9), IRQLIST_16(0xa), IRQLIST_16(0xb), - IRQLIST_16(0xc), IRQLIST_16(0xd), IRQLIST_16(0xe), IRQLIST_16(0xf) -}; - -#undef IRQ -#undef IRQLIST_16 - -/* - * This is the 'legacy' 8259A Programmable Interrupt Controller, - * present in the majority of PC/AT boxes. - * plus some generic x86 specific things if generic specifics makes - * any sense at all. - * this file should become arch/i386/kernel/irq.c when the old irq.c - * moves to arch independent land - */ - -static int i8259A_auto_eoi; -DEFINE_SPINLOCK(i8259A_lock); -static void mask_and_ack_8259A(unsigned int); - -static struct irq_chip i8259A_chip = { - .name = "XT-PIC", - .mask = disable_8259A_irq, - .disable = disable_8259A_irq, - .unmask = enable_8259A_irq, - .mask_ack = mask_and_ack_8259A, -}; - -/* - * 8259A PIC functions to handle ISA devices: - */ - -/* - * This contains the irq mask for both 8259A irq controllers, - */ -unsigned int cached_irq_mask = 0xffff; - -/* - * Not all IRQs can be routed through the IO-APIC, eg. on certain (older) - * boards the timer interrupt is not really connected to any IO-APIC pin, - * it's fed to the master 8259A's IR0 line only. - * - * Any '1' bit in this mask means the IRQ is routed through the IO-APIC. - * this 'mixed mode' IRQ handling costs nothing because it's only used - * at IRQ setup time. - */ -unsigned long io_apic_irqs; - -void disable_8259A_irq(unsigned int irq) -{ - unsigned int mask = 1 << irq; - unsigned long flags; - - spin_lock_irqsave(&i8259A_lock, flags); - cached_irq_mask |= mask; - if (irq & 8) - outb(cached_slave_mask, PIC_SLAVE_IMR); - else - outb(cached_master_mask, PIC_MASTER_IMR); - spin_unlock_irqrestore(&i8259A_lock, flags); -} - -void enable_8259A_irq(unsigned int irq) -{ - unsigned int mask = ~(1 << irq); - unsigned long flags; - - spin_lock_irqsave(&i8259A_lock, flags); - cached_irq_mask &= mask; - if (irq & 8) - outb(cached_slave_mask, PIC_SLAVE_IMR); - else - outb(cached_master_mask, PIC_MASTER_IMR); - spin_unlock_irqrestore(&i8259A_lock, flags); -} - -int i8259A_irq_pending(unsigned int irq) -{ - unsigned int mask = 1<<irq; - unsigned long flags; - int ret; - - spin_lock_irqsave(&i8259A_lock, flags); - if (irq < 8) - ret = inb(PIC_MASTER_CMD) & mask; - else - ret = inb(PIC_SLAVE_CMD) & (mask >> 8); - spin_unlock_irqrestore(&i8259A_lock, flags); - - return ret; -} - -void make_8259A_irq(unsigned int irq) -{ - disable_irq_nosync(irq); - io_apic_irqs &= ~(1<<irq); - set_irq_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq, - "XT"); - enable_irq(irq); -} - -/* - * This function assumes to be called rarely. Switching between - * 8259A registers is slow. - * This has to be protected by the irq controller spinlock - * before being called. - */ -static inline int i8259A_irq_real(unsigned int irq) -{ - int value; - int irqmask = 1<<irq; - - if (irq < 8) { - outb(0x0B,PIC_MASTER_CMD); /* ISR register */ - value = inb(PIC_MASTER_CMD) & irqmask; - outb(0x0A,PIC_MASTER_CMD); /* back to the IRR register */ - return value; - } - outb(0x0B,PIC_SLAVE_CMD); /* ISR register */ - value = inb(PIC_SLAVE_CMD) & (irqmask >> 8); - outb(0x0A,PIC_SLAVE_CMD); /* back to the IRR register */ - return value; -} - -/* - * Careful! The 8259A is a fragile beast, it pretty - * much _has_ to be done exactly like this (mask it - * first, _then_ send the EOI, and the order of EOI - * to the two 8259s is important! - */ -static void mask_and_ack_8259A(unsigned int irq) -{ - unsigned int irqmask = 1 << irq; - unsigned long flags; - - spin_lock_irqsave(&i8259A_lock, flags); - /* - * Lightweight spurious IRQ detection. We do not want - * to overdo spurious IRQ handling - it's usually a sign - * of hardware problems, so we only do the checks we can - * do without slowing down good hardware unnecessarily. - * - * Note that IRQ7 and IRQ15 (the two spurious IRQs - * usually resulting from the 8259A-1|2 PICs) occur - * even if the IRQ is masked in the 8259A. Thus we - * can check spurious 8259A IRQs without doing the - * quite slow i8259A_irq_real() call for every IRQ. - * This does not cover 100% of spurious interrupts, - * but should be enough to warn the user that there - * is something bad going on ... - */ - if (cached_irq_mask & irqmask) - goto spurious_8259A_irq; - cached_irq_mask |= irqmask; - -handle_real_irq: - if (irq & 8) { - inb(PIC_SLAVE_IMR); /* DUMMY - (do we need this?) */ - outb(cached_slave_mask, PIC_SLAVE_IMR); - /* 'Specific EOI' to slave */ - outb(0x60+(irq&7),PIC_SLAVE_CMD); - /* 'Specific EOI' to master-IRQ2 */ - outb(0x60+PIC_CASCADE_IR,PIC_MASTER_CMD); - } else { - inb(PIC_MASTER_IMR); /* DUMMY - (do we need this?) */ - outb(cached_master_mask, PIC_MASTER_IMR); - /* 'Specific EOI' to master */ - outb(0x60+irq,PIC_MASTER_CMD); - } - spin_unlock_irqrestore(&i8259A_lock, flags); - return; - -spurious_8259A_irq: - /* - * this is the slow path - should happen rarely. - */ - if (i8259A_irq_real(irq)) - /* - * oops, the IRQ _is_ in service according to the - * 8259A - not spurious, go handle it. - */ - goto handle_real_irq; - - { - static int spurious_irq_mask; - /* - * At this point we can be sure the IRQ is spurious, - * lets ACK and report it. [once per IRQ] - */ - if (!(spurious_irq_mask & irqmask)) { - printk(KERN_DEBUG - "spurious 8259A interrupt: IRQ%d.\n", irq); - spurious_irq_mask |= irqmask; - } - atomic_inc(&irq_err_count); - /* - * Theoretically we do not have to handle this IRQ, - * but in Linux this does not cause problems and is - * simpler for us. - */ - goto handle_real_irq; - } -} - -static char irq_trigger[2]; -/** - * ELCR registers (0x4d0, 0x4d1) control edge/level of IRQ - */ -static void restore_ELCR(char *trigger) -{ - outb(trigger[0], 0x4d0); - outb(trigger[1], 0x4d1); -} - -static void save_ELCR(char *trigger) -{ - /* IRQ 0,1,2,8,13 are marked as reserved */ - trigger[0] = inb(0x4d0) & 0xF8; - trigger[1] = inb(0x4d1) & 0xDE; -} - -static int i8259A_resume(struct sys_device *dev) -{ - init_8259A(i8259A_auto_eoi); - restore_ELCR(irq_trigger); - return 0; -} - -static int i8259A_suspend(struct sys_device *dev, pm_message_t state) -{ - save_ELCR(irq_trigger); - return 0; -} - -static int i8259A_shutdown(struct sys_device *dev) -{ - /* Put the i8259A into a quiescent state that - * the kernel initialization code can get it - * out of. - */ - outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */ - outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-1 */ - return 0; -} - -static struct sysdev_class i8259_sysdev_class = { - .name = "i8259", - .suspend = i8259A_suspend, - .resume = i8259A_resume, - .shutdown = i8259A_shutdown, -}; - -static struct sys_device device_i8259A = { - .id = 0, - .cls = &i8259_sysdev_class, -}; - -static int __init i8259A_init_sysfs(void) -{ - int error = sysdev_class_register(&i8259_sysdev_class); - if (!error) - error = sysdev_register(&device_i8259A); - return error; -} - -device_initcall(i8259A_init_sysfs); - -void init_8259A(int auto_eoi) -{ - unsigned long flags; - - i8259A_auto_eoi = auto_eoi; - - spin_lock_irqsave(&i8259A_lock, flags); - - outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */ - outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-2 */ - - /* - * outb_pic - this has to work on a wide range of PC hardware. - */ - outb_pic(0x11, PIC_MASTER_CMD); /* ICW1: select 8259A-1 init */ - /* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 */ - outb_pic(IRQ0_VECTOR, PIC_MASTER_IMR); - /* 8259A-1 (the master) has a slave on IR2 */ - outb_pic(0x04, PIC_MASTER_IMR); - if (auto_eoi) /* master does Auto EOI */ - outb_pic(MASTER_ICW4_DEFAULT | PIC_ICW4_AEOI, PIC_MASTER_IMR); - else /* master expects normal EOI */ - outb_pic(MASTER_ICW4_DEFAULT, PIC_MASTER_IMR); - - outb_pic(0x11, PIC_SLAVE_CMD); /* ICW1: select 8259A-2 init */ - /* ICW2: 8259A-2 IR0-7 mapped to 0x38-0x3f */ - outb_pic(IRQ8_VECTOR, PIC_SLAVE_IMR); - /* 8259A-2 is a slave on master's IR2 */ - outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR); - /* (slave's support for AEOI in flat mode is to be investigated) */ - outb_pic(SLAVE_ICW4_DEFAULT, PIC_SLAVE_IMR); - - if (auto_eoi) - /* - * In AEOI mode we just have to mask the interrupt - * when acking. - */ - i8259A_chip.mask_ack = disable_8259A_irq; - else - i8259A_chip.mask_ack = mask_and_ack_8259A; - - udelay(100); /* wait for 8259A to initialize */ - - outb(cached_master_mask, PIC_MASTER_IMR); /* restore master IRQ mask */ - outb(cached_slave_mask, PIC_SLAVE_IMR); /* restore slave IRQ mask */ - - spin_unlock_irqrestore(&i8259A_lock, flags); -} - - - - -/* - * IRQ2 is cascade interrupt to second interrupt controller - */ - -static struct irqaction irq2 = { - .handler = no_action, - .mask = CPU_MASK_NONE, - .name = "cascade", -}; -DEFINE_PER_CPU(vector_irq_t, vector_irq) = { - [0 ... IRQ0_VECTOR - 1] = -1, - [IRQ0_VECTOR] = 0, - [IRQ1_VECTOR] = 1, - [IRQ2_VECTOR] = 2, - [IRQ3_VECTOR] = 3, - [IRQ4_VECTOR] = 4, - [IRQ5_VECTOR] = 5, - [IRQ6_VECTOR] = 6, - [IRQ7_VECTOR] = 7, - [IRQ8_VECTOR] = 8, - [IRQ9_VECTOR] = 9, - [IRQ10_VECTOR] = 10, - [IRQ11_VECTOR] = 11, - [IRQ12_VECTOR] = 12, - [IRQ13_VECTOR] = 13, - [IRQ14_VECTOR] = 14, - [IRQ15_VECTOR] = 15, - [IRQ15_VECTOR + 1 ... NR_VECTORS - 1] = -1 -}; - -void __init init_ISA_irqs (void) -{ - int i; - - init_bsp_APIC(); - init_8259A(0); - - for (i = 0; i < NR_IRQS; i++) { - irq_desc[i].status = IRQ_DISABLED; - irq_desc[i].action = NULL; - irq_desc[i].depth = 1; - - if (i < 16) { - /* - * 16 old-style INTA-cycle interrupts: - */ - set_irq_chip_and_handler_name(i, &i8259A_chip, - handle_level_irq, "XT"); - } else { - /* - * 'high' PCI IRQs filled in on demand - */ - irq_desc[i].chip = &no_irq_chip; - } - } -} - -void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ"))); - -void __init native_init_IRQ(void) -{ - int i; - - init_ISA_irqs(); - /* - * Cover the whole vector space, no vector can escape - * us. (some of these will be overridden and become - * 'special' SMP interrupts) - */ - for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) { - int vector = FIRST_EXTERNAL_VECTOR + i; - if (vector != IA32_SYSCALL_VECTOR) - set_intr_gate(vector, interrupt[i]); - } - -#ifdef CONFIG_SMP - /* - * The reschedule interrupt is a CPU-to-CPU reschedule-helper - * IPI, driven by wakeup. - */ - set_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt); - - /* IPIs for invalidation */ - set_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0); - set_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1); - set_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2); - set_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3); - set_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4); - set_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5); - set_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6); - set_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7); - - /* IPI for generic function call */ - set_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt); - - /* Low priority IPI to cleanup after moving an irq */ - set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt); -#endif - set_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt); - set_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt); - - /* self generated IPI for local APIC timer */ - set_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt); - - /* IPI vectors for APIC spurious and error interrupts */ - set_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt); - set_intr_gate(ERROR_APIC_VECTOR, error_interrupt); - - if (!acpi_ioapic) - setup_irq(2, &irq2); -} diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c index a40d54fc1fdd..558abf4c796a 100644 --- a/arch/x86/kernel/io_apic_32.c +++ b/arch/x86/kernel/io_apic_32.c @@ -25,6 +25,7 @@ #include <linux/init.h> #include <linux/delay.h> #include <linux/sched.h> +#include <linux/bootmem.h> #include <linux/mc146818rtc.h> #include <linux/compiler.h> #include <linux/acpi.h> @@ -58,7 +59,7 @@ static struct { int pin, apic; } ioapic_i8259 = { -1, -1 }; static DEFINE_SPINLOCK(ioapic_lock); static DEFINE_SPINLOCK(vector_lock); -int timer_over_8254 __initdata = 1; +int timer_through_8259 __initdata; /* * Is the SiS APIC rmw bug present ? @@ -72,15 +73,21 @@ int sis_apic_bug = -1; int nr_ioapic_registers[MAX_IO_APICS]; /* I/O APIC entries */ -struct mpc_config_ioapic mp_ioapics[MAX_IO_APICS]; +struct mp_config_ioapic mp_ioapics[MAX_IO_APICS]; int nr_ioapics; /* MP IRQ source entries */ -struct mpc_config_intsrc mp_irqs[MAX_IRQ_SOURCES]; +struct mp_config_intsrc mp_irqs[MAX_IRQ_SOURCES]; /* # of MP IRQ source entries */ int mp_irq_entries; +#if defined (CONFIG_MCA) || defined (CONFIG_EISA) +int mp_bus_id_to_type[MAX_MP_BUSSES]; +#endif + +DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES); + static int disable_timer_pin_1 __initdata; /* @@ -110,7 +117,7 @@ struct io_apic { static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx) { return (void __iomem *) __fix_to_virt(FIX_IO_APIC_BASE_0 + idx) - + (mp_ioapics[idx].mpc_apicaddr & ~PAGE_MASK); + + (mp_ioapics[idx].mp_apicaddr & ~PAGE_MASK); } static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg) @@ -239,7 +246,7 @@ static void __init replace_pin_at_irq(unsigned int irq, } } -static void __modify_IO_APIC_irq (unsigned int irq, unsigned long enable, unsigned long disable) +static void __modify_IO_APIC_irq(unsigned int irq, unsigned long enable, unsigned long disable) { struct irq_pin_list *entry = irq_2_pin + irq; unsigned int pin, reg; @@ -259,30 +266,32 @@ static void __modify_IO_APIC_irq (unsigned int irq, unsigned long enable, unsign } /* mask = 1 */ -static void __mask_IO_APIC_irq (unsigned int irq) +static void __mask_IO_APIC_irq(unsigned int irq) { - __modify_IO_APIC_irq(irq, 0x00010000, 0); + __modify_IO_APIC_irq(irq, IO_APIC_REDIR_MASKED, 0); } /* mask = 0 */ -static void __unmask_IO_APIC_irq (unsigned int irq) +static void __unmask_IO_APIC_irq(unsigned int irq) { - __modify_IO_APIC_irq(irq, 0, 0x00010000); + __modify_IO_APIC_irq(irq, 0, IO_APIC_REDIR_MASKED); } /* mask = 1, trigger = 0 */ -static void __mask_and_edge_IO_APIC_irq (unsigned int irq) +static void __mask_and_edge_IO_APIC_irq(unsigned int irq) { - __modify_IO_APIC_irq(irq, 0x00010000, 0x00008000); + __modify_IO_APIC_irq(irq, IO_APIC_REDIR_MASKED, + IO_APIC_REDIR_LEVEL_TRIGGER); } /* mask = 0, trigger = 1 */ -static void __unmask_and_level_IO_APIC_irq (unsigned int irq) +static void __unmask_and_level_IO_APIC_irq(unsigned int irq) { - __modify_IO_APIC_irq(irq, 0x00008000, 0x00010000); + __modify_IO_APIC_irq(irq, IO_APIC_REDIR_LEVEL_TRIGGER, + IO_APIC_REDIR_MASKED); } -static void mask_IO_APIC_irq (unsigned int irq) +static void mask_IO_APIC_irq(unsigned int irq) { unsigned long flags; @@ -291,7 +300,7 @@ static void mask_IO_APIC_irq (unsigned int irq) spin_unlock_irqrestore(&ioapic_lock, flags); } -static void unmask_IO_APIC_irq (unsigned int irq) +static void unmask_IO_APIC_irq(unsigned int irq) { unsigned long flags; @@ -303,7 +312,7 @@ static void unmask_IO_APIC_irq (unsigned int irq) static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) { struct IO_APIC_route_entry entry; - + /* Check delivery_mode to be sure we're not clearing an SMI pin */ entry = ioapic_read_entry(apic, pin); if (entry.delivery_mode == dest_SMI) @@ -315,7 +324,7 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) ioapic_mask_entry(apic, pin); } -static void clear_IO_APIC (void) +static void clear_IO_APIC(void) { int apic, pin; @@ -332,7 +341,7 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask) struct irq_pin_list *entry = irq_2_pin + irq; unsigned int apicid_value; cpumask_t tmp; - + cpus_and(tmp, cpumask, cpu_online_map); if (cpus_empty(tmp)) tmp = TARGET_CPUS; @@ -361,7 +370,7 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask) # include <linux/kernel_stat.h> /* kstat */ # include <linux/slab.h> /* kmalloc() */ # include <linux/timer.h> - + #define IRQBALANCE_CHECK_ARCH -999 #define MAX_BALANCED_IRQ_INTERVAL (5*HZ) #define MIN_BALANCED_IRQ_INTERVAL (HZ/2) @@ -373,14 +382,14 @@ static int physical_balance __read_mostly; static long balanced_irq_interval __read_mostly = MAX_BALANCED_IRQ_INTERVAL; static struct irq_cpu_info { - unsigned long * last_irq; - unsigned long * irq_delta; + unsigned long *last_irq; + unsigned long *irq_delta; unsigned long irq; } irq_cpu_data[NR_CPUS]; #define CPU_IRQ(cpu) (irq_cpu_data[cpu].irq) -#define LAST_CPU_IRQ(cpu,irq) (irq_cpu_data[cpu].last_irq[irq]) -#define IRQ_DELTA(cpu,irq) (irq_cpu_data[cpu].irq_delta[irq]) +#define LAST_CPU_IRQ(cpu, irq) (irq_cpu_data[cpu].last_irq[irq]) +#define IRQ_DELTA(cpu, irq) (irq_cpu_data[cpu].irq_delta[irq]) #define IDLE_ENOUGH(cpu,now) \ (idle_cpu(cpu) && ((now) - per_cpu(irq_stat, (cpu)).idle_timestamp > 1)) @@ -419,8 +428,8 @@ inside: if (cpu == -1) cpu = NR_CPUS-1; } - } while (!cpu_online(cpu) || !IRQ_ALLOWED(cpu,allowed_mask) || - (search_idle && !IDLE_ENOUGH(cpu,now))); + } while (!cpu_online(cpu) || !IRQ_ALLOWED(cpu, allowed_mask) || + (search_idle && !IDLE_ENOUGH(cpu, now))); return cpu; } @@ -430,15 +439,14 @@ static inline void balance_irq(int cpu, int irq) unsigned long now = jiffies; cpumask_t allowed_mask; unsigned int new_cpu; - + if (irqbalance_disabled) - return; + return; cpus_and(allowed_mask, cpu_online_map, balance_irq_affinity[irq]); new_cpu = move(cpu, allowed_mask, now, 1); - if (cpu != new_cpu) { + if (cpu != new_cpu) set_pending_irq(irq, cpumask_of_cpu(new_cpu)); - } } static inline void rotate_irqs_among_cpus(unsigned long useful_load_threshold) @@ -450,14 +458,14 @@ static inline void rotate_irqs_among_cpus(unsigned long useful_load_threshold) if (!irq_desc[j].action) continue; /* Is it a significant load ? */ - if (IRQ_DELTA(CPU_TO_PACKAGEINDEX(i),j) < + if (IRQ_DELTA(CPU_TO_PACKAGEINDEX(i), j) < useful_load_threshold) continue; balance_irq(i, j); } } balanced_irq_interval = max((long)MIN_BALANCED_IRQ_INTERVAL, - balanced_irq_interval - BALANCED_IRQ_LESS_DELTA); + balanced_irq_interval - BALANCED_IRQ_LESS_DELTA); return; } @@ -486,22 +494,22 @@ static void do_irq_balance(void) /* Is this an active IRQ or balancing disabled ? */ if (!irq_desc[j].action || irq_balancing_disabled(j)) continue; - if ( package_index == i ) - IRQ_DELTA(package_index,j) = 0; + if (package_index == i) + IRQ_DELTA(package_index, j) = 0; /* Determine the total count per processor per IRQ */ value_now = (unsigned long) kstat_cpu(i).irqs[j]; /* Determine the activity per processor per IRQ */ - delta = value_now - LAST_CPU_IRQ(i,j); + delta = value_now - LAST_CPU_IRQ(i, j); /* Update last_cpu_irq[][] for the next time */ - LAST_CPU_IRQ(i,j) = value_now; + LAST_CPU_IRQ(i, j) = value_now; /* Ignore IRQs whose rate is less than the clock */ if (delta < useful_load_threshold) continue; /* update the load for the processor or package total */ - IRQ_DELTA(package_index,j) += delta; + IRQ_DELTA(package_index, j) += delta; /* Keep track of the higher numbered sibling as well */ if (i != package_index) @@ -527,7 +535,8 @@ static void do_irq_balance(void) max_cpu_irq = ULONG_MAX; tryanothercpu: - /* Look for heaviest loaded processor. + /* + * Look for heaviest loaded processor. * We may come back to get the next heaviest loaded processor. * Skip processors with trivial loads. */ @@ -536,7 +545,7 @@ tryanothercpu: for_each_online_cpu(i) { if (i != CPU_TO_PACKAGEINDEX(i)) continue; - if (max_cpu_irq <= CPU_IRQ(i)) + if (max_cpu_irq <= CPU_IRQ(i)) continue; if (tmp_cpu_irq < CPU_IRQ(i)) { tmp_cpu_irq = CPU_IRQ(i); @@ -545,8 +554,9 @@ tryanothercpu: } if (tmp_loaded == -1) { - /* In the case of small number of heavy interrupt sources, - * loading some of the cpus too much. We use Ingo's original + /* + * In the case of small number of heavy interrupt sources, + * loading some of the cpus too much. We use Ingo's original * approach to rotate them around. */ if (!first_attempt && imbalance >= useful_load_threshold) { @@ -555,13 +565,14 @@ tryanothercpu: } goto not_worth_the_effort; } - + first_attempt = 0; /* heaviest search */ max_cpu_irq = tmp_cpu_irq; /* load */ max_loaded = tmp_loaded; /* processor */ imbalance = (max_cpu_irq - min_cpu_irq) / 2; - - /* if imbalance is less than approx 10% of max load, then + + /* + * if imbalance is less than approx 10% of max load, then * observe diminishing returns action. - quit */ if (imbalance < (max_cpu_irq >> 3)) @@ -577,26 +588,25 @@ tryanotherirq: /* Is this an active IRQ? */ if (!irq_desc[j].action) continue; - if (imbalance <= IRQ_DELTA(max_loaded,j)) + if (imbalance <= IRQ_DELTA(max_loaded, j)) continue; /* Try to find the IRQ that is closest to the imbalance * without going over. */ - if (move_this_load < IRQ_DELTA(max_loaded,j)) { - move_this_load = IRQ_DELTA(max_loaded,j); + if (move_this_load < IRQ_DELTA(max_loaded, j)) { + move_this_load = IRQ_DELTA(max_loaded, j); selected_irq = j; } } - if (selected_irq == -1) { + if (selected_irq == -1) goto tryanothercpu; - } imbalance = move_this_load; - + /* For physical_balance case, we accumulated both load * values in the one of the siblings cpu_irq[], * to use the same code for physical and logical processors - * as much as possible. + * as much as possible. * * NOTE: the cpu_irq[] array holds the sum of the load for * sibling A and sibling B in the slot for the lowest numbered @@ -625,11 +635,11 @@ tryanotherirq: /* mark for change destination */ set_pending_irq(selected_irq, cpumask_of_cpu(min_loaded)); - /* Since we made a change, come back sooner to + /* Since we made a change, come back sooner to * check for more variation. */ balanced_irq_interval = max((long)MIN_BALANCED_IRQ_INTERVAL, - balanced_irq_interval - BALANCED_IRQ_LESS_DELTA); + balanced_irq_interval - BALANCED_IRQ_LESS_DELTA); return; } goto tryanotherirq; @@ -640,7 +650,7 @@ not_worth_the_effort: * upward */ balanced_irq_interval = min((long)MAX_BALANCED_IRQ_INTERVAL, - balanced_irq_interval + BALANCED_IRQ_MORE_DELTA); + balanced_irq_interval + BALANCED_IRQ_MORE_DELTA); return; } @@ -679,13 +689,13 @@ static int __init balanced_irq_init(void) cpumask_t tmp; cpus_shift_right(tmp, cpu_online_map, 2); - c = &boot_cpu_data; + c = &boot_cpu_data; /* When not overwritten by the command line ask subarchitecture. */ if (irqbalance_disabled == IRQBALANCE_CHECK_ARCH) irqbalance_disabled = NO_BALANCE_IRQ; if (irqbalance_disabled) return 0; - + /* disable irqbalance completely if there is only one processor online */ if (num_online_cpus() < 2) { irqbalance_disabled = 1; @@ -699,16 +709,14 @@ static int __init balanced_irq_init(void) physical_balance = 1; for_each_online_cpu(i) { - irq_cpu_data[i].irq_delta = kmalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL); - irq_cpu_data[i].last_irq = kmalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL); + irq_cpu_data[i].irq_delta = kzalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL); + irq_cpu_data[i].last_irq = kzalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL); if (irq_cpu_data[i].irq_delta == NULL || irq_cpu_data[i].last_irq == NULL) { printk(KERN_ERR "balanced_irq_init: out of memory"); goto failed; } - memset(irq_cpu_data[i].irq_delta,0,sizeof(unsigned long) * NR_IRQS); - memset(irq_cpu_data[i].last_irq,0,sizeof(unsigned long) * NR_IRQS); } - + printk(KERN_INFO "Starting balanced_irq\n"); if (!IS_ERR(kthread_run(balanced_irq, NULL, "kirqd"))) return 0; @@ -801,10 +809,10 @@ static int find_irq_entry(int apic, int pin, int type) int i; for (i = 0; i < mp_irq_entries; i++) - if (mp_irqs[i].mpc_irqtype == type && - (mp_irqs[i].mpc_dstapic == mp_ioapics[apic].mpc_apicid || - mp_irqs[i].mpc_dstapic == MP_APIC_ALL) && - mp_irqs[i].mpc_dstirq == pin) + if (mp_irqs[i].mp_irqtype == type && + (mp_irqs[i].mp_dstapic == mp_ioapics[apic].mp_apicid || + mp_irqs[i].mp_dstapic == MP_APIC_ALL) && + mp_irqs[i].mp_dstirq == pin) return i; return -1; @@ -818,13 +826,13 @@ static int __init find_isa_irq_pin(int irq, int type) int i; for (i = 0; i < mp_irq_entries; i++) { - int lbus = mp_irqs[i].mpc_srcbus; + int lbus = mp_irqs[i].mp_srcbus; if (test_bit(lbus, mp_bus_not_pci) && - (mp_irqs[i].mpc_irqtype == type) && - (mp_irqs[i].mpc_srcbusirq == irq)) + (mp_irqs[i].mp_irqtype == type) && + (mp_irqs[i].mp_srcbusirq == irq)) - return mp_irqs[i].mpc_dstirq; + return mp_irqs[i].mp_dstirq; } return -1; } @@ -834,17 +842,17 @@ static int __init find_isa_irq_apic(int irq, int type) int i; for (i = 0; i < mp_irq_entries; i++) { - int lbus = mp_irqs[i].mpc_srcbus; + int lbus = mp_irqs[i].mp_srcbus; if (test_bit(lbus, mp_bus_not_pci) && - (mp_irqs[i].mpc_irqtype == type) && - (mp_irqs[i].mpc_srcbusirq == irq)) + (mp_irqs[i].mp_irqtype == type) && + (mp_irqs[i].mp_srcbusirq == irq)) break; } if (i < mp_irq_entries) { int apic; - for(apic = 0; apic < nr_ioapics; apic++) { - if (mp_ioapics[apic].mpc_apicid == mp_irqs[i].mpc_dstapic) + for (apic = 0; apic < nr_ioapics; apic++) { + if (mp_ioapics[apic].mp_apicid == mp_irqs[i].mp_dstapic) return apic; } } @@ -864,28 +872,28 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin) apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, " "slot:%d, pin:%d.\n", bus, slot, pin); - if (mp_bus_id_to_pci_bus[bus] == -1) { + if (test_bit(bus, mp_bus_not_pci)) { printk(KERN_WARNING "PCI BIOS passed nonexistent PCI bus %d!\n", bus); return -1; } for (i = 0; i < mp_irq_entries; i++) { - int lbus = mp_irqs[i].mpc_srcbus; + int lbus = mp_irqs[i].mp_srcbus; for (apic = 0; apic < nr_ioapics; apic++) - if (mp_ioapics[apic].mpc_apicid == mp_irqs[i].mpc_dstapic || - mp_irqs[i].mpc_dstapic == MP_APIC_ALL) + if (mp_ioapics[apic].mp_apicid == mp_irqs[i].mp_dstapic || + mp_irqs[i].mp_dstapic == MP_APIC_ALL) break; if (!test_bit(lbus, mp_bus_not_pci) && - !mp_irqs[i].mpc_irqtype && + !mp_irqs[i].mp_irqtype && (bus == lbus) && - (slot == ((mp_irqs[i].mpc_srcbusirq >> 2) & 0x1f))) { - int irq = pin_2_irq(i,apic,mp_irqs[i].mpc_dstirq); + (slot == ((mp_irqs[i].mp_srcbusirq >> 2) & 0x1f))) { + int irq = pin_2_irq(i, apic, mp_irqs[i].mp_dstirq); if (!(apic || IO_APIC_IRQ(irq))) continue; - if (pin == (mp_irqs[i].mpc_srcbusirq & 3)) + if (pin == (mp_irqs[i].mp_srcbusirq & 3)) return irq; /* * Use the first all-but-pin matching entry as a @@ -900,7 +908,7 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin) EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector); /* - * This function currently is only a helper for the i386 smp boot process where + * This function currently is only a helper for the i386 smp boot process where * we need to reprogram the ioredtbls to cater for the cpus which have come online * so mask in all cases should simply be TARGET_CPUS */ @@ -952,7 +960,7 @@ static int EISA_ELCR(unsigned int irq) * EISA conforming in the MP table, that means its trigger type must * be read in from the ELCR */ -#define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].mpc_srcbusirq)) +#define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].mp_srcbusirq)) #define default_EISA_polarity(idx) default_ISA_polarity(idx) /* PCI interrupts are always polarity one level triggered, @@ -969,118 +977,115 @@ static int EISA_ELCR(unsigned int irq) static int MPBIOS_polarity(int idx) { - int bus = mp_irqs[idx].mpc_srcbus; + int bus = mp_irqs[idx].mp_srcbus; int polarity; /* * Determine IRQ line polarity (high active or low active): */ - switch (mp_irqs[idx].mpc_irqflag & 3) + switch (mp_irqs[idx].mp_irqflag & 3) { + case 0: /* conforms, ie. bus-type dependent polarity */ { - case 0: /* conforms, ie. bus-type dependent polarity */ - { - polarity = test_bit(bus, mp_bus_not_pci)? - default_ISA_polarity(idx): - default_PCI_polarity(idx); - break; - } - case 1: /* high active */ - { - polarity = 0; - break; - } - case 2: /* reserved */ - { - printk(KERN_WARNING "broken BIOS!!\n"); - polarity = 1; - break; - } - case 3: /* low active */ - { - polarity = 1; - break; - } - default: /* invalid */ - { - printk(KERN_WARNING "broken BIOS!!\n"); - polarity = 1; - break; - } + polarity = test_bit(bus, mp_bus_not_pci)? + default_ISA_polarity(idx): + default_PCI_polarity(idx); + break; + } + case 1: /* high active */ + { + polarity = 0; + break; + } + case 2: /* reserved */ + { + printk(KERN_WARNING "broken BIOS!!\n"); + polarity = 1; + break; + } + case 3: /* low active */ + { + polarity = 1; + break; + } + default: /* invalid */ + { + printk(KERN_WARNING "broken BIOS!!\n"); + polarity = 1; + break; + } } return polarity; } static int MPBIOS_trigger(int idx) { - int bus = mp_irqs[idx].mpc_srcbus; + int bus = mp_irqs[idx].mp_srcbus; int trigger; /* * Determine IRQ trigger mode (edge or level sensitive): */ - switch ((mp_irqs[idx].mpc_irqflag>>2) & 3) + switch ((mp_irqs[idx].mp_irqflag>>2) & 3) { + case 0: /* conforms, ie. bus-type dependent */ { - case 0: /* conforms, ie. bus-type dependent */ - { - trigger = test_bit(bus, mp_bus_not_pci)? - default_ISA_trigger(idx): - default_PCI_trigger(idx); + trigger = test_bit(bus, mp_bus_not_pci)? + default_ISA_trigger(idx): + default_PCI_trigger(idx); #if defined(CONFIG_EISA) || defined(CONFIG_MCA) - switch (mp_bus_id_to_type[bus]) - { - case MP_BUS_ISA: /* ISA pin */ - { - /* set before the switch */ - break; - } - case MP_BUS_EISA: /* EISA pin */ - { - trigger = default_EISA_trigger(idx); - break; - } - case MP_BUS_PCI: /* PCI pin */ - { - /* set before the switch */ - break; - } - case MP_BUS_MCA: /* MCA pin */ - { - trigger = default_MCA_trigger(idx); - break; - } - default: - { - printk(KERN_WARNING "broken BIOS!!\n"); - trigger = 1; - break; - } - } -#endif + switch (mp_bus_id_to_type[bus]) { + case MP_BUS_ISA: /* ISA pin */ + { + /* set before the switch */ break; } - case 1: /* edge */ + case MP_BUS_EISA: /* EISA pin */ { - trigger = 0; + trigger = default_EISA_trigger(idx); break; } - case 2: /* reserved */ + case MP_BUS_PCI: /* PCI pin */ { - printk(KERN_WARNING "broken BIOS!!\n"); - trigger = 1; + /* set before the switch */ break; } - case 3: /* level */ + case MP_BUS_MCA: /* MCA pin */ { - trigger = 1; + trigger = default_MCA_trigger(idx); break; } - default: /* invalid */ + default: { printk(KERN_WARNING "broken BIOS!!\n"); - trigger = 0; + trigger = 1; break; } } +#endif + break; + } + case 1: /* edge */ + { + trigger = 0; + break; + } + case 2: /* reserved */ + { + printk(KERN_WARNING "broken BIOS!!\n"); + trigger = 1; + break; + } + case 3: /* level */ + { + trigger = 1; + break; + } + default: /* invalid */ + { + printk(KERN_WARNING "broken BIOS!!\n"); + trigger = 0; + break; + } + } return trigger; } @@ -1097,16 +1102,16 @@ static inline int irq_trigger(int idx) static int pin_2_irq(int idx, int apic, int pin) { int irq, i; - int bus = mp_irqs[idx].mpc_srcbus; + int bus = mp_irqs[idx].mp_srcbus; /* * Debugging check, we are in big trouble if this message pops up! */ - if (mp_irqs[idx].mpc_dstirq != pin) + if (mp_irqs[idx].mp_dstirq != pin) printk(KERN_ERR "broken BIOS or MPTABLE parser, ayiee!!\n"); if (test_bit(bus, mp_bus_not_pci)) - irq = mp_irqs[idx].mpc_srcbusirq; + irq = mp_irqs[idx].mp_srcbusirq; else { /* * PCI IRQs are mapped in order @@ -1148,8 +1153,8 @@ static inline int IO_APIC_irq_trigger(int irq) for (apic = 0; apic < nr_ioapics; apic++) { for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) { - idx = find_irq_entry(apic,pin,mp_INT); - if ((idx != -1) && (irq == pin_2_irq(idx,apic,pin))) + idx = find_irq_entry(apic, pin, mp_INT); + if ((idx != -1) && (irq == pin_2_irq(idx, apic, pin))) return irq_trigger(idx); } } @@ -1164,7 +1169,7 @@ static u8 irq_vector[NR_IRQ_VECTORS] __read_mostly = { FIRST_DEVICE_VECTOR , 0 } static int __assign_irq_vector(int irq) { - static int current_vector = FIRST_DEVICE_VECTOR, current_offset = 0; + static int current_vector = FIRST_DEVICE_VECTOR, current_offset; int vector, offset; BUG_ON((unsigned)irq >= NR_IRQ_VECTORS); @@ -1176,7 +1181,7 @@ static int __assign_irq_vector(int irq) offset = current_offset; next: vector += 8; - if (vector >= FIRST_SYSTEM_VECTOR) { + if (vector >= first_system_vector) { offset = (offset + 1) % 8; vector = FIRST_DEVICE_VECTOR + offset; } @@ -1203,6 +1208,11 @@ static int assign_irq_vector(int irq) return vector; } + +void setup_vector_irq(int cpu) +{ +} + static struct irq_chip ioapic_chip; #define IOAPIC_AUTO -1 @@ -1237,25 +1247,25 @@ static void __init setup_IO_APIC_irqs(void) /* * add it to the IO-APIC irq-routing table: */ - memset(&entry,0,sizeof(entry)); + memset(&entry, 0, sizeof(entry)); entry.delivery_mode = INT_DELIVERY_MODE; entry.dest_mode = INT_DEST_MODE; entry.mask = 0; /* enable IRQ */ - entry.dest.logical.logical_dest = + entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS); - idx = find_irq_entry(apic,pin,mp_INT); + idx = find_irq_entry(apic, pin, mp_INT); if (idx == -1) { if (first_notcon) { apic_printk(APIC_VERBOSE, KERN_DEBUG " IO-APIC (apicid-pin) %d-%d", - mp_ioapics[apic].mpc_apicid, + mp_ioapics[apic].mp_apicid, pin); first_notcon = 0; } else apic_printk(APIC_VERBOSE, ", %d-%d", - mp_ioapics[apic].mpc_apicid, pin); + mp_ioapics[apic].mp_apicid, pin); continue; } @@ -1289,7 +1299,7 @@ static void __init setup_IO_APIC_irqs(void) vector = assign_irq_vector(irq); entry.vector = vector; ioapic_register_intr(irq, vector, IOAPIC_AUTO); - + if (!apic && (irq < 16)) disable_8259A_irq(irq); } @@ -1302,25 +1312,21 @@ static void __init setup_IO_APIC_irqs(void) } /* - * Set up the 8259A-master output pin: + * Set up the timer pin, possibly with the 8259A-master behind. */ -static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, int vector) +static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin, + int vector) { struct IO_APIC_route_entry entry; - memset(&entry,0,sizeof(entry)); - - disable_8259A_irq(0); - - /* mask LVT0 */ - apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT); + memset(&entry, 0, sizeof(entry)); /* * We use logical delivery to get the timer IRQ * to the first CPU. */ entry.dest_mode = INT_DEST_MODE; - entry.mask = 0; /* unmask IRQ now */ + entry.mask = 1; /* mask IRQ now */ entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS); entry.delivery_mode = INT_DELIVERY_MODE; entry.polarity = 0; @@ -1329,17 +1335,14 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in /* * The timer IRQ doesn't have to know that behind the - * scene we have a 8259A-master in AEOI mode ... + * scene we may have a 8259A-master in AEOI mode ... */ - irq_desc[0].chip = &ioapic_chip; - set_irq_handler(0, handle_edge_irq); + ioapic_register_intr(0, vector, IOAPIC_EDGE); /* * Add it to the IO-APIC irq-routing table: */ ioapic_write_entry(apic, pin, entry); - - enable_8259A_irq(0); } void __init print_IO_APIC(void) @@ -1354,10 +1357,10 @@ void __init print_IO_APIC(void) if (apic_verbosity == APIC_QUIET) return; - printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries); + printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries); for (i = 0; i < nr_ioapics; i++) printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n", - mp_ioapics[i].mpc_apicid, nr_ioapic_registers[i]); + mp_ioapics[i].mp_apicid, nr_ioapic_registers[i]); /* * We are a bit conservative about what we expect. We have to @@ -1376,7 +1379,7 @@ void __init print_IO_APIC(void) reg_03.raw = io_apic_read(apic, 3); spin_unlock_irqrestore(&ioapic_lock, flags); - printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mpc_apicid); + printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mp_apicid); printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw); printk(KERN_DEBUG "....... : physical APIC id: %02X\n", reg_00.bits.ID); printk(KERN_DEBUG "....... : Delivery Type: %X\n", reg_00.bits.delivery_type); @@ -1459,7 +1462,7 @@ void __init print_IO_APIC(void) #if 0 -static void print_APIC_bitfield (int base) +static void print_APIC_bitfield(int base) { unsigned int v; int i, j; @@ -1480,7 +1483,7 @@ static void print_APIC_bitfield (int base) } } -void /*__init*/ print_local_APIC(void * dummy) +void /*__init*/ print_local_APIC(void *dummy) { unsigned int v, ver, maxlvt; @@ -1489,6 +1492,7 @@ void /*__init*/ print_local_APIC(void * dummy) printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n", smp_processor_id(), hard_smp_processor_id()); + v = apic_read(APIC_ID); printk(KERN_INFO "... APIC ID: %08x (%01x)\n", v, GET_APIC_ID(read_apic_id())); v = apic_read(APIC_LVR); @@ -1563,9 +1567,9 @@ void /*__init*/ print_local_APIC(void * dummy) printk("\n"); } -void print_all_local_APICs (void) +void print_all_local_APICs(void) { - on_each_cpu(print_local_APIC, NULL, 1, 1); + on_each_cpu(print_local_APIC, NULL, 1); } void /*__init*/ print_PIC(void) @@ -1586,11 +1590,11 @@ void /*__init*/ print_PIC(void) v = inb(0xa0) << 8 | inb(0x20); printk(KERN_DEBUG "... PIC IRR: %04x\n", v); - outb(0x0b,0xa0); - outb(0x0b,0x20); + outb(0x0b, 0xa0); + outb(0x0b, 0x20); v = inb(0xa0) << 8 | inb(0x20); - outb(0x0a,0xa0); - outb(0x0a,0x20); + outb(0x0a, 0xa0); + outb(0x0a, 0x20); spin_unlock_irqrestore(&i8259A_lock, flags); @@ -1626,7 +1630,7 @@ static void __init enable_IO_APIC(void) spin_unlock_irqrestore(&ioapic_lock, flags); nr_ioapic_registers[apic] = reg_01.bits.entries+1; } - for(apic = 0; apic < nr_ioapics; apic++) { + for (apic = 0; apic < nr_ioapics; apic++) { int pin; /* See if any of the pins is in ExtINT mode */ for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) { @@ -1716,7 +1720,6 @@ void disable_IO_APIC(void) * by Matt Domsch <Matt_Domsch@dell.com> Tue Dec 21 12:25:05 CST 1999 */ -#ifndef CONFIG_X86_NUMAQ static void __init setup_ioapic_ids_from_mpc(void) { union IO_APIC_reg_00 reg_00; @@ -1726,6 +1729,11 @@ static void __init setup_ioapic_ids_from_mpc(void) unsigned char old_id; unsigned long flags; +#ifdef CONFIG_X86_NUMAQ + if (found_numaq) + return; +#endif + /* * Don't check I/O APIC IDs for xAPIC systems. They have * no meaning without the serial APIC bus. @@ -1748,15 +1756,15 @@ static void __init setup_ioapic_ids_from_mpc(void) spin_lock_irqsave(&ioapic_lock, flags); reg_00.raw = io_apic_read(apic, 0); spin_unlock_irqrestore(&ioapic_lock, flags); - - old_id = mp_ioapics[apic].mpc_apicid; - if (mp_ioapics[apic].mpc_apicid >= get_physical_broadcast()) { + old_id = mp_ioapics[apic].mp_apicid; + + if (mp_ioapics[apic].mp_apicid >= get_physical_broadcast()) { printk(KERN_ERR "BIOS bug, IO-APIC#%d ID is %d in the MPC table!...\n", - apic, mp_ioapics[apic].mpc_apicid); + apic, mp_ioapics[apic].mp_apicid); printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n", reg_00.bits.ID); - mp_ioapics[apic].mpc_apicid = reg_00.bits.ID; + mp_ioapics[apic].mp_apicid = reg_00.bits.ID; } /* @@ -1765,9 +1773,9 @@ static void __init setup_ioapic_ids_from_mpc(void) * 'stuck on smp_invalidate_needed IPI wait' messages. */ if (check_apicid_used(phys_id_present_map, - mp_ioapics[apic].mpc_apicid)) { + mp_ioapics[apic].mp_apicid)) { printk(KERN_ERR "BIOS bug, IO-APIC#%d ID %d is already used!...\n", - apic, mp_ioapics[apic].mpc_apicid); + apic, mp_ioapics[apic].mp_apicid); for (i = 0; i < get_physical_broadcast(); i++) if (!physid_isset(i, phys_id_present_map)) break; @@ -1776,13 +1784,13 @@ static void __init setup_ioapic_ids_from_mpc(void) printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n", i); physid_set(i, phys_id_present_map); - mp_ioapics[apic].mpc_apicid = i; + mp_ioapics[apic].mp_apicid = i; } else { physid_mask_t tmp; - tmp = apicid_to_cpu_present(mp_ioapics[apic].mpc_apicid); + tmp = apicid_to_cpu_present(mp_ioapics[apic].mp_apicid); apic_printk(APIC_VERBOSE, "Setting %d in the " "phys_id_present_map\n", - mp_ioapics[apic].mpc_apicid); + mp_ioapics[apic].mp_apicid); physids_or(phys_id_present_map, phys_id_present_map, tmp); } @@ -1791,21 +1799,21 @@ static void __init setup_ioapic_ids_from_mpc(void) * We need to adjust the IRQ routing table * if the ID changed. */ - if (old_id != mp_ioapics[apic].mpc_apicid) + if (old_id != mp_ioapics[apic].mp_apicid) for (i = 0; i < mp_irq_entries; i++) - if (mp_irqs[i].mpc_dstapic == old_id) - mp_irqs[i].mpc_dstapic - = mp_ioapics[apic].mpc_apicid; + if (mp_irqs[i].mp_dstapic == old_id) + mp_irqs[i].mp_dstapic + = mp_ioapics[apic].mp_apicid; /* * Read the right value from the MPC table and * write it into the ID register. - */ + */ apic_printk(APIC_VERBOSE, KERN_INFO "...changing IO-APIC physical APIC ID to %d ...", - mp_ioapics[apic].mpc_apicid); + mp_ioapics[apic].mp_apicid); - reg_00.bits.ID = mp_ioapics[apic].mpc_apicid; + reg_00.bits.ID = mp_ioapics[apic].mp_apicid; spin_lock_irqsave(&ioapic_lock, flags); io_apic_write(apic, 0, reg_00.raw); spin_unlock_irqrestore(&ioapic_lock, flags); @@ -1816,15 +1824,12 @@ static void __init setup_ioapic_ids_from_mpc(void) spin_lock_irqsave(&ioapic_lock, flags); reg_00.raw = io_apic_read(apic, 0); spin_unlock_irqrestore(&ioapic_lock, flags); - if (reg_00.bits.ID != mp_ioapics[apic].mpc_apicid) + if (reg_00.bits.ID != mp_ioapics[apic].mp_apicid) printk("could not set ID!\n"); else apic_printk(APIC_VERBOSE, " ok.\n"); } } -#else -static void __init setup_ioapic_ids_from_mpc(void) { } -#endif int no_timer_check __initdata; @@ -2015,12 +2020,12 @@ static inline void init_IO_APIC_traps(void) * The local APIC irq-chip implementation: */ -static void ack_apic(unsigned int irq) +static void ack_lapic_irq(unsigned int irq) { ack_APIC_irq(); } -static void mask_lapic_irq (unsigned int irq) +static void mask_lapic_irq(unsigned int irq) { unsigned long v; @@ -2028,7 +2033,7 @@ static void mask_lapic_irq (unsigned int irq) apic_write_around(APIC_LVT0, v | APIC_LVT_MASKED); } -static void unmask_lapic_irq (unsigned int irq) +static void unmask_lapic_irq(unsigned int irq) { unsigned long v; @@ -2037,23 +2042,31 @@ static void unmask_lapic_irq (unsigned int irq) } static struct irq_chip lapic_chip __read_mostly = { - .name = "local-APIC-edge", + .name = "local-APIC", .mask = mask_lapic_irq, .unmask = unmask_lapic_irq, - .eoi = ack_apic, + .ack = ack_lapic_irq, }; +static void lapic_register_intr(int irq, int vector) +{ + irq_desc[irq].status &= ~IRQ_LEVEL; + set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq, + "edge"); + set_intr_gate(vector, interrupt[irq]); +} + static void __init setup_nmi(void) { /* - * Dirty trick to enable the NMI watchdog ... + * Dirty trick to enable the NMI watchdog ... * We put the 8259A master into AEOI mode and * unmask on all local APICs LVT0 as NMI. * * The idea to use the 8259A in AEOI mode ('8259A Virtual Wire') * is from Maciej W. Rozycki - so we do not have to EOI from * the NMI handler or the timer interrupt. - */ + */ apic_printk(APIC_VERBOSE, KERN_INFO "activating NMI Watchdog ..."); enable_NMI_through_LVT0(); @@ -2129,6 +2142,7 @@ static inline void __init unlock_ExtINT_logic(void) static inline void __init check_timer(void) { int apic1, pin1, apic2, pin2; + int no_pin1 = 0; int vector; unsigned int ver; unsigned long flags; @@ -2146,21 +2160,17 @@ static inline void __init check_timer(void) set_intr_gate(vector, interrupt[0]); /* - * Subtle, code in do_timer_interrupt() expects an AEOI - * mode for the 8259A whenever interrupts are routed - * through I/O APICs. Also IRQ0 has to be enabled in - * the 8259A which implies the virtual wire has to be - * disabled in the local APIC. Finally timer interrupts - * need to be acknowledged manually in the 8259A for - * timer_interrupt() and for the i82489DX when using - * the NMI watchdog. + * As IRQ0 is to be enabled in the 8259A, the virtual + * wire has to be disabled in the local APIC. Also + * timer interrupts need to be acknowledged manually in + * the 8259A for the i82489DX when using the NMI + * watchdog as that APIC treats NMIs as level-triggered. + * The AEOI mode will finish them in the 8259A + * automatically. */ apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT); init_8259A(1); - timer_ack = !cpu_has_tsc; - timer_ack |= (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver)); - if (timer_over_8254 > 0) - enable_8259A_irq(0); + timer_ack = (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver)); pin1 = find_isa_irq_pin(0, mp_INT); apic1 = find_isa_irq_apic(0, mp_INT); @@ -2170,14 +2180,33 @@ static inline void __init check_timer(void) printk(KERN_INFO "..TIMER: vector=0x%02X apic1=%d pin1=%d apic2=%d pin2=%d\n", vector, apic1, pin1, apic2, pin2); + /* + * Some BIOS writers are clueless and report the ExtINTA + * I/O APIC input from the cascaded 8259A as the timer + * interrupt input. So just in case, if only one pin + * was found above, try it both directly and through the + * 8259A. + */ + if (pin1 == -1) { + pin1 = pin2; + apic1 = apic2; + no_pin1 = 1; + } else if (pin2 == -1) { + pin2 = pin1; + apic2 = apic1; + } + if (pin1 != -1) { /* * Ok, does IRQ0 through the IOAPIC work? */ + if (no_pin1) { + add_pin_to_irq(0, apic1, pin1); + setup_timer_IRQ0_pin(apic1, pin1, vector); + } unmask_IO_APIC_irq(0); if (timer_irq_works()) { if (nmi_watchdog == NMI_IO_APIC) { - disable_8259A_irq(0); setup_nmi(); enable_8259A_irq(0); } @@ -2186,45 +2215,47 @@ static inline void __init check_timer(void) goto out; } clear_IO_APIC_pin(apic1, pin1); - printk(KERN_ERR "..MP-BIOS bug: 8254 timer not connected to " - "IO-APIC\n"); - } + if (!no_pin1) + printk(KERN_ERR "..MP-BIOS bug: " + "8254 timer not connected to IO-APIC\n"); - printk(KERN_INFO "...trying to set up timer (IRQ0) through the 8259A ... "); - if (pin2 != -1) { + printk(KERN_INFO "...trying to set up timer (IRQ0) " + "through the 8259A ... "); printk("\n..... (found pin %d) ...", pin2); /* * legacy devices should be connected to IO APIC #0 */ - setup_ExtINT_IRQ0_pin(apic2, pin2, vector); + replace_pin_at_irq(0, apic1, pin1, apic2, pin2); + setup_timer_IRQ0_pin(apic2, pin2, vector); + unmask_IO_APIC_irq(0); + enable_8259A_irq(0); if (timer_irq_works()) { printk("works.\n"); - if (pin1 != -1) - replace_pin_at_irq(0, apic1, pin1, apic2, pin2); - else - add_pin_to_irq(0, apic2, pin2); + timer_through_8259 = 1; if (nmi_watchdog == NMI_IO_APIC) { + disable_8259A_irq(0); setup_nmi(); + enable_8259A_irq(0); } goto out; } /* * Cleanup, just in case ... */ + disable_8259A_irq(0); clear_IO_APIC_pin(apic2, pin2); + printk(" failed.\n"); } - printk(" failed.\n"); if (nmi_watchdog == NMI_IO_APIC) { printk(KERN_WARNING "timer doesn't work through the IO-APIC - disabling NMI Watchdog!\n"); - nmi_watchdog = 0; + nmi_watchdog = NMI_NONE; } + timer_ack = 0; printk(KERN_INFO "...trying to set up timer as Virtual Wire IRQ..."); - disable_8259A_irq(0); - set_irq_chip_and_handler_name(0, &lapic_chip, handle_fasteoi_irq, - "fasteoi"); + lapic_register_intr(0, vector); apic_write_around(APIC_LVT0, APIC_DM_FIXED | vector); /* Fixed mode */ enable_8259A_irq(0); @@ -2232,12 +2263,12 @@ static inline void __init check_timer(void) printk(" works.\n"); goto out; } + disable_8259A_irq(0); apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | vector); printk(" failed.\n"); printk(KERN_INFO "...trying to set up timer as ExtINT IRQ..."); - timer_ack = 0; init_8259A(0); make_8259A_irq(0); apic_write_around(APIC_LVT0, APIC_DM_EXTINT); @@ -2256,11 +2287,21 @@ out: } /* - * - * IRQ's that are handled by the PIC in the MPS IOAPIC case. - * - IRQ2 is the cascade IRQ, and cannot be a io-apic IRQ. - * Linux doesn't really care, as it's not actually used - * for any interrupt handling anyway. + * Traditionally ISA IRQ2 is the cascade IRQ, and is not available + * to devices. However there may be an I/O APIC pin available for + * this interrupt regardless. The pin may be left unconnected, but + * typically it will be reused as an ExtINT cascade interrupt for + * the master 8259A. In the MPS case such a pin will normally be + * reported as an ExtINT interrupt in the MP table. With ACPI + * there is no provision for ExtINT interrupts, and in the absence + * of an override it would be treated as an ordinary ISA I/O APIC + * interrupt, that is edge-triggered and unmasked by default. We + * used to do this, but it caused problems on some systems because + * of the NMI watchdog and sometimes IRQ0 of the 8254 timer using + * the same ExtINT cascade interrupt to drive the local APIC of the + * bootstrap processor. Therefore we refrain from routing IRQ2 to + * the I/O APIC in all cases now. No actual device should request + * it anyway. --macro */ #define PIC_IRQS (1 << PIC_CASCADE_IR) @@ -2269,15 +2310,12 @@ void __init setup_IO_APIC(void) int i; /* Reserve all the system vectors. */ - for (i = FIRST_SYSTEM_VECTOR; i < NR_VECTORS; i++) + for (i = first_system_vector; i < NR_VECTORS; i++) set_bit(i, used_vectors); enable_IO_APIC(); - if (acpi_ioapic) - io_apic_irqs = ~0; /* all IRQs go through IOAPIC */ - else - io_apic_irqs = ~PIC_IRQS; + io_apic_irqs = ~PIC_IRQS; printk("ENABLING IO-APIC IRQs\n"); @@ -2294,28 +2332,14 @@ void __init setup_IO_APIC(void) print_IO_APIC(); } -static int __init setup_disable_8254_timer(char *s) -{ - timer_over_8254 = -1; - return 1; -} -static int __init setup_enable_8254_timer(char *s) -{ - timer_over_8254 = 2; - return 1; -} - -__setup("disable_8254_timer", setup_disable_8254_timer); -__setup("enable_8254_timer", setup_enable_8254_timer); - /* * Called after all the initialization is done. If we didnt find any * APIC bugs then we can allow the modify fast path */ - + static int __init io_apic_bug_finalize(void) { - if(sis_apic_bug == -1) + if (sis_apic_bug == -1) sis_apic_bug = 0; return 0; } @@ -2326,17 +2350,17 @@ struct sysfs_ioapic_data { struct sys_device dev; struct IO_APIC_route_entry entry[0]; }; -static struct sysfs_ioapic_data * mp_ioapic_data[MAX_IO_APICS]; +static struct sysfs_ioapic_data *mp_ioapic_data[MAX_IO_APICS]; static int ioapic_suspend(struct sys_device *dev, pm_message_t state) { struct IO_APIC_route_entry *entry; struct sysfs_ioapic_data *data; int i; - + data = container_of(dev, struct sysfs_ioapic_data, dev); entry = data->entry; - for (i = 0; i < nr_ioapic_registers[dev->id]; i ++) + for (i = 0; i < nr_ioapic_registers[dev->id]; i++) entry[i] = ioapic_read_entry(dev->id, i); return 0; @@ -2349,18 +2373,18 @@ static int ioapic_resume(struct sys_device *dev) unsigned long flags; union IO_APIC_reg_00 reg_00; int i; - + data = container_of(dev, struct sysfs_ioapic_data, dev); entry = data->entry; spin_lock_irqsave(&ioapic_lock, flags); reg_00.raw = io_apic_read(dev->id, 0); - if (reg_00.bits.ID != mp_ioapics[dev->id].mpc_apicid) { - reg_00.bits.ID = mp_ioapics[dev->id].mpc_apicid; + if (reg_00.bits.ID != mp_ioapics[dev->id].mp_apicid) { + reg_00.bits.ID = mp_ioapics[dev->id].mp_apicid; io_apic_write(dev->id, 0, reg_00.raw); } spin_unlock_irqrestore(&ioapic_lock, flags); - for (i = 0; i < nr_ioapic_registers[dev->id]; i ++) + for (i = 0; i < nr_ioapic_registers[dev->id]; i++) ioapic_write_entry(dev->id, i, entry[i]); return 0; @@ -2374,24 +2398,23 @@ static struct sysdev_class ioapic_sysdev_class = { static int __init ioapic_init_sysfs(void) { - struct sys_device * dev; + struct sys_device *dev; int i, size, error = 0; error = sysdev_class_register(&ioapic_sysdev_class); if (error) return error; - for (i = 0; i < nr_ioapics; i++ ) { - size = sizeof(struct sys_device) + nr_ioapic_registers[i] + for (i = 0; i < nr_ioapics; i++) { + size = sizeof(struct sys_device) + nr_ioapic_registers[i] * sizeof(struct IO_APIC_route_entry); - mp_ioapic_data[i] = kmalloc(size, GFP_KERNEL); + mp_ioapic_data[i] = kzalloc(size, GFP_KERNEL); if (!mp_ioapic_data[i]) { printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i); continue; } - memset(mp_ioapic_data[i], 0, size); dev = &mp_ioapic_data[i]->dev; - dev->id = i; + dev->id = i; dev->cls = &ioapic_sysdev_class; error = sysdev_register(dev); if (error) { @@ -2466,7 +2489,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms msg->address_lo = MSI_ADDR_BASE_LO | ((INT_DEST_MODE == 0) ? - MSI_ADDR_DEST_MODE_PHYSICAL: +MSI_ADDR_DEST_MODE_PHYSICAL: MSI_ADDR_DEST_MODE_LOGICAL) | ((INT_DELIVERY_MODE != dest_LowestPrio) ? MSI_ADDR_REDIRECTION_CPU: @@ -2477,7 +2500,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms MSI_DATA_TRIGGER_EDGE | MSI_DATA_LEVEL_ASSERT | ((INT_DELIVERY_MODE != dest_LowestPrio) ? - MSI_DATA_DELIVERY_FIXED: +MSI_DATA_DELIVERY_FIXED: MSI_DATA_DELIVERY_LOWPRI) | MSI_DATA_VECTOR(vector); } @@ -2648,12 +2671,12 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) #endif /* CONFIG_HT_IRQ */ /* -------------------------------------------------------------------------- - ACPI-based IOAPIC Configuration + ACPI-based IOAPIC Configuration -------------------------------------------------------------------------- */ #ifdef CONFIG_ACPI -int __init io_apic_get_unique_id (int ioapic, int apic_id) +int __init io_apic_get_unique_id(int ioapic, int apic_id) { union IO_APIC_reg_00 reg_00; static physid_mask_t apic_id_map = PHYSID_MASK_NONE; @@ -2662,10 +2685,10 @@ int __init io_apic_get_unique_id (int ioapic, int apic_id) int i = 0; /* - * The P4 platform supports up to 256 APIC IDs on two separate APIC - * buses (one for LAPICs, one for IOAPICs), where predecessors only + * The P4 platform supports up to 256 APIC IDs on two separate APIC + * buses (one for LAPICs, one for IOAPICs), where predecessors only * supports up to 16 on one shared APIC bus. - * + * * TBD: Expand LAPIC/IOAPIC support on P4-class systems to take full * advantage of new APIC bus architecture. */ @@ -2684,7 +2707,7 @@ int __init io_apic_get_unique_id (int ioapic, int apic_id) } /* - * Every APIC in a system must have a unique ID or we get lots of nice + * Every APIC in a system must have a unique ID or we get lots of nice * 'stuck on smp_invalidate_needed IPI wait' messages. */ if (check_apicid_used(apic_id_map, apic_id)) { @@ -2701,7 +2724,7 @@ int __init io_apic_get_unique_id (int ioapic, int apic_id) "trying %d\n", ioapic, apic_id, i); apic_id = i; - } + } tmp = apicid_to_cpu_present(apic_id); physids_or(apic_id_map, apic_id_map, tmp); @@ -2728,7 +2751,7 @@ int __init io_apic_get_unique_id (int ioapic, int apic_id) } -int __init io_apic_get_version (int ioapic) +int __init io_apic_get_version(int ioapic) { union IO_APIC_reg_01 reg_01; unsigned long flags; @@ -2741,7 +2764,7 @@ int __init io_apic_get_version (int ioapic) } -int __init io_apic_get_redir_entries (int ioapic) +int __init io_apic_get_redir_entries(int ioapic) { union IO_APIC_reg_01 reg_01; unsigned long flags; @@ -2754,7 +2777,7 @@ int __init io_apic_get_redir_entries (int ioapic) } -int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int active_high_low) +int io_apic_set_pci_routing(int ioapic, int pin, int irq, int edge_level, int active_high_low) { struct IO_APIC_route_entry entry; @@ -2770,7 +2793,7 @@ int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int a * corresponding device driver registers for this IRQ. */ - memset(&entry,0,sizeof(entry)); + memset(&entry, 0, sizeof(entry)); entry.delivery_mode = INT_DELIVERY_MODE; entry.dest_mode = INT_DEST_MODE; @@ -2789,7 +2812,7 @@ int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int a apic_printk(APIC_DEBUG, KERN_DEBUG "IOAPIC[%d]: Set PCI routing entry " "(%d-%d -> 0x%x -> IRQ %d Mode:%i Active:%i)\n", ioapic, - mp_ioapics[ioapic].mpc_apicid, pin, entry.vector, irq, + mp_ioapics[ioapic].mp_apicid, pin, entry.vector, irq, edge_level, active_high_low); ioapic_register_intr(irq, entry.vector, edge_level); @@ -2810,8 +2833,8 @@ int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity) return -1; for (i = 0; i < mp_irq_entries; i++) - if (mp_irqs[i].mpc_irqtype == mp_INT && - mp_irqs[i].mpc_srcbusirq == bus_irq) + if (mp_irqs[i].mp_irqtype == mp_INT && + mp_irqs[i].mp_srcbusirq == bus_irq) break; if (i >= mp_irq_entries) return -1; @@ -2844,3 +2867,34 @@ static int __init parse_noapic(char *arg) return 0; } early_param("noapic", parse_noapic); + +void __init ioapic_init_mappings(void) +{ + unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0; + int i; + + for (i = 0; i < nr_ioapics; i++) { + if (smp_found_config) { + ioapic_phys = mp_ioapics[i].mp_apicaddr; + if (!ioapic_phys) { + printk(KERN_ERR + "WARNING: bogus zero IO-APIC " + "address found in MPTABLE, " + "disabling IO/APIC support!\n"); + smp_found_config = 0; + skip_ioapic_setup = 1; + goto fake_ioapic_page; + } + } else { +fake_ioapic_page: + ioapic_phys = (unsigned long) + alloc_bootmem_pages(PAGE_SIZE); + ioapic_phys = __pa(ioapic_phys); + } + set_fixmap_nocache(idx, ioapic_phys); + printk(KERN_DEBUG "mapped IOAPIC to %08lx (%08lx)\n", + __fix_to_virt(idx), ioapic_phys); + idx++; + } +} + diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c index ef1a8dfcc529..6510cde36b35 100644 --- a/arch/x86/kernel/io_apic_64.c +++ b/arch/x86/kernel/io_apic_64.c @@ -61,7 +61,7 @@ struct irq_cfg { }; /* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */ -struct irq_cfg irq_cfg[NR_IRQS] __read_mostly = { +static struct irq_cfg irq_cfg[NR_IRQS] __read_mostly = { [0] = { .domain = CPU_MASK_ALL, .vector = IRQ0_VECTOR, }, [1] = { .domain = CPU_MASK_ALL, .vector = IRQ1_VECTOR, }, [2] = { .domain = CPU_MASK_ALL, .vector = IRQ2_VECTOR, }, @@ -82,6 +82,10 @@ struct irq_cfg irq_cfg[NR_IRQS] __read_mostly = { static int assign_irq_vector(int irq, cpumask_t mask); +int first_system_vector = 0xfe; + +char system_vectors[NR_VECTORS] = { [0 ... NR_VECTORS-1] = SYS_VECTOR_FREE}; + #define __apicdebuginit __init int sis_apic_bug; /* not actually supported, dummy for compile */ @@ -90,7 +94,7 @@ static int no_timer_check; static int disable_timer_pin_1 __initdata; -int timer_over_8254 __initdata = 1; +int timer_through_8259 __initdata; /* Where if anywhere is the i8259 connect in external int mode */ static struct { int pin, apic; } ioapic_i8259 = { -1, -1 }; @@ -104,15 +108,17 @@ DEFINE_SPINLOCK(vector_lock); int nr_ioapic_registers[MAX_IO_APICS]; /* I/O APIC entries */ -struct mpc_config_ioapic mp_ioapics[MAX_IO_APICS]; +struct mp_config_ioapic mp_ioapics[MAX_IO_APICS]; int nr_ioapics; /* MP IRQ source entries */ -struct mpc_config_intsrc mp_irqs[MAX_IRQ_SOURCES]; +struct mp_config_intsrc mp_irqs[MAX_IRQ_SOURCES]; /* # of MP IRQ source entries */ int mp_irq_entries; +DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES); + /* * Rough estimation of how many shared IRQs there are, can * be changed anytime. @@ -140,7 +146,7 @@ struct io_apic { static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx) { return (void __iomem *) __fix_to_virt(FIX_IO_APIC_BASE_0 + idx) - + (mp_ioapics[idx].mpc_apicaddr & ~PAGE_MASK); + + (mp_ioapics[idx].mp_apicaddr & ~PAGE_MASK); } static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg) @@ -183,7 +189,7 @@ static bool io_apic_level_ack_pending(unsigned int irq) break; reg = io_apic_read(entry->apic, 0x10 + pin*2); /* Is the remote IRR bit set? */ - if ((reg >> 14) & 1) { + if (reg & IO_APIC_REDIR_REMOTE_IRR) { spin_unlock_irqrestore(&ioapic_lock, flags); return true; } @@ -298,7 +304,7 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, u8 vector) break; io_apic_write(apic, 0x11 + pin*2, dest); reg = io_apic_read(apic, 0x10 + pin*2); - reg &= ~0x000000ff; + reg &= ~IO_APIC_REDIR_VECTOR_MASK; reg |= vector; io_apic_modify(apic, reg); if (!entry->next) @@ -360,16 +366,37 @@ static void add_pin_to_irq(unsigned int irq, int apic, int pin) entry->pin = pin; } +/* + * Reroute an IRQ to a different pin. + */ +static void __init replace_pin_at_irq(unsigned int irq, + int oldapic, int oldpin, + int newapic, int newpin) +{ + struct irq_pin_list *entry = irq_2_pin + irq; + + while (1) { + if (entry->apic == oldapic && entry->pin == oldpin) { + entry->apic = newapic; + entry->pin = newpin; + } + if (!entry->next) + break; + entry = irq_2_pin + entry->next; + } +} + #define DO_ACTION(name,R,ACTION, FINAL) \ \ static void name##_IO_APIC_irq (unsigned int irq) \ __DO_ACTION(R, ACTION, FINAL) -DO_ACTION( __mask, 0, |= 0x00010000, io_apic_sync(entry->apic) ) - /* mask = 1 */ -DO_ACTION( __unmask, 0, &= 0xfffeffff, ) - /* mask = 0 */ +/* mask = 1 */ +DO_ACTION(__mask, 0, |= IO_APIC_REDIR_MASKED, io_apic_sync(entry->apic)) + +/* mask = 0 */ +DO_ACTION(__unmask, 0, &= ~IO_APIC_REDIR_MASKED, ) static void mask_IO_APIC_irq (unsigned int irq) { @@ -430,20 +457,6 @@ static int __init disable_timer_pin_setup(char *arg) } __setup("disable_timer_pin_1", disable_timer_pin_setup); -static int __init setup_disable_8254_timer(char *s) -{ - timer_over_8254 = -1; - return 1; -} -static int __init setup_enable_8254_timer(char *s) -{ - timer_over_8254 = 2; - return 1; -} - -__setup("disable_8254_timer", setup_disable_8254_timer); -__setup("enable_8254_timer", setup_enable_8254_timer); - /* * Find the IRQ entry number of a certain pin. @@ -453,10 +466,10 @@ static int find_irq_entry(int apic, int pin, int type) int i; for (i = 0; i < mp_irq_entries; i++) - if (mp_irqs[i].mpc_irqtype == type && - (mp_irqs[i].mpc_dstapic == mp_ioapics[apic].mpc_apicid || - mp_irqs[i].mpc_dstapic == MP_APIC_ALL) && - mp_irqs[i].mpc_dstirq == pin) + if (mp_irqs[i].mp_irqtype == type && + (mp_irqs[i].mp_dstapic == mp_ioapics[apic].mp_apicid || + mp_irqs[i].mp_dstapic == MP_APIC_ALL) && + mp_irqs[i].mp_dstirq == pin) return i; return -1; @@ -470,13 +483,13 @@ static int __init find_isa_irq_pin(int irq, int type) int i; for (i = 0; i < mp_irq_entries; i++) { - int lbus = mp_irqs[i].mpc_srcbus; + int lbus = mp_irqs[i].mp_srcbus; if (test_bit(lbus, mp_bus_not_pci) && - (mp_irqs[i].mpc_irqtype == type) && - (mp_irqs[i].mpc_srcbusirq == irq)) + (mp_irqs[i].mp_irqtype == type) && + (mp_irqs[i].mp_srcbusirq == irq)) - return mp_irqs[i].mpc_dstirq; + return mp_irqs[i].mp_dstirq; } return -1; } @@ -486,17 +499,17 @@ static int __init find_isa_irq_apic(int irq, int type) int i; for (i = 0; i < mp_irq_entries; i++) { - int lbus = mp_irqs[i].mpc_srcbus; + int lbus = mp_irqs[i].mp_srcbus; if (test_bit(lbus, mp_bus_not_pci) && - (mp_irqs[i].mpc_irqtype == type) && - (mp_irqs[i].mpc_srcbusirq == irq)) + (mp_irqs[i].mp_irqtype == type) && + (mp_irqs[i].mp_srcbusirq == irq)) break; } if (i < mp_irq_entries) { int apic; for(apic = 0; apic < nr_ioapics; apic++) { - if (mp_ioapics[apic].mpc_apicid == mp_irqs[i].mpc_dstapic) + if (mp_ioapics[apic].mp_apicid == mp_irqs[i].mp_dstapic) return apic; } } @@ -516,28 +529,28 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin) apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n", bus, slot, pin); - if (mp_bus_id_to_pci_bus[bus] == -1) { + if (test_bit(bus, mp_bus_not_pci)) { apic_printk(APIC_VERBOSE, "PCI BIOS passed nonexistent PCI bus %d!\n", bus); return -1; } for (i = 0; i < mp_irq_entries; i++) { - int lbus = mp_irqs[i].mpc_srcbus; + int lbus = mp_irqs[i].mp_srcbus; for (apic = 0; apic < nr_ioapics; apic++) - if (mp_ioapics[apic].mpc_apicid == mp_irqs[i].mpc_dstapic || - mp_irqs[i].mpc_dstapic == MP_APIC_ALL) + if (mp_ioapics[apic].mp_apicid == mp_irqs[i].mp_dstapic || + mp_irqs[i].mp_dstapic == MP_APIC_ALL) break; if (!test_bit(lbus, mp_bus_not_pci) && - !mp_irqs[i].mpc_irqtype && + !mp_irqs[i].mp_irqtype && (bus == lbus) && - (slot == ((mp_irqs[i].mpc_srcbusirq >> 2) & 0x1f))) { - int irq = pin_2_irq(i,apic,mp_irqs[i].mpc_dstirq); + (slot == ((mp_irqs[i].mp_srcbusirq >> 2) & 0x1f))) { + int irq = pin_2_irq(i,apic,mp_irqs[i].mp_dstirq); if (!(apic || IO_APIC_IRQ(irq))) continue; - if (pin == (mp_irqs[i].mpc_srcbusirq & 3)) + if (pin == (mp_irqs[i].mp_srcbusirq & 3)) return irq; /* * Use the first all-but-pin matching entry as a @@ -565,13 +578,13 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin) static int MPBIOS_polarity(int idx) { - int bus = mp_irqs[idx].mpc_srcbus; + int bus = mp_irqs[idx].mp_srcbus; int polarity; /* * Determine IRQ line polarity (high active or low active): */ - switch (mp_irqs[idx].mpc_irqflag & 3) + switch (mp_irqs[idx].mp_irqflag & 3) { case 0: /* conforms, ie. bus-type dependent polarity */ if (test_bit(bus, mp_bus_not_pci)) @@ -607,13 +620,13 @@ static int MPBIOS_polarity(int idx) static int MPBIOS_trigger(int idx) { - int bus = mp_irqs[idx].mpc_srcbus; + int bus = mp_irqs[idx].mp_srcbus; int trigger; /* * Determine IRQ trigger mode (edge or level sensitive): */ - switch ((mp_irqs[idx].mpc_irqflag>>2) & 3) + switch ((mp_irqs[idx].mp_irqflag>>2) & 3) { case 0: /* conforms, ie. bus-type dependent */ if (test_bit(bus, mp_bus_not_pci)) @@ -660,16 +673,16 @@ static inline int irq_trigger(int idx) static int pin_2_irq(int idx, int apic, int pin) { int irq, i; - int bus = mp_irqs[idx].mpc_srcbus; + int bus = mp_irqs[idx].mp_srcbus; /* * Debugging check, we are in big trouble if this message pops up! */ - if (mp_irqs[idx].mpc_dstirq != pin) + if (mp_irqs[idx].mp_dstirq != pin) printk(KERN_ERR "broken BIOS or MPTABLE parser, ayiee!!\n"); if (test_bit(bus, mp_bus_not_pci)) { - irq = mp_irqs[idx].mpc_srcbusirq; + irq = mp_irqs[idx].mp_srcbusirq; } else { /* * PCI IRQs are mapped in order @@ -730,7 +743,7 @@ static int __assign_irq_vector(int irq, cpumask_t mask) offset = current_offset; next: vector += 8; - if (vector >= FIRST_SYSTEM_VECTOR) { + if (vector >= first_system_vector) { /* If we run out of vectors on large boxen, must share them. */ offset = (offset + 1) % 8; vector = FIRST_DEVICE_VECTOR + offset; @@ -788,7 +801,7 @@ static void __clear_irq_vector(int irq) cpus_clear(cfg->domain); } -void __setup_vector_irq(int cpu) +static void __setup_vector_irq(int cpu) { /* Initialize vector_irq on a new cpu */ /* This function must be called with vector_lock held */ @@ -811,6 +824,13 @@ void __setup_vector_irq(int cpu) } } +void setup_vector_irq(int cpu) +{ + spin_lock(&vector_lock); + __setup_vector_irq(smp_processor_id()); + spin_unlock(&vector_lock); +} + static struct irq_chip ioapic_chip; @@ -846,7 +866,7 @@ static void setup_IO_APIC_irq(int apic, int pin, unsigned int irq, apic_printk(APIC_VERBOSE,KERN_DEBUG "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> " "IRQ %d Mode:%i Active:%i)\n", - apic, mp_ioapics[apic].mpc_apicid, pin, cfg->vector, + apic, mp_ioapics[apic].mp_apicid, pin, cfg->vector, irq, trigger, polarity); /* @@ -887,10 +907,10 @@ static void __init setup_IO_APIC_irqs(void) idx = find_irq_entry(apic,pin,mp_INT); if (idx == -1) { if (first_notcon) { - apic_printk(APIC_VERBOSE, KERN_DEBUG " IO-APIC (apicid-pin) %d-%d", mp_ioapics[apic].mpc_apicid, pin); + apic_printk(APIC_VERBOSE, KERN_DEBUG " IO-APIC (apicid-pin) %d-%d", mp_ioapics[apic].mp_apicid, pin); first_notcon = 0; } else - apic_printk(APIC_VERBOSE, ", %d-%d", mp_ioapics[apic].mpc_apicid, pin); + apic_printk(APIC_VERBOSE, ", %d-%d", mp_ioapics[apic].mp_apicid, pin); continue; } if (!first_notcon) { @@ -911,26 +931,21 @@ static void __init setup_IO_APIC_irqs(void) } /* - * Set up the 8259A-master output pin as broadcast to all - * CPUs. + * Set up the timer pin, possibly with the 8259A-master behind. */ -static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, int vector) +static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin, + int vector) { struct IO_APIC_route_entry entry; memset(&entry, 0, sizeof(entry)); - disable_8259A_irq(0); - - /* mask LVT0 */ - apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT); - /* * We use logical delivery to get the timer IRQ * to the first CPU. */ entry.dest_mode = INT_DEST_MODE; - entry.mask = 0; /* unmask IRQ now */ + entry.mask = 1; /* mask IRQ now */ entry.dest = cpu_mask_to_apicid(TARGET_CPUS); entry.delivery_mode = INT_DELIVERY_MODE; entry.polarity = 0; @@ -939,7 +954,7 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in /* * The timer IRQ doesn't have to know that behind the - * scene we have a 8259A-master in AEOI mode ... + * scene we may have a 8259A-master in AEOI mode ... */ set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge"); @@ -947,8 +962,6 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in * Add it to the IO-APIC irq-routing table: */ ioapic_write_entry(apic, pin, entry); - - enable_8259A_irq(0); } void __apicdebuginit print_IO_APIC(void) @@ -965,7 +978,7 @@ void __apicdebuginit print_IO_APIC(void) printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries); for (i = 0; i < nr_ioapics; i++) printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n", - mp_ioapics[i].mpc_apicid, nr_ioapic_registers[i]); + mp_ioapics[i].mp_apicid, nr_ioapic_registers[i]); /* * We are a bit conservative about what we expect. We have to @@ -983,7 +996,7 @@ void __apicdebuginit print_IO_APIC(void) spin_unlock_irqrestore(&ioapic_lock, flags); printk("\n"); - printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mpc_apicid); + printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mp_apicid); printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw); printk(KERN_DEBUG "....... : physical APIC id: %02X\n", reg_00.bits.ID); @@ -1077,6 +1090,7 @@ void __apicdebuginit print_local_APIC(void * dummy) printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n", smp_processor_id(), hard_smp_processor_id()); + v = apic_read(APIC_ID); printk(KERN_INFO "... APIC ID: %08x (%01x)\n", v, GET_APIC_ID(read_apic_id())); v = apic_read(APIC_LVR); printk(KERN_INFO "... APIC VERSION: %08x\n", v); @@ -1146,7 +1160,7 @@ void __apicdebuginit print_local_APIC(void * dummy) void print_all_local_APICs (void) { - on_each_cpu(print_local_APIC, NULL, 1, 1); + on_each_cpu(print_local_APIC, NULL, 1); } void __apicdebuginit print_PIC(void) @@ -1540,7 +1554,7 @@ static inline void init_IO_APIC_traps(void) } } -static void enable_lapic_irq (unsigned int irq) +static void unmask_lapic_irq(unsigned int irq) { unsigned long v; @@ -1548,7 +1562,7 @@ static void enable_lapic_irq (unsigned int irq) apic_write(APIC_LVT0, v & ~APIC_LVT_MASKED); } -static void disable_lapic_irq (unsigned int irq) +static void mask_lapic_irq(unsigned int irq) { unsigned long v; @@ -1561,19 +1575,20 @@ static void ack_lapic_irq (unsigned int irq) ack_APIC_irq(); } -static void end_lapic_irq (unsigned int i) { /* nothing */ } - -static struct hw_interrupt_type lapic_irq_type __read_mostly = { - .name = "local-APIC", - .typename = "local-APIC-edge", - .startup = NULL, /* startup_irq() not used for IRQ0 */ - .shutdown = NULL, /* shutdown_irq() not used for IRQ0 */ - .enable = enable_lapic_irq, - .disable = disable_lapic_irq, - .ack = ack_lapic_irq, - .end = end_lapic_irq, +static struct irq_chip lapic_chip __read_mostly = { + .name = "local-APIC", + .mask = mask_lapic_irq, + .unmask = unmask_lapic_irq, + .ack = ack_lapic_irq, }; +static void lapic_register_intr(int irq) +{ + irq_desc[irq].status &= ~IRQ_LEVEL; + set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq, + "edge"); +} + static void __init setup_nmi(void) { /* @@ -1659,6 +1674,7 @@ static inline void __init check_timer(void) struct irq_cfg *cfg = irq_cfg + 0; int apic1, pin1, apic2, pin2; unsigned long flags; + int no_pin1 = 0; local_irq_save(flags); @@ -1669,16 +1685,11 @@ static inline void __init check_timer(void) assign_irq_vector(0, TARGET_CPUS); /* - * Subtle, code in do_timer_interrupt() expects an AEOI - * mode for the 8259A whenever interrupts are routed - * through I/O APICs. Also IRQ0 has to be enabled in - * the 8259A which implies the virtual wire has to be - * disabled in the local APIC. + * As IRQ0 is to be enabled in the 8259A, the virtual + * wire has to be disabled in the local APIC. */ apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT); init_8259A(1); - if (timer_over_8254 > 0) - enable_8259A_irq(0); pin1 = find_isa_irq_pin(0, mp_INT); apic1 = find_isa_irq_apic(0, mp_INT); @@ -1688,15 +1699,33 @@ static inline void __init check_timer(void) apic_printk(APIC_VERBOSE,KERN_INFO "..TIMER: vector=0x%02X apic1=%d pin1=%d apic2=%d pin2=%d\n", cfg->vector, apic1, pin1, apic2, pin2); + /* + * Some BIOS writers are clueless and report the ExtINTA + * I/O APIC input from the cascaded 8259A as the timer + * interrupt input. So just in case, if only one pin + * was found above, try it both directly and through the + * 8259A. + */ + if (pin1 == -1) { + pin1 = pin2; + apic1 = apic2; + no_pin1 = 1; + } else if (pin2 == -1) { + pin2 = pin1; + apic2 = apic1; + } + if (pin1 != -1) { /* * Ok, does IRQ0 through the IOAPIC work? */ + if (no_pin1) { + add_pin_to_irq(0, apic1, pin1); + setup_timer_IRQ0_pin(apic1, pin1, cfg->vector); + } unmask_IO_APIC_irq(0); if (!no_timer_check && timer_irq_works()) { - nmi_watchdog_default(); if (nmi_watchdog == NMI_IO_APIC) { - disable_8259A_irq(0); setup_nmi(); enable_8259A_irq(0); } @@ -1705,43 +1734,48 @@ static inline void __init check_timer(void) goto out; } clear_IO_APIC_pin(apic1, pin1); - apic_printk(APIC_QUIET,KERN_ERR "..MP-BIOS bug: 8254 timer not " - "connected to IO-APIC\n"); - } + if (!no_pin1) + apic_printk(APIC_QUIET,KERN_ERR "..MP-BIOS bug: " + "8254 timer not connected to IO-APIC\n"); - apic_printk(APIC_VERBOSE,KERN_INFO "...trying to set up timer (IRQ0) " - "through the 8259A ... "); - if (pin2 != -1) { + apic_printk(APIC_VERBOSE,KERN_INFO + "...trying to set up timer (IRQ0) " + "through the 8259A ... "); apic_printk(APIC_VERBOSE,"\n..... (found apic %d pin %d) ...", apic2, pin2); /* * legacy devices should be connected to IO APIC #0 */ - setup_ExtINT_IRQ0_pin(apic2, pin2, cfg->vector); + replace_pin_at_irq(0, apic1, pin1, apic2, pin2); + setup_timer_IRQ0_pin(apic2, pin2, cfg->vector); + unmask_IO_APIC_irq(0); + enable_8259A_irq(0); if (timer_irq_works()) { apic_printk(APIC_VERBOSE," works.\n"); - nmi_watchdog_default(); + timer_through_8259 = 1; if (nmi_watchdog == NMI_IO_APIC) { + disable_8259A_irq(0); setup_nmi(); + enable_8259A_irq(0); } goto out; } /* * Cleanup, just in case ... */ + disable_8259A_irq(0); clear_IO_APIC_pin(apic2, pin2); + apic_printk(APIC_VERBOSE," failed.\n"); } - apic_printk(APIC_VERBOSE," failed.\n"); if (nmi_watchdog == NMI_IO_APIC) { printk(KERN_WARNING "timer doesn't work through the IO-APIC - disabling NMI Watchdog!\n"); - nmi_watchdog = 0; + nmi_watchdog = NMI_NONE; } apic_printk(APIC_VERBOSE, KERN_INFO "...trying to set up timer as Virtual Wire IRQ..."); - disable_8259A_irq(0); - irq_desc[0].chip = &lapic_irq_type; + lapic_register_intr(0); apic_write(APIC_LVT0, APIC_DM_FIXED | cfg->vector); /* Fixed mode */ enable_8259A_irq(0); @@ -1749,6 +1783,7 @@ static inline void __init check_timer(void) apic_printk(APIC_VERBOSE," works.\n"); goto out; } + disable_8259A_irq(0); apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | cfg->vector); apic_printk(APIC_VERBOSE," failed.\n"); @@ -1778,11 +1813,21 @@ static int __init notimercheck(char *s) __setup("no_timer_check", notimercheck); /* - * - * IRQs that are handled by the PIC in the MPS IOAPIC case. - * - IRQ2 is the cascade IRQ, and cannot be a io-apic IRQ. - * Linux doesn't really care, as it's not actually used - * for any interrupt handling anyway. + * Traditionally ISA IRQ2 is the cascade IRQ, and is not available + * to devices. However there may be an I/O APIC pin available for + * this interrupt regardless. The pin may be left unconnected, but + * typically it will be reused as an ExtINT cascade interrupt for + * the master 8259A. In the MPS case such a pin will normally be + * reported as an ExtINT interrupt in the MP table. With ACPI + * there is no provision for ExtINT interrupts, and in the absence + * of an override it would be treated as an ordinary ISA I/O APIC + * interrupt, that is edge-triggered and unmasked by default. We + * used to do this, but it caused problems on some systems because + * of the NMI watchdog and sometimes IRQ0 of the 8254 timer using + * the same ExtINT cascade interrupt to drive the local APIC of the + * bootstrap processor. Therefore we refrain from routing IRQ2 to + * the I/O APIC in all cases now. No actual device should request + * it anyway. --macro */ #define PIC_IRQS (1<<2) @@ -1793,10 +1838,7 @@ void __init setup_IO_APIC(void) * calling enable_IO_APIC() is moved to setup_local_APIC for BP */ - if (acpi_ioapic) - io_apic_irqs = ~0; /* all IRQs go through IOAPIC */ - else - io_apic_irqs = ~PIC_IRQS; + io_apic_irqs = ~PIC_IRQS; apic_printk(APIC_VERBOSE, "ENABLING IO-APIC IRQs\n"); @@ -1841,8 +1883,8 @@ static int ioapic_resume(struct sys_device *dev) spin_lock_irqsave(&ioapic_lock, flags); reg_00.raw = io_apic_read(dev->id, 0); - if (reg_00.bits.ID != mp_ioapics[dev->id].mpc_apicid) { - reg_00.bits.ID = mp_ioapics[dev->id].mpc_apicid; + if (reg_00.bits.ID != mp_ioapics[dev->id].mp_apicid) { + reg_00.bits.ID = mp_ioapics[dev->id].mp_apicid; io_apic_write(dev->id, 0, reg_00.raw); } spin_unlock_irqrestore(&ioapic_lock, flags); @@ -2242,8 +2284,8 @@ int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity) return -1; for (i = 0; i < mp_irq_entries; i++) - if (mp_irqs[i].mpc_irqtype == mp_INT && - mp_irqs[i].mpc_srcbusirq == bus_irq) + if (mp_irqs[i].mp_irqtype == mp_INT && + mp_irqs[i].mp_srcbusirq == bus_irq) break; if (i >= mp_irq_entries) return -1; @@ -2336,7 +2378,7 @@ void __init ioapic_init_mappings(void) ioapic_res = ioapic_setup_resources(); for (i = 0; i < nr_ioapics; i++) { if (smp_found_config) { - ioapic_phys = mp_ioapics[i].mpc_apicaddr; + ioapic_phys = mp_ioapics[i].mp_apicaddr; } else { ioapic_phys = (unsigned long) alloc_bootmem_pages(PAGE_SIZE); diff --git a/arch/x86/kernel/ipi.c b/arch/x86/kernel/ipi.c index c0df7b89ca23..9d98cda39ad9 100644 --- a/arch/x86/kernel/ipi.c +++ b/arch/x86/kernel/ipi.c @@ -8,7 +8,6 @@ #include <linux/kernel_stat.h> #include <linux/mc146818rtc.h> #include <linux/cache.h> -#include <linux/interrupt.h> #include <linux/cpu.h> #include <linux/module.h> diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 147352df28b9..47a6f6f12478 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -48,6 +48,29 @@ void ack_bad_irq(unsigned int irq) #endif } +#ifdef CONFIG_DEBUG_STACKOVERFLOW +/* Debugging check for stack overflow: is there less than 1KB free? */ +static int check_stack_overflow(void) +{ + long sp; + + __asm__ __volatile__("andl %%esp,%0" : + "=r" (sp) : "0" (THREAD_SIZE - 1)); + + return sp < (sizeof(struct thread_info) + STACK_WARN); +} + +static void print_stack_overflow(void) +{ + printk(KERN_WARNING "low stack detected by irq handler\n"); + dump_stack(); +} + +#else +static inline int check_stack_overflow(void) { return 0; } +static inline void print_stack_overflow(void) { } +#endif + #ifdef CONFIG_4KSTACKS /* * per-CPU IRQ handling contexts (thread information and stack) @@ -59,48 +82,29 @@ union irq_ctx { static union irq_ctx *hardirq_ctx[NR_CPUS] __read_mostly; static union irq_ctx *softirq_ctx[NR_CPUS] __read_mostly; -#endif -/* - * do_IRQ handles all normal device IRQ's (the special - * SMP cross-CPU interrupts have their own specific - * handlers). - */ -unsigned int do_IRQ(struct pt_regs *regs) -{ - struct pt_regs *old_regs; - /* high bit used in ret_from_ code */ - int irq = ~regs->orig_ax; - struct irq_desc *desc = irq_desc + irq; -#ifdef CONFIG_4KSTACKS - union irq_ctx *curctx, *irqctx; - u32 *isp; -#endif +static char softirq_stack[NR_CPUS * THREAD_SIZE] + __attribute__((__section__(".bss.page_aligned"))); - if (unlikely((unsigned)irq >= NR_IRQS)) { - printk(KERN_EMERG "%s: cannot handle IRQ %d\n", - __func__, irq); - BUG(); - } +static char hardirq_stack[NR_CPUS * THREAD_SIZE] + __attribute__((__section__(".bss.page_aligned"))); - old_regs = set_irq_regs(regs); - irq_enter(); -#ifdef CONFIG_DEBUG_STACKOVERFLOW - /* Debugging check for stack overflow: is there less than 1KB free? */ - { - long sp; - - __asm__ __volatile__("andl %%esp,%0" : - "=r" (sp) : "0" (THREAD_SIZE - 1)); - if (unlikely(sp < (sizeof(struct thread_info) + STACK_WARN))) { - printk("do_IRQ: stack overflow: %ld\n", - sp - sizeof(struct thread_info)); - dump_stack(); - } - } -#endif +static void call_on_stack(void *func, void *stack) +{ + asm volatile("xchgl %%ebx,%%esp \n" + "call *%%edi \n" + "movl %%ebx,%%esp \n" + : "=b" (stack) + : "0" (stack), + "D"(func) + : "memory", "cc", "edx", "ecx", "eax"); +} -#ifdef CONFIG_4KSTACKS +static inline int +execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) +{ + union irq_ctx *curctx, *irqctx; + u32 *isp, arg1, arg2; curctx = (union irq_ctx *) current_thread_info(); irqctx = hardirq_ctx[smp_processor_id()]; @@ -111,52 +115,39 @@ unsigned int do_IRQ(struct pt_regs *regs) * handler) we can't do that and just have to keep using the * current stack (which is the irq stack already after all) */ - if (curctx != irqctx) { - int arg1, arg2, bx; - - /* build the stack frame on the IRQ stack */ - isp = (u32*) ((char*)irqctx + sizeof(*irqctx)); - irqctx->tinfo.task = curctx->tinfo.task; - irqctx->tinfo.previous_esp = current_stack_pointer; + if (unlikely(curctx == irqctx)) + return 0; - /* - * Copy the softirq bits in preempt_count so that the - * softirq checks work in the hardirq context. - */ - irqctx->tinfo.preempt_count = - (irqctx->tinfo.preempt_count & ~SOFTIRQ_MASK) | - (curctx->tinfo.preempt_count & SOFTIRQ_MASK); - - asm volatile( - " xchgl %%ebx,%%esp \n" - " call *%%edi \n" - " movl %%ebx,%%esp \n" - : "=a" (arg1), "=d" (arg2), "=b" (bx) - : "0" (irq), "1" (desc), "2" (isp), - "D" (desc->handle_irq) - : "memory", "cc", "ecx" - ); - } else -#endif - desc->handle_irq(irq, desc); + /* build the stack frame on the IRQ stack */ + isp = (u32 *) ((char*)irqctx + sizeof(*irqctx)); + irqctx->tinfo.task = curctx->tinfo.task; + irqctx->tinfo.previous_esp = current_stack_pointer; - irq_exit(); - set_irq_regs(old_regs); + /* + * Copy the softirq bits in preempt_count so that the + * softirq checks work in the hardirq context. + */ + irqctx->tinfo.preempt_count = + (irqctx->tinfo.preempt_count & ~SOFTIRQ_MASK) | + (curctx->tinfo.preempt_count & SOFTIRQ_MASK); + + if (unlikely(overflow)) + call_on_stack(print_stack_overflow, isp); + + asm volatile("xchgl %%ebx,%%esp \n" + "call *%%edi \n" + "movl %%ebx,%%esp \n" + : "=a" (arg1), "=d" (arg2), "=b" (isp) + : "0" (irq), "1" (desc), "2" (isp), + "D" (desc->handle_irq) + : "memory", "cc", "ecx"); return 1; } -#ifdef CONFIG_4KSTACKS - -static char softirq_stack[NR_CPUS * THREAD_SIZE] - __attribute__((__section__(".bss.page_aligned"))); - -static char hardirq_stack[NR_CPUS * THREAD_SIZE] - __attribute__((__section__(".bss.page_aligned"))); - /* * allocate per-cpu stacks for hardirq and for softirq processing */ -void irq_ctx_init(int cpu) +void __cpuinit irq_ctx_init(int cpu) { union irq_ctx *irqctx; @@ -164,25 +155,25 @@ void irq_ctx_init(int cpu) return; irqctx = (union irq_ctx*) &hardirq_stack[cpu*THREAD_SIZE]; - irqctx->tinfo.task = NULL; - irqctx->tinfo.exec_domain = NULL; - irqctx->tinfo.cpu = cpu; - irqctx->tinfo.preempt_count = HARDIRQ_OFFSET; - irqctx->tinfo.addr_limit = MAKE_MM_SEG(0); + irqctx->tinfo.task = NULL; + irqctx->tinfo.exec_domain = NULL; + irqctx->tinfo.cpu = cpu; + irqctx->tinfo.preempt_count = HARDIRQ_OFFSET; + irqctx->tinfo.addr_limit = MAKE_MM_SEG(0); hardirq_ctx[cpu] = irqctx; irqctx = (union irq_ctx*) &softirq_stack[cpu*THREAD_SIZE]; - irqctx->tinfo.task = NULL; - irqctx->tinfo.exec_domain = NULL; - irqctx->tinfo.cpu = cpu; - irqctx->tinfo.preempt_count = 0; - irqctx->tinfo.addr_limit = MAKE_MM_SEG(0); + irqctx->tinfo.task = NULL; + irqctx->tinfo.exec_domain = NULL; + irqctx->tinfo.cpu = cpu; + irqctx->tinfo.preempt_count = 0; + irqctx->tinfo.addr_limit = MAKE_MM_SEG(0); softirq_ctx[cpu] = irqctx; - printk("CPU %u irqstacks, hard=%p soft=%p\n", - cpu,hardirq_ctx[cpu],softirq_ctx[cpu]); + printk(KERN_DEBUG "CPU %u irqstacks, hard=%p soft=%p\n", + cpu,hardirq_ctx[cpu],softirq_ctx[cpu]); } void irq_ctx_exit(int cpu) @@ -211,25 +202,56 @@ asmlinkage void do_softirq(void) /* build the stack frame on the softirq stack */ isp = (u32*) ((char*)irqctx + sizeof(*irqctx)); - asm volatile( - " xchgl %%ebx,%%esp \n" - " call __do_softirq \n" - " movl %%ebx,%%esp \n" - : "=b"(isp) - : "0"(isp) - : "memory", "cc", "edx", "ecx", "eax" - ); + call_on_stack(__do_softirq, isp); /* * Shouldnt happen, we returned above if in_interrupt(): - */ + */ WARN_ON_ONCE(softirq_count()); } local_irq_restore(flags); } + +#else +static inline int +execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) { return 0; } #endif /* + * do_IRQ handles all normal device IRQ's (the special + * SMP cross-CPU interrupts have their own specific + * handlers). + */ +unsigned int do_IRQ(struct pt_regs *regs) +{ + struct pt_regs *old_regs; + /* high bit used in ret_from_ code */ + int overflow, irq = ~regs->orig_ax; + struct irq_desc *desc = irq_desc + irq; + + if (unlikely((unsigned)irq >= NR_IRQS)) { + printk(KERN_EMERG "%s: cannot handle IRQ %d\n", + __func__, irq); + BUG(); + } + + old_regs = set_irq_regs(regs); + irq_enter(); + + overflow = check_stack_overflow(); + + if (!execute_on_irq_stack(overflow, desc, irq)) { + if (unlikely(overflow)) + print_stack_overflow(); + desc->handle_irq(irq, desc); + } + + irq_exit(); + set_irq_regs(old_regs); + return 1; +} + +/* * Interrupt statistics: */ @@ -313,16 +335,20 @@ skip: per_cpu(irq_stat,j).irq_tlb_count); seq_printf(p, " TLB shootdowns\n"); #endif +#ifdef CONFIG_X86_MCE seq_printf(p, "TRM: "); for_each_online_cpu(j) seq_printf(p, "%10u ", per_cpu(irq_stat,j).irq_thermal_count); seq_printf(p, " Thermal event interrupts\n"); +#endif +#ifdef CONFIG_X86_LOCAL_APIC seq_printf(p, "SPU: "); for_each_online_cpu(j) seq_printf(p, "%10u ", per_cpu(irq_stat,j).irq_spurious_count); seq_printf(p, " Spurious interrupts\n"); +#endif seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count)); #if defined(CONFIG_X86_IO_APIC) seq_printf(p, "MIS: %10u\n", atomic_read(&irq_mis_count)); @@ -331,6 +357,40 @@ skip: return 0; } +/* + * /proc/stat helpers + */ +u64 arch_irq_stat_cpu(unsigned int cpu) +{ + u64 sum = nmi_count(cpu); + +#ifdef CONFIG_X86_LOCAL_APIC + sum += per_cpu(irq_stat, cpu).apic_timer_irqs; +#endif +#ifdef CONFIG_SMP + sum += per_cpu(irq_stat, cpu).irq_resched_count; + sum += per_cpu(irq_stat, cpu).irq_call_count; + sum += per_cpu(irq_stat, cpu).irq_tlb_count; +#endif +#ifdef CONFIG_X86_MCE + sum += per_cpu(irq_stat, cpu).irq_thermal_count; +#endif +#ifdef CONFIG_X86_LOCAL_APIC + sum += per_cpu(irq_stat, cpu).irq_spurious_count; +#endif + return sum; +} + +u64 arch_irq_stat(void) +{ + u64 sum = atomic_read(&irq_err_count); + +#ifdef CONFIG_X86_IO_APIC + sum += atomic_read(&irq_mis_count); +#endif + return sum; +} + #ifdef CONFIG_HOTPLUG_CPU #include <mach_apic.h> diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 3aac15466a91..1f78b238d8d2 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -135,6 +135,7 @@ skip: seq_printf(p, "%10u ", cpu_pda(j)->irq_tlb_count); seq_printf(p, " TLB shootdowns\n"); #endif +#ifdef CONFIG_X86_MCE seq_printf(p, "TRM: "); for_each_online_cpu(j) seq_printf(p, "%10u ", cpu_pda(j)->irq_thermal_count); @@ -143,6 +144,7 @@ skip: for_each_online_cpu(j) seq_printf(p, "%10u ", cpu_pda(j)->irq_threshold_count); seq_printf(p, " Threshold APIC interrupts\n"); +#endif seq_printf(p, "SPU: "); for_each_online_cpu(j) seq_printf(p, "%10u ", cpu_pda(j)->irq_spurious_count); @@ -153,6 +155,32 @@ skip: } /* + * /proc/stat helpers + */ +u64 arch_irq_stat_cpu(unsigned int cpu) +{ + u64 sum = cpu_pda(cpu)->__nmi_count; + + sum += cpu_pda(cpu)->apic_timer_irqs; +#ifdef CONFIG_SMP + sum += cpu_pda(cpu)->irq_resched_count; + sum += cpu_pda(cpu)->irq_call_count; + sum += cpu_pda(cpu)->irq_tlb_count; +#endif +#ifdef CONFIG_X86_MCE + sum += cpu_pda(cpu)->irq_thermal_count; + sum += cpu_pda(cpu)->irq_threshold_count; +#endif + sum += cpu_pda(cpu)->irq_spurious_count; + return sum; +} + +u64 arch_irq_stat(void) +{ + return atomic_read(&irq_err_count); +} + +/* * do_IRQ handles all normal device IRQ's (the special * SMP cross-CPU interrupts have their own specific * handlers). diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit_32.c new file mode 100644 index 000000000000..d66914287ee1 --- /dev/null +++ b/arch/x86/kernel/irqinit_32.c @@ -0,0 +1,114 @@ +#include <linux/errno.h> +#include <linux/signal.h> +#include <linux/sched.h> +#include <linux/ioport.h> +#include <linux/interrupt.h> +#include <linux/slab.h> +#include <linux/random.h> +#include <linux/init.h> +#include <linux/kernel_stat.h> +#include <linux/sysdev.h> +#include <linux/bitops.h> + +#include <asm/atomic.h> +#include <asm/system.h> +#include <asm/io.h> +#include <asm/timer.h> +#include <asm/pgtable.h> +#include <asm/delay.h> +#include <asm/desc.h> +#include <asm/apic.h> +#include <asm/arch_hooks.h> +#include <asm/i8259.h> + + + +/* + * Note that on a 486, we don't want to do a SIGFPE on an irq13 + * as the irq is unreliable, and exception 16 works correctly + * (ie as explained in the intel literature). On a 386, you + * can't use exception 16 due to bad IBM design, so we have to + * rely on the less exact irq13. + * + * Careful.. Not only is IRQ13 unreliable, but it is also + * leads to races. IBM designers who came up with it should + * be shot. + */ + + +static irqreturn_t math_error_irq(int cpl, void *dev_id) +{ + extern void math_error(void __user *); + outb(0,0xF0); + if (ignore_fpu_irq || !boot_cpu_data.hard_math) + return IRQ_NONE; + math_error((void __user *)get_irq_regs()->ip); + return IRQ_HANDLED; +} + +/* + * New motherboards sometimes make IRQ 13 be a PCI interrupt, + * so allow interrupt sharing. + */ +static struct irqaction fpu_irq = { + .handler = math_error_irq, + .mask = CPU_MASK_NONE, + .name = "fpu", +}; + +void __init init_ISA_irqs (void) +{ + int i; + +#ifdef CONFIG_X86_LOCAL_APIC + init_bsp_APIC(); +#endif + init_8259A(0); + + /* + * 16 old-style INTA-cycle interrupts: + */ + for (i = 0; i < 16; i++) { + set_irq_chip_and_handler_name(i, &i8259A_chip, + handle_level_irq, "XT"); + } +} + +/* Overridden in paravirt.c */ +void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ"))); + +void __init native_init_IRQ(void) +{ + int i; + + /* all the set up before the call gates are initialised */ + pre_intr_init_hook(); + + /* + * Cover the whole vector space, no vector can escape + * us. (some of these will be overridden and become + * 'special' SMP interrupts) + */ + for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) { + int vector = FIRST_EXTERNAL_VECTOR + i; + if (i >= NR_IRQS) + break; + /* SYSCALL_VECTOR was reserved in trap_init. */ + if (!test_bit(vector, used_vectors)) + set_intr_gate(vector, interrupt[i]); + } + + /* setup after call gates are initialised (usually add in + * the architecture specific gates) + */ + intr_init_hook(); + + /* + * External FPU? Set up irq13 if so, for + * original braindamaged IBM FERR coupling. + */ + if (boot_cpu_data.hard_math && !cpu_has_fpu) + setup_irq(FPU_IRQ, &fpu_irq); + + irq_ctx_init(smp_processor_id()); +} diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c new file mode 100644 index 000000000000..0373e88de95a --- /dev/null +++ b/arch/x86/kernel/irqinit_64.c @@ -0,0 +1,221 @@ +#include <linux/linkage.h> +#include <linux/errno.h> +#include <linux/signal.h> +#include <linux/sched.h> +#include <linux/ioport.h> +#include <linux/interrupt.h> +#include <linux/timex.h> +#include <linux/slab.h> +#include <linux/random.h> +#include <linux/init.h> +#include <linux/kernel_stat.h> +#include <linux/sysdev.h> +#include <linux/bitops.h> + +#include <asm/acpi.h> +#include <asm/atomic.h> +#include <asm/system.h> +#include <asm/io.h> +#include <asm/hw_irq.h> +#include <asm/pgtable.h> +#include <asm/delay.h> +#include <asm/desc.h> +#include <asm/apic.h> +#include <asm/i8259.h> + +/* + * Common place to define all x86 IRQ vectors + * + * This builds up the IRQ handler stubs using some ugly macros in irq.h + * + * These macros create the low-level assembly IRQ routines that save + * register context and call do_IRQ(). do_IRQ() then does all the + * operations that are needed to keep the AT (or SMP IOAPIC) + * interrupt-controller happy. + */ + +#define IRQ_NAME2(nr) nr##_interrupt(void) +#define IRQ_NAME(nr) IRQ_NAME2(IRQ##nr) + +/* + * SMP has a few special interrupts for IPI messages + */ + +#define BUILD_IRQ(nr) \ + asmlinkage void IRQ_NAME(nr); \ + asm("\n.p2align\n" \ + "IRQ" #nr "_interrupt:\n\t" \ + "push $~(" #nr ") ; " \ + "jmp common_interrupt"); + +#define BI(x,y) \ + BUILD_IRQ(x##y) + +#define BUILD_16_IRQS(x) \ + BI(x,0) BI(x,1) BI(x,2) BI(x,3) \ + BI(x,4) BI(x,5) BI(x,6) BI(x,7) \ + BI(x,8) BI(x,9) BI(x,a) BI(x,b) \ + BI(x,c) BI(x,d) BI(x,e) BI(x,f) + +/* + * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts: + * (these are usually mapped to vectors 0x30-0x3f) + */ + +/* + * The IO-APIC gives us many more interrupt sources. Most of these + * are unused but an SMP system is supposed to have enough memory ... + * sometimes (mostly wrt. hw bugs) we get corrupted vectors all + * across the spectrum, so we really want to be prepared to get all + * of these. Plus, more powerful systems might have more than 64 + * IO-APIC registers. + * + * (these are usually mapped into the 0x30-0xff vector range) + */ + BUILD_16_IRQS(0x2) BUILD_16_IRQS(0x3) +BUILD_16_IRQS(0x4) BUILD_16_IRQS(0x5) BUILD_16_IRQS(0x6) BUILD_16_IRQS(0x7) +BUILD_16_IRQS(0x8) BUILD_16_IRQS(0x9) BUILD_16_IRQS(0xa) BUILD_16_IRQS(0xb) +BUILD_16_IRQS(0xc) BUILD_16_IRQS(0xd) BUILD_16_IRQS(0xe) BUILD_16_IRQS(0xf) + +#undef BUILD_16_IRQS +#undef BI + + +#define IRQ(x,y) \ + IRQ##x##y##_interrupt + +#define IRQLIST_16(x) \ + IRQ(x,0), IRQ(x,1), IRQ(x,2), IRQ(x,3), \ + IRQ(x,4), IRQ(x,5), IRQ(x,6), IRQ(x,7), \ + IRQ(x,8), IRQ(x,9), IRQ(x,a), IRQ(x,b), \ + IRQ(x,c), IRQ(x,d), IRQ(x,e), IRQ(x,f) + +/* for the irq vectors */ +static void (*__initdata interrupt[NR_VECTORS - FIRST_EXTERNAL_VECTOR])(void) = { + IRQLIST_16(0x2), IRQLIST_16(0x3), + IRQLIST_16(0x4), IRQLIST_16(0x5), IRQLIST_16(0x6), IRQLIST_16(0x7), + IRQLIST_16(0x8), IRQLIST_16(0x9), IRQLIST_16(0xa), IRQLIST_16(0xb), + IRQLIST_16(0xc), IRQLIST_16(0xd), IRQLIST_16(0xe), IRQLIST_16(0xf) +}; + +#undef IRQ +#undef IRQLIST_16 + + + + +/* + * IRQ2 is cascade interrupt to second interrupt controller + */ + +static struct irqaction irq2 = { + .handler = no_action, + .mask = CPU_MASK_NONE, + .name = "cascade", +}; +DEFINE_PER_CPU(vector_irq_t, vector_irq) = { + [0 ... IRQ0_VECTOR - 1] = -1, + [IRQ0_VECTOR] = 0, + [IRQ1_VECTOR] = 1, + [IRQ2_VECTOR] = 2, + [IRQ3_VECTOR] = 3, + [IRQ4_VECTOR] = 4, + [IRQ5_VECTOR] = 5, + [IRQ6_VECTOR] = 6, + [IRQ7_VECTOR] = 7, + [IRQ8_VECTOR] = 8, + [IRQ9_VECTOR] = 9, + [IRQ10_VECTOR] = 10, + [IRQ11_VECTOR] = 11, + [IRQ12_VECTOR] = 12, + [IRQ13_VECTOR] = 13, + [IRQ14_VECTOR] = 14, + [IRQ15_VECTOR] = 15, + [IRQ15_VECTOR + 1 ... NR_VECTORS - 1] = -1 +}; + +static void __init init_ISA_irqs (void) +{ + int i; + + init_bsp_APIC(); + init_8259A(0); + + for (i = 0; i < NR_IRQS; i++) { + irq_desc[i].status = IRQ_DISABLED; + irq_desc[i].action = NULL; + irq_desc[i].depth = 1; + + if (i < 16) { + /* + * 16 old-style INTA-cycle interrupts: + */ + set_irq_chip_and_handler_name(i, &i8259A_chip, + handle_level_irq, "XT"); + } else { + /* + * 'high' PCI IRQs filled in on demand + */ + irq_desc[i].chip = &no_irq_chip; + } + } +} + +void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ"))); + +void __init native_init_IRQ(void) +{ + int i; + + init_ISA_irqs(); + /* + * Cover the whole vector space, no vector can escape + * us. (some of these will be overridden and become + * 'special' SMP interrupts) + */ + for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) { + int vector = FIRST_EXTERNAL_VECTOR + i; + if (vector != IA32_SYSCALL_VECTOR) + set_intr_gate(vector, interrupt[i]); + } + +#ifdef CONFIG_SMP + /* + * The reschedule interrupt is a CPU-to-CPU reschedule-helper + * IPI, driven by wakeup. + */ + alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt); + + /* IPIs for invalidation */ + alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0); + alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1); + alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2); + alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3); + alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4); + alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5); + alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6); + alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7); + + /* IPI for generic function call */ + alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt); + + /* IPI for generic single function call */ + alloc_intr_gate(CALL_FUNCTION_SINGLE_VECTOR, + call_function_single_interrupt); + + /* Low priority IPI to cleanup after moving an irq */ + set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt); +#endif + alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt); + alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt); + + /* self generated IPI for local APIC timer */ + alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt); + + /* IPI vectors for APIC spurious and error interrupts */ + alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt); + alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt); + + if (!acpi_ioapic) + setup_irq(2, &irq2); +} diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 08a30986d472..87edf1ceb1df 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -18,6 +18,7 @@ #include <linux/clocksource.h> #include <linux/kvm_para.h> +#include <asm/pvclock.h> #include <asm/arch_hooks.h> #include <asm/msr.h> #include <asm/apic.h> @@ -36,18 +37,9 @@ static int parse_no_kvmclock(char *arg) early_param("no-kvmclock", parse_no_kvmclock); /* The hypervisor will put information about time periodically here */ -static DEFINE_PER_CPU_SHARED_ALIGNED(struct kvm_vcpu_time_info, hv_clock); -#define get_clock(cpu, field) per_cpu(hv_clock, cpu).field +static DEFINE_PER_CPU_SHARED_ALIGNED(struct pvclock_vcpu_time_info, hv_clock); +static struct pvclock_wall_clock wall_clock; -static inline u64 kvm_get_delta(u64 last_tsc) -{ - int cpu = smp_processor_id(); - u64 delta = native_read_tsc() - last_tsc; - return (delta * get_clock(cpu, tsc_to_system_mul)) >> KVM_SCALE; -} - -static struct kvm_wall_clock wall_clock; -static cycle_t kvm_clock_read(void); /* * The wallclock is the time of day when we booted. Since then, some time may * have elapsed since the hypervisor wrote the data. So we try to account for @@ -55,64 +47,37 @@ static cycle_t kvm_clock_read(void); */ static unsigned long kvm_get_wallclock(void) { - u32 wc_sec, wc_nsec; - u64 delta; + struct pvclock_vcpu_time_info *vcpu_time; struct timespec ts; - int version, nsec; int low, high; low = (int)__pa(&wall_clock); high = ((u64)__pa(&wall_clock) >> 32); + native_write_msr(MSR_KVM_WALL_CLOCK, low, high); - delta = kvm_clock_read(); + vcpu_time = &get_cpu_var(hv_clock); + pvclock_read_wallclock(&wall_clock, vcpu_time, &ts); + put_cpu_var(hv_clock); - native_write_msr(MSR_KVM_WALL_CLOCK, low, high); - do { - version = wall_clock.wc_version; - rmb(); - wc_sec = wall_clock.wc_sec; - wc_nsec = wall_clock.wc_nsec; - rmb(); - } while ((wall_clock.wc_version != version) || (version & 1)); - - delta = kvm_clock_read() - delta; - delta += wc_nsec; - nsec = do_div(delta, NSEC_PER_SEC); - set_normalized_timespec(&ts, wc_sec + delta, nsec); - /* - * Of all mechanisms of time adjustment I've tested, this one - * was the champion! - */ - return ts.tv_sec + 1; + return ts.tv_sec; } static int kvm_set_wallclock(unsigned long now) { - return 0; + return -1; } -/* - * This is our read_clock function. The host puts an tsc timestamp each time - * it updates a new time. Without the tsc adjustment, we can have a situation - * in which a vcpu starts to run earlier (smaller system_time), but probes - * time later (compared to another vcpu), leading to backwards time - */ static cycle_t kvm_clock_read(void) { - u64 last_tsc, now; - int cpu; + struct pvclock_vcpu_time_info *src; + cycle_t ret; - preempt_disable(); - cpu = smp_processor_id(); - - last_tsc = get_clock(cpu, tsc_timestamp); - now = get_clock(cpu, system_time); - - now += kvm_get_delta(last_tsc); - preempt_enable(); - - return now; + src = &get_cpu_var(hv_clock); + ret = pvclock_clocksource_read(src); + put_cpu_var(hv_clock); + return ret; } + static struct clocksource kvm_clock = { .name = "kvm-clock", .read = kvm_clock_read, @@ -123,13 +88,14 @@ static struct clocksource kvm_clock = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; -static int kvm_register_clock(void) +static int kvm_register_clock(char *txt) { int cpu = smp_processor_id(); int low, high; low = (int)__pa(&per_cpu(hv_clock, cpu)) | 1; high = ((u64)__pa(&per_cpu(hv_clock, cpu)) >> 32); - + printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n", + cpu, high, low, txt); return native_write_msr_safe(MSR_KVM_SYSTEM_TIME, low, high); } @@ -140,12 +106,20 @@ static void kvm_setup_secondary_clock(void) * Now that the first cpu already had this clocksource initialized, * we shouldn't fail. */ - WARN_ON(kvm_register_clock()); + WARN_ON(kvm_register_clock("secondary cpu clock")); /* ok, done with our trickery, call native */ setup_secondary_APIC_clock(); } #endif +#ifdef CONFIG_SMP +void __init kvm_smp_prepare_boot_cpu(void) +{ + WARN_ON(kvm_register_clock("primary cpu clock")); + native_smp_prepare_boot_cpu(); +} +#endif + /* * After the clock is registered, the host will keep writing to the * registered memory location. If the guest happens to shutdown, this memory @@ -174,7 +148,7 @@ void __init kvmclock_init(void) return; if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) { - if (kvm_register_clock()) + if (kvm_register_clock("boot clock")) return; pv_time_ops.get_wallclock = kvm_get_wallclock; pv_time_ops.set_wallclock = kvm_set_wallclock; @@ -182,6 +156,9 @@ void __init kvmclock_init(void) #ifdef CONFIG_X86_LOCAL_APIC pv_apic_ops.setup_secondary_clock = kvm_setup_secondary_clock; #endif +#ifdef CONFIG_SMP + smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; +#endif machine_ops.shutdown = kvm_shutdown; #ifdef CONFIG_KEXEC machine_ops.crash_shutdown = kvm_crash_shutdown; diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index 0224c3637c73..a8449571858a 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -20,9 +20,9 @@ #include <asm/mmu_context.h> #ifdef CONFIG_SMP -static void flush_ldt(void *null) +static void flush_ldt(void *current_mm) { - if (current->active_mm) + if (current->active_mm == current_mm) load_LDT(¤t->active_mm->context); } #endif @@ -68,7 +68,7 @@ static int alloc_ldt(mm_context_t *pc, int mincount, int reload) load_LDT(pc); mask = cpumask_of_cpu(smp_processor_id()); if (!cpus_equal(current->mm->cpu_vm_mask, mask)) - smp_call_function(flush_ldt, NULL, 1, 1); + smp_call_function(flush_ldt, current->mm, 1); preempt_enable(); #else load_LDT(pc); diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index d0b234c9fc31..8864230d55af 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -11,6 +11,8 @@ #include <linux/delay.h> #include <linux/init.h> #include <linux/numa.h> +#include <linux/ftrace.h> + #include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> @@ -39,7 +41,7 @@ static void set_idt(void *newidt, __u16 limit) curidt.address = (unsigned long)newidt; load_idt(&curidt); -}; +} static void set_gdt(void *newgdt, __u16 limit) @@ -51,7 +53,7 @@ static void set_gdt(void *newgdt, __u16 limit) curgdt.address = (unsigned long)newgdt; load_gdt(&curgdt); -}; +} static void load_segments(void) { @@ -107,6 +109,8 @@ NORET_TYPE void machine_kexec(struct kimage *image) unsigned long page_list[PAGES_NR]; void *control_page; + tracer_disable(); + /* Interrupts aren't acceptable while we reboot */ local_irq_disable(); diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 576a03db4511..9dd9262693a3 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -11,6 +11,8 @@ #include <linux/string.h> #include <linux/reboot.h> #include <linux/numa.h> +#include <linux/ftrace.h> + #include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> @@ -110,7 +112,7 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) { pgd_t *level4p; level4p = (pgd_t *)__va(start_pgtable); - return init_level4_page(image, level4p, 0, end_pfn << PAGE_SHIFT); + return init_level4_page(image, level4p, 0, max_pfn << PAGE_SHIFT); } static void set_idt(void *newidt, u16 limit) @@ -184,6 +186,8 @@ NORET_TYPE void machine_kexec(struct kimage *image) unsigned long page_list[PAGES_NR]; void *control_page; + tracer_disable(); + /* Interrupts aren't acceptable while we reboot */ local_irq_disable(); diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c index 3cad17fe026b..07c0f828f488 100644 --- a/arch/x86/kernel/mfgpt_32.c +++ b/arch/x86/kernel/mfgpt_32.c @@ -155,6 +155,7 @@ int geode_mfgpt_toggle_event(int timer, int cmp, int event, int enable) wrmsr(msr, value, dummy); return 0; } +EXPORT_SYMBOL_GPL(geode_mfgpt_toggle_event); int geode_mfgpt_set_irq(int timer, int cmp, int irq, int enable) { @@ -222,6 +223,7 @@ int geode_mfgpt_alloc_timer(int timer, int domain) /* No timers available - too bad */ return -1; } +EXPORT_SYMBOL_GPL(geode_mfgpt_alloc_timer); #ifdef CONFIG_GEODE_MFGPT_TIMER diff --git a/arch/x86/kernel/microcode.c b/arch/x86/kernel/microcode.c index 69729e38b78a..56b933119a04 100644 --- a/arch/x86/kernel/microcode.c +++ b/arch/x86/kernel/microcode.c @@ -5,13 +5,14 @@ * 2006 Shaohua Li <shaohua.li@intel.com> * * This driver allows to upgrade microcode on Intel processors - * belonging to IA-32 family - PentiumPro, Pentium II, + * belonging to IA-32 family - PentiumPro, Pentium II, * Pentium III, Xeon, Pentium 4, etc. * - * Reference: Section 8.10 of Volume III, Intel Pentium 4 Manual, - * Order Number 245472 or free download from: - * - * http://developer.intel.com/design/pentium4/manuals/245472.htm + * Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture + * Software Developer's Manual + * Order Number 253668 or free download from: + * + * http://developer.intel.com/design/pentium4/manuals/253668.htm * * For more information, go to http://www.urbanmyth.org/microcode * @@ -58,12 +59,12 @@ * nature of implementation. * 1.11 22 Mar 2002 Tigran Aivazian <tigran@veritas.com> * Fix the panic when writing zero-length microcode chunk. - * 1.12 29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>, + * 1.12 29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>, * Jun Nakajima <jun.nakajima@intel.com> * Support for the microcode updates in the new format. * 1.13 10 Oct 2003 Tigran Aivazian <tigran@veritas.com> * Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl - * because we no longer hold a copy of applied microcode + * because we no longer hold a copy of applied microcode * in kernel memory. * 1.14 25 Jun 2004 Tigran Aivazian <tigran@veritas.com> * Fix sigmatch() macro to handle old CPUs with pf == 0. @@ -75,6 +76,7 @@ #include <linux/kernel.h> #include <linux/init.h> #include <linux/sched.h> +#include <linux/smp_lock.h> #include <linux/cpumask.h> #include <linux/module.h> #include <linux/slab.h> @@ -320,11 +322,11 @@ static void apply_microcode(int cpu) return; /* serialize access to the physical write to MSR 0x79 */ - spin_lock_irqsave(µcode_update_lock, flags); + spin_lock_irqsave(µcode_update_lock, flags); /* write microcode via MSR 0x79 */ wrmsr(MSR_IA32_UCODE_WRITE, - (unsigned long) uci->mc->bits, + (unsigned long) uci->mc->bits, (unsigned long) uci->mc->bits >> 16 >> 16); wrmsr(MSR_IA32_UCODE_REV, 0, 0); @@ -341,7 +343,7 @@ static void apply_microcode(int cpu) return; } printk(KERN_INFO "microcode: CPU%d updated from revision " - "0x%x to 0x%x, date = %08x \n", + "0x%x to 0x%x, date = %08x \n", cpu_num, uci->rev, val[1], uci->mc->hdr.date); uci->rev = val[1]; } @@ -422,6 +424,7 @@ out: static int microcode_open (struct inode *unused1, struct file *unused2) { + cycle_kernel_lock(); return capable(CAP_SYS_RAWIO) ? 0 : -EPERM; } @@ -488,7 +491,7 @@ MODULE_ALIAS_MISCDEV(MICROCODE_MINOR); #define microcode_dev_exit() do { } while(0) #endif -static long get_next_ucode_from_buffer(void **mc, void *buf, +static long get_next_ucode_from_buffer(void **mc, const u8 *buf, unsigned long size, long offset) { microcode_header_t *mc_header; @@ -522,7 +525,7 @@ static int cpu_request_microcode(int cpu) char name[30]; struct cpuinfo_x86 *c = &cpu_data(cpu); const struct firmware *firmware; - void *buf; + const u8 *buf; unsigned long size; long offset = 0; int error; @@ -534,7 +537,7 @@ static int cpu_request_microcode(int cpu) c->x86, c->x86_model, c->x86_mask); error = request_firmware(&firmware, name, µcode_pdev->dev); if (error) { - pr_debug("microcode: ucode data file %s load failed\n", name); + pr_debug("microcode: data file %s load failed\n", name); return error; } buf = firmware->data; @@ -805,6 +808,9 @@ static int __init microcode_init (void) { int error; + printk(KERN_INFO + "IA-32 Microcode Update Driver: v" MICROCODE_VERSION " <tigran@aivazian.fsnet.co.uk>\n"); + error = microcode_dev_init(); if (error) return error; @@ -825,9 +831,6 @@ static int __init microcode_init (void) } register_hotcpu_notifier(&mc_cpu_notifier); - - printk(KERN_INFO - "IA-32 Microcode Update Driver: v" MICROCODE_VERSION " <tigran@aivazian.fsnet.co.uk>\n"); return 0; } diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c index edc5fbfe85c0..fdfdc550b366 100644 --- a/arch/x86/kernel/mmconf-fam10h_64.c +++ b/arch/x86/kernel/mmconf-fam10h_64.c @@ -12,6 +12,7 @@ #include <asm/io.h> #include <asm/msr.h> #include <asm/acpi.h> +#include <asm/mmconfig.h> #include "../pci/pci.h" diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 404683b94e79..3b25e49380c6 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -25,6 +25,8 @@ #include <asm/proto.h> #include <asm/acpi.h> #include <asm/bios_ebda.h> +#include <asm/e820.h> +#include <asm/trampoline.h> #include <mach_apic.h> #ifdef CONFIG_X86_32 @@ -32,28 +34,6 @@ #include <mach_mpparse.h> #endif -/* Have we found an MP table */ -int smp_found_config; - -/* - * Various Linux-internal data structures created from the - * MP-table. - */ -#if defined (CONFIG_MCA) || defined (CONFIG_EISA) -int mp_bus_id_to_type[MAX_MP_BUSSES]; -#endif - -DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES); -int mp_bus_id_to_pci_bus[MAX_MP_BUSSES] = {[0 ... MAX_MP_BUSSES - 1] = -1 }; - -static int mp_current_pci_id; - -int pic_mode; - -/* - * Intel MP BIOS table parsing routines: - */ - /* * Checksum an MP configuration block. */ @@ -69,15 +49,73 @@ static int __init mpf_checksum(unsigned char *mp, int len) } #ifdef CONFIG_X86_NUMAQ +int found_numaq; /* * Have to match translation table entries to main table entries by counter * hence the mpc_record variable .... can't see a less disgusting way of * doing this .... */ +struct mpc_config_translation { + unsigned char mpc_type; + unsigned char trans_len; + unsigned char trans_type; + unsigned char trans_quad; + unsigned char trans_global; + unsigned char trans_local; + unsigned short trans_reserved; +}; + static int mpc_record; static struct mpc_config_translation *translation_table[MAX_MPC_ENTRY] __cpuinitdata; + +static inline int generate_logical_apicid(int quad, int phys_apicid) +{ + return (quad << 4) + (phys_apicid ? phys_apicid << 1 : 1); +} + + +static inline int mpc_apic_id(struct mpc_config_processor *m, + struct mpc_config_translation *translation_record) +{ + int quad = translation_record->trans_quad; + int logical_apicid = generate_logical_apicid(quad, m->mpc_apicid); + + printk(KERN_DEBUG "Processor #%d %u:%u APIC version %d (quad %d, apic %d)\n", + m->mpc_apicid, + (m->mpc_cpufeature & CPU_FAMILY_MASK) >> 8, + (m->mpc_cpufeature & CPU_MODEL_MASK) >> 4, + m->mpc_apicver, quad, logical_apicid); + return logical_apicid; +} + +int mp_bus_id_to_node[MAX_MP_BUSSES]; + +int mp_bus_id_to_local[MAX_MP_BUSSES]; + +static void mpc_oem_bus_info(struct mpc_config_bus *m, char *name, + struct mpc_config_translation *translation) +{ + int quad = translation->trans_quad; + int local = translation->trans_local; + + mp_bus_id_to_node[m->mpc_busid] = quad; + mp_bus_id_to_local[m->mpc_busid] = local; + printk(KERN_INFO "Bus #%d is %s (node %d)\n", + m->mpc_busid, name, quad); +} + +int quad_local_to_mp_bus_id [NR_CPUS/4][4]; +static void mpc_oem_pci_bus(struct mpc_config_bus *m, + struct mpc_config_translation *translation) +{ + int quad = translation->trans_quad; + int local = translation->trans_local; + + quad_local_to_mp_bus_id[quad][local] = m->mpc_busid; +} + #endif static void __cpuinit MP_processor_info(struct mpc_config_processor *m) @@ -90,7 +128,10 @@ static void __cpuinit MP_processor_info(struct mpc_config_processor *m) return; } #ifdef CONFIG_X86_NUMAQ - apicid = mpc_apic_id(m, translation_table[mpc_record]); + if (found_numaq) + apicid = mpc_apic_id(m, translation_table[mpc_record]); + else + apicid = m->mpc_apicid; #else apicid = m->mpc_apicid; #endif @@ -103,17 +144,18 @@ static void __cpuinit MP_processor_info(struct mpc_config_processor *m) generic_processor_info(apicid, m->mpc_apicver); } +#ifdef CONFIG_X86_IO_APIC static void __init MP_bus_info(struct mpc_config_bus *m) { char str[7]; - memcpy(str, m->mpc_bustype, 6); str[6] = 0; #ifdef CONFIG_X86_NUMAQ - mpc_oem_bus_info(m, str, translation_table[mpc_record]); + if (found_numaq) + mpc_oem_bus_info(m, str, translation_table[mpc_record]); #else - Dprintk("Bus #%d is %s\n", m->mpc_busid, str); + printk(KERN_INFO "Bus #%d is %s\n", m->mpc_busid, str); #endif #if MAX_MP_BUSSES < 256 @@ -132,11 +174,10 @@ static void __init MP_bus_info(struct mpc_config_bus *m) #endif } else if (strncmp(str, BUSTYPE_PCI, sizeof(BUSTYPE_PCI) - 1) == 0) { #ifdef CONFIG_X86_NUMAQ - mpc_oem_pci_bus(m, translation_table[mpc_record]); + if (found_numaq) + mpc_oem_pci_bus(m, translation_table[mpc_record]); #endif clear_bit(m->mpc_busid, mp_bus_not_pci); - mp_bus_id_to_pci_bus[m->mpc_busid] = mp_current_pci_id; - mp_current_pci_id++; #if defined(CONFIG_EISA) || defined (CONFIG_MCA) mp_bus_id_to_type[m->mpc_busid] = MP_BUS_PCI; } else if (strncmp(str, BUSTYPE_EISA, sizeof(BUSTYPE_EISA) - 1) == 0) { @@ -147,6 +188,7 @@ static void __init MP_bus_info(struct mpc_config_bus *m) } else printk(KERN_WARNING "Unknown bustype %s - ignoring\n", str); } +#endif #ifdef CONFIG_X86_IO_APIC @@ -176,18 +218,89 @@ static void __init MP_ioapic_info(struct mpc_config_ioapic *m) if (bad_ioapic(m->mpc_apicaddr)) return; - mp_ioapics[nr_ioapics] = *m; + mp_ioapics[nr_ioapics].mp_apicaddr = m->mpc_apicaddr; + mp_ioapics[nr_ioapics].mp_apicid = m->mpc_apicid; + mp_ioapics[nr_ioapics].mp_type = m->mpc_type; + mp_ioapics[nr_ioapics].mp_apicver = m->mpc_apicver; + mp_ioapics[nr_ioapics].mp_flags = m->mpc_flags; nr_ioapics++; } -static void __init MP_intsrc_info(struct mpc_config_intsrc *m) +static void print_MP_intsrc_info(struct mpc_config_intsrc *m) { - mp_irqs[mp_irq_entries] = *m; - Dprintk("Int: type %d, pol %d, trig %d, bus %d," + printk(KERN_CONT "Int: type %d, pol %d, trig %d, bus %02x," " IRQ %02x, APIC ID %x, APIC INT %02x\n", m->mpc_irqtype, m->mpc_irqflag & 3, (m->mpc_irqflag >> 2) & 3, m->mpc_srcbus, m->mpc_srcbusirq, m->mpc_dstapic, m->mpc_dstirq); +} + +static void __init print_mp_irq_info(struct mp_config_intsrc *mp_irq) +{ + printk(KERN_CONT "Int: type %d, pol %d, trig %d, bus %02x," + " IRQ %02x, APIC ID %x, APIC INT %02x\n", + mp_irq->mp_irqtype, mp_irq->mp_irqflag & 3, + (mp_irq->mp_irqflag >> 2) & 3, mp_irq->mp_srcbus, + mp_irq->mp_srcbusirq, mp_irq->mp_dstapic, mp_irq->mp_dstirq); +} + +static void __init assign_to_mp_irq(struct mpc_config_intsrc *m, + struct mp_config_intsrc *mp_irq) +{ + mp_irq->mp_dstapic = m->mpc_dstapic; + mp_irq->mp_type = m->mpc_type; + mp_irq->mp_irqtype = m->mpc_irqtype; + mp_irq->mp_irqflag = m->mpc_irqflag; + mp_irq->mp_srcbus = m->mpc_srcbus; + mp_irq->mp_srcbusirq = m->mpc_srcbusirq; + mp_irq->mp_dstirq = m->mpc_dstirq; +} + +static void __init assign_to_mpc_intsrc(struct mp_config_intsrc *mp_irq, + struct mpc_config_intsrc *m) +{ + m->mpc_dstapic = mp_irq->mp_dstapic; + m->mpc_type = mp_irq->mp_type; + m->mpc_irqtype = mp_irq->mp_irqtype; + m->mpc_irqflag = mp_irq->mp_irqflag; + m->mpc_srcbus = mp_irq->mp_srcbus; + m->mpc_srcbusirq = mp_irq->mp_srcbusirq; + m->mpc_dstirq = mp_irq->mp_dstirq; +} + +static int __init mp_irq_mpc_intsrc_cmp(struct mp_config_intsrc *mp_irq, + struct mpc_config_intsrc *m) +{ + if (mp_irq->mp_dstapic != m->mpc_dstapic) + return 1; + if (mp_irq->mp_type != m->mpc_type) + return 2; + if (mp_irq->mp_irqtype != m->mpc_irqtype) + return 3; + if (mp_irq->mp_irqflag != m->mpc_irqflag) + return 4; + if (mp_irq->mp_srcbus != m->mpc_srcbus) + return 5; + if (mp_irq->mp_srcbusirq != m->mpc_srcbusirq) + return 6; + if (mp_irq->mp_dstirq != m->mpc_dstirq) + return 7; + + return 0; +} + +static void __init MP_intsrc_info(struct mpc_config_intsrc *m) +{ + int i; + + print_MP_intsrc_info(m); + + for (i = 0; i < mp_irq_entries; i++) { + if (!mp_irq_mpc_intsrc_cmp(&mp_irqs[i], m)) + return; + } + + assign_to_mp_irq(m, &mp_irqs[mp_irq_entries]); if (++mp_irq_entries == MAX_IRQ_SOURCES) panic("Max # of irq sources exceeded!!\n"); } @@ -196,7 +309,7 @@ static void __init MP_intsrc_info(struct mpc_config_intsrc *m) static void __init MP_lintsrc_info(struct mpc_config_lintsrc *m) { - Dprintk("Lint: type %d, pol %d, trig %d, bus %d," + printk(KERN_INFO "Lint: type %d, pol %d, trig %d, bus %02x," " IRQ %02x, APIC ID %x, APIC LINT %02x\n", m->mpc_irqtype, m->mpc_irqflag & 3, (m->mpc_irqflag >> 2) & 3, m->mpc_srcbusid, @@ -266,11 +379,14 @@ static void __init smp_read_mpc_oem(struct mp_config_oemtable *oemtable, } } -static inline void mps_oem_check(struct mp_config_table *mpc, char *oem, +void numaq_mps_oem_check(struct mp_config_table *mpc, char *oem, char *productid) { if (strncmp(oem, "IBM NUMA", 8)) - printk("Warning! May not be a NUMA-Q system!\n"); + printk("Warning! Not a NUMA-Q system!\n"); + else + found_numaq = 1; + if (mpc->mpc_oemptr) smp_read_mpc_oem((struct mp_config_oemtable *)mpc->mpc_oemptr, mpc->mpc_oemsize); @@ -281,12 +397,9 @@ static inline void mps_oem_check(struct mp_config_table *mpc, char *oem, * Read/parse the MPC */ -static int __init smp_read_mpc(struct mp_config_table *mpc, unsigned early) +static int __init smp_check_mpc(struct mp_config_table *mpc, char *oem, + char *str) { - char str[16]; - char oem[10]; - int count = sizeof(*mpc); - unsigned char *mpt = ((unsigned char *)mpc) + count; if (memcmp(mpc->mpc_signature, MPC_SIGNATURE, 4)) { printk(KERN_ERR "MPTABLE: bad signature [%c%c%c%c]!\n", @@ -309,19 +422,42 @@ static int __init smp_read_mpc(struct mp_config_table *mpc, unsigned early) } memcpy(oem, mpc->mpc_oem, 8); oem[8] = 0; - printk(KERN_INFO "MPTABLE: OEM ID: %s ", oem); + printk(KERN_INFO "MPTABLE: OEM ID: %s\n", oem); memcpy(str, mpc->mpc_productid, 12); str[12] = 0; - printk("Product ID: %s ", str); -#ifdef CONFIG_X86_32 - mps_oem_check(mpc, oem, str); -#endif - printk(KERN_INFO "MPTABLE: Product ID: %s ", str); + printk(KERN_INFO "MPTABLE: Product ID: %s\n", str); printk(KERN_INFO "MPTABLE: APIC at: 0x%X\n", mpc->mpc_lapic); + return 1; +} + +static int __init smp_read_mpc(struct mp_config_table *mpc, unsigned early) +{ + char str[16]; + char oem[10]; + + int count = sizeof(*mpc); + unsigned char *mpt = ((unsigned char *)mpc) + count; + + if (!smp_check_mpc(mpc, oem, str)) + return 0; + +#ifdef CONFIG_X86_32 + /* + * need to make sure summit and es7000's mps_oem_check is safe to be + * called early via genericarch 's mps_oem_check + */ + if (early) { +#ifdef CONFIG_X86_NUMAQ + numaq_mps_oem_check(mpc, oem, str); +#endif + } else + mps_oem_check(mpc, oem, str); +#endif + /* save the local APIC address, it might be non-default */ if (!acpi_lapic) mp_lapic_addr = mpc->mpc_lapic; @@ -352,7 +488,9 @@ static int __init smp_read_mpc(struct mp_config_table *mpc, unsigned early) { struct mpc_config_bus *m = (struct mpc_config_bus *)mpt; +#ifdef CONFIG_X86_IO_APIC MP_bus_info(m); +#endif mpt += sizeof(*m); count += sizeof(*m); break; @@ -402,6 +540,11 @@ static int __init smp_read_mpc(struct mp_config_table *mpc, unsigned early) ++mpc_record; #endif } + +#ifdef CONFIG_X86_GENERICARCH + generic_bigsmp_probe(); +#endif + setup_apic_routing(); if (!num_processors) printk(KERN_ERR "MPTABLE: no processors registered!\n"); @@ -427,7 +570,7 @@ static void __init construct_default_ioirq_mptable(int mpc_default_type) intsrc.mpc_type = MP_INTSRC; intsrc.mpc_irqflag = 0; /* conforming */ intsrc.mpc_srcbus = 0; - intsrc.mpc_dstapic = mp_ioapics[0].mpc_apicid; + intsrc.mpc_dstapic = mp_ioapics[0].mp_apicid; intsrc.mpc_irqtype = mp_INT; @@ -488,40 +631,11 @@ static void __init construct_default_ioirq_mptable(int mpc_default_type) MP_intsrc_info(&intsrc); } -#endif -static inline void __init construct_default_ISA_mptable(int mpc_default_type) +static void construct_ioapic_table(int mpc_default_type) { - struct mpc_config_processor processor; - struct mpc_config_bus bus; -#ifdef CONFIG_X86_IO_APIC struct mpc_config_ioapic ioapic; -#endif - struct mpc_config_lintsrc lintsrc; - int linttypes[2] = { mp_ExtINT, mp_NMI }; - int i; - - /* - * local APIC has default address - */ - mp_lapic_addr = APIC_DEFAULT_PHYS_BASE; - - /* - * 2 CPUs, numbered 0 & 1. - */ - processor.mpc_type = MP_PROCESSOR; - /* Either an integrated APIC or a discrete 82489DX. */ - processor.mpc_apicver = mpc_default_type > 4 ? 0x10 : 0x01; - processor.mpc_cpuflag = CPU_ENABLED; - processor.mpc_cpufeature = (boot_cpu_data.x86 << 8) | - (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_mask; - processor.mpc_featureflag = boot_cpu_data.x86_capability[0]; - processor.mpc_reserved[0] = 0; - processor.mpc_reserved[1] = 0; - for (i = 0; i < 2; i++) { - processor.mpc_apicid = i; - MP_processor_info(&processor); - } + struct mpc_config_bus bus; bus.mpc_type = MP_BUS; bus.mpc_busid = 0; @@ -550,7 +664,6 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type) MP_bus_info(&bus); } -#ifdef CONFIG_X86_IO_APIC ioapic.mpc_type = MP_IOAPIC; ioapic.mpc_apicid = 2; ioapic.mpc_apicver = mpc_default_type > 4 ? 0x10 : 0x01; @@ -562,7 +675,42 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type) * We set up most of the low 16 IO-APIC pins according to MPS rules. */ construct_default_ioirq_mptable(mpc_default_type); +} +#else +static inline void construct_ioapic_table(int mpc_default_type) { } #endif + +static inline void __init construct_default_ISA_mptable(int mpc_default_type) +{ + struct mpc_config_processor processor; + struct mpc_config_lintsrc lintsrc; + int linttypes[2] = { mp_ExtINT, mp_NMI }; + int i; + + /* + * local APIC has default address + */ + mp_lapic_addr = APIC_DEFAULT_PHYS_BASE; + + /* + * 2 CPUs, numbered 0 & 1. + */ + processor.mpc_type = MP_PROCESSOR; + /* Either an integrated APIC or a discrete 82489DX. */ + processor.mpc_apicver = mpc_default_type > 4 ? 0x10 : 0x01; + processor.mpc_cpuflag = CPU_ENABLED; + processor.mpc_cpufeature = (boot_cpu_data.x86 << 8) | + (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_mask; + processor.mpc_featureflag = boot_cpu_data.x86_capability[0]; + processor.mpc_reserved[0] = 0; + processor.mpc_reserved[1] = 0; + for (i = 0; i < 2; i++) { + processor.mpc_apicid = i; + MP_processor_info(&processor); + } + + construct_ioapic_table(mpc_default_type); + lintsrc.mpc_type = MP_LINTSRC; lintsrc.mpc_irqflag = 0; /* conforming */ lintsrc.mpc_srcbusid = 0; @@ -578,12 +726,22 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type) static struct intel_mp_floating *mpf_found; /* + * Machine specific quirk for finding the SMP config before other setup + * activities destroy the table: + */ +int (*mach_get_smp_config_quirk)(unsigned int early); + +/* * Scan the memory blocks for an SMP configuration block. */ -static void __init __get_smp_config(unsigned early) +static void __init __get_smp_config(unsigned int early) { struct intel_mp_floating *mpf = mpf_found; + if (mach_get_smp_config_quirk) { + if (mach_get_smp_config_quirk(early)) + return; + } if (acpi_lapic && early) return; /* @@ -600,7 +758,7 @@ static void __init __get_smp_config(unsigned early) printk(KERN_INFO "Intel MultiProcessor Specification v1.%d\n", mpf->mpf_specification); -#ifdef CONFIG_X86_32 +#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32) if (mpf->mpf_feature2 & (1 << 7)) { printk(KERN_INFO " IMCR and PIC compatibility mode.\n"); pic_mode = 1; @@ -632,7 +790,9 @@ static void __init __get_smp_config(unsigned early) * override the defaults. */ if (!smp_read_mpc(phys_to_virt(mpf->mpf_physptr), early)) { +#ifdef CONFIG_X86_LOCAL_APIC smp_found_config = 0; +#endif printk(KERN_ERR "BIOS bug, MP table errors detected!...\n"); printk(KERN_ERR "... disabling SMP support. " @@ -689,7 +849,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length, unsigned int *bp = phys_to_virt(base); struct intel_mp_floating *mpf; - Dprintk("Scan SMP from %p for %ld bytes.\n", bp, length); + printk(KERN_DEBUG "Scan SMP from %p for %ld bytes.\n", bp, length); BUILD_BUG_ON(sizeof(*mpf) != 16); while (length > 0) { @@ -699,15 +859,21 @@ static int __init smp_scan_config(unsigned long base, unsigned long length, !mpf_checksum((unsigned char *)bp, 16) && ((mpf->mpf_specification == 1) || (mpf->mpf_specification == 4))) { - +#ifdef CONFIG_X86_LOCAL_APIC smp_found_config = 1; +#endif mpf_found = mpf; -#ifdef CONFIG_X86_32 + printk(KERN_INFO "found SMP MP-table at [%p] %08lx\n", mpf, virt_to_phys(mpf)); - reserve_bootmem(virt_to_phys(mpf), PAGE_SIZE, + + if (!reserve) + return 1; + reserve_bootmem_generic(virt_to_phys(mpf), PAGE_SIZE, BOOTMEM_DEFAULT); if (mpf->mpf_physptr) { + unsigned long size = PAGE_SIZE; +#ifdef CONFIG_X86_32 /* * We cannot access to MPC table to compute * table size yet, as only few megabytes from @@ -717,24 +883,15 @@ static int __init smp_scan_config(unsigned long base, unsigned long length, * PAGE_SIZE from mpg->mpf_physptr yields BUG() * in reserve_bootmem. */ - unsigned long size = PAGE_SIZE; unsigned long end = max_low_pfn * PAGE_SIZE; if (mpf->mpf_physptr + size > end) size = end - mpf->mpf_physptr; - reserve_bootmem(mpf->mpf_physptr, size, +#endif + reserve_bootmem_generic(mpf->mpf_physptr, size, BOOTMEM_DEFAULT); } -#else - if (!reserve) - return 1; - - reserve_bootmem_generic(virt_to_phys(mpf), PAGE_SIZE); - if (mpf->mpf_physptr) - reserve_bootmem_generic(mpf->mpf_physptr, - PAGE_SIZE); -#endif - return 1; + return 1; } bp += 4; length -= 16; @@ -742,10 +899,16 @@ static int __init smp_scan_config(unsigned long base, unsigned long length, return 0; } -static void __init __find_smp_config(unsigned reserve) +int (*mach_find_smp_config_quirk)(unsigned int reserve); + +static void __init __find_smp_config(unsigned int reserve) { unsigned int address; + if (mach_find_smp_config_quirk) { + if (mach_find_smp_config_quirk(reserve)) + return; + } /* * FIXME: Linux assumes you have 640K of base ram.. * this continues the error... @@ -790,298 +953,294 @@ void __init find_smp_config(void) __find_smp_config(1); } -/* -------------------------------------------------------------------------- - ACPI-based MP Configuration - -------------------------------------------------------------------------- */ +#ifdef CONFIG_X86_IO_APIC +static u8 __initdata irq_used[MAX_IRQ_SOURCES]; -/* - * Keep this outside and initialized to 0, for !CONFIG_ACPI builds: - */ -int es7000_plat; +static int __init get_MP_intsrc_index(struct mpc_config_intsrc *m) +{ + int i; -#ifdef CONFIG_ACPI + if (m->mpc_irqtype != mp_INT) + return 0; -#ifdef CONFIG_X86_IO_APIC + if (m->mpc_irqflag != 0x0f) + return 0; -#define MP_ISA_BUS 0 + /* not legacy */ -extern struct mp_ioapic_routing mp_ioapic_routing[MAX_IO_APICS]; + for (i = 0; i < mp_irq_entries; i++) { + if (mp_irqs[i].mp_irqtype != mp_INT) + continue; -static int mp_find_ioapic(int gsi) -{ - int i = 0; + if (mp_irqs[i].mp_irqflag != 0x0f) + continue; - /* Find the IOAPIC that manages this GSI. */ - for (i = 0; i < nr_ioapics; i++) { - if ((gsi >= mp_ioapic_routing[i].gsi_base) - && (gsi <= mp_ioapic_routing[i].gsi_end)) - return i; + if (mp_irqs[i].mp_srcbus != m->mpc_srcbus) + continue; + if (mp_irqs[i].mp_srcbusirq != m->mpc_srcbusirq) + continue; + if (irq_used[i]) { + /* already claimed */ + return -2; + } + irq_used[i] = 1; + return i; } - printk(KERN_ERR "ERROR: Unable to locate IOAPIC for GSI %d\n", gsi); + /* not found */ return -1; } -static u8 __init uniq_ioapic_id(u8 id) -{ -#ifdef CONFIG_X86_32 - if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && - !APIC_XAPIC(apic_version[boot_cpu_physical_apicid])) - return io_apic_get_unique_id(nr_ioapics, id); - else - return id; -#else - int i; - DECLARE_BITMAP(used, 256); - bitmap_zero(used, 256); - for (i = 0; i < nr_ioapics; i++) { - struct mpc_config_ioapic *ia = &mp_ioapics[i]; - __set_bit(ia->mpc_apicid, used); - } - if (!test_bit(id, used)) - return id; - return find_first_zero_bit(used, 256); +#define SPARE_SLOT_NUM 20 + +static struct mpc_config_intsrc __initdata *m_spare[SPARE_SLOT_NUM]; #endif -} -void __init mp_register_ioapic(int id, u32 address, u32 gsi_base) +static int __init replace_intsrc_all(struct mp_config_table *mpc, + unsigned long mpc_new_phys, + unsigned long mpc_new_length) { - int idx = 0; - - if (bad_ioapic(address)) - return; +#ifdef CONFIG_X86_IO_APIC + int i; + int nr_m_spare = 0; +#endif - idx = nr_ioapics; + int count = sizeof(*mpc); + unsigned char *mpt = ((unsigned char *)mpc) + count; - mp_ioapics[idx].mpc_type = MP_IOAPIC; - mp_ioapics[idx].mpc_flags = MPC_APIC_USABLE; - mp_ioapics[idx].mpc_apicaddr = address; + printk(KERN_INFO "mpc_length %x\n", mpc->mpc_length); + while (count < mpc->mpc_length) { + switch (*mpt) { + case MP_PROCESSOR: + { + struct mpc_config_processor *m = + (struct mpc_config_processor *)mpt; + mpt += sizeof(*m); + count += sizeof(*m); + break; + } + case MP_BUS: + { + struct mpc_config_bus *m = + (struct mpc_config_bus *)mpt; + mpt += sizeof(*m); + count += sizeof(*m); + break; + } + case MP_IOAPIC: + { + mpt += sizeof(struct mpc_config_ioapic); + count += sizeof(struct mpc_config_ioapic); + break; + } + case MP_INTSRC: + { +#ifdef CONFIG_X86_IO_APIC + struct mpc_config_intsrc *m = + (struct mpc_config_intsrc *)mpt; - set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address); - mp_ioapics[idx].mpc_apicid = uniq_ioapic_id(id); -#ifdef CONFIG_X86_32 - mp_ioapics[idx].mpc_apicver = io_apic_get_version(idx); -#else - mp_ioapics[idx].mpc_apicver = 0; + printk(KERN_INFO "OLD "); + print_MP_intsrc_info(m); + i = get_MP_intsrc_index(m); + if (i > 0) { + assign_to_mpc_intsrc(&mp_irqs[i], m); + printk(KERN_INFO "NEW "); + print_mp_irq_info(&mp_irqs[i]); + } else if (!i) { + /* legacy, do nothing */ + } else if (nr_m_spare < SPARE_SLOT_NUM) { + /* + * not found (-1), or duplicated (-2) + * are invalid entries, + * we need to use the slot later + */ + m_spare[nr_m_spare] = m; + nr_m_spare++; + } #endif - /* - * Build basic GSI lookup table to facilitate gsi->io_apic lookups - * and to prevent reprogramming of IOAPIC pins (PCI GSIs). - */ - mp_ioapic_routing[idx].apic_id = mp_ioapics[idx].mpc_apicid; - mp_ioapic_routing[idx].gsi_base = gsi_base; - mp_ioapic_routing[idx].gsi_end = gsi_base + - io_apic_get_redir_entries(idx); - - printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%x, " - "GSI %d-%d\n", idx, mp_ioapics[idx].mpc_apicid, - mp_ioapics[idx].mpc_apicver, mp_ioapics[idx].mpc_apicaddr, - mp_ioapic_routing[idx].gsi_base, mp_ioapic_routing[idx].gsi_end); - - nr_ioapics++; -} + mpt += sizeof(struct mpc_config_intsrc); + count += sizeof(struct mpc_config_intsrc); + break; + } + case MP_LINTSRC: + { + struct mpc_config_lintsrc *m = + (struct mpc_config_lintsrc *)mpt; + mpt += sizeof(*m); + count += sizeof(*m); + break; + } + default: + /* wrong mptable */ + printk(KERN_ERR "Your mptable is wrong, contact your HW vendor!\n"); + printk(KERN_ERR "type %x\n", *mpt); + print_hex_dump(KERN_ERR, " ", DUMP_PREFIX_ADDRESS, 16, + 1, mpc, mpc->mpc_length, 1); + goto out; + } + } -void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi) -{ - struct mpc_config_intsrc intsrc; - int ioapic = -1; - int pin = -1; +#ifdef CONFIG_X86_IO_APIC + for (i = 0; i < mp_irq_entries; i++) { + if (irq_used[i]) + continue; - /* - * Convert 'gsi' to 'ioapic.pin'. - */ - ioapic = mp_find_ioapic(gsi); - if (ioapic < 0) - return; - pin = gsi - mp_ioapic_routing[ioapic].gsi_base; + if (mp_irqs[i].mp_irqtype != mp_INT) + continue; - /* - * TBD: This check is for faulty timer entries, where the override - * erroneously sets the trigger to level, resulting in a HUGE - * increase of timer interrupts! - */ - if ((bus_irq == 0) && (trigger == 3)) - trigger = 1; + if (mp_irqs[i].mp_irqflag != 0x0f) + continue; - intsrc.mpc_type = MP_INTSRC; - intsrc.mpc_irqtype = mp_INT; - intsrc.mpc_irqflag = (trigger << 2) | polarity; - intsrc.mpc_srcbus = MP_ISA_BUS; - intsrc.mpc_srcbusirq = bus_irq; /* IRQ */ - intsrc.mpc_dstapic = mp_ioapics[ioapic].mpc_apicid; /* APIC ID */ - intsrc.mpc_dstirq = pin; /* INTIN# */ + if (nr_m_spare > 0) { + printk(KERN_INFO "*NEW* found "); + nr_m_spare--; + assign_to_mpc_intsrc(&mp_irqs[i], m_spare[nr_m_spare]); + m_spare[nr_m_spare] = NULL; + } else { + struct mpc_config_intsrc *m = + (struct mpc_config_intsrc *)mpt; + count += sizeof(struct mpc_config_intsrc); + if (!mpc_new_phys) { + printk(KERN_INFO "No spare slots, try to append...take your risk, new mpc_length %x\n", count); + } else { + if (count <= mpc_new_length) + printk(KERN_INFO "No spare slots, try to append..., new mpc_length %x\n", count); + else { + printk(KERN_ERR "mpc_new_length %lx is too small\n", mpc_new_length); + goto out; + } + } + assign_to_mpc_intsrc(&mp_irqs[i], m); + mpc->mpc_length = count; + mpt += sizeof(struct mpc_config_intsrc); + } + print_mp_irq_info(&mp_irqs[i]); + } +#endif +out: + /* update checksum */ + mpc->mpc_checksum = 0; + mpc->mpc_checksum -= mpf_checksum((unsigned char *)mpc, + mpc->mpc_length); - MP_intsrc_info(&intsrc); + return 0; } -void __init mp_config_acpi_legacy_irqs(void) -{ - struct mpc_config_intsrc intsrc; - int i = 0; - int ioapic = -1; +static int __initdata enable_update_mptable; -#if defined (CONFIG_MCA) || defined (CONFIG_EISA) - /* - * Fabricate the legacy ISA bus (bus #31). - */ - mp_bus_id_to_type[MP_ISA_BUS] = MP_BUS_ISA; -#endif - set_bit(MP_ISA_BUS, mp_bus_not_pci); - Dprintk("Bus #%d is ISA\n", MP_ISA_BUS); +static int __init update_mptable_setup(char *str) +{ + enable_update_mptable = 1; + return 0; +} +early_param("update_mptable", update_mptable_setup); - /* - * Older generations of ES7000 have no legacy identity mappings - */ - if (es7000_plat == 1) - return; +static unsigned long __initdata mpc_new_phys; +static unsigned long mpc_new_length __initdata = 4096; - /* - * Locate the IOAPIC that manages the ISA IRQs (0-15). - */ - ioapic = mp_find_ioapic(0); - if (ioapic < 0) - return; +/* alloc_mptable or alloc_mptable=4k */ +static int __initdata alloc_mptable; +static int __init parse_alloc_mptable_opt(char *p) +{ + enable_update_mptable = 1; + alloc_mptable = 1; + if (!p) + return 0; + mpc_new_length = memparse(p, &p); + return 0; +} +early_param("alloc_mptable", parse_alloc_mptable_opt); - intsrc.mpc_type = MP_INTSRC; - intsrc.mpc_irqflag = 0; /* Conforming */ - intsrc.mpc_srcbus = MP_ISA_BUS; -#ifdef CONFIG_X86_IO_APIC - intsrc.mpc_dstapic = mp_ioapics[ioapic].mpc_apicid; +void __init early_reserve_e820_mpc_new(void) +{ + if (enable_update_mptable && alloc_mptable) { + u64 startt = 0; +#ifdef CONFIG_X86_TRAMPOLINE + startt = TRAMPOLINE_BASE; #endif - /* - * Use the default configuration for the IRQs 0-15. Unless - * overridden by (MADT) interrupt source override entries. - */ - for (i = 0; i < 16; i++) { - int idx; - - for (idx = 0; idx < mp_irq_entries; idx++) { - struct mpc_config_intsrc *irq = mp_irqs + idx; - - /* Do we already have a mapping for this ISA IRQ? */ - if (irq->mpc_srcbus == MP_ISA_BUS - && irq->mpc_srcbusirq == i) - break; - - /* Do we already have a mapping for this IOAPIC pin */ - if ((irq->mpc_dstapic == intsrc.mpc_dstapic) && - (irq->mpc_dstirq == i)) - break; - } - - if (idx != mp_irq_entries) { - printk(KERN_DEBUG "ACPI: IRQ%d used by override.\n", i); - continue; /* IRQ already used */ - } - - intsrc.mpc_irqtype = mp_INT; - intsrc.mpc_srcbusirq = i; /* Identity mapped */ - intsrc.mpc_dstirq = i; - - MP_intsrc_info(&intsrc); + mpc_new_phys = early_reserve_e820(startt, mpc_new_length, 4); } } -int mp_register_gsi(u32 gsi, int triggering, int polarity) +static int __init update_mp_table(void) { - int ioapic; - int ioapic_pin; -#ifdef CONFIG_X86_32 -#define MAX_GSI_NUM 4096 -#define IRQ_COMPRESSION_START 64 + char str[16]; + char oem[10]; + struct intel_mp_floating *mpf; + struct mp_config_table *mpc; + struct mp_config_table *mpc_new; + + if (!enable_update_mptable) + return 0; + + mpf = mpf_found; + if (!mpf) + return 0; - static int pci_irq = IRQ_COMPRESSION_START; /* - * Mapping between Global System Interrupts, which - * represent all possible interrupts, and IRQs - * assigned to actual devices. + * Now see if we need to go further. */ - static int gsi_to_irq[MAX_GSI_NUM]; -#else - - if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC) - return gsi; -#endif + if (mpf->mpf_feature1 != 0) + return 0; - /* Don't set up the ACPI SCI because it's already set up */ - if (acpi_gbl_FADT.sci_interrupt == gsi) - return gsi; + if (!mpf->mpf_physptr) + return 0; - ioapic = mp_find_ioapic(gsi); - if (ioapic < 0) { - printk(KERN_WARNING "No IOAPIC for GSI %u\n", gsi); - return gsi; - } + mpc = phys_to_virt(mpf->mpf_physptr); - ioapic_pin = gsi - mp_ioapic_routing[ioapic].gsi_base; + if (!smp_check_mpc(mpc, oem, str)) + return 0; -#ifdef CONFIG_X86_32 - if (ioapic_renumber_irq) - gsi = ioapic_renumber_irq(ioapic, gsi); -#endif + printk(KERN_INFO "mpf: %lx\n", virt_to_phys(mpf)); + printk(KERN_INFO "mpf_physptr: %x\n", mpf->mpf_physptr); - /* - * Avoid pin reprogramming. PRTs typically include entries - * with redundant pin->gsi mappings (but unique PCI devices); - * we only program the IOAPIC on the first. - */ - if (ioapic_pin > MP_MAX_IOAPIC_PIN) { - printk(KERN_ERR "Invalid reference to IOAPIC pin " - "%d-%d\n", mp_ioapic_routing[ioapic].apic_id, - ioapic_pin); - return gsi; + if (mpc_new_phys && mpc->mpc_length > mpc_new_length) { + mpc_new_phys = 0; + printk(KERN_INFO "mpc_new_length is %ld, please use alloc_mptable=8k\n", + mpc_new_length); } - if (test_bit(ioapic_pin, mp_ioapic_routing[ioapic].pin_programmed)) { - Dprintk(KERN_DEBUG "Pin %d-%d already programmed\n", - mp_ioapic_routing[ioapic].apic_id, ioapic_pin); -#ifdef CONFIG_X86_32 - return (gsi < IRQ_COMPRESSION_START ? gsi : gsi_to_irq[gsi]); -#else - return gsi; -#endif + + if (!mpc_new_phys) { + unsigned char old, new; + /* check if we can change the postion */ + mpc->mpc_checksum = 0; + old = mpf_checksum((unsigned char *)mpc, mpc->mpc_length); + mpc->mpc_checksum = 0xff; + new = mpf_checksum((unsigned char *)mpc, mpc->mpc_length); + if (old == new) { + printk(KERN_INFO "mpc is readonly, please try alloc_mptable instead\n"); + return 0; + } + printk(KERN_INFO "use in-positon replacing\n"); + } else { + mpf->mpf_physptr = mpc_new_phys; + mpc_new = phys_to_virt(mpc_new_phys); + memcpy(mpc_new, mpc, mpc->mpc_length); + mpc = mpc_new; + /* check if we can modify that */ + if (mpc_new_phys - mpf->mpf_physptr) { + struct intel_mp_floating *mpf_new; + /* steal 16 bytes from [0, 1k) */ + printk(KERN_INFO "mpf new: %x\n", 0x400 - 16); + mpf_new = phys_to_virt(0x400 - 16); + memcpy(mpf_new, mpf, 16); + mpf = mpf_new; + mpf->mpf_physptr = mpc_new_phys; + } + mpf->mpf_checksum = 0; + mpf->mpf_checksum -= mpf_checksum((unsigned char *)mpf, 16); + printk(KERN_INFO "mpf_physptr new: %x\n", mpf->mpf_physptr); } - set_bit(ioapic_pin, mp_ioapic_routing[ioapic].pin_programmed); -#ifdef CONFIG_X86_32 /* - * For GSI >= 64, use IRQ compression + * only replace the one with mp_INT and + * MP_IRQ_TRIGGER_LEVEL|MP_IRQ_POLARITY_LOW, + * already in mp_irqs , stored by ... and mp_config_acpi_gsi, + * may need pci=routeirq for all coverage */ - if ((gsi >= IRQ_COMPRESSION_START) - && (triggering == ACPI_LEVEL_SENSITIVE)) { - /* - * For PCI devices assign IRQs in order, avoiding gaps - * due to unused I/O APIC pins. - */ - int irq = gsi; - if (gsi < MAX_GSI_NUM) { - /* - * Retain the VIA chipset work-around (gsi > 15), but - * avoid a problem where the 8254 timer (IRQ0) is setup - * via an override (so it's not on pin 0 of the ioapic), - * and at the same time, the pin 0 interrupt is a PCI - * type. The gsi > 15 test could cause these two pins - * to be shared as IRQ0, and they are not shareable. - * So test for this condition, and if necessary, avoid - * the pin collision. - */ - gsi = pci_irq++; - /* - * Don't assign IRQ used by ACPI SCI - */ - if (gsi == acpi_gbl_FADT.sci_interrupt) - gsi = pci_irq++; - gsi_to_irq[irq] = gsi; - } else { - printk(KERN_ERR "GSI %u is too high\n", gsi); - return gsi; - } - } -#endif - io_apic_set_pci_routing(ioapic, ioapic_pin, gsi, - triggering == ACPI_EDGE_SENSITIVE ? 0 : 1, - polarity == ACPI_ACTIVE_HIGH ? 0 : 1); - return gsi; + replace_intsrc_all(mpc, mpc_new_phys, mpc_new_length); + + return 0; } -#endif /* CONFIG_X86_IO_APIC */ -#endif /* CONFIG_ACPI */ +late_initcall(update_mp_table); diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 1f3abe048e93..a153b3905f60 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -117,12 +117,20 @@ static int msr_open(struct inode *inode, struct file *file) { unsigned int cpu = iminor(file->f_path.dentry->d_inode); struct cpuinfo_x86 *c = &cpu_data(cpu); + int ret = 0; - if (cpu >= NR_CPUS || !cpu_online(cpu)) - return -ENXIO; /* No such CPU */ - if (!cpu_has(c, X86_FEATURE_MSR)) - return -EIO; /* MSR not supported */ + lock_kernel(); + cpu = iminor(file->f_path.dentry->d_inode); + if (cpu >= NR_CPUS || !cpu_online(cpu)) { + ret = -ENXIO; /* No such CPU */ + goto out; + } + c = &cpu_data(cpu); + if (!cpu_has(c, X86_FEATURE_MSR)) + ret = -EIO; /* MSR not supported */ +out: + unlock_kernel(); return 0; } diff --git a/arch/x86/kernel/nmi_32.c b/arch/x86/kernel/nmi.c index 11b14bbaa61e..ec024b3baad0 100644 --- a/arch/x86/kernel/nmi_32.c +++ b/arch/x86/kernel/nmi.c @@ -11,10 +11,13 @@ * Mikael Pettersson : PM converted to driver model. Disable/enable API. */ +#include <asm/apic.h> + +#include <linux/nmi.h> +#include <linux/mm.h> #include <linux/delay.h> #include <linux/interrupt.h> #include <linux/module.h> -#include <linux/nmi.h> #include <linux/sysdev.h> #include <linux/sysctl.h> #include <linux/percpu.h> @@ -22,13 +25,18 @@ #include <linux/cpumask.h> #include <linux/kernel_stat.h> #include <linux/kdebug.h> -#include <linux/slab.h> +#include <linux/smp.h> +#include <asm/i8259.h> +#include <asm/io_apic.h> #include <asm/smp.h> #include <asm/nmi.h> +#include <asm/proto.h> #include <asm/timer.h> -#include "mach_traps.h" +#include <asm/mce.h> + +#include <mach_traps.h> int unknown_nmi_panic; int nmi_watchdog_enabled; @@ -42,28 +50,65 @@ static cpumask_t backtrace_mask = CPU_MASK_NONE; * 0: the lapic NMI watchdog is disabled, but can be enabled */ atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */ +EXPORT_SYMBOL(nmi_active); -unsigned int nmi_watchdog = NMI_DEFAULT; -static unsigned int nmi_hz = HZ; +unsigned int nmi_watchdog = NMI_NONE; +EXPORT_SYMBOL(nmi_watchdog); +static int panic_on_timeout; + +static unsigned int nmi_hz = HZ; static DEFINE_PER_CPU(short, wd_enabled); +static int endflag __initdata; -static int endflag __initdata = 0; +static inline unsigned int get_nmi_count(int cpu) +{ +#ifdef CONFIG_X86_64 + return cpu_pda(cpu)->__nmi_count; +#else + return nmi_count(cpu); +#endif +} + +static inline int mce_in_progress(void) +{ +#if defined(CONFIG_X86_64) && defined(CONFIG_X86_MCE) + return atomic_read(&mce_entry) > 0; +#endif + return 0; +} + +/* + * Take the local apic timer and PIT/HPET into account. We don't + * know which one is active, when we have highres/dyntick on + */ +static inline unsigned int get_timer_irqs(int cpu) +{ +#ifdef CONFIG_X86_64 + return read_pda(apic_timer_irqs) + read_pda(irq0_irqs); +#else + return per_cpu(irq_stat, cpu).apic_timer_irqs + + per_cpu(irq_stat, cpu).irq0_irqs; +#endif +} #ifdef CONFIG_SMP -/* The performance counters used by NMI_LOCAL_APIC don't trigger when +/* + * The performance counters used by NMI_LOCAL_APIC don't trigger when * the CPU is idle. To make sure the NMI watchdog really ticks on all * CPUs during the test make them busy. */ static __init void nmi_cpu_busy(void *data) { local_irq_enable_in_hardirq(); - /* Intentionally don't use cpu_relax here. This is - to make sure that the performance counter really ticks, - even if there is a simulator or similar that catches the - pause instruction. On a real HT machine this is fine because - all other CPUs are busy with "useless" delay loops and don't - care if they get somewhat less cycles. */ + /* + * Intentionally don't use cpu_relax here. This is + * to make sure that the performance counter really ticks, + * even if there is a simulator or similar that catches the + * pause instruction. On a real HT machine this is fine because + * all other CPUs are busy with "useless" delay loops and don't + * care if they get somewhat less cycles. + */ while (endflag == 0) mb(); } @@ -74,13 +119,10 @@ int __init check_nmi_watchdog(void) unsigned int *prev_nmi_count; int cpu; - if ((nmi_watchdog == NMI_NONE) || (nmi_watchdog == NMI_DISABLED)) - return 0; - - if (!atomic_read(&nmi_active)) + if (!nmi_watchdog_active() || !atomic_read(&nmi_active)) return 0; - prev_nmi_count = kmalloc(NR_CPUS * sizeof(int), GFP_KERNEL); + prev_nmi_count = kmalloc(nr_cpu_ids * sizeof(int), GFP_KERNEL); if (!prev_nmi_count) goto error; @@ -88,29 +130,23 @@ int __init check_nmi_watchdog(void) #ifdef CONFIG_SMP if (nmi_watchdog == NMI_LOCAL_APIC) - smp_call_function(nmi_cpu_busy, (void *)&endflag, 0, 0); + smp_call_function(nmi_cpu_busy, (void *)&endflag, 0); #endif for_each_possible_cpu(cpu) - prev_nmi_count[cpu] = nmi_count(cpu); + prev_nmi_count[cpu] = get_nmi_count(cpu); local_irq_enable(); - mdelay((20*1000)/nmi_hz); // wait 20 ticks + mdelay((20 * 1000) / nmi_hz); /* wait 20 ticks */ - for_each_possible_cpu(cpu) { -#ifdef CONFIG_SMP - /* Check cpu_callin_map here because that is set - after the timer is started. */ - if (!cpu_isset(cpu, cpu_callin_map)) - continue; -#endif + for_each_online_cpu(cpu) { if (!per_cpu(wd_enabled, cpu)) continue; - if (nmi_count(cpu) - prev_nmi_count[cpu] <= 5) { + if (get_nmi_count(cpu) - prev_nmi_count[cpu] <= 5) { printk(KERN_WARNING "WARNING: CPU#%d: NMI " "appears to be stuck (%d->%d)!\n", cpu, prev_nmi_count[cpu], - nmi_count(cpu)); + get_nmi_count(cpu)); per_cpu(wd_enabled, cpu) = 0; atomic_dec(&nmi_active); } @@ -123,37 +159,49 @@ int __init check_nmi_watchdog(void) } printk("OK.\n"); - /* now that we know it works we can reduce NMI frequency to - something more reasonable; makes a difference in some configs */ + /* + * now that we know it works we can reduce NMI frequency to + * something more reasonable; makes a difference in some configs + */ if (nmi_watchdog == NMI_LOCAL_APIC) nmi_hz = lapic_adjust_nmi_hz(1); kfree(prev_nmi_count); return 0; error: - timer_ack = !cpu_has_tsc; - + if (nmi_watchdog == NMI_IO_APIC && !timer_through_8259) + disable_8259A_irq(0); +#ifdef CONFIG_X86_32 + timer_ack = 0; +#endif return -1; } static int __init setup_nmi_watchdog(char *str) { - int nmi; + unsigned int nmi; + + if (!strncmp(str, "panic", 5)) { + panic_on_timeout = 1; + str = strchr(str, ','); + if (!str) + return 1; + ++str; + } get_option(&str, &nmi); - if ((nmi >= NMI_INVALID) || (nmi < NMI_NONE)) + if (nmi >= NMI_INVALID) return 0; nmi_watchdog = nmi; return 1; } - __setup("nmi_watchdog=", setup_nmi_watchdog); - -/* Suspend/resume support */ - +/* + * Suspend/resume support + */ #ifdef CONFIG_PM static int nmi_pm_active; /* nmi_active before suspend */ @@ -177,7 +225,6 @@ static int lapic_nmi_resume(struct sys_device *dev) return 0; } - static struct sysdev_class nmi_sysclass = { .name = "lapic_nmi", .resume = lapic_nmi_resume, @@ -193,7 +240,8 @@ static int __init init_lapic_nmi_sysfs(void) { int error; - /* should really be a BUG_ON but b/c this is an + /* + * should really be a BUG_ON but b/c this is an * init call, it just doesn't work. -dcz */ if (nmi_watchdog != NMI_LOCAL_APIC) @@ -207,6 +255,7 @@ static int __init init_lapic_nmi_sysfs(void) error = sysdev_register(&device_lapic_nmi); return error; } + /* must come after the local APIC's device_initcall() */ late_initcall(init_lapic_nmi_sysfs); @@ -223,12 +272,12 @@ static void __acpi_nmi_enable(void *__unused) void acpi_nmi_enable(void) { if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC) - on_each_cpu(__acpi_nmi_enable, NULL, 0, 1); + on_each_cpu(__acpi_nmi_enable, NULL, 1); } static void __acpi_nmi_disable(void *__unused) { - apic_write(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED); + apic_write_around(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED); } /* @@ -237,7 +286,7 @@ static void __acpi_nmi_disable(void *__unused) void acpi_nmi_disable(void) { if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC) - on_each_cpu(__acpi_nmi_disable, NULL, 0, 1); + on_each_cpu(__acpi_nmi_disable, NULL, 1); } void setup_apic_nmi_watchdog(void *unused) @@ -247,12 +296,13 @@ void setup_apic_nmi_watchdog(void *unused) /* cheap hack to support suspend/resume */ /* if cpu0 is not active neither should the other cpus */ - if ((smp_processor_id() != 0) && (atomic_read(&nmi_active) <= 0)) + if (smp_processor_id() != 0 && atomic_read(&nmi_active) <= 0) return; switch (nmi_watchdog) { case NMI_LOCAL_APIC: - __get_cpu_var(wd_enabled) = 1; /* enable it before to avoid race with handler */ + /* enable it before to avoid race with handler */ + __get_cpu_var(wd_enabled) = 1; if (lapic_watchdog_init(nmi_hz) < 0) { __get_cpu_var(wd_enabled) = 0; return; @@ -267,9 +317,8 @@ void setup_apic_nmi_watchdog(void *unused) void stop_apic_nmi_watchdog(void *unused) { /* only support LOCAL and IO APICs for now */ - if ((nmi_watchdog != NMI_LOCAL_APIC) && - (nmi_watchdog != NMI_IO_APIC)) - return; + if (!nmi_watchdog_active()) + return; if (__get_cpu_var(wd_enabled) == 0) return; if (nmi_watchdog == NMI_LOCAL_APIC) @@ -289,26 +338,26 @@ void stop_apic_nmi_watchdog(void *unused) * since NMIs don't listen to _any_ locks, we have to be extremely * careful not to rely on unsafe variables. The printk might lock * up though, so we have to break up any console locks first ... - * [when there will be more tty-related locks, break them up - * here too!] + * [when there will be more tty-related locks, break them up here too!] */ -static unsigned int - last_irq_sums [NR_CPUS], - alert_counter [NR_CPUS]; +static DEFINE_PER_CPU(unsigned, last_irq_sum); +static DEFINE_PER_CPU(local_t, alert_counter); +static DEFINE_PER_CPU(int, nmi_touch); void touch_nmi_watchdog(void) { - if (nmi_watchdog > 0) { + if (nmi_watchdog_active()) { unsigned cpu; /* - * Just reset the alert counters, (other CPUs might be - * spinning on locks we hold): + * Tell other CPUs to reset their alert counters. We cannot + * do it ourselves because the alert count increase is not + * atomic. */ for_each_present_cpu(cpu) { - if (alert_counter[cpu]) - alert_counter[cpu] = 0; + if (per_cpu(nmi_touch, cpu) != 1) + per_cpu(nmi_touch, cpu) = 1; } } @@ -319,12 +368,9 @@ void touch_nmi_watchdog(void) } EXPORT_SYMBOL(touch_nmi_watchdog); -extern void die_nmi(struct pt_regs *, const char *msg); - notrace __kprobes int nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) { - /* * Since current_thread_info()-> is always on the stack, and we * always switch the stack NMI-atomically, it's safe to use @@ -342,39 +388,45 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) touched = 1; } + sum = get_timer_irqs(cpu); + + if (__get_cpu_var(nmi_touch)) { + __get_cpu_var(nmi_touch) = 0; + touched = 1; + } + if (cpu_isset(cpu, backtrace_mask)) { static DEFINE_SPINLOCK(lock); /* Serialise the printks */ spin_lock(&lock); - printk("NMI backtrace for cpu %d\n", cpu); + printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu); dump_stack(); spin_unlock(&lock); cpu_clear(cpu, backtrace_mask); } - /* - * Take the local apic timer and PIT/HPET into account. We don't - * know which one is active, when we have highres/dyntick on - */ - sum = per_cpu(irq_stat, cpu).apic_timer_irqs + - per_cpu(irq_stat, cpu).irq0_irqs; + /* Could check oops_in_progress here too, but it's safer not to */ + if (mce_in_progress()) + touched = 1; /* if the none of the timers isn't firing, this cpu isn't doing much */ - if (!touched && last_irq_sums[cpu] == sum) { + if (!touched && __get_cpu_var(last_irq_sum) == sum) { /* * Ayiee, looks like this CPU is stuck ... * wait a few IRQs (5 seconds) before doing the oops ... */ - alert_counter[cpu]++; - if (alert_counter[cpu] == 5*nmi_hz) + local_inc(&__get_cpu_var(alert_counter)); + if (local_read(&__get_cpu_var(alert_counter)) == 5 * nmi_hz) /* * die_nmi will return ONLY if NOTIFY_STOP happens.. */ - die_nmi(regs, "BUG: NMI Watchdog detected LOCKUP"); + die_nmi("BUG: NMI Watchdog detected LOCKUP", + regs, panic_on_timeout); } else { - last_irq_sums[cpu] = sum; - alert_counter[cpu] = 0; + __get_cpu_var(last_irq_sum) = sum; + local_set(&__get_cpu_var(alert_counter), 0); } + /* see if the nmi watchdog went off */ if (!__get_cpu_var(wd_enabled)) return rc; @@ -383,7 +435,8 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) rc |= lapic_wd_event(nmi_hz); break; case NMI_IO_APIC: - /* don't know how to accurately check for this. + /* + * don't know how to accurately check for this. * just assume it was a watchdog timer interrupt * This matches the old behaviour. */ @@ -401,7 +454,7 @@ static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu) char buf[64]; sprintf(buf, "NMI received for unknown reason %02x\n", reason); - die_nmi(regs, buf); + die_nmi(buf, regs, 1); /* Always panic here */ return 0; } @@ -419,32 +472,26 @@ int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file, if (!!old_state == !!nmi_watchdog_enabled) return 0; - if (atomic_read(&nmi_active) < 0 || nmi_watchdog == NMI_DISABLED) { - printk( KERN_WARNING "NMI watchdog is permanently disabled\n"); + if (atomic_read(&nmi_active) < 0 || !nmi_watchdog_active()) { + printk(KERN_WARNING + "NMI watchdog is permanently disabled\n"); return -EIO; } - if (nmi_watchdog == NMI_DEFAULT) { - if (lapic_watchdog_ok()) - nmi_watchdog = NMI_LOCAL_APIC; - else - nmi_watchdog = NMI_IO_APIC; - } - if (nmi_watchdog == NMI_LOCAL_APIC) { if (nmi_watchdog_enabled) enable_lapic_nmi_watchdog(); else disable_lapic_nmi_watchdog(); } else { - printk( KERN_WARNING + printk(KERN_WARNING "NMI watchdog doesn't know what hardware to touch\n"); return -EIO; } return 0; } -#endif +#endif /* CONFIG_SYSCTL */ int do_nmi_callback(struct pt_regs *regs, int cpu) { @@ -467,6 +514,3 @@ void __trigger_all_cpu_backtrace(void) mdelay(1); } } - -EXPORT_SYMBOL(nmi_active); -EXPORT_SYMBOL(nmi_watchdog); diff --git a/arch/x86/kernel/nmi_64.c b/arch/x86/kernel/nmi_64.c deleted file mode 100644 index 5a29ded994fa..000000000000 --- a/arch/x86/kernel/nmi_64.c +++ /dev/null @@ -1,482 +0,0 @@ -/* - * NMI watchdog support on APIC systems - * - * Started by Ingo Molnar <mingo@redhat.com> - * - * Fixes: - * Mikael Pettersson : AMD K7 support for local APIC NMI watchdog. - * Mikael Pettersson : Power Management for local APIC NMI watchdog. - * Pavel Machek and - * Mikael Pettersson : PM converted to driver model. Disable/enable API. - */ - -#include <linux/nmi.h> -#include <linux/mm.h> -#include <linux/delay.h> -#include <linux/interrupt.h> -#include <linux/module.h> -#include <linux/sysdev.h> -#include <linux/sysctl.h> -#include <linux/kprobes.h> -#include <linux/cpumask.h> -#include <linux/kdebug.h> - -#include <asm/smp.h> -#include <asm/nmi.h> -#include <asm/proto.h> -#include <asm/mce.h> - -#include <mach_traps.h> - -int unknown_nmi_panic; -int nmi_watchdog_enabled; -int panic_on_unrecovered_nmi; - -static cpumask_t backtrace_mask = CPU_MASK_NONE; - -/* nmi_active: - * >0: the lapic NMI watchdog is active, but can be disabled - * <0: the lapic NMI watchdog has not been set up, and cannot - * be enabled - * 0: the lapic NMI watchdog is disabled, but can be enabled - */ -atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */ -static int panic_on_timeout; - -unsigned int nmi_watchdog = NMI_DEFAULT; -static unsigned int nmi_hz = HZ; - -static DEFINE_PER_CPU(short, wd_enabled); - -/* Run after command line and cpu_init init, but before all other checks */ -void nmi_watchdog_default(void) -{ - if (nmi_watchdog != NMI_DEFAULT) - return; - nmi_watchdog = NMI_NONE; -} - -static int endflag __initdata = 0; - -#ifdef CONFIG_SMP -/* The performance counters used by NMI_LOCAL_APIC don't trigger when - * the CPU is idle. To make sure the NMI watchdog really ticks on all - * CPUs during the test make them busy. - */ -static __init void nmi_cpu_busy(void *data) -{ - local_irq_enable_in_hardirq(); - /* Intentionally don't use cpu_relax here. This is - to make sure that the performance counter really ticks, - even if there is a simulator or similar that catches the - pause instruction. On a real HT machine this is fine because - all other CPUs are busy with "useless" delay loops and don't - care if they get somewhat less cycles. */ - while (endflag == 0) - mb(); -} -#endif - -int __init check_nmi_watchdog(void) -{ - int *prev_nmi_count; - int cpu; - - if ((nmi_watchdog == NMI_NONE) || (nmi_watchdog == NMI_DISABLED)) - return 0; - - if (!atomic_read(&nmi_active)) - return 0; - - prev_nmi_count = kmalloc(NR_CPUS * sizeof(int), GFP_KERNEL); - if (!prev_nmi_count) - return -1; - - printk(KERN_INFO "Testing NMI watchdog ... "); - -#ifdef CONFIG_SMP - if (nmi_watchdog == NMI_LOCAL_APIC) - smp_call_function(nmi_cpu_busy, (void *)&endflag, 0, 0); -#endif - - for (cpu = 0; cpu < NR_CPUS; cpu++) - prev_nmi_count[cpu] = cpu_pda(cpu)->__nmi_count; - local_irq_enable(); - mdelay((20*1000)/nmi_hz); // wait 20 ticks - - for_each_online_cpu(cpu) { - if (!per_cpu(wd_enabled, cpu)) - continue; - if (cpu_pda(cpu)->__nmi_count - prev_nmi_count[cpu] <= 5) { - printk(KERN_WARNING "WARNING: CPU#%d: NMI " - "appears to be stuck (%d->%d)!\n", - cpu, - prev_nmi_count[cpu], - cpu_pda(cpu)->__nmi_count); - per_cpu(wd_enabled, cpu) = 0; - atomic_dec(&nmi_active); - } - } - endflag = 1; - if (!atomic_read(&nmi_active)) { - kfree(prev_nmi_count); - atomic_set(&nmi_active, -1); - return -1; - } - printk("OK.\n"); - - /* now that we know it works we can reduce NMI frequency to - something more reasonable; makes a difference in some configs */ - if (nmi_watchdog == NMI_LOCAL_APIC) - nmi_hz = lapic_adjust_nmi_hz(1); - - kfree(prev_nmi_count); - return 0; -} - -static int __init setup_nmi_watchdog(char *str) -{ - int nmi; - - if (!strncmp(str,"panic",5)) { - panic_on_timeout = 1; - str = strchr(str, ','); - if (!str) - return 1; - ++str; - } - - get_option(&str, &nmi); - - if ((nmi >= NMI_INVALID) || (nmi < NMI_NONE)) - return 0; - - nmi_watchdog = nmi; - return 1; -} - -__setup("nmi_watchdog=", setup_nmi_watchdog); - -#ifdef CONFIG_PM - -static int nmi_pm_active; /* nmi_active before suspend */ - -static int lapic_nmi_suspend(struct sys_device *dev, pm_message_t state) -{ - /* only CPU0 goes here, other CPUs should be offline */ - nmi_pm_active = atomic_read(&nmi_active); - stop_apic_nmi_watchdog(NULL); - BUG_ON(atomic_read(&nmi_active) != 0); - return 0; -} - -static int lapic_nmi_resume(struct sys_device *dev) -{ - /* only CPU0 goes here, other CPUs should be offline */ - if (nmi_pm_active > 0) { - setup_apic_nmi_watchdog(NULL); - touch_nmi_watchdog(); - } - return 0; -} - -static struct sysdev_class nmi_sysclass = { - .name = "lapic_nmi", - .resume = lapic_nmi_resume, - .suspend = lapic_nmi_suspend, -}; - -static struct sys_device device_lapic_nmi = { - .id = 0, - .cls = &nmi_sysclass, -}; - -static int __init init_lapic_nmi_sysfs(void) -{ - int error; - - /* should really be a BUG_ON but b/c this is an - * init call, it just doesn't work. -dcz - */ - if (nmi_watchdog != NMI_LOCAL_APIC) - return 0; - - if (atomic_read(&nmi_active) < 0) - return 0; - - error = sysdev_class_register(&nmi_sysclass); - if (!error) - error = sysdev_register(&device_lapic_nmi); - return error; -} -/* must come after the local APIC's device_initcall() */ -late_initcall(init_lapic_nmi_sysfs); - -#endif /* CONFIG_PM */ - -static void __acpi_nmi_enable(void *__unused) -{ - apic_write(APIC_LVT0, APIC_DM_NMI); -} - -/* - * Enable timer based NMIs on all CPUs: - */ -void acpi_nmi_enable(void) -{ - if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC) - on_each_cpu(__acpi_nmi_enable, NULL, 0, 1); -} - -static void __acpi_nmi_disable(void *__unused) -{ - apic_write(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED); -} - -/* - * Disable timer based NMIs on all CPUs: - */ -void acpi_nmi_disable(void) -{ - if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC) - on_each_cpu(__acpi_nmi_disable, NULL, 0, 1); -} - -void setup_apic_nmi_watchdog(void *unused) -{ - if (__get_cpu_var(wd_enabled)) - return; - - /* cheap hack to support suspend/resume */ - /* if cpu0 is not active neither should the other cpus */ - if ((smp_processor_id() != 0) && (atomic_read(&nmi_active) <= 0)) - return; - - switch (nmi_watchdog) { - case NMI_LOCAL_APIC: - __get_cpu_var(wd_enabled) = 1; - if (lapic_watchdog_init(nmi_hz) < 0) { - __get_cpu_var(wd_enabled) = 0; - return; - } - /* FALL THROUGH */ - case NMI_IO_APIC: - __get_cpu_var(wd_enabled) = 1; - atomic_inc(&nmi_active); - } -} - -void stop_apic_nmi_watchdog(void *unused) -{ - /* only support LOCAL and IO APICs for now */ - if ((nmi_watchdog != NMI_LOCAL_APIC) && - (nmi_watchdog != NMI_IO_APIC)) - return; - if (__get_cpu_var(wd_enabled) == 0) - return; - if (nmi_watchdog == NMI_LOCAL_APIC) - lapic_watchdog_stop(); - __get_cpu_var(wd_enabled) = 0; - atomic_dec(&nmi_active); -} - -/* - * the best way to detect whether a CPU has a 'hard lockup' problem - * is to check it's local APIC timer IRQ counts. If they are not - * changing then that CPU has some problem. - * - * as these watchdog NMI IRQs are generated on every CPU, we only - * have to check the current processor. - */ - -static DEFINE_PER_CPU(unsigned, last_irq_sum); -static DEFINE_PER_CPU(local_t, alert_counter); -static DEFINE_PER_CPU(int, nmi_touch); - -void touch_nmi_watchdog(void) -{ - if (nmi_watchdog > 0) { - unsigned cpu; - - /* - * Tell other CPUs to reset their alert counters. We cannot - * do it ourselves because the alert count increase is not - * atomic. - */ - for_each_present_cpu(cpu) { - if (per_cpu(nmi_touch, cpu) != 1) - per_cpu(nmi_touch, cpu) = 1; - } - } - - touch_softlockup_watchdog(); -} -EXPORT_SYMBOL(touch_nmi_watchdog); - -notrace __kprobes int -nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) -{ - int sum; - int touched = 0; - int cpu = smp_processor_id(); - int rc = 0; - - /* check for other users first */ - if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) - == NOTIFY_STOP) { - rc = 1; - touched = 1; - } - - sum = read_pda(apic_timer_irqs) + read_pda(irq0_irqs); - if (__get_cpu_var(nmi_touch)) { - __get_cpu_var(nmi_touch) = 0; - touched = 1; - } - - if (cpu_isset(cpu, backtrace_mask)) { - static DEFINE_SPINLOCK(lock); /* Serialise the printks */ - - spin_lock(&lock); - printk("NMI backtrace for cpu %d\n", cpu); - dump_stack(); - spin_unlock(&lock); - cpu_clear(cpu, backtrace_mask); - } - -#ifdef CONFIG_X86_MCE - /* Could check oops_in_progress here too, but it's safer - not too */ - if (atomic_read(&mce_entry) > 0) - touched = 1; -#endif - /* if the apic timer isn't firing, this cpu isn't doing much */ - if (!touched && __get_cpu_var(last_irq_sum) == sum) { - /* - * Ayiee, looks like this CPU is stuck ... - * wait a few IRQs (5 seconds) before doing the oops ... - */ - local_inc(&__get_cpu_var(alert_counter)); - if (local_read(&__get_cpu_var(alert_counter)) == 5*nmi_hz) - die_nmi("NMI Watchdog detected LOCKUP on CPU %d\n", regs, - panic_on_timeout); - } else { - __get_cpu_var(last_irq_sum) = sum; - local_set(&__get_cpu_var(alert_counter), 0); - } - - /* see if the nmi watchdog went off */ - if (!__get_cpu_var(wd_enabled)) - return rc; - switch (nmi_watchdog) { - case NMI_LOCAL_APIC: - rc |= lapic_wd_event(nmi_hz); - break; - case NMI_IO_APIC: - /* don't know how to accurately check for this. - * just assume it was a watchdog timer interrupt - * This matches the old behaviour. - */ - rc = 1; - break; - } - return rc; -} - -static unsigned ignore_nmis; - -asmlinkage notrace __kprobes void -do_nmi(struct pt_regs *regs, long error_code) -{ - nmi_enter(); - add_pda(__nmi_count,1); - if (!ignore_nmis) - default_do_nmi(regs); - nmi_exit(); -} - -void stop_nmi(void) -{ - acpi_nmi_disable(); - ignore_nmis++; -} - -void restart_nmi(void) -{ - ignore_nmis--; - acpi_nmi_enable(); -} - -#ifdef CONFIG_SYSCTL - -static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu) -{ - unsigned char reason = get_nmi_reason(); - char buf[64]; - - sprintf(buf, "NMI received for unknown reason %02x\n", reason); - die_nmi(buf, regs, 1); /* Always panic here */ - return 0; -} - -/* - * proc handler for /proc/sys/kernel/nmi - */ -int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file, - void __user *buffer, size_t *length, loff_t *ppos) -{ - int old_state; - - nmi_watchdog_enabled = (atomic_read(&nmi_active) > 0) ? 1 : 0; - old_state = nmi_watchdog_enabled; - proc_dointvec(table, write, file, buffer, length, ppos); - if (!!old_state == !!nmi_watchdog_enabled) - return 0; - - if (atomic_read(&nmi_active) < 0 || nmi_watchdog == NMI_DISABLED) { - printk( KERN_WARNING "NMI watchdog is permanently disabled\n"); - return -EIO; - } - - /* if nmi_watchdog is not set yet, then set it */ - nmi_watchdog_default(); - - if (nmi_watchdog == NMI_LOCAL_APIC) { - if (nmi_watchdog_enabled) - enable_lapic_nmi_watchdog(); - else - disable_lapic_nmi_watchdog(); - } else { - printk( KERN_WARNING - "NMI watchdog doesn't know what hardware to touch\n"); - return -EIO; - } - return 0; -} - -#endif - -int do_nmi_callback(struct pt_regs *regs, int cpu) -{ -#ifdef CONFIG_SYSCTL - if (unknown_nmi_panic) - return unknown_nmi_panic_callback(regs, cpu); -#endif - return 0; -} - -void __trigger_all_cpu_backtrace(void) -{ - int i; - - backtrace_mask = cpu_online_map; - /* Wait for up to 10 seconds for all CPUs to do the backtrace */ - for (i = 0; i < 10 * 1000; i++) { - if (cpus_empty(backtrace_mask)) - break; - mdelay(1); - } -} - -EXPORT_SYMBOL(nmi_active); -EXPORT_SYMBOL(nmi_watchdog); diff --git a/arch/x86/kernel/numaq_32.c b/arch/x86/kernel/numaq_32.c index e65281b1634b..a23e8233b9ac 100644 --- a/arch/x86/kernel/numaq_32.c +++ b/arch/x86/kernel/numaq_32.c @@ -31,6 +31,8 @@ #include <asm/numaq.h> #include <asm/topology.h> #include <asm/processor.h> +#include <asm/mpspec.h> +#include <asm/e820.h> #define MB_TO_PAGES(addr) ((addr) << (20 - PAGE_SHIFT)) @@ -58,6 +60,8 @@ static void __init smp_dump_qct(void) node_end_pfn[node] = MB_TO_PAGES( eq->hi_shrd_mem_start + eq->hi_shrd_mem_size); + e820_register_active_regions(node, node_start_pfn[node], + node_end_pfn[node]); memory_present(node, node_start_pfn[node], node_end_pfn[node]); node_remap_size[node] = node_memmap_size_bytes(node, @@ -67,23 +71,35 @@ static void __init smp_dump_qct(void) } } -/* - * Unlike Summit, we don't really care to let the NUMA-Q - * fall back to flat mode. Don't compile for NUMA-Q - * unless you really need it! - */ +static __init void early_check_numaq(void) +{ + /* + * Find possible boot-time SMP configuration: + */ + early_find_smp_config(); + /* + * get boot-time SMP configuration: + */ + if (smp_found_config) + early_get_smp_config(); +} + int __init get_memcfg_numaq(void) { + early_check_numaq(); + if (!found_numaq) + return 0; smp_dump_qct(); return 1; } -static int __init numaq_tsc_disable(void) +void __init numaq_tsc_disable(void) { + if (!found_numaq) + return; + if (num_online_nodes() > 1) { printk(KERN_DEBUG "NUMAQ: disabling TSC\n"); setup_clear_cpu_cap(X86_FEATURE_TSC); } - return 0; } -arch_initcall(numaq_tsc_disable); diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 74f0c5ea2a03..e0f571d58c19 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -30,6 +30,7 @@ #include <asm/setup.h> #include <asm/arch_hooks.h> #include <asm/time.h> +#include <asm/pgalloc.h> #include <asm/irq.h> #include <asm/delay.h> #include <asm/fixmap.h> @@ -139,7 +140,9 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf, /* If the operation is a nop, then nop the callsite */ ret = paravirt_patch_nop(); else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) || - type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_syscall_ret)) + type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit) || + type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret32) || + type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret64)) /* If operation requires a jmp, then jmp */ ret = paravirt_patch_jmp(insnbuf, opfunc, addr, len); else @@ -190,7 +193,9 @@ static void native_flush_tlb_single(unsigned long addr) /* These are in entry.S */ extern void native_iret(void); -extern void native_irq_enable_syscall_ret(void); +extern void native_irq_enable_sysexit(void); +extern void native_usergs_sysret32(void); +extern void native_usergs_sysret64(void); static int __init print_banner(void) { @@ -280,7 +285,7 @@ struct pv_time_ops pv_time_ops = { .get_wallclock = native_get_wallclock, .set_wallclock = native_set_wallclock, .sched_clock = native_sched_clock, - .get_cpu_khz = native_calculate_cpu_khz, + .get_tsc_khz = native_calibrate_tsc, }; struct pv_irq_ops pv_irq_ops = { @@ -291,6 +296,9 @@ struct pv_irq_ops pv_irq_ops = { .irq_enable = native_irq_enable, .safe_halt = native_safe_halt, .halt = native_halt, +#ifdef CONFIG_X86_64 + .adjust_exception_frame = paravirt_nop, +#endif }; struct pv_cpu_ops pv_cpu_ops = { @@ -321,12 +329,23 @@ struct pv_cpu_ops pv_cpu_ops = { .store_idt = native_store_idt, .store_tr = native_store_tr, .load_tls = native_load_tls, +#ifdef CONFIG_X86_64 + .load_gs_index = native_load_gs_index, +#endif .write_ldt_entry = native_write_ldt_entry, .write_gdt_entry = native_write_gdt_entry, .write_idt_entry = native_write_idt_entry, .load_sp0 = native_load_sp0, - .irq_enable_syscall_ret = native_irq_enable_syscall_ret, +#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) + .irq_enable_sysexit = native_irq_enable_sysexit, +#endif +#ifdef CONFIG_X86_64 +#ifdef CONFIG_IA32_EMULATION + .usergs_sysret32 = native_usergs_sysret32, +#endif + .usergs_sysret64 = native_usergs_sysret64, +#endif .iret = native_iret, .swapgs = native_swapgs, @@ -366,6 +385,9 @@ struct pv_mmu_ops pv_mmu_ops = { .flush_tlb_single = native_flush_tlb_single, .flush_tlb_others = native_flush_tlb_others, + .pgd_alloc = __paravirt_pgd_alloc, + .pgd_free = paravirt_nop, + .alloc_pte = paravirt_nop, .alloc_pmd = paravirt_nop, .alloc_pmd_clone = paravirt_nop, @@ -380,6 +402,9 @@ struct pv_mmu_ops pv_mmu_ops = { .pte_update = paravirt_nop, .pte_update_defer = paravirt_nop, + .ptep_modify_prot_start = __ptep_modify_prot_start, + .ptep_modify_prot_commit = __ptep_modify_prot_commit, + #ifdef CONFIG_HIGHPTE .kmap_atomic_pte = kmap_atomic, #endif @@ -403,6 +428,7 @@ struct pv_mmu_ops pv_mmu_ops = { #endif /* PAGETABLE_LEVELS >= 3 */ .pte_val = native_pte_val, + .pte_flags = native_pte_val, .pgd_val = native_pgd_val, .make_pte = native_make_pte, @@ -416,6 +442,8 @@ struct pv_mmu_ops pv_mmu_ops = { .enter = paravirt_nop, .leave = paravirt_nop, }, + + .set_fixmap = native_set_fixmap, }; EXPORT_SYMBOL_GPL(pv_time_ops); diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c index 82fc5fcab4f4..58262218781b 100644 --- a/arch/x86/kernel/paravirt_patch_32.c +++ b/arch/x86/kernel/paravirt_patch_32.c @@ -5,7 +5,7 @@ DEF_NATIVE(pv_irq_ops, irq_enable, "sti"); DEF_NATIVE(pv_irq_ops, restore_fl, "push %eax; popf"); DEF_NATIVE(pv_irq_ops, save_fl, "pushf; pop %eax"); DEF_NATIVE(pv_cpu_ops, iret, "iret"); -DEF_NATIVE(pv_cpu_ops, irq_enable_syscall_ret, "sti; sysexit"); +DEF_NATIVE(pv_cpu_ops, irq_enable_sysexit, "sti; sysexit"); DEF_NATIVE(pv_mmu_ops, read_cr2, "mov %cr2, %eax"); DEF_NATIVE(pv_mmu_ops, write_cr3, "mov %eax, %cr3"); DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax"); @@ -29,7 +29,7 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_irq_ops, restore_fl); PATCH_SITE(pv_irq_ops, save_fl); PATCH_SITE(pv_cpu_ops, iret); - PATCH_SITE(pv_cpu_ops, irq_enable_syscall_ret); + PATCH_SITE(pv_cpu_ops, irq_enable_sysexit); PATCH_SITE(pv_mmu_ops, read_cr2); PATCH_SITE(pv_mmu_ops, read_cr3); PATCH_SITE(pv_mmu_ops, write_cr3); diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index 7d904e138d7e..061d01df9ae6 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -14,8 +14,9 @@ DEF_NATIVE(pv_mmu_ops, flush_tlb_single, "invlpg (%rdi)"); DEF_NATIVE(pv_cpu_ops, clts, "clts"); DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd"); -/* the three commands give us more control to how to return from a syscall */ -DEF_NATIVE(pv_cpu_ops, irq_enable_syscall_ret, "movq %gs:" __stringify(pda_oldrsp) ", %rsp; swapgs; sysretq;"); +DEF_NATIVE(pv_cpu_ops, irq_enable_sysexit, "swapgs; sti; sysexit"); +DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq"); +DEF_NATIVE(pv_cpu_ops, usergs_sysret32, "swapgs; sysretl"); DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs"); unsigned native_patch(u8 type, u16 clobbers, void *ibuf, @@ -35,7 +36,9 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_irq_ops, irq_enable); PATCH_SITE(pv_irq_ops, irq_disable); PATCH_SITE(pv_cpu_ops, iret); - PATCH_SITE(pv_cpu_ops, irq_enable_syscall_ret); + PATCH_SITE(pv_cpu_ops, irq_enable_sysexit); + PATCH_SITE(pv_cpu_ops, usergs_sysret32); + PATCH_SITE(pv_cpu_ops, usergs_sysret64); PATCH_SITE(pv_cpu_ops, swapgs); PATCH_SITE(pv_mmu_ops, read_cr2); PATCH_SITE(pv_mmu_ops, read_cr3); diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index e28ec497e142..6959b5c45df4 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -1394,7 +1394,7 @@ void __init detect_calgary(void) return; } - specified_table_size = determine_tce_table_size(end_pfn * PAGE_SIZE); + specified_table_size = determine_tce_table_size(max_pfn * PAGE_SIZE); for (bus = 0; bus < MAX_PHB_BUS_NUM; bus++) { struct calgary_bus_info *info = &bus_info[bus]; @@ -1459,7 +1459,7 @@ int __init calgary_iommu_init(void) if (ret) { printk(KERN_ERR "PCI-DMA: Calgary init failed %d, " "falling back to no_iommu\n", ret); - if (end_pfn > MAX_DMA32_PFN) + if (max_pfn > MAX_DMA32_PFN) printk(KERN_ERR "WARNING more than 4GB of memory, " "32bit PCI may malfunction.\n"); return ret; diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index c5ef1af8e79d..8467ec2320f1 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -7,6 +7,7 @@ #include <asm/dma.h> #include <asm/gart.h> #include <asm/calgary.h> +#include <asm/amd_iommu.h> int forbid_dac __read_mostly; EXPORT_SYMBOL(forbid_dac); @@ -74,13 +75,17 @@ early_param("dma32_size", parse_dma32_size_opt); void __init dma32_reserve_bootmem(void) { unsigned long size, align; - if (end_pfn <= MAX_DMA32_PFN) + if (max_pfn <= MAX_DMA32_PFN) return; + /* + * check aperture_64.c allocate_aperture() for reason about + * using 512M as goal + */ align = 64ULL<<20; size = round_up(dma32_bootmem_size, align); dma32_bootmem_ptr = __alloc_bootmem_nopanic(size, align, - __pa(MAX_DMA_ADDRESS)); + 512ULL<<20); if (dma32_bootmem_ptr) dma32_bootmem_size = size; else @@ -88,17 +93,14 @@ void __init dma32_reserve_bootmem(void) } static void __init dma32_free_bootmem(void) { - int node; - if (end_pfn <= MAX_DMA32_PFN) + if (max_pfn <= MAX_DMA32_PFN) return; if (!dma32_bootmem_ptr) return; - for_each_online_node(node) - free_bootmem_node(NODE_DATA(node), __pa(dma32_bootmem_ptr), - dma32_bootmem_size); + free_bootmem(__pa(dma32_bootmem_ptr), dma32_bootmem_size); dma32_bootmem_ptr = NULL; dma32_bootmem_size = 0; @@ -122,6 +124,8 @@ void __init pci_iommu_alloc(void) detect_intel_iommu(); + amd_iommu_detect(); + #ifdef CONFIG_SWIOTLB pci_swiotlb_init(); #endif @@ -357,7 +361,7 @@ int dma_supported(struct device *dev, u64 mask) EXPORT_SYMBOL(dma_supported); /* Allocate DMA memory on node near device */ -noinline struct page * +static noinline struct page * dma_alloc_pages(struct device *dev, gfp_t gfp, unsigned order) { int node; @@ -378,6 +382,7 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, struct page *page; unsigned long dma_mask = 0; dma_addr_t bus; + int noretry = 0; /* ignore region specifiers */ gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); @@ -397,20 +402,25 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, if (dev->dma_mask == NULL) return NULL; - /* Don't invoke OOM killer */ - gfp |= __GFP_NORETRY; + /* Don't invoke OOM killer or retry in lower 16MB DMA zone */ + if (gfp & __GFP_DMA) + noretry = 1; #ifdef CONFIG_X86_64 /* Why <=? Even when the mask is smaller than 4GB it is often larger than 16MB and in this case we have a chance of finding fitting memory in the next higher zone first. If not retry with true GFP_DMA. -AK */ - if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA)) + if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA)) { gfp |= GFP_DMA32; + if (dma_mask < DMA_32BIT_MASK) + noretry = 1; + } #endif again: - page = dma_alloc_pages(dev, gfp, get_order(size)); + page = dma_alloc_pages(dev, + noretry ? gfp | __GFP_NORETRY : gfp, get_order(size)); if (page == NULL) return NULL; @@ -496,6 +506,8 @@ static int __init pci_iommu_init(void) intel_iommu_init(); + amd_iommu_init(); + #ifdef CONFIG_GART_IOMMU gart_iommu_init(); #endif diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index c07455d1695f..c3fe78406d18 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -26,6 +26,7 @@ #include <linux/kdebug.h> #include <linux/scatterlist.h> #include <linux/iommu-helper.h> +#include <linux/sysdev.h> #include <asm/atomic.h> #include <asm/io.h> #include <asm/mtrr.h> @@ -103,7 +104,6 @@ static unsigned long alloc_iommu(struct device *dev, int size) size, base_index, boundary_size, 0); } if (offset != -1) { - set_bit_string(iommu_gart_bitmap, offset, size); next_bit = offset+size; if (next_bit >= iommu_pages) { next_bit = 0; @@ -533,8 +533,8 @@ static __init unsigned read_aperture(struct pci_dev *dev, u32 *size) unsigned aper_size = 0, aper_base_32, aper_order; u64 aper_base; - pci_read_config_dword(dev, 0x94, &aper_base_32); - pci_read_config_dword(dev, 0x90, &aper_order); + pci_read_config_dword(dev, AMD64_GARTAPERTUREBASE, &aper_base_32); + pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &aper_order); aper_order = (aper_order >> 1) & 7; aper_base = aper_base_32 & 0x7fff; @@ -548,6 +548,77 @@ static __init unsigned read_aperture(struct pci_dev *dev, u32 *size) return aper_base; } +static void enable_gart_translations(void) +{ + int i; + + for (i = 0; i < num_k8_northbridges; i++) { + struct pci_dev *dev = k8_northbridges[i]; + + enable_gart_translation(dev, __pa(agp_gatt_table)); + } +} + +/* + * If fix_up_north_bridges is set, the north bridges have to be fixed up on + * resume in the same way as they are handled in gart_iommu_hole_init(). + */ +static bool fix_up_north_bridges; +static u32 aperture_order; +static u32 aperture_alloc; + +void set_up_gart_resume(u32 aper_order, u32 aper_alloc) +{ + fix_up_north_bridges = true; + aperture_order = aper_order; + aperture_alloc = aper_alloc; +} + +static int gart_resume(struct sys_device *dev) +{ + printk(KERN_INFO "PCI-DMA: Resuming GART IOMMU\n"); + + if (fix_up_north_bridges) { + int i; + + printk(KERN_INFO "PCI-DMA: Restoring GART aperture settings\n"); + + for (i = 0; i < num_k8_northbridges; i++) { + struct pci_dev *dev = k8_northbridges[i]; + + /* + * Don't enable translations just yet. That is the next + * step. Restore the pre-suspend aperture settings. + */ + pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, + aperture_order << 1); + pci_write_config_dword(dev, AMD64_GARTAPERTUREBASE, + aperture_alloc >> 25); + } + } + + enable_gart_translations(); + + return 0; +} + +static int gart_suspend(struct sys_device *dev, pm_message_t state) +{ + return 0; +} + +static struct sysdev_class gart_sysdev_class = { + .name = "gart", + .suspend = gart_suspend, + .resume = gart_resume, + +}; + +static struct sys_device device_gart = { + .id = 0, + .cls = &gart_sysdev_class, +}; + /* * Private Northbridge GATT initialization in case we cannot use the * AGP driver for some reason. @@ -558,7 +629,8 @@ static __init int init_k8_gatt(struct agp_kern_info *info) unsigned aper_base, new_aper_base; struct pci_dev *dev; void *gatt; - int i; + int i, error; + unsigned long start_pfn, end_pfn; printk(KERN_INFO "PCI-DMA: Disabling AGP.\n"); aper_size = aper_base = info->aper_size = 0; @@ -591,25 +663,25 @@ static __init int init_k8_gatt(struct agp_kern_info *info) memset(gatt, 0, gatt_size); agp_gatt_table = gatt; - for (i = 0; i < num_k8_northbridges; i++) { - u32 gatt_reg; - u32 ctl; + enable_gart_translations(); - dev = k8_northbridges[i]; - gatt_reg = __pa(gatt) >> 12; - gatt_reg <<= 4; - pci_write_config_dword(dev, 0x98, gatt_reg); - pci_read_config_dword(dev, 0x90, &ctl); - - ctl |= 1; - ctl &= ~((1<<4) | (1<<5)); + error = sysdev_class_register(&gart_sysdev_class); + if (!error) + error = sysdev_register(&device_gart); + if (error) + panic("Could not register gart_sysdev -- would corrupt data on next suspend"); - pci_write_config_dword(dev, 0x90, ctl); - } flush_gart(); printk(KERN_INFO "PCI-DMA: aperture base @ %x size %u KB\n", aper_base, aper_size>>10); + + /* need to map that range */ + end_pfn = (aper_base>>PAGE_SHIFT) + (aper_size>>PAGE_SHIFT); + if (end_pfn > max_low_pfn_mapped) { + start_pfn = (aper_base>>PAGE_SHIFT); + init_memory_mapping(start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT); + } return 0; nommu: @@ -648,11 +720,11 @@ void gart_iommu_shutdown(void) u32 ctl; dev = k8_northbridges[i]; - pci_read_config_dword(dev, 0x90, &ctl); + pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl); - ctl &= ~1; + ctl &= ~GARTEN; - pci_write_config_dword(dev, 0x90, ctl); + pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl); } } @@ -687,10 +759,10 @@ void __init gart_iommu_init(void) return; if (no_iommu || - (!force_iommu && end_pfn <= MAX_DMA32_PFN) || + (!force_iommu && max_pfn <= MAX_DMA32_PFN) || !gart_iommu_aperture || (no_agp && init_k8_gatt(&info) < 0)) { - if (end_pfn > MAX_DMA32_PFN) { + if (max_pfn > MAX_DMA32_PFN) { printk(KERN_WARNING "More than 4GB of memory " "but GART IOMMU not available.\n" KERN_WARNING "falling back to iommu=soft.\n"); @@ -759,10 +831,10 @@ void __init gart_iommu_init(void) wbinvd(); /* - * Try to workaround a bug (thanks to BenH) + * Try to workaround a bug (thanks to BenH): * Set unmapped entries to a scratch page instead of 0. * Any prefetches that hit unmapped entries won't get an bus abort - * then. + * then. (P2P bridge may be prefetching on DMA reads). */ scratch = get_zeroed_page(GFP_KERNEL); if (!scratch) diff --git a/arch/x86/kernel/pci-swiotlb_64.c b/arch/x86/kernel/pci-swiotlb_64.c index 490da7f4b8d0..82299cd1d04d 100644 --- a/arch/x86/kernel/pci-swiotlb_64.c +++ b/arch/x86/kernel/pci-swiotlb_64.c @@ -38,7 +38,7 @@ const struct dma_mapping_ops swiotlb_dma_ops = { void __init pci_swiotlb_init(void) { /* don't initialize swiotlb if iommu=off (no_iommu=1) */ - if (!iommu_detected && !no_iommu && end_pfn > MAX_DMA32_PFN) + if (!iommu_detected && !no_iommu && max_pfn > MAX_DMA32_PFN) swiotlb = 1; if (swiotlb_force) swiotlb = 1; diff --git a/arch/x86/kernel/probe_roms_32.c b/arch/x86/kernel/probe_roms_32.c new file mode 100644 index 000000000000..675a48c404a5 --- /dev/null +++ b/arch/x86/kernel/probe_roms_32.c @@ -0,0 +1,166 @@ +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/uaccess.h> +#include <linux/mmzone.h> +#include <linux/ioport.h> +#include <linux/seq_file.h> +#include <linux/console.h> +#include <linux/init.h> +#include <linux/edd.h> +#include <linux/dmi.h> +#include <linux/pfn.h> +#include <linux/pci.h> +#include <asm/pci-direct.h> + + +#include <asm/e820.h> +#include <asm/mmzone.h> +#include <asm/setup.h> +#include <asm/sections.h> +#include <asm/io.h> +#include <setup_arch.h> + +static struct resource system_rom_resource = { + .name = "System ROM", + .start = 0xf0000, + .end = 0xfffff, + .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM +}; + +static struct resource extension_rom_resource = { + .name = "Extension ROM", + .start = 0xe0000, + .end = 0xeffff, + .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM +}; + +static struct resource adapter_rom_resources[] = { { + .name = "Adapter ROM", + .start = 0xc8000, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM +}, { + .name = "Adapter ROM", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM +}, { + .name = "Adapter ROM", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM +}, { + .name = "Adapter ROM", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM +}, { + .name = "Adapter ROM", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM +}, { + .name = "Adapter ROM", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM +} }; + +static struct resource video_rom_resource = { + .name = "Video ROM", + .start = 0xc0000, + .end = 0xc7fff, + .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM +}; + +#define ROMSIGNATURE 0xaa55 + +static int __init romsignature(const unsigned char *rom) +{ + const unsigned short * const ptr = (const unsigned short *)rom; + unsigned short sig; + + return probe_kernel_address(ptr, sig) == 0 && sig == ROMSIGNATURE; +} + +static int __init romchecksum(const unsigned char *rom, unsigned long length) +{ + unsigned char sum, c; + + for (sum = 0; length && probe_kernel_address(rom++, c) == 0; length--) + sum += c; + return !length && !sum; +} + +void __init probe_roms(void) +{ + const unsigned char *rom; + unsigned long start, length, upper; + unsigned char c; + int i; + + /* video rom */ + upper = adapter_rom_resources[0].start; + for (start = video_rom_resource.start; start < upper; start += 2048) { + rom = isa_bus_to_virt(start); + if (!romsignature(rom)) + continue; + + video_rom_resource.start = start; + + if (probe_kernel_address(rom + 2, c) != 0) + continue; + + /* 0 < length <= 0x7f * 512, historically */ + length = c * 512; + + /* if checksum okay, trust length byte */ + if (length && romchecksum(rom, length)) + video_rom_resource.end = start + length - 1; + + request_resource(&iomem_resource, &video_rom_resource); + break; + } + + start = (video_rom_resource.end + 1 + 2047) & ~2047UL; + if (start < upper) + start = upper; + + /* system rom */ + request_resource(&iomem_resource, &system_rom_resource); + upper = system_rom_resource.start; + + /* check for extension rom (ignore length byte!) */ + rom = isa_bus_to_virt(extension_rom_resource.start); + if (romsignature(rom)) { + length = extension_rom_resource.end - extension_rom_resource.start + 1; + if (romchecksum(rom, length)) { + request_resource(&iomem_resource, &extension_rom_resource); + upper = extension_rom_resource.start; + } + } + + /* check for adapter roms on 2k boundaries */ + for (i = 0; i < ARRAY_SIZE(adapter_rom_resources) && start < upper; start += 2048) { + rom = isa_bus_to_virt(start); + if (!romsignature(rom)) + continue; + + if (probe_kernel_address(rom + 2, c) != 0) + continue; + + /* 0 < length <= 0x7f * 512, historically */ + length = c * 512; + + /* but accept any length that fits if checksum okay */ + if (!length || start + length > upper || !romchecksum(rom, length)) + continue; + + adapter_rom_resources[i].start = start; + adapter_rom_resources[i].end = start + length - 1; + request_resource(&iomem_resource, &adapter_rom_resources[i]); + + start = adapter_rom_resources[i++].end & ~2047UL; + } +} + diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index ba370dc8685b..4d629c62f4f8 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -6,6 +6,13 @@ #include <linux/sched.h> #include <linux/module.h> #include <linux/pm.h> +#include <linux/clockchips.h> +#include <asm/system.h> + +unsigned long idle_halt; +EXPORT_SYMBOL(idle_halt); +unsigned long idle_nomwait; +EXPORT_SYMBOL(idle_nomwait); struct kmem_cache *task_xstate_cachep; @@ -45,6 +52,76 @@ void arch_task_cache_init(void) SLAB_PANIC, NULL); } +/* + * Idle related variables and functions + */ +unsigned long boot_option_idle_override = 0; +EXPORT_SYMBOL(boot_option_idle_override); + +/* + * Powermanagement idle function, if any.. + */ +void (*pm_idle)(void); +EXPORT_SYMBOL(pm_idle); + +#ifdef CONFIG_X86_32 +/* + * This halt magic was a workaround for ancient floppy DMA + * wreckage. It should be safe to remove. + */ +static int hlt_counter; +void disable_hlt(void) +{ + hlt_counter++; +} +EXPORT_SYMBOL(disable_hlt); + +void enable_hlt(void) +{ + hlt_counter--; +} +EXPORT_SYMBOL(enable_hlt); + +static inline int hlt_use_halt(void) +{ + return (!hlt_counter && boot_cpu_data.hlt_works_ok); +} +#else +static inline int hlt_use_halt(void) +{ + return 1; +} +#endif + +/* + * We use this if we don't have any better + * idle routine.. + */ +void default_idle(void) +{ + if (hlt_use_halt()) { + current_thread_info()->status &= ~TS_POLLING; + /* + * TS_POLLING-cleared state must be visible before we + * test NEED_RESCHED: + */ + smp_mb(); + + if (!need_resched()) + safe_halt(); /* enables interrupts racelessly */ + else + local_irq_enable(); + current_thread_info()->status |= TS_POLLING; + } else { + local_irq_enable(); + /* loop is done by the caller */ + cpu_relax(); + } +} +#ifdef CONFIG_APM_MODULE +EXPORT_SYMBOL(default_idle); +#endif + static void do_nothing(void *unused) { } @@ -61,7 +138,7 @@ void cpu_idle_wait(void) { smp_mb(); /* kick all the CPUs so that they exit out of pm_idle */ - smp_call_function(do_nothing, NULL, 0, 1); + smp_call_function(do_nothing, NULL, 1); } EXPORT_SYMBOL_GPL(cpu_idle_wait); @@ -122,44 +199,129 @@ static void poll_idle(void) * * idle=mwait overrides this decision and forces the usage of mwait. */ + +#define MWAIT_INFO 0x05 +#define MWAIT_ECX_EXTENDED_INFO 0x01 +#define MWAIT_EDX_C1 0xf0 + static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c) { + u32 eax, ebx, ecx, edx; + if (force_mwait) return 1; - if (c->x86_vendor == X86_VENDOR_AMD) { - switch(c->x86) { - case 0x10: - case 0x11: - return 0; - } - } + if (c->cpuid_level < MWAIT_INFO) + return 0; + + cpuid(MWAIT_INFO, &eax, &ebx, &ecx, &edx); + /* Check, whether EDX has extended info about MWAIT */ + if (!(ecx & MWAIT_ECX_EXTENDED_INFO)) + return 1; + + /* + * edx enumeratios MONITOR/MWAIT extensions. Check, whether + * C1 supports MWAIT + */ + return (edx & MWAIT_EDX_C1); +} + +/* + * Check for AMD CPUs, which have potentially C1E support + */ +static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c) +{ + if (c->x86_vendor != X86_VENDOR_AMD) + return 0; + + if (c->x86 < 0x0F) + return 0; + + /* Family 0x0f models < rev F do not have C1E */ + if (c->x86 == 0x0f && c->x86_model < 0x40) + return 0; + return 1; } -void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) +/* + * C1E aware idle routine. We check for C1E active in the interrupt + * pending message MSR. If we detect C1E, then we handle it the same + * way as C3 power states (local apic timer and TSC stop) + */ +static void c1e_idle(void) { - static int selected; + static cpumask_t c1e_mask = CPU_MASK_NONE; + static int c1e_detected; - if (selected) + if (need_resched()) return; + + if (!c1e_detected) { + u32 lo, hi; + + rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi); + if (lo & K8_INTP_C1E_ACTIVE_MASK) { + c1e_detected = 1; + mark_tsc_unstable("TSC halt in C1E"); + printk(KERN_INFO "System has C1E enabled\n"); + } + } + + if (c1e_detected) { + int cpu = smp_processor_id(); + + if (!cpu_isset(cpu, c1e_mask)) { + cpu_set(cpu, c1e_mask); + /* + * Force broadcast so ACPI can not interfere. Needs + * to run with interrupts enabled as it uses + * smp_function_call. + */ + local_irq_enable(); + clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE, + &cpu); + printk(KERN_INFO "Switch to broadcast mode on CPU%d\n", + cpu); + local_irq_disable(); + } + clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu); + + default_idle(); + + /* + * The switch back from broadcast mode needs to be + * called with interrupts disabled. + */ + local_irq_disable(); + clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu); + local_irq_enable(); + } else + default_idle(); +} + +void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) +{ #ifdef CONFIG_X86_SMP if (pm_idle == poll_idle && smp_num_siblings > 1) { printk(KERN_WARNING "WARNING: polling idle and HT enabled," " performance may degrade.\n"); } #endif + if (pm_idle) + return; + if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) { /* - * Skip, if setup has overridden idle. * One CPU supports mwait => All CPUs supports mwait */ - if (!pm_idle) { - printk(KERN_INFO "using mwait in idle threads.\n"); - pm_idle = mwait_idle; - } - } - selected = 1; + printk(KERN_INFO "using mwait in idle threads.\n"); + pm_idle = mwait_idle; + } else if (check_c1e_idle(c)) { + printk(KERN_INFO "using C1E aware idle routine\n"); + pm_idle = c1e_idle; + } else + pm_idle = default_idle; } static int __init idle_setup(char *str) @@ -169,7 +331,27 @@ static int __init idle_setup(char *str) pm_idle = poll_idle; } else if (!strcmp(str, "mwait")) force_mwait = 1; - else + else if (!strcmp(str, "halt")) { + /* + * When the boot option of idle=halt is added, halt is + * forced to be used for CPU idle. In such case CPU C2/C3 + * won't be used again. + * To continue to load the CPU idle driver, don't touch + * the boot_option_idle_override. + */ + pm_idle = default_idle; + idle_halt = 1; + return 0; + } else if (!strcmp(str, "nomwait")) { + /* + * If the boot option of "idle=nomwait" is added, + * it means that mwait will be disabled for CPU C2/C3 + * states. In such case it won't touch the variable + * of boot_option_idle_override. + */ + idle_nomwait = 1; + return 0; + } else return -1; boot_option_idle_override = 1; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 1f5fa1cf16dd..53bc653ed5ca 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -58,11 +58,6 @@ asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); -static int hlt_counter; - -unsigned long boot_option_idle_override = 0; -EXPORT_SYMBOL(boot_option_idle_override); - DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task; EXPORT_PER_CPU_SYMBOL(current_task); @@ -77,57 +72,24 @@ unsigned long thread_saved_pc(struct task_struct *tsk) return ((unsigned long *)tsk->thread.sp)[3]; } -/* - * Powermanagement idle function, if any.. - */ -void (*pm_idle)(void); -EXPORT_SYMBOL(pm_idle); +#ifdef CONFIG_HOTPLUG_CPU +#include <asm/nmi.h> -void disable_hlt(void) +static void cpu_exit_clear(void) { - hlt_counter++; -} + int cpu = raw_smp_processor_id(); -EXPORT_SYMBOL(disable_hlt); + idle_task_exit(); -void enable_hlt(void) -{ - hlt_counter--; -} + cpu_uninit(); + irq_ctx_exit(cpu); -EXPORT_SYMBOL(enable_hlt); + cpu_clear(cpu, cpu_callout_map); + cpu_clear(cpu, cpu_callin_map); -/* - * We use this if we don't have any better - * idle routine.. - */ -void default_idle(void) -{ - if (!hlt_counter && boot_cpu_data.hlt_works_ok) { - current_thread_info()->status &= ~TS_POLLING; - /* - * TS_POLLING-cleared state must be visible before we - * test NEED_RESCHED: - */ - smp_mb(); - - if (!need_resched()) - safe_halt(); /* enables interrupts racelessly */ - else - local_irq_enable(); - current_thread_info()->status |= TS_POLLING; - } else { - local_irq_enable(); - /* loop is done by the caller */ - cpu_relax(); - } + numa_remove_cpu(cpu); } -#ifdef CONFIG_APM_MODULE -EXPORT_SYMBOL(default_idle); -#endif -#ifdef CONFIG_HOTPLUG_CPU -#include <asm/nmi.h> /* We don't actually take CPU down, just spin without interrupts. */ static inline void play_dead(void) { @@ -168,24 +130,22 @@ void cpu_idle(void) while (1) { tick_nohz_stop_sched_tick(1); while (!need_resched()) { - void (*idle)(void); check_pgt_cache(); rmb(); - idle = pm_idle; if (rcu_pending(cpu)) rcu_check_callbacks(cpu, 0); - if (!idle) - idle = default_idle; - if (cpu_is_offline(cpu)) play_dead(); local_irq_disable(); __get_cpu_var(irq_stat).idle_timestamp = jiffies; - idle(); + /* Don't trace irqs off for idle */ + stop_critical_timings(); + pm_idle(); + start_critical_timings(); } tick_nohz_restart_sched_tick(); preempt_enable_no_resched(); @@ -333,6 +293,7 @@ void flush_thread(void) /* * Forget coprocessor state.. */ + tsk->fpu_counter = 0; clear_fpu(tsk); clear_used_math(); } @@ -649,8 +610,11 @@ struct task_struct * __switch_to(struct task_struct *prev_p, struct task_struct /* If the task has used fpu the last 5 timeslices, just do a full * restore of the math state immediately to avoid the trap; the * chances of needing FPU soon are obviously high now + * + * tsk_used_math() checks prevent calling math_state_restore(), + * which can sleep in the case of !tsk_used_math() */ - if (next_p->fpu_counter > 5) + if (tsk_used_math(next_p) && next_p->fpu_counter > 5) math_state_restore(); /* diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index c0a5c2a687e6..9a10c1897921 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -56,15 +56,6 @@ asmlinkage extern void ret_from_fork(void); unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED; -unsigned long boot_option_idle_override = 0; -EXPORT_SYMBOL(boot_option_idle_override); - -/* - * Powermanagement idle function, if any.. - */ -void (*pm_idle)(void); -EXPORT_SYMBOL(pm_idle); - static ATOMIC_NOTIFIER_HEAD(idle_notifier); void idle_notifier_register(struct notifier_block *n) @@ -94,25 +85,6 @@ void exit_idle(void) __exit_idle(); } -/* - * We use this if we don't have any better - * idle routine.. - */ -void default_idle(void) -{ - current_thread_info()->status &= ~TS_POLLING; - /* - * TS_POLLING-cleared state must be visible before we - * test NEED_RESCHED: - */ - smp_mb(); - if (!need_resched()) - safe_halt(); /* enables interrupts racelessly */ - else - local_irq_enable(); - current_thread_info()->status |= TS_POLLING; -} - #ifdef CONFIG_HOTPLUG_CPU DECLARE_PER_CPU(int, cpu_state); @@ -150,12 +122,9 @@ void cpu_idle(void) while (1) { tick_nohz_stop_sched_tick(1); while (!need_resched()) { - void (*idle)(void); rmb(); - idle = pm_idle; - if (!idle) - idle = default_idle; + if (cpu_is_offline(smp_processor_id())) play_dead(); /* @@ -165,7 +134,10 @@ void cpu_idle(void) */ local_irq_disable(); enter_idle(); - idle(); + /* Don't trace irqs off for idle */ + stop_critical_timings(); + pm_idle(); + start_critical_timings(); /* In many cases the interrupt that ended idle has already called exit_idle. But some idle loops can be woken up without interrupt. */ @@ -294,6 +266,7 @@ void flush_thread(void) /* * Forget coprocessor state.. */ + tsk->fpu_counter = 0; clear_fpu(tsk); clear_used_math(); } @@ -365,10 +338,10 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long sp, p->thread.fs = me->thread.fs; p->thread.gs = me->thread.gs; - asm("mov %%gs,%0" : "=m" (p->thread.gsindex)); - asm("mov %%fs,%0" : "=m" (p->thread.fsindex)); - asm("mov %%es,%0" : "=m" (p->thread.es)); - asm("mov %%ds,%0" : "=m" (p->thread.ds)); + savesegment(gs, p->thread.gsindex); + savesegment(fs, p->thread.fsindex); + savesegment(es, p->thread.es); + savesegment(ds, p->thread.ds); if (unlikely(test_tsk_thread_flag(me, TIF_IO_BITMAP))) { p->thread.io_bitmap_ptr = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL); @@ -407,7 +380,9 @@ out: void start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) { - asm volatile("movl %0, %%fs; movl %0, %%es; movl %0, %%ds" :: "r"(0)); + loadsegment(fs, 0); + loadsegment(es, 0); + loadsegment(ds, 0); load_gs_index(0); regs->ip = new_ip; regs->sp = new_sp; @@ -566,6 +541,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) *next = &next_p->thread; int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(init_tss, cpu); + unsigned fsindex, gsindex; /* we're going to use this soon, after a few expensive things */ if (next_p->fpu_counter>5) @@ -580,22 +556,38 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * Switch DS and ES. * This won't pick up thread selector changes, but I guess that is ok. */ - asm volatile("mov %%es,%0" : "=m" (prev->es)); + savesegment(es, prev->es); if (unlikely(next->es | prev->es)) loadsegment(es, next->es); - - asm volatile ("mov %%ds,%0" : "=m" (prev->ds)); + + savesegment(ds, prev->ds); if (unlikely(next->ds | prev->ds)) loadsegment(ds, next->ds); + + /* We must save %fs and %gs before load_TLS() because + * %fs and %gs may be cleared by load_TLS(). + * + * (e.g. xen_load_tls()) + */ + savesegment(fs, fsindex); + savesegment(gs, gsindex); + load_TLS(next, cpu); + /* + * Leave lazy mode, flushing any hypercalls made here. + * This must be done before restoring TLS segments so + * the GDT and LDT are properly updated, and must be + * done before math_state_restore, so the TS bit is up + * to date. + */ + arch_leave_lazy_cpu_mode(); + /* * Switch FS and GS. */ { - unsigned fsindex; - asm volatile("movl %%fs,%0" : "=r" (fsindex)); /* segment register != 0 always requires a reload. also reload when it has changed. when prev process used 64bit base always reload @@ -613,10 +605,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) if (next->fs) wrmsrl(MSR_FS_BASE, next->fs); prev->fsindex = fsindex; - } - { - unsigned gsindex; - asm volatile("movl %%gs,%0" : "=r" (gsindex)); + if (unlikely(gsindex | next->gsindex | prev->gs)) { load_gs_index(next->gsindex); if (gsindex) @@ -658,8 +647,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) /* If the task has used fpu the last 5 timeslices, just do a full * restore of the math state immediately to avoid the trap; the * chances of needing FPU soon are obviously high now + * + * tsk_used_math() checks prevent calling math_state_restore(), + * which can sleep in the case of !tsk_used_math() */ - if (next_p->fpu_counter>5) + if (tsk_used_math(next_p) && next_p->fpu_counter > 5) math_state_restore(); return prev_p; } @@ -794,7 +786,7 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) set_32bit_tls(task, FS_TLS, addr); if (doit) { load_TLS(&task->thread, cpu); - asm volatile("movl %0,%%fs" :: "r"(FS_TLS_SEL)); + loadsegment(fs, FS_TLS_SEL); } task->thread.fsindex = FS_TLS_SEL; task->thread.fs = 0; @@ -804,7 +796,7 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) if (doit) { /* set the selector to 0 to not confuse __switch_to */ - asm volatile("movl %0,%%fs" :: "r" (0)); + loadsegment(fs, 0); ret = checking_wrmsrl(MSR_FS_BASE, addr); } } @@ -827,7 +819,7 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) if (task->thread.gsindex == GS_TLS_SEL) base = read_32bit_tls(task, GS_TLS); else if (doit) { - asm("movl %%gs,%0" : "=r" (gsindex)); + savesegment(gs, gsindex); if (gsindex) rdmsrl(MSR_KERNEL_GS_BASE, base); else diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index a7835f282936..77040b6070e1 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -943,13 +943,13 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) return copy_regset_to_user(child, &user_x86_32_view, REGSET_XFP, 0, sizeof(struct user_fxsr_struct), - datap); + datap) ? -EIO : 0; case PTRACE_SETFPXREGS: /* Set the child extended FPU state. */ return copy_regset_from_user(child, &user_x86_32_view, REGSET_XFP, 0, sizeof(struct user_fxsr_struct), - datap); + datap) ? -EIO : 0; #endif #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c new file mode 100644 index 000000000000..05fbe9a0325a --- /dev/null +++ b/arch/x86/kernel/pvclock.c @@ -0,0 +1,141 @@ +/* paravirtual clock -- common code used by kvm/xen + + 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. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA +*/ + +#include <linux/kernel.h> +#include <linux/percpu.h> +#include <asm/pvclock.h> + +/* + * These are perodically updated + * xen: magic shared_info page + * kvm: gpa registered via msr + * and then copied here. + */ +struct pvclock_shadow_time { + u64 tsc_timestamp; /* TSC at last update of time vals. */ + u64 system_timestamp; /* Time, in nanosecs, since boot. */ + u32 tsc_to_nsec_mul; + int tsc_shift; + u32 version; +}; + +/* + * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction, + * yielding a 64-bit result. + */ +static inline u64 scale_delta(u64 delta, u32 mul_frac, int shift) +{ + u64 product; +#ifdef __i386__ + u32 tmp1, tmp2; +#endif + + if (shift < 0) + delta >>= -shift; + else + delta <<= shift; + +#ifdef __i386__ + __asm__ ( + "mul %5 ; " + "mov %4,%%eax ; " + "mov %%edx,%4 ; " + "mul %5 ; " + "xor %5,%5 ; " + "add %4,%%eax ; " + "adc %5,%%edx ; " + : "=A" (product), "=r" (tmp1), "=r" (tmp2) + : "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) ); +#elif __x86_64__ + __asm__ ( + "mul %%rdx ; shrd $32,%%rdx,%%rax" + : "=a" (product) : "0" (delta), "d" ((u64)mul_frac) ); +#else +#error implement me! +#endif + + return product; +} + +static u64 pvclock_get_nsec_offset(struct pvclock_shadow_time *shadow) +{ + u64 delta = native_read_tsc() - shadow->tsc_timestamp; + return scale_delta(delta, shadow->tsc_to_nsec_mul, shadow->tsc_shift); +} + +/* + * Reads a consistent set of time-base values from hypervisor, + * into a shadow data area. + */ +static unsigned pvclock_get_time_values(struct pvclock_shadow_time *dst, + struct pvclock_vcpu_time_info *src) +{ + do { + dst->version = src->version; + rmb(); /* fetch version before data */ + dst->tsc_timestamp = src->tsc_timestamp; + dst->system_timestamp = src->system_time; + dst->tsc_to_nsec_mul = src->tsc_to_system_mul; + dst->tsc_shift = src->tsc_shift; + rmb(); /* test version after fetching data */ + } while ((src->version & 1) || (dst->version != src->version)); + + return dst->version; +} + +cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) +{ + struct pvclock_shadow_time shadow; + unsigned version; + cycle_t ret, offset; + + do { + version = pvclock_get_time_values(&shadow, src); + barrier(); + offset = pvclock_get_nsec_offset(&shadow); + ret = shadow.system_timestamp + offset; + barrier(); + } while (version != src->version); + + return ret; +} + +void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, + struct pvclock_vcpu_time_info *vcpu_time, + struct timespec *ts) +{ + u32 version; + u64 delta; + struct timespec now; + + /* get wallclock at system boot */ + do { + version = wall_clock->version; + rmb(); /* fetch version before time */ + now.tv_sec = wall_clock->sec; + now.tv_nsec = wall_clock->nsec; + rmb(); /* fetch time before checking version */ + } while ((wall_clock->version & 1) || (version != wall_clock->version)); + + delta = pvclock_clocksource_read(vcpu_time); /* time since system boot */ + delta += now.tv_sec * (u64)NSEC_PER_SEC + now.tv_nsec; + + now.tv_nsec = do_div(delta, NSEC_PER_SEC); + now.tv_sec = delta; + + set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); +} diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index d89a648fe710..d13858818100 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -65,6 +65,7 @@ static enum { ICH_FORCE_HPET_RESUME, VT8237_FORCE_HPET_RESUME, NVIDIA_FORCE_HPET_RESUME, + ATI_FORCE_HPET_RESUME, } force_hpet_resume_type; static void __iomem *rcba_base; @@ -158,6 +159,8 @@ static void ich_force_enable_hpet(struct pci_dev *dev) DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB2_0, ich_force_enable_hpet); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH6_0, + ich_force_enable_hpet); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH6_1, ich_force_enable_hpet); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH7_0, @@ -174,6 +177,12 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH9_7, static struct pci_dev *cached_dev; +static void hpet_print_force_info(void) +{ + printk(KERN_INFO "HPET not enabled in BIOS. " + "You might try hpet=force boot option\n"); +} + static void old_ich_force_hpet_resume(void) { u32 val; @@ -253,8 +262,12 @@ static void old_ich_force_enable_hpet_user(struct pci_dev *dev) { if (hpet_force_user) old_ich_force_enable_hpet(dev); + else + hpet_print_force_info(); } +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB_1, + old_ich_force_enable_hpet_user); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801CA_0, old_ich_force_enable_hpet_user); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801CA_12, @@ -290,9 +303,14 @@ static void vt8237_force_enable_hpet(struct pci_dev *dev) { u32 uninitialized_var(val); - if (!hpet_force_user || hpet_address || force_hpet_address) + if (hpet_address || force_hpet_address) return; + if (!hpet_force_user) { + hpet_print_force_info(); + return; + } + pci_read_config_dword(dev, 0x68, &val); /* * Bit 7 is HPET enable bit. @@ -330,6 +348,36 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8235, DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8237, vt8237_force_enable_hpet); +static void ati_force_hpet_resume(void) +{ + pci_write_config_dword(cached_dev, 0x14, 0xfed00000); + printk(KERN_DEBUG "Force enabled HPET at resume\n"); +} + +static void ati_force_enable_hpet(struct pci_dev *dev) +{ + u32 uninitialized_var(val); + + if (hpet_address || force_hpet_address) + return; + + if (!hpet_force_user) { + hpet_print_force_info(); + return; + } + + pci_write_config_dword(dev, 0x14, 0xfed00000); + pci_read_config_dword(dev, 0x14, &val); + force_hpet_address = val; + force_hpet_resume_type = ATI_FORCE_HPET_RESUME; + dev_printk(KERN_DEBUG, &dev->dev, "Force enabled HPET at 0x%lx\n", + force_hpet_address); + cached_dev = dev; + return; +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_IXP400_SMBUS, + ati_force_enable_hpet); + /* * Undocumented chipset feature taken from LinuxBIOS. */ @@ -343,8 +391,13 @@ static void nvidia_force_enable_hpet(struct pci_dev *dev) { u32 uninitialized_var(val); - if (!hpet_force_user || hpet_address || force_hpet_address) + if (hpet_address || force_hpet_address) + return; + + if (!hpet_force_user) { + hpet_print_force_info(); return; + } pci_write_config_dword(dev, 0x44, 0xfed00001); pci_read_config_dword(dev, 0x44, &val); @@ -397,6 +450,9 @@ void force_hpet_resume(void) case NVIDIA_FORCE_HPET_RESUME: nvidia_force_hpet_resume(); return; + case ATI_FORCE_HPET_RESUME: + ati_force_hpet_resume(); + return; default: break; } diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index f6be7d5f82f8..f8a62160e151 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -27,7 +27,7 @@ void (*pm_power_off)(void); EXPORT_SYMBOL(pm_power_off); -static long no_idt[3]; +static const struct desc_ptr no_idt = {}; static int reboot_mode; enum reboot_type reboot_type = BOOT_KBD; int reboot_force; @@ -201,15 +201,15 @@ core_initcall(reboot_init); controller to pulse the CPU reset line, which is more thorough, but doesn't work with at least one type of 486 motherboard. It is easy to stop this code working; hence the copious comments. */ -static unsigned long long +static const unsigned long long real_mode_gdt_entries [3] = { 0x0000000000000000ULL, /* Null descriptor */ - 0x00009a000000ffffULL, /* 16-bit real-mode 64k code at 0x00000000 */ - 0x000092000100ffffULL /* 16-bit real-mode 64k data at 0x00000100 */ + 0x00009b000000ffffULL, /* 16-bit real-mode 64k code at 0x00000000 */ + 0x000093000100ffffULL /* 16-bit real-mode 64k data at 0x00000100 */ }; -static struct desc_ptr +static const struct desc_ptr real_mode_gdt = { sizeof (real_mode_gdt_entries) - 1, (long)real_mode_gdt_entries }, real_mode_idt = { 0x3ff, 0 }; @@ -231,7 +231,7 @@ real_mode_idt = { 0x3ff, 0 }; More could be done here to set up the registers as if a CPU reset had occurred; hopefully real BIOSs don't assume much. */ -static unsigned char real_mode_switch [] = +static const unsigned char real_mode_switch [] = { 0x66, 0x0f, 0x20, 0xc0, /* movl %cr0,%eax */ 0x66, 0x83, 0xe0, 0x11, /* andl $0x00000011,%eax */ @@ -245,7 +245,7 @@ static unsigned char real_mode_switch [] = 0x24, 0x10, /* f: andb $0x10,al */ 0x66, 0x0f, 0x22, 0xc0 /* movl %eax,%cr0 */ }; -static unsigned char jump_to_bios [] = +static const unsigned char jump_to_bios [] = { 0xea, 0x00, 0x00, 0xff, 0xff /* ljmp $0xffff,$0x0000 */ }; @@ -255,7 +255,7 @@ static unsigned char jump_to_bios [] = * specified by the code and length parameters. * We assume that length will aways be less that 100! */ -void machine_real_restart(unsigned char *code, int length) +void machine_real_restart(const unsigned char *code, int length) { local_irq_disable(); @@ -368,7 +368,7 @@ static void native_machine_emergency_restart(void) } case BOOT_TRIPLE: - load_idt((const struct desc_ptr *)&no_idt); + load_idt(&no_idt); __asm__ __volatile__("int3"); reboot_type = BOOT_KBD; diff --git a/arch/x86/kernel/reboot_fixups_32.c b/arch/x86/kernel/reboot_fixups_32.c index dec0b5ec25c2..61a837743fe5 100644 --- a/arch/x86/kernel/reboot_fixups_32.c +++ b/arch/x86/kernel/reboot_fixups_32.c @@ -49,7 +49,7 @@ struct device_fixup { void (*reboot_fixup)(struct pci_dev *); }; -static struct device_fixup fixups_table[] = { +static const struct device_fixup fixups_table[] = { { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5530_LEGACY, cs5530a_warm_reset }, { PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CS5536_ISA, cs5536_warm_reset }, { PCI_VENDOR_ID_NS, PCI_DEVICE_ID_NS_SC1100_BRIDGE, cs5530a_warm_reset }, @@ -64,7 +64,7 @@ static struct device_fixup fixups_table[] = { */ void mach_reboot_fixups(void) { - struct device_fixup *cur; + const struct device_fixup *cur; struct pci_dev *dev; int i; diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 9615eee9b775..05191bbc68b8 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -4,6 +4,8 @@ #include <linux/acpi.h> #include <linux/bcd.h> #include <linux/mc146818rtc.h> +#include <linux/platform_device.h> +#include <linux/pnp.h> #include <asm/time.h> #include <asm/vsyscall.h> @@ -197,3 +199,35 @@ unsigned long long native_read_tsc(void) } EXPORT_SYMBOL(native_read_tsc); + +static struct resource rtc_resources[] = { + [0] = { + .start = RTC_PORT(0), + .end = RTC_PORT(1), + .flags = IORESOURCE_IO, + }, + [1] = { + .start = RTC_IRQ, + .end = RTC_IRQ, + .flags = IORESOURCE_IRQ, + } +}; + +static struct platform_device rtc_device = { + .name = "rtc_cmos", + .id = -1, + .resource = rtc_resources, + .num_resources = ARRAY_SIZE(rtc_resources), +}; + +static __init int add_rtc_cmos(void) +{ +#ifdef CONFIG_PNP + if (!pnp_platform_devices) + platform_device_register(&rtc_device); +#else + platform_device_register(&rtc_device); +#endif /* CONFIG_PNP */ + return 0; +} +device_initcall(add_rtc_cmos); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 6f80b852a196..531b55b8e81a 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1,139 +1,894 @@ -#include <linux/kernel.h> +/* + * Copyright (C) 1995 Linus Torvalds + * + * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 + * + * Memory region support + * David Parsons <orc@pell.chi.il.us>, July-August 1999 + * + * Added E820 sanitization routine (removes overlapping memory regions); + * Brian Moyle <bmoyle@mvista.com>, February 2001 + * + * Moved CPU detection code to cpu/${cpu}.c + * Patrick Mochel <mochel@osdl.org>, March 2002 + * + * Provisions for empty E820 memory regions (reported by certain BIOSes). + * Alex Achenbach <xela@slit.de>, December 2002. + * + */ + +/* + * This file handles the architecture-dependent parts of initialization + */ + +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/mmzone.h> +#include <linux/screen_info.h> +#include <linux/ioport.h> +#include <linux/acpi.h> +#include <linux/apm_bios.h> +#include <linux/initrd.h> +#include <linux/bootmem.h> +#include <linux/seq_file.h> +#include <linux/console.h> +#include <linux/mca.h> +#include <linux/root_dev.h> +#include <linux/highmem.h> #include <linux/module.h> +#include <linux/efi.h> #include <linux/init.h> -#include <linux/bootmem.h> +#include <linux/edd.h> +#include <linux/iscsi_ibft.h> +#include <linux/nodemask.h> +#include <linux/kexec.h> +#include <linux/dmi.h> +#include <linux/pfn.h> +#include <linux/pci.h> +#include <asm/pci-direct.h> +#include <linux/init_ohci1394_dma.h> +#include <linux/kvm_para.h> + +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/stddef.h> +#include <linux/unistd.h> +#include <linux/ptrace.h> +#include <linux/slab.h> +#include <linux/user.h> +#include <linux/delay.h> +#include <linux/highmem.h> + +#include <linux/kallsyms.h> +#include <linux/edd.h> +#include <linux/iscsi_ibft.h> +#include <linux/kexec.h> +#include <linux/cpufreq.h> +#include <linux/dma-mapping.h> +#include <linux/ctype.h> +#include <linux/uaccess.h> + #include <linux/percpu.h> +#include <linux/crash_dump.h> + +#include <video/edid.h> + +#include <asm/mtrr.h> +#include <asm/apic.h> +#include <asm/e820.h> +#include <asm/mpspec.h> +#include <asm/setup.h> +#include <asm/arch_hooks.h> +#include <asm/efi.h> +#include <asm/sections.h> +#include <asm/dmi.h> +#include <asm/io_apic.h> +#include <asm/ist.h> +#include <asm/vmi.h> +#include <setup_arch.h> +#include <asm/bios_ebda.h> +#include <asm/cacheflush.h> +#include <asm/processor.h> +#include <asm/bugs.h> + +#include <asm/system.h> +#include <asm/vsyscall.h> #include <asm/smp.h> +#include <asm/desc.h> +#include <asm/dma.h> +#include <asm/gart.h> +#include <asm/mmu_context.h> +#include <asm/proto.h> + +#include <mach_apic.h> +#include <asm/paravirt.h> + #include <asm/percpu.h> #include <asm/sections.h> -#include <asm/processor.h> -#include <asm/setup.h> #include <asm/topology.h> -#include <asm/mpspec.h> #include <asm/apicdef.h> +#ifdef CONFIG_X86_64 +#include <asm/numa_64.h> +#endif -#ifdef CONFIG_X86_LOCAL_APIC -unsigned int num_processors; -unsigned disabled_cpus __cpuinitdata; -/* Processor that is doing the boot up */ -unsigned int boot_cpu_physical_apicid = -1U; -EXPORT_SYMBOL(boot_cpu_physical_apicid); +#ifndef ARCH_SETUP +#define ARCH_SETUP +#endif + +#ifndef CONFIG_DEBUG_BOOT_PARAMS +struct boot_params __initdata boot_params; +#else +struct boot_params boot_params; +#endif + +/* + * Machine setup.. + */ +static struct resource data_resource = { + .name = "Kernel data", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_MEM +}; + +static struct resource code_resource = { + .name = "Kernel code", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_MEM +}; + +static struct resource bss_resource = { + .name = "Kernel bss", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_MEM +}; + + +#ifdef CONFIG_X86_32 +/* This value is set up by the early boot code to point to the value + immediately after the boot time page tables. It contains a *physical* + address, and must not be in the .bss segment! */ +unsigned long init_pg_tables_start __initdata = ~0UL; +unsigned long init_pg_tables_end __initdata = ~0UL; + +static struct resource video_ram_resource = { + .name = "Video RAM area", + .start = 0xa0000, + .end = 0xbffff, + .flags = IORESOURCE_BUSY | IORESOURCE_MEM +}; + +/* cpu data as detected by the assembly code in head.S */ +struct cpuinfo_x86 new_cpu_data __cpuinitdata = {0, 0, 0, 0, -1, 1, 0, 0, -1}; +/* common cpu data for all cpus */ +struct cpuinfo_x86 boot_cpu_data __read_mostly = {0, 0, 0, 0, -1, 1, 0, 0, -1}; +EXPORT_SYMBOL(boot_cpu_data); +static void set_mca_bus(int x) +{ +#ifdef CONFIG_MCA + MCA_bus = x; +#endif +} + +unsigned int def_to_bigsmp; + +/* for MCA, but anyone else can use it if they want */ +unsigned int machine_id; +unsigned int machine_submodel_id; +unsigned int BIOS_revision; + +struct apm_info apm_info; +EXPORT_SYMBOL(apm_info); + +#if defined(CONFIG_X86_SPEEDSTEP_SMI) || \ + defined(CONFIG_X86_SPEEDSTEP_SMI_MODULE) +struct ist_info ist_info; +EXPORT_SYMBOL(ist_info); +#else +struct ist_info ist_info; +#endif + +#else +struct cpuinfo_x86 boot_cpu_data __read_mostly; +EXPORT_SYMBOL(boot_cpu_data); +#endif -DEFINE_PER_CPU(u16, x86_cpu_to_apicid) = BAD_APICID; -EXPORT_PER_CPU_SYMBOL(x86_cpu_to_apicid); -/* Bitmask of physically existing CPUs */ -physid_mask_t phys_cpu_present_map; +#if !defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64) +unsigned long mmu_cr4_features; +#else +unsigned long mmu_cr4_features = X86_CR4_PAE; #endif -#if defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) && defined(CONFIG_X86_SMP) +/* Boot loader ID as an integer, for the benefit of proc_dointvec */ +int bootloader_type; + /* - * Copy data used in early init routines from the initial arrays to the - * per cpu data areas. These arrays then become expendable and the - * *_early_ptr's are zeroed indicating that the static arrays are gone. + * Early DMI memory + */ +int dmi_alloc_index; +char dmi_alloc_data[DMI_MAX_DATA]; + +/* + * Setup options + */ +struct screen_info screen_info; +EXPORT_SYMBOL(screen_info); +struct edid_info edid_info; +EXPORT_SYMBOL_GPL(edid_info); + +extern int root_mountflags; + +unsigned long saved_video_mode; + +#define RAMDISK_IMAGE_START_MASK 0x07FF +#define RAMDISK_PROMPT_FLAG 0x8000 +#define RAMDISK_LOAD_FLAG 0x4000 + +static char __initdata command_line[COMMAND_LINE_SIZE]; + +#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE) +struct edd edd; +#ifdef CONFIG_EDD_MODULE +EXPORT_SYMBOL(edd); +#endif +/** + * copy_edd() - Copy the BIOS EDD information + * from boot_params into a safe place. + * */ -static void __init setup_per_cpu_maps(void) +static inline void copy_edd(void) +{ + memcpy(edd.mbr_signature, boot_params.edd_mbr_sig_buffer, + sizeof(edd.mbr_signature)); + memcpy(edd.edd_info, boot_params.eddbuf, sizeof(edd.edd_info)); + edd.mbr_signature_nr = boot_params.edd_mbr_sig_buf_entries; + edd.edd_info_nr = boot_params.eddbuf_entries; +} +#else +static inline void copy_edd(void) +{ +} +#endif + +#ifdef CONFIG_BLK_DEV_INITRD + +#ifdef CONFIG_X86_32 + +#define MAX_MAP_CHUNK (NR_FIX_BTMAPS << PAGE_SHIFT) +static void __init relocate_initrd(void) { - int cpu; - for_each_possible_cpu(cpu) { - per_cpu(x86_cpu_to_apicid, cpu) = x86_cpu_to_apicid_init[cpu]; - per_cpu(x86_bios_cpu_apicid, cpu) = - x86_bios_cpu_apicid_init[cpu]; -#ifdef CONFIG_NUMA - per_cpu(x86_cpu_to_node_map, cpu) = - x86_cpu_to_node_map_init[cpu]; + u64 ramdisk_image = boot_params.hdr.ramdisk_image; + u64 ramdisk_size = boot_params.hdr.ramdisk_size; + u64 end_of_lowmem = max_low_pfn << PAGE_SHIFT; + u64 ramdisk_here; + unsigned long slop, clen, mapaddr; + char *p, *q; + + /* We need to move the initrd down into lowmem */ + ramdisk_here = find_e820_area(0, end_of_lowmem, ramdisk_size, + PAGE_SIZE); + + if (ramdisk_here == -1ULL) + panic("Cannot find place for new RAMDISK of size %lld\n", + ramdisk_size); + + /* Note: this includes all the lowmem currently occupied by + the initrd, we rely on that fact to keep the data intact. */ + reserve_early(ramdisk_here, ramdisk_here + ramdisk_size, + "NEW RAMDISK"); + initrd_start = ramdisk_here + PAGE_OFFSET; + initrd_end = initrd_start + ramdisk_size; + printk(KERN_INFO "Allocated new RAMDISK: %08llx - %08llx\n", + ramdisk_here, ramdisk_here + ramdisk_size); + + q = (char *)initrd_start; + + /* Copy any lowmem portion of the initrd */ + if (ramdisk_image < end_of_lowmem) { + clen = end_of_lowmem - ramdisk_image; + p = (char *)__va(ramdisk_image); + memcpy(q, p, clen); + q += clen; + ramdisk_image += clen; + ramdisk_size -= clen; + } + + /* Copy the highmem portion of the initrd */ + while (ramdisk_size) { + slop = ramdisk_image & ~PAGE_MASK; + clen = ramdisk_size; + if (clen > MAX_MAP_CHUNK-slop) + clen = MAX_MAP_CHUNK-slop; + mapaddr = ramdisk_image & PAGE_MASK; + p = early_ioremap(mapaddr, clen+slop); + memcpy(q, p+slop, clen); + early_iounmap(p, clen+slop); + q += clen; + ramdisk_image += clen; + ramdisk_size -= clen; + } + /* high pages is not converted by early_res_to_bootmem */ + ramdisk_image = boot_params.hdr.ramdisk_image; + ramdisk_size = boot_params.hdr.ramdisk_size; + printk(KERN_INFO "Move RAMDISK from %016llx - %016llx to" + " %08llx - %08llx\n", + ramdisk_image, ramdisk_image + ramdisk_size - 1, + ramdisk_here, ramdisk_here + ramdisk_size - 1); +} #endif + +static void __init reserve_initrd(void) +{ + u64 ramdisk_image = boot_params.hdr.ramdisk_image; + u64 ramdisk_size = boot_params.hdr.ramdisk_size; + u64 ramdisk_end = ramdisk_image + ramdisk_size; + u64 end_of_lowmem = max_low_pfn << PAGE_SHIFT; + + if (!boot_params.hdr.type_of_loader || + !ramdisk_image || !ramdisk_size) + return; /* No initrd provided by bootloader */ + + initrd_start = 0; + + if (ramdisk_size >= (end_of_lowmem>>1)) { + free_early(ramdisk_image, ramdisk_end); + printk(KERN_ERR "initrd too large to handle, " + "disabling initrd\n"); + return; + } + + printk(KERN_INFO "RAMDISK: %08llx - %08llx\n", ramdisk_image, + ramdisk_end); + + + if (ramdisk_end <= end_of_lowmem) { + /* All in lowmem, easy case */ + /* + * don't need to reserve again, already reserved early + * in i386_start_kernel + */ + initrd_start = ramdisk_image + PAGE_OFFSET; + initrd_end = initrd_start + ramdisk_size; + return; } - /* indicate the early static arrays will soon be gone */ - x86_cpu_to_apicid_early_ptr = NULL; - x86_bios_cpu_apicid_early_ptr = NULL; -#ifdef CONFIG_NUMA - x86_cpu_to_node_map_early_ptr = NULL; +#ifdef CONFIG_X86_32 + relocate_initrd(); +#else + printk(KERN_ERR "initrd extends beyond end of memory " + "(0x%08llx > 0x%08llx)\ndisabling initrd\n", + ramdisk_end, end_of_lowmem); + initrd_start = 0; #endif + free_early(ramdisk_image, ramdisk_end); } +#else +static void __init reserve_initrd(void) +{ +} +#endif /* CONFIG_BLK_DEV_INITRD */ + +static void __init parse_setup_data(void) +{ + struct setup_data *data; + u64 pa_data; + + if (boot_params.hdr.version < 0x0209) + return; + pa_data = boot_params.hdr.setup_data; + while (pa_data) { + data = early_ioremap(pa_data, PAGE_SIZE); + switch (data->type) { + case SETUP_E820_EXT: + parse_e820_ext(data, pa_data); + break; + default: + break; + } + pa_data = data->next; + early_iounmap(data, PAGE_SIZE); + } +} + +static void __init e820_reserve_setup_data(void) +{ + struct setup_data *data; + u64 pa_data; + int found = 0; + + if (boot_params.hdr.version < 0x0209) + return; + pa_data = boot_params.hdr.setup_data; + while (pa_data) { + data = early_ioremap(pa_data, sizeof(*data)); + e820_update_range(pa_data, sizeof(*data)+data->len, + E820_RAM, E820_RESERVED_KERN); + found = 1; + pa_data = data->next; + early_iounmap(data, sizeof(*data)); + } + if (!found) + return; -#ifdef CONFIG_HAVE_CPUMASK_OF_CPU_MAP -cpumask_t *cpumask_of_cpu_map __read_mostly; -EXPORT_SYMBOL(cpumask_of_cpu_map); + sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); + memcpy(&e820_saved, &e820, sizeof(struct e820map)); + printk(KERN_INFO "extended physical RAM map:\n"); + e820_print_map("reserve setup_data"); +} -/* requires nr_cpu_ids to be initialized */ -static void __init setup_cpumask_of_cpu(void) +static void __init reserve_early_setup_data(void) { - int i; + struct setup_data *data; + u64 pa_data; + char buf[32]; + + if (boot_params.hdr.version < 0x0209) + return; + pa_data = boot_params.hdr.setup_data; + while (pa_data) { + data = early_ioremap(pa_data, sizeof(*data)); + sprintf(buf, "setup data %x", data->type); + reserve_early(pa_data, pa_data+sizeof(*data)+data->len, buf); + pa_data = data->next; + early_iounmap(data, sizeof(*data)); + } +} + +/* + * --------- Crashkernel reservation ------------------------------ + */ + +#ifdef CONFIG_KEXEC + +/** + * Reserve @size bytes of crashkernel memory at any suitable offset. + * + * @size: Size of the crashkernel memory to reserve. + * Returns the base address on success, and -1ULL on failure. + */ +unsigned long long find_and_reserve_crashkernel(unsigned long long size) +{ + const unsigned long long alignment = 16<<20; /* 16M */ + unsigned long long start = 0LL; + + while (1) { + int ret; + + start = find_e820_area(start, ULONG_MAX, size, alignment); + if (start == -1ULL) + return start; + + /* try to reserve it */ + ret = reserve_bootmem_generic(start, size, BOOTMEM_EXCLUSIVE); + if (ret >= 0) + return start; + + start += alignment; + } +} + +static inline unsigned long long get_total_mem(void) +{ + unsigned long long total; + + total = max_low_pfn - min_low_pfn; +#ifdef CONFIG_HIGHMEM + total += highend_pfn - highstart_pfn; +#endif + + return total << PAGE_SHIFT; +} + +static void __init reserve_crashkernel(void) +{ + unsigned long long total_mem; + unsigned long long crash_size, crash_base; + int ret; + + total_mem = get_total_mem(); - /* alloc_bootmem zeroes memory */ - cpumask_of_cpu_map = alloc_bootmem_low(sizeof(cpumask_t) * nr_cpu_ids); - for (i = 0; i < nr_cpu_ids; i++) - cpu_set(i, cpumask_of_cpu_map[i]); + ret = parse_crashkernel(boot_command_line, total_mem, + &crash_size, &crash_base); + if (ret != 0 || crash_size <= 0) + return; + + /* 0 means: find the address automatically */ + if (crash_base <= 0) { + crash_base = find_and_reserve_crashkernel(crash_size); + if (crash_base == -1ULL) { + pr_info("crashkernel reservation failed. " + "No suitable area found.\n"); + return; + } + } else { + ret = reserve_bootmem_generic(crash_base, crash_size, + BOOTMEM_EXCLUSIVE); + if (ret < 0) { + pr_info("crashkernel reservation failed - " + "memory is in use\n"); + return; + } + } + + printk(KERN_INFO "Reserving %ldMB of memory at %ldMB " + "for crashkernel (System RAM: %ldMB)\n", + (unsigned long)(crash_size >> 20), + (unsigned long)(crash_base >> 20), + (unsigned long)(total_mem >> 20)); + + crashk_res.start = crash_base; + crashk_res.end = crash_base + crash_size - 1; + insert_resource(&iomem_resource, &crashk_res); } #else -static inline void setup_cpumask_of_cpu(void) { } +static void __init reserve_crashkernel(void) +{ +} #endif -#ifdef CONFIG_X86_32 -/* - * Great future not-so-futuristic plan: make i386 and x86_64 do it - * the same way +static struct resource standard_io_resources[] = { + { .name = "dma1", .start = 0x00, .end = 0x1f, + .flags = IORESOURCE_BUSY | IORESOURCE_IO }, + { .name = "pic1", .start = 0x20, .end = 0x21, + .flags = IORESOURCE_BUSY | IORESOURCE_IO }, + { .name = "timer0", .start = 0x40, .end = 0x43, + .flags = IORESOURCE_BUSY | IORESOURCE_IO }, + { .name = "timer1", .start = 0x50, .end = 0x53, + .flags = IORESOURCE_BUSY | IORESOURCE_IO }, + { .name = "keyboard", .start = 0x60, .end = 0x60, + .flags = IORESOURCE_BUSY | IORESOURCE_IO }, + { .name = "keyboard", .start = 0x64, .end = 0x64, + .flags = IORESOURCE_BUSY | IORESOURCE_IO }, + { .name = "dma page reg", .start = 0x80, .end = 0x8f, + .flags = IORESOURCE_BUSY | IORESOURCE_IO }, + { .name = "pic2", .start = 0xa0, .end = 0xa1, + .flags = IORESOURCE_BUSY | IORESOURCE_IO }, + { .name = "dma2", .start = 0xc0, .end = 0xdf, + .flags = IORESOURCE_BUSY | IORESOURCE_IO }, + { .name = "fpu", .start = 0xf0, .end = 0xff, + .flags = IORESOURCE_BUSY | IORESOURCE_IO } +}; + +static void __init reserve_standard_io_resources(void) +{ + int i; + + /* request I/O space for devices used on all i[345]86 PCs */ + for (i = 0; i < ARRAY_SIZE(standard_io_resources); i++) + request_resource(&ioport_resource, &standard_io_resources[i]); + +} + +#ifdef CONFIG_PROC_VMCORE +/* elfcorehdr= specifies the location of elf core header + * stored by the crashed kernel. This option will be passed + * by kexec loader to the capture kernel. */ -unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; -EXPORT_SYMBOL(__per_cpu_offset); +static int __init setup_elfcorehdr(char *arg) +{ + char *end; + if (!arg) + return -EINVAL; + elfcorehdr_addr = memparse(arg, &end); + return end > arg ? 0 : -EINVAL; +} +early_param("elfcorehdr", setup_elfcorehdr); #endif /* - * Great future plan: - * Declare PDA itself and support (irqstack,tss,pgd) as per cpu data. - * Always point %gs to its beginning + * Determine if we were loaded by an EFI loader. If so, then we have also been + * passed the efi memmap, systab, etc., so we should use these data structures + * for initialization. Note, the efi init code path is determined by the + * global efi_enabled. This allows the same kernel image to be used on existing + * systems (with a traditional BIOS) as well as on EFI systems. + */ +/* + * setup_arch - architecture-specific boot-time initializations + * + * Note: On x86_64, fixmaps are ready for use even before this is called. */ -void __init setup_per_cpu_areas(void) + +void __init setup_arch(char **cmdline_p) { - int i, highest_cpu = 0; - unsigned long size; +#ifdef CONFIG_X86_32 + memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data)); + visws_early_detect(); + pre_setup_arch_hook(); + early_cpu_init(); +#else + printk(KERN_INFO "Command line: %s\n", boot_command_line); +#endif -#ifdef CONFIG_HOTPLUG_CPU - prefill_possible_map(); + early_ioremap_init(); + + ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev); + screen_info = boot_params.screen_info; + edid_info = boot_params.edid_info; +#ifdef CONFIG_X86_32 + apm_info.bios = boot_params.apm_bios_info; + ist_info = boot_params.ist_info; + if (boot_params.sys_desc_table.length != 0) { + set_mca_bus(boot_params.sys_desc_table.table[3] & 0x2); + machine_id = boot_params.sys_desc_table.table[0]; + machine_submodel_id = boot_params.sys_desc_table.table[1]; + BIOS_revision = boot_params.sys_desc_table.table[2]; + } +#endif + saved_video_mode = boot_params.hdr.vid_mode; + bootloader_type = boot_params.hdr.type_of_loader; + +#ifdef CONFIG_BLK_DEV_RAM + rd_image_start = boot_params.hdr.ram_size & RAMDISK_IMAGE_START_MASK; + rd_prompt = ((boot_params.hdr.ram_size & RAMDISK_PROMPT_FLAG) != 0); + rd_doload = ((boot_params.hdr.ram_size & RAMDISK_LOAD_FLAG) != 0); +#endif +#ifdef CONFIG_EFI + if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, +#ifdef CONFIG_X86_32 + "EL32", +#else + "EL64", +#endif + 4)) { + efi_enabled = 1; + efi_reserve_early(); + } #endif - /* Copy section for each CPU (we discard the original) */ - size = PERCPU_ENOUGH_ROOM; - printk(KERN_INFO "PERCPU: Allocating %lu bytes of per cpu data\n", - size); + ARCH_SETUP - for_each_possible_cpu(i) { - char *ptr; -#ifndef CONFIG_NEED_MULTIPLE_NODES - ptr = alloc_bootmem_pages(size); + setup_memory_map(); + parse_setup_data(); + /* update the e820_saved too */ + e820_reserve_setup_data(); + + copy_edd(); + + if (!boot_params.hdr.root_flags) + root_mountflags &= ~MS_RDONLY; + init_mm.start_code = (unsigned long) _text; + init_mm.end_code = (unsigned long) _etext; + init_mm.end_data = (unsigned long) _edata; +#ifdef CONFIG_X86_32 + init_mm.brk = init_pg_tables_end + PAGE_OFFSET; #else - int node = early_cpu_to_node(i); - if (!node_online(node) || !NODE_DATA(node)) { - ptr = alloc_bootmem_pages(size); - printk(KERN_INFO - "cpu %d has no node or node-local memory\n", i); - } - else - ptr = alloc_bootmem_pages_node(NODE_DATA(node), size); + init_mm.brk = (unsigned long) &_end; #endif - if (!ptr) - panic("Cannot allocate cpu data for CPU %d\n", i); + + code_resource.start = virt_to_phys(_text); + code_resource.end = virt_to_phys(_etext)-1; + data_resource.start = virt_to_phys(_etext); + data_resource.end = virt_to_phys(_edata)-1; + bss_resource.start = virt_to_phys(&__bss_start); + bss_resource.end = virt_to_phys(&__bss_stop)-1; + #ifdef CONFIG_X86_64 - cpu_pda(i)->data_offset = ptr - __per_cpu_start; + early_cpu_init(); +#endif + strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE); + *cmdline_p = command_line; + + parse_early_param(); + + /* after early param, so could get panic from serial */ + reserve_early_setup_data(); + + if (acpi_mps_check()) { +#ifdef CONFIG_X86_LOCAL_APIC + disable_apic = 1; +#endif + clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC); + } + +#ifdef CONFIG_PCI + if (pci_early_dump_regs) + early_dump_pci_devices(); +#endif + + finish_e820_parsing(); + +#ifdef CONFIG_X86_32 + probe_roms(); +#endif + + /* after parse_early_param, so could debug it */ + insert_resource(&iomem_resource, &code_resource); + insert_resource(&iomem_resource, &data_resource); + insert_resource(&iomem_resource, &bss_resource); + + if (efi_enabled) + efi_init(); + +#ifdef CONFIG_X86_32 + if (ppro_with_ram_bug()) { + e820_update_range(0x70000000ULL, 0x40000ULL, E820_RAM, + E820_RESERVED); + sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); + printk(KERN_INFO "fixed physical RAM map:\n"); + e820_print_map("bad_ppro"); + } +#else + early_gart_iommu_check(); +#endif + + /* + * partially used pages are not usable - thus + * we are rounding upwards: + */ + max_pfn = e820_end_of_ram_pfn(); + + /* preallocate 4k for mptable mpc */ + early_reserve_e820_mpc_new(); + /* update e820 for memory not covered by WB MTRRs */ + mtrr_bp_init(); + if (mtrr_trim_uncached_memory(max_pfn)) + max_pfn = e820_end_of_ram_pfn(); + +#ifdef CONFIG_X86_32 + /* max_low_pfn get updated here */ + find_low_pfn_range(); #else - __per_cpu_offset[i] = ptr - __per_cpu_start; + num_physpages = max_pfn; + + check_efer(); + + /* How many end-of-memory variables you have, grandma! */ + /* need this before calling reserve_initrd */ + if (max_pfn > (1UL<<(32 - PAGE_SHIFT))) + max_low_pfn = e820_end_of_low_ram_pfn(); + else + max_low_pfn = max_pfn; + + high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1; #endif - memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start); - highest_cpu = i; + /* max_pfn_mapped is updated here */ + max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<<PAGE_SHIFT); + max_pfn_mapped = max_low_pfn_mapped; + +#ifdef CONFIG_X86_64 + if (max_pfn > max_low_pfn) { + max_pfn_mapped = init_memory_mapping(1UL<<32, + max_pfn<<PAGE_SHIFT); + /* can we preseve max_low_pfn ?*/ + max_low_pfn = max_pfn; } +#endif - nr_cpu_ids = highest_cpu + 1; - printk(KERN_DEBUG "NR_CPUS: %d, nr_cpu_ids: %d\n", NR_CPUS, nr_cpu_ids); + /* + * NOTE: On x86-32, only from this point on, fixmaps are ready for use. + */ - /* Setup percpu data maps */ - setup_per_cpu_maps(); +#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT + if (init_ohci1394_dma_early) + init_ohci1394_dma_on_all_controllers(); +#endif - /* Setup cpumask_of_cpu map */ - setup_cpumask_of_cpu(); -} + reserve_initrd(); + +#ifdef CONFIG_X86_64 + vsmp_init(); +#endif + + dmi_scan_machine(); + + io_delay_init(); + + /* + * Parse the ACPI tables for possible boot-time SMP configuration. + */ + acpi_boot_table_init(); + +#ifdef CONFIG_ACPI_NUMA + /* + * Parse SRAT to discover nodes. + */ + acpi_numa_init(); +#endif + + initmem_init(0, max_pfn); + +#ifdef CONFIG_X86_64 + dma32_reserve_bootmem(); +#endif + +#ifdef CONFIG_ACPI_SLEEP + /* + * Reserve low memory region for sleep support. + */ + acpi_reserve_bootmem(); +#endif +#ifdef CONFIG_X86_FIND_SMP_CONFIG + /* + * Find and reserve possible boot-time SMP configuration: + */ + find_smp_config(); +#endif + reserve_crashkernel(); + + reserve_ibft_region(); + +#ifdef CONFIG_KVM_CLOCK + kvmclock_init(); +#endif + +#if defined(CONFIG_VMI) && defined(CONFIG_X86_32) + /* + * Must be after max_low_pfn is determined, and before kernel + * pagetables are setup. + */ + vmi_init(); +#endif + + paging_init(); + +#ifdef CONFIG_X86_64 + map_vsyscall(); +#endif + +#ifdef CONFIG_X86_GENERICARCH + generic_apic_probe(); +#endif + + early_quirks(); + + /* + * Read APIC and some other early information from ACPI tables. + */ + acpi_boot_init(); + +#if defined(CONFIG_X86_MPPARSE) || defined(CONFIG_X86_VISWS) + /* + * get boot-time SMP configuration: + */ + if (smp_found_config) + get_smp_config(); +#endif + prefill_possible_map(); +#ifdef CONFIG_X86_64 + init_cpu_to_node(); +#endif + +#ifdef CONFIG_X86_NUMAQ + /* + * need to check online nodes num, call it + * here before time_init/tsc_init + */ + numaq_tsc_disable(); +#endif + + init_apic_mappings(); + ioapic_init_mappings(); + +#if defined(CONFIG_SMP) && defined(CONFIG_X86_PC) && defined(CONFIG_X86_32) + if (def_to_bigsmp) + printk(KERN_WARNING "More than 8 CPUs detected and " + "CONFIG_X86_PC cannot handle it.\nUse " + "CONFIG_X86_GENERICARCH or CONFIG_X86_BIGSMP.\n"); +#endif + kvm_guest_init(); + + e820_reserve_resources(); + e820_mark_nosave_regions(max_low_pfn); + +#ifdef CONFIG_X86_32 + request_resource(&iomem_resource, &video_ram_resource); +#endif + reserve_standard_io_resources(); + + e820_setup_gap(); + +#ifdef CONFIG_VT +#if defined(CONFIG_VGA_CONSOLE) + if (!efi_enabled || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY)) + conswitchp = &vga_con; +#elif defined(CONFIG_DUMMY_CONSOLE) + conswitchp = &dummy_con; #endif +#endif +} diff --git a/arch/x86/kernel/setup64.c b/arch/x86/kernel/setup64.c deleted file mode 100644 index aee0e8200777..000000000000 --- a/arch/x86/kernel/setup64.c +++ /dev/null @@ -1,287 +0,0 @@ -/* - * X86-64 specific CPU setup. - * Copyright (C) 1995 Linus Torvalds - * Copyright 2001, 2002, 2003 SuSE Labs / Andi Kleen. - * See setup.c for older changelog. - */ -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/string.h> -#include <linux/bootmem.h> -#include <linux/bitops.h> -#include <linux/module.h> -#include <linux/kgdb.h> -#include <asm/pda.h> -#include <asm/pgtable.h> -#include <asm/processor.h> -#include <asm/desc.h> -#include <asm/atomic.h> -#include <asm/mmu_context.h> -#include <asm/smp.h> -#include <asm/i387.h> -#include <asm/percpu.h> -#include <asm/proto.h> -#include <asm/sections.h> -#include <asm/setup.h> -#include <asm/genapic.h> - -#ifndef CONFIG_DEBUG_BOOT_PARAMS -struct boot_params __initdata boot_params; -#else -struct boot_params boot_params; -#endif - -cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE; - -struct x8664_pda *_cpu_pda[NR_CPUS] __read_mostly; -EXPORT_SYMBOL(_cpu_pda); -struct x8664_pda boot_cpu_pda[NR_CPUS] __cacheline_aligned; - -struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table }; - -char boot_cpu_stack[IRQSTACKSIZE] __attribute__((section(".bss.page_aligned"))); - -unsigned long __supported_pte_mask __read_mostly = ~0UL; -EXPORT_SYMBOL_GPL(__supported_pte_mask); - -static int do_not_nx __cpuinitdata = 0; - -/* noexec=on|off -Control non executable mappings for 64bit processes. - -on Enable(default) -off Disable -*/ -static int __init nonx_setup(char *str) -{ - if (!str) - return -EINVAL; - if (!strncmp(str, "on", 2)) { - __supported_pte_mask |= _PAGE_NX; - do_not_nx = 0; - } else if (!strncmp(str, "off", 3)) { - do_not_nx = 1; - __supported_pte_mask &= ~_PAGE_NX; - } - return 0; -} -early_param("noexec", nonx_setup); - -int force_personality32 = 0; - -/* noexec32=on|off -Control non executable heap for 32bit processes. -To control the stack too use noexec=off - -on PROT_READ does not imply PROT_EXEC for 32bit processes (default) -off PROT_READ implies PROT_EXEC -*/ -static int __init nonx32_setup(char *str) -{ - if (!strcmp(str, "on")) - force_personality32 &= ~READ_IMPLIES_EXEC; - else if (!strcmp(str, "off")) - force_personality32 |= READ_IMPLIES_EXEC; - return 1; -} -__setup("noexec32=", nonx32_setup); - -void pda_init(int cpu) -{ - struct x8664_pda *pda = cpu_pda(cpu); - - /* Setup up data that may be needed in __get_free_pages early */ - asm volatile("movl %0,%%fs ; movl %0,%%gs" :: "r" (0)); - /* Memory clobbers used to order PDA accessed */ - mb(); - wrmsrl(MSR_GS_BASE, pda); - mb(); - - pda->cpunumber = cpu; - pda->irqcount = -1; - pda->kernelstack = - (unsigned long)stack_thread_info() - PDA_STACKOFFSET + THREAD_SIZE; - pda->active_mm = &init_mm; - pda->mmu_state = 0; - - if (cpu == 0) { - /* others are initialized in smpboot.c */ - pda->pcurrent = &init_task; - pda->irqstackptr = boot_cpu_stack; - } else { - pda->irqstackptr = (char *) - __get_free_pages(GFP_ATOMIC, IRQSTACK_ORDER); - if (!pda->irqstackptr) - panic("cannot allocate irqstack for cpu %d", cpu); - } - - - pda->irqstackptr += IRQSTACKSIZE-64; -} - -char boot_exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ] -__attribute__((section(".bss.page_aligned"))); - -extern asmlinkage void ignore_sysret(void); - -/* May not be marked __init: used by software suspend */ -void syscall_init(void) -{ - /* - * LSTAR and STAR live in a bit strange symbiosis. - * They both write to the same internal register. STAR allows to set CS/DS - * but only a 32bit target. LSTAR sets the 64bit rip. - */ - wrmsrl(MSR_STAR, ((u64)__USER32_CS)<<48 | ((u64)__KERNEL_CS)<<32); - wrmsrl(MSR_LSTAR, system_call); - wrmsrl(MSR_CSTAR, ignore_sysret); - -#ifdef CONFIG_IA32_EMULATION - syscall32_cpu_init (); -#endif - - /* Flags to clear on syscall */ - wrmsrl(MSR_SYSCALL_MASK, - X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|X86_EFLAGS_IOPL); -} - -void __cpuinit check_efer(void) -{ - unsigned long efer; - - rdmsrl(MSR_EFER, efer); - if (!(efer & EFER_NX) || do_not_nx) { - __supported_pte_mask &= ~_PAGE_NX; - } -} - -unsigned long kernel_eflags; - -/* - * Copies of the original ist values from the tss are only accessed during - * debugging, no special alignment required. - */ -DEFINE_PER_CPU(struct orig_ist, orig_ist); - -/* - * cpu_init() initializes state that is per-CPU. Some data is already - * initialized (naturally) in the bootstrap process, such as the GDT - * and IDT. We reload them nevertheless, this function acts as a - * 'CPU state barrier', nothing should get across. - * A lot of state is already set up in PDA init. - */ -void __cpuinit cpu_init (void) -{ - int cpu = stack_smp_processor_id(); - struct tss_struct *t = &per_cpu(init_tss, cpu); - struct orig_ist *orig_ist = &per_cpu(orig_ist, cpu); - unsigned long v; - char *estacks = NULL; - struct task_struct *me; - int i; - - /* CPU 0 is initialised in head64.c */ - if (cpu != 0) { - pda_init(cpu); - } else - estacks = boot_exception_stacks; - - me = current; - - if (cpu_test_and_set(cpu, cpu_initialized)) - panic("CPU#%d already initialized!\n", cpu); - - printk("Initializing CPU#%d\n", cpu); - - clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); - - /* - * Initialize the per-CPU GDT with the boot GDT, - * and set up the GDT descriptor: - */ - if (cpu) - memcpy(get_cpu_gdt_table(cpu), cpu_gdt_table, GDT_SIZE); - - cpu_gdt_descr[cpu].size = GDT_SIZE; - load_gdt((const struct desc_ptr *)&cpu_gdt_descr[cpu]); - load_idt((const struct desc_ptr *)&idt_descr); - - memset(me->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8); - syscall_init(); - - wrmsrl(MSR_FS_BASE, 0); - wrmsrl(MSR_KERNEL_GS_BASE, 0); - barrier(); - - check_efer(); - - /* - * set up and load the per-CPU TSS - */ - for (v = 0; v < N_EXCEPTION_STACKS; v++) { - static const unsigned int order[N_EXCEPTION_STACKS] = { - [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STACK_ORDER, - [DEBUG_STACK - 1] = DEBUG_STACK_ORDER - }; - if (cpu) { - estacks = (char *)__get_free_pages(GFP_ATOMIC, order[v]); - if (!estacks) - panic("Cannot allocate exception stack %ld %d\n", - v, cpu); - } - estacks += PAGE_SIZE << order[v]; - orig_ist->ist[v] = t->x86_tss.ist[v] = (unsigned long)estacks; - } - - t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap); - /* - * <= is required because the CPU will access up to - * 8 bits beyond the end of the IO permission bitmap. - */ - for (i = 0; i <= IO_BITMAP_LONGS; i++) - t->io_bitmap[i] = ~0UL; - - atomic_inc(&init_mm.mm_count); - me->active_mm = &init_mm; - if (me->mm) - BUG(); - enter_lazy_tlb(&init_mm, me); - - set_tss_desc(cpu, t); - load_TR_desc(); - load_LDT(&init_mm.context); - -#ifdef CONFIG_KGDB - /* - * If the kgdb is connected no debug regs should be altered. This - * is only applicable when KGDB and a KGDB I/O module are built - * into the kernel and you are using early debugging with - * kgdbwait. KGDB will control the kernel HW breakpoint registers. - */ - if (kgdb_connected && arch_kgdb_ops.correct_hw_break) - arch_kgdb_ops.correct_hw_break(); - else { -#endif - /* - * Clear all 6 debug registers: - */ - - set_debugreg(0UL, 0); - set_debugreg(0UL, 1); - set_debugreg(0UL, 2); - set_debugreg(0UL, 3); - set_debugreg(0UL, 6); - set_debugreg(0UL, 7); -#ifdef CONFIG_KGDB - /* If the kgdb is connected no debug regs should be altered. */ - } -#endif - - fpu_init(); - - raw_local_save_flags(kernel_eflags); - - if (is_uv_system()) - uv_cpu_init(); -} diff --git a/arch/x86/kernel/setup_32.c b/arch/x86/kernel/setup_32.c deleted file mode 100644 index 2c5f8b213e86..000000000000 --- a/arch/x86/kernel/setup_32.c +++ /dev/null @@ -1,958 +0,0 @@ -/* - * Copyright (C) 1995 Linus Torvalds - * - * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 - * - * Memory region support - * David Parsons <orc@pell.chi.il.us>, July-August 1999 - * - * Added E820 sanitization routine (removes overlapping memory regions); - * Brian Moyle <bmoyle@mvista.com>, February 2001 - * - * Moved CPU detection code to cpu/${cpu}.c - * Patrick Mochel <mochel@osdl.org>, March 2002 - * - * Provisions for empty E820 memory regions (reported by certain BIOSes). - * Alex Achenbach <xela@slit.de>, December 2002. - * - */ - -/* - * This file handles the architecture-dependent parts of initialization - */ - -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/mmzone.h> -#include <linux/screen_info.h> -#include <linux/ioport.h> -#include <linux/acpi.h> -#include <linux/apm_bios.h> -#include <linux/initrd.h> -#include <linux/bootmem.h> -#include <linux/seq_file.h> -#include <linux/console.h> -#include <linux/mca.h> -#include <linux/root_dev.h> -#include <linux/highmem.h> -#include <linux/module.h> -#include <linux/efi.h> -#include <linux/init.h> -#include <linux/edd.h> -#include <linux/iscsi_ibft.h> -#include <linux/nodemask.h> -#include <linux/kexec.h> -#include <linux/crash_dump.h> -#include <linux/dmi.h> -#include <linux/pfn.h> -#include <linux/pci.h> -#include <linux/init_ohci1394_dma.h> -#include <linux/kvm_para.h> - -#include <video/edid.h> - -#include <asm/mtrr.h> -#include <asm/apic.h> -#include <asm/e820.h> -#include <asm/mpspec.h> -#include <asm/mmzone.h> -#include <asm/setup.h> -#include <asm/arch_hooks.h> -#include <asm/sections.h> -#include <asm/io_apic.h> -#include <asm/ist.h> -#include <asm/io.h> -#include <asm/vmi.h> -#include <setup_arch.h> -#include <asm/bios_ebda.h> -#include <asm/cacheflush.h> -#include <asm/processor.h> - -/* This value is set up by the early boot code to point to the value - immediately after the boot time page tables. It contains a *physical* - address, and must not be in the .bss segment! */ -unsigned long init_pg_tables_end __initdata = ~0UL; - -/* - * Machine setup.. - */ -static struct resource data_resource = { - .name = "Kernel data", - .start = 0, - .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM -}; - -static struct resource code_resource = { - .name = "Kernel code", - .start = 0, - .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM -}; - -static struct resource bss_resource = { - .name = "Kernel bss", - .start = 0, - .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM -}; - -static struct resource video_ram_resource = { - .name = "Video RAM area", - .start = 0xa0000, - .end = 0xbffff, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM -}; - -static struct resource standard_io_resources[] = { { - .name = "dma1", - .start = 0x0000, - .end = 0x001f, - .flags = IORESOURCE_BUSY | IORESOURCE_IO -}, { - .name = "pic1", - .start = 0x0020, - .end = 0x0021, - .flags = IORESOURCE_BUSY | IORESOURCE_IO -}, { - .name = "timer0", - .start = 0x0040, - .end = 0x0043, - .flags = IORESOURCE_BUSY | IORESOURCE_IO -}, { - .name = "timer1", - .start = 0x0050, - .end = 0x0053, - .flags = IORESOURCE_BUSY | IORESOURCE_IO -}, { - .name = "keyboard", - .start = 0x0060, - .end = 0x0060, - .flags = IORESOURCE_BUSY | IORESOURCE_IO -}, { - .name = "keyboard", - .start = 0x0064, - .end = 0x0064, - .flags = IORESOURCE_BUSY | IORESOURCE_IO -}, { - .name = "dma page reg", - .start = 0x0080, - .end = 0x008f, - .flags = IORESOURCE_BUSY | IORESOURCE_IO -}, { - .name = "pic2", - .start = 0x00a0, - .end = 0x00a1, - .flags = IORESOURCE_BUSY | IORESOURCE_IO -}, { - .name = "dma2", - .start = 0x00c0, - .end = 0x00df, - .flags = IORESOURCE_BUSY | IORESOURCE_IO -}, { - .name = "fpu", - .start = 0x00f0, - .end = 0x00ff, - .flags = IORESOURCE_BUSY | IORESOURCE_IO -} }; - -/* cpu data as detected by the assembly code in head.S */ -struct cpuinfo_x86 new_cpu_data __cpuinitdata = { 0, 0, 0, 0, -1, 1, 0, 0, -1 }; -/* common cpu data for all cpus */ -struct cpuinfo_x86 boot_cpu_data __read_mostly = { 0, 0, 0, 0, -1, 1, 0, 0, -1 }; -EXPORT_SYMBOL(boot_cpu_data); - -unsigned int def_to_bigsmp; - -#ifndef CONFIG_X86_PAE -unsigned long mmu_cr4_features; -#else -unsigned long mmu_cr4_features = X86_CR4_PAE; -#endif - -/* for MCA, but anyone else can use it if they want */ -unsigned int machine_id; -unsigned int machine_submodel_id; -unsigned int BIOS_revision; - -/* Boot loader ID as an integer, for the benefit of proc_dointvec */ -int bootloader_type; - -/* user-defined highmem size */ -static unsigned int highmem_pages = -1; - -/* - * Setup options - */ -struct screen_info screen_info; -EXPORT_SYMBOL(screen_info); -struct apm_info apm_info; -EXPORT_SYMBOL(apm_info); -struct edid_info edid_info; -EXPORT_SYMBOL_GPL(edid_info); -struct ist_info ist_info; -#if defined(CONFIG_X86_SPEEDSTEP_SMI) || \ - defined(CONFIG_X86_SPEEDSTEP_SMI_MODULE) -EXPORT_SYMBOL(ist_info); -#endif - -extern void early_cpu_init(void); -extern int root_mountflags; - -unsigned long saved_video_mode; - -#define RAMDISK_IMAGE_START_MASK 0x07FF -#define RAMDISK_PROMPT_FLAG 0x8000 -#define RAMDISK_LOAD_FLAG 0x4000 - -static char __initdata command_line[COMMAND_LINE_SIZE]; - -#ifndef CONFIG_DEBUG_BOOT_PARAMS -struct boot_params __initdata boot_params; -#else -struct boot_params boot_params; -#endif - -#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE) -struct edd edd; -#ifdef CONFIG_EDD_MODULE -EXPORT_SYMBOL(edd); -#endif -/** - * copy_edd() - Copy the BIOS EDD information - * from boot_params into a safe place. - * - */ -static inline void copy_edd(void) -{ - memcpy(edd.mbr_signature, boot_params.edd_mbr_sig_buffer, - sizeof(edd.mbr_signature)); - memcpy(edd.edd_info, boot_params.eddbuf, sizeof(edd.edd_info)); - edd.mbr_signature_nr = boot_params.edd_mbr_sig_buf_entries; - edd.edd_info_nr = boot_params.eddbuf_entries; -} -#else -static inline void copy_edd(void) -{ -} -#endif - -int __initdata user_defined_memmap; - -/* - * "mem=nopentium" disables the 4MB page tables. - * "mem=XXX[kKmM]" defines a memory region from HIGH_MEM - * to <mem>, overriding the bios size. - * "memmap=XXX[KkmM]@XXX[KkmM]" defines a memory region from - * <start> to <start>+<mem>, overriding the bios size. - * - * HPA tells me bootloaders need to parse mem=, so no new - * option should be mem= [also see Documentation/i386/boot.txt] - */ -static int __init parse_mem(char *arg) -{ - if (!arg) - return -EINVAL; - - if (strcmp(arg, "nopentium") == 0) { - setup_clear_cpu_cap(X86_FEATURE_PSE); - } else { - /* If the user specifies memory size, we - * limit the BIOS-provided memory map to - * that size. exactmap can be used to specify - * the exact map. mem=number can be used to - * trim the existing memory map. - */ - unsigned long long mem_size; - - mem_size = memparse(arg, &arg); - limit_regions(mem_size); - user_defined_memmap = 1; - } - return 0; -} -early_param("mem", parse_mem); - -#ifdef CONFIG_PROC_VMCORE -/* elfcorehdr= specifies the location of elf core header - * stored by the crashed kernel. - */ -static int __init parse_elfcorehdr(char *arg) -{ - if (!arg) - return -EINVAL; - - elfcorehdr_addr = memparse(arg, &arg); - return 0; -} -early_param("elfcorehdr", parse_elfcorehdr); -#endif /* CONFIG_PROC_VMCORE */ - -/* - * highmem=size forces highmem to be exactly 'size' bytes. - * This works even on boxes that have no highmem otherwise. - * This also works to reduce highmem size on bigger boxes. - */ -static int __init parse_highmem(char *arg) -{ - if (!arg) - return -EINVAL; - - highmem_pages = memparse(arg, &arg) >> PAGE_SHIFT; - return 0; -} -early_param("highmem", parse_highmem); - -/* - * vmalloc=size forces the vmalloc area to be exactly 'size' - * bytes. This can be used to increase (or decrease) the - * vmalloc area - the default is 128m. - */ -static int __init parse_vmalloc(char *arg) -{ - if (!arg) - return -EINVAL; - - __VMALLOC_RESERVE = memparse(arg, &arg); - return 0; -} -early_param("vmalloc", parse_vmalloc); - -/* - * reservetop=size reserves a hole at the top of the kernel address space which - * a hypervisor can load into later. Needed for dynamically loaded hypervisors, - * so relocating the fixmap can be done before paging initialization. - */ -static int __init parse_reservetop(char *arg) -{ - unsigned long address; - - if (!arg) - return -EINVAL; - - address = memparse(arg, &arg); - reserve_top_address(address); - return 0; -} -early_param("reservetop", parse_reservetop); - -/* - * Determine low and high memory ranges: - */ -unsigned long __init find_max_low_pfn(void) -{ - unsigned long max_low_pfn; - - max_low_pfn = max_pfn; - if (max_low_pfn > MAXMEM_PFN) { - if (highmem_pages == -1) - highmem_pages = max_pfn - MAXMEM_PFN; - if (highmem_pages + MAXMEM_PFN < max_pfn) - max_pfn = MAXMEM_PFN + highmem_pages; - if (highmem_pages + MAXMEM_PFN > max_pfn) { - printk("only %luMB highmem pages available, ignoring highmem size of %uMB.\n", pages_to_mb(max_pfn - MAXMEM_PFN), pages_to_mb(highmem_pages)); - highmem_pages = 0; - } - max_low_pfn = MAXMEM_PFN; -#ifndef CONFIG_HIGHMEM - /* Maximum memory usable is what is directly addressable */ - printk(KERN_WARNING "Warning only %ldMB will be used.\n", - MAXMEM>>20); - if (max_pfn > MAX_NONPAE_PFN) - printk(KERN_WARNING "Use a HIGHMEM64G enabled kernel.\n"); - else - printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n"); - max_pfn = MAXMEM_PFN; -#else /* !CONFIG_HIGHMEM */ -#ifndef CONFIG_HIGHMEM64G - if (max_pfn > MAX_NONPAE_PFN) { - max_pfn = MAX_NONPAE_PFN; - printk(KERN_WARNING "Warning only 4GB will be used.\n"); - printk(KERN_WARNING "Use a HIGHMEM64G enabled kernel.\n"); - } -#endif /* !CONFIG_HIGHMEM64G */ -#endif /* !CONFIG_HIGHMEM */ - } else { - if (highmem_pages == -1) - highmem_pages = 0; -#ifdef CONFIG_HIGHMEM - if (highmem_pages >= max_pfn) { - printk(KERN_ERR "highmem size specified (%uMB) is bigger than pages available (%luMB)!.\n", pages_to_mb(highmem_pages), pages_to_mb(max_pfn)); - highmem_pages = 0; - } - if (highmem_pages) { - if (max_low_pfn-highmem_pages < 64*1024*1024/PAGE_SIZE){ - printk(KERN_ERR "highmem size %uMB results in smaller than 64MB lowmem, ignoring it.\n", pages_to_mb(highmem_pages)); - highmem_pages = 0; - } - max_low_pfn -= highmem_pages; - } -#else - if (highmem_pages) - printk(KERN_ERR "ignoring highmem size on non-highmem kernel!\n"); -#endif - } - return max_low_pfn; -} - -#define BIOS_LOWMEM_KILOBYTES 0x413 - -/* - * The BIOS places the EBDA/XBDA at the top of conventional - * memory, and usually decreases the reported amount of - * conventional memory (int 0x12) too. This also contains a - * workaround for Dell systems that neglect to reserve EBDA. - * The same workaround also avoids a problem with the AMD768MPX - * chipset: reserve a page before VGA to prevent PCI prefetch - * into it (errata #56). Usually the page is reserved anyways, - * unless you have no PS/2 mouse plugged in. - */ -static void __init reserve_ebda_region(void) -{ - unsigned int lowmem, ebda_addr; - - /* To determine the position of the EBDA and the */ - /* end of conventional memory, we need to look at */ - /* the BIOS data area. In a paravirtual environment */ - /* that area is absent. We'll just have to assume */ - /* that the paravirt case can handle memory setup */ - /* correctly, without our help. */ - if (paravirt_enabled()) - return; - - /* end of low (conventional) memory */ - lowmem = *(unsigned short *)__va(BIOS_LOWMEM_KILOBYTES); - lowmem <<= 10; - - /* start of EBDA area */ - ebda_addr = get_bios_ebda(); - - /* Fixup: bios puts an EBDA in the top 64K segment */ - /* of conventional memory, but does not adjust lowmem. */ - if ((lowmem - ebda_addr) <= 0x10000) - lowmem = ebda_addr; - - /* Fixup: bios does not report an EBDA at all. */ - /* Some old Dells seem to need 4k anyhow (bugzilla 2990) */ - if ((ebda_addr == 0) && (lowmem >= 0x9f000)) - lowmem = 0x9f000; - - /* Paranoia: should never happen, but... */ - if ((lowmem == 0) || (lowmem >= 0x100000)) - lowmem = 0x9f000; - - /* reserve all memory between lowmem and the 1MB mark */ - reserve_bootmem(lowmem, 0x100000 - lowmem, BOOTMEM_DEFAULT); -} - -#ifndef CONFIG_NEED_MULTIPLE_NODES -static void __init setup_bootmem_allocator(void); -static unsigned long __init setup_memory(void) -{ - /* - * partially used pages are not usable - thus - * we are rounding upwards: - */ - min_low_pfn = PFN_UP(init_pg_tables_end); - - max_low_pfn = find_max_low_pfn(); - -#ifdef CONFIG_HIGHMEM - highstart_pfn = highend_pfn = max_pfn; - if (max_pfn > max_low_pfn) { - highstart_pfn = max_low_pfn; - } - printk(KERN_NOTICE "%ldMB HIGHMEM available.\n", - pages_to_mb(highend_pfn - highstart_pfn)); - num_physpages = highend_pfn; - high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1; -#else - num_physpages = max_low_pfn; - high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1; -#endif -#ifdef CONFIG_FLATMEM - max_mapnr = num_physpages; -#endif - printk(KERN_NOTICE "%ldMB LOWMEM available.\n", - pages_to_mb(max_low_pfn)); - - setup_bootmem_allocator(); - - return max_low_pfn; -} - -static void __init zone_sizes_init(void) -{ - unsigned long max_zone_pfns[MAX_NR_ZONES]; - memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); - max_zone_pfns[ZONE_DMA] = - virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT; - max_zone_pfns[ZONE_NORMAL] = max_low_pfn; -#ifdef CONFIG_HIGHMEM - max_zone_pfns[ZONE_HIGHMEM] = highend_pfn; - add_active_range(0, 0, highend_pfn); -#else - add_active_range(0, 0, max_low_pfn); -#endif - - free_area_init_nodes(max_zone_pfns); -} -#else -extern unsigned long __init setup_memory(void); -extern void zone_sizes_init(void); -#endif /* !CONFIG_NEED_MULTIPLE_NODES */ - -static inline unsigned long long get_total_mem(void) -{ - unsigned long long total; - - total = max_low_pfn - min_low_pfn; -#ifdef CONFIG_HIGHMEM - total += highend_pfn - highstart_pfn; -#endif - - return total << PAGE_SHIFT; -} - -#ifdef CONFIG_KEXEC -static void __init reserve_crashkernel(void) -{ - unsigned long long total_mem; - unsigned long long crash_size, crash_base; - int ret; - - total_mem = get_total_mem(); - - ret = parse_crashkernel(boot_command_line, total_mem, - &crash_size, &crash_base); - if (ret == 0 && crash_size > 0) { - if (crash_base > 0) { - printk(KERN_INFO "Reserving %ldMB of memory at %ldMB " - "for crashkernel (System RAM: %ldMB)\n", - (unsigned long)(crash_size >> 20), - (unsigned long)(crash_base >> 20), - (unsigned long)(total_mem >> 20)); - crashk_res.start = crash_base; - crashk_res.end = crash_base + crash_size - 1; - reserve_bootmem(crash_base, crash_size, - BOOTMEM_DEFAULT); - } else - printk(KERN_INFO "crashkernel reservation failed - " - "you have to specify a base address\n"); - } -} -#else -static inline void __init reserve_crashkernel(void) -{} -#endif - -#ifdef CONFIG_BLK_DEV_INITRD - -static bool do_relocate_initrd = false; - -static void __init reserve_initrd(void) -{ - unsigned long ramdisk_image = boot_params.hdr.ramdisk_image; - unsigned long ramdisk_size = boot_params.hdr.ramdisk_size; - unsigned long ramdisk_end = ramdisk_image + ramdisk_size; - unsigned long end_of_lowmem = max_low_pfn << PAGE_SHIFT; - unsigned long ramdisk_here; - - initrd_start = 0; - - if (!boot_params.hdr.type_of_loader || - !ramdisk_image || !ramdisk_size) - return; /* No initrd provided by bootloader */ - - if (ramdisk_end < ramdisk_image) { - printk(KERN_ERR "initrd wraps around end of memory, " - "disabling initrd\n"); - return; - } - if (ramdisk_size >= end_of_lowmem/2) { - printk(KERN_ERR "initrd too large to handle, " - "disabling initrd\n"); - return; - } - if (ramdisk_end <= end_of_lowmem) { - /* All in lowmem, easy case */ - reserve_bootmem(ramdisk_image, ramdisk_size, BOOTMEM_DEFAULT); - initrd_start = ramdisk_image + PAGE_OFFSET; - initrd_end = initrd_start+ramdisk_size; - return; - } - - /* We need to move the initrd down into lowmem */ - ramdisk_here = (end_of_lowmem - ramdisk_size) & PAGE_MASK; - - /* Note: this includes all the lowmem currently occupied by - the initrd, we rely on that fact to keep the data intact. */ - reserve_bootmem(ramdisk_here, ramdisk_size, BOOTMEM_DEFAULT); - initrd_start = ramdisk_here + PAGE_OFFSET; - initrd_end = initrd_start + ramdisk_size; - - do_relocate_initrd = true; -} - -#define MAX_MAP_CHUNK (NR_FIX_BTMAPS << PAGE_SHIFT) - -static void __init relocate_initrd(void) -{ - unsigned long ramdisk_image = boot_params.hdr.ramdisk_image; - unsigned long ramdisk_size = boot_params.hdr.ramdisk_size; - unsigned long end_of_lowmem = max_low_pfn << PAGE_SHIFT; - unsigned long ramdisk_here; - unsigned long slop, clen, mapaddr; - char *p, *q; - - if (!do_relocate_initrd) - return; - - ramdisk_here = initrd_start - PAGE_OFFSET; - - q = (char *)initrd_start; - - /* Copy any lowmem portion of the initrd */ - if (ramdisk_image < end_of_lowmem) { - clen = end_of_lowmem - ramdisk_image; - p = (char *)__va(ramdisk_image); - memcpy(q, p, clen); - q += clen; - ramdisk_image += clen; - ramdisk_size -= clen; - } - - /* Copy the highmem portion of the initrd */ - while (ramdisk_size) { - slop = ramdisk_image & ~PAGE_MASK; - clen = ramdisk_size; - if (clen > MAX_MAP_CHUNK-slop) - clen = MAX_MAP_CHUNK-slop; - mapaddr = ramdisk_image & PAGE_MASK; - p = early_ioremap(mapaddr, clen+slop); - memcpy(q, p+slop, clen); - early_iounmap(p, clen+slop); - q += clen; - ramdisk_image += clen; - ramdisk_size -= clen; - } -} - -#endif /* CONFIG_BLK_DEV_INITRD */ - -void __init setup_bootmem_allocator(void) -{ - unsigned long bootmap_size; - /* - * Initialize the boot-time allocator (with low memory only): - */ - bootmap_size = init_bootmem(min_low_pfn, max_low_pfn); - - register_bootmem_low_pages(max_low_pfn); - - /* - * Reserve the bootmem bitmap itself as well. We do this in two - * steps (first step was init_bootmem()) because this catches - * the (very unlikely) case of us accidentally initializing the - * bootmem allocator with an invalid RAM area. - */ - reserve_bootmem(__pa_symbol(_text), (PFN_PHYS(min_low_pfn) + - bootmap_size + PAGE_SIZE-1) - __pa_symbol(_text), - BOOTMEM_DEFAULT); - - /* - * reserve physical page 0 - it's a special BIOS page on many boxes, - * enabling clean reboots, SMP operation, laptop functions. - */ - reserve_bootmem(0, PAGE_SIZE, BOOTMEM_DEFAULT); - - /* reserve EBDA region */ - reserve_ebda_region(); - -#ifdef CONFIG_SMP - /* - * But first pinch a few for the stack/trampoline stuff - * FIXME: Don't need the extra page at 4K, but need to fix - * trampoline before removing it. (see the GDT stuff) - */ - reserve_bootmem(PAGE_SIZE, PAGE_SIZE, BOOTMEM_DEFAULT); -#endif -#ifdef CONFIG_ACPI_SLEEP - /* - * Reserve low memory region for sleep support. - */ - acpi_reserve_bootmem(); -#endif -#ifdef CONFIG_X86_FIND_SMP_CONFIG - /* - * Find and reserve possible boot-time SMP configuration: - */ - find_smp_config(); -#endif -#ifdef CONFIG_BLK_DEV_INITRD - reserve_initrd(); -#endif - numa_kva_reserve(); - reserve_crashkernel(); - - reserve_ibft_region(); -} - -/* - * The node 0 pgdat is initialized before all of these because - * it's needed for bootmem. node>0 pgdats have their virtual - * space allocated before the pagetables are in place to access - * them, so they can't be cleared then. - * - * This should all compile down to nothing when NUMA is off. - */ -static void __init remapped_pgdat_init(void) -{ - int nid; - - for_each_online_node(nid) { - if (nid != 0) - memset(NODE_DATA(nid), 0, sizeof(struct pglist_data)); - } -} - -#ifdef CONFIG_MCA -static void set_mca_bus(int x) -{ - MCA_bus = x; -} -#else -static void set_mca_bus(int x) { } -#endif - -/* Overridden in paravirt.c if CONFIG_PARAVIRT */ -char * __init __attribute__((weak)) memory_setup(void) -{ - return machine_specific_memory_setup(); -} - -#ifdef CONFIG_NUMA -/* - * In the golden day, when everything among i386 and x86_64 will be - * integrated, this will not live here - */ -void *x86_cpu_to_node_map_early_ptr; -int x86_cpu_to_node_map_init[NR_CPUS] = { - [0 ... NR_CPUS-1] = NUMA_NO_NODE -}; -DEFINE_PER_CPU(int, x86_cpu_to_node_map) = NUMA_NO_NODE; -#endif - -/* - * Determine if we were loaded by an EFI loader. If so, then we have also been - * passed the efi memmap, systab, etc., so we should use these data structures - * for initialization. Note, the efi init code path is determined by the - * global efi_enabled. This allows the same kernel image to be used on existing - * systems (with a traditional BIOS) as well as on EFI systems. - */ -void __init setup_arch(char **cmdline_p) -{ - unsigned long max_low_pfn; - - memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data)); - pre_setup_arch_hook(); - early_cpu_init(); - early_ioremap_init(); - -#ifdef CONFIG_EFI - if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, - "EL32", 4)) - efi_enabled = 1; -#endif - - ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev); - screen_info = boot_params.screen_info; - edid_info = boot_params.edid_info; - apm_info.bios = boot_params.apm_bios_info; - ist_info = boot_params.ist_info; - saved_video_mode = boot_params.hdr.vid_mode; - if( boot_params.sys_desc_table.length != 0 ) { - set_mca_bus(boot_params.sys_desc_table.table[3] & 0x2); - machine_id = boot_params.sys_desc_table.table[0]; - machine_submodel_id = boot_params.sys_desc_table.table[1]; - BIOS_revision = boot_params.sys_desc_table.table[2]; - } - bootloader_type = boot_params.hdr.type_of_loader; - -#ifdef CONFIG_BLK_DEV_RAM - rd_image_start = boot_params.hdr.ram_size & RAMDISK_IMAGE_START_MASK; - rd_prompt = ((boot_params.hdr.ram_size & RAMDISK_PROMPT_FLAG) != 0); - rd_doload = ((boot_params.hdr.ram_size & RAMDISK_LOAD_FLAG) != 0); -#endif - ARCH_SETUP - - printk(KERN_INFO "BIOS-provided physical RAM map:\n"); - print_memory_map(memory_setup()); - - copy_edd(); - - if (!boot_params.hdr.root_flags) - root_mountflags &= ~MS_RDONLY; - init_mm.start_code = (unsigned long) _text; - init_mm.end_code = (unsigned long) _etext; - init_mm.end_data = (unsigned long) _edata; - init_mm.brk = init_pg_tables_end + PAGE_OFFSET; - - code_resource.start = virt_to_phys(_text); - code_resource.end = virt_to_phys(_etext)-1; - data_resource.start = virt_to_phys(_etext); - data_resource.end = virt_to_phys(_edata)-1; - bss_resource.start = virt_to_phys(&__bss_start); - bss_resource.end = virt_to_phys(&__bss_stop)-1; - - parse_early_param(); - - if (user_defined_memmap) { - printk(KERN_INFO "user-defined physical RAM map:\n"); - print_memory_map("user"); - } - - strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE); - *cmdline_p = command_line; - - if (efi_enabled) - efi_init(); - - /* update e820 for memory not covered by WB MTRRs */ - propagate_e820_map(); - mtrr_bp_init(); - if (mtrr_trim_uncached_memory(max_pfn)) - propagate_e820_map(); - - max_low_pfn = setup_memory(); - -#ifdef CONFIG_KVM_CLOCK - kvmclock_init(); -#endif - -#ifdef CONFIG_VMI - /* - * Must be after max_low_pfn is determined, and before kernel - * pagetables are setup. - */ - vmi_init(); -#endif - kvm_guest_init(); - - /* - * NOTE: before this point _nobody_ is allowed to allocate - * any memory using the bootmem allocator. Although the - * allocator is now initialised only the first 8Mb of the kernel - * virtual address space has been mapped. All allocations before - * paging_init() has completed must use the alloc_bootmem_low_pages() - * variant (which allocates DMA'able memory) and care must be taken - * not to exceed the 8Mb limit. - */ - -#ifdef CONFIG_SMP - smp_alloc_memory(); /* AP processor realmode stacks in low memory*/ -#endif - paging_init(); - - /* - * NOTE: On x86-32, only from this point on, fixmaps are ready for use. - */ - -#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT - if (init_ohci1394_dma_early) - init_ohci1394_dma_on_all_controllers(); -#endif - - remapped_pgdat_init(); - sparse_init(); - zone_sizes_init(); - - /* - * NOTE: at this point the bootmem allocator is fully available. - */ - -#ifdef CONFIG_BLK_DEV_INITRD - relocate_initrd(); -#endif - - paravirt_post_allocator_init(); - - dmi_scan_machine(); - - io_delay_init(); - -#ifdef CONFIG_X86_SMP - /* - * setup to use the early static init tables during kernel startup - * X86_SMP will exclude sub-arches that don't deal well with it. - */ - x86_cpu_to_apicid_early_ptr = (void *)x86_cpu_to_apicid_init; - x86_bios_cpu_apicid_early_ptr = (void *)x86_bios_cpu_apicid_init; -#ifdef CONFIG_NUMA - x86_cpu_to_node_map_early_ptr = (void *)x86_cpu_to_node_map_init; -#endif -#endif - -#ifdef CONFIG_X86_GENERICARCH - generic_apic_probe(); -#endif - -#ifdef CONFIG_ACPI - /* - * Parse the ACPI tables for possible boot-time SMP configuration. - */ - acpi_boot_table_init(); -#endif - - early_quirks(); - -#ifdef CONFIG_ACPI - acpi_boot_init(); - -#if defined(CONFIG_SMP) && defined(CONFIG_X86_PC) - if (def_to_bigsmp) - printk(KERN_WARNING "More than 8 CPUs detected and " - "CONFIG_X86_PC cannot handle it.\nUse " - "CONFIG_X86_GENERICARCH or CONFIG_X86_BIGSMP.\n"); -#endif -#endif -#ifdef CONFIG_X86_LOCAL_APIC - if (smp_found_config) - get_smp_config(); -#endif - - e820_register_memory(); - e820_mark_nosave_regions(); - -#ifdef CONFIG_VT -#if defined(CONFIG_VGA_CONSOLE) - if (!efi_enabled || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY)) - conswitchp = &vga_con; -#elif defined(CONFIG_DUMMY_CONSOLE) - conswitchp = &dummy_con; -#endif -#endif -} - -/* - * Request address space for all standard resources - * - * This is called just before pcibios_init(), which is also a - * subsys_initcall, but is linked in later (in arch/i386/pci/common.c). - */ -static int __init request_standard_resources(void) -{ - int i; - - printk(KERN_INFO "Setting up standard PCI resources\n"); - init_iomem_resources(&code_resource, &data_resource, &bss_resource); - - request_resource(&iomem_resource, &video_ram_resource); - - /* request I/O space for devices used on all i[345]86 PCs */ - for (i = 0; i < ARRAY_SIZE(standard_io_resources); i++) - request_resource(&ioport_resource, &standard_io_resources[i]); - return 0; -} - -subsys_initcall(request_standard_resources); diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c deleted file mode 100644 index 6dff1286ad8a..000000000000 --- a/arch/x86/kernel/setup_64.c +++ /dev/null @@ -1,1194 +0,0 @@ -/* - * Copyright (C) 1995 Linus Torvalds - */ - -/* - * This file handles the architecture-dependent parts of initialization - */ - -#include <linux/errno.h> -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/stddef.h> -#include <linux/unistd.h> -#include <linux/ptrace.h> -#include <linux/slab.h> -#include <linux/user.h> -#include <linux/screen_info.h> -#include <linux/ioport.h> -#include <linux/delay.h> -#include <linux/init.h> -#include <linux/initrd.h> -#include <linux/highmem.h> -#include <linux/bootmem.h> -#include <linux/module.h> -#include <asm/processor.h> -#include <linux/console.h> -#include <linux/seq_file.h> -#include <linux/crash_dump.h> -#include <linux/root_dev.h> -#include <linux/pci.h> -#include <asm/pci-direct.h> -#include <linux/efi.h> -#include <linux/acpi.h> -#include <linux/kallsyms.h> -#include <linux/edd.h> -#include <linux/iscsi_ibft.h> -#include <linux/mmzone.h> -#include <linux/kexec.h> -#include <linux/cpufreq.h> -#include <linux/dmi.h> -#include <linux/dma-mapping.h> -#include <linux/ctype.h> -#include <linux/sort.h> -#include <linux/uaccess.h> -#include <linux/init_ohci1394_dma.h> -#include <linux/kvm_para.h> - -#include <asm/mtrr.h> -#include <asm/uaccess.h> -#include <asm/system.h> -#include <asm/vsyscall.h> -#include <asm/io.h> -#include <asm/smp.h> -#include <asm/msr.h> -#include <asm/desc.h> -#include <video/edid.h> -#include <asm/e820.h> -#include <asm/dma.h> -#include <asm/gart.h> -#include <asm/mpspec.h> -#include <asm/mmu_context.h> -#include <asm/proto.h> -#include <asm/setup.h> -#include <asm/numa.h> -#include <asm/sections.h> -#include <asm/dmi.h> -#include <asm/cacheflush.h> -#include <asm/mce.h> -#include <asm/ds.h> -#include <asm/topology.h> -#include <asm/trampoline.h> -#include <asm/pat.h> - -#include <mach_apic.h> -#ifdef CONFIG_PARAVIRT -#include <asm/paravirt.h> -#else -#define ARCH_SETUP -#endif - -/* - * Machine setup.. - */ - -struct cpuinfo_x86 boot_cpu_data __read_mostly; -EXPORT_SYMBOL(boot_cpu_data); - -__u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata; - -unsigned long mmu_cr4_features; - -/* Boot loader ID as an integer, for the benefit of proc_dointvec */ -int bootloader_type; - -unsigned long saved_video_mode; - -int force_mwait __cpuinitdata; - -/* - * Early DMI memory - */ -int dmi_alloc_index; -char dmi_alloc_data[DMI_MAX_DATA]; - -/* - * Setup options - */ -struct screen_info screen_info; -EXPORT_SYMBOL(screen_info); -struct sys_desc_table_struct { - unsigned short length; - unsigned char table[0]; -}; - -struct edid_info edid_info; -EXPORT_SYMBOL_GPL(edid_info); - -extern int root_mountflags; - -char __initdata command_line[COMMAND_LINE_SIZE]; - -static struct resource standard_io_resources[] = { - { .name = "dma1", .start = 0x00, .end = 0x1f, - .flags = IORESOURCE_BUSY | IORESOURCE_IO }, - { .name = "pic1", .start = 0x20, .end = 0x21, - .flags = IORESOURCE_BUSY | IORESOURCE_IO }, - { .name = "timer0", .start = 0x40, .end = 0x43, - .flags = IORESOURCE_BUSY | IORESOURCE_IO }, - { .name = "timer1", .start = 0x50, .end = 0x53, - .flags = IORESOURCE_BUSY | IORESOURCE_IO }, - { .name = "keyboard", .start = 0x60, .end = 0x60, - .flags = IORESOURCE_BUSY | IORESOURCE_IO }, - { .name = "keyboard", .start = 0x64, .end = 0x64, - .flags = IORESOURCE_BUSY | IORESOURCE_IO }, - { .name = "dma page reg", .start = 0x80, .end = 0x8f, - .flags = IORESOURCE_BUSY | IORESOURCE_IO }, - { .name = "pic2", .start = 0xa0, .end = 0xa1, - .flags = IORESOURCE_BUSY | IORESOURCE_IO }, - { .name = "dma2", .start = 0xc0, .end = 0xdf, - .flags = IORESOURCE_BUSY | IORESOURCE_IO }, - { .name = "fpu", .start = 0xf0, .end = 0xff, - .flags = IORESOURCE_BUSY | IORESOURCE_IO } -}; - -#define IORESOURCE_RAM (IORESOURCE_BUSY | IORESOURCE_MEM) - -static struct resource data_resource = { - .name = "Kernel data", - .start = 0, - .end = 0, - .flags = IORESOURCE_RAM, -}; -static struct resource code_resource = { - .name = "Kernel code", - .start = 0, - .end = 0, - .flags = IORESOURCE_RAM, -}; -static struct resource bss_resource = { - .name = "Kernel bss", - .start = 0, - .end = 0, - .flags = IORESOURCE_RAM, -}; - -static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c); - -#ifdef CONFIG_PROC_VMCORE -/* elfcorehdr= specifies the location of elf core header - * stored by the crashed kernel. This option will be passed - * by kexec loader to the capture kernel. - */ -static int __init setup_elfcorehdr(char *arg) -{ - char *end; - if (!arg) - return -EINVAL; - elfcorehdr_addr = memparse(arg, &end); - return end > arg ? 0 : -EINVAL; -} -early_param("elfcorehdr", setup_elfcorehdr); -#endif - -#ifndef CONFIG_NUMA -static void __init -contig_initmem_init(unsigned long start_pfn, unsigned long end_pfn) -{ - unsigned long bootmap_size, bootmap; - - bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT; - bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size, - PAGE_SIZE); - if (bootmap == -1L) - panic("Cannot find bootmem map of size %ld\n", bootmap_size); - bootmap_size = init_bootmem(bootmap >> PAGE_SHIFT, end_pfn); - e820_register_active_regions(0, start_pfn, end_pfn); - free_bootmem_with_active_regions(0, end_pfn); - early_res_to_bootmem(0, end_pfn<<PAGE_SHIFT); - reserve_bootmem(bootmap, bootmap_size, BOOTMEM_DEFAULT); -} -#endif - -#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE) -struct edd edd; -#ifdef CONFIG_EDD_MODULE -EXPORT_SYMBOL(edd); -#endif -/** - * copy_edd() - Copy the BIOS EDD information - * from boot_params into a safe place. - * - */ -static inline void copy_edd(void) -{ - memcpy(edd.mbr_signature, boot_params.edd_mbr_sig_buffer, - sizeof(edd.mbr_signature)); - memcpy(edd.edd_info, boot_params.eddbuf, sizeof(edd.edd_info)); - edd.mbr_signature_nr = boot_params.edd_mbr_sig_buf_entries; - edd.edd_info_nr = boot_params.eddbuf_entries; -} -#else -static inline void copy_edd(void) -{ -} -#endif - -#ifdef CONFIG_KEXEC -static void __init reserve_crashkernel(void) -{ - unsigned long long total_mem; - unsigned long long crash_size, crash_base; - int ret; - - total_mem = ((unsigned long long)max_low_pfn - min_low_pfn) << PAGE_SHIFT; - - ret = parse_crashkernel(boot_command_line, total_mem, - &crash_size, &crash_base); - if (ret == 0 && crash_size) { - if (crash_base <= 0) { - printk(KERN_INFO "crashkernel reservation failed - " - "you have to specify a base address\n"); - return; - } - - if (reserve_bootmem(crash_base, crash_size, - BOOTMEM_EXCLUSIVE) < 0) { - printk(KERN_INFO "crashkernel reservation failed - " - "memory is in use\n"); - return; - } - - printk(KERN_INFO "Reserving %ldMB of memory at %ldMB " - "for crashkernel (System RAM: %ldMB)\n", - (unsigned long)(crash_size >> 20), - (unsigned long)(crash_base >> 20), - (unsigned long)(total_mem >> 20)); - crashk_res.start = crash_base; - crashk_res.end = crash_base + crash_size - 1; - insert_resource(&iomem_resource, &crashk_res); - } -} -#else -static inline void __init reserve_crashkernel(void) -{} -#endif - -/* Overridden in paravirt.c if CONFIG_PARAVIRT */ -void __attribute__((weak)) __init memory_setup(void) -{ - machine_specific_memory_setup(); -} - -static void __init parse_setup_data(void) -{ - struct setup_data *data; - unsigned long pa_data; - - if (boot_params.hdr.version < 0x0209) - return; - pa_data = boot_params.hdr.setup_data; - while (pa_data) { - data = early_ioremap(pa_data, PAGE_SIZE); - switch (data->type) { - default: - break; - } -#ifndef CONFIG_DEBUG_BOOT_PARAMS - free_early(pa_data, pa_data+sizeof(*data)+data->len); -#endif - pa_data = data->next; - early_iounmap(data, PAGE_SIZE); - } -} - -#ifdef CONFIG_PCI_MMCONFIG -extern void __cpuinit fam10h_check_enable_mmcfg(void); -extern void __init check_enable_amd_mmconf_dmi(void); -#else -void __cpuinit fam10h_check_enable_mmcfg(void) -{ -} -void __init check_enable_amd_mmconf_dmi(void) -{ -} -#endif - -/* - * setup_arch - architecture-specific boot-time initializations - * - * Note: On x86_64, fixmaps are ready for use even before this is called. - */ -void __init setup_arch(char **cmdline_p) -{ - unsigned i; - - printk(KERN_INFO "Command line: %s\n", boot_command_line); - - ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev); - screen_info = boot_params.screen_info; - edid_info = boot_params.edid_info; - saved_video_mode = boot_params.hdr.vid_mode; - bootloader_type = boot_params.hdr.type_of_loader; - -#ifdef CONFIG_BLK_DEV_RAM - rd_image_start = boot_params.hdr.ram_size & RAMDISK_IMAGE_START_MASK; - rd_prompt = ((boot_params.hdr.ram_size & RAMDISK_PROMPT_FLAG) != 0); - rd_doload = ((boot_params.hdr.ram_size & RAMDISK_LOAD_FLAG) != 0); -#endif -#ifdef CONFIG_EFI - if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, - "EL64", 4)) - efi_enabled = 1; -#endif - - ARCH_SETUP - - memory_setup(); - copy_edd(); - - if (!boot_params.hdr.root_flags) - root_mountflags &= ~MS_RDONLY; - init_mm.start_code = (unsigned long) &_text; - init_mm.end_code = (unsigned long) &_etext; - init_mm.end_data = (unsigned long) &_edata; - init_mm.brk = (unsigned long) &_end; - - code_resource.start = virt_to_phys(&_text); - code_resource.end = virt_to_phys(&_etext)-1; - data_resource.start = virt_to_phys(&_etext); - data_resource.end = virt_to_phys(&_edata)-1; - bss_resource.start = virt_to_phys(&__bss_start); - bss_resource.end = virt_to_phys(&__bss_stop)-1; - - early_identify_cpu(&boot_cpu_data); - - strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE); - *cmdline_p = command_line; - - parse_setup_data(); - - parse_early_param(); - -#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT - if (init_ohci1394_dma_early) - init_ohci1394_dma_on_all_controllers(); -#endif - - finish_e820_parsing(); - - /* after parse_early_param, so could debug it */ - insert_resource(&iomem_resource, &code_resource); - insert_resource(&iomem_resource, &data_resource); - insert_resource(&iomem_resource, &bss_resource); - - early_gart_iommu_check(); - - e820_register_active_regions(0, 0, -1UL); - /* - * partially used pages are not usable - thus - * we are rounding upwards: - */ - end_pfn = e820_end_of_ram(); - /* update e820 for memory not covered by WB MTRRs */ - mtrr_bp_init(); - if (mtrr_trim_uncached_memory(end_pfn)) { - e820_register_active_regions(0, 0, -1UL); - end_pfn = e820_end_of_ram(); - } - - num_physpages = end_pfn; - - check_efer(); - - max_pfn_mapped = init_memory_mapping(0, (max_pfn_mapped << PAGE_SHIFT)); - if (efi_enabled) - efi_init(); - - vsmp_init(); - - dmi_scan_machine(); - - io_delay_init(); - -#ifdef CONFIG_KVM_CLOCK - kvmclock_init(); -#endif - -#ifdef CONFIG_SMP - /* setup to use the early static init tables during kernel startup */ - x86_cpu_to_apicid_early_ptr = (void *)x86_cpu_to_apicid_init; - x86_bios_cpu_apicid_early_ptr = (void *)x86_bios_cpu_apicid_init; -#ifdef CONFIG_NUMA - x86_cpu_to_node_map_early_ptr = (void *)x86_cpu_to_node_map_init; -#endif -#endif - -#ifdef CONFIG_ACPI - /* - * Initialize the ACPI boot-time table parser (gets the RSDP and SDT). - * Call this early for SRAT node setup. - */ - acpi_boot_table_init(); -#endif - - /* How many end-of-memory variables you have, grandma! */ - max_low_pfn = end_pfn; - max_pfn = end_pfn; - high_memory = (void *)__va(end_pfn * PAGE_SIZE - 1) + 1; - - /* Remove active ranges so rediscovery with NUMA-awareness happens */ - remove_all_active_ranges(); - -#ifdef CONFIG_ACPI_NUMA - /* - * Parse SRAT to discover nodes. - */ - acpi_numa_init(); -#endif - -#ifdef CONFIG_NUMA - numa_initmem_init(0, end_pfn); -#else - contig_initmem_init(0, end_pfn); -#endif - - dma32_reserve_bootmem(); - -#ifdef CONFIG_ACPI_SLEEP - /* - * Reserve low memory region for sleep support. - */ - acpi_reserve_bootmem(); -#endif - - if (efi_enabled) - efi_reserve_bootmem(); - - /* - * Find and reserve possible boot-time SMP configuration: - */ - find_smp_config(); -#ifdef CONFIG_BLK_DEV_INITRD - if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) { - unsigned long ramdisk_image = boot_params.hdr.ramdisk_image; - unsigned long ramdisk_size = boot_params.hdr.ramdisk_size; - unsigned long ramdisk_end = ramdisk_image + ramdisk_size; - unsigned long end_of_mem = end_pfn << PAGE_SHIFT; - - if (ramdisk_end <= end_of_mem) { - /* - * don't need to reserve again, already reserved early - * in x86_64_start_kernel, and early_res_to_bootmem - * convert that to reserved in bootmem - */ - initrd_start = ramdisk_image + PAGE_OFFSET; - initrd_end = initrd_start+ramdisk_size; - } else { - free_bootmem(ramdisk_image, ramdisk_size); - printk(KERN_ERR "initrd extends beyond end of memory " - "(0x%08lx > 0x%08lx)\ndisabling initrd\n", - ramdisk_end, end_of_mem); - initrd_start = 0; - } - } -#endif - reserve_crashkernel(); - - reserve_ibft_region(); - - paging_init(); - map_vsyscall(); - - early_quirks(); - -#ifdef CONFIG_ACPI - /* - * Read APIC and some other early information from ACPI tables. - */ - acpi_boot_init(); -#endif - - init_cpu_to_node(); - - /* - * get boot-time SMP configuration: - */ - if (smp_found_config) - get_smp_config(); - init_apic_mappings(); - ioapic_init_mappings(); - - kvm_guest_init(); - - /* - * We trust e820 completely. No explicit ROM probing in memory. - */ - e820_reserve_resources(); - e820_mark_nosave_regions(); - - /* request I/O space for devices used on all i[345]86 PCs */ - for (i = 0; i < ARRAY_SIZE(standard_io_resources); i++) - request_resource(&ioport_resource, &standard_io_resources[i]); - - e820_setup_gap(); - -#ifdef CONFIG_VT -#if defined(CONFIG_VGA_CONSOLE) - if (!efi_enabled || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY)) - conswitchp = &vga_con; -#elif defined(CONFIG_DUMMY_CONSOLE) - conswitchp = &dummy_con; -#endif -#endif - - /* do this before identify_cpu for boot cpu */ - check_enable_amd_mmconf_dmi(); -} - -static int __cpuinit get_model_name(struct cpuinfo_x86 *c) -{ - unsigned int *v; - - if (c->extended_cpuid_level < 0x80000004) - return 0; - - v = (unsigned int *) c->x86_model_id; - cpuid(0x80000002, &v[0], &v[1], &v[2], &v[3]); - cpuid(0x80000003, &v[4], &v[5], &v[6], &v[7]); - cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]); - c->x86_model_id[48] = 0; - return 1; -} - - -static void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c) -{ - unsigned int n, dummy, eax, ebx, ecx, edx; - - n = c->extended_cpuid_level; - - if (n >= 0x80000005) { - cpuid(0x80000005, &dummy, &ebx, &ecx, &edx); - printk(KERN_INFO "CPU: L1 I Cache: %dK (%d bytes/line), " - "D cache %dK (%d bytes/line)\n", - edx>>24, edx&0xFF, ecx>>24, ecx&0xFF); - c->x86_cache_size = (ecx>>24) + (edx>>24); - /* On K8 L1 TLB is inclusive, so don't count it */ - c->x86_tlbsize = 0; - } - - if (n >= 0x80000006) { - cpuid(0x80000006, &dummy, &ebx, &ecx, &edx); - ecx = cpuid_ecx(0x80000006); - c->x86_cache_size = ecx >> 16; - c->x86_tlbsize += ((ebx >> 16) & 0xfff) + (ebx & 0xfff); - - printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n", - c->x86_cache_size, ecx & 0xFF); - } - if (n >= 0x80000008) { - cpuid(0x80000008, &eax, &dummy, &dummy, &dummy); - c->x86_virt_bits = (eax >> 8) & 0xff; - c->x86_phys_bits = eax & 0xff; - } -} - -#ifdef CONFIG_NUMA -static int __cpuinit nearby_node(int apicid) -{ - int i, node; - - for (i = apicid - 1; i >= 0; i--) { - node = apicid_to_node[i]; - if (node != NUMA_NO_NODE && node_online(node)) - return node; - } - for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) { - node = apicid_to_node[i]; - if (node != NUMA_NO_NODE && node_online(node)) - return node; - } - return first_node(node_online_map); /* Shouldn't happen */ -} -#endif - -/* - * On a AMD dual core setup the lower bits of the APIC id distingush the cores. - * Assumes number of cores is a power of two. - */ -static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c) -{ -#ifdef CONFIG_SMP - unsigned bits; -#ifdef CONFIG_NUMA - int cpu = smp_processor_id(); - int node = 0; - unsigned apicid = hard_smp_processor_id(); -#endif - bits = c->x86_coreid_bits; - - /* Low order bits define the core id (index of core in socket) */ - c->cpu_core_id = c->initial_apicid & ((1 << bits)-1); - /* Convert the initial APIC ID into the socket ID */ - c->phys_proc_id = c->initial_apicid >> bits; - -#ifdef CONFIG_NUMA - node = c->phys_proc_id; - if (apicid_to_node[apicid] != NUMA_NO_NODE) - node = apicid_to_node[apicid]; - if (!node_online(node)) { - /* Two possibilities here: - - The CPU is missing memory and no node was created. - In that case try picking one from a nearby CPU - - The APIC IDs differ from the HyperTransport node IDs - which the K8 northbridge parsing fills in. - Assume they are all increased by a constant offset, - but in the same order as the HT nodeids. - If that doesn't result in a usable node fall back to the - path for the previous case. */ - - int ht_nodeid = c->initial_apicid; - - if (ht_nodeid >= 0 && - apicid_to_node[ht_nodeid] != NUMA_NO_NODE) - node = apicid_to_node[ht_nodeid]; - /* Pick a nearby node */ - if (!node_online(node)) - node = nearby_node(apicid); - } - numa_set_node(cpu, node); - - printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node); -#endif -#endif -} - -static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c) -{ -#ifdef CONFIG_SMP - unsigned bits, ecx; - - /* Multi core CPU? */ - if (c->extended_cpuid_level < 0x80000008) - return; - - ecx = cpuid_ecx(0x80000008); - - c->x86_max_cores = (ecx & 0xff) + 1; - - /* CPU telling us the core id bits shift? */ - bits = (ecx >> 12) & 0xF; - - /* Otherwise recompute */ - if (bits == 0) { - while ((1 << bits) < c->x86_max_cores) - bits++; - } - - c->x86_coreid_bits = bits; - -#endif -} - -#define ENABLE_C1E_MASK 0x18000000 -#define CPUID_PROCESSOR_SIGNATURE 1 -#define CPUID_XFAM 0x0ff00000 -#define CPUID_XFAM_K8 0x00000000 -#define CPUID_XFAM_10H 0x00100000 -#define CPUID_XFAM_11H 0x00200000 -#define CPUID_XMOD 0x000f0000 -#define CPUID_XMOD_REV_F 0x00040000 - -/* AMD systems with C1E don't have a working lAPIC timer. Check for that. */ -static __cpuinit int amd_apic_timer_broken(void) -{ - u32 lo, hi, eax = cpuid_eax(CPUID_PROCESSOR_SIGNATURE); - - switch (eax & CPUID_XFAM) { - case CPUID_XFAM_K8: - if ((eax & CPUID_XMOD) < CPUID_XMOD_REV_F) - break; - case CPUID_XFAM_10H: - case CPUID_XFAM_11H: - rdmsr(MSR_K8_ENABLE_C1E, lo, hi); - if (lo & ENABLE_C1E_MASK) - return 1; - break; - default: - /* err on the side of caution */ - return 1; - } - return 0; -} - -static void __cpuinit early_init_amd(struct cpuinfo_x86 *c) -{ - early_init_amd_mc(c); - - /* c->x86_power is 8000_0007 edx. Bit 8 is constant TSC */ - if (c->x86_power & (1<<8)) - set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); -} - -static void __cpuinit init_amd(struct cpuinfo_x86 *c) -{ - unsigned level; - -#ifdef CONFIG_SMP - unsigned long value; - - /* - * Disable TLB flush filter by setting HWCR.FFDIS on K8 - * bit 6 of msr C001_0015 - * - * Errata 63 for SH-B3 steppings - * Errata 122 for all steppings (F+ have it disabled by default) - */ - if (c->x86 == 15) { - rdmsrl(MSR_K8_HWCR, value); - value |= 1 << 6; - wrmsrl(MSR_K8_HWCR, value); - } -#endif - - /* Bit 31 in normal CPUID used for nonstandard 3DNow ID; - 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */ - clear_cpu_cap(c, 0*32+31); - - /* On C+ stepping K8 rep microcode works well for copy/memset */ - level = cpuid_eax(1); - if (c->x86 == 15 && ((level >= 0x0f48 && level < 0x0f50) || - level >= 0x0f58)) - set_cpu_cap(c, X86_FEATURE_REP_GOOD); - if (c->x86 == 0x10 || c->x86 == 0x11) - set_cpu_cap(c, X86_FEATURE_REP_GOOD); - - /* Enable workaround for FXSAVE leak */ - if (c->x86 >= 6) - set_cpu_cap(c, X86_FEATURE_FXSAVE_LEAK); - - level = get_model_name(c); - if (!level) { - switch (c->x86) { - case 15: - /* Should distinguish Models here, but this is only - a fallback anyways. */ - strcpy(c->x86_model_id, "Hammer"); - break; - } - } - display_cacheinfo(c); - - /* Multi core CPU? */ - if (c->extended_cpuid_level >= 0x80000008) - amd_detect_cmp(c); - - if (c->extended_cpuid_level >= 0x80000006 && - (cpuid_edx(0x80000006) & 0xf000)) - num_cache_leaves = 4; - else - num_cache_leaves = 3; - - if (c->x86 == 0xf || c->x86 == 0x10 || c->x86 == 0x11) - set_cpu_cap(c, X86_FEATURE_K8); - - /* MFENCE stops RDTSC speculation */ - set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); - - if (c->x86 == 0x10) - fam10h_check_enable_mmcfg(); - - if (amd_apic_timer_broken()) - disable_apic_timer = 1; - - if (c == &boot_cpu_data && c->x86 >= 0xf && c->x86 <= 0x11) { - unsigned long long tseg; - - /* - * Split up direct mapping around the TSEG SMM area. - * Don't do it for gbpages because there seems very little - * benefit in doing so. - */ - if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg) && - (tseg >> PMD_SHIFT) < (max_pfn_mapped >> (PMD_SHIFT-PAGE_SHIFT))) - set_memory_4k((unsigned long)__va(tseg), 1); - } -} - -void __cpuinit detect_ht(struct cpuinfo_x86 *c) -{ -#ifdef CONFIG_SMP - u32 eax, ebx, ecx, edx; - int index_msb, core_bits; - - cpuid(1, &eax, &ebx, &ecx, &edx); - - - if (!cpu_has(c, X86_FEATURE_HT)) - return; - if (cpu_has(c, X86_FEATURE_CMP_LEGACY)) - goto out; - - smp_num_siblings = (ebx & 0xff0000) >> 16; - - if (smp_num_siblings == 1) { - printk(KERN_INFO "CPU: Hyper-Threading is disabled\n"); - } else if (smp_num_siblings > 1) { - - if (smp_num_siblings > NR_CPUS) { - printk(KERN_WARNING "CPU: Unsupported number of " - "siblings %d", smp_num_siblings); - smp_num_siblings = 1; - return; - } - - index_msb = get_count_order(smp_num_siblings); - c->phys_proc_id = phys_pkg_id(index_msb); - - smp_num_siblings = smp_num_siblings / c->x86_max_cores; - - index_msb = get_count_order(smp_num_siblings); - - core_bits = get_count_order(c->x86_max_cores); - - c->cpu_core_id = phys_pkg_id(index_msb) & - ((1 << core_bits) - 1); - } -out: - if ((c->x86_max_cores * smp_num_siblings) > 1) { - printk(KERN_INFO "CPU: Physical Processor ID: %d\n", - c->phys_proc_id); - printk(KERN_INFO "CPU: Processor Core ID: %d\n", - c->cpu_core_id); - } - -#endif -} - -/* - * find out the number of processor cores on the die - */ -static int __cpuinit intel_num_cpu_cores(struct cpuinfo_x86 *c) -{ - unsigned int eax, t; - - if (c->cpuid_level < 4) - return 1; - - cpuid_count(4, 0, &eax, &t, &t, &t); - - if (eax & 0x1f) - return ((eax >> 26) + 1); - else - return 1; -} - -static void __cpuinit srat_detect_node(void) -{ -#ifdef CONFIG_NUMA - unsigned node; - int cpu = smp_processor_id(); - int apicid = hard_smp_processor_id(); - - /* Don't do the funky fallback heuristics the AMD version employs - for now. */ - node = apicid_to_node[apicid]; - if (node == NUMA_NO_NODE || !node_online(node)) - node = first_node(node_online_map); - numa_set_node(cpu, node); - - printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node); -#endif -} - -static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) -{ - if ((c->x86 == 0xf && c->x86_model >= 0x03) || - (c->x86 == 0x6 && c->x86_model >= 0x0e)) - set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); -} - -static void __cpuinit init_intel(struct cpuinfo_x86 *c) -{ - /* Cache sizes */ - unsigned n; - - init_intel_cacheinfo(c); - if (c->cpuid_level > 9) { - unsigned eax = cpuid_eax(10); - /* Check for version and the number of counters */ - if ((eax & 0xff) && (((eax>>8) & 0xff) > 1)) - set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON); - } - - if (cpu_has_ds) { - unsigned int l1, l2; - rdmsr(MSR_IA32_MISC_ENABLE, l1, l2); - if (!(l1 & (1<<11))) - set_cpu_cap(c, X86_FEATURE_BTS); - if (!(l1 & (1<<12))) - set_cpu_cap(c, X86_FEATURE_PEBS); - } - - - if (cpu_has_bts) - ds_init_intel(c); - - n = c->extended_cpuid_level; - if (n >= 0x80000008) { - unsigned eax = cpuid_eax(0x80000008); - c->x86_virt_bits = (eax >> 8) & 0xff; - c->x86_phys_bits = eax & 0xff; - /* CPUID workaround for Intel 0F34 CPU */ - if (c->x86_vendor == X86_VENDOR_INTEL && - c->x86 == 0xF && c->x86_model == 0x3 && - c->x86_mask == 0x4) - c->x86_phys_bits = 36; - } - - if (c->x86 == 15) - c->x86_cache_alignment = c->x86_clflush_size * 2; - if (c->x86 == 6) - set_cpu_cap(c, X86_FEATURE_REP_GOOD); - set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); - c->x86_max_cores = intel_num_cpu_cores(c); - - srat_detect_node(); -} - -static void __cpuinit early_init_centaur(struct cpuinfo_x86 *c) -{ - if (c->x86 == 0x6 && c->x86_model >= 0xf) - set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); -} - -static void __cpuinit init_centaur(struct cpuinfo_x86 *c) -{ - /* Cache sizes */ - unsigned n; - - n = c->extended_cpuid_level; - if (n >= 0x80000008) { - unsigned eax = cpuid_eax(0x80000008); - c->x86_virt_bits = (eax >> 8) & 0xff; - c->x86_phys_bits = eax & 0xff; - } - - if (c->x86 == 0x6 && c->x86_model >= 0xf) { - c->x86_cache_alignment = c->x86_clflush_size * 2; - set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); - set_cpu_cap(c, X86_FEATURE_REP_GOOD); - } - set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); -} - -static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c) -{ - char *v = c->x86_vendor_id; - - if (!strcmp(v, "AuthenticAMD")) - c->x86_vendor = X86_VENDOR_AMD; - else if (!strcmp(v, "GenuineIntel")) - c->x86_vendor = X86_VENDOR_INTEL; - else if (!strcmp(v, "CentaurHauls")) - c->x86_vendor = X86_VENDOR_CENTAUR; - else - c->x86_vendor = X86_VENDOR_UNKNOWN; -} - -/* Do some early cpuid on the boot CPU to get some parameter that are - needed before check_bugs. Everything advanced is in identify_cpu - below. */ -static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c) -{ - u32 tfms, xlvl; - - c->loops_per_jiffy = loops_per_jiffy; - c->x86_cache_size = -1; - c->x86_vendor = X86_VENDOR_UNKNOWN; - c->x86_model = c->x86_mask = 0; /* So far unknown... */ - c->x86_vendor_id[0] = '\0'; /* Unset */ - c->x86_model_id[0] = '\0'; /* Unset */ - c->x86_clflush_size = 64; - c->x86_cache_alignment = c->x86_clflush_size; - c->x86_max_cores = 1; - c->x86_coreid_bits = 0; - c->extended_cpuid_level = 0; - memset(&c->x86_capability, 0, sizeof c->x86_capability); - - /* Get vendor name */ - cpuid(0x00000000, (unsigned int *)&c->cpuid_level, - (unsigned int *)&c->x86_vendor_id[0], - (unsigned int *)&c->x86_vendor_id[8], - (unsigned int *)&c->x86_vendor_id[4]); - - get_cpu_vendor(c); - - /* Initialize the standard set of capabilities */ - /* Note that the vendor-specific code below might override */ - - /* Intel-defined flags: level 0x00000001 */ - if (c->cpuid_level >= 0x00000001) { - __u32 misc; - cpuid(0x00000001, &tfms, &misc, &c->x86_capability[4], - &c->x86_capability[0]); - c->x86 = (tfms >> 8) & 0xf; - c->x86_model = (tfms >> 4) & 0xf; - c->x86_mask = tfms & 0xf; - if (c->x86 == 0xf) - c->x86 += (tfms >> 20) & 0xff; - if (c->x86 >= 0x6) - c->x86_model += ((tfms >> 16) & 0xF) << 4; - if (test_cpu_cap(c, X86_FEATURE_CLFLSH)) - c->x86_clflush_size = ((misc >> 8) & 0xff) * 8; - } else { - /* Have CPUID level 0 only - unheard of */ - c->x86 = 4; - } - - c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xff; -#ifdef CONFIG_SMP - c->phys_proc_id = c->initial_apicid; -#endif - /* AMD-defined flags: level 0x80000001 */ - xlvl = cpuid_eax(0x80000000); - c->extended_cpuid_level = xlvl; - if ((xlvl & 0xffff0000) == 0x80000000) { - if (xlvl >= 0x80000001) { - c->x86_capability[1] = cpuid_edx(0x80000001); - c->x86_capability[6] = cpuid_ecx(0x80000001); - } - if (xlvl >= 0x80000004) - get_model_name(c); /* Default name */ - } - - /* Transmeta-defined flags: level 0x80860001 */ - xlvl = cpuid_eax(0x80860000); - if ((xlvl & 0xffff0000) == 0x80860000) { - /* Don't set x86_cpuid_level here for now to not confuse. */ - if (xlvl >= 0x80860001) - c->x86_capability[2] = cpuid_edx(0x80860001); - } - - c->extended_cpuid_level = cpuid_eax(0x80000000); - if (c->extended_cpuid_level >= 0x80000007) - c->x86_power = cpuid_edx(0x80000007); - - switch (c->x86_vendor) { - case X86_VENDOR_AMD: - early_init_amd(c); - break; - case X86_VENDOR_INTEL: - early_init_intel(c); - break; - case X86_VENDOR_CENTAUR: - early_init_centaur(c); - break; - } - - validate_pat_support(c); -} - -/* - * This does the hard work of actually picking apart the CPU stuff... - */ -void __cpuinit identify_cpu(struct cpuinfo_x86 *c) -{ - int i; - - early_identify_cpu(c); - - init_scattered_cpuid_features(c); - - c->apicid = phys_pkg_id(0); - - /* - * Vendor-specific initialization. In this section we - * canonicalize the feature flags, meaning if there are - * features a certain CPU supports which CPUID doesn't - * tell us, CPUID claiming incorrect flags, or other bugs, - * we handle them here. - * - * At the end of this section, c->x86_capability better - * indicate the features this CPU genuinely supports! - */ - switch (c->x86_vendor) { - case X86_VENDOR_AMD: - init_amd(c); - break; - - case X86_VENDOR_INTEL: - init_intel(c); - break; - - case X86_VENDOR_CENTAUR: - init_centaur(c); - break; - - case X86_VENDOR_UNKNOWN: - default: - display_cacheinfo(c); - break; - } - - detect_ht(c); - - /* - * On SMP, boot_cpu_data holds the common feature set between - * all CPUs; so make sure that we indicate which features are - * common between the CPUs. The first time this routine gets - * executed, c == &boot_cpu_data. - */ - if (c != &boot_cpu_data) { - /* AND the already accumulated flags with these */ - for (i = 0; i < NCAPINTS; i++) - boot_cpu_data.x86_capability[i] &= c->x86_capability[i]; - } - - /* Clear all flags overriden by options */ - for (i = 0; i < NCAPINTS; i++) - c->x86_capability[i] &= ~cleared_cpu_caps[i]; - -#ifdef CONFIG_X86_MCE - mcheck_init(c); -#endif - select_idle_routine(c); - -#ifdef CONFIG_NUMA - numa_add_cpu(smp_processor_id()); -#endif - -} - -void __cpuinit identify_boot_cpu(void) -{ - identify_cpu(&boot_cpu_data); -} - -void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c) -{ - BUG_ON(c == &boot_cpu_data); - identify_cpu(c); - mtrr_ap_init(); -} - -static __init int setup_noclflush(char *arg) -{ - setup_clear_cpu_cap(X86_FEATURE_CLFLSH); - return 1; -} -__setup("noclflush", setup_noclflush); - -void __cpuinit print_cpu_info(struct cpuinfo_x86 *c) -{ - if (c->x86_model_id[0]) - printk(KERN_CONT "%s", c->x86_model_id); - - if (c->x86_mask || c->cpuid_level >= 0) - printk(KERN_CONT " stepping %02x\n", c->x86_mask); - else - printk(KERN_CONT "\n"); -} - -static __init int setup_disablecpuid(char *arg) -{ - int bit; - if (get_option(&arg, &bit) && bit < NCAPINTS*32) - setup_clear_cpu_cap(bit); - else - return 0; - return 1; -} -__setup("clearcpuid=", setup_disablecpuid); diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c new file mode 100644 index 000000000000..cac68430d31f --- /dev/null +++ b/arch/x86/kernel/setup_percpu.c @@ -0,0 +1,399 @@ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/bootmem.h> +#include <linux/percpu.h> +#include <linux/kexec.h> +#include <linux/crash_dump.h> +#include <asm/smp.h> +#include <asm/percpu.h> +#include <asm/sections.h> +#include <asm/processor.h> +#include <asm/setup.h> +#include <asm/topology.h> +#include <asm/mpspec.h> +#include <asm/apicdef.h> +#include <asm/highmem.h> + +#ifdef CONFIG_X86_LOCAL_APIC +unsigned int num_processors; +unsigned disabled_cpus __cpuinitdata; +/* Processor that is doing the boot up */ +unsigned int boot_cpu_physical_apicid = -1U; +unsigned int max_physical_apicid; +EXPORT_SYMBOL(boot_cpu_physical_apicid); + +/* Bitmask of physically existing CPUs */ +physid_mask_t phys_cpu_present_map; +#endif + +/* map cpu index to physical APIC ID */ +DEFINE_EARLY_PER_CPU(u16, x86_cpu_to_apicid, BAD_APICID); +DEFINE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid, BAD_APICID); +EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid); +EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid); + +#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64) +#define X86_64_NUMA 1 + +/* map cpu index to node index */ +DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE); +EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map); + +/* which logical CPUs are on which nodes */ +cpumask_t *node_to_cpumask_map; +EXPORT_SYMBOL(node_to_cpumask_map); + +/* setup node_to_cpumask_map */ +static void __init setup_node_to_cpumask_map(void); + +#else +static inline void setup_node_to_cpumask_map(void) { } +#endif + +#if defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) && defined(CONFIG_X86_SMP) +/* + * Copy data used in early init routines from the initial arrays to the + * per cpu data areas. These arrays then become expendable and the + * *_early_ptr's are zeroed indicating that the static arrays are gone. + */ +static void __init setup_per_cpu_maps(void) +{ + int cpu; + + for_each_possible_cpu(cpu) { + per_cpu(x86_cpu_to_apicid, cpu) = + early_per_cpu_map(x86_cpu_to_apicid, cpu); + per_cpu(x86_bios_cpu_apicid, cpu) = + early_per_cpu_map(x86_bios_cpu_apicid, cpu); +#ifdef X86_64_NUMA + per_cpu(x86_cpu_to_node_map, cpu) = + early_per_cpu_map(x86_cpu_to_node_map, cpu); +#endif + } + + /* indicate the early static arrays will soon be gone */ + early_per_cpu_ptr(x86_cpu_to_apicid) = NULL; + early_per_cpu_ptr(x86_bios_cpu_apicid) = NULL; +#ifdef X86_64_NUMA + early_per_cpu_ptr(x86_cpu_to_node_map) = NULL; +#endif +} + +#ifdef CONFIG_HAVE_CPUMASK_OF_CPU_MAP +cpumask_t *cpumask_of_cpu_map __read_mostly; +EXPORT_SYMBOL(cpumask_of_cpu_map); + +/* requires nr_cpu_ids to be initialized */ +static void __init setup_cpumask_of_cpu(void) +{ + int i; + + /* alloc_bootmem zeroes memory */ + cpumask_of_cpu_map = alloc_bootmem_low(sizeof(cpumask_t) * nr_cpu_ids); + for (i = 0; i < nr_cpu_ids; i++) + cpu_set(i, cpumask_of_cpu_map[i]); +} +#else +static inline void setup_cpumask_of_cpu(void) { } +#endif + +#ifdef CONFIG_X86_32 +/* + * Great future not-so-futuristic plan: make i386 and x86_64 do it + * the same way + */ +unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; +EXPORT_SYMBOL(__per_cpu_offset); +static inline void setup_cpu_pda_map(void) { } + +#elif !defined(CONFIG_SMP) +static inline void setup_cpu_pda_map(void) { } + +#else /* CONFIG_SMP && CONFIG_X86_64 */ + +/* + * Allocate cpu_pda pointer table and array via alloc_bootmem. + */ +static void __init setup_cpu_pda_map(void) +{ + char *pda; + struct x8664_pda **new_cpu_pda; + unsigned long size; + int cpu; + + size = roundup(sizeof(struct x8664_pda), cache_line_size()); + + /* allocate cpu_pda array and pointer table */ + { + unsigned long tsize = nr_cpu_ids * sizeof(void *); + unsigned long asize = size * (nr_cpu_ids - 1); + + tsize = roundup(tsize, cache_line_size()); + new_cpu_pda = alloc_bootmem(tsize + asize); + pda = (char *)new_cpu_pda + tsize; + } + + /* initialize pointer table to static pda's */ + for_each_possible_cpu(cpu) { + if (cpu == 0) { + /* leave boot cpu pda in place */ + new_cpu_pda[0] = cpu_pda(0); + continue; + } + new_cpu_pda[cpu] = (struct x8664_pda *)pda; + new_cpu_pda[cpu]->in_bootmem = 1; + pda += size; + } + + /* point to new pointer table */ + _cpu_pda = new_cpu_pda; +} +#endif + +/* + * Great future plan: + * Declare PDA itself and support (irqstack,tss,pgd) as per cpu data. + * Always point %gs to its beginning + */ +void __init setup_per_cpu_areas(void) +{ + ssize_t size = PERCPU_ENOUGH_ROOM; + char *ptr; + int cpu; + + /* Setup cpu_pda map */ + setup_cpu_pda_map(); + + /* Copy section for each CPU (we discard the original) */ + size = PERCPU_ENOUGH_ROOM; + printk(KERN_INFO "PERCPU: Allocating %zd bytes of per cpu data\n", + size); + + for_each_possible_cpu(cpu) { +#ifndef CONFIG_NEED_MULTIPLE_NODES + ptr = alloc_bootmem_pages(size); +#else + int node = early_cpu_to_node(cpu); + if (!node_online(node) || !NODE_DATA(node)) { + ptr = alloc_bootmem_pages(size); + printk(KERN_INFO + "cpu %d has no node %d or node-local memory\n", + cpu, node); + } + else + ptr = alloc_bootmem_pages_node(NODE_DATA(node), size); +#endif + per_cpu_offset(cpu) = ptr - __per_cpu_start; + memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start); + + } + + printk(KERN_DEBUG "NR_CPUS: %d, nr_cpu_ids: %d, nr_node_ids %d\n", + NR_CPUS, nr_cpu_ids, nr_node_ids); + + /* Setup percpu data maps */ + setup_per_cpu_maps(); + + /* Setup node to cpumask map */ + setup_node_to_cpumask_map(); + + /* Setup cpumask_of_cpu map */ + setup_cpumask_of_cpu(); +} + +#endif + +#ifdef X86_64_NUMA + +/* + * Allocate node_to_cpumask_map based on number of available nodes + * Requires node_possible_map to be valid. + * + * Note: node_to_cpumask() is not valid until after this is done. + */ +static void __init setup_node_to_cpumask_map(void) +{ + unsigned int node, num = 0; + cpumask_t *map; + + /* setup nr_node_ids if not done yet */ + if (nr_node_ids == MAX_NUMNODES) { + for_each_node_mask(node, node_possible_map) + num = node; + nr_node_ids = num + 1; + } + + /* allocate the map */ + map = alloc_bootmem_low(nr_node_ids * sizeof(cpumask_t)); + + Dprintk(KERN_DEBUG "Node to cpumask map at %p for %d nodes\n", + map, nr_node_ids); + + /* node_to_cpumask() will now work */ + node_to_cpumask_map = map; +} + +void __cpuinit numa_set_node(int cpu, int node) +{ + int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map); + + if (cpu_pda(cpu) && node != NUMA_NO_NODE) + cpu_pda(cpu)->nodenumber = node; + + if (cpu_to_node_map) + cpu_to_node_map[cpu] = node; + + else if (per_cpu_offset(cpu)) + per_cpu(x86_cpu_to_node_map, cpu) = node; + + else + Dprintk(KERN_INFO "Setting node for non-present cpu %d\n", cpu); +} + +void __cpuinit numa_clear_node(int cpu) +{ + numa_set_node(cpu, NUMA_NO_NODE); +} + +#ifndef CONFIG_DEBUG_PER_CPU_MAPS + +void __cpuinit numa_add_cpu(int cpu) +{ + cpu_set(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); +} + +void __cpuinit numa_remove_cpu(int cpu) +{ + cpu_clear(cpu, node_to_cpumask_map[cpu_to_node(cpu)]); +} + +#else /* CONFIG_DEBUG_PER_CPU_MAPS */ + +/* + * --------- debug versions of the numa functions --------- + */ +static void __cpuinit numa_set_cpumask(int cpu, int enable) +{ + int node = cpu_to_node(cpu); + cpumask_t *mask; + char buf[64]; + + if (node_to_cpumask_map == NULL) { + printk(KERN_ERR "node_to_cpumask_map NULL\n"); + dump_stack(); + return; + } + + mask = &node_to_cpumask_map[node]; + if (enable) + cpu_set(cpu, *mask); + else + cpu_clear(cpu, *mask); + + cpulist_scnprintf(buf, sizeof(buf), *mask); + printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n", + enable? "numa_add_cpu":"numa_remove_cpu", cpu, node, buf); + } + +void __cpuinit numa_add_cpu(int cpu) +{ + numa_set_cpumask(cpu, 1); +} + +void __cpuinit numa_remove_cpu(int cpu) +{ + numa_set_cpumask(cpu, 0); +} + +int cpu_to_node(int cpu) +{ + if (early_per_cpu_ptr(x86_cpu_to_node_map)) { + printk(KERN_WARNING + "cpu_to_node(%d): usage too early!\n", cpu); + dump_stack(); + return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu]; + } + return per_cpu(x86_cpu_to_node_map, cpu); +} +EXPORT_SYMBOL(cpu_to_node); + +/* + * Same function as cpu_to_node() but used if called before the + * per_cpu areas are setup. + */ +int early_cpu_to_node(int cpu) +{ + if (early_per_cpu_ptr(x86_cpu_to_node_map)) + return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu]; + + if (!per_cpu_offset(cpu)) { + printk(KERN_WARNING + "early_cpu_to_node(%d): no per_cpu area!\n", cpu); + dump_stack(); + return NUMA_NO_NODE; + } + return per_cpu(x86_cpu_to_node_map, cpu); +} + + +/* empty cpumask */ +static const cpumask_t cpu_mask_none; + +/* + * Returns a pointer to the bitmask of CPUs on Node 'node'. + */ +const cpumask_t *_node_to_cpumask_ptr(int node) +{ + if (node_to_cpumask_map == NULL) { + printk(KERN_WARNING + "_node_to_cpumask_ptr(%d): no node_to_cpumask_map!\n", + node); + dump_stack(); + return (const cpumask_t *)&cpu_online_map; + } + if (node >= nr_node_ids) { + printk(KERN_WARNING + "_node_to_cpumask_ptr(%d): node > nr_node_ids(%d)\n", + node, nr_node_ids); + dump_stack(); + return &cpu_mask_none; + } + return &node_to_cpumask_map[node]; +} +EXPORT_SYMBOL(_node_to_cpumask_ptr); + +/* + * Returns a bitmask of CPUs on Node 'node'. + * + * Side note: this function creates the returned cpumask on the stack + * so with a high NR_CPUS count, excessive stack space is used. The + * node_to_cpumask_ptr function should be used whenever possible. + */ +cpumask_t node_to_cpumask(int node) +{ + if (node_to_cpumask_map == NULL) { + printk(KERN_WARNING + "node_to_cpumask(%d): no node_to_cpumask_map!\n", node); + dump_stack(); + return cpu_online_map; + } + if (node >= nr_node_ids) { + printk(KERN_WARNING + "node_to_cpumask(%d): node > nr_node_ids(%d)\n", + node, nr_node_ids); + dump_stack(); + return cpu_mask_none; + } + return node_to_cpumask_map[node]; +} +EXPORT_SYMBOL(node_to_cpumask); + +/* + * --------- end of debug versions of the numa functions --------- + */ + +#endif /* CONFIG_DEBUG_PER_CPU_MAPS */ + +#endif /* X86_64_NUMA */ + diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 0cb7aadc87cd..361b7a4c640c 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -121,132 +121,23 @@ static void native_smp_send_reschedule(int cpu) send_IPI_mask(cpumask_of_cpu(cpu), RESCHEDULE_VECTOR); } -/* - * Structure and data for smp_call_function(). This is designed to minimise - * static memory requirements. It also looks cleaner. - */ -static DEFINE_SPINLOCK(call_lock); - -struct call_data_struct { - void (*func) (void *info); - void *info; - atomic_t started; - atomic_t finished; - int wait; -}; - -void lock_ipi_call_lock(void) +void native_send_call_func_single_ipi(int cpu) { - spin_lock_irq(&call_lock); -} - -void unlock_ipi_call_lock(void) -{ - spin_unlock_irq(&call_lock); -} - -static struct call_data_struct *call_data; - -static void __smp_call_function(void (*func) (void *info), void *info, - int nonatomic, int wait) -{ - struct call_data_struct data; - int cpus = num_online_cpus() - 1; - - if (!cpus) - return; - - data.func = func; - data.info = info; - atomic_set(&data.started, 0); - data.wait = wait; - if (wait) - atomic_set(&data.finished, 0); - - call_data = &data; - mb(); - - /* Send a message to all other CPUs and wait for them to respond */ - send_IPI_allbutself(CALL_FUNCTION_VECTOR); - - /* Wait for response */ - while (atomic_read(&data.started) != cpus) - cpu_relax(); - - if (wait) - while (atomic_read(&data.finished) != cpus) - cpu_relax(); + send_IPI_mask(cpumask_of_cpu(cpu), CALL_FUNCTION_SINGLE_VECTOR); } - -/** - * smp_call_function_mask(): Run a function on a set of other CPUs. - * @mask: The set of cpus to run on. Must not include the current cpu. - * @func: The function to run. This must be fast and non-blocking. - * @info: An arbitrary pointer to pass to the function. - * @wait: If true, wait (atomically) until function has completed on other CPUs. - * - * Returns 0 on success, else a negative status code. - * - * If @wait is true, then returns once @func has returned; otherwise - * it returns just before the target cpu calls @func. - * - * You must not call this function with disabled interrupts or from a - * hardware interrupt handler or from a bottom half handler. - */ -static int -native_smp_call_function_mask(cpumask_t mask, - void (*func)(void *), void *info, - int wait) +void native_send_call_func_ipi(cpumask_t mask) { - struct call_data_struct data; cpumask_t allbutself; - int cpus; - - /* Can deadlock when called with interrupts disabled */ - WARN_ON(irqs_disabled()); - - /* Holding any lock stops cpus from going down. */ - spin_lock(&call_lock); allbutself = cpu_online_map; cpu_clear(smp_processor_id(), allbutself); - cpus_and(mask, mask, allbutself); - cpus = cpus_weight(mask); - - if (!cpus) { - spin_unlock(&call_lock); - return 0; - } - - data.func = func; - data.info = info; - atomic_set(&data.started, 0); - data.wait = wait; - if (wait) - atomic_set(&data.finished, 0); - - call_data = &data; - wmb(); - - /* Send a message to other CPUs */ if (cpus_equal(mask, allbutself) && cpus_equal(cpu_online_map, cpu_callout_map)) send_IPI_allbutself(CALL_FUNCTION_VECTOR); else send_IPI_mask(mask, CALL_FUNCTION_VECTOR); - - /* Wait for response */ - while (atomic_read(&data.started) != cpus) - cpu_relax(); - - if (wait) - while (atomic_read(&data.finished) != cpus) - cpu_relax(); - spin_unlock(&call_lock); - - return 0; } static void stop_this_cpu(void *dummy) @@ -268,18 +159,13 @@ static void stop_this_cpu(void *dummy) static void native_smp_send_stop(void) { - int nolock; unsigned long flags; if (reboot_force) return; - /* Don't deadlock on the call lock in panic */ - nolock = !spin_trylock(&call_lock); + smp_call_function(stop_this_cpu, NULL, 0); local_irq_save(flags); - __smp_call_function(stop_this_cpu, NULL, 0, 0); - if (!nolock) - spin_unlock(&call_lock); disable_local_APIC(); local_irq_restore(flags); } @@ -301,33 +187,28 @@ void smp_reschedule_interrupt(struct pt_regs *regs) void smp_call_function_interrupt(struct pt_regs *regs) { - void (*func) (void *info) = call_data->func; - void *info = call_data->info; - int wait = call_data->wait; - ack_APIC_irq(); - /* - * Notify initiating CPU that I've grabbed the data and am - * about to execute the function - */ - mb(); - atomic_inc(&call_data->started); - /* - * At this point the info structure may be out of scope unless wait==1 - */ irq_enter(); - (*func)(info); + generic_smp_call_function_interrupt(); #ifdef CONFIG_X86_32 __get_cpu_var(irq_stat).irq_call_count++; #else add_pda(irq_call_count, 1); #endif irq_exit(); +} - if (wait) { - mb(); - atomic_inc(&call_data->finished); - } +void smp_call_function_single_interrupt(struct pt_regs *regs) +{ + ack_APIC_irq(); + irq_enter(); + generic_smp_call_function_single_interrupt(); +#ifdef CONFIG_X86_32 + __get_cpu_var(irq_stat).irq_call_count++; +#else + add_pda(irq_call_count, 1); +#endif + irq_exit(); } struct smp_ops smp_ops = { @@ -338,7 +219,8 @@ struct smp_ops smp_ops = { .smp_send_stop = native_smp_send_stop, .smp_send_reschedule = native_smp_send_reschedule, - .smp_call_function_mask = native_smp_call_function_mask, + + .send_call_func_ipi = native_send_call_func_ipi, + .send_call_func_single_ipi = native_send_call_func_single_ipi, }; EXPORT_SYMBOL_GPL(smp_ops); - diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 38988491c622..687376ab07e8 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -59,7 +59,6 @@ #include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/mtrr.h> -#include <asm/nmi.h> #include <asm/vmi.h> #include <asm/genapic.h> #include <linux/mc146818rtc.h> @@ -68,22 +67,6 @@ #include <mach_wakecpu.h> #include <smpboot_hooks.h> -/* - * FIXME: For x86_64, those are defined in other files. But moving them here, - * would make the setup areas dependent on smp, which is a loss. When we - * integrate apic between arches, we can probably do a better job, but - * right now, they'll stay here -- glommer - */ - -/* which logical CPU number maps to which CPU (physical APIC ID) */ -u16 x86_cpu_to_apicid_init[NR_CPUS] __initdata = - { [0 ... NR_CPUS-1] = BAD_APICID }; -void *x86_cpu_to_apicid_early_ptr; - -u16 x86_bios_cpu_apicid_init[NR_CPUS] __initdata - = { [0 ... NR_CPUS-1] = BAD_APICID }; -void *x86_bios_cpu_apicid_early_ptr; - #ifdef CONFIG_X86_32 u8 apicid_2_node[MAX_APICID]; static int low_mappings; @@ -198,13 +181,12 @@ static void map_cpu_to_logical_apicid(void) map_cpu_to_node(cpu, node); } -static void unmap_cpu_to_logical_apicid(int cpu) +void numa_remove_cpu(int cpu) { cpu_2_logical_apicid[cpu] = BAD_APICID; unmap_cpu_to_node(cpu); } #else -#define unmap_cpu_to_logical_apicid(cpu) do {} while (0) #define map_cpu_to_logical_apicid() do {} while (0) #endif @@ -345,19 +327,12 @@ static void __cpuinit start_secondary(void *unused) * lock helps us to not include this cpu in a currently in progress * smp_call_function(). */ - lock_ipi_call_lock(); -#ifdef CONFIG_X86_64 - spin_lock(&vector_lock); - - /* Setup the per cpu irq handling data structures */ - __setup_vector_irq(smp_processor_id()); - /* - * Allow the master to continue. - */ - spin_unlock(&vector_lock); + ipi_call_lock_irq(); +#ifdef CONFIG_X86_IO_APIC + setup_vector_irq(smp_processor_id()); #endif cpu_set(smp_processor_id(), cpu_online_map); - unlock_ipi_call_lock(); + ipi_call_unlock_irq(); per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; setup_secondary_clock(); @@ -366,31 +341,8 @@ static void __cpuinit start_secondary(void *unused) cpu_idle(); } -#ifdef CONFIG_X86_32 -/* - * Everything has been set up for the secondary - * CPUs - they just need to reload everything - * from the task structure - * This function must not return. - */ -void __devinit initialize_secondary(void) -{ - /* - * We don't actually need to load the full TSS, - * basically just the stack pointer and the ip. - */ - - asm volatile( - "movl %0,%%esp\n\t" - "jmp *%1" - : - :"m" (current->thread.sp), "m" (current->thread.ip)); -} -#endif - static void __cpuinit smp_apply_quirks(struct cpuinfo_x86 *c) { -#ifdef CONFIG_X86_32 /* * Mask B, Pentium, but not Pentium MMX */ @@ -440,7 +392,6 @@ static void __cpuinit smp_apply_quirks(struct cpuinfo_x86 *c) valid_k7: ; -#endif } static void __cpuinit smp_checks(void) @@ -555,23 +506,6 @@ cpumask_t cpu_coregroup_map(int cpu) return c->llc_shared_map; } -#ifdef CONFIG_X86_32 -/* - * We are called very early to get the low memory for the - * SMP bootup trampoline page. - */ -void __init smp_alloc_memory(void) -{ - trampoline_base = alloc_bootmem_low_pages(PAGE_SIZE); - /* - * Has to be in very low memory so we can execute - * real-mode AP code. - */ - if (__pa(trampoline_base) >= 0x9F000) - BUG(); -} -#endif - static void impress_friends(void) { int cpu; @@ -748,11 +682,7 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip) * target processor state. */ startup_ipi_hook(phys_apicid, (unsigned long) start_secondary, -#ifdef CONFIG_X86_64 - (unsigned long)init_rsp); -#else (unsigned long)stack_start.sp); -#endif /* * Run STARTUP IPI loop. @@ -832,6 +762,45 @@ static void __cpuinit do_fork_idle(struct work_struct *work) complete(&c_idle->done); } +#ifdef CONFIG_X86_64 +/* + * Allocate node local memory for the AP pda. + * + * Must be called after the _cpu_pda pointer table is initialized. + */ +static int __cpuinit get_local_pda(int cpu) +{ + struct x8664_pda *oldpda, *newpda; + unsigned long size = sizeof(struct x8664_pda); + int node = cpu_to_node(cpu); + + if (cpu_pda(cpu) && !cpu_pda(cpu)->in_bootmem) + return 0; + + oldpda = cpu_pda(cpu); + newpda = kmalloc_node(size, GFP_ATOMIC, node); + if (!newpda) { + printk(KERN_ERR "Could not allocate node local PDA " + "for CPU %d on node %d\n", cpu, node); + + if (oldpda) + return 0; /* have a usable pda */ + else + return -1; + } + + if (oldpda) { + memcpy(newpda, oldpda, size); + if (!after_bootmem) + free_bootmem((unsigned long)oldpda, size); + } + + newpda->in_bootmem = 0; + cpu_pda(cpu) = newpda; + return 0; +} +#endif /* CONFIG_X86_64 */ + static int __cpuinit do_boot_cpu(int apicid, int cpu) /* * NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad @@ -848,28 +817,14 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu) .done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done), }; INIT_WORK(&c_idle.work, do_fork_idle); -#ifdef CONFIG_X86_64 - /* allocate memory for gdts of secondary cpus. Hotplug is considered */ - if (!cpu_gdt_descr[cpu].address && - !(cpu_gdt_descr[cpu].address = get_zeroed_page(GFP_KERNEL))) { - printk(KERN_ERR "Failed to allocate GDT for CPU %d\n", cpu); - return -1; - } +#ifdef CONFIG_X86_64 /* Allocate node local memory for AP pdas */ - if (cpu_pda(cpu) == &boot_cpu_pda[cpu]) { - struct x8664_pda *newpda, *pda; - int node = cpu_to_node(cpu); - pda = cpu_pda(cpu); - newpda = kmalloc_node(sizeof(struct x8664_pda), GFP_ATOMIC, - node); - if (newpda) { - memcpy(newpda, pda, sizeof(struct x8664_pda)); - cpu_pda(cpu) = newpda; - } else - printk(KERN_ERR - "Could not allocate node local PDA for CPU %d on node %d\n", - cpu, node); + if (cpu > 0) { + boot_error = get_local_pda(cpu); + if (boot_error) + goto restore_state; + /* if can't get pda memory, can't start cpu */ } #endif @@ -905,18 +860,15 @@ do_rest: #ifdef CONFIG_X86_32 per_cpu(current_task, cpu) = c_idle.idle; init_gdt(cpu); - early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu); - c_idle.idle->thread.ip = (unsigned long) start_secondary; /* Stack for startup_32 can be just as for start_secondary onwards */ - stack_start.sp = (void *) c_idle.idle->thread.sp; irq_ctx_init(cpu); #else cpu_pda(cpu)->pcurrent = c_idle.idle; - init_rsp = c_idle.idle->thread.sp; - load_sp0(&per_cpu(init_tss, cpu), &c_idle.idle->thread); - initial_code = (unsigned long)start_secondary; clear_tsk_thread_flag(c_idle.idle, TIF_FORK); #endif + early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu); + initial_code = (unsigned long)start_secondary; + stack_start.sp = (void *) c_idle.idle->thread.sp; /* start_ip had better be page-aligned! */ start_ip = setup_trampoline(); @@ -987,16 +939,14 @@ do_rest: inquire_remote_apic(apicid); } } - - if (boot_error) { - /* Try to put things back the way they were before ... */ - unmap_cpu_to_logical_apicid(cpu); #ifdef CONFIG_X86_64 - clear_node_cpumask(cpu); /* was set by numa_add_cpu */ +restore_state: #endif + if (boot_error) { + /* Try to put things back the way they were before ... */ + numa_remove_cpu(cpu); /* was set by numa_add_cpu */ cpu_clear(cpu, cpu_callout_map); /* was set by do_boot_cpu() */ cpu_clear(cpu, cpu_initialized); /* was set by cpu_init() */ - cpu_clear(cpu, cpu_possible_map); cpu_clear(cpu, cpu_present_map); per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID; } @@ -1088,14 +1038,12 @@ static __init void disable_smp(void) { cpu_present_map = cpumask_of_cpu(0); cpu_possible_map = cpumask_of_cpu(0); -#ifdef CONFIG_X86_32 smpboot_clear_io_apic_irqs(); -#endif + if (smp_found_config) - phys_cpu_present_map = - physid_mask_of_physid(boot_cpu_physical_apicid); + physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map); else - phys_cpu_present_map = physid_mask_of_physid(0); + physid_set_mask_of_physid(0, &phys_cpu_present_map); map_cpu_to_logical_apicid(); cpu_set(0, per_cpu(cpu_sibling_map, 0)); cpu_set(0, per_cpu(cpu_core_map, 0)); @@ -1158,12 +1106,12 @@ static int __init smp_sanity_check(unsigned max_cpus) * If SMP should be disabled, then really disable it! */ if (!max_cpus) { - printk(KERN_INFO "SMP mode deactivated," - "forcing use of dummy APIC emulation.\n"); + printk(KERN_INFO "SMP mode deactivated.\n"); smpboot_clear_io_apic(); -#ifdef CONFIG_X86_32 + + localise_nmi_watchdog(); + connect_bsp_APIC(); -#endif setup_local_APIC(); end_local_APIC_setup(); return -1; @@ -1190,7 +1138,7 @@ static void __init smp_cpu_index_default(void) */ void __init native_smp_prepare_cpus(unsigned int max_cpus) { - nmi_watchdog_default(); + preempt_disable(); smp_cpu_index_default(); current_cpu_data = boot_cpu_data; cpu_callin_map = cpumask_of_cpu(0); @@ -1206,7 +1154,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) if (smp_sanity_check(max_cpus) < 0) { printk(KERN_INFO "SMP disabled\n"); disable_smp(); - return; + goto out; } preempt_disable(); @@ -1217,9 +1165,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) } preempt_enable(); -#ifdef CONFIG_X86_32 connect_bsp_APIC(); -#endif + /* * Switch from PIC to APIC mode. */ @@ -1246,6 +1193,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) printk(KERN_INFO "CPU%d: ", 0); print_cpu_info(&cpu_data(0)); setup_boot_clock(); +out: + preempt_enable(); } /* * Early setup to make printk work. @@ -1255,8 +1204,8 @@ void __init native_smp_prepare_boot_cpu(void) int me = smp_processor_id(); #ifdef CONFIG_X86_32 init_gdt(me); - switch_to_new_gdt(); #endif + switch_to_new_gdt(); /* already set me in cpu_online_map in boot_cpu_init() */ cpu_set(me, cpu_callout_map); per_cpu(cpu_state, me) = CPU_ONLINE; @@ -1276,23 +1225,6 @@ void __init native_smp_cpus_done(unsigned int max_cpus) #ifdef CONFIG_HOTPLUG_CPU -# ifdef CONFIG_X86_32 -void cpu_exit_clear(void) -{ - int cpu = raw_smp_processor_id(); - - idle_task_exit(); - - cpu_uninit(); - irq_ctx_exit(cpu); - - cpu_clear(cpu, cpu_callout_map); - cpu_clear(cpu, cpu_callin_map); - - unmap_cpu_to_logical_apicid(cpu); -} -# endif /* CONFIG_X86_32 */ - static void remove_siblinginfo(int cpu) { int sibling; @@ -1346,12 +1278,20 @@ __init void prefill_possible_map(void) int i; int possible; + /* no processor from mptable or madt */ + if (!num_processors) + num_processors = 1; + +#ifdef CONFIG_HOTPLUG_CPU if (additional_cpus == -1) { if (disabled_cpus > 0) additional_cpus = disabled_cpus; else additional_cpus = 0; } +#else + additional_cpus = 0; +#endif possible = num_processors + additional_cpus; if (possible > NR_CPUS) possible = NR_CPUS; @@ -1361,18 +1301,18 @@ __init void prefill_possible_map(void) for (i = 0; i < possible; i++) cpu_set(i, cpu_possible_map); + + nr_cpu_ids = possible; } static void __ref remove_cpu_from_maps(int cpu) { cpu_clear(cpu, cpu_online_map); -#ifdef CONFIG_X86_64 cpu_clear(cpu, cpu_callout_map); cpu_clear(cpu, cpu_callin_map); /* was set by cpu_init() */ clear_bit(cpu, (unsigned long *)&cpu_initialized); - clear_node_cpumask(cpu); -#endif + numa_remove_cpu(cpu); } int __cpu_disable(void) diff --git a/arch/x86/kernel/smpcommon.c b/arch/x86/kernel/smpcommon.c index 3449064d141a..99941b37eca0 100644 --- a/arch/x86/kernel/smpcommon.c +++ b/arch/x86/kernel/smpcommon.c @@ -25,59 +25,3 @@ __cpuinit void init_gdt(int cpu) per_cpu(cpu_number, cpu) = cpu; } #endif - -/** - * smp_call_function(): Run a function on all other CPUs. - * @func: The function to run. This must be fast and non-blocking. - * @info: An arbitrary pointer to pass to the function. - * @nonatomic: Unused. - * @wait: If true, wait (atomically) until function has completed on other CPUs. - * - * Returns 0 on success, else a negative status code. - * - * If @wait is true, then returns once @func has returned; otherwise - * it returns just before the target cpu calls @func. - * - * You must not call this function with disabled interrupts or from a - * hardware interrupt handler or from a bottom half handler. - */ -int smp_call_function(void (*func) (void *info), void *info, int nonatomic, - int wait) -{ - return smp_call_function_mask(cpu_online_map, func, info, wait); -} -EXPORT_SYMBOL(smp_call_function); - -/** - * smp_call_function_single - Run a function on a specific CPU - * @cpu: The target CPU. Cannot be the calling CPU. - * @func: The function to run. This must be fast and non-blocking. - * @info: An arbitrary pointer to pass to the function. - * @nonatomic: Unused. - * @wait: If true, wait until function has completed on other CPUs. - * - * Returns 0 on success, else a negative status code. - * - * If @wait is true, then returns once @func has returned; otherwise - * it returns just before the target cpu calls @func. - */ -int smp_call_function_single(int cpu, void (*func) (void *info), void *info, - int nonatomic, int wait) -{ - /* prevent preemption and reschedule on another processor */ - int ret; - int me = get_cpu(); - if (cpu == me) { - local_irq_disable(); - func(info); - local_irq_enable(); - put_cpu(); - return 0; - } - - ret = smp_call_function_mask(cpumask_of_cpu(cpu), func, info, wait); - - put_cpu(); - return ret; -} -EXPORT_SYMBOL(smp_call_function_single); diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index c28c342c162f..a03e7f6d90c3 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -74,6 +74,7 @@ void save_stack_trace(struct stack_trace *trace) if (trace->nr_entries < trace->max_entries) trace->entries[trace->nr_entries++] = ULONG_MAX; } +EXPORT_SYMBOL_GPL(save_stack_trace); void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) { @@ -81,3 +82,4 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) if (trace->nr_entries < trace->max_entries) trace->entries[trace->nr_entries++] = ULONG_MAX; } +EXPORT_SYMBOL_GPL(save_stack_trace_tsk); diff --git a/arch/x86/kernel/summit_32.c b/arch/x86/kernel/summit_32.c index ae751094eba9..d67ce5f044ba 100644 --- a/arch/x86/kernel/summit_32.c +++ b/arch/x86/kernel/summit_32.c @@ -36,7 +36,9 @@ static struct rio_table_hdr *rio_table_hdr __initdata; static struct scal_detail *scal_devs[MAX_NUMNODES] __initdata; static struct rio_detail *rio_devs[MAX_NUMNODES*4] __initdata; +#ifndef CONFIG_X86_NUMAQ static int mp_bus_id_to_node[MAX_MP_BUSSES] __initdata; +#endif static int __init setup_pci_node_map_for_wpeg(int wpeg_num, int last_bus) { diff --git a/arch/x86/kernel/sys_i386_32.c b/arch/x86/kernel/sys_i386_32.c index d2ab52cc1d6b..7066cb855a60 100644 --- a/arch/x86/kernel/sys_i386_32.c +++ b/arch/x86/kernel/sys_i386_32.c @@ -19,8 +19,8 @@ #include <linux/utsname.h> #include <linux/ipc.h> -#include <asm/uaccess.h> -#include <asm/unistd.h> +#include <linux/uaccess.h> +#include <linux/unistd.h> asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, @@ -103,7 +103,7 @@ asmlinkage int old_select(struct sel_arg_struct __user *arg) * * This is really horribly ugly. */ -asmlinkage int sys_ipc (uint call, int first, int second, +asmlinkage int sys_ipc(uint call, int first, int second, int third, void __user *ptr, long fifth) { int version, ret; @@ -113,24 +113,24 @@ asmlinkage int sys_ipc (uint call, int first, int second, switch (call) { case SEMOP: - return sys_semtimedop (first, (struct sembuf __user *)ptr, second, NULL); + return sys_semtimedop(first, (struct sembuf __user *)ptr, second, NULL); case SEMTIMEDOP: return sys_semtimedop(first, (struct sembuf __user *)ptr, second, (const struct timespec __user *)fifth); case SEMGET: - return sys_semget (first, second, third); + return sys_semget(first, second, third); case SEMCTL: { union semun fourth; if (!ptr) return -EINVAL; if (get_user(fourth.__pad, (void __user * __user *) ptr)) return -EFAULT; - return sys_semctl (first, second, third, fourth); + return sys_semctl(first, second, third, fourth); } case MSGSND: - return sys_msgsnd (first, (struct msgbuf __user *) ptr, + return sys_msgsnd(first, (struct msgbuf __user *) ptr, second, third); case MSGRCV: switch (version) { @@ -138,45 +138,45 @@ asmlinkage int sys_ipc (uint call, int first, int second, struct ipc_kludge tmp; if (!ptr) return -EINVAL; - + if (copy_from_user(&tmp, - (struct ipc_kludge __user *) ptr, - sizeof (tmp))) + (struct ipc_kludge __user *) ptr, + sizeof(tmp))) return -EFAULT; - return sys_msgrcv (first, tmp.msgp, second, + return sys_msgrcv(first, tmp.msgp, second, tmp.msgtyp, third); } default: - return sys_msgrcv (first, + return sys_msgrcv(first, (struct msgbuf __user *) ptr, second, fifth, third); } case MSGGET: - return sys_msgget ((key_t) first, second); + return sys_msgget((key_t) first, second); case MSGCTL: - return sys_msgctl (first, second, (struct msqid_ds __user *) ptr); + return sys_msgctl(first, second, (struct msqid_ds __user *) ptr); case SHMAT: switch (version) { default: { ulong raddr; - ret = do_shmat (first, (char __user *) ptr, second, &raddr); + ret = do_shmat(first, (char __user *) ptr, second, &raddr); if (ret) return ret; - return put_user (raddr, (ulong __user *) third); + return put_user(raddr, (ulong __user *) third); } case 1: /* iBCS2 emulator entry point */ if (!segment_eq(get_fs(), get_ds())) return -EINVAL; /* The "(ulong *) third" is valid _only_ because of the kernel segment thing */ - return do_shmat (first, (char __user *) ptr, second, (ulong *) third); + return do_shmat(first, (char __user *) ptr, second, (ulong *) third); } - case SHMDT: - return sys_shmdt ((char __user *)ptr); + case SHMDT: + return sys_shmdt((char __user *)ptr); case SHMGET: - return sys_shmget (first, second, third); + return sys_shmget(first, second, third); case SHMCTL: - return sys_shmctl (first, second, + return sys_shmctl(first, second, (struct shmid_ds __user *) ptr); default: return -ENOSYS; @@ -186,28 +186,28 @@ asmlinkage int sys_ipc (uint call, int first, int second, /* * Old cruft */ -asmlinkage int sys_uname(struct old_utsname __user * name) +asmlinkage int sys_uname(struct old_utsname __user *name) { int err; if (!name) return -EFAULT; down_read(&uts_sem); - err = copy_to_user(name, utsname(), sizeof (*name)); + err = copy_to_user(name, utsname(), sizeof(*name)); up_read(&uts_sem); - return err?-EFAULT:0; + return err? -EFAULT:0; } -asmlinkage int sys_olduname(struct oldold_utsname __user * name) +asmlinkage int sys_olduname(struct oldold_utsname __user *name) { int error; if (!name) return -EFAULT; - if (!access_ok(VERIFY_WRITE,name,sizeof(struct oldold_utsname))) + if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname))) return -EFAULT; - - down_read(&uts_sem); - + + down_read(&uts_sem); + error = __copy_to_user(&name->sysname, &utsname()->sysname, __OLD_UTS_LEN); error |= __put_user(0, name->sysname + __OLD_UTS_LEN); @@ -223,9 +223,9 @@ asmlinkage int sys_olduname(struct oldold_utsname __user * name) error |= __copy_to_user(&name->machine, &utsname()->machine, __OLD_UTS_LEN); error |= __put_user(0, name->machine + __OLD_UTS_LEN); - + up_read(&uts_sem); - + error = error ? -EFAULT : 0; return error; @@ -241,6 +241,6 @@ int kernel_execve(const char *filename, char *const argv[], char *const envp[]) long __res; asm volatile ("push %%ebx ; movl %2,%%ebx ; int $0x80 ; pop %%ebx" : "=a" (__res) - : "0" (__NR_execve),"ri" (filename),"c" (argv), "d" (envp) : "memory"); + : "0" (__NR_execve), "ri" (filename), "c" (argv), "d" (envp) : "memory"); return __res; } diff --git a/arch/x86/kernel/time_32.c b/arch/x86/kernel/time_32.c index 2ff21f398934..059ca6ee59b4 100644 --- a/arch/x86/kernel/time_32.c +++ b/arch/x86/kernel/time_32.c @@ -39,9 +39,6 @@ #include "do_timer.h" -unsigned int cpu_khz; /* Detected as we calibrate the TSC */ -EXPORT_SYMBOL(cpu_khz); - int timer_ack; unsigned long profile_pc(struct pt_regs *regs) @@ -84,8 +81,7 @@ irqreturn_t timer_interrupt(int irq, void *dev_id) if (timer_ack) { /* * Subtle, when I/O APICs are used we have to ack timer IRQ - * manually to reset the IRR bit for do_slow_gettimeoffset(). - * This will also deassert NMI lines for the watchdog if run + * manually to deassert NMI lines for the watchdog if run * on an 82489DX-based system. */ spin_lock(&i8259A_lock); diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c index c737849e2ef7..e3d49c553af2 100644 --- a/arch/x86/kernel/time_64.c +++ b/arch/x86/kernel/time_64.c @@ -56,7 +56,7 @@ static irqreturn_t timer_event_interrupt(int irq, void *dev_id) /* calibrate_cpu is used on systems with fixed rate TSCs to determine * processor frequency */ #define TICK_COUNT 100000000 -unsigned long __init native_calculate_cpu_khz(void) +unsigned long __init calibrate_cpu(void) { int tsc_start, tsc_now; int i, no_ctr_free; @@ -116,23 +116,11 @@ void __init hpet_time_init(void) void __init time_init(void) { - tsc_calibrate(); - - cpu_khz = tsc_khz; - if (cpu_has(&boot_cpu_data, X86_FEATURE_CONSTANT_TSC) && - (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)) - cpu_khz = calculate_cpu_khz(); - - if (unsynchronized_tsc()) - mark_tsc_unstable("TSCs unsynchronized"); - + tsc_init(); if (cpu_has(&boot_cpu_data, X86_FEATURE_RDTSCP)) vgetcpu_mode = VGETCPU_RDTSCP; else vgetcpu_mode = VGETCPU_LSL; - printk(KERN_INFO "time.c: Detected %d.%03d MHz processor.\n", - cpu_khz / 1000, cpu_khz % 1000); - init_tsc_clocksource(); late_time_init = choose_time_init(); } diff --git a/arch/x86/kernel/tlb_32.c b/arch/x86/kernel/tlb_32.c index 9bb2363851af..fec1ecedc9b7 100644 --- a/arch/x86/kernel/tlb_32.c +++ b/arch/x86/kernel/tlb_32.c @@ -238,6 +238,6 @@ static void do_flush_tlb_all(void *info) void flush_tlb_all(void) { - on_each_cpu(do_flush_tlb_all, NULL, 1, 1); + on_each_cpu(do_flush_tlb_all, NULL, 1); } diff --git a/arch/x86/kernel/tlb_64.c b/arch/x86/kernel/tlb_64.c index a1f07d793202..dcbf7a1159ea 100644 --- a/arch/x86/kernel/tlb_64.c +++ b/arch/x86/kernel/tlb_64.c @@ -15,6 +15,8 @@ #include <asm/proto.h> #include <asm/apicdef.h> #include <asm/idle.h> +#include <asm/uv/uv_hub.h> +#include <asm/uv/uv_bau.h> #include <mach_ipi.h> /* @@ -162,6 +164,9 @@ void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm, union smp_flush_state *f; cpumask_t cpumask = *cpumaskp; + if (is_uv_system() && uv_flush_tlb_others(&cpumask, mm, va)) + return; + /* Caller has disabled preemption */ sender = smp_processor_id() % NUM_INVALIDATE_TLB_VECTORS; f = &per_cpu(flush_state, sender); @@ -270,5 +275,5 @@ static void do_flush_tlb_all(void *info) void flush_tlb_all(void) { - on_each_cpu(do_flush_tlb_all, NULL, 1, 1); + on_each_cpu(do_flush_tlb_all, NULL, 1); } diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c new file mode 100644 index 000000000000..d0fbb7712ab0 --- /dev/null +++ b/arch/x86/kernel/tlb_uv.c @@ -0,0 +1,792 @@ +/* + * SGI UltraViolet TLB flush routines. + * + * (c) 2008 Cliff Wickman <cpw@sgi.com>, SGI. + * + * This code is released under the GNU General Public License version 2 or + * later. + */ +#include <linux/mc146818rtc.h> +#include <linux/proc_fs.h> +#include <linux/kernel.h> + +#include <asm/mmu_context.h> +#include <asm/uv/uv_mmrs.h> +#include <asm/uv/uv_hub.h> +#include <asm/uv/uv_bau.h> +#include <asm/genapic.h> +#include <asm/idle.h> +#include <asm/tsc.h> + +#include <mach_apic.h> + +static struct bau_control **uv_bau_table_bases __read_mostly; +static int uv_bau_retry_limit __read_mostly; + +/* position of pnode (which is nasid>>1): */ +static int uv_nshift __read_mostly; + +static unsigned long uv_mmask __read_mostly; + +static DEFINE_PER_CPU(struct ptc_stats, ptcstats); +static DEFINE_PER_CPU(struct bau_control, bau_control); + +/* + * Free a software acknowledge hardware resource by clearing its Pending + * bit. This will return a reply to the sender. + * If the message has timed out, a reply has already been sent by the + * hardware but the resource has not been released. In that case our + * clear of the Timeout bit (as well) will free the resource. No reply will + * be sent (the hardware will only do one reply per message). + */ +static void uv_reply_to_message(int resource, + struct bau_payload_queue_entry *msg, + struct bau_msg_status *msp) +{ + unsigned long dw; + + dw = (1 << (resource + UV_SW_ACK_NPENDING)) | (1 << resource); + msg->replied_to = 1; + msg->sw_ack_vector = 0; + if (msp) + msp->seen_by.bits = 0; + uv_write_local_mmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, dw); +} + +/* + * Do all the things a cpu should do for a TLB shootdown message. + * Other cpu's may come here at the same time for this message. + */ +static void uv_bau_process_message(struct bau_payload_queue_entry *msg, + int msg_slot, int sw_ack_slot) +{ + unsigned long this_cpu_mask; + struct bau_msg_status *msp; + int cpu; + + msp = __get_cpu_var(bau_control).msg_statuses + msg_slot; + cpu = uv_blade_processor_id(); + msg->number_of_cpus = + uv_blade_nr_online_cpus(uv_node_to_blade_id(numa_node_id())); + this_cpu_mask = 1UL << cpu; + if (msp->seen_by.bits & this_cpu_mask) + return; + atomic_or_long(&msp->seen_by.bits, this_cpu_mask); + + if (msg->replied_to == 1) + return; + + if (msg->address == TLB_FLUSH_ALL) { + local_flush_tlb(); + __get_cpu_var(ptcstats).alltlb++; + } else { + __flush_tlb_one(msg->address); + __get_cpu_var(ptcstats).onetlb++; + } + + __get_cpu_var(ptcstats).requestee++; + + atomic_inc_short(&msg->acknowledge_count); + if (msg->number_of_cpus == msg->acknowledge_count) + uv_reply_to_message(sw_ack_slot, msg, msp); +} + +/* + * Examine the payload queue on one distribution node to see + * which messages have not been seen, and which cpu(s) have not seen them. + * + * Returns the number of cpu's that have not responded. + */ +static int uv_examine_destination(struct bau_control *bau_tablesp, int sender) +{ + struct bau_payload_queue_entry *msg; + struct bau_msg_status *msp; + int count = 0; + int i; + int j; + + for (msg = bau_tablesp->va_queue_first, i = 0; i < DEST_Q_SIZE; + msg++, i++) { + if ((msg->sending_cpu == sender) && (!msg->replied_to)) { + msp = bau_tablesp->msg_statuses + i; + printk(KERN_DEBUG + "blade %d: address:%#lx %d of %d, not cpu(s): ", + i, msg->address, msg->acknowledge_count, + msg->number_of_cpus); + for (j = 0; j < msg->number_of_cpus; j++) { + if (!((1L << j) & msp->seen_by.bits)) { + count++; + printk("%d ", j); + } + } + printk("\n"); + } + } + return count; +} + +/* + * Examine the payload queue on all the distribution nodes to see + * which messages have not been seen, and which cpu(s) have not seen them. + * + * Returns the number of cpu's that have not responded. + */ +static int uv_examine_destinations(struct bau_target_nodemask *distribution) +{ + int sender; + int i; + int count = 0; + + sender = smp_processor_id(); + for (i = 0; i < sizeof(struct bau_target_nodemask) * BITSPERBYTE; i++) { + if (!bau_node_isset(i, distribution)) + continue; + count += uv_examine_destination(uv_bau_table_bases[i], sender); + } + return count; +} + +/* + * wait for completion of a broadcast message + * + * return COMPLETE, RETRY or GIVEUP + */ +static int uv_wait_completion(struct bau_desc *bau_desc, + unsigned long mmr_offset, int right_shift) +{ + int exams = 0; + long destination_timeouts = 0; + long source_timeouts = 0; + unsigned long descriptor_status; + + while ((descriptor_status = (((unsigned long) + uv_read_local_mmr(mmr_offset) >> + right_shift) & UV_ACT_STATUS_MASK)) != + DESC_STATUS_IDLE) { + if (descriptor_status == DESC_STATUS_SOURCE_TIMEOUT) { + source_timeouts++; + if (source_timeouts > SOURCE_TIMEOUT_LIMIT) + source_timeouts = 0; + __get_cpu_var(ptcstats).s_retry++; + return FLUSH_RETRY; + } + /* + * spin here looking for progress at the destinations + */ + if (descriptor_status == DESC_STATUS_DESTINATION_TIMEOUT) { + destination_timeouts++; + if (destination_timeouts > DESTINATION_TIMEOUT_LIMIT) { + /* + * returns number of cpus not responding + */ + if (uv_examine_destinations + (&bau_desc->distribution) == 0) { + __get_cpu_var(ptcstats).d_retry++; + return FLUSH_RETRY; + } + exams++; + if (exams >= uv_bau_retry_limit) { + printk(KERN_DEBUG + "uv_flush_tlb_others"); + printk("giving up on cpu %d\n", + smp_processor_id()); + return FLUSH_GIVEUP; + } + /* + * delays can hang the simulator + udelay(1000); + */ + destination_timeouts = 0; + } + } + } + return FLUSH_COMPLETE; +} + +/** + * uv_flush_send_and_wait + * + * Send a broadcast and wait for a broadcast message to complete. + * + * The cpumaskp mask contains the cpus the broadcast was sent to. + * + * Returns 1 if all remote flushing was done. The mask is zeroed. + * Returns 0 if some remote flushing remains to be done. The mask is left + * unchanged. + */ +int uv_flush_send_and_wait(int cpu, int this_blade, struct bau_desc *bau_desc, + cpumask_t *cpumaskp) +{ + int completion_status = 0; + int right_shift; + int tries = 0; + int blade; + int bit; + unsigned long mmr_offset; + unsigned long index; + cycles_t time1; + cycles_t time2; + + if (cpu < UV_CPUS_PER_ACT_STATUS) { + mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0; + right_shift = cpu * UV_ACT_STATUS_SIZE; + } else { + mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1; + right_shift = + ((cpu - UV_CPUS_PER_ACT_STATUS) * UV_ACT_STATUS_SIZE); + } + time1 = get_cycles(); + do { + tries++; + index = (1UL << UVH_LB_BAU_SB_ACTIVATION_CONTROL_PUSH_SHFT) | + cpu; + uv_write_local_mmr(UVH_LB_BAU_SB_ACTIVATION_CONTROL, index); + completion_status = uv_wait_completion(bau_desc, mmr_offset, + right_shift); + } while (completion_status == FLUSH_RETRY); + time2 = get_cycles(); + __get_cpu_var(ptcstats).sflush += (time2 - time1); + if (tries > 1) + __get_cpu_var(ptcstats).retriesok++; + + if (completion_status == FLUSH_GIVEUP) { + /* + * Cause the caller to do an IPI-style TLB shootdown on + * the cpu's, all of which are still in the mask. + */ + __get_cpu_var(ptcstats).ptc_i++; + return 0; + } + + /* + * Success, so clear the remote cpu's from the mask so we don't + * use the IPI method of shootdown on them. + */ + for_each_cpu_mask(bit, *cpumaskp) { + blade = uv_cpu_to_blade_id(bit); + if (blade == this_blade) + continue; + cpu_clear(bit, *cpumaskp); + } + if (!cpus_empty(*cpumaskp)) + return 0; + return 1; +} + +/** + * uv_flush_tlb_others - globally purge translation cache of a virtual + * address or all TLB's + * @cpumaskp: mask of all cpu's in which the address is to be removed + * @mm: mm_struct containing virtual address range + * @va: virtual address to be removed (or TLB_FLUSH_ALL for all TLB's on cpu) + * + * This is the entry point for initiating any UV global TLB shootdown. + * + * Purges the translation caches of all specified processors of the given + * virtual address, or purges all TLB's on specified processors. + * + * The caller has derived the cpumaskp from the mm_struct and has subtracted + * the local cpu from the mask. This function is called only if there + * are bits set in the mask. (e.g. flush_tlb_page()) + * + * The cpumaskp is converted into a nodemask of the nodes containing + * the cpus. + * + * Returns 1 if all remote flushing was done. + * Returns 0 if some remote flushing remains to be done. + */ +int uv_flush_tlb_others(cpumask_t *cpumaskp, struct mm_struct *mm, + unsigned long va) +{ + int i; + int bit; + int blade; + int cpu; + int this_blade; + int locals = 0; + struct bau_desc *bau_desc; + + cpu = uv_blade_processor_id(); + this_blade = uv_numa_blade_id(); + bau_desc = __get_cpu_var(bau_control).descriptor_base; + bau_desc += UV_ITEMS_PER_DESCRIPTOR * cpu; + + bau_nodes_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE); + + i = 0; + for_each_cpu_mask(bit, *cpumaskp) { + blade = uv_cpu_to_blade_id(bit); + BUG_ON(blade > (UV_DISTRIBUTION_SIZE - 1)); + if (blade == this_blade) { + locals++; + continue; + } + bau_node_set(blade, &bau_desc->distribution); + i++; + } + if (i == 0) { + /* + * no off_node flushing; return status for local node + */ + if (locals) + return 0; + else + return 1; + } + __get_cpu_var(ptcstats).requestor++; + __get_cpu_var(ptcstats).ntargeted += i; + + bau_desc->payload.address = va; + bau_desc->payload.sending_cpu = smp_processor_id(); + + return uv_flush_send_and_wait(cpu, this_blade, bau_desc, cpumaskp); +} + +/* + * The BAU message interrupt comes here. (registered by set_intr_gate) + * See entry_64.S + * + * We received a broadcast assist message. + * + * Interrupts may have been disabled; this interrupt could represent + * the receipt of several messages. + * + * All cores/threads on this node get this interrupt. + * The last one to see it does the s/w ack. + * (the resource will not be freed until noninterruptable cpus see this + * interrupt; hardware will timeout the s/w ack and reply ERROR) + */ +void uv_bau_message_interrupt(struct pt_regs *regs) +{ + struct bau_payload_queue_entry *va_queue_first; + struct bau_payload_queue_entry *va_queue_last; + struct bau_payload_queue_entry *msg; + struct pt_regs *old_regs = set_irq_regs(regs); + cycles_t time1; + cycles_t time2; + int msg_slot; + int sw_ack_slot; + int fw; + int count = 0; + unsigned long local_pnode; + + ack_APIC_irq(); + exit_idle(); + irq_enter(); + + time1 = get_cycles(); + + local_pnode = uv_blade_to_pnode(uv_numa_blade_id()); + + va_queue_first = __get_cpu_var(bau_control).va_queue_first; + va_queue_last = __get_cpu_var(bau_control).va_queue_last; + + msg = __get_cpu_var(bau_control).bau_msg_head; + while (msg->sw_ack_vector) { + count++; + fw = msg->sw_ack_vector; + msg_slot = msg - va_queue_first; + sw_ack_slot = ffs(fw) - 1; + + uv_bau_process_message(msg, msg_slot, sw_ack_slot); + + msg++; + if (msg > va_queue_last) + msg = va_queue_first; + __get_cpu_var(bau_control).bau_msg_head = msg; + } + if (!count) + __get_cpu_var(ptcstats).nomsg++; + else if (count > 1) + __get_cpu_var(ptcstats).multmsg++; + + time2 = get_cycles(); + __get_cpu_var(ptcstats).dflush += (time2 - time1); + + irq_exit(); + set_irq_regs(old_regs); +} + +static void uv_enable_timeouts(void) +{ + int i; + int blade; + int last_blade; + int pnode; + int cur_cpu = 0; + unsigned long apicid; + + last_blade = -1; + for_each_online_node(i) { + blade = uv_node_to_blade_id(i); + if (blade == last_blade) + continue; + last_blade = blade; + apicid = per_cpu(x86_cpu_to_apicid, cur_cpu); + pnode = uv_blade_to_pnode(blade); + cur_cpu += uv_blade_nr_possible_cpus(i); + } +} + +static void *uv_ptc_seq_start(struct seq_file *file, loff_t *offset) +{ + if (*offset < num_possible_cpus()) + return offset; + return NULL; +} + +static void *uv_ptc_seq_next(struct seq_file *file, void *data, loff_t *offset) +{ + (*offset)++; + if (*offset < num_possible_cpus()) + return offset; + return NULL; +} + +static void uv_ptc_seq_stop(struct seq_file *file, void *data) +{ +} + +/* + * Display the statistics thru /proc + * data points to the cpu number + */ +static int uv_ptc_seq_show(struct seq_file *file, void *data) +{ + struct ptc_stats *stat; + int cpu; + + cpu = *(loff_t *)data; + + if (!cpu) { + seq_printf(file, + "# cpu requestor requestee one all sretry dretry ptc_i "); + seq_printf(file, + "sw_ack sflush dflush sok dnomsg dmult starget\n"); + } + if (cpu < num_possible_cpus() && cpu_online(cpu)) { + stat = &per_cpu(ptcstats, cpu); + seq_printf(file, "cpu %d %ld %ld %ld %ld %ld %ld %ld ", + cpu, stat->requestor, + stat->requestee, stat->onetlb, stat->alltlb, + stat->s_retry, stat->d_retry, stat->ptc_i); + seq_printf(file, "%lx %ld %ld %ld %ld %ld %ld\n", + uv_read_global_mmr64(uv_blade_to_pnode + (uv_cpu_to_blade_id(cpu)), + UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE), + stat->sflush, stat->dflush, + stat->retriesok, stat->nomsg, + stat->multmsg, stat->ntargeted); + } + + return 0; +} + +/* + * 0: display meaning of the statistics + * >0: retry limit + */ +static ssize_t uv_ptc_proc_write(struct file *file, const char __user *user, + size_t count, loff_t *data) +{ + long newmode; + char optstr[64]; + + if (count == 0 || count > sizeof(optstr)) + return -EINVAL; + if (copy_from_user(optstr, user, count)) + return -EFAULT; + optstr[count - 1] = '\0'; + if (strict_strtoul(optstr, 10, &newmode) < 0) { + printk(KERN_DEBUG "%s is invalid\n", optstr); + return -EINVAL; + } + + if (newmode == 0) { + printk(KERN_DEBUG "# cpu: cpu number\n"); + printk(KERN_DEBUG + "requestor: times this cpu was the flush requestor\n"); + printk(KERN_DEBUG + "requestee: times this cpu was requested to flush its TLBs\n"); + printk(KERN_DEBUG + "one: times requested to flush a single address\n"); + printk(KERN_DEBUG + "all: times requested to flush all TLB's\n"); + printk(KERN_DEBUG + "sretry: number of retries of source-side timeouts\n"); + printk(KERN_DEBUG + "dretry: number of retries of destination-side timeouts\n"); + printk(KERN_DEBUG + "ptc_i: times UV fell through to IPI-style flushes\n"); + printk(KERN_DEBUG + "sw_ack: image of UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE\n"); + printk(KERN_DEBUG + "sflush_us: cycles spent in uv_flush_tlb_others()\n"); + printk(KERN_DEBUG + "dflush_us: cycles spent in handling flush requests\n"); + printk(KERN_DEBUG "sok: successes on retry\n"); + printk(KERN_DEBUG "dnomsg: interrupts with no message\n"); + printk(KERN_DEBUG + "dmult: interrupts with multiple messages\n"); + printk(KERN_DEBUG "starget: nodes targeted\n"); + } else { + uv_bau_retry_limit = newmode; + printk(KERN_DEBUG "timeout retry limit:%d\n", + uv_bau_retry_limit); + } + + return count; +} + +static const struct seq_operations uv_ptc_seq_ops = { + .start = uv_ptc_seq_start, + .next = uv_ptc_seq_next, + .stop = uv_ptc_seq_stop, + .show = uv_ptc_seq_show +}; + +static int uv_ptc_proc_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &uv_ptc_seq_ops); +} + +static const struct file_operations proc_uv_ptc_operations = { + .open = uv_ptc_proc_open, + .read = seq_read, + .write = uv_ptc_proc_write, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init uv_ptc_init(void) +{ + struct proc_dir_entry *proc_uv_ptc; + + if (!is_uv_system()) + return 0; + + if (!proc_mkdir("sgi_uv", NULL)) + return -EINVAL; + + proc_uv_ptc = create_proc_entry(UV_PTC_BASENAME, 0444, NULL); + if (!proc_uv_ptc) { + printk(KERN_ERR "unable to create %s proc entry\n", + UV_PTC_BASENAME); + remove_proc_entry("sgi_uv", NULL); + return -EINVAL; + } + proc_uv_ptc->proc_fops = &proc_uv_ptc_operations; + return 0; +} + +/* + * begin the initialization of the per-blade control structures + */ +static struct bau_control * __init uv_table_bases_init(int blade, int node) +{ + int i; + int *ip; + struct bau_msg_status *msp; + struct bau_control *bau_tabp; + + bau_tabp = + kmalloc_node(sizeof(struct bau_control), GFP_KERNEL, node); + BUG_ON(!bau_tabp); + + bau_tabp->msg_statuses = + kmalloc_node(sizeof(struct bau_msg_status) * + DEST_Q_SIZE, GFP_KERNEL, node); + BUG_ON(!bau_tabp->msg_statuses); + + for (i = 0, msp = bau_tabp->msg_statuses; i < DEST_Q_SIZE; i++, msp++) + bau_cpubits_clear(&msp->seen_by, (int) + uv_blade_nr_possible_cpus(blade)); + + bau_tabp->watching = + kmalloc_node(sizeof(int) * DEST_NUM_RESOURCES, GFP_KERNEL, node); + BUG_ON(!bau_tabp->watching); + + for (i = 0, ip = bau_tabp->watching; i < DEST_Q_SIZE; i++, ip++) + *ip = 0; + + uv_bau_table_bases[blade] = bau_tabp; + + return bau_tabp; +} + +/* + * finish the initialization of the per-blade control structures + */ +static void __init +uv_table_bases_finish(int blade, int node, int cur_cpu, + struct bau_control *bau_tablesp, + struct bau_desc *adp) +{ + struct bau_control *bcp; + int i; + + for (i = cur_cpu; i < cur_cpu + uv_blade_nr_possible_cpus(blade); i++) { + bcp = (struct bau_control *)&per_cpu(bau_control, i); + + bcp->bau_msg_head = bau_tablesp->va_queue_first; + bcp->va_queue_first = bau_tablesp->va_queue_first; + bcp->va_queue_last = bau_tablesp->va_queue_last; + bcp->watching = bau_tablesp->watching; + bcp->msg_statuses = bau_tablesp->msg_statuses; + bcp->descriptor_base = adp; + } +} + +/* + * initialize the sending side's sending buffers + */ +static struct bau_desc * __init +uv_activation_descriptor_init(int node, int pnode) +{ + int i; + unsigned long pa; + unsigned long m; + unsigned long n; + unsigned long mmr_image; + struct bau_desc *adp; + struct bau_desc *ad2; + + adp = (struct bau_desc *) + kmalloc_node(16384, GFP_KERNEL, node); + BUG_ON(!adp); + + pa = __pa((unsigned long)adp); + n = pa >> uv_nshift; + m = pa & uv_mmask; + + mmr_image = uv_read_global_mmr64(pnode, UVH_LB_BAU_SB_DESCRIPTOR_BASE); + if (mmr_image) { + uv_write_global_mmr64(pnode, (unsigned long) + UVH_LB_BAU_SB_DESCRIPTOR_BASE, + (n << UV_DESC_BASE_PNODE_SHIFT | m)); + } + + for (i = 0, ad2 = adp; i < UV_ACTIVATION_DESCRIPTOR_SIZE; i++, ad2++) { + memset(ad2, 0, sizeof(struct bau_desc)); + ad2->header.sw_ack_flag = 1; + ad2->header.base_dest_nodeid = + uv_blade_to_pnode(uv_cpu_to_blade_id(0)); + ad2->header.command = UV_NET_ENDPOINT_INTD; + ad2->header.int_both = 1; + /* + * all others need to be set to zero: + * fairness chaining multilevel count replied_to + */ + } + return adp; +} + +/* + * initialize the destination side's receiving buffers + */ +static struct bau_payload_queue_entry * __init +uv_payload_queue_init(int node, int pnode, struct bau_control *bau_tablesp) +{ + struct bau_payload_queue_entry *pqp; + char *cp; + + pqp = (struct bau_payload_queue_entry *) kmalloc_node( + (DEST_Q_SIZE + 1) * sizeof(struct bau_payload_queue_entry), + GFP_KERNEL, node); + BUG_ON(!pqp); + + cp = (char *)pqp + 31; + pqp = (struct bau_payload_queue_entry *)(((unsigned long)cp >> 5) << 5); + bau_tablesp->va_queue_first = pqp; + uv_write_global_mmr64(pnode, + UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST, + ((unsigned long)pnode << + UV_PAYLOADQ_PNODE_SHIFT) | + uv_physnodeaddr(pqp)); + uv_write_global_mmr64(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL, + uv_physnodeaddr(pqp)); + bau_tablesp->va_queue_last = pqp + (DEST_Q_SIZE - 1); + uv_write_global_mmr64(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST, + (unsigned long) + uv_physnodeaddr(bau_tablesp->va_queue_last)); + memset(pqp, 0, sizeof(struct bau_payload_queue_entry) * DEST_Q_SIZE); + + return pqp; +} + +/* + * Initialization of each UV blade's structures + */ +static int __init uv_init_blade(int blade, int node, int cur_cpu) +{ + int pnode; + unsigned long pa; + unsigned long apicid; + struct bau_desc *adp; + struct bau_payload_queue_entry *pqp; + struct bau_control *bau_tablesp; + + bau_tablesp = uv_table_bases_init(blade, node); + pnode = uv_blade_to_pnode(blade); + adp = uv_activation_descriptor_init(node, pnode); + pqp = uv_payload_queue_init(node, pnode, bau_tablesp); + uv_table_bases_finish(blade, node, cur_cpu, bau_tablesp, adp); + /* + * the below initialization can't be in firmware because the + * messaging IRQ will be determined by the OS + */ + apicid = per_cpu(x86_cpu_to_apicid, cur_cpu); + pa = uv_read_global_mmr64(pnode, UVH_BAU_DATA_CONFIG); + if ((pa & 0xff) != UV_BAU_MESSAGE) { + uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG, + ((apicid << 32) | UV_BAU_MESSAGE)); + } + return 0; +} + +/* + * Initialization of BAU-related structures + */ +static int __init uv_bau_init(void) +{ + int blade; + int node; + int nblades; + int last_blade; + int cur_cpu = 0; + + if (!is_uv_system()) + return 0; + + uv_bau_retry_limit = 1; + uv_nshift = uv_hub_info->n_val; + uv_mmask = (1UL << uv_hub_info->n_val) - 1; + nblades = 0; + last_blade = -1; + for_each_online_node(node) { + blade = uv_node_to_blade_id(node); + if (blade == last_blade) + continue; + last_blade = blade; + nblades++; + } + uv_bau_table_bases = (struct bau_control **) + kmalloc(nblades * sizeof(struct bau_control *), GFP_KERNEL); + BUG_ON(!uv_bau_table_bases); + + last_blade = -1; + for_each_online_node(node) { + blade = uv_node_to_blade_id(node); + if (blade == last_blade) + continue; + last_blade = blade; + uv_init_blade(blade, node, cur_cpu); + cur_cpu += uv_blade_nr_possible_cpus(blade); + } + set_intr_gate(UV_BAU_MESSAGE, uv_bau_message_intr1); + uv_enable_timeouts(); + + return 0; +} +__initcall(uv_bau_init); +__initcall(uv_ptc_init); diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c index abbf199adebb..1106fac6024d 100644 --- a/arch/x86/kernel/trampoline.c +++ b/arch/x86/kernel/trampoline.c @@ -2,7 +2,7 @@ #include <asm/trampoline.h> -/* ready for x86_64, no harm for x86, since it will overwrite after alloc */ +/* ready for x86_64 and x86 */ unsigned char *trampoline_base = __va(TRAMPOLINE_BASE); /* diff --git a/arch/x86/kernel/traps_32.c b/arch/x86/kernel/traps_32.c index bde6f63e15d5..8a768973c4f0 100644 --- a/arch/x86/kernel/traps_32.c +++ b/arch/x86/kernel/traps_32.c @@ -1,5 +1,6 @@ /* * Copyright (C) 1991, 1992 Linus Torvalds + * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs * * Pentium III FXSR, SSE support * Gareth Hughes <gareth@valinux.com>, May 2000 @@ -60,8 +61,6 @@ #include "mach_traps.h" -int panic_on_unrecovered_nmi; - DECLARE_BITMAP(used_vectors, NR_VECTORS); EXPORT_SYMBOL_GPL(used_vectors); @@ -98,19 +97,22 @@ asmlinkage void alignment_check(void); asmlinkage void spurious_interrupt_bug(void); asmlinkage void machine_check(void); +int panic_on_unrecovered_nmi; int kstack_depth_to_print = 24; static unsigned int code_bytes = 64; +static int ignore_nmis; +static int die_counter; void printk_address(unsigned long address, int reliable) { #ifdef CONFIG_KALLSYMS - char namebuf[KSYM_NAME_LEN]; unsigned long offset = 0; unsigned long symsize; const char *symname; - char reliab[4] = ""; - char *delim = ":"; char *modname; + char *delim = ":"; + char namebuf[KSYM_NAME_LEN]; + char reliab[4] = ""; symname = kallsyms_lookup(address, &symsize, &offset, &modname, namebuf); @@ -130,22 +132,23 @@ void printk_address(unsigned long address, int reliable) #endif } -static inline int valid_stack_ptr(struct thread_info *tinfo, void *p, unsigned size) +static inline int valid_stack_ptr(struct thread_info *tinfo, + void *p, unsigned int size) { - return p > (void *)tinfo && - p <= (void *)tinfo + THREAD_SIZE - size; + void *t = tinfo; + return p > t && p <= t + THREAD_SIZE - size; } /* The form of the top of the frame on the stack */ struct stack_frame { - struct stack_frame *next_frame; - unsigned long return_address; + struct stack_frame *next_frame; + unsigned long return_address; }; static inline unsigned long print_context_stack(struct thread_info *tinfo, - unsigned long *stack, unsigned long bp, - const struct stacktrace_ops *ops, void *data) + unsigned long *stack, unsigned long bp, + const struct stacktrace_ops *ops, void *data) { struct stack_frame *frame = (struct stack_frame *)bp; @@ -167,8 +170,6 @@ print_context_stack(struct thread_info *tinfo, return bp; } -#define MSG(msg) ops->warning(data, msg) - void dump_trace(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data) @@ -178,7 +179,6 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, if (!stack) { unsigned long dummy; - stack = &dummy; if (task != current) stack = (unsigned long *)task->thread.sp; @@ -196,7 +196,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, } #endif - while (1) { + for (;;) { struct thread_info *context; context = (struct thread_info *) @@ -248,10 +248,10 @@ static void print_trace_address(void *data, unsigned long addr, int reliable) } static const struct stacktrace_ops print_trace_ops = { - .warning = print_trace_warning, - .warning_symbol = print_trace_warning_symbol, - .stack = print_trace_stack, - .address = print_trace_address, + .warning = print_trace_warning, + .warning_symbol = print_trace_warning_symbol, + .stack = print_trace_stack, + .address = print_trace_address, }; static void @@ -351,15 +351,14 @@ void show_registers(struct pt_regs *regs) printk(KERN_EMERG "Code: "); ip = (u8 *)regs->ip - code_prologue; - if (ip < (u8 *)PAGE_OFFSET || - probe_kernel_address(ip, c)) { + if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) { /* try starting at EIP */ ip = (u8 *)regs->ip; code_len = code_len - code_prologue + 1; } for (i = 0; i < code_len; i++, ip++) { if (ip < (u8 *)PAGE_OFFSET || - probe_kernel_address(ip, c)) { + probe_kernel_address(ip, c)) { printk(" Bad EIP value."); break; } @@ -384,8 +383,6 @@ int is_valid_bugaddr(unsigned long ip) return ud2 == 0x0b0f; } -static int die_counter; - int __kprobes __die(const char *str, struct pt_regs *regs, long err) { unsigned short ss; @@ -402,26 +399,22 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err) printk("DEBUG_PAGEALLOC"); #endif printk("\n"); - if (notify_die(DIE_OOPS, str, regs, err, - current->thread.trap_no, SIGSEGV) != NOTIFY_STOP) { - - show_registers(regs); - /* Executive summary in case the oops scrolled away */ - sp = (unsigned long) (®s->sp); - savesegment(ss, ss); - if (user_mode(regs)) { - sp = regs->sp; - ss = regs->ss & 0xffff; - } - printk(KERN_EMERG "EIP: [<%08lx>] ", regs->ip); - print_symbol("%s", regs->ip); - printk(" SS:ESP %04x:%08lx\n", ss, sp); + current->thread.trap_no, SIGSEGV) == NOTIFY_STOP) + return 1; - return 0; + show_registers(regs); + /* Executive summary in case the oops scrolled away */ + sp = (unsigned long) (®s->sp); + savesegment(ss, ss); + if (user_mode(regs)) { + sp = regs->sp; + ss = regs->ss & 0xffff; } - - return 1; + printk(KERN_EMERG "EIP: [<%08lx>] ", regs->ip); + print_symbol("%s", regs->ip); + printk(" SS:ESP %04x:%08lx\n", ss, sp); + return 0; } /* @@ -544,8 +537,9 @@ vm86_trap: #define DO_ERROR(trapnr, signr, str, name) \ void do_##name(struct pt_regs *regs, long error_code) \ { \ + trace_hardirqs_fixup(); \ if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ + == NOTIFY_STOP) \ return; \ do_trap(trapnr, signr, str, 0, regs, error_code, NULL); \ } @@ -561,7 +555,7 @@ void do_##name(struct pt_regs *regs, long error_code) \ info.si_code = sicode; \ info.si_addr = (void __user *)siaddr; \ if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ + == NOTIFY_STOP) \ return; \ do_trap(trapnr, signr, str, 0, regs, error_code, &info); \ } @@ -570,7 +564,7 @@ void do_##name(struct pt_regs *regs, long error_code) \ void do_##name(struct pt_regs *regs, long error_code) \ { \ if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ + == NOTIFY_STOP) \ return; \ do_trap(trapnr, signr, str, 1, regs, error_code, NULL); \ } @@ -585,27 +579,29 @@ void do_##name(struct pt_regs *regs, long error_code) \ info.si_addr = (void __user *)siaddr; \ trace_hardirqs_fixup(); \ if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ + == NOTIFY_STOP) \ return; \ do_trap(trapnr, signr, str, 1, regs, error_code, &info); \ } -DO_VM86_ERROR_INFO(0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->ip) +DO_VM86_ERROR_INFO(0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->ip) #ifndef CONFIG_KPROBES DO_VM86_ERROR(3, SIGTRAP, "int3", int3) #endif DO_VM86_ERROR(4, SIGSEGV, "overflow", overflow) DO_VM86_ERROR(5, SIGSEGV, "bounds", bounds) -DO_ERROR_INFO(6, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, regs->ip, 0) -DO_ERROR(9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun) +DO_ERROR_INFO(6, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, regs->ip, 0) +DO_ERROR(9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun) DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS) -DO_ERROR(11, SIGBUS, "segment not present", segment_not_present) -DO_ERROR(12, SIGBUS, "stack segment", stack_segment) +DO_ERROR(11, SIGBUS, "segment not present", segment_not_present) +DO_ERROR(12, SIGBUS, "stack segment", stack_segment) DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0, 0) DO_ERROR_INFO(32, SIGILL, "iret exception", iret_error, ILL_BADSTK, 0, 1) -void __kprobes do_general_protection(struct pt_regs *regs, long error_code) +void __kprobes +do_general_protection(struct pt_regs *regs, long error_code) { + struct task_struct *tsk; struct thread_struct *thread; struct tss_struct *tss; int cpu; @@ -646,23 +642,24 @@ void __kprobes do_general_protection(struct pt_regs *regs, long error_code) if (regs->flags & X86_VM_MASK) goto gp_in_vm86; + tsk = current; if (!user_mode(regs)) goto gp_in_kernel; - current->thread.error_code = error_code; - current->thread.trap_no = 13; + tsk->thread.error_code = error_code; + tsk->thread.trap_no = 13; - if (show_unhandled_signals && unhandled_signal(current, SIGSEGV) && - printk_ratelimit()) { + if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) && + printk_ratelimit()) { printk(KERN_INFO - "%s[%d] general protection ip:%lx sp:%lx error:%lx", - current->comm, task_pid_nr(current), - regs->ip, regs->sp, error_code); + "%s[%d] general protection ip:%lx sp:%lx error:%lx", + tsk->comm, task_pid_nr(tsk), + regs->ip, regs->sp, error_code); print_vma_addr(" in ", regs->ip); printk("\n"); } - force_sig(SIGSEGV, current); + force_sig(SIGSEGV, tsk); return; gp_in_vm86: @@ -671,14 +668,15 @@ gp_in_vm86: return; gp_in_kernel: - if (!fixup_exception(regs)) { - current->thread.error_code = error_code; - current->thread.trap_no = 13; - if (notify_die(DIE_GPF, "general protection fault", regs, + if (fixup_exception(regs)) + return; + + tsk->thread.error_code = error_code; + tsk->thread.trap_no = 13; + if (notify_die(DIE_GPF, "general protection fault", regs, error_code, 13, SIGSEGV) == NOTIFY_STOP) - return; - die("general protection fault", regs, error_code); - } + return; + die("general protection fault", regs, error_code); } static notrace __kprobes void @@ -755,9 +753,9 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs) static DEFINE_SPINLOCK(nmi_print_lock); -void notrace __kprobes die_nmi(struct pt_regs *regs, const char *msg) +void notrace __kprobes die_nmi(char *str, struct pt_regs *regs, int do_panic) { - if (notify_die(DIE_NMIWATCHDOG, msg, regs, 0, 2, SIGINT) == NOTIFY_STOP) + if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP) return; spin_lock(&nmi_print_lock); @@ -766,10 +764,12 @@ void notrace __kprobes die_nmi(struct pt_regs *regs, const char *msg) * to get a message out: */ bust_spinlocks(1); - printk(KERN_EMERG "%s", msg); + printk(KERN_EMERG "%s", str); printk(" on CPU%d, ip %08lx, registers:\n", smp_processor_id(), regs->ip); show_registers(regs); + if (do_panic) + panic("Non maskable interrupt"); console_silent(); spin_unlock(&nmi_print_lock); bust_spinlocks(0); @@ -789,14 +789,17 @@ void notrace __kprobes die_nmi(struct pt_regs *regs, const char *msg) static notrace __kprobes void default_do_nmi(struct pt_regs *regs) { unsigned char reason = 0; + int cpu; + + cpu = smp_processor_id(); - /* Only the BSP gets external NMIs from the system: */ - if (!smp_processor_id()) + /* Only the BSP gets external NMIs from the system. */ + if (!cpu) reason = get_nmi_reason(); if (!(reason & 0xc0)) { if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 2, SIGINT) - == NOTIFY_STOP) + == NOTIFY_STOP) return; #ifdef CONFIG_X86_LOCAL_APIC /* @@ -805,7 +808,7 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs) */ if (nmi_watchdog_tick(regs, reason)) return; - if (!do_nmi_callback(regs, smp_processor_id())) + if (!do_nmi_callback(regs, cpu)) unknown_nmi_error(reason, regs); #else unknown_nmi_error(reason, regs); @@ -815,6 +818,8 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs) } if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP) return; + + /* AK: following checks seem to be broken on modern chipsets. FIXME */ if (reason & 0x80) mem_parity_error(reason, regs); if (reason & 0x40) @@ -826,8 +831,6 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs) reassert_nmi(); } -static int ignore_nmis; - notrace __kprobes void do_nmi(struct pt_regs *regs, long error_code) { int cpu; @@ -912,7 +915,7 @@ void __kprobes do_debug(struct pt_regs *regs, long error_code) tsk->thread.debugctlmsr = 0; if (notify_die(DIE_DEBUG, "debug", regs, condition, error_code, - SIGTRAP) == NOTIFY_STOP) + SIGTRAP) == NOTIFY_STOP) return; /* It's safe to allow irq's after DR6 has been saved */ if (regs->flags & X86_EFLAGS_IF) @@ -973,9 +976,8 @@ clear_TF_reenable: void math_error(void __user *ip) { struct task_struct *task; - unsigned short cwd; - unsigned short swd; siginfo_t info; + unsigned short cwd, swd; /* * Save the info for the exception handler and clear the error. @@ -994,7 +996,7 @@ void math_error(void __user *ip) * C1 reg you need in case of a stack fault, 0x040 is the stack * fault bit. We should only be taking one exception at a time, * so if this combination doesn't produce any single exception, - * then we have a bad program that isn't syncronizing its FPU usage + * then we have a bad program that isn't synchronizing its FPU usage * and it will suffer the consequences since we won't be able to * fully reproduce the context of the exception */ @@ -1003,7 +1005,7 @@ void math_error(void __user *ip) switch (swd & ~cwd & 0x3f) { case 0x000: /* No unmasked exception */ return; - default: /* Multiple exceptions */ + default: /* Multiple exceptions */ break; case 0x001: /* Invalid Op */ /* @@ -1039,8 +1041,8 @@ void do_coprocessor_error(struct pt_regs *regs, long error_code) static void simd_math_error(void __user *ip) { struct task_struct *task; - unsigned short mxcsr; siginfo_t info; + unsigned short mxcsr; /* * Save the info for the exception handler and clear the error. @@ -1116,7 +1118,7 @@ void do_spurious_interrupt_bug(struct pt_regs *regs, long error_code) unsigned long patch_espfix_desc(unsigned long uesp, unsigned long kesp) { - struct desc_struct *gdt = __get_cpu_var(gdt_page).gdt; + struct desc_struct *gdt = get_cpu_gdt_table(smp_processor_id()); unsigned long base = (kesp - uesp) & -THREAD_SIZE; unsigned long new_kesp = kesp - base; unsigned long lim_pages = (new_kesp | (THREAD_SIZE - 1)) >> PAGE_SHIFT; @@ -1195,19 +1197,16 @@ void __init trap_init(void) early_iounmap(p, 4); #endif -#ifdef CONFIG_X86_LOCAL_APIC - init_apic_mappings(); -#endif - set_trap_gate(0, ÷_error); - set_intr_gate(1, &debug); - set_intr_gate(2, &nmi); - set_system_intr_gate(3, &int3); /* int3/4 can be called from all */ - set_system_gate(4, &overflow); - set_trap_gate(5, &bounds); - set_trap_gate(6, &invalid_op); - set_trap_gate(7, &device_not_available); - set_task_gate(8, GDT_ENTRY_DOUBLEFAULT_TSS); - set_trap_gate(9, &coprocessor_segment_overrun); + set_trap_gate(0, ÷_error); + set_intr_gate(1, &debug); + set_intr_gate(2, &nmi); + set_system_intr_gate(3, &int3); /* int3 can be called from all */ + set_system_gate(4, &overflow); /* int4 can be called from all */ + set_trap_gate(5, &bounds); + set_trap_gate(6, &invalid_op); + set_trap_gate(7, &device_not_available); + set_task_gate(8, GDT_ENTRY_DOUBLEFAULT_TSS); + set_trap_gate(9, &coprocessor_segment_overrun); set_trap_gate(10, &invalid_TSS); set_trap_gate(11, &segment_not_present); set_trap_gate(12, &stack_segment); diff --git a/arch/x86/kernel/traps_64.c b/arch/x86/kernel/traps_64.c index adff76ea97c4..2696a6837782 100644 --- a/arch/x86/kernel/traps_64.c +++ b/arch/x86/kernel/traps_64.c @@ -10,49 +10,49 @@ * 'Traps.c' handles hardware traps and faults after we have saved some * state in 'entry.S'. */ -#include <linux/sched.h> +#include <linux/moduleparam.h> +#include <linux/interrupt.h> +#include <linux/kallsyms.h> +#include <linux/spinlock.h> +#include <linux/kprobes.h> +#include <linux/uaccess.h> +#include <linux/utsname.h> +#include <linux/kdebug.h> #include <linux/kernel.h> +#include <linux/module.h> +#include <linux/ptrace.h> #include <linux/string.h> +#include <linux/unwind.h> +#include <linux/delay.h> #include <linux/errno.h> -#include <linux/ptrace.h> +#include <linux/kexec.h> +#include <linux/sched.h> #include <linux/timer.h> -#include <linux/mm.h> #include <linux/init.h> -#include <linux/delay.h> -#include <linux/spinlock.h> -#include <linux/interrupt.h> -#include <linux/kallsyms.h> -#include <linux/module.h> -#include <linux/moduleparam.h> -#include <linux/nmi.h> -#include <linux/kprobes.h> -#include <linux/kexec.h> -#include <linux/unwind.h> -#include <linux/uaccess.h> #include <linux/bug.h> -#include <linux/kdebug.h> -#include <linux/utsname.h> - -#include <mach_traps.h> +#include <linux/nmi.h> +#include <linux/mm.h> #if defined(CONFIG_EDAC) #include <linux/edac.h> #endif -#include <asm/system.h> -#include <asm/io.h> -#include <asm/atomic.h> +#include <asm/stacktrace.h> +#include <asm/processor.h> #include <asm/debugreg.h> +#include <asm/atomic.h> +#include <asm/system.h> +#include <asm/unwind.h> #include <asm/desc.h> #include <asm/i387.h> -#include <asm/processor.h> -#include <asm/unwind.h> +#include <asm/nmi.h> #include <asm/smp.h> +#include <asm/io.h> #include <asm/pgalloc.h> -#include <asm/pda.h> #include <asm/proto.h> -#include <asm/nmi.h> -#include <asm/stacktrace.h> +#include <asm/pda.h> + +#include <mach_traps.h> asmlinkage void divide_error(void); asmlinkage void debug(void); @@ -71,12 +71,15 @@ asmlinkage void general_protection(void); asmlinkage void page_fault(void); asmlinkage void coprocessor_error(void); asmlinkage void simd_coprocessor_error(void); -asmlinkage void reserved(void); asmlinkage void alignment_check(void); -asmlinkage void machine_check(void); asmlinkage void spurious_interrupt_bug(void); +asmlinkage void machine_check(void); +int panic_on_unrecovered_nmi; +int kstack_depth_to_print = 12; static unsigned int code_bytes = 64; +static int ignore_nmis; +static int die_counter; static inline void conditional_sti(struct pt_regs *regs) { @@ -100,34 +103,9 @@ static inline void preempt_conditional_cli(struct pt_regs *regs) dec_preempt_count(); } -int kstack_depth_to_print = 12; - void printk_address(unsigned long address, int reliable) { -#ifdef CONFIG_KALLSYMS - unsigned long offset = 0, symsize; - const char *symname; - char *modname; - char *delim = ":"; - char namebuf[KSYM_NAME_LEN]; - char reliab[4] = ""; - - symname = kallsyms_lookup(address, &symsize, &offset, - &modname, namebuf); - if (!symname) { - printk(" [<%016lx>]\n", address); - return; - } - if (!reliable) - strcpy(reliab, "? "); - - if (!modname) - modname = delim = ""; - printk(" [<%016lx>] %s%s%s%s%s+0x%lx/0x%lx\n", - address, reliab, delim, modname, delim, symname, offset, symsize); -#else - printk(" [<%016lx>]\n", address); -#endif + printk(" [<%016lx>] %s%pS\n", address, reliable ? "": "? ", (void *) address); } static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack, @@ -204,8 +182,6 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack, return NULL; } -#define MSG(txt) ops->warning(data, txt) - /* * x86-64 can have up to three kernel stacks: * process stack @@ -232,11 +208,11 @@ struct stack_frame { unsigned long return_address; }; - -static inline unsigned long print_context_stack(struct thread_info *tinfo, - unsigned long *stack, unsigned long bp, - const struct stacktrace_ops *ops, void *data, - unsigned long *end) +static inline unsigned long +print_context_stack(struct thread_info *tinfo, + unsigned long *stack, unsigned long bp, + const struct stacktrace_ops *ops, void *data, + unsigned long *end) { struct stack_frame *frame = (struct stack_frame *)bp; @@ -258,7 +234,7 @@ static inline unsigned long print_context_stack(struct thread_info *tinfo, return bp; } -void dump_trace(struct task_struct *tsk, struct pt_regs *regs, +void dump_trace(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data) { @@ -267,36 +243,34 @@ void dump_trace(struct task_struct *tsk, struct pt_regs *regs, unsigned used = 0; struct thread_info *tinfo; - if (!tsk) - tsk = current; - tinfo = task_thread_info(tsk); + if (!task) + task = current; if (!stack) { unsigned long dummy; stack = &dummy; - if (tsk && tsk != current) - stack = (unsigned long *)tsk->thread.sp; + if (task && task != current) + stack = (unsigned long *)task->thread.sp; } #ifdef CONFIG_FRAME_POINTER if (!bp) { - if (tsk == current) { + if (task == current) { /* Grab bp right from our regs */ - asm("movq %%rbp, %0" : "=r" (bp):); + asm("movq %%rbp, %0" : "=r" (bp) :); } else { /* bp is the last reg pushed by switch_to */ - bp = *(unsigned long *) tsk->thread.sp; + bp = *(unsigned long *) task->thread.sp; } } #endif - - /* * Print function call entries in all stacks, starting at the * current stack address. If the stacks consist of nested * exceptions */ + tinfo = task_thread_info(task); for (;;) { char *id; unsigned long *estack_end; @@ -381,18 +355,17 @@ static const struct stacktrace_ops print_trace_ops = { .address = print_trace_address, }; -void -show_trace(struct task_struct *tsk, struct pt_regs *regs, unsigned long *stack, - unsigned long bp) +void show_trace(struct task_struct *task, struct pt_regs *regs, + unsigned long *stack, unsigned long bp) { printk("\nCall Trace:\n"); - dump_trace(tsk, regs, stack, bp, &print_trace_ops, NULL); + dump_trace(task, regs, stack, bp, &print_trace_ops, NULL); printk("\n"); } static void -_show_stack(struct task_struct *tsk, struct pt_regs *regs, unsigned long *sp, - unsigned long bp) +_show_stack(struct task_struct *task, struct pt_regs *regs, + unsigned long *sp, unsigned long bp) { unsigned long *stack; int i; @@ -404,14 +377,14 @@ _show_stack(struct task_struct *tsk, struct pt_regs *regs, unsigned long *sp, // back trace for this cpu. if (sp == NULL) { - if (tsk) - sp = (unsigned long *)tsk->thread.sp; + if (task) + sp = (unsigned long *)task->thread.sp; else sp = (unsigned long *)&sp; } stack = sp; - for(i=0; i < kstack_depth_to_print; i++) { + for (i = 0; i < kstack_depth_to_print; i++) { if (stack >= irqstack && stack <= irqstack_end) { if (stack == irqstack_end) { stack = (unsigned long *) (irqstack_end[-1]); @@ -426,12 +399,12 @@ _show_stack(struct task_struct *tsk, struct pt_regs *regs, unsigned long *sp, printk(" %016lx", *stack++); touch_nmi_watchdog(); } - show_trace(tsk, regs, sp, bp); + show_trace(task, regs, sp, bp); } -void show_stack(struct task_struct *tsk, unsigned long * sp) +void show_stack(struct task_struct *task, unsigned long *sp) { - _show_stack(tsk, NULL, sp, 0); + _show_stack(task, NULL, sp, 0); } /* @@ -439,8 +412,8 @@ void show_stack(struct task_struct *tsk, unsigned long * sp) */ void dump_stack(void) { - unsigned long dummy; unsigned long bp = 0; + unsigned long stack; #ifdef CONFIG_FRAME_POINTER if (!bp) @@ -452,7 +425,7 @@ void dump_stack(void) init_utsname()->release, (int)strcspn(init_utsname()->version, " "), init_utsname()->version); - show_trace(NULL, NULL, &dummy, bp); + show_trace(NULL, NULL, &stack, bp); } EXPORT_SYMBOL(dump_stack); @@ -463,12 +436,8 @@ void show_registers(struct pt_regs *regs) unsigned long sp; const int cpu = smp_processor_id(); struct task_struct *cur = cpu_pda(cpu)->pcurrent; - u8 *ip; - unsigned int code_prologue = code_bytes * 43 / 64; - unsigned int code_len = code_bytes; sp = regs->sp; - ip = (u8 *) regs->ip - code_prologue; printk("CPU %d ", cpu); __show_regs(regs); printk("Process %s (pid: %d, threadinfo %p, task %p)\n", @@ -479,15 +448,21 @@ void show_registers(struct pt_regs *regs) * time of the fault.. */ if (!user_mode(regs)) { + unsigned int code_prologue = code_bytes * 43 / 64; + unsigned int code_len = code_bytes; unsigned char c; + u8 *ip; + printk("Stack: "); _show_stack(NULL, regs, (unsigned long *)sp, regs->bp); printk("\n"); printk(KERN_EMERG "Code: "); + + ip = (u8 *)regs->ip - code_prologue; if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) { /* try starting at RIP */ - ip = (u8 *) regs->ip; + ip = (u8 *)regs->ip; code_len = code_len - code_prologue + 1; } for (i = 0; i < code_len; i++, ip++) { @@ -503,7 +478,7 @@ void show_registers(struct pt_regs *regs) } } printk("\n"); -} +} int is_valid_bugaddr(unsigned long ip) { @@ -561,10 +536,9 @@ void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr) do_exit(signr); } -int __kprobes __die(const char * str, struct pt_regs * regs, long err) +int __kprobes __die(const char *str, struct pt_regs *regs, long err) { - static int die_counter; - printk(KERN_EMERG "%s: %04lx [%u] ", str, err & 0xffff,++die_counter); + printk(KERN_EMERG "%s: %04lx [%u] ", str, err & 0xffff, ++die_counter); #ifdef CONFIG_PREEMPT printk("PREEMPT "); #endif @@ -575,8 +549,10 @@ int __kprobes __die(const char * str, struct pt_regs * regs, long err) printk("DEBUG_PAGEALLOC"); #endif printk("\n"); - if (notify_die(DIE_OOPS, str, regs, err, current->thread.trap_no, SIGSEGV) == NOTIFY_STOP) + if (notify_die(DIE_OOPS, str, regs, err, + current->thread.trap_no, SIGSEGV) == NOTIFY_STOP) return 1; + show_registers(regs); add_taint(TAINT_DIE); /* Executive summary in case the oops scrolled away */ @@ -588,7 +564,7 @@ int __kprobes __die(const char * str, struct pt_regs * regs, long err) return 0; } -void die(const char * str, struct pt_regs * regs, long err) +void die(const char *str, struct pt_regs *regs, long err) { unsigned long flags = oops_begin(); @@ -605,8 +581,7 @@ die_nmi(char *str, struct pt_regs *regs, int do_panic) { unsigned long flags; - if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == - NOTIFY_STOP) + if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP) return; flags = oops_begin(); @@ -614,7 +589,9 @@ die_nmi(char *str, struct pt_regs *regs, int do_panic) * We are in trouble anyway, lets at least try * to get a message out. */ - printk(str, smp_processor_id()); + printk(KERN_EMERG "%s", str); + printk(" on CPU%d, ip %08lx, registers:\n", + smp_processor_id(), regs->ip); show_registers(regs); if (kexec_should_crash(current)) crash_kexec(regs); @@ -626,44 +603,44 @@ die_nmi(char *str, struct pt_regs *regs, int do_panic) do_exit(SIGBUS); } -static void __kprobes do_trap(int trapnr, int signr, char *str, - struct pt_regs * regs, long error_code, - siginfo_t *info) +static void __kprobes +do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, + long error_code, siginfo_t *info) { struct task_struct *tsk = current; - if (user_mode(regs)) { - /* - * We want error_code and trap_no set for userspace - * faults and kernelspace faults which result in - * die(), but not kernelspace faults which are fixed - * up. die() gives the process no chance to handle - * the signal and notice the kernel fault information, - * so that won't result in polluting the information - * about previously queued, but not yet delivered, - * faults. See also do_general_protection below. - */ - tsk->thread.error_code = error_code; - tsk->thread.trap_no = trapnr; - - if (show_unhandled_signals && unhandled_signal(tsk, signr) && - printk_ratelimit()) { - printk(KERN_INFO - "%s[%d] trap %s ip:%lx sp:%lx error:%lx", - tsk->comm, tsk->pid, str, - regs->ip, regs->sp, error_code); - print_vma_addr(" in ", regs->ip); - printk("\n"); - } + if (!user_mode(regs)) + goto kernel_trap; - if (info) - force_sig_info(signr, info, tsk); - else - force_sig(signr, tsk); - return; + /* + * We want error_code and trap_no set for userspace faults and + * kernelspace faults which result in die(), but not + * kernelspace faults which are fixed up. die() gives the + * process no chance to handle the signal and notice the + * kernel fault information, so that won't result in polluting + * the information about previously queued, but not yet + * delivered, faults. See also do_general_protection below. + */ + tsk->thread.error_code = error_code; + tsk->thread.trap_no = trapnr; + + if (show_unhandled_signals && unhandled_signal(tsk, signr) && + printk_ratelimit()) { + printk(KERN_INFO + "%s[%d] trap %s ip:%lx sp:%lx error:%lx", + tsk->comm, tsk->pid, str, + regs->ip, regs->sp, error_code); + print_vma_addr(" in ", regs->ip); + printk("\n"); } + if (info) + force_sig_info(signr, info, tsk); + else + force_sig(signr, tsk); + return; +kernel_trap: if (!fixup_exception(regs)) { tsk->thread.error_code = error_code; tsk->thread.trap_no = trapnr; @@ -673,41 +650,39 @@ static void __kprobes do_trap(int trapnr, int signr, char *str, } #define DO_ERROR(trapnr, signr, str, name) \ -asmlinkage void do_##name(struct pt_regs * regs, long error_code) \ -{ \ - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ - return; \ +asmlinkage void do_##name(struct pt_regs * regs, long error_code) \ +{ \ + if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ + == NOTIFY_STOP) \ + return; \ conditional_sti(regs); \ - do_trap(trapnr, signr, str, regs, error_code, NULL); \ + do_trap(trapnr, signr, str, regs, error_code, NULL); \ } -#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ -asmlinkage void do_##name(struct pt_regs * regs, long error_code) \ -{ \ - siginfo_t info; \ - info.si_signo = signr; \ - info.si_errno = 0; \ - info.si_code = sicode; \ - info.si_addr = (void __user *)siaddr; \ - trace_hardirqs_fixup(); \ - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ - return; \ +#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ +asmlinkage void do_##name(struct pt_regs * regs, long error_code) \ +{ \ + siginfo_t info; \ + info.si_signo = signr; \ + info.si_errno = 0; \ + info.si_code = sicode; \ + info.si_addr = (void __user *)siaddr; \ + trace_hardirqs_fixup(); \ + if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ + == NOTIFY_STOP) \ + return; \ conditional_sti(regs); \ - do_trap(trapnr, signr, str, regs, error_code, &info); \ + do_trap(trapnr, signr, str, regs, error_code, &info); \ } -DO_ERROR_INFO( 0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->ip) -DO_ERROR( 4, SIGSEGV, "overflow", overflow) -DO_ERROR( 5, SIGSEGV, "bounds", bounds) -DO_ERROR_INFO( 6, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, regs->ip) -DO_ERROR( 7, SIGSEGV, "device not available", device_not_available) -DO_ERROR( 9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun) +DO_ERROR_INFO(0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->ip) +DO_ERROR(4, SIGSEGV, "overflow", overflow) +DO_ERROR(5, SIGSEGV, "bounds", bounds) +DO_ERROR_INFO(6, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, regs->ip) +DO_ERROR(9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun) DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS) -DO_ERROR(11, SIGBUS, "segment not present", segment_not_present) +DO_ERROR(11, SIGBUS, "segment not present", segment_not_present) DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0) -DO_ERROR(18, SIGSEGV, "reserved", reserved) /* Runs on IST stack */ asmlinkage void do_stack_segment(struct pt_regs *regs, long error_code) @@ -737,31 +712,34 @@ asmlinkage void do_double_fault(struct pt_regs * regs, long error_code) die(str, regs, error_code); } -asmlinkage void __kprobes do_general_protection(struct pt_regs * regs, - long error_code) +asmlinkage void __kprobes +do_general_protection(struct pt_regs *regs, long error_code) { - struct task_struct *tsk = current; + struct task_struct *tsk; conditional_sti(regs); - if (user_mode(regs)) { - tsk->thread.error_code = error_code; - tsk->thread.trap_no = 13; - - if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) && - printk_ratelimit()) { - printk(KERN_INFO - "%s[%d] general protection ip:%lx sp:%lx error:%lx", - tsk->comm, tsk->pid, - regs->ip, regs->sp, error_code); - print_vma_addr(" in ", regs->ip); - printk("\n"); - } + tsk = current; + if (!user_mode(regs)) + goto gp_in_kernel; - force_sig(SIGSEGV, tsk); - return; - } + tsk->thread.error_code = error_code; + tsk->thread.trap_no = 13; + + if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) && + printk_ratelimit()) { + printk(KERN_INFO + "%s[%d] general protection ip:%lx sp:%lx error:%lx", + tsk->comm, tsk->pid, + regs->ip, regs->sp, error_code); + print_vma_addr(" in ", regs->ip); + printk("\n"); + } + force_sig(SIGSEGV, tsk); + return; + +gp_in_kernel: if (fixup_exception(regs)) return; @@ -774,14 +752,14 @@ asmlinkage void __kprobes do_general_protection(struct pt_regs * regs, } static notrace __kprobes void -mem_parity_error(unsigned char reason, struct pt_regs * regs) +mem_parity_error(unsigned char reason, struct pt_regs *regs) { printk(KERN_EMERG "Uhhuh. NMI received for unknown reason %02x.\n", reason); printk(KERN_EMERG "You have some hardware problem, likely on the PCI bus.\n"); #if defined(CONFIG_EDAC) - if(edac_handler_set()) { + if (edac_handler_set()) { edac_atomic_assert_error(); return; } @@ -798,7 +776,7 @@ mem_parity_error(unsigned char reason, struct pt_regs * regs) } static notrace __kprobes void -io_check_error(unsigned char reason, struct pt_regs * regs) +io_check_error(unsigned char reason, struct pt_regs *regs) { printk("NMI: IOCK error (debug interrupt?)\n"); show_registers(regs); @@ -828,14 +806,14 @@ unknown_nmi_error(unsigned char reason, struct pt_regs * regs) /* Runs on IST stack. This code must keep interrupts off all the time. Nested NMIs are prevented by the CPU. */ -asmlinkage notrace __kprobes void default_do_nmi(struct pt_regs *regs) +asmlinkage notrace __kprobes void default_do_nmi(struct pt_regs *regs) { unsigned char reason = 0; int cpu; cpu = smp_processor_id(); - /* Only the BSP gets external NMIs from the system. */ + /* Only the BSP gets external NMIs from the system. */ if (!cpu) reason = get_nmi_reason(); @@ -847,32 +825,57 @@ asmlinkage notrace __kprobes void default_do_nmi(struct pt_regs *regs) * Ok, so this is none of the documented NMI sources, * so it must be the NMI watchdog. */ - if (nmi_watchdog_tick(regs,reason)) + if (nmi_watchdog_tick(regs, reason)) return; - if (!do_nmi_callback(regs,cpu)) + if (!do_nmi_callback(regs, cpu)) unknown_nmi_error(reason, regs); return; } if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP) - return; + return; /* AK: following checks seem to be broken on modern chipsets. FIXME */ - if (reason & 0x80) mem_parity_error(reason, regs); if (reason & 0x40) io_check_error(reason, regs); } +asmlinkage notrace __kprobes void +do_nmi(struct pt_regs *regs, long error_code) +{ + nmi_enter(); + + add_pda(__nmi_count, 1); + + if (!ignore_nmis) + default_do_nmi(regs); + + nmi_exit(); +} + +void stop_nmi(void) +{ + acpi_nmi_disable(); + ignore_nmis++; +} + +void restart_nmi(void) +{ + ignore_nmis--; + acpi_nmi_enable(); +} + /* runs on IST stack. */ -asmlinkage void __kprobes do_int3(struct pt_regs * regs, long error_code) +asmlinkage void __kprobes do_int3(struct pt_regs *regs, long error_code) { trace_hardirqs_fixup(); - if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) == NOTIFY_STOP) { + if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) + == NOTIFY_STOP) return; - } + preempt_conditional_sti(regs); do_trap(3, SIGTRAP, "int3", regs, error_code, NULL); preempt_conditional_cli(regs); @@ -903,8 +906,8 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) asmlinkage void __kprobes do_debug(struct pt_regs * regs, unsigned long error_code) { - unsigned long condition; struct task_struct *tsk = current; + unsigned long condition; siginfo_t info; trace_hardirqs_fixup(); @@ -925,21 +928,19 @@ asmlinkage void __kprobes do_debug(struct pt_regs * regs, /* Mask out spurious debug traps due to lazy DR7 setting */ if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) { - if (!tsk->thread.debugreg7) { + if (!tsk->thread.debugreg7) goto clear_dr7; - } } tsk->thread.debugreg6 = condition; - /* * Single-stepping through TF: make sure we ignore any events in * kernel space (but re-enable TF when returning to user mode). */ if (condition & DR_STEP) { - if (!user_mode(regs)) - goto clear_TF_reenable; + if (!user_mode(regs)) + goto clear_TF_reenable; } /* Ok, finally something we can handle */ @@ -952,7 +953,7 @@ asmlinkage void __kprobes do_debug(struct pt_regs * regs, force_sig_info(SIGTRAP, &info, tsk); clear_dr7: - set_debugreg(0UL, 7); + set_debugreg(0, 7); preempt_conditional_cli(regs); return; @@ -960,6 +961,7 @@ clear_TF_reenable: set_tsk_thread_flag(tsk, TIF_SINGLESTEP); regs->flags &= ~X86_EFLAGS_TF; preempt_conditional_cli(regs); + return; } static int kernel_math_error(struct pt_regs *regs, const char *str, int trapnr) @@ -982,7 +984,7 @@ static int kernel_math_error(struct pt_regs *regs, const char *str, int trapnr) asmlinkage void do_coprocessor_error(struct pt_regs *regs) { void __user *ip = (void __user *)(regs->ip); - struct task_struct * task; + struct task_struct *task; siginfo_t info; unsigned short cwd, swd; @@ -1015,30 +1017,30 @@ asmlinkage void do_coprocessor_error(struct pt_regs *regs) cwd = get_fpu_cwd(task); swd = get_fpu_swd(task); switch (swd & ~cwd & 0x3f) { - case 0x000: - default: - break; - case 0x001: /* Invalid Op */ - /* - * swd & 0x240 == 0x040: Stack Underflow - * swd & 0x240 == 0x240: Stack Overflow - * User must clear the SF bit (0x40) if set - */ - info.si_code = FPE_FLTINV; - break; - case 0x002: /* Denormalize */ - case 0x010: /* Underflow */ - info.si_code = FPE_FLTUND; - break; - case 0x004: /* Zero Divide */ - info.si_code = FPE_FLTDIV; - break; - case 0x008: /* Overflow */ - info.si_code = FPE_FLTOVF; - break; - case 0x020: /* Precision */ - info.si_code = FPE_FLTRES; - break; + case 0x000: /* No unmasked exception */ + default: /* Multiple exceptions */ + break; + case 0x001: /* Invalid Op */ + /* + * swd & 0x240 == 0x040: Stack Underflow + * swd & 0x240 == 0x240: Stack Overflow + * User must clear the SF bit (0x40) if set + */ + info.si_code = FPE_FLTINV; + break; + case 0x002: /* Denormalize */ + case 0x010: /* Underflow */ + info.si_code = FPE_FLTUND; + break; + case 0x004: /* Zero Divide */ + info.si_code = FPE_FLTDIV; + break; + case 0x008: /* Overflow */ + info.si_code = FPE_FLTOVF; + break; + case 0x020: /* Precision */ + info.si_code = FPE_FLTRES; + break; } force_sig_info(SIGFPE, &info, task); } @@ -1051,7 +1053,7 @@ asmlinkage void bad_intr(void) asmlinkage void do_simd_coprocessor_error(struct pt_regs *regs) { void __user *ip = (void __user *)(regs->ip); - struct task_struct * task; + struct task_struct *task; siginfo_t info; unsigned short mxcsr; @@ -1079,25 +1081,25 @@ asmlinkage void do_simd_coprocessor_error(struct pt_regs *regs) */ mxcsr = get_fpu_mxcsr(task); switch (~((mxcsr & 0x1f80) >> 7) & (mxcsr & 0x3f)) { - case 0x000: - default: - break; - case 0x001: /* Invalid Op */ - info.si_code = FPE_FLTINV; - break; - case 0x002: /* Denormalize */ - case 0x010: /* Underflow */ - info.si_code = FPE_FLTUND; - break; - case 0x004: /* Zero Divide */ - info.si_code = FPE_FLTDIV; - break; - case 0x008: /* Overflow */ - info.si_code = FPE_FLTOVF; - break; - case 0x020: /* Precision */ - info.si_code = FPE_FLTRES; - break; + case 0x000: + default: + break; + case 0x001: /* Invalid Op */ + info.si_code = FPE_FLTINV; + break; + case 0x002: /* Denormalize */ + case 0x010: /* Underflow */ + info.si_code = FPE_FLTUND; + break; + case 0x004: /* Zero Divide */ + info.si_code = FPE_FLTDIV; + break; + case 0x008: /* Overflow */ + info.si_code = FPE_FLTOVF; + break; + case 0x020: /* Precision */ + info.si_code = FPE_FLTRES; + break; } force_sig_info(SIGFPE, &info, task); } @@ -1115,7 +1117,7 @@ asmlinkage void __attribute__((weak)) mce_threshold_interrupt(void) } /* - * 'math_state_restore()' saves the current math information in the + * 'math_state_restore()' saves the current math information in the * old math state array, and gets the new ones from the current task * * Careful.. There are problems with IBM-designed IRQ13 behaviour. @@ -1140,7 +1142,7 @@ asmlinkage void math_state_restore(void) local_irq_disable(); } - clts(); /* Allow maths ops (or we recurse) */ + clts(); /* Allow maths ops (or we recurse) */ restore_fpu_checking(&me->thread.xstate->fxsave); task_thread_info(me)->status |= TS_USEDFPU; me->fpu_counter++; @@ -1149,64 +1151,61 @@ EXPORT_SYMBOL_GPL(math_state_restore); void __init trap_init(void) { - set_intr_gate(0,÷_error); - set_intr_gate_ist(1,&debug,DEBUG_STACK); - set_intr_gate_ist(2,&nmi,NMI_STACK); - set_system_gate_ist(3,&int3,DEBUG_STACK); /* int3 can be called from all */ - set_system_gate(4,&overflow); /* int4 can be called from all */ - set_intr_gate(5,&bounds); - set_intr_gate(6,&invalid_op); - set_intr_gate(7,&device_not_available); - set_intr_gate_ist(8,&double_fault, DOUBLEFAULT_STACK); - set_intr_gate(9,&coprocessor_segment_overrun); - set_intr_gate(10,&invalid_TSS); - set_intr_gate(11,&segment_not_present); - set_intr_gate_ist(12,&stack_segment,STACKFAULT_STACK); - set_intr_gate(13,&general_protection); - set_intr_gate(14,&page_fault); - set_intr_gate(15,&spurious_interrupt_bug); - set_intr_gate(16,&coprocessor_error); - set_intr_gate(17,&alignment_check); + set_intr_gate(0, ÷_error); + set_intr_gate_ist(1, &debug, DEBUG_STACK); + set_intr_gate_ist(2, &nmi, NMI_STACK); + set_system_gate_ist(3, &int3, DEBUG_STACK); /* int3 can be called from all */ + set_system_gate(4, &overflow); /* int4 can be called from all */ + set_intr_gate(5, &bounds); + set_intr_gate(6, &invalid_op); + set_intr_gate(7, &device_not_available); + set_intr_gate_ist(8, &double_fault, DOUBLEFAULT_STACK); + set_intr_gate(9, &coprocessor_segment_overrun); + set_intr_gate(10, &invalid_TSS); + set_intr_gate(11, &segment_not_present); + set_intr_gate_ist(12, &stack_segment, STACKFAULT_STACK); + set_intr_gate(13, &general_protection); + set_intr_gate(14, &page_fault); + set_intr_gate(15, &spurious_interrupt_bug); + set_intr_gate(16, &coprocessor_error); + set_intr_gate(17, &alignment_check); #ifdef CONFIG_X86_MCE - set_intr_gate_ist(18,&machine_check, MCE_STACK); + set_intr_gate_ist(18, &machine_check, MCE_STACK); #endif - set_intr_gate(19,&simd_coprocessor_error); + set_intr_gate(19, &simd_coprocessor_error); #ifdef CONFIG_IA32_EMULATION set_system_gate(IA32_SYSCALL_VECTOR, ia32_syscall); #endif - /* * initialize the per thread extended state: */ - init_thread_xstate(); + init_thread_xstate(); /* - * Should be a barrier for any external CPU state. + * Should be a barrier for any external CPU state: */ cpu_init(); } - static int __init oops_setup(char *s) -{ +{ if (!s) return -EINVAL; if (!strcmp(s, "panic")) panic_on_oops = 1; return 0; -} +} early_param("oops", oops_setup); static int __init kstack_setup(char *s) { if (!s) return -EINVAL; - kstack_depth_to_print = simple_strtoul(s,NULL,0); + kstack_depth_to_print = simple_strtoul(s, NULL, 0); return 0; } early_param("kstack", kstack_setup); - static int __init code_bytes_setup(char *s) { code_bytes = simple_strtoul(s, NULL, 0); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c new file mode 100644 index 000000000000..7603c0553909 --- /dev/null +++ b/arch/x86/kernel/tsc.c @@ -0,0 +1,535 @@ +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/timer.h> +#include <linux/acpi_pmtmr.h> +#include <linux/cpufreq.h> +#include <linux/dmi.h> +#include <linux/delay.h> +#include <linux/clocksource.h> +#include <linux/percpu.h> + +#include <asm/hpet.h> +#include <asm/timer.h> +#include <asm/vgtod.h> +#include <asm/time.h> +#include <asm/delay.h> + +unsigned int cpu_khz; /* TSC clocks / usec, not used here */ +EXPORT_SYMBOL(cpu_khz); +unsigned int tsc_khz; +EXPORT_SYMBOL(tsc_khz); + +/* + * TSC can be unstable due to cpufreq or due to unsynced TSCs + */ +static int tsc_unstable; + +/* native_sched_clock() is called before tsc_init(), so + we must start with the TSC soft disabled to prevent + erroneous rdtsc usage on !cpu_has_tsc processors */ +static int tsc_disabled = -1; + +/* + * Scheduler clock - returns current time in nanosec units. + */ +u64 native_sched_clock(void) +{ + u64 this_offset; + + /* + * Fall back to jiffies if there's no TSC available: + * ( But note that we still use it if the TSC is marked + * unstable. We do this because unlike Time Of Day, + * the scheduler clock tolerates small errors and it's + * very important for it to be as fast as the platform + * can achive it. ) + */ + if (unlikely(tsc_disabled)) { + /* No locking but a rare wrong value is not a big deal: */ + return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ); + } + + /* read the Time Stamp Counter: */ + rdtscll(this_offset); + + /* return the value in ns */ + return cycles_2_ns(this_offset); +} + +/* We need to define a real function for sched_clock, to override the + weak default version */ +#ifdef CONFIG_PARAVIRT +unsigned long long sched_clock(void) +{ + return paravirt_sched_clock(); +} +#else +unsigned long long +sched_clock(void) __attribute__((alias("native_sched_clock"))); +#endif + +int check_tsc_unstable(void) +{ + return tsc_unstable; +} +EXPORT_SYMBOL_GPL(check_tsc_unstable); + +#ifdef CONFIG_X86_TSC +int __init notsc_setup(char *str) +{ + printk(KERN_WARNING "notsc: Kernel compiled with CONFIG_X86_TSC, " + "cannot disable TSC completely.\n"); + tsc_disabled = 1; + return 1; +} +#else +/* + * disable flag for tsc. Takes effect by clearing the TSC cpu flag + * in cpu/common.c + */ +int __init notsc_setup(char *str) +{ + setup_clear_cpu_cap(X86_FEATURE_TSC); + return 1; +} +#endif + +__setup("notsc", notsc_setup); + +#define MAX_RETRIES 5 +#define SMI_TRESHOLD 50000 + +/* + * Read TSC and the reference counters. Take care of SMI disturbance + */ +static u64 __init tsc_read_refs(u64 *pm, u64 *hpet) +{ + u64 t1, t2; + int i; + + for (i = 0; i < MAX_RETRIES; i++) { + t1 = get_cycles(); + if (hpet) + *hpet = hpet_readl(HPET_COUNTER) & 0xFFFFFFFF; + else + *pm = acpi_pm_read_early(); + t2 = get_cycles(); + if ((t2 - t1) < SMI_TRESHOLD) + return t2; + } + return ULLONG_MAX; +} + +/** + * native_calibrate_tsc - calibrate the tsc on boot + */ +unsigned long native_calibrate_tsc(void) +{ + unsigned long flags; + u64 tsc1, tsc2, tr1, tr2, delta, pm1, pm2, hpet1, hpet2; + int hpet = is_hpet_enabled(); + unsigned int tsc_khz_val = 0; + + local_irq_save(flags); + + tsc1 = tsc_read_refs(&pm1, hpet ? &hpet1 : NULL); + + outb((inb(0x61) & ~0x02) | 0x01, 0x61); + + outb(0xb0, 0x43); + outb((CLOCK_TICK_RATE / (1000 / 50)) & 0xff, 0x42); + outb((CLOCK_TICK_RATE / (1000 / 50)) >> 8, 0x42); + tr1 = get_cycles(); + while ((inb(0x61) & 0x20) == 0); + tr2 = get_cycles(); + + tsc2 = tsc_read_refs(&pm2, hpet ? &hpet2 : NULL); + + local_irq_restore(flags); + + /* + * Preset the result with the raw and inaccurate PIT + * calibration value + */ + delta = (tr2 - tr1); + do_div(delta, 50); + tsc_khz_val = delta; + + /* hpet or pmtimer available ? */ + if (!hpet && !pm1 && !pm2) { + printk(KERN_INFO "TSC calibrated against PIT\n"); + goto out; + } + + /* Check, whether the sampling was disturbed by an SMI */ + if (tsc1 == ULLONG_MAX || tsc2 == ULLONG_MAX) { + printk(KERN_WARNING "TSC calibration disturbed by SMI, " + "using PIT calibration result\n"); + goto out; + } + + tsc2 = (tsc2 - tsc1) * 1000000LL; + + if (hpet) { + printk(KERN_INFO "TSC calibrated against HPET\n"); + if (hpet2 < hpet1) + hpet2 += 0x100000000ULL; + hpet2 -= hpet1; + tsc1 = ((u64)hpet2 * hpet_readl(HPET_PERIOD)); + do_div(tsc1, 1000000); + } else { + printk(KERN_INFO "TSC calibrated against PM_TIMER\n"); + if (pm2 < pm1) + pm2 += (u64)ACPI_PM_OVRRUN; + pm2 -= pm1; + tsc1 = pm2 * 1000000000LL; + do_div(tsc1, PMTMR_TICKS_PER_SEC); + } + + do_div(tsc2, tsc1); + tsc_khz_val = tsc2; + +out: + return tsc_khz_val; +} + + +#ifdef CONFIG_X86_32 +/* Only called from the Powernow K7 cpu freq driver */ +int recalibrate_cpu_khz(void) +{ +#ifndef CONFIG_SMP + unsigned long cpu_khz_old = cpu_khz; + + if (cpu_has_tsc) { + tsc_khz = calibrate_tsc(); + cpu_khz = tsc_khz; + cpu_data(0).loops_per_jiffy = + cpufreq_scale(cpu_data(0).loops_per_jiffy, + cpu_khz_old, cpu_khz); + return 0; + } else + return -ENODEV; +#else + return -ENODEV; +#endif +} + +EXPORT_SYMBOL(recalibrate_cpu_khz); + +#endif /* CONFIG_X86_32 */ + +/* Accelerators for sched_clock() + * convert from cycles(64bits) => nanoseconds (64bits) + * basic equation: + * ns = cycles / (freq / ns_per_sec) + * ns = cycles * (ns_per_sec / freq) + * ns = cycles * (10^9 / (cpu_khz * 10^3)) + * ns = cycles * (10^6 / cpu_khz) + * + * Then we use scaling math (suggested by george@mvista.com) to get: + * ns = cycles * (10^6 * SC / cpu_khz) / SC + * ns = cycles * cyc2ns_scale / SC + * + * And since SC is a constant power of two, we can convert the div + * into a shift. + * + * We can use khz divisor instead of mhz to keep a better precision, since + * cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits. + * (mathieu.desnoyers@polymtl.ca) + * + * -johnstul@us.ibm.com "math is hard, lets go shopping!" + */ + +DEFINE_PER_CPU(unsigned long, cyc2ns); + +static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) +{ + unsigned long long tsc_now, ns_now; + unsigned long flags, *scale; + + local_irq_save(flags); + sched_clock_idle_sleep_event(); + + scale = &per_cpu(cyc2ns, cpu); + + rdtscll(tsc_now); + ns_now = __cycles_2_ns(tsc_now); + + if (cpu_khz) + *scale = (NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR)/cpu_khz; + + sched_clock_idle_wakeup_event(0); + local_irq_restore(flags); +} + +#ifdef CONFIG_CPU_FREQ + +/* Frequency scaling support. Adjust the TSC based timer when the cpu frequency + * changes. + * + * RED-PEN: On SMP we assume all CPUs run with the same frequency. It's + * not that important because current Opteron setups do not support + * scaling on SMP anyroads. + * + * Should fix up last_tsc too. Currently gettimeofday in the + * first tick after the change will be slightly wrong. + */ + +static unsigned int ref_freq; +static unsigned long loops_per_jiffy_ref; +static unsigned long tsc_khz_ref; + +static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct cpufreq_freqs *freq = data; + unsigned long *lpj, dummy; + + if (cpu_has(&cpu_data(freq->cpu), X86_FEATURE_CONSTANT_TSC)) + return 0; + + lpj = &dummy; + if (!(freq->flags & CPUFREQ_CONST_LOOPS)) +#ifdef CONFIG_SMP + lpj = &cpu_data(freq->cpu).loops_per_jiffy; +#else + lpj = &boot_cpu_data.loops_per_jiffy; +#endif + + if (!ref_freq) { + ref_freq = freq->old; + loops_per_jiffy_ref = *lpj; + tsc_khz_ref = tsc_khz; + } + if ((val == CPUFREQ_PRECHANGE && freq->old < freq->new) || + (val == CPUFREQ_POSTCHANGE && freq->old > freq->new) || + (val == CPUFREQ_RESUMECHANGE)) { + *lpj = cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new); + + tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new); + if (!(freq->flags & CPUFREQ_CONST_LOOPS)) + mark_tsc_unstable("cpufreq changes"); + } + + set_cyc2ns_scale(tsc_khz_ref, freq->cpu); + + return 0; +} + +static struct notifier_block time_cpufreq_notifier_block = { + .notifier_call = time_cpufreq_notifier +}; + +static int __init cpufreq_tsc(void) +{ + cpufreq_register_notifier(&time_cpufreq_notifier_block, + CPUFREQ_TRANSITION_NOTIFIER); + return 0; +} + +core_initcall(cpufreq_tsc); + +#endif /* CONFIG_CPU_FREQ */ + +/* clocksource code */ + +static struct clocksource clocksource_tsc; + +/* + * We compare the TSC to the cycle_last value in the clocksource + * structure to avoid a nasty time-warp. This can be observed in a + * very small window right after one CPU updated cycle_last under + * xtime/vsyscall_gtod lock and the other CPU reads a TSC value which + * is smaller than the cycle_last reference value due to a TSC which + * is slighty behind. This delta is nowhere else observable, but in + * that case it results in a forward time jump in the range of hours + * due to the unsigned delta calculation of the time keeping core + * code, which is necessary to support wrapping clocksources like pm + * timer. + */ +static cycle_t read_tsc(void) +{ + cycle_t ret = (cycle_t)get_cycles(); + + return ret >= clocksource_tsc.cycle_last ? + ret : clocksource_tsc.cycle_last; +} + +#ifdef CONFIG_X86_64 +static cycle_t __vsyscall_fn vread_tsc(void) +{ + cycle_t ret = (cycle_t)vget_cycles(); + + return ret >= __vsyscall_gtod_data.clock.cycle_last ? + ret : __vsyscall_gtod_data.clock.cycle_last; +} +#endif + +static struct clocksource clocksource_tsc = { + .name = "tsc", + .rating = 300, + .read = read_tsc, + .mask = CLOCKSOURCE_MASK(64), + .shift = 22, + .flags = CLOCK_SOURCE_IS_CONTINUOUS | + CLOCK_SOURCE_MUST_VERIFY, +#ifdef CONFIG_X86_64 + .vread = vread_tsc, +#endif +}; + +void mark_tsc_unstable(char *reason) +{ + if (!tsc_unstable) { + tsc_unstable = 1; + printk("Marking TSC unstable due to %s\n", reason); + /* Change only the rating, when not registered */ + if (clocksource_tsc.mult) + clocksource_change_rating(&clocksource_tsc, 0); + else + clocksource_tsc.rating = 0; + } +} + +EXPORT_SYMBOL_GPL(mark_tsc_unstable); + +static int __init dmi_mark_tsc_unstable(const struct dmi_system_id *d) +{ + printk(KERN_NOTICE "%s detected: marking TSC unstable.\n", + d->ident); + tsc_unstable = 1; + return 0; +} + +/* List of systems that have known TSC problems */ +static struct dmi_system_id __initdata bad_tsc_dmi_table[] = { + { + .callback = dmi_mark_tsc_unstable, + .ident = "IBM Thinkpad 380XD", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "IBM"), + DMI_MATCH(DMI_BOARD_NAME, "2635FA0"), + }, + }, + {} +}; + +/* + * Geode_LX - the OLPC CPU has a possibly a very reliable TSC + */ +#ifdef CONFIG_MGEODE_LX +/* RTSC counts during suspend */ +#define RTSC_SUSP 0x100 + +static void __init check_geode_tsc_reliable(void) +{ + unsigned long res_low, res_high; + + rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high); + if (res_low & RTSC_SUSP) + clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY; +} +#else +static inline void check_geode_tsc_reliable(void) { } +#endif + +/* + * Make an educated guess if the TSC is trustworthy and synchronized + * over all CPUs. + */ +__cpuinit int unsynchronized_tsc(void) +{ + if (!cpu_has_tsc || tsc_unstable) + return 1; + +#ifdef CONFIG_SMP + if (apic_is_clustered_box()) + return 1; +#endif + + if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) + return 0; + /* + * Intel systems are normally all synchronized. + * Exceptions must mark TSC as unstable: + */ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) { + /* assume multi socket systems are not synchronized: */ + if (num_possible_cpus() > 1) + tsc_unstable = 1; + } + + return tsc_unstable; +} + +static void __init init_tsc_clocksource(void) +{ + clocksource_tsc.mult = clocksource_khz2mult(tsc_khz, + clocksource_tsc.shift); + /* lower the rating if we already know its unstable: */ + if (check_tsc_unstable()) { + clocksource_tsc.rating = 0; + clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS; + } + clocksource_register(&clocksource_tsc); +} + +void __init tsc_init(void) +{ + u64 lpj; + int cpu; + + if (!cpu_has_tsc) + return; + + tsc_khz = calibrate_tsc(); + cpu_khz = tsc_khz; + + if (!tsc_khz) { + mark_tsc_unstable("could not calculate TSC khz"); + return; + } + +#ifdef CONFIG_X86_64 + if (cpu_has(&boot_cpu_data, X86_FEATURE_CONSTANT_TSC) && + (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)) + cpu_khz = calibrate_cpu(); +#endif + + lpj = ((u64)tsc_khz * 1000); + do_div(lpj, HZ); + lpj_fine = lpj; + + printk("Detected %lu.%03lu MHz processor.\n", + (unsigned long)cpu_khz / 1000, + (unsigned long)cpu_khz % 1000); + + /* + * Secondary CPUs do not run through tsc_init(), so set up + * all the scale factors for all CPUs, assuming the same + * speed as the bootup CPU. (cpufreq notifiers will fix this + * up if their speed diverges) + */ + for_each_possible_cpu(cpu) + set_cyc2ns_scale(cpu_khz, cpu); + + if (tsc_disabled > 0) + return; + + /* now allow native_sched_clock() to use rdtsc */ + tsc_disabled = 0; + + use_tsc_delay(); + /* Check and install the TSC clocksource */ + dmi_check_system(bad_tsc_dmi_table); + + if (unsynchronized_tsc()) + mark_tsc_unstable("TSCs unsynchronized"); + + check_geode_tsc_reliable(); + init_tsc_clocksource(); +} + diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c deleted file mode 100644 index 068759db63dd..000000000000 --- a/arch/x86/kernel/tsc_32.c +++ /dev/null @@ -1,453 +0,0 @@ -#include <linux/sched.h> -#include <linux/clocksource.h> -#include <linux/workqueue.h> -#include <linux/cpufreq.h> -#include <linux/jiffies.h> -#include <linux/init.h> -#include <linux/dmi.h> -#include <linux/percpu.h> - -#include <asm/delay.h> -#include <asm/tsc.h> -#include <asm/io.h> -#include <asm/timer.h> - -#include "mach_timer.h" - -static int tsc_disabled; - -/* - * On some systems the TSC frequency does not - * change with the cpu frequency. So we need - * an extra value to store the TSC freq - */ -unsigned int tsc_khz; -EXPORT_SYMBOL_GPL(tsc_khz); - -#ifdef CONFIG_X86_TSC -static int __init tsc_setup(char *str) -{ - printk(KERN_WARNING "notsc: Kernel compiled with CONFIG_X86_TSC, " - "cannot disable TSC completely.\n"); - tsc_disabled = 1; - return 1; -} -#else -/* - * disable flag for tsc. Takes effect by clearing the TSC cpu flag - * in cpu/common.c - */ -static int __init tsc_setup(char *str) -{ - setup_clear_cpu_cap(X86_FEATURE_TSC); - return 1; -} -#endif - -__setup("notsc", tsc_setup); - -/* - * code to mark and check if the TSC is unstable - * due to cpufreq or due to unsynced TSCs - */ -static int tsc_unstable; - -int check_tsc_unstable(void) -{ - return tsc_unstable; -} -EXPORT_SYMBOL_GPL(check_tsc_unstable); - -/* Accelerators for sched_clock() - * convert from cycles(64bits) => nanoseconds (64bits) - * basic equation: - * ns = cycles / (freq / ns_per_sec) - * ns = cycles * (ns_per_sec / freq) - * ns = cycles * (10^9 / (cpu_khz * 10^3)) - * ns = cycles * (10^6 / cpu_khz) - * - * Then we use scaling math (suggested by george@mvista.com) to get: - * ns = cycles * (10^6 * SC / cpu_khz) / SC - * ns = cycles * cyc2ns_scale / SC - * - * And since SC is a constant power of two, we can convert the div - * into a shift. - * - * We can use khz divisor instead of mhz to keep a better precision, since - * cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits. - * (mathieu.desnoyers@polymtl.ca) - * - * -johnstul@us.ibm.com "math is hard, lets go shopping!" - */ - -DEFINE_PER_CPU(unsigned long, cyc2ns); - -static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) -{ - unsigned long long tsc_now, ns_now; - unsigned long flags, *scale; - - local_irq_save(flags); - sched_clock_idle_sleep_event(); - - scale = &per_cpu(cyc2ns, cpu); - - rdtscll(tsc_now); - ns_now = __cycles_2_ns(tsc_now); - - if (cpu_khz) - *scale = (NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR)/cpu_khz; - - /* - * Start smoothly with the new frequency: - */ - sched_clock_idle_wakeup_event(0); - local_irq_restore(flags); -} - -/* - * Scheduler clock - returns current time in nanosec units. - */ -unsigned long long native_sched_clock(void) -{ - unsigned long long this_offset; - - /* - * Fall back to jiffies if there's no TSC available: - * ( But note that we still use it if the TSC is marked - * unstable. We do this because unlike Time Of Day, - * the scheduler clock tolerates small errors and it's - * very important for it to be as fast as the platform - * can achive it. ) - */ - if (unlikely(tsc_disabled)) - /* No locking but a rare wrong value is not a big deal: */ - return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ); - - /* read the Time Stamp Counter: */ - rdtscll(this_offset); - - /* return the value in ns */ - return cycles_2_ns(this_offset); -} - -/* We need to define a real function for sched_clock, to override the - weak default version */ -#ifdef CONFIG_PARAVIRT -unsigned long long sched_clock(void) -{ - return paravirt_sched_clock(); -} -#else -unsigned long long sched_clock(void) - __attribute__((alias("native_sched_clock"))); -#endif - -unsigned long native_calculate_cpu_khz(void) -{ - unsigned long long start, end; - unsigned long count; - u64 delta64 = (u64)ULLONG_MAX; - int i; - unsigned long flags; - - local_irq_save(flags); - - /* run 3 times to ensure the cache is warm and to get an accurate reading */ - for (i = 0; i < 3; i++) { - mach_prepare_counter(); - rdtscll(start); - mach_countup(&count); - rdtscll(end); - - /* - * Error: ECTCNEVERSET - * The CTC wasn't reliable: we got a hit on the very first read, - * or the CPU was so fast/slow that the quotient wouldn't fit in - * 32 bits.. - */ - if (count <= 1) - continue; - - /* cpu freq too slow: */ - if ((end - start) <= CALIBRATE_TIME_MSEC) - continue; - - /* - * We want the minimum time of all runs in case one of them - * is inaccurate due to SMI or other delay - */ - delta64 = min(delta64, (end - start)); - } - - /* cpu freq too fast (or every run was bad): */ - if (delta64 > (1ULL<<32)) - goto err; - - delta64 += CALIBRATE_TIME_MSEC/2; /* round for do_div */ - do_div(delta64,CALIBRATE_TIME_MSEC); - - local_irq_restore(flags); - return (unsigned long)delta64; -err: - local_irq_restore(flags); - return 0; -} - -int recalibrate_cpu_khz(void) -{ -#ifndef CONFIG_SMP - unsigned long cpu_khz_old = cpu_khz; - - if (cpu_has_tsc) { - cpu_khz = calculate_cpu_khz(); - tsc_khz = cpu_khz; - cpu_data(0).loops_per_jiffy = - cpufreq_scale(cpu_data(0).loops_per_jiffy, - cpu_khz_old, cpu_khz); - return 0; - } else - return -ENODEV; -#else - return -ENODEV; -#endif -} - -EXPORT_SYMBOL(recalibrate_cpu_khz); - -#ifdef CONFIG_CPU_FREQ - -/* - * if the CPU frequency is scaled, TSC-based delays will need a different - * loops_per_jiffy value to function properly. - */ -static unsigned int ref_freq; -static unsigned long loops_per_jiffy_ref; -static unsigned long cpu_khz_ref; - -static int -time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, void *data) -{ - struct cpufreq_freqs *freq = data; - - if (!ref_freq) { - if (!freq->old){ - ref_freq = freq->new; - return 0; - } - ref_freq = freq->old; - loops_per_jiffy_ref = cpu_data(freq->cpu).loops_per_jiffy; - cpu_khz_ref = cpu_khz; - } - - if ((val == CPUFREQ_PRECHANGE && freq->old < freq->new) || - (val == CPUFREQ_POSTCHANGE && freq->old > freq->new) || - (val == CPUFREQ_RESUMECHANGE)) { - if (!(freq->flags & CPUFREQ_CONST_LOOPS)) - cpu_data(freq->cpu).loops_per_jiffy = - cpufreq_scale(loops_per_jiffy_ref, - ref_freq, freq->new); - - if (cpu_khz) { - - if (num_online_cpus() == 1) - cpu_khz = cpufreq_scale(cpu_khz_ref, - ref_freq, freq->new); - if (!(freq->flags & CPUFREQ_CONST_LOOPS)) { - tsc_khz = cpu_khz; - set_cyc2ns_scale(cpu_khz, freq->cpu); - /* - * TSC based sched_clock turns - * to junk w/ cpufreq - */ - mark_tsc_unstable("cpufreq changes"); - } - } - } - - return 0; -} - -static struct notifier_block time_cpufreq_notifier_block = { - .notifier_call = time_cpufreq_notifier -}; - -static int __init cpufreq_tsc(void) -{ - return cpufreq_register_notifier(&time_cpufreq_notifier_block, - CPUFREQ_TRANSITION_NOTIFIER); -} -core_initcall(cpufreq_tsc); - -#endif - -/* clock source code */ - -static unsigned long current_tsc_khz; -static struct clocksource clocksource_tsc; - -/* - * We compare the TSC to the cycle_last value in the clocksource - * structure to avoid a nasty time-warp issue. This can be observed in - * a very small window right after one CPU updated cycle_last under - * xtime lock and the other CPU reads a TSC value which is smaller - * than the cycle_last reference value due to a TSC which is slighty - * behind. This delta is nowhere else observable, but in that case it - * results in a forward time jump in the range of hours due to the - * unsigned delta calculation of the time keeping core code, which is - * necessary to support wrapping clocksources like pm timer. - */ -static cycle_t read_tsc(void) -{ - cycle_t ret; - - rdtscll(ret); - - return ret >= clocksource_tsc.cycle_last ? - ret : clocksource_tsc.cycle_last; -} - -static struct clocksource clocksource_tsc = { - .name = "tsc", - .rating = 300, - .read = read_tsc, - .mask = CLOCKSOURCE_MASK(64), - .mult = 0, /* to be set */ - .shift = 22, - .flags = CLOCK_SOURCE_IS_CONTINUOUS | - CLOCK_SOURCE_MUST_VERIFY, -}; - -void mark_tsc_unstable(char *reason) -{ - if (!tsc_unstable) { - tsc_unstable = 1; - printk("Marking TSC unstable due to: %s.\n", reason); - /* Can be called before registration */ - if (clocksource_tsc.mult) - clocksource_change_rating(&clocksource_tsc, 0); - else - clocksource_tsc.rating = 0; - } -} -EXPORT_SYMBOL_GPL(mark_tsc_unstable); - -static int __init dmi_mark_tsc_unstable(const struct dmi_system_id *d) -{ - printk(KERN_NOTICE "%s detected: marking TSC unstable.\n", - d->ident); - tsc_unstable = 1; - return 0; -} - -/* List of systems that have known TSC problems */ -static struct dmi_system_id __initdata bad_tsc_dmi_table[] = { - { - .callback = dmi_mark_tsc_unstable, - .ident = "IBM Thinkpad 380XD", - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "IBM"), - DMI_MATCH(DMI_BOARD_NAME, "2635FA0"), - }, - }, - {} -}; - -/* - * Make an educated guess if the TSC is trustworthy and synchronized - * over all CPUs. - */ -__cpuinit int unsynchronized_tsc(void) -{ - if (!cpu_has_tsc || tsc_unstable) - return 1; - - /* Anything with constant TSC should be synchronized */ - if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) - return 0; - - /* - * Intel systems are normally all synchronized. - * Exceptions must mark TSC as unstable: - */ - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) { - /* assume multi socket systems are not synchronized: */ - if (num_possible_cpus() > 1) - tsc_unstable = 1; - } - return tsc_unstable; -} - -/* - * Geode_LX - the OLPC CPU has a possibly a very reliable TSC - */ -#ifdef CONFIG_MGEODE_LX -/* RTSC counts during suspend */ -#define RTSC_SUSP 0x100 - -static void __init check_geode_tsc_reliable(void) -{ - unsigned long res_low, res_high; - - rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high); - if (res_low & RTSC_SUSP) - clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY; -} -#else -static inline void check_geode_tsc_reliable(void) { } -#endif - - -void __init tsc_init(void) -{ - int cpu; - - if (!cpu_has_tsc || tsc_disabled) { - /* Disable the TSC in case of !cpu_has_tsc */ - tsc_disabled = 1; - return; - } - - cpu_khz = calculate_cpu_khz(); - tsc_khz = cpu_khz; - - if (!cpu_khz) { - mark_tsc_unstable("could not calculate TSC khz"); - /* - * We need to disable the TSC completely in this case - * to prevent sched_clock() from using it. - */ - tsc_disabled = 1; - return; - } - - printk("Detected %lu.%03lu MHz processor.\n", - (unsigned long)cpu_khz / 1000, - (unsigned long)cpu_khz % 1000); - - /* - * Secondary CPUs do not run through tsc_init(), so set up - * all the scale factors for all CPUs, assuming the same - * speed as the bootup CPU. (cpufreq notifiers will fix this - * up if their speed diverges) - */ - for_each_possible_cpu(cpu) - set_cyc2ns_scale(cpu_khz, cpu); - - use_tsc_delay(); - - /* Check and install the TSC clocksource */ - dmi_check_system(bad_tsc_dmi_table); - - unsynchronized_tsc(); - check_geode_tsc_reliable(); - current_tsc_khz = tsc_khz; - clocksource_tsc.mult = clocksource_khz2mult(current_tsc_khz, - clocksource_tsc.shift); - /* lower the rating if we already know its unstable: */ - if (check_tsc_unstable()) { - clocksource_tsc.rating = 0; - clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS; - } - clocksource_register(&clocksource_tsc); -} diff --git a/arch/x86/kernel/tsc_64.c b/arch/x86/kernel/tsc_64.c deleted file mode 100644 index 1784b8077a12..000000000000 --- a/arch/x86/kernel/tsc_64.c +++ /dev/null @@ -1,357 +0,0 @@ -#include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/interrupt.h> -#include <linux/init.h> -#include <linux/clocksource.h> -#include <linux/time.h> -#include <linux/acpi.h> -#include <linux/cpufreq.h> -#include <linux/acpi_pmtmr.h> - -#include <asm/hpet.h> -#include <asm/timex.h> -#include <asm/timer.h> -#include <asm/vgtod.h> - -static int notsc __initdata = 0; - -unsigned int cpu_khz; /* TSC clocks / usec, not used here */ -EXPORT_SYMBOL(cpu_khz); -unsigned int tsc_khz; -EXPORT_SYMBOL(tsc_khz); - -/* Accelerators for sched_clock() - * convert from cycles(64bits) => nanoseconds (64bits) - * basic equation: - * ns = cycles / (freq / ns_per_sec) - * ns = cycles * (ns_per_sec / freq) - * ns = cycles * (10^9 / (cpu_khz * 10^3)) - * ns = cycles * (10^6 / cpu_khz) - * - * Then we use scaling math (suggested by george@mvista.com) to get: - * ns = cycles * (10^6 * SC / cpu_khz) / SC - * ns = cycles * cyc2ns_scale / SC - * - * And since SC is a constant power of two, we can convert the div - * into a shift. - * - * We can use khz divisor instead of mhz to keep a better precision, since - * cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits. - * (mathieu.desnoyers@polymtl.ca) - * - * -johnstul@us.ibm.com "math is hard, lets go shopping!" - */ -DEFINE_PER_CPU(unsigned long, cyc2ns); - -static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) -{ - unsigned long long tsc_now, ns_now; - unsigned long flags, *scale; - - local_irq_save(flags); - sched_clock_idle_sleep_event(); - - scale = &per_cpu(cyc2ns, cpu); - - rdtscll(tsc_now); - ns_now = __cycles_2_ns(tsc_now); - - if (cpu_khz) - *scale = (NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR)/cpu_khz; - - sched_clock_idle_wakeup_event(0); - local_irq_restore(flags); -} - -unsigned long long native_sched_clock(void) -{ - unsigned long a = 0; - - /* Could do CPU core sync here. Opteron can execute rdtsc speculatively, - * which means it is not completely exact and may not be monotonous - * between CPUs. But the errors should be too small to matter for - * scheduling purposes. - */ - - rdtscll(a); - return cycles_2_ns(a); -} - -/* We need to define a real function for sched_clock, to override the - weak default version */ -#ifdef CONFIG_PARAVIRT -unsigned long long sched_clock(void) -{ - return paravirt_sched_clock(); -} -#else -unsigned long long -sched_clock(void) __attribute__((alias("native_sched_clock"))); -#endif - - -static int tsc_unstable; - -int check_tsc_unstable(void) -{ - return tsc_unstable; -} -EXPORT_SYMBOL_GPL(check_tsc_unstable); - -#ifdef CONFIG_CPU_FREQ - -/* Frequency scaling support. Adjust the TSC based timer when the cpu frequency - * changes. - * - * RED-PEN: On SMP we assume all CPUs run with the same frequency. It's - * not that important because current Opteron setups do not support - * scaling on SMP anyroads. - * - * Should fix up last_tsc too. Currently gettimeofday in the - * first tick after the change will be slightly wrong. - */ - -static unsigned int ref_freq; -static unsigned long loops_per_jiffy_ref; -static unsigned long tsc_khz_ref; - -static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, - void *data) -{ - struct cpufreq_freqs *freq = data; - unsigned long *lpj, dummy; - - if (cpu_has(&cpu_data(freq->cpu), X86_FEATURE_CONSTANT_TSC)) - return 0; - - lpj = &dummy; - if (!(freq->flags & CPUFREQ_CONST_LOOPS)) -#ifdef CONFIG_SMP - lpj = &cpu_data(freq->cpu).loops_per_jiffy; -#else - lpj = &boot_cpu_data.loops_per_jiffy; -#endif - - if (!ref_freq) { - ref_freq = freq->old; - loops_per_jiffy_ref = *lpj; - tsc_khz_ref = tsc_khz; - } - if ((val == CPUFREQ_PRECHANGE && freq->old < freq->new) || - (val == CPUFREQ_POSTCHANGE && freq->old > freq->new) || - (val == CPUFREQ_RESUMECHANGE)) { - *lpj = - cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new); - - tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new); - if (!(freq->flags & CPUFREQ_CONST_LOOPS)) - mark_tsc_unstable("cpufreq changes"); - } - - set_cyc2ns_scale(tsc_khz_ref, freq->cpu); - - return 0; -} - -static struct notifier_block time_cpufreq_notifier_block = { - .notifier_call = time_cpufreq_notifier -}; - -static int __init cpufreq_tsc(void) -{ - cpufreq_register_notifier(&time_cpufreq_notifier_block, - CPUFREQ_TRANSITION_NOTIFIER); - return 0; -} - -core_initcall(cpufreq_tsc); - -#endif - -#define MAX_RETRIES 5 -#define SMI_TRESHOLD 50000 - -/* - * Read TSC and the reference counters. Take care of SMI disturbance - */ -static unsigned long __init tsc_read_refs(unsigned long *pm, - unsigned long *hpet) -{ - unsigned long t1, t2; - int i; - - for (i = 0; i < MAX_RETRIES; i++) { - t1 = get_cycles(); - if (hpet) - *hpet = hpet_readl(HPET_COUNTER) & 0xFFFFFFFF; - else - *pm = acpi_pm_read_early(); - t2 = get_cycles(); - if ((t2 - t1) < SMI_TRESHOLD) - return t2; - } - return ULONG_MAX; -} - -/** - * tsc_calibrate - calibrate the tsc on boot - */ -void __init tsc_calibrate(void) -{ - unsigned long flags, tsc1, tsc2, tr1, tr2, pm1, pm2, hpet1, hpet2; - int hpet = is_hpet_enabled(), cpu; - - local_irq_save(flags); - - tsc1 = tsc_read_refs(&pm1, hpet ? &hpet1 : NULL); - - outb((inb(0x61) & ~0x02) | 0x01, 0x61); - - outb(0xb0, 0x43); - outb((CLOCK_TICK_RATE / (1000 / 50)) & 0xff, 0x42); - outb((CLOCK_TICK_RATE / (1000 / 50)) >> 8, 0x42); - tr1 = get_cycles(); - while ((inb(0x61) & 0x20) == 0); - tr2 = get_cycles(); - - tsc2 = tsc_read_refs(&pm2, hpet ? &hpet2 : NULL); - - local_irq_restore(flags); - - /* - * Preset the result with the raw and inaccurate PIT - * calibration value - */ - tsc_khz = (tr2 - tr1) / 50; - - /* hpet or pmtimer available ? */ - if (!hpet && !pm1 && !pm2) { - printk(KERN_INFO "TSC calibrated against PIT\n"); - goto out; - } - - /* Check, whether the sampling was disturbed by an SMI */ - if (tsc1 == ULONG_MAX || tsc2 == ULONG_MAX) { - printk(KERN_WARNING "TSC calibration disturbed by SMI, " - "using PIT calibration result\n"); - goto out; - } - - tsc2 = (tsc2 - tsc1) * 1000000L; - - if (hpet) { - printk(KERN_INFO "TSC calibrated against HPET\n"); - if (hpet2 < hpet1) - hpet2 += 0x100000000; - hpet2 -= hpet1; - tsc1 = (hpet2 * hpet_readl(HPET_PERIOD)) / 1000000; - } else { - printk(KERN_INFO "TSC calibrated against PM_TIMER\n"); - if (pm2 < pm1) - pm2 += ACPI_PM_OVRRUN; - pm2 -= pm1; - tsc1 = (pm2 * 1000000000) / PMTMR_TICKS_PER_SEC; - } - - tsc_khz = tsc2 / tsc1; - -out: - for_each_possible_cpu(cpu) - set_cyc2ns_scale(tsc_khz, cpu); -} - -/* - * Make an educated guess if the TSC is trustworthy and synchronized - * over all CPUs. - */ -__cpuinit int unsynchronized_tsc(void) -{ - if (tsc_unstable) - return 1; - -#ifdef CONFIG_SMP - if (apic_is_clustered_box()) - return 1; -#endif - - if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) - return 0; - - /* Assume multi socket systems are not synchronized */ - return num_present_cpus() > 1; -} - -int __init notsc_setup(char *s) -{ - notsc = 1; - return 1; -} - -__setup("notsc", notsc_setup); - -static struct clocksource clocksource_tsc; - -/* - * We compare the TSC to the cycle_last value in the clocksource - * structure to avoid a nasty time-warp. This can be observed in a - * very small window right after one CPU updated cycle_last under - * xtime/vsyscall_gtod lock and the other CPU reads a TSC value which - * is smaller than the cycle_last reference value due to a TSC which - * is slighty behind. This delta is nowhere else observable, but in - * that case it results in a forward time jump in the range of hours - * due to the unsigned delta calculation of the time keeping core - * code, which is necessary to support wrapping clocksources like pm - * timer. - */ -static cycle_t read_tsc(void) -{ - cycle_t ret = (cycle_t)get_cycles(); - - return ret >= clocksource_tsc.cycle_last ? - ret : clocksource_tsc.cycle_last; -} - -static cycle_t __vsyscall_fn vread_tsc(void) -{ - cycle_t ret = (cycle_t)vget_cycles(); - - return ret >= __vsyscall_gtod_data.clock.cycle_last ? - ret : __vsyscall_gtod_data.clock.cycle_last; -} - -static struct clocksource clocksource_tsc = { - .name = "tsc", - .rating = 300, - .read = read_tsc, - .mask = CLOCKSOURCE_MASK(64), - .shift = 22, - .flags = CLOCK_SOURCE_IS_CONTINUOUS | - CLOCK_SOURCE_MUST_VERIFY, - .vread = vread_tsc, -}; - -void mark_tsc_unstable(char *reason) -{ - if (!tsc_unstable) { - tsc_unstable = 1; - printk("Marking TSC unstable due to %s\n", reason); - /* Change only the rating, when not registered */ - if (clocksource_tsc.mult) - clocksource_change_rating(&clocksource_tsc, 0); - else - clocksource_tsc.rating = 0; - } -} -EXPORT_SYMBOL_GPL(mark_tsc_unstable); - -void __init init_tsc_clocksource(void) -{ - if (!notsc) { - clocksource_tsc.mult = clocksource_khz2mult(tsc_khz, - clocksource_tsc.shift); - if (check_tsc_unstable()) - clocksource_tsc.rating = 0; - - clocksource_register(&clocksource_tsc); - } -} diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c new file mode 100644 index 000000000000..e94bdb6add1d --- /dev/null +++ b/arch/x86/kernel/visws_quirks.c @@ -0,0 +1,709 @@ +/* + * SGI Visual Workstation support and quirks, unmaintained. + * + * Split out from setup.c by davej@suse.de + * + * Copyright (C) 1999 Bent Hagemark, Ingo Molnar + * + * SGI Visual Workstation interrupt controller + * + * The Cobalt system ASIC in the Visual Workstation contains a "Cobalt" APIC + * which serves as the main interrupt controller in the system. Non-legacy + * hardware in the system uses this controller directly. Legacy devices + * are connected to the PIIX4 which in turn has its 8259(s) connected to + * a of the Cobalt APIC entry. + * + * 09/02/2000 - Updated for 2.4 by jbarnes@sgi.com + * + * 25/11/2002 - Updated for 2.5 by Andrey Panin <pazke@orbita1.ru> + */ +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/smp.h> + +#include <asm/visws/cobalt.h> +#include <asm/visws/piix4.h> +#include <asm/arch_hooks.h> +#include <asm/fixmap.h> +#include <asm/reboot.h> +#include <asm/setup.h> +#include <asm/e820.h> +#include <asm/smp.h> +#include <asm/io.h> + +#include <mach_ipi.h> + +#include "mach_apic.h" + +#include <linux/init.h> +#include <linux/smp.h> + +#include <linux/kernel_stat.h> +#include <linux/interrupt.h> +#include <linux/init.h> + +#include <asm/io.h> +#include <asm/apic.h> +#include <asm/i8259.h> +#include <asm/irq_vectors.h> +#include <asm/visws/cobalt.h> +#include <asm/visws/lithium.h> +#include <asm/visws/piix4.h> + +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/pci.h> +#include <linux/pci_ids.h> + +extern int no_broadcast; + +#include <asm/io.h> +#include <asm/apic.h> +#include <asm/arch_hooks.h> +#include <asm/visws/cobalt.h> +#include <asm/visws/lithium.h> + +char visws_board_type = -1; +char visws_board_rev = -1; + +int is_visws_box(void) +{ + return visws_board_type >= 0; +} + +static int __init visws_time_init_quirk(void) +{ + printk(KERN_INFO "Starting Cobalt Timer system clock\n"); + + /* Set the countdown value */ + co_cpu_write(CO_CPU_TIMEVAL, CO_TIME_HZ/HZ); + + /* Start the timer */ + co_cpu_write(CO_CPU_CTRL, co_cpu_read(CO_CPU_CTRL) | CO_CTRL_TIMERUN); + + /* Enable (unmask) the timer interrupt */ + co_cpu_write(CO_CPU_CTRL, co_cpu_read(CO_CPU_CTRL) & ~CO_CTRL_TIMEMASK); + + /* + * Zero return means the generic timer setup code will set up + * the standard vector: + */ + return 0; +} + +static int __init visws_pre_intr_init_quirk(void) +{ + init_VISWS_APIC_irqs(); + + /* + * We dont want ISA irqs to be set up by the generic code: + */ + return 1; +} + +/* Quirk for machine specific memory setup. */ + +#define MB (1024 * 1024) + +unsigned long sgivwfb_mem_phys; +unsigned long sgivwfb_mem_size; +EXPORT_SYMBOL(sgivwfb_mem_phys); +EXPORT_SYMBOL(sgivwfb_mem_size); + +long long mem_size __initdata = 0; + +static char * __init visws_memory_setup_quirk(void) +{ + long long gfx_mem_size = 8 * MB; + + mem_size = boot_params.alt_mem_k; + + if (!mem_size) { + printk(KERN_WARNING "Bootloader didn't set memory size, upgrade it !\n"); + mem_size = 128 * MB; + } + + /* + * this hardcodes the graphics memory to 8 MB + * it really should be sized dynamically (or at least + * set as a boot param) + */ + if (!sgivwfb_mem_size) { + printk(KERN_WARNING "Defaulting to 8 MB framebuffer size\n"); + sgivwfb_mem_size = 8 * MB; + } + + /* + * Trim to nearest MB + */ + sgivwfb_mem_size &= ~((1 << 20) - 1); + sgivwfb_mem_phys = mem_size - gfx_mem_size; + + e820_add_region(0, LOWMEMSIZE(), E820_RAM); + e820_add_region(HIGH_MEMORY, mem_size - sgivwfb_mem_size - HIGH_MEMORY, E820_RAM); + e820_add_region(sgivwfb_mem_phys, sgivwfb_mem_size, E820_RESERVED); + + return "PROM"; +} + +static void visws_machine_emergency_restart(void) +{ + /* + * Visual Workstations restart after this + * register is poked on the PIIX4 + */ + outb(PIIX4_RESET_VAL, PIIX4_RESET_PORT); +} + +static void visws_machine_power_off(void) +{ + unsigned short pm_status; +/* extern unsigned int pci_bus0; */ + + while ((pm_status = inw(PMSTS_PORT)) & 0x100) + outw(pm_status, PMSTS_PORT); + + outw(PM_SUSPEND_ENABLE, PMCNTRL_PORT); + + mdelay(10); + +#define PCI_CONF1_ADDRESS(bus, devfn, reg) \ + (0x80000000 | (bus << 16) | (devfn << 8) | (reg & ~3)) + +/* outl(PCI_CONF1_ADDRESS(pci_bus0, SPECIAL_DEV, SPECIAL_REG), 0xCF8); */ + outl(PIIX_SPECIAL_STOP, 0xCFC); +} + +static int __init visws_get_smp_config_quirk(unsigned int early) +{ + /* + * Prevent MP-table parsing by the generic code: + */ + return 1; +} + +extern unsigned int __cpuinitdata maxcpus; + +/* + * The Visual Workstation is Intel MP compliant in the hardware + * sense, but it doesn't have a BIOS(-configuration table). + * No problem for Linux. + */ + +static void __init MP_processor_info (struct mpc_config_processor *m) +{ + int ver, logical_apicid; + physid_mask_t apic_cpus; + + if (!(m->mpc_cpuflag & CPU_ENABLED)) + return; + + logical_apicid = m->mpc_apicid; + printk(KERN_INFO "%sCPU #%d %u:%u APIC version %d\n", + m->mpc_cpuflag & CPU_BOOTPROCESSOR ? "Bootup " : "", + m->mpc_apicid, + (m->mpc_cpufeature & CPU_FAMILY_MASK) >> 8, + (m->mpc_cpufeature & CPU_MODEL_MASK) >> 4, + m->mpc_apicver); + + if (m->mpc_cpuflag & CPU_BOOTPROCESSOR) + boot_cpu_physical_apicid = m->mpc_apicid; + + ver = m->mpc_apicver; + if ((ver >= 0x14 && m->mpc_apicid >= 0xff) || m->mpc_apicid >= 0xf) { + printk(KERN_ERR "Processor #%d INVALID. (Max ID: %d).\n", + m->mpc_apicid, MAX_APICS); + return; + } + + apic_cpus = apicid_to_cpu_present(m->mpc_apicid); + physids_or(phys_cpu_present_map, phys_cpu_present_map, apic_cpus); + /* + * Validate version + */ + if (ver == 0x0) { + printk(KERN_ERR "BIOS bug, APIC version is 0 for CPU#%d! " + "fixing up to 0x10. (tell your hw vendor)\n", + m->mpc_apicid); + ver = 0x10; + } + apic_version[m->mpc_apicid] = ver; +} + +int __init visws_find_smp_config_quirk(unsigned int reserve) +{ + struct mpc_config_processor *mp = phys_to_virt(CO_CPU_TAB_PHYS); + unsigned short ncpus = readw(phys_to_virt(CO_CPU_NUM_PHYS)); + + if (ncpus > CO_CPU_MAX) { + printk(KERN_WARNING "find_visws_smp: got cpu count of %d at %p\n", + ncpus, mp); + + ncpus = CO_CPU_MAX; + } + + if (ncpus > maxcpus) + ncpus = maxcpus; + +#ifdef CONFIG_X86_LOCAL_APIC + smp_found_config = 1; +#endif + while (ncpus--) + MP_processor_info(mp++); + + mp_lapic_addr = APIC_DEFAULT_PHYS_BASE; + + return 1; +} + +extern int visws_trap_init_quirk(void); + +void __init visws_early_detect(void) +{ + int raw; + + visws_board_type = (char)(inb_p(PIIX_GPI_BD_REG) & PIIX_GPI_BD_REG) + >> PIIX_GPI_BD_SHIFT; + + if (visws_board_type < 0) + return; + + /* + * Install special quirks for timer, interrupt and memory setup: + */ + arch_time_init_quirk = visws_time_init_quirk; + arch_pre_intr_init_quirk = visws_pre_intr_init_quirk; + arch_memory_setup_quirk = visws_memory_setup_quirk; + + /* + * Fall back to generic behavior for traps: + */ + arch_intr_init_quirk = NULL; + arch_trap_init_quirk = visws_trap_init_quirk; + + /* + * Install reboot quirks: + */ + pm_power_off = visws_machine_power_off; + machine_ops.emergency_restart = visws_machine_emergency_restart; + + /* + * Do not use broadcast IPIs: + */ + no_broadcast = 0; + + /* + * Override generic MP-table parsing: + */ + mach_get_smp_config_quirk = visws_get_smp_config_quirk; + mach_find_smp_config_quirk = visws_find_smp_config_quirk; + +#ifdef CONFIG_X86_IO_APIC + /* + * Turn off IO-APIC detection and initialization: + */ + skip_ioapic_setup = 1; +#endif + + /* + * Get Board rev. + * First, we have to initialize the 307 part to allow us access + * to the GPIO registers. Let's map them at 0x0fc0 which is right + * after the PIIX4 PM section. + */ + outb_p(SIO_DEV_SEL, SIO_INDEX); + outb_p(SIO_GP_DEV, SIO_DATA); /* Talk to GPIO regs. */ + + outb_p(SIO_DEV_MSB, SIO_INDEX); + outb_p(SIO_GP_MSB, SIO_DATA); /* MSB of GPIO base address */ + + outb_p(SIO_DEV_LSB, SIO_INDEX); + outb_p(SIO_GP_LSB, SIO_DATA); /* LSB of GPIO base address */ + + outb_p(SIO_DEV_ENB, SIO_INDEX); + outb_p(1, SIO_DATA); /* Enable GPIO registers. */ + + /* + * Now, we have to map the power management section to write + * a bit which enables access to the GPIO registers. + * What lunatic came up with this shit? + */ + outb_p(SIO_DEV_SEL, SIO_INDEX); + outb_p(SIO_PM_DEV, SIO_DATA); /* Talk to GPIO regs. */ + + outb_p(SIO_DEV_MSB, SIO_INDEX); + outb_p(SIO_PM_MSB, SIO_DATA); /* MSB of PM base address */ + + outb_p(SIO_DEV_LSB, SIO_INDEX); + outb_p(SIO_PM_LSB, SIO_DATA); /* LSB of PM base address */ + + outb_p(SIO_DEV_ENB, SIO_INDEX); + outb_p(1, SIO_DATA); /* Enable PM registers. */ + + /* + * Now, write the PM register which enables the GPIO registers. + */ + outb_p(SIO_PM_FER2, SIO_PM_INDEX); + outb_p(SIO_PM_GP_EN, SIO_PM_DATA); + + /* + * Now, initialize the GPIO registers. + * We want them all to be inputs which is the + * power on default, so let's leave them alone. + * So, let's just read the board rev! + */ + raw = inb_p(SIO_GP_DATA1); + raw &= 0x7f; /* 7 bits of valid board revision ID. */ + + if (visws_board_type == VISWS_320) { + if (raw < 0x6) { + visws_board_rev = 4; + } else if (raw < 0xc) { + visws_board_rev = 5; + } else { + visws_board_rev = 6; + } + } else if (visws_board_type == VISWS_540) { + visws_board_rev = 2; + } else { + visws_board_rev = raw; + } + + printk(KERN_INFO "Silicon Graphics Visual Workstation %s (rev %d) detected\n", + (visws_board_type == VISWS_320 ? "320" : + (visws_board_type == VISWS_540 ? "540" : + "unknown")), visws_board_rev); +} + +#define A01234 (LI_INTA_0 | LI_INTA_1 | LI_INTA_2 | LI_INTA_3 | LI_INTA_4) +#define BCD (LI_INTB | LI_INTC | LI_INTD) +#define ALLDEVS (A01234 | BCD) + +static __init void lithium_init(void) +{ + set_fixmap(FIX_LI_PCIA, LI_PCI_A_PHYS); + set_fixmap(FIX_LI_PCIB, LI_PCI_B_PHYS); + + if ((li_pcia_read16(PCI_VENDOR_ID) != PCI_VENDOR_ID_SGI) || + (li_pcia_read16(PCI_DEVICE_ID) != PCI_DEVICE_ID_SGI_LITHIUM)) { + printk(KERN_EMERG "Lithium hostbridge %c not found\n", 'A'); +/* panic("This machine is not SGI Visual Workstation 320/540"); */ + } + + if ((li_pcib_read16(PCI_VENDOR_ID) != PCI_VENDOR_ID_SGI) || + (li_pcib_read16(PCI_DEVICE_ID) != PCI_DEVICE_ID_SGI_LITHIUM)) { + printk(KERN_EMERG "Lithium hostbridge %c not found\n", 'B'); +/* panic("This machine is not SGI Visual Workstation 320/540"); */ + } + + li_pcia_write16(LI_PCI_INTEN, ALLDEVS); + li_pcib_write16(LI_PCI_INTEN, ALLDEVS); +} + +static __init void cobalt_init(void) +{ + /* + * On normal SMP PC this is used only with SMP, but we have to + * use it and set it up here to start the Cobalt clock + */ + set_fixmap(FIX_APIC_BASE, APIC_DEFAULT_PHYS_BASE); + setup_local_APIC(); + printk(KERN_INFO "Local APIC Version %#x, ID %#x\n", + (unsigned int)apic_read(APIC_LVR), + (unsigned int)apic_read(APIC_ID)); + + set_fixmap(FIX_CO_CPU, CO_CPU_PHYS); + set_fixmap(FIX_CO_APIC, CO_APIC_PHYS); + printk(KERN_INFO "Cobalt Revision %#lx, APIC ID %#lx\n", + co_cpu_read(CO_CPU_REV), co_apic_read(CO_APIC_ID)); + + /* Enable Cobalt APIC being careful to NOT change the ID! */ + co_apic_write(CO_APIC_ID, co_apic_read(CO_APIC_ID) | CO_APIC_ENABLE); + + printk(KERN_INFO "Cobalt APIC enabled: ID reg %#lx\n", + co_apic_read(CO_APIC_ID)); +} + +int __init visws_trap_init_quirk(void) +{ + lithium_init(); + cobalt_init(); + + return 1; +} + +/* + * IRQ controller / APIC support: + */ + +static DEFINE_SPINLOCK(cobalt_lock); + +/* + * Set the given Cobalt APIC Redirection Table entry to point + * to the given IDT vector/index. + */ +static inline void co_apic_set(int entry, int irq) +{ + co_apic_write(CO_APIC_LO(entry), CO_APIC_LEVEL | (irq + FIRST_EXTERNAL_VECTOR)); + co_apic_write(CO_APIC_HI(entry), 0); +} + +/* + * Cobalt (IO)-APIC functions to handle PCI devices. + */ +static inline int co_apic_ide0_hack(void) +{ + extern char visws_board_type; + extern char visws_board_rev; + + if (visws_board_type == VISWS_320 && visws_board_rev == 5) + return 5; + return CO_APIC_IDE0; +} + +static int is_co_apic(unsigned int irq) +{ + if (IS_CO_APIC(irq)) + return CO_APIC(irq); + + switch (irq) { + case 0: return CO_APIC_CPU; + case CO_IRQ_IDE0: return co_apic_ide0_hack(); + case CO_IRQ_IDE1: return CO_APIC_IDE1; + default: return -1; + } +} + + +/* + * This is the SGI Cobalt (IO-)APIC: + */ + +static void enable_cobalt_irq(unsigned int irq) +{ + co_apic_set(is_co_apic(irq), irq); +} + +static void disable_cobalt_irq(unsigned int irq) +{ + int entry = is_co_apic(irq); + + co_apic_write(CO_APIC_LO(entry), CO_APIC_MASK); + co_apic_read(CO_APIC_LO(entry)); +} + +/* + * "irq" really just serves to identify the device. Here is where we + * map this to the Cobalt APIC entry where it's physically wired. + * This is called via request_irq -> setup_irq -> irq_desc->startup() + */ +static unsigned int startup_cobalt_irq(unsigned int irq) +{ + unsigned long flags; + + spin_lock_irqsave(&cobalt_lock, flags); + if ((irq_desc[irq].status & (IRQ_DISABLED | IRQ_INPROGRESS | IRQ_WAITING))) + irq_desc[irq].status &= ~(IRQ_DISABLED | IRQ_INPROGRESS | IRQ_WAITING); + enable_cobalt_irq(irq); + spin_unlock_irqrestore(&cobalt_lock, flags); + return 0; +} + +static void ack_cobalt_irq(unsigned int irq) +{ + unsigned long flags; + + spin_lock_irqsave(&cobalt_lock, flags); + disable_cobalt_irq(irq); + apic_write(APIC_EOI, APIC_EIO_ACK); + spin_unlock_irqrestore(&cobalt_lock, flags); +} + +static void end_cobalt_irq(unsigned int irq) +{ + unsigned long flags; + + spin_lock_irqsave(&cobalt_lock, flags); + if (!(irq_desc[irq].status & (IRQ_DISABLED | IRQ_INPROGRESS))) + enable_cobalt_irq(irq); + spin_unlock_irqrestore(&cobalt_lock, flags); +} + +static struct irq_chip cobalt_irq_type = { + .typename = "Cobalt-APIC", + .startup = startup_cobalt_irq, + .shutdown = disable_cobalt_irq, + .enable = enable_cobalt_irq, + .disable = disable_cobalt_irq, + .ack = ack_cobalt_irq, + .end = end_cobalt_irq, +}; + + +/* + * This is the PIIX4-based 8259 that is wired up indirectly to Cobalt + * -- not the manner expected by the code in i8259.c. + * + * there is a 'master' physical interrupt source that gets sent to + * the CPU. But in the chipset there are various 'virtual' interrupts + * waiting to be handled. We represent this to Linux through a 'master' + * interrupt controller type, and through a special virtual interrupt- + * controller. Device drivers only see the virtual interrupt sources. + */ +static unsigned int startup_piix4_master_irq(unsigned int irq) +{ + init_8259A(0); + + return startup_cobalt_irq(irq); +} + +static void end_piix4_master_irq(unsigned int irq) +{ + unsigned long flags; + + spin_lock_irqsave(&cobalt_lock, flags); + enable_cobalt_irq(irq); + spin_unlock_irqrestore(&cobalt_lock, flags); +} + +static struct irq_chip piix4_master_irq_type = { + .typename = "PIIX4-master", + .startup = startup_piix4_master_irq, + .ack = ack_cobalt_irq, + .end = end_piix4_master_irq, +}; + + +static struct irq_chip piix4_virtual_irq_type = { + .typename = "PIIX4-virtual", + .shutdown = disable_8259A_irq, + .enable = enable_8259A_irq, + .disable = disable_8259A_irq, +}; + + +/* + * PIIX4-8259 master/virtual functions to handle interrupt requests + * from legacy devices: floppy, parallel, serial, rtc. + * + * None of these get Cobalt APIC entries, neither do they have IDT + * entries. These interrupts are purely virtual and distributed from + * the 'master' interrupt source: CO_IRQ_8259. + * + * When the 8259 interrupts its handler figures out which of these + * devices is interrupting and dispatches to its handler. + * + * CAREFUL: devices see the 'virtual' interrupt only. Thus disable/ + * enable_irq gets the right irq. This 'master' irq is never directly + * manipulated by any driver. + */ +static irqreturn_t piix4_master_intr(int irq, void *dev_id) +{ + int realirq; + irq_desc_t *desc; + unsigned long flags; + + spin_lock_irqsave(&i8259A_lock, flags); + + /* Find out what's interrupting in the PIIX4 master 8259 */ + outb(0x0c, 0x20); /* OCW3 Poll command */ + realirq = inb(0x20); + + /* + * Bit 7 == 0 means invalid/spurious + */ + if (unlikely(!(realirq & 0x80))) + goto out_unlock; + + realirq &= 7; + + if (unlikely(realirq == 2)) { + outb(0x0c, 0xa0); + realirq = inb(0xa0); + + if (unlikely(!(realirq & 0x80))) + goto out_unlock; + + realirq = (realirq & 7) + 8; + } + + /* mask and ack interrupt */ + cached_irq_mask |= 1 << realirq; + if (unlikely(realirq > 7)) { + inb(0xa1); + outb(cached_slave_mask, 0xa1); + outb(0x60 + (realirq & 7), 0xa0); + outb(0x60 + 2, 0x20); + } else { + inb(0x21); + outb(cached_master_mask, 0x21); + outb(0x60 + realirq, 0x20); + } + + spin_unlock_irqrestore(&i8259A_lock, flags); + + desc = irq_desc + realirq; + + /* + * handle this 'virtual interrupt' as a Cobalt one now. + */ + kstat_cpu(smp_processor_id()).irqs[realirq]++; + + if (likely(desc->action != NULL)) + handle_IRQ_event(realirq, desc->action); + + if (!(desc->status & IRQ_DISABLED)) + enable_8259A_irq(realirq); + + return IRQ_HANDLED; + +out_unlock: + spin_unlock_irqrestore(&i8259A_lock, flags); + return IRQ_NONE; +} + +static struct irqaction master_action = { + .handler = piix4_master_intr, + .name = "PIIX4-8259", +}; + +static struct irqaction cascade_action = { + .handler = no_action, + .name = "cascade", +}; + + +void init_VISWS_APIC_irqs(void) +{ + int i; + + for (i = 0; i < CO_IRQ_APIC0 + CO_APIC_LAST + 1; i++) { + irq_desc[i].status = IRQ_DISABLED; + irq_desc[i].action = 0; + irq_desc[i].depth = 1; + + if (i == 0) { + irq_desc[i].chip = &cobalt_irq_type; + } + else if (i == CO_IRQ_IDE0) { + irq_desc[i].chip = &cobalt_irq_type; + } + else if (i == CO_IRQ_IDE1) { + irq_desc[i].chip = &cobalt_irq_type; + } + else if (i == CO_IRQ_8259) { + irq_desc[i].chip = &piix4_master_irq_type; + } + else if (i < CO_IRQ_APIC0) { + irq_desc[i].chip = &piix4_virtual_irq_type; + } + else if (IS_CO_APIC(i)) { + irq_desc[i].chip = &cobalt_irq_type; + } + } + + setup_irq(CO_IRQ_8259, &master_action); + setup_irq(2, &cascade_action); +} diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c index 956f38927aa7..b15346092b7b 100644 --- a/arch/x86/kernel/vmi_32.c +++ b/arch/x86/kernel/vmi_32.c @@ -151,7 +151,7 @@ static unsigned vmi_patch(u8 type, u16 clobbers, void *insns, insns, ip); case PARAVIRT_PATCH(pv_cpu_ops.iret): return patch_internal(VMI_CALL_IRET, len, insns, ip); - case PARAVIRT_PATCH(pv_cpu_ops.irq_enable_syscall_ret): + case PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit): return patch_internal(VMI_CALL_SYSEXIT, len, insns, ip); default: break; @@ -896,7 +896,7 @@ static inline int __init activate_vmi(void) * the backend. They are performance critical anyway, so requiring * a patch is not a big problem. */ - pv_cpu_ops.irq_enable_syscall_ret = (void *)0xfeedbab0; + pv_cpu_ops.irq_enable_sysexit = (void *)0xfeedbab0; pv_cpu_ops.iret = (void *)0xbadbab0; #ifdef CONFIG_SMP @@ -932,7 +932,7 @@ static inline int __init activate_vmi(void) pv_apic_ops.setup_secondary_clock = vmi_time_ap_init; #endif pv_time_ops.sched_clock = vmi_sched_clock; - pv_time_ops.get_cpu_khz = vmi_cpu_khz; + pv_time_ops.get_tsc_khz = vmi_tsc_khz; /* We have true wallclock functions; disable CMOS clock sync */ no_sync_cmos_clock = 1; diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c index a2b030780aa9..6953859fe289 100644 --- a/arch/x86/kernel/vmiclock_32.c +++ b/arch/x86/kernel/vmiclock_32.c @@ -33,8 +33,7 @@ #include <asm/apic.h> #include <asm/timer.h> #include <asm/i8253.h> - -#include <irq_vectors.h> +#include <asm/irq_vectors.h> #define VMI_ONESHOT (VMI_ALARM_IS_ONESHOT | VMI_CYCLES_REAL | vmi_get_alarm_wiring()) #define VMI_PERIODIC (VMI_ALARM_IS_PERIODIC | VMI_CYCLES_REAL | vmi_get_alarm_wiring()) @@ -70,8 +69,8 @@ unsigned long long vmi_sched_clock(void) return cycles_2_ns(vmi_timer_ops.get_cycle_counter(VMI_CYCLES_AVAILABLE)); } -/* paravirt_ops.get_cpu_khz = vmi_cpu_khz */ -unsigned long vmi_cpu_khz(void) +/* paravirt_ops.get_tsc_khz = vmi_tsc_khz */ +unsigned long vmi_tsc_khz(void) { unsigned long long khz; khz = vmi_timer_ops.get_cycle_frequency(); diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S index ce5ed083a1e9..cdb2363697d2 100644 --- a/arch/x86/kernel/vmlinux_32.lds.S +++ b/arch/x86/kernel/vmlinux_32.lds.S @@ -49,23 +49,14 @@ SECTIONS _etext = .; /* End of text section */ } :text = 0x9090 + NOTES :text :note + . = ALIGN(16); /* Exception table */ __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) { __start___ex_table = .; *(__ex_table) __stop___ex_table = .; - } - - NOTES :text :note - - BUG_TABLE :text - - . = ALIGN(4); - .tracedata : AT(ADDR(.tracedata) - LOAD_OFFSET) { - __tracedata_start = .; - *(.tracedata) - __tracedata_end = .; - } + } :text = 0x9090 RODATA diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S index fad3674b06a5..63e5c1a22e88 100644 --- a/arch/x86/kernel/vmlinux_64.lds.S +++ b/arch/x86/kernel/vmlinux_64.lds.S @@ -19,7 +19,7 @@ PHDRS { data PT_LOAD FLAGS(7); /* RWE */ user PT_LOAD FLAGS(7); /* RWE */ data.init PT_LOAD FLAGS(7); /* RWE */ - note PT_NOTE FLAGS(4); /* R__ */ + note PT_NOTE FLAGS(0); /* ___ */ } SECTIONS { @@ -40,26 +40,17 @@ SECTIONS _etext = .; /* End of text section */ } :text = 0x9090 + NOTES :text :note + . = ALIGN(16); /* Exception table */ __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) { __start___ex_table = .; *(__ex_table) __stop___ex_table = .; - } - - NOTES :text :note - - BUG_TABLE :text + } :text = 0x9090 RODATA - . = ALIGN(4); - .tracedata : AT(ADDR(.tracedata) - LOAD_OFFSET) { - __tracedata_start = .; - *(.tracedata) - __tracedata_end = .; - } - . = ALIGN(PAGE_SIZE); /* Align data segment to page size boundary */ /* Data */ .data : AT(ADDR(.data) - LOAD_OFFSET) { @@ -177,6 +168,7 @@ SECTIONS *(.con_initcall.init) } __con_initcall_end = .; + . = ALIGN(16); __x86cpuvendor_start = .; .x86cpuvendor.init : AT(ADDR(.x86cpuvendor.init) - LOAD_OFFSET) { *(.x86cpuvendor.init) diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index ba8c0b75ab0a..0c029e8959c7 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -15,9 +15,12 @@ #include <linux/init.h> #include <linux/pci_ids.h> #include <linux/pci_regs.h> + +#include <asm/apic.h> #include <asm/pci-direct.h> #include <asm/io.h> #include <asm/paravirt.h> +#include <asm/setup.h> #if defined CONFIG_PCI && defined CONFIG_PARAVIRT /* diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 61efa2f7d564..0b8b6690a86d 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -42,7 +42,8 @@ #include <asm/topology.h> #include <asm/vgtod.h> -#define __vsyscall(nr) __attribute__ ((unused,__section__(".vsyscall_" #nr))) +#define __vsyscall(nr) \ + __attribute__ ((unused, __section__(".vsyscall_" #nr))) notrace #define __syscall_clobber "r11","cx","memory" /* @@ -249,7 +250,7 @@ static ctl_table kernel_root_table2[] = { doesn't violate that. We'll find out if it does. */ static void __cpuinit vsyscall_set_cpu(int cpu) { - unsigned long *d; + unsigned long d; unsigned long node = 0; #ifdef CONFIG_NUMA node = cpu_to_node(cpu); @@ -260,11 +261,11 @@ static void __cpuinit vsyscall_set_cpu(int cpu) /* Store cpu number in limit so that it can be loaded quickly in user space in vgetcpu. 12 bits for the CPU and 8 bits for the node. */ - d = (unsigned long *)(get_cpu_gdt_table(cpu) + GDT_ENTRY_PER_CPU); - *d = 0x0f40000000000ULL; - *d |= cpu; - *d |= (node & 0xf) << 12; - *d |= (node >> 4) << 48; + d = 0x0f40000000000ULL; + d |= cpu; + d |= (node & 0xf) << 12; + d |= (node >> 4) << 48; + write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S); } static void __cpuinit cpu_vsyscall_init(void *arg) @@ -278,7 +279,7 @@ cpu_vsyscall_notifier(struct notifier_block *n, unsigned long action, void *arg) { long cpu = (long)arg; if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) - smp_call_function_single(cpu, cpu_vsyscall_init, NULL, 0, 1); + smp_call_function_single(cpu, cpu_vsyscall_init, NULL, 1); return NOTIFY_DONE; } @@ -301,7 +302,7 @@ static int __init vsyscall_init(void) #ifdef CONFIG_SYSCTL register_sysctl_table(kernel_root_table2); #endif - on_each_cpu(cpu_vsyscall_init, NULL, 0, 1); + on_each_cpu(cpu_vsyscall_init, NULL, 1); hotcpu_notifier(cpu_vsyscall_notifier, 0); return 0; } diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index f6c05d0410fb..b545f371b5f5 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -2,13 +2,20 @@ All C exports should go in the respective C files. */ #include <linux/module.h> -#include <net/checksum.h> #include <linux/smp.h> +#include <net/checksum.h> + #include <asm/processor.h> -#include <asm/uaccess.h> #include <asm/pgtable.h> +#include <asm/uaccess.h> #include <asm/desc.h> +#include <asm/ftrace.h> + +#ifdef CONFIG_FTRACE +/* mcount is defined in assembly */ +EXPORT_SYMBOL(mcount); +#endif EXPORT_SYMBOL(kernel_thread); @@ -53,8 +60,3 @@ EXPORT_SYMBOL(init_level4_pgt); EXPORT_SYMBOL(load_gs_index); EXPORT_SYMBOL(_proxy_pda); - -#ifdef CONFIG_PARAVIRT -/* Virtualized guests may want to use it */ -EXPORT_SYMBOL_GPL(cpu_gdt_descr); -#endif diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 7c077a9d9777..3829aa7b663f 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -200,10 +200,12 @@ int __pit_timer_fn(struct kvm_kpit_state *ps) atomic_inc(&pt->pending); smp_mb__after_atomic_inc(); - /* FIXME: handle case where the guest is in guest mode */ - if (vcpu0 && waitqueue_active(&vcpu0->wq)) { - vcpu0->arch.mp_state = KVM_MP_STATE_RUNNABLE; - wake_up_interruptible(&vcpu0->wq); + if (vcpu0) { + set_bit(KVM_REQ_PENDING_TIMER, &vcpu0->requests); + if (waitqueue_active(&vcpu0->wq)) { + vcpu0->arch.mp_state = KVM_MP_STATE_RUNNABLE; + wake_up_interruptible(&vcpu0->wq); + } } pt->timer.expires = ktime_add_ns(pt->timer.expires, pt->period); @@ -237,6 +239,19 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data) return HRTIMER_NORESTART; } +void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu) +{ + struct kvm_pit *pit = vcpu->kvm->arch.vpit; + struct hrtimer *timer; + + if (vcpu->vcpu_id != 0 || !pit) + return; + + timer = &pit->pit_state.pit_timer.timer; + if (hrtimer_cancel(timer)) + hrtimer_start(timer, timer->expires, HRTIMER_MODE_ABS); +} + static void destroy_pit_timer(struct kvm_kpit_timer *pt) { pr_debug("pit: execute del timer!\n"); diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index ce1f583459b1..76d736b5f664 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -94,3 +94,9 @@ void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec) /* TODO: PIT, RTC etc. */ } EXPORT_SYMBOL_GPL(kvm_timer_intr_post); + +void __kvm_migrate_timers(struct kvm_vcpu *vcpu) +{ + __kvm_migrate_apic_timer(vcpu); + __kvm_migrate_pit_timer(vcpu); +} diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 1802134b836f..2a15be2275c0 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -84,6 +84,8 @@ void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec); void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu); void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu); void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu); +void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu); +void __kvm_migrate_timers(struct kvm_vcpu *vcpu); int pit_has_pending_timer(struct kvm_vcpu *vcpu); int apic_has_pending_timer(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index c297c50eba63..ebc03f5ae162 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -940,6 +940,7 @@ static int __apic_timer_fn(struct kvm_lapic *apic) wait_queue_head_t *q = &apic->vcpu->wq; atomic_inc(&apic->timer.pending); + set_bit(KVM_REQ_PENDING_TIMER, &apic->vcpu->requests); if (waitqueue_active(q)) { apic->vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; wake_up_interruptible(q); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 7246b60afb96..7e7c3969f7a2 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -640,6 +640,7 @@ static void rmap_write_protect(struct kvm *kvm, u64 gfn) rmap_remove(kvm, spte); --kvm->stat.lpages; set_shadow_pte(spte, shadow_trap_nonpresent_pte); + spte = NULL; write_protected = 1; } spte = rmap_next(kvm, rmapp, spte); @@ -658,7 +659,7 @@ static int is_empty_shadow_page(u64 *spt) u64 *end; for (pos = spt, end = pos + PAGE_SIZE / sizeof(u64); pos != end; pos++) - if (*pos != shadow_trap_nonpresent_pte) { + if (is_shadow_present_pte(*pos)) { printk(KERN_ERR "%s: %p %llx\n", __func__, pos, *pos); return 0; @@ -1082,10 +1083,6 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, struct kvm_mmu_page *shadow; spte |= PT_WRITABLE_MASK; - if (user_fault) { - mmu_unshadow(vcpu->kvm, gfn); - goto unshadowed; - } shadow = kvm_mmu_lookup_page(vcpu->kvm, gfn); if (shadow || @@ -1102,8 +1099,6 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, } } -unshadowed: - if (pte_access & ACC_WRITE_MASK) mark_page_dirty(vcpu->kvm, gfn); @@ -1580,11 +1575,13 @@ static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu, u64 *spte, const void *new) { - if ((sp->role.level != PT_PAGE_TABLE_LEVEL) - && !vcpu->arch.update_pte.largepage) { - ++vcpu->kvm->stat.mmu_pde_zapped; - return; - } + if (sp->role.level != PT_PAGE_TABLE_LEVEL) { + if (!vcpu->arch.update_pte.largepage || + sp->role.glevels == PT32_ROOT_LEVEL) { + ++vcpu->kvm->stat.mmu_pde_zapped; + return; + } + } ++vcpu->kvm->stat.mmu_pte_updated; if (sp->role.glevels == PT32_ROOT_LEVEL) @@ -1858,6 +1855,7 @@ static void free_mmu_pages(struct kvm_vcpu *vcpu) sp = container_of(vcpu->kvm->arch.active_mmu_pages.next, struct kvm_mmu_page, link); kvm_mmu_zap_page(vcpu->kvm, sp); + cond_resched(); } free_page((unsigned long)vcpu->arch.mmu.pae_root); } diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 156fe10288ae..934c7b619396 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -418,7 +418,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, /* mmio */ if (is_error_pfn(pfn)) { - pgprintk("gfn %x is mmio\n", walker.gfn); + pgprintk("gfn %lx is mmio\n", walker.gfn); kvm_release_pfn_clean(pfn); return 1; } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index ab22615eee89..6b0d5fa5bab3 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -688,7 +688,7 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) delta = vcpu->arch.host_tsc - tsc_this; svm->vmcb->control.tsc_offset += delta; vcpu->cpu = cpu; - kvm_migrate_apic_timer(vcpu); + kvm_migrate_timers(vcpu); } for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index bfe4db11989c..10ce6ee4c491 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -335,7 +335,7 @@ static void vcpu_clear(struct vcpu_vmx *vmx) { if (vmx->vcpu.cpu == -1) return; - smp_call_function_single(vmx->vcpu.cpu, __vcpu_clear, vmx, 0, 1); + smp_call_function_single(vmx->vcpu.cpu, __vcpu_clear, vmx, 1); vmx->launched = 0; } @@ -566,7 +566,7 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu) load_transition_efer(vmx); } -static void vmx_load_host_state(struct vcpu_vmx *vmx) +static void __vmx_load_host_state(struct vcpu_vmx *vmx) { unsigned long flags; @@ -596,6 +596,13 @@ static void vmx_load_host_state(struct vcpu_vmx *vmx) reload_host_efer(vmx); } +static void vmx_load_host_state(struct vcpu_vmx *vmx) +{ + preempt_disable(); + __vmx_load_host_state(vmx); + preempt_enable(); +} + /* * Switches to specified vcpu, until a matching vcpu_put(), but assumes * vcpu mutex is already taken. @@ -608,7 +615,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (vcpu->cpu != cpu) { vcpu_clear(vmx); - kvm_migrate_apic_timer(vcpu); + kvm_migrate_timers(vcpu); vpid_sync_vcpu_all(vmx); } @@ -654,7 +661,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) static void vmx_vcpu_put(struct kvm_vcpu *vcpu) { - vmx_load_host_state(to_vmx(vcpu)); + __vmx_load_host_state(to_vmx(vcpu)); } static void vmx_fpu_activate(struct kvm_vcpu *vcpu) @@ -884,11 +891,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) switch (msr_index) { #ifdef CONFIG_X86_64 case MSR_EFER: + vmx_load_host_state(vmx); ret = kvm_set_msr_common(vcpu, msr_index, data); - if (vmx->host_state.loaded) { - reload_host_efer(vmx); - load_transition_efer(vmx); - } break; case MSR_FS_BASE: vmcs_writel(GUEST_FS_BASE, data); @@ -910,11 +914,10 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) guest_write_tsc(data); break; default: + vmx_load_host_state(vmx); msr = find_msr_entry(vmx, msr_index); if (msr) { msr->data = data; - if (vmx->host_state.loaded) - load_msrs(vmx->guest_msrs, vmx->save_nmsrs); break; } ret = kvm_set_msr_common(vcpu, msr_index, data); @@ -1036,6 +1039,7 @@ static void hardware_enable(void *garbage) static void hardware_disable(void *garbage) { asm volatile (ASM_VMX_VMXOFF : : : "cc"); + write_cr4(read_cr4() & ~X86_CR4_VMXE); } static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, @@ -2964,7 +2968,7 @@ static void vmx_free_vmcs(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); if (vmx->vmcs) { - on_each_cpu(__vcpu_clear, vmx, 0, 1); + on_each_cpu(__vcpu_clear, vmx, 1); free_vmcs(vmx->vmcs); vmx->vmcs = NULL; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 21338bdb28ff..0faa2546b1cd 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -492,8 +492,8 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) { static int version; - struct kvm_wall_clock wc; - struct timespec wc_ts; + struct pvclock_wall_clock wc; + struct timespec now, sys, boot; if (!wall_clock) return; @@ -502,10 +502,19 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) kvm_write_guest(kvm, wall_clock, &version, sizeof(version)); - wc_ts = current_kernel_time(); - wc.wc_sec = wc_ts.tv_sec; - wc.wc_nsec = wc_ts.tv_nsec; - wc.wc_version = version; + /* + * The guest calculates current wall clock time by adding + * system time (updated by kvm_write_guest_time below) to the + * wall clock specified here. guest system time equals host + * system time for us, thus we must fill in host boot time here. + */ + now = current_kernel_time(); + ktime_get_ts(&sys); + boot = ns_to_timespec(timespec_to_ns(&now) - timespec_to_ns(&sys)); + + wc.sec = boot.tv_sec; + wc.nsec = boot.tv_nsec; + wc.version = version; kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc)); @@ -513,6 +522,45 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) kvm_write_guest(kvm, wall_clock, &version, sizeof(version)); } +static uint32_t div_frac(uint32_t dividend, uint32_t divisor) +{ + uint32_t quotient, remainder; + + /* Don't try to replace with do_div(), this one calculates + * "(dividend << 32) / divisor" */ + __asm__ ( "divl %4" + : "=a" (quotient), "=d" (remainder) + : "0" (0), "1" (dividend), "r" (divisor) ); + return quotient; +} + +static void kvm_set_time_scale(uint32_t tsc_khz, struct pvclock_vcpu_time_info *hv_clock) +{ + uint64_t nsecs = 1000000000LL; + int32_t shift = 0; + uint64_t tps64; + uint32_t tps32; + + tps64 = tsc_khz * 1000LL; + while (tps64 > nsecs*2) { + tps64 >>= 1; + shift--; + } + + tps32 = (uint32_t)tps64; + while (tps32 <= (uint32_t)nsecs) { + tps32 <<= 1; + shift++; + } + + hv_clock->tsc_shift = shift; + hv_clock->tsc_to_system_mul = div_frac(nsecs, tps32); + + pr_debug("%s: tsc_khz %u, tsc_shift %d, tsc_mul %u\n", + __FUNCTION__, tsc_khz, hv_clock->tsc_shift, + hv_clock->tsc_to_system_mul); +} + static void kvm_write_guest_time(struct kvm_vcpu *v) { struct timespec ts; @@ -523,6 +571,11 @@ static void kvm_write_guest_time(struct kvm_vcpu *v) if ((!vcpu->time_page)) return; + if (unlikely(vcpu->hv_clock_tsc_khz != tsc_khz)) { + kvm_set_time_scale(tsc_khz, &vcpu->hv_clock); + vcpu->hv_clock_tsc_khz = tsc_khz; + } + /* Keep irq disabled to prevent changes to the clock */ local_irq_save(flags); kvm_get_msr(v, MSR_IA32_TIME_STAMP_COUNTER, @@ -537,14 +590,14 @@ static void kvm_write_guest_time(struct kvm_vcpu *v) /* * The interface expects us to write an even number signaling that the * update is finished. Since the guest won't see the intermediate - * state, we just write "2" at the end + * state, we just increase by 2 at the end. */ - vcpu->hv_clock.version = 2; + vcpu->hv_clock.version += 2; shared_kaddr = kmap_atomic(vcpu->time_page, KM_USER0); memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock, - sizeof(vcpu->hv_clock)); + sizeof(vcpu->hv_clock)); kunmap_atomic(shared_kaddr, KM_USER0); @@ -599,10 +652,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) /* ...but clean it before doing the actual write */ vcpu->arch.time_offset = data & ~(PAGE_MASK | 1); - vcpu->arch.hv_clock.tsc_to_system_mul = - clocksource_khz2mult(tsc_khz, 22); - vcpu->arch.hv_clock.tsc_shift = 22; - down_read(¤t->mm->mmap_sem); vcpu->arch.time_page = gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT); @@ -2758,7 +2807,9 @@ again: if (vcpu->requests) { if (test_and_clear_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests)) - __kvm_migrate_apic_timer(vcpu); + __kvm_migrate_timers(vcpu); + if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests)) + kvm_x86_ops->tlb_flush(vcpu); if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS, &vcpu->requests)) { kvm_run->exit_reason = KVM_EXIT_TPR_ACCESS; @@ -2772,6 +2823,7 @@ again: } } + clear_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests); kvm_inject_pending_timer_irqs(vcpu); preempt_disable(); @@ -2781,21 +2833,13 @@ again: local_irq_disable(); - if (need_resched()) { + if (vcpu->requests || need_resched()) { local_irq_enable(); preempt_enable(); r = 1; goto out; } - if (vcpu->requests) - if (test_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests)) { - local_irq_enable(); - preempt_enable(); - r = 1; - goto out; - } - if (signal_pending(current)) { local_irq_enable(); preempt_enable(); @@ -2825,9 +2869,6 @@ again: kvm_guest_enter(); - if (vcpu->requests) - if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests)) - kvm_x86_ops->tlb_flush(vcpu); KVMTRACE_0D(VMENTRY, vcpu, entryexit); kvm_x86_ops->run(vcpu, kvm_run); @@ -4003,6 +4044,6 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) * So need not to call smp_call_function_single() in that case. */ if (vcpu->guest_mode && vcpu->cpu != cpu) - smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0, 0); + smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0); put_cpu(); } diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c index 8a96320ab071..932f216d890c 100644 --- a/arch/x86/kvm/x86_emulate.c +++ b/arch/x86/kvm/x86_emulate.c @@ -1727,7 +1727,8 @@ twobyte_insn: if (rc) goto done; - kvm_emulate_hypercall(ctxt->vcpu); + /* Let the processor re-execute the fixed hypercall */ + c->eip = ctxt->vcpu->arch.rip; /* Disable writeback. */ c->dst.type = OP_NONE; break; diff --git a/arch/x86/lguest/Kconfig b/arch/x86/lguest/Kconfig index 964dfa36d367..c70e12b1a637 100644 --- a/arch/x86/lguest/Kconfig +++ b/arch/x86/lguest/Kconfig @@ -3,7 +3,7 @@ config LGUEST_GUEST select PARAVIRT depends on X86_32 depends on !X86_PAE - depends on !(X86_VISWS || X86_VOYAGER) + depends on !X86_VOYAGER select VIRTIO select VIRTIO_RING select VIRTIO_CONSOLE diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index af65b2da3ba0..50dad44fb542 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -582,8 +582,9 @@ static void __init lguest_init_IRQ(void) int vector = FIRST_EXTERNAL_VECTOR + i; if (vector != SYSCALL_VECTOR) { set_intr_gate(vector, interrupt[i]); - set_irq_chip_and_handler(i, &lguest_irq_controller, - handle_level_irq); + set_irq_chip_and_handler_name(i, &lguest_irq_controller, + handle_level_irq, + "level"); } } /* This call is required to set up for 4k stacks, where we have @@ -606,7 +607,7 @@ static unsigned long lguest_get_wallclock(void) * what speed it runs at, or 0 if it's unusable as a reliable clock source. * This matches what we want here: if we return 0 from this function, the x86 * TSC clock will give up and not register itself. */ -static unsigned long lguest_cpu_khz(void) +static unsigned long lguest_tsc_khz(void) { return lguest_data.tsc_khz; } @@ -834,7 +835,7 @@ static __init char *lguest_memory_setup(void) /* The Linux bootloader header contains an "e820" memory map: the * Launcher populated the first entry with our memory limit. */ - add_memory_region(boot_params.e820_map[0].addr, + e820_add_region(boot_params.e820_map[0].addr, boot_params.e820_map[0].size, boot_params.e820_map[0].type); @@ -997,7 +998,7 @@ __init void lguest_init(void) /* time operations */ pv_time_ops.get_wallclock = lguest_get_wallclock; pv_time_ops.time_init = lguest_time_init; - pv_time_ops.get_cpu_khz = lguest_cpu_khz; + pv_time_ops.get_tsc_khz = lguest_tsc_khz; /* Now is a good time to look at the implementations of these functions * before returning to the rest of lguest_init(). */ @@ -1011,6 +1012,7 @@ __init void lguest_init(void) * clobbered. The Launcher places our initial pagetables somewhere at * the top of our physical memory, so we don't need extra space: set * init_pg_tables_end to the end of the kernel. */ + init_pg_tables_start = __pa(pg0); init_pg_tables_end = __pa(pg0); /* Load the %fs segment register (the per-cpu segment register) with @@ -1064,9 +1066,9 @@ __init void lguest_init(void) pm_power_off = lguest_power_off; machine_ops.restart = lguest_restart; - /* Now we're set up, call start_kernel() in init/main.c and we proceed + /* Now we're set up, call i386_start_kernel() in head32.c and we proceed * to boot as normal. It never returns. */ - start_kernel(); + i386_start_kernel(); } /* * This marks the end of stage II of our journey, The Guest. diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 76f60f52a885..aa3fa4119424 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -4,8 +4,9 @@ obj-$(CONFIG_SMP) := msr-on-cpu.o -lib-y := delay_$(BITS).o -lib-y += usercopy_$(BITS).o getuser_$(BITS).o putuser_$(BITS).o +lib-y := delay.o +lib-y += thunk_$(BITS).o +lib-y += usercopy_$(BITS).o getuser.o putuser.o lib-y += memcpy_$(BITS).o ifeq ($(CONFIG_X86_32),y) diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 70bebd310408..dfdf428975c0 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -1,8 +1,10 @@ -/* Copyright 2002 Andi Kleen, SuSE Labs. +/* + * Copyright 2008 Vitaly Mayatskikh <vmayatsk@redhat.com> + * Copyright 2002 Andi Kleen, SuSE Labs. * Subject to the GNU Public License v2. - * - * Functions to copy from and to user space. - */ + * + * Functions to copy from and to user space. + */ #include <linux/linkage.h> #include <asm/dwarf2.h> @@ -20,60 +22,88 @@ .long \orig-1f /* by default jump to orig */ 1: .section .altinstr_replacement,"ax" -2: .byte 0xe9 /* near jump with 32bit immediate */ +2: .byte 0xe9 /* near jump with 32bit immediate */ .long \alt-1b /* offset */ /* or alternatively to alt */ .previous .section .altinstructions,"a" .align 8 .quad 0b .quad 2b - .byte \feature /* when feature is set */ + .byte \feature /* when feature is set */ .byte 5 .byte 5 .previous .endm -/* Standard copy_to_user with segment limit checking */ + .macro ALIGN_DESTINATION +#ifdef FIX_ALIGNMENT + /* check for bad alignment of destination */ + movl %edi,%ecx + andl $7,%ecx + jz 102f /* already aligned */ + subl $8,%ecx + negl %ecx + subl %ecx,%edx +100: movb (%rsi),%al +101: movb %al,(%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz 100b +102: + .section .fixup,"ax" +103: addl %r8d,%edx /* ecx is zerorest also */ + jmp copy_user_handle_tail + .previous + + .section __ex_table,"a" + .align 8 + .quad 100b,103b + .quad 101b,103b + .previous +#endif + .endm + +/* Standard copy_to_user with segment limit checking */ ENTRY(copy_to_user) CFI_STARTPROC GET_THREAD_INFO(%rax) movq %rdi,%rcx addq %rdx,%rcx - jc bad_to_user - cmpq threadinfo_addr_limit(%rax),%rcx + jc bad_to_user + cmpq TI_addr_limit(%rax),%rcx jae bad_to_user - xorl %eax,%eax /* clear zero flag */ ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string CFI_ENDPROC -ENTRY(copy_user_generic) +/* Standard copy_from_user with segment limit checking */ +ENTRY(copy_from_user) CFI_STARTPROC - movl $1,%ecx /* set zero flag */ + GET_THREAD_INFO(%rax) + movq %rsi,%rcx + addq %rdx,%rcx + jc bad_from_user + cmpq TI_addr_limit(%rax),%rcx + jae bad_from_user ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string CFI_ENDPROC +ENDPROC(copy_from_user) -ENTRY(__copy_from_user_inatomic) +ENTRY(copy_user_generic) CFI_STARTPROC - xorl %ecx,%ecx /* clear zero flag */ ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string CFI_ENDPROC +ENDPROC(copy_user_generic) -/* Standard copy_from_user with segment limit checking */ -ENTRY(copy_from_user) +ENTRY(__copy_from_user_inatomic) CFI_STARTPROC - GET_THREAD_INFO(%rax) - movq %rsi,%rcx - addq %rdx,%rcx - jc bad_from_user - cmpq threadinfo_addr_limit(%rax),%rcx - jae bad_from_user - movl $1,%ecx /* set zero flag */ ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string CFI_ENDPROC -ENDPROC(copy_from_user) - +ENDPROC(__copy_from_user_inatomic) + .section .fixup,"ax" /* must zero dest */ +ENTRY(bad_from_user) bad_from_user: CFI_STARTPROC movl %edx,%ecx @@ -81,274 +111,158 @@ bad_from_user: rep stosb bad_to_user: - movl %edx,%eax + movl %edx,%eax ret CFI_ENDPROC -END(bad_from_user) +ENDPROC(bad_from_user) .previous - - + /* * copy_user_generic_unrolled - memory copy with exception handling. - * This version is for CPUs like P4 that don't have efficient micro code for rep movsq - * - * Input: + * This version is for CPUs like P4 that don't have efficient micro + * code for rep movsq + * + * Input: * rdi destination * rsi source * rdx count - * ecx zero flag -- if true zero destination on error * - * Output: - * eax uncopied bytes or 0 if successful. + * Output: + * eax uncopied bytes or 0 if successfull. */ ENTRY(copy_user_generic_unrolled) CFI_STARTPROC - pushq %rbx - CFI_ADJUST_CFA_OFFSET 8 - CFI_REL_OFFSET rbx, 0 - pushq %rcx - CFI_ADJUST_CFA_OFFSET 8 - CFI_REL_OFFSET rcx, 0 - xorl %eax,%eax /*zero for the exception handler */ - -#ifdef FIX_ALIGNMENT - /* check for bad alignment of destination */ - movl %edi,%ecx - andl $7,%ecx - jnz .Lbad_alignment -.Lafter_bad_alignment: -#endif - - movq %rdx,%rcx - - movl $64,%ebx - shrq $6,%rdx - decq %rdx - js .Lhandle_tail - - .p2align 4 -.Lloop: -.Ls1: movq (%rsi),%r11 -.Ls2: movq 1*8(%rsi),%r8 -.Ls3: movq 2*8(%rsi),%r9 -.Ls4: movq 3*8(%rsi),%r10 -.Ld1: movq %r11,(%rdi) -.Ld2: movq %r8,1*8(%rdi) -.Ld3: movq %r9,2*8(%rdi) -.Ld4: movq %r10,3*8(%rdi) - -.Ls5: movq 4*8(%rsi),%r11 -.Ls6: movq 5*8(%rsi),%r8 -.Ls7: movq 6*8(%rsi),%r9 -.Ls8: movq 7*8(%rsi),%r10 -.Ld5: movq %r11,4*8(%rdi) -.Ld6: movq %r8,5*8(%rdi) -.Ld7: movq %r9,6*8(%rdi) -.Ld8: movq %r10,7*8(%rdi) - - decq %rdx - + cmpl $8,%edx + jb 20f /* less then 8 bytes, go to byte copy loop */ + ALIGN_DESTINATION + movl %edx,%ecx + andl $63,%edx + shrl $6,%ecx + jz 17f +1: movq (%rsi),%r8 +2: movq 1*8(%rsi),%r9 +3: movq 2*8(%rsi),%r10 +4: movq 3*8(%rsi),%r11 +5: movq %r8,(%rdi) +6: movq %r9,1*8(%rdi) +7: movq %r10,2*8(%rdi) +8: movq %r11,3*8(%rdi) +9: movq 4*8(%rsi),%r8 +10: movq 5*8(%rsi),%r9 +11: movq 6*8(%rsi),%r10 +12: movq 7*8(%rsi),%r11 +13: movq %r8,4*8(%rdi) +14: movq %r9,5*8(%rdi) +15: movq %r10,6*8(%rdi) +16: movq %r11,7*8(%rdi) leaq 64(%rsi),%rsi leaq 64(%rdi),%rdi - - jns .Lloop - - .p2align 4 -.Lhandle_tail: - movl %ecx,%edx - andl $63,%ecx - shrl $3,%ecx - jz .Lhandle_7 - movl $8,%ebx - .p2align 4 -.Lloop_8: -.Ls9: movq (%rsi),%r8 -.Ld9: movq %r8,(%rdi) decl %ecx - leaq 8(%rdi),%rdi + jnz 1b +17: movl %edx,%ecx + andl $7,%edx + shrl $3,%ecx + jz 20f +18: movq (%rsi),%r8 +19: movq %r8,(%rdi) leaq 8(%rsi),%rsi - jnz .Lloop_8 - -.Lhandle_7: + leaq 8(%rdi),%rdi + decl %ecx + jnz 18b +20: andl %edx,%edx + jz 23f movl %edx,%ecx - andl $7,%ecx - jz .Lende - .p2align 4 -.Lloop_1: -.Ls10: movb (%rsi),%bl -.Ld10: movb %bl,(%rdi) - incq %rdi +21: movb (%rsi),%al +22: movb %al,(%rdi) incq %rsi + incq %rdi decl %ecx - jnz .Lloop_1 - - CFI_REMEMBER_STATE -.Lende: - popq %rcx - CFI_ADJUST_CFA_OFFSET -8 - CFI_RESTORE rcx - popq %rbx - CFI_ADJUST_CFA_OFFSET -8 - CFI_RESTORE rbx + jnz 21b +23: xor %eax,%eax ret - CFI_RESTORE_STATE -#ifdef FIX_ALIGNMENT - /* align destination */ - .p2align 4 -.Lbad_alignment: - movl $8,%r9d - subl %ecx,%r9d - movl %r9d,%ecx - cmpq %r9,%rdx - jz .Lhandle_7 - js .Lhandle_7 -.Lalign_1: -.Ls11: movb (%rsi),%bl -.Ld11: movb %bl,(%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz .Lalign_1 - subq %r9,%rdx - jmp .Lafter_bad_alignment -#endif + .section .fixup,"ax" +30: shll $6,%ecx + addl %ecx,%edx + jmp 60f +40: lea (%rdx,%rcx,8),%rdx + jmp 60f +50: movl %ecx,%edx +60: jmp copy_user_handle_tail /* ecx is zerorest also */ + .previous - /* table sorted by exception address */ .section __ex_table,"a" .align 8 - .quad .Ls1,.Ls1e - .quad .Ls2,.Ls2e - .quad .Ls3,.Ls3e - .quad .Ls4,.Ls4e - .quad .Ld1,.Ls1e - .quad .Ld2,.Ls2e - .quad .Ld3,.Ls3e - .quad .Ld4,.Ls4e - .quad .Ls5,.Ls5e - .quad .Ls6,.Ls6e - .quad .Ls7,.Ls7e - .quad .Ls8,.Ls8e - .quad .Ld5,.Ls5e - .quad .Ld6,.Ls6e - .quad .Ld7,.Ls7e - .quad .Ld8,.Ls8e - .quad .Ls9,.Le_quad - .quad .Ld9,.Le_quad - .quad .Ls10,.Le_byte - .quad .Ld10,.Le_byte -#ifdef FIX_ALIGNMENT - .quad .Ls11,.Lzero_rest - .quad .Ld11,.Lzero_rest -#endif - .quad .Le5,.Le_zero + .quad 1b,30b + .quad 2b,30b + .quad 3b,30b + .quad 4b,30b + .quad 5b,30b + .quad 6b,30b + .quad 7b,30b + .quad 8b,30b + .quad 9b,30b + .quad 10b,30b + .quad 11b,30b + .quad 12b,30b + .quad 13b,30b + .quad 14b,30b + .quad 15b,30b + .quad 16b,30b + .quad 18b,40b + .quad 19b,40b + .quad 21b,50b + .quad 22b,50b .previous - - /* compute 64-offset for main loop. 8 bytes accuracy with error on the - pessimistic side. this is gross. it would be better to fix the - interface. */ - /* eax: zero, ebx: 64 */ -.Ls1e: addl $8,%eax -.Ls2e: addl $8,%eax -.Ls3e: addl $8,%eax -.Ls4e: addl $8,%eax -.Ls5e: addl $8,%eax -.Ls6e: addl $8,%eax -.Ls7e: addl $8,%eax -.Ls8e: addl $8,%eax - addq %rbx,%rdi /* +64 */ - subq %rax,%rdi /* correct destination with computed offset */ - - shlq $6,%rdx /* loop counter * 64 (stride length) */ - addq %rax,%rdx /* add offset to loopcnt */ - andl $63,%ecx /* remaining bytes */ - addq %rcx,%rdx /* add them */ - jmp .Lzero_rest - - /* exception on quad word loop in tail handling */ - /* ecx: loopcnt/8, %edx: length, rdi: correct */ -.Le_quad: - shll $3,%ecx - andl $7,%edx - addl %ecx,%edx - /* edx: bytes to zero, rdi: dest, eax:zero */ -.Lzero_rest: - cmpl $0,(%rsp) - jz .Le_zero - movq %rdx,%rcx -.Le_byte: - xorl %eax,%eax -.Le5: rep - stosb - /* when there is another exception while zeroing the rest just return */ -.Le_zero: - movq %rdx,%rax - jmp .Lende CFI_ENDPROC -ENDPROC(copy_user_generic) +ENDPROC(copy_user_generic_unrolled) - - /* Some CPUs run faster using the string copy instructions. - This is also a lot simpler. Use them when possible. - Patch in jmps to this code instead of copying it fully - to avoid unwanted aliasing in the exception tables. */ - - /* rdi destination - * rsi source - * rdx count - * ecx zero flag - * - * Output: - * eax uncopied bytes or 0 if successfull. - * - * Only 4GB of copy is supported. This shouldn't be a problem - * because the kernel normally only writes from/to page sized chunks - * even if user space passed a longer buffer. - * And more would be dangerous because both Intel and AMD have - * errata with rep movsq > 4GB. If someone feels the need to fix - * this please consider this. - */ +/* Some CPUs run faster using the string copy instructions. + * This is also a lot simpler. Use them when possible. + * + * Only 4GB of copy is supported. This shouldn't be a problem + * because the kernel normally only writes from/to page sized chunks + * even if user space passed a longer buffer. + * And more would be dangerous because both Intel and AMD have + * errata with rep movsq > 4GB. If someone feels the need to fix + * this please consider this. + * + * Input: + * rdi destination + * rsi source + * rdx count + * + * Output: + * eax uncopied bytes or 0 if successful. + */ ENTRY(copy_user_generic_string) CFI_STARTPROC - movl %ecx,%r8d /* save zero flag */ + andl %edx,%edx + jz 4f + cmpl $8,%edx + jb 2f /* less than 8 bytes, go to byte copy loop */ + ALIGN_DESTINATION movl %edx,%ecx shrl $3,%ecx - andl $7,%edx - jz 10f -1: rep - movsq - movl %edx,%ecx -2: rep - movsb -9: movl %ecx,%eax - ret - - /* multiple of 8 byte */ -10: rep + andl $7,%edx +1: rep movsq - xor %eax,%eax +2: movl %edx,%ecx +3: rep + movsb +4: xorl %eax,%eax ret - /* exception handling */ -3: lea (%rdx,%rcx,8),%rax /* exception on quad loop */ - jmp 6f -5: movl %ecx,%eax /* exception on byte loop */ - /* eax: left over bytes */ -6: testl %r8d,%r8d /* zero flag set? */ - jz 7f - movl %eax,%ecx /* initialize x86 loop counter */ - push %rax - xorl %eax,%eax -8: rep - stosb /* zero the rest */ -11: pop %rax -7: ret - CFI_ENDPROC -END(copy_user_generic_c) + .section .fixup,"ax" +11: lea (%rdx,%rcx,8),%rcx +12: movl %ecx,%edx /* ecx is zerorest also */ + jmp copy_user_handle_tail + .previous .section __ex_table,"a" - .quad 1b,3b - .quad 2b,5b - .quad 8b,11b - .quad 10b,3b + .align 8 + .quad 1b,11b + .quad 3b,12b .previous + CFI_ENDPROC +ENDPROC(copy_user_generic_string) diff --git a/arch/x86/lib/copy_user_nocache_64.S b/arch/x86/lib/copy_user_nocache_64.S index 5196762b3b0e..40e0e309d27e 100644 --- a/arch/x86/lib/copy_user_nocache_64.S +++ b/arch/x86/lib/copy_user_nocache_64.S @@ -1,4 +1,6 @@ -/* Copyright 2002 Andi Kleen, SuSE Labs. +/* + * Copyright 2008 Vitaly Mayatskikh <vmayatsk@redhat.com> + * Copyright 2002 Andi Kleen, SuSE Labs. * Subject to the GNU Public License v2. * * Functions to copy from and to user space. @@ -12,207 +14,125 @@ #include <asm/current.h> #include <asm/asm-offsets.h> #include <asm/thread_info.h> -#include <asm/cpufeature.h> - -/* - * copy_user_nocache - Uncached memory copy with exception handling - * This will force destination/source out of cache for more performance. - * - * Input: - * rdi destination - * rsi source - * rdx count - * rcx zero flag when 1 zero on exception - * - * Output: - * eax uncopied bytes or 0 if successful. - */ -ENTRY(__copy_user_nocache) - CFI_STARTPROC - pushq %rbx - CFI_ADJUST_CFA_OFFSET 8 - CFI_REL_OFFSET rbx, 0 - pushq %rcx /* save zero flag */ - CFI_ADJUST_CFA_OFFSET 8 - CFI_REL_OFFSET rcx, 0 - - xorl %eax,%eax /* zero for the exception handler */ + .macro ALIGN_DESTINATION #ifdef FIX_ALIGNMENT /* check for bad alignment of destination */ movl %edi,%ecx andl $7,%ecx - jnz .Lbad_alignment -.Lafter_bad_alignment: -#endif - - movq %rdx,%rcx - - movl $64,%ebx - shrq $6,%rdx - decq %rdx - js .Lhandle_tail - - .p2align 4 -.Lloop: -.Ls1: movq (%rsi),%r11 -.Ls2: movq 1*8(%rsi),%r8 -.Ls3: movq 2*8(%rsi),%r9 -.Ls4: movq 3*8(%rsi),%r10 -.Ld1: movnti %r11,(%rdi) -.Ld2: movnti %r8,1*8(%rdi) -.Ld3: movnti %r9,2*8(%rdi) -.Ld4: movnti %r10,3*8(%rdi) - -.Ls5: movq 4*8(%rsi),%r11 -.Ls6: movq 5*8(%rsi),%r8 -.Ls7: movq 6*8(%rsi),%r9 -.Ls8: movq 7*8(%rsi),%r10 -.Ld5: movnti %r11,4*8(%rdi) -.Ld6: movnti %r8,5*8(%rdi) -.Ld7: movnti %r9,6*8(%rdi) -.Ld8: movnti %r10,7*8(%rdi) + jz 102f /* already aligned */ + subl $8,%ecx + negl %ecx + subl %ecx,%edx +100: movb (%rsi),%al +101: movb %al,(%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz 100b +102: + .section .fixup,"ax" +103: addl %r8d,%edx /* ecx is zerorest also */ + jmp copy_user_handle_tail + .previous - dec %rdx + .section __ex_table,"a" + .align 8 + .quad 100b,103b + .quad 101b,103b + .previous +#endif + .endm +/* + * copy_user_nocache - Uncached memory copy with exception handling + * This will force destination/source out of cache for more performance. + */ +ENTRY(__copy_user_nocache) + CFI_STARTPROC + cmpl $8,%edx + jb 20f /* less then 8 bytes, go to byte copy loop */ + ALIGN_DESTINATION + movl %edx,%ecx + andl $63,%edx + shrl $6,%ecx + jz 17f +1: movq (%rsi),%r8 +2: movq 1*8(%rsi),%r9 +3: movq 2*8(%rsi),%r10 +4: movq 3*8(%rsi),%r11 +5: movnti %r8,(%rdi) +6: movnti %r9,1*8(%rdi) +7: movnti %r10,2*8(%rdi) +8: movnti %r11,3*8(%rdi) +9: movq 4*8(%rsi),%r8 +10: movq 5*8(%rsi),%r9 +11: movq 6*8(%rsi),%r10 +12: movq 7*8(%rsi),%r11 +13: movnti %r8,4*8(%rdi) +14: movnti %r9,5*8(%rdi) +15: movnti %r10,6*8(%rdi) +16: movnti %r11,7*8(%rdi) leaq 64(%rsi),%rsi leaq 64(%rdi),%rdi - - jns .Lloop - - .p2align 4 -.Lhandle_tail: - movl %ecx,%edx - andl $63,%ecx - shrl $3,%ecx - jz .Lhandle_7 - movl $8,%ebx - .p2align 4 -.Lloop_8: -.Ls9: movq (%rsi),%r8 -.Ld9: movnti %r8,(%rdi) decl %ecx - leaq 8(%rdi),%rdi + jnz 1b +17: movl %edx,%ecx + andl $7,%edx + shrl $3,%ecx + jz 20f +18: movq (%rsi),%r8 +19: movnti %r8,(%rdi) leaq 8(%rsi),%rsi - jnz .Lloop_8 - -.Lhandle_7: + leaq 8(%rdi),%rdi + decl %ecx + jnz 18b +20: andl %edx,%edx + jz 23f movl %edx,%ecx - andl $7,%ecx - jz .Lende - .p2align 4 -.Lloop_1: -.Ls10: movb (%rsi),%bl -.Ld10: movb %bl,(%rdi) - incq %rdi +21: movb (%rsi),%al +22: movb %al,(%rdi) incq %rsi + incq %rdi decl %ecx - jnz .Lloop_1 - - CFI_REMEMBER_STATE -.Lende: - popq %rcx - CFI_ADJUST_CFA_OFFSET -8 - CFI_RESTORE %rcx - popq %rbx - CFI_ADJUST_CFA_OFFSET -8 - CFI_RESTORE rbx + jnz 21b +23: xorl %eax,%eax sfence ret - CFI_RESTORE_STATE -#ifdef FIX_ALIGNMENT - /* align destination */ - .p2align 4 -.Lbad_alignment: - movl $8,%r9d - subl %ecx,%r9d - movl %r9d,%ecx - cmpq %r9,%rdx - jz .Lhandle_7 - js .Lhandle_7 -.Lalign_1: -.Ls11: movb (%rsi),%bl -.Ld11: movb %bl,(%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz .Lalign_1 - subq %r9,%rdx - jmp .Lafter_bad_alignment -#endif + .section .fixup,"ax" +30: shll $6,%ecx + addl %ecx,%edx + jmp 60f +40: lea (%rdx,%rcx,8),%rdx + jmp 60f +50: movl %ecx,%edx +60: sfence + movl %r8d,%ecx + jmp copy_user_handle_tail + .previous - /* table sorted by exception address */ .section __ex_table,"a" - .align 8 - .quad .Ls1,.Ls1e - .quad .Ls2,.Ls2e - .quad .Ls3,.Ls3e - .quad .Ls4,.Ls4e - .quad .Ld1,.Ls1e - .quad .Ld2,.Ls2e - .quad .Ld3,.Ls3e - .quad .Ld4,.Ls4e - .quad .Ls5,.Ls5e - .quad .Ls6,.Ls6e - .quad .Ls7,.Ls7e - .quad .Ls8,.Ls8e - .quad .Ld5,.Ls5e - .quad .Ld6,.Ls6e - .quad .Ld7,.Ls7e - .quad .Ld8,.Ls8e - .quad .Ls9,.Le_quad - .quad .Ld9,.Le_quad - .quad .Ls10,.Le_byte - .quad .Ld10,.Le_byte -#ifdef FIX_ALIGNMENT - .quad .Ls11,.Lzero_rest - .quad .Ld11,.Lzero_rest -#endif - .quad .Le5,.Le_zero + .quad 1b,30b + .quad 2b,30b + .quad 3b,30b + .quad 4b,30b + .quad 5b,30b + .quad 6b,30b + .quad 7b,30b + .quad 8b,30b + .quad 9b,30b + .quad 10b,30b + .quad 11b,30b + .quad 12b,30b + .quad 13b,30b + .quad 14b,30b + .quad 15b,30b + .quad 16b,30b + .quad 18b,40b + .quad 19b,40b + .quad 21b,50b + .quad 22b,50b .previous - - /* compute 64-offset for main loop. 8 bytes accuracy with error on the - pessimistic side. this is gross. it would be better to fix the - interface. */ - /* eax: zero, ebx: 64 */ -.Ls1e: addl $8,%eax -.Ls2e: addl $8,%eax -.Ls3e: addl $8,%eax -.Ls4e: addl $8,%eax -.Ls5e: addl $8,%eax -.Ls6e: addl $8,%eax -.Ls7e: addl $8,%eax -.Ls8e: addl $8,%eax - addq %rbx,%rdi /* +64 */ - subq %rax,%rdi /* correct destination with computed offset */ - - shlq $6,%rdx /* loop counter * 64 (stride length) */ - addq %rax,%rdx /* add offset to loopcnt */ - andl $63,%ecx /* remaining bytes */ - addq %rcx,%rdx /* add them */ - jmp .Lzero_rest - - /* exception on quad word loop in tail handling */ - /* ecx: loopcnt/8, %edx: length, rdi: correct */ -.Le_quad: - shll $3,%ecx - andl $7,%edx - addl %ecx,%edx - /* edx: bytes to zero, rdi: dest, eax:zero */ -.Lzero_rest: - cmpl $0,(%rsp) /* zero flag set? */ - jz .Le_zero - movq %rdx,%rcx -.Le_byte: - xorl %eax,%eax -.Le5: rep - stosb - /* when there is another exception while zeroing the rest just return */ -.Le_zero: - movq %rdx,%rax - jmp .Lende CFI_ENDPROC ENDPROC(__copy_user_nocache) - - diff --git a/arch/x86/lib/delay_32.c b/arch/x86/lib/delay.c index 4535e6d147ad..f4568605d7d5 100644 --- a/arch/x86/lib/delay_32.c +++ b/arch/x86/lib/delay.c @@ -3,6 +3,7 @@ * * Copyright (C) 1993 Linus Torvalds * Copyright (C) 1997 Martin Mares <mj@atrey.karlin.mff.cuni.cz> + * Copyright (C) 2008 Jiri Hladky <hladky _dot_ jiri _at_ gmail _dot_ com> * * The __delay function must _NOT_ be inlined as its execution time * depends wildly on alignment on many x86 processors. The additional @@ -28,29 +29,58 @@ /* simple loop based delay: */ static void delay_loop(unsigned long loops) { - int d0; - - __asm__ __volatile__( - "\tjmp 1f\n" - ".align 16\n" - "1:\tjmp 2f\n" - ".align 16\n" - "2:\tdecl %0\n\tjns 2b" - :"=&a" (d0) - :"0" (loops)); + asm volatile( + " test %0,%0 \n" + " jz 3f \n" + " jmp 1f \n" + + ".align 16 \n" + "1: jmp 2f \n" + + ".align 16 \n" + "2: dec %0 \n" + " jnz 2b \n" + "3: dec %0 \n" + + : /* we don't need output */ + :"a" (loops) + ); } /* TSC based delay: */ static void delay_tsc(unsigned long loops) { unsigned long bclock, now; + int cpu; - preempt_disable(); /* TSC's are per-cpu */ + preempt_disable(); + cpu = smp_processor_id(); rdtscl(bclock); - do { - rep_nop(); + for (;;) { rdtscl(now); - } while ((now-bclock) < loops); + if ((now - bclock) >= loops) + break; + + /* Allow RT tasks to run */ + preempt_enable(); + rep_nop(); + preempt_disable(); + + /* + * It is possible that we moved to another CPU, and + * since TSC's are per-cpu we need to calculate + * that. The delay must guarantee that we wait "at + * least" the amount of time. Being moved to another + * CPU could make the wait longer but we just need to + * make sure we waited long enough. Rebalance the + * counter for this CPU. + */ + if (unlikely(cpu != smp_processor_id())) { + loops -= (now - bclock); + cpu = smp_processor_id(); + rdtscl(bclock); + } + } preempt_enable(); } @@ -68,7 +98,7 @@ void use_tsc_delay(void) int __devinit read_current_timer(unsigned long *timer_val) { if (delay_fn == delay_tsc) { - rdtscl(*timer_val); + rdtscll(*timer_val); return 0; } return -1; @@ -78,31 +108,30 @@ void __delay(unsigned long loops) { delay_fn(loops); } +EXPORT_SYMBOL(__delay); inline void __const_udelay(unsigned long xloops) { int d0; xloops *= 4; - __asm__("mull %0" + asm("mull %%edx" :"=d" (xloops), "=&a" (d0) :"1" (xloops), "0" (cpu_data(raw_smp_processor_id()).loops_per_jiffy * (HZ/4))); __delay(++xloops); } +EXPORT_SYMBOL(__const_udelay); void __udelay(unsigned long usecs) { __const_udelay(usecs * 0x000010c7); /* 2**32 / 1000000 (rounded up) */ } +EXPORT_SYMBOL(__udelay); void __ndelay(unsigned long nsecs) { __const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */ } - -EXPORT_SYMBOL(__delay); -EXPORT_SYMBOL(__const_udelay); -EXPORT_SYMBOL(__udelay); EXPORT_SYMBOL(__ndelay); diff --git a/arch/x86/lib/delay_64.c b/arch/x86/lib/delay_64.c deleted file mode 100644 index bbc610518516..000000000000 --- a/arch/x86/lib/delay_64.c +++ /dev/null @@ -1,63 +0,0 @@ -/* - * Precise Delay Loops for x86-64 - * - * Copyright (C) 1993 Linus Torvalds - * Copyright (C) 1997 Martin Mares <mj@atrey.karlin.mff.cuni.cz> - * - * The __delay function must _NOT_ be inlined as its execution time - * depends wildly on alignment on many x86 processors. - */ - -#include <linux/module.h> -#include <linux/sched.h> -#include <linux/timex.h> -#include <linux/preempt.h> -#include <linux/delay.h> -#include <linux/init.h> - -#include <asm/delay.h> -#include <asm/msr.h> - -#ifdef CONFIG_SMP -#include <asm/smp.h> -#endif - -int __devinit read_current_timer(unsigned long *timer_value) -{ - rdtscll(*timer_value); - return 0; -} - -void __delay(unsigned long loops) -{ - unsigned bclock, now; - - preempt_disable(); /* TSC's are pre-cpu */ - rdtscl(bclock); - do { - rep_nop(); - rdtscl(now); - } - while ((now-bclock) < loops); - preempt_enable(); -} -EXPORT_SYMBOL(__delay); - -inline void __const_udelay(unsigned long xloops) -{ - __delay(((xloops * HZ * - cpu_data(raw_smp_processor_id()).loops_per_jiffy) >> 32) + 1); -} -EXPORT_SYMBOL(__const_udelay); - -void __udelay(unsigned long usecs) -{ - __const_udelay(usecs * 0x000010c7); /* 2**32 / 1000000 (rounded up) */ -} -EXPORT_SYMBOL(__udelay); - -void __ndelay(unsigned long nsecs) -{ - __const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */ -} -EXPORT_SYMBOL(__ndelay); diff --git a/arch/x86/lib/getuser_64.S b/arch/x86/lib/getuser.S index 5448876261f8..ad374003742f 100644 --- a/arch/x86/lib/getuser_64.S +++ b/arch/x86/lib/getuser.S @@ -3,6 +3,7 @@ * * (C) Copyright 1998 Linus Torvalds * (C) Copyright 2005 Andi Kleen + * (C) Copyright 2008 Glauber Costa * * These functions have a non-standard call interface * to make them more efficient, especially as they @@ -13,14 +14,13 @@ /* * __get_user_X * - * Inputs: %rcx contains the address. + * Inputs: %[r|e]ax contains the address. * The register is modified, but all changes are undone * before returning because the C code doesn't know about it. * - * Outputs: %rax is error code (0 or -EFAULT) - * %rdx contains zero-extended value - * - * %r8 is destroyed. + * Outputs: %[r|e]ax is error code (0 or -EFAULT) + * %[r|e]dx contains zero-extended value + * * * These functions should not modify any other registers, * as they get called from within inline assembly. @@ -32,78 +32,73 @@ #include <asm/errno.h> #include <asm/asm-offsets.h> #include <asm/thread_info.h> +#include <asm/asm.h> .text ENTRY(__get_user_1) CFI_STARTPROC - GET_THREAD_INFO(%r8) - cmpq threadinfo_addr_limit(%r8),%rcx + GET_THREAD_INFO(%_ASM_DX) + cmp TI_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user -1: movzb (%rcx),%edx - xorl %eax,%eax +1: movzb (%_ASM_AX),%edx + xor %eax,%eax ret CFI_ENDPROC ENDPROC(__get_user_1) ENTRY(__get_user_2) CFI_STARTPROC - GET_THREAD_INFO(%r8) - addq $1,%rcx - jc 20f - cmpq threadinfo_addr_limit(%r8),%rcx - jae 20f - decq %rcx -2: movzwl (%rcx),%edx - xorl %eax,%eax + add $1,%_ASM_AX + jc bad_get_user + GET_THREAD_INFO(%_ASM_DX) + cmp TI_addr_limit(%_ASM_DX),%_ASM_AX + jae bad_get_user +2: movzwl -1(%_ASM_AX),%edx + xor %eax,%eax ret -20: decq %rcx - jmp bad_get_user CFI_ENDPROC ENDPROC(__get_user_2) ENTRY(__get_user_4) CFI_STARTPROC - GET_THREAD_INFO(%r8) - addq $3,%rcx - jc 30f - cmpq threadinfo_addr_limit(%r8),%rcx - jae 30f - subq $3,%rcx -3: movl (%rcx),%edx - xorl %eax,%eax + add $3,%_ASM_AX + jc bad_get_user + GET_THREAD_INFO(%_ASM_DX) + cmp TI_addr_limit(%_ASM_DX),%_ASM_AX + jae bad_get_user +3: mov -3(%_ASM_AX),%edx + xor %eax,%eax ret -30: subq $3,%rcx - jmp bad_get_user CFI_ENDPROC ENDPROC(__get_user_4) +#ifdef CONFIG_X86_64 ENTRY(__get_user_8) CFI_STARTPROC - GET_THREAD_INFO(%r8) - addq $7,%rcx - jc 40f - cmpq threadinfo_addr_limit(%r8),%rcx - jae 40f - subq $7,%rcx -4: movq (%rcx),%rdx - xorl %eax,%eax + add $7,%_ASM_AX + jc bad_get_user + GET_THREAD_INFO(%_ASM_DX) + cmp TI_addr_limit(%_ASM_DX),%_ASM_AX + jae bad_get_user +4: movq -7(%_ASM_AX),%_ASM_DX + xor %eax,%eax ret -40: subq $7,%rcx - jmp bad_get_user CFI_ENDPROC ENDPROC(__get_user_8) +#endif bad_get_user: CFI_STARTPROC - xorl %edx,%edx - movq $(-EFAULT),%rax + xor %edx,%edx + mov $(-EFAULT),%_ASM_AX ret CFI_ENDPROC END(bad_get_user) .section __ex_table,"a" - .quad 1b,bad_get_user - .quad 2b,bad_get_user - .quad 3b,bad_get_user - .quad 4b,bad_get_user -.previous + _ASM_PTR 1b,bad_get_user + _ASM_PTR 2b,bad_get_user + _ASM_PTR 3b,bad_get_user +#ifdef CONFIG_X86_64 + _ASM_PTR 4b,bad_get_user +#endif diff --git a/arch/x86/lib/getuser_32.S b/arch/x86/lib/getuser_32.S deleted file mode 100644 index 6d84b53f12a2..000000000000 --- a/arch/x86/lib/getuser_32.S +++ /dev/null @@ -1,78 +0,0 @@ -/* - * __get_user functions. - * - * (C) Copyright 1998 Linus Torvalds - * - * These functions have a non-standard call interface - * to make them more efficient, especially as they - * return an error value in addition to the "real" - * return value. - */ -#include <linux/linkage.h> -#include <asm/dwarf2.h> -#include <asm/thread_info.h> - - -/* - * __get_user_X - * - * Inputs: %eax contains the address - * - * Outputs: %eax is error code (0 or -EFAULT) - * %edx contains zero-extended value - * - * These functions should not modify any other registers, - * as they get called from within inline assembly. - */ - -.text -ENTRY(__get_user_1) - CFI_STARTPROC - GET_THREAD_INFO(%edx) - cmpl TI_addr_limit(%edx),%eax - jae bad_get_user -1: movzbl (%eax),%edx - xorl %eax,%eax - ret - CFI_ENDPROC -ENDPROC(__get_user_1) - -ENTRY(__get_user_2) - CFI_STARTPROC - addl $1,%eax - jc bad_get_user - GET_THREAD_INFO(%edx) - cmpl TI_addr_limit(%edx),%eax - jae bad_get_user -2: movzwl -1(%eax),%edx - xorl %eax,%eax - ret - CFI_ENDPROC -ENDPROC(__get_user_2) - -ENTRY(__get_user_4) - CFI_STARTPROC - addl $3,%eax - jc bad_get_user - GET_THREAD_INFO(%edx) - cmpl TI_addr_limit(%edx),%eax - jae bad_get_user -3: movl -3(%eax),%edx - xorl %eax,%eax - ret - CFI_ENDPROC -ENDPROC(__get_user_4) - -bad_get_user: - CFI_STARTPROC - xorl %edx,%edx - movl $-14,%eax - ret - CFI_ENDPROC -END(bad_get_user) - -.section __ex_table,"a" - .long 1b,bad_get_user - .long 2b,bad_get_user - .long 3b,bad_get_user -.previous diff --git a/arch/x86/lib/msr-on-cpu.c b/arch/x86/lib/msr-on-cpu.c index 57d043fa893e..d5a2b39f882b 100644 --- a/arch/x86/lib/msr-on-cpu.c +++ b/arch/x86/lib/msr-on-cpu.c @@ -30,10 +30,10 @@ static int _rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h, int safe) rv.msr_no = msr_no; if (safe) { - smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 0, 1); + smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 1); err = rv.err; } else { - smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 0, 1); + smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 1); } *l = rv.l; *h = rv.h; @@ -64,10 +64,10 @@ static int _wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h, int safe) rv.l = l; rv.h = h; if (safe) { - smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 0, 1); + smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 1); err = rv.err; } else { - smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 0, 1); + smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 1); } return err; diff --git a/arch/x86/lib/putuser_32.S b/arch/x86/lib/putuser.S index f58fba109d18..36b0d15ae6e9 100644 --- a/arch/x86/lib/putuser_32.S +++ b/arch/x86/lib/putuser.S @@ -2,6 +2,8 @@ * __put_user functions. * * (C) Copyright 2005 Linus Torvalds + * (C) Copyright 2005 Andi Kleen + * (C) Copyright 2008 Glauber Costa * * These functions have a non-standard call interface * to make them more efficient, especially as they @@ -11,6 +13,8 @@ #include <linux/linkage.h> #include <asm/dwarf2.h> #include <asm/thread_info.h> +#include <asm/errno.h> +#include <asm/asm.h> /* @@ -26,73 +30,68 @@ */ #define ENTER CFI_STARTPROC ; \ - pushl %ebx ; \ - CFI_ADJUST_CFA_OFFSET 4 ; \ - CFI_REL_OFFSET ebx, 0 ; \ - GET_THREAD_INFO(%ebx) -#define EXIT popl %ebx ; \ - CFI_ADJUST_CFA_OFFSET -4 ; \ - CFI_RESTORE ebx ; \ - ret ; \ + GET_THREAD_INFO(%_ASM_BX) +#define EXIT ret ; \ CFI_ENDPROC .text ENTRY(__put_user_1) ENTER - cmpl TI_addr_limit(%ebx),%ecx + cmp TI_addr_limit(%_ASM_BX),%_ASM_CX jae bad_put_user -1: movb %al,(%ecx) - xorl %eax,%eax +1: movb %al,(%_ASM_CX) + xor %eax,%eax EXIT ENDPROC(__put_user_1) ENTRY(__put_user_2) ENTER - movl TI_addr_limit(%ebx),%ebx - subl $1,%ebx - cmpl %ebx,%ecx + mov TI_addr_limit(%_ASM_BX),%_ASM_BX + sub $1,%_ASM_BX + cmp %_ASM_BX,%_ASM_CX jae bad_put_user -2: movw %ax,(%ecx) - xorl %eax,%eax +2: movw %ax,(%_ASM_CX) + xor %eax,%eax EXIT ENDPROC(__put_user_2) ENTRY(__put_user_4) ENTER - movl TI_addr_limit(%ebx),%ebx - subl $3,%ebx - cmpl %ebx,%ecx + mov TI_addr_limit(%_ASM_BX),%_ASM_BX + sub $3,%_ASM_BX + cmp %_ASM_BX,%_ASM_CX jae bad_put_user -3: movl %eax,(%ecx) - xorl %eax,%eax +3: movl %eax,(%_ASM_CX) + xor %eax,%eax EXIT ENDPROC(__put_user_4) ENTRY(__put_user_8) ENTER - movl TI_addr_limit(%ebx),%ebx - subl $7,%ebx - cmpl %ebx,%ecx + mov TI_addr_limit(%_ASM_BX),%_ASM_BX + sub $7,%_ASM_BX + cmp %_ASM_BX,%_ASM_CX jae bad_put_user -4: movl %eax,(%ecx) -5: movl %edx,4(%ecx) - xorl %eax,%eax +4: mov %_ASM_AX,(%_ASM_CX) +#ifdef CONFIG_X86_32 +5: movl %edx,4(%_ASM_CX) +#endif + xor %eax,%eax EXIT ENDPROC(__put_user_8) bad_put_user: - CFI_STARTPROC simple - CFI_DEF_CFA esp, 2*4 - CFI_OFFSET eip, -1*4 - CFI_OFFSET ebx, -2*4 - movl $-14,%eax + CFI_STARTPROC + movl $-EFAULT,%eax EXIT END(bad_put_user) .section __ex_table,"a" - .long 1b,bad_put_user - .long 2b,bad_put_user - .long 3b,bad_put_user - .long 4b,bad_put_user - .long 5b,bad_put_user + _ASM_PTR 1b,bad_put_user + _ASM_PTR 2b,bad_put_user + _ASM_PTR 3b,bad_put_user + _ASM_PTR 4b,bad_put_user +#ifdef CONFIG_X86_32 + _ASM_PTR 5b,bad_put_user +#endif .previous diff --git a/arch/x86/lib/putuser_64.S b/arch/x86/lib/putuser_64.S deleted file mode 100644 index 4989f5a8fa9b..000000000000 --- a/arch/x86/lib/putuser_64.S +++ /dev/null @@ -1,106 +0,0 @@ -/* - * __put_user functions. - * - * (C) Copyright 1998 Linus Torvalds - * (C) Copyright 2005 Andi Kleen - * - * These functions have a non-standard call interface - * to make them more efficient, especially as they - * return an error value in addition to the "real" - * return value. - */ - -/* - * __put_user_X - * - * Inputs: %rcx contains the address - * %rdx contains new value - * - * Outputs: %rax is error code (0 or -EFAULT) - * - * %r8 is destroyed. - * - * These functions should not modify any other registers, - * as they get called from within inline assembly. - */ - -#include <linux/linkage.h> -#include <asm/dwarf2.h> -#include <asm/page.h> -#include <asm/errno.h> -#include <asm/asm-offsets.h> -#include <asm/thread_info.h> - - .text -ENTRY(__put_user_1) - CFI_STARTPROC - GET_THREAD_INFO(%r8) - cmpq threadinfo_addr_limit(%r8),%rcx - jae bad_put_user -1: movb %dl,(%rcx) - xorl %eax,%eax - ret - CFI_ENDPROC -ENDPROC(__put_user_1) - -ENTRY(__put_user_2) - CFI_STARTPROC - GET_THREAD_INFO(%r8) - addq $1,%rcx - jc 20f - cmpq threadinfo_addr_limit(%r8),%rcx - jae 20f - decq %rcx -2: movw %dx,(%rcx) - xorl %eax,%eax - ret -20: decq %rcx - jmp bad_put_user - CFI_ENDPROC -ENDPROC(__put_user_2) - -ENTRY(__put_user_4) - CFI_STARTPROC - GET_THREAD_INFO(%r8) - addq $3,%rcx - jc 30f - cmpq threadinfo_addr_limit(%r8),%rcx - jae 30f - subq $3,%rcx -3: movl %edx,(%rcx) - xorl %eax,%eax - ret -30: subq $3,%rcx - jmp bad_put_user - CFI_ENDPROC -ENDPROC(__put_user_4) - -ENTRY(__put_user_8) - CFI_STARTPROC - GET_THREAD_INFO(%r8) - addq $7,%rcx - jc 40f - cmpq threadinfo_addr_limit(%r8),%rcx - jae 40f - subq $7,%rcx -4: movq %rdx,(%rcx) - xorl %eax,%eax - ret -40: subq $7,%rcx - jmp bad_put_user - CFI_ENDPROC -ENDPROC(__put_user_8) - -bad_put_user: - CFI_STARTPROC - movq $(-EFAULT),%rax - ret - CFI_ENDPROC -END(bad_put_user) - -.section __ex_table,"a" - .quad 1b,bad_put_user - .quad 2b,bad_put_user - .quad 3b,bad_put_user - .quad 4b,bad_put_user -.previous diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/lib/thunk_32.S new file mode 100644 index 000000000000..650b11e00ecc --- /dev/null +++ b/arch/x86/lib/thunk_32.S @@ -0,0 +1,47 @@ +/* + * Trampoline to trace irqs off. (otherwise CALLER_ADDR1 might crash) + * Copyright 2008 by Steven Rostedt, Red Hat, Inc + * (inspired by Andi Kleen's thunk_64.S) + * Subject to the GNU public license, v.2. No warranty of any kind. + */ + + #include <linux/linkage.h> + +#define ARCH_TRACE_IRQS_ON \ + pushl %eax; \ + pushl %ecx; \ + pushl %edx; \ + call trace_hardirqs_on; \ + popl %edx; \ + popl %ecx; \ + popl %eax; + +#define ARCH_TRACE_IRQS_OFF \ + pushl %eax; \ + pushl %ecx; \ + pushl %edx; \ + call trace_hardirqs_off; \ + popl %edx; \ + popl %ecx; \ + popl %eax; + +#ifdef CONFIG_TRACE_IRQFLAGS + /* put return address in eax (arg1) */ + .macro thunk_ra name,func + .globl \name +\name: + pushl %eax + pushl %ecx + pushl %edx + /* Place EIP in the arg1 */ + movl 3*4(%esp), %eax + call \func + popl %edx + popl %ecx + popl %eax + ret + .endm + + thunk_ra trace_hardirqs_on_thunk,trace_hardirqs_on_caller + thunk_ra trace_hardirqs_off_thunk,trace_hardirqs_off_caller +#endif diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/lib/thunk_64.S index e009251d4e9f..bf9a7d5a5428 100644 --- a/arch/x86/lib/thunk_64.S +++ b/arch/x86/lib/thunk_64.S @@ -2,6 +2,7 @@ * Save registers before calling assembly functions. This avoids * disturbance of register allocation in some inline assembly constructs. * Copyright 2001,2002 by Andi Kleen, SuSE Labs. + * Added trace_hardirqs callers - Copyright 2007 Steven Rostedt, Red Hat, Inc. * Subject to the GNU public license, v.2. No warranty of any kind. */ @@ -42,8 +43,22 @@ #endif #ifdef CONFIG_TRACE_IRQFLAGS - thunk trace_hardirqs_on_thunk,trace_hardirqs_on - thunk trace_hardirqs_off_thunk,trace_hardirqs_off + /* put return address in rdi (arg1) */ + .macro thunk_ra name,func + .globl \name +\name: + CFI_STARTPROC + SAVE_ARGS + /* SAVE_ARGS pushs 9 elements */ + /* the next element would be the rip */ + movq 9*8(%rsp), %rdi + call \func + jmp restore + CFI_ENDPROC + .endm + + thunk_ra trace_hardirqs_on_thunk,trace_hardirqs_on_caller + thunk_ra trace_hardirqs_off_thunk,trace_hardirqs_off_caller #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index 0c89d1bb0287..f4df6e7c718b 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -158,3 +158,26 @@ unsigned long copy_in_user(void __user *to, const void __user *from, unsigned le } EXPORT_SYMBOL(copy_in_user); +/* + * Try to copy last bytes and clear the rest if needed. + * Since protection fault in copy_from/to_user is not a normal situation, + * it is not necessary to optimize tail handling. + */ +unsigned long +copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest) +{ + char c; + unsigned zero_len; + + for (; len; --len) { + if (__get_user_nocheck(c, from++, sizeof(char))) + break; + if (__put_user_nocheck(c, to++, sizeof(char))) + break; + } + + for (c = 0, zero_len = len; zerorest && zero_len; --zero_len) + if (__put_user_nocheck(c, to++, sizeof(char))) + break; + return len; +} diff --git a/arch/x86/mach-default/setup.c b/arch/x86/mach-default/setup.c index 0c28a071824c..48278fa7d3de 100644 --- a/arch/x86/mach-default/setup.c +++ b/arch/x86/mach-default/setup.c @@ -10,6 +10,14 @@ #include <asm/e820.h> #include <asm/setup.h> +/* + * Any quirks to be performed to initialize timers/irqs/etc? + */ +int (*arch_time_init_quirk)(void); +int (*arch_pre_intr_init_quirk)(void); +int (*arch_intr_init_quirk)(void); +int (*arch_trap_init_quirk)(void); + #ifdef CONFIG_HOTPLUG_CPU #define DEFAULT_SEND_IPI (1) #else @@ -29,6 +37,10 @@ int no_broadcast=DEFAULT_SEND_IPI; **/ void __init pre_intr_init_hook(void) { + if (arch_pre_intr_init_quirk) { + if (arch_pre_intr_init_quirk()) + return; + } init_ISA_irqs(); } @@ -52,6 +64,10 @@ static struct irqaction irq2 = { **/ void __init intr_init_hook(void) { + if (arch_intr_init_quirk) { + if (arch_intr_init_quirk()) + return; + } #ifdef CONFIG_X86_LOCAL_APIC apic_intr_init(); #endif @@ -65,7 +81,7 @@ void __init intr_init_hook(void) * * Description: * generally used to activate any machine specific identification - * routines that may be needed before setup_arch() runs. On VISWS + * routines that may be needed before setup_arch() runs. On Voyager * this is used to get the board revision and type. **/ void __init pre_setup_arch_hook(void) @@ -81,6 +97,10 @@ void __init pre_setup_arch_hook(void) **/ void __init trap_init_hook(void) { + if (arch_trap_init_quirk) { + if (arch_trap_init_quirk()) + return; + } } static struct irqaction irq0 = { @@ -99,6 +119,16 @@ static struct irqaction irq0 = { **/ void __init time_init_hook(void) { + if (arch_time_init_quirk) { + /* + * A nonzero return code does not mean failure, it means + * that the architecture quirk does not want any + * generic (timer) setup to be performed after this: + */ + if (arch_time_init_quirk()) + return; + } + irq0.mask = cpumask_of_cpu(0); setup_irq(0, &irq0); } @@ -142,45 +172,3 @@ static int __init print_ipi_mode(void) late_initcall(print_ipi_mode); -/** - * machine_specific_memory_setup - Hook for machine specific memory setup. - * - * Description: - * This is included late in kernel/setup.c so that it can make - * use of all of the static functions. - **/ - -char * __init machine_specific_memory_setup(void) -{ - char *who; - - - who = "BIOS-e820"; - - /* - * Try to copy the BIOS-supplied E820-map. - * - * Otherwise fake a memory map; one section from 0k->640k, - * the next section from 1mb->appropriate_mem_k - */ - sanitize_e820_map(boot_params.e820_map, &boot_params.e820_entries); - if (copy_e820_map(boot_params.e820_map, boot_params.e820_entries) - < 0) { - unsigned long mem_size; - - /* compare results from other methods and take the greater */ - if (boot_params.alt_mem_k - < boot_params.screen_info.ext_mem_k) { - mem_size = boot_params.screen_info.ext_mem_k; - who = "BIOS-88"; - } else { - mem_size = boot_params.alt_mem_k; - who = "BIOS-e801"; - } - - e820.nr_map = 0; - add_memory_region(0, LOWMEMSIZE(), E820_RAM); - add_memory_region(HIGH_MEMORY, mem_size << 10, E820_RAM); - } - return who; -} diff --git a/arch/x86/mach-es7000/Makefile b/arch/x86/mach-es7000/Makefile index 69dd4da218dc..3ef8b43b62fc 100644 --- a/arch/x86/mach-es7000/Makefile +++ b/arch/x86/mach-es7000/Makefile @@ -3,4 +3,3 @@ # obj-$(CONFIG_X86_ES7000) := es7000plat.o -obj-$(CONFIG_X86_GENERICARCH) := es7000plat.o diff --git a/arch/x86/mach-es7000/es7000plat.c b/arch/x86/mach-es7000/es7000plat.c index f5d6f7d8b86e..4354ce804889 100644 --- a/arch/x86/mach-es7000/es7000plat.c +++ b/arch/x86/mach-es7000/es7000plat.c @@ -52,6 +52,8 @@ static struct mip_reg *host_reg; static int mip_port; static unsigned long mip_addr, host_addr; +int es7000_plat; + /* * GSI override for ES7000 platforms. */ @@ -175,53 +177,6 @@ find_unisys_acpi_oem_table(unsigned long *oem_addr) } #endif -/* - * This file also gets compiled if CONFIG_X86_GENERICARCH is set. Generic - * arch already has got following function definitions (asm-generic/es7000.c) - * hence no need to define these for that case. - */ -#ifndef CONFIG_X86_GENERICARCH -void es7000_sw_apic(void); -void __init enable_apic_mode(void) -{ - es7000_sw_apic(); - return; -} - -__init int mps_oem_check(struct mp_config_table *mpc, char *oem, - char *productid) -{ - if (mpc->mpc_oemptr) { - struct mp_config_oemtable *oem_table = - (struct mp_config_oemtable *)mpc->mpc_oemptr; - if (!strncmp(oem, "UNISYS", 6)) - return parse_unisys_oem((char *)oem_table); - } - return 0; -} -#ifdef CONFIG_ACPI -/* Hook from generic ACPI tables.c */ -int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id) -{ - unsigned long oem_addr; - if (!find_unisys_acpi_oem_table(&oem_addr)) { - if (es7000_check_dsdt()) - return parse_unisys_oem((char *)oem_addr); - else { - setup_unisys(); - return 1; - } - } - return 0; -} -#else -int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id) -{ - return 0; -} -#endif -#endif /* COFIG_X86_GENERICARCH */ - static void es7000_spin(int n) { diff --git a/arch/x86/mach-generic/Makefile b/arch/x86/mach-generic/Makefile index 19d6d407737b..0dbd7803a1d5 100644 --- a/arch/x86/mach-generic/Makefile +++ b/arch/x86/mach-generic/Makefile @@ -2,7 +2,11 @@ # Makefile for the generic architecture # -EXTRA_CFLAGS := -Iarch/x86/kernel +EXTRA_CFLAGS := -Iarch/x86/kernel -obj-y := probe.o summit.o bigsmp.o es7000.o default.o -obj-y += ../../x86/mach-es7000/ +obj-y := probe.o default.o +obj-$(CONFIG_X86_NUMAQ) += numaq.o +obj-$(CONFIG_X86_SUMMIT) += summit.o +obj-$(CONFIG_X86_BIGSMP) += bigsmp.o +obj-$(CONFIG_X86_ES7000) += es7000.o +obj-$(CONFIG_X86_ES7000) += ../../x86/mach-es7000/ diff --git a/arch/x86/mach-generic/bigsmp.c b/arch/x86/mach-generic/bigsmp.c index 95fc463056d0..59d771714559 100644 --- a/arch/x86/mach-generic/bigsmp.c +++ b/arch/x86/mach-generic/bigsmp.c @@ -23,10 +23,8 @@ static int dmi_bigsmp; /* can be set by dmi scanners */ static int hp_ht_bigsmp(const struct dmi_system_id *d) { -#ifdef CONFIG_X86_GENERICARCH printk(KERN_NOTICE "%s detected: force use of apic=bigsmp\n", d->ident); dmi_bigsmp = 1; -#endif return 0; } @@ -48,7 +46,7 @@ static const struct dmi_system_id bigsmp_dmi_table[] = { static int probe_bigsmp(void) { if (def_to_bigsmp) - dmi_bigsmp = 1; + dmi_bigsmp = 1; else dmi_check_system(bigsmp_dmi_table); return dmi_bigsmp; diff --git a/arch/x86/mach-generic/numaq.c b/arch/x86/mach-generic/numaq.c new file mode 100644 index 000000000000..8091e68764c4 --- /dev/null +++ b/arch/x86/mach-generic/numaq.c @@ -0,0 +1,41 @@ +/* + * APIC driver for the IBM NUMAQ chipset. + */ +#define APIC_DEFINITION 1 +#include <linux/threads.h> +#include <linux/cpumask.h> +#include <linux/smp.h> +#include <asm/mpspec.h> +#include <asm/genapic.h> +#include <asm/fixmap.h> +#include <asm/apicdef.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/init.h> +#include <asm/mach-numaq/mach_apic.h> +#include <asm/mach-numaq/mach_apicdef.h> +#include <asm/mach-numaq/mach_ipi.h> +#include <asm/mach-numaq/mach_mpparse.h> +#include <asm/mach-numaq/mach_wakecpu.h> +#include <asm/numaq.h> + +static int mps_oem_check(struct mp_config_table *mpc, char *oem, + char *productid) +{ + numaq_mps_oem_check(mpc, oem, productid); + return found_numaq; +} + +static int probe_numaq(void) +{ + /* already know from get_memcfg_numaq() */ + return found_numaq; +} + +/* Hook from generic ACPI tables.c */ +static int acpi_madt_oem_check(char *oem_id, char *oem_table_id) +{ + return 0; +} + +struct genapic apic_numaq = APIC_INIT("NUMAQ", probe_numaq); diff --git a/arch/x86/mach-generic/probe.c b/arch/x86/mach-generic/probe.c index c5ae751b994a..5a7e4619e1c4 100644 --- a/arch/x86/mach-generic/probe.c +++ b/arch/x86/mach-generic/probe.c @@ -16,6 +16,7 @@ #include <asm/apicdef.h> #include <asm/genapic.h> +extern struct genapic apic_numaq; extern struct genapic apic_summit; extern struct genapic apic_bigsmp; extern struct genapic apic_es7000; @@ -24,9 +25,18 @@ extern struct genapic apic_default; struct genapic *genapic = &apic_default; static struct genapic *apic_probe[] __initdata = { +#ifdef CONFIG_X86_NUMAQ + &apic_numaq, +#endif +#ifdef CONFIG_X86_SUMMIT &apic_summit, +#endif +#ifdef CONFIG_X86_BIGSMP &apic_bigsmp, +#endif +#ifdef CONFIG_X86_ES7000 &apic_es7000, +#endif &apic_default, /* must be last */ NULL, }; @@ -54,6 +64,7 @@ early_param("apic", parse_apic); void __init generic_bigsmp_probe(void) { +#ifdef CONFIG_X86_BIGSMP /* * This routine is used to switch to bigsmp mode when * - There is no apic= option specified by the user @@ -67,6 +78,7 @@ void __init generic_bigsmp_probe(void) printk(KERN_INFO "Overriding APIC driver with %s\n", genapic->name); } +#endif } void __init generic_apic_probe(void) @@ -88,7 +100,8 @@ void __init generic_apic_probe(void) /* These functions can switch the APIC even after the initial ->probe() */ -int __init mps_oem_check(struct mp_config_table *mpc, char *oem, char *productid) +int __init mps_oem_check(struct mp_config_table *mpc, char *oem, + char *productid) { int i; for (i = 0; apic_probe[i]; ++i) { diff --git a/arch/x86/mach-visws/Makefile b/arch/x86/mach-visws/Makefile deleted file mode 100644 index 835fd96ad768..000000000000 --- a/arch/x86/mach-visws/Makefile +++ /dev/null @@ -1,8 +0,0 @@ -# -# Makefile for the linux kernel. -# - -obj-y := setup.o traps.o reboot.o - -obj-$(CONFIG_X86_VISWS_APIC) += visws_apic.o -obj-$(CONFIG_X86_LOCAL_APIC) += mpparse.o diff --git a/arch/x86/mach-visws/mpparse.c b/arch/x86/mach-visws/mpparse.c deleted file mode 100644 index 57484e91ab90..000000000000 --- a/arch/x86/mach-visws/mpparse.c +++ /dev/null @@ -1,88 +0,0 @@ - -#include <linux/init.h> -#include <linux/smp.h> - -#include <asm/smp.h> -#include <asm/io.h> - -#include "cobalt.h" -#include "mach_apic.h" - -/* Have we found an MP table */ -int smp_found_config; - -int pic_mode; - -extern unsigned int __cpuinitdata maxcpus; - -/* - * The Visual Workstation is Intel MP compliant in the hardware - * sense, but it doesn't have a BIOS(-configuration table). - * No problem for Linux. - */ - -static void __init MP_processor_info (struct mpc_config_processor *m) -{ - int ver, logical_apicid; - physid_mask_t apic_cpus; - - if (!(m->mpc_cpuflag & CPU_ENABLED)) - return; - - logical_apicid = m->mpc_apicid; - printk(KERN_INFO "%sCPU #%d %u:%u APIC version %d\n", - m->mpc_cpuflag & CPU_BOOTPROCESSOR ? "Bootup " : "", - m->mpc_apicid, - (m->mpc_cpufeature & CPU_FAMILY_MASK) >> 8, - (m->mpc_cpufeature & CPU_MODEL_MASK) >> 4, - m->mpc_apicver); - - if (m->mpc_cpuflag & CPU_BOOTPROCESSOR) - boot_cpu_physical_apicid = m->mpc_apicid; - - ver = m->mpc_apicver; - if ((ver >= 0x14 && m->mpc_apicid >= 0xff) || m->mpc_apicid >= 0xf) { - printk(KERN_ERR "Processor #%d INVALID. (Max ID: %d).\n", - m->mpc_apicid, MAX_APICS); - return; - } - - apic_cpus = apicid_to_cpu_present(m->mpc_apicid); - physids_or(phys_cpu_present_map, phys_cpu_present_map, apic_cpus); - /* - * Validate version - */ - if (ver == 0x0) { - printk(KERN_ERR "BIOS bug, APIC version is 0 for CPU#%d! " - "fixing up to 0x10. (tell your hw vendor)\n", - m->mpc_apicid); - ver = 0x10; - } - apic_version[m->mpc_apicid] = ver; -} - -void __init find_smp_config(void) -{ - struct mpc_config_processor *mp = phys_to_virt(CO_CPU_TAB_PHYS); - unsigned short ncpus = readw(phys_to_virt(CO_CPU_NUM_PHYS)); - - if (ncpus > CO_CPU_MAX) { - printk(KERN_WARNING "find_visws_smp: got cpu count of %d at %p\n", - ncpus, mp); - - ncpus = CO_CPU_MAX; - } - - if (ncpus > maxcpus) - ncpus = maxcpus; - - smp_found_config = 1; - while (ncpus--) - MP_processor_info(mp++); - - mp_lapic_addr = APIC_DEFAULT_PHYS_BASE; -} - -void __init get_smp_config (void) -{ -} diff --git a/arch/x86/mach-visws/reboot.c b/arch/x86/mach-visws/reboot.c deleted file mode 100644 index 99332abfad42..000000000000 --- a/arch/x86/mach-visws/reboot.c +++ /dev/null @@ -1,55 +0,0 @@ -#include <linux/module.h> -#include <linux/smp.h> -#include <linux/delay.h> - -#include <asm/io.h> -#include "piix4.h" - -void (*pm_power_off)(void); -EXPORT_SYMBOL(pm_power_off); - -void machine_shutdown(void) -{ -#ifdef CONFIG_SMP - smp_send_stop(); -#endif -} - -void machine_emergency_restart(void) -{ - /* - * Visual Workstations restart after this - * register is poked on the PIIX4 - */ - outb(PIIX4_RESET_VAL, PIIX4_RESET_PORT); -} - -void machine_restart(char * __unused) -{ - machine_shutdown(); - machine_emergency_restart(); -} - -void machine_power_off(void) -{ - unsigned short pm_status; - extern unsigned int pci_bus0; - - while ((pm_status = inw(PMSTS_PORT)) & 0x100) - outw(pm_status, PMSTS_PORT); - - outw(PM_SUSPEND_ENABLE, PMCNTRL_PORT); - - mdelay(10); - -#define PCI_CONF1_ADDRESS(bus, devfn, reg) \ - (0x80000000 | (bus << 16) | (devfn << 8) | (reg & ~3)) - - outl(PCI_CONF1_ADDRESS(pci_bus0, SPECIAL_DEV, SPECIAL_REG), 0xCF8); - outl(PIIX_SPECIAL_STOP, 0xCFC); -} - -void machine_halt(void) -{ -} - diff --git a/arch/x86/mach-visws/setup.c b/arch/x86/mach-visws/setup.c deleted file mode 100644 index de4c9dbd086f..000000000000 --- a/arch/x86/mach-visws/setup.c +++ /dev/null @@ -1,183 +0,0 @@ -/* - * Unmaintained SGI Visual Workstation support. - * Split out from setup.c by davej@suse.de - */ - -#include <linux/smp.h> -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/module.h> - -#include <asm/fixmap.h> -#include <asm/arch_hooks.h> -#include <asm/io.h> -#include <asm/e820.h> -#include <asm/setup.h> -#include "cobalt.h" -#include "piix4.h" - -int no_broadcast; - -char visws_board_type = -1; -char visws_board_rev = -1; - -void __init visws_get_board_type_and_rev(void) -{ - int raw; - - visws_board_type = (char)(inb_p(PIIX_GPI_BD_REG) & PIIX_GPI_BD_REG) - >> PIIX_GPI_BD_SHIFT; - /* - * Get Board rev. - * First, we have to initialize the 307 part to allow us access - * to the GPIO registers. Let's map them at 0x0fc0 which is right - * after the PIIX4 PM section. - */ - outb_p(SIO_DEV_SEL, SIO_INDEX); - outb_p(SIO_GP_DEV, SIO_DATA); /* Talk to GPIO regs. */ - - outb_p(SIO_DEV_MSB, SIO_INDEX); - outb_p(SIO_GP_MSB, SIO_DATA); /* MSB of GPIO base address */ - - outb_p(SIO_DEV_LSB, SIO_INDEX); - outb_p(SIO_GP_LSB, SIO_DATA); /* LSB of GPIO base address */ - - outb_p(SIO_DEV_ENB, SIO_INDEX); - outb_p(1, SIO_DATA); /* Enable GPIO registers. */ - - /* - * Now, we have to map the power management section to write - * a bit which enables access to the GPIO registers. - * What lunatic came up with this shit? - */ - outb_p(SIO_DEV_SEL, SIO_INDEX); - outb_p(SIO_PM_DEV, SIO_DATA); /* Talk to GPIO regs. */ - - outb_p(SIO_DEV_MSB, SIO_INDEX); - outb_p(SIO_PM_MSB, SIO_DATA); /* MSB of PM base address */ - - outb_p(SIO_DEV_LSB, SIO_INDEX); - outb_p(SIO_PM_LSB, SIO_DATA); /* LSB of PM base address */ - - outb_p(SIO_DEV_ENB, SIO_INDEX); - outb_p(1, SIO_DATA); /* Enable PM registers. */ - - /* - * Now, write the PM register which enables the GPIO registers. - */ - outb_p(SIO_PM_FER2, SIO_PM_INDEX); - outb_p(SIO_PM_GP_EN, SIO_PM_DATA); - - /* - * Now, initialize the GPIO registers. - * We want them all to be inputs which is the - * power on default, so let's leave them alone. - * So, let's just read the board rev! - */ - raw = inb_p(SIO_GP_DATA1); - raw &= 0x7f; /* 7 bits of valid board revision ID. */ - - if (visws_board_type == VISWS_320) { - if (raw < 0x6) { - visws_board_rev = 4; - } else if (raw < 0xc) { - visws_board_rev = 5; - } else { - visws_board_rev = 6; - } - } else if (visws_board_type == VISWS_540) { - visws_board_rev = 2; - } else { - visws_board_rev = raw; - } - - printk(KERN_INFO "Silicon Graphics Visual Workstation %s (rev %d) detected\n", - (visws_board_type == VISWS_320 ? "320" : - (visws_board_type == VISWS_540 ? "540" : - "unknown")), visws_board_rev); -} - -void __init pre_intr_init_hook(void) -{ - init_VISWS_APIC_irqs(); -} - -void __init intr_init_hook(void) -{ -#ifdef CONFIG_X86_LOCAL_APIC - apic_intr_init(); -#endif -} - -void __init pre_setup_arch_hook() -{ - visws_get_board_type_and_rev(); -} - -static struct irqaction irq0 = { - .handler = timer_interrupt, - .flags = IRQF_DISABLED | IRQF_IRQPOLL, - .name = "timer", -}; - -void __init time_init_hook(void) -{ - printk(KERN_INFO "Starting Cobalt Timer system clock\n"); - - /* Set the countdown value */ - co_cpu_write(CO_CPU_TIMEVAL, CO_TIME_HZ/HZ); - - /* Start the timer */ - co_cpu_write(CO_CPU_CTRL, co_cpu_read(CO_CPU_CTRL) | CO_CTRL_TIMERUN); - - /* Enable (unmask) the timer interrupt */ - co_cpu_write(CO_CPU_CTRL, co_cpu_read(CO_CPU_CTRL) & ~CO_CTRL_TIMEMASK); - - /* Wire cpu IDT entry to s/w handler (and Cobalt APIC to IDT) */ - setup_irq(0, &irq0); -} - -/* Hook for machine specific memory setup. */ - -#define MB (1024 * 1024) - -unsigned long sgivwfb_mem_phys; -unsigned long sgivwfb_mem_size; -EXPORT_SYMBOL(sgivwfb_mem_phys); -EXPORT_SYMBOL(sgivwfb_mem_size); - -long long mem_size __initdata = 0; - -char * __init machine_specific_memory_setup(void) -{ - long long gfx_mem_size = 8 * MB; - - mem_size = boot_params.alt_mem_k; - - if (!mem_size) { - printk(KERN_WARNING "Bootloader didn't set memory size, upgrade it !\n"); - mem_size = 128 * MB; - } - - /* - * this hardcodes the graphics memory to 8 MB - * it really should be sized dynamically (or at least - * set as a boot param) - */ - if (!sgivwfb_mem_size) { - printk(KERN_WARNING "Defaulting to 8 MB framebuffer size\n"); - sgivwfb_mem_size = 8 * MB; - } - - /* - * Trim to nearest MB - */ - sgivwfb_mem_size &= ~((1 << 20) - 1); - sgivwfb_mem_phys = mem_size - gfx_mem_size; - - add_memory_region(0, LOWMEMSIZE(), E820_RAM); - add_memory_region(HIGH_MEMORY, mem_size - sgivwfb_mem_size - HIGH_MEMORY, E820_RAM); - add_memory_region(sgivwfb_mem_phys, sgivwfb_mem_size, E820_RESERVED); - - return "PROM"; -} diff --git a/arch/x86/mach-visws/traps.c b/arch/x86/mach-visws/traps.c deleted file mode 100644 index bfac6ba10f8a..000000000000 --- a/arch/x86/mach-visws/traps.c +++ /dev/null @@ -1,69 +0,0 @@ -/* VISWS traps */ - -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/pci.h> -#include <linux/pci_ids.h> - -#include <asm/io.h> -#include <asm/arch_hooks.h> -#include <asm/apic.h> -#include "cobalt.h" -#include "lithium.h" - - -#define A01234 (LI_INTA_0 | LI_INTA_1 | LI_INTA_2 | LI_INTA_3 | LI_INTA_4) -#define BCD (LI_INTB | LI_INTC | LI_INTD) -#define ALLDEVS (A01234 | BCD) - -static __init void lithium_init(void) -{ - set_fixmap(FIX_LI_PCIA, LI_PCI_A_PHYS); - set_fixmap(FIX_LI_PCIB, LI_PCI_B_PHYS); - - if ((li_pcia_read16(PCI_VENDOR_ID) != PCI_VENDOR_ID_SGI) || - (li_pcia_read16(PCI_DEVICE_ID) != PCI_DEVICE_ID_SGI_LITHIUM)) { - printk(KERN_EMERG "Lithium hostbridge %c not found\n", 'A'); - panic("This machine is not SGI Visual Workstation 320/540"); - } - - if ((li_pcib_read16(PCI_VENDOR_ID) != PCI_VENDOR_ID_SGI) || - (li_pcib_read16(PCI_DEVICE_ID) != PCI_DEVICE_ID_SGI_LITHIUM)) { - printk(KERN_EMERG "Lithium hostbridge %c not found\n", 'B'); - panic("This machine is not SGI Visual Workstation 320/540"); - } - - li_pcia_write16(LI_PCI_INTEN, ALLDEVS); - li_pcib_write16(LI_PCI_INTEN, ALLDEVS); -} - -static __init void cobalt_init(void) -{ - /* - * On normal SMP PC this is used only with SMP, but we have to - * use it and set it up here to start the Cobalt clock - */ - set_fixmap(FIX_APIC_BASE, APIC_DEFAULT_PHYS_BASE); - setup_local_APIC(); - printk(KERN_INFO "Local APIC Version %#x, ID %#x\n", - (unsigned int)apic_read(APIC_LVR), - (unsigned int)apic_read(APIC_ID)); - - set_fixmap(FIX_CO_CPU, CO_CPU_PHYS); - set_fixmap(FIX_CO_APIC, CO_APIC_PHYS); - printk(KERN_INFO "Cobalt Revision %#lx, APIC ID %#lx\n", - co_cpu_read(CO_CPU_REV), co_apic_read(CO_APIC_ID)); - - /* Enable Cobalt APIC being careful to NOT change the ID! */ - co_apic_write(CO_APIC_ID, co_apic_read(CO_APIC_ID) | CO_APIC_ENABLE); - - printk(KERN_INFO "Cobalt APIC enabled: ID reg %#lx\n", - co_apic_read(CO_APIC_ID)); -} - -void __init trap_init_hook(void) -{ - lithium_init(); - cobalt_init(); -} diff --git a/arch/x86/mach-visws/visws_apic.c b/arch/x86/mach-visws/visws_apic.c deleted file mode 100644 index cef9cb1d15ac..000000000000 --- a/arch/x86/mach-visws/visws_apic.c +++ /dev/null @@ -1,297 +0,0 @@ -/* - * Copyright (C) 1999 Bent Hagemark, Ingo Molnar - * - * SGI Visual Workstation interrupt controller - * - * The Cobalt system ASIC in the Visual Workstation contains a "Cobalt" APIC - * which serves as the main interrupt controller in the system. Non-legacy - * hardware in the system uses this controller directly. Legacy devices - * are connected to the PIIX4 which in turn has its 8259(s) connected to - * a of the Cobalt APIC entry. - * - * 09/02/2000 - Updated for 2.4 by jbarnes@sgi.com - * - * 25/11/2002 - Updated for 2.5 by Andrey Panin <pazke@orbita1.ru> - */ - -#include <linux/kernel_stat.h> -#include <linux/interrupt.h> -#include <linux/init.h> - -#include <asm/io.h> -#include <asm/apic.h> -#include <asm/i8259.h> - -#include "cobalt.h" -#include "irq_vectors.h" - - -static DEFINE_SPINLOCK(cobalt_lock); - -/* - * Set the given Cobalt APIC Redirection Table entry to point - * to the given IDT vector/index. - */ -static inline void co_apic_set(int entry, int irq) -{ - co_apic_write(CO_APIC_LO(entry), CO_APIC_LEVEL | (irq + FIRST_EXTERNAL_VECTOR)); - co_apic_write(CO_APIC_HI(entry), 0); -} - -/* - * Cobalt (IO)-APIC functions to handle PCI devices. - */ -static inline int co_apic_ide0_hack(void) -{ - extern char visws_board_type; - extern char visws_board_rev; - - if (visws_board_type == VISWS_320 && visws_board_rev == 5) - return 5; - return CO_APIC_IDE0; -} - -static int is_co_apic(unsigned int irq) -{ - if (IS_CO_APIC(irq)) - return CO_APIC(irq); - - switch (irq) { - case 0: return CO_APIC_CPU; - case CO_IRQ_IDE0: return co_apic_ide0_hack(); - case CO_IRQ_IDE1: return CO_APIC_IDE1; - default: return -1; - } -} - - -/* - * This is the SGI Cobalt (IO-)APIC: - */ - -static void enable_cobalt_irq(unsigned int irq) -{ - co_apic_set(is_co_apic(irq), irq); -} - -static void disable_cobalt_irq(unsigned int irq) -{ - int entry = is_co_apic(irq); - - co_apic_write(CO_APIC_LO(entry), CO_APIC_MASK); - co_apic_read(CO_APIC_LO(entry)); -} - -/* - * "irq" really just serves to identify the device. Here is where we - * map this to the Cobalt APIC entry where it's physically wired. - * This is called via request_irq -> setup_irq -> irq_desc->startup() - */ -static unsigned int startup_cobalt_irq(unsigned int irq) -{ - unsigned long flags; - - spin_lock_irqsave(&cobalt_lock, flags); - if ((irq_desc[irq].status & (IRQ_DISABLED | IRQ_INPROGRESS | IRQ_WAITING))) - irq_desc[irq].status &= ~(IRQ_DISABLED | IRQ_INPROGRESS | IRQ_WAITING); - enable_cobalt_irq(irq); - spin_unlock_irqrestore(&cobalt_lock, flags); - return 0; -} - -static void ack_cobalt_irq(unsigned int irq) -{ - unsigned long flags; - - spin_lock_irqsave(&cobalt_lock, flags); - disable_cobalt_irq(irq); - apic_write(APIC_EOI, APIC_EIO_ACK); - spin_unlock_irqrestore(&cobalt_lock, flags); -} - -static void end_cobalt_irq(unsigned int irq) -{ - unsigned long flags; - - spin_lock_irqsave(&cobalt_lock, flags); - if (!(irq_desc[irq].status & (IRQ_DISABLED | IRQ_INPROGRESS))) - enable_cobalt_irq(irq); - spin_unlock_irqrestore(&cobalt_lock, flags); -} - -static struct irq_chip cobalt_irq_type = { - .typename = "Cobalt-APIC", - .startup = startup_cobalt_irq, - .shutdown = disable_cobalt_irq, - .enable = enable_cobalt_irq, - .disable = disable_cobalt_irq, - .ack = ack_cobalt_irq, - .end = end_cobalt_irq, -}; - - -/* - * This is the PIIX4-based 8259 that is wired up indirectly to Cobalt - * -- not the manner expected by the code in i8259.c. - * - * there is a 'master' physical interrupt source that gets sent to - * the CPU. But in the chipset there are various 'virtual' interrupts - * waiting to be handled. We represent this to Linux through a 'master' - * interrupt controller type, and through a special virtual interrupt- - * controller. Device drivers only see the virtual interrupt sources. - */ -static unsigned int startup_piix4_master_irq(unsigned int irq) -{ - init_8259A(0); - - return startup_cobalt_irq(irq); -} - -static void end_piix4_master_irq(unsigned int irq) -{ - unsigned long flags; - - spin_lock_irqsave(&cobalt_lock, flags); - enable_cobalt_irq(irq); - spin_unlock_irqrestore(&cobalt_lock, flags); -} - -static struct irq_chip piix4_master_irq_type = { - .typename = "PIIX4-master", - .startup = startup_piix4_master_irq, - .ack = ack_cobalt_irq, - .end = end_piix4_master_irq, -}; - - -static struct irq_chip piix4_virtual_irq_type = { - .typename = "PIIX4-virtual", - .shutdown = disable_8259A_irq, - .enable = enable_8259A_irq, - .disable = disable_8259A_irq, -}; - - -/* - * PIIX4-8259 master/virtual functions to handle interrupt requests - * from legacy devices: floppy, parallel, serial, rtc. - * - * None of these get Cobalt APIC entries, neither do they have IDT - * entries. These interrupts are purely virtual and distributed from - * the 'master' interrupt source: CO_IRQ_8259. - * - * When the 8259 interrupts its handler figures out which of these - * devices is interrupting and dispatches to its handler. - * - * CAREFUL: devices see the 'virtual' interrupt only. Thus disable/ - * enable_irq gets the right irq. This 'master' irq is never directly - * manipulated by any driver. - */ -static irqreturn_t piix4_master_intr(int irq, void *dev_id) -{ - int realirq; - irq_desc_t *desc; - unsigned long flags; - - spin_lock_irqsave(&i8259A_lock, flags); - - /* Find out what's interrupting in the PIIX4 master 8259 */ - outb(0x0c, 0x20); /* OCW3 Poll command */ - realirq = inb(0x20); - - /* - * Bit 7 == 0 means invalid/spurious - */ - if (unlikely(!(realirq & 0x80))) - goto out_unlock; - - realirq &= 7; - - if (unlikely(realirq == 2)) { - outb(0x0c, 0xa0); - realirq = inb(0xa0); - - if (unlikely(!(realirq & 0x80))) - goto out_unlock; - - realirq = (realirq & 7) + 8; - } - - /* mask and ack interrupt */ - cached_irq_mask |= 1 << realirq; - if (unlikely(realirq > 7)) { - inb(0xa1); - outb(cached_slave_mask, 0xa1); - outb(0x60 + (realirq & 7), 0xa0); - outb(0x60 + 2, 0x20); - } else { - inb(0x21); - outb(cached_master_mask, 0x21); - outb(0x60 + realirq, 0x20); - } - - spin_unlock_irqrestore(&i8259A_lock, flags); - - desc = irq_desc + realirq; - - /* - * handle this 'virtual interrupt' as a Cobalt one now. - */ - kstat_cpu(smp_processor_id()).irqs[realirq]++; - - if (likely(desc->action != NULL)) - handle_IRQ_event(realirq, desc->action); - - if (!(desc->status & IRQ_DISABLED)) - enable_8259A_irq(realirq); - - return IRQ_HANDLED; - -out_unlock: - spin_unlock_irqrestore(&i8259A_lock, flags); - return IRQ_NONE; -} - -static struct irqaction master_action = { - .handler = piix4_master_intr, - .name = "PIIX4-8259", -}; - -static struct irqaction cascade_action = { - .handler = no_action, - .name = "cascade", -}; - - -void init_VISWS_APIC_irqs(void) -{ - int i; - - for (i = 0; i < CO_IRQ_APIC0 + CO_APIC_LAST + 1; i++) { - irq_desc[i].status = IRQ_DISABLED; - irq_desc[i].action = 0; - irq_desc[i].depth = 1; - - if (i == 0) { - irq_desc[i].chip = &cobalt_irq_type; - } - else if (i == CO_IRQ_IDE0) { - irq_desc[i].chip = &cobalt_irq_type; - } - else if (i == CO_IRQ_IDE1) { - irq_desc[i].chip = &cobalt_irq_type; - } - else if (i == CO_IRQ_8259) { - irq_desc[i].chip = &piix4_master_irq_type; - } - else if (i < CO_IRQ_APIC0) { - irq_desc[i].chip = &piix4_virtual_irq_type; - } - else if (IS_CO_APIC(i)) { - irq_desc[i].chip = &cobalt_irq_type; - } - } - - setup_irq(CO_IRQ_8259, &master_action); - setup_irq(2, &cascade_action); -} diff --git a/arch/x86/mach-voyager/setup.c b/arch/x86/mach-voyager/setup.c index 5ae5466b9eb9..6bbdd633864c 100644 --- a/arch/x86/mach-voyager/setup.c +++ b/arch/x86/mach-voyager/setup.c @@ -62,6 +62,7 @@ void __init time_init_hook(void) char *__init machine_specific_memory_setup(void) { char *who; + int new_nr; who = "NOT VOYAGER"; @@ -73,7 +74,7 @@ char *__init machine_specific_memory_setup(void) e820.nr_map = 0; for (i = 0; voyager_memory_detect(i, &addr, &length); i++) { - add_memory_region(addr, length, E820_RAM); + e820_add_region(addr, length, E820_RAM); } return who; } else if (voyager_level == 4) { @@ -91,43 +92,17 @@ char *__init machine_specific_memory_setup(void) tom = (boot_params.screen_info.ext_mem_k) << 10; } who = "Voyager-TOM"; - add_memory_region(0, 0x9f000, E820_RAM); + e820_add_region(0, 0x9f000, E820_RAM); /* map from 1M to top of memory */ - add_memory_region(1 * 1024 * 1024, tom - 1 * 1024 * 1024, + e820_add_region(1 * 1024 * 1024, tom - 1 * 1024 * 1024, E820_RAM); /* FIXME: Should check the ASICs to see if I need to * take out the 8M window. Just do it at the moment * */ - add_memory_region(8 * 1024 * 1024, 8 * 1024 * 1024, + e820_add_region(8 * 1024 * 1024, 8 * 1024 * 1024, E820_RESERVED); return who; } - who = "BIOS-e820"; - - /* - * Try to copy the BIOS-supplied E820-map. - * - * Otherwise fake a memory map; one section from 0k->640k, - * the next section from 1mb->appropriate_mem_k - */ - sanitize_e820_map(boot_params.e820_map, &boot_params.e820_entries); - if (copy_e820_map(boot_params.e820_map, boot_params.e820_entries) - < 0) { - unsigned long mem_size; - - /* compare results from other methods and take the greater */ - if (boot_params.alt_mem_k < boot_params.screen_info.ext_mem_k) { - mem_size = boot_params.screen_info.ext_mem_k; - who = "BIOS-88"; - } else { - mem_size = boot_params.alt_mem_k; - who = "BIOS-e801"; - } - - e820.nr_map = 0; - add_memory_region(0, LOWMEMSIZE(), E820_RAM); - add_memory_region(HIGH_MEMORY, mem_size << 10, E820_RAM); - } - return who; + return default_machine_specific_memory_setup(); } diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c index 8acbf0cdf1a5..ee0fba092157 100644 --- a/arch/x86/mach-voyager/voyager_smp.c +++ b/arch/x86/mach-voyager/voyager_smp.c @@ -59,11 +59,6 @@ __u32 voyager_quad_processors = 0; * activity count. Finally exported by i386_ksyms.c */ static int voyager_extended_cpus = 1; -/* Have we found an SMP box - used by time.c to do the profiling - interrupt for timeslicing; do not set to 1 until the per CPU timer - interrupt is active */ -int smp_found_config = 0; - /* Used for the invalidate map that's also checked in the spinlock */ static volatile unsigned long smp_invalidate_needed; @@ -955,94 +950,24 @@ static void smp_stop_cpu_function(void *dummy) halt(); } -static DEFINE_SPINLOCK(call_lock); - -struct call_data_struct { - void (*func) (void *info); - void *info; - volatile unsigned long started; - volatile unsigned long finished; - int wait; -}; - -static struct call_data_struct *call_data; - /* execute a thread on a new CPU. The function to be called must be * previously set up. This is used to schedule a function for * execution on all CPUs - set up the function then broadcast a * function_interrupt CPI to come here on each CPU */ static void smp_call_function_interrupt(void) { - void (*func) (void *info) = call_data->func; - void *info = call_data->info; - /* must take copy of wait because call_data may be replaced - * unless the function is waiting for us to finish */ - int wait = call_data->wait; - __u8 cpu = smp_processor_id(); - - /* - * Notify initiating CPU that I've grabbed the data and am - * about to execute the function - */ - mb(); - if (!test_and_clear_bit(cpu, &call_data->started)) { - /* If the bit wasn't set, this could be a replay */ - printk(KERN_WARNING "VOYAGER SMP: CPU %d received call funtion" - " with no call pending\n", cpu); - return; - } - /* - * At this point the info structure may be out of scope unless wait==1 - */ irq_enter(); - (*func) (info); + generic_smp_call_function_interrupt(); __get_cpu_var(irq_stat).irq_call_count++; irq_exit(); - if (wait) { - mb(); - clear_bit(cpu, &call_data->finished); - } } -static int -voyager_smp_call_function_mask(cpumask_t cpumask, - void (*func) (void *info), void *info, int wait) +static void smp_call_function_single_interrupt(void) { - struct call_data_struct data; - u32 mask = cpus_addr(cpumask)[0]; - - mask &= ~(1 << smp_processor_id()); - - if (!mask) - return 0; - - /* Can deadlock when called with interrupts disabled */ - WARN_ON(irqs_disabled()); - - data.func = func; - data.info = info; - data.started = mask; - data.wait = wait; - if (wait) - data.finished = mask; - - spin_lock(&call_lock); - call_data = &data; - wmb(); - /* Send a message to all other CPUs and wait for them to respond */ - send_CPI(mask, VIC_CALL_FUNCTION_CPI); - - /* Wait for response */ - while (data.started) - barrier(); - - if (wait) - while (data.finished) - barrier(); - - spin_unlock(&call_lock); - - return 0; + irq_enter(); + generic_smp_call_function_single_interrupt(); + __get_cpu_var(irq_stat).irq_call_count++; + irq_exit(); } /* Sorry about the name. In an APIC based system, the APICs @@ -1099,6 +1024,12 @@ void smp_qic_call_function_interrupt(struct pt_regs *regs) smp_call_function_interrupt(); } +void smp_qic_call_function_single_interrupt(struct pt_regs *regs) +{ + ack_QIC_CPI(QIC_CALL_FUNCTION_SINGLE_CPI); + smp_call_function_single_interrupt(); +} + void smp_vic_cpi_interrupt(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); @@ -1119,6 +1050,8 @@ void smp_vic_cpi_interrupt(struct pt_regs *regs) smp_enable_irq_interrupt(); if (test_and_clear_bit(VIC_CALL_FUNCTION_CPI, &vic_cpi_mailbox[cpu])) smp_call_function_interrupt(); + if (test_and_clear_bit(VIC_CALL_FUNCTION_SINGLE_CPI, &vic_cpi_mailbox[cpu])) + smp_call_function_single_interrupt(); set_irq_regs(old_regs); } @@ -1134,16 +1067,7 @@ static void do_flush_tlb_all(void *info) /* flush the TLB of every active CPU in the system */ void flush_tlb_all(void) { - on_each_cpu(do_flush_tlb_all, 0, 1, 1); -} - -/* used to set up the trampoline for other CPUs when the memory manager - * is sorted out */ -void __init smp_alloc_memory(void) -{ - trampoline_base = alloc_bootmem_low_pages(PAGE_SIZE); - if (__pa(trampoline_base) >= 0x93000) - BUG(); + on_each_cpu(do_flush_tlb_all, 0, 1); } /* send a reschedule CPI to one CPU by physical CPU number*/ @@ -1175,7 +1099,7 @@ int safe_smp_processor_id(void) /* broadcast a halt to all other CPUs */ static void voyager_smp_send_stop(void) { - smp_call_function(smp_stop_cpu_function, NULL, 1, 1); + smp_call_function(smp_stop_cpu_function, NULL, 1); } /* this function is triggered in time.c when a clock tick fires @@ -1862,5 +1786,7 @@ struct smp_ops smp_ops = { .smp_send_stop = voyager_smp_send_stop, .smp_send_reschedule = voyager_smp_send_reschedule, - .smp_call_function_mask = voyager_smp_call_function_mask, + + .send_call_func_ipi = native_send_call_func_ipi, + .send_call_func_single_ipi = native_send_call_func_single_ipi, }; diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c index 6e38d877ea77..c7b06feb139b 100644 --- a/arch/x86/math-emu/fpu_entry.c +++ b/arch/x86/math-emu/fpu_entry.c @@ -30,6 +30,7 @@ #include <asm/uaccess.h> #include <asm/desc.h> #include <asm/user.h> +#include <asm/i387.h> #include "fpu_system.h" #include "fpu_emu.h" @@ -146,6 +147,13 @@ asmlinkage void math_emulate(long arg) unsigned long code_limit = 0; /* Initialized to stop compiler warnings */ struct desc_struct code_descriptor; + if (!used_math()) { + if (init_fpu(current)) { + do_group_exit(SIGKILL); + return; + } + } + #ifdef RE_ENTRANT_CHECKING if (emulating) { printk("ERROR: wm-FPU-emu is not RE-ENTRANT!\n"); @@ -153,11 +161,6 @@ asmlinkage void math_emulate(long arg) RE_ENTRANT_CHECK_ON; #endif /* RE_ENTRANT_CHECKING */ - if (!used_math()) { - finit(); - set_used_math(); - } - SETUP_DATA_AREA(arg); FPU_ORIG_EIP = FPU_EIP; diff --git a/arch/x86/math-emu/reg_constant.c b/arch/x86/math-emu/reg_constant.c index 04869e64b18e..00548354912f 100644 --- a/arch/x86/math-emu/reg_constant.c +++ b/arch/x86/math-emu/reg_constant.c @@ -16,8 +16,8 @@ #include "reg_constant.h" #include "control_w.h" -#define MAKE_REG(s,e,l,h) { l, h, \ - ((EXTENDED_Ebias+(e)) | ((SIGN_##s != 0)*0x8000)) } +#define MAKE_REG(s, e, l, h) { l, h, \ + ((EXTENDED_Ebias+(e)) | ((SIGN_##s != 0)*0x8000)) } FPU_REG const CONST_1 = MAKE_REG(POS, 0, 0x00000000, 0x80000000); #if 0 @@ -40,7 +40,7 @@ FPU_REG const CONST_PI2extra = MAKE_REG(NEG, -66, FPU_REG const CONST_Z = MAKE_REG(POS, EXP_UNDER, 0x0, 0x0); /* Only the sign and significand (and tag) are used in internal NaNs */ -/* The 80486 never generates one of these +/* The 80486 never generates one of these FPU_REG const CONST_SNAN = MAKE_REG(POS, EXP_OVER, 0x00000001, 0x80000000); */ /* This is the real indefinite QNaN */ @@ -49,7 +49,7 @@ FPU_REG const CONST_QNaN = MAKE_REG(NEG, EXP_OVER, 0x00000000, 0xC0000000); /* Only the sign (and tag) is used in internal infinities */ FPU_REG const CONST_INF = MAKE_REG(POS, EXP_OVER, 0x00000000, 0x80000000); -static void fld_const(FPU_REG const *c, int adj, u_char tag) +static void fld_const(FPU_REG const * c, int adj, u_char tag) { FPU_REG *st_new_ptr; diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index b7b3e4c7cfc9..9873716e9f76 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -8,10 +8,16 @@ obj-$(CONFIG_X86_PTDUMP) += dump_pagetables.o obj-$(CONFIG_HIGHMEM) += highmem_32.o +obj-$(CONFIG_MMIOTRACE_HOOKS) += kmmio.o +obj-$(CONFIG_MMIOTRACE) += mmiotrace.o +mmiotrace-y := pf_in.o mmio-mod.o +obj-$(CONFIG_MMIOTRACE_TEST) += testmmiotrace.o + ifeq ($(CONFIG_X86_32),y) obj-$(CONFIG_NUMA) += discontig_32.o else obj-$(CONFIG_NUMA) += numa_64.o obj-$(CONFIG_K8_NUMA) += k8topology_64.o -obj-$(CONFIG_ACPI_NUMA) += srat_64.o endif +obj-$(CONFIG_ACPI_NUMA) += srat_$(BITS).o + diff --git a/arch/x86/mm/discontig_32.c b/arch/x86/mm/discontig_32.c index 914ccf983687..5dfef9fa061a 100644 --- a/arch/x86/mm/discontig_32.c +++ b/arch/x86/mm/discontig_32.c @@ -38,6 +38,7 @@ #include <asm/setup.h> #include <asm/mmzone.h> #include <asm/bios_ebda.h> +#include <asm/proto.h> struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); @@ -59,14 +60,14 @@ unsigned long node_end_pfn[MAX_NUMNODES] __read_mostly; /* * 4) physnode_map - the mapping between a pfn and owning node * physnode_map keeps track of the physical memory layout of a generic - * numa node on a 256Mb break (each element of the array will - * represent 256Mb of memory and will be marked by the node id. so, + * numa node on a 64Mb break (each element of the array will + * represent 64Mb of memory and will be marked by the node id. so, * if the first gig is on node 0, and the second gig is on node 1 * physnode_map will contain: * - * physnode_map[0-3] = 0; - * physnode_map[4-7] = 1; - * physnode_map[8- ] = -1; + * physnode_map[0-15] = 0; + * physnode_map[16-31] = 1; + * physnode_map[32- ] = -1; */ s8 physnode_map[MAX_ELEMENTS] __read_mostly = { [0 ... (MAX_ELEMENTS - 1)] = -1}; EXPORT_SYMBOL(physnode_map); @@ -75,15 +76,15 @@ void memory_present(int nid, unsigned long start, unsigned long end) { unsigned long pfn; - printk(KERN_INFO "Node: %d, start_pfn: %ld, end_pfn: %ld\n", + printk(KERN_INFO "Node: %d, start_pfn: %lx, end_pfn: %lx\n", nid, start, end); printk(KERN_DEBUG " Setting physnode_map array to node %d for pfns:\n", nid); printk(KERN_DEBUG " "); for (pfn = start; pfn < end; pfn += PAGES_PER_ELEMENT) { physnode_map[pfn / PAGES_PER_ELEMENT] = nid; - printk("%ld ", pfn); + printk(KERN_CONT "%lx ", pfn); } - printk("\n"); + printk(KERN_CONT "\n"); } unsigned long node_memmap_size_bytes(int nid, unsigned long start_pfn, @@ -99,7 +100,6 @@ unsigned long node_memmap_size_bytes(int nid, unsigned long start_pfn, #endif extern unsigned long find_max_low_pfn(void); -extern void add_one_highpage_init(struct page *, int, int); extern unsigned long highend_pfn, highstart_pfn; #define LARGE_PAGE_BYTES (PTRS_PER_PTE * PAGE_SIZE) @@ -117,13 +117,13 @@ static unsigned long kva_pages; */ int __init get_memcfg_numa_flat(void) { - printk("NUMA - single node, flat memory mode\n"); + printk(KERN_DEBUG "NUMA - single node, flat memory mode\n"); - /* Run the memory configuration and find the top of memory. */ - propagate_e820_map(); node_start_pfn[0] = 0; node_end_pfn[0] = max_pfn; + e820_register_active_regions(0, 0, max_pfn); memory_present(0, 0, max_pfn); + node_remap_size[0] = node_memmap_size_bytes(0, 0, max_pfn); /* Indicate there is one node available. */ nodes_clear(node_online_map); @@ -156,24 +156,32 @@ static void __init propagate_e820_map_node(int nid) */ static void __init allocate_pgdat(int nid) { - if (nid && node_has_online_mem(nid)) + char buf[16]; + + if (node_has_online_mem(nid) && node_remap_start_vaddr[nid]) NODE_DATA(nid) = (pg_data_t *)node_remap_start_vaddr[nid]; else { - NODE_DATA(nid) = (pg_data_t *)(pfn_to_kaddr(min_low_pfn)); - min_low_pfn += PFN_UP(sizeof(pg_data_t)); + unsigned long pgdat_phys; + pgdat_phys = find_e820_area(min_low_pfn<<PAGE_SHIFT, + max_pfn_mapped<<PAGE_SHIFT, + sizeof(pg_data_t), + PAGE_SIZE); + NODE_DATA(nid) = (pg_data_t *)(pfn_to_kaddr(pgdat_phys>>PAGE_SHIFT)); + memset(buf, 0, sizeof(buf)); + sprintf(buf, "NODE_DATA %d", nid); + reserve_early(pgdat_phys, pgdat_phys + sizeof(pg_data_t), buf); } + printk(KERN_DEBUG "allocate_pgdat: node %d NODE_DATA %08lx\n", + nid, (unsigned long)NODE_DATA(nid)); } -#ifdef CONFIG_DISCONTIGMEM /* - * In the discontig memory model, a portion of the kernel virtual area (KVA) - * is reserved and portions of nodes are mapped using it. This is to allow - * node-local memory to be allocated for structures that would normally require - * ZONE_NORMAL. The memory is allocated with alloc_remap() and callers - * should be prepared to allocate from the bootmem allocator instead. This KVA - * mechanism is incompatible with SPARSEMEM as it makes assumptions about the - * layout of memory that are broken if alloc_remap() succeeds for some of the - * map and fails for others + * In the DISCONTIGMEM and SPARSEMEM memory model, a portion of the kernel + * virtual address space (KVA) is reserved and portions of nodes are mapped + * using it. This is to allow node-local memory to be allocated for + * structures that would normally require ZONE_NORMAL. The memory is + * allocated with alloc_remap() and callers should be prepared to allocate + * from the bootmem allocator instead. */ static unsigned long node_remap_start_pfn[MAX_NUMNODES]; static void *node_remap_end_vaddr[MAX_NUMNODES]; @@ -195,15 +203,19 @@ void *alloc_remap(int nid, unsigned long size) return allocation; } -void __init remap_numa_kva(void) +static void __init remap_numa_kva(void) { void *vaddr; unsigned long pfn; int node; for_each_online_node(node) { + printk(KERN_DEBUG "remap_numa_kva: node %d\n", node); for (pfn=0; pfn < node_remap_size[node]; pfn += PTRS_PER_PTE) { vaddr = node_remap_start_vaddr[node]+(pfn<<PAGE_SHIFT); + printk(KERN_DEBUG "remap_numa_kva: %08lx to pfn %08lx\n", + (unsigned long)vaddr, + node_remap_start_pfn[node] + pfn); set_pmd_pfn((ulong) vaddr, node_remap_start_pfn[node] + pfn, PAGE_KERNEL_LARGE); @@ -215,17 +227,21 @@ static unsigned long calculate_numa_remap_pages(void) { int nid; unsigned long size, reserve_pages = 0; - unsigned long pfn; for_each_online_node(nid) { - unsigned old_end_pfn = node_end_pfn[nid]; + u64 node_kva_target; + u64 node_kva_final; /* * The acpi/srat node info can show hot-add memroy zones * where memory could be added but not currently present. */ + printk(KERN_DEBUG "node %d pfn: [%lx - %lx]\n", + nid, node_start_pfn[nid], node_end_pfn[nid]); if (node_start_pfn[nid] > max_pfn) continue; + if (!node_end_pfn[nid]) + continue; if (node_end_pfn[nid] > max_pfn) node_end_pfn[nid] = max_pfn; @@ -237,41 +253,48 @@ static unsigned long calculate_numa_remap_pages(void) /* now the roundup is correct, convert to PAGE_SIZE pages */ size = size * PTRS_PER_PTE; - /* - * Validate the region we are allocating only contains valid - * pages. - */ - for (pfn = node_end_pfn[nid] - size; - pfn < node_end_pfn[nid]; pfn++) - if (!page_is_ram(pfn)) - break; - - if (pfn != node_end_pfn[nid]) - size = 0; + node_kva_target = round_down(node_end_pfn[nid] - size, + PTRS_PER_PTE); + node_kva_target <<= PAGE_SHIFT; + do { + node_kva_final = find_e820_area(node_kva_target, + ((u64)node_end_pfn[nid])<<PAGE_SHIFT, + ((u64)size)<<PAGE_SHIFT, + LARGE_PAGE_BYTES); + node_kva_target -= LARGE_PAGE_BYTES; + } while (node_kva_final == -1ULL && + (node_kva_target>>PAGE_SHIFT) > (node_start_pfn[nid])); + + if (node_kva_final == -1ULL) + panic("Can not get kva ram\n"); - printk("Reserving %ld pages of KVA for lmem_map of node %d\n", - size, nid); node_remap_size[nid] = size; node_remap_offset[nid] = reserve_pages; reserve_pages += size; - printk("Shrinking node %d from %ld pages to %ld pages\n", - nid, node_end_pfn[nid], node_end_pfn[nid] - size); - - if (node_end_pfn[nid] & (PTRS_PER_PTE-1)) { - /* - * Align node_end_pfn[] and node_remap_start_pfn[] to - * pmd boundary. remap_numa_kva will barf otherwise. - */ - printk("Shrinking node %d further by %ld pages for proper alignment\n", - nid, node_end_pfn[nid] & (PTRS_PER_PTE-1)); - size += node_end_pfn[nid] & (PTRS_PER_PTE-1); - } + printk(KERN_DEBUG "Reserving %ld pages of KVA for lmem_map of" + " node %d at %llx\n", + size, nid, node_kva_final>>PAGE_SHIFT); + + /* + * prevent kva address below max_low_pfn want it on system + * with less memory later. + * layout will be: KVA address , KVA RAM + * + * we are supposed to only record the one less then max_low_pfn + * but we could have some hole in high memory, and it will only + * check page_is_ram(pfn) && !page_is_reserved_early(pfn) to decide + * to use it as free. + * So reserve_early here, hope we don't run out of that array + */ + reserve_early(node_kva_final, + node_kva_final+(((u64)size)<<PAGE_SHIFT), + "KVA RAM"); - node_end_pfn[nid] -= size; - node_remap_start_pfn[nid] = node_end_pfn[nid]; - shrink_active_range(nid, old_end_pfn, node_end_pfn[nid]); + node_remap_start_pfn[nid] = node_kva_final>>PAGE_SHIFT; + remove_active_range(nid, node_remap_start_pfn[nid], + node_remap_start_pfn[nid] + size); } - printk("Reserving total of %ld pages for numa KVA remap\n", + printk(KERN_INFO "Reserving total of %lx pages for numa KVA remap\n", reserve_pages); return reserve_pages; } @@ -285,37 +308,16 @@ static void init_remap_allocator(int nid) node_remap_alloc_vaddr[nid] = node_remap_start_vaddr[nid] + ALIGN(sizeof(pg_data_t), PAGE_SIZE); - printk ("node %d will remap to vaddr %08lx - %08lx\n", nid, + printk(KERN_DEBUG "node %d will remap to vaddr %08lx - %08lx\n", nid, (ulong) node_remap_start_vaddr[nid], - (ulong) pfn_to_kaddr(highstart_pfn - + node_remap_offset[nid] + node_remap_size[nid])); -} -#else -void *alloc_remap(int nid, unsigned long size) -{ - return NULL; -} - -static unsigned long calculate_numa_remap_pages(void) -{ - return 0; -} - -static void init_remap_allocator(int nid) -{ -} - -void __init remap_numa_kva(void) -{ + (ulong) node_remap_end_vaddr[nid]); } -#endif /* CONFIG_DISCONTIGMEM */ -extern void setup_bootmem_allocator(void); -unsigned long __init setup_memory(void) +void __init initmem_init(unsigned long start_pfn, + unsigned long end_pfn) { int nid; - unsigned long system_start_pfn, system_max_low_pfn; - unsigned long wasted_pages; + long kva_target_pfn; /* * When mapping a NUMA machine we allocate the node_mem_map arrays @@ -324,109 +326,77 @@ unsigned long __init setup_memory(void) * this space and use it to adjust the boundary between ZONE_NORMAL * and ZONE_HIGHMEM. */ - get_memcfg_numa(); - kva_pages = calculate_numa_remap_pages(); + get_memcfg_numa(); - /* partially used pages are not usable - thus round upwards */ - system_start_pfn = min_low_pfn = PFN_UP(init_pg_tables_end); + kva_pages = round_up(calculate_numa_remap_pages(), PTRS_PER_PTE); - kva_start_pfn = find_max_low_pfn() - kva_pages; + kva_target_pfn = round_down(max_low_pfn - kva_pages, PTRS_PER_PTE); + do { + kva_start_pfn = find_e820_area(kva_target_pfn<<PAGE_SHIFT, + max_low_pfn<<PAGE_SHIFT, + kva_pages<<PAGE_SHIFT, + PTRS_PER_PTE<<PAGE_SHIFT) >> PAGE_SHIFT; + kva_target_pfn -= PTRS_PER_PTE; + } while (kva_start_pfn == -1UL && kva_target_pfn > min_low_pfn); -#ifdef CONFIG_BLK_DEV_INITRD - /* Numa kva area is below the initrd */ - if (initrd_start) - kva_start_pfn = PFN_DOWN(initrd_start - PAGE_OFFSET) - - kva_pages; -#endif + if (kva_start_pfn == -1UL) + panic("Can not get kva space\n"); - /* - * We waste pages past at the end of the KVA for no good reason other - * than how it is located. This is bad. - */ - wasted_pages = kva_start_pfn & (PTRS_PER_PTE-1); - kva_start_pfn -= wasted_pages; - kva_pages += wasted_pages; - - system_max_low_pfn = max_low_pfn = find_max_low_pfn(); - printk("kva_start_pfn ~ %ld find_max_low_pfn() ~ %ld\n", + printk(KERN_INFO "kva_start_pfn ~ %lx max_low_pfn ~ %lx\n", kva_start_pfn, max_low_pfn); - printk("max_pfn = %ld\n", max_pfn); + printk(KERN_INFO "max_pfn = %lx\n", max_pfn); + + /* avoid clash with initrd */ + reserve_early(kva_start_pfn<<PAGE_SHIFT, + (kva_start_pfn + kva_pages)<<PAGE_SHIFT, + "KVA PG"); #ifdef CONFIG_HIGHMEM highstart_pfn = highend_pfn = max_pfn; - if (max_pfn > system_max_low_pfn) - highstart_pfn = system_max_low_pfn; + if (max_pfn > max_low_pfn) + highstart_pfn = max_low_pfn; printk(KERN_NOTICE "%ldMB HIGHMEM available.\n", pages_to_mb(highend_pfn - highstart_pfn)); num_physpages = highend_pfn; high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1; #else - num_physpages = system_max_low_pfn; - high_memory = (void *) __va(system_max_low_pfn * PAGE_SIZE - 1) + 1; + num_physpages = max_low_pfn; + high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1; #endif printk(KERN_NOTICE "%ldMB LOWMEM available.\n", - pages_to_mb(system_max_low_pfn)); - printk("min_low_pfn = %ld, max_low_pfn = %ld, highstart_pfn = %ld\n", - min_low_pfn, max_low_pfn, highstart_pfn); + pages_to_mb(max_low_pfn)); + printk(KERN_DEBUG "max_low_pfn = %lx, highstart_pfn = %lx\n", + max_low_pfn, highstart_pfn); - printk("Low memory ends at vaddr %08lx\n", + printk(KERN_DEBUG "Low memory ends at vaddr %08lx\n", (ulong) pfn_to_kaddr(max_low_pfn)); for_each_online_node(nid) { init_remap_allocator(nid); allocate_pgdat(nid); } - printk("High memory starts at vaddr %08lx\n", + remap_numa_kva(); + + printk(KERN_DEBUG "High memory starts at vaddr %08lx\n", (ulong) pfn_to_kaddr(highstart_pfn)); for_each_online_node(nid) propagate_e820_map_node(nid); - memset(NODE_DATA(0), 0, sizeof(struct pglist_data)); + for_each_online_node(nid) + memset(NODE_DATA(nid), 0, sizeof(struct pglist_data)); + NODE_DATA(0)->bdata = &node0_bdata; setup_bootmem_allocator(); - return max_low_pfn; -} - -void __init numa_kva_reserve(void) -{ - if (kva_pages) - reserve_bootmem(PFN_PHYS(kva_start_pfn), PFN_PHYS(kva_pages), - BOOTMEM_DEFAULT); } -void __init zone_sizes_init(void) -{ - int nid; - unsigned long max_zone_pfns[MAX_NR_ZONES]; - memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); - max_zone_pfns[ZONE_DMA] = - virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT; - max_zone_pfns[ZONE_NORMAL] = max_low_pfn; -#ifdef CONFIG_HIGHMEM - max_zone_pfns[ZONE_HIGHMEM] = highend_pfn; -#endif - - /* If SRAT has not registered memory, register it now */ - if (find_max_pfn_with_active_regions() == 0) { - for_each_online_node(nid) { - if (node_has_online_mem(nid)) - add_active_range(nid, node_start_pfn[nid], - node_end_pfn[nid]); - } - } - - free_area_init_nodes(max_zone_pfns); - return; -} - -void __init set_highmem_pages_init(int bad_ppro) +void __init set_highmem_pages_init(void) { #ifdef CONFIG_HIGHMEM struct zone *zone; - struct page *page; + int nid; for_each_zone(zone) { - unsigned long node_pfn, zone_start_pfn, zone_end_pfn; + unsigned long zone_start_pfn, zone_end_pfn; if (!is_highmem(zone)) continue; @@ -434,16 +404,12 @@ void __init set_highmem_pages_init(int bad_ppro) zone_start_pfn = zone->zone_start_pfn; zone_end_pfn = zone_start_pfn + zone->spanned_pages; - printk("Initializing %s for node %d (%08lx:%08lx)\n", - zone->name, zone_to_nid(zone), - zone_start_pfn, zone_end_pfn); + nid = zone_to_nid(zone); + printk(KERN_INFO "Initializing %s for node %d (%08lx:%08lx)\n", + zone->name, nid, zone_start_pfn, zone_end_pfn); - for (node_pfn = zone_start_pfn; node_pfn < zone_end_pfn; node_pfn++) { - if (!pfn_valid(node_pfn)) - continue; - page = pfn_to_page(node_pfn); - add_one_highpage_init(page, node_pfn, bad_ppro); - } + add_highpages_with_active_regions(nid, zone_start_pfn, + zone_end_pfn); } totalram_pages += totalhigh_pages; #endif @@ -476,3 +442,4 @@ int memory_add_physaddr_to_nid(u64 addr) EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif + diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 2c24bea92c66..0bb0caed8971 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -42,7 +42,7 @@ static struct addr_marker address_markers[] = { { 0, "User Space" }, #ifdef CONFIG_X86_64 { 0x8000000000000000UL, "Kernel Space" }, - { 0xffff810000000000UL, "Low Kernel Mapping" }, + { PAGE_OFFSET, "Low Kernel Mapping" }, { VMALLOC_START, "vmalloc() Area" }, { VMEMMAP_START, "Vmemmap" }, { __START_KERNEL_map, "High Kernel Mapping" }, diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index fd7e1798c75a..455f3fe67b42 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -10,6 +10,7 @@ #include <linux/string.h> #include <linux/types.h> #include <linux/ptrace.h> +#include <linux/mmiotrace.h> #include <linux/mman.h> #include <linux/mm.h> #include <linux/smp.h> @@ -49,17 +50,23 @@ #define PF_RSVD (1<<3) #define PF_INSTR (1<<4) +static inline int kmmio_fault(struct pt_regs *regs, unsigned long addr) +{ +#ifdef CONFIG_MMIOTRACE_HOOKS + if (unlikely(is_kmmio_active())) + if (kmmio_handler(regs, addr) == 1) + return -1; +#endif + return 0; +} + static inline int notify_page_fault(struct pt_regs *regs) { #ifdef CONFIG_KPROBES int ret = 0; /* kprobe_running() needs smp_processor_id() */ -#ifdef CONFIG_X86_32 if (!user_mode_vm(regs)) { -#else - if (!user_mode(regs)) { -#endif preempt_disable(); if (kprobe_running() && kprobe_fault_handler(regs, 14)) ret = 1; @@ -396,11 +403,7 @@ static void show_fault_oops(struct pt_regs *regs, unsigned long error_code, printk(KERN_CONT "NULL pointer dereference"); else printk(KERN_CONT "paging request"); -#ifdef CONFIG_X86_32 - printk(KERN_CONT " at %08lx\n", address); -#else - printk(KERN_CONT " at %016lx\n", address); -#endif + printk(KERN_CONT " at %p\n", (void *) address); printk(KERN_ALERT "IP:"); printk_address(regs->ip, 1); dump_pagetable(address); @@ -497,6 +500,11 @@ static int vmalloc_fault(unsigned long address) unsigned long pgd_paddr; pmd_t *pmd_k; pte_t *pte_k; + + /* Make sure we are in vmalloc area */ + if (!(address >= VMALLOC_START && address < VMALLOC_END)) + return -1; + /* * Synchronize this task's top level page-table * with the 'reference' page table. @@ -601,6 +609,8 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) if (notify_page_fault(regs)) return; + if (unlikely(kmmio_fault(regs, address))) + return; /* * We fault-in kernel-space virtual memory on-demand. The @@ -795,14 +805,10 @@ bad_area_nosemaphore: if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) && printk_ratelimit()) { printk( -#ifdef CONFIG_X86_32 - "%s%s[%d]: segfault at %lx ip %08lx sp %08lx error %lx", -#else - "%s%s[%d]: segfault at %lx ip %lx sp %lx error %lx", -#endif + "%s%s[%d]: segfault at %lx ip %p sp %p error %lx", task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, - tsk->comm, task_pid_nr(tsk), address, regs->ip, - regs->sp, error_code); + tsk->comm, task_pid_nr(tsk), address, + (void *) regs->ip, (void *) regs->sp, error_code); print_vma_addr(" in ", regs->ip); printk("\n"); } @@ -910,14 +916,7 @@ LIST_HEAD(pgd_list); void vmalloc_sync_all(void) { #ifdef CONFIG_X86_32 - /* - * Note that races in the updates of insync and start aren't - * problematic: insync can only get set bits added, and updates to - * start are only improving performance (without affecting correctness - * if undone). - */ - static DECLARE_BITMAP(insync, PTRS_PER_PGD); - static unsigned long start = TASK_SIZE; + unsigned long start = VMALLOC_START & PGDIR_MASK; unsigned long address; if (SHARED_KERNEL_PMD) @@ -925,56 +924,38 @@ void vmalloc_sync_all(void) BUILD_BUG_ON(TASK_SIZE & ~PGDIR_MASK); for (address = start; address >= TASK_SIZE; address += PGDIR_SIZE) { - if (!test_bit(pgd_index(address), insync)) { - unsigned long flags; - struct page *page; - - spin_lock_irqsave(&pgd_lock, flags); - list_for_each_entry(page, &pgd_list, lru) { - if (!vmalloc_sync_one(page_address(page), - address)) - break; - } - spin_unlock_irqrestore(&pgd_lock, flags); - if (!page) - set_bit(pgd_index(address), insync); + unsigned long flags; + struct page *page; + + spin_lock_irqsave(&pgd_lock, flags); + list_for_each_entry(page, &pgd_list, lru) { + if (!vmalloc_sync_one(page_address(page), + address)) + break; } - if (address == start && test_bit(pgd_index(address), insync)) - start = address + PGDIR_SIZE; + spin_unlock_irqrestore(&pgd_lock, flags); } #else /* CONFIG_X86_64 */ - /* - * Note that races in the updates of insync and start aren't - * problematic: insync can only get set bits added, and updates to - * start are only improving performance (without affecting correctness - * if undone). - */ - static DECLARE_BITMAP(insync, PTRS_PER_PGD); - static unsigned long start = VMALLOC_START & PGDIR_MASK; + unsigned long start = VMALLOC_START & PGDIR_MASK; unsigned long address; for (address = start; address <= VMALLOC_END; address += PGDIR_SIZE) { - if (!test_bit(pgd_index(address), insync)) { - const pgd_t *pgd_ref = pgd_offset_k(address); - unsigned long flags; - struct page *page; - - if (pgd_none(*pgd_ref)) - continue; - spin_lock_irqsave(&pgd_lock, flags); - list_for_each_entry(page, &pgd_list, lru) { - pgd_t *pgd; - pgd = (pgd_t *)page_address(page) + pgd_index(address); - if (pgd_none(*pgd)) - set_pgd(pgd, *pgd_ref); - else - BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref)); - } - spin_unlock_irqrestore(&pgd_lock, flags); - set_bit(pgd_index(address), insync); + const pgd_t *pgd_ref = pgd_offset_k(address); + unsigned long flags; + struct page *page; + + if (pgd_none(*pgd_ref)) + continue; + spin_lock_irqsave(&pgd_lock, flags); + list_for_each_entry(page, &pgd_list, lru) { + pgd_t *pgd; + pgd = (pgd_t *)page_address(page) + pgd_index(address); + if (pgd_none(*pgd)) + set_pgd(pgd, *pgd_ref); + else + BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref)); } - if (address == start) - start = address + PGDIR_SIZE; + spin_unlock_irqrestore(&pgd_lock, flags); } #endif } diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index ec30d10154b6..9689a5138e64 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -50,6 +50,7 @@ unsigned int __VMALLOC_RESERVE = 128 << 20; +unsigned long max_low_pfn_mapped; unsigned long max_pfn_mapped; DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); @@ -57,6 +58,27 @@ unsigned long highstart_pfn, highend_pfn; static noinline int do_test_wp_bit(void); + +static unsigned long __initdata table_start; +static unsigned long __meminitdata table_end; +static unsigned long __meminitdata table_top; + +static int __initdata after_init_bootmem; + +static __init void *alloc_low_page(unsigned long *phys) +{ + unsigned long pfn = table_end++; + void *adr; + + if (pfn >= table_top) + panic("alloc_low_page: ran out of memory"); + + adr = __va(pfn * PAGE_SIZE); + memset(adr, 0, PAGE_SIZE); + *phys = pfn * PAGE_SIZE; + return adr; +} + /* * Creates a middle page table and puts a pointer to it in the * given global directory entry. This only returns the gd entry @@ -68,9 +90,12 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd) pmd_t *pmd_table; #ifdef CONFIG_X86_PAE + unsigned long phys; if (!(pgd_val(*pgd) & _PAGE_PRESENT)) { - pmd_table = (pmd_t *) alloc_bootmem_low_pages(PAGE_SIZE); - + if (after_init_bootmem) + pmd_table = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE); + else + pmd_table = (pmd_t *)alloc_low_page(&phys); paravirt_alloc_pmd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT); set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT)); pud = pud_offset(pgd, 0); @@ -92,12 +117,16 @@ static pte_t * __init one_page_table_init(pmd_t *pmd) if (!(pmd_val(*pmd) & _PAGE_PRESENT)) { pte_t *page_table = NULL; + if (after_init_bootmem) { #ifdef CONFIG_DEBUG_PAGEALLOC - page_table = (pte_t *) alloc_bootmem_pages(PAGE_SIZE); + page_table = (pte_t *) alloc_bootmem_pages(PAGE_SIZE); #endif - if (!page_table) { - page_table = + if (!page_table) + page_table = (pte_t *)alloc_bootmem_low_pages(PAGE_SIZE); + } else { + unsigned long phys; + page_table = (pte_t *)alloc_low_page(&phys); } paravirt_alloc_pte(&init_mm, __pa(page_table) >> PAGE_SHIFT); @@ -155,38 +184,44 @@ static inline int is_kernel_text(unsigned long addr) * of max_low_pfn pages, by creating page tables starting from address * PAGE_OFFSET: */ -static void __init kernel_physical_mapping_init(pgd_t *pgd_base) +static void __init kernel_physical_mapping_init(pgd_t *pgd_base, + unsigned long start_pfn, + unsigned long end_pfn, + int use_pse) { int pgd_idx, pmd_idx, pte_ofs; unsigned long pfn; pgd_t *pgd; pmd_t *pmd; pte_t *pte; + unsigned pages_2m = 0, pages_4k = 0; - pgd_idx = pgd_index(PAGE_OFFSET); - pgd = pgd_base + pgd_idx; - pfn = 0; + if (!cpu_has_pse) + use_pse = 0; + pfn = start_pfn; + pgd_idx = pgd_index((pfn<<PAGE_SHIFT) + PAGE_OFFSET); + pgd = pgd_base + pgd_idx; for (; pgd_idx < PTRS_PER_PGD; pgd++, pgd_idx++) { pmd = one_md_table_init(pgd); - if (pfn >= max_low_pfn) - continue; - for (pmd_idx = 0; - pmd_idx < PTRS_PER_PMD && pfn < max_low_pfn; + if (pfn >= end_pfn) + continue; +#ifdef CONFIG_X86_PAE + pmd_idx = pmd_index((pfn<<PAGE_SHIFT) + PAGE_OFFSET); + pmd += pmd_idx; +#else + pmd_idx = 0; +#endif + for (; pmd_idx < PTRS_PER_PMD && pfn < end_pfn; pmd++, pmd_idx++) { unsigned int addr = pfn * PAGE_SIZE + PAGE_OFFSET; /* * Map with big pages if possible, otherwise * create normal page tables: - * - * Don't use a large page for the first 2/4MB of memory - * because there are often fixed size MTRRs in there - * and overlapping MTRRs into large pages can cause - * slowdowns. */ - if (cpu_has_pse && !(pgd_idx == 0 && pmd_idx == 0)) { + if (use_pse) { unsigned int addr2; pgprot_t prot = PAGE_KERNEL_LARGE; @@ -197,34 +232,30 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base) is_kernel_text(addr2)) prot = PAGE_KERNEL_LARGE_EXEC; + pages_2m++; set_pmd(pmd, pfn_pmd(pfn, prot)); pfn += PTRS_PER_PTE; - max_pfn_mapped = pfn; continue; } pte = one_page_table_init(pmd); - for (pte_ofs = 0; - pte_ofs < PTRS_PER_PTE && pfn < max_low_pfn; + pte_ofs = pte_index((pfn<<PAGE_SHIFT) + PAGE_OFFSET); + pte += pte_ofs; + for (; pte_ofs < PTRS_PER_PTE && pfn < end_pfn; pte++, pfn++, pte_ofs++, addr += PAGE_SIZE) { pgprot_t prot = PAGE_KERNEL; if (is_kernel_text(addr)) prot = PAGE_KERNEL_EXEC; + pages_4k++; set_pte(pte, pfn_pte(pfn, prot)); } - max_pfn_mapped = pfn; } } -} - -static inline int page_kills_ppro(unsigned long pagenr) -{ - if (pagenr >= 0x70000 && pagenr <= 0x7003F) - return 1; - return 0; + update_page_count(PG_LEVEL_2M, pages_2m); + update_page_count(PG_LEVEL_4K, pages_4k); } /* @@ -287,29 +318,62 @@ static void __init permanent_kmaps_init(pgd_t *pgd_base) pkmap_page_table = pte; } -void __init add_one_highpage_init(struct page *page, int pfn, int bad_ppro) +static void __init add_one_highpage_init(struct page *page, int pfn) { - if (page_is_ram(pfn) && !(bad_ppro && page_kills_ppro(pfn))) { - ClearPageReserved(page); - init_page_count(page); - __free_page(page); - totalhigh_pages++; - } else - SetPageReserved(page); + ClearPageReserved(page); + init_page_count(page); + __free_page(page); + totalhigh_pages++; } -#ifndef CONFIG_NUMA -static void __init set_highmem_pages_init(int bad_ppro) +struct add_highpages_data { + unsigned long start_pfn; + unsigned long end_pfn; +}; + +static int __init add_highpages_work_fn(unsigned long start_pfn, + unsigned long end_pfn, void *datax) { - int pfn; + int node_pfn; + struct page *page; + unsigned long final_start_pfn, final_end_pfn; + struct add_highpages_data *data; - for (pfn = highstart_pfn; pfn < highend_pfn; pfn++) { - /* - * Holes under sparsemem might not have no mem_map[]: - */ - if (pfn_valid(pfn)) - add_one_highpage_init(pfn_to_page(pfn), pfn, bad_ppro); + data = (struct add_highpages_data *)datax; + + final_start_pfn = max(start_pfn, data->start_pfn); + final_end_pfn = min(end_pfn, data->end_pfn); + if (final_start_pfn >= final_end_pfn) + return 0; + + for (node_pfn = final_start_pfn; node_pfn < final_end_pfn; + node_pfn++) { + if (!pfn_valid(node_pfn)) + continue; + page = pfn_to_page(node_pfn); + add_one_highpage_init(page, node_pfn); } + + return 0; + +} + +void __init add_highpages_with_active_regions(int nid, unsigned long start_pfn, + unsigned long end_pfn) +{ + struct add_highpages_data data; + + data.start_pfn = start_pfn; + data.end_pfn = end_pfn; + + work_with_active_regions(nid, add_highpages_work_fn, &data); +} + +#ifndef CONFIG_NUMA +static void __init set_highmem_pages_init(void) +{ + add_highpages_with_active_regions(0, highstart_pfn, highend_pfn); + totalram_pages += totalhigh_pages; } #endif /* !CONFIG_NUMA */ @@ -317,14 +381,9 @@ static void __init set_highmem_pages_init(int bad_ppro) #else # define kmap_init() do { } while (0) # define permanent_kmaps_init(pgd_base) do { } while (0) -# define set_highmem_pages_init(bad_ppro) do { } while (0) +# define set_highmem_pages_init() do { } while (0) #endif /* CONFIG_HIGHMEM */ -pteval_t __PAGE_KERNEL = _PAGE_KERNEL; -EXPORT_SYMBOL(__PAGE_KERNEL); - -pteval_t __PAGE_KERNEL_EXEC = _PAGE_KERNEL_EXEC; - void __init native_pagetable_setup_start(pgd_t *base) { unsigned long pfn, va; @@ -380,27 +439,10 @@ void __init native_pagetable_setup_done(pgd_t *base) * be partially populated, and so it avoids stomping on any existing * mappings. */ -static void __init pagetable_init(void) +static void __init early_ioremap_page_table_range_init(pgd_t *pgd_base) { - pgd_t *pgd_base = swapper_pg_dir; unsigned long vaddr, end; - paravirt_pagetable_setup_start(pgd_base); - - /* Enable PSE if available */ - if (cpu_has_pse) - set_in_cr4(X86_CR4_PSE); - - /* Enable PGE if available */ - if (cpu_has_pge) { - set_in_cr4(X86_CR4_PGE); - __PAGE_KERNEL |= _PAGE_GLOBAL; - __PAGE_KERNEL_EXEC |= _PAGE_GLOBAL; - } - - kernel_physical_mapping_init(pgd_base); - remap_numa_kva(); - /* * Fixed mappings, only the page table structure has to be * created - mappings will be set by set_fixmap(): @@ -410,6 +452,13 @@ static void __init pagetable_init(void) end = (FIXADDR_TOP + PMD_SIZE - 1) & PMD_MASK; page_table_range_init(vaddr, end, pgd_base); early_ioremap_reset(); +} + +static void __init pagetable_init(void) +{ + pgd_t *pgd_base = swapper_pg_dir; + + paravirt_pagetable_setup_start(pgd_base); permanent_kmaps_init(pgd_base); @@ -456,7 +505,7 @@ void zap_low_mappings(void) int nx_enabled; -pteval_t __supported_pte_mask __read_mostly = ~_PAGE_NX; +pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL); EXPORT_SYMBOL_GPL(__supported_pte_mask); #ifdef CONFIG_X86_PAE @@ -509,27 +558,318 @@ static void __init set_nx(void) } #endif +/* user-defined highmem size */ +static unsigned int highmem_pages = -1; + /* - * paging_init() sets up the page tables - note that the first 8MB are - * already mapped by head.S. - * - * This routines also unmaps the page at virtual kernel address 0, so - * that we can trap those pesky NULL-reference errors in the kernel. + * highmem=size forces highmem to be exactly 'size' bytes. + * This works even on boxes that have no highmem otherwise. + * This also works to reduce highmem size on bigger boxes. */ -void __init paging_init(void) +static int __init parse_highmem(char *arg) +{ + if (!arg) + return -EINVAL; + + highmem_pages = memparse(arg, &arg) >> PAGE_SHIFT; + return 0; +} +early_param("highmem", parse_highmem); + +/* + * Determine low and high memory ranges: + */ +void __init find_low_pfn_range(void) +{ + /* it could update max_pfn */ + + /* max_low_pfn is 0, we already have early_res support */ + + max_low_pfn = max_pfn; + if (max_low_pfn > MAXMEM_PFN) { + if (highmem_pages == -1) + highmem_pages = max_pfn - MAXMEM_PFN; + if (highmem_pages + MAXMEM_PFN < max_pfn) + max_pfn = MAXMEM_PFN + highmem_pages; + if (highmem_pages + MAXMEM_PFN > max_pfn) { + printk(KERN_WARNING "only %luMB highmem pages " + "available, ignoring highmem size of %uMB.\n", + pages_to_mb(max_pfn - MAXMEM_PFN), + pages_to_mb(highmem_pages)); + highmem_pages = 0; + } + max_low_pfn = MAXMEM_PFN; +#ifndef CONFIG_HIGHMEM + /* Maximum memory usable is what is directly addressable */ + printk(KERN_WARNING "Warning only %ldMB will be used.\n", + MAXMEM>>20); + if (max_pfn > MAX_NONPAE_PFN) + printk(KERN_WARNING + "Use a HIGHMEM64G enabled kernel.\n"); + else + printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n"); + max_pfn = MAXMEM_PFN; +#else /* !CONFIG_HIGHMEM */ +#ifndef CONFIG_HIGHMEM64G + if (max_pfn > MAX_NONPAE_PFN) { + max_pfn = MAX_NONPAE_PFN; + printk(KERN_WARNING "Warning only 4GB will be used." + "Use a HIGHMEM64G enabled kernel.\n"); + } +#endif /* !CONFIG_HIGHMEM64G */ +#endif /* !CONFIG_HIGHMEM */ + } else { + if (highmem_pages == -1) + highmem_pages = 0; +#ifdef CONFIG_HIGHMEM + if (highmem_pages >= max_pfn) { + printk(KERN_ERR "highmem size specified (%uMB) is " + "bigger than pages available (%luMB)!.\n", + pages_to_mb(highmem_pages), + pages_to_mb(max_pfn)); + highmem_pages = 0; + } + if (highmem_pages) { + if (max_low_pfn - highmem_pages < + 64*1024*1024/PAGE_SIZE){ + printk(KERN_ERR "highmem size %uMB results in " + "smaller than 64MB lowmem, ignoring it.\n" + , pages_to_mb(highmem_pages)); + highmem_pages = 0; + } + max_low_pfn -= highmem_pages; + } +#else + if (highmem_pages) + printk(KERN_ERR "ignoring highmem size on non-highmem" + " kernel!\n"); +#endif + } +} + +#ifndef CONFIG_NEED_MULTIPLE_NODES +void __init initmem_init(unsigned long start_pfn, + unsigned long end_pfn) { +#ifdef CONFIG_HIGHMEM + highstart_pfn = highend_pfn = max_pfn; + if (max_pfn > max_low_pfn) + highstart_pfn = max_low_pfn; + memory_present(0, 0, highend_pfn); + e820_register_active_regions(0, 0, highend_pfn); + printk(KERN_NOTICE "%ldMB HIGHMEM available.\n", + pages_to_mb(highend_pfn - highstart_pfn)); + num_physpages = highend_pfn; + high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1; +#else + memory_present(0, 0, max_low_pfn); + e820_register_active_regions(0, 0, max_low_pfn); + num_physpages = max_low_pfn; + high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1; +#endif +#ifdef CONFIG_FLATMEM + max_mapnr = num_physpages; +#endif + printk(KERN_NOTICE "%ldMB LOWMEM available.\n", + pages_to_mb(max_low_pfn)); + + setup_bootmem_allocator(); +} +#endif /* !CONFIG_NEED_MULTIPLE_NODES */ + +static void __init zone_sizes_init(void) +{ + unsigned long max_zone_pfns[MAX_NR_ZONES]; + memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); + max_zone_pfns[ZONE_DMA] = + virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT; + max_zone_pfns[ZONE_NORMAL] = max_low_pfn; +#ifdef CONFIG_HIGHMEM + max_zone_pfns[ZONE_HIGHMEM] = highend_pfn; +#endif + + free_area_init_nodes(max_zone_pfns); +} + +void __init setup_bootmem_allocator(void) +{ + int i; + unsigned long bootmap_size, bootmap; + /* + * Initialize the boot-time allocator (with low memory only): + */ + bootmap_size = bootmem_bootmap_pages(max_low_pfn)<<PAGE_SHIFT; + bootmap = find_e820_area(min_low_pfn<<PAGE_SHIFT, + max_pfn_mapped<<PAGE_SHIFT, bootmap_size, + PAGE_SIZE); + if (bootmap == -1L) + panic("Cannot find bootmem map of size %ld\n", bootmap_size); + reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP"); + + /* don't touch min_low_pfn */ + bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT, + min_low_pfn, max_low_pfn); + printk(KERN_INFO " mapped low ram: 0 - %08lx\n", + max_pfn_mapped<<PAGE_SHIFT); + printk(KERN_INFO " low ram: %08lx - %08lx\n", + min_low_pfn<<PAGE_SHIFT, max_low_pfn<<PAGE_SHIFT); + printk(KERN_INFO " bootmap %08lx - %08lx\n", + bootmap, bootmap + bootmap_size); + for_each_online_node(i) + free_bootmem_with_active_regions(i, max_low_pfn); + early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT); + + after_init_bootmem = 1; +} + +static void __init find_early_table_space(unsigned long end) +{ + unsigned long puds, pmds, ptes, tables, start; + + puds = (end + PUD_SIZE - 1) >> PUD_SHIFT; + tables = PAGE_ALIGN(puds * sizeof(pud_t)); + + pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT; + tables += PAGE_ALIGN(pmds * sizeof(pmd_t)); + + if (cpu_has_pse) { + unsigned long extra; + + extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT); + extra += PMD_SIZE; + ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT; + } else + ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT; + + tables += PAGE_ALIGN(ptes * sizeof(pte_t)); + + /* for fixmap */ + tables += PAGE_SIZE * 2; + + /* + * RED-PEN putting page tables only on node 0 could + * cause a hotspot and fill up ZONE_DMA. The page tables + * need roughly 0.5KB per GB. + */ + start = 0x7000; + table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT, + tables, PAGE_SIZE); + if (table_start == -1UL) + panic("Cannot find space for the kernel page tables"); + + table_start >>= PAGE_SHIFT; + table_end = table_start; + table_top = table_start + (tables>>PAGE_SHIFT); + + printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n", + end, table_start << PAGE_SHIFT, + (table_start << PAGE_SHIFT) + tables); +} + +unsigned long __init_refok init_memory_mapping(unsigned long start, + unsigned long end) +{ + pgd_t *pgd_base = swapper_pg_dir; + unsigned long start_pfn, end_pfn; + unsigned long big_page_start; + + /* + * Find space for the kernel direct mapping tables. + */ + if (!after_init_bootmem) + find_early_table_space(end); + #ifdef CONFIG_X86_PAE set_nx(); if (nx_enabled) printk(KERN_INFO "NX (Execute Disable) protection: active\n"); #endif - pagetable_init(); + + /* Enable PSE if available */ + if (cpu_has_pse) + set_in_cr4(X86_CR4_PSE); + + /* Enable PGE if available */ + if (cpu_has_pge) { + set_in_cr4(X86_CR4_PGE); + __supported_pte_mask |= _PAGE_GLOBAL; + } + + /* + * Don't use a large page for the first 2/4MB of memory + * because there are often fixed size MTRRs in there + * and overlapping MTRRs into large pages can cause + * slowdowns. + */ + big_page_start = PMD_SIZE; + + if (start < big_page_start) { + start_pfn = start >> PAGE_SHIFT; + end_pfn = min(big_page_start>>PAGE_SHIFT, end>>PAGE_SHIFT); + } else { + /* head is not big page alignment ? */ + start_pfn = start >> PAGE_SHIFT; + end_pfn = ((start + (PMD_SIZE - 1))>>PMD_SHIFT) + << (PMD_SHIFT - PAGE_SHIFT); + } + if (start_pfn < end_pfn) + kernel_physical_mapping_init(pgd_base, start_pfn, end_pfn, 0); + + /* big page range */ + start_pfn = ((start + (PMD_SIZE - 1))>>PMD_SHIFT) + << (PMD_SHIFT - PAGE_SHIFT); + if (start_pfn < (big_page_start >> PAGE_SHIFT)) + start_pfn = big_page_start >> PAGE_SHIFT; + end_pfn = (end>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT); + if (start_pfn < end_pfn) + kernel_physical_mapping_init(pgd_base, start_pfn, end_pfn, + cpu_has_pse); + + /* tail is not big page alignment ? */ + start_pfn = end_pfn; + if (start_pfn > (big_page_start>>PAGE_SHIFT)) { + end_pfn = end >> PAGE_SHIFT; + if (start_pfn < end_pfn) + kernel_physical_mapping_init(pgd_base, start_pfn, + end_pfn, 0); + } + + early_ioremap_page_table_range_init(pgd_base); load_cr3(swapper_pg_dir); __flush_tlb_all(); + if (!after_init_bootmem) + reserve_early(table_start << PAGE_SHIFT, + table_end << PAGE_SHIFT, "PGTABLE"); + + return end >> PAGE_SHIFT; +} + + +/* + * paging_init() sets up the page tables - note that the first 8MB are + * already mapped by head.S. + * + * This routines also unmaps the page at virtual kernel address 0, so + * that we can trap those pesky NULL-reference errors in the kernel. + */ +void __init paging_init(void) +{ + pagetable_init(); + + __flush_tlb_all(); + kmap_init(); + + /* + * NOTE: at this point the bootmem allocator is fully available. + */ + sparse_init(); + zone_sizes_init(); + + paravirt_post_allocator_init(); } /* @@ -564,24 +904,11 @@ static struct kcore_list kcore_mem, kcore_vmalloc; void __init mem_init(void) { int codesize, reservedpages, datasize, initsize; - int tmp, bad_ppro; + int tmp; #ifdef CONFIG_FLATMEM BUG_ON(!mem_map); #endif - bad_ppro = ppro_with_ram_bug(); - -#ifdef CONFIG_HIGHMEM - /* check that fixmap and pkmap do not overlap */ - if (PKMAP_BASE + LAST_PKMAP*PAGE_SIZE >= FIXADDR_START) { - printk(KERN_ERR - "fixmap and kmap areas overlap - this will crash\n"); - printk(KERN_ERR "pkstart: %lxh pkend: %lxh fixstart %lxh\n", - PKMAP_BASE, PKMAP_BASE + LAST_PKMAP*PAGE_SIZE, - FIXADDR_START); - BUG(); - } -#endif /* this will put all low memory onto the freelists */ totalram_pages += free_all_bootmem(); @@ -593,7 +920,7 @@ void __init mem_init(void) if (page_is_ram(tmp) && PageReserved(pfn_to_page(tmp))) reservedpages++; - set_highmem_pages_init(bad_ppro); + set_highmem_pages_init(); codesize = (unsigned long) &_etext - (unsigned long) &_text; datasize = (unsigned long) &_edata - (unsigned long) &_etext; @@ -614,7 +941,6 @@ void __init mem_init(void) (unsigned long) (totalhigh_pages << (PAGE_SHIFT-10)) ); -#if 1 /* double-sanity-check paranoia */ printk(KERN_INFO "virtual kernel memory layout:\n" " fixmap : 0x%08lx - 0x%08lx (%4ld kB)\n" #ifdef CONFIG_HIGHMEM @@ -655,7 +981,6 @@ void __init mem_init(void) #endif BUG_ON(VMALLOC_START > VMALLOC_END); BUG_ON((unsigned long)high_memory > VMALLOC_START); -#endif /* double-sanity-check paranoia */ if (boot_cpu_data.wp_works_ok < 0) test_wp_bit(); @@ -710,6 +1035,8 @@ void mark_rodata_ro(void) unsigned long start = PFN_ALIGN(_text); unsigned long size = PFN_ALIGN(_etext) - start; +#ifndef CONFIG_DYNAMIC_FTRACE + /* Dynamic tracing modifies the kernel text section */ set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); printk(KERN_INFO "Write protecting the kernel text: %luk\n", size >> 10); @@ -722,6 +1049,8 @@ void mark_rodata_ro(void) printk(KERN_INFO "Testing CPA: write protecting again\n"); set_pages_ro(virt_to_page(start), size>>PAGE_SHIFT); #endif +#endif /* CONFIG_DYNAMIC_FTRACE */ + start += size; size = (unsigned long)__end_rodata - start; set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); @@ -784,3 +1113,9 @@ void free_initrd_mem(unsigned long start, unsigned long end) free_init_pages("initrd memory", start, end); } #endif + +int __init reserve_bootmem_generic(unsigned long phys, unsigned long len, + int flags) +{ + return reserve_bootmem(phys, len, flags); +} diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 32ba13b0f818..306049edd553 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -18,6 +18,7 @@ #include <linux/swap.h> #include <linux/smp.h> #include <linux/init.h> +#include <linux/initrd.h> #include <linux/pagemap.h> #include <linux/bootmem.h> #include <linux/proc_fs.h> @@ -47,6 +48,14 @@ #include <asm/numa.h> #include <asm/cacheflush.h> +/* + * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries. + * The direct mapping extends to max_pfn_mapped, so that we can directly access + * apertures, ACPI and other tables without having to play with fixmaps. + */ +unsigned long max_low_pfn_mapped; +unsigned long max_pfn_mapped; + static unsigned long dma_reserve __initdata; DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); @@ -135,26 +144,17 @@ static __init void *spp_getpage(void) return ptr; } -static void -set_pte_phys(unsigned long vaddr, unsigned long phys, pgprot_t prot) +void +set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte) { - pgd_t *pgd; pud_t *pud; pmd_t *pmd; - pte_t *pte, new_pte; - - pr_debug("set_pte_phys %lx to %lx\n", vaddr, phys); + pte_t *pte; - pgd = pgd_offset_k(vaddr); - if (pgd_none(*pgd)) { - printk(KERN_ERR - "PGD FIXMAP MISSING, it should be setup in head.S!\n"); - return; - } - pud = pud_offset(pgd, vaddr); + pud = pud_page + pud_index(vaddr); if (pud_none(*pud)) { pmd = (pmd_t *) spp_getpage(); - set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE | _PAGE_USER)); + pud_populate(&init_mm, pud, pmd); if (pmd != pmd_offset(pud, 0)) { printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n", pmd, pmd_offset(pud, 0)); @@ -164,13 +164,12 @@ set_pte_phys(unsigned long vaddr, unsigned long phys, pgprot_t prot) pmd = pmd_offset(pud, vaddr); if (pmd_none(*pmd)) { pte = (pte_t *) spp_getpage(); - set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE | _PAGE_USER)); + pmd_populate_kernel(&init_mm, pmd, pte); if (pte != pte_offset_kernel(pmd, 0)) { printk(KERN_ERR "PAGETABLE BUG #02!\n"); return; } } - new_pte = pfn_pte(phys >> PAGE_SHIFT, prot); pte = pte_offset_kernel(pmd, vaddr); if (!pte_none(*pte) && pte_val(new_pte) && @@ -185,6 +184,64 @@ set_pte_phys(unsigned long vaddr, unsigned long phys, pgprot_t prot) __flush_tlb_one(vaddr); } +void +set_pte_vaddr(unsigned long vaddr, pte_t pteval) +{ + pgd_t *pgd; + pud_t *pud_page; + + pr_debug("set_pte_vaddr %lx to %lx\n", vaddr, native_pte_val(pteval)); + + pgd = pgd_offset_k(vaddr); + if (pgd_none(*pgd)) { + printk(KERN_ERR + "PGD FIXMAP MISSING, it should be setup in head.S!\n"); + return; + } + pud_page = (pud_t*)pgd_page_vaddr(*pgd); + set_pte_vaddr_pud(pud_page, vaddr, pteval); +} + +/* + * Create large page table mappings for a range of physical addresses. + */ +static void __init __init_extra_mapping(unsigned long phys, unsigned long size, + pgprot_t prot) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + + BUG_ON((phys & ~PMD_MASK) || (size & ~PMD_MASK)); + for (; size; phys += PMD_SIZE, size -= PMD_SIZE) { + pgd = pgd_offset_k((unsigned long)__va(phys)); + if (pgd_none(*pgd)) { + pud = (pud_t *) spp_getpage(); + set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE | + _PAGE_USER)); + } + pud = pud_offset(pgd, (unsigned long)__va(phys)); + if (pud_none(*pud)) { + pmd = (pmd_t *) spp_getpage(); + set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE | + _PAGE_USER)); + } + pmd = pmd_offset(pud, phys); + BUG_ON(!pmd_none(*pmd)); + set_pmd(pmd, __pmd(phys | pgprot_val(prot))); + } +} + +void __init init_extra_mapping_wb(unsigned long phys, unsigned long size) +{ + __init_extra_mapping(phys, size, PAGE_KERNEL_LARGE); +} + +void __init init_extra_mapping_uc(unsigned long phys, unsigned long size) +{ + __init_extra_mapping(phys, size, PAGE_KERNEL_LARGE_NOCACHE); +} + /* * The head.S code sets up the kernel high mapping: * @@ -206,27 +263,16 @@ void __init cleanup_highmap(void) pmd_t *last_pmd = pmd + PTRS_PER_PMD; for (; pmd < last_pmd; pmd++, vaddr += PMD_SIZE) { - if (!pmd_present(*pmd)) + if (pmd_none(*pmd)) continue; if (vaddr < (unsigned long) _text || vaddr > end) set_pmd(pmd, __pmd(0)); } } -/* NOTE: this is meant to be run only at boot */ -void __set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t prot) -{ - unsigned long address = __fix_to_virt(idx); - - if (idx >= __end_of_fixed_addresses) { - printk(KERN_ERR "Invalid __set_fixmap\n"); - return; - } - set_pte_phys(address, phys, prot); -} - static unsigned long __initdata table_start; static unsigned long __meminitdata table_end; +static unsigned long __meminitdata table_top; static __meminit void *alloc_low_page(unsigned long *phys) { @@ -240,7 +286,7 @@ static __meminit void *alloc_low_page(unsigned long *phys) return adr; } - if (pfn >= end_pfn) + if (pfn >= table_top) panic("alloc_low_page: ran out of memory"); adr = early_ioremap(pfn * PAGE_SIZE, PAGE_SIZE); @@ -257,65 +303,61 @@ static __meminit void unmap_low_page(void *adr) early_iounmap(adr, PAGE_SIZE); } -/* Must run before zap_low_mappings */ -__meminit void *early_ioremap(unsigned long addr, unsigned long size) +static unsigned long __meminit +phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end) { - pmd_t *pmd, *last_pmd; - unsigned long vaddr; - int i, pmds; + unsigned pages = 0; + unsigned long last_map_addr = end; + int i; + + pte_t *pte = pte_page + pte_index(addr); - pmds = ((addr & ~PMD_MASK) + size + ~PMD_MASK) / PMD_SIZE; - vaddr = __START_KERNEL_map; - pmd = level2_kernel_pgt; - last_pmd = level2_kernel_pgt + PTRS_PER_PMD - 1; + for(i = pte_index(addr); i < PTRS_PER_PTE; i++, addr += PAGE_SIZE, pte++) { - for (; pmd <= last_pmd; pmd++, vaddr += PMD_SIZE) { - for (i = 0; i < pmds; i++) { - if (pmd_present(pmd[i])) - goto continue_outer_loop; + if (addr >= end) { + if (!after_bootmem) { + for(; i < PTRS_PER_PTE; i++, pte++) + set_pte(pte, __pte(0)); + } + break; } - vaddr += addr & ~PMD_MASK; - addr &= PMD_MASK; - for (i = 0; i < pmds; i++, addr += PMD_SIZE) - set_pmd(pmd+i, __pmd(addr | __PAGE_KERNEL_LARGE_EXEC)); - __flush_tlb_all(); + if (pte_val(*pte)) + continue; - return (void *)vaddr; -continue_outer_loop: - ; + if (0) + printk(" pte=%p addr=%lx pte=%016lx\n", + pte, addr, pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL).pte); + set_pte(pte, pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL)); + last_map_addr = (addr & PAGE_MASK) + PAGE_SIZE; + pages++; } - printk(KERN_ERR "early_ioremap(0x%lx, %lu) failed\n", addr, size); + update_page_count(PG_LEVEL_4K, pages); - return NULL; + return last_map_addr; } -/* - * To avoid virtual aliases later: - */ -__meminit void early_iounmap(void *addr, unsigned long size) +static unsigned long __meminit +phys_pte_update(pmd_t *pmd, unsigned long address, unsigned long end) { - unsigned long vaddr; - pmd_t *pmd; - int i, pmds; - - vaddr = (unsigned long)addr; - pmds = ((vaddr & ~PMD_MASK) + size + ~PMD_MASK) / PMD_SIZE; - pmd = level2_kernel_pgt + pmd_index(vaddr); + pte_t *pte = (pte_t *)pmd_page_vaddr(*pmd); - for (i = 0; i < pmds; i++) - pmd_clear(pmd + i); - - __flush_tlb_all(); + return phys_pte_init(pte, address, end); } static unsigned long __meminit -phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end) +phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end, + unsigned long page_size_mask) { + unsigned long pages = 0; + unsigned long last_map_addr = end; + int i = pmd_index(address); for (; i < PTRS_PER_PMD; i++, address += PMD_SIZE) { + unsigned long pte_phys; pmd_t *pmd = pmd_page + pmd_index(address); + pte_t *pte; if (address >= end) { if (!after_bootmem) { @@ -325,31 +367,50 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end) break; } - if (pmd_val(*pmd)) + if (pmd_val(*pmd)) { + if (!pmd_large(*pmd)) + last_map_addr = phys_pte_update(pmd, address, + end); + continue; + } + + if (page_size_mask & (1<<PG_LEVEL_2M)) { + pages++; + set_pte((pte_t *)pmd, + pfn_pte(address >> PAGE_SHIFT, PAGE_KERNEL_LARGE)); + last_map_addr = (address & PMD_MASK) + PMD_SIZE; continue; + } - set_pte((pte_t *)pmd, - pfn_pte(address >> PAGE_SHIFT, PAGE_KERNEL_LARGE)); + pte = alloc_low_page(&pte_phys); + last_map_addr = phys_pte_init(pte, address, end); + unmap_low_page(pte); + + pmd_populate_kernel(&init_mm, pmd, __va(pte_phys)); } - return address; + update_page_count(PG_LEVEL_2M, pages); + return last_map_addr; } static unsigned long __meminit -phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end) +phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end, + unsigned long page_size_mask) { pmd_t *pmd = pmd_offset(pud, 0); unsigned long last_map_addr; spin_lock(&init_mm.page_table_lock); - last_map_addr = phys_pmd_init(pmd, address, end); + last_map_addr = phys_pmd_init(pmd, address, end, page_size_mask); spin_unlock(&init_mm.page_table_lock); __flush_tlb_all(); return last_map_addr; } static unsigned long __meminit -phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end) +phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end, + unsigned long page_size_mask) { + unsigned long pages = 0; unsigned long last_map_addr = end; int i = pud_index(addr); @@ -369,11 +430,13 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end) if (pud_val(*pud)) { if (!pud_large(*pud)) - last_map_addr = phys_pmd_update(pud, addr, end); + last_map_addr = phys_pmd_update(pud, addr, end, + page_size_mask); continue; } - if (direct_gbpages) { + if (page_size_mask & (1<<PG_LEVEL_1G)) { + pages++; set_pte((pte_t *)pud, pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL_LARGE)); last_map_addr = (addr & PUD_MASK) + PUD_SIZE; @@ -383,27 +446,50 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end) pmd = alloc_low_page(&pmd_phys); spin_lock(&init_mm.page_table_lock); - set_pud(pud, __pud(pmd_phys | _KERNPG_TABLE)); - last_map_addr = phys_pmd_init(pmd, addr, end); + last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask); + unmap_low_page(pmd); + pud_populate(&init_mm, pud, __va(pmd_phys)); spin_unlock(&init_mm.page_table_lock); - unmap_low_page(pmd); } __flush_tlb_all(); + update_page_count(PG_LEVEL_1G, pages); - return last_map_addr >> PAGE_SHIFT; + return last_map_addr; +} + +static unsigned long __meminit +phys_pud_update(pgd_t *pgd, unsigned long addr, unsigned long end, + unsigned long page_size_mask) +{ + pud_t *pud; + + pud = (pud_t *)pgd_page_vaddr(*pgd); + + return phys_pud_init(pud, addr, end, page_size_mask); } static void __init find_early_table_space(unsigned long end) { - unsigned long puds, pmds, tables, start; + unsigned long puds, pmds, ptes, tables, start; puds = (end + PUD_SIZE - 1) >> PUD_SHIFT; tables = round_up(puds * sizeof(pud_t), PAGE_SIZE); - if (!direct_gbpages) { + if (direct_gbpages) { + unsigned long extra; + extra = end - ((end>>PUD_SHIFT) << PUD_SHIFT); + pmds = (extra + PMD_SIZE - 1) >> PMD_SHIFT; + } else pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT; - tables += round_up(pmds * sizeof(pmd_t), PAGE_SIZE); - } + tables += round_up(pmds * sizeof(pmd_t), PAGE_SIZE); + + if (cpu_has_pse) { + unsigned long extra; + extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT); + ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT; + } else + ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT; + tables += round_up(ptes * sizeof(pte_t), PAGE_SIZE); /* * RED-PEN putting page tables only on node 0 could @@ -417,10 +503,10 @@ static void __init find_early_table_space(unsigned long end) table_start >>= PAGE_SHIFT; table_end = table_start; + table_top = table_start + (tables >> PAGE_SHIFT); - early_printk("kernel direct mapping tables up to %lx @ %lx-%lx\n", - end, table_start << PAGE_SHIFT, - (table_start << PAGE_SHIFT) + tables); + printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n", + end, table_start << PAGE_SHIFT, table_top << PAGE_SHIFT); } static void __init init_gbpages(void) @@ -431,7 +517,7 @@ static void __init init_gbpages(void) direct_gbpages = 0; } -#ifdef CONFIG_MEMTEST_BOOTPARAM +#ifdef CONFIG_MEMTEST static void __init memtest(unsigned long start_phys, unsigned long size, unsigned pattern) @@ -493,7 +579,8 @@ static void __init memtest(unsigned long start_phys, unsigned long size, } -static int memtest_pattern __initdata = CONFIG_MEMTEST_BOOTPARAM_VALUE; +/* default is disabled */ +static int memtest_pattern __initdata; static int __init parse_memtest(char *arg) { @@ -506,7 +593,7 @@ early_param("memtest", parse_memtest); static void __init early_memtest(unsigned long start, unsigned long end) { - unsigned long t_start, t_size; + u64 t_start, t_size; unsigned pattern; if (!memtest_pattern) @@ -525,8 +612,9 @@ static void __init early_memtest(unsigned long start, unsigned long end) if (t_start + t_size > end) t_size = end - t_start; - printk(KERN_CONT "\n %016lx - %016lx pattern %d", - t_start, t_start + t_size, pattern); + printk(KERN_CONT "\n %016llx - %016llx pattern %d", + (unsigned long long)t_start, + (unsigned long long)t_start + t_size, pattern); memtest(t_start, t_size, pattern); @@ -541,15 +629,85 @@ static void __init early_memtest(unsigned long start, unsigned long end) } #endif +static unsigned long __init kernel_physical_mapping_init(unsigned long start, + unsigned long end, + unsigned long page_size_mask) +{ + + unsigned long next, last_map_addr = end; + + start = (unsigned long)__va(start); + end = (unsigned long)__va(end); + + for (; start < end; start = next) { + pgd_t *pgd = pgd_offset_k(start); + unsigned long pud_phys; + pud_t *pud; + + next = (start + PGDIR_SIZE) & PGDIR_MASK; + if (next > end) + next = end; + + if (pgd_val(*pgd)) { + last_map_addr = phys_pud_update(pgd, __pa(start), + __pa(end), page_size_mask); + continue; + } + + if (after_bootmem) + pud = pud_offset(pgd, start & PGDIR_MASK); + else + pud = alloc_low_page(&pud_phys); + + last_map_addr = phys_pud_init(pud, __pa(start), __pa(next), + page_size_mask); + unmap_low_page(pud); + pgd_populate(&init_mm, pgd_offset_k(start), + __va(pud_phys)); + } + + return last_map_addr; +} + +struct map_range { + unsigned long start; + unsigned long end; + unsigned page_size_mask; +}; + +#define NR_RANGE_MR 5 + +static int save_mr(struct map_range *mr, int nr_range, + unsigned long start_pfn, unsigned long end_pfn, + unsigned long page_size_mask) +{ + + if (start_pfn < end_pfn) { + if (nr_range >= NR_RANGE_MR) + panic("run out of range for init_memory_mapping\n"); + mr[nr_range].start = start_pfn<<PAGE_SHIFT; + mr[nr_range].end = end_pfn<<PAGE_SHIFT; + mr[nr_range].page_size_mask = page_size_mask; + nr_range++; + } + + return nr_range; +} + /* * Setup the direct mapping of the physical memory at PAGE_OFFSET. * This runs before bootmem is initialized and gets pages directly from * the physical memory. To access them they are temporarily mapped. */ -unsigned long __init_refok init_memory_mapping(unsigned long start, unsigned long end) +unsigned long __init_refok init_memory_mapping(unsigned long start, + unsigned long end) { - unsigned long next, last_map_addr = end; - unsigned long start_phys = start, end_phys = end; + unsigned long last_map_addr = 0; + unsigned long page_size_mask = 0; + unsigned long start_pfn, end_pfn; + + struct map_range mr[NR_RANGE_MR]; + int nr_range, i; printk(KERN_INFO "init_memory_mapping\n"); @@ -560,48 +718,115 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, unsigned lon * memory mapped. Unfortunately this is done currently before the * nodes are discovered. */ - if (!after_bootmem) { + if (!after_bootmem) init_gbpages(); - find_early_table_space(end); + + if (direct_gbpages) + page_size_mask |= 1 << PG_LEVEL_1G; + if (cpu_has_pse) + page_size_mask |= 1 << PG_LEVEL_2M; + + memset(mr, 0, sizeof(mr)); + nr_range = 0; + + /* head if not big page alignment ?*/ + start_pfn = start >> PAGE_SHIFT; + end_pfn = ((start + (PMD_SIZE - 1)) >> PMD_SHIFT) + << (PMD_SHIFT - PAGE_SHIFT); + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); + + /* big page (2M) range*/ + start_pfn = ((start + (PMD_SIZE - 1))>>PMD_SHIFT) + << (PMD_SHIFT - PAGE_SHIFT); + end_pfn = ((start + (PUD_SIZE - 1))>>PUD_SHIFT) + << (PUD_SHIFT - PAGE_SHIFT); + if (end_pfn > ((end>>PUD_SHIFT)<<(PUD_SHIFT - PAGE_SHIFT))) + end_pfn = ((end>>PUD_SHIFT)<<(PUD_SHIFT - PAGE_SHIFT)); + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, + page_size_mask & (1<<PG_LEVEL_2M)); + + /* big page (1G) range */ + start_pfn = end_pfn; + end_pfn = (end>>PUD_SHIFT) << (PUD_SHIFT - PAGE_SHIFT); + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, + page_size_mask & + ((1<<PG_LEVEL_2M)|(1<<PG_LEVEL_1G))); + + /* tail is not big page (1G) alignment */ + start_pfn = end_pfn; + end_pfn = (end>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT); + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, + page_size_mask & (1<<PG_LEVEL_2M)); + + /* tail is not big page (2M) alignment */ + start_pfn = end_pfn; + end_pfn = end>>PAGE_SHIFT; + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); + + /* try to merge same page size and continuous */ + for (i = 0; nr_range > 1 && i < nr_range - 1; i++) { + unsigned long old_start; + if (mr[i].end != mr[i+1].start || + mr[i].page_size_mask != mr[i+1].page_size_mask) + continue; + /* move it */ + old_start = mr[i].start; + memmove(&mr[i], &mr[i+1], + (nr_range - 1 - i) * sizeof (struct map_range)); + mr[i].start = old_start; + nr_range--; } - start = (unsigned long)__va(start); - end = (unsigned long)__va(end); + for (i = 0; i < nr_range; i++) + printk(KERN_DEBUG " %010lx - %010lx page %s\n", + mr[i].start, mr[i].end, + (mr[i].page_size_mask & (1<<PG_LEVEL_1G))?"1G":( + (mr[i].page_size_mask & (1<<PG_LEVEL_2M))?"2M":"4k")); - for (; start < end; start = next) { - pgd_t *pgd = pgd_offset_k(start); - unsigned long pud_phys; - pud_t *pud; - - if (after_bootmem) - pud = pud_offset(pgd, start & PGDIR_MASK); - else - pud = alloc_low_page(&pud_phys); + if (!after_bootmem) + find_early_table_space(end); - next = start + PGDIR_SIZE; - if (next > end) - next = end; - last_map_addr = phys_pud_init(pud, __pa(start), __pa(next)); - if (!after_bootmem) - set_pgd(pgd_offset_k(start), mk_kernel_pgd(pud_phys)); - unmap_low_page(pud); - } + for (i = 0; i < nr_range; i++) + last_map_addr = kernel_physical_mapping_init( + mr[i].start, mr[i].end, + mr[i].page_size_mask); if (!after_bootmem) mmu_cr4_features = read_cr4(); __flush_tlb_all(); - if (!after_bootmem) + if (!after_bootmem && table_end > table_start) reserve_early(table_start << PAGE_SHIFT, table_end << PAGE_SHIFT, "PGTABLE"); + printk(KERN_INFO "last_map_addr: %lx end: %lx\n", + last_map_addr, end); + if (!after_bootmem) - early_memtest(start_phys, end_phys); + early_memtest(start, end); - return last_map_addr; + return last_map_addr >> PAGE_SHIFT; } #ifndef CONFIG_NUMA +void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn) +{ + unsigned long bootmap_size, bootmap; + + bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT; + bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size, + PAGE_SIZE); + if (bootmap == -1L) + panic("Cannot find bootmem map of size %ld\n", bootmap_size); + /* don't touch min_low_pfn */ + bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT, + 0, end_pfn); + e820_register_active_regions(0, start_pfn, end_pfn); + free_bootmem_with_active_regions(0, end_pfn); + early_res_to_bootmem(0, end_pfn<<PAGE_SHIFT); + reserve_bootmem(bootmap, bootmap_size, BOOTMEM_DEFAULT); +} + void __init paging_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES]; @@ -609,9 +834,9 @@ void __init paging_init(void) memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN; max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN; - max_zone_pfns[ZONE_NORMAL] = end_pfn; + max_zone_pfns[ZONE_NORMAL] = max_pfn; - memory_present(0, 0, end_pfn); + memory_present(0, 0, max_pfn); sparse_init(); free_area_init_nodes(max_zone_pfns); } @@ -693,8 +918,8 @@ void __init mem_init(void) #else totalram_pages = free_all_bootmem(); #endif - reservedpages = end_pfn - totalram_pages - - absent_pages_in_range(0, end_pfn); + reservedpages = max_pfn - totalram_pages - + absent_pages_in_range(0, max_pfn); after_bootmem = 1; codesize = (unsigned long) &_etext - (unsigned long) &_text; @@ -713,7 +938,7 @@ void __init mem_init(void) printk(KERN_INFO "Memory: %luk/%luk available (%ldk kernel code, " "%ldk reserved, %ldk data, %ldk init)\n", (unsigned long) nr_free_pages() << (PAGE_SHIFT-10), - end_pfn << (PAGE_SHIFT-10), + max_pfn << (PAGE_SHIFT-10), codesize >> 10, reservedpages << (PAGE_SHIFT-10), datasize >> 10, @@ -766,6 +991,13 @@ EXPORT_SYMBOL_GPL(rodata_test_data); void mark_rodata_ro(void) { unsigned long start = PFN_ALIGN(_stext), end = PFN_ALIGN(__end_rodata); + unsigned long rodata_start = + ((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK; + +#ifdef CONFIG_DYNAMIC_FTRACE + /* Dynamic tracing modifies the kernel text section */ + start = rodata_start; +#endif printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n", (end - start) >> 10); @@ -775,8 +1007,7 @@ void mark_rodata_ro(void) * The rodata section (but not the kernel text!) should also be * not-executable. */ - start = ((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK; - set_memory_nx(start, (end - start) >> PAGE_SHIFT); + set_memory_nx(rodata_start, (end - rodata_start) >> PAGE_SHIFT); rodata_test(); @@ -798,24 +1029,26 @@ void free_initrd_mem(unsigned long start, unsigned long end) } #endif -void __init reserve_bootmem_generic(unsigned long phys, unsigned len) +int __init reserve_bootmem_generic(unsigned long phys, unsigned long len, + int flags) { #ifdef CONFIG_NUMA int nid, next_nid; + int ret; #endif unsigned long pfn = phys >> PAGE_SHIFT; - if (pfn >= end_pfn) { + if (pfn >= max_pfn) { /* * This can happen with kdump kernels when accessing * firmware tables: */ if (pfn < max_pfn_mapped) - return; + return -EFAULT; - printk(KERN_ERR "reserve_bootmem: illegal reserve %lx %u\n", + printk(KERN_ERR "reserve_bootmem: illegal reserve %lx %lu\n", phys, len); - return; + return -EFAULT; } /* Should check here against the e820 map to avoid double free */ @@ -823,9 +1056,13 @@ void __init reserve_bootmem_generic(unsigned long phys, unsigned len) nid = phys_to_nid(phys); next_nid = phys_to_nid(phys + len - 1); if (nid == next_nid) - reserve_bootmem_node(NODE_DATA(nid), phys, len, BOOTMEM_DEFAULT); + ret = reserve_bootmem_node(NODE_DATA(nid), phys, len, flags); else - reserve_bootmem(phys, len, BOOTMEM_DEFAULT); + ret = reserve_bootmem(phys, len, flags); + + if (ret != 0) + return ret; + #else reserve_bootmem(phys, len, BOOTMEM_DEFAULT); #endif @@ -834,6 +1071,8 @@ void __init reserve_bootmem_generic(unsigned long phys, unsigned len) dma_reserve += len / PAGE_SIZE; set_dma_reserve(dma_reserve); } + + return 0; } int kern_addr_valid(unsigned long addr) @@ -938,7 +1177,7 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node) pmd_t *pmd; for (; addr < end; addr = next) { - next = pmd_addr_end(addr, end); + void *p = NULL; pgd = vmemmap_pgd_populate(addr, node); if (!pgd) @@ -948,33 +1187,51 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node) if (!pud) return -ENOMEM; - pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) { - pte_t entry; - void *p; + if (!cpu_has_pse) { + next = (addr + PAGE_SIZE) & PAGE_MASK; + pmd = vmemmap_pmd_populate(pud, addr, node); + + if (!pmd) + return -ENOMEM; + + p = vmemmap_pte_populate(pmd, addr, node); - p = vmemmap_alloc_block(PMD_SIZE, node); if (!p) return -ENOMEM; - entry = pfn_pte(__pa(p) >> PAGE_SHIFT, - PAGE_KERNEL_LARGE); - set_pmd(pmd, __pmd(pte_val(entry))); - - /* check to see if we have contiguous blocks */ - if (p_end != p || node_start != node) { - if (p_start) - printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n", - addr_start, addr_end-1, p_start, p_end-1, node_start); - addr_start = addr; - node_start = node; - p_start = p; - } - addr_end = addr + PMD_SIZE; - p_end = p + PMD_SIZE; + addr_end = addr + PAGE_SIZE; + p_end = p + PAGE_SIZE; } else { - vmemmap_verify((pte_t *)pmd, node, addr, next); + next = pmd_addr_end(addr, end); + + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) { + pte_t entry; + + p = vmemmap_alloc_block(PMD_SIZE, node); + if (!p) + return -ENOMEM; + + entry = pfn_pte(__pa(p) >> PAGE_SHIFT, + PAGE_KERNEL_LARGE); + set_pmd(pmd, __pmd(pte_val(entry))); + + /* check to see if we have contiguous blocks */ + if (p_end != p || node_start != node) { + if (p_start) + printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n", + addr_start, addr_end-1, p_start, p_end-1, node_start); + addr_start = addr; + node_start = node; + p_start = p; + } + + addr_end = addr + PMD_SIZE; + p_end = p + PMD_SIZE; + } else + vmemmap_verify((pte_t *)pmd, node, addr, next); } + } return 0; } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 71bb3159031a..24c1d3c30186 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -12,6 +12,7 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/vmalloc.h> +#include <linux/mmiotrace.h> #include <asm/cacheflush.h> #include <asm/e820.h> @@ -122,10 +123,13 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, { unsigned long pfn, offset, vaddr; resource_size_t last_addr; + const resource_size_t unaligned_phys_addr = phys_addr; + const unsigned long unaligned_size = size; struct vm_struct *area; unsigned long new_prot_val; pgprot_t prot; int retval; + void __iomem *ret_addr; /* Don't allow wraparound or zero size */ last_addr = phys_addr + size - 1; @@ -142,7 +146,7 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, /* * Don't remap the low PCI/ISA area, it's always mapped.. */ - if (phys_addr >= ISA_START_ADDRESS && last_addr < ISA_END_ADDRESS) + if (is_ISA_range(phys_addr, last_addr)) return (__force void __iomem *)phys_to_virt(phys_addr); /* @@ -233,7 +237,10 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, return NULL; } - return (void __iomem *) (vaddr + offset); + ret_addr = (void __iomem *) (vaddr + offset); + mmiotrace_ioremap(unaligned_phys_addr, unaligned_size, ret_addr); + + return ret_addr; } /** @@ -261,7 +268,7 @@ void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size) { /* * Ideally, this should be: - * pat_wc_enabled ? _PAGE_CACHE_UC : _PAGE_CACHE_UC_MINUS; + * pat_enabled ? _PAGE_CACHE_UC : _PAGE_CACHE_UC_MINUS; * * Till we fix all X drivers to use ioremap_wc(), we will use * UC MINUS. @@ -285,7 +292,7 @@ EXPORT_SYMBOL(ioremap_nocache); */ void __iomem *ioremap_wc(unsigned long phys_addr, unsigned long size) { - if (pat_wc_enabled) + if (pat_enabled) return __ioremap_caller(phys_addr, size, _PAGE_CACHE_WC, __builtin_return_address(0)); else @@ -300,6 +307,29 @@ void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size) } EXPORT_SYMBOL(ioremap_cache); +static void __iomem *ioremap_default(resource_size_t phys_addr, + unsigned long size) +{ + unsigned long flags; + void *ret; + int err; + + /* + * - WB for WB-able memory and no other conflicting mappings + * - UC_MINUS for non-WB-able memory with no other conflicting mappings + * - Inherit from confliting mappings otherwise + */ + err = reserve_memtype(phys_addr, phys_addr + size, -1, &flags); + if (err < 0) + return NULL; + + ret = (void *) __ioremap_caller(phys_addr, size, flags, + __builtin_return_address(0)); + + free_memtype(phys_addr, phys_addr + size); + return (void __iomem *)ret; +} + /** * iounmap - Free a IO remapping * @addr: virtual address from ioremap_* @@ -318,13 +348,15 @@ void iounmap(volatile void __iomem *addr) * vm_area and by simply returning an address into the kernel mapping * of ISA space. So handle that here. */ - if (addr >= phys_to_virt(ISA_START_ADDRESS) && - addr < phys_to_virt(ISA_END_ADDRESS)) + if ((void __force *)addr >= phys_to_virt(ISA_START_ADDRESS) && + (void __force *)addr < phys_to_virt(ISA_END_ADDRESS)) return; addr = (volatile void __iomem *) (PAGE_MASK & (unsigned long __force)addr); + mmiotrace_iounmap(addr); + /* Use the vm area unlocked, assuming the caller ensures there isn't another iounmap for the same address in parallel. Reuse of the virtual address is prevented by @@ -332,7 +364,7 @@ void iounmap(volatile void __iomem *addr) cpa takes care of the direct mappings. */ read_lock(&vmlist_lock); for (p = vmlist; p; p = p->next) { - if (p->addr == addr) + if (p->addr == (void __force *)addr) break; } read_unlock(&vmlist_lock); @@ -346,7 +378,7 @@ void iounmap(volatile void __iomem *addr) free_memtype(p->phys_addr, p->phys_addr + get_vm_area_size(p)); /* Finally remove it */ - o = remove_vm_area((void *)addr); + o = remove_vm_area((void __force *)addr); BUG_ON(p != o || o == NULL); kfree(p); } @@ -365,7 +397,7 @@ void *xlate_dev_mem_ptr(unsigned long phys) if (page_is_ram(start >> PAGE_SHIFT)) return __va(phys); - addr = (void *)ioremap(start, PAGE_SIZE); + addr = (void __force *)ioremap_default(start, PAGE_SIZE); if (addr) addr = (void *)((unsigned long)addr | (phys & ~PAGE_MASK)); @@ -381,8 +413,6 @@ void unxlate_dev_mem_ptr(unsigned long phys, void *addr) return; } -#ifdef CONFIG_X86_32 - int __initdata early_ioremap_debug; static int __init early_ioremap_debug_setup(char *str) @@ -394,8 +424,7 @@ static int __init early_ioremap_debug_setup(char *str) early_param("early_ioremap_debug", early_ioremap_debug_setup); static __initdata int after_paging_init; -static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] - __section(.bss.page_aligned); +static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] __page_aligned_bss; static inline pmd_t * __init early_ioremap_pmd(unsigned long addr) { @@ -484,10 +513,11 @@ static void __init __early_set_fixmap(enum fixed_addresses idx, return; } pte = early_ioremap_pte(addr); + if (pgprot_val(flags)) set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags)); else - pte_clear(NULL, addr, pte); + pte_clear(&init_mm, addr, pte); __flush_tlb_one(addr); } @@ -593,10 +623,11 @@ void __init early_iounmap(void *addr, unsigned long size) unsigned long offset; unsigned int nrpages; enum fixed_addresses idx; - unsigned int nesting; + int nesting; nesting = --early_ioremap_nested; - WARN_ON(nesting < 0); + if (WARN_ON(nesting < 0)) + return; if (early_ioremap_debug) { printk(KERN_INFO "early_iounmap(%p, %08lx) [%d]\n", addr, @@ -624,5 +655,3 @@ void __this_fixmap_does_not_exist(void) { WARN_ON(1); } - -#endif /* CONFIG_X86_32 */ diff --git a/arch/x86/mm/k8topology_64.c b/arch/x86/mm/k8topology_64.c index 1f476e477844..41f1b5c00a1d 100644 --- a/arch/x86/mm/k8topology_64.c +++ b/arch/x86/mm/k8topology_64.c @@ -22,6 +22,7 @@ #include <asm/numa.h> #include <asm/mpspec.h> #include <asm/apic.h> +#include <asm/k8.h> static __init int find_northbridge(void) { @@ -56,34 +57,33 @@ static __init void early_get_boot_cpu_id(void) /* * Find possible boot-time SMP configuration: */ +#ifdef CONFIG_X86_MPPARSE early_find_smp_config(); +#endif #ifdef CONFIG_ACPI /* * Read APIC information from ACPI tables. */ early_acpi_boot_init(); #endif +#ifdef CONFIG_X86_MPPARSE /* * get boot-time SMP configuration: */ if (smp_found_config) early_get_smp_config(); +#endif early_init_lapic_mapping(); } int __init k8_scan_nodes(unsigned long start, unsigned long end) { + unsigned numnodes, cores, bits, apicid_base; unsigned long prevbase; struct bootnode nodes[8]; - int nodeid, i, nb; unsigned char nodeids[8]; - int found = 0; - u32 reg; - unsigned numnodes; - unsigned cores; - unsigned bits; - int j; - unsigned apicid_base; + int i, j, nb, found = 0; + u32 nodeid, reg; if (!early_pci_allowed()) return -1; @@ -105,7 +105,6 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end) prevbase = 0; for (i = 0; i < 8; i++) { unsigned long base, limit; - u32 nodeid; base = read_pci_config(0, nb, 1, 0x40 + i*8); limit = read_pci_config(0, nb, 1, 0x44 + i*8); @@ -144,8 +143,8 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end) limit |= (1<<24)-1; limit++; - if (limit > end_pfn << PAGE_SHIFT) - limit = end_pfn << PAGE_SHIFT; + if (limit > max_pfn << PAGE_SHIFT) + limit = max_pfn << PAGE_SHIFT; if (limit <= base) continue; diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c new file mode 100644 index 000000000000..93d82038af4b --- /dev/null +++ b/arch/x86/mm/kmmio.c @@ -0,0 +1,510 @@ +/* Support for MMIO probes. + * Benfit many code from kprobes + * (C) 2002 Louis Zhuang <louis.zhuang@intel.com>. + * 2007 Alexander Eichner + * 2008 Pekka Paalanen <pq@iki.fi> + */ + +#include <linux/list.h> +#include <linux/rculist.h> +#include <linux/spinlock.h> +#include <linux/hash.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/uaccess.h> +#include <linux/ptrace.h> +#include <linux/preempt.h> +#include <linux/percpu.h> +#include <linux/kdebug.h> +#include <linux/mutex.h> +#include <linux/io.h> +#include <asm/cacheflush.h> +#include <asm/tlbflush.h> +#include <linux/errno.h> +#include <asm/debugreg.h> +#include <linux/mmiotrace.h> + +#define KMMIO_PAGE_HASH_BITS 4 +#define KMMIO_PAGE_TABLE_SIZE (1 << KMMIO_PAGE_HASH_BITS) + +struct kmmio_fault_page { + struct list_head list; + struct kmmio_fault_page *release_next; + unsigned long page; /* location of the fault page */ + + /* + * Number of times this page has been registered as a part + * of a probe. If zero, page is disarmed and this may be freed. + * Used only by writers (RCU). + */ + int count; +}; + +struct kmmio_delayed_release { + struct rcu_head rcu; + struct kmmio_fault_page *release_list; +}; + +struct kmmio_context { + struct kmmio_fault_page *fpage; + struct kmmio_probe *probe; + unsigned long saved_flags; + unsigned long addr; + int active; +}; + +static DEFINE_SPINLOCK(kmmio_lock); + +/* Protected by kmmio_lock */ +unsigned int kmmio_count; + +/* Read-protected by RCU, write-protected by kmmio_lock. */ +static struct list_head kmmio_page_table[KMMIO_PAGE_TABLE_SIZE]; +static LIST_HEAD(kmmio_probes); + +static struct list_head *kmmio_page_list(unsigned long page) +{ + return &kmmio_page_table[hash_long(page, KMMIO_PAGE_HASH_BITS)]; +} + +/* Accessed per-cpu */ +static DEFINE_PER_CPU(struct kmmio_context, kmmio_ctx); + +/* + * this is basically a dynamic stabbing problem: + * Could use the existing prio tree code or + * Possible better implementations: + * The Interval Skip List: A Data Structure for Finding All Intervals That + * Overlap a Point (might be simple) + * Space Efficient Dynamic Stabbing with Fast Queries - Mikkel Thorup + */ +/* Get the kmmio at this addr (if any). You must be holding RCU read lock. */ +static struct kmmio_probe *get_kmmio_probe(unsigned long addr) +{ + struct kmmio_probe *p; + list_for_each_entry_rcu(p, &kmmio_probes, list) { + if (addr >= p->addr && addr <= (p->addr + p->len)) + return p; + } + return NULL; +} + +/* You must be holding RCU read lock. */ +static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long page) +{ + struct list_head *head; + struct kmmio_fault_page *p; + + page &= PAGE_MASK; + head = kmmio_page_list(page); + list_for_each_entry_rcu(p, head, list) { + if (p->page == page) + return p; + } + return NULL; +} + +static void set_page_present(unsigned long addr, bool present, + unsigned int *pglevel) +{ + pteval_t pteval; + pmdval_t pmdval; + unsigned int level; + pmd_t *pmd; + pte_t *pte = lookup_address(addr, &level); + + if (!pte) { + pr_err("kmmio: no pte for page 0x%08lx\n", addr); + return; + } + + if (pglevel) + *pglevel = level; + + switch (level) { + case PG_LEVEL_2M: + pmd = (pmd_t *)pte; + pmdval = pmd_val(*pmd) & ~_PAGE_PRESENT; + if (present) + pmdval |= _PAGE_PRESENT; + set_pmd(pmd, __pmd(pmdval)); + break; + + case PG_LEVEL_4K: + pteval = pte_val(*pte) & ~_PAGE_PRESENT; + if (present) + pteval |= _PAGE_PRESENT; + set_pte_atomic(pte, __pte(pteval)); + break; + + default: + pr_err("kmmio: unexpected page level 0x%x.\n", level); + return; + } + + __flush_tlb_one(addr); +} + +/** Mark the given page as not present. Access to it will trigger a fault. */ +static void arm_kmmio_fault_page(unsigned long page, unsigned int *pglevel) +{ + set_page_present(page & PAGE_MASK, false, pglevel); +} + +/** Mark the given page as present. */ +static void disarm_kmmio_fault_page(unsigned long page, unsigned int *pglevel) +{ + set_page_present(page & PAGE_MASK, true, pglevel); +} + +/* + * This is being called from do_page_fault(). + * + * We may be in an interrupt or a critical section. Also prefecthing may + * trigger a page fault. We may be in the middle of process switch. + * We cannot take any locks, because we could be executing especially + * within a kmmio critical section. + * + * Local interrupts are disabled, so preemption cannot happen. + * Do not enable interrupts, do not sleep, and watch out for other CPUs. + */ +/* + * Interrupts are disabled on entry as trap3 is an interrupt gate + * and they remain disabled thorough out this function. + */ +int kmmio_handler(struct pt_regs *regs, unsigned long addr) +{ + struct kmmio_context *ctx; + struct kmmio_fault_page *faultpage; + int ret = 0; /* default to fault not handled */ + + /* + * Preemption is now disabled to prevent process switch during + * single stepping. We can only handle one active kmmio trace + * per cpu, so ensure that we finish it before something else + * gets to run. We also hold the RCU read lock over single + * stepping to avoid looking up the probe and kmmio_fault_page + * again. + */ + preempt_disable(); + rcu_read_lock(); + + faultpage = get_kmmio_fault_page(addr); + if (!faultpage) { + /* + * Either this page fault is not caused by kmmio, or + * another CPU just pulled the kmmio probe from under + * our feet. The latter case should not be possible. + */ + goto no_kmmio; + } + + ctx = &get_cpu_var(kmmio_ctx); + if (ctx->active) { + disarm_kmmio_fault_page(faultpage->page, NULL); + if (addr == ctx->addr) { + /* + * On SMP we sometimes get recursive probe hits on the + * same address. Context is already saved, fall out. + */ + pr_debug("kmmio: duplicate probe hit on CPU %d, for " + "address 0x%08lx.\n", + smp_processor_id(), addr); + ret = 1; + goto no_kmmio_ctx; + } + /* + * Prevent overwriting already in-flight context. + * This should not happen, let's hope disarming at least + * prevents a panic. + */ + pr_emerg("kmmio: recursive probe hit on CPU %d, " + "for address 0x%08lx. Ignoring.\n", + smp_processor_id(), addr); + pr_emerg("kmmio: previous hit was at 0x%08lx.\n", + ctx->addr); + goto no_kmmio_ctx; + } + ctx->active++; + + ctx->fpage = faultpage; + ctx->probe = get_kmmio_probe(addr); + ctx->saved_flags = (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF)); + ctx->addr = addr; + + if (ctx->probe && ctx->probe->pre_handler) + ctx->probe->pre_handler(ctx->probe, regs, addr); + + /* + * Enable single-stepping and disable interrupts for the faulting + * context. Local interrupts must not get enabled during stepping. + */ + regs->flags |= X86_EFLAGS_TF; + regs->flags &= ~X86_EFLAGS_IF; + + /* Now we set present bit in PTE and single step. */ + disarm_kmmio_fault_page(ctx->fpage->page, NULL); + + /* + * If another cpu accesses the same page while we are stepping, + * the access will not be caught. It will simply succeed and the + * only downside is we lose the event. If this becomes a problem, + * the user should drop to single cpu before tracing. + */ + + put_cpu_var(kmmio_ctx); + return 1; /* fault handled */ + +no_kmmio_ctx: + put_cpu_var(kmmio_ctx); +no_kmmio: + rcu_read_unlock(); + preempt_enable_no_resched(); + return ret; +} + +/* + * Interrupts are disabled on entry as trap1 is an interrupt gate + * and they remain disabled thorough out this function. + * This must always get called as the pair to kmmio_handler(). + */ +static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs) +{ + int ret = 0; + struct kmmio_context *ctx = &get_cpu_var(kmmio_ctx); + + if (!ctx->active) { + pr_debug("kmmio: spurious debug trap on CPU %d.\n", + smp_processor_id()); + goto out; + } + + if (ctx->probe && ctx->probe->post_handler) + ctx->probe->post_handler(ctx->probe, condition, regs); + + arm_kmmio_fault_page(ctx->fpage->page, NULL); + + regs->flags &= ~X86_EFLAGS_TF; + regs->flags |= ctx->saved_flags; + + /* These were acquired in kmmio_handler(). */ + ctx->active--; + BUG_ON(ctx->active); + rcu_read_unlock(); + preempt_enable_no_resched(); + + /* + * if somebody else is singlestepping across a probe point, flags + * will have TF set, in which case, continue the remaining processing + * of do_debug, as if this is not a probe hit. + */ + if (!(regs->flags & X86_EFLAGS_TF)) + ret = 1; +out: + put_cpu_var(kmmio_ctx); + return ret; +} + +/* You must be holding kmmio_lock. */ +static int add_kmmio_fault_page(unsigned long page) +{ + struct kmmio_fault_page *f; + + page &= PAGE_MASK; + f = get_kmmio_fault_page(page); + if (f) { + if (!f->count) + arm_kmmio_fault_page(f->page, NULL); + f->count++; + return 0; + } + + f = kmalloc(sizeof(*f), GFP_ATOMIC); + if (!f) + return -1; + + f->count = 1; + f->page = page; + list_add_rcu(&f->list, kmmio_page_list(f->page)); + + arm_kmmio_fault_page(f->page, NULL); + + return 0; +} + +/* You must be holding kmmio_lock. */ +static void release_kmmio_fault_page(unsigned long page, + struct kmmio_fault_page **release_list) +{ + struct kmmio_fault_page *f; + + page &= PAGE_MASK; + f = get_kmmio_fault_page(page); + if (!f) + return; + + f->count--; + BUG_ON(f->count < 0); + if (!f->count) { + disarm_kmmio_fault_page(f->page, NULL); + f->release_next = *release_list; + *release_list = f; + } +} + +/* + * With page-unaligned ioremaps, one or two armed pages may contain + * addresses from outside the intended mapping. Events for these addresses + * are currently silently dropped. The events may result only from programming + * mistakes by accessing addresses before the beginning or past the end of a + * mapping. + */ +int register_kmmio_probe(struct kmmio_probe *p) +{ + unsigned long flags; + int ret = 0; + unsigned long size = 0; + const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK); + + spin_lock_irqsave(&kmmio_lock, flags); + if (get_kmmio_probe(p->addr)) { + ret = -EEXIST; + goto out; + } + kmmio_count++; + list_add_rcu(&p->list, &kmmio_probes); + while (size < size_lim) { + if (add_kmmio_fault_page(p->addr + size)) + pr_err("kmmio: Unable to set page fault.\n"); + size += PAGE_SIZE; + } +out: + spin_unlock_irqrestore(&kmmio_lock, flags); + /* + * XXX: What should I do here? + * Here was a call to global_flush_tlb(), but it does not exist + * anymore. It seems it's not needed after all. + */ + return ret; +} +EXPORT_SYMBOL(register_kmmio_probe); + +static void rcu_free_kmmio_fault_pages(struct rcu_head *head) +{ + struct kmmio_delayed_release *dr = container_of( + head, + struct kmmio_delayed_release, + rcu); + struct kmmio_fault_page *p = dr->release_list; + while (p) { + struct kmmio_fault_page *next = p->release_next; + BUG_ON(p->count); + kfree(p); + p = next; + } + kfree(dr); +} + +static void remove_kmmio_fault_pages(struct rcu_head *head) +{ + struct kmmio_delayed_release *dr = container_of( + head, + struct kmmio_delayed_release, + rcu); + struct kmmio_fault_page *p = dr->release_list; + struct kmmio_fault_page **prevp = &dr->release_list; + unsigned long flags; + spin_lock_irqsave(&kmmio_lock, flags); + while (p) { + if (!p->count) + list_del_rcu(&p->list); + else + *prevp = p->release_next; + prevp = &p->release_next; + p = p->release_next; + } + spin_unlock_irqrestore(&kmmio_lock, flags); + /* This is the real RCU destroy call. */ + call_rcu(&dr->rcu, rcu_free_kmmio_fault_pages); +} + +/* + * Remove a kmmio probe. You have to synchronize_rcu() before you can be + * sure that the callbacks will not be called anymore. Only after that + * you may actually release your struct kmmio_probe. + * + * Unregistering a kmmio fault page has three steps: + * 1. release_kmmio_fault_page() + * Disarm the page, wait a grace period to let all faults finish. + * 2. remove_kmmio_fault_pages() + * Remove the pages from kmmio_page_table. + * 3. rcu_free_kmmio_fault_pages() + * Actally free the kmmio_fault_page structs as with RCU. + */ +void unregister_kmmio_probe(struct kmmio_probe *p) +{ + unsigned long flags; + unsigned long size = 0; + const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK); + struct kmmio_fault_page *release_list = NULL; + struct kmmio_delayed_release *drelease; + + spin_lock_irqsave(&kmmio_lock, flags); + while (size < size_lim) { + release_kmmio_fault_page(p->addr + size, &release_list); + size += PAGE_SIZE; + } + list_del_rcu(&p->list); + kmmio_count--; + spin_unlock_irqrestore(&kmmio_lock, flags); + + drelease = kmalloc(sizeof(*drelease), GFP_ATOMIC); + if (!drelease) { + pr_crit("kmmio: leaking kmmio_fault_page objects.\n"); + return; + } + drelease->release_list = release_list; + + /* + * This is not really RCU here. We have just disarmed a set of + * pages so that they cannot trigger page faults anymore. However, + * we cannot remove the pages from kmmio_page_table, + * because a probe hit might be in flight on another CPU. The + * pages are collected into a list, and they will be removed from + * kmmio_page_table when it is certain that no probe hit related to + * these pages can be in flight. RCU grace period sounds like a + * good choice. + * + * If we removed the pages too early, kmmio page fault handler might + * not find the respective kmmio_fault_page and determine it's not + * a kmmio fault, when it actually is. This would lead to madness. + */ + call_rcu(&drelease->rcu, remove_kmmio_fault_pages); +} +EXPORT_SYMBOL(unregister_kmmio_probe); + +static int kmmio_die_notifier(struct notifier_block *nb, unsigned long val, + void *args) +{ + struct die_args *arg = args; + + if (val == DIE_DEBUG && (arg->err & DR_STEP)) + if (post_kmmio_handler(arg->err, arg->regs) == 1) + return NOTIFY_STOP; + + return NOTIFY_DONE; +} + +static struct notifier_block nb_die = { + .notifier_call = kmmio_die_notifier +}; + +static int __init init_kmmio(void) +{ + int i; + for (i = 0; i < KMMIO_PAGE_TABLE_SIZE; i++) + INIT_LIST_HEAD(&kmmio_page_table[i]); + return register_die_notifier(&nb_die); +} +fs_initcall(init_kmmio); /* should be before device_initcall() */ diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c new file mode 100644 index 000000000000..e7397e108beb --- /dev/null +++ b/arch/x86/mm/mmio-mod.c @@ -0,0 +1,515 @@ +/* + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2005 + * Jeff Muizelaar, 2006, 2007 + * Pekka Paalanen, 2008 <pq@iki.fi> + * + * Derived from the read-mod example from relay-examples by Tom Zanussi. + */ +#define DEBUG 1 + +#include <linux/module.h> +#include <linux/debugfs.h> +#include <linux/uaccess.h> +#include <linux/io.h> +#include <linux/version.h> +#include <linux/kallsyms.h> +#include <asm/pgtable.h> +#include <linux/mmiotrace.h> +#include <asm/e820.h> /* for ISA_START_ADDRESS */ +#include <asm/atomic.h> +#include <linux/percpu.h> +#include <linux/cpu.h> + +#include "pf_in.h" + +#define NAME "mmiotrace: " + +struct trap_reason { + unsigned long addr; + unsigned long ip; + enum reason_type type; + int active_traces; +}; + +struct remap_trace { + struct list_head list; + struct kmmio_probe probe; + resource_size_t phys; + unsigned long id; +}; + +/* Accessed per-cpu. */ +static DEFINE_PER_CPU(struct trap_reason, pf_reason); +static DEFINE_PER_CPU(struct mmiotrace_rw, cpu_trace); + +#if 0 /* XXX: no way gather this info anymore */ +/* Access to this is not per-cpu. */ +static DEFINE_PER_CPU(atomic_t, dropped); +#endif + +static struct dentry *marker_file; + +static DEFINE_MUTEX(mmiotrace_mutex); +static DEFINE_SPINLOCK(trace_lock); +static atomic_t mmiotrace_enabled; +static LIST_HEAD(trace_list); /* struct remap_trace */ + +/* + * Locking in this file: + * - mmiotrace_mutex enforces enable/disable_mmiotrace() critical sections. + * - mmiotrace_enabled may be modified only when holding mmiotrace_mutex + * and trace_lock. + * - Routines depending on is_enabled() must take trace_lock. + * - trace_list users must hold trace_lock. + * - is_enabled() guarantees that mmio_trace_record is allowed. + * - pre/post callbacks assume the effect of is_enabled() being true. + */ + +/* module parameters */ +static unsigned long filter_offset; +static int nommiotrace; +static int trace_pc; + +module_param(filter_offset, ulong, 0); +module_param(nommiotrace, bool, 0); +module_param(trace_pc, bool, 0); + +MODULE_PARM_DESC(filter_offset, "Start address of traced mappings."); +MODULE_PARM_DESC(nommiotrace, "Disable actual MMIO tracing."); +MODULE_PARM_DESC(trace_pc, "Record address of faulting instructions."); + +static bool is_enabled(void) +{ + return atomic_read(&mmiotrace_enabled); +} + +#if 0 /* XXX: needs rewrite */ +/* + * Write callback for the debugfs entry: + * Read a marker and write it to the mmio trace log + */ +static ssize_t write_marker(struct file *file, const char __user *buffer, + size_t count, loff_t *ppos) +{ + char *event = NULL; + struct mm_io_header *headp; + ssize_t len = (count > 65535) ? 65535 : count; + + event = kzalloc(sizeof(*headp) + len, GFP_KERNEL); + if (!event) + return -ENOMEM; + + headp = (struct mm_io_header *)event; + headp->type = MMIO_MAGIC | (MMIO_MARKER << MMIO_OPCODE_SHIFT); + headp->data_len = len; + + if (copy_from_user(event + sizeof(*headp), buffer, len)) { + kfree(event); + return -EFAULT; + } + + spin_lock_irq(&trace_lock); +#if 0 /* XXX: convert this to use tracing */ + if (is_enabled()) + relay_write(chan, event, sizeof(*headp) + len); + else +#endif + len = -EINVAL; + spin_unlock_irq(&trace_lock); + kfree(event); + return len; +} +#endif + +static void print_pte(unsigned long address) +{ + unsigned int level; + pte_t *pte = lookup_address(address, &level); + + if (!pte) { + pr_err(NAME "Error in %s: no pte for page 0x%08lx\n", + __func__, address); + return; + } + + if (level == PG_LEVEL_2M) { + pr_emerg(NAME "4MB pages are not currently supported: " + "0x%08lx\n", address); + BUG(); + } + pr_info(NAME "pte for 0x%lx: 0x%llx 0x%llx\n", address, + (unsigned long long)pte_val(*pte), + (unsigned long long)pte_val(*pte) & _PAGE_PRESENT); +} + +/* + * For some reason the pre/post pairs have been called in an + * unmatched order. Report and die. + */ +static void die_kmmio_nesting_error(struct pt_regs *regs, unsigned long addr) +{ + const struct trap_reason *my_reason = &get_cpu_var(pf_reason); + pr_emerg(NAME "unexpected fault for address: 0x%08lx, " + "last fault for address: 0x%08lx\n", + addr, my_reason->addr); + print_pte(addr); + print_symbol(KERN_EMERG "faulting IP is at %s\n", regs->ip); + print_symbol(KERN_EMERG "last faulting IP was at %s\n", my_reason->ip); +#ifdef __i386__ + pr_emerg("eax: %08lx ebx: %08lx ecx: %08lx edx: %08lx\n", + regs->ax, regs->bx, regs->cx, regs->dx); + pr_emerg("esi: %08lx edi: %08lx ebp: %08lx esp: %08lx\n", + regs->si, regs->di, regs->bp, regs->sp); +#else + pr_emerg("rax: %016lx rcx: %016lx rdx: %016lx\n", + regs->ax, regs->cx, regs->dx); + pr_emerg("rsi: %016lx rdi: %016lx rbp: %016lx rsp: %016lx\n", + regs->si, regs->di, regs->bp, regs->sp); +#endif + put_cpu_var(pf_reason); + BUG(); +} + +static void pre(struct kmmio_probe *p, struct pt_regs *regs, + unsigned long addr) +{ + struct trap_reason *my_reason = &get_cpu_var(pf_reason); + struct mmiotrace_rw *my_trace = &get_cpu_var(cpu_trace); + const unsigned long instptr = instruction_pointer(regs); + const enum reason_type type = get_ins_type(instptr); + struct remap_trace *trace = p->private; + + /* it doesn't make sense to have more than one active trace per cpu */ + if (my_reason->active_traces) + die_kmmio_nesting_error(regs, addr); + else + my_reason->active_traces++; + + my_reason->type = type; + my_reason->addr = addr; + my_reason->ip = instptr; + + my_trace->phys = addr - trace->probe.addr + trace->phys; + my_trace->map_id = trace->id; + + /* + * Only record the program counter when requested. + * It may taint clean-room reverse engineering. + */ + if (trace_pc) + my_trace->pc = instptr; + else + my_trace->pc = 0; + + /* + * XXX: the timestamp recorded will be *after* the tracing has been + * done, not at the time we hit the instruction. SMP implications + * on event ordering? + */ + + switch (type) { + case REG_READ: + my_trace->opcode = MMIO_READ; + my_trace->width = get_ins_mem_width(instptr); + break; + case REG_WRITE: + my_trace->opcode = MMIO_WRITE; + my_trace->width = get_ins_mem_width(instptr); + my_trace->value = get_ins_reg_val(instptr, regs); + break; + case IMM_WRITE: + my_trace->opcode = MMIO_WRITE; + my_trace->width = get_ins_mem_width(instptr); + my_trace->value = get_ins_imm_val(instptr); + break; + default: + { + unsigned char *ip = (unsigned char *)instptr; + my_trace->opcode = MMIO_UNKNOWN_OP; + my_trace->width = 0; + my_trace->value = (*ip) << 16 | *(ip + 1) << 8 | + *(ip + 2); + } + } + put_cpu_var(cpu_trace); + put_cpu_var(pf_reason); +} + +static void post(struct kmmio_probe *p, unsigned long condition, + struct pt_regs *regs) +{ + struct trap_reason *my_reason = &get_cpu_var(pf_reason); + struct mmiotrace_rw *my_trace = &get_cpu_var(cpu_trace); + + /* this should always return the active_trace count to 0 */ + my_reason->active_traces--; + if (my_reason->active_traces) { + pr_emerg(NAME "unexpected post handler"); + BUG(); + } + + switch (my_reason->type) { + case REG_READ: + my_trace->value = get_ins_reg_val(my_reason->ip, regs); + break; + default: + break; + } + + mmio_trace_rw(my_trace); + put_cpu_var(cpu_trace); + put_cpu_var(pf_reason); +} + +static void ioremap_trace_core(resource_size_t offset, unsigned long size, + void __iomem *addr) +{ + static atomic_t next_id; + struct remap_trace *trace = kmalloc(sizeof(*trace), GFP_KERNEL); + /* These are page-unaligned. */ + struct mmiotrace_map map = { + .phys = offset, + .virt = (unsigned long)addr, + .len = size, + .opcode = MMIO_PROBE + }; + + if (!trace) { + pr_err(NAME "kmalloc failed in ioremap\n"); + return; + } + + *trace = (struct remap_trace) { + .probe = { + .addr = (unsigned long)addr, + .len = size, + .pre_handler = pre, + .post_handler = post, + .private = trace + }, + .phys = offset, + .id = atomic_inc_return(&next_id) + }; + map.map_id = trace->id; + + spin_lock_irq(&trace_lock); + if (!is_enabled()) + goto not_enabled; + + mmio_trace_mapping(&map); + list_add_tail(&trace->list, &trace_list); + if (!nommiotrace) + register_kmmio_probe(&trace->probe); + +not_enabled: + spin_unlock_irq(&trace_lock); +} + +void mmiotrace_ioremap(resource_size_t offset, unsigned long size, + void __iomem *addr) +{ + if (!is_enabled()) /* recheck and proper locking in *_core() */ + return; + + pr_debug(NAME "ioremap_*(0x%llx, 0x%lx) = %p\n", + (unsigned long long)offset, size, addr); + if ((filter_offset) && (offset != filter_offset)) + return; + ioremap_trace_core(offset, size, addr); +} + +static void iounmap_trace_core(volatile void __iomem *addr) +{ + struct mmiotrace_map map = { + .phys = 0, + .virt = (unsigned long)addr, + .len = 0, + .opcode = MMIO_UNPROBE + }; + struct remap_trace *trace; + struct remap_trace *tmp; + struct remap_trace *found_trace = NULL; + + pr_debug(NAME "Unmapping %p.\n", addr); + + spin_lock_irq(&trace_lock); + if (!is_enabled()) + goto not_enabled; + + list_for_each_entry_safe(trace, tmp, &trace_list, list) { + if ((unsigned long)addr == trace->probe.addr) { + if (!nommiotrace) + unregister_kmmio_probe(&trace->probe); + list_del(&trace->list); + found_trace = trace; + break; + } + } + map.map_id = (found_trace) ? found_trace->id : -1; + mmio_trace_mapping(&map); + +not_enabled: + spin_unlock_irq(&trace_lock); + if (found_trace) { + synchronize_rcu(); /* unregister_kmmio_probe() requirement */ + kfree(found_trace); + } +} + +void mmiotrace_iounmap(volatile void __iomem *addr) +{ + might_sleep(); + if (is_enabled()) /* recheck and proper locking in *_core() */ + iounmap_trace_core(addr); +} + +static void clear_trace_list(void) +{ + struct remap_trace *trace; + struct remap_trace *tmp; + + /* + * No locking required, because the caller ensures we are in a + * critical section via mutex, and is_enabled() is false, + * i.e. nothing can traverse or modify this list. + * Caller also ensures is_enabled() cannot change. + */ + list_for_each_entry(trace, &trace_list, list) { + pr_notice(NAME "purging non-iounmapped " + "trace @0x%08lx, size 0x%lx.\n", + trace->probe.addr, trace->probe.len); + if (!nommiotrace) + unregister_kmmio_probe(&trace->probe); + } + synchronize_rcu(); /* unregister_kmmio_probe() requirement */ + + list_for_each_entry_safe(trace, tmp, &trace_list, list) { + list_del(&trace->list); + kfree(trace); + } +} + +#ifdef CONFIG_HOTPLUG_CPU +static cpumask_t downed_cpus; + +static void enter_uniprocessor(void) +{ + int cpu; + int err; + + get_online_cpus(); + downed_cpus = cpu_online_map; + cpu_clear(first_cpu(cpu_online_map), downed_cpus); + if (num_online_cpus() > 1) + pr_notice(NAME "Disabling non-boot CPUs...\n"); + put_online_cpus(); + + for_each_cpu_mask(cpu, downed_cpus) { + err = cpu_down(cpu); + if (!err) + pr_info(NAME "CPU%d is down.\n", cpu); + else + pr_err(NAME "Error taking CPU%d down: %d\n", cpu, err); + } + if (num_online_cpus() > 1) + pr_warning(NAME "multiple CPUs still online, " + "may miss events.\n"); +} + +static void leave_uniprocessor(void) +{ + int cpu; + int err; + + if (cpus_weight(downed_cpus) == 0) + return; + pr_notice(NAME "Re-enabling CPUs...\n"); + for_each_cpu_mask(cpu, downed_cpus) { + err = cpu_up(cpu); + if (!err) + pr_info(NAME "enabled CPU%d.\n", cpu); + else + pr_err(NAME "cannot re-enable CPU%d: %d\n", cpu, err); + } +} + +#else /* !CONFIG_HOTPLUG_CPU */ +static void enter_uniprocessor(void) +{ + if (num_online_cpus() > 1) + pr_warning(NAME "multiple CPUs are online, may miss events. " + "Suggest booting with maxcpus=1 kernel argument.\n"); +} + +static void leave_uniprocessor(void) +{ +} +#endif + +#if 0 /* XXX: out of order */ +static struct file_operations fops_marker = { + .owner = THIS_MODULE, + .write = write_marker +}; +#endif + +void enable_mmiotrace(void) +{ + mutex_lock(&mmiotrace_mutex); + if (is_enabled()) + goto out; + +#if 0 /* XXX: tracing does not support text entries */ + marker_file = debugfs_create_file("marker", 0660, dir, NULL, + &fops_marker); + if (!marker_file) + pr_err(NAME "marker file creation failed.\n"); +#endif + + if (nommiotrace) + pr_info(NAME "MMIO tracing disabled.\n"); + enter_uniprocessor(); + spin_lock_irq(&trace_lock); + atomic_inc(&mmiotrace_enabled); + spin_unlock_irq(&trace_lock); + pr_info(NAME "enabled.\n"); +out: + mutex_unlock(&mmiotrace_mutex); +} + +void disable_mmiotrace(void) +{ + mutex_lock(&mmiotrace_mutex); + if (!is_enabled()) + goto out; + + spin_lock_irq(&trace_lock); + atomic_dec(&mmiotrace_enabled); + BUG_ON(is_enabled()); + spin_unlock_irq(&trace_lock); + + clear_trace_list(); /* guarantees: no more kmmio callbacks */ + leave_uniprocessor(); + if (marker_file) { + debugfs_remove(marker_file); + marker_file = NULL; + } + + pr_info(NAME "disabled.\n"); +out: + mutex_unlock(&mmiotrace_mutex); +} diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index c5066d519e5d..b432d5781773 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -27,30 +27,17 @@ struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); -bootmem_data_t plat_node_bdata[MAX_NUMNODES]; +static bootmem_data_t plat_node_bdata[MAX_NUMNODES]; struct memnode memnode; -#ifdef CONFIG_SMP -int x86_cpu_to_node_map_init[NR_CPUS] = { - [0 ... NR_CPUS-1] = NUMA_NO_NODE -}; -void *x86_cpu_to_node_map_early_ptr; -EXPORT_SYMBOL(x86_cpu_to_node_map_early_ptr); -#endif -DEFINE_PER_CPU(int, x86_cpu_to_node_map) = NUMA_NO_NODE; -EXPORT_PER_CPU_SYMBOL(x86_cpu_to_node_map); - s16 apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = { [0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE }; -cpumask_t node_to_cpumask_map[MAX_NUMNODES] __read_mostly; -EXPORT_SYMBOL(node_to_cpumask_map); - int numa_off __initdata; -unsigned long __initdata nodemap_addr; -unsigned long __initdata nodemap_size; +static unsigned long __initdata nodemap_addr; +static unsigned long __initdata nodemap_size; /* * Given a shift value, try to populate memnodemap[] @@ -99,7 +86,7 @@ static int __init allocate_cachealigned_memnodemap(void) addr = 0x8000; nodemap_size = round_up(sizeof(s16) * memnodemapsize, L1_CACHE_BYTES); - nodemap_addr = find_e820_area(addr, end_pfn<<PAGE_SHIFT, + nodemap_addr = find_e820_area(addr, max_pfn<<PAGE_SHIFT, nodemap_size, L1_CACHE_BYTES); if (nodemap_addr == -1UL) { printk(KERN_ERR @@ -192,7 +179,7 @@ static void * __init early_node_mem(int nodeid, unsigned long start, void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long end) { - unsigned long start_pfn, end_pfn, bootmap_pages, bootmap_size; + unsigned long start_pfn, last_pfn, bootmap_pages, bootmap_size; unsigned long bootmap_start, nodedata_phys; void *bootmap; const int pgdat_size = round_up(sizeof(pg_data_t), PAGE_SIZE); @@ -204,7 +191,7 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, start, end); start_pfn = start >> PAGE_SHIFT; - end_pfn = end >> PAGE_SHIFT; + last_pfn = end >> PAGE_SHIFT; node_data[nodeid] = early_node_mem(nodeid, start, end, pgdat_size, SMP_CACHE_BYTES); @@ -217,7 +204,7 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t)); NODE_DATA(nodeid)->bdata = &plat_node_bdata[nodeid]; NODE_DATA(nodeid)->node_start_pfn = start_pfn; - NODE_DATA(nodeid)->node_spanned_pages = end_pfn - start_pfn; + NODE_DATA(nodeid)->node_spanned_pages = last_pfn - start_pfn; /* * Find a place for the bootmem map @@ -226,14 +213,14 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, * early_node_mem will get that with find_e820_area instead * of alloc_bootmem, that could clash with reserved range */ - bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn); + bootmap_pages = bootmem_bootmap_pages(last_pfn - start_pfn); nid = phys_to_nid(nodedata_phys); if (nid == nodeid) bootmap_start = round_up(nodedata_phys + pgdat_size, PAGE_SIZE); else bootmap_start = round_up(start, PAGE_SIZE); /* - * SMP_CAHCE_BYTES could be enough, but init_bootmem_node like + * SMP_CACHE_BYTES could be enough, but init_bootmem_node like * to use that to align to PAGE_SIZE */ bootmap = early_node_mem(nodeid, bootmap_start, end, @@ -248,7 +235,7 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, bootmap_size = init_bootmem_node(NODE_DATA(nodeid), bootmap_start >> PAGE_SHIFT, - start_pfn, end_pfn); + start_pfn, last_pfn); printk(KERN_INFO " bootmap [%016lx - %016lx] pages %lx\n", bootmap_start, bootmap_start + bootmap_size - 1, @@ -309,7 +296,7 @@ void __init numa_init_array(void) #ifdef CONFIG_NUMA_EMU /* Numa emulation */ -char *cmdline __initdata; +static char *cmdline __initdata; /* * Setups up nid to range from addr to addr + size. If the end @@ -413,15 +400,15 @@ static int __init split_nodes_by_size(struct bootnode *nodes, u64 *addr, } /* - * Sets up the system RAM area from start_pfn to end_pfn according to the + * Sets up the system RAM area from start_pfn to last_pfn according to the * numa=fake command-line option. */ static struct bootnode nodes[MAX_NUMNODES] __initdata; -static int __init numa_emulation(unsigned long start_pfn, unsigned long end_pfn) +static int __init numa_emulation(unsigned long start_pfn, unsigned long last_pfn) { u64 size, addr = start_pfn << PAGE_SHIFT; - u64 max_addr = end_pfn << PAGE_SHIFT; + u64 max_addr = last_pfn << PAGE_SHIFT; int num_nodes = 0, num = 0, coeff_flag, coeff = -1, i; memset(&nodes, 0, sizeof(nodes)); @@ -527,7 +514,7 @@ out: } #endif /* CONFIG_NUMA_EMU */ -void __init numa_initmem_init(unsigned long start_pfn, unsigned long end_pfn) +void __init initmem_init(unsigned long start_pfn, unsigned long last_pfn) { int i; @@ -535,7 +522,7 @@ void __init numa_initmem_init(unsigned long start_pfn, unsigned long end_pfn) nodes_clear(node_online_map); #ifdef CONFIG_NUMA_EMU - if (cmdline && !numa_emulation(start_pfn, end_pfn)) + if (cmdline && !numa_emulation(start_pfn, last_pfn)) return; nodes_clear(node_possible_map); nodes_clear(node_online_map); @@ -543,7 +530,7 @@ void __init numa_initmem_init(unsigned long start_pfn, unsigned long end_pfn) #ifdef CONFIG_ACPI_NUMA if (!numa_off && !acpi_scan_nodes(start_pfn << PAGE_SHIFT, - end_pfn << PAGE_SHIFT)) + last_pfn << PAGE_SHIFT)) return; nodes_clear(node_possible_map); nodes_clear(node_online_map); @@ -551,7 +538,7 @@ void __init numa_initmem_init(unsigned long start_pfn, unsigned long end_pfn) #ifdef CONFIG_K8_NUMA if (!numa_off && !k8_scan_nodes(start_pfn<<PAGE_SHIFT, - end_pfn<<PAGE_SHIFT)) + last_pfn<<PAGE_SHIFT)) return; nodes_clear(node_possible_map); nodes_clear(node_online_map); @@ -561,7 +548,7 @@ void __init numa_initmem_init(unsigned long start_pfn, unsigned long end_pfn) printk(KERN_INFO "Faking a node at %016lx-%016lx\n", start_pfn << PAGE_SHIFT, - end_pfn << PAGE_SHIFT); + last_pfn << PAGE_SHIFT); /* setup dummy node covering all memory */ memnode_shift = 63; memnodemap = memnode.embedded_map; @@ -570,29 +557,8 @@ void __init numa_initmem_init(unsigned long start_pfn, unsigned long end_pfn) node_set(0, node_possible_map); for (i = 0; i < NR_CPUS; i++) numa_set_node(i, 0); - /* cpumask_of_cpu() may not be available during early startup */ - memset(&node_to_cpumask_map[0], 0, sizeof(node_to_cpumask_map[0])); - cpu_set(0, node_to_cpumask_map[0]); - e820_register_active_regions(0, start_pfn, end_pfn); - setup_node_bootmem(0, start_pfn << PAGE_SHIFT, end_pfn << PAGE_SHIFT); -} - -__cpuinit void numa_add_cpu(int cpu) -{ - set_bit(cpu, - (unsigned long *)&node_to_cpumask_map[early_cpu_to_node(cpu)]); -} - -void __cpuinit numa_set_node(int cpu, int node) -{ - int *cpu_to_node_map = x86_cpu_to_node_map_early_ptr; - - if(cpu_to_node_map) - cpu_to_node_map[cpu] = node; - else if(per_cpu_offset(cpu)) - per_cpu(x86_cpu_to_node_map, cpu) = node; - else - Dprintk(KERN_INFO "Setting node for non-present cpu %d\n", cpu); + e820_register_active_regions(0, start_pfn, last_pfn); + setup_node_bootmem(0, start_pfn << PAGE_SHIFT, last_pfn << PAGE_SHIFT); } unsigned long __init numa_free_all_bootmem(void) @@ -613,7 +579,7 @@ void __init paging_init(void) memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN; max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN; - max_zone_pfns[ZONE_NORMAL] = end_pfn; + max_zone_pfns[ZONE_NORMAL] = max_pfn; sparse_memory_present_with_active_regions(MAX_NUMNODES); sparse_init(); @@ -641,6 +607,7 @@ static __init int numa_setup(char *opt) } early_param("numa", numa_setup); +#ifdef CONFIG_NUMA /* * Setup early cpu_to_node. * @@ -652,14 +619,19 @@ early_param("numa", numa_setup); * is already initialized in a round robin manner at numa_init_array, * prior to this call, and this initialization is good enough * for the fake NUMA cases. + * + * Called before the per_cpu areas are setup. */ void __init init_cpu_to_node(void) { - int i; + int cpu; + u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid); - for (i = 0; i < NR_CPUS; i++) { + BUG_ON(cpu_to_apicid == NULL); + + for_each_possible_cpu(cpu) { int node; - u16 apicid = x86_cpu_to_apicid_init[i]; + u16 apicid = cpu_to_apicid[cpu]; if (apicid == BAD_APICID) continue; @@ -668,8 +640,9 @@ void __init init_cpu_to_node(void) continue; if (!node_online(node)) continue; - numa_set_node(i, node); + numa_set_node(cpu, node); } } +#endif diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c index 75f1b109aae8..0dcd42eb94e6 100644 --- a/arch/x86/mm/pageattr-test.c +++ b/arch/x86/mm/pageattr-test.c @@ -1,8 +1,8 @@ /* * self test for change_page_attr. * - * Clears the global bit on random pages in the direct mapping, then reverts - * and compares page tables forwards and afterwards. + * Clears the a test pte bit on random pages in the direct mapping, + * then reverts and compares page tables forwards and afterwards. */ #include <linux/bootmem.h> #include <linux/kthread.h> @@ -32,6 +32,13 @@ enum { GPS = (1<<30) }; +#define PAGE_TESTBIT __pgprot(_PAGE_UNUSED1) + +static int pte_testbit(pte_t pte) +{ + return pte_flags(pte) & _PAGE_UNUSED1; +} + struct split_state { long lpg, gpg, spg, exec; long min_exec, max_exec; @@ -165,15 +172,14 @@ static int pageattr_test(void) continue; } - err = change_page_attr_clear(addr[i], len[i], - __pgprot(_PAGE_GLOBAL)); + err = change_page_attr_set(addr[i], len[i], PAGE_TESTBIT); if (err < 0) { printk(KERN_ERR "CPA %d failed %d\n", i, err); failed++; } pte = lookup_address(addr[i], &level); - if (!pte || pte_global(*pte) || pte_huge(*pte)) { + if (!pte || !pte_testbit(*pte) || pte_huge(*pte)) { printk(KERN_ERR "CPA %lx: bad pte %Lx\n", addr[i], pte ? (u64)pte_val(*pte) : 0ULL); failed++; @@ -198,14 +204,13 @@ static int pageattr_test(void) failed++; continue; } - err = change_page_attr_set(addr[i], len[i], - __pgprot(_PAGE_GLOBAL)); + err = change_page_attr_clear(addr[i], len[i], PAGE_TESTBIT); if (err < 0) { printk(KERN_ERR "CPA reverting failed: %d\n", err); failed++; } pte = lookup_address(addr[i], &level); - if (!pte || !pte_global(*pte)) { + if (!pte || pte_testbit(*pte)) { printk(KERN_ERR "CPA %lx: bad pte after revert %Lx\n", addr[i], pte ? (u64)pte_val(*pte) : 0ULL); failed++; diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 60bcb5b6a37e..65c6e46bf059 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -34,6 +34,41 @@ struct cpa_data { unsigned force_split : 1; }; +#ifdef CONFIG_PROC_FS +static unsigned long direct_pages_count[PG_LEVEL_NUM]; + +void update_page_count(int level, unsigned long pages) +{ + unsigned long flags; + + /* Protect against CPA */ + spin_lock_irqsave(&pgd_lock, flags); + direct_pages_count[level] += pages; + spin_unlock_irqrestore(&pgd_lock, flags); +} + +static void split_page_count(int level) +{ + direct_pages_count[level]--; + direct_pages_count[level - 1] += PTRS_PER_PTE; +} + +int arch_report_meminfo(char *page) +{ + int n = sprintf(page, "DirectMap4k: %8lu\n" + "DirectMap2M: %8lu\n", + direct_pages_count[PG_LEVEL_4K], + direct_pages_count[PG_LEVEL_2M]); +#ifdef CONFIG_X86_64 + n += sprintf(page + n, "DirectMap1G: %8lu\n", + direct_pages_count[PG_LEVEL_1G]); +#endif + return n; +} +#else +static inline void split_page_count(int level) { } +#endif + #ifdef CONFIG_X86_64 static inline unsigned long highmap_start_pfn(void) @@ -106,7 +141,7 @@ static void cpa_flush_all(unsigned long cache) { BUG_ON(irqs_disabled()); - on_each_cpu(__cpa_flush_all, (void *) cache, 1, 1); + on_each_cpu(__cpa_flush_all, (void *) cache, 1); } static void __cpa_flush_range(void *arg) @@ -127,7 +162,7 @@ static void cpa_flush_range(unsigned long start, int numpages, int cache) BUG_ON(irqs_disabled()); WARN_ON(PAGE_ALIGN(start) != start); - on_each_cpu(__cpa_flush_range, NULL, 1, 1); + on_each_cpu(__cpa_flush_range, NULL, 1); if (!cache) return; @@ -227,6 +262,7 @@ pte_t *lookup_address(unsigned long address, unsigned int *level) return pte_offset_kernel(pmd, address); } +EXPORT_SYMBOL_GPL(lookup_address); /* * Set the new pmd in all the pgds we know about: @@ -500,6 +536,16 @@ static int split_large_page(pte_t *kpte, unsigned long address) for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc) set_pte(&pbase[i], pfn_pte(pfn, ref_prot)); + if (address >= (unsigned long)__va(0) && + address < (unsigned long)__va(max_low_pfn_mapped << PAGE_SHIFT)) + split_page_count(level); + +#ifdef CONFIG_X86_64 + if (address >= (unsigned long)__va(1UL<<32) && + address < (unsigned long)__va(max_pfn_mapped << PAGE_SHIFT)) + split_page_count(level); +#endif + /* * Install the new, split up pagetable. Important details here: * @@ -613,15 +659,24 @@ static int cpa_process_alias(struct cpa_data *cpa) struct cpa_data alias_cpa; int ret = 0; - if (cpa->pfn > max_pfn_mapped) + if (cpa->pfn >= max_pfn_mapped) return 0; +#ifdef CONFIG_X86_64 + if (cpa->pfn >= max_low_pfn_mapped && cpa->pfn < (1UL<<(32-PAGE_SHIFT))) + return 0; +#endif /* * No need to redo, when the primary call touched the direct * mapping already: */ - if (!within(cpa->vaddr, PAGE_OFFSET, - PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT))) { + if (!(within(cpa->vaddr, PAGE_OFFSET, + PAGE_OFFSET + (max_low_pfn_mapped << PAGE_SHIFT)) +#ifdef CONFIG_X86_64 + || within(cpa->vaddr, PAGE_OFFSET + (1UL<<32), + PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT)) +#endif + )) { alias_cpa = *cpa; alias_cpa.vaddr = (unsigned long) __va(cpa->pfn << PAGE_SHIFT); @@ -805,7 +860,7 @@ int _set_memory_wc(unsigned long addr, int numpages) int set_memory_wc(unsigned long addr, int numpages) { - if (!pat_wc_enabled) + if (!pat_enabled) return set_memory_uc(addr, numpages); if (reserve_memtype(addr, addr + numpages * PAGE_SIZE, diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index de3a99812450..d4585077977a 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -26,15 +26,15 @@ #include <asm/io.h> #ifdef CONFIG_X86_PAT -int __read_mostly pat_wc_enabled = 1; +int __read_mostly pat_enabled = 1; void __cpuinit pat_disable(char *reason) { - pat_wc_enabled = 0; + pat_enabled = 0; printk(KERN_INFO "%s\n", reason); } -static int nopat(char *str) +static int __init nopat(char *str) { pat_disable("PAT support disabled."); return 0; @@ -42,6 +42,19 @@ static int nopat(char *str) early_param("nopat", nopat); #endif + +static int debug_enable; +static int __init pat_debug_setup(char *str) +{ + debug_enable = 1; + return 0; +} +__setup("debugpat", pat_debug_setup); + +#define dprintk(fmt, arg...) \ + do { if (debug_enable) printk(KERN_INFO fmt, ##arg); } while (0) + + static u64 __read_mostly boot_pat_state; enum { @@ -53,24 +66,25 @@ enum { PAT_UC_MINUS = 7, /* UC, but can be overriden by MTRR */ }; -#define PAT(x,y) ((u64)PAT_ ## y << ((x)*8)) +#define PAT(x, y) ((u64)PAT_ ## y << ((x)*8)) void pat_init(void) { u64 pat; - if (!pat_wc_enabled) + if (!pat_enabled) return; /* Paranoia check. */ - if (!cpu_has_pat) { - printk(KERN_ERR "PAT enabled, but CPU feature cleared\n"); + if (!cpu_has_pat && boot_pat_state) { /* - * Panic if this happens on the secondary CPU, and we + * If this happens we are on a secondary CPU, but * switched to PAT on the boot CPU. We have no way to * undo PAT. - */ - BUG_ON(boot_pat_state); + */ + printk(KERN_ERR "PAT enabled, " + "but not supported by secondary CPU\n"); + BUG(); } /* Set PWT to Write-Combining. All other bits stay the same */ @@ -86,8 +100,8 @@ void pat_init(void) * 011 UC _PAGE_CACHE_UC * PAT bit unused */ - pat = PAT(0,WB) | PAT(1,WC) | PAT(2,UC_MINUS) | PAT(3,UC) | - PAT(4,WB) | PAT(5,WC) | PAT(6,UC_MINUS) | PAT(7,UC); + pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) | + PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC); /* Boot CPU check */ if (!boot_pat_state) @@ -103,11 +117,11 @@ void pat_init(void) static char *cattr_name(unsigned long flags) { switch (flags & _PAGE_CACHE_MASK) { - case _PAGE_CACHE_UC: return "uncached"; - case _PAGE_CACHE_UC_MINUS: return "uncached-minus"; - case _PAGE_CACHE_WB: return "write-back"; - case _PAGE_CACHE_WC: return "write-combining"; - default: return "broken"; + case _PAGE_CACHE_UC: return "uncached"; + case _PAGE_CACHE_UC_MINUS: return "uncached-minus"; + case _PAGE_CACHE_WB: return "write-back"; + case _PAGE_CACHE_WC: return "write-combining"; + default: return "broken"; } } @@ -145,46 +159,50 @@ static DEFINE_SPINLOCK(memtype_lock); /* protects memtype list */ * The intersection is based on "Effective Memory Type" tables in IA-32 * SDM vol 3a */ -static int pat_x_mtrr_type(u64 start, u64 end, unsigned long prot, - unsigned long *ret_prot) +static unsigned long pat_x_mtrr_type(u64 start, u64 end, unsigned long req_type) { - unsigned long pat_type; - u8 mtrr_type; - - mtrr_type = mtrr_type_lookup(start, end); - if (mtrr_type == 0xFF) { /* MTRR not enabled */ - *ret_prot = prot; - return 0; - } - if (mtrr_type == 0xFE) { /* MTRR match error */ - *ret_prot = _PAGE_CACHE_UC; - return -1; - } - if (mtrr_type != MTRR_TYPE_UNCACHABLE && - mtrr_type != MTRR_TYPE_WRBACK && - mtrr_type != MTRR_TYPE_WRCOMB) { /* MTRR type unhandled */ - *ret_prot = _PAGE_CACHE_UC; - return -1; + /* + * Look for MTRR hint to get the effective type in case where PAT + * request is for WB. + */ + if (req_type == _PAGE_CACHE_WB) { + u8 mtrr_type; + + mtrr_type = mtrr_type_lookup(start, end); + if (mtrr_type == MTRR_TYPE_UNCACHABLE) + return _PAGE_CACHE_UC; + if (mtrr_type == MTRR_TYPE_WRCOMB) + return _PAGE_CACHE_WC; } - pat_type = prot & _PAGE_CACHE_MASK; - prot &= (~_PAGE_CACHE_MASK); - - /* Currently doing intersection by hand. Optimize it later. */ - if (pat_type == _PAGE_CACHE_WC) { - *ret_prot = prot | _PAGE_CACHE_WC; - } else if (pat_type == _PAGE_CACHE_UC_MINUS) { - *ret_prot = prot | _PAGE_CACHE_UC_MINUS; - } else if (pat_type == _PAGE_CACHE_UC || - mtrr_type == MTRR_TYPE_UNCACHABLE) { - *ret_prot = prot | _PAGE_CACHE_UC; - } else if (mtrr_type == MTRR_TYPE_WRCOMB) { - *ret_prot = prot | _PAGE_CACHE_WC; - } else { - *ret_prot = prot | _PAGE_CACHE_WB; + return req_type; +} + +static int chk_conflict(struct memtype *new, struct memtype *entry, + unsigned long *type) +{ + if (new->type != entry->type) { + if (type) { + new->type = entry->type; + *type = entry->type; + } else + goto conflict; } + /* check overlaps with more than one entry in the list */ + list_for_each_entry_continue(entry, &memtype_list, nd) { + if (new->end <= entry->start) + break; + else if (new->type != entry->type) + goto conflict; + } return 0; + + conflict: + printk(KERN_INFO "%s:%d conflicting memory types " + "%Lx-%Lx %s<->%s\n", current->comm, current->pid, new->start, + new->end, cattr_name(new->type), cattr_name(entry->type)); + return -EBUSY; } /* @@ -197,251 +215,134 @@ static int pat_x_mtrr_type(u64 start, u64 end, unsigned long prot, * req_type will have a special case value '-1', when requester want to inherit * the memory type from mtrr (if WB), existing PAT, defaulting to UC_MINUS. * - * If ret_type is NULL, function will return an error if it cannot reserve the - * region with req_type. If ret_type is non-null, function will return - * available type in ret_type in case of no error. In case of any error + * If new_type is NULL, function will return an error if it cannot reserve the + * region with req_type. If new_type is non-NULL, function will return + * available type in new_type in case of no error. In case of any error * it will return a negative return value. */ int reserve_memtype(u64 start, u64 end, unsigned long req_type, - unsigned long *ret_type) + unsigned long *new_type) { - struct memtype *new_entry = NULL; - struct memtype *parse; + struct memtype *new, *entry; unsigned long actual_type; + struct list_head *where; int err = 0; - /* Only track when pat_wc_enabled */ - if (!pat_wc_enabled) { + BUG_ON(start >= end); /* end is exclusive */ + + if (!pat_enabled) { /* This is identical to page table setting without PAT */ - if (ret_type) { - if (req_type == -1) { - *ret_type = _PAGE_CACHE_WB; - } else { - *ret_type = req_type; - } + if (new_type) { + if (req_type == -1) + *new_type = _PAGE_CACHE_WB; + else + *new_type = req_type & _PAGE_CACHE_MASK; } return 0; } /* Low ISA region is always mapped WB in page table. No need to track */ - if (start >= ISA_START_ADDRESS && (end - 1) <= ISA_END_ADDRESS) { - if (ret_type) - *ret_type = _PAGE_CACHE_WB; - + if (is_ISA_range(start, end - 1)) { + if (new_type) + *new_type = _PAGE_CACHE_WB; return 0; } if (req_type == -1) { /* - * Special case where caller wants to inherit from mtrr or - * existing pat mapping, defaulting to UC_MINUS in case of - * no match. + * Call mtrr_lookup to get the type hint. This is an + * optimization for /dev/mem mmap'ers into WB memory (BIOS + * tools and ACPI tools). Use WB request for WB memory and use + * UC_MINUS otherwise. */ u8 mtrr_type = mtrr_type_lookup(start, end); - if (mtrr_type == 0xFE) { /* MTRR match error */ - err = -1; - } - if (mtrr_type == MTRR_TYPE_WRBACK) { - req_type = _PAGE_CACHE_WB; + if (mtrr_type == MTRR_TYPE_WRBACK) actual_type = _PAGE_CACHE_WB; - } else { - req_type = _PAGE_CACHE_UC_MINUS; + else actual_type = _PAGE_CACHE_UC_MINUS; - } - } else { - req_type &= _PAGE_CACHE_MASK; - err = pat_x_mtrr_type(start, end, req_type, &actual_type); - } + } else + actual_type = pat_x_mtrr_type(start, end, + req_type & _PAGE_CACHE_MASK); - if (err) { - if (ret_type) - *ret_type = actual_type; - - return -EINVAL; - } - - new_entry = kmalloc(sizeof(struct memtype), GFP_KERNEL); - if (!new_entry) + new = kmalloc(sizeof(struct memtype), GFP_KERNEL); + if (!new) return -ENOMEM; - new_entry->start = start; - new_entry->end = end; - new_entry->type = actual_type; + new->start = start; + new->end = end; + new->type = actual_type; - if (ret_type) - *ret_type = actual_type; + if (new_type) + *new_type = actual_type; spin_lock(&memtype_lock); /* Search for existing mapping that overlaps the current range */ - list_for_each_entry(parse, &memtype_list, nd) { - struct memtype *saved_ptr; - - if (parse->start >= end) { - pr_debug("New Entry\n"); - list_add(&new_entry->nd, parse->nd.prev); - new_entry = NULL; + where = NULL; + list_for_each_entry(entry, &memtype_list, nd) { + if (end <= entry->start) { + where = entry->nd.prev; break; - } - - if (start <= parse->start && end >= parse->start) { - if (actual_type != parse->type && ret_type) { - actual_type = parse->type; - *ret_type = actual_type; - new_entry->type = actual_type; - } - - if (actual_type != parse->type) { - printk( - KERN_INFO "%s:%d conflicting memory types %Lx-%Lx %s<->%s\n", - current->comm, current->pid, - start, end, - cattr_name(actual_type), - cattr_name(parse->type)); - err = -EBUSY; - break; - } - - saved_ptr = parse; - /* - * Check to see whether the request overlaps more - * than one entry in the list - */ - list_for_each_entry_continue(parse, &memtype_list, nd) { - if (end <= parse->start) { - break; - } - - if (actual_type != parse->type) { - printk( - KERN_INFO "%s:%d conflicting memory types %Lx-%Lx %s<->%s\n", - current->comm, current->pid, - start, end, - cattr_name(actual_type), - cattr_name(parse->type)); - err = -EBUSY; - break; - } + } else if (start <= entry->start) { /* end > entry->start */ + err = chk_conflict(new, entry, new_type); + if (!err) { + dprintk("Overlap at 0x%Lx-0x%Lx\n", + entry->start, entry->end); + where = entry->nd.prev; } - - if (err) { - break; - } - - pr_debug("Overlap at 0x%Lx-0x%Lx\n", - saved_ptr->start, saved_ptr->end); - /* No conflict. Go ahead and add this new entry */ - list_add(&new_entry->nd, saved_ptr->nd.prev); - new_entry = NULL; break; - } - - if (start < parse->end) { - if (actual_type != parse->type && ret_type) { - actual_type = parse->type; - *ret_type = actual_type; - new_entry->type = actual_type; - } - - if (actual_type != parse->type) { - printk( - KERN_INFO "%s:%d conflicting memory types %Lx-%Lx %s<->%s\n", - current->comm, current->pid, - start, end, - cattr_name(actual_type), - cattr_name(parse->type)); - err = -EBUSY; - break; + } else if (start < entry->end) { /* start > entry->start */ + err = chk_conflict(new, entry, new_type); + if (!err) { + dprintk("Overlap at 0x%Lx-0x%Lx\n", + entry->start, entry->end); + where = &entry->nd; } - - saved_ptr = parse; - /* - * Check to see whether the request overlaps more - * than one entry in the list - */ - list_for_each_entry_continue(parse, &memtype_list, nd) { - if (end <= parse->start) { - break; - } - - if (actual_type != parse->type) { - printk( - KERN_INFO "%s:%d conflicting memory types %Lx-%Lx %s<->%s\n", - current->comm, current->pid, - start, end, - cattr_name(actual_type), - cattr_name(parse->type)); - err = -EBUSY; - break; - } - } - - if (err) { - break; - } - - pr_debug(KERN_INFO "Overlap at 0x%Lx-0x%Lx\n", - saved_ptr->start, saved_ptr->end); - /* No conflict. Go ahead and add this new entry */ - list_add(&new_entry->nd, &saved_ptr->nd); - new_entry = NULL; break; } } if (err) { - printk(KERN_INFO - "reserve_memtype failed 0x%Lx-0x%Lx, track %s, req %s\n", - start, end, cattr_name(new_entry->type), - cattr_name(req_type)); - kfree(new_entry); + printk(KERN_INFO "reserve_memtype failed 0x%Lx-0x%Lx, " + "track %s, req %s\n", + start, end, cattr_name(new->type), cattr_name(req_type)); + kfree(new); spin_unlock(&memtype_lock); return err; } - if (new_entry) { - /* No conflict. Not yet added to the list. Add to the tail */ - list_add_tail(&new_entry->nd, &memtype_list); - pr_debug("New Entry\n"); - } - - if (ret_type) { - pr_debug( - "reserve_memtype added 0x%Lx-0x%Lx, track %s, req %s, ret %s\n", - start, end, cattr_name(actual_type), - cattr_name(req_type), cattr_name(*ret_type)); - } else { - pr_debug( - "reserve_memtype added 0x%Lx-0x%Lx, track %s, req %s\n", - start, end, cattr_name(actual_type), - cattr_name(req_type)); - } + if (where) + list_add(&new->nd, where); + else + list_add_tail(&new->nd, &memtype_list); spin_unlock(&memtype_lock); + + dprintk("reserve_memtype added 0x%Lx-0x%Lx, track %s, req %s, ret %s\n", + start, end, cattr_name(new->type), cattr_name(req_type), + new_type ? cattr_name(*new_type) : "-"); + return err; } int free_memtype(u64 start, u64 end) { - struct memtype *ml; + struct memtype *entry; int err = -EINVAL; - /* Only track when pat_wc_enabled */ - if (!pat_wc_enabled) { + if (!pat_enabled) return 0; - } /* Low ISA region is always mapped WB. No need to track */ - if (start >= ISA_START_ADDRESS && end <= ISA_END_ADDRESS) { + if (is_ISA_range(start, end - 1)) return 0; - } spin_lock(&memtype_lock); - list_for_each_entry(ml, &memtype_list, nd) { - if (ml->start == start && ml->end == end) { - list_del(&ml->nd); - kfree(ml); + list_for_each_entry(entry, &memtype_list, nd) { + if (entry->start == start && entry->end == end) { + list_del(&entry->nd); + kfree(entry); err = 0; break; } @@ -453,7 +354,7 @@ int free_memtype(u64 start, u64 end) current->comm, current->pid, start, end); } - pr_debug("free_memtype request 0x%Lx-0x%Lx\n", start, end); + dprintk("free_memtype request 0x%Lx-0x%Lx\n", start, end); return err; } @@ -522,12 +423,12 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, * caching for the high addresses through the KEN pin, but * we maintain the tradition of paranoia in this code. */ - if (!pat_wc_enabled && - ! ( test_bit(X86_FEATURE_MTRR, boot_cpu_data.x86_capability) || - test_bit(X86_FEATURE_K6_MTRR, boot_cpu_data.x86_capability) || - test_bit(X86_FEATURE_CYRIX_ARR, boot_cpu_data.x86_capability) || - test_bit(X86_FEATURE_CENTAUR_MCR, boot_cpu_data.x86_capability)) && - (pfn << PAGE_SHIFT) >= __pa(high_memory)) { + if (!pat_enabled && + !(boot_cpu_has(X86_FEATURE_MTRR) || + boot_cpu_has(X86_FEATURE_K6_MTRR) || + boot_cpu_has(X86_FEATURE_CYRIX_ARR) || + boot_cpu_has(X86_FEATURE_CENTAUR_MCR)) && + (pfn << PAGE_SHIFT) >= __pa(high_memory)) { flags = _PAGE_CACHE_UC; } #endif @@ -548,8 +449,9 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, if (retval < 0) return 0; - if (pfn <= max_pfn_mapped && - ioremap_change_attr((unsigned long)__va(offset), size, flags) < 0) { + if (((pfn < max_low_pfn_mapped) || + (pfn >= (1UL<<(32 - PAGE_SHIFT)) && pfn < max_pfn_mapped)) && + ioremap_change_attr((unsigned long)__va(offset), size, flags) < 0) { free_memtype(offset, offset + size); printk(KERN_INFO "%s:%d /dev/mem ioremap_change_attr failed %s for %Lx-%Lx\n", @@ -587,4 +489,3 @@ void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot) free_memtype(addr, addr + size); } - diff --git a/arch/x86/mm/pf_in.c b/arch/x86/mm/pf_in.c new file mode 100644 index 000000000000..efa1911e20ca --- /dev/null +++ b/arch/x86/mm/pf_in.c @@ -0,0 +1,489 @@ +/* + * Fault Injection Test harness (FI) + * Copyright (C) Intel Crop. + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, + * USA. + * + */ + +/* Id: pf_in.c,v 1.1.1.1 2002/11/12 05:56:32 brlock Exp + * Copyright by Intel Crop., 2002 + * Louis Zhuang (louis.zhuang@intel.com) + * + * Bjorn Steinbrink (B.Steinbrink@gmx.de), 2007 + */ + +#include <linux/module.h> +#include <linux/ptrace.h> /* struct pt_regs */ +#include "pf_in.h" + +#ifdef __i386__ +/* IA32 Manual 3, 2-1 */ +static unsigned char prefix_codes[] = { + 0xF0, 0xF2, 0xF3, 0x2E, 0x36, 0x3E, 0x26, 0x64, + 0x65, 0x2E, 0x3E, 0x66, 0x67 +}; +/* IA32 Manual 3, 3-432*/ +static unsigned int reg_rop[] = { + 0x8A, 0x8B, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F +}; +static unsigned int reg_wop[] = { 0x88, 0x89 }; +static unsigned int imm_wop[] = { 0xC6, 0xC7 }; +/* IA32 Manual 3, 3-432*/ +static unsigned int rw8[] = { 0x88, 0x8A, 0xC6 }; +static unsigned int rw32[] = { + 0x89, 0x8B, 0xC7, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F +}; +static unsigned int mw8[] = { 0x88, 0x8A, 0xC6, 0xB60F, 0xBE0F }; +static unsigned int mw16[] = { 0xB70F, 0xBF0F }; +static unsigned int mw32[] = { 0x89, 0x8B, 0xC7 }; +static unsigned int mw64[] = {}; +#else /* not __i386__ */ +static unsigned char prefix_codes[] = { + 0x66, 0x67, 0x2E, 0x3E, 0x26, 0x64, 0x65, 0x36, + 0xF0, 0xF3, 0xF2, + /* REX Prefixes */ + 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, + 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f +}; +/* AMD64 Manual 3, Appendix A*/ +static unsigned int reg_rop[] = { + 0x8A, 0x8B, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F +}; +static unsigned int reg_wop[] = { 0x88, 0x89 }; +static unsigned int imm_wop[] = { 0xC6, 0xC7 }; +static unsigned int rw8[] = { 0xC6, 0x88, 0x8A }; +static unsigned int rw32[] = { + 0xC7, 0x89, 0x8B, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F +}; +/* 8 bit only */ +static unsigned int mw8[] = { 0xC6, 0x88, 0x8A, 0xB60F, 0xBE0F }; +/* 16 bit only */ +static unsigned int mw16[] = { 0xB70F, 0xBF0F }; +/* 16 or 32 bit */ +static unsigned int mw32[] = { 0xC7 }; +/* 16, 32 or 64 bit */ +static unsigned int mw64[] = { 0x89, 0x8B }; +#endif /* not __i386__ */ + +static int skip_prefix(unsigned char *addr, int *shorted, int *enlarged, + int *rexr) +{ + int i; + unsigned char *p = addr; + *shorted = 0; + *enlarged = 0; + *rexr = 0; + +restart: + for (i = 0; i < ARRAY_SIZE(prefix_codes); i++) { + if (*p == prefix_codes[i]) { + if (*p == 0x66) + *shorted = 1; +#ifdef __amd64__ + if ((*p & 0xf8) == 0x48) + *enlarged = 1; + if ((*p & 0xf4) == 0x44) + *rexr = 1; +#endif + p++; + goto restart; + } + } + + return (p - addr); +} + +static int get_opcode(unsigned char *addr, unsigned int *opcode) +{ + int len; + + if (*addr == 0x0F) { + /* 0x0F is extension instruction */ + *opcode = *(unsigned short *)addr; + len = 2; + } else { + *opcode = *addr; + len = 1; + } + + return len; +} + +#define CHECK_OP_TYPE(opcode, array, type) \ + for (i = 0; i < ARRAY_SIZE(array); i++) { \ + if (array[i] == opcode) { \ + rv = type; \ + goto exit; \ + } \ + } + +enum reason_type get_ins_type(unsigned long ins_addr) +{ + unsigned int opcode; + unsigned char *p; + int shorted, enlarged, rexr; + int i; + enum reason_type rv = OTHERS; + + p = (unsigned char *)ins_addr; + p += skip_prefix(p, &shorted, &enlarged, &rexr); + p += get_opcode(p, &opcode); + + CHECK_OP_TYPE(opcode, reg_rop, REG_READ); + CHECK_OP_TYPE(opcode, reg_wop, REG_WRITE); + CHECK_OP_TYPE(opcode, imm_wop, IMM_WRITE); + +exit: + return rv; +} +#undef CHECK_OP_TYPE + +static unsigned int get_ins_reg_width(unsigned long ins_addr) +{ + unsigned int opcode; + unsigned char *p; + int i, shorted, enlarged, rexr; + + p = (unsigned char *)ins_addr; + p += skip_prefix(p, &shorted, &enlarged, &rexr); + p += get_opcode(p, &opcode); + + for (i = 0; i < ARRAY_SIZE(rw8); i++) + if (rw8[i] == opcode) + return 1; + + for (i = 0; i < ARRAY_SIZE(rw32); i++) + if (rw32[i] == opcode) + return (shorted ? 2 : (enlarged ? 8 : 4)); + + printk(KERN_ERR "mmiotrace: Unknown opcode 0x%02x\n", opcode); + return 0; +} + +unsigned int get_ins_mem_width(unsigned long ins_addr) +{ + unsigned int opcode; + unsigned char *p; + int i, shorted, enlarged, rexr; + + p = (unsigned char *)ins_addr; + p += skip_prefix(p, &shorted, &enlarged, &rexr); + p += get_opcode(p, &opcode); + + for (i = 0; i < ARRAY_SIZE(mw8); i++) + if (mw8[i] == opcode) + return 1; + + for (i = 0; i < ARRAY_SIZE(mw16); i++) + if (mw16[i] == opcode) + return 2; + + for (i = 0; i < ARRAY_SIZE(mw32); i++) + if (mw32[i] == opcode) + return shorted ? 2 : 4; + + for (i = 0; i < ARRAY_SIZE(mw64); i++) + if (mw64[i] == opcode) + return shorted ? 2 : (enlarged ? 8 : 4); + + printk(KERN_ERR "mmiotrace: Unknown opcode 0x%02x\n", opcode); + return 0; +} + +/* + * Define register ident in mod/rm byte. + * Note: these are NOT the same as in ptrace-abi.h. + */ +enum { + arg_AL = 0, + arg_CL = 1, + arg_DL = 2, + arg_BL = 3, + arg_AH = 4, + arg_CH = 5, + arg_DH = 6, + arg_BH = 7, + + arg_AX = 0, + arg_CX = 1, + arg_DX = 2, + arg_BX = 3, + arg_SP = 4, + arg_BP = 5, + arg_SI = 6, + arg_DI = 7, +#ifdef __amd64__ + arg_R8 = 8, + arg_R9 = 9, + arg_R10 = 10, + arg_R11 = 11, + arg_R12 = 12, + arg_R13 = 13, + arg_R14 = 14, + arg_R15 = 15 +#endif +}; + +static unsigned char *get_reg_w8(int no, struct pt_regs *regs) +{ + unsigned char *rv = NULL; + + switch (no) { + case arg_AL: + rv = (unsigned char *)®s->ax; + break; + case arg_BL: + rv = (unsigned char *)®s->bx; + break; + case arg_CL: + rv = (unsigned char *)®s->cx; + break; + case arg_DL: + rv = (unsigned char *)®s->dx; + break; + case arg_AH: + rv = 1 + (unsigned char *)®s->ax; + break; + case arg_BH: + rv = 1 + (unsigned char *)®s->bx; + break; + case arg_CH: + rv = 1 + (unsigned char *)®s->cx; + break; + case arg_DH: + rv = 1 + (unsigned char *)®s->dx; + break; +#ifdef __amd64__ + case arg_R8: + rv = (unsigned char *)®s->r8; + break; + case arg_R9: + rv = (unsigned char *)®s->r9; + break; + case arg_R10: + rv = (unsigned char *)®s->r10; + break; + case arg_R11: + rv = (unsigned char *)®s->r11; + break; + case arg_R12: + rv = (unsigned char *)®s->r12; + break; + case arg_R13: + rv = (unsigned char *)®s->r13; + break; + case arg_R14: + rv = (unsigned char *)®s->r14; + break; + case arg_R15: + rv = (unsigned char *)®s->r15; + break; +#endif + default: + printk(KERN_ERR "mmiotrace: Error reg no# %d\n", no); + break; + } + return rv; +} + +static unsigned long *get_reg_w32(int no, struct pt_regs *regs) +{ + unsigned long *rv = NULL; + + switch (no) { + case arg_AX: + rv = ®s->ax; + break; + case arg_BX: + rv = ®s->bx; + break; + case arg_CX: + rv = ®s->cx; + break; + case arg_DX: + rv = ®s->dx; + break; + case arg_SP: + rv = ®s->sp; + break; + case arg_BP: + rv = ®s->bp; + break; + case arg_SI: + rv = ®s->si; + break; + case arg_DI: + rv = ®s->di; + break; +#ifdef __amd64__ + case arg_R8: + rv = ®s->r8; + break; + case arg_R9: + rv = ®s->r9; + break; + case arg_R10: + rv = ®s->r10; + break; + case arg_R11: + rv = ®s->r11; + break; + case arg_R12: + rv = ®s->r12; + break; + case arg_R13: + rv = ®s->r13; + break; + case arg_R14: + rv = ®s->r14; + break; + case arg_R15: + rv = ®s->r15; + break; +#endif + default: + printk(KERN_ERR "mmiotrace: Error reg no# %d\n", no); + } + + return rv; +} + +unsigned long get_ins_reg_val(unsigned long ins_addr, struct pt_regs *regs) +{ + unsigned int opcode; + unsigned char mod_rm; + int reg; + unsigned char *p; + int i, shorted, enlarged, rexr; + unsigned long rv; + + p = (unsigned char *)ins_addr; + p += skip_prefix(p, &shorted, &enlarged, &rexr); + p += get_opcode(p, &opcode); + for (i = 0; i < ARRAY_SIZE(reg_rop); i++) + if (reg_rop[i] == opcode) { + rv = REG_READ; + goto do_work; + } + + for (i = 0; i < ARRAY_SIZE(reg_wop); i++) + if (reg_wop[i] == opcode) { + rv = REG_WRITE; + goto do_work; + } + + printk(KERN_ERR "mmiotrace: Not a register instruction, opcode " + "0x%02x\n", opcode); + goto err; + +do_work: + mod_rm = *p; + reg = ((mod_rm >> 3) & 0x7) | (rexr << 3); + switch (get_ins_reg_width(ins_addr)) { + case 1: + return *get_reg_w8(reg, regs); + + case 2: + return *(unsigned short *)get_reg_w32(reg, regs); + + case 4: + return *(unsigned int *)get_reg_w32(reg, regs); + +#ifdef __amd64__ + case 8: + return *(unsigned long *)get_reg_w32(reg, regs); +#endif + + default: + printk(KERN_ERR "mmiotrace: Error width# %d\n", reg); + } + +err: + return 0; +} + +unsigned long get_ins_imm_val(unsigned long ins_addr) +{ + unsigned int opcode; + unsigned char mod_rm; + unsigned char mod; + unsigned char *p; + int i, shorted, enlarged, rexr; + unsigned long rv; + + p = (unsigned char *)ins_addr; + p += skip_prefix(p, &shorted, &enlarged, &rexr); + p += get_opcode(p, &opcode); + for (i = 0; i < ARRAY_SIZE(imm_wop); i++) + if (imm_wop[i] == opcode) { + rv = IMM_WRITE; + goto do_work; + } + + printk(KERN_ERR "mmiotrace: Not an immediate instruction, opcode " + "0x%02x\n", opcode); + goto err; + +do_work: + mod_rm = *p; + mod = mod_rm >> 6; + p++; + switch (mod) { + case 0: + /* if r/m is 5 we have a 32 disp (IA32 Manual 3, Table 2-2) */ + /* AMD64: XXX Check for address size prefix? */ + if ((mod_rm & 0x7) == 0x5) + p += 4; + break; + + case 1: + p += 1; + break; + + case 2: + p += 4; + break; + + case 3: + default: + printk(KERN_ERR "mmiotrace: not a memory access instruction " + "at 0x%lx, rm_mod=0x%02x\n", + ins_addr, mod_rm); + } + + switch (get_ins_reg_width(ins_addr)) { + case 1: + return *(unsigned char *)p; + + case 2: + return *(unsigned short *)p; + + case 4: + return *(unsigned int *)p; + +#ifdef __amd64__ + case 8: + return *(unsigned long *)p; +#endif + + default: + printk(KERN_ERR "mmiotrace: Error: width.\n"); + } + +err: + return 0; +} diff --git a/arch/x86/mm/pf_in.h b/arch/x86/mm/pf_in.h new file mode 100644 index 000000000000..e05341a51a27 --- /dev/null +++ b/arch/x86/mm/pf_in.h @@ -0,0 +1,39 @@ +/* + * Fault Injection Test harness (FI) + * Copyright (C) Intel Crop. + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, + * USA. + * + */ + +#ifndef __PF_H_ +#define __PF_H_ + +enum reason_type { + NOT_ME, /* page fault is not in regions */ + NOTHING, /* access others point in regions */ + REG_READ, /* read from addr to reg */ + REG_WRITE, /* write from reg to addr */ + IMM_WRITE, /* write from imm to addr */ + OTHERS /* Other instructions can not intercept */ +}; + +enum reason_type get_ins_type(unsigned long ins_addr); +unsigned int get_ins_mem_width(unsigned long ins_addr); +unsigned long get_ins_reg_val(unsigned long ins_addr, struct pt_regs *regs); +unsigned long get_ins_imm_val(unsigned long ins_addr); + +#endif /* __PF_H_ */ diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 50159764f694..557b2abceef8 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -2,6 +2,7 @@ #include <asm/pgalloc.h> #include <asm/pgtable.h> #include <asm/tlb.h> +#include <asm/fixmap.h> pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { @@ -65,12 +66,6 @@ static inline void pgd_list_del(pgd_t *pgd) static void pgd_ctor(void *p) { pgd_t *pgd = p; - unsigned long flags; - - /* Clear usermode parts of PGD */ - memset(pgd, 0, KERNEL_PGD_BOUNDARY*sizeof(pgd_t)); - - spin_lock_irqsave(&pgd_lock, flags); /* If the pgd points to a shared pagetable level (either the ptes in non-PAE, or shared PMD in PAE), then just copy the @@ -90,8 +85,6 @@ static void pgd_ctor(void *p) /* list required to sync kernel mapping updates */ if (!SHARED_KERNEL_PMD) pgd_list_add(pgd); - - spin_unlock_irqrestore(&pgd_lock, flags); } static void pgd_dtor(void *pgd) @@ -119,6 +112,72 @@ static void pgd_dtor(void *pgd) #ifdef CONFIG_X86_PAE /* + * In PAE mode, we need to do a cr3 reload (=tlb flush) when + * updating the top-level pagetable entries to guarantee the + * processor notices the update. Since this is expensive, and + * all 4 top-level entries are used almost immediately in a + * new process's life, we just pre-populate them here. + * + * Also, if we're in a paravirt environment where the kernel pmd is + * not shared between pagetables (!SHARED_KERNEL_PMDS), we allocate + * and initialize the kernel pmds here. + */ +#define PREALLOCATED_PMDS UNSHARED_PTRS_PER_PGD + +void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd) +{ + paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); + + /* Note: almost everything apart from _PAGE_PRESENT is + reserved at the pmd (PDPT) level. */ + set_pud(pudp, __pud(__pa(pmd) | _PAGE_PRESENT)); + + /* + * According to Intel App note "TLBs, Paging-Structure Caches, + * and Their Invalidation", April 2007, document 317080-001, + * section 8.1: in PAE mode we explicitly have to flush the + * TLB via cr3 if the top-level pgd is changed... + */ + if (mm == current->active_mm) + write_cr3(read_cr3()); +} +#else /* !CONFIG_X86_PAE */ + +/* No need to prepopulate any pagetable entries in non-PAE modes. */ +#define PREALLOCATED_PMDS 0 + +#endif /* CONFIG_X86_PAE */ + +static void free_pmds(pmd_t *pmds[]) +{ + int i; + + for(i = 0; i < PREALLOCATED_PMDS; i++) + if (pmds[i]) + free_page((unsigned long)pmds[i]); +} + +static int preallocate_pmds(pmd_t *pmds[]) +{ + int i; + bool failed = false; + + for(i = 0; i < PREALLOCATED_PMDS; i++) { + pmd_t *pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); + if (pmd == NULL) + failed = true; + pmds[i] = pmd; + } + + if (failed) { + free_pmds(pmds); + return -ENOMEM; + } + + return 0; +} + +/* * Mop up any pmd pages which may still be attached to the pgd. * Normally they will be freed by munmap/exit_mmap, but any pmd we * preallocate which never got a corresponding vma will need to be @@ -128,7 +187,7 @@ static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) { int i; - for(i = 0; i < UNSHARED_PTRS_PER_PGD; i++) { + for(i = 0; i < PREALLOCATED_PMDS; i++) { pgd_t pgd = pgdp[i]; if (pgd_val(pgd) != 0) { @@ -142,32 +201,17 @@ static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) } } -/* - * In PAE mode, we need to do a cr3 reload (=tlb flush) when - * updating the top-level pagetable entries to guarantee the - * processor notices the update. Since this is expensive, and - * all 4 top-level entries are used almost immediately in a - * new process's life, we just pre-populate them here. - * - * Also, if we're in a paravirt environment where the kernel pmd is - * not shared between pagetables (!SHARED_KERNEL_PMDS), we allocate - * and initialize the kernel pmds here. - */ -static int pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd) +static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[]) { pud_t *pud; unsigned long addr; int i; pud = pud_offset(pgd, 0); - for (addr = i = 0; i < UNSHARED_PTRS_PER_PGD; - i++, pud++, addr += PUD_SIZE) { - pmd_t *pmd = pmd_alloc_one(mm, addr); - if (!pmd) { - pgd_mop_up_pmds(mm, pgd); - return 0; - } + for (addr = i = 0; i < PREALLOCATED_PMDS; + i++, pud++, addr += PUD_SIZE) { + pmd_t *pmd = pmds[i]; if (i >= KERNEL_PGD_BOUNDARY) memcpy(pmd, (pmd_t *)pgd_page_vaddr(swapper_pg_dir[i]), @@ -175,61 +219,54 @@ static int pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd) pud_populate(mm, pud, pmd); } - - return 1; } -void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd) +pgd_t *pgd_alloc(struct mm_struct *mm) { - paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); + pgd_t *pgd; + pmd_t *pmds[PREALLOCATED_PMDS]; + unsigned long flags; - /* Note: almost everything apart from _PAGE_PRESENT is - reserved at the pmd (PDPT) level. */ - set_pud(pudp, __pud(__pa(pmd) | _PAGE_PRESENT)); + pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); - /* - * According to Intel App note "TLBs, Paging-Structure Caches, - * and Their Invalidation", April 2007, document 317080-001, - * section 8.1: in PAE mode we explicitly have to flush the - * TLB via cr3 if the top-level pgd is changed... - */ - if (mm == current->active_mm) - write_cr3(read_cr3()); -} -#else /* !CONFIG_X86_PAE */ -/* No need to prepopulate any pagetable entries in non-PAE modes. */ -static int pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd) -{ - return 1; -} + if (pgd == NULL) + goto out; -static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgd) -{ -} -#endif /* CONFIG_X86_PAE */ + mm->pgd = pgd; -pgd_t *pgd_alloc(struct mm_struct *mm) -{ - pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); + if (preallocate_pmds(pmds) != 0) + goto out_free_pgd; - /* so that alloc_pmd can use it */ - mm->pgd = pgd; - if (pgd) - pgd_ctor(pgd); + if (paravirt_pgd_alloc(mm) != 0) + goto out_free_pmds; - if (pgd && !pgd_prepopulate_pmd(mm, pgd)) { - pgd_dtor(pgd); - free_page((unsigned long)pgd); - pgd = NULL; - } + /* + * Make sure that pre-populating the pmds is atomic with + * respect to anything walking the pgd_list, so that they + * never see a partially populated pgd. + */ + spin_lock_irqsave(&pgd_lock, flags); + + pgd_ctor(pgd); + pgd_prepopulate_pmd(mm, pgd, pmds); + + spin_unlock_irqrestore(&pgd_lock, flags); return pgd; + +out_free_pmds: + free_pmds(pmds); +out_free_pgd: + free_page((unsigned long)pgd); +out: + return NULL; } void pgd_free(struct mm_struct *mm, pgd_t *pgd) { pgd_mop_up_pmds(mm, pgd); pgd_dtor(pgd); + paravirt_pgd_free(mm, pgd); free_page((unsigned long)pgd); } @@ -255,7 +292,7 @@ int ptep_test_and_clear_young(struct vm_area_struct *vma, if (pte_young(*ptep)) ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, - &ptep->pte); + (unsigned long *) &ptep->pte); if (ret) pte_update(vma->vm_mm, addr, ptep); @@ -274,3 +311,22 @@ int ptep_clear_flush_young(struct vm_area_struct *vma, return young; } + +int fixmaps_set; + +void __native_set_fixmap(enum fixed_addresses idx, pte_t pte) +{ + unsigned long address = __fix_to_virt(idx); + + if (idx >= __end_of_fixed_addresses) { + BUG(); + return; + } + set_pte_vaddr(address, pte); + fixmaps_set++; +} + +void native_set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t flags) +{ + __native_set_fixmap(idx, pfn_pte(phys >> PAGE_SHIFT, flags)); +} diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index 369cf065b6a4..b4becbf8c570 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -71,7 +71,7 @@ void show_mem(void) * Associate a virtual page frame with a given physical page frame * and protection flags for that frame. */ -static void set_pte_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags) +void set_pte_vaddr(unsigned long vaddr, pte_t pteval) { pgd_t *pgd; pud_t *pud; @@ -94,8 +94,8 @@ static void set_pte_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags) return; } pte = pte_offset_kernel(pmd, vaddr); - if (pgprot_val(flags)) - set_pte_present(&init_mm, vaddr, pte, pfn_pte(pfn, flags)); + if (pte_val(pteval)) + set_pte_present(&init_mm, vaddr, pte, pteval); else pte_clear(&init_mm, vaddr, pte); @@ -141,22 +141,9 @@ void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags) __flush_tlb_one(vaddr); } -static int fixmaps; unsigned long __FIXADDR_TOP = 0xfffff000; EXPORT_SYMBOL(__FIXADDR_TOP); -void __set_fixmap (enum fixed_addresses idx, unsigned long phys, pgprot_t flags) -{ - unsigned long address = __fix_to_virt(idx); - - if (idx >= __end_of_fixed_addresses) { - BUG(); - return; - } - set_pte_pfn(address, phys >> PAGE_SHIFT, flags); - fixmaps++; -} - /** * reserve_top_address - reserves a hole in the top of kernel address space * @reserve - size of hole to reserve @@ -164,11 +151,44 @@ void __set_fixmap (enum fixed_addresses idx, unsigned long phys, pgprot_t flags) * Can be used to relocate the fixmap area and poke a hole in the top * of kernel address space to make room for a hypervisor. */ -void reserve_top_address(unsigned long reserve) +void __init reserve_top_address(unsigned long reserve) { - BUG_ON(fixmaps > 0); + BUG_ON(fixmaps_set > 0); printk(KERN_INFO "Reserving virtual address space above 0x%08x\n", (int)-reserve); __FIXADDR_TOP = -reserve - PAGE_SIZE; __VMALLOC_RESERVE += reserve; } + +/* + * vmalloc=size forces the vmalloc area to be exactly 'size' + * bytes. This can be used to increase (or decrease) the + * vmalloc area - the default is 128m. + */ +static int __init parse_vmalloc(char *arg) +{ + if (!arg) + return -EINVAL; + + __VMALLOC_RESERVE = memparse(arg, &arg); + return 0; +} +early_param("vmalloc", parse_vmalloc); + +/* + * reservetop=size reserves a hole at the top of the kernel address space which + * a hypervisor can load into later. Needed for dynamically loaded hypervisors, + * so relocating the fixmap can be done before paging initialization. + */ +static int __init parse_reservetop(char *arg) +{ + unsigned long address; + + if (!arg) + return -EINVAL; + + address = memparse(arg, &arg); + reserve_top_address(address); + return 0; +} +early_param("reservetop", parse_reservetop); diff --git a/arch/x86/kernel/srat_32.c b/arch/x86/mm/srat_32.c index 70e4a374b4e8..1eb2973a301c 100644 --- a/arch/x86/kernel/srat_32.c +++ b/arch/x86/mm/srat_32.c @@ -31,6 +31,7 @@ #include <asm/srat.h> #include <asm/topology.h> #include <asm/smp.h> +#include <asm/e820.h> /* * proximity macros and definitions @@ -41,7 +42,7 @@ #define BMAP_TEST(bmap, bit) ((bmap)[NODE_ARRAY_INDEX(bit)] & (1 << NODE_ARRAY_OFFSET(bit))) /* bitmap length; _PXM is at most 255 */ #define PXM_BITMAP_LEN (MAX_PXM_DOMAINS / 8) -static u8 pxm_bitmap[PXM_BITMAP_LEN]; /* bitmap of proximity domains */ +static u8 __initdata pxm_bitmap[PXM_BITMAP_LEN]; /* bitmap of proximity domains */ #define MAX_CHUNKS_PER_NODE 3 #define MAXCHUNKS (MAX_CHUNKS_PER_NODE * MAX_NUMNODES) @@ -52,16 +53,37 @@ struct node_memory_chunk_s { u8 nid; // which cnode contains this chunk? u8 bank; // which mem bank on this node }; -static struct node_memory_chunk_s node_memory_chunk[MAXCHUNKS]; +static struct node_memory_chunk_s __initdata node_memory_chunk[MAXCHUNKS]; -static int num_memory_chunks; /* total number of memory chunks */ +static int __initdata num_memory_chunks; /* total number of memory chunks */ static u8 __initdata apicid_to_pxm[MAX_APICID]; +int numa_off __initdata; +int acpi_numa __initdata; + +static __init void bad_srat(void) +{ + printk(KERN_ERR "SRAT: SRAT not used.\n"); + acpi_numa = -1; + num_memory_chunks = 0; +} + +static __init inline int srat_disabled(void) +{ + return numa_off || acpi_numa < 0; +} + /* Identify CPU proximity domains */ -static void __init parse_cpu_affinity_structure(char *p) +void __init +acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *cpu_affinity) { - struct acpi_srat_cpu_affinity *cpu_affinity = - (struct acpi_srat_cpu_affinity *) p; + if (srat_disabled()) + return; + if (cpu_affinity->header.length != + sizeof(struct acpi_srat_cpu_affinity)) { + bad_srat(); + return; + } if ((cpu_affinity->flags & ACPI_SRAT_CPU_ENABLED) == 0) return; /* empty entry */ @@ -71,7 +93,7 @@ static void __init parse_cpu_affinity_structure(char *p) apicid_to_pxm[cpu_affinity->apic_id] = cpu_affinity->proximity_domain_lo; - printk("CPU 0x%02X in proximity domain 0x%02X\n", + printk(KERN_DEBUG "CPU %02x in proximity domain %02x\n", cpu_affinity->apic_id, cpu_affinity->proximity_domain_lo); } @@ -79,14 +101,21 @@ static void __init parse_cpu_affinity_structure(char *p) * Identify memory proximity domains and hot-remove capabilities. * Fill node memory chunk list structure. */ -static void __init parse_memory_affinity_structure (char *sratp) +void __init +acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *memory_affinity) { unsigned long long paddr, size; unsigned long start_pfn, end_pfn; u8 pxm; struct node_memory_chunk_s *p, *q, *pend; - struct acpi_srat_mem_affinity *memory_affinity = - (struct acpi_srat_mem_affinity *) sratp; + + if (srat_disabled()) + return; + if (memory_affinity->header.length != + sizeof(struct acpi_srat_mem_affinity)) { + bad_srat(); + return; + } if ((memory_affinity->flags & ACPI_SRAT_MEM_ENABLED) == 0) return; /* empty entry */ @@ -105,7 +134,8 @@ static void __init parse_memory_affinity_structure (char *sratp) if (num_memory_chunks >= MAXCHUNKS) { - printk("Too many mem chunks in SRAT. Ignoring %lld MBytes at %llx\n", + printk(KERN_WARNING "Too many mem chunks in SRAT." + " Ignoring %lld MBytes at %llx\n", size/(1024*1024), paddr); return; } @@ -126,14 +156,22 @@ static void __init parse_memory_affinity_structure (char *sratp) num_memory_chunks++; - printk("Memory range 0x%lX to 0x%lX (type 0x%X) in proximity domain 0x%02X %s\n", + printk(KERN_DEBUG "Memory range %08lx to %08lx" + " in proximity domain %02x %s\n", start_pfn, end_pfn, - memory_affinity->memory_type, pxm, ((memory_affinity->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) ? "enabled and removable" : "enabled" ) ); } +/* Callback for SLIT parsing */ +void __init acpi_numa_slit_init(struct acpi_table_slit *slit) +{ +} + +void acpi_numa_arch_fixup(void) +{ +} /* * The SRAT table always lists ascending addresses, so can always * assume that the first "start" address that you see is the real @@ -149,7 +187,7 @@ static __init void node_read_chunk(int nid, struct node_memory_chunk_s *memory_c * *possible* memory hotplug areas the same as normal RAM. */ if (memory_chunk->start_pfn >= max_pfn) { - printk (KERN_INFO "Ignoring SRAT pfns: 0x%08lx -> %08lx\n", + printk(KERN_INFO "Ignoring SRAT pfns: %08lx - %08lx\n", memory_chunk->start_pfn, memory_chunk->end_pfn); return; } @@ -166,42 +204,17 @@ static __init void node_read_chunk(int nid, struct node_memory_chunk_s *memory_c node_end_pfn[nid] = memory_chunk->end_pfn; } -/* Parse the ACPI Static Resource Affinity Table */ -static int __init acpi20_parse_srat(struct acpi_table_srat *sratp) +int __init get_memcfg_from_srat(void) { - u8 *start, *end, *p; int i, j, nid; - start = (u8 *)(&(sratp->reserved) + 1); /* skip header */ - p = start; - end = (u8 *)sratp + sratp->header.length; - memset(pxm_bitmap, 0, sizeof(pxm_bitmap)); /* init proximity domain bitmap */ - memset(node_memory_chunk, 0, sizeof(node_memory_chunk)); - - num_memory_chunks = 0; - while (p < end) { - switch (*p) { - case ACPI_SRAT_TYPE_CPU_AFFINITY: - parse_cpu_affinity_structure(p); - break; - case ACPI_SRAT_TYPE_MEMORY_AFFINITY: - parse_memory_affinity_structure(p); - break; - default: - printk("ACPI 2.0 SRAT: unknown entry skipped: type=0x%02X, len=%d\n", p[0], p[1]); - break; - } - p += p[1]; - if (p[1] == 0) { - printk("acpi20_parse_srat: Entry length value is zero;" - " can't parse any further!\n"); - break; - } - } + if (srat_disabled()) + goto out_fail; if (num_memory_chunks == 0) { - printk("could not finy any ACPI SRAT memory areas.\n"); + printk(KERN_WARNING + "could not finy any ACPI SRAT memory areas.\n"); goto out_fail; } @@ -228,131 +241,39 @@ static int __init acpi20_parse_srat(struct acpi_table_srat *sratp) for (i = 0; i < num_memory_chunks; i++) node_memory_chunk[i].nid = pxm_to_node(node_memory_chunk[i].pxm); - printk("pxm bitmap: "); + printk(KERN_DEBUG "pxm bitmap: "); for (i = 0; i < sizeof(pxm_bitmap); i++) { - printk("%02X ", pxm_bitmap[i]); + printk(KERN_CONT "%02x ", pxm_bitmap[i]); } - printk("\n"); - printk("Number of logical nodes in system = %d\n", num_online_nodes()); - printk("Number of memory chunks in system = %d\n", num_memory_chunks); + printk(KERN_CONT "\n"); + printk(KERN_DEBUG "Number of logical nodes in system = %d\n", + num_online_nodes()); + printk(KERN_DEBUG "Number of memory chunks in system = %d\n", + num_memory_chunks); for (i = 0; i < MAX_APICID; i++) apicid_2_node[i] = pxm_to_node(apicid_to_pxm[i]); for (j = 0; j < num_memory_chunks; j++){ struct node_memory_chunk_s * chunk = &node_memory_chunk[j]; - printk("chunk %d nid %d start_pfn %08lx end_pfn %08lx\n", + printk(KERN_DEBUG + "chunk %d nid %d start_pfn %08lx end_pfn %08lx\n", j, chunk->nid, chunk->start_pfn, chunk->end_pfn); node_read_chunk(chunk->nid, chunk); - add_active_range(chunk->nid, chunk->start_pfn, chunk->end_pfn); + e820_register_active_regions(chunk->nid, chunk->start_pfn, + min(chunk->end_pfn, max_pfn)); } - + for_each_online_node(nid) { unsigned long start = node_start_pfn[nid]; - unsigned long end = node_end_pfn[nid]; + unsigned long end = min(node_end_pfn[nid], max_pfn); memory_present(nid, start, end); node_remap_size[nid] = node_memmap_size_bytes(nid, start, end); } return 1; out_fail: - return 0; -} - -struct acpi_static_rsdt { - struct acpi_table_rsdt table; - u32 padding[7]; /* Allow for 7 more table entries */ -}; - -int __init get_memcfg_from_srat(void) -{ - struct acpi_table_header *header = NULL; - struct acpi_table_rsdp *rsdp = NULL; - struct acpi_table_rsdt *rsdt = NULL; - acpi_native_uint rsdp_address = 0; - struct acpi_static_rsdt saved_rsdt; - int tables = 0; - int i = 0; - - rsdp_address = acpi_os_get_root_pointer(); - if (!rsdp_address) { - printk("%s: System description tables not found\n", - __func__); - goto out_err; - } - - printk("%s: assigning address to rsdp\n", __func__); - rsdp = (struct acpi_table_rsdp *)(u32)rsdp_address; - if (!rsdp) { - printk("%s: Didn't find ACPI root!\n", __func__); - goto out_err; - } - - printk(KERN_INFO "%.8s v%d [%.6s]\n", rsdp->signature, rsdp->revision, - rsdp->oem_id); - - if (strncmp(rsdp->signature, ACPI_SIG_RSDP,strlen(ACPI_SIG_RSDP))) { - printk(KERN_WARNING "%s: RSDP table signature incorrect\n", __func__); - goto out_err; - } - - rsdt = (struct acpi_table_rsdt *) - early_ioremap(rsdp->rsdt_physical_address, sizeof(struct acpi_table_rsdt)); - - if (!rsdt) { - printk(KERN_WARNING - "%s: ACPI: Invalid root system description tables (RSDT)\n", - __func__); - goto out_err; - } - - header = &rsdt->header; - - if (strncmp(header->signature, ACPI_SIG_RSDT, strlen(ACPI_SIG_RSDT))) { - printk(KERN_WARNING "ACPI: RSDT signature incorrect\n"); - goto out_err; - } - - /* - * The number of tables is computed by taking the - * size of all entries (header size minus total - * size of RSDT) divided by the size of each entry - * (4-byte table pointers). - */ - tables = (header->length - sizeof(struct acpi_table_header)) / 4; - - if (!tables) - goto out_err; - - memcpy(&saved_rsdt, rsdt, sizeof(saved_rsdt)); - - if (saved_rsdt.table.header.length > sizeof(saved_rsdt)) { - printk(KERN_WARNING "ACPI: Too big length in RSDT: %d\n", - saved_rsdt.table.header.length); - goto out_err; - } - - printk("Begin SRAT table scan....\n"); - - for (i = 0; i < tables; i++) { - /* Map in header, then map in full table length. */ - header = (struct acpi_table_header *) - early_ioremap(saved_rsdt.table.table_offset_entry[i], sizeof(struct acpi_table_header)); - if (!header) - break; - header = (struct acpi_table_header *) - early_ioremap(saved_rsdt.table.table_offset_entry[i], header->length); - if (!header) - break; - - if (strncmp((char *) &header->signature, ACPI_SIG_SRAT, 4)) - continue; - - /* we've found the srat table. don't need to look at any more tables */ - return acpi20_parse_srat((struct acpi_table_srat *)header); - } -out_err: - remove_all_active_ranges(); - printk("failed to get NUMA memory information from SRAT table\n"); + printk(KERN_ERR "failed to get NUMA memory information from SRAT" + " table\n"); return 0; } diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index 3890234e5b26..1b4763e26ea9 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -97,37 +97,22 @@ static __init inline int srat_disabled(void) return numa_off || acpi_numa < 0; } -/* - * A lot of BIOS fill in 10 (= no distance) everywhere. This messes - * up the NUMA heuristics which wants the local node to have a smaller - * distance than the others. - * Do some quick checks here and only use the SLIT if it passes. - */ -static __init int slit_valid(struct acpi_table_slit *slit) -{ - int i, j; - int d = slit->locality_count; - for (i = 0; i < d; i++) { - for (j = 0; j < d; j++) { - u8 val = slit->entry[d*i + j]; - if (i == j) { - if (val != LOCAL_DISTANCE) - return 0; - } else if (val <= LOCAL_DISTANCE) - return 0; - } - } - return 1; -} - /* Callback for SLIT parsing */ void __init acpi_numa_slit_init(struct acpi_table_slit *slit) { - if (!slit_valid(slit)) { - printk(KERN_INFO "ACPI: SLIT table looks invalid. Not used.\n"); - return; - } - acpi_slit = slit; + unsigned length; + unsigned long phys; + + length = slit->header.length; + phys = find_e820_area(0, max_pfn_mapped<<PAGE_SHIFT, length, + PAGE_SIZE); + + if (phys == -1L) + panic(" Can not save slit!\n"); + + acpi_slit = __va(phys); + memcpy(acpi_slit, slit, length); + reserve_early(phys, phys + length, "ACPI SLIT"); } /* Callback for Proximity Domain -> LAPIC mapping */ @@ -326,7 +311,7 @@ static int __init nodes_cover_memory(const struct bootnode *nodes) pxmram = 0; } - e820ram = end_pfn - absent_pages_in_range(0, end_pfn); + e820ram = max_pfn - absent_pages_in_range(0, max_pfn); /* We seem to lose 3 pages somewhere. Allow a bit of slack. */ if ((long)(e820ram - pxmram) >= 1*1024*1024) { printk(KERN_ERR @@ -403,7 +388,7 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end) if (node == NUMA_NO_NODE) continue; if (!node_isset(node, node_possible_map)) - numa_set_node(i, NUMA_NO_NODE); + numa_clear_node(i); } numa_init_array(); return 0; @@ -522,6 +507,7 @@ int __node_distance(int a, int b) EXPORT_SYMBOL(__node_distance); +#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) || defined(CONFIG_ACPI_HOTPLUG_MEMORY) int memory_add_physaddr_to_nid(u64 start) { int i, ret = 0; @@ -533,4 +519,4 @@ int memory_add_physaddr_to_nid(u64 start) return ret; } EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); - +#endif diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c new file mode 100644 index 000000000000..d877c5b423ef --- /dev/null +++ b/arch/x86/mm/testmmiotrace.c @@ -0,0 +1,71 @@ +/* + * Written by Pekka Paalanen, 2008 <pq@iki.fi> + */ +#include <linux/module.h> +#include <linux/io.h> + +#define MODULE_NAME "testmmiotrace" + +static unsigned long mmio_address; +module_param(mmio_address, ulong, 0); +MODULE_PARM_DESC(mmio_address, "Start address of the mapping of 16 kB."); + +static void do_write_test(void __iomem *p) +{ + unsigned int i; + for (i = 0; i < 256; i++) + iowrite8(i, p + i); + for (i = 1024; i < (5 * 1024); i += 2) + iowrite16(i * 12 + 7, p + i); + for (i = (5 * 1024); i < (16 * 1024); i += 4) + iowrite32(i * 212371 + 13, p + i); +} + +static void do_read_test(void __iomem *p) +{ + unsigned int i; + for (i = 0; i < 256; i++) + ioread8(p + i); + for (i = 1024; i < (5 * 1024); i += 2) + ioread16(p + i); + for (i = (5 * 1024); i < (16 * 1024); i += 4) + ioread32(p + i); +} + +static void do_test(void) +{ + void __iomem *p = ioremap_nocache(mmio_address, 0x4000); + if (!p) { + pr_err(MODULE_NAME ": could not ioremap, aborting.\n"); + return; + } + do_write_test(p); + do_read_test(p); + iounmap(p); +} + +static int __init init(void) +{ + if (mmio_address == 0) { + pr_err(MODULE_NAME ": you have to use the module argument " + "mmio_address.\n"); + pr_err(MODULE_NAME ": DO NOT LOAD THIS MODULE UNLESS" + " YOU REALLY KNOW WHAT YOU ARE DOING!\n"); + return -ENXIO; + } + + pr_warning(MODULE_NAME ": WARNING: mapping 16 kB @ 0x%08lx " + "in PCI address space, and writing " + "rubbish in there.\n", mmio_address); + do_test(); + return 0; +} + +static void __exit cleanup(void) +{ + pr_debug(MODULE_NAME ": unloaded.\n"); +} + +module_init(init); +module_exit(cleanup); +MODULE_LICENSE("GPL"); diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index cc48d3fde545..7f3329b55d2e 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -218,8 +218,8 @@ static int nmi_setup(void) } } - on_each_cpu(nmi_save_registers, NULL, 0, 1); - on_each_cpu(nmi_cpu_setup, NULL, 0, 1); + on_each_cpu(nmi_save_registers, NULL, 1); + on_each_cpu(nmi_cpu_setup, NULL, 1); nmi_enabled = 1; return 0; } @@ -269,12 +269,13 @@ static void nmi_cpu_shutdown(void *dummy) static void nmi_shutdown(void) { - struct op_msrs *msrs = &__get_cpu_var(cpu_msrs); + struct op_msrs *msrs = &get_cpu_var(cpu_msrs); nmi_enabled = 0; - on_each_cpu(nmi_cpu_shutdown, NULL, 0, 1); + on_each_cpu(nmi_cpu_shutdown, NULL, 1); unregister_die_notifier(&profile_exceptions_nb); model->shutdown(msrs); free_msrs(); + put_cpu_var(cpu_msrs); } static void nmi_cpu_start(void *dummy) @@ -285,7 +286,7 @@ static void nmi_cpu_start(void *dummy) static int nmi_start(void) { - on_each_cpu(nmi_cpu_start, NULL, 0, 1); + on_each_cpu(nmi_cpu_start, NULL, 1); return 0; } @@ -297,7 +298,7 @@ static void nmi_cpu_stop(void *dummy) static void nmi_stop(void) { - on_each_cpu(nmi_cpu_stop, NULL, 0, 1); + on_each_cpu(nmi_cpu_stop, NULL, 1); } struct op_counter_config counter_config[OP_MAX_COUNTER]; diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile index c5c8e485fc44..e515e8db842a 100644 --- a/arch/x86/pci/Makefile +++ b/arch/x86/pci/Makefile @@ -1,5 +1,17 @@ -ifeq ($(CONFIG_X86_32),y) -include ${srctree}/arch/x86/pci/Makefile_32 -else -include ${srctree}/arch/x86/pci/Makefile_64 -endif +obj-y := i386.o init.o + +obj-$(CONFIG_PCI_BIOS) += pcbios.o +obj-$(CONFIG_PCI_MMCONFIG) += mmconfig_$(BITS).o direct.o mmconfig-shared.o +obj-$(CONFIG_PCI_DIRECT) += direct.o +obj-$(CONFIG_PCI_OLPC) += olpc.o + +pci-y := fixup.o +pci-$(CONFIG_ACPI) += acpi.o +pci-y += legacy.o irq.o + +pci-$(CONFIG_X86_VISWS) += visws.o + +pci-$(CONFIG_X86_NUMAQ) += numa.o + +obj-y += $(pci-y) common.o early.o +obj-y += amd_bus.o diff --git a/arch/x86/pci/Makefile_32 b/arch/x86/pci/Makefile_32 deleted file mode 100644 index 89ec35d00efd..000000000000 --- a/arch/x86/pci/Makefile_32 +++ /dev/null @@ -1,24 +0,0 @@ -obj-y := i386.o init.o - -obj-$(CONFIG_PCI_BIOS) += pcbios.o -obj-$(CONFIG_PCI_MMCONFIG) += mmconfig_32.o direct.o mmconfig-shared.o -obj-$(CONFIG_PCI_DIRECT) += direct.o -obj-$(CONFIG_PCI_OLPC) += olpc.o - -pci-y := fixup.o - -# Do not change the ordering here. There is a nasty init function -# ordering dependency which breaks when you move acpi.o below -# legacy/irq.o -pci-$(CONFIG_ACPI) += acpi.o -pci-y += legacy.o irq.o - -# Careful: VISWS and NUMAQ overrule the pci-y above. The colons are -# therefor correct. This needs a proper fix by distangling the code. -pci-$(CONFIG_X86_VISWS) := visws.o fixup.o -pci-$(CONFIG_X86_NUMAQ) := numa.o irq.o - -# Necessary for NUMAQ as well -pci-$(CONFIG_NUMA) += mp_bus_to_node.o - -obj-y += $(pci-y) common.o early.o diff --git a/arch/x86/pci/Makefile_64 b/arch/x86/pci/Makefile_64 deleted file mode 100644 index 8fbd19832cf6..000000000000 --- a/arch/x86/pci/Makefile_64 +++ /dev/null @@ -1,17 +0,0 @@ -# -# Makefile for X86_64 specific PCI routines -# -# Reuse the i386 PCI subsystem -# -EXTRA_CFLAGS += -Iarch/x86/pci - -obj-y := i386.o -obj-$(CONFIG_PCI_DIRECT)+= direct.o -obj-y += fixup.o init.o -obj-$(CONFIG_ACPI) += acpi.o -obj-y += legacy.o irq.o common.o early.o -# mmconfig has a 64bit special -obj-$(CONFIG_PCI_MMCONFIG) += mmconfig_64.o direct.o mmconfig-shared.o - -obj-y += k8-bus_64.o - diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index d95de2f199cd..19af06927fbc 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -171,8 +171,11 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do if (node != -1) set_mp_bus_to_node(busnum, node); else - node = get_mp_bus_to_node(busnum); #endif + node = get_mp_bus_to_node(busnum); + + if (node != -1 && !node_online(node)) + node = -1; /* Allocate per-root-bus (not per bus) arch-specific data. * TODO: leak; this memory is never freed. @@ -204,22 +207,23 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do if (!bus) kfree(sd); + if (bus && node != -1) { #ifdef CONFIG_ACPI_NUMA - if (bus) { - if (pxm >= 0) { + if (pxm >= 0) printk(KERN_DEBUG "bus %02x -> pxm %d -> node %d\n", - busnum, pxm, pxm_to_node(pxm)); - } - } + busnum, pxm, node); +#else + printk(KERN_DEBUG "bus %02x -> node %d\n", + busnum, node); #endif + } if (bus && (pci_probe & PCI_USE__CRS)) get_current_resources(device, busnum, domain, bus); return bus; } -extern int pci_routeirq; -static int __init pci_acpi_init(void) +int __init pci_acpi_init(void) { struct pci_dev *dev = NULL; @@ -253,4 +257,3 @@ static int __init pci_acpi_init(void) return 0; } -subsys_initcall(pci_acpi_init); diff --git a/arch/x86/pci/k8-bus_64.c b/arch/x86/pci/amd_bus.c index 5c2799c20e47..dbf532369711 100644 --- a/arch/x86/pci/k8-bus_64.c +++ b/arch/x86/pci/amd_bus.c @@ -1,40 +1,25 @@ #include <linux/init.h> #include <linux/pci.h> +#include <linux/topology.h> +#include "pci.h" + +#ifdef CONFIG_X86_64 #include <asm/pci-direct.h> #include <asm/mpspec.h> #include <linux/cpumask.h> -#include <linux/topology.h> +#endif /* * This discovers the pcibus <-> node mapping on AMD K8. * also get peer root bus resource for io,mmio */ - -/* - * sub bus (transparent) will use entres from 3 to store extra from root, - * so need to make sure have enought slot there, increase PCI_BUS_NUM_RESOURCES? - */ -#define RES_NUM 16 -struct pci_root_info { - char name[12]; - unsigned int res_num; - struct resource res[RES_NUM]; - int bus_min; - int bus_max; - int node; - int link; -}; - -/* 4 at this time, it may become to 32 */ -#define PCI_ROOT_NR 4 -static int pci_root_num; -static struct pci_root_info pci_root_info[PCI_ROOT_NR]; - #ifdef CONFIG_NUMA #define BUS_NR 256 +#ifdef CONFIG_X86_64 + static int mp_bus_to_node[BUS_NR]; void set_mp_bus_to_node(int busnum, int node) @@ -61,7 +46,52 @@ int get_mp_bus_to_node(int busnum) return node; } -#endif + +#else /* CONFIG_X86_32 */ + +static unsigned char mp_bus_to_node[BUS_NR]; + +void set_mp_bus_to_node(int busnum, int node) +{ + if (busnum >= 0 && busnum < BUS_NR) + mp_bus_to_node[busnum] = (unsigned char) node; +} + +int get_mp_bus_to_node(int busnum) +{ + int node; + + if (busnum < 0 || busnum > (BUS_NR - 1)) + return 0; + node = mp_bus_to_node[busnum]; + return node; +} + +#endif /* CONFIG_X86_32 */ + +#endif /* CONFIG_NUMA */ + +#ifdef CONFIG_X86_64 + +/* + * sub bus (transparent) will use entres from 3 to store extra from root, + * so need to make sure have enought slot there, increase PCI_BUS_NUM_RESOURCES? + */ +#define RES_NUM 16 +struct pci_root_info { + char name[12]; + unsigned int res_num; + struct resource res[RES_NUM]; + int bus_min; + int bus_max; + int node; + int link; +}; + +/* 4 at this time, it may become to 32 */ +#define PCI_ROOT_NR 4 +static int pci_root_num; +static struct pci_root_info pci_root_info[PCI_ROOT_NR]; void set_pci_bus_resources_arch_default(struct pci_bus *b) { @@ -384,7 +414,7 @@ static int __init early_fill_mp_bus_info(void) /* need to take out [0, TOM) for RAM*/ address = MSR_K8_TOP_MEM1; rdmsrl(address, val); - end = (val & 0xffffff8000000ULL); + end = (val & 0xffffff800000ULL); printk(KERN_INFO "TOM: %016lx aka %ldM\n", end, end>>20); if (end < (1ULL<<32)) update_range(range, 0, end - 1); @@ -478,7 +508,7 @@ static int __init early_fill_mp_bus_info(void) /* TOP_MEM2 */ address = MSR_K8_TOP_MEM2; rdmsrl(address, val); - end = (val & 0xffffff8000000ULL); + end = (val & 0xffffff800000ULL); printk(KERN_INFO "TOM2: %016lx aka %ldM\n", end, end>>20); update_range(range, 1ULL<<32, end - 1); } @@ -526,3 +556,31 @@ static int __init early_fill_mp_bus_info(void) } postcore_initcall(early_fill_mp_bus_info); + +#endif + +/* common 32/64 bit code */ + +#define ENABLE_CF8_EXT_CFG (1ULL << 46) + +static void enable_pci_io_ecs_per_cpu(void *unused) +{ + u64 reg; + rdmsrl(MSR_AMD64_NB_CFG, reg); + if (!(reg & ENABLE_CF8_EXT_CFG)) { + reg |= ENABLE_CF8_EXT_CFG; + wrmsrl(MSR_AMD64_NB_CFG, reg); + } +} + +static int __init enable_pci_io_ecs(void) +{ + /* assume all cpus from fam10h have IO ECS */ + if (boot_cpu_data.x86 < 0x10) + return 0; + on_each_cpu(enable_pci_io_ecs_per_cpu, NULL, 1); + pci_probe |= PCI_HAS_IO_ECS; + return 0; +} + +postcore_initcall(enable_pci_io_ecs); diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 6e64aaf00d1d..b67732bbb85a 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -20,6 +20,7 @@ unsigned int pci_probe = PCI_PROBE_BIOS | PCI_PROBE_CONF1 | PCI_PROBE_CONF2 | PCI_PROBE_MMCONF; +unsigned int pci_early_dump_regs; static int pci_bf_sort; int pci_routeirq; int pcibios_last_bus = -1; @@ -31,7 +32,7 @@ struct pci_raw_ops *raw_pci_ext_ops; int raw_pci_read(unsigned int domain, unsigned int bus, unsigned int devfn, int reg, int len, u32 *val) { - if (reg < 256 && raw_pci_ops) + if (domain == 0 && reg < 256 && raw_pci_ops) return raw_pci_ops->read(domain, bus, devfn, reg, len, val); if (raw_pci_ext_ops) return raw_pci_ext_ops->read(domain, bus, devfn, reg, len, val); @@ -41,7 +42,7 @@ int raw_pci_read(unsigned int domain, unsigned int bus, unsigned int devfn, int raw_pci_write(unsigned int domain, unsigned int bus, unsigned int devfn, int reg, int len, u32 val) { - if (reg < 256 && raw_pci_ops) + if (domain == 0 && reg < 256 && raw_pci_ops) return raw_pci_ops->write(domain, bus, devfn, reg, len, val); if (raw_pci_ext_ops) return raw_pci_ext_ops->write(domain, bus, devfn, reg, len, val); @@ -121,6 +122,21 @@ void __init dmi_check_skip_isa_align(void) dmi_check_system(can_skip_pciprobe_dmi_table); } +static void __devinit pcibios_fixup_device_resources(struct pci_dev *dev) +{ + struct resource *rom_r = &dev->resource[PCI_ROM_RESOURCE]; + + if (pci_probe & PCI_NOASSIGN_ROMS) { + if (rom_r->parent) + return; + if (rom_r->start) { + /* we deal with BIOS assigned ROM later */ + return; + } + rom_r->start = rom_r->end = rom_r->flags = 0; + } +} + /* * Called after each bus is probed, but before its children * are examined. @@ -128,7 +144,11 @@ void __init dmi_check_skip_isa_align(void) void __devinit pcibios_fixup_bus(struct pci_bus *b) { + struct pci_dev *dev; + pci_read_bridge_bases(b); + list_for_each_entry(dev, &b->devices, bus_list) + pcibios_fixup_device_resources(dev); } /* @@ -384,7 +404,7 @@ struct pci_bus * __devinit pcibios_scan_root(int busnum) extern u8 pci_cache_line_size; -static int __init pcibios_init(void) +int __init pcibios_init(void) { struct cpuinfo_x86 *c = &boot_cpu_data; @@ -411,8 +431,6 @@ static int __init pcibios_init(void) return 0; } -subsys_initcall(pcibios_init); - char * __devinit pcibios_setup(char *str) { if (!strcmp(str, "off")) { @@ -483,12 +501,18 @@ char * __devinit pcibios_setup(char *str) else if (!strcmp(str, "rom")) { pci_probe |= PCI_ASSIGN_ROMS; return NULL; + } else if (!strcmp(str, "norom")) { + pci_probe |= PCI_NOASSIGN_ROMS; + return NULL; } else if (!strcmp(str, "assign-busses")) { pci_probe |= PCI_ASSIGN_ALL_BUSSES; return NULL; } else if (!strcmp(str, "use_crs")) { pci_probe |= PCI_USE__CRS; return NULL; + } else if (!strcmp(str, "earlydump")) { + pci_early_dump_regs = 1; + return NULL; } else if (!strcmp(str, "routeirq")) { pci_routeirq = 1; return NULL; diff --git a/arch/x86/pci/direct.c b/arch/x86/pci/direct.c index 21d1e0e0d535..9915293500fb 100644 --- a/arch/x86/pci/direct.c +++ b/arch/x86/pci/direct.c @@ -8,18 +8,21 @@ #include "pci.h" /* - * Functions for accessing PCI configuration space with type 1 accesses + * Functions for accessing PCI base (first 256 bytes) and extended + * (4096 bytes per PCI function) configuration space with type 1 + * accesses. */ #define PCI_CONF1_ADDRESS(bus, devfn, reg) \ - (0x80000000 | (bus << 16) | (devfn << 8) | (reg & ~3)) + (0x80000000 | ((reg & 0xF00) << 16) | (bus << 16) \ + | (devfn << 8) | (reg & 0xFC)) static int pci_conf1_read(unsigned int seg, unsigned int bus, unsigned int devfn, int reg, int len, u32 *value) { unsigned long flags; - if ((bus > 255) || (devfn > 255) || (reg > 255)) { + if ((bus > 255) || (devfn > 255) || (reg > 4095)) { *value = -1; return -EINVAL; } @@ -50,7 +53,7 @@ static int pci_conf1_write(unsigned int seg, unsigned int bus, { unsigned long flags; - if ((bus > 255) || (devfn > 255) || (reg > 255)) + if ((bus > 255) || (devfn > 255) || (reg > 4095)) return -EINVAL; spin_lock_irqsave(&pci_config_lock, flags); @@ -260,10 +263,18 @@ void __init pci_direct_init(int type) return; printk(KERN_INFO "PCI: Using configuration type %d for base access\n", type); - if (type == 1) + if (type == 1) { raw_pci_ops = &pci_direct_conf1; - else - raw_pci_ops = &pci_direct_conf2; + if (raw_pci_ext_ops) + return; + if (!(pci_probe & PCI_HAS_IO_ECS)) + return; + printk(KERN_INFO "PCI: Using configuration type 1 " + "for extended access\n"); + raw_pci_ext_ops = &pci_direct_conf1; + return; + } + raw_pci_ops = &pci_direct_conf2; } int __init pci_direct_probe(void) diff --git a/arch/x86/pci/early.c b/arch/x86/pci/early.c index 42df4b6606df..858dbe3399f9 100644 --- a/arch/x86/pci/early.c +++ b/arch/x86/pci/early.c @@ -49,7 +49,14 @@ void write_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset, u8 val) { PDprintk("%x writing to %x: %x\n", slot, offset, val); outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8); - outb(val, 0xcfc); + outb(val, 0xcfc + (offset&3)); +} + +void write_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset, u16 val) +{ + PDprintk("%x writing to %x: %x\n", slot, offset, val); + outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8); + outw(val, 0xcfc + (offset&2)); } int early_pci_allowed(void) @@ -57,3 +64,54 @@ int early_pci_allowed(void) return (pci_probe & (PCI_PROBE_CONF1|PCI_PROBE_NOEARLY)) == PCI_PROBE_CONF1; } + +void early_dump_pci_device(u8 bus, u8 slot, u8 func) +{ + int i; + int j; + u32 val; + + printk("PCI: %02x:%02x:%02x", bus, slot, func); + + for (i = 0; i < 256; i += 4) { + if (!(i & 0x0f)) + printk("\n%04x:",i); + + val = read_pci_config(bus, slot, func, i); + for (j = 0; j < 4; j++) { + printk(" %02x", val & 0xff); + val >>= 8; + } + } + printk("\n"); +} + +void early_dump_pci_devices(void) +{ + unsigned bus, slot, func; + + if (!early_pci_allowed()) + return; + + for (bus = 0; bus < 256; bus++) { + for (slot = 0; slot < 32; slot++) { + for (func = 0; func < 8; func++) { + u32 class; + u8 type; + class = read_pci_config(bus, slot, func, + PCI_CLASS_REVISION); + if (class == 0xffffffff) + break; + + early_dump_pci_device(bus, slot, func); + + /* No multi-function device? */ + type = read_pci_config_byte(bus, slot, func, + PCI_HEADER_TYPE); + if (!(type & 0x80)) + break; + } + } + } +} + diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 10fb308fded8..2aafb67dc5f1 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -299,9 +299,9 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, return -EINVAL; prot = pgprot_val(vma->vm_page_prot); - if (pat_wc_enabled && write_combine) + if (pat_enabled && write_combine) prot |= _PAGE_CACHE_WC; - else if (pat_wc_enabled || boot_cpu_data.x86 > 3) + else if (pat_enabled || boot_cpu_data.x86 > 3) /* * ioremap() and ioremap_nocache() defaults to UC MINUS for now. * To avoid attribute conflicts, request UC MINUS here @@ -334,7 +334,9 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, flags = new_flags; } - if (vma->vm_pgoff <= max_pfn_mapped && + if (((vma->vm_pgoff < max_low_pfn_mapped) || + (vma->vm_pgoff >= (1UL<<(32 - PAGE_SHIFT)) && + vma->vm_pgoff < max_pfn_mapped)) && ioremap_change_attr((unsigned long)__va(addr), len, flags)) { free_memtype(addr, addr + len); return -EINVAL; diff --git a/arch/x86/pci/init.c b/arch/x86/pci/init.c index e70b9c57b88e..d6c950f81858 100644 --- a/arch/x86/pci/init.c +++ b/arch/x86/pci/init.c @@ -4,7 +4,7 @@ /* arch_initcall has too random ordering, so call the initializers in the right sequence from here. */ -static __init int pci_access_init(void) +static __init int pci_arch_init(void) { #ifdef CONFIG_PCI_DIRECT int type = 0; @@ -15,7 +15,8 @@ static __init int pci_access_init(void) pci_mmcfg_early_init(); #ifdef CONFIG_PCI_OLPC - pci_olpc_init(); + if (!pci_olpc_init()) + return 0; /* skip additional checks if it's an XO */ #endif #ifdef CONFIG_PCI_BIOS pci_pcbios_init(); @@ -39,4 +40,4 @@ static __init int pci_access_init(void) return 0; } -arch_initcall(pci_access_init); +arch_initcall(pci_arch_init); diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 0908fca901bf..6a06a2eb0597 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -11,8 +11,8 @@ #include <linux/slab.h> #include <linux/interrupt.h> #include <linux/dmi.h> -#include <asm/io.h> -#include <asm/smp.h> +#include <linux/io.h> +#include <linux/smp.h> #include <asm/io_apic.h> #include <linux/irq.h> #include <linux/acpi.h> @@ -45,7 +45,8 @@ struct irq_router { char *name; u16 vendor, device; int (*get)(struct pci_dev *router, struct pci_dev *dev, int pirq); - int (*set)(struct pci_dev *router, struct pci_dev *dev, int pirq, int new); + int (*set)(struct pci_dev *router, struct pci_dev *dev, int pirq, + int new); }; struct irq_router_handler { @@ -61,7 +62,7 @@ void (*pcibios_disable_irq)(struct pci_dev *dev) = NULL; * and perform checksum verification. */ -static inline struct irq_routing_table * pirq_check_routing_table(u8 *addr) +static inline struct irq_routing_table *pirq_check_routing_table(u8 *addr) { struct irq_routing_table *rt; int i; @@ -74,10 +75,11 @@ static inline struct irq_routing_table * pirq_check_routing_table(u8 *addr) rt->size < sizeof(struct irq_routing_table)) return NULL; sum = 0; - for (i=0; i < rt->size; i++) + for (i = 0; i < rt->size; i++) sum += addr[i]; if (!sum) { - DBG(KERN_DEBUG "PCI: Interrupt Routing Table found at 0x%p\n", rt); + DBG(KERN_DEBUG "PCI: Interrupt Routing Table found at 0x%p\n", + rt); return rt; } return NULL; @@ -100,7 +102,7 @@ static struct irq_routing_table * __init pirq_find_routing_table(void) return rt; printk(KERN_WARNING "PCI: PIRQ table NOT found at pirqaddr\n"); } - for(addr = (u8 *) __va(0xf0000); addr < (u8 *) __va(0x100000); addr += 16) { + for (addr = (u8 *) __va(0xf0000); addr < (u8 *) __va(0x100000); addr += 16) { rt = pirq_check_routing_table(addr); if (rt) return rt; @@ -122,20 +124,20 @@ static void __init pirq_peer_trick(void) struct irq_info *e; memset(busmap, 0, sizeof(busmap)); - for(i=0; i < (rt->size - sizeof(struct irq_routing_table)) / sizeof(struct irq_info); i++) { + for (i = 0; i < (rt->size - sizeof(struct irq_routing_table)) / sizeof(struct irq_info); i++) { e = &rt->slots[i]; #ifdef DEBUG { int j; DBG(KERN_DEBUG "%02x:%02x slot=%02x", e->bus, e->devfn/8, e->slot); - for(j=0; j<4; j++) + for (j = 0; j < 4; j++) DBG(" %d:%02x/%04x", j, e->irq[j].link, e->irq[j].bitmap); DBG("\n"); } #endif busmap[e->bus] = 1; } - for(i = 1; i < 256; i++) { + for (i = 1; i < 256; i++) { int node; if (!busmap[i] || pci_find_bus(0, i)) continue; @@ -183,7 +185,8 @@ static unsigned int read_config_nybble(struct pci_dev *router, unsigned offset, return (nr & 1) ? (x >> 4) : (x & 0xf); } -static void write_config_nybble(struct pci_dev *router, unsigned offset, unsigned nr, unsigned int val) +static void write_config_nybble(struct pci_dev *router, unsigned offset, + unsigned nr, unsigned int val) { u8 x; unsigned reg = offset + (nr >> 1); @@ -285,7 +288,7 @@ static int pirq_ite_get(struct pci_dev *router, struct pci_dev *dev, int pirq) static const unsigned char pirqmap[4] = { 1, 0, 2, 3 }; WARN_ON_ONCE(pirq > 4); - return read_config_nybble(router,0x43, pirqmap[pirq-1]); + return read_config_nybble(router, 0x43, pirqmap[pirq-1]); } static int pirq_ite_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) @@ -314,7 +317,7 @@ static int pirq_opti_set(struct pci_dev *router, struct pci_dev *dev, int pirq, /* * Cyrix: nibble offset 0x5C - * 0x5C bits 7:4 is INTB bits 3:0 is INTA + * 0x5C bits 7:4 is INTB bits 3:0 is INTA * 0x5D bits 7:4 is INTD bits 3:0 is INTC */ static int pirq_cyrix_get(struct pci_dev *router, struct pci_dev *dev, int pirq) @@ -350,7 +353,7 @@ static int pirq_cyrix_set(struct pci_dev *router, struct pci_dev *dev, int pirq, * Apparently there are systems implementing PCI routing table using * link values 0x01-0x04 and others using 0x41-0x44 for PCI INTA..D. * We try our best to handle both link mappings. - * + * * Currently (2003-05-21) it appears most SiS chipsets follow the * definition of routing registers from the SiS-5595 southbridge. * According to the SiS 5595 datasheets the revision id's of the @@ -370,7 +373,7 @@ static int pirq_cyrix_set(struct pci_dev *router, struct pci_dev *dev, int pirq, * * 0x62: USBIRQ: * bit 6 OHCI function disabled (0), enabled (1) - * + * * 0x6a: ACPI/SCI IRQ: bits 4-6 reserved * * 0x7e: Data Acq. Module IRQ - bits 4-6 reserved @@ -467,7 +470,8 @@ static int pirq_serverworks_get(struct pci_dev *router, struct pci_dev *dev, int return inb(0xc01) & 0xf; } -static int pirq_serverworks_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +static int pirq_serverworks_set(struct pci_dev *router, struct pci_dev *dev, + int pirq, int irq) { outb(pirq, 0xc00); outb(irq, 0xc01); @@ -487,9 +491,7 @@ static int pirq_amd756_get(struct pci_dev *router, struct pci_dev *dev, int pirq u8 irq; irq = 0; if (pirq <= 4) - { irq = read_config_nybble(router, 0x56, pirq - 1); - } printk(KERN_INFO "AMD756: dev %04x:%04x, router pirq : %d get irq : %2d\n", dev->vendor, dev->device, pirq, irq); return irq; @@ -497,12 +499,10 @@ static int pirq_amd756_get(struct pci_dev *router, struct pci_dev *dev, int pirq static int pirq_amd756_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) { - printk(KERN_INFO "AMD756: dev %04x:%04x, router pirq : %d SET irq : %2d\n", + printk(KERN_INFO "AMD756: dev %04x:%04x, router pirq : %d SET irq : %2d\n", dev->vendor, dev->device, pirq, irq); if (pirq <= 4) - { write_config_nybble(router, 0x56, pirq - 1, irq); - } return 1; } @@ -549,50 +549,49 @@ static __init int intel_router_probe(struct irq_router *r, struct pci_dev *route if (pci_dev_present(pirq_440gx)) return 0; - switch(device) - { - case PCI_DEVICE_ID_INTEL_82371FB_0: - case PCI_DEVICE_ID_INTEL_82371SB_0: - case PCI_DEVICE_ID_INTEL_82371AB_0: - case PCI_DEVICE_ID_INTEL_82371MX: - case PCI_DEVICE_ID_INTEL_82443MX_0: - case PCI_DEVICE_ID_INTEL_82801AA_0: - case PCI_DEVICE_ID_INTEL_82801AB_0: - case PCI_DEVICE_ID_INTEL_82801BA_0: - case PCI_DEVICE_ID_INTEL_82801BA_10: - case PCI_DEVICE_ID_INTEL_82801CA_0: - case PCI_DEVICE_ID_INTEL_82801CA_12: - case PCI_DEVICE_ID_INTEL_82801DB_0: - case PCI_DEVICE_ID_INTEL_82801E_0: - case PCI_DEVICE_ID_INTEL_82801EB_0: - case PCI_DEVICE_ID_INTEL_ESB_1: - case PCI_DEVICE_ID_INTEL_ICH6_0: - case PCI_DEVICE_ID_INTEL_ICH6_1: - case PCI_DEVICE_ID_INTEL_ICH7_0: - case PCI_DEVICE_ID_INTEL_ICH7_1: - case PCI_DEVICE_ID_INTEL_ICH7_30: - case PCI_DEVICE_ID_INTEL_ICH7_31: - case PCI_DEVICE_ID_INTEL_ESB2_0: - case PCI_DEVICE_ID_INTEL_ICH8_0: - case PCI_DEVICE_ID_INTEL_ICH8_1: - case PCI_DEVICE_ID_INTEL_ICH8_2: - case PCI_DEVICE_ID_INTEL_ICH8_3: - case PCI_DEVICE_ID_INTEL_ICH8_4: - case PCI_DEVICE_ID_INTEL_ICH9_0: - case PCI_DEVICE_ID_INTEL_ICH9_1: - case PCI_DEVICE_ID_INTEL_ICH9_2: - case PCI_DEVICE_ID_INTEL_ICH9_3: - case PCI_DEVICE_ID_INTEL_ICH9_4: - case PCI_DEVICE_ID_INTEL_ICH9_5: - case PCI_DEVICE_ID_INTEL_TOLAPAI_0: - case PCI_DEVICE_ID_INTEL_ICH10_0: - case PCI_DEVICE_ID_INTEL_ICH10_1: - case PCI_DEVICE_ID_INTEL_ICH10_2: - case PCI_DEVICE_ID_INTEL_ICH10_3: - r->name = "PIIX/ICH"; - r->get = pirq_piix_get; - r->set = pirq_piix_set; - return 1; + switch (device) { + case PCI_DEVICE_ID_INTEL_82371FB_0: + case PCI_DEVICE_ID_INTEL_82371SB_0: + case PCI_DEVICE_ID_INTEL_82371AB_0: + case PCI_DEVICE_ID_INTEL_82371MX: + case PCI_DEVICE_ID_INTEL_82443MX_0: + case PCI_DEVICE_ID_INTEL_82801AA_0: + case PCI_DEVICE_ID_INTEL_82801AB_0: + case PCI_DEVICE_ID_INTEL_82801BA_0: + case PCI_DEVICE_ID_INTEL_82801BA_10: + case PCI_DEVICE_ID_INTEL_82801CA_0: + case PCI_DEVICE_ID_INTEL_82801CA_12: + case PCI_DEVICE_ID_INTEL_82801DB_0: + case PCI_DEVICE_ID_INTEL_82801E_0: + case PCI_DEVICE_ID_INTEL_82801EB_0: + case PCI_DEVICE_ID_INTEL_ESB_1: + case PCI_DEVICE_ID_INTEL_ICH6_0: + case PCI_DEVICE_ID_INTEL_ICH6_1: + case PCI_DEVICE_ID_INTEL_ICH7_0: + case PCI_DEVICE_ID_INTEL_ICH7_1: + case PCI_DEVICE_ID_INTEL_ICH7_30: + case PCI_DEVICE_ID_INTEL_ICH7_31: + case PCI_DEVICE_ID_INTEL_ESB2_0: + case PCI_DEVICE_ID_INTEL_ICH8_0: + case PCI_DEVICE_ID_INTEL_ICH8_1: + case PCI_DEVICE_ID_INTEL_ICH8_2: + case PCI_DEVICE_ID_INTEL_ICH8_3: + case PCI_DEVICE_ID_INTEL_ICH8_4: + case PCI_DEVICE_ID_INTEL_ICH9_0: + case PCI_DEVICE_ID_INTEL_ICH9_1: + case PCI_DEVICE_ID_INTEL_ICH9_2: + case PCI_DEVICE_ID_INTEL_ICH9_3: + case PCI_DEVICE_ID_INTEL_ICH9_4: + case PCI_DEVICE_ID_INTEL_ICH9_5: + case PCI_DEVICE_ID_INTEL_TOLAPAI_0: + case PCI_DEVICE_ID_INTEL_ICH10_0: + case PCI_DEVICE_ID_INTEL_ICH10_1: + case PCI_DEVICE_ID_INTEL_ICH10_2: + case PCI_DEVICE_ID_INTEL_ICH10_3: + r->name = "PIIX/ICH"; + r->get = pirq_piix_get; + r->set = pirq_piix_set; + return 1; } return 0; } @@ -606,7 +605,7 @@ static __init int via_router_probe(struct irq_router *r, * workarounds for some buggy BIOSes */ if (device == PCI_DEVICE_ID_VIA_82C586_0) { - switch(router->device) { + switch (router->device) { case PCI_DEVICE_ID_VIA_82C686: /* * Asus k7m bios wrongly reports 82C686A @@ -621,10 +620,17 @@ static __init int via_router_probe(struct irq_router *r, */ device = PCI_DEVICE_ID_VIA_8235; break; + case PCI_DEVICE_ID_VIA_8237: + /** + * Asus a7v600 bios wrongly reports 8237 + * as 586-compatible + */ + device = PCI_DEVICE_ID_VIA_8237; + break; } } - switch(device) { + switch (device) { case PCI_DEVICE_ID_VIA_82C586_0: r->name = "VIA"; r->get = pirq_via586_get; @@ -647,28 +653,27 @@ static __init int via_router_probe(struct irq_router *r, static __init int vlsi_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) { - switch(device) - { - case PCI_DEVICE_ID_VLSI_82C534: - r->name = "VLSI 82C534"; - r->get = pirq_vlsi_get; - r->set = pirq_vlsi_set; - return 1; + switch (device) { + case PCI_DEVICE_ID_VLSI_82C534: + r->name = "VLSI 82C534"; + r->get = pirq_vlsi_get; + r->set = pirq_vlsi_set; + return 1; } return 0; } -static __init int serverworks_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) +static __init int serverworks_router_probe(struct irq_router *r, + struct pci_dev *router, u16 device) { - switch(device) - { - case PCI_DEVICE_ID_SERVERWORKS_OSB4: - case PCI_DEVICE_ID_SERVERWORKS_CSB5: - r->name = "ServerWorks"; - r->get = pirq_serverworks_get; - r->set = pirq_serverworks_set; - return 1; + switch (device) { + case PCI_DEVICE_ID_SERVERWORKS_OSB4: + case PCI_DEVICE_ID_SERVERWORKS_CSB5: + r->name = "ServerWorks"; + r->get = pirq_serverworks_get; + r->set = pirq_serverworks_set; + return 1; } return 0; } @@ -677,7 +682,7 @@ static __init int sis_router_probe(struct irq_router *r, struct pci_dev *router, { if (device != PCI_DEVICE_ID_SI_503) return 0; - + r->name = "SIS"; r->get = pirq_sis_get; r->set = pirq_sis_set; @@ -686,47 +691,43 @@ static __init int sis_router_probe(struct irq_router *r, struct pci_dev *router, static __init int cyrix_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) { - switch(device) - { - case PCI_DEVICE_ID_CYRIX_5520: - r->name = "NatSemi"; - r->get = pirq_cyrix_get; - r->set = pirq_cyrix_set; - return 1; + switch (device) { + case PCI_DEVICE_ID_CYRIX_5520: + r->name = "NatSemi"; + r->get = pirq_cyrix_get; + r->set = pirq_cyrix_set; + return 1; } return 0; } static __init int opti_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) { - switch(device) - { - case PCI_DEVICE_ID_OPTI_82C700: - r->name = "OPTI"; - r->get = pirq_opti_get; - r->set = pirq_opti_set; - return 1; + switch (device) { + case PCI_DEVICE_ID_OPTI_82C700: + r->name = "OPTI"; + r->get = pirq_opti_get; + r->set = pirq_opti_set; + return 1; } return 0; } static __init int ite_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) { - switch(device) - { - case PCI_DEVICE_ID_ITE_IT8330G_0: - r->name = "ITE"; - r->get = pirq_ite_get; - r->set = pirq_ite_set; - return 1; + switch (device) { + case PCI_DEVICE_ID_ITE_IT8330G_0: + r->name = "ITE"; + r->get = pirq_ite_get; + r->set = pirq_ite_set; + return 1; } return 0; } static __init int ali_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) { - switch(device) - { + switch (device) { case PCI_DEVICE_ID_AL_M1533: case PCI_DEVICE_ID_AL_M1563: printk(KERN_DEBUG "PCI: Using ALI IRQ Router\n"); @@ -740,25 +741,24 @@ static __init int ali_router_probe(struct irq_router *r, struct pci_dev *router, static __init int amd_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) { - switch(device) - { - case PCI_DEVICE_ID_AMD_VIPER_740B: - r->name = "AMD756"; - break; - case PCI_DEVICE_ID_AMD_VIPER_7413: - r->name = "AMD766"; - break; - case PCI_DEVICE_ID_AMD_VIPER_7443: - r->name = "AMD768"; - break; - default: - return 0; + switch (device) { + case PCI_DEVICE_ID_AMD_VIPER_740B: + r->name = "AMD756"; + break; + case PCI_DEVICE_ID_AMD_VIPER_7413: + r->name = "AMD766"; + break; + case PCI_DEVICE_ID_AMD_VIPER_7443: + r->name = "AMD768"; + break; + default: + return 0; } r->get = pirq_amd756_get; r->set = pirq_amd756_set; return 1; } - + static __init int pico_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) { switch (device) { @@ -800,7 +800,7 @@ static struct pci_dev *pirq_router_dev; * FIXME: should we have an option to say "generic for * chipset" ? */ - + static void __init pirq_find_router(struct irq_router *r) { struct irq_routing_table *rt = pirq_table; @@ -819,7 +819,7 @@ static void __init pirq_find_router(struct irq_router *r) r->name = "default"; r->get = NULL; r->set = NULL; - + DBG(KERN_DEBUG "PCI: Attempting to find IRQ router for %04x:%04x\n", rt->rtr_vendor, rt->rtr_device); @@ -830,12 +830,14 @@ static void __init pirq_find_router(struct irq_router *r) return; } - for( h = pirq_routers; h->vendor; h++) { + for (h = pirq_routers; h->vendor; h++) { /* First look for a router match */ - if (rt->rtr_vendor == h->vendor && h->probe(r, pirq_router_dev, rt->rtr_device)) + if (rt->rtr_vendor == h->vendor && + h->probe(r, pirq_router_dev, rt->rtr_device)) break; /* Fall back to a device match */ - if (pirq_router_dev->vendor == h->vendor && h->probe(r, pirq_router_dev, pirq_router_dev->device)) + if (pirq_router_dev->vendor == h->vendor && + h->probe(r, pirq_router_dev, pirq_router_dev->device)) break; } printk(KERN_INFO "PCI: Using IRQ router %s [%04x/%04x] at %s\n", @@ -850,11 +852,13 @@ static void __init pirq_find_router(struct irq_router *r) static struct irq_info *pirq_get_info(struct pci_dev *dev) { struct irq_routing_table *rt = pirq_table; - int entries = (rt->size - sizeof(struct irq_routing_table)) / sizeof(struct irq_info); + int entries = (rt->size - sizeof(struct irq_routing_table)) / + sizeof(struct irq_info); struct irq_info *info; for (info = rt->slots; entries--; info++) - if (info->bus == dev->bus->number && PCI_SLOT(info->devfn) == PCI_SLOT(dev->devfn)) + if (info->bus == dev->bus->number && + PCI_SLOT(info->devfn) == PCI_SLOT(dev->devfn)) return info; return NULL; } @@ -882,7 +886,7 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) if (!pirq_table) return 0; - + DBG(KERN_DEBUG "IRQ for %s[%c]", pci_name(dev), 'A' + pin); info = pirq_get_info(dev); if (!info) { @@ -895,7 +899,8 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) DBG(" -> not routed\n" KERN_DEBUG); return 0; } - DBG(" -> PIRQ %02x, mask %04x, excl %04x", pirq, mask, pirq_table->exclusive_irqs); + DBG(" -> PIRQ %02x, mask %04x, excl %04x", pirq, mask, + pirq_table->exclusive_irqs); mask &= pcibios_irq_mask; /* Work around broken HP Pavilion Notebooks which assign USB to @@ -908,7 +913,8 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) } /* same for Acer Travelmate 360, but with CB and irq 11 -> 10 */ - if (acer_tm360_irqrouting && dev->irq == 11 && dev->vendor == PCI_VENDOR_ID_O2) { + if (acer_tm360_irqrouting && dev->irq == 11 && + dev->vendor == PCI_VENDOR_ID_O2) { pirq = 0x68; mask = 0x400; dev->irq = r->get(pirq_router_dev, dev, pirq); @@ -921,17 +927,20 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) */ newirq = dev->irq; if (newirq && !((1 << newirq) & mask)) { - if ( pci_probe & PCI_USE_PIRQ_MASK) newirq = 0; - else printk("\n" KERN_WARNING - "PCI: IRQ %i for device %s doesn't match PIRQ mask " - "- try pci=usepirqmask\n" KERN_DEBUG, newirq, - pci_name(dev)); + if (pci_probe & PCI_USE_PIRQ_MASK) + newirq = 0; + else + printk("\n" KERN_WARNING + "PCI: IRQ %i for device %s doesn't match PIRQ mask - try pci=usepirqmask\n" + KERN_DEBUG, newirq, + pci_name(dev)); } if (!newirq && assign) { for (i = 0; i < 16; i++) { if (!(mask & (1 << i))) continue; - if (pirq_penalty[i] < pirq_penalty[newirq] && can_request_irq(i, IRQF_SHARED)) + if (pirq_penalty[i] < pirq_penalty[newirq] && + can_request_irq(i, IRQF_SHARED)) newirq = i; } } @@ -942,12 +951,13 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) irq = pirq & 0xf; DBG(" -> hardcoded IRQ %d\n", irq); msg = "Hardcoded"; - } else if ( r->get && (irq = r->get(pirq_router_dev, dev, pirq)) && \ - ((!(pci_probe & PCI_USE_PIRQ_MASK)) || ((1 << irq) & mask)) ) { + } else if (r->get && (irq = r->get(pirq_router_dev, dev, pirq)) && \ + ((!(pci_probe & PCI_USE_PIRQ_MASK)) || ((1 << irq) & mask))) { DBG(" -> got IRQ %d\n", irq); msg = "Found"; eisa_set_level_irq(irq); - } else if (newirq && r->set && (dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) { + } else if (newirq && r->set && + (dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) { DBG(" -> assigning IRQ %d", newirq); if (r->set(pirq_router_dev, dev, pirq, newirq)) { eisa_set_level_irq(newirq); @@ -965,7 +975,8 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) } else return 0; } - printk(KERN_INFO "PCI: %s IRQ %d for device %s\n", msg, irq, pci_name(dev)); + printk(KERN_INFO "PCI: %s IRQ %d for device %s\n", msg, irq, + pci_name(dev)); /* Update IRQ for all devices with the same pirq value */ while ((dev2 = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev2)) != NULL) { @@ -977,20 +988,25 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) if (!info) continue; if (info->irq[pin].link == pirq) { - /* We refuse to override the dev->irq information. Give a warning! */ - if ( dev2->irq && dev2->irq != irq && \ + /* + * We refuse to override the dev->irq + * information. Give a warning! + */ + if (dev2->irq && dev2->irq != irq && \ (!(pci_probe & PCI_USE_PIRQ_MASK) || \ - ((1 << dev2->irq) & mask)) ) { + ((1 << dev2->irq) & mask))) { #ifndef CONFIG_PCI_MSI - printk(KERN_INFO "IRQ routing conflict for %s, have irq %d, want irq %d\n", + printk(KERN_INFO "IRQ routing conflict for %s, have irq %d, want irq %d\n", pci_name(dev2), dev2->irq, irq); #endif - continue; - } + continue; + } dev2->irq = irq; pirq_penalty[irq]++; if (dev != dev2) - printk(KERN_INFO "PCI: Sharing IRQ %d with %s\n", irq, pci_name(dev2)); + printk(KERN_INFO + "PCI: Sharing IRQ %d with %s\n", + irq, pci_name(dev2)); } } return 1; @@ -1004,15 +1020,21 @@ static void __init pcibios_fixup_irqs(void) DBG(KERN_DEBUG "PCI: IRQ fixup\n"); while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { /* - * If the BIOS has set an out of range IRQ number, just ignore it. - * Also keep track of which IRQ's are already in use. + * If the BIOS has set an out of range IRQ number, just + * ignore it. Also keep track of which IRQ's are + * already in use. */ if (dev->irq >= 16) { - DBG(KERN_DEBUG "%s: ignoring bogus IRQ %d\n", pci_name(dev), dev->irq); + DBG(KERN_DEBUG "%s: ignoring bogus IRQ %d\n", + pci_name(dev), dev->irq); dev->irq = 0; } - /* If the IRQ is already assigned to a PCI device, ignore its ISA use penalty */ - if (pirq_penalty[dev->irq] >= 100 && pirq_penalty[dev->irq] < 100000) + /* + * If the IRQ is already assigned to a PCI device, + * ignore its ISA use penalty + */ + if (pirq_penalty[dev->irq] >= 100 && + pirq_penalty[dev->irq] < 100000) pirq_penalty[dev->irq] = 0; pirq_penalty[dev->irq]++; } @@ -1024,13 +1046,17 @@ static void __init pcibios_fixup_irqs(void) /* * Recalculate IRQ numbers if we use the I/O APIC. */ - if (io_apic_assign_pci_irqs) - { + if (io_apic_assign_pci_irqs) { int irq; if (pin) { - pin--; /* interrupt pins are numbered starting from 1 */ - irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, PCI_SLOT(dev->devfn), pin); + /* + * interrupt pins are numbered starting + * from 1 + */ + pin--; + irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, + PCI_SLOT(dev->devfn), pin); /* * Busses behind bridges are typically not listed in the MP-table. * In this case we have to look up the IRQ based on the parent bus, @@ -1038,10 +1064,10 @@ static void __init pcibios_fixup_irqs(void) * busses itself so we should get into this branch reliably. */ if (irq < 0 && dev->bus->parent) { /* go back to the bridge */ - struct pci_dev * bridge = dev->bus->self; + struct pci_dev *bridge = dev->bus->self; pin = (pin + PCI_SLOT(dev->devfn)) % 4; - irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number, + irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number, PCI_SLOT(bridge->devfn), pin); if (irq >= 0) printk(KERN_WARNING "PCI: using PPB %s[%c] to get irq %d\n", @@ -1071,7 +1097,8 @@ static int __init fix_broken_hp_bios_irq9(const struct dmi_system_id *d) { if (!broken_hp_bios_irq9) { broken_hp_bios_irq9 = 1; - printk(KERN_INFO "%s detected - fixing broken IRQ routing\n", d->ident); + printk(KERN_INFO "%s detected - fixing broken IRQ routing\n", + d->ident); } return 0; } @@ -1084,7 +1111,8 @@ static int __init fix_acer_tm360_irqrouting(const struct dmi_system_id *d) { if (!acer_tm360_irqrouting) { acer_tm360_irqrouting = 1; - printk(KERN_INFO "%s detected - fixing broken IRQ routing\n", d->ident); + printk(KERN_INFO "%s detected - fixing broken IRQ routing\n", + d->ident); } return 0; } @@ -1096,7 +1124,8 @@ static struct dmi_system_id __initdata pciirq_dmi_table[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), DMI_MATCH(DMI_BIOS_VERSION, "GE.M1.03"), - DMI_MATCH(DMI_PRODUCT_VERSION, "HP Pavilion Notebook Model GE"), + DMI_MATCH(DMI_PRODUCT_VERSION, + "HP Pavilion Notebook Model GE"), DMI_MATCH(DMI_BOARD_VERSION, "OmniBook N32N-736"), }, }, @@ -1111,7 +1140,7 @@ static struct dmi_system_id __initdata pciirq_dmi_table[] = { { } }; -static int __init pcibios_irq_init(void) +int __init pcibios_irq_init(void) { DBG(KERN_DEBUG "PCI: IRQ init\n"); @@ -1131,11 +1160,14 @@ static int __init pcibios_irq_init(void) pirq_find_router(&pirq_router); if (pirq_table->exclusive_irqs) { int i; - for (i=0; i<16; i++) + for (i = 0; i < 16; i++) if (!(pirq_table->exclusive_irqs & (1 << i))) pirq_penalty[i] += 100; } - /* If we're using the I/O APIC, avoid using the PCI IRQ routing table */ + /* + * If we're using the I/O APIC, avoid using the PCI IRQ + * routing table + */ if (io_apic_assign_pci_irqs) pirq_table = NULL; } @@ -1146,9 +1178,6 @@ static int __init pcibios_irq_init(void) return 0; } -subsys_initcall(pcibios_irq_init); - - static void pirq_penalize_isa_irq(int irq, int active) { /* @@ -1182,7 +1211,7 @@ static int pirq_enable_irq(struct pci_dev *dev) if (pin && !pcibios_lookup_irq(dev, 1) && !dev->irq) { char *msg = ""; - pin--; /* interrupt pins are numbered starting from 1 */ + pin--; /* interrupt pins are numbered starting from 1 */ if (io_apic_assign_pci_irqs) { int irq; @@ -1196,19 +1225,22 @@ static int pirq_enable_irq(struct pci_dev *dev) */ temp_dev = dev; while (irq < 0 && dev->bus->parent) { /* go back to the bridge */ - struct pci_dev * bridge = dev->bus->self; + struct pci_dev *bridge = dev->bus->self; pin = (pin + PCI_SLOT(dev->devfn)) % 4; - irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number, + irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number, PCI_SLOT(bridge->devfn), pin); if (irq >= 0) - printk(KERN_WARNING "PCI: using PPB %s[%c] to get irq %d\n", - pci_name(bridge), 'A' + pin, irq); + printk(KERN_WARNING + "PCI: using PPB %s[%c] to get irq %d\n", + pci_name(bridge), + 'A' + pin, irq); dev = bridge; } dev = temp_dev; if (irq >= 0) { - printk(KERN_INFO "PCI->APIC IRQ transform: %s[%c] -> IRQ %d\n", + printk(KERN_INFO + "PCI->APIC IRQ transform: %s[%c] -> IRQ %d\n", pci_name(dev), 'A' + pin, irq); dev->irq = irq; return 0; @@ -1219,12 +1251,17 @@ static int pirq_enable_irq(struct pci_dev *dev) else msg = " Please try using pci=biosirq."; - /* With IDE legacy devices the IRQ lookup failure is not a problem.. */ - if (dev->class >> 8 == PCI_CLASS_STORAGE_IDE && !(dev->class & 0x5)) + /* + * With IDE legacy devices the IRQ lookup failure is not + * a problem.. + */ + if (dev->class >> 8 == PCI_CLASS_STORAGE_IDE && + !(dev->class & 0x5)) return 0; - printk(KERN_WARNING "PCI: No IRQ known for interrupt pin %c of device %s.%s\n", - 'A' + pin, pci_name(dev), msg); + printk(KERN_WARNING + "PCI: No IRQ known for interrupt pin %c of device %s.%s\n", + 'A' + pin, pci_name(dev), msg); } return 0; } diff --git a/arch/x86/pci/legacy.c b/arch/x86/pci/legacy.c index a67921ce60af..132876cc6fca 100644 --- a/arch/x86/pci/legacy.c +++ b/arch/x86/pci/legacy.c @@ -55,4 +55,18 @@ static int __init pci_legacy_init(void) return 0; } -subsys_initcall(pci_legacy_init); +int __init pci_subsys_init(void) +{ +#ifdef CONFIG_ACPI + pci_acpi_init(); +#endif + pci_legacy_init(); + pcibios_irq_init(); +#ifdef CONFIG_X86_NUMAQ + pci_numa_init(); +#endif + pcibios_init(); + + return 0; +} +subsys_initcall(pci_subsys_init); diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 0cfebecf2a8f..23faaa890ffc 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -374,7 +374,7 @@ reject: static int __initdata known_bridge; -void __init __pci_mmcfg_init(int early) +static void __init __pci_mmcfg_init(int early) { /* MMCONFIG disabled */ if ((pci_probe & PCI_PROBE_MMCONF) == 0) diff --git a/arch/x86/pci/mp_bus_to_node.c b/arch/x86/pci/mp_bus_to_node.c deleted file mode 100644 index 022943999b84..000000000000 --- a/arch/x86/pci/mp_bus_to_node.c +++ /dev/null @@ -1,23 +0,0 @@ -#include <linux/pci.h> -#include <linux/init.h> -#include <linux/topology.h> - -#define BUS_NR 256 - -static unsigned char mp_bus_to_node[BUS_NR]; - -void set_mp_bus_to_node(int busnum, int node) -{ - if (busnum >= 0 && busnum < BUS_NR) - mp_bus_to_node[busnum] = (unsigned char) node; -} - -int get_mp_bus_to_node(int busnum) -{ - int node; - - if (busnum < 0 || busnum > (BUS_NR - 1)) - return 0; - node = mp_bus_to_node[busnum]; - return node; -} diff --git a/arch/x86/pci/numa.c b/arch/x86/pci/numa.c index d9afbae5092b..8b5ca1966731 100644 --- a/arch/x86/pci/numa.c +++ b/arch/x86/pci/numa.c @@ -6,45 +6,21 @@ #include <linux/init.h> #include <linux/nodemask.h> #include <mach_apic.h> +#include <asm/mpspec.h> #include "pci.h" #define XQUAD_PORTIO_BASE 0xfe400000 #define XQUAD_PORTIO_QUAD 0x40000 /* 256k per quad. */ -int mp_bus_id_to_node[MAX_MP_BUSSES]; #define BUS2QUAD(global) (mp_bus_id_to_node[global]) -int mp_bus_id_to_local[MAX_MP_BUSSES]; #define BUS2LOCAL(global) (mp_bus_id_to_local[global]) -void mpc_oem_bus_info(struct mpc_config_bus *m, char *name, - struct mpc_config_translation *translation) -{ - int quad = translation->trans_quad; - int local = translation->trans_local; - - mp_bus_id_to_node[m->mpc_busid] = quad; - mp_bus_id_to_local[m->mpc_busid] = local; - printk(KERN_INFO "Bus #%d is %s (node %d)\n", - m->mpc_busid, name, quad); -} - -int quad_local_to_mp_bus_id [NR_CPUS/4][4]; #define QUADLOCAL2BUS(quad,local) (quad_local_to_mp_bus_id[quad][local]) -void mpc_oem_pci_bus(struct mpc_config_bus *m, - struct mpc_config_translation *translation) -{ - int quad = translation->trans_quad; - int local = translation->trans_local; - - quad_local_to_mp_bus_id[quad][local] = m->mpc_busid; -} /* Where the IO area was mapped on multiquad, always 0 otherwise */ void *xquad_portio; -#ifdef CONFIG_X86_NUMAQ EXPORT_SYMBOL(xquad_portio); -#endif #define XQUAD_PORT_ADDR(port, quad) (xquad_portio + (XQUAD_PORTIO_QUAD*quad) + port) @@ -175,10 +151,13 @@ static void __devinit pci_fixup_i450nx(struct pci_dev *d) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82451NX, pci_fixup_i450nx); -static int __init pci_numa_init(void) +int __init pci_numa_init(void) { int quad; + if (!found_numaq) + return 0; + raw_pci_ops = &pci_direct_conf1_mq; if (pcibios_scanned++) @@ -197,5 +176,3 @@ static int __init pci_numa_init(void) } return 0; } - -subsys_initcall(pci_numa_init); diff --git a/arch/x86/pci/olpc.c b/arch/x86/pci/olpc.c index 5e7636558c02..e11e9e803d5f 100644 --- a/arch/x86/pci/olpc.c +++ b/arch/x86/pci/olpc.c @@ -302,12 +302,13 @@ static struct pci_raw_ops pci_olpc_conf = { .write = pci_olpc_write, }; -void __init pci_olpc_init(void) +int __init pci_olpc_init(void) { if (!machine_is_olpc() || olpc_has_vsa()) - return; + return -ENODEV; printk(KERN_INFO "PCI: Using configuration type OLPC\n"); raw_pci_ops = &pci_olpc_conf; is_lx = is_geode_lx(); + return 0; } diff --git a/arch/x86/pci/pci.h b/arch/x86/pci/pci.h index f3972b12c60a..3e25deb821ac 100644 --- a/arch/x86/pci/pci.h +++ b/arch/x86/pci/pci.h @@ -27,6 +27,8 @@ #define PCI_CAN_SKIP_ISA_ALIGN 0x8000 #define PCI_USE__CRS 0x10000 #define PCI_CHECK_ENABLE_AMD_MMCONF 0x20000 +#define PCI_HAS_IO_ECS 0x40000 +#define PCI_NOASSIGN_ROMS 0x80000 extern unsigned int pci_probe; extern unsigned long pirq_table_addr; @@ -38,9 +40,6 @@ enum pci_bf_sort_state { pci_dmi_bf, }; -extern void __init dmi_check_pciprobe(void); -extern void __init dmi_check_skip_isa_align(void); - /* pci-i386.c */ extern unsigned int pcibios_max_latency; @@ -98,10 +97,19 @@ extern struct pci_raw_ops *raw_pci_ext_ops; extern struct pci_raw_ops pci_direct_conf1; +/* arch_initcall level */ extern int pci_direct_probe(void); extern void pci_direct_init(int type); extern void pci_pcbios_init(void); -extern void pci_olpc_init(void); +extern int pci_olpc_init(void); +extern void __init dmi_check_pciprobe(void); +extern void __init dmi_check_skip_isa_align(void); + +/* some common used subsys_initcalls */ +extern int __init pci_acpi_init(void); +extern int __init pcibios_irq_init(void); +extern int __init pci_numa_init(void); +extern int __init pcibios_init(void); /* pci-mmconfig.c */ diff --git a/arch/x86/pci/visws.c b/arch/x86/pci/visws.c index c2df4e97eed6..1a7bed492bb1 100644 --- a/arch/x86/pci/visws.c +++ b/arch/x86/pci/visws.c @@ -8,18 +8,19 @@ #include <linux/pci.h> #include <linux/init.h> -#include "cobalt.h" -#include "lithium.h" +#include <asm/setup.h> +#include <asm/visws/cobalt.h> +#include <asm/visws/lithium.h> #include "pci.h" static int pci_visws_enable_irq(struct pci_dev *dev) { return 0; } static void pci_visws_disable_irq(struct pci_dev *dev) { } -int (*pcibios_enable_irq)(struct pci_dev *dev) = &pci_visws_enable_irq; -void (*pcibios_disable_irq)(struct pci_dev *dev) = &pci_visws_disable_irq; +/* int (*pcibios_enable_irq)(struct pci_dev *dev) = &pci_visws_enable_irq; */ +/* void (*pcibios_disable_irq)(struct pci_dev *dev) = &pci_visws_disable_irq; */ -void __init pcibios_penalize_isa_irq(int irq, int active) {} +/* void __init pcibios_penalize_isa_irq(int irq, int active) {} */ unsigned int pci_bus0, pci_bus1; @@ -85,7 +86,7 @@ void __init pcibios_update_irq(struct pci_dev *dev, int irq) pci_write_config_byte(dev, PCI_INTERRUPT_LINE, irq); } -static int __init pcibios_init(void) +static int __init pci_visws_init(void) { /* The VISWS supports configuration access type 1 only */ pci_probe = (pci_probe | PCI_PROBE_CONF1) & @@ -105,4 +106,17 @@ static int __init pcibios_init(void) return 0; } -subsys_initcall(pcibios_init); +static __init int pci_subsys_init(void) +{ + if (!is_visws_box()) + return -1; + + pcibios_enable_irq = &pci_visws_enable_irq; + pcibios_disable_irq = &pci_visws_disable_irq; + + pci_visws_init(); + pcibios_init(); + + return 0; +} +subsys_initcall(pci_subsys_init); diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index b542355e0e34..6dd000dd7933 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -83,7 +83,7 @@ static int set_up_temporary_mappings(void) /* Set up the direct mapping from scratch */ start = (unsigned long)pfn_to_kaddr(0); - end = (unsigned long)pfn_to_kaddr(end_pfn); + end = (unsigned long)pfn_to_kaddr(max_pfn); for (; start < end; start = next) { pud_t *pud = (pud_t *)get_safe_page(GFP_ATOMIC); diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index efa2ba7c6005..1ef0f90813d6 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -23,7 +23,7 @@ #define gtod vdso_vsyscall_gtod_data -static long vdso_fallback_gettime(long clock, struct timespec *ts) +notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { long ret; asm("syscall" : "=a" (ret) : @@ -31,7 +31,7 @@ static long vdso_fallback_gettime(long clock, struct timespec *ts) return ret; } -static inline long vgetns(void) +notrace static inline long vgetns(void) { long v; cycles_t (*vread)(void); @@ -40,7 +40,7 @@ static inline long vgetns(void) return (v * gtod->clock.mult) >> gtod->clock.shift; } -static noinline int do_realtime(struct timespec *ts) +notrace static noinline int do_realtime(struct timespec *ts) { unsigned long seq, ns; do { @@ -54,7 +54,8 @@ static noinline int do_realtime(struct timespec *ts) } /* Copy of the version in kernel/time.c which we cannot directly access */ -static void vset_normalized_timespec(struct timespec *ts, long sec, long nsec) +notrace static void +vset_normalized_timespec(struct timespec *ts, long sec, long nsec) { while (nsec >= NSEC_PER_SEC) { nsec -= NSEC_PER_SEC; @@ -68,7 +69,7 @@ static void vset_normalized_timespec(struct timespec *ts, long sec, long nsec) ts->tv_nsec = nsec; } -static noinline int do_monotonic(struct timespec *ts) +notrace static noinline int do_monotonic(struct timespec *ts) { unsigned long seq, ns, secs; do { @@ -82,7 +83,7 @@ static noinline int do_monotonic(struct timespec *ts) return 0; } -int __vdso_clock_gettime(clockid_t clock, struct timespec *ts) +notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts) { if (likely(gtod->sysctl_enabled && gtod->clock.vread)) switch (clock) { @@ -96,7 +97,7 @@ int __vdso_clock_gettime(clockid_t clock, struct timespec *ts) int clock_gettime(clockid_t, struct timespec *) __attribute__((weak, alias("__vdso_clock_gettime"))); -int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) +notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) { long ret; if (likely(gtod->sysctl_enabled && gtod->clock.vread)) { diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c index cf058fecfcee..0bce5429a515 100644 --- a/arch/x86/vdso/vdso32-setup.c +++ b/arch/x86/vdso/vdso32-setup.c @@ -203,20 +203,11 @@ static struct page *vdso32_pages[1]; #ifdef CONFIG_X86_64 -static int use_sysenter __read_mostly = -1; - -#define vdso32_sysenter() (use_sysenter > 0) +#define vdso32_sysenter() (boot_cpu_has(X86_FEATURE_SYSENTER32)) /* May not be __init: called during resume */ void syscall32_cpu_init(void) { - if (use_sysenter < 0) { - if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) - use_sysenter = 1; - if (boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR) - use_sysenter = 1; - } - /* Load these always in case some future AMD CPU supports SYSENTER from compat mode too. */ checking_wrmsrl(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); diff --git a/arch/x86/vdso/vgetcpu.c b/arch/x86/vdso/vgetcpu.c index c8097f17f8a9..9fbc6b20026b 100644 --- a/arch/x86/vdso/vgetcpu.c +++ b/arch/x86/vdso/vgetcpu.c @@ -13,7 +13,8 @@ #include <asm/vgtod.h> #include "vextern.h" -long __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused) +notrace long +__vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused) { unsigned int p; diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c index 3fdd51497a83..19a6cfaf5db9 100644 --- a/arch/x86/vdso/vma.c +++ b/arch/x86/vdso/vma.c @@ -16,7 +16,7 @@ #include "vextern.h" /* Just for VMAGIC. */ #undef VEXTERN -int vdso_enabled = 1; +unsigned int __read_mostly vdso_enabled = 1; extern char vdso_start[], vdso_end[]; extern unsigned short vdso_sync_cpuid; diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 2e641be2737e..c2cc99580871 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -5,9 +5,20 @@ config XEN bool "Xen guest support" select PARAVIRT + select PARAVIRT_CLOCK depends on X86_32 - depends on X86_CMPXCHG && X86_TSC && !(X86_VISWS || X86_VOYAGER) + depends on X86_CMPXCHG && X86_TSC && X86_PAE && !(X86_VISWS || X86_VOYAGER) help This is the Linux Xen port. Enabling this will allow the kernel to boot in a paravirtualized environment under the Xen hypervisor. + +config XEN_MAX_DOMAIN_MEMORY + int "Maximum allowed size of a domain in gigabytes" + default 8 + depends on XEN + help + The pseudo-physical to machine address array is sized + according to the maximum possible memory size of a Xen + domain. This array uses 1 page per gigabyte, so there's no + need to be too stingy here.
\ No newline at end of file diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 3d8df981d5fd..2ba2d1649131 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -1,4 +1,4 @@ obj-y := enlighten.o setup.o multicalls.o mmu.o \ - time.o manage.o xen-asm.o grant-table.o + time.o xen-asm.o grant-table.o suspend.o obj-$(CONFIG_SMP) += smp.o diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index c8a56e457d61..bb508456ef52 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -45,6 +45,7 @@ #include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/reboot.h> +#include <asm/pgalloc.h> #include "xen-ops.h" #include "mmu.h" @@ -75,13 +76,13 @@ DEFINE_PER_CPU(unsigned long, xen_current_cr3); /* actual vcpu cr3 */ struct start_info *xen_start_info; EXPORT_SYMBOL_GPL(xen_start_info); -static /* __initdata */ struct shared_info dummy_shared_info; +struct shared_info xen_dummy_shared_info; /* * Point at some empty memory to start with. We map the real shared_info * page as soon as fixmap is up and running. */ -struct shared_info *HYPERVISOR_shared_info = (void *)&dummy_shared_info; +struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info; /* * Flag to determine whether vcpu info placement is available on all @@ -98,13 +99,13 @@ struct shared_info *HYPERVISOR_shared_info = (void *)&dummy_shared_info; */ static int have_vcpu_info_placement = 1; -static void __init xen_vcpu_setup(int cpu) +static void xen_vcpu_setup(int cpu) { struct vcpu_register_vcpu_info info; int err; struct vcpu_info *vcpup; - BUG_ON(HYPERVISOR_shared_info == &dummy_shared_info); + BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info); per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; if (!have_vcpu_info_placement) @@ -136,11 +137,41 @@ static void __init xen_vcpu_setup(int cpu) } } +/* + * On restore, set the vcpu placement up again. + * If it fails, then we're in a bad state, since + * we can't back out from using it... + */ +void xen_vcpu_restore(void) +{ + if (have_vcpu_info_placement) { + int cpu; + + for_each_online_cpu(cpu) { + bool other_cpu = (cpu != smp_processor_id()); + + if (other_cpu && + HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL)) + BUG(); + + xen_vcpu_setup(cpu); + + if (other_cpu && + HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL)) + BUG(); + } + + BUG_ON(!have_vcpu_info_placement); + } +} + static void __init xen_banner(void) { printk(KERN_INFO "Booting paravirtualized kernel on %s\n", pv_info.name); - printk(KERN_INFO "Hypervisor signature: %s\n", xen_start_info->magic); + printk(KERN_INFO "Hypervisor signature: %s%s\n", + xen_start_info->magic, + xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : ""); } static void xen_cpuid(unsigned int *ax, unsigned int *bx, @@ -235,13 +266,13 @@ static void xen_irq_enable(void) { struct vcpu_info *vcpu; - /* There's a one instruction preempt window here. We need to - make sure we're don't switch CPUs between getting the vcpu - pointer and updating the mask. */ - preempt_disable(); + /* We don't need to worry about being preempted here, since + either a) interrupts are disabled, so no preemption, or b) + the caller is confused and is trying to re-enable interrupts + on an indeterminate processor. */ + vcpu = x86_read_percpu(xen_vcpu); vcpu->evtchn_upcall_mask = 0; - preempt_enable_no_resched(); /* Doesn't matter if we get preempted here, because any pending event will get dealt with anyway. */ @@ -254,7 +285,7 @@ static void xen_irq_enable(void) static void xen_safe_halt(void) { /* Blocking includes an implicit local_irq_enable(). */ - if (HYPERVISOR_sched_op(SCHEDOP_block, 0) != 0) + if (HYPERVISOR_sched_op(SCHEDOP_block, NULL) != 0) BUG(); } @@ -607,6 +638,30 @@ static void xen_flush_tlb_others(const cpumask_t *cpus, struct mm_struct *mm, xen_mc_issue(PARAVIRT_LAZY_MMU); } +static void xen_clts(void) +{ + struct multicall_space mcs; + + mcs = xen_mc_entry(0); + + MULTI_fpu_taskswitch(mcs.mc, 0); + + xen_mc_issue(PARAVIRT_LAZY_CPU); +} + +static void xen_write_cr0(unsigned long cr0) +{ + struct multicall_space mcs; + + /* Only pay attention to cr0.TS; everything else is + ignored. */ + mcs = xen_mc_entry(0); + + MULTI_fpu_taskswitch(mcs.mc, (cr0 & X86_CR0_TS) != 0); + + xen_mc_issue(PARAVIRT_LAZY_CPU); +} + static void xen_write_cr2(unsigned long cr2) { x86_read_percpu(xen_vcpu)->arch.cr2 = cr2; @@ -624,8 +679,10 @@ static unsigned long xen_read_cr2_direct(void) static void xen_write_cr4(unsigned long cr4) { - /* Just ignore cr4 changes; Xen doesn't allow us to do - anything anyway. */ + cr4 &= ~X86_CR4_PGE; + cr4 &= ~X86_CR4_PSE; + + native_write_cr4(cr4); } static unsigned long xen_read_cr3(void) @@ -785,38 +842,35 @@ static __init void xen_set_pte_init(pte_t *ptep, pte_t pte) static __init void xen_pagetable_setup_start(pgd_t *base) { pgd_t *xen_pgd = (pgd_t *)xen_start_info->pt_base; + int i; /* special set_pte for pagetable initialization */ pv_mmu_ops.set_pte = xen_set_pte_init; init_mm.pgd = base; /* - * copy top-level of Xen-supplied pagetable into place. For - * !PAE we can use this as-is, but for PAE it is a stand-in - * while we copy the pmd pages. + * copy top-level of Xen-supplied pagetable into place. This + * is a stand-in while we copy the pmd pages. */ memcpy(base, xen_pgd, PTRS_PER_PGD * sizeof(pgd_t)); - if (PTRS_PER_PMD > 1) { - int i; - /* - * For PAE, need to allocate new pmds, rather than - * share Xen's, since Xen doesn't like pmd's being - * shared between address spaces. - */ - for (i = 0; i < PTRS_PER_PGD; i++) { - if (pgd_val_ma(xen_pgd[i]) & _PAGE_PRESENT) { - pmd_t *pmd = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE); + /* + * For PAE, need to allocate new pmds, rather than + * share Xen's, since Xen doesn't like pmd's being + * shared between address spaces. + */ + for (i = 0; i < PTRS_PER_PGD; i++) { + if (pgd_val_ma(xen_pgd[i]) & _PAGE_PRESENT) { + pmd_t *pmd = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE); - memcpy(pmd, (void *)pgd_page_vaddr(xen_pgd[i]), - PAGE_SIZE); + memcpy(pmd, (void *)pgd_page_vaddr(xen_pgd[i]), + PAGE_SIZE); - make_lowmem_page_readonly(pmd); + make_lowmem_page_readonly(pmd); - set_pgd(&base[i], __pgd(1 + __pa(pmd))); - } else - pgd_clear(&base[i]); - } + set_pgd(&base[i], __pgd(1 + __pa(pmd))); + } else + pgd_clear(&base[i]); } /* make sure zero_page is mapped RO so we can use it in pagetables */ @@ -834,7 +888,7 @@ static __init void xen_pagetable_setup_start(pgd_t *base) PFN_DOWN(__pa(xen_start_info->pt_base))); } -static __init void setup_shared_info(void) +void xen_setup_shared_info(void) { if (!xen_feature(XENFEAT_auto_translated_physmap)) { unsigned long addr = fix_to_virt(FIX_PARAVIRT_BOOTMAP); @@ -857,6 +911,8 @@ static __init void setup_shared_info(void) /* In UP this is as good a place as any to set up shared info */ xen_setup_vcpu_info_placement(); #endif + + xen_setup_mfn_list_list(); } static __init void xen_pagetable_setup_done(pgd_t *base) @@ -869,25 +925,23 @@ static __init void xen_pagetable_setup_done(pgd_t *base) pv_mmu_ops.release_pmd = xen_release_pmd; pv_mmu_ops.set_pte = xen_set_pte; - setup_shared_info(); + xen_setup_shared_info(); /* Actually pin the pagetable down, but we can't set PG_pinned yet because the page structures don't exist yet. */ - { - unsigned level; + pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(base))); +} -#ifdef CONFIG_X86_PAE - level = MMUEXT_PIN_L3_TABLE; -#else - level = MMUEXT_PIN_L2_TABLE; -#endif +static __init void xen_post_allocator_init(void) +{ + pv_mmu_ops.set_pmd = xen_set_pmd; + pv_mmu_ops.set_pud = xen_set_pud; - pin_pagetable_pfn(level, PFN_DOWN(__pa(base))); - } + xen_mark_init_mm_pinned(); } /* This is called once we have the cpu_possible_map */ -void __init xen_setup_vcpu_info_placement(void) +void xen_setup_vcpu_info_placement(void) { int cpu; @@ -960,6 +1014,33 @@ static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf, return ret; } +static void xen_set_fixmap(unsigned idx, unsigned long phys, pgprot_t prot) +{ + pte_t pte; + + phys >>= PAGE_SHIFT; + + switch (idx) { + case FIX_BTMAP_END ... FIX_BTMAP_BEGIN: +#ifdef CONFIG_X86_F00F_BUG + case FIX_F00F_IDT: +#endif + case FIX_WP_TEST: + case FIX_VDSO: +#ifdef CONFIG_X86_LOCAL_APIC + case FIX_APIC_BASE: /* maps dummy local APIC */ +#endif + pte = pfn_pte(phys, prot); + break; + + default: + pte = mfn_pte(phys, prot); + break; + } + + __native_set_fixmap(idx, pte); +} + static const struct pv_info xen_info __initdata = { .paravirt_enabled = 1, .shared_kernel_pmd = 0, @@ -973,7 +1054,7 @@ static const struct pv_init_ops xen_init_ops __initdata = { .banner = xen_banner, .memory_setup = xen_memory_setup, .arch_setup = xen_arch_setup, - .post_allocator_init = xen_mark_init_mm_pinned, + .post_allocator_init = xen_post_allocator_init, }; static const struct pv_time_ops xen_time_ops __initdata = { @@ -981,7 +1062,7 @@ static const struct pv_time_ops xen_time_ops __initdata = { .set_wallclock = xen_set_wallclock, .get_wallclock = xen_get_wallclock, - .get_cpu_khz = xen_cpu_khz, + .get_tsc_khz = xen_tsc_khz, .sched_clock = xen_sched_clock, }; @@ -991,10 +1072,10 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = { .set_debugreg = xen_set_debugreg, .get_debugreg = xen_get_debugreg, - .clts = native_clts, + .clts = xen_clts, .read_cr0 = native_read_cr0, - .write_cr0 = native_write_cr0, + .write_cr0 = xen_write_cr0, .read_cr4 = native_read_cr4, .read_cr4_safe = native_read_cr4_safe, @@ -1008,7 +1089,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = { .read_pmc = native_read_pmc, .iret = xen_iret, - .irq_enable_syscall_ret = xen_sysexit, + .irq_enable_sysexit = xen_sysexit, .load_tr_desc = paravirt_nop, .set_ldt = xen_set_ldt, @@ -1042,6 +1123,9 @@ static const struct pv_irq_ops xen_irq_ops __initdata = { .irq_enable = xen_irq_enable, .safe_halt = xen_safe_halt, .halt = xen_halt, +#ifdef CONFIG_X86_64 + .adjust_exception_frame = paravirt_nop, +#endif }; static const struct pv_apic_ops xen_apic_ops __initdata = { @@ -1073,6 +1157,9 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = { .pte_update = paravirt_nop, .pte_update_defer = paravirt_nop, + .pgd_alloc = __paravirt_pgd_alloc, + .pgd_free = paravirt_nop, + .alloc_pte = xen_alloc_pte_init, .release_pte = xen_release_pte_init, .alloc_pmd = xen_alloc_pte_init, @@ -1085,24 +1172,26 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = { .set_pte = NULL, /* see xen_pagetable_setup_* */ .set_pte_at = xen_set_pte_at, - .set_pmd = xen_set_pmd, + .set_pmd = xen_set_pmd_hyper, + + .ptep_modify_prot_start = __ptep_modify_prot_start, + .ptep_modify_prot_commit = __ptep_modify_prot_commit, .pte_val = xen_pte_val, + .pte_flags = native_pte_val, .pgd_val = xen_pgd_val, .make_pte = xen_make_pte, .make_pgd = xen_make_pgd, -#ifdef CONFIG_X86_PAE .set_pte_atomic = xen_set_pte_atomic, .set_pte_present = xen_set_pte_at, - .set_pud = xen_set_pud, + .set_pud = xen_set_pud_hyper, .pte_clear = xen_pte_clear, .pmd_clear = xen_pmd_clear, .make_pmd = xen_make_pmd, .pmd_val = xen_pmd_val, -#endif /* PAE */ .activate_mm = xen_activate_mm, .dup_mmap = xen_dup_mmap, @@ -1112,6 +1201,8 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = { .enter = paravirt_enter_lazy_mmu, .leave = xen_leave_lazy, }, + + .set_fixmap = xen_set_fixmap, }; #ifdef CONFIG_SMP @@ -1123,17 +1214,21 @@ static const struct smp_ops xen_smp_ops __initdata = { .smp_send_stop = xen_smp_send_stop, .smp_send_reschedule = xen_smp_send_reschedule, - .smp_call_function_mask = xen_smp_call_function_mask, + + .send_call_func_ipi = xen_smp_send_call_function_ipi, + .send_call_func_single_ipi = xen_smp_send_call_function_single_ipi, }; #endif /* CONFIG_SMP */ static void xen_reboot(int reason) { + struct sched_shutdown r = { .reason = reason }; + #ifdef CONFIG_SMP smp_send_stop(); #endif - if (HYPERVISOR_sched_op(SCHEDOP_shutdown, reason)) + if (HYPERVISOR_sched_op(SCHEDOP_shutdown, &r)) BUG(); } @@ -1188,6 +1283,8 @@ asmlinkage void __init xen_start_kernel(void) BUG_ON(memcmp(xen_start_info->magic, "xen-3", 5) != 0); + xen_setup_features(); + /* Install Xen paravirt ops */ pv_info = xen_info; pv_init_ops = xen_init_ops; @@ -1197,21 +1294,26 @@ asmlinkage void __init xen_start_kernel(void) pv_apic_ops = xen_apic_ops; pv_mmu_ops = xen_mmu_ops; + if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) { + pv_mmu_ops.ptep_modify_prot_start = xen_ptep_modify_prot_start; + pv_mmu_ops.ptep_modify_prot_commit = xen_ptep_modify_prot_commit; + } + machine_ops = xen_machine_ops; #ifdef CONFIG_SMP smp_ops = xen_smp_ops; #endif - xen_setup_features(); - /* Get mfn list */ if (!xen_feature(XENFEAT_auto_translated_physmap)) - phys_to_machine_mapping = (unsigned long *)xen_start_info->mfn_list; + xen_build_dynamic_phys_to_machine(); pgd = (pgd_t *)xen_start_info->pt_base; + init_pg_tables_start = __pa(pgd); init_pg_tables_end = __pa(pgd) + xen_start_info->nr_pt_frames*PAGE_SIZE; + max_pfn_mapped = (init_pg_tables_end + 512*1024) >> PAGE_SHIFT; init_mm.pgd = pgd; /* use the Xen pagetables to start */ @@ -1228,6 +1330,11 @@ asmlinkage void __init xen_start_kernel(void) if (xen_feature(XENFEAT_supervisor_mode_kernel)) pv_info.kernel_rpl = 0; + /* Prevent unwanted bits from being set in PTEs. */ + __supported_pte_mask &= ~_PAGE_GLOBAL; + if (!is_initial_xendomain()) + __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD); + /* set the limit of our address space */ xen_reserve_top(); @@ -1242,9 +1349,12 @@ asmlinkage void __init xen_start_kernel(void) ? __pa(xen_start_info->mod_start) : 0; boot_params.hdr.ramdisk_size = xen_start_info->mod_len; - if (!is_initial_xendomain()) + if (!is_initial_xendomain()) { + add_preferred_console("xenboot", 0, NULL); + add_preferred_console("tty", 0, NULL); add_preferred_console("hvc", 0, NULL); + } /* Start the world */ - start_kernel(); + i386_start_kernel(); } diff --git a/arch/x86/xen/manage.c b/arch/x86/xen/manage.c deleted file mode 100644 index aa7af9e6abc0..000000000000 --- a/arch/x86/xen/manage.c +++ /dev/null @@ -1,143 +0,0 @@ -/* - * Handle extern requests for shutdown, reboot and sysrq - */ -#include <linux/kernel.h> -#include <linux/err.h> -#include <linux/reboot.h> -#include <linux/sysrq.h> - -#include <xen/xenbus.h> - -#define SHUTDOWN_INVALID -1 -#define SHUTDOWN_POWEROFF 0 -#define SHUTDOWN_SUSPEND 2 -/* Code 3 is SHUTDOWN_CRASH, which we don't use because the domain can only - * report a crash, not be instructed to crash! - * HALT is the same as POWEROFF, as far as we're concerned. The tools use - * the distinction when we return the reason code to them. - */ -#define SHUTDOWN_HALT 4 - -/* Ignore multiple shutdown requests. */ -static int shutting_down = SHUTDOWN_INVALID; - -static void shutdown_handler(struct xenbus_watch *watch, - const char **vec, unsigned int len) -{ - char *str; - struct xenbus_transaction xbt; - int err; - - if (shutting_down != SHUTDOWN_INVALID) - return; - - again: - err = xenbus_transaction_start(&xbt); - if (err) - return; - - str = (char *)xenbus_read(xbt, "control", "shutdown", NULL); - /* Ignore read errors and empty reads. */ - if (XENBUS_IS_ERR_READ(str)) { - xenbus_transaction_end(xbt, 1); - return; - } - - xenbus_write(xbt, "control", "shutdown", ""); - - err = xenbus_transaction_end(xbt, 0); - if (err == -EAGAIN) { - kfree(str); - goto again; - } - - if (strcmp(str, "poweroff") == 0 || - strcmp(str, "halt") == 0) - orderly_poweroff(false); - else if (strcmp(str, "reboot") == 0) - ctrl_alt_del(); - else { - printk(KERN_INFO "Ignoring shutdown request: %s\n", str); - shutting_down = SHUTDOWN_INVALID; - } - - kfree(str); -} - -static void sysrq_handler(struct xenbus_watch *watch, const char **vec, - unsigned int len) -{ - char sysrq_key = '\0'; - struct xenbus_transaction xbt; - int err; - - again: - err = xenbus_transaction_start(&xbt); - if (err) - return; - if (!xenbus_scanf(xbt, "control", "sysrq", "%c", &sysrq_key)) { - printk(KERN_ERR "Unable to read sysrq code in " - "control/sysrq\n"); - xenbus_transaction_end(xbt, 1); - return; - } - - if (sysrq_key != '\0') - xenbus_printf(xbt, "control", "sysrq", "%c", '\0'); - - err = xenbus_transaction_end(xbt, 0); - if (err == -EAGAIN) - goto again; - - if (sysrq_key != '\0') - handle_sysrq(sysrq_key, NULL); -} - -static struct xenbus_watch shutdown_watch = { - .node = "control/shutdown", - .callback = shutdown_handler -}; - -static struct xenbus_watch sysrq_watch = { - .node = "control/sysrq", - .callback = sysrq_handler -}; - -static int setup_shutdown_watcher(void) -{ - int err; - - err = register_xenbus_watch(&shutdown_watch); - if (err) { - printk(KERN_ERR "Failed to set shutdown watcher\n"); - return err; - } - - err = register_xenbus_watch(&sysrq_watch); - if (err) { - printk(KERN_ERR "Failed to set sysrq watcher\n"); - return err; - } - - return 0; -} - -static int shutdown_event(struct notifier_block *notifier, - unsigned long event, - void *data) -{ - setup_shutdown_watcher(); - return NOTIFY_DONE; -} - -static int __init setup_shutdown_event(void) -{ - static struct notifier_block xenstore_notifier = { - .notifier_call = shutdown_event - }; - register_xenstore_notifier(&xenstore_notifier); - - return 0; -} - -subsys_initcall(setup_shutdown_event); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 3525ef523a74..ff0aa74afaa1 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -56,6 +56,131 @@ #include "multicalls.h" #include "mmu.h" +#define P2M_ENTRIES_PER_PAGE (PAGE_SIZE / sizeof(unsigned long)) +#define TOP_ENTRIES (MAX_DOMAIN_PAGES / P2M_ENTRIES_PER_PAGE) + +/* Placeholder for holes in the address space */ +static unsigned long p2m_missing[P2M_ENTRIES_PER_PAGE] + __attribute__((section(".data.page_aligned"))) = + { [ 0 ... P2M_ENTRIES_PER_PAGE-1 ] = ~0UL }; + + /* Array of pointers to pages containing p2m entries */ +static unsigned long *p2m_top[TOP_ENTRIES] + __attribute__((section(".data.page_aligned"))) = + { [ 0 ... TOP_ENTRIES - 1] = &p2m_missing[0] }; + +/* Arrays of p2m arrays expressed in mfns used for save/restore */ +static unsigned long p2m_top_mfn[TOP_ENTRIES] + __attribute__((section(".bss.page_aligned"))); + +static unsigned long p2m_top_mfn_list[ + PAGE_ALIGN(TOP_ENTRIES / P2M_ENTRIES_PER_PAGE)] + __attribute__((section(".bss.page_aligned"))); + +static inline unsigned p2m_top_index(unsigned long pfn) +{ + BUG_ON(pfn >= MAX_DOMAIN_PAGES); + return pfn / P2M_ENTRIES_PER_PAGE; +} + +static inline unsigned p2m_index(unsigned long pfn) +{ + return pfn % P2M_ENTRIES_PER_PAGE; +} + +/* Build the parallel p2m_top_mfn structures */ +void xen_setup_mfn_list_list(void) +{ + unsigned pfn, idx; + + for(pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_ENTRIES_PER_PAGE) { + unsigned topidx = p2m_top_index(pfn); + + p2m_top_mfn[topidx] = virt_to_mfn(p2m_top[topidx]); + } + + for(idx = 0; idx < ARRAY_SIZE(p2m_top_mfn_list); idx++) { + unsigned topidx = idx * P2M_ENTRIES_PER_PAGE; + p2m_top_mfn_list[idx] = virt_to_mfn(&p2m_top_mfn[topidx]); + } + + BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info); + + HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = + virt_to_mfn(p2m_top_mfn_list); + HYPERVISOR_shared_info->arch.max_pfn = xen_start_info->nr_pages; +} + +/* Set up p2m_top to point to the domain-builder provided p2m pages */ +void __init xen_build_dynamic_phys_to_machine(void) +{ + unsigned long *mfn_list = (unsigned long *)xen_start_info->mfn_list; + unsigned long max_pfn = min(MAX_DOMAIN_PAGES, xen_start_info->nr_pages); + unsigned pfn; + + for(pfn = 0; pfn < max_pfn; pfn += P2M_ENTRIES_PER_PAGE) { + unsigned topidx = p2m_top_index(pfn); + + p2m_top[topidx] = &mfn_list[pfn]; + } +} + +unsigned long get_phys_to_machine(unsigned long pfn) +{ + unsigned topidx, idx; + + if (unlikely(pfn >= MAX_DOMAIN_PAGES)) + return INVALID_P2M_ENTRY; + + topidx = p2m_top_index(pfn); + idx = p2m_index(pfn); + return p2m_top[topidx][idx]; +} +EXPORT_SYMBOL_GPL(get_phys_to_machine); + +static void alloc_p2m(unsigned long **pp, unsigned long *mfnp) +{ + unsigned long *p; + unsigned i; + + p = (void *)__get_free_page(GFP_KERNEL | __GFP_NOFAIL); + BUG_ON(p == NULL); + + for(i = 0; i < P2M_ENTRIES_PER_PAGE; i++) + p[i] = INVALID_P2M_ENTRY; + + if (cmpxchg(pp, p2m_missing, p) != p2m_missing) + free_page((unsigned long)p); + else + *mfnp = virt_to_mfn(p); +} + +void set_phys_to_machine(unsigned long pfn, unsigned long mfn) +{ + unsigned topidx, idx; + + if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) { + BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); + return; + } + + if (unlikely(pfn >= MAX_DOMAIN_PAGES)) { + BUG_ON(mfn != INVALID_P2M_ENTRY); + return; + } + + topidx = p2m_top_index(pfn); + if (p2m_top[topidx] == p2m_missing) { + /* no need to allocate a page to store an invalid entry */ + if (mfn == INVALID_P2M_ENTRY) + return; + alloc_p2m(&p2m_top[topidx], &p2m_top_mfn[topidx]); + } + + idx = p2m_index(pfn); + p2m_top[topidx][idx] = mfn; +} + xmaddr_t arbitrary_virt_to_machine(unsigned long address) { unsigned int level; @@ -98,24 +223,60 @@ void make_lowmem_page_readwrite(void *vaddr) } -void xen_set_pmd(pmd_t *ptr, pmd_t val) +static bool page_pinned(void *ptr) +{ + struct page *page = virt_to_page(ptr); + + return PagePinned(page); +} + +static void extend_mmu_update(const struct mmu_update *update) { struct multicall_space mcs; struct mmu_update *u; - preempt_disable(); + mcs = xen_mc_extend_args(__HYPERVISOR_mmu_update, sizeof(*u)); + + if (mcs.mc != NULL) + mcs.mc->args[1]++; + else { + mcs = __xen_mc_entry(sizeof(*u)); + MULTI_mmu_update(mcs.mc, mcs.args, 1, NULL, DOMID_SELF); + } - mcs = xen_mc_entry(sizeof(*u)); u = mcs.args; - u->ptr = virt_to_machine(ptr).maddr; - u->val = pmd_val_ma(val); - MULTI_mmu_update(mcs.mc, u, 1, NULL, DOMID_SELF); + *u = *update; +} + +void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val) +{ + struct mmu_update u; + + preempt_disable(); + + xen_mc_batch(); + + u.ptr = virt_to_machine(ptr).maddr; + u.val = pmd_val_ma(val); + extend_mmu_update(&u); xen_mc_issue(PARAVIRT_LAZY_MMU); preempt_enable(); } +void xen_set_pmd(pmd_t *ptr, pmd_t val) +{ + /* If page is not pinned, we can just update the entry + directly */ + if (!page_pinned(ptr)) { + *ptr = val; + return; + } + + xen_set_pmd_hyper(ptr, val); +} + /* * Associate a virtual page frame with a given physical page frame * and protection flags for that frame. @@ -179,68 +340,105 @@ out: preempt_enable(); } -pteval_t xen_pte_val(pte_t pte) +pte_t xen_ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - pteval_t ret = pte.pte; + /* Just return the pte as-is. We preserve the bits on commit */ + return *ptep; +} + +void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ + struct mmu_update u; + + xen_mc_batch(); - if (ret & _PAGE_PRESENT) - ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT; + u.ptr = virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD; + u.val = pte_val_ma(pte); + extend_mmu_update(&u); - return ret; + xen_mc_issue(PARAVIRT_LAZY_MMU); } -pgdval_t xen_pgd_val(pgd_t pgd) +/* Assume pteval_t is equivalent to all the other *val_t types. */ +static pteval_t pte_mfn_to_pfn(pteval_t val) { - pgdval_t ret = pgd.pgd; - if (ret & _PAGE_PRESENT) - ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT; - return ret; + if (val & _PAGE_PRESENT) { + unsigned long mfn = (val & PTE_MASK) >> PAGE_SHIFT; + pteval_t flags = val & ~PTE_MASK; + val = ((pteval_t)mfn_to_pfn(mfn) << PAGE_SHIFT) | flags; + } + + return val; } -pte_t xen_make_pte(pteval_t pte) +static pteval_t pte_pfn_to_mfn(pteval_t val) { - if (pte & _PAGE_PRESENT) { - pte = phys_to_machine(XPADDR(pte)).maddr; - pte &= ~(_PAGE_PCD | _PAGE_PWT); + if (val & _PAGE_PRESENT) { + unsigned long pfn = (val & PTE_MASK) >> PAGE_SHIFT; + pteval_t flags = val & ~PTE_MASK; + val = ((pteval_t)pfn_to_mfn(pfn) << PAGE_SHIFT) | flags; } - return (pte_t){ .pte = pte }; + return val; } -pgd_t xen_make_pgd(pgdval_t pgd) +pteval_t xen_pte_val(pte_t pte) { - if (pgd & _PAGE_PRESENT) - pgd = phys_to_machine(XPADDR(pgd)).maddr; + return pte_mfn_to_pfn(pte.pte); +} - return (pgd_t){ pgd }; +pgdval_t xen_pgd_val(pgd_t pgd) +{ + return pte_mfn_to_pfn(pgd.pgd); +} + +pte_t xen_make_pte(pteval_t pte) +{ + pte = pte_pfn_to_mfn(pte); + return native_make_pte(pte); +} + +pgd_t xen_make_pgd(pgdval_t pgd) +{ + pgd = pte_pfn_to_mfn(pgd); + return native_make_pgd(pgd); } pmdval_t xen_pmd_val(pmd_t pmd) { - pmdval_t ret = native_pmd_val(pmd); - if (ret & _PAGE_PRESENT) - ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT; - return ret; + return pte_mfn_to_pfn(pmd.pmd); } -#ifdef CONFIG_X86_PAE -void xen_set_pud(pud_t *ptr, pud_t val) + +void xen_set_pud_hyper(pud_t *ptr, pud_t val) { - struct multicall_space mcs; - struct mmu_update *u; + struct mmu_update u; preempt_disable(); - mcs = xen_mc_entry(sizeof(*u)); - u = mcs.args; - u->ptr = virt_to_machine(ptr).maddr; - u->val = pud_val_ma(val); - MULTI_mmu_update(mcs.mc, u, 1, NULL, DOMID_SELF); + xen_mc_batch(); + + u.ptr = virt_to_machine(ptr).maddr; + u.val = pud_val_ma(val); + extend_mmu_update(&u); xen_mc_issue(PARAVIRT_LAZY_MMU); preempt_enable(); } +void xen_set_pud(pud_t *ptr, pud_t val) +{ + /* If page is not pinned, we can just update the entry + directly */ + if (!page_pinned(ptr)) { + *ptr = val; + return; + } + + xen_set_pud_hyper(ptr, val); +} + void xen_set_pte(pte_t *ptep, pte_t pte) { ptep->pte_high = pte.pte_high; @@ -262,22 +460,14 @@ void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) void xen_pmd_clear(pmd_t *pmdp) { - xen_set_pmd(pmdp, __pmd(0)); + set_pmd(pmdp, __pmd(0)); } pmd_t xen_make_pmd(pmdval_t pmd) { - if (pmd & _PAGE_PRESENT) - pmd = phys_to_machine(XPADDR(pmd)).maddr; - + pmd = pte_pfn_to_mfn(pmd); return native_make_pmd(pmd); } -#else /* !PAE */ -void xen_set_pte(pte_t *ptep, pte_t pte) -{ - *ptep = pte; -} -#endif /* CONFIG_X86_PAE */ /* (Yet another) pagetable walker. This one is intended for pinning a @@ -430,8 +620,6 @@ static int pin_page(struct page *page, enum pt_level level) read-only, and can be pinned. */ void xen_pgd_pin(pgd_t *pgd) { - unsigned level; - xen_mc_batch(); if (pgd_walk(pgd, pin_page, TASK_SIZE)) { @@ -441,15 +629,31 @@ void xen_pgd_pin(pgd_t *pgd) xen_mc_batch(); } -#ifdef CONFIG_X86_PAE - level = MMUEXT_PIN_L3_TABLE; -#else - level = MMUEXT_PIN_L2_TABLE; -#endif + xen_do_pin(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(pgd))); + xen_mc_issue(0); +} + +/* + * On save, we need to pin all pagetables to make sure they get their + * mfns turned into pfns. Search the list for any unpinned pgds and pin + * them (unpinned pgds are not currently in use, probably because the + * process is under construction or destruction). + */ +void xen_mm_pin_all(void) +{ + unsigned long flags; + struct page *page; - xen_do_pin(level, PFN_DOWN(__pa(pgd))); + spin_lock_irqsave(&pgd_lock, flags); - xen_mc_issue(0); + list_for_each_entry(page, &pgd_list, lru) { + if (!PagePinned(page)) { + xen_pgd_pin((pgd_t *)page_address(page)); + SetPageSavePinned(page); + } + } + + spin_unlock_irqrestore(&pgd_lock, flags); } /* The init_mm pagetable is really pinned as soon as its created, but @@ -509,6 +713,29 @@ static void xen_pgd_unpin(pgd_t *pgd) xen_mc_issue(0); } +/* + * On resume, undo any pinning done at save, so that the rest of the + * kernel doesn't see any unexpected pinned pagetables. + */ +void xen_mm_unpin_all(void) +{ + unsigned long flags; + struct page *page; + + spin_lock_irqsave(&pgd_lock, flags); + + list_for_each_entry(page, &pgd_list, lru) { + if (PageSavePinned(page)) { + BUG_ON(!PagePinned(page)); + printk("unpinning pinned %p\n", page_address(page)); + xen_pgd_unpin((pgd_t *)page_address(page)); + ClearPageSavePinned(page); + } + } + + spin_unlock_irqrestore(&pgd_lock, flags); +} + void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next) { spin_lock(&next->page_table_lock); @@ -569,7 +796,7 @@ static void drop_mm_ref(struct mm_struct *mm) } if (!cpus_empty(mask)) - xen_smp_call_function_mask(mask, drop_other_mm_ref, mm, 1); + smp_call_function_mask(mask, drop_other_mm_ref, mm, 1); } #else static void drop_mm_ref(struct mm_struct *mm) @@ -602,7 +829,7 @@ void xen_exit_mmap(struct mm_struct *mm) spin_lock(&mm->page_table_lock); /* pgd may not be pinned in the error exit path of execve */ - if (PagePinned(virt_to_page(mm->pgd))) + if (page_pinned(mm->pgd)) xen_pgd_unpin(mm->pgd); spin_unlock(&mm->page_table_lock); diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h index b5e189b1519d..297bf9f5b8bc 100644 --- a/arch/x86/xen/mmu.h +++ b/arch/x86/xen/mmu.h @@ -25,10 +25,6 @@ enum pt_level { void set_pte_mfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags); -void xen_set_pte(pte_t *ptep, pte_t pteval); -void xen_set_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pteval); -void xen_set_pmd(pmd_t *pmdp, pmd_t pmdval); void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next); void xen_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm); @@ -37,31 +33,27 @@ void xen_exit_mmap(struct mm_struct *mm); void xen_pgd_pin(pgd_t *pgd); //void xen_pgd_unpin(pgd_t *pgd); -#ifdef CONFIG_X86_PAE -unsigned long long xen_pte_val(pte_t); -unsigned long long xen_pmd_val(pmd_t); -unsigned long long xen_pgd_val(pgd_t); +pteval_t xen_pte_val(pte_t); +pmdval_t xen_pmd_val(pmd_t); +pgdval_t xen_pgd_val(pgd_t); -pte_t xen_make_pte(unsigned long long); -pmd_t xen_make_pmd(unsigned long long); -pgd_t xen_make_pgd(unsigned long long); +pte_t xen_make_pte(pteval_t); +pmd_t xen_make_pmd(pmdval_t); +pgd_t xen_make_pgd(pgdval_t); +void xen_set_pte(pte_t *ptep, pte_t pteval); void xen_set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pteval); void xen_set_pte_atomic(pte_t *ptep, pte_t pte); +void xen_set_pmd(pmd_t *pmdp, pmd_t pmdval); void xen_set_pud(pud_t *ptr, pud_t val); +void xen_set_pmd_hyper(pmd_t *pmdp, pmd_t pmdval); +void xen_set_pud_hyper(pud_t *ptr, pud_t val); void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep); void xen_pmd_clear(pmd_t *pmdp); - -#else -unsigned long xen_pte_val(pte_t); -unsigned long xen_pmd_val(pmd_t); -unsigned long xen_pgd_val(pgd_t); - -pte_t xen_make_pte(unsigned long); -pmd_t xen_make_pmd(unsigned long); -pgd_t xen_make_pgd(unsigned long); -#endif +pte_t xen_ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr, pte_t *ptep); +void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte); #endif /* _XEN_MMU_H */ diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c index 5791eb2e3750..3c63c4da7ed1 100644 --- a/arch/x86/xen/multicalls.c +++ b/arch/x86/xen/multicalls.c @@ -29,14 +29,14 @@ #define MC_DEBUG 1 #define MC_BATCH 32 -#define MC_ARGS (MC_BATCH * 16 / sizeof(u64)) +#define MC_ARGS (MC_BATCH * 16) struct mc_buffer { struct multicall_entry entries[MC_BATCH]; #if MC_DEBUG struct multicall_entry debug[MC_BATCH]; #endif - u64 args[MC_ARGS]; + unsigned char args[MC_ARGS]; struct callback { void (*fn)(void *); void *data; @@ -107,20 +107,48 @@ struct multicall_space __xen_mc_entry(size_t args) { struct mc_buffer *b = &__get_cpu_var(mc_buffer); struct multicall_space ret; - unsigned argspace = (args + sizeof(u64) - 1) / sizeof(u64); + unsigned argidx = roundup(b->argidx, sizeof(u64)); BUG_ON(preemptible()); - BUG_ON(argspace > MC_ARGS); + BUG_ON(b->argidx > MC_ARGS); if (b->mcidx == MC_BATCH || - (b->argidx + argspace) > MC_ARGS) + (argidx + args) > MC_ARGS) { xen_mc_flush(); + argidx = roundup(b->argidx, sizeof(u64)); + } ret.mc = &b->entries[b->mcidx]; b->mcidx++; + ret.args = &b->args[argidx]; + b->argidx = argidx + args; + + BUG_ON(b->argidx > MC_ARGS); + return ret; +} + +struct multicall_space xen_mc_extend_args(unsigned long op, size_t size) +{ + struct mc_buffer *b = &__get_cpu_var(mc_buffer); + struct multicall_space ret = { NULL, NULL }; + + BUG_ON(preemptible()); + BUG_ON(b->argidx > MC_ARGS); + + if (b->mcidx == 0) + return ret; + + if (b->entries[b->mcidx - 1].op != op) + return ret; + + if ((b->argidx + size) > MC_ARGS) + return ret; + + ret.mc = &b->entries[b->mcidx - 1]; ret.args = &b->args[b->argidx]; - b->argidx += argspace; + b->argidx += size; + BUG_ON(b->argidx > MC_ARGS); return ret; } diff --git a/arch/x86/xen/multicalls.h b/arch/x86/xen/multicalls.h index 8bae996d99a3..858938241616 100644 --- a/arch/x86/xen/multicalls.h +++ b/arch/x86/xen/multicalls.h @@ -45,4 +45,16 @@ static inline void xen_mc_issue(unsigned mode) /* Set up a callback to be called when the current batch is flushed */ void xen_mc_callback(void (*fn)(void *), void *data); +/* + * Try to extend the arguments of the previous multicall command. The + * previous command's op must match. If it does, then it attempts to + * extend the argument space allocated to the multicall entry by + * arg_size bytes. + * + * The returned multicall_space will return with mc pointing to the + * command on success, or NULL on failure, and args pointing to the + * newly allocated space. + */ +struct multicall_space xen_mc_extend_args(unsigned long op, size_t arg_size); + #endif /* _XEN_MULTICALLS_H */ diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 82517e4a752a..e0a39595bde3 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -13,9 +13,11 @@ #include <asm/vdso.h> #include <asm/e820.h> #include <asm/setup.h> +#include <asm/acpi.h> #include <asm/xen/hypervisor.h> #include <asm/xen/hypercall.h> +#include <xen/page.h> #include <xen/interface/callback.h> #include <xen/interface/physdev.h> #include <xen/features.h> @@ -27,8 +29,6 @@ extern const char xen_hypervisor_callback[]; extern const char xen_failsafe_callback[]; -unsigned long *phys_to_machine_mapping; -EXPORT_SYMBOL(phys_to_machine_mapping); /** * machine_specific_memory_setup - Hook for machine specific memory setup. @@ -38,9 +38,31 @@ char * __init xen_memory_setup(void) { unsigned long max_pfn = xen_start_info->nr_pages; + max_pfn = min(MAX_DOMAIN_PAGES, max_pfn); + e820.nr_map = 0; - add_memory_region(0, LOWMEMSIZE(), E820_RAM); - add_memory_region(HIGH_MEMORY, PFN_PHYS(max_pfn)-HIGH_MEMORY, E820_RAM); + + e820_add_region(0, PFN_PHYS(max_pfn), E820_RAM); + + /* + * Even though this is normal, usable memory under Xen, reserve + * ISA memory anyway because too many things think they can poke + * about in there. + */ + e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS, + E820_RESERVED); + + /* + * Reserve Xen bits: + * - mfn_list + * - xen_start_info + * See comment above "struct start_info" in <xen/interface/xen.h> + */ + e820_add_region(__pa(xen_start_info->mfn_list), + xen_start_info->pt_base - xen_start_info->mfn_list, + E820_RESERVED); + + sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); return "Xen"; } diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 94e69000f982..233156f39b7f 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -35,28 +35,15 @@ #include "xen-ops.h" #include "mmu.h" -static cpumask_t xen_cpu_initialized_map; -static DEFINE_PER_CPU(int, resched_irq) = -1; -static DEFINE_PER_CPU(int, callfunc_irq) = -1; -static DEFINE_PER_CPU(int, debug_irq) = -1; - -/* - * Structure and data for smp_call_function(). This is designed to minimise - * static memory requirements. It also looks cleaner. - */ -static DEFINE_SPINLOCK(call_lock); +cpumask_t xen_cpu_initialized_map; -struct call_data_struct { - void (*func) (void *info); - void *info; - atomic_t started; - atomic_t finished; - int wait; -}; +static DEFINE_PER_CPU(int, resched_irq); +static DEFINE_PER_CPU(int, callfunc_irq); +static DEFINE_PER_CPU(int, callfuncsingle_irq); +static DEFINE_PER_CPU(int, debug_irq) = -1; static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id); - -static struct call_data_struct *call_data; +static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id); /* * Reschedule call back. Nothing to do, @@ -65,6 +52,12 @@ static struct call_data_struct *call_data; */ static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id) { +#ifdef CONFIG_X86_32 + __get_cpu_var(irq_stat).irq_resched_count++; +#else + add_pda(irq_resched_count, 1); +#endif + return IRQ_HANDLED; } @@ -122,6 +115,17 @@ static int xen_smp_intr_init(unsigned int cpu) goto fail; per_cpu(debug_irq, cpu) = rc; + callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu); + rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR, + cpu, + xen_call_function_single_interrupt, + IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING, + callfunc_name, + NULL); + if (rc < 0) + goto fail; + per_cpu(callfuncsingle_irq, cpu) = rc; + return 0; fail: @@ -131,6 +135,9 @@ static int xen_smp_intr_init(unsigned int cpu) unbind_from_irqhandler(per_cpu(callfunc_irq, cpu), NULL); if (per_cpu(debug_irq, cpu) >= 0) unbind_from_irqhandler(per_cpu(debug_irq, cpu), NULL); + if (per_cpu(callfuncsingle_irq, cpu) >= 0) + unbind_from_irqhandler(per_cpu(callfuncsingle_irq, cpu), NULL); + return rc; } @@ -330,7 +337,7 @@ static void stop_self(void *v) void xen_smp_send_stop(void) { - smp_call_function(stop_self, NULL, 0, 0); + smp_call_function(stop_self, NULL, 0); } void xen_smp_send_reschedule(int cpu) @@ -338,7 +345,6 @@ void xen_smp_send_reschedule(int cpu) xen_send_IPI_one(cpu, XEN_RESCHEDULE_VECTOR); } - static void xen_send_IPI_mask(cpumask_t mask, enum ipi_vector vector) { unsigned cpu; @@ -349,83 +355,42 @@ static void xen_send_IPI_mask(cpumask_t mask, enum ipi_vector vector) xen_send_IPI_one(cpu, vector); } +void xen_smp_send_call_function_ipi(cpumask_t mask) +{ + int cpu; + + xen_send_IPI_mask(mask, XEN_CALL_FUNCTION_VECTOR); + + /* Make sure other vcpus get a chance to run if they need to. */ + for_each_cpu_mask(cpu, mask) { + if (xen_vcpu_stolen(cpu)) { + HYPERVISOR_sched_op(SCHEDOP_yield, 0); + break; + } + } +} + +void xen_smp_send_call_function_single_ipi(int cpu) +{ + xen_send_IPI_mask(cpumask_of_cpu(cpu), XEN_CALL_FUNCTION_SINGLE_VECTOR); +} + static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id) { - void (*func) (void *info) = call_data->func; - void *info = call_data->info; - int wait = call_data->wait; - - /* - * Notify initiating CPU that I've grabbed the data and am - * about to execute the function - */ - mb(); - atomic_inc(&call_data->started); - /* - * At this point the info structure may be out of scope unless wait==1 - */ irq_enter(); - (*func)(info); + generic_smp_call_function_interrupt(); __get_cpu_var(irq_stat).irq_call_count++; irq_exit(); - if (wait) { - mb(); /* commit everything before setting finished */ - atomic_inc(&call_data->finished); - } - return IRQ_HANDLED; } -int xen_smp_call_function_mask(cpumask_t mask, void (*func)(void *), - void *info, int wait) +static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id) { - struct call_data_struct data; - int cpus, cpu; - bool yield; - - /* Holding any lock stops cpus from going down. */ - spin_lock(&call_lock); - - cpu_clear(smp_processor_id(), mask); - - cpus = cpus_weight(mask); - if (!cpus) { - spin_unlock(&call_lock); - return 0; - } - - /* Can deadlock when called with interrupts disabled */ - WARN_ON(irqs_disabled()); - - data.func = func; - data.info = info; - atomic_set(&data.started, 0); - data.wait = wait; - if (wait) - atomic_set(&data.finished, 0); - - call_data = &data; - mb(); /* write everything before IPI */ - - /* Send a message to other CPUs and wait for them to respond */ - xen_send_IPI_mask(mask, XEN_CALL_FUNCTION_VECTOR); - - /* Make sure other vcpus get a chance to run if they need to. */ - yield = false; - for_each_cpu_mask(cpu, mask) - if (xen_vcpu_stolen(cpu)) - yield = true; - - if (yield) - HYPERVISOR_sched_op(SCHEDOP_yield, 0); - - /* Wait for response */ - while (atomic_read(&data.started) != cpus || - (wait && atomic_read(&data.finished) != cpus)) - cpu_relax(); - - spin_unlock(&call_lock); + irq_enter(); + generic_smp_call_function_single_interrupt(); + __get_cpu_var(irq_stat).irq_call_count++; + irq_exit(); - return 0; + return IRQ_HANDLED; } diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c new file mode 100644 index 000000000000..251669a932d4 --- /dev/null +++ b/arch/x86/xen/suspend.c @@ -0,0 +1,45 @@ +#include <linux/types.h> + +#include <xen/interface/xen.h> +#include <xen/grant_table.h> +#include <xen/events.h> + +#include <asm/xen/hypercall.h> +#include <asm/xen/page.h> + +#include "xen-ops.h" +#include "mmu.h" + +void xen_pre_suspend(void) +{ + xen_start_info->store_mfn = mfn_to_pfn(xen_start_info->store_mfn); + xen_start_info->console.domU.mfn = + mfn_to_pfn(xen_start_info->console.domU.mfn); + + BUG_ON(!irqs_disabled()); + + HYPERVISOR_shared_info = &xen_dummy_shared_info; + if (HYPERVISOR_update_va_mapping(fix_to_virt(FIX_PARAVIRT_BOOTMAP), + __pte_ma(0), 0)) + BUG(); +} + +void xen_post_suspend(int suspend_cancelled) +{ + xen_setup_shared_info(); + + if (suspend_cancelled) { + xen_start_info->store_mfn = + pfn_to_mfn(xen_start_info->store_mfn); + xen_start_info->console.domU.mfn = + pfn_to_mfn(xen_start_info->console.domU.mfn); + } else { +#ifdef CONFIG_SMP + xen_cpu_initialized_map = cpu_online_map; +#endif + xen_vcpu_restore(); + xen_timer_resume(); + } + +} + diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index c39e1a5aa241..685b77470fc3 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -12,7 +12,9 @@ #include <linux/clocksource.h> #include <linux/clockchips.h> #include <linux/kernel_stat.h> +#include <linux/math64.h> +#include <asm/pvclock.h> #include <asm/xen/hypervisor.h> #include <asm/xen/hypercall.h> @@ -30,17 +32,6 @@ static cycle_t xen_clocksource_read(void); -/* These are perodically updated in shared_info, and then copied here. */ -struct shadow_time_info { - u64 tsc_timestamp; /* TSC at last update of time vals. */ - u64 system_timestamp; /* Time, in nanosecs, since boot. */ - u32 tsc_to_nsec_mul; - int tsc_shift; - u32 version; -}; - -static DEFINE_PER_CPU(struct shadow_time_info, shadow_time); - /* runstate info updated by Xen */ static DEFINE_PER_CPU(struct vcpu_runstate_info, runstate); @@ -150,11 +141,7 @@ static void do_stolen_accounting(void) if (stolen < 0) stolen = 0; - ticks = 0; - while (stolen >= NS_PER_TICK) { - ticks++; - stolen -= NS_PER_TICK; - } + ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen); __get_cpu_var(residual_stolen) = stolen; account_steal_time(NULL, ticks); @@ -166,11 +153,7 @@ static void do_stolen_accounting(void) if (blocked < 0) blocked = 0; - ticks = 0; - while (blocked >= NS_PER_TICK) { - ticks++; - blocked -= NS_PER_TICK; - } + ticks = iter_div_u64_rem(blocked, NS_PER_TICK, &blocked); __get_cpu_var(residual_blocked) = blocked; account_steal_time(idle_task(smp_processor_id()), ticks); } @@ -214,11 +197,11 @@ unsigned long long xen_sched_clock(void) } -/* Get the CPU speed from Xen */ -unsigned long xen_cpu_khz(void) +/* Get the TSC speed from Xen */ +unsigned long xen_tsc_khz(void) { u64 xen_khz = 1000000ULL << 32; - const struct vcpu_time_info *info = + const struct pvclock_vcpu_time_info *info = &HYPERVISOR_shared_info->vcpu_info[0].time; do_div(xen_khz, info->tsc_to_system_mul); @@ -230,121 +213,26 @@ unsigned long xen_cpu_khz(void) return xen_khz; } -/* - * Reads a consistent set of time-base values from Xen, into a shadow data - * area. - */ -static unsigned get_time_values_from_xen(void) -{ - struct vcpu_time_info *src; - struct shadow_time_info *dst; - - /* src is shared memory with the hypervisor, so we need to - make sure we get a consistent snapshot, even in the face of - being preempted. */ - src = &__get_cpu_var(xen_vcpu)->time; - dst = &__get_cpu_var(shadow_time); - - do { - dst->version = src->version; - rmb(); /* fetch version before data */ - dst->tsc_timestamp = src->tsc_timestamp; - dst->system_timestamp = src->system_time; - dst->tsc_to_nsec_mul = src->tsc_to_system_mul; - dst->tsc_shift = src->tsc_shift; - rmb(); /* test version after fetching data */ - } while ((src->version & 1) | (dst->version ^ src->version)); - - return dst->version; -} - -/* - * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction, - * yielding a 64-bit result. - */ -static inline u64 scale_delta(u64 delta, u32 mul_frac, int shift) -{ - u64 product; -#ifdef __i386__ - u32 tmp1, tmp2; -#endif - - if (shift < 0) - delta >>= -shift; - else - delta <<= shift; - -#ifdef __i386__ - __asm__ ( - "mul %5 ; " - "mov %4,%%eax ; " - "mov %%edx,%4 ; " - "mul %5 ; " - "xor %5,%5 ; " - "add %4,%%eax ; " - "adc %5,%%edx ; " - : "=A" (product), "=r" (tmp1), "=r" (tmp2) - : "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) ); -#elif __x86_64__ - __asm__ ( - "mul %%rdx ; shrd $32,%%rdx,%%rax" - : "=a" (product) : "0" (delta), "d" ((u64)mul_frac) ); -#else -#error implement me! -#endif - - return product; -} - -static u64 get_nsec_offset(struct shadow_time_info *shadow) -{ - u64 now, delta; - now = native_read_tsc(); - delta = now - shadow->tsc_timestamp; - return scale_delta(delta, shadow->tsc_to_nsec_mul, shadow->tsc_shift); -} - static cycle_t xen_clocksource_read(void) { - struct shadow_time_info *shadow = &get_cpu_var(shadow_time); + struct pvclock_vcpu_time_info *src; cycle_t ret; - unsigned version; - - do { - version = get_time_values_from_xen(); - barrier(); - ret = shadow->system_timestamp + get_nsec_offset(shadow); - barrier(); - } while (version != __get_cpu_var(xen_vcpu)->time.version); - - put_cpu_var(shadow_time); + src = &get_cpu_var(xen_vcpu)->time; + ret = pvclock_clocksource_read(src); + put_cpu_var(xen_vcpu); return ret; } static void xen_read_wallclock(struct timespec *ts) { - const struct shared_info *s = HYPERVISOR_shared_info; - u32 version; - u64 delta; - struct timespec now; - - /* get wallclock at system boot */ - do { - version = s->wc_version; - rmb(); /* fetch version before time */ - now.tv_sec = s->wc_sec; - now.tv_nsec = s->wc_nsec; - rmb(); /* fetch time before checking version */ - } while ((s->wc_version & 1) | (version ^ s->wc_version)); - - delta = xen_clocksource_read(); /* time since system boot */ - delta += now.tv_sec * (u64)NSEC_PER_SEC + now.tv_nsec; - - now.tv_nsec = do_div(delta, NSEC_PER_SEC); - now.tv_sec = delta; + struct shared_info *s = HYPERVISOR_shared_info; + struct pvclock_wall_clock *wall_clock = &(s->wc); + struct pvclock_vcpu_time_info *vcpu_time; - set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); + vcpu_time = &get_cpu_var(xen_vcpu)->time; + pvclock_read_wallclock(wall_clock, vcpu_time, ts); + put_cpu_var(xen_vcpu); } unsigned long xen_get_wallclock(void) @@ -352,7 +240,6 @@ unsigned long xen_get_wallclock(void) struct timespec ts; xen_read_wallclock(&ts); - return ts.tv_sec; } @@ -572,12 +459,23 @@ void xen_setup_cpu_clockevents(void) clockevents_register_device(&__get_cpu_var(xen_clock_events)); } +void xen_timer_resume(void) +{ + int cpu; + + if (xen_clockevent != &xen_vcpuop_clockevent) + return; + + for_each_online_cpu(cpu) { + if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL)) + BUG(); + } +} + __init void xen_time_init(void) { int cpu = smp_processor_id(); - get_time_values_from_xen(); - clocksource_register(&xen_clocksource); if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL) == 0) { diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 288d587ce73c..7c0cf6320a0a 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -7,6 +7,7 @@ #include <linux/init.h> #include <asm/boot.h> #include <xen/interface/elfnote.h> +#include <asm/xen/interface.h> __INIT ENTRY(startup_xen) @@ -17,7 +18,7 @@ ENTRY(startup_xen) __FINIT -.pushsection .bss.page_aligned +.pushsection .text .align PAGE_SIZE_asm ENTRY(hypercall_page) .skip 0x1000 @@ -30,11 +31,11 @@ ENTRY(hypercall_page) ELFNOTE(Xen, XEN_ELFNOTE_ENTRY, .long startup_xen) ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, .long hypercall_page) ELFNOTE(Xen, XEN_ELFNOTE_FEATURES, .asciz "!writable_page_tables|pae_pgdir_above_4gb") -#ifdef CONFIG_X86_PAE ELFNOTE(Xen, XEN_ELFNOTE_PAE_MODE, .asciz "yes") -#else - ELFNOTE(Xen, XEN_ELFNOTE_PAE_MODE, .asciz "no") -#endif ELFNOTE(Xen, XEN_ELFNOTE_LOADER, .asciz "generic") + ELFNOTE(Xen, XEN_ELFNOTE_L1_MFN_VALID, + .quad _PAGE_PRESENT; .quad _PAGE_PRESENT) + ELFNOTE(Xen, XEN_ELFNOTE_SUSPEND_CANCEL, .long 1) + ELFNOTE(Xen, XEN_ELFNOTE_HV_START_LOW, .long __HYPERVISOR_VIRT_START) #endif /*CONFIG_XEN */ diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index f1063ae08037..6f4b1045c1c2 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -9,26 +9,35 @@ extern const char xen_hypervisor_callback[]; extern const char xen_failsafe_callback[]; +struct trap_info; void xen_copy_trap_info(struct trap_info *traps); DECLARE_PER_CPU(unsigned long, xen_cr3); DECLARE_PER_CPU(unsigned long, xen_current_cr3); extern struct start_info *xen_start_info; +extern struct shared_info xen_dummy_shared_info; extern struct shared_info *HYPERVISOR_shared_info; +void xen_setup_mfn_list_list(void); +void xen_setup_shared_info(void); + char * __init xen_memory_setup(void); void __init xen_arch_setup(void); void __init xen_init_IRQ(void); void xen_enable_sysenter(void); +void xen_vcpu_restore(void); + +void __init xen_build_dynamic_phys_to_machine(void); void xen_setup_timer(int cpu); void xen_setup_cpu_clockevents(void); -unsigned long xen_cpu_khz(void); +unsigned long xen_tsc_khz(void); void __init xen_time_init(void); unsigned long xen_get_wallclock(void); int xen_set_wallclock(unsigned long time); unsigned long long xen_sched_clock(void); +void xen_timer_resume(void); irqreturn_t xen_debug_interrupt(int irq, void *dev_id); @@ -46,13 +55,10 @@ void xen_smp_cpus_done(unsigned int max_cpus); void xen_smp_send_stop(void); void xen_smp_send_reschedule(int cpu); -int xen_smp_call_function (void (*func) (void *info), void *info, int nonatomic, - int wait); -int xen_smp_call_function_single(int cpu, void (*func) (void *info), void *info, - int nonatomic, int wait); +void xen_smp_send_call_function_ipi(cpumask_t mask); +void xen_smp_send_call_function_single_ipi(int cpu); -int xen_smp_call_function_mask(cpumask_t mask, void (*func)(void *), - void *info, int wait); +extern cpumask_t xen_cpu_initialized_map; /* Declare an asm function, along with symbols needed to make it |