diff options
Diffstat (limited to 'arch/x86')
299 files changed, 16405 insertions, 11629 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 6c70fed0f9a0..c3f880902d66 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -23,6 +23,19 @@ config X86 select HAVE_KPROBES select HAVE_KRETPROBES select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64) + select HAVE_ARCH_KGDB if !X86_VOYAGER + +config DEFCONFIG_LIST + string + depends on X86_32 + option defconfig_list + default "arch/x86/configs/i386_defconfig" + +config DEFCONFIG_LIST + string + depends on X86_64 + option defconfig_list + default "arch/x86/configs/x86_64_defconfig" config GENERIC_LOCKBREAK @@ -53,9 +66,6 @@ config STACKTRACE_SUPPORT config HAVE_LATENCYTOP_SUPPORT def_bool y -config SEMAPHORE_SLEEPERS - def_bool y - config FAST_CMPXCHG_LOCAL bool default y @@ -88,9 +98,6 @@ config GENERIC_GPIO config ARCH_MAY_HAVE_PC_FDC def_bool y -config DMI - def_bool y - config RWSEM_GENERIC_SPINLOCK def_bool !X86_XADD @@ -116,8 +123,14 @@ config GENERIC_TIME_VSYSCALL config ARCH_HAS_CPU_RELAX def_bool y +config ARCH_HAS_CACHE_LINE_SIZE + def_bool y + config HAVE_SETUP_PER_CPU_AREA - def_bool X86_64 + def_bool X86_64 || (X86_SMP && !X86_VOYAGER) + +config HAVE_CPUMASK_OF_CPU_MAP + def_bool X86_64_SMP config ARCH_HIBERNATION_POSSIBLE def_bool y @@ -141,6 +154,9 @@ config AUDIT_ARCH config ARCH_SUPPORTS_AOUT def_bool y +config ARCH_SUPPORTS_OPTIMIZED_INLINING + def_bool y + # Use the generic interrupt handling code in kernel/irq/: config GENERIC_HARDIRQS bool @@ -171,17 +187,17 @@ config X86_64_SMP config X86_HT bool depends on SMP - depends on (X86_32 && !(X86_VISWS || X86_VOYAGER)) || (X86_64 && !MK8) + depends on (X86_32 && !(X86_VISWS || X86_VOYAGER)) || X86_64 default y config X86_BIOS_REBOOT bool - depends on X86_32 && !(X86_VISWS || X86_VOYAGER) + depends on !X86_VISWS && !X86_VOYAGER default y config X86_TRAMPOLINE bool - depends on X86_SMP || (X86_VOYAGER && SMP) + depends on X86_SMP || (X86_VOYAGER && SMP) || (64BIT && ACPI_SLEEP) default y config KTIME_SCALAR @@ -241,8 +257,7 @@ config X86_ELAN config X86_VOYAGER bool "Voyager (NCR)" - depends on X86_32 - select SMP if !BROKEN + depends on X86_32 && (SMP || BROKEN) help Voyager is an MCA-based 32-way capable SMP architecture proprietary to NCR Corp. Machine classes 345x/35xx/4100/51xx are Voyager-based. @@ -254,9 +269,8 @@ config X86_VOYAGER config X86_NUMAQ bool "NUMAQ (IBM/Sequent)" - select SMP + depends on SMP && X86_32 select NUMA - depends on X86_32 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, @@ -327,8 +341,9 @@ config X86_RDC321X config X86_VSMP bool "Support for ScaleMP vSMP" - depends on X86_64 && PCI - help + select PARAVIRT + depends on X86_64 + 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 if you have one of these machines. @@ -370,6 +385,25 @@ config VMI at the moment), by linking the kernel to a GPL-ed ROM module provided by the hypervisor. +config KVM_CLOCK + bool "KVM paravirtualized clock" + select PARAVIRT + depends on !(X86_VISWS || 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 + (or probably other) emulation by the underlying device model, the host + provides the guest with timing infrastructure such as time of day, and + system time + +config KVM_GUEST + bool "KVM Guest support" + select PARAVIRT + depends on !(X86_VISWS || X86_VOYAGER) + help + This option enables various optimizations for running under the KVM + hypervisor. + source "arch/x86/lguest/Kconfig" config PARAVIRT @@ -383,6 +417,35 @@ config PARAVIRT endif +config MEMTEST_BOOTPARAM + bool "Memtest boot parameter" + 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) @@ -431,6 +494,15 @@ config HPET_EMULATE_RTC # Mark as embedded because too many people got it wrong. # The code disables itself when not needed. +config DMI + default y + bool "Enable DMI scanning" if EMBEDDED + help + Enabled scanning of DMI to identify machine quirks. Say Y + here unless you have verified that your setup is not + affected by entries in the DMI blacklist. Required by PNP + BIOS code. + config GART_IOMMU bool "GART IOMMU support" if EMBEDDED default y @@ -477,9 +549,6 @@ config CALGARY_IOMMU_ENABLED_BY_DEFAULT Calgary anyway, pass 'iommu=calgary' on the kernel command line. If unsure, say Y. -config IOMMU_HELPER - def_bool (CALGARY_IOMMU || GART_IOMMU) - # need this always selected by IOMMU for the VIA workaround config SWIOTLB bool @@ -490,6 +559,8 @@ config SWIOTLB access 32-bits of memory can be used on systems with more than 3 GB of memory. If unsure, say Y. +config IOMMU_HELPER + def_bool (CALGARY_IOMMU || GART_IOMMU || SWIOTLB) config NR_CPUS int "Maximum number of CPUs (2-255)" @@ -507,7 +578,7 @@ config NR_CPUS config SCHED_SMT bool "SMT (Hyperthreading) scheduler support" - depends on (X86_64 && SMP) || (X86_32 && X86_HT) + depends on X86_HT help SMT scheduler support improves the CPU scheduler's decision making when dealing with Intel Pentium 4 chips with HyperThreading at a @@ -517,7 +588,7 @@ config SCHED_SMT config SCHED_MC def_bool y prompt "Multi-core scheduler support" - depends on (X86_64 && SMP) || (X86_32 && X86_HT) + depends on X86_HT help Multi-core scheduler support improves the CPU scheduler's decision making when dealing with multi-core CPU chips at a cost of slightly @@ -877,6 +948,15 @@ config X86_64_ACPI_NUMA help Enable ACPI SRAT based node topology detection. +# Some NUMA nodes have memory ranges that span +# other nodes. Even though a pfn is valid and +# between a node's start and end pfns, it may not +# reside on that node. See memmap_init_zone() +# for details. +config NODES_SPAN_OTHER_NODES + def_bool y + depends on X86_64_ACPI_NUMA + config NUMA_EMU bool "NUMA emulation" depends on X86_64 && NUMA @@ -886,7 +966,7 @@ config NUMA_EMU number of nodes. This is only useful for debugging. config NODES_SHIFT - int + int "Max num nodes shift(1-15)" range 1 15 if X86_64 default "6" if X86_64 default "4" if X86_NUMAQ @@ -1010,6 +1090,21 @@ config MTRR See <file:Documentation/mtrr.txt> for more information. +config X86_PAT + bool + prompt "x86 PAT support" + depends on MTRR + help + Use PAT attributes to setup page level cache control. + + PATs are the modern equivalents of MTRRs and are much more + flexible than MTRRs. + + Say N here if you see bootup problems (boot crash, boot hang, + spontaneous reboots) or a non-working video driver. + + If unsure, say Y. + config EFI def_bool n prompt "EFI runtime service support" @@ -1078,6 +1173,7 @@ source kernel/Kconfig.hz config KEXEC bool "kexec system call" + depends on X86_BIOS_REBOOT help kexec is a system call that implements the ability to shutdown your current kernel, and to start another kernel. It is like a reboot @@ -1379,7 +1475,7 @@ endmenu menu "Bus options (PCI etc.)" config PCI - bool "PCI support" if !X86_VISWS + bool "PCI support" if !X86_VISWS && !X86_VSMP depends on !X86_VOYAGER default y select ARCH_SUPPORTS_MSI if (X86_LOCAL_APIC && X86_IO_APIC) @@ -1420,6 +1516,10 @@ config PCI_GODIRECT config PCI_GOANY bool "Any" +config PCI_GOOLPC + bool "OLPC" + depends on OLPC + endchoice config PCI_BIOS @@ -1429,12 +1529,17 @@ config PCI_BIOS # 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) || X86_VISWS) + depends on PCI && (X86_64 || (PCI_GODIRECT || PCI_GOANY || PCI_GOOLPC) || X86_VISWS) 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 + config PCI_DOMAINS def_bool y depends on PCI @@ -1554,6 +1659,13 @@ config GEODE_MFGPT_TIMER MFGPTs have a better resolution and max interval than the generic PIT, and are suitable for use as high-res timers. +config OLPC + bool "One Laptop Per Child support" + default n + help + Add support for detecting the unique features of the OLPC + XO hardware. + endif # X86_32 config K8_NB diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 9304bfba7d45..2ad6301849a1 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -21,8 +21,8 @@ config M386 Here are the settings recommended for greatest speed: - "386" for the AMD/Cyrix/Intel 386DX/DXL/SL/SLC/SX, Cyrix/TI - 486DLC/DLC2, UMC 486SX-S and NexGen Nx586. Only "386" kernels - will run on a 386 class machine. + 486DLC/DLC2, and UMC 486SX-S. Only "386" kernels will run on a 386 + class machine. - "486" for the AMD/Cyrix/IBM/Intel 486DX/DX2/DX4 or SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or U5S. - "586" for generic Pentium CPUs lacking the TSC @@ -292,6 +292,11 @@ config X86_GENERIC endif +config X86_CPU + def_bool y + select GENERIC_FIND_FIRST_BIT + select GENERIC_FIND_NEXT_BIT + # # Define implied options from the CPU selection here config X86_L1_CACHE_BYTES @@ -388,7 +393,7 @@ config X86_OOSTORE # config X86_P6_NOP def_bool y - depends on (X86_64 || !X86_GENERIC) && (M686 || MPENTIUMII || MPENTIUMIII || MPENTIUMM || MCORE2 || MPENTIUM4) + depends on (X86_64 || !X86_GENERIC) && (M686 || MPENTIUMII || MPENTIUMIII || MPENTIUMM || MCORE2 || MPENTIUM4 || MPSC) config X86_TSC def_bool y @@ -398,7 +403,7 @@ config X86_TSC # generates cmov. config X86_CMOV def_bool y - depends on (MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7) + depends on (MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || X86_64) config X86_MINIMUM_CPU_FAMILY int diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 702eb39901ca..ac1e31ba4795 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -5,6 +5,17 @@ config TRACE_IRQFLAGS_SUPPORT source "lib/Kconfig.debug" +config NONPROMISC_DEVMEM + bool "Disable promiscuous /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. + config EARLY_PRINTK bool "Early printk" if EMBEDDED default y @@ -54,6 +65,18 @@ config DEBUG_PER_CPU_MAPS Say N if unsure. +config X86_PTDUMP + bool "Export kernel pagetable layout to userspace via debugfs" + depends on DEBUG_KERNEL + select DEBUG_FS + help + Say Y here if you want to show the kernel pagetable layout in a + debugfs file. This information is only useful for kernel developers + who are working in architecture specific areas of the kernel. + It is probably not a good idea to enable this feature in a production + kernel. + If in doubt, say "N" + config DEBUG_RODATA bool "Write protect kernel read-only data structures" default y @@ -64,6 +87,18 @@ config DEBUG_RODATA data. This is recommended so that we can catch kernel bugs sooner. If in doubt, say "Y". +config DIRECT_GBPAGES + bool "Enable gbpages-mapped kernel pagetables" + depends on DEBUG_KERNEL && EXPERIMENTAL && X86_64 + help + Enable gigabyte pages support (if the CPU supports it). This can + improve the kernel's performance a tiny bit by reducing TLB + pressure. + + This is experimental code. + + If in doubt, say "N". + config DEBUG_RODATA_TEST bool "Testcase for the DEBUG_RODATA feature" depends on DEBUG_RODATA @@ -82,7 +117,6 @@ config DEBUG_NX_TEST config 4KSTACKS bool "Use 4Kb for kernel stacks instead of 8Kb" - depends on DEBUG_KERNEL depends on X86_32 help If you say Y here the kernel will use a 4Kb stacksize for the @@ -221,4 +255,18 @@ config CPA_DEBUG help Do change_page_attr() self-tests every 30 seconds. +config OPTIMIZE_INLINING + bool "Allow gcc to uninline functions marked 'inline'" + depends on BROKEN + help + This option determines if the kernel forces gcc to inline the functions + developers have marked 'inline'. Doing so takes away freedom from gcc to + do what it thinks is best, which is desirable for the gcc 3.x series of + compilers. The gcc 4.x series have a rewritten inlining algorithm and + disabling this option will generate a smaller kernel there. Hopefully + this algorithm is so good that allowing gcc4 to make the decision can + become the default in the future, until then this option is there to + test gcc for this. + endmenu + diff --git a/arch/x86/Makefile b/arch/x86/Makefile index f1e739a43d41..3cff3c894cf3 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -151,7 +151,6 @@ mflags-y += -Iinclude/asm-x86/mach-default # 64 bit does not support subarch support - clear sub arch variables fcore-$(CONFIG_X86_64) := mcore-$(CONFIG_X86_64) := -mflags-$(CONFIG_X86_64) := KBUILD_CFLAGS += $(mflags-y) KBUILD_AFLAGS += $(mflags-y) @@ -159,9 +158,9 @@ KBUILD_AFLAGS += $(mflags-y) ### # Kernel objects -head-y := arch/x86/kernel/head_$(BITS).o -head-$(CONFIG_X86_64) += arch/x86/kernel/head64.o -head-y += arch/x86/kernel/init_task.o +head-y := arch/x86/kernel/head_$(BITS).o +head-y += arch/x86/kernel/head$(BITS).o +head-y += arch/x86/kernel/init_task.o libs-y += arch/x86/lib/ diff --git a/arch/x86/boot/.gitignore b/arch/x86/boot/.gitignore index b1bdc4c6f9f2..172cf8a98bdd 100644 --- a/arch/x86/boot/.gitignore +++ b/arch/x86/boot/.gitignore @@ -1,7 +1,8 @@ bootsect bzImage +cpustr.h +mkcpustr +offsets.h setup setup.bin setup.elf -cpustr.h -mkcpustr diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index f88458e83ef0..7ee102f9c4f8 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -30,7 +30,7 @@ subdir- := compressed setup-y += a20.o cmdline.o copy.o cpu.o cpucheck.o edd.o setup-y += header.o main.o mca.o memory.o pm.o pmjump.o -setup-y += printf.o string.o tty.o video.o version.o +setup-y += printf.o string.o tty.o video.o video-mode.o version.o setup-$(CONFIG_X86_APM_BOOT) += apm.o setup-$(CONFIG_X86_VOYAGER) += voyager.o @@ -94,6 +94,20 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE SETUP_OBJS = $(addprefix $(obj)/,$(setup-y)) +sed-offsets := -e 's/^00*/0/' \ + -e 's/^\([0-9a-fA-F]*\) . \(input_data\|input_data_end\)$$/\#define \2 0x\1/p' + +quiet_cmd_offsets = OFFSETS $@ + cmd_offsets = $(NM) $< | sed -n $(sed-offsets) > $@ + +$(obj)/offsets.h: $(obj)/compressed/vmlinux FORCE + $(call if_changed,offsets) + +targets += offsets.h + +AFLAGS_header.o += -I$(obj) +$(obj)/header.o: $(obj)/offsets.h + LDFLAGS_setup.elf := -T $(obj)/setup.elf: $(src)/setup.ld $(SETUP_OBJS) FORCE $(call if_changed,ld) diff --git a/arch/x86/boot/a20.c b/arch/x86/boot/a20.c index 31348d054fca..90943f83e84d 100644 --- a/arch/x86/boot/a20.c +++ b/arch/x86/boot/a20.c @@ -9,8 +9,6 @@ * ----------------------------------------------------------------------- */ /* - * arch/i386/boot/a20.c - * * Enable A20 gate (return -1 on failure) */ diff --git a/arch/x86/boot/apm.c b/arch/x86/boot/apm.c index c117c7fb859c..7aa6033001f9 100644 --- a/arch/x86/boot/apm.c +++ b/arch/x86/boot/apm.c @@ -12,8 +12,6 @@ * ----------------------------------------------------------------------- */ /* - * arch/i386/boot/apm.c - * * Get APM BIOS information */ diff --git a/arch/x86/boot/bitops.h b/arch/x86/boot/bitops.h index 8dcc8dc7db88..878e4b9940d9 100644 --- a/arch/x86/boot/bitops.h +++ b/arch/x86/boot/bitops.h @@ -9,8 +9,6 @@ * ----------------------------------------------------------------------- */ /* - * arch/i386/boot/bitops.h - * * Very simple bitops for the boot code. */ diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index 7822a4983da2..a34b9982c7cb 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -9,8 +9,6 @@ * ----------------------------------------------------------------------- */ /* - * arch/i386/boot/boot.h - * * Header file for the real-mode kernel code */ @@ -286,6 +284,11 @@ int getchar_timeout(void); /* video.c */ void set_video(void); +/* video-mode.c */ +int set_mode(u16 mode); +int mode_defined(u16 mode); +void probe_cards(int unsafe); + /* video-vesa.c */ void vesa_store_edid(void); diff --git a/arch/x86/boot/cmdline.c b/arch/x86/boot/cmdline.c index 680408a0f463..a1d35634bce0 100644 --- a/arch/x86/boot/cmdline.c +++ b/arch/x86/boot/cmdline.c @@ -9,8 +9,6 @@ * ----------------------------------------------------------------------- */ /* - * arch/i386/boot/cmdline.c - * * Simple command-line parser for early boot. */ diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index d2b9f3bb87c0..92fdd35bd93e 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -22,7 +22,7 @@ $(obj)/vmlinux: $(src)/vmlinux_$(BITS).lds $(obj)/head_$(BITS).o $(obj)/misc.o $ $(call if_changed,ld) @: -OBJCOPYFLAGS_vmlinux.bin := -O binary -R .note -R .comment -S +OBJCOPYFLAGS_vmlinux.bin := -R .comment -S $(obj)/vmlinux.bin: vmlinux FORCE $(call if_changed,objcopy) diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 036e635f18a3..ba7736cf2ec7 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -130,7 +130,7 @@ relocated: /* * Setup the stack for the decompressor */ - leal stack_end(%ebx), %esp + leal boot_stack_end(%ebx), %esp /* * Do the decompression, and jump to the new kernel.. @@ -142,8 +142,8 @@ relocated: pushl %eax # input_len leal input_data(%ebx), %eax pushl %eax # input_data - leal _end(%ebx), %eax - pushl %eax # end of the image as third argument + leal boot_heap(%ebx), %eax + pushl %eax # heap area as third argument pushl %esi # real mode pointer as second arg call decompress_kernel addl $20, %esp @@ -181,7 +181,10 @@ relocated: jmp *%ebp .bss +/* Stack and heap for uncompression */ .balign 4 -stack: - .fill 4096, 1, 0 -stack_end: +boot_heap: + .fill BOOT_HEAP_SIZE, 1, 0 +boot_stack: + .fill BOOT_STACK_SIZE, 1, 0 +boot_stack_end: diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index e8657b98c902..d8819efac81d 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -28,6 +28,7 @@ #include <asm/segment.h> #include <asm/pgtable.h> #include <asm/page.h> +#include <asm/boot.h> #include <asm/msr.h> #include <asm/asm-offsets.h> @@ -62,7 +63,7 @@ startup_32: subl $1b, %ebp /* setup a stack and make sure cpu supports long mode. */ - movl $user_stack_end, %eax + movl $boot_stack_end, %eax addl %ebp, %eax movl %eax, %esp @@ -243,9 +244,9 @@ ENTRY(startup_64) /* Copy the compressed kernel to the end of our buffer * where decompression in place becomes safe. */ - leaq _end(%rip), %r8 - leaq _end(%rbx), %r9 - movq $_end /* - $startup_32 */, %rcx + leaq _end_before_pgt(%rip), %r8 + leaq _end_before_pgt(%rbx), %r9 + movq $_end_before_pgt /* - $startup_32 */, %rcx 1: subq $8, %r8 subq $8, %r9 movq 0(%r8), %rax @@ -267,14 +268,14 @@ relocated: */ xorq %rax, %rax leaq _edata(%rbx), %rdi - leaq _end(%rbx), %rcx + leaq _end_before_pgt(%rbx), %rcx subq %rdi, %rcx cld rep stosb /* Setup the stack */ - leaq user_stack_end(%rip), %rsp + leaq boot_stack_end(%rip), %rsp /* zero EFLAGS after setting rsp */ pushq $0 @@ -285,7 +286,7 @@ relocated: */ pushq %rsi # Save the real mode argument movq %rsi, %rdi # real mode address - leaq _heap(%rip), %rsi # _heap + leaq boot_heap(%rip), %rsi # malloc area for uncompression leaq input_data(%rip), %rdx # input_data movl input_len(%rip), %eax movq %rax, %rcx # input_len @@ -310,9 +311,12 @@ gdt: .quad 0x0080890000000000 /* TS descriptor */ .quad 0x0000000000000000 /* TS continued */ gdt_end: - .bss -/* Stack for uncompression */ - .balign 4 -user_stack: - .fill 4096,4,0 -user_stack_end: + +.bss +/* Stack and heap for uncompression */ +.balign 4 +boot_heap: + .fill BOOT_HEAP_SIZE, 1, 0 +boot_stack: + .fill BOOT_STACK_SIZE, 1, 0 +boot_stack_end: diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 8182e32c1b42..90456cee47c3 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -15,6 +15,10 @@ * we just keep it from happening */ #undef CONFIG_PARAVIRT +#ifdef CONFIG_X86_32 +#define _ASM_DESC_H_ 1 +#endif + #ifdef CONFIG_X86_64 #define _LINUX_STRING_H_ 1 #define __LINUX_BITMAP_H 1 @@ -22,6 +26,7 @@ #include <linux/linkage.h> #include <linux/screen_info.h> +#include <linux/elf.h> #include <asm/io.h> #include <asm/page.h> #include <asm/boot.h> @@ -53,8 +58,8 @@ * 1 bit (last block flag) * 2 bits (block type) * - * 1 block occurs every 32K -1 bytes or when there 50% compression has been achieved. - * The smallest block type encoding is always used. + * 1 block occurs every 32K -1 bytes or when there 50% compression + * has been achieved. The smallest block type encoding is always used. * * stored: * 32 bits length in bytes. @@ -90,9 +95,9 @@ * * All of which is enough to compute an amount of extra data that is required * to be safe. To avoid problems at the block level allocating 5 extra bytes - * per 32767 bytes of data is sufficient. To avoind problems internal to a block - * adding an extra 32767 bytes (the worst case uncompressed block size) is - * sufficient, to ensure that in the worst case the decompressed data for + * per 32767 bytes of data is sufficient. To avoind problems internal to a + * block adding an extra 32767 bytes (the worst case uncompressed block size) + * is sufficient, to ensure that in the worst case the decompressed data for * block will stop the byte before the compressed data for a block begins. * To avoid problems with the compressed data's meta information an extra 18 * bytes are needed. Leading to the formula: @@ -111,58 +116,66 @@ * gzip declarations */ -#define OF(args) args -#define STATIC static +#define OF(args) args +#define STATIC static #undef memset #undef memcpy -#define memzero(s, n) memset ((s), 0, (n)) +#define memzero(s, n) memset((s), 0, (n)) -typedef unsigned char uch; -typedef unsigned short ush; -typedef unsigned long ulg; +typedef unsigned char uch; +typedef unsigned short ush; +typedef unsigned long ulg; -#define WSIZE 0x80000000 /* Window size must be at least 32k, - * and a power of two - * We don't actually have a window just - * a huge output buffer so I report - * a 2G windows size, as that should - * always be larger than our output buffer. - */ +/* + * Window size must be at least 32k, and a power of two. + * We don't actually have a window just a huge output buffer, + * so we report a 2G window size, as that should always be + * larger than our output buffer: + */ +#define WSIZE 0x80000000 -static uch *inbuf; /* input buffer */ -static uch *window; /* Sliding window buffer, (and final output buffer) */ +/* Input buffer: */ +static unsigned char *inbuf; -static unsigned insize; /* valid bytes in inbuf */ -static unsigned inptr; /* index of next byte to be processed in inbuf */ -static unsigned outcnt; /* bytes in output buffer */ +/* Sliding window buffer (and final output buffer): */ +static unsigned char *window; + +/* Valid bytes in inbuf: */ +static unsigned insize; + +/* Index of next byte to be processed in inbuf: */ +static unsigned inptr; + +/* Bytes in output buffer: */ +static unsigned outcnt; /* gzip flag byte */ -#define ASCII_FLAG 0x01 /* bit 0 set: file probably ASCII text */ -#define CONTINUATION 0x02 /* bit 1 set: continuation of multi-part gzip file */ -#define EXTRA_FIELD 0x04 /* bit 2 set: extra field present */ -#define ORIG_NAME 0x08 /* bit 3 set: original file name present */ -#define COMMENT 0x10 /* bit 4 set: file comment present */ -#define ENCRYPTED 0x20 /* bit 5 set: file is encrypted */ -#define RESERVED 0xC0 /* bit 6,7: reserved */ - -#define get_byte() (inptr < insize ? inbuf[inptr++] : fill_inbuf()) - +#define ASCII_FLAG 0x01 /* bit 0 set: file probably ASCII text */ +#define CONTINUATION 0x02 /* bit 1 set: continuation of multi-part gz file */ +#define EXTRA_FIELD 0x04 /* bit 2 set: extra field present */ +#define ORIG_NAM 0x08 /* bit 3 set: original file name present */ +#define COMMENT 0x10 /* bit 4 set: file comment present */ +#define ENCRYPTED 0x20 /* bit 5 set: file is encrypted */ +#define RESERVED 0xC0 /* bit 6, 7: reserved */ + +#define get_byte() (inptr < insize ? inbuf[inptr++] : fill_inbuf()) + /* Diagnostic functions */ #ifdef DEBUG -# define Assert(cond,msg) {if(!(cond)) error(msg);} -# define Trace(x) fprintf x -# define Tracev(x) {if (verbose) fprintf x ;} -# define Tracevv(x) {if (verbose>1) fprintf x ;} -# define Tracec(c,x) {if (verbose && (c)) fprintf x ;} -# define Tracecv(c,x) {if (verbose>1 && (c)) fprintf x ;} +# define Assert(cond, msg) do { if (!(cond)) error(msg); } while (0) +# define Trace(x) do { fprintf x; } while (0) +# define Tracev(x) do { if (verbose) fprintf x ; } while (0) +# define Tracevv(x) do { if (verbose > 1) fprintf x ; } while (0) +# define Tracec(c, x) do { if (verbose && (c)) fprintf x ; } while (0) +# define Tracecv(c, x) do { if (verbose > 1 && (c)) fprintf x ; } while (0) #else -# define Assert(cond,msg) +# define Assert(cond, msg) # define Trace(x) # define Tracev(x) # define Tracevv(x) -# define Tracec(c,x) -# define Tracecv(c,x) +# define Tracec(c, x) +# define Tracecv(c, x) #endif static int fill_inbuf(void); @@ -170,7 +183,7 @@ static void flush_window(void); static void error(char *m); static void gzip_mark(void **); static void gzip_release(void **); - + /* * This is set up by the setup-routine at boot-time */ @@ -185,7 +198,7 @@ static unsigned char *real_mode; /* Pointer to real-mode data */ extern unsigned char input_data[]; extern int input_len; -static long bytes_out = 0; +static long bytes_out; static void *malloc(int size); static void free(void *where); @@ -204,13 +217,7 @@ static void putstr(const char *); static memptr free_mem_ptr; static memptr free_mem_end_ptr; -#ifdef CONFIG_X86_64 -#define HEAP_SIZE 0x7000 -#else -#define HEAP_SIZE 0x4000 -#endif - -static char *vidmem = (char *)0xb8000; +static char *vidmem; static int vidport; static int lines, cols; @@ -224,8 +231,10 @@ static void *malloc(int size) { void *p; - if (size <0) error("Malloc error"); - if (free_mem_ptr <= 0) error("Memory error"); + if (size < 0) + error("Malloc error"); + if (free_mem_ptr <= 0) + error("Memory error"); free_mem_ptr = (free_mem_ptr + 3) & ~3; /* Align */ @@ -251,19 +260,19 @@ static void gzip_release(void **ptr) { free_mem_ptr = (memptr) *ptr; } - + static void scroll(void) { int i; - memcpy ( vidmem, vidmem + cols * 2, ( lines - 1 ) * cols * 2 ); - for ( i = ( lines - 1 ) * cols * 2; i < lines * cols * 2; i += 2 ) + memcpy(vidmem, vidmem + cols * 2, (lines - 1) * cols * 2); + for (i = (lines - 1) * cols * 2; i < lines * cols * 2; i += 2) vidmem[i] = ' '; } static void putstr(const char *s) { - int x,y,pos; + int x, y, pos; char c; #ifdef CONFIG_X86_32 @@ -274,18 +283,18 @@ static void putstr(const char *s) x = RM_SCREEN_INFO.orig_x; y = RM_SCREEN_INFO.orig_y; - while ( ( c = *s++ ) != '\0' ) { - if ( c == '\n' ) { + while ((c = *s++) != '\0') { + if (c == '\n') { x = 0; - if ( ++y >= lines ) { + if (++y >= lines) { scroll(); y--; } } else { vidmem [(x + cols * y) * 2] = c; - if ( ++x >= cols ) { + if (++x >= cols) { x = 0; - if ( ++y >= lines ) { + if (++y >= lines) { scroll(); y--; } @@ -303,22 +312,22 @@ static void putstr(const char *s) outb(0xff & (pos >> 1), vidport+1); } -static void* memset(void* s, int c, unsigned n) +static void *memset(void *s, int c, unsigned n) { int i; char *ss = s; - for (i=0;i<n;i++) ss[i] = c; + for (i = 0; i < n; i++) ss[i] = c; return s; } -static void* memcpy(void* dest, const void* src, unsigned n) +static void *memcpy(void *dest, const void *src, unsigned n) { int i; const char *s = src; char *d = dest; - for (i=0;i<n;i++) d[i] = s[i]; + for (i = 0; i < n; i++) d[i] = s[i]; return dest; } @@ -341,9 +350,9 @@ static void flush_window(void) /* With my window equal to my output buffer * I only need to compute the crc here. */ - ulg c = crc; /* temporary variable */ + unsigned long c = crc; /* temporary variable */ unsigned n; - uch *in, ch; + unsigned char *in, ch; in = window; for (n = 0; n < outcnt; n++) { @@ -351,7 +360,7 @@ static void flush_window(void) c = crc_32_tab[((int)c ^ ch) & 0xff] ^ (c >> 8); } crc = c; - bytes_out += (ulg)outcnt; + bytes_out += (unsigned long)outcnt; outcnt = 0; } @@ -365,9 +374,59 @@ static void error(char *x) asm("hlt"); } +static void parse_elf(void *output) +{ +#ifdef CONFIG_X86_64 + Elf64_Ehdr ehdr; + Elf64_Phdr *phdrs, *phdr; +#else + Elf32_Ehdr ehdr; + Elf32_Phdr *phdrs, *phdr; +#endif + void *dest; + int i; + + memcpy(&ehdr, output, sizeof(ehdr)); + if (ehdr.e_ident[EI_MAG0] != ELFMAG0 || + ehdr.e_ident[EI_MAG1] != ELFMAG1 || + ehdr.e_ident[EI_MAG2] != ELFMAG2 || + ehdr.e_ident[EI_MAG3] != ELFMAG3) { + error("Kernel is not a valid ELF file"); + return; + } + + putstr("Parsing ELF... "); + + phdrs = malloc(sizeof(*phdrs) * ehdr.e_phnum); + if (!phdrs) + error("Failed to allocate space for phdrs"); + + memcpy(phdrs, output + ehdr.e_phoff, sizeof(*phdrs) * ehdr.e_phnum); + + for (i = 0; i < ehdr.e_phnum; i++) { + phdr = &phdrs[i]; + + switch (phdr->p_type) { + case PT_LOAD: +#ifdef CONFIG_RELOCATABLE + dest = output; + dest += (phdr->p_paddr - LOAD_PHYSICAL_ADDR); +#else + dest = (void *)(phdr->p_paddr); +#endif + memcpy(dest, + output + phdr->p_offset, + phdr->p_filesz); + break; + default: /* Ignore other PT_* */ break; + } + } +} + asmlinkage void decompress_kernel(void *rmode, memptr heap, - uch *input_data, unsigned long input_len, - uch *output) + unsigned char *input_data, + unsigned long input_len, + unsigned char *output) { real_mode = rmode; @@ -384,18 +443,18 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap, window = output; /* Output buffer (Normally at 1M) */ free_mem_ptr = heap; /* Heap */ - free_mem_end_ptr = heap + HEAP_SIZE; + free_mem_end_ptr = heap + BOOT_HEAP_SIZE; inbuf = input_data; /* Input buffer */ insize = input_len; inptr = 0; #ifdef CONFIG_X86_64 - if ((ulg)output & (__KERNEL_ALIGN - 1)) + if ((unsigned long)output & (__KERNEL_ALIGN - 1)) error("Destination address not 2M aligned"); - if ((ulg)output >= 0xffffffffffUL) + if ((unsigned long)output >= 0xffffffffffUL) error("Destination address too large"); #else - if ((u32)output & (CONFIG_PHYSICAL_ALIGN -1)) + if ((u32)output & (CONFIG_PHYSICAL_ALIGN - 1)) error("Destination address not CONFIG_PHYSICAL_ALIGN aligned"); if (heap > ((-__PAGE_OFFSET-(512<<20)-1) & 0x7fffffff)) error("Destination address too large"); @@ -408,6 +467,7 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap, makecrc(); putstr("\nDecompressing Linux... "); gunzip(); + parse_elf(output); putstr("done.\nBooting the kernel.\n"); return; } diff --git a/arch/x86/boot/compressed/vmlinux_64.lds b/arch/x86/boot/compressed/vmlinux_64.lds index 7e5c7209f6cc..bef1ac891bce 100644 --- a/arch/x86/boot/compressed/vmlinux_64.lds +++ b/arch/x86/boot/compressed/vmlinux_64.lds @@ -39,10 +39,10 @@ SECTIONS *(.bss.*) *(COMMON) . = ALIGN(8); - _end = . ; + _end_before_pgt = . ; . = ALIGN(4096); pgtable = . ; . = . + 4096 * 6; - _heap = .; + _ebss = .; } } diff --git a/arch/x86/boot/copy.S b/arch/x86/boot/copy.S index ef127e56a3cf..ef50c84e8b4b 100644 --- a/arch/x86/boot/copy.S +++ b/arch/x86/boot/copy.S @@ -9,8 +9,6 @@ * ----------------------------------------------------------------------- */ /* - * arch/i386/boot/copy.S - * * Memory copy routines */ diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c index 769065bd23d7..7804389ee005 100644 --- a/arch/x86/boot/cpucheck.c +++ b/arch/x86/boot/cpucheck.c @@ -9,8 +9,6 @@ * ----------------------------------------------------------------------- */ /* - * arch/i386/boot/cpucheck.c - * * Check for obligatory CPU features and abort if the features are not * present. This code should be compilable as 16-, 32- or 64-bit * code, so be very careful with types and inline assembly. @@ -56,27 +54,27 @@ static const u32 req_flags[NCAPINTS] = REQUIRED_MASK7, }; -#define A32(a,b,c,d) (((d) << 24)+((c) << 16)+((b) << 8)+(a)) +#define A32(a, b, c, d) (((d) << 24)+((c) << 16)+((b) << 8)+(a)) static int is_amd(void) { - return cpu_vendor[0] == A32('A','u','t','h') && - cpu_vendor[1] == A32('e','n','t','i') && - cpu_vendor[2] == A32('c','A','M','D'); + return cpu_vendor[0] == A32('A', 'u', 't', 'h') && + cpu_vendor[1] == A32('e', 'n', 't', 'i') && + cpu_vendor[2] == A32('c', 'A', 'M', 'D'); } static int is_centaur(void) { - return cpu_vendor[0] == A32('C','e','n','t') && - cpu_vendor[1] == A32('a','u','r','H') && - cpu_vendor[2] == A32('a','u','l','s'); + return cpu_vendor[0] == A32('C', 'e', 'n', 't') && + cpu_vendor[1] == A32('a', 'u', 'r', 'H') && + cpu_vendor[2] == A32('a', 'u', 'l', 's'); } static int is_transmeta(void) { - return cpu_vendor[0] == A32('G','e','n','u') && - cpu_vendor[1] == A32('i','n','e','T') && - cpu_vendor[2] == A32('M','x','8','6'); + return cpu_vendor[0] == A32('G', 'e', 'n', 'u') && + cpu_vendor[1] == A32('i', 'n', 'e', 'T') && + cpu_vendor[2] == A32('M', 'x', '8', '6'); } static int has_fpu(void) diff --git a/arch/x86/boot/edd.c b/arch/x86/boot/edd.c index 8721dc46a0b6..03399d64013b 100644 --- a/arch/x86/boot/edd.c +++ b/arch/x86/boot/edd.c @@ -9,8 +9,6 @@ * ----------------------------------------------------------------------- */ /* - * arch/i386/boot/edd.c - * * Get EDD BIOS disk information */ @@ -128,17 +126,25 @@ void query_edd(void) { char eddarg[8]; int do_mbr = 1; +#ifdef CONFIG_EDD_OFF + int do_edd = 0; +#else int do_edd = 1; +#endif int be_quiet; int devno; struct edd_info ei, *edp; u32 *mbrptr; if (cmdline_find_option("edd", eddarg, sizeof eddarg) > 0) { - if (!strcmp(eddarg, "skipmbr") || !strcmp(eddarg, "skip")) + if (!strcmp(eddarg, "skipmbr") || !strcmp(eddarg, "skip")) { + do_edd = 1; do_mbr = 0; + } else if (!strcmp(eddarg, "off")) do_edd = 0; + else if (!strcmp(eddarg, "on")) + do_edd = 1; } be_quiet = cmdline_find_option_bool("quiet"); diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 64ad9016585a..af86e431acfa 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -22,6 +22,7 @@ #include <asm/page.h> #include <asm/setup.h> #include "boot.h" +#include "offsets.h" SETUPSECTS = 4 /* default nr of setup-sectors */ BOOTSEG = 0x07C0 /* original address of boot-sector */ @@ -119,7 +120,7 @@ _start: # Part 2 of the header, from the old setup.S .ascii "HdrS" # header signature - .word 0x0207 # header version number (>= 0x0105) + .word 0x0209 # header version number (>= 0x0105) # or else old loadlin-1.5 will fail) .globl realmode_swtch realmode_swtch: .word 0, 0 # default_switch, SETUPSEG @@ -223,6 +224,13 @@ hardware_subarch: .long 0 # subarchitecture, added with 2.07 hardware_subarch_data: .quad 0 +payload_offset: .long input_data +payload_length: .long input_data_end-input_data + +setup_data: .quad 0 # 64-bit physical pointer to + # single linked list of + # struct setup_data + # End of setup header ##################################################### .section ".inittext", "ax" diff --git a/arch/x86/boot/install.sh b/arch/x86/boot/install.sh index 88d77761d01b..8d60ee15dfd9 100644 --- a/arch/x86/boot/install.sh +++ b/arch/x86/boot/install.sh @@ -1,7 +1,5 @@ #!/bin/sh # -# arch/i386/boot/install.sh -# # This file is subject to the terms and conditions of the GNU General Public # License. See the file "COPYING" in the main directory of this archive # for more details. diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c index 7828da5cfd07..77569a4a3be1 100644 --- a/arch/x86/boot/main.c +++ b/arch/x86/boot/main.c @@ -9,8 +9,6 @@ * ----------------------------------------------------------------------- */ /* - * arch/i386/boot/main.c - * * Main module for the real-mode kernel code */ diff --git a/arch/x86/boot/mca.c b/arch/x86/boot/mca.c index 68222f2d4b67..911eaae5d696 100644 --- a/arch/x86/boot/mca.c +++ b/arch/x86/boot/mca.c @@ -9,8 +9,6 @@ * ----------------------------------------------------------------------- */ /* - * arch/i386/boot/mca.c - * * Get the MCA system description table */ diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c index e77d89f9e8aa..acad32eb4290 100644 --- a/arch/x86/boot/memory.c +++ b/arch/x86/boot/memory.c @@ -9,8 +9,6 @@ * ----------------------------------------------------------------------- */ /* - * arch/i386/boot/memory.c - * * Memory detection code */ diff --git a/arch/x86/boot/pm.c b/arch/x86/boot/pm.c index 1a0f936c160b..328956fdb59e 100644 --- a/arch/x86/boot/pm.c +++ b/arch/x86/boot/pm.c @@ -9,8 +9,6 @@ * ----------------------------------------------------------------------- */ /* - * arch/i386/boot/pm.c - * * Prepare the machine for transition to protected mode. */ @@ -100,7 +98,7 @@ static void reset_coprocessor(void) /* * Set up the GDT */ -#define GDT_ENTRY(flags,base,limit) \ +#define GDT_ENTRY(flags, base, limit) \ (((u64)(base & 0xff000000) << 32) | \ ((u64)flags << 40) | \ ((u64)(limit & 0x00ff0000) << 32) | \ diff --git a/arch/x86/boot/pmjump.S b/arch/x86/boot/pmjump.S index f5402d51f7c3..ab049d40a884 100644 --- a/arch/x86/boot/pmjump.S +++ b/arch/x86/boot/pmjump.S @@ -9,8 +9,6 @@ * ----------------------------------------------------------------------- */ /* - * arch/i386/boot/pmjump.S - * * The actual transition into protected mode */ diff --git a/arch/x86/boot/printf.c b/arch/x86/boot/printf.c index 7e7e890699be..c1d00c0274c4 100644 --- a/arch/x86/boot/printf.c +++ b/arch/x86/boot/printf.c @@ -9,8 +9,6 @@ * ----------------------------------------------------------------------- */ /* - * arch/i386/boot/printf.c - * * Oh, it's a waste of space, but oh-so-yummy for debugging. This * version of printf() does not include 64-bit support. "Live with * it." diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index 481a22097781..f94b7a0c2abf 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -9,8 +9,6 @@ * ----------------------------------------------------------------------- */ /* - * arch/i386/boot/string.c - * * Very basic string functions */ diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index b4248740ff0d..44dc1923c0e3 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -50,6 +50,75 @@ typedef unsigned long u32; u8 buf[SETUP_SECT_MAX*512]; int is_big_kernel; +/*----------------------------------------------------------------------*/ + +static const u32 crctab32[] = { + 0x00000000, 0x77073096, 0xee0e612c, 0x990951ba, 0x076dc419, + 0x706af48f, 0xe963a535, 0x9e6495a3, 0x0edb8832, 0x79dcb8a4, + 0xe0d5e91e, 0x97d2d988, 0x09b64c2b, 0x7eb17cbd, 0xe7b82d07, + 0x90bf1d91, 0x1db71064, 0x6ab020f2, 0xf3b97148, 0x84be41de, + 0x1adad47d, 0x6ddde4eb, 0xf4d4b551, 0x83d385c7, 0x136c9856, + 0x646ba8c0, 0xfd62f97a, 0x8a65c9ec, 0x14015c4f, 0x63066cd9, + 0xfa0f3d63, 0x8d080df5, 0x3b6e20c8, 0x4c69105e, 0xd56041e4, + 0xa2677172, 0x3c03e4d1, 0x4b04d447, 0xd20d85fd, 0xa50ab56b, + 0x35b5a8fa, 0x42b2986c, 0xdbbbc9d6, 0xacbcf940, 0x32d86ce3, + 0x45df5c75, 0xdcd60dcf, 0xabd13d59, 0x26d930ac, 0x51de003a, + 0xc8d75180, 0xbfd06116, 0x21b4f4b5, 0x56b3c423, 0xcfba9599, + 0xb8bda50f, 0x2802b89e, 0x5f058808, 0xc60cd9b2, 0xb10be924, + 0x2f6f7c87, 0x58684c11, 0xc1611dab, 0xb6662d3d, 0x76dc4190, + 0x01db7106, 0x98d220bc, 0xefd5102a, 0x71b18589, 0x06b6b51f, + 0x9fbfe4a5, 0xe8b8d433, 0x7807c9a2, 0x0f00f934, 0x9609a88e, + 0xe10e9818, 0x7f6a0dbb, 0x086d3d2d, 0x91646c97, 0xe6635c01, + 0x6b6b51f4, 0x1c6c6162, 0x856530d8, 0xf262004e, 0x6c0695ed, + 0x1b01a57b, 0x8208f4c1, 0xf50fc457, 0x65b0d9c6, 0x12b7e950, + 0x8bbeb8ea, 0xfcb9887c, 0x62dd1ddf, 0x15da2d49, 0x8cd37cf3, + 0xfbd44c65, 0x4db26158, 0x3ab551ce, 0xa3bc0074, 0xd4bb30e2, + 0x4adfa541, 0x3dd895d7, 0xa4d1c46d, 0xd3d6f4fb, 0x4369e96a, + 0x346ed9fc, 0xad678846, 0xda60b8d0, 0x44042d73, 0x33031de5, + 0xaa0a4c5f, 0xdd0d7cc9, 0x5005713c, 0x270241aa, 0xbe0b1010, + 0xc90c2086, 0x5768b525, 0x206f85b3, 0xb966d409, 0xce61e49f, + 0x5edef90e, 0x29d9c998, 0xb0d09822, 0xc7d7a8b4, 0x59b33d17, + 0x2eb40d81, 0xb7bd5c3b, 0xc0ba6cad, 0xedb88320, 0x9abfb3b6, + 0x03b6e20c, 0x74b1d29a, 0xead54739, 0x9dd277af, 0x04db2615, + 0x73dc1683, 0xe3630b12, 0x94643b84, 0x0d6d6a3e, 0x7a6a5aa8, + 0xe40ecf0b, 0x9309ff9d, 0x0a00ae27, 0x7d079eb1, 0xf00f9344, + 0x8708a3d2, 0x1e01f268, 0x6906c2fe, 0xf762575d, 0x806567cb, + 0x196c3671, 0x6e6b06e7, 0xfed41b76, 0x89d32be0, 0x10da7a5a, + 0x67dd4acc, 0xf9b9df6f, 0x8ebeeff9, 0x17b7be43, 0x60b08ed5, + 0xd6d6a3e8, 0xa1d1937e, 0x38d8c2c4, 0x4fdff252, 0xd1bb67f1, + 0xa6bc5767, 0x3fb506dd, 0x48b2364b, 0xd80d2bda, 0xaf0a1b4c, + 0x36034af6, 0x41047a60, 0xdf60efc3, 0xa867df55, 0x316e8eef, + 0x4669be79, 0xcb61b38c, 0xbc66831a, 0x256fd2a0, 0x5268e236, + 0xcc0c7795, 0xbb0b4703, 0x220216b9, 0x5505262f, 0xc5ba3bbe, + 0xb2bd0b28, 0x2bb45a92, 0x5cb36a04, 0xc2d7ffa7, 0xb5d0cf31, + 0x2cd99e8b, 0x5bdeae1d, 0x9b64c2b0, 0xec63f226, 0x756aa39c, + 0x026d930a, 0x9c0906a9, 0xeb0e363f, 0x72076785, 0x05005713, + 0x95bf4a82, 0xe2b87a14, 0x7bb12bae, 0x0cb61b38, 0x92d28e9b, + 0xe5d5be0d, 0x7cdcefb7, 0x0bdbdf21, 0x86d3d2d4, 0xf1d4e242, + 0x68ddb3f8, 0x1fda836e, 0x81be16cd, 0xf6b9265b, 0x6fb077e1, + 0x18b74777, 0x88085ae6, 0xff0f6a70, 0x66063bca, 0x11010b5c, + 0x8f659eff, 0xf862ae69, 0x616bffd3, 0x166ccf45, 0xa00ae278, + 0xd70dd2ee, 0x4e048354, 0x3903b3c2, 0xa7672661, 0xd06016f7, + 0x4969474d, 0x3e6e77db, 0xaed16a4a, 0xd9d65adc, 0x40df0b66, + 0x37d83bf0, 0xa9bcae53, 0xdebb9ec5, 0x47b2cf7f, 0x30b5ffe9, + 0xbdbdf21c, 0xcabac28a, 0x53b39330, 0x24b4a3a6, 0xbad03605, + 0xcdd70693, 0x54de5729, 0x23d967bf, 0xb3667a2e, 0xc4614ab8, + 0x5d681b02, 0x2a6f2b94, 0xb40bbe37, 0xc30c8ea1, 0x5a05df1b, + 0x2d02ef8d +}; + +static u32 partial_crc32_one(u8 c, u32 crc) +{ + return crctab32[(crc ^ c) & 0xff] ^ (crc >> 8); +} + +static u32 partial_crc32(const u8 *s, int len, u32 crc) +{ + while (len--) + crc = partial_crc32_one(*s++, crc); + return crc; +} + static void die(const char * str, ...) { va_list args; @@ -74,6 +143,7 @@ int main(int argc, char ** argv) FILE *file; int fd; void *kernel; + u32 crc = 0xffffffffUL; if (argc > 2 && !strcmp(argv[1], "-b")) { @@ -144,7 +214,8 @@ int main(int argc, char ** argv) kernel = mmap(NULL, sz, PROT_READ, MAP_SHARED, fd, 0); if (kernel == MAP_FAILED) die("Unable to mmap '%s': %m", argv[2]); - sys_size = (sz + 15) / 16; + /* Number of 16-byte paragraphs, including space for a 4-byte CRC */ + sys_size = (sz + 15 + 4) / 16; if (!is_big_kernel && sys_size > DEF_SYSSIZE) die("System is too big. Try using bzImage or modules."); @@ -155,12 +226,27 @@ int main(int argc, char ** argv) buf[0x1f6] = sys_size >> 16; buf[0x1f7] = sys_size >> 24; + crc = partial_crc32(buf, i, crc); if (fwrite(buf, 1, i, stdout) != i) die("Writing setup failed"); /* Copy the kernel code */ + crc = partial_crc32(kernel, sz, crc); if (fwrite(kernel, 1, sz, stdout) != sz) die("Writing kernel failed"); + + /* Add padding leaving 4 bytes for the checksum */ + while (sz++ < (sys_size*16) - 4) { + crc = partial_crc32_one('\0', crc); + if (fwrite("\0", 1, 1, stdout) != 1) + die("Writing padding failed"); + } + + /* Write the CRC */ + fprintf(stderr, "CRC %lx\n", crc); + if (fwrite(&crc, 1, 4, stdout) != 4) + die("Writing CRC failed"); + close(fd); /* Everything is OK */ diff --git a/arch/x86/boot/tty.c b/arch/x86/boot/tty.c index f3f14bd26371..0be77b39328a 100644 --- a/arch/x86/boot/tty.c +++ b/arch/x86/boot/tty.c @@ -9,8 +9,6 @@ * ----------------------------------------------------------------------- */ /* - * arch/i386/boot/tty.c - * * Very simple screen I/O * XXX: Probably should add very simple serial I/O? */ diff --git a/arch/x86/boot/version.c b/arch/x86/boot/version.c index c61462f7d9a7..2723d9b5ce43 100644 --- a/arch/x86/boot/version.c +++ b/arch/x86/boot/version.c @@ -9,8 +9,6 @@ * ----------------------------------------------------------------------- */ /* - * arch/i386/boot/version.c - * * Kernel version string */ diff --git a/arch/x86/boot/video-bios.c b/arch/x86/boot/video-bios.c index ff664a117096..49f26aaaebc8 100644 --- a/arch/x86/boot/video-bios.c +++ b/arch/x86/boot/video-bios.c @@ -9,8 +9,6 @@ * ----------------------------------------------------------------------- */ /* - * arch/i386/boot/video-bios.c - * * Standard video BIOS modes * * We have two options for this; silent and scanned. @@ -50,6 +48,7 @@ static int set_bios_mode(u8 mode) if (new_mode == mode) return 0; /* Mode change OK */ +#ifndef _WAKEUP if (new_mode != boot_params.screen_info.orig_video_mode) { /* Mode setting failed, but we didn't end up where we started. That's bad. Try to revert to the original @@ -59,13 +58,18 @@ static int set_bios_mode(u8 mode) : "+a" (ax) : : "ebx", "ecx", "edx", "esi", "edi"); } +#endif return -1; } static int bios_probe(void) { u8 mode; +#ifdef _WAKEUP + u8 saved_mode = 0x03; +#else u8 saved_mode = boot_params.screen_info.orig_video_mode; +#endif u16 crtc; struct mode_info *mi; int nmodes = 0; diff --git a/arch/x86/boot/video-mode.c b/arch/x86/boot/video-mode.c new file mode 100644 index 000000000000..748e8d06290a --- /dev/null +++ b/arch/x86/boot/video-mode.c @@ -0,0 +1,173 @@ +/* -*- linux-c -*- ------------------------------------------------------- * + * + * Copyright (C) 1991, 1992 Linus Torvalds + * 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. + * + * ----------------------------------------------------------------------- */ + +/* + * arch/i386/boot/video-mode.c + * + * Set the video mode. This is separated out into a different + * file in order to be shared with the ACPI wakeup code. + */ + +#include "boot.h" +#include "video.h" +#include "vesa.h" + +/* + * Common variables + */ +int adapter; /* 0=CGA/MDA/HGC, 1=EGA, 2=VGA+ */ +u16 video_segment; +int force_x, force_y; /* Don't query the BIOS for cols/rows */ + +int do_restore; /* Screen contents changed during mode flip */ +int graphic_mode; /* Graphic mode with linear frame buffer */ + +/* Probe the video drivers and have them generate their mode lists. */ +void probe_cards(int unsafe) +{ + struct card_info *card; + static u8 probed[2]; + + if (probed[unsafe]) + return; + + probed[unsafe] = 1; + + for (card = video_cards; card < video_cards_end; card++) { + if (card->unsafe == unsafe) { + if (card->probe) + card->nmodes = card->probe(); + else + card->nmodes = 0; + } + } +} + +/* Test if a mode is defined */ +int mode_defined(u16 mode) +{ + struct card_info *card; + struct mode_info *mi; + int i; + + for (card = video_cards; card < video_cards_end; card++) { + mi = card->modes; + for (i = 0; i < card->nmodes; i++, mi++) { + if (mi->mode == mode) + return 1; + } + } + + return 0; +} + +/* Set mode (without recalc) */ +static int raw_set_mode(u16 mode, u16 *real_mode) +{ + int nmode, i; + struct card_info *card; + struct mode_info *mi; + + /* Drop the recalc bit if set */ + mode &= ~VIDEO_RECALC; + + /* Scan for mode based on fixed ID, position, or resolution */ + nmode = 0; + for (card = video_cards; card < video_cards_end; card++) { + mi = card->modes; + for (i = 0; i < card->nmodes; i++, mi++) { + int visible = mi->x || mi->y; + + if ((mode == nmode && visible) || + mode == mi->mode || + mode == (mi->y << 8)+mi->x) { + *real_mode = mi->mode; + return card->set_mode(mi); + } + + if (visible) + nmode++; + } + } + + /* Nothing found? Is it an "exceptional" (unprobed) mode? */ + for (card = video_cards; card < video_cards_end; card++) { + if (mode >= card->xmode_first && + mode < card->xmode_first+card->xmode_n) { + struct mode_info mix; + *real_mode = mix.mode = mode; + mix.x = mix.y = 0; + return card->set_mode(&mix); + } + } + + /* Otherwise, failure... */ + return -1; +} + +/* + * Recalculate the vertical video cutoff (hack!) + */ +static void vga_recalc_vertical(void) +{ + unsigned int font_size, rows; + u16 crtc; + u8 pt, ov; + + set_fs(0); + font_size = rdfs8(0x485); /* BIOS: font size (pixels) */ + rows = force_y ? force_y : rdfs8(0x484)+1; /* Text rows */ + + rows *= font_size; /* Visible scan lines */ + rows--; /* ... minus one */ + + crtc = vga_crtc(); + + pt = in_idx(crtc, 0x11); + pt &= ~0x80; /* Unlock CR0-7 */ + out_idx(pt, crtc, 0x11); + + out_idx((u8)rows, crtc, 0x12); /* Lower height register */ + + ov = in_idx(crtc, 0x07); /* Overflow register */ + ov &= 0xbd; + ov |= (rows >> (8-1)) & 0x02; + ov |= (rows >> (9-6)) & 0x40; + out_idx(ov, crtc, 0x07); +} + +/* Set mode (with recalc if specified) */ +int set_mode(u16 mode) +{ + int rv; + u16 real_mode; + + /* Very special mode numbers... */ + if (mode == VIDEO_CURRENT_MODE) + return 0; /* Nothing to do... */ + else if (mode == NORMAL_VGA) + mode = VIDEO_80x25; + else if (mode == EXTENDED_VGA) + mode = VIDEO_8POINT; + + rv = raw_set_mode(mode, &real_mode); + if (rv) + return rv; + + if (mode & VIDEO_RECALC) + vga_recalc_vertical(); + + /* Save the canonical mode number for the kernel, not + an alias, size specification or menu position */ +#ifndef _WAKEUP + boot_params.hdr.vid_mode = real_mode; +#endif + return 0; +} diff --git a/arch/x86/boot/video-vesa.c b/arch/x86/boot/video-vesa.c index 419b5c273374..401ad998ad08 100644 --- a/arch/x86/boot/video-vesa.c +++ b/arch/x86/boot/video-vesa.c @@ -9,8 +9,6 @@ * ----------------------------------------------------------------------- */ /* - * arch/i386/boot/video-vesa.c - * * VESA text modes */ @@ -24,7 +22,11 @@ static struct vesa_mode_info vminfo; __videocard video_vesa; +#ifndef _WAKEUP static void vesa_store_mode_params_graphics(void); +#else /* _WAKEUP */ +static inline void vesa_store_mode_params_graphics(void) {} +#endif /* _WAKEUP */ static int vesa_probe(void) { @@ -165,6 +167,8 @@ static int vesa_set_mode(struct mode_info *mode) } +#ifndef _WAKEUP + /* Switch DAC to 8-bit mode */ static void vesa_dac_set_8bits(void) { @@ -288,6 +292,8 @@ void vesa_store_edid(void) #endif /* CONFIG_FIRMWARE_EDID */ } +#endif /* not _WAKEUP */ + __videocard video_vesa = { .card_name = "VESA", diff --git a/arch/x86/boot/video-vga.c b/arch/x86/boot/video-vga.c index 7259387b7d19..40ecb8d7688c 100644 --- a/arch/x86/boot/video-vga.c +++ b/arch/x86/boot/video-vga.c @@ -9,8 +9,6 @@ * ----------------------------------------------------------------------- */ /* - * arch/i386/boot/video-vga.c - * * Common all-VGA modes */ @@ -210,6 +208,8 @@ static int vga_set_mode(struct mode_info *mode) */ static int vga_probe(void) { + u16 ega_bx; + static const char *card_name[] = { "CGA/MDA/HGC", "EGA", "VGA" }; @@ -226,12 +226,16 @@ static int vga_probe(void) u8 vga_flag; asm(INT10 - : "=b" (boot_params.screen_info.orig_video_ega_bx) + : "=b" (ega_bx) : "a" (0x1200), "b" (0x10) /* Check EGA/VGA */ : "ecx", "edx", "esi", "edi"); +#ifndef _WAKEUP + boot_params.screen_info.orig_video_ega_bx = ega_bx; +#endif + /* If we have MDA/CGA/HGC then BL will be unchanged at 0x10 */ - if ((u8)boot_params.screen_info.orig_video_ega_bx != 0x10) { + if ((u8)ega_bx != 0x10) { /* EGA/VGA */ asm(INT10 : "=a" (vga_flag) @@ -240,7 +244,9 @@ static int vga_probe(void) if (vga_flag == 0x1a) { adapter = ADAPTER_VGA; +#ifndef _WAKEUP boot_params.screen_info.orig_video_isVGA = 1; +#endif } else { adapter = ADAPTER_EGA; } diff --git a/arch/x86/boot/video.c b/arch/x86/boot/video.c index 696d08f3843c..83598b23093a 100644 --- a/arch/x86/boot/video.c +++ b/arch/x86/boot/video.c @@ -9,8 +9,6 @@ * ----------------------------------------------------------------------- */ /* - * arch/i386/boot/video.c - * * Select video mode */ @@ -18,21 +16,6 @@ #include "video.h" #include "vesa.h" -/* - * Mode list variables - */ -static struct card_info cards[]; /* List of cards to probe for */ - -/* - * Common variables - */ -int adapter; /* 0=CGA/MDA/HGC, 1=EGA, 2=VGA+ */ -u16 video_segment; -int force_x, force_y; /* Don't query the BIOS for cols/rows */ - -int do_restore = 0; /* Screen contents changed during mode flip */ -int graphic_mode; /* Graphic mode with linear frame buffer */ - static void store_cursor_position(void) { u16 curpos; @@ -107,147 +90,6 @@ static void store_mode_params(void) boot_params.screen_info.orig_video_lines = y; } -/* Probe the video drivers and have them generate their mode lists. */ -static void probe_cards(int unsafe) -{ - struct card_info *card; - static u8 probed[2]; - - if (probed[unsafe]) - return; - - probed[unsafe] = 1; - - for (card = video_cards; card < video_cards_end; card++) { - if (card->unsafe == unsafe) { - if (card->probe) - card->nmodes = card->probe(); - else - card->nmodes = 0; - } - } -} - -/* Test if a mode is defined */ -int mode_defined(u16 mode) -{ - struct card_info *card; - struct mode_info *mi; - int i; - - for (card = video_cards; card < video_cards_end; card++) { - mi = card->modes; - for (i = 0; i < card->nmodes; i++, mi++) { - if (mi->mode == mode) - return 1; - } - } - - return 0; -} - -/* Set mode (without recalc) */ -static int raw_set_mode(u16 mode, u16 *real_mode) -{ - int nmode, i; - struct card_info *card; - struct mode_info *mi; - - /* Drop the recalc bit if set */ - mode &= ~VIDEO_RECALC; - - /* Scan for mode based on fixed ID, position, or resolution */ - nmode = 0; - for (card = video_cards; card < video_cards_end; card++) { - mi = card->modes; - for (i = 0; i < card->nmodes; i++, mi++) { - int visible = mi->x || mi->y; - - if ((mode == nmode && visible) || - mode == mi->mode || - mode == (mi->y << 8)+mi->x) { - *real_mode = mi->mode; - return card->set_mode(mi); - } - - if (visible) - nmode++; - } - } - - /* Nothing found? Is it an "exceptional" (unprobed) mode? */ - for (card = video_cards; card < video_cards_end; card++) { - if (mode >= card->xmode_first && - mode < card->xmode_first+card->xmode_n) { - struct mode_info mix; - *real_mode = mix.mode = mode; - mix.x = mix.y = 0; - return card->set_mode(&mix); - } - } - - /* Otherwise, failure... */ - return -1; -} - -/* - * Recalculate the vertical video cutoff (hack!) - */ -static void vga_recalc_vertical(void) -{ - unsigned int font_size, rows; - u16 crtc; - u8 pt, ov; - - set_fs(0); - font_size = rdfs8(0x485); /* BIOS: font size (pixels) */ - rows = force_y ? force_y : rdfs8(0x484)+1; /* Text rows */ - - rows *= font_size; /* Visible scan lines */ - rows--; /* ... minus one */ - - crtc = vga_crtc(); - - pt = in_idx(crtc, 0x11); - pt &= ~0x80; /* Unlock CR0-7 */ - out_idx(pt, crtc, 0x11); - - out_idx((u8)rows, crtc, 0x12); /* Lower height register */ - - ov = in_idx(crtc, 0x07); /* Overflow register */ - ov &= 0xbd; - ov |= (rows >> (8-1)) & 0x02; - ov |= (rows >> (9-6)) & 0x40; - out_idx(ov, crtc, 0x07); -} - -/* Set mode (with recalc if specified) */ -static int set_mode(u16 mode) -{ - int rv; - u16 real_mode; - - /* Very special mode numbers... */ - if (mode == VIDEO_CURRENT_MODE) - return 0; /* Nothing to do... */ - else if (mode == NORMAL_VGA) - mode = VIDEO_80x25; - else if (mode == EXTENDED_VGA) - mode = VIDEO_8POINT; - - rv = raw_set_mode(mode, &real_mode); - if (rv) - return rv; - - if (mode & VIDEO_RECALC) - vga_recalc_vertical(); - - /* Save the canonical mode number for the kernel, not - an alias, size specification or menu position */ - boot_params.hdr.vid_mode = real_mode; - return 0; -} - static unsigned int get_entry(void) { char entry_buf[4]; @@ -486,6 +328,7 @@ void set_video(void) printf("Undefined video mode number: %x\n", mode); mode = ASK_VGA; } + boot_params.hdr.vid_mode = mode; vesa_store_edid(); store_mode_params(); diff --git a/arch/x86/boot/video.h b/arch/x86/boot/video.h index d69347f79e8e..ee63f5d14461 100644 --- a/arch/x86/boot/video.h +++ b/arch/x86/boot/video.h @@ -9,8 +9,6 @@ * ----------------------------------------------------------------------- */ /* - * arch/i386/boot/video.h - * * Header file for the real-mode video probing code */ diff --git a/arch/x86/boot/voyager.c b/arch/x86/boot/voyager.c index 6499e3239b41..433909d61e5c 100644 --- a/arch/x86/boot/voyager.c +++ b/arch/x86/boot/voyager.c @@ -9,8 +9,6 @@ * ----------------------------------------------------------------------- */ /* - * arch/i386/boot/voyager.c - * * Get the Voyager config information */ diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 3df340b54e57..ad7ddaaff588 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -1421,6 +1421,7 @@ CONFIG_DEBUG_BUGVERBOSE=y # CONFIG_DEBUG_VM is not set # CONFIG_DEBUG_LIST is not set # CONFIG_FRAME_POINTER is not set +CONFIG_OPTIMIZE_INLINING=y # CONFIG_RCU_TORTURE_TEST is not set # CONFIG_LKDTM is not set # CONFIG_FAULT_INJECTION is not set diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index eef98cb00c62..2d6f5b2809d2 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -1346,6 +1346,7 @@ CONFIG_DEBUG_BUGVERBOSE=y # CONFIG_DEBUG_VM is not set # CONFIG_DEBUG_LIST is not set # CONFIG_FRAME_POINTER is not set +CONFIG_OPTIMIZE_INLINING=y # CONFIG_RCU_TORTURE_TEST is not set # CONFIG_LKDTM is not set # CONFIG_FAULT_INJECTION is not set diff --git a/arch/x86/crypto/aes-i586-asm_32.S b/arch/x86/crypto/aes-i586-asm_32.S index 1093bede3e0a..e41b147f4509 100644 --- a/arch/x86/crypto/aes-i586-asm_32.S +++ b/arch/x86/crypto/aes-i586-asm_32.S @@ -289,7 +289,6 @@ aes_enc_blk: pop %ebx mov %r0,(%ebp) pop %ebp - mov $1,%eax ret // AES (Rijndael) Decryption Subroutine @@ -365,6 +364,4 @@ aes_dec_blk: pop %ebx mov %r0,(%ebp) pop %ebp - mov $1,%eax ret - diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 5e7771a3ba2f..cb3856a18c85 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -128,7 +128,7 @@ asmlinkage long sys32_sigsuspend(int history0, int history1, old_sigset_t mask) current->state = TASK_INTERRUPTIBLE; schedule(); - set_thread_flag(TIF_RESTORE_SIGMASK); + set_restore_sigmask(); return -ERESTARTNOHAND; } @@ -468,7 +468,7 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka, restorer = ka->sa.sa_restorer; } else { /* Return stub is in 32bit vsyscall page */ - if (current->binfmt->hasvdso) + if (current->mm->context.vdso) restorer = VDSO32_SYMBOL(current->mm->context.vdso, sigreturn); else @@ -499,11 +499,6 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka, regs->cs = __USER32_CS; regs->ss = __USER32_DS; - set_fs(USER_DS); - regs->flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_DF); - if (test_thread_flag(TIF_SINGLESTEP)) - ptrace_notify(SIGTRAP); - #if DEBUG_SIG printk(KERN_DEBUG "SIG deliver (%s:%d): sp=%p pc=%lx ra=%u\n", current->comm, current->pid, frame, regs->ip, frame->pretcode); @@ -599,11 +594,6 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, regs->cs = __USER32_CS; regs->ss = __USER32_DS; - set_fs(USER_DS); - regs->flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_DF); - if (test_thread_flag(TIF_SINGLESTEP)) - ptrace_notify(SIGTRAP); - #if DEBUG_SIG printk(KERN_DEBUG "SIG deliver (%s:%d): sp=%p pc=%lx ra=%u\n", current->comm, current->pid, frame, regs->ip, frame->pretcode); diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 8022d3c695c0..b5e329da166c 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -162,12 +162,14 @@ sysenter_tracesys: SAVE_REST CLEAR_RREGS movq %r9,R9(%rsp) - movq $-ENOSYS,RAX(%rsp) /* really needed? */ + movq $-ENOSYS,RAX(%rsp)/* ptrace can change this for a bad syscall */ movq %rsp,%rdi /* &pt_regs -> arg1 */ call syscall_trace_enter LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */ RESTORE_REST xchgl %ebp,%r9d + cmpl $(IA32_NR_syscalls-1),%eax + ja int_ret_from_sys_call /* sysenter_tracesys has set RAX(%rsp) */ jmp sysenter_do_call CFI_ENDPROC ENDPROC(ia32_sysenter_target) @@ -261,13 +263,15 @@ cstar_tracesys: SAVE_REST CLEAR_RREGS movq %r9,R9(%rsp) - movq $-ENOSYS,RAX(%rsp) /* really needed? */ + movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */ movq %rsp,%rdi /* &pt_regs -> arg1 */ call syscall_trace_enter LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */ RESTORE_REST xchgl %ebp,%r9d movl RSP-ARGOFFSET(%rsp), %r8d + cmpl $(IA32_NR_syscalls-1),%eax + ja int_ret_from_sys_call /* cstar_tracesys has set RAX(%rsp) */ jmp cstar_do_call END(ia32_cstar_target) @@ -325,7 +329,7 @@ ENTRY(ia32_syscall) jnz ia32_tracesys ia32_do_syscall: cmpl $(IA32_NR_syscalls-1),%eax - ja ia32_badsys + ja int_ret_from_sys_call /* ia32_tracesys has set RAX(%rsp) */ IA32_ARG_FIXUP call *ia32_sys_call_table(,%rax,8) # xxx: rip relative ia32_sysret: @@ -335,7 +339,7 @@ ia32_sysret: ia32_tracesys: SAVE_REST CLEAR_RREGS - movq $-ENOSYS,RAX(%rsp) /* really needed? */ + movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */ movq %rsp,%rdi /* &pt_regs -> arg1 */ call syscall_trace_enter LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */ @@ -426,7 +430,7 @@ ia32_sys_call_table: .quad sys_setuid16 .quad sys_getuid16 .quad compat_sys_stime /* stime */ /* 25 */ - .quad sys32_ptrace /* ptrace */ + .quad compat_sys_ptrace /* ptrace */ .quad sys_alarm .quad sys_fstat /* (old)fstat */ .quad sys_pause diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index abf71d26fc2a..f00afdf61e67 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -26,51 +26,26 @@ #include <linux/file.h> #include <linux/signal.h> #include <linux/syscalls.h> -#include <linux/resource.h> #include <linux/times.h> #include <linux/utsname.h> -#include <linux/smp.h> #include <linux/smp_lock.h> -#include <linux/sem.h> -#include <linux/msg.h> #include <linux/mm.h> -#include <linux/shm.h> -#include <linux/slab.h> #include <linux/uio.h> -#include <linux/nfs_fs.h> -#include <linux/quota.h> -#include <linux/module.h> -#include <linux/sunrpc/svc.h> -#include <linux/nfsd/nfsd.h> -#include <linux/nfsd/cache.h> -#include <linux/nfsd/xdr.h> -#include <linux/nfsd/syscall.h> #include <linux/poll.h> #include <linux/personality.h> #include <linux/stat.h> -#include <linux/ipc.h> #include <linux/rwsem.h> -#include <linux/binfmts.h> -#include <linux/init.h> -#include <linux/aio_abi.h> -#include <linux/aio.h> #include <linux/compat.h> #include <linux/vfs.h> #include <linux/ptrace.h> #include <linux/highuid.h> -#include <linux/vmalloc.h> -#include <linux/fsnotify.h> #include <linux/sysctl.h> #include <asm/mman.h> #include <asm/types.h> #include <asm/uaccess.h> -#include <asm/semaphore.h> #include <asm/atomic.h> -#include <asm/ldt.h> - -#include <net/scm.h> -#include <net/sock.h> #include <asm/ia32.h> +#include <asm/vgtod.h> #define AA(__x) ((unsigned long)(__x)) @@ -804,11 +779,6 @@ asmlinkage long sys32_execve(char __user *name, compat_uptr_t __user *argv, if (IS_ERR(filename)) return error; error = compat_do_execve(filename, argv, envp, regs); - if (error == 0) { - task_lock(current); - current->ptrace &= ~PT_DTRACE; - task_unlock(current); - } putname(filename); return error; } diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 4eb5ce841106..bbdacb398d48 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -2,8 +2,7 @@ # Makefile for the linux kernel. # -extra-y := head_$(BITS).o init_task.o vmlinux.lds -extra-$(CONFIG_X86_64) += head64.o +extra-y := head_$(BITS).o head$(BITS).o init_task.o vmlinux.lds CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE) @@ -19,16 +18,18 @@ CFLAGS_tsc_64.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_$(BITS).o +obj-y += setup_$(BITS).o i8259_$(BITS).o setup.o obj-$(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 += pci-dma_$(BITS).o bootflag.o e820_$(BITS).o -obj-y += quirks.o i8237.o topology.o kdebugfs.o -obj-y += alternative.o i8253.o -obj-$(CONFIG_X86_64) += pci-nommu_64.o bugs_64.o +obj-y += bootflag.o e820_$(BITS).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-$(CONFIG_X86_TRAMPOLINE) += trampoline.o +obj-y += process.o obj-y += i387.o obj-y += ptrace.o obj-y += ds.o @@ -39,7 +40,6 @@ obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-y += cpu/ obj-y += acpi/ obj-$(CONFIG_X86_BIOS_REBOOT) += reboot.o -obj-$(CONFIG_X86_64) += reboot.o obj-$(CONFIG_MCA) += mca_32.o obj-$(CONFIG_X86_MSR) += msr.o obj-$(CONFIG_X86_CPUID) += cpuid.o @@ -47,11 +47,12 @@ obj-$(CONFIG_MICROCODE) += microcode.o obj-$(CONFIG_PCI) += early-quirks.o apm-y := apm_32.o obj-$(CONFIG_APM) += apm.o -obj-$(CONFIG_X86_SMP) += smp_$(BITS).o smpboot_$(BITS).o tsc_sync.o -obj-$(CONFIG_X86_32_SMP) += smpcommon_32.o -obj-$(CONFIG_X86_64_SMP) += smp_64.o smpboot_64.o tsc_sync.o +obj-$(CONFIG_X86_SMP) += smp.o +obj-$(CONFIG_X86_SMP) += smpboot.o tsc_sync.o ipi.o tlb_$(BITS).o +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-$(CONFIG_X86_MPPARSE) += mpparse_$(BITS).o +obj-$(CONFIG_X86_MPPARSE) += mpparse.o obj-$(CONFIG_X86_LOCAL_APIC) += apic_$(BITS).o nmi_$(BITS).o obj-$(CONFIG_X86_IO_APIC) += io_apic_$(BITS).o obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o @@ -60,12 +61,13 @@ obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o obj-$(CONFIG_X86_NUMAQ) += numaq_32.o obj-$(CONFIG_X86_SUMMIT_NUMA) += summit_32.o -obj-$(CONFIG_X86_VSMP) += vsmp_64.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-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_VM86) += vm86_32.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o @@ -77,6 +79,8 @@ obj-$(CONFIG_DEBUG_RODATA_TEST) += test_rodata.o obj-$(CONFIG_DEBUG_NX_TEST) += test_nx.o obj-$(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 ifdef CONFIG_INPUT_PCSPKR @@ -86,14 +90,18 @@ endif obj-$(CONFIG_SCx200) += scx200.o scx200-y += scx200_32.o +obj-$(CONFIG_OLPC) += olpc.o + ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) - obj-y += genapic_64.o genapic_flat_64.o + obj-y += genapic_64.o genapic_flat_64.o genx2apic_uv_x.o obj-$(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_SWIOTLB) += pci-swiotlb_64.o + + obj-$(CONFIG_PCI_MMCONFIG) += mmconf-fam10h_64.o endif diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile index 19d3d6e9d09b..7335959b6aff 100644 --- a/arch/x86/kernel/acpi/Makefile +++ b/arch/x86/kernel/acpi/Makefile @@ -1,7 +1,14 @@ +subdir- := realmode + obj-$(CONFIG_ACPI) += boot.o -obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup_$(BITS).o +obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup_rm.o wakeup_$(BITS).o ifneq ($(CONFIG_ACPI_PROCESSOR),) obj-y += cstate.o processor.o endif +$(obj)/wakeup_rm.o: $(obj)/realmode/wakeup.bin + +$(obj)/realmode/wakeup.bin: FORCE + $(Q)$(MAKE) $(build)=$(obj)/realmode $@ + diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 2cdc9de9371d..c49ebcc6c41e 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -39,6 +39,11 @@ #include <asm/apic.h> #include <asm/io.h> #include <asm/mpspec.h> +#include <asm/smp.h> + +#ifdef CONFIG_X86_LOCAL_APIC +# include <mach_apic.h> +#endif static int __initdata acpi_force = 0; @@ -52,9 +57,7 @@ EXPORT_SYMBOL(acpi_disabled); #ifdef CONFIG_X86_64 #include <asm/proto.h> - -static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id) { return 0; } - +#include <asm/genapic.h> #else /* X86 */ @@ -111,7 +114,7 @@ char *__init __acpi_map_table(unsigned long phys_addr, unsigned long size) if (!phys_addr || !size) return NULL; - if (phys_addr+size <= (end_pfn_map << PAGE_SHIFT) + PAGE_SIZE) + if (phys_addr+size <= (max_pfn_mapped << PAGE_SHIFT) + PAGE_SIZE) return __va(phys_addr); return NULL; @@ -237,6 +240,16 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) return 0; } +static void __cpuinit acpi_register_lapic(int id, u8 enabled) +{ + if (!enabled) { + ++disabled_cpus; + return; + } + + generic_processor_info(id, 0); +} + static int __init acpi_parse_lapic(struct acpi_subtable_header * header, const unsigned long end) { @@ -256,8 +269,26 @@ acpi_parse_lapic(struct acpi_subtable_header * header, const unsigned long end) * to not preallocating memory for all NR_CPUS * when we use CPU hotplug. */ - mp_register_lapic(processor->id, /* APIC ID */ - processor->lapic_flags & ACPI_MADT_ENABLED); /* Enabled? */ + acpi_register_lapic(processor->id, /* APIC ID */ + processor->lapic_flags & ACPI_MADT_ENABLED); + + return 0; +} + +static int __init +acpi_parse_sapic(struct acpi_subtable_header *header, const unsigned long end) +{ + struct acpi_madt_local_sapic *processor = NULL; + + processor = (struct acpi_madt_local_sapic *)header; + + if (BAD_MADT_ENTRY(processor, end)) + return -EINVAL; + + acpi_table_print_madt_entry(header); + + acpi_register_lapic((processor->id << 8) | processor->eid,/* APIC ID */ + processor->lapic_flags & ACPI_MADT_ENABLED); return 0; } @@ -300,6 +331,8 @@ 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) { @@ -532,7 +565,7 @@ static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu) buffer.pointer = NULL; tmp_map = cpu_present_map; - mp_register_lapic(physid, lapic->lapic_flags & ACPI_MADT_ENABLED); + acpi_register_lapic(physid, lapic->lapic_flags & ACPI_MADT_ENABLED); /* * If mp_register_lapic successfully generates a new logical cpu @@ -664,10 +697,6 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table) #define HPET_RESOURCE_NAME_SIZE 9 hpet_res = alloc_bootmem(sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE); - if (!hpet_res) - return 0; - - memset(hpet_res, 0, sizeof(*hpet_res)); hpet_res->name = (void *)&hpet_res[1]; hpet_res->flags = IORESOURCE_MEM; snprintf((char *)hpet_res->name, HPET_RESOURCE_NAME_SIZE, "HPET %u", @@ -732,6 +761,42 @@ static int __init acpi_parse_fadt(struct acpi_table_header *table) * Parse LAPIC entries in MADT * returns 0 on success, < 0 on error */ + +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) + boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id()); +} + +static int __init early_acpi_parse_madt_lapic_addr_ovr(void) +{ + int count; + + if (!cpu_has_apic) + return -ENODEV; + + /* + * Note that the LAPIC address is obtained from the MADT (32-bit value) + * and (optionally) overriden by a LAPIC_ADDR_OVR entry (64-bit value). + */ + + count = + acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_OVERRIDE, + acpi_parse_lapic_addr_ovr, 0); + if (count < 0) { + printk(KERN_ERR PREFIX + "Error parsing LAPIC address override entry\n"); + return count; + } + + acpi_register_lapic_address(acpi_lapic_addr); + + return count; +} + static int __init acpi_parse_madt_lapic_entries(void) { int count; @@ -753,10 +818,14 @@ static int __init acpi_parse_madt_lapic_entries(void) return count; } - mp_register_lapic_address(acpi_lapic_addr); + acpi_register_lapic_address(acpi_lapic_addr); + + count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_SAPIC, + acpi_parse_sapic, MAX_APICS); - count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC, acpi_parse_lapic, - MAX_APICS); + if (!count) + count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC, + acpi_parse_lapic, MAX_APICS); if (!count) { printk(KERN_ERR PREFIX "No LAPIC entries present\n"); /* TBD: Cleanup to allow fallback to MPS */ @@ -858,6 +927,33 @@ static inline int acpi_parse_madt_ioapic_entries(void) } #endif /* !CONFIG_X86_IO_APIC */ +static void __init early_acpi_process_madt(void) +{ +#ifdef CONFIG_X86_LOCAL_APIC + int error; + + if (!acpi_table_parse(ACPI_SIG_MADT, acpi_parse_madt)) { + + /* + * Parse MADT LAPIC entries + */ + error = early_acpi_parse_madt_lapic_addr_ovr(); + if (!error) { + acpi_lapic = 1; + smp_found_config = 1; + } + if (error == -EINVAL) { + /* + * Dell Precision Workstation 410, 610 come here. + */ + printk(KERN_ERR PREFIX + "Invalid BIOS MADT, disabling ACPI\n"); + disable_acpi(); + } + } +#endif +} + static void __init acpi_process_madt(void) { #ifdef CONFIG_X86_LOCAL_APIC @@ -1190,6 +1286,23 @@ int __init acpi_boot_table_init(void) return 0; } +int __init early_acpi_boot_init(void) +{ + /* + * If acpi_disabled, bail out + * One exception: acpi=ht continues far enough to enumerate LAPICs + */ + if (acpi_disabled && !acpi_ht) + return 1; + + /* + * Process the Multiple APIC Description Table (MADT), if present + */ + early_acpi_process_madt(); + + return 0; +} + int __init acpi_boot_init(void) { /* diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index 8ca3557a6d59..c2502eb9aa83 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -1,6 +1,4 @@ /* - * arch/i386/kernel/acpi/cstate.c - * * Copyright (C) 2005 Intel Corporation * Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> * - Added _PDC for SMP C-states on Intel CPUs @@ -93,7 +91,7 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu, /* Make sure we are running on right CPU */ saved_mask = current->cpus_allowed; - retval = set_cpus_allowed(current, cpumask_of_cpu(cpu)); + retval = set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); if (retval) return -1; @@ -130,7 +128,7 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu, cx->address); out: - set_cpus_allowed(current, saved_mask); + set_cpus_allowed_ptr(current, &saved_mask); return retval; } EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe); diff --git a/arch/x86/kernel/acpi/processor.c b/arch/x86/kernel/acpi/processor.c index 324eb0cab19c..de2d2e4ebad9 100644 --- a/arch/x86/kernel/acpi/processor.c +++ b/arch/x86/kernel/acpi/processor.c @@ -1,6 +1,4 @@ /* - * arch/i386/kernel/acpi/processor.c - * * Copyright (C) 2005 Intel Corporation * Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> * - Added _PDC for platforms with Intel CPUs diff --git a/arch/x86/kernel/acpi/realmode/.gitignore b/arch/x86/kernel/acpi/realmode/.gitignore new file mode 100644 index 000000000000..58f1f48a58f8 --- /dev/null +++ b/arch/x86/kernel/acpi/realmode/.gitignore @@ -0,0 +1,3 @@ +wakeup.bin +wakeup.elf +wakeup.lds diff --git a/arch/x86/kernel/acpi/realmode/Makefile b/arch/x86/kernel/acpi/realmode/Makefile new file mode 100644 index 000000000000..092900854acc --- /dev/null +++ b/arch/x86/kernel/acpi/realmode/Makefile @@ -0,0 +1,57 @@ +# +# arch/x86/kernel/acpi/realmode/Makefile +# +# This file is subject to the terms and conditions of the GNU General Public +# License. See the file "COPYING" in the main directory of this archive +# for more details. +# + +targets := wakeup.bin wakeup.elf + +wakeup-y += wakeup.o wakemain.o video-mode.o copy.o + +# The link order of the video-*.o modules can matter. In particular, +# video-vga.o *must* be listed first, followed by video-vesa.o. +# Hardware-specific drivers should follow in the order they should be +# probed, and video-bios.o should typically be last. +wakeup-y += video-vga.o +wakeup-y += video-vesa.o +wakeup-y += video-bios.o + +targets += $(wakeup-y) + +bootsrc := $(src)/../../../boot + +# --------------------------------------------------------------------------- + +# How to compile the 16-bit code. Note we always compile for -march=i386, +# that way we can complain to the user if the CPU is insufficient. +# Compile with _SETUP since this is similar to the boot-time setup code. +KBUILD_CFLAGS := $(LINUXINCLUDE) -g -Os -D_SETUP -D_WAKEUP -D__KERNEL__ \ + -I$(srctree)/$(bootsrc) \ + $(cflags-y) \ + -Wall -Wstrict-prototypes \ + -march=i386 -mregparm=3 \ + -include $(srctree)/$(bootsrc)/code16gcc.h \ + -fno-strict-aliasing -fomit-frame-pointer \ + $(call cc-option, -ffreestanding) \ + $(call cc-option, -fno-toplevel-reorder,\ + $(call cc-option, -fno-unit-at-a-time)) \ + $(call cc-option, -fno-stack-protector) \ + $(call cc-option, -mpreferred-stack-boundary=2) +KBUILD_CFLAGS += $(call cc-option, -m32) +KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ + +WAKEUP_OBJS = $(addprefix $(obj)/,$(wakeup-y)) + +LDFLAGS_wakeup.elf := -T + +CPPFLAGS_wakeup.lds += -P -C + +$(obj)/wakeup.elf: $(src)/wakeup.lds $(WAKEUP_OBJS) FORCE + $(call if_changed,ld) + +OBJCOPYFLAGS_wakeup.bin := -O binary + +$(obj)/wakeup.bin: $(obj)/wakeup.elf FORCE + $(call if_changed,objcopy) diff --git a/arch/x86/kernel/acpi/realmode/copy.S b/arch/x86/kernel/acpi/realmode/copy.S new file mode 100644 index 000000000000..dc59ebee69d8 --- /dev/null +++ b/arch/x86/kernel/acpi/realmode/copy.S @@ -0,0 +1 @@ +#include "../../../boot/copy.S" diff --git a/arch/x86/kernel/acpi/realmode/video-bios.c b/arch/x86/kernel/acpi/realmode/video-bios.c new file mode 100644 index 000000000000..7deabc144a27 --- /dev/null +++ b/arch/x86/kernel/acpi/realmode/video-bios.c @@ -0,0 +1 @@ +#include "../../../boot/video-bios.c" diff --git a/arch/x86/kernel/acpi/realmode/video-mode.c b/arch/x86/kernel/acpi/realmode/video-mode.c new file mode 100644 index 000000000000..328ad209f113 --- /dev/null +++ b/arch/x86/kernel/acpi/realmode/video-mode.c @@ -0,0 +1 @@ +#include "../../../boot/video-mode.c" diff --git a/arch/x86/kernel/acpi/realmode/video-vesa.c b/arch/x86/kernel/acpi/realmode/video-vesa.c new file mode 100644 index 000000000000..9dbb9672226a --- /dev/null +++ b/arch/x86/kernel/acpi/realmode/video-vesa.c @@ -0,0 +1 @@ +#include "../../../boot/video-vesa.c" diff --git a/arch/x86/kernel/acpi/realmode/video-vga.c b/arch/x86/kernel/acpi/realmode/video-vga.c new file mode 100644 index 000000000000..bcc81255f374 --- /dev/null +++ b/arch/x86/kernel/acpi/realmode/video-vga.c @@ -0,0 +1 @@ +#include "../../../boot/video-vga.c" diff --git a/arch/x86/kernel/acpi/realmode/wakemain.c b/arch/x86/kernel/acpi/realmode/wakemain.c new file mode 100644 index 000000000000..883962d9eef2 --- /dev/null +++ b/arch/x86/kernel/acpi/realmode/wakemain.c @@ -0,0 +1,81 @@ +#include "wakeup.h" +#include "boot.h" + +static void udelay(int loops) +{ + while (loops--) + io_delay(); /* Approximately 1 us */ +} + +static void beep(unsigned int hz) +{ + u8 enable; + + if (!hz) { + enable = 0x00; /* Turn off speaker */ + } else { + u16 div = 1193181/hz; + + outb(0xb6, 0x43); /* Ctr 2, squarewave, load, binary */ + io_delay(); + outb(div, 0x42); /* LSB of counter */ + io_delay(); + outb(div >> 8, 0x42); /* MSB of counter */ + io_delay(); + + enable = 0x03; /* Turn on speaker */ + } + inb(0x61); /* Dummy read of System Control Port B */ + io_delay(); + outb(enable, 0x61); /* Enable timer 2 output to speaker */ + io_delay(); +} + +#define DOT_HZ 880 +#define DASH_HZ 587 +#define US_PER_DOT 125000 + +/* Okay, this is totally silly, but it's kind of fun. */ +static void send_morse(const char *pattern) +{ + char s; + + while ((s = *pattern++)) { + switch (s) { + case '.': + beep(DOT_HZ); + udelay(US_PER_DOT); + beep(0); + udelay(US_PER_DOT); + break; + case '-': + beep(DASH_HZ); + udelay(US_PER_DOT * 3); + beep(0); + udelay(US_PER_DOT); + break; + default: /* Assume it's a space */ + udelay(US_PER_DOT * 3); + break; + } + } +} + +void main(void) +{ + /* Kill machine if structures are wrong */ + if (wakeup_header.real_magic != 0x12345678) + while (1); + + if (wakeup_header.realmode_flags & 4) + send_morse("...-"); + + if (wakeup_header.realmode_flags & 1) + asm volatile("lcallw $0xc000,$3"); + + if (wakeup_header.realmode_flags & 2) { + /* Need to call BIOS */ + probe_cards(0); + set_mode(wakeup_header.video_mode); + } +} diff --git a/arch/x86/kernel/acpi/realmode/wakeup.S b/arch/x86/kernel/acpi/realmode/wakeup.S new file mode 100644 index 000000000000..f9b77fb37e5b --- /dev/null +++ b/arch/x86/kernel/acpi/realmode/wakeup.S @@ -0,0 +1,113 @@ +/* + * ACPI wakeup real mode startup stub + */ +#include <asm/segment.h> +#include <asm/msr-index.h> +#include <asm/page.h> +#include <asm/pgtable.h> + + .code16 + .section ".header", "a" + +/* This should match the structure in wakeup.h */ + .globl wakeup_header +wakeup_header: +video_mode: .short 0 /* Video mode number */ +pmode_return: .byte 0x66, 0xea /* ljmpl */ + .long 0 /* offset goes here */ + .short __KERNEL_CS +pmode_cr0: .long 0 /* Saved %cr0 */ +pmode_cr3: .long 0 /* Saved %cr3 */ +pmode_cr4: .long 0 /* Saved %cr4 */ +pmode_efer: .quad 0 /* Saved EFER */ +pmode_gdt: .quad 0 +realmode_flags: .long 0 +real_magic: .long 0 +trampoline_segment: .word 0 +signature: .long 0x51ee1111 + + .text + .globl _start + .code16 +wakeup_code: +_start: + cli + cld + + /* Set up segments */ + movw %cs, %ax + movw %ax, %ds + movw %ax, %es + movw %ax, %ss + + movl $wakeup_stack_end, %esp + + /* Clear the EFLAGS */ + pushl $0 + popfl + + /* Check header signature... */ + movl signature, %eax + cmpl $0x51ee1111, %eax + jne bogus_real_magic + + /* Check we really have everything... */ + movl end_signature, %eax + cmpl $0x65a22c82, %eax + jne bogus_real_magic + + /* Call the C code */ + calll main + + /* Do any other stuff... */ + +#ifndef CONFIG_64BIT + /* This could also be done in C code... */ + movl pmode_cr3, %eax + movl %eax, %cr3 + + movl pmode_cr4, %ecx + jecxz 1f + movl %ecx, %cr4 +1: + movl pmode_efer, %eax + movl pmode_efer + 4, %edx + movl %eax, %ecx + orl %edx, %ecx + jz 1f + movl $0xc0000080, %ecx + wrmsr +1: + + lgdtl pmode_gdt + + /* This really couldn't... */ + movl pmode_cr0, %eax + movl %eax, %cr0 + jmp pmode_return +#else + pushw $0 + pushw trampoline_segment + pushw $0 + lret +#endif + +bogus_real_magic: +1: + hlt + jmp 1b + + .data + .balign 4 + .globl HEAP, heap_end +HEAP: + .long wakeup_heap +heap_end: + .long wakeup_stack + + .bss +wakeup_heap: + .space 2048 +wakeup_stack: + .space 2048 +wakeup_stack_end: diff --git a/arch/x86/kernel/acpi/realmode/wakeup.h b/arch/x86/kernel/acpi/realmode/wakeup.h new file mode 100644 index 000000000000..ef8166fe8020 --- /dev/null +++ b/arch/x86/kernel/acpi/realmode/wakeup.h @@ -0,0 +1,36 @@ +/* + * Definitions for the wakeup data structure at the head of the + * wakeup code. + */ + +#ifndef ARCH_X86_KERNEL_ACPI_RM_WAKEUP_H +#define ARCH_X86_KERNEL_ACPI_RM_WAKEUP_H + +#ifndef __ASSEMBLY__ +#include <linux/types.h> + +/* This must match data at wakeup.S */ +struct wakeup_header { + u16 video_mode; /* Video mode number */ + u16 _jmp1; /* ljmpl opcode, 32-bit only */ + u32 pmode_entry; /* Protected mode resume point, 32-bit only */ + u16 _jmp2; /* CS value, 32-bit only */ + u32 pmode_cr0; /* Protected mode cr0 */ + u32 pmode_cr3; /* Protected mode cr3 */ + u32 pmode_cr4; /* Protected mode cr4 */ + u32 pmode_efer_low; /* Protected mode EFER */ + u32 pmode_efer_high; + u64 pmode_gdt; + u32 realmode_flags; + u32 real_magic; + u16 trampoline_segment; /* segment with trampoline code, 64-bit only */ + u32 signature; /* To check we have correct structure */ +} __attribute__((__packed__)); + +extern struct wakeup_header wakeup_header; +#endif + +#define HEADER_OFFSET 0x3f00 +#define WAKEUP_SIZE 0x4000 + +#endif /* ARCH_X86_KERNEL_ACPI_RM_WAKEUP_H */ diff --git a/arch/x86/kernel/acpi/realmode/wakeup.lds.S b/arch/x86/kernel/acpi/realmode/wakeup.lds.S new file mode 100644 index 000000000000..22fab6c4be15 --- /dev/null +++ b/arch/x86/kernel/acpi/realmode/wakeup.lds.S @@ -0,0 +1,61 @@ +/* + * wakeup.ld + * + * Linker script for the real-mode wakeup code + */ +#undef i386 +#include "wakeup.h" + +OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386") +OUTPUT_ARCH(i386) +ENTRY(_start) + +SECTIONS +{ + . = HEADER_OFFSET; + .header : { + *(.header) + } + + . = 0; + .text : { + *(.text*) + } + + . = ALIGN(16); + .rodata : { + *(.rodata*) + } + + .videocards : { + video_cards = .; + *(.videocards) + video_cards_end = .; + } + + . = ALIGN(16); + .data : { + *(.data*) + } + + .signature : { + end_signature = .; + LONG(0x65a22c82) + } + + . = ALIGN(16); + .bss : { + __bss_start = .; + *(.bss) + __bss_end = .; + } + + . = ALIGN(16); + _end = .; + + /DISCARD/ : { + *(.note*) + } + + . = ASSERT(_end <= WAKEUP_SIZE, "Wakeup too big!"); +} diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 6bc815cd8cb3..afc25ee9964b 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -10,30 +10,72 @@ #include <linux/dmi.h> #include <linux/cpumask.h> -#include <asm/smp.h> +#include "realmode/wakeup.h" +#include "sleep.h" -/* address in low memory of the wakeup routine. */ -unsigned long acpi_wakeup_address = 0; +unsigned long acpi_wakeup_address; unsigned long acpi_realmode_flags; -extern char wakeup_start, wakeup_end; -extern unsigned long acpi_copy_wakeup_routine(unsigned long); +/* address in low memory of the wakeup routine. */ +static unsigned long acpi_realmode; + +#ifdef CONFIG_64BIT +static char temp_stack[10240]; +#endif /** * acpi_save_state_mem - save kernel state * * Create an identity mapped page table and copy the wakeup routine to * low memory. + * + * Note that this is too late to change acpi_wakeup_address. */ int acpi_save_state_mem(void) { - if (!acpi_wakeup_address) { - printk(KERN_ERR "Could not allocate memory during boot, S3 disabled\n"); + struct wakeup_header *header; + + if (!acpi_realmode) { + printk(KERN_ERR "Could not allocate memory during boot, " + "S3 disabled\n"); return -ENOMEM; } - memcpy((void *)acpi_wakeup_address, &wakeup_start, - &wakeup_end - &wakeup_start); - acpi_copy_wakeup_routine(acpi_wakeup_address); + memcpy((void *)acpi_realmode, &wakeup_code_start, WAKEUP_SIZE); + + header = (struct wakeup_header *)(acpi_realmode + HEADER_OFFSET); + if (header->signature != 0x51ee1111) { + printk(KERN_ERR "wakeup header does not match\n"); + return -EINVAL; + } + + header->video_mode = saved_video_mode; + +#ifndef CONFIG_64BIT + store_gdt((struct desc_ptr *)&header->pmode_gdt); + + header->pmode_efer_low = nx_enabled; + if (header->pmode_efer_low & 1) { + /* This is strange, why not save efer, always? */ + rdmsr(MSR_EFER, header->pmode_efer_low, + header->pmode_efer_high); + } +#endif /* !CONFIG_64BIT */ + + header->pmode_cr0 = read_cr0(); + header->pmode_cr4 = read_cr4(); + header->realmode_flags = acpi_realmode_flags; + header->real_magic = 0x12345678; + +#ifndef CONFIG_64BIT + header->pmode_entry = (u32)&wakeup_pmode_return; + header->pmode_cr3 = (u32)(swsusp_pg_dir - __PAGE_OFFSET); + saved_magic = 0x12345678; +#else /* CONFIG_64BIT */ + header->trampoline_segment = setup_trampoline() >> 4; + init_rsp = (unsigned long)temp_stack + 4096; + initial_code = (unsigned long)wakeup_long64; + saved_magic = 0x123456789abcdef0; +#endif /* CONFIG_64BIT */ return 0; } @@ -56,15 +98,20 @@ void acpi_restore_state_mem(void) */ void __init acpi_reserve_bootmem(void) { - if ((&wakeup_end - &wakeup_start) > PAGE_SIZE*2) { + if ((&wakeup_code_end - &wakeup_code_start) > WAKEUP_SIZE) { printk(KERN_ERR "ACPI: Wakeup code way too big, S3 disabled.\n"); return; } - acpi_wakeup_address = (unsigned long)alloc_bootmem_low(PAGE_SIZE*2); - if (!acpi_wakeup_address) + acpi_realmode = (unsigned long)alloc_bootmem_low(WAKEUP_SIZE); + + if (!acpi_realmode) { printk(KERN_ERR "ACPI: Cannot allocate lowmem, S3 disabled.\n"); + return; + } + + acpi_wakeup_address = acpi_realmode; } diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h new file mode 100644 index 000000000000..adbcbaa6f1df --- /dev/null +++ b/arch/x86/kernel/acpi/sleep.h @@ -0,0 +1,16 @@ +/* + * Variables and functions used by the code in sleep.c + */ + +#include <asm/trampoline.h> + +extern char wakeup_code_start, wakeup_code_end; + +extern unsigned long saved_video_mode; +extern long saved_magic; + +extern int wakeup_pmode_return; +extern char swsusp_pg_dir[PAGE_SIZE]; + +extern unsigned long acpi_copy_wakeup_routine(unsigned long); +extern void wakeup_long64(void); diff --git a/arch/x86/kernel/acpi/sleep_32.c b/arch/x86/kernel/acpi/sleep_32.c deleted file mode 100644 index 63fe5525e026..000000000000 --- a/arch/x86/kernel/acpi/sleep_32.c +++ /dev/null @@ -1,40 +0,0 @@ -/* - * sleep.c - x86-specific ACPI sleep support. - * - * Copyright (C) 2001-2003 Patrick Mochel - * Copyright (C) 2001-2003 Pavel Machek <pavel@suse.cz> - */ - -#include <linux/acpi.h> -#include <linux/bootmem.h> -#include <linux/dmi.h> -#include <linux/cpumask.h> - -#include <asm/smp.h> - -/* Ouch, we want to delete this. We already have better version in userspace, in - s2ram from suspend.sf.net project */ -static __init int reset_videomode_after_s3(const struct dmi_system_id *d) -{ - acpi_realmode_flags |= 2; - return 0; -} - -static __initdata struct dmi_system_id acpisleep_dmi_table[] = { - { /* Reset video mode after returning from ACPI S3 sleep */ - .callback = reset_videomode_after_s3, - .ident = "Toshiba Satellite 4030cdt", - .matches = { - DMI_MATCH(DMI_PRODUCT_NAME, "S4030CDT/4.3"), - }, - }, - {} -}; - -static int __init acpisleep_dmi_init(void) -{ - dmi_check_system(acpisleep_dmi_table); - return 0; -} - -core_initcall(acpisleep_dmi_init); diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S index f53e3277f8e5..a12e6a9fb659 100644 --- a/arch/x86/kernel/acpi/wakeup_32.S +++ b/arch/x86/kernel/acpi/wakeup_32.S @@ -3,178 +3,12 @@ #include <asm/segment.h> #include <asm/page.h> -# -# wakeup_code runs in real mode, and at unknown address (determined at run-time). -# Therefore it must only use relative jumps/calls. -# -# Do we need to deal with A20? It is okay: ACPI specs says A20 must be enabled -# -# If physical address of wakeup_code is 0x12345, BIOS should call us with -# cs = 0x1234, eip = 0x05 -# - -#define BEEP \ - inb $97, %al; \ - outb %al, $0x80; \ - movb $3, %al; \ - outb %al, $97; \ - outb %al, $0x80; \ - movb $-74, %al; \ - outb %al, $67; \ - outb %al, $0x80; \ - movb $-119, %al; \ - outb %al, $66; \ - outb %al, $0x80; \ - movb $15, %al; \ - outb %al, $66; - -ALIGN - .align 4096 -ENTRY(wakeup_start) -wakeup_code: - wakeup_code_start = . - .code16 - - cli - cld - - # setup data segment - movw %cs, %ax - movw %ax, %ds # Make ds:0 point to wakeup_start - movw %ax, %ss - - testl $4, realmode_flags - wakeup_code - jz 1f - BEEP -1: - mov $(wakeup_stack - wakeup_code), %sp # Private stack is needed for ASUS board - - pushl $0 # Kill any dangerous flags - popfl - - movl real_magic - wakeup_code, %eax - cmpl $0x12345678, %eax - jne bogus_real_magic - - testl $1, realmode_flags - wakeup_code - jz 1f - lcall $0xc000,$3 - movw %cs, %ax - movw %ax, %ds # Bios might have played with that - movw %ax, %ss -1: - - testl $2, realmode_flags - wakeup_code - jz 1f - mov video_mode - wakeup_code, %ax - call mode_set -1: - - # set up page table - movl $swsusp_pg_dir-__PAGE_OFFSET, %eax - movl %eax, %cr3 - - testl $1, real_efer_save_restore - wakeup_code - jz 4f - # restore efer setting - movl real_save_efer_edx - wakeup_code, %edx - movl real_save_efer_eax - wakeup_code, %eax - mov $0xc0000080, %ecx - wrmsr -4: - # make sure %cr4 is set correctly (features, etc) - movl real_save_cr4 - wakeup_code, %eax - movl %eax, %cr4 - - # need a gdt -- use lgdtl to force 32-bit operands, in case - # the GDT is located past 16 megabytes. - lgdtl real_save_gdt - wakeup_code - - movl real_save_cr0 - wakeup_code, %eax - movl %eax, %cr0 - jmp 1f -1: - movl real_magic - wakeup_code, %eax - cmpl $0x12345678, %eax - jne bogus_real_magic - - testl $8, realmode_flags - wakeup_code - jz 1f - BEEP -1: - ljmpl $__KERNEL_CS, $wakeup_pmode_return - -real_save_gdt: .word 0 - .long 0 -real_save_cr0: .long 0 -real_save_cr3: .long 0 -real_save_cr4: .long 0 -real_magic: .long 0 -video_mode: .long 0 -realmode_flags: .long 0 -real_efer_save_restore: .long 0 -real_save_efer_edx: .long 0 -real_save_efer_eax: .long 0 - -bogus_real_magic: - jmp bogus_real_magic - -/* This code uses an extended set of video mode numbers. These include: - * Aliases for standard modes - * NORMAL_VGA (-1) - * EXTENDED_VGA (-2) - * ASK_VGA (-3) - * Video modes numbered by menu position -- NOT RECOMMENDED because of lack - * of compatibility when extending the table. These are between 0x00 and 0xff. - */ -#define VIDEO_FIRST_MENU 0x0000 - -/* Standard BIOS video modes (BIOS number + 0x0100) */ -#define VIDEO_FIRST_BIOS 0x0100 - -/* VESA BIOS video modes (VESA number + 0x0200) */ -#define VIDEO_FIRST_VESA 0x0200 - -/* Video7 special modes (BIOS number + 0x0900) */ -#define VIDEO_FIRST_V7 0x0900 - -# Setting of user mode (AX=mode ID) => CF=success - -# For now, we only handle VESA modes (0x0200..0x03ff). To handle other -# modes, we should probably compile in the video code from the boot -# directory. -mode_set: - movw %ax, %bx - subb $VIDEO_FIRST_VESA>>8, %bh - cmpb $2, %bh - jb check_vesa - -setbad: - clc - ret - -check_vesa: - orw $0x4000, %bx # Use linear frame buffer - movw $0x4f02, %ax # VESA BIOS mode set call - int $0x10 - cmpw $0x004f, %ax # AL=4f if implemented - jnz setbad # AH=0 if OK - - stc - ret +# Copyright 2003, 2008 Pavel Machek <pavel@suse.cz>, distribute under GPLv2 .code32 ALIGN -.org 0x800 -wakeup_stack_begin: # Stack grows down - -.org 0xff0 # Just below end of page -wakeup_stack: -ENTRY(wakeup_end) - -.org 0x1000 - +ENTRY(wakeup_pmode_return) wakeup_pmode_return: movw $__KERNEL_DS, %ax movw %ax, %ss @@ -187,7 +21,7 @@ wakeup_pmode_return: lgdt saved_gdt lidt saved_idt lldt saved_ldt - ljmp $(__KERNEL_CS),$1f + ljmp $(__KERNEL_CS), $1f 1: movl %cr3, %eax movl %eax, %cr3 @@ -201,82 +35,41 @@ wakeup_pmode_return: jne bogus_magic # jump to place where we left off - movl saved_eip,%eax + movl saved_eip, %eax jmp *%eax bogus_magic: jmp bogus_magic -## -# acpi_copy_wakeup_routine -# -# Copy the above routine to low memory. -# -# Parameters: -# %eax: place to copy wakeup routine to -# -# Returned address is location of code in low memory (past data and stack) -# -ENTRY(acpi_copy_wakeup_routine) - pushl %ebx +save_registers: sgdt saved_gdt sidt saved_idt sldt saved_ldt str saved_tss - movl nx_enabled, %edx - movl %edx, real_efer_save_restore - wakeup_start (%eax) - testl $1, real_efer_save_restore - wakeup_start (%eax) - jz 2f - # save efer setting - pushl %eax - movl %eax, %ebx - mov $0xc0000080, %ecx - rdmsr - movl %edx, real_save_efer_edx - wakeup_start (%ebx) - movl %eax, real_save_efer_eax - wakeup_start (%ebx) - popl %eax -2: - - movl %cr3, %edx - movl %edx, real_save_cr3 - wakeup_start (%eax) - movl %cr4, %edx - movl %edx, real_save_cr4 - wakeup_start (%eax) - movl %cr0, %edx - movl %edx, real_save_cr0 - wakeup_start (%eax) - sgdt real_save_gdt - wakeup_start (%eax) - - movl saved_videomode, %edx - movl %edx, video_mode - wakeup_start (%eax) - movl acpi_realmode_flags, %edx - movl %edx, realmode_flags - wakeup_start (%eax) - movl $0x12345678, real_magic - wakeup_start (%eax) - movl $0x12345678, saved_magic - popl %ebx - ret - -save_registers: leal 4(%esp), %eax movl %eax, saved_context_esp - movl %ebx, saved_context_ebx - movl %ebp, saved_context_ebp - movl %esi, saved_context_esi - movl %edi, saved_context_edi - pushfl ; popl saved_context_eflags - - movl $ret_point, saved_eip + movl %ebx, saved_context_ebx + movl %ebp, saved_context_ebp + movl %esi, saved_context_esi + movl %edi, saved_context_edi + pushfl + popl saved_context_eflags + + movl $ret_point, saved_eip ret restore_registers: - movl saved_context_ebp, %ebp - movl saved_context_ebx, %ebx - movl saved_context_esi, %esi - movl saved_context_edi, %edi - pushl saved_context_eflags ; popfl - ret + movl saved_context_ebp, %ebp + movl saved_context_ebx, %ebx + movl saved_context_esi, %esi + movl saved_context_edi, %edi + pushl saved_context_eflags + popfl + ret ENTRY(do_suspend_lowlevel) call save_processor_state diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index 2e1b9e0d0767..bcc293423a70 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -7,191 +7,18 @@ #include <asm/asm-offsets.h> # Copyright 2003 Pavel Machek <pavel@suse.cz>, distribute under GPLv2 -# -# wakeup_code runs in real mode, and at unknown address (determined at run-time). -# Therefore it must only use relative jumps/calls. -# -# Do we need to deal with A20? It is okay: ACPI specs says A20 must be enabled -# -# If physical address of wakeup_code is 0x12345, BIOS should call us with -# cs = 0x1234, eip = 0x05 -# - -#define BEEP \ - inb $97, %al; \ - outb %al, $0x80; \ - movb $3, %al; \ - outb %al, $97; \ - outb %al, $0x80; \ - movb $-74, %al; \ - outb %al, $67; \ - outb %al, $0x80; \ - movb $-119, %al; \ - outb %al, $66; \ - outb %al, $0x80; \ - movb $15, %al; \ - outb %al, $66; - - -ALIGN - .align 16 -ENTRY(wakeup_start) -wakeup_code: - wakeup_code_start = . - .code16 - -# Running in *copy* of this code, somewhere in low 1MB. - - cli - cld - # setup data segment - movw %cs, %ax - movw %ax, %ds # Make ds:0 point to wakeup_start - movw %ax, %ss - - # Data segment must be set up before we can see whether to beep. - testl $4, realmode_flags - wakeup_code - jz 1f - BEEP -1: - - # Private stack is needed for ASUS board - mov $(wakeup_stack - wakeup_code), %sp - - pushl $0 # Kill any dangerous flags - popfl - - movl real_magic - wakeup_code, %eax - cmpl $0x12345678, %eax - jne bogus_real_magic - - testl $1, realmode_flags - wakeup_code - jz 1f - lcall $0xc000,$3 - movw %cs, %ax - movw %ax, %ds # Bios might have played with that - movw %ax, %ss -1: - - testl $2, realmode_flags - wakeup_code - jz 1f - mov video_mode - wakeup_code, %ax - call mode_set -1: - - mov %ds, %ax # Find 32bit wakeup_code addr - movzx %ax, %esi # (Convert %ds:gdt to a liner ptr) - shll $4, %esi - # Fix up the vectors - addl %esi, wakeup_32_vector - wakeup_code - addl %esi, wakeup_long64_vector - wakeup_code - addl %esi, gdt_48a + 2 - wakeup_code # Fixup the gdt pointer - - lidtl %ds:idt_48a - wakeup_code - lgdtl %ds:gdt_48a - wakeup_code # load gdt with whatever is - # appropriate - - movl $1, %eax # protected mode (PE) bit - lmsw %ax # This is it! - jmp 1f -1: - - ljmpl *(wakeup_32_vector - wakeup_code) - - .balign 4 -wakeup_32_vector: - .long wakeup_32 - wakeup_code - .word __KERNEL32_CS, 0 - - .code32 -wakeup_32: -# Running in this code, but at low address; paging is not yet turned on. - - movl $__KERNEL_DS, %eax - movl %eax, %ds - - /* - * Prepare for entering 64bits mode - */ - - /* Enable PAE */ - xorl %eax, %eax - btsl $5, %eax - movl %eax, %cr4 - - /* Setup early boot stage 4 level pagetables */ - leal (wakeup_level4_pgt - wakeup_code)(%esi), %eax - movl %eax, %cr3 - - /* Check if nx is implemented */ - movl $0x80000001, %eax - cpuid - movl %edx,%edi - - /* Enable Long Mode */ - xorl %eax, %eax - btsl $_EFER_LME, %eax - - /* No Execute supported? */ - btl $20,%edi - jnc 1f - btsl $_EFER_NX, %eax - - /* Make changes effective */ -1: movl $MSR_EFER, %ecx - xorl %edx, %edx - wrmsr - - xorl %eax, %eax - btsl $31, %eax /* Enable paging and in turn activate Long Mode */ - btsl $0, %eax /* Enable protected mode */ - - /* Make changes effective */ - movl %eax, %cr0 - - /* At this point: - CR4.PAE must be 1 - CS.L must be 0 - CR3 must point to PML4 - Next instruction must be a branch - This must be on identity-mapped page - */ - /* - * At this point we're in long mode but in 32bit compatibility mode - * with EFER.LME = 1, CS.L = 0, CS.D = 1 (and in turn - * EFER.LMA = 1). Now we want to jump in 64bit mode, to do that we load - * the new gdt/idt that has __KERNEL_CS with CS.L = 1. - */ - - /* Finally jump in 64bit mode */ - ljmp *(wakeup_long64_vector - wakeup_code)(%esi) - - .balign 4 -wakeup_long64_vector: - .long wakeup_long64 - wakeup_code - .word __KERNEL_CS, 0 .code64 - - /* Hooray, we are in Long 64-bit mode (but still running in - * low memory) - */ -wakeup_long64: /* - * We must switch to a new descriptor in kernel space for the GDT - * because soon the kernel won't have access anymore to the userspace - * addresses where we're currently running on. We have to do that here - * because in 32bit we couldn't load a 64bit linear address. + * Hooray, we are in Long 64-bit mode (but still running in low memory) */ - lgdt cpu_gdt_descr - - movq saved_magic, %rax - movq $0x123456789abcdef0, %rdx - cmpq %rdx, %rax - jne bogus_64_magic +ENTRY(wakeup_long64) +wakeup_long64: + movq saved_magic, %rax + movq $0x123456789abcdef0, %rdx + cmpq %rdx, %rax + jne bogus_64_magic - nop - nop movw $__KERNEL_DS, %ax movw %ax, %ss movw %ax, %ds @@ -208,130 +35,8 @@ wakeup_long64: movq saved_rip, %rax jmp *%rax -.code32 - - .align 64 -gdta: - /* Its good to keep gdt in sync with one in trampoline.S */ - .word 0, 0, 0, 0 # dummy - /* ??? Why I need the accessed bit set in order for this to work? */ - .quad 0x00cf9b000000ffff # __KERNEL32_CS - .quad 0x00af9b000000ffff # __KERNEL_CS - .quad 0x00cf93000000ffff # __KERNEL_DS - -idt_48a: - .word 0 # idt limit = 0 - .word 0, 0 # idt base = 0L - -gdt_48a: - .word 0x800 # gdt limit=2048, - # 256 GDT entries - .long gdta - wakeup_code # gdt base (relocated in later) - -real_magic: .quad 0 -video_mode: .quad 0 -realmode_flags: .quad 0 - -.code16 -bogus_real_magic: - jmp bogus_real_magic - -.code64 bogus_64_magic: - jmp bogus_64_magic - -/* This code uses an extended set of video mode numbers. These include: - * Aliases for standard modes - * NORMAL_VGA (-1) - * EXTENDED_VGA (-2) - * ASK_VGA (-3) - * Video modes numbered by menu position -- NOT RECOMMENDED because of lack - * of compatibility when extending the table. These are between 0x00 and 0xff. - */ -#define VIDEO_FIRST_MENU 0x0000 - -/* Standard BIOS video modes (BIOS number + 0x0100) */ -#define VIDEO_FIRST_BIOS 0x0100 - -/* VESA BIOS video modes (VESA number + 0x0200) */ -#define VIDEO_FIRST_VESA 0x0200 - -/* Video7 special modes (BIOS number + 0x0900) */ -#define VIDEO_FIRST_V7 0x0900 - -# Setting of user mode (AX=mode ID) => CF=success - -# For now, we only handle VESA modes (0x0200..0x03ff). To handle other -# modes, we should probably compile in the video code from the boot -# directory. -.code16 -mode_set: - movw %ax, %bx - subb $VIDEO_FIRST_VESA>>8, %bh - cmpb $2, %bh - jb check_vesa - -setbad: - clc - ret - -check_vesa: - orw $0x4000, %bx # Use linear frame buffer - movw $0x4f02, %ax # VESA BIOS mode set call - int $0x10 - cmpw $0x004f, %ax # AL=4f if implemented - jnz setbad # AH=0 if OK - - stc - ret - -wakeup_stack_begin: # Stack grows down - -.org 0xff0 -wakeup_stack: # Just below end of page - -.org 0x1000 -ENTRY(wakeup_level4_pgt) - .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE - .fill 510,8,0 - /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */ - .quad level3_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE - -ENTRY(wakeup_end) - -## -# acpi_copy_wakeup_routine -# -# Copy the above routine to low memory. -# -# Parameters: -# %rdi: place to copy wakeup routine to -# -# Returned address is location of code in low memory (past data and stack) -# - .code64 -ENTRY(acpi_copy_wakeup_routine) - pushq %rax - pushq %rdx - - movl saved_video_mode, %edx - movl %edx, video_mode - wakeup_start (,%rdi) - movl acpi_realmode_flags, %edx - movl %edx, realmode_flags - wakeup_start (,%rdi) - movq $0x12345678, real_magic - wakeup_start (,%rdi) - movq $0x123456789abcdef0, %rdx - movq %rdx, saved_magic - - movq saved_magic, %rax - movq $0x123456789abcdef0, %rdx - cmpq %rdx, %rax - jne bogus_64_magic - - # restore the regs we used - popq %rdx - popq %rax -ENTRY(do_suspend_lowlevel_s4bios) - ret + jmp bogus_64_magic .align 2 .p2align 4,,15 @@ -414,7 +119,7 @@ do_suspend_lowlevel: jmp restore_processor_state .LFE5: .Lfe5: - .size do_suspend_lowlevel,.Lfe5-do_suspend_lowlevel + .size do_suspend_lowlevel, .Lfe5-do_suspend_lowlevel .data ALIGN diff --git a/arch/x86/kernel/acpi/wakeup_rm.S b/arch/x86/kernel/acpi/wakeup_rm.S new file mode 100644 index 000000000000..6ff3b5730575 --- /dev/null +++ b/arch/x86/kernel/acpi/wakeup_rm.S @@ -0,0 +1,10 @@ +/* + * Wrapper script for the realmode binary as a transport object + * before copying to low memory. + */ + .section ".rodata","a" + .globl wakeup_code_start, wakeup_code_end +wakeup_code_start: + .incbin "arch/x86/kernel/acpi/realmode/wakeup.bin" +wakeup_code_end: + .size wakeup_code_start, .-wakeup_code_start diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 5fed98ca0e1f..65c7857a90dd 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -11,6 +11,8 @@ #include <asm/mce.h> #include <asm/nmi.h> #include <asm/vsyscall.h> +#include <asm/cacheflush.h> +#include <asm/io.h> #define MAX_PATCH_LEN (255-1) @@ -177,7 +179,7 @@ static const unsigned char*const * find_nop_table(void) #endif /* CONFIG_X86_64 */ /* Use this to add nops to a buffer, then text_poke the whole buffer. */ -static void add_nops(void *insns, unsigned int len) +void add_nops(void *insns, unsigned int len) { const unsigned char *const *noptable = find_nop_table(); @@ -190,6 +192,7 @@ static void add_nops(void *insns, unsigned int len) len -= noplen; } } +EXPORT_SYMBOL_GPL(add_nops); extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; extern u8 *__smp_locks[], *__smp_locks_end[]; @@ -205,7 +208,7 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end) struct alt_instr *a; char insnbuf[MAX_PATCH_LEN]; - DPRINTK("%s: alt table %p -> %p\n", __FUNCTION__, start, end); + DPRINTK("%s: alt table %p -> %p\n", __func__, start, end); for (a = start; a < end; a++) { u8 *instr = a->instr; BUG_ON(a->replacementlen > a->instrlen); @@ -217,13 +220,13 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end) if (instr >= (u8 *)VSYSCALL_START && instr < (u8*)VSYSCALL_END) { instr = __va(instr - (u8*)VSYSCALL_START + (u8*)__pa_symbol(&__vsyscall_0)); DPRINTK("%s: vsyscall fixup: %p => %p\n", - __FUNCTION__, a->instr, instr); + __func__, a->instr, instr); } #endif memcpy(insnbuf, a->replacement, a->replacementlen); add_nops(insnbuf + a->replacementlen, a->instrlen - a->replacementlen); - text_poke(instr, insnbuf, a->instrlen); + text_poke_early(instr, insnbuf, a->instrlen); } } @@ -284,7 +287,6 @@ void alternatives_smp_module_add(struct module *mod, char *name, void *text, void *text_end) { struct smp_alt_module *smp; - unsigned long flags; if (noreplace_smp) return; @@ -307,42 +309,40 @@ void alternatives_smp_module_add(struct module *mod, char *name, smp->text = text; smp->text_end = text_end; DPRINTK("%s: locks %p -> %p, text %p -> %p, name %s\n", - __FUNCTION__, smp->locks, smp->locks_end, + __func__, smp->locks, smp->locks_end, smp->text, smp->text_end, smp->name); - spin_lock_irqsave(&smp_alt, flags); + spin_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_irqrestore(&smp_alt, flags); + spin_unlock(&smp_alt); } void alternatives_smp_module_del(struct module *mod) { struct smp_alt_module *item; - unsigned long flags; if (smp_alt_once || noreplace_smp) return; - spin_lock_irqsave(&smp_alt, flags); + spin_lock(&smp_alt); list_for_each_entry(item, &smp_alt_modules, next) { if (mod != item->mod) continue; list_del(&item->next); - spin_unlock_irqrestore(&smp_alt, flags); - DPRINTK("%s: %s\n", __FUNCTION__, item->name); + spin_unlock(&smp_alt); + DPRINTK("%s: %s\n", __func__, item->name); kfree(item); return; } - spin_unlock_irqrestore(&smp_alt, flags); + spin_unlock(&smp_alt); } void alternatives_smp_switch(int smp) { struct smp_alt_module *mod; - unsigned long flags; #ifdef CONFIG_LOCKDEP /* @@ -359,7 +359,7 @@ void alternatives_smp_switch(int smp) return; BUG_ON(!smp && (num_online_cpus() > 1)); - spin_lock_irqsave(&smp_alt, flags); + spin_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_irqrestore(&smp_alt, flags); + spin_unlock(&smp_alt); } #endif @@ -411,7 +411,7 @@ void apply_paravirt(struct paravirt_patch_site *start, /* Pad the rest with nops */ add_nops(insnbuf + used, p->len - used); - text_poke(p->instr, insnbuf, p->len); + text_poke_early(p->instr, insnbuf, p->len); } } extern struct paravirt_patch_site __start_parainstructions[], @@ -420,8 +420,6 @@ extern struct paravirt_patch_site __start_parainstructions[], void __init alternative_instructions(void) { - unsigned long flags; - /* The patching is not fully atomic, so try to avoid local interruptions that might execute the to be patched code. Other CPUs are not running. */ @@ -430,7 +428,6 @@ void __init alternative_instructions(void) stop_mce(); #endif - local_irq_save(flags); apply_alternatives(__alt_instructions, __alt_instructions_end); /* switch to patch-once-at-boottime-only mode and free the @@ -462,7 +459,6 @@ void __init alternative_instructions(void) } #endif apply_paravirt(__parainstructions, __parainstructions_end); - local_irq_restore(flags); if (smp_alt_once) free_init_pages("SMP alternatives", @@ -475,18 +471,70 @@ void __init alternative_instructions(void) #endif } -/* - * Warning: +/** + * text_poke_early - Update instructions on a live kernel at boot time + * @addr: address to modify + * @opcode: source of the copy + * @len: length to copy + * * When you use this code to patch more than one byte of an instruction * you need to make sure that other CPUs cannot execute this code in parallel. - * Also no thread must be currently preempted in the middle of these instructions. - * And on the local CPU you need to be protected again NMI or MCE handlers - * seeing an inconsistent instruction while you patch. + * Also no thread must be currently preempted in the middle of these + * instructions. And on the local CPU you need to be protected again NMI or MCE + * handlers seeing an inconsistent instruction while you patch. */ -void __kprobes text_poke(void *addr, unsigned char *opcode, int len) +void *text_poke_early(void *addr, const void *opcode, size_t len) { + unsigned long flags; + local_irq_save(flags); memcpy(addr, opcode, len); + local_irq_restore(flags); + sync_core(); + /* Could also do a CLFLUSH here to speed up CPU recovery; but + that causes hangs on some VIA CPUs. */ + return addr; +} + +/** + * text_poke - Update instructions on a live kernel + * @addr: address to modify + * @opcode: source of the copy + * @len: length to copy + * + * Only atomic text poke/set should be allowed when not doing early patching. + * It means the size must be writable atomically and the address must be aligned + * in a way that permits an atomic write. It also makes sure we fit on a single + * page. + */ +void *__kprobes text_poke(void *addr, const void *opcode, size_t len) +{ + unsigned long flags; + char *vaddr; + int nr_pages = 2; + struct page *pages[2]; + int i; + + if (!core_kernel_text((unsigned long)addr)) { + pages[0] = vmalloc_to_page(addr); + pages[1] = vmalloc_to_page(addr + PAGE_SIZE); + } else { + pages[0] = virt_to_page(addr); + WARN_ON(!PageReserved(pages[0])); + pages[1] = virt_to_page(addr + PAGE_SIZE); + } + BUG_ON(!pages[0]); + if (!pages[1]) + nr_pages = 1; + vaddr = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL); + BUG_ON(!vaddr); + local_irq_save(flags); + memcpy(&vaddr[(unsigned long)addr & ~PAGE_MASK], opcode, len); + local_irq_restore(flags); + vunmap(vaddr); sync_core(); /* Could also do a CLFLUSH here to speed up CPU recovery; but that causes hangs on some VIA CPUs. */ + for (i = 0; i < len; i++) + BUG_ON(((char *)addr)[i] != ((char *)opcode)[i]); + return addr; } diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 00df126169b4..479926d9e004 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -27,11 +27,11 @@ #include <asm/k8.h> int gart_iommu_aperture; -int gart_iommu_aperture_disabled __initdata = 0; -int gart_iommu_aperture_allowed __initdata = 0; +int gart_iommu_aperture_disabled __initdata; +int gart_iommu_aperture_allowed __initdata; int fallback_aper_order __initdata = 1; /* 64MB */ -int fallback_aper_force __initdata = 0; +int fallback_aper_force __initdata; int fix_aperture __initdata = 1; diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c index 35a568ea8400..4b99b1bdeb6c 100644 --- a/arch/x86/kernel/apic_32.c +++ b/arch/x86/kernel/apic_32.c @@ -50,6 +50,11 @@ # error SPURIOUS_APIC_VECTOR definition error #endif +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. * @@ -446,7 +451,8 @@ void __init setup_boot_APIC_clock(void) } /* Calculate the scaled math multiplication factor */ - lapic_clockevent.mult = div_sc(delta, TICK_NSEC * LAPIC_CAL_LOOPS, 32); + lapic_clockevent.mult = div_sc(delta, TICK_NSEC * LAPIC_CAL_LOOPS, + lapic_clockevent.shift); lapic_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFF, &lapic_clockevent); lapic_clockevent.min_delta_ns = @@ -621,6 +627,35 @@ int setup_profiling_timer(unsigned int multiplier) } /* + * Setup extended LVT, AMD specific (K8, family 10h) + * + * Vector mappings are hard coded. On K8 only offset 0 (APIC500) and + * MCE interrupts are supported. Thus MCE offset must be set to 0. + */ + +#define APIC_EILVT_LVTOFF_MCE 0 +#define APIC_EILVT_LVTOFF_IBS 1 + +static void setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask) +{ + unsigned long reg = (lvt_off << 4) + APIC_EILVT0; + unsigned int v = (mask << 16) | (msg_type << 8) | vector; + apic_write(reg, v); +} + +u8 setup_APIC_eilvt_mce(u8 vector, u8 msg_type, u8 mask) +{ + setup_APIC_eilvt(APIC_EILVT_LVTOFF_MCE, vector, msg_type, mask); + return APIC_EILVT_LVTOFF_MCE; +} + +u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask) +{ + setup_APIC_eilvt(APIC_EILVT_LVTOFF_IBS, vector, msg_type, mask); + return APIC_EILVT_LVTOFF_IBS; +} + +/* * Local APIC start and shutdown */ @@ -868,12 +903,50 @@ void __init init_bsp_APIC(void) apic_write_around(APIC_LVT1, value); } +static void __cpuinit lapic_setup_esr(void) +{ + unsigned long oldvalue, value, maxlvt; + if (lapic_is_integrated() && !esr_disable) { + /* !82489DX */ + maxlvt = lapic_get_maxlvt(); + if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */ + apic_write(APIC_ESR, 0); + oldvalue = apic_read(APIC_ESR); + + /* enables sending errors */ + value = ERROR_APIC_VECTOR; + apic_write_around(APIC_LVTERR, value); + /* + * spec says clear errors after enabling vector. + */ + if (maxlvt > 3) + apic_write(APIC_ESR, 0); + value = apic_read(APIC_ESR); + if (value != oldvalue) + apic_printk(APIC_VERBOSE, "ESR value before enabling " + "vector: 0x%08lx after: 0x%08lx\n", + oldvalue, value); + } else { + if (esr_disable) + /* + * Something untraceable is creating bad interrupts on + * secondary quads ... for the moment, just leave the + * ESR disabled - we can't do anything useful with the + * errors anyway - mbligh + */ + printk(KERN_INFO "Leaving ESR disabled.\n"); + else + printk(KERN_INFO "No ESR for 82489DX.\n"); + } +} + + /** * setup_local_APIC - setup the local APIC */ void __cpuinit setup_local_APIC(void) { - unsigned long oldvalue, value, maxlvt, integrated; + unsigned long value, integrated; int i, j; /* Pound the ESR really hard over the head with a big hammer - mbligh */ @@ -997,40 +1070,13 @@ void __cpuinit setup_local_APIC(void) if (!integrated) /* 82489DX */ value |= APIC_LVT_LEVEL_TRIGGER; apic_write_around(APIC_LVT1, value); +} - if (integrated && !esr_disable) { - /* !82489DX */ - maxlvt = lapic_get_maxlvt(); - if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */ - apic_write(APIC_ESR, 0); - oldvalue = apic_read(APIC_ESR); - - /* enables sending errors */ - value = ERROR_APIC_VECTOR; - apic_write_around(APIC_LVTERR, value); - /* - * spec says clear errors after enabling vector. - */ - if (maxlvt > 3) - apic_write(APIC_ESR, 0); - value = apic_read(APIC_ESR); - if (value != oldvalue) - apic_printk(APIC_VERBOSE, "ESR value before enabling " - "vector: 0x%08lx after: 0x%08lx\n", - oldvalue, value); - } else { - if (esr_disable) - /* - * Something untraceable is creating bad interrupts on - * secondary quads ... for the moment, just leave the - * ESR disabled - we can't do anything useful with the - * errors anyway - mbligh - */ - printk(KERN_INFO "Leaving ESR disabled.\n"); - else - printk(KERN_INFO "No ESR for 82489DX.\n"); - } +void __cpuinit end_local_APIC_setup(void) +{ + unsigned long value; + lapic_setup_esr(); /* Disable the local apic timer */ value = apic_read(APIC_LVTT); value |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR); @@ -1147,7 +1193,7 @@ void __init init_apic_mappings(void) * default configuration (or the MP table is broken). */ if (boot_cpu_physical_apicid == -1U) - boot_cpu_physical_apicid = GET_APIC_ID(apic_read(APIC_ID)); + boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id()); #ifdef CONFIG_X86_IO_APIC { @@ -1185,6 +1231,9 @@ fake_ioapic_page: * This initializes the IO-APIC and APIC hardware if this is * a UP kernel. */ + +int apic_version[MAX_APICS]; + int __init APIC_init_uniprocessor(void) { if (enable_local_apic < 0) @@ -1214,12 +1263,13 @@ int __init APIC_init_uniprocessor(void) * might be zero if read from MP tables. Get it from LAPIC. */ #ifdef CONFIG_CRASH_DUMP - boot_cpu_physical_apicid = GET_APIC_ID(apic_read(APIC_ID)); + boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id()); #endif phys_cpu_present_map = physid_mask_of_physid(boot_cpu_physical_apicid); setup_local_APIC(); + end_local_APIC_setup(); #ifdef CONFIG_X86_IO_APIC if (smp_found_config) if (!skip_ioapic_setup && nr_ioapics) @@ -1288,6 +1338,29 @@ void smp_error_interrupt(struct pt_regs *regs) irq_exit(); } +#ifdef CONFIG_SMP +void __init smp_intr_init(void) +{ + /* + * IRQ0 must be given a fixed assignment and initialized, + * because it's used before the IO-APIC is set up. + */ + set_intr_gate(FIRST_DEVICE_VECTOR, interrupt[0]); + + /* + * The reschedule interrupt is a CPU-to-CPU reschedule-helper + * IPI, driven by wakeup. + */ + set_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt); + + /* IPI for invalidation */ + set_intr_gate(INVALIDATE_TLB_VECTOR, invalidate_interrupt); + + /* IPI for generic function call */ + set_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt); +} +#endif + /* * Initialize APIC interrupts */ @@ -1394,6 +1467,88 @@ void disconnect_bsp_APIC(int virt_wire_setup) } } +unsigned int __cpuinitdata maxcpus = NR_CPUS; + +void __cpuinit generic_processor_info(int apicid, int version) +{ + int cpu; + cpumask_t tmp_map; + physid_mask_t phys_cpu; + + /* + * Validate version + */ + if (version == 0x0) { + printk(KERN_WARNING "BIOS bug, APIC version is 0 for CPU#%d! " + "fixing up to 0x10. (tell your hw vendor)\n", + version); + version = 0x10; + } + apic_version[apicid] = version; + + phys_cpu = apicid_to_cpu_present(apicid); + physids_or(phys_cpu_present_map, phys_cpu_present_map, phys_cpu); + + if (num_processors >= NR_CPUS) { + printk(KERN_WARNING "WARNING: NR_CPUS limit of %i reached." + " Processor ignored.\n", NR_CPUS); + return; + } + + if (num_processors >= maxcpus) { + printk(KERN_WARNING "WARNING: maxcpus limit of %i reached." + " Processor ignored.\n", maxcpus); + return; + } + + num_processors++; + cpus_complement(tmp_map, cpu_present_map); + cpu = first_cpu(tmp_map); + + if (apicid == boot_cpu_physical_apicid) + /* + * x86_bios_cpu_apicid is required to have processors listed + * in same order as logical cpu numbers. Hence the first + * entry is BSP, and so on. + */ + cpu = 0; + + /* + * Would be preferable to switch to bigsmp when CONFIG_HOTPLUG_CPU=y + * but we need to work other dependencies like SMP_SUSPEND etc + * before this can be done without some confusion. + * if (CPU_HOTPLUG_ENABLED || num_processors > 8) + * - Ashok Raj <ashok.raj@intel.com> + */ + if (num_processors > 8) { + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_INTEL: + if (!APIC_XAPIC(version)) { + def_to_bigsmp = 0; + break; + } + /* If P4 and above fall through */ + case X86_VENDOR_AMD: + def_to_bigsmp = 1; + } + } +#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; + + cpu_to_apicid[cpu] = apicid; + bios_cpu_apicid[cpu] = apicid; + } else { + per_cpu(x86_cpu_to_apicid, cpu) = apicid; + per_cpu(x86_bios_cpu_apicid, cpu) = apicid; + } +#endif + cpu_set(cpu, cpu_possible_map); + cpu_set(cpu, cpu_present_map); +} + /* * Power management */ diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c index d8d03e09dea2..5910020c3f24 100644 --- a/arch/x86/kernel/apic_64.c +++ b/arch/x86/kernel/apic_64.c @@ -34,13 +34,15 @@ #include <asm/mpspec.h> #include <asm/hpet.h> #include <asm/pgalloc.h> -#include <asm/mach_apic.h> #include <asm/nmi.h> #include <asm/idle.h> #include <asm/proto.h> #include <asm/timex.h> #include <asm/apic.h> +#include <mach_ipi.h> +#include <mach_apic.h> + int disable_apic_timer __cpuinitdata; static int apic_calibrate_pmtmr __initdata; int disable_apic; @@ -83,6 +85,12 @@ static DEFINE_PER_CPU(struct clock_event_device, lapic_events); 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 */ @@ -352,7 +360,8 @@ static void __init calibrate_APIC_clock(void) result / 1000 / 1000, result / 1000 % 1000); /* Calculate the scaled math multiplication factor */ - lapic_clockevent.mult = div_sc(result, NSEC_PER_SEC, 32); + lapic_clockevent.mult = div_sc(result, NSEC_PER_SEC, + lapic_clockevent.shift); lapic_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFF, &lapic_clockevent); lapic_clockevent.min_delta_ns = @@ -421,7 +430,7 @@ void __init setup_boot_APIC_clock(void) * set the DUMMY flag again and force the broadcast mode in the * clockevents layer. */ -void __cpuinit check_boot_apic_timer_broadcast(void) +static void __cpuinit check_boot_apic_timer_broadcast(void) { if (!disable_apic_timer || (lapic_clockevent.features & CLOCK_EVT_FEAT_DUMMY)) @@ -431,7 +440,8 @@ void __cpuinit check_boot_apic_timer_broadcast(void) lapic_clockevent.features |= CLOCK_EVT_FEAT_DUMMY; local_irq_enable(); - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE, &boot_cpu_id); + clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE, + &boot_cpu_physical_apicid); local_irq_disable(); } @@ -640,10 +650,10 @@ int __init verify_local_APIC(void) /* * The ID register is read/write in a real APIC. */ - reg0 = apic_read(APIC_ID); + reg0 = read_apic_id(); apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg0); apic_write(APIC_ID, reg0 ^ APIC_ID_MASK); - reg1 = apic_read(APIC_ID); + reg1 = read_apic_id(); apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg1); apic_write(APIC_ID, reg0); if (reg1 != (reg0 ^ APIC_ID_MASK)) @@ -728,6 +738,7 @@ void __cpuinit setup_local_APIC(void) unsigned int value; int i, j; + preempt_disable(); value = apic_read(APIC_LVR); BUILD_BUG_ON((SPURIOUS_APIC_VECTOR & 0x0f) != 0x0f); @@ -821,9 +832,10 @@ void __cpuinit setup_local_APIC(void) else value = APIC_DM_NMI | APIC_LVT_MASKED; apic_write(APIC_LVT1, value); + preempt_enable(); } -void __cpuinit lapic_setup_esr(void) +static void __cpuinit lapic_setup_esr(void) { unsigned maxlvt = lapic_get_maxlvt(); @@ -857,10 +869,34 @@ static int __init detect_init_APIC(void) } mp_lapic_addr = APIC_DEFAULT_PHYS_BASE; - boot_cpu_id = 0; + boot_cpu_physical_apicid = 0; return 0; } +void __init early_init_lapic_mapping(void) +{ + unsigned long apic_phys; + + /* + * If no local APIC can be found then go out + * : it means there is no mpatable and MADT + */ + if (!smp_found_config) + return; + + apic_phys = mp_lapic_addr; + + set_fixmap_nocache(FIX_APIC_BASE, apic_phys); + apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n", + APIC_BASE, apic_phys); + + /* + * Fetch the APIC ID of the BSP in case we have a + * default configuration (or the MP table is broken). + */ + boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id()); +} + /** * init_apic_mappings - initialize APIC mappings */ @@ -881,16 +917,11 @@ void __init init_apic_mappings(void) apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n", APIC_BASE, apic_phys); - /* 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); - /* * Fetch the APIC ID of the BSP in case we have a * default configuration (or the MP table is broken). */ - boot_cpu_id = GET_APIC_ID(apic_read(APIC_ID)); + boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id()); } /* @@ -911,8 +942,8 @@ int __init APIC_init_uniprocessor(void) verify_local_APIC(); - phys_cpu_present_map = physid_mask_of_physid(boot_cpu_id); - apic_write(APIC_ID, SET_APIC_ID(boot_cpu_id)); + phys_cpu_present_map = physid_mask_of_physid(boot_cpu_physical_apicid); + apic_write(APIC_ID, SET_APIC_ID(boot_cpu_physical_apicid)); setup_local_APIC(); @@ -1029,6 +1060,52 @@ void disconnect_bsp_APIC(int virt_wire_setup) apic_write(APIC_LVT1, value); } +void __cpuinit generic_processor_info(int apicid, int version) +{ + int cpu; + cpumask_t tmp_map; + + if (num_processors >= NR_CPUS) { + printk(KERN_WARNING "WARNING: NR_CPUS limit of %i reached." + " Processor ignored.\n", NR_CPUS); + return; + } + + if (num_processors >= maxcpus) { + printk(KERN_WARNING "WARNING: maxcpus limit of %i reached." + " Processor ignored.\n", maxcpus); + return; + } + + num_processors++; + cpus_complement(tmp_map, cpu_present_map); + cpu = first_cpu(tmp_map); + + physid_set(apicid, phys_cpu_present_map); + if (apicid == boot_cpu_physical_apicid) { + /* + * x86_bios_cpu_apicid is required to have processors listed + * in same order as logical cpu numbers. Hence the first + * entry is BSP, and so on. + */ + cpu = 0; + } + /* 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; + + cpu_to_apicid[cpu] = apicid; + bios_cpu_apicid[cpu] = apicid; + } else { + per_cpu(x86_cpu_to_apicid, cpu) = apicid; + per_cpu(x86_bios_cpu_apicid, cpu) = apicid; + } + + cpu_set(cpu, cpu_possible_map); + cpu_set(cpu, cpu_present_map); +} + /* * Power management */ @@ -1065,7 +1142,7 @@ static int lapic_suspend(struct sys_device *dev, pm_message_t state) maxlvt = lapic_get_maxlvt(); - apic_pm_state.apic_id = apic_read(APIC_ID); + apic_pm_state.apic_id = read_apic_id(); apic_pm_state.apic_taskpri = apic_read(APIC_TASKPRI); apic_pm_state.apic_ldr = apic_read(APIC_LDR); apic_pm_state.apic_dfr = apic_read(APIC_DFR); @@ -1180,9 +1257,19 @@ __cpuinit int apic_is_clustered_box(void) { int i, clusters, zeros; unsigned id; - u16 *bios_cpu_apicid = x86_bios_cpu_apicid_early_ptr; + u16 *bios_cpu_apicid; DECLARE_BITMAP(clustermap, NUM_APIC_CLUSTERS); + /* + * there is not this kind of box with AMD CPU yet. + * Some AMD box with quadcore cpu and 8 sockets apicid + * will be [4, 0x23] or [8, 0x27] could be thought to + * vsmp box still need checking... + */ + if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && !is_vsmp_box()) + return 0; + + bios_cpu_apicid = x86_bios_cpu_apicid_early_ptr; bitmap_zero(clustermap, NUM_APIC_CLUSTERS); for (i = 0; i < NR_CPUS; i++) { @@ -1219,6 +1306,12 @@ __cpuinit int apic_is_clustered_box(void) ++zeros; } + /* ScaleMP vSMPowered boxes have one cluster per board and TSCs are + * not guaranteed to be synced between boards + */ + if (is_vsmp_box() && clusters > 1) + return 1; + /* * If clusters > 2, then should be multi-chassis. * May have to revisit this when multi-core + hyperthreaded CPUs come @@ -1290,3 +1383,21 @@ static __init int setup_apicpmtimer(char *s) } __setup("apicpmtimer", setup_apicpmtimer); +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/apm_32.c b/arch/x86/kernel/apm_32.c index d4438ef296d8..bf9290e29013 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -904,6 +904,7 @@ recalc: original_pm_idle(); else default_idle(); + local_irq_disable(); jiffies_since_last_check = jiffies - last_jiffies; if (jiffies_since_last_check > idle_period) goto recalc; @@ -911,6 +912,8 @@ recalc: if (apm_idle_done) apm_do_busy(); + + local_irq_enable(); } /** @@ -1189,19 +1192,6 @@ static int suspend(int vetoable) int err; struct apm_user *as; - if (pm_send_all(PM_SUSPEND, (void *)3)) { - /* Vetoed */ - if (vetoable) { - if (apm_info.connection_version > 0x100) - set_system_power_state(APM_STATE_REJECT); - err = -EBUSY; - ignore_sys_suspend = 0; - printk(KERN_WARNING "apm: suspend was vetoed.\n"); - goto out; - } - printk(KERN_CRIT "apm: suspend was vetoed, but suspending anyway.\n"); - } - device_suspend(PMSG_SUSPEND); local_irq_disable(); device_power_down(PMSG_SUSPEND); @@ -1224,9 +1214,7 @@ static int suspend(int vetoable) device_power_up(); local_irq_enable(); device_resume(); - pm_send_all(PM_RESUME, (void *)0); queue_event(APM_NORMAL_RESUME, NULL); - out: spin_lock(&user_list_lock); for (as = user_list; as != NULL; as = as->next) { as->suspend_wait = 0; @@ -1337,7 +1325,6 @@ static void check_events(void) if ((event != APM_NORMAL_RESUME) || (ignore_normal_resume == 0)) { device_resume(); - pm_send_all(PM_RESUME, (void *)0); queue_event(event, NULL); } ignore_normal_resume = 0; @@ -2217,7 +2204,6 @@ static struct dmi_system_id __initdata apm_dmi_table[] = { */ static int __init apm_init(void) { - struct proc_dir_entry *apm_proc; struct desc_struct *gdt; int err; @@ -2322,9 +2308,7 @@ static int __init apm_init(void) set_base(gdt[APM_DS >> 3], __va((unsigned long)apm_info.bios.dseg << 4)); - apm_proc = create_proc_entry("apm", 0, NULL); - if (apm_proc) - apm_proc->proc_fops = &apm_file_ops; + proc_create("apm", 0, NULL, &apm_file_ops); kapmd_task = kthread_create(apm, NULL, "kapmd"); if (IS_ERR(kapmd_task)) { diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index 8ea040124f7d..92588083950f 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -9,8 +9,9 @@ #include <linux/signal.h> #include <linux/personality.h> #include <linux/suspend.h> +#include <linux/kbuild.h> #include <asm/ucontext.h> -#include "sigframe_32.h" +#include "sigframe.h" #include <asm/pgtable.h> #include <asm/fixmap.h> #include <asm/processor.h> @@ -23,14 +24,6 @@ #include <linux/lguest.h> #include "../../../drivers/lguest/lg.h" -#define DEFINE(sym, val) \ - asm volatile("\n->" #sym " %0 " #val : : "i" (val)) - -#define BLANK() asm volatile("\n->" : : ) - -#define OFFSET(sym, str, mem) \ - DEFINE(sym, offsetof(struct str, mem)); - /* workaround for a warning with -Wmissing-prototypes */ void foo(void); diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 494e1e096ee6..f126c05d6170 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -10,6 +10,7 @@ #include <linux/errno.h> #include <linux/hardirq.h> #include <linux/suspend.h> +#include <linux/kbuild.h> #include <asm/pda.h> #include <asm/processor.h> #include <asm/segment.h> @@ -17,14 +18,6 @@ #include <asm/ia32.h> #include <asm/bootparam.h> -#define DEFINE(sym, val) \ - asm volatile("\n->" #sym " %0 " #val : : "i" (val)) - -#define BLANK() asm volatile("\n->" : : ) - -#define OFFSET(sym, str, mem) \ - DEFINE(sym, offsetof(struct str, mem)) - #define __NO_STUBS 1 #undef __SYSCALL #undef _ASM_X86_64_UNISTD_H_ diff --git a/arch/x86/kernel/bugs_64.c b/arch/x86/kernel/bugs_64.c index 8f520f93ffd4..9a3ed0649d4e 100644 --- a/arch/x86/kernel/bugs_64.c +++ b/arch/x86/kernel/bugs_64.c @@ -9,13 +9,25 @@ #include <asm/bugs.h> #include <asm/processor.h> #include <asm/mtrr.h> +#include <asm/cacheflush.h> void __init check_bugs(void) { - identify_cpu(&boot_cpu_data); + identify_boot_cpu(); #if !defined(CONFIG_SMP) printk("CPU: "); print_cpu_info(&boot_cpu_data); #endif alternative_instructions(); + + /* + * Make sure the first 2MB area is not mapped by huge pages + * There are typically fixed size MTRRs in there and overlapping + * MTRRs into large pages causes slow downs. + * + * Right now we don't do that with gbpages because there seems + * very little benefit for that case. + */ + if (!direct_gbpages) + set_memory_4k((unsigned long)__va(0), 1); } diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index a0c4d7c5dbd7..a0c6f8190887 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -3,15 +3,14 @@ # obj-y := intel_cacheinfo.o addon_cpuid_features.o -obj-y += feature_names.o +obj-y += proc.o feature_names.o -obj-$(CONFIG_X86_32) += common.o proc.o bugs.o +obj-$(CONFIG_X86_32) += common.o bugs.o obj-$(CONFIG_X86_32) += amd.o obj-$(CONFIG_X86_32) += cyrix.o obj-$(CONFIG_X86_32) += centaur.o obj-$(CONFIG_X86_32) += transmeta.o obj-$(CONFIG_X86_32) += intel.o -obj-$(CONFIG_X86_32) += nexgen.o obj-$(CONFIG_X86_32) += umc.o obj-$(CONFIG_X86_MCE) += mcheck/ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 693e353999cd..245866828294 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -4,8 +4,8 @@ #include <asm/io.h> #include <asm/processor.h> #include <asm/apic.h> -#include <asm/mach_apic.h> +#include <mach_apic.h> #include "cpu.h" /* @@ -20,7 +20,7 @@ * the chip setting when fixing the bug but they also tweaked some * performance at the same time.. */ - + extern void vide(void); __asm__(".align 4\nvide: ret"); @@ -63,12 +63,12 @@ static __cpuinit int amd_apic_timer_broken(void) int force_mwait __cpuinitdata; -void __cpuinit early_init_amd(struct cpuinfo_x86 *c) +static void __cpuinit early_init_amd(struct cpuinfo_x86 *c) { if (cpuid_eax(0x80000000) >= 0x80000007) { c->x86_power = cpuid_edx(0x80000007); if (c->x86_power & (1<<8)) - set_bit(X86_FEATURE_CONSTANT_TSC, c->x86_capability); + set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); } } @@ -81,7 +81,8 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) #ifdef CONFIG_SMP unsigned long long value; - /* Disable TLB flush filter by setting HWCR.FFDIS on K8 + /* + * Disable TLB flush filter by setting HWCR.FFDIS on K8 * bit 6 of msr C001_0015 * * Errata 63 for SH-B3 steppings @@ -102,15 +103,16 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) * no bus pipeline) */ - /* Bit 31 in normal CPUID used for nonstandard 3DNow ID; - 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */ - clear_bit(0*32+31, c->x86_capability); - + /* + * 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); + r = get_model_name(c); - switch(c->x86) - { - case 4: + switch (c->x86) { + case 4: /* * General Systems BIOSen alias the cpu frequency registers * of the Elan at 0x000df000. Unfortuantly, one of the Linux @@ -120,61 +122,60 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) #define CBAR (0xfffc) /* Configuration Base Address (32-bit) */ #define CBAR_ENB (0x80000000) #define CBAR_KEY (0X000000CB) - if (c->x86_model==9 || c->x86_model == 10) { + if (c->x86_model == 9 || c->x86_model == 10) { if (inl (CBAR) & CBAR_ENB) outl (0 | CBAR_KEY, CBAR); } break; - case 5: - if( c->x86_model < 6 ) - { + case 5: + if (c->x86_model < 6) { /* Based on AMD doc 20734R - June 2000 */ - if ( c->x86_model == 0 ) { - clear_bit(X86_FEATURE_APIC, c->x86_capability); - set_bit(X86_FEATURE_PGE, c->x86_capability); + if (c->x86_model == 0) { + clear_cpu_cap(c, X86_FEATURE_APIC); + set_cpu_cap(c, X86_FEATURE_PGE); } break; } - - if ( c->x86_model == 6 && c->x86_mask == 1 ) { + + if (c->x86_model == 6 && c->x86_mask == 1) { const int K6_BUG_LOOP = 1000000; int n; void (*f_vide)(void); unsigned long d, d2; - + printk(KERN_INFO "AMD K6 stepping B detected - "); - + /* - * It looks like AMD fixed the 2.6.2 bug and improved indirect + * It looks like AMD fixed the 2.6.2 bug and improved indirect * calls at the same time. */ n = K6_BUG_LOOP; f_vide = vide; rdtscl(d); - while (n--) + while (n--) f_vide(); rdtscl(d2); d = d2-d; - if (d > 20*K6_BUG_LOOP) + if (d > 20*K6_BUG_LOOP) printk("system stability may be impaired when more than 32 MB are used.\n"); - else + else printk("probably OK (after B9730xxxx).\n"); printk(KERN_INFO "Please see http://membres.lycos.fr/poulot/k6bug.html\n"); } /* K6 with old style WHCR */ if (c->x86_model < 8 || - (c->x86_model== 8 && c->x86_mask < 8)) { + (c->x86_model == 8 && c->x86_mask < 8)) { /* We can only write allocate on the low 508Mb */ - if(mbytes>508) - mbytes=508; + if (mbytes > 508) + mbytes = 508; rdmsr(MSR_K6_WHCR, l, h); - if ((l&0x0000FFFF)==0) { + if ((l&0x0000FFFF) == 0) { unsigned long flags; - l=(1<<0)|((mbytes/4)<<1); + l = (1<<0)|((mbytes/4)<<1); local_irq_save(flags); wbinvd(); wrmsr(MSR_K6_WHCR, l, h); @@ -185,17 +186,17 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) break; } - if ((c->x86_model == 8 && c->x86_mask >7) || + if ((c->x86_model == 8 && c->x86_mask > 7) || c->x86_model == 9 || c->x86_model == 13) { /* The more serious chips .. */ - if(mbytes>4092) - mbytes=4092; + if (mbytes > 4092) + mbytes = 4092; rdmsr(MSR_K6_WHCR, l, h); - if ((l&0xFFFF0000)==0) { + if ((l&0xFFFF0000) == 0) { unsigned long flags; - l=((mbytes>>2)<<22)|(1<<16); + l = ((mbytes>>2)<<22)|(1<<16); local_irq_save(flags); wbinvd(); wrmsr(MSR_K6_WHCR, l, h); @@ -207,7 +208,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) /* Set MTRR capability flag if appropriate */ if (c->x86_model == 13 || c->x86_model == 9 || (c->x86_model == 8 && c->x86_mask >= 8)) - set_bit(X86_FEATURE_K6_MTRR, c->x86_capability); + set_cpu_cap(c, X86_FEATURE_K6_MTRR); break; } @@ -217,10 +218,11 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) break; } break; - case 6: /* An Athlon/Duron */ - - /* Bit 15 of Athlon specific MSR 15, needs to be 0 - * to enable SSE on Palomino/Morgan/Barton CPU's. + case 6: /* An Athlon/Duron */ + + /* + * Bit 15 of Athlon specific MSR 15, needs to be 0 + * to enable SSE on Palomino/Morgan/Barton CPU's. * If the BIOS didn't enable it already, enable it here. */ if (c->x86_model >= 6 && c->x86_model <= 10) { @@ -229,15 +231,16 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) rdmsr(MSR_K7_HWCR, l, h); l &= ~0x00008000; wrmsr(MSR_K7_HWCR, l, h); - set_bit(X86_FEATURE_XMM, c->x86_capability); + set_cpu_cap(c, X86_FEATURE_XMM); } } - /* It's been determined by AMD that Athlons since model 8 stepping 1 + /* + * It's been determined by AMD that Athlons since model 8 stepping 1 * are more robust with CLK_CTL set to 200xxxxx instead of 600xxxxx * As per AMD technical note 27212 0.2 */ - if ((c->x86_model == 8 && c->x86_mask>=1) || (c->x86_model > 8)) { + if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) { rdmsr(MSR_K7_CLK_CTL, l, h); if ((l & 0xfff00000) != 0x20000000) { printk ("CPU: CLK_CTL MSR was %x. Reprogramming to %x\n", l, @@ -253,20 +256,19 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) /* Use K8 tuning for Fam10h and Fam11h */ case 0x10: case 0x11: - set_bit(X86_FEATURE_K8, c->x86_capability); + set_cpu_cap(c, X86_FEATURE_K8); break; case 6: - set_bit(X86_FEATURE_K7, c->x86_capability); + set_cpu_cap(c, X86_FEATURE_K7); break; } if (c->x86 >= 6) - set_bit(X86_FEATURE_FXSAVE_LEAK, c->x86_capability); + set_cpu_cap(c, X86_FEATURE_FXSAVE_LEAK); display_cacheinfo(c); - if (cpuid_eax(0x80000000) >= 0x80000008) { + if (cpuid_eax(0x80000000) >= 0x80000008) c->x86_max_cores = (cpuid_ecx(0x80000008) & 0xff) + 1; - } #ifdef CONFIG_X86_HT /* @@ -302,20 +304,20 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) /* K6s reports MCEs but don't actually have all the MSRs */ if (c->x86 < 6) - clear_bit(X86_FEATURE_MCE, c->x86_capability); + clear_cpu_cap(c, X86_FEATURE_MCE); if (cpu_has_xmm2) - set_bit(X86_FEATURE_MFENCE_RDTSC, c->x86_capability); + set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); } -static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 * c, unsigned int size) +static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 *c, unsigned int size) { /* AMD errata T13 (order #21922) */ if ((c->x86 == 6)) { if (c->x86_model == 3 && c->x86_mask == 0) /* Duron Rev A0 */ size = 64; if (c->x86_model == 4 && - (c->x86_mask==0 || c->x86_mask==1)) /* Tbird rev A1/A2 */ + (c->x86_mask == 0 || c->x86_mask == 1)) /* Tbird rev A1/A2 */ size = 256; } return size; @@ -323,25 +325,22 @@ static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 * c, unsigned in static struct cpu_dev amd_cpu_dev __cpuinitdata = { .c_vendor = "AMD", - .c_ident = { "AuthenticAMD" }, + .c_ident = { "AuthenticAMD" }, .c_models = { { .vendor = X86_VENDOR_AMD, .family = 4, .model_names = { [3] = "486 DX/2", [7] = "486 DX/2-WB", - [8] = "486 DX/4", - [9] = "486 DX/4-WB", + [8] = "486 DX/4", + [9] = "486 DX/4-WB", [14] = "Am5x86-WT", - [15] = "Am5x86-WB" + [15] = "Am5x86-WB" } }, }, + .c_early_init = early_init_amd, .c_init = init_amd, .c_size_cache = amd_size_cache, }; -int __init amd_init_cpu(void) -{ - cpu_devs[X86_VENDOR_AMD] = &amd_cpu_dev; - return 0; -} +cpu_vendor_dev_register(X86_VENDOR_AMD, &amd_cpu_dev); diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 9681fa15ddf0..e0f45edd6a55 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -1,31 +1,34 @@ #include <linux/kernel.h> #include <linux/init.h> #include <linux/bitops.h> + #include <asm/processor.h> #include <asm/msr.h> #include <asm/e820.h> #include <asm/mtrr.h> + #include "cpu.h" #ifdef CONFIG_X86_OOSTORE static u32 __cpuinit power2(u32 x) { - u32 s=1; - while(s<=x) - s<<=1; - return s>>=1; + u32 s = 1; + + while (s <= x) + s <<= 1; + + return s >>= 1; } /* - * Set up an actual MCR + * Set up an actual MCR */ - static void __cpuinit centaur_mcr_insert(int reg, u32 base, u32 size, int key) { u32 lo, hi; - + hi = base & ~0xFFF; lo = ~(size-1); /* Size is a power of 2 so this makes a mask */ lo &= ~0xFFF; /* Remove the ctrl value bits */ @@ -35,30 +38,28 @@ static void __cpuinit centaur_mcr_insert(int reg, u32 base, u32 size, int key) } /* - * Figure what we can cover with MCR's + * Figure what we can cover with MCR's * - * Shortcut: We know you can't put 4Gig of RAM on a winchip + * Shortcut: We know you can't put 4Gig of RAM on a winchip */ - -static u32 __cpuinit ramtop(void) /* 16388 */ +static u32 __cpuinit ramtop(void) { - int i; - u32 top = 0; u32 clip = 0xFFFFFFFFUL; - + u32 top = 0; + int i; + for (i = 0; i < e820.nr_map; i++) { unsigned long start, end; if (e820.map[i].addr > 0xFFFFFFFFUL) continue; /* - * Don't MCR over reserved space. Ignore the ISA hole - * we frob around that catastrophe already + * Don't MCR over reserved space. Ignore the ISA hole + * we frob around that catastrophe already */ - - if (e820.map[i].type == E820_RESERVED) - { - if(e820.map[i].addr >= 0x100000UL && e820.map[i].addr < clip) + if (e820.map[i].type == E820_RESERVED) { + if (e820.map[i].addr >= 0x100000UL && + e820.map[i].addr < clip) clip = e820.map[i].addr; continue; } @@ -69,28 +70,27 @@ static u32 __cpuinit ramtop(void) /* 16388 */ if (end > top) top = end; } - /* Everything below 'top' should be RAM except for the ISA hole. - Because of the limited MCR's we want to map NV/ACPI into our - MCR range for gunk in RAM - - Clip might cause us to MCR insufficient RAM but that is an - acceptable failure mode and should only bite obscure boxes with - a VESA hole at 15Mb - - The second case Clip sometimes kicks in is when the EBDA is marked - as reserved. Again we fail safe with reasonable results - */ - - if(top>clip) - top=clip; - + /* + * Everything below 'top' should be RAM except for the ISA hole. + * Because of the limited MCR's we want to map NV/ACPI into our + * MCR range for gunk in RAM + * + * Clip might cause us to MCR insufficient RAM but that is an + * acceptable failure mode and should only bite obscure boxes with + * a VESA hole at 15Mb + * + * The second case Clip sometimes kicks in is when the EBDA is marked + * as reserved. Again we fail safe with reasonable results + */ + if (top > clip) + top = clip; + return top; } /* - * Compute a set of MCR's to give maximum coverage + * Compute a set of MCR's to give maximum coverage */ - static int __cpuinit centaur_mcr_compute(int nr, int key) { u32 mem = ramtop(); @@ -99,141 +99,131 @@ static int __cpuinit centaur_mcr_compute(int nr, int key) u32 top = root; u32 floor = 0; int ct = 0; - - while(ct<nr) - { + + while (ct < nr) { u32 fspace = 0; + u32 high; + u32 low; /* - * Find the largest block we will fill going upwards + * Find the largest block we will fill going upwards */ - - u32 high = power2(mem-top); + high = power2(mem-top); /* - * Find the largest block we will fill going downwards + * Find the largest block we will fill going downwards */ - - u32 low = base/2; + low = base/2; /* - * Don't fill below 1Mb going downwards as there - * is an ISA hole in the way. - */ - - if(base <= 1024*1024) + * Don't fill below 1Mb going downwards as there + * is an ISA hole in the way. + */ + if (base <= 1024*1024) low = 0; - + /* - * See how much space we could cover by filling below - * the ISA hole + * See how much space we could cover by filling below + * the ISA hole */ - - if(floor == 0) + + if (floor == 0) fspace = 512*1024; - else if(floor ==512*1024) + else if (floor == 512*1024) fspace = 128*1024; /* And forget ROM space */ - + /* - * Now install the largest coverage we get + * Now install the largest coverage we get */ - - if(fspace > high && fspace > low) - { + if (fspace > high && fspace > low) { centaur_mcr_insert(ct, floor, fspace, key); floor += fspace; - } - else if(high > low) - { + } else if (high > low) { centaur_mcr_insert(ct, top, high, key); top += high; - } - else if(low > 0) - { + } else if (low > 0) { base -= low; centaur_mcr_insert(ct, base, low, key); - } - else break; + } else + break; ct++; } /* - * We loaded ct values. We now need to set the mask. The caller - * must do this bit. + * We loaded ct values. We now need to set the mask. The caller + * must do this bit. */ - return ct; } static void __cpuinit centaur_create_optimal_mcr(void) { + int used; int i; + /* - * Allocate up to 6 mcrs to mark as much of ram as possible - * as write combining and weak write ordered. + * Allocate up to 6 mcrs to mark as much of ram as possible + * as write combining and weak write ordered. * - * To experiment with: Linux never uses stack operations for - * mmio spaces so we could globally enable stack operation wc + * To experiment with: Linux never uses stack operations for + * mmio spaces so we could globally enable stack operation wc * - * Load the registers with type 31 - full write combining, all - * writes weakly ordered. + * Load the registers with type 31 - full write combining, all + * writes weakly ordered. */ - int used = centaur_mcr_compute(6, 31); + used = centaur_mcr_compute(6, 31); /* - * Wipe unused MCRs + * Wipe unused MCRs */ - - for(i=used;i<8;i++) + for (i = used; i < 8; i++) wrmsr(MSR_IDT_MCR0+i, 0, 0); } static void __cpuinit winchip2_create_optimal_mcr(void) { u32 lo, hi; + int used; int i; /* - * Allocate up to 6 mcrs to mark as much of ram as possible - * as write combining, weak store ordered. + * Allocate up to 6 mcrs to mark as much of ram as possible + * as write combining, weak store ordered. * - * Load the registers with type 25 - * 8 - weak write ordering - * 16 - weak read ordering - * 1 - write combining + * Load the registers with type 25 + * 8 - weak write ordering + * 16 - weak read ordering + * 1 - write combining */ + used = centaur_mcr_compute(6, 25); - int used = centaur_mcr_compute(6, 25); - /* - * Mark the registers we are using. + * Mark the registers we are using. */ - rdmsr(MSR_IDT_MCR_CTRL, lo, hi); - for(i=0;i<used;i++) - lo|=1<<(9+i); + for (i = 0; i < used; i++) + lo |= 1<<(9+i); wrmsr(MSR_IDT_MCR_CTRL, lo, hi); - + /* - * Wipe unused MCRs + * Wipe unused MCRs */ - - for(i=used;i<8;i++) + + for (i = used; i < 8; i++) wrmsr(MSR_IDT_MCR0+i, 0, 0); } /* - * Handle the MCR key on the Winchip 2. + * Handle the MCR key on the Winchip 2. */ - static void __cpuinit winchip2_unprotect_mcr(void) { u32 lo, hi; u32 key; - + rdmsr(MSR_IDT_MCR_CTRL, lo, hi); - lo&=~0x1C0; /* blank bits 8-6 */ + lo &= ~0x1C0; /* blank bits 8-6 */ key = (lo>>17) & 7; lo |= key<<6; /* replace with unlock key */ wrmsr(MSR_IDT_MCR_CTRL, lo, hi); @@ -242,9 +232,9 @@ static void __cpuinit winchip2_unprotect_mcr(void) static void __cpuinit winchip2_protect_mcr(void) { u32 lo, hi; - + rdmsr(MSR_IDT_MCR_CTRL, lo, hi); - lo&=~0x1C0; /* blank bits 8-6 */ + lo &= ~0x1C0; /* blank bits 8-6 */ wrmsr(MSR_IDT_MCR_CTRL, lo, hi); } #endif /* CONFIG_X86_OOSTORE */ @@ -267,17 +257,17 @@ static void __cpuinit init_c3(struct cpuinfo_x86 *c) /* enable ACE unit, if present and disabled */ if ((tmp & (ACE_PRESENT | ACE_ENABLED)) == ACE_PRESENT) { - rdmsr (MSR_VIA_FCR, lo, hi); + rdmsr(MSR_VIA_FCR, lo, hi); lo |= ACE_FCR; /* enable ACE unit */ - wrmsr (MSR_VIA_FCR, lo, hi); + wrmsr(MSR_VIA_FCR, lo, hi); printk(KERN_INFO "CPU: Enabled ACE h/w crypto\n"); } /* enable RNG unit, if present and disabled */ if ((tmp & (RNG_PRESENT | RNG_ENABLED)) == RNG_PRESENT) { - rdmsr (MSR_VIA_RNG, lo, hi); + rdmsr(MSR_VIA_RNG, lo, hi); lo |= RNG_ENABLE; /* enable RNG unit */ - wrmsr (MSR_VIA_RNG, lo, hi); + wrmsr(MSR_VIA_RNG, lo, hi); printk(KERN_INFO "CPU: Enabled h/w RNG\n"); } @@ -288,171 +278,183 @@ static void __cpuinit init_c3(struct cpuinfo_x86 *c) } /* Cyrix III family needs CX8 & PGE explicitly enabled. */ - if (c->x86_model >=6 && c->x86_model <= 9) { - rdmsr (MSR_VIA_FCR, lo, hi); + if (c->x86_model >= 6 && c->x86_model <= 9) { + rdmsr(MSR_VIA_FCR, lo, hi); lo |= (1<<1 | 1<<7); - wrmsr (MSR_VIA_FCR, lo, hi); - set_bit(X86_FEATURE_CX8, c->x86_capability); + wrmsr(MSR_VIA_FCR, lo, hi); + set_cpu_cap(c, X86_FEATURE_CX8); } /* Before Nehemiah, the C3's had 3dNOW! */ - if (c->x86_model >=6 && c->x86_model <9) - set_bit(X86_FEATURE_3DNOW, c->x86_capability); + if (c->x86_model >= 6 && c->x86_model < 9) + set_cpu_cap(c, X86_FEATURE_3DNOW); get_model_name(c); display_cacheinfo(c); } +enum { + ECX8 = 1<<1, + EIERRINT = 1<<2, + DPM = 1<<3, + DMCE = 1<<4, + DSTPCLK = 1<<5, + ELINEAR = 1<<6, + DSMC = 1<<7, + DTLOCK = 1<<8, + EDCTLB = 1<<8, + EMMX = 1<<9, + DPDC = 1<<11, + EBRPRED = 1<<12, + DIC = 1<<13, + DDC = 1<<14, + DNA = 1<<15, + ERETSTK = 1<<16, + E2MMX = 1<<19, + EAMD3D = 1<<20, +}; + static void __cpuinit init_centaur(struct cpuinfo_x86 *c) { - enum { - ECX8=1<<1, - EIERRINT=1<<2, - DPM=1<<3, - DMCE=1<<4, - DSTPCLK=1<<5, - ELINEAR=1<<6, - DSMC=1<<7, - DTLOCK=1<<8, - EDCTLB=1<<8, - EMMX=1<<9, - DPDC=1<<11, - EBRPRED=1<<12, - DIC=1<<13, - DDC=1<<14, - DNA=1<<15, - ERETSTK=1<<16, - E2MMX=1<<19, - EAMD3D=1<<20, - }; char *name; - u32 fcr_set=0; - u32 fcr_clr=0; - u32 lo,hi,newlo; - u32 aa,bb,cc,dd; + u32 fcr_set = 0; + u32 fcr_clr = 0; + u32 lo, hi, newlo; + u32 aa, bb, cc, dd; - /* Bit 31 in normal CPUID used for nonstandard 3DNow ID; - 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */ - clear_bit(0*32+31, c->x86_capability); + /* + * 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); switch (c->x86) { - - case 5: - switch(c->x86_model) { - case 4: - name="C6"; - fcr_set=ECX8|DSMC|EDCTLB|EMMX|ERETSTK; - fcr_clr=DPDC; - printk(KERN_NOTICE "Disabling bugged TSC.\n"); - clear_bit(X86_FEATURE_TSC, c->x86_capability); + case 5: + switch (c->x86_model) { + case 4: + name = "C6"; + fcr_set = ECX8|DSMC|EDCTLB|EMMX|ERETSTK; + fcr_clr = DPDC; + printk(KERN_NOTICE "Disabling bugged TSC.\n"); + clear_cpu_cap(c, X86_FEATURE_TSC); #ifdef CONFIG_X86_OOSTORE - centaur_create_optimal_mcr(); - /* Enable - write combining on non-stack, non-string - write combining on string, all types - weak write ordering - - The C6 original lacks weak read order - - Note 0x120 is write only on Winchip 1 */ - - wrmsr(MSR_IDT_MCR_CTRL, 0x01F0001F, 0); -#endif + centaur_create_optimal_mcr(); + /* + * Enable: + * write combining on non-stack, non-string + * write combining on string, all types + * weak write ordering + * + * The C6 original lacks weak read order + * + * Note 0x120 is write only on Winchip 1 + */ + wrmsr(MSR_IDT_MCR_CTRL, 0x01F0001F, 0); +#endif + break; + case 8: + switch (c->x86_mask) { + default: + name = "2"; + break; + case 7 ... 9: + name = "2A"; break; - case 8: - switch(c->x86_mask) { - default: - name="2"; - break; - case 7 ... 9: - name="2A"; - break; - case 10 ... 15: - name="2B"; - break; - } - fcr_set=ECX8|DSMC|DTLOCK|EMMX|EBRPRED|ERETSTK|E2MMX|EAMD3D; - fcr_clr=DPDC; + case 10 ... 15: + name = "2B"; + break; + } + fcr_set = ECX8|DSMC|DTLOCK|EMMX|EBRPRED|ERETSTK| + E2MMX|EAMD3D; + fcr_clr = DPDC; #ifdef CONFIG_X86_OOSTORE - winchip2_unprotect_mcr(); - winchip2_create_optimal_mcr(); - rdmsr(MSR_IDT_MCR_CTRL, lo, hi); - /* Enable - write combining on non-stack, non-string - write combining on string, all types - weak write ordering - */ - lo|=31; - wrmsr(MSR_IDT_MCR_CTRL, lo, hi); - winchip2_protect_mcr(); + winchip2_unprotect_mcr(); + winchip2_create_optimal_mcr(); + rdmsr(MSR_IDT_MCR_CTRL, lo, hi); + /* + * Enable: + * write combining on non-stack, non-string + * write combining on string, all types + * weak write ordering + */ + lo |= 31; + wrmsr(MSR_IDT_MCR_CTRL, lo, hi); + winchip2_protect_mcr(); #endif - break; - case 9: - name="3"; - fcr_set=ECX8|DSMC|DTLOCK|EMMX|EBRPRED|ERETSTK|E2MMX|EAMD3D; - fcr_clr=DPDC; + break; + case 9: + name = "3"; + fcr_set = ECX8|DSMC|DTLOCK|EMMX|EBRPRED|ERETSTK| + E2MMX|EAMD3D; + fcr_clr = DPDC; #ifdef CONFIG_X86_OOSTORE - winchip2_unprotect_mcr(); - winchip2_create_optimal_mcr(); - rdmsr(MSR_IDT_MCR_CTRL, lo, hi); - /* Enable - write combining on non-stack, non-string - write combining on string, all types - weak write ordering - */ - lo|=31; - wrmsr(MSR_IDT_MCR_CTRL, lo, hi); - winchip2_protect_mcr(); + winchip2_unprotect_mcr(); + winchip2_create_optimal_mcr(); + rdmsr(MSR_IDT_MCR_CTRL, lo, hi); + /* + * Enable: + * write combining on non-stack, non-string + * write combining on string, all types + * weak write ordering + */ + lo |= 31; + wrmsr(MSR_IDT_MCR_CTRL, lo, hi); + winchip2_protect_mcr(); #endif - break; - default: - name="??"; - } + break; + default: + name = "??"; + } - rdmsr(MSR_IDT_FCR1, lo, hi); - newlo=(lo|fcr_set) & (~fcr_clr); + rdmsr(MSR_IDT_FCR1, lo, hi); + newlo = (lo|fcr_set) & (~fcr_clr); - if (newlo!=lo) { - printk(KERN_INFO "Centaur FCR was 0x%X now 0x%X\n", lo, newlo ); - wrmsr(MSR_IDT_FCR1, newlo, hi ); - } else { - printk(KERN_INFO "Centaur FCR is 0x%X\n",lo); - } - /* Emulate MTRRs using Centaur's MCR. */ - set_bit(X86_FEATURE_CENTAUR_MCR, c->x86_capability); - /* Report CX8 */ - set_bit(X86_FEATURE_CX8, c->x86_capability); - /* Set 3DNow! on Winchip 2 and above. */ - if (c->x86_model >=8) - set_bit(X86_FEATURE_3DNOW, c->x86_capability); - /* See if we can find out some more. */ - if ( cpuid_eax(0x80000000) >= 0x80000005 ) { - /* Yes, we can. */ - cpuid(0x80000005,&aa,&bb,&cc,&dd); - /* Add L1 data and code cache sizes. */ - c->x86_cache_size = (cc>>24)+(dd>>24); - } - sprintf( c->x86_model_id, "WinChip %s", name ); - break; + if (newlo != lo) { + printk(KERN_INFO "Centaur FCR was 0x%X now 0x%X\n", + lo, newlo); + wrmsr(MSR_IDT_FCR1, newlo, hi); + } else { + printk(KERN_INFO "Centaur FCR is 0x%X\n", lo); + } + /* Emulate MTRRs using Centaur's MCR. */ + set_cpu_cap(c, X86_FEATURE_CENTAUR_MCR); + /* Report CX8 */ + set_cpu_cap(c, X86_FEATURE_CX8); + /* Set 3DNow! on Winchip 2 and above. */ + if (c->x86_model >= 8) + set_cpu_cap(c, X86_FEATURE_3DNOW); + /* See if we can find out some more. */ + if (cpuid_eax(0x80000000) >= 0x80000005) { + /* Yes, we can. */ + cpuid(0x80000005, &aa, &bb, &cc, &dd); + /* Add L1 data and code cache sizes. */ + c->x86_cache_size = (cc>>24)+(dd>>24); + } + sprintf(c->x86_model_id, "WinChip %s", name); + break; - case 6: - init_c3(c); - break; + case 6: + init_c3(c); + break; } } -static unsigned int __cpuinit centaur_size_cache(struct cpuinfo_x86 * c, unsigned int size) +static unsigned int __cpuinit +centaur_size_cache(struct cpuinfo_x86 *c, unsigned int size) { /* VIA C3 CPUs (670-68F) need further shifting. */ if ((c->x86 == 6) && ((c->x86_model == 7) || (c->x86_model == 8))) size >>= 8; - /* VIA also screwed up Nehemiah stepping 1, and made - it return '65KB' instead of '64KB' - - Note, it seems this may only be in engineering samples. */ - if ((c->x86==6) && (c->x86_model==9) && (c->x86_mask==1) && (size==65)) - size -=1; + /* + * There's also an erratum in Nehemiah stepping 1, which + * returns '65KB' instead of '64KB' + * - Note, it seems this may only be in engineering samples. + */ + if ((c->x86 == 6) && (c->x86_model == 9) && + (c->x86_mask == 1) && (size == 65)) + size -= 1; return size; } @@ -464,8 +466,4 @@ static struct cpu_dev centaur_cpu_dev __cpuinitdata = { .c_size_cache = centaur_size_cache, }; -int __init centaur_init_cpu(void) -{ - cpu_devs[X86_VENDOR_CENTAUR] = ¢aur_cpu_dev; - return 0; -} +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 a38aafaefc23..35b4f6a9c8ef 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -5,7 +5,6 @@ #include <linux/module.h> #include <linux/percpu.h> #include <linux/bootmem.h> -#include <asm/semaphore.h> #include <asm/processor.h> #include <asm/i387.h> #include <asm/msr.h> @@ -62,9 +61,9 @@ __u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata; static int cachesize_override __cpuinitdata = -1; static int disable_x86_serial_nr __cpuinitdata = 1; -struct cpu_dev * cpu_devs[X86_VENDOR_NUM] = {}; +struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {}; -static void __cpuinit default_init(struct cpuinfo_x86 * c) +static void __cpuinit default_init(struct cpuinfo_x86 *c) { /* Not much we can do here... */ /* Check if at least it has cpuid */ @@ -81,11 +80,11 @@ static struct cpu_dev __cpuinitdata default_cpu = { .c_init = default_init, .c_vendor = "Unknown", }; -static struct cpu_dev * this_cpu __cpuinitdata = &default_cpu; +static struct cpu_dev *this_cpu __cpuinitdata = &default_cpu; static int __init cachesize_setup(char *str) { - get_option (&str, &cachesize_override); + get_option(&str, &cachesize_override); return 1; } __setup("cachesize=", cachesize_setup); @@ -107,12 +106,12 @@ int __cpuinit get_model_name(struct cpuinfo_x86 *c) /* Intel chips right-justify this string for some dumb reason; undo that brain damage */ p = q = &c->x86_model_id[0]; - while ( *p == ' ' ) + while (*p == ' ') p++; - if ( p != q ) { - while ( *p ) + if (p != q) { + while (*p) *q++ = *p++; - while ( q <= &c->x86_model_id[48] ) + while (q <= &c->x86_model_id[48]) *q++ = '\0'; /* Zero-pad the rest */ } @@ -130,7 +129,7 @@ void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c) cpuid(0x80000005, &dummy, &dummy, &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); + c->x86_cache_size = (ecx>>24)+(edx>>24); } if (n < 0x80000006) /* Some chips just has a large L1. */ @@ -138,16 +137,16 @@ void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c) ecx = cpuid_ecx(0x80000006); l2size = ecx >> 16; - + /* do processor-specific cache resizing */ if (this_cpu->c_size_cache) - l2size = this_cpu->c_size_cache(c,l2size); + l2size = this_cpu->c_size_cache(c, l2size); /* Allow user to override all this if necessary. */ if (cachesize_override != -1) l2size = cachesize_override; - if ( l2size == 0 ) + if (l2size == 0) return; /* Again, no L2 cache is possible */ c->x86_cache_size = l2size; @@ -156,16 +155,19 @@ void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c) l2size, ecx & 0xFF); } -/* Naming convention should be: <Name> [(<Codename>)] */ -/* This table only is used unless init_<vendor>() below doesn't set it; */ -/* in particular, if CPUID levels 0x80000002..4 are supported, this isn't used */ +/* + * Naming convention should be: <Name> [(<Codename>)] + * This table only is used unless init_<vendor>() below doesn't set it; + * in particular, if CPUID levels 0x80000002..4 are supported, this isn't used + * + */ /* Look up CPU names by table lookup. */ static char __cpuinit *table_lookup_model(struct cpuinfo_x86 *c) { struct cpu_model_info *info; - if ( c->x86_model >= 16 ) + if (c->x86_model >= 16) return NULL; /* Range check */ if (!this_cpu) @@ -190,9 +192,9 @@ static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c, int early) 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]))) { + 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; if (!early) this_cpu = cpu_devs[i]; @@ -210,7 +212,7 @@ static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c, int early) } -static int __init x86_fxsr_setup(char * s) +static int __init x86_fxsr_setup(char *s) { setup_clear_cpu_cap(X86_FEATURE_FXSR); setup_clear_cpu_cap(X86_FEATURE_XMM); @@ -219,7 +221,7 @@ static int __init x86_fxsr_setup(char * s) __setup("nofxsr", x86_fxsr_setup); -static int __init x86_sep_setup(char * s) +static int __init x86_sep_setup(char *s) { setup_clear_cpu_cap(X86_FEATURE_SEP); return 1; @@ -306,14 +308,30 @@ static void __cpuinit early_get_cap(struct cpuinfo_x86 *c) } -} + clear_cpu_cap(c, X86_FEATURE_PAT); + + switch (c->x86_vendor) { + case X86_VENDOR_AMD: + if (c->x86 >= 0xf && c->x86 <= 0x11) + set_cpu_cap(c, X86_FEATURE_PAT); + break; + case X86_VENDOR_INTEL: + if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15)) + set_cpu_cap(c, X86_FEATURE_PAT); + break; + } -/* Do minimum CPU detection early. - Fields really needed: vendor, cpuid_level, family, model, mask, cache alignment. - The others are not touched to avoid unwanted side effects. +} - WARNING: this function is only called on the BP. Don't add code here - that is supposed to run on all CPUs. */ +/* + * Do minimum CPU detection early. + * Fields really needed: vendor, cpuid_level, family, model, mask, + * cache alignment. + * The others are not touched to avoid unwanted side effects. + * + * WARNING: this function is only called on the BP. Don't add code here + * that is supposed to run on all CPUs. + */ static void __init early_cpu_detect(void) { struct cpuinfo_x86 *c = &boot_cpu_data; @@ -328,19 +346,14 @@ static void __init early_cpu_detect(void) get_cpu_vendor(c, 1); - switch (c->x86_vendor) { - case X86_VENDOR_AMD: - early_init_amd(c); - break; - case X86_VENDOR_INTEL: - early_init_intel(c); - break; - } + if (c->x86_vendor != X86_VENDOR_UNKNOWN && + cpu_devs[c->x86_vendor]->c_early_init) + cpu_devs[c->x86_vendor]->c_early_init(c); early_get_cap(c); } -static void __cpuinit generic_identify(struct cpuinfo_x86 * c) +static void __cpuinit generic_identify(struct cpuinfo_x86 *c) { u32 tfms, xlvl; unsigned int ebx; @@ -351,13 +364,12 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 * c) (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, 0); /* 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 ) { + if (c->cpuid_level >= 0x00000001) { u32 capability, excap; cpuid(0x00000001, &tfms, &ebx, &excap, &capability); c->x86_capability[0] = capability; @@ -369,12 +381,14 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 * c) if (c->x86 >= 0x6) c->x86_model += ((tfms >> 16) & 0xF) << 4; c->x86_mask = tfms & 15; + c->initial_apicid = (ebx >> 24) & 0xFF; #ifdef CONFIG_X86_HT - c->apicid = phys_pkg_id((ebx >> 24) & 0xFF, 0); + c->apicid = phys_pkg_id(c->initial_apicid, 0); + c->phys_proc_id = c->initial_apicid; #else - c->apicid = (ebx >> 24) & 0xFF; + c->apicid = c->initial_apicid; #endif - if (c->x86_capability[0] & (1<<19)) + if (test_cpu_cap(c, X86_FEATURE_CLFLSH)) c->x86_clflush_size = ((ebx >> 8) & 0xff) * 8; } else { /* Have CPUID level 0 only - unheard of */ @@ -383,33 +397,42 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 * c) /* AMD-defined flags: level 0x80000001 */ xlvl = cpuid_eax(0x80000000); - if ( (xlvl & 0xffff0000) == 0x80000000 ) { - if ( xlvl >= 0x80000001 ) { + if ((xlvl & 0xffff0000) == 0x80000000) { + if (xlvl >= 0x80000001) { c->x86_capability[1] = cpuid_edx(0x80000001); c->x86_capability[6] = cpuid_ecx(0x80000001); } - if ( xlvl >= 0x80000004 ) + if (xlvl >= 0x80000004) get_model_name(c); /* Default name */ } init_scattered_cpuid_features(c); } -#ifdef CONFIG_X86_HT - c->phys_proc_id = (cpuid_ebx(1) >> 24) & 0xff; -#endif + clear_cpu_cap(c, X86_FEATURE_PAT); + + switch (c->x86_vendor) { + case X86_VENDOR_AMD: + if (c->x86 >= 0xf && c->x86 <= 0x11) + set_cpu_cap(c, X86_FEATURE_PAT); + break; + case X86_VENDOR_INTEL: + if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15)) + set_cpu_cap(c, X86_FEATURE_PAT); + break; + } } static void __cpuinit squash_the_stupid_serial_number(struct cpuinfo_x86 *c) { - if (cpu_has(c, X86_FEATURE_PN) && disable_x86_serial_nr ) { + if (cpu_has(c, X86_FEATURE_PN) && disable_x86_serial_nr) { /* Disable processor serial number */ - unsigned long lo,hi; - rdmsr(MSR_IA32_BBL_CR_CTL,lo,hi); + unsigned long lo, hi; + rdmsr(MSR_IA32_BBL_CR_CTL, lo, hi); lo |= 0x200000; - wrmsr(MSR_IA32_BBL_CR_CTL,lo,hi); + wrmsr(MSR_IA32_BBL_CR_CTL, lo, hi); printk(KERN_NOTICE "CPU serial number disabled.\n"); - clear_bit(X86_FEATURE_PN, c->x86_capability); + clear_cpu_cap(c, X86_FEATURE_PN); /* Disabling the serial number may affect the cpuid level */ c->cpuid_level = cpuid_eax(0); @@ -444,9 +467,11 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c) memset(&c->x86_capability, 0, sizeof c->x86_capability); if (!have_cpuid_p()) { - /* First of all, decide if this is a 486 or higher */ - /* It's a 486 if we can modify the AC flag */ - if ( flag_is_changeable_p(X86_EFLAGS_AC) ) + /* + * First of all, decide if this is a 486 or higher + * It's a 486 if we can modify the AC flag + */ + if (flag_is_changeable_p(X86_EFLAGS_AC)) c->x86 = 4; else c->x86 = 3; @@ -479,10 +504,10 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c) */ /* If the model name is still unset, do table lookup. */ - if ( !c->x86_model_id[0] ) { + if (!c->x86_model_id[0]) { char *p; p = table_lookup_model(c); - if ( p ) + if (p) strcpy(c->x86_model_id, p); else /* Last resort... */ @@ -496,9 +521,9 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c) * common between the CPUs. The first time this routine gets * executed, c == &boot_cpu_data. */ - if ( c != &boot_cpu_data ) { + if (c != &boot_cpu_data) { /* AND the already accumulated flags with these */ - for ( i = 0 ; i < NCAPINTS ; i++ ) + for (i = 0 ; i < NCAPINTS ; i++) boot_cpu_data.x86_capability[i] &= c->x86_capability[i]; } @@ -542,7 +567,7 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c) if (smp_num_siblings == 1) { printk(KERN_INFO "CPU: Hyper-Threading is disabled\n"); - } else if (smp_num_siblings > 1 ) { + } else if (smp_num_siblings > 1) { if (smp_num_siblings > NR_CPUS) { printk(KERN_WARNING "CPU: Unsupported number of the " @@ -552,7 +577,7 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c) } index_msb = get_count_order(smp_num_siblings); - c->phys_proc_id = phys_pkg_id((ebx >> 24) & 0xFF, index_msb); + c->phys_proc_id = phys_pkg_id(c->initial_apicid, index_msb); printk(KERN_INFO "CPU: Physical Processor ID: %d\n", c->phys_proc_id); @@ -563,7 +588,7 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c) core_bits = get_count_order(c->x86_max_cores); - c->cpu_core_id = phys_pkg_id((ebx >> 24) & 0xFF, index_msb) & + c->cpu_core_id = phys_pkg_id(c->initial_apicid, index_msb) & ((1 << core_bits) - 1); if (c->x86_max_cores > 1) @@ -597,7 +622,7 @@ void __cpuinit print_cpu_info(struct cpuinfo_x86 *c) else printk("%s", c->x86_model_id); - if (c->x86_mask || c->cpuid_level >= 0) + if (c->x86_mask || c->cpuid_level >= 0) printk(" stepping %02x\n", c->x86_mask); else printk("\n"); @@ -616,23 +641,15 @@ __setup("clearcpuid=", setup_disablecpuid); cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE; -/* This is hacky. :) - * We're emulating future behavior. - * In the future, the cpu-specific init functions will be called implicitly - * via the magic of initcalls. - * They will insert themselves into the cpu_devs structure. - * Then, when cpu_init() is called, we can just iterate over that array. - */ void __init early_cpu_init(void) { - intel_cpu_init(); - cyrix_init_cpu(); - nsc_init_cpu(); - amd_init_cpu(); - centaur_init_cpu(); - transmeta_init_cpu(); - nexgen_init_cpu(); - umc_init_cpu(); + struct cpu_vendor_dev *cvdev; + + for (cvdev = __x86cpuvendor_start ; + cvdev < __x86cpuvendor_end ; + cvdev++) + cpu_devs[cvdev->vendor] = cvdev->cpu_dev; + early_cpu_detect(); } @@ -666,7 +683,7 @@ void __cpuinit cpu_init(void) { int cpu = smp_processor_id(); struct task_struct *curr = current; - struct tss_struct * t = &per_cpu(init_tss, cpu); + struct tss_struct *t = &per_cpu(init_tss, cpu); struct thread_struct *thread = &curr->thread; if (cpu_test_and_set(cpu, cpu_initialized)) { @@ -692,7 +709,7 @@ void __cpuinit cpu_init(void) enter_lazy_tlb(&init_mm, curr); load_sp0(t, thread); - set_tss_desc(cpu,t); + set_tss_desc(cpu, t); load_TR_desc(); load_LDT(&init_mm.context); diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index e0b38c33d842..783691b2a738 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -14,6 +14,7 @@ struct cpu_dev { struct cpu_model_info c_models[4]; + void (*c_early_init)(struct cpuinfo_x86 *c); void (*c_init)(struct cpuinfo_x86 * c); void (*c_identify)(struct cpuinfo_x86 * c); unsigned int (*c_size_cache)(struct cpuinfo_x86 * c, unsigned int size); @@ -21,18 +22,17 @@ struct cpu_dev { extern struct cpu_dev * cpu_devs [X86_VENDOR_NUM]; +struct cpu_vendor_dev { + int vendor; + struct cpu_dev *cpu_dev; +}; + +#define cpu_vendor_dev_register(cpu_vendor_id, cpu_dev) \ + static struct cpu_vendor_dev __cpu_vendor_dev_##cpu_vendor_id __used \ + __attribute__((__section__(".x86cpuvendor.init"))) = \ + { cpu_vendor_id, cpu_dev } + +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); - -extern void early_init_intel(struct cpuinfo_x86 *c); -extern void early_init_amd(struct cpuinfo_x86 *c); - -/* Specific CPU type init functions */ -int intel_cpu_init(void); -int amd_init_cpu(void); -int cyrix_init_cpu(void); -int nsc_init_cpu(void); -int centaur_init_cpu(void); -int transmeta_init_cpu(void); -int nexgen_init_cpu(void); -int umc_init_cpu(void); diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index a962dcb9c408..b0c8208df9fa 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -192,9 +192,9 @@ static void drv_read(struct drv_cmd *cmd) cpumask_t saved_mask = current->cpus_allowed; cmd->val = 0; - set_cpus_allowed(current, cmd->mask); + set_cpus_allowed_ptr(current, &cmd->mask); do_drv_read(cmd); - set_cpus_allowed(current, saved_mask); + set_cpus_allowed_ptr(current, &saved_mask); } static void drv_write(struct drv_cmd *cmd) @@ -203,30 +203,30 @@ static void drv_write(struct drv_cmd *cmd) unsigned int i; for_each_cpu_mask(i, cmd->mask) { - set_cpus_allowed(current, cpumask_of_cpu(i)); + set_cpus_allowed_ptr(current, &cpumask_of_cpu(i)); do_drv_write(cmd); } - set_cpus_allowed(current, saved_mask); + set_cpus_allowed_ptr(current, &saved_mask); return; } -static u32 get_cur_val(cpumask_t mask) +static u32 get_cur_val(const cpumask_t *mask) { struct acpi_processor_performance *perf; struct drv_cmd cmd; - if (unlikely(cpus_empty(mask))) + if (unlikely(cpus_empty(*mask))) return 0; - switch (per_cpu(drv_data, first_cpu(mask))->cpu_feature) { + switch (per_cpu(drv_data, first_cpu(*mask))->cpu_feature) { case SYSTEM_INTEL_MSR_CAPABLE: cmd.type = SYSTEM_INTEL_MSR_CAPABLE; cmd.addr.msr.reg = MSR_IA32_PERF_STATUS; break; case SYSTEM_IO_CAPABLE: cmd.type = SYSTEM_IO_CAPABLE; - perf = per_cpu(drv_data, first_cpu(mask))->acpi_data; + perf = per_cpu(drv_data, first_cpu(*mask))->acpi_data; cmd.addr.io.port = perf->control_register.address; cmd.addr.io.bit_width = perf->control_register.bit_width; break; @@ -234,7 +234,7 @@ static u32 get_cur_val(cpumask_t mask) return 0; } - cmd.mask = mask; + cmd.mask = *mask; drv_read(&cmd); @@ -271,7 +271,7 @@ static unsigned int get_measured_perf(unsigned int cpu) unsigned int retval; saved_mask = current->cpus_allowed; - set_cpus_allowed(current, cpumask_of_cpu(cpu)); + set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); if (get_cpu() != cpu) { /* We were not able to run on requested processor */ put_cpu(); @@ -329,7 +329,7 @@ static unsigned int get_measured_perf(unsigned int cpu) retval = per_cpu(drv_data, cpu)->max_freq * perf_percent / 100; put_cpu(); - set_cpus_allowed(current, saved_mask); + set_cpus_allowed_ptr(current, &saved_mask); dprintk("cpu %d: performance percent %d\n", cpu, perf_percent); return retval; @@ -339,6 +339,7 @@ static unsigned int get_cur_freq_on_cpu(unsigned int cpu) { struct acpi_cpufreq_data *data = per_cpu(drv_data, cpu); unsigned int freq; + unsigned int cached_freq; dprintk("get_cur_freq_on_cpu (%d)\n", cpu); @@ -347,13 +348,22 @@ static unsigned int get_cur_freq_on_cpu(unsigned int cpu) return 0; } - freq = extract_freq(get_cur_val(cpumask_of_cpu(cpu)), data); + cached_freq = data->freq_table[data->acpi_data->state].frequency; + freq = extract_freq(get_cur_val(&cpumask_of_cpu(cpu)), data); + if (freq != cached_freq) { + /* + * The dreaded BIOS frequency change behind our back. + * Force set the frequency on next target call. + */ + data->resume = 1; + } + dprintk("cur freq = %u\n", freq); return freq; } -static unsigned int check_freqs(cpumask_t mask, unsigned int freq, +static unsigned int check_freqs(const cpumask_t *mask, unsigned int freq, struct acpi_cpufreq_data *data) { unsigned int cur_freq; @@ -449,7 +459,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy, drv_write(&cmd); if (acpi_pstate_strict) { - if (!check_freqs(cmd.mask, freqs.new, data)) { + if (!check_freqs(&cmd.mask, freqs.new, data)) { dprintk("acpi_cpufreq_target failed (%d)\n", policy->cpu); return -EAGAIN; @@ -591,6 +601,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) { policy->cpus = perf->shared_cpu_map; } + policy->related_cpus = perf->shared_cpu_map; #ifdef CONFIG_SMP dmi_check_system(sw_any_bug_dmi_table); diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c index 14791ec55cfd..199e4e05e5dc 100644 --- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c @@ -289,8 +289,8 @@ static int __init cpufreq_p4_init(void) if (c->x86_vendor != X86_VENDOR_INTEL) return -ENODEV; - if (!test_bit(X86_FEATURE_ACPI, c->x86_capability) || - !test_bit(X86_FEATURE_ACC, c->x86_capability)) + if (!test_cpu_cap(c, X86_FEATURE_ACPI) || + !test_cpu_cap(c, X86_FEATURE_ACC)) return -ENODEV; ret = cpufreq_register_driver(&p4clockmod_driver); diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index c99d59d8ef2e..46d4034d9f37 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -478,12 +478,12 @@ static int core_voltage_post_transition(struct powernow_k8_data *data, u32 reqvi static int check_supported_cpu(unsigned int cpu) { - cpumask_t oldmask = CPU_MASK_ALL; + cpumask_t oldmask; u32 eax, ebx, ecx, edx; unsigned int rc = 0; oldmask = current->cpus_allowed; - set_cpus_allowed(current, cpumask_of_cpu(cpu)); + set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); if (smp_processor_id() != cpu) { printk(KERN_ERR PFX "limiting to cpu %u failed\n", cpu); @@ -528,7 +528,7 @@ static int check_supported_cpu(unsigned int cpu) rc = 1; out: - set_cpus_allowed(current, oldmask); + set_cpus_allowed_ptr(current, &oldmask); return rc; } @@ -1015,7 +1015,7 @@ static int transition_frequency_pstate(struct powernow_k8_data *data, unsigned i /* Driver entry point to switch to the target frequency */ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsigned relation) { - cpumask_t oldmask = CPU_MASK_ALL; + cpumask_t oldmask; struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu); u32 checkfid; u32 checkvid; @@ -1030,7 +1030,7 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi /* only run on specific CPU from here on */ oldmask = current->cpus_allowed; - set_cpus_allowed(current, cpumask_of_cpu(pol->cpu)); + set_cpus_allowed_ptr(current, &cpumask_of_cpu(pol->cpu)); if (smp_processor_id() != pol->cpu) { printk(KERN_ERR PFX "limiting to cpu %u failed\n", pol->cpu); @@ -1085,7 +1085,7 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi ret = 0; err_out: - set_cpus_allowed(current, oldmask); + set_cpus_allowed_ptr(current, &oldmask); return ret; } @@ -1104,7 +1104,7 @@ static int powernowk8_verify(struct cpufreq_policy *pol) static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) { struct powernow_k8_data *data; - cpumask_t oldmask = CPU_MASK_ALL; + cpumask_t oldmask; int rc; if (!cpu_online(pol->cpu)) @@ -1145,7 +1145,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) /* only run on specific CPU from here on */ oldmask = current->cpus_allowed; - set_cpus_allowed(current, cpumask_of_cpu(pol->cpu)); + set_cpus_allowed_ptr(current, &cpumask_of_cpu(pol->cpu)); if (smp_processor_id() != pol->cpu) { printk(KERN_ERR PFX "limiting to cpu %u failed\n", pol->cpu); @@ -1164,7 +1164,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) fidvid_msr_init(); /* run on any CPU again */ - set_cpus_allowed(current, oldmask); + set_cpus_allowed_ptr(current, &oldmask); if (cpu_family == CPU_HW_PSTATE) pol->cpus = cpumask_of_cpu(pol->cpu); @@ -1205,7 +1205,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) return 0; err_out: - set_cpus_allowed(current, oldmask); + set_cpus_allowed_ptr(current, &oldmask); powernow_k8_cpu_exit_acpi(data); kfree(data); @@ -1242,10 +1242,11 @@ static unsigned int powernowk8_get (unsigned int cpu) if (!data) return -EINVAL; - set_cpus_allowed(current, cpumask_of_cpu(cpu)); + set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); if (smp_processor_id() != cpu) { - printk(KERN_ERR PFX "limiting to CPU %d failed in powernowk8_get\n", cpu); - set_cpus_allowed(current, oldmask); + printk(KERN_ERR PFX + "limiting to CPU %d failed in powernowk8_get\n", cpu); + set_cpus_allowed_ptr(current, &oldmask); return 0; } @@ -1253,13 +1254,14 @@ static unsigned int powernowk8_get (unsigned int cpu) goto out; if (cpu_family == CPU_HW_PSTATE) - khz = find_khz_freq_from_pstate(data->powernow_table, data->currpstate); + khz = find_khz_freq_from_pstate(data->powernow_table, + data->currpstate); else khz = find_khz_freq_from_fid(data->currfid); out: - set_cpus_allowed(current, oldmask); + set_cpus_allowed_ptr(current, &oldmask); return khz; } diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c index 3031f1196192..908dd347c67e 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c @@ -315,7 +315,7 @@ static unsigned int get_cur_freq(unsigned int cpu) cpumask_t saved_mask; saved_mask = current->cpus_allowed; - set_cpus_allowed(current, cpumask_of_cpu(cpu)); + set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); if (smp_processor_id() != cpu) return 0; @@ -333,7 +333,7 @@ static unsigned int get_cur_freq(unsigned int cpu) clock_freq = extract_clock(l, cpu, 1); } - set_cpus_allowed(current, saved_mask); + set_cpus_allowed_ptr(current, &saved_mask); return clock_freq; } @@ -487,7 +487,7 @@ static int centrino_target (struct cpufreq_policy *policy, else cpu_set(j, set_mask); - set_cpus_allowed(current, set_mask); + set_cpus_allowed_ptr(current, &set_mask); preempt_disable(); if (unlikely(!cpu_isset(smp_processor_id(), set_mask))) { dprintk("couldn't limit to CPUs in this domain\n"); @@ -555,7 +555,8 @@ static int centrino_target (struct cpufreq_policy *policy, if (!cpus_empty(covered_cpus)) { for_each_cpu_mask(j, covered_cpus) { - set_cpus_allowed(current, cpumask_of_cpu(j)); + set_cpus_allowed_ptr(current, + &cpumask_of_cpu(j)); wrmsr(MSR_IA32_PERF_CTL, oldmsr, h); } } @@ -569,12 +570,12 @@ static int centrino_target (struct cpufreq_policy *policy, cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); } } - set_cpus_allowed(current, saved_mask); + set_cpus_allowed_ptr(current, &saved_mask); return 0; migrate_end: preempt_enable(); - set_cpus_allowed(current, saved_mask); + set_cpus_allowed_ptr(current, &saved_mask); return 0; } diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c index 14d68aa301ee..1b50244b1fdf 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c @@ -229,22 +229,22 @@ static unsigned int speedstep_detect_chipset (void) return 0; } -static unsigned int _speedstep_get(cpumask_t cpus) +static unsigned int _speedstep_get(const cpumask_t *cpus) { unsigned int speed; cpumask_t cpus_allowed; cpus_allowed = current->cpus_allowed; - set_cpus_allowed(current, cpus); + set_cpus_allowed_ptr(current, cpus); speed = speedstep_get_processor_frequency(speedstep_processor); - set_cpus_allowed(current, cpus_allowed); + set_cpus_allowed_ptr(current, &cpus_allowed); dprintk("detected %u kHz as current frequency\n", speed); return speed; } static unsigned int speedstep_get(unsigned int cpu) { - return _speedstep_get(cpumask_of_cpu(cpu)); + return _speedstep_get(&cpumask_of_cpu(cpu)); } /** @@ -267,7 +267,7 @@ static int speedstep_target (struct cpufreq_policy *policy, if (cpufreq_frequency_table_target(policy, &speedstep_freqs[0], target_freq, relation, &newstate)) return -EINVAL; - freqs.old = _speedstep_get(policy->cpus); + freqs.old = _speedstep_get(&policy->cpus); freqs.new = speedstep_freqs[newstate].frequency; freqs.cpu = policy->cpu; @@ -285,12 +285,12 @@ static int speedstep_target (struct cpufreq_policy *policy, } /* switch to physical CPU where state is to be changed */ - set_cpus_allowed(current, policy->cpus); + set_cpus_allowed_ptr(current, &policy->cpus); speedstep_set_state(newstate); /* allow to be run on all CPUs */ - set_cpus_allowed(current, cpus_allowed); + set_cpus_allowed_ptr(current, &cpus_allowed); for_each_cpu_mask(i, policy->cpus) { freqs.cpu = i; @@ -326,7 +326,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) #endif cpus_allowed = current->cpus_allowed; - set_cpus_allowed(current, policy->cpus); + set_cpus_allowed_ptr(current, &policy->cpus); /* detect low and high frequency and transition latency */ result = speedstep_get_freqs(speedstep_processor, @@ -334,12 +334,12 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) &speedstep_freqs[SPEEDSTEP_HIGH].frequency, &policy->cpuinfo.transition_latency, &speedstep_set_state); - set_cpus_allowed(current, cpus_allowed); + set_cpus_allowed_ptr(current, &cpus_allowed); if (result) return result; /* get current speed setting */ - speed = _speedstep_get(policy->cpus); + speed = _speedstep_get(&policy->cpus); if (!speed) return -EIO; diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 7139b0262703..3fd7a67bb06a 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -19,7 +19,7 @@ static void __cpuinit do_cyrix_devid(unsigned char *dir0, unsigned char *dir1) { unsigned char ccr2, ccr3; unsigned long flags; - + /* we test for DEVID by checking whether CCR3 is writable */ local_irq_save(flags); ccr3 = getCx86(CX86_CCR3); @@ -37,8 +37,7 @@ static void __cpuinit do_cyrix_devid(unsigned char *dir0, unsigned char *dir1) setCx86(CX86_CCR2, ccr2); *dir0 = 0xfe; } - } - else { + } else { setCx86(CX86_CCR3, ccr3); /* restore CCR3 */ /* read DIR0 and DIR1 CPU registers */ @@ -86,7 +85,7 @@ static char cyrix_model_mult2[] __cpuinitdata = "12233445"; static void __cpuinit check_cx686_slop(struct cpuinfo_x86 *c) { unsigned long flags; - + if (Cx86_dir0_msb == 3) { unsigned char ccr3, ccr5; @@ -132,7 +131,7 @@ static void __cpuinit set_cx86_memwb(void) /* set 'Not Write-through' */ write_cr0(read_cr0() | X86_CR0_NW); /* CCR2 bit 2: lock NW bit and set WT1 */ - setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x14 ); + setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x14); } static void __cpuinit set_cx86_inc(void) @@ -148,7 +147,7 @@ static void __cpuinit set_cx86_inc(void) setCx86(CX86_PCR1, getCx86(CX86_PCR1) | 0x02); /* PCR0 -- Performance Control */ /* Incrementor Margin 10 */ - setCx86(CX86_PCR0, getCx86(CX86_PCR0) | 0x04); + setCx86(CX86_PCR0, getCx86(CX86_PCR0) | 0x04); setCx86(CX86_CCR3, ccr3); /* disable MAPEN */ } @@ -167,16 +166,16 @@ static void __cpuinit geode_configure(void) ccr3 = getCx86(CX86_CCR3); setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */ - + /* FPU fast, DTE cache, Mem bypass */ setCx86(CX86_CCR4, getCx86(CX86_CCR4) | 0x38); setCx86(CX86_CCR3, ccr3); /* disable MAPEN */ - + set_cx86_memwb(); - set_cx86_reorder(); + set_cx86_reorder(); set_cx86_inc(); - + local_irq_restore(flags); } @@ -187,14 +186,16 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c) char *buf = c->x86_model_id; const char *p = NULL; - /* Bit 31 in normal CPUID used for nonstandard 3DNow ID; - 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */ - clear_bit(0*32+31, c->x86_capability); + /* + * 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); /* Cyrix used bit 24 in extended (AMD) CPUID for Cyrix MMX extensions */ - if ( test_bit(1*32+24, c->x86_capability) ) { - clear_bit(1*32+24, c->x86_capability); - set_bit(X86_FEATURE_CXMMX, c->x86_capability); + if (test_cpu_cap(c, 1*32+24)) { + clear_cpu_cap(c, 1*32+24); + set_cpu_cap(c, X86_FEATURE_CXMMX); } do_cyrix_devid(&dir0, &dir1); @@ -213,7 +214,7 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c) * the model, multiplier and stepping. Black magic included, * to make the silicon step/rev numbers match the printed ones. */ - + switch (dir0_msn) { unsigned char tmp; @@ -241,7 +242,7 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c) } else /* 686 */ p = Cx86_cb+1; /* Emulate MTRRs using Cyrix's ARRs. */ - set_bit(X86_FEATURE_CYRIX_ARR, c->x86_capability); + set_cpu_cap(c, X86_FEATURE_CYRIX_ARR); /* 6x86's contain this bug */ c->coma_bug = 1; break; @@ -250,17 +251,18 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c) #ifdef CONFIG_PCI { u32 vendor, device; - /* It isn't really a PCI quirk directly, but the cure is the - same. The MediaGX has deep magic SMM stuff that handles the - SB emulation. It throws away the fifo on disable_dma() which - is wrong and ruins the audio. - - Bug2: VSA1 has a wrap bug so that using maximum sized DMA - causes bad things. According to NatSemi VSA2 has another - bug to do with 'hlt'. I've not seen any boards using VSA2 - and X doesn't seem to support it either so who cares 8). - VSA1 we work around however. - */ + /* + * It isn't really a PCI quirk directly, but the cure is the + * same. The MediaGX has deep magic SMM stuff that handles the + * SB emulation. It throws away the fifo on disable_dma() which + * is wrong and ruins the audio. + * + * Bug2: VSA1 has a wrap bug so that using maximum sized DMA + * causes bad things. According to NatSemi VSA2 has another + * bug to do with 'hlt'. I've not seen any boards using VSA2 + * and X doesn't seem to support it either so who cares 8). + * VSA1 we work around however. + */ printk(KERN_INFO "Working around Cyrix MediaGX virtual DMA bugs.\n"); isa_dma_bridge_buggy = 2; @@ -273,55 +275,51 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c) /* * The 5510/5520 companion chips have a funky PIT. - */ + */ if (vendor == PCI_VENDOR_ID_CYRIX && (device == PCI_DEVICE_ID_CYRIX_5510 || device == PCI_DEVICE_ID_CYRIX_5520)) mark_tsc_unstable("cyrix 5510/5520 detected"); } #endif - c->x86_cache_size=16; /* Yep 16K integrated cache thats it */ + c->x86_cache_size = 16; /* Yep 16K integrated cache thats it */ /* GXm supports extended cpuid levels 'ala' AMD */ if (c->cpuid_level == 2) { /* Enable cxMMX extensions (GX1 Datasheet 54) */ setCx86(CX86_CCR7, getCx86(CX86_CCR7) | 1); - + /* * GXm : 0x30 ... 0x5f GXm datasheet 51 * GXlv: 0x6x GXlv datasheet 54 * ? : 0x7x * GX1 : 0x8x GX1 datasheet 56 */ - if((0x30 <= dir1 && dir1 <= 0x6f) || (0x80 <=dir1 && dir1 <= 0x8f)) + if ((0x30 <= dir1 && dir1 <= 0x6f) || (0x80 <= dir1 && dir1 <= 0x8f)) geode_configure(); get_model_name(c); /* get CPU marketing name */ return; - } - else { /* MediaGX */ + } else { /* MediaGX */ Cx86_cb[2] = (dir0_lsn & 1) ? '3' : '4'; p = Cx86_cb+2; c->x86_model = (dir1 & 0x20) ? 1 : 2; } break; - case 5: /* 6x86MX/M II */ - if (dir1 > 7) - { + case 5: /* 6x86MX/M II */ + if (dir1 > 7) { dir0_msn++; /* M II */ /* Enable MMX extensions (App note 108) */ setCx86(CX86_CCR7, getCx86(CX86_CCR7)|1); - } - else - { + } else { c->coma_bug = 1; /* 6x86MX, it has the bug. */ } tmp = (!(dir0_lsn & 7) || dir0_lsn & 1) ? 2 : 0; Cx86_cb[tmp] = cyrix_model_mult2[dir0_lsn & 7]; p = Cx86_cb+tmp; - if (((dir1 & 0x0f) > 4) || ((dir1 & 0xf0) == 0x20)) + if (((dir1 & 0x0f) > 4) || ((dir1 & 0xf0) == 0x20)) (c->x86_model)++; /* Emulate MTRRs using Cyrix's ARRs. */ - set_bit(X86_FEATURE_CYRIX_ARR, c->x86_capability); + set_cpu_cap(c, X86_FEATURE_CYRIX_ARR); break; case 0xf: /* Cyrix 486 without DEVID registers */ @@ -343,7 +341,8 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c) break; } strcpy(buf, Cx86_model[dir0_msn & 7]); - if (p) strcat(buf, p); + if (p) + strcat(buf, p); return; } @@ -352,7 +351,8 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c) */ static void __cpuinit init_nsc(struct cpuinfo_x86 *c) { - /* There may be GX1 processors in the wild that are branded + /* + * There may be GX1 processors in the wild that are branded * NSC and not Cyrix. * * This function only handles the GX processor, and kicks every @@ -377,7 +377,7 @@ static void __cpuinit init_nsc(struct cpuinfo_x86 *c) * by the fact that they preserve the flags across the division of 5/2. * PII and PPro exhibit this behavior too, but they have cpuid available. */ - + /* * Perform the Cyrix 5/2 test. A Cyrix won't change * the flags, while other 486 chips will. @@ -398,27 +398,26 @@ static inline int test_cyrix_52div(void) return (unsigned char) (test >> 8) == 0x02; } -static void __cpuinit cyrix_identify(struct cpuinfo_x86 * c) +static void __cpuinit cyrix_identify(struct cpuinfo_x86 *c) { /* Detect Cyrix with disabled CPUID */ - if ( c->x86 == 4 && test_cyrix_52div() ) { + if (c->x86 == 4 && test_cyrix_52div()) { unsigned char dir0, dir1; - + strcpy(c->x86_vendor_id, "CyrixInstead"); - c->x86_vendor = X86_VENDOR_CYRIX; - - /* Actually enable cpuid on the older cyrix */ - - /* Retrieve CPU revisions */ - + c->x86_vendor = X86_VENDOR_CYRIX; + + /* Actually enable cpuid on the older cyrix */ + + /* Retrieve CPU revisions */ + do_cyrix_devid(&dir0, &dir1); - dir0>>=4; - + dir0 >>= 4; + /* Check it is an affected model */ - - if (dir0 == 5 || dir0 == 3) - { + + if (dir0 == 5 || dir0 == 3) { unsigned char ccr3; unsigned long flags; printk(KERN_INFO "Enabling CPUID on Cyrix processor.\n"); @@ -434,26 +433,17 @@ static void __cpuinit cyrix_identify(struct cpuinfo_x86 * c) static struct cpu_dev cyrix_cpu_dev __cpuinitdata = { .c_vendor = "Cyrix", - .c_ident = { "CyrixInstead" }, + .c_ident = { "CyrixInstead" }, .c_init = init_cyrix, .c_identify = cyrix_identify, }; -int __init cyrix_init_cpu(void) -{ - cpu_devs[X86_VENDOR_CYRIX] = &cyrix_cpu_dev; - return 0; -} +cpu_vendor_dev_register(X86_VENDOR_CYRIX, &cyrix_cpu_dev); static struct cpu_dev nsc_cpu_dev __cpuinitdata = { .c_vendor = "NSC", - .c_ident = { "Geode by NSC" }, + .c_ident = { "Geode by NSC" }, .c_init = init_nsc, }; -int __init nsc_init_cpu(void) -{ - cpu_devs[X86_VENDOR_NSC] = &nsc_cpu_dev; - return 0; -} - +cpu_vendor_dev_register(X86_VENDOR_NSC, &nsc_cpu_dev); diff --git a/arch/x86/kernel/cpu/feature_names.c b/arch/x86/kernel/cpu/feature_names.c index ee975ac6bbcb..e43ad4ad4cba 100644 --- a/arch/x86/kernel/cpu/feature_names.c +++ b/arch/x86/kernel/cpu/feature_names.c @@ -4,7 +4,7 @@ * This file must not contain any executable code. */ -#include "asm/cpufeature.h" +#include <asm/cpufeature.h> /* * These flag bits must match the definitions in <asm/cpufeature.h>. diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index fae31ce747bd..fe9224c51d37 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -30,7 +30,7 @@ struct movsl_mask movsl_mask __read_mostly; #endif -void __cpuinit early_init_intel(struct cpuinfo_x86 *c) +static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) { /* Netburst reports 64 bytes clflush size, but does IO in 128 bytes */ if (c->x86 == 15 && c->x86_cache_alignment == 64) @@ -45,7 +45,7 @@ void __cpuinit early_init_intel(struct cpuinfo_x86 *c) * * This is called before we do cpu ident work */ - + int __cpuinit ppro_with_ram_bug(void) { /* Uses data from early_cpu_detect now */ @@ -58,7 +58,7 @@ int __cpuinit ppro_with_ram_bug(void) } return 0; } - + /* * P4 Xeon errata 037 workaround. @@ -69,7 +69,7 @@ static void __cpuinit Intel_errata_workarounds(struct cpuinfo_x86 *c) unsigned long lo, hi; if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_mask == 1)) { - rdmsr (MSR_IA32_MISC_ENABLE, lo, hi); + rdmsr(MSR_IA32_MISC_ENABLE, lo, hi); if ((lo & (1<<9)) == 0) { printk (KERN_INFO "CPU: C0 stepping P4 Xeon detected.\n"); printk (KERN_INFO "CPU: Disabling hardware prefetching (Errata 037)\n"); @@ -127,10 +127,10 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) */ c->f00f_bug = 0; if (!paravirt_enabled() && c->x86 == 5) { - static int f00f_workaround_enabled = 0; + static int f00f_workaround_enabled; c->f00f_bug = 1; - if ( !f00f_workaround_enabled ) { + if (!f00f_workaround_enabled) { trap_init_f00f_bug(); printk(KERN_NOTICE "Intel Pentium with F0 0F bug - workaround enabled.\n"); f00f_workaround_enabled = 1; @@ -139,20 +139,22 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) #endif l2 = init_intel_cacheinfo(c); - if (c->cpuid_level > 9 ) { + 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_bit(X86_FEATURE_ARCH_PERFMON, c->x86_capability); + set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON); } /* SEP CPUID bug: Pentium Pro reports SEP but doesn't have it until model 3 mask 3 */ if ((c->x86<<8 | c->x86_model<<4 | c->x86_mask) < 0x633) - clear_bit(X86_FEATURE_SEP, c->x86_capability); + clear_cpu_cap(c, X86_FEATURE_SEP); - /* Names for the Pentium II/Celeron processors - detectable only by also checking the cache size. - Dixon is NOT a Celeron. */ + /* + * Names for the Pentium II/Celeron processors + * detectable only by also checking the cache size. + * Dixon is NOT a Celeron. + */ if (c->x86 == 6) { switch (c->x86_model) { case 5: @@ -163,14 +165,14 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) p = "Mobile Pentium II (Dixon)"; } break; - + case 6: if (l2 == 128) p = "Celeron (Mendocino)"; else if (c->x86_mask == 0 || c->x86_mask == 5) p = "Celeron-A"; break; - + case 8: if (l2 == 128) p = "Celeron (Coppermine)"; @@ -178,9 +180,9 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) } } - if ( p ) + if (p) strcpy(c->x86_model_id, p); - + c->x86_max_cores = num_cpu_cores(c); detect_ht(c); @@ -207,28 +209,29 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) #endif if (cpu_has_xmm2) - set_bit(X86_FEATURE_LFENCE_RDTSC, c->x86_capability); + set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); if (c->x86 == 15) { - set_bit(X86_FEATURE_P4, c->x86_capability); + set_cpu_cap(c, X86_FEATURE_P4); } - if (c->x86 == 6) - set_bit(X86_FEATURE_P3, c->x86_capability); + if (c->x86 == 6) + set_cpu_cap(c, X86_FEATURE_P3); if (cpu_has_ds) { unsigned int l1; rdmsr(MSR_IA32_MISC_ENABLE, l1, l2); if (!(l1 & (1<<11))) - set_bit(X86_FEATURE_BTS, c->x86_capability); + set_cpu_cap(c, X86_FEATURE_BTS); if (!(l1 & (1<<12))) - set_bit(X86_FEATURE_PEBS, c->x86_capability); + set_cpu_cap(c, X86_FEATURE_PEBS); } if (cpu_has_bts) ds_init_intel(c); } -static unsigned int __cpuinit intel_size_cache(struct cpuinfo_x86 * c, unsigned int size) +static unsigned int __cpuinit intel_size_cache(struct cpuinfo_x86 *c, unsigned int size) { - /* Intel PIII Tualatin. This comes in two flavours. + /* + * Intel PIII Tualatin. This comes in two flavours. * One has 256kb of cache, the other 512. We have no way * to determine which, so we use a boottime override * for the 512kb model, and assume 256 otherwise. @@ -240,42 +243,42 @@ static unsigned int __cpuinit intel_size_cache(struct cpuinfo_x86 * c, unsigned static struct cpu_dev intel_cpu_dev __cpuinitdata = { .c_vendor = "Intel", - .c_ident = { "GenuineIntel" }, + .c_ident = { "GenuineIntel" }, .c_models = { - { .vendor = X86_VENDOR_INTEL, .family = 4, .model_names = - { - [0] = "486 DX-25/33", - [1] = "486 DX-50", - [2] = "486 SX", - [3] = "486 DX/2", - [4] = "486 SL", - [5] = "486 SX/2", - [7] = "486 DX/2-WB", - [8] = "486 DX/4", + { .vendor = X86_VENDOR_INTEL, .family = 4, .model_names = + { + [0] = "486 DX-25/33", + [1] = "486 DX-50", + [2] = "486 SX", + [3] = "486 DX/2", + [4] = "486 SL", + [5] = "486 SX/2", + [7] = "486 DX/2-WB", + [8] = "486 DX/4", [9] = "486 DX/4-WB" } }, { .vendor = X86_VENDOR_INTEL, .family = 5, .model_names = - { - [0] = "Pentium 60/66 A-step", - [1] = "Pentium 60/66", + { + [0] = "Pentium 60/66 A-step", + [1] = "Pentium 60/66", [2] = "Pentium 75 - 200", - [3] = "OverDrive PODP5V83", + [3] = "OverDrive PODP5V83", [4] = "Pentium MMX", - [7] = "Mobile Pentium 75 - 200", + [7] = "Mobile Pentium 75 - 200", [8] = "Mobile Pentium MMX" } }, { .vendor = X86_VENDOR_INTEL, .family = 6, .model_names = - { + { [0] = "Pentium Pro A-step", - [1] = "Pentium Pro", - [3] = "Pentium II (Klamath)", - [4] = "Pentium II (Deschutes)", - [5] = "Pentium II (Deschutes)", + [1] = "Pentium Pro", + [3] = "Pentium II (Klamath)", + [4] = "Pentium II (Deschutes)", + [5] = "Pentium II (Deschutes)", [6] = "Mobile Pentium II", - [7] = "Pentium III (Katmai)", - [8] = "Pentium III (Coppermine)", + [7] = "Pentium III (Katmai)", + [8] = "Pentium III (Coppermine)", [10] = "Pentium III (Cascades)", [11] = "Pentium III (Tualatin)", } @@ -290,15 +293,12 @@ static struct cpu_dev intel_cpu_dev __cpuinitdata = { } }, }, + .c_early_init = early_init_intel, .c_init = init_intel, .c_size_cache = intel_size_cache, }; -__init int intel_cpu_init(void) -{ - cpu_devs[X86_VENDOR_INTEL] = &intel_cpu_dev; - return 0; -} +cpu_vendor_dev_register(X86_VENDOR_INTEL, &intel_cpu_dev); #ifndef CONFIG_X86_CMPXCHG unsigned long cmpxchg_386_u8(volatile void *ptr, u8 old, u8 new) @@ -364,5 +364,5 @@ unsigned long long cmpxchg_486_u64(volatile void *ptr, u64 old, u64 new) EXPORT_SYMBOL(cmpxchg_486_u64); #endif -// arch_initcall(intel_cpu_init); +/* arch_initcall(intel_cpu_init); */ diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 1b889860eb73..26d615dcb149 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -129,7 +129,7 @@ struct _cpuid4_info { union _cpuid4_leaf_ebx ebx; union _cpuid4_leaf_ecx ecx; unsigned long size; - cpumask_t shared_cpu_map; + cpumask_t shared_cpu_map; /* future?: only cpus/node is needed */ }; unsigned short num_cache_leaves; @@ -451,8 +451,8 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) } /* pointer to _cpuid4_info array (for each cache leaf) */ -static struct _cpuid4_info *cpuid4_info[NR_CPUS]; -#define CPUID4_INFO_IDX(x,y) (&((cpuid4_info[x])[y])) +static DEFINE_PER_CPU(struct _cpuid4_info *, cpuid4_info); +#define CPUID4_INFO_IDX(x, y) (&((per_cpu(cpuid4_info, x))[y])) #ifdef CONFIG_SMP static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) @@ -474,7 +474,7 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) if (cpu_data(i).apicid >> index_msb == c->apicid >> index_msb) { cpu_set(i, this_leaf->shared_cpu_map); - if (i != cpu && cpuid4_info[i]) { + if (i != cpu && per_cpu(cpuid4_info, i)) { sibling_leaf = CPUID4_INFO_IDX(i, index); cpu_set(cpu, sibling_leaf->shared_cpu_map); } @@ -505,8 +505,8 @@ static void __cpuinit free_cache_attributes(unsigned int cpu) for (i = 0; i < num_cache_leaves; i++) cache_remove_shared_cpu_map(cpu, i); - kfree(cpuid4_info[cpu]); - cpuid4_info[cpu] = NULL; + kfree(per_cpu(cpuid4_info, cpu)); + per_cpu(cpuid4_info, cpu) = NULL; } static int __cpuinit detect_cache_attributes(unsigned int cpu) @@ -519,13 +519,13 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu) if (num_cache_leaves == 0) return -ENOENT; - cpuid4_info[cpu] = kzalloc( + per_cpu(cpuid4_info, cpu) = kzalloc( sizeof(struct _cpuid4_info) * num_cache_leaves, GFP_KERNEL); - if (cpuid4_info[cpu] == NULL) + if (per_cpu(cpuid4_info, cpu) == NULL) return -ENOMEM; oldmask = current->cpus_allowed; - retval = set_cpus_allowed(current, cpumask_of_cpu(cpu)); + retval = set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); if (retval) goto out; @@ -542,12 +542,12 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu) } cache_shared_cpu_map_setup(cpu, j); } - set_cpus_allowed(current, oldmask); + set_cpus_allowed_ptr(current, &oldmask); out: if (retval) { - kfree(cpuid4_info[cpu]); - cpuid4_info[cpu] = NULL; + kfree(per_cpu(cpuid4_info, cpu)); + per_cpu(cpuid4_info, cpu) = NULL; } return retval; @@ -561,7 +561,7 @@ out: extern struct sysdev_class cpu_sysdev_class; /* from drivers/base/cpu.c */ /* pointer to kobject for cpuX/cache */ -static struct kobject * cache_kobject[NR_CPUS]; +static DEFINE_PER_CPU(struct kobject *, cache_kobject); struct _index_kobject { struct kobject kobj; @@ -570,8 +570,8 @@ struct _index_kobject { }; /* pointer to array of kobjects for cpuX/cache/indexY */ -static struct _index_kobject *index_kobject[NR_CPUS]; -#define INDEX_KOBJECT_PTR(x,y) (&((index_kobject[x])[y])) +static DEFINE_PER_CPU(struct _index_kobject *, index_kobject); +#define INDEX_KOBJECT_PTR(x, y) (&((per_cpu(index_kobject, x))[y])) #define show_one_plus(file_name, object, val) \ static ssize_t show_##file_name \ @@ -591,11 +591,32 @@ static ssize_t show_size(struct _cpuid4_info *this_leaf, char *buf) return sprintf (buf, "%luK\n", this_leaf->size / 1024); } -static ssize_t show_shared_cpu_map(struct _cpuid4_info *this_leaf, char *buf) +static ssize_t show_shared_cpu_map_func(struct _cpuid4_info *this_leaf, + int type, char *buf) { - char mask_str[NR_CPUS]; - cpumask_scnprintf(mask_str, NR_CPUS, this_leaf->shared_cpu_map); - return sprintf(buf, "%s\n", mask_str); + ptrdiff_t len = PTR_ALIGN(buf + PAGE_SIZE - 1, PAGE_SIZE) - buf; + int n = 0; + + if (len > 1) { + cpumask_t *mask = &this_leaf->shared_cpu_map; + + n = type? + cpulist_scnprintf(buf, len-2, *mask): + cpumask_scnprintf(buf, len-2, *mask); + buf[n++] = '\n'; + buf[n] = '\0'; + } + return n; +} + +static inline ssize_t show_shared_cpu_map(struct _cpuid4_info *leaf, char *buf) +{ + return show_shared_cpu_map_func(leaf, 0, buf); +} + +static inline ssize_t show_shared_cpu_list(struct _cpuid4_info *leaf, char *buf) +{ + return show_shared_cpu_map_func(leaf, 1, buf); } static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf) { @@ -633,6 +654,7 @@ define_one_ro(ways_of_associativity); define_one_ro(number_of_sets); define_one_ro(size); define_one_ro(shared_cpu_map); +define_one_ro(shared_cpu_list); static struct attribute * default_attrs[] = { &type.attr, @@ -643,6 +665,7 @@ static struct attribute * default_attrs[] = { &number_of_sets.attr, &size.attr, &shared_cpu_map.attr, + &shared_cpu_list.attr, NULL }; @@ -684,10 +707,10 @@ static struct kobj_type ktype_percpu_entry = { static void __cpuinit cpuid4_cache_sysfs_exit(unsigned int cpu) { - kfree(cache_kobject[cpu]); - kfree(index_kobject[cpu]); - cache_kobject[cpu] = NULL; - index_kobject[cpu] = NULL; + kfree(per_cpu(cache_kobject, cpu)); + kfree(per_cpu(index_kobject, cpu)); + per_cpu(cache_kobject, cpu) = NULL; + per_cpu(index_kobject, cpu) = NULL; free_cache_attributes(cpu); } @@ -703,13 +726,14 @@ static int __cpuinit cpuid4_cache_sysfs_init(unsigned int cpu) return err; /* Allocate all required memory */ - cache_kobject[cpu] = kzalloc(sizeof(struct kobject), GFP_KERNEL); - if (unlikely(cache_kobject[cpu] == NULL)) + per_cpu(cache_kobject, cpu) = + kzalloc(sizeof(struct kobject), GFP_KERNEL); + if (unlikely(per_cpu(cache_kobject, cpu) == NULL)) goto err_out; - index_kobject[cpu] = kzalloc( + per_cpu(index_kobject, cpu) = kzalloc( sizeof(struct _index_kobject ) * num_cache_leaves, GFP_KERNEL); - if (unlikely(index_kobject[cpu] == NULL)) + if (unlikely(per_cpu(index_kobject, cpu) == NULL)) goto err_out; return 0; @@ -733,7 +757,8 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev) if (unlikely(retval < 0)) return retval; - retval = kobject_init_and_add(cache_kobject[cpu], &ktype_percpu_entry, + retval = kobject_init_and_add(per_cpu(cache_kobject, cpu), + &ktype_percpu_entry, &sys_dev->kobj, "%s", "cache"); if (retval < 0) { cpuid4_cache_sysfs_exit(cpu); @@ -745,13 +770,14 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev) this_object->cpu = cpu; this_object->index = i; retval = kobject_init_and_add(&(this_object->kobj), - &ktype_cache, cache_kobject[cpu], + &ktype_cache, + per_cpu(cache_kobject, cpu), "index%1lu", i); if (unlikely(retval)) { for (j = 0; j < i; j++) { kobject_put(&(INDEX_KOBJECT_PTR(cpu,j)->kobj)); } - kobject_put(cache_kobject[cpu]); + kobject_put(per_cpu(cache_kobject, cpu)); cpuid4_cache_sysfs_exit(cpu); break; } @@ -760,7 +786,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev) if (!retval) cpu_set(cpu, cache_dev_map); - kobject_uevent(cache_kobject[cpu], KOBJ_ADD); + kobject_uevent(per_cpu(cache_kobject, cpu), KOBJ_ADD); return retval; } @@ -769,7 +795,7 @@ static void __cpuinit cache_remove_dev(struct sys_device * sys_dev) unsigned int cpu = sys_dev->id; unsigned long i; - if (cpuid4_info[cpu] == NULL) + if (per_cpu(cpuid4_info, cpu) == NULL) return; if (!cpu_isset(cpu, cache_dev_map)) return; @@ -777,7 +803,7 @@ static void __cpuinit cache_remove_dev(struct sys_device * sys_dev) for (i = 0; i < num_cache_leaves; i++) kobject_put(&(INDEX_KOBJECT_PTR(cpu,i)->kobj)); - kobject_put(cache_kobject[cpu]); + kobject_put(per_cpu(cache_kobject, cpu)); cpuid4_cache_sysfs_exit(cpu); } diff --git a/arch/x86/kernel/cpu/mcheck/mce_32.c b/arch/x86/kernel/cpu/mcheck/mce_32.c index a5182dcd94ae..774d87cfd8cd 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_32.c +++ b/arch/x86/kernel/cpu/mcheck/mce_32.c @@ -10,20 +10,20 @@ #include <linux/smp.h> #include <linux/thread_info.h> -#include <asm/processor.h> +#include <asm/processor.h> #include <asm/system.h> #include <asm/mce.h> #include "mce.h" -int mce_disabled = 0; +int mce_disabled; int nr_mce_banks; EXPORT_SYMBOL_GPL(nr_mce_banks); /* non-fatal.o */ /* Handle unconfigured int18 (should never happen) */ -static void unexpected_machine_check(struct pt_regs * regs, long error_code) -{ +static void unexpected_machine_check(struct pt_regs *regs, long error_code) +{ printk(KERN_ERR "CPU#%d: Unexpected int18 (Machine Check).\n", smp_processor_id()); } @@ -33,30 +33,30 @@ void (*machine_check_vector)(struct pt_regs *, long error_code) = unexpected_mac /* This has to be run for each processor */ void mcheck_init(struct cpuinfo_x86 *c) { - if (mce_disabled==1) + if (mce_disabled == 1) return; switch (c->x86_vendor) { - case X86_VENDOR_AMD: - amd_mcheck_init(c); - break; - - case X86_VENDOR_INTEL: - if (c->x86==5) - intel_p5_mcheck_init(c); - if (c->x86==6) - intel_p6_mcheck_init(c); - if (c->x86==15) - intel_p4_mcheck_init(c); - break; - - case X86_VENDOR_CENTAUR: - if (c->x86==5) - winchip_mcheck_init(c); - break; - - default: - break; + case X86_VENDOR_AMD: + amd_mcheck_init(c); + break; + + case X86_VENDOR_INTEL: + if (c->x86 == 5) + intel_p5_mcheck_init(c); + if (c->x86 == 6) + intel_p6_mcheck_init(c); + if (c->x86 == 15) + intel_p4_mcheck_init(c); + break; + + case X86_VENDOR_CENTAUR: + if (c->x86 == 5) + winchip_mcheck_init(c); + break; + + default: + break; } } diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c index 9a699ed03598..e07e8c068ae0 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_64.c @@ -49,7 +49,7 @@ static int banks; static unsigned long bank[NR_BANKS] = { [0 ... NR_BANKS-1] = ~0UL }; static unsigned long notify_user; static int rip_msr; -static int mce_bootlog = 1; +static int mce_bootlog = -1; static atomic_t mce_events; static char trigger[128]; @@ -471,13 +471,15 @@ static void mce_init(void *dummy) static void __cpuinit mce_cpu_quirks(struct cpuinfo_x86 *c) { /* This should be disabled by the BIOS, but isn't always */ - if (c->x86_vendor == X86_VENDOR_AMD && c->x86 == 15) { - /* disable GART TBL walk error reporting, which trips off - incorrectly with the IOMMU & 3ware & Cerberus. */ - clear_bit(10, &bank[4]); - /* Lots of broken BIOS around that don't clear them - by default and leave crap in there. Don't log. */ - mce_bootlog = 0; + if (c->x86_vendor == X86_VENDOR_AMD) { + if(c->x86 == 15) + /* disable GART TBL walk error reporting, which trips off + incorrectly with the IOMMU & 3ware & Cerberus. */ + clear_bit(10, &bank[4]); + if(c->x86 <= 17 && mce_bootlog < 0) + /* Lots of broken BIOS around that don't clear them + by default and leave crap in there. Don't log. */ + mce_bootlog = 0; } } diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c index 32671da8184e..7c9a813e1193 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c @@ -251,18 +251,18 @@ struct threshold_attr { ssize_t(*store) (struct threshold_block *, const char *, size_t count); }; -static cpumask_t affinity_set(unsigned int cpu) +static void affinity_set(unsigned int cpu, cpumask_t *oldmask, + cpumask_t *newmask) { - cpumask_t oldmask = current->cpus_allowed; - cpumask_t newmask = CPU_MASK_NONE; - cpu_set(cpu, newmask); - set_cpus_allowed(current, newmask); - return oldmask; + *oldmask = current->cpus_allowed; + cpus_clear(*newmask); + cpu_set(cpu, *newmask); + set_cpus_allowed_ptr(current, newmask); } -static void affinity_restore(cpumask_t oldmask) +static void affinity_restore(const cpumask_t *oldmask) { - set_cpus_allowed(current, oldmask); + set_cpus_allowed_ptr(current, oldmask); } #define SHOW_FIELDS(name) \ @@ -277,15 +277,15 @@ static ssize_t store_interrupt_enable(struct threshold_block *b, const char *buf, size_t count) { char *end; - cpumask_t oldmask; + cpumask_t oldmask, newmask; unsigned long new = simple_strtoul(buf, &end, 0); if (end == buf) return -EINVAL; b->interrupt_enable = !!new; - oldmask = affinity_set(b->cpu); + affinity_set(b->cpu, &oldmask, &newmask); threshold_restart_bank(b, 0, 0); - affinity_restore(oldmask); + affinity_restore(&oldmask); return end - buf; } @@ -294,7 +294,7 @@ static ssize_t store_threshold_limit(struct threshold_block *b, const char *buf, size_t count) { char *end; - cpumask_t oldmask; + cpumask_t oldmask, newmask; u16 old; unsigned long new = simple_strtoul(buf, &end, 0); if (end == buf) @@ -306,9 +306,9 @@ static ssize_t store_threshold_limit(struct threshold_block *b, old = b->threshold_limit; b->threshold_limit = new; - oldmask = affinity_set(b->cpu); + affinity_set(b->cpu, &oldmask, &newmask); threshold_restart_bank(b, 0, old); - affinity_restore(oldmask); + affinity_restore(&oldmask); return end - buf; } @@ -316,10 +316,10 @@ static ssize_t store_threshold_limit(struct threshold_block *b, static ssize_t show_error_count(struct threshold_block *b, char *buf) { u32 high, low; - cpumask_t oldmask; - oldmask = affinity_set(b->cpu); + cpumask_t oldmask, newmask; + affinity_set(b->cpu, &oldmask, &newmask); rdmsr(b->address, low, high); - affinity_restore(oldmask); + affinity_restore(&oldmask); return sprintf(buf, "%x\n", (high & 0xFFF) - (THRESHOLD_MAX - b->threshold_limit)); } @@ -327,10 +327,10 @@ static ssize_t show_error_count(struct threshold_block *b, char *buf) static ssize_t store_error_count(struct threshold_block *b, const char *buf, size_t count) { - cpumask_t oldmask; - oldmask = affinity_set(b->cpu); + cpumask_t oldmask, newmask; + affinity_set(b->cpu, &oldmask, &newmask); threshold_restart_bank(b, 1, 0); - affinity_restore(oldmask); + affinity_restore(&oldmask); return 1; } @@ -468,7 +468,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) { int i, err = 0; struct threshold_bank *b = NULL; - cpumask_t oldmask = CPU_MASK_NONE; + cpumask_t oldmask, newmask; char name[32]; sprintf(name, "threshold_bank%i", bank); @@ -519,10 +519,10 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) per_cpu(threshold_banks, cpu)[bank] = b; - oldmask = affinity_set(cpu); + affinity_set(cpu, &oldmask, &newmask); err = allocate_threshold_blocks(cpu, bank, 0, MSR_IA32_MC0_MISC + bank * 4); - affinity_restore(oldmask); + affinity_restore(&oldmask); if (err) goto out_free; diff --git a/arch/x86/kernel/cpu/mcheck/non-fatal.c b/arch/x86/kernel/cpu/mcheck/non-fatal.c index bf39409b3838..00ccb6c14ec2 100644 --- a/arch/x86/kernel/cpu/mcheck/non-fatal.c +++ b/arch/x86/kernel/cpu/mcheck/non-fatal.c @@ -16,7 +16,7 @@ #include <linux/smp.h> #include <linux/module.h> -#include <asm/processor.h> +#include <asm/processor.h> #include <asm/system.h> #include <asm/msr.h> @@ -26,23 +26,26 @@ static int firstbank; #define MCE_RATE 15*HZ /* timer rate is 15s */ -static void mce_checkregs (void *info) +static void mce_checkregs(void *info) { u32 low, high; int i; - for (i=firstbank; i<nr_mce_banks; i++) { - rdmsr (MSR_IA32_MC0_STATUS+i*4, low, high); + for (i = firstbank; i < nr_mce_banks; i++) { + rdmsr(MSR_IA32_MC0_STATUS+i*4, low, high); if (high & (1<<31)) { printk(KERN_INFO "MCE: The hardware reports a non " "fatal, correctable incident occurred on " "CPU %d.\n", smp_processor_id()); - printk (KERN_INFO "Bank %d: %08x%08x\n", i, high, low); + printk(KERN_INFO "Bank %d: %08x%08x\n", i, high, low); - /* Scrub the error so we don't pick it up in MCE_RATE seconds time. */ - wrmsr (MSR_IA32_MC0_STATUS+i*4, 0UL, 0UL); + /* + * Scrub the error so we don't pick it up in MCE_RATE + * seconds time. + */ + wrmsr(MSR_IA32_MC0_STATUS+i*4, 0UL, 0UL); /* Serialize */ wmb(); @@ -55,10 +58,10 @@ static void mce_work_fn(struct work_struct *work); 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); schedule_delayed_work(&mce_work, round_jiffies_relative(MCE_RATE)); -} +} static int __init init_nonfatal_mce_checker(void) { diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c index a18310aaae0c..bfa5817afdda 100644 --- a/arch/x86/kernel/cpu/mcheck/p5.c +++ b/arch/x86/kernel/cpu/mcheck/p5.c @@ -9,20 +9,20 @@ #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 Pentium class Intel */ -static void pentium_machine_check(struct pt_regs * regs, long error_code) +static void pentium_machine_check(struct pt_regs *regs, long error_code) { u32 loaddr, hi, lotype; rdmsr(MSR_IA32_P5_MC_ADDR, loaddr, hi); rdmsr(MSR_IA32_P5_MC_TYPE, lotype, hi); printk(KERN_EMERG "CPU#%d: Machine Check Exception: 0x%8X (type 0x%8X).\n", smp_processor_id(), loaddr, lotype); - if(lotype&(1<<5)) + if (lotype&(1<<5)) printk(KERN_EMERG "CPU#%d: Possible thermal failure (CPU on fire ?).\n", smp_processor_id()); add_taint(TAINT_MACHINE_CHECK); } @@ -31,13 +31,13 @@ static void pentium_machine_check(struct pt_regs * regs, long error_code) void intel_p5_mcheck_init(struct cpuinfo_x86 *c) { u32 l, h; - + /*Check for MCE support */ - if( !cpu_has(c, X86_FEATURE_MCE) ) - return; + if (!cpu_has(c, X86_FEATURE_MCE)) + return; /* Default P5 to off as its often misconnected */ - if(mce_disabled != -1) + if (mce_disabled != -1) return; machine_check_vector = pentium_machine_check; wmb(); @@ -47,7 +47,7 @@ void intel_p5_mcheck_init(struct cpuinfo_x86 *c) rdmsr(MSR_IA32_P5_MC_TYPE, l, h); printk(KERN_INFO "Intel old style machine check architecture supported.\n"); - /* Enable MCE */ + /* Enable MCE */ set_in_cr4(X86_CR4_MCE); printk(KERN_INFO "Intel old style machine check reporting enabled on CPU#%d.\n", smp_processor_id()); } diff --git a/arch/x86/kernel/cpu/mcheck/p6.c b/arch/x86/kernel/cpu/mcheck/p6.c index 74342604d30e..62efc9c2b3af 100644 --- a/arch/x86/kernel/cpu/mcheck/p6.c +++ b/arch/x86/kernel/cpu/mcheck/p6.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 PII/PIII */ -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); @@ -55,30 +55,30 @@ 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 + printk(KERN_EMERG "Attempting to continue.\n"); + /* + * 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++) { unsigned int 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); + wrmsr(msr, 0UL, 0UL); /* Serialize */ wmb(); add_taint(TAINT_MACHINE_CHECK); } } mcgstl &= ~(1<<2); - wrmsr (MSR_IA32_MCG_STATUS,mcgstl, mcgsth); + wrmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth); } /* Set up machine check reporting for processors with Intel style MCE */ @@ -86,21 +86,21 @@ void intel_p6_mcheck_init(struct cpuinfo_x86 *c) { u32 l, h; int i; - + /* Check for MCE support */ if (!cpu_has(c, X86_FEATURE_MCE)) return; /* Check for PPro style MCA */ - if (!cpu_has(c, X86_FEATURE_MCA)) + if (!cpu_has(c, X86_FEATURE_MCA)) return; /* Ok machine check is available */ 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); nr_mce_banks = l & 0xff; @@ -110,13 +110,13 @@ void intel_p6_mcheck_init(struct cpuinfo_x86 *c) * - MC0_CTL should not be written * - Status registers on all banks should be cleared on reset */ - for (i=1; i<nr_mce_banks; i++) - wrmsr (MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff); + for (i = 1; i < nr_mce_banks; i++) + wrmsr(MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff); - for (i=0; i<nr_mce_banks; i++) - wrmsr (MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0); + for (i = 0; i < nr_mce_banks; i++) + 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/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 9b7e01daa1ca..1f4cc48c14c6 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -1,5 +1,4 @@ /* - * linux/arch/i386/kernel/cpu/mcheck/therm_throt.c * * Thermal throttle event support code (such as syslog messaging and rate * limiting) that was factored out from x86_64 (mce_intel.c) and i386 (p4.c). diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c index 3d428d5afc52..f2be3e190c6b 100644 --- a/arch/x86/kernel/cpu/mcheck/winchip.c +++ b/arch/x86/kernel/cpu/mcheck/winchip.c @@ -8,14 +8,14 @@ #include <linux/kernel.h> #include <linux/interrupt.h> -#include <asm/processor.h> +#include <asm/processor.h> #include <asm/system.h> #include <asm/msr.h> #include "mce.h" /* Machine check handler for WinChip C6 */ -static void winchip_machine_check(struct pt_regs * regs, long error_code) +static void winchip_machine_check(struct pt_regs *regs, long error_code) { printk(KERN_EMERG "CPU0: Machine Check Exception.\n"); add_taint(TAINT_MACHINE_CHECK); @@ -28,8 +28,8 @@ void winchip_mcheck_init(struct cpuinfo_x86 *c) machine_check_vector = winchip_machine_check; wmb(); rdmsr(MSR_IDT_FCR1, lo, hi); - lo|= (1<<2); /* Enable EIERRINT (int 18 MCE) */ - lo&= ~(1<<4); /* Enable MCE */ + lo |= (1<<2); /* Enable EIERRINT (int 18 MCE) */ + lo &= ~(1<<4); /* Enable MCE */ wrmsr(MSR_IDT_FCR1, lo, hi); set_in_cr4(X86_CR4_MCE); printk(KERN_INFO "Winchip machine check reporting enabled on CPU#0.\n"); diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 3e18db4cefee..5d241ce94a44 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -11,6 +11,7 @@ #include <asm/cpufeature.h> #include <asm/processor-flags.h> #include <asm/tlbflush.h> +#include <asm/pat.h> #include "mtrr.h" struct mtrr_state { @@ -35,6 +36,8 @@ 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; #undef MODULE_PARAM_PREFIX #define MODULE_PARAM_PREFIX "mtrr." @@ -42,6 +45,111 @@ static struct mtrr_state mtrr_state = {}; static int mtrr_show; module_param_named(show, mtrr_show, bool, 0); +/* + * Returns the effective MTRR type for the region + * Error returns: + * - 0xFE - when the range is "not entirely covered" by _any_ var range MTRR + * - 0xFF - when MTRR is not enabled + */ +u8 mtrr_type_lookup(u64 start, u64 end) +{ + int i; + u64 base, mask; + u8 prev_match, curr_match; + + if (!mtrr_state_set) + return 0xFF; + + if (!mtrr_state.enabled) + return 0xFF; + + /* Make end inclusive end, instead of exclusive */ + end--; + + /* Look in fixed ranges. Just return the type as per start */ + if (mtrr_state.have_fixed && (start < 0x100000)) { + int idx; + + if (start < 0x80000) { + idx = 0; + idx += (start >> 16); + return mtrr_state.fixed_ranges[idx]; + } else if (start < 0xC0000) { + idx = 1 * 8; + idx += ((start - 0x80000) >> 14); + return mtrr_state.fixed_ranges[idx]; + } else if (start < 0x1000000) { + idx = 3 * 8; + idx += ((start - 0xC0000) >> 12); + return mtrr_state.fixed_ranges[idx]; + } + } + + /* + * Look in variable ranges + * Look of multiple ranges matching this address and pick type + * as per MTRR precedence + */ + if (!(mtrr_state.enabled & 2)) { + return mtrr_state.def_type; + } + + prev_match = 0xFF; + for (i = 0; i < num_var_ranges; ++i) { + unsigned short start_state, end_state; + + if (!(mtrr_state.var_ranges[i].mask_lo & (1 << 11))) + continue; + + base = (((u64)mtrr_state.var_ranges[i].base_hi) << 32) + + (mtrr_state.var_ranges[i].base_lo & PAGE_MASK); + mask = (((u64)mtrr_state.var_ranges[i].mask_hi) << 32) + + (mtrr_state.var_ranges[i].mask_lo & PAGE_MASK); + + start_state = ((start & mask) == (base & mask)); + end_state = ((end & mask) == (base & mask)); + if (start_state != end_state) + return 0xFE; + + if ((start & mask) != (base & mask)) { + continue; + } + + curr_match = mtrr_state.var_ranges[i].base_lo & 0xff; + if (prev_match == 0xFF) { + prev_match = curr_match; + continue; + } + + if (prev_match == MTRR_TYPE_UNCACHABLE || + curr_match == MTRR_TYPE_UNCACHABLE) { + return MTRR_TYPE_UNCACHABLE; + } + + if ((prev_match == MTRR_TYPE_WRBACK && + curr_match == MTRR_TYPE_WRTHROUGH) || + (prev_match == MTRR_TYPE_WRTHROUGH && + curr_match == MTRR_TYPE_WRBACK)) { + prev_match = MTRR_TYPE_WRTHROUGH; + curr_match = MTRR_TYPE_WRTHROUGH; + } + + if (prev_match != curr_match) { + return MTRR_TYPE_UNCACHABLE; + } + } + + if (tom2) { + if (start >= (1ULL<<32) && (end < tom2)) + return MTRR_TYPE_WRBACK; + } + + if (prev_match != 0xFF) + return prev_match; + + return mtrr_state.def_type; +} + /* Get the MSR pair relating to a var range */ static void get_mtrr_var_range(unsigned int index, struct mtrr_var_range *vr) @@ -79,12 +187,16 @@ static void print_fixed(unsigned base, unsigned step, const mtrr_type*types) base, base + step - 1, mtrr_attrib_to_str(*types)); } +static void prepare_set(void); +static void post_set(void); + /* Grab all of the MTRR state for this CPU into *state */ void __init get_mtrr_state(void) { unsigned int i; struct mtrr_var_range *vrs; unsigned lo, dummy; + unsigned long flags; vrs = mtrr_state.var_ranges; @@ -100,6 +212,15 @@ void __init get_mtrr_state(void) mtrr_state.def_type = (lo & 0xff); mtrr_state.enabled = (lo & 0xc00) >> 10; + if (amd_special_default_mtrr()) { + unsigned lo, hi; + /* TOP_MEM2 */ + rdmsr(MSR_K8_TOP_MEM2, lo, hi); + tom2 = hi; + tom2 <<= 32; + tom2 |= lo; + tom2 &= 0xffffff8000000ULL; + } if (mtrr_show) { int high_width; @@ -130,7 +251,22 @@ void __init get_mtrr_state(void) else printk(KERN_INFO "MTRR %u disabled\n", i); } + if (tom2) { + printk(KERN_INFO "TOM2: %016llx aka %lldM\n", + tom2, tom2>>20); + } } + mtrr_state_set = 1; + + /* PAT setup for BP. We need to go through sync steps here */ + local_irq_save(flags); + prepare_set(); + + pat_init(); + + post_set(); + local_irq_restore(flags); + } /* Some BIOS's are fucked and don't set all MTRRs the same! */ @@ -397,6 +533,9 @@ static void generic_set_all(void) /* Actually set the state */ mask = set_mtrr_state(); + /* also set PAT */ + pat_init(); + post_set(); local_irq_restore(flags); diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c index 91e150acb46c..84c480bb3715 100644 --- a/arch/x86/kernel/cpu/mtrr/if.c +++ b/arch/x86/kernel/cpu/mtrr/if.c @@ -424,11 +424,10 @@ static int __init mtrr_if_init(void) return -ENODEV; proc_root_mtrr = - create_proc_entry("mtrr", S_IWUSR | S_IRUGO, &proc_root); - if (proc_root_mtrr) { + proc_create("mtrr", S_IWUSR | S_IRUGO, NULL, &mtrr_fops); + + if (proc_root_mtrr) proc_root_mtrr->owner = THIS_MODULE; - proc_root_mtrr->proc_fops = &mtrr_fops; - } return 0; } diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index a6450b3ae759..6a1e278d9323 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -627,7 +627,7 @@ early_param("disable_mtrr_trim", disable_mtrr_trim_setup); #define Tom2Enabled (1U << 21) #define Tom2ForceMemTypeWB (1U << 22) -static __init int amd_special_default_mtrr(void) +int __init amd_special_default_mtrr(void) { u32 l, h; diff --git a/arch/x86/kernel/cpu/mtrr/state.c b/arch/x86/kernel/cpu/mtrr/state.c index 9f8ba923d1c9..7f7e2753685b 100644 --- a/arch/x86/kernel/cpu/mtrr/state.c +++ b/arch/x86/kernel/cpu/mtrr/state.c @@ -19,13 +19,15 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt) if (use_intel() || is_cpu(CYRIX)) { /* Save value of CR4 and clear Page Global Enable (bit 7) */ - if ( cpu_has_pge ) { + if (cpu_has_pge) { ctxt->cr4val = read_cr4(); write_cr4(ctxt->cr4val & ~X86_CR4_PGE); } - /* Disable and flush caches. Note that wbinvd flushes the TLBs as - a side-effect */ + /* + * Disable and flush caches. Note that wbinvd flushes the TLBs + * as a side-effect + */ cr0 = read_cr0() | X86_CR0_CD; wbinvd(); write_cr0(cr0); @@ -42,7 +44,7 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt) void set_mtrr_cache_disable(struct set_mtrr_context *ctxt) { - if (use_intel()) + if (use_intel()) /* Disable MTRRs, and set the default type to uncached */ mtrr_wrmsr(MTRRdefType_MSR, ctxt->deftype_lo & 0xf300UL, ctxt->deftype_hi); @@ -66,12 +68,12 @@ void set_mtrr_done(struct set_mtrr_context *ctxt) else /* Cyrix ARRs - everything else was excluded at the top */ setCx86(CX86_CCR3, ctxt->ccr3); - + /* Enable caches */ write_cr0(read_cr0() & 0xbfffffff); /* Restore value of CR4 */ - if ( cpu_has_pge ) + if (cpu_has_pge) write_cr4(ctxt->cr4val); } /* Re-enable interrupts locally (if enabled previously) */ diff --git a/arch/x86/kernel/cpu/nexgen.c b/arch/x86/kernel/cpu/nexgen.c deleted file mode 100644 index 961fbe1a748f..000000000000 --- a/arch/x86/kernel/cpu/nexgen.c +++ /dev/null @@ -1,60 +0,0 @@ -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/string.h> -#include <asm/processor.h> - -#include "cpu.h" - -/* - * Detect a NexGen CPU running without BIOS hypercode new enough - * to have CPUID. (Thanks to Herbert Oppmann) - */ - -static int __cpuinit deep_magic_nexgen_probe(void) -{ - int ret; - - __asm__ __volatile__ ( - " movw $0x5555, %%ax\n" - " xorw %%dx,%%dx\n" - " movw $2, %%cx\n" - " divw %%cx\n" - " movl $0, %%eax\n" - " jnz 1f\n" - " movl $1, %%eax\n" - "1:\n" - : "=a" (ret) : : "cx", "dx" ); - return ret; -} - -static void __cpuinit init_nexgen(struct cpuinfo_x86 * c) -{ - c->x86_cache_size = 256; /* A few had 1 MB... */ -} - -static void __cpuinit nexgen_identify(struct cpuinfo_x86 * c) -{ - /* Detect NexGen with old hypercode */ - if ( deep_magic_nexgen_probe() ) { - strcpy(c->x86_vendor_id, "NexGenDriven"); - } -} - -static struct cpu_dev nexgen_cpu_dev __cpuinitdata = { - .c_vendor = "Nexgen", - .c_ident = { "NexGenDriven" }, - .c_models = { - { .vendor = X86_VENDOR_NEXGEN, - .family = 5, - .model_names = { [1] = "Nx586" } - }, - }, - .c_init = init_nexgen, - .c_identify = nexgen_identify, -}; - -int __init nexgen_init_cpu(void) -{ - cpu_devs[X86_VENDOR_NEXGEN] = &nexgen_cpu_dev; - return 0; -} diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index b943e10ad814..f9ae93adffe5 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -614,16 +614,6 @@ static struct wd_ops intel_arch_wd_ops __read_mostly = { .evntsel = MSR_ARCH_PERFMON_EVENTSEL1, }; -static struct wd_ops coreduo_wd_ops = { - .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_PERFCTR0, - .evntsel = MSR_ARCH_PERFMON_EVENTSEL0, -}; - static void probe_nmi_watchdog(void) { switch (boot_cpu_data.x86_vendor) { @@ -637,8 +627,8 @@ static void probe_nmi_watchdog(void) /* 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) { - wd_ops = &coreduo_wd_ops; - break; + intel_arch_wd_ops.perfctr = MSR_ARCH_PERFMON_PERFCTR0; + intel_arch_wd_ops.evntsel = MSR_ARCH_PERFMON_EVENTSEL0; } if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { wd_ops = &intel_arch_wd_ops; diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index af11d31dce0a..0d0d9057e7c0 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -1,85 +1,145 @@ #include <linux/smp.h> #include <linux/timex.h> #include <linux/string.h> -#include <asm/semaphore.h> #include <linux/seq_file.h> #include <linux/cpufreq.h> /* * Get CPU information for use by the procfs. */ +#ifdef CONFIG_X86_32 +static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c, + unsigned int cpu) +{ +#ifdef CONFIG_X86_HT + if (c->x86_max_cores * smp_num_siblings > 1) { + seq_printf(m, "physical id\t: %d\n", c->phys_proc_id); + seq_printf(m, "siblings\t: %d\n", + cpus_weight(per_cpu(cpu_core_map, cpu))); + seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id); + seq_printf(m, "cpu cores\t: %d\n", c->booted_cores); + seq_printf(m, "apicid\t\t: %d\n", c->apicid); + seq_printf(m, "initial apicid\t: %d\n", c->initial_apicid); + } +#endif +} + +static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) +{ + /* + * We use exception 16 if we have hardware math and we've either seen + * it or the CPU claims it is internal + */ + int fpu_exception = c->hard_math && (ignore_fpu_irq || cpu_has_fpu); + seq_printf(m, + "fdiv_bug\t: %s\n" + "hlt_bug\t\t: %s\n" + "f00f_bug\t: %s\n" + "coma_bug\t: %s\n" + "fpu\t\t: %s\n" + "fpu_exception\t: %s\n" + "cpuid level\t: %d\n" + "wp\t\t: %s\n", + c->fdiv_bug ? "yes" : "no", + c->hlt_works_ok ? "no" : "yes", + c->f00f_bug ? "yes" : "no", + c->coma_bug ? "yes" : "no", + c->hard_math ? "yes" : "no", + fpu_exception ? "yes" : "no", + c->cpuid_level, + c->wp_works_ok ? "yes" : "no"); +} +#else +static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c, + unsigned int cpu) +{ +#ifdef CONFIG_SMP + if (c->x86_max_cores * smp_num_siblings > 1) { + seq_printf(m, "physical id\t: %d\n", c->phys_proc_id); + seq_printf(m, "siblings\t: %d\n", + cpus_weight(per_cpu(cpu_core_map, cpu))); + seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id); + seq_printf(m, "cpu cores\t: %d\n", c->booted_cores); + seq_printf(m, "apicid\t\t: %d\n", c->apicid); + seq_printf(m, "initial apicid\t: %d\n", c->initial_apicid); + } +#endif +} + +static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) +{ + seq_printf(m, + "fpu\t\t: yes\n" + "fpu_exception\t: yes\n" + "cpuid level\t: %d\n" + "wp\t\t: yes\n", + c->cpuid_level); +} +#endif + static int show_cpuinfo(struct seq_file *m, void *v) { struct cpuinfo_x86 *c = v; - int i, n = 0; - int fpu_exception; + unsigned int cpu = 0; + int i; #ifdef CONFIG_SMP - n = c->cpu_index; + cpu = c->cpu_index; #endif - seq_printf(m, "processor\t: %d\n" - "vendor_id\t: %s\n" - "cpu family\t: %d\n" - "model\t\t: %d\n" - "model name\t: %s\n", - n, - c->x86_vendor_id[0] ? c->x86_vendor_id : "unknown", - c->x86, - c->x86_model, - c->x86_model_id[0] ? c->x86_model_id : "unknown"); + seq_printf(m, "processor\t: %u\n" + "vendor_id\t: %s\n" + "cpu family\t: %d\n" + "model\t\t: %u\n" + "model name\t: %s\n", + cpu, + c->x86_vendor_id[0] ? c->x86_vendor_id : "unknown", + c->x86, + c->x86_model, + c->x86_model_id[0] ? c->x86_model_id : "unknown"); if (c->x86_mask || c->cpuid_level >= 0) seq_printf(m, "stepping\t: %d\n", c->x86_mask); else seq_printf(m, "stepping\t: unknown\n"); - if ( cpu_has(c, X86_FEATURE_TSC) ) { - unsigned int freq = cpufreq_quick_get(n); + if (cpu_has(c, X86_FEATURE_TSC)) { + unsigned int freq = cpufreq_quick_get(cpu); + if (!freq) freq = cpu_khz; seq_printf(m, "cpu MHz\t\t: %u.%03u\n", - freq / 1000, (freq % 1000)); + freq / 1000, (freq % 1000)); } /* Cache size */ if (c->x86_cache_size >= 0) seq_printf(m, "cache size\t: %d KB\n", c->x86_cache_size); -#ifdef CONFIG_X86_HT - if (c->x86_max_cores * smp_num_siblings > 1) { - seq_printf(m, "physical id\t: %d\n", c->phys_proc_id); - seq_printf(m, "siblings\t: %d\n", - cpus_weight(per_cpu(cpu_core_map, n))); - seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id); - seq_printf(m, "cpu cores\t: %d\n", c->booted_cores); - } -#endif - - /* We use exception 16 if we have hardware math and we've either seen it or the CPU claims it is internal */ - fpu_exception = c->hard_math && (ignore_fpu_irq || cpu_has_fpu); - seq_printf(m, "fdiv_bug\t: %s\n" - "hlt_bug\t\t: %s\n" - "f00f_bug\t: %s\n" - "coma_bug\t: %s\n" - "fpu\t\t: %s\n" - "fpu_exception\t: %s\n" - "cpuid level\t: %d\n" - "wp\t\t: %s\n" - "flags\t\t:", - c->fdiv_bug ? "yes" : "no", - c->hlt_works_ok ? "no" : "yes", - c->f00f_bug ? "yes" : "no", - c->coma_bug ? "yes" : "no", - c->hard_math ? "yes" : "no", - fpu_exception ? "yes" : "no", - c->cpuid_level, - c->wp_works_ok ? "yes" : "no"); - - for ( i = 0 ; i < 32*NCAPINTS ; i++ ) - if ( test_bit(i, c->x86_capability) && - x86_cap_flags[i] != NULL ) + + show_cpuinfo_core(m, c, cpu); + show_cpuinfo_misc(m, c); + + seq_printf(m, "flags\t\t:"); + for (i = 0; i < 32*NCAPINTS; i++) + if (cpu_has(c, i) && x86_cap_flags[i] != NULL) seq_printf(m, " %s", x86_cap_flags[i]); - for (i = 0; i < 32; i++) + seq_printf(m, "\nbogomips\t: %lu.%02lu\n", + c->loops_per_jiffy/(500000/HZ), + (c->loops_per_jiffy/(5000/HZ)) % 100); + +#ifdef CONFIG_X86_64 + if (c->x86_tlbsize > 0) + seq_printf(m, "TLB size\t: %d 4K pages\n", c->x86_tlbsize); +#endif + seq_printf(m, "clflush size\t: %u\n", c->x86_clflush_size); +#ifdef CONFIG_X86_64 + seq_printf(m, "cache_alignment\t: %d\n", c->x86_cache_alignment); + seq_printf(m, "address sizes\t: %u bits physical, %u bits virtual\n", + c->x86_phys_bits, c->x86_virt_bits); +#endif + + seq_printf(m, "power management:"); + for (i = 0; i < 32; i++) { if (c->x86_power & (1 << i)) { if (i < ARRAY_SIZE(x86_power_flags) && x86_power_flags[i]) @@ -89,11 +149,9 @@ static int show_cpuinfo(struct seq_file *m, void *v) else seq_printf(m, " [%d]", i); } + } - seq_printf(m, "\nbogomips\t: %lu.%02lu\n", - c->loops_per_jiffy/(500000/HZ), - (c->loops_per_jiffy/(5000/HZ)) % 100); - seq_printf(m, "clflush size\t: %u\n\n", c->x86_clflush_size); + seq_printf(m, "\n\n"); return 0; } @@ -106,14 +164,17 @@ static void *c_start(struct seq_file *m, loff_t *pos) return &cpu_data(*pos); return NULL; } + static void *c_next(struct seq_file *m, void *v, loff_t *pos) { *pos = next_cpu(*pos, cpu_online_map); return c_start(m, pos); } + static void c_stop(struct seq_file *m, void *v) { } + const struct seq_operations cpuinfo_op = { .start = c_start, .next = c_next, diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index e8b422c1c512..b911a2c61b8f 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -18,8 +18,8 @@ static void __cpuinit init_transmeta(struct cpuinfo_x86 *c) /* Print CMS and CPU revision */ max = cpuid_eax(0x80860000); cpu_rev = 0; - if ( max >= 0x80860001 ) { - cpuid(0x80860001, &dummy, &cpu_rev, &cpu_freq, &cpu_flags); + if (max >= 0x80860001) { + cpuid(0x80860001, &dummy, &cpu_rev, &cpu_freq, &cpu_flags); if (cpu_rev != 0x02000000) { printk(KERN_INFO "CPU: Processor revision %u.%u.%u.%u, %u MHz\n", (cpu_rev >> 24) & 0xff, @@ -29,7 +29,7 @@ static void __cpuinit init_transmeta(struct cpuinfo_x86 *c) cpu_freq); } } - if ( max >= 0x80860002 ) { + if (max >= 0x80860002) { cpuid(0x80860002, &new_cpu_rev, &cms_rev1, &cms_rev2, &dummy); if (cpu_rev == 0x02000000) { printk(KERN_INFO "CPU: Processor revision %08X, %u MHz\n", @@ -42,7 +42,7 @@ static void __cpuinit init_transmeta(struct cpuinfo_x86 *c) cms_rev1 & 0xff, cms_rev2); } - if ( max >= 0x80860006 ) { + if (max >= 0x80860006) { cpuid(0x80860003, (void *)&cpu_info[0], (void *)&cpu_info[4], @@ -74,23 +74,25 @@ static void __cpuinit init_transmeta(struct cpuinfo_x86 *c) wrmsr(0x80860004, cap_mask, uk); /* All Transmeta CPUs have a constant TSC */ - set_bit(X86_FEATURE_CONSTANT_TSC, c->x86_capability); - + set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); + #ifdef CONFIG_SYSCTL - /* randomize_va_space slows us down enormously; - it probably triggers retranslation of x86->native bytecode */ + /* + * randomize_va_space slows us down enormously; + * it probably triggers retranslation of x86->native bytecode + */ randomize_va_space = 0; #endif } -static void __cpuinit transmeta_identify(struct cpuinfo_x86 * c) +static void __cpuinit transmeta_identify(struct cpuinfo_x86 *c) { u32 xlvl; /* Transmeta-defined flags: level 0x80860001 */ xlvl = cpuid_eax(0x80860000); - if ( (xlvl & 0xffff0000) == 0x80860000 ) { - if ( xlvl >= 0x80860001 ) + if ((xlvl & 0xffff0000) == 0x80860000) { + if (xlvl >= 0x80860001) c->x86_capability[2] = cpuid_edx(0x80860001); } } @@ -102,8 +104,4 @@ static struct cpu_dev transmeta_cpu_dev __cpuinitdata = { .c_identify = transmeta_identify, }; -int __init transmeta_init_cpu(void) -{ - cpu_devs[X86_VENDOR_TRANSMETA] = &transmeta_cpu_dev; - return 0; -} +cpu_vendor_dev_register(X86_VENDOR_TRANSMETA, &transmeta_cpu_dev); diff --git a/arch/x86/kernel/cpu/umc.c b/arch/x86/kernel/cpu/umc.c index a7a4e75bdcd7..b1fc90989d75 100644 --- a/arch/x86/kernel/cpu/umc.c +++ b/arch/x86/kernel/cpu/umc.c @@ -3,24 +3,23 @@ #include <asm/processor.h> #include "cpu.h" -/* UMC chips appear to be only either 386 or 486, so no special init takes place. +/* + * UMC chips appear to be only either 386 or 486, + * so no special init takes place. */ static struct cpu_dev umc_cpu_dev __cpuinitdata = { .c_vendor = "UMC", - .c_ident = { "UMC UMC UMC" }, + .c_ident = { "UMC UMC UMC" }, .c_models = { { .vendor = X86_VENDOR_UMC, .family = 4, .model_names = - { - [1] = "U5D", - [2] = "U5S", + { + [1] = "U5D", + [2] = "U5S", } }, }, }; -int __init umc_init_cpu(void) -{ - cpu_devs[X86_VENDOR_UMC] = &umc_cpu_dev; - return 0; -} +cpu_vendor_dev_register(X86_VENDOR_UMC, &umc_cpu_dev); + diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index 288e7a6598ac..daff52a62248 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -154,12 +154,10 @@ static int __cpuinit cpuid_class_cpu_callback(struct notifier_block *nfb, err = cpuid_device_create(cpu); break; case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: case CPU_DEAD: cpuid_device_destroy(cpu); break; - case CPU_UP_CANCELED_FROZEN: - destroy_suspended_device(cpuid_class, MKDEV(CPUID_MAJOR, cpu)); - break; } return err ? NOTIFY_BAD : NOTIFY_OK; } diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 9a5fa0abfcc7..268553817909 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -25,12 +25,9 @@ #include <asm/hpet.h> #include <linux/kdebug.h> #include <asm/smp.h> +#include <asm/reboot.h> -#ifdef CONFIG_X86_32 #include <mach_ipi.h> -#else -#include <asm/mach_apic.h> -#endif /* This keeps a track of which one is crashing cpu. */ static int crashing_cpu; @@ -121,7 +118,7 @@ static void nmi_shootdown_cpus(void) } #endif -void machine_crash_shutdown(struct pt_regs *regs) +void native_machine_crash_shutdown(struct pt_regs *regs) { /* This function is only called after the system * has panicked or is otherwise in a critical state. diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c index dcd918c1580d..11c11b8ec48d 100644 --- a/arch/x86/kernel/ds.c +++ b/arch/x86/kernel/ds.c @@ -220,11 +220,11 @@ int ds_allocate(void **dsp, size_t bts_size_in_bytes) int ds_free(void **dsp) { - if (*dsp) + if (*dsp) { kfree((void *)get_bts_buffer_base(*dsp)); - kfree(*dsp); - *dsp = NULL; - + kfree(*dsp); + *dsp = NULL; + } return 0; } diff --git a/arch/x86/kernel/e820_32.c b/arch/x86/kernel/e820_32.c index 80444c5c9b14..ed733e7cf4e6 100644 --- a/arch/x86/kernel/e820_32.c +++ b/arch/x86/kernel/e820_32.c @@ -450,45 +450,32 @@ int __init sanitize_e820_map(struct e820entry * biosmap, char * pnr_map) * thinkpad 560x, for example, does not cooperate with the memory * detection code.) */ -int __init copy_e820_map(struct e820entry * biosmap, int nr_map) +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 { - unsigned long long start = biosmap->addr; - unsigned long long size = biosmap->size; - unsigned long long end = start + size; - unsigned long type = biosmap->type; + 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; - /* - * Some BIOSes claim RAM in the 640k - 1M region. - * Not right. Fix it up. - */ - if (type == E820_RAM) { - if (start < 0x100000ULL && end > 0xA0000ULL) { - if (start < 0xA0000ULL) - add_memory_region(start, 0xA0000ULL-start, type); - if (end <= 0x100000ULL) - continue; - start = 0x100000ULL; - size = end - start; - } - } add_memory_region(start, size, type); - } while (biosmap++,--nr_map); + } while (biosmap++, --nr_map); + return 0; } /* * Find the highest page frame number we have available */ -void __init find_max_pfn(void) +void __init propagate_e820_map(void) { int i; @@ -717,7 +704,7 @@ static int __init parse_memmap(char *arg) * size before original memory map is * reset. */ - find_max_pfn(); + propagate_e820_map(); saved_max_pfn = max_pfn; #endif e820.nr_map = 0; diff --git a/arch/x86/kernel/e820_64.c b/arch/x86/kernel/e820_64.c index 9be697126013..124480c0008d 100644 --- a/arch/x86/kernel/e820_64.c +++ b/arch/x86/kernel/e820_64.c @@ -27,6 +27,7 @@ #include <asm/setup.h> #include <asm/sections.h> #include <asm/kdebug.h> +#include <asm/trampoline.h> struct e820map e820; @@ -36,11 +37,11 @@ struct e820map e820; unsigned long end_pfn; /* - * end_pfn only includes RAM, while end_pfn_map includes all e820 entries. - * The direct mapping extends to end_pfn_map, so that we can directly access + * 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 end_pfn_map; +unsigned long max_pfn_mapped; /* * Last pfn which the user wants to use. @@ -58,8 +59,8 @@ struct early_res { }; static struct early_res early_res[MAX_EARLY_RES] __initdata = { { 0, PAGE_SIZE, "BIOS data page" }, /* BIOS data page */ -#ifdef CONFIG_SMP - { SMP_TRAMPOLINE_BASE, SMP_TRAMPOLINE_BASE + 2*PAGE_SIZE, "SMP_TRAMPOLINE" }, +#ifdef CONFIG_X86_TRAMPOLINE + { TRAMPOLINE_BASE, TRAMPOLINE_BASE + 2 * PAGE_SIZE, "TRAMPOLINE" }, #endif {} }; @@ -83,19 +84,47 @@ void __init reserve_early(unsigned long start, unsigned long end, char *name) strncpy(r->name, name, sizeof(r->name) - 1); } -void __init early_res_to_bootmem(void) +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]; - printk(KERN_INFO "early res: %d [%lx-%lx] %s\n", i, - r->start, r->end - 1, r->name); - reserve_bootmem_generic(r->start, r->end - r->start); + 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 bad_addr(unsigned long *addrp, unsigned long size) +static inline int __init +bad_addr(unsigned long *addrp, unsigned long size, unsigned long align) { int i; unsigned long addr = *addrp, last; @@ -105,7 +134,7 @@ again: 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 = r->end; + *addrp = addr = round_up(r->end, align); changed = 1; goto again; } @@ -113,6 +142,40 @@ 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. @@ -174,26 +237,27 @@ int __init e820_all_mapped(unsigned long start, unsigned long end, * Find a free area with specified alignment in a specific range. */ unsigned long __init find_e820_area(unsigned long start, unsigned long end, - unsigned size, unsigned long align) + unsigned long size, unsigned long align) { int i; - unsigned long mask = ~(align - 1); for (i = 0; i < e820.nr_map; i++) { struct e820entry *ei = &e820.map[i]; - unsigned long addr = ei->addr, last; + 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 = start; - if (addr > ei->addr + ei->size) + addr = round_up(start, align); + if (addr >= ei_last) continue; - while (bad_addr(&addr, size) && addr+size <= ei->addr+ei->size) + while (bad_addr(&addr, size, align) && addr+size <= ei_last) ; - addr = (addr + align - 1) & mask; last = addr + size; - if (last > ei->addr + ei->size) + if (last > ei_last) continue; if (last > end) continue; @@ -203,6 +267,40 @@ unsigned long __init find_e820_area(unsigned long start, unsigned long end, } /* + * 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) @@ -211,29 +309,29 @@ unsigned long __init e820_end_of_ram(void) end_pfn = find_max_pfn_with_active_regions(); - if (end_pfn > end_pfn_map) - end_pfn_map = end_pfn; - if (end_pfn_map > MAXMEM>>PAGE_SHIFT) - end_pfn_map = MAXMEM>>PAGE_SHIFT; + 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 > end_pfn_map) - end_pfn = end_pfn_map; + if (end_pfn > max_pfn_mapped) + end_pfn = max_pfn_mapped; - printk(KERN_INFO "end_pfn_map = %lu\n", end_pfn_map); + 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(struct resource *code_resource, - struct resource *data_resource, struct resource *bss_resource) +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++) { - struct resource *res; - res = alloc_bootmem_low(sizeof(struct resource)); switch (e820.map[i].type) { case E820_RAM: res->name = "System RAM"; break; case E820_ACPI: res->name = "ACPI Tables"; break; @@ -243,21 +341,8 @@ void __init e820_reserve_resources(struct resource *code_resource, res->start = e820.map[i].addr; res->end = res->start + e820.map[i].size - 1; res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; - request_resource(&iomem_resource, res); - if (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 - } + insert_resource(&iomem_resource, res); + res++; } } @@ -309,9 +394,9 @@ static int __init e820_find_active_region(const struct e820entry *ei, if (*ei_startpfn >= *ei_endpfn) return 0; - /* Check if end_pfn_map should be updated */ - if (ei->type != E820_RAM && *ei_endpfn > end_pfn_map) - end_pfn_map = *ei_endpfn; + /* 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 || @@ -634,10 +719,10 @@ static int __init copy_e820_map(struct e820entry *biosmap, int nr_map) return -1; do { - unsigned long start = biosmap->addr; - unsigned long size = biosmap->size; - unsigned long end = start + size; - unsigned long type = biosmap->type; + 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) @@ -702,7 +787,7 @@ static int __init parse_memmap_opt(char *p) saved_max_pfn = e820_end_of_ram(); remove_all_active_ranges(); #endif - end_pfn_map = 0; + max_pfn_mapped = 0; e820.nr_map = 0; userdef = 1; return 0; diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index cff84cd9987f..643fd861b724 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -13,7 +13,7 @@ #define VGABASE (__ISA_IO_base + 0xb8000) static int max_ypos = 25, max_xpos = 80; -static int current_ypos = 25, current_xpos = 0; +static int current_ypos = 25, current_xpos; static void early_vga_write(struct console *con, const char *str, unsigned n) { @@ -108,12 +108,12 @@ static __init void early_serial_init(char *s) if (*s) { unsigned port; - if (!strncmp(s,"0x",2)) { + if (!strncmp(s, "0x", 2)) { early_serial_base = simple_strtoul(s, &e, 16); } else { static int bases[] = { 0x3f8, 0x2f8 }; - if (!strncmp(s,"ttyS",4)) + if (!strncmp(s, "ttyS", 4)) s += 4; port = simple_strtoul(s, &e, 10); if (port > 1 || s == e) @@ -194,7 +194,7 @@ static struct console simnow_console = { /* Direct interface for emergencies */ static struct console *early_console = &early_vga_console; -static int early_console_initialized = 0; +static int early_console_initialized; void early_printk(const char *fmt, ...) { @@ -202,9 +202,9 @@ void early_printk(const char *fmt, ...) int n; va_list ap; - va_start(ap,fmt); - n = vscnprintf(buf,512,fmt,ap); - early_console->write(early_console,buf,n); + va_start(ap, fmt); + n = vscnprintf(buf, 512, fmt, ap); + early_console->write(early_console, buf, n); va_end(ap); } @@ -229,15 +229,15 @@ static int __init setup_early_printk(char *buf) early_serial_init(buf); early_console = &early_serial_console; } else if (!strncmp(buf, "vga", 3) - && boot_params.screen_info.orig_video_isVGA == 1) { + && boot_params.screen_info.orig_video_isVGA == 1) { max_xpos = boot_params.screen_info.orig_video_cols; max_ypos = boot_params.screen_info.orig_video_lines; current_ypos = boot_params.screen_info.orig_y; early_console = &early_vga_console; - } else if (!strncmp(buf, "simnow", 6)) { - simnow_init(buf + 6); - early_console = &simnow_console; - keep_early = 1; + } else if (!strncmp(buf, "simnow", 6)) { + simnow_init(buf + 6); + early_console = &simnow_console; + keep_early = 1; #ifdef CONFIG_HVC_XEN } else if (!strncmp(buf, "xen", 3)) { early_console = &xenboot_console; diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c index 759e02bec070..77d424cf68b3 100644 --- a/arch/x86/kernel/efi.c +++ b/arch/x86/kernel/efi.c @@ -383,6 +383,7 @@ static void __init runtime_code_page_mkexec(void) { efi_memory_desc_t *md; void *p; + u64 addr, npages; /* Make EFI runtime service code area executable */ for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { @@ -391,7 +392,10 @@ static void __init runtime_code_page_mkexec(void) if (md->type != EFI_RUNTIME_SERVICES_CODE) continue; - set_memory_x(md->virt_addr, md->num_pages); + addr = md->virt_addr; + npages = md->num_pages; + memrange_efi_to_native(&addr, &npages); + set_memory_x(addr, npages); } } @@ -408,7 +412,7 @@ void __init efi_enter_virtual_mode(void) efi_memory_desc_t *md; efi_status_t status; unsigned long size; - u64 end, systab; + u64 end, systab, addr, npages; void *p, *va; efi.systab = NULL; @@ -420,7 +424,7 @@ void __init efi_enter_virtual_mode(void) size = md->num_pages << EFI_PAGE_SHIFT; end = md->phys_addr + size; - if ((end >> PAGE_SHIFT) <= max_pfn_mapped) + if (PFN_UP(end) <= max_pfn_mapped) va = __va(md->phys_addr); else va = efi_ioremap(md->phys_addr, size); @@ -433,8 +437,12 @@ void __init efi_enter_virtual_mode(void) continue; } - if (!(md->attribute & EFI_MEMORY_WB)) - set_memory_uc(md->virt_addr, md->num_pages); + if (!(md->attribute & EFI_MEMORY_WB)) { + addr = md->virt_addr; + npages = md->num_pages; + memrange_efi_to_native(&addr, &npages); + set_memory_uc(addr, npages); + } systab = (u64) (unsigned long) efi_phys.systab; if (md->phys_addr <= systab && systab < end) { diff --git a/arch/x86/kernel/efi_64.c b/arch/x86/kernel/efi_64.c index d143a1e76b30..d0060fdcccac 100644 --- a/arch/x86/kernel/efi_64.c +++ b/arch/x86/kernel/efi_64.c @@ -105,14 +105,14 @@ void __init efi_reserve_bootmem(void) void __iomem * __init efi_ioremap(unsigned long phys_addr, unsigned long size) { - static unsigned pages_mapped; + static unsigned pages_mapped __initdata; unsigned i, pages; + unsigned long offset; - /* phys_addr and size must be page aligned */ - if ((phys_addr & ~PAGE_MASK) || (size & ~PAGE_MASK)) - return NULL; + pages = PFN_UP(phys_addr + size) - PFN_DOWN(phys_addr); + offset = phys_addr & ~PAGE_MASK; + phys_addr &= PAGE_MASK; - pages = size >> PAGE_SHIFT; if (pages_mapped + pages > MAX_EFI_IO_PAGES) return NULL; @@ -124,5 +124,5 @@ void __iomem * __init efi_ioremap(unsigned long phys_addr, unsigned long size) } return (void __iomem *)__fix_to_virt(FIX_EFI_IO_MAP_FIRST_PAGE - \ - (pages_mapped - pages)); + (pages_mapped - pages)) + offset; } diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 4b87c32b639f..2a609dc3271c 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -1,5 +1,4 @@ /* - * linux/arch/i386/entry.S * * Copyright (C) 1991, 1992 Linus Torvalds */ @@ -51,6 +50,7 @@ #include <asm/desc.h> #include <asm/percpu.h> #include <asm/dwarf2.h> +#include <asm/processor-flags.h> #include "irq_vectors.h" /* @@ -68,13 +68,6 @@ #define nr_syscalls ((syscall_table_size)/4) -CF_MASK = 0x00000001 -TF_MASK = 0x00000100 -IF_MASK = 0x00000200 -DF_MASK = 0x00000400 -NT_MASK = 0x00004000 -VM_MASK = 0x00020000 - #ifdef CONFIG_PREEMPT #define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF #else @@ -84,7 +77,7 @@ VM_MASK = 0x00020000 .macro TRACE_IRQS_IRET #ifdef CONFIG_TRACE_IRQFLAGS - testl $IF_MASK,PT_EFLAGS(%esp) # interrupts off? + testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off? jz 1f TRACE_IRQS_ON 1: @@ -246,7 +239,7 @@ ret_from_intr: check_userspace: movl PT_EFLAGS(%esp), %eax # mix EFLAGS and CS movb PT_CS(%esp), %al - andl $(VM_MASK | SEGMENT_RPL_MASK), %eax + andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax cmpl $USER_RPL, %eax jb resume_kernel # not returning to v8086 or userspace @@ -271,7 +264,7 @@ need_resched: movl TI_flags(%ebp), %ecx # need_resched set ? testb $_TIF_NEED_RESCHED, %cl jz restore_all - testl $IF_MASK,PT_EFLAGS(%esp) # interrupts off (exception path) ? + testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off (exception path) ? jz restore_all call preempt_schedule_irq jmp need_resched @@ -291,10 +284,10 @@ ENTRY(ia32_sysenter_target) movl TSS_sysenter_sp0(%esp),%esp sysenter_past_esp: /* - * No need to follow this irqs on/off section: the syscall - * disabled irqs and here we enable it straight after entry: + * Interrupts are disabled here, but we can't trace it until + * enough kernel state to call TRACE_IRQS_OFF can be called - but + * we immediately enable interrupts at that point anyway. */ - ENABLE_INTERRUPTS(CLBR_NONE) pushl $(__USER_DS) CFI_ADJUST_CFA_OFFSET 4 /*CFI_REL_OFFSET ss, 0*/ @@ -302,6 +295,7 @@ sysenter_past_esp: CFI_ADJUST_CFA_OFFSET 4 CFI_REL_OFFSET esp, 0 pushfl + orl $X86_EFLAGS_IF, (%esp) CFI_ADJUST_CFA_OFFSET 4 pushl $(__USER_CS) CFI_ADJUST_CFA_OFFSET 4 @@ -315,6 +309,11 @@ sysenter_past_esp: CFI_ADJUST_CFA_OFFSET 4 CFI_REL_OFFSET eip, 0 + pushl %eax + CFI_ADJUST_CFA_OFFSET 4 + SAVE_ALL + ENABLE_INTERRUPTS(CLBR_NONE) + /* * Load the potential sixth argument from user stack. * Careful about security. @@ -322,14 +321,12 @@ sysenter_past_esp: cmpl $__PAGE_OFFSET-3,%ebp jae syscall_fault 1: movl (%ebp),%ebp + movl %ebp,PT_EBP(%esp) .section __ex_table,"a" .align 4 .long 1b,syscall_fault .previous - pushl %eax - CFI_ADJUST_CFA_OFFSET 4 - SAVE_ALL GET_THREAD_INFO(%ebp) /* Note, _TIF_SECCOMP is bit number 8, and so it needs testw and not testb */ @@ -384,7 +381,7 @@ syscall_exit: # setting need_resched or sigpending # between sampling and the iret TRACE_IRQS_OFF - testl $TF_MASK,PT_EFLAGS(%esp) # If tracing set singlestep flag on exit + testl $X86_EFLAGS_TF,PT_EFLAGS(%esp) # If tracing set singlestep flag on exit jz no_singlestep orl $_TIF_SINGLESTEP,TI_flags(%ebp) no_singlestep: @@ -399,7 +396,7 @@ restore_all: # See comments in process.c:copy_thread() for details. movb PT_OLDSS(%esp), %ah movb PT_CS(%esp), %al - andl $(VM_MASK | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax + andl $(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax CFI_REMEMBER_STATE je ldt_ss # returning to user-space with LDT SS @@ -412,7 +409,7 @@ restore_nocheck_notrace: irq_return: INTERRUPT_RETURN .section .fixup,"ax" -iret_exc: +ENTRY(iret_exc) pushl $0 # no error code pushl $do_iret_error jmp error_code @@ -486,7 +483,7 @@ work_resched: work_notifysig: # deal with pending signals and # notify-resume requests #ifdef CONFIG_VM86 - testl $VM_MASK, PT_EFLAGS(%esp) + testl $X86_EFLAGS_VM, PT_EFLAGS(%esp) movl %esp, %eax jne work_notifysig_v86 # returning to kernel-space or # vm86-space @@ -543,9 +540,6 @@ END(syscall_exit_work) RING0_INT_FRAME # can't unwind into user space anyway syscall_fault: - pushl %eax # save orig_eax - CFI_ADJUST_CFA_OFFSET 4 - SAVE_ALL GET_THREAD_INFO(%ebp) movl $-EFAULT,PT_EAX(%esp) jmp resume_userspace @@ -1023,6 +1017,13 @@ ENTRY(kernel_thread_helper) ENDPROC(kernel_thread_helper) #ifdef CONFIG_XEN +/* Xen doesn't set %esp to be precisely what the normal sysenter + entrypoint expects, so fix it up before using the normal path. */ +ENTRY(xen_sysenter_target) + RING0_INT_FRAME + addl $5*4, %esp /* remove xen-provided frame */ + jmp sysenter_past_esp + ENTRY(xen_hypervisor_callback) CFI_STARTPROC pushl $0 @@ -1041,8 +1042,9 @@ ENTRY(xen_hypervisor_callback) cmpl $xen_iret_end_crit,%eax jae 1f - call xen_iret_crit_fixup + jmp xen_iret_crit_fixup +ENTRY(xen_do_upcall) 1: mov %esp, %eax call xen_evtchn_do_upcall jmp ret_from_intr diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index c20c9e7e08dd..556a8df522a7 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -319,19 +319,17 @@ badsys: /* Do syscall tracing */ tracesys: SAVE_REST - movq $-ENOSYS,RAX(%rsp) + movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */ FIXUP_TOP_OF_STACK %rdi movq %rsp,%rdi call syscall_trace_enter LOAD_ARGS ARGOFFSET /* reload args from stack in case ptrace changed it */ RESTORE_REST cmpq $__NR_syscall_max,%rax - movq $-ENOSYS,%rcx - cmova %rcx,%rax - ja 1f + ja int_ret_from_sys_call /* RAX(%rsp) set to -ENOSYS above */ movq %r10,%rcx /* fixup for C */ call *sys_call_table(,%rax,8) -1: movq %rax,RAX-ARGOFFSET(%rsp) + movq %rax,RAX-ARGOFFSET(%rsp) /* Use IRET because user could have changed frame */ /* diff --git a/arch/x86/kernel/genapic_64.c b/arch/x86/kernel/genapic_64.c index 4ae7b6440260..cbaaf69bedb2 100644 --- a/arch/x86/kernel/genapic_64.c +++ b/arch/x86/kernel/genapic_64.c @@ -15,6 +15,7 @@ #include <linux/kernel.h> #include <linux/ctype.h> #include <linux/init.h> +#include <linux/hardirq.h> #include <asm/smp.h> #include <asm/ipi.h> @@ -24,20 +25,20 @@ #include <acpi/acpi_bus.h> #endif -/* 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; -DEFINE_PER_CPU(u16, x86_cpu_to_apicid) = BAD_APICID; -EXPORT_PER_CPU_SYMBOL(x86_cpu_to_apicid); +DEFINE_PER_CPU(int, x2apic_extra_bits); struct genapic __read_mostly *genapic = &apic_flat; +static enum uv_system_type uv_system_type; + /* * Check the APIC IDs in bios_cpu_apicid and choose the APIC mode. */ void __init setup_apic_routing(void) { + if (uv_system_type == UV_NON_UNIQUE_APIC) + genapic = &apic_x2apic_uv_x; + else #ifdef CONFIG_ACPI /* * Quirk: some x86_64 machines can only use physical APIC mode @@ -50,7 +51,7 @@ void __init setup_apic_routing(void) else #endif - if (cpus_weight(cpu_possible_map) <= 8) + if (num_possible_cpus() <= 8) genapic = &apic_flat; else genapic = &apic_physflat; @@ -64,3 +65,37 @@ void send_IPI_self(int vector) { __send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL); } + +int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id) +{ + if (!strcmp(oem_id, "SGI")) { + if (!strcmp(oem_table_id, "UVL")) + uv_system_type = UV_LEGACY_APIC; + else if (!strcmp(oem_table_id, "UVX")) + uv_system_type = UV_X2APIC; + else if (!strcmp(oem_table_id, "UVH")) + uv_system_type = UV_NON_UNIQUE_APIC; + } + return 0; +} + +unsigned int read_apic_id(void) +{ + unsigned int id; + + WARN_ON(preemptible() && num_online_cpus() > 1); + id = apic_read(APIC_ID); + if (uv_system_type >= UV_X2APIC) + id |= __get_cpu_var(x2apic_extra_bits); + return id; +} + +enum uv_system_type get_uv_system_type(void) +{ + return uv_system_type; +} + +int is_uv_system(void) +{ + return uv_system_type != UV_NONE; +} diff --git a/arch/x86/kernel/genapic_flat_64.c b/arch/x86/kernel/genapic_flat_64.c index 07352b74bda6..1a9c68845ee8 100644 --- a/arch/x86/kernel/genapic_flat_64.c +++ b/arch/x86/kernel/genapic_flat_64.c @@ -97,7 +97,7 @@ static void flat_send_IPI_all(int vector) static int flat_apic_id_registered(void) { - return physid_isset(GET_APIC_ID(apic_read(APIC_ID)), phys_cpu_present_map); + return physid_isset(GET_APIC_ID(read_apic_id()), phys_cpu_present_map); } static unsigned int flat_cpu_mask_to_apicid(cpumask_t cpumask) @@ -138,12 +138,9 @@ static cpumask_t physflat_target_cpus(void) static cpumask_t physflat_vector_allocation_domain(int cpu) { - cpumask_t domain = CPU_MASK_NONE; - cpu_set(cpu, domain); - return domain; + return cpumask_of_cpu(cpu); } - static void physflat_send_IPI_mask(cpumask_t cpumask, int vector) { send_IPI_mask_sequence(cpumask, vector); diff --git a/arch/x86/kernel/genx2apic_uv_x.c b/arch/x86/kernel/genx2apic_uv_x.c new file mode 100644 index 000000000000..ebf13908a743 --- /dev/null +++ b/arch/x86/kernel/genx2apic_uv_x.c @@ -0,0 +1,250 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * SGI UV APIC functions (note: not an Intel compatible APIC) + * + * Copyright (C) 2007 Silicon Graphics, Inc. All rights reserved. + */ + +#include <linux/threads.h> +#include <linux/cpumask.h> +#include <linux/string.h> +#include <linux/kernel.h> +#include <linux/ctype.h> +#include <linux/init.h> +#include <linux/sched.h> +#include <linux/bootmem.h> +#include <linux/module.h> +#include <asm/smp.h> +#include <asm/ipi.h> +#include <asm/genapic.h> +#include <asm/uv/uv_mmrs.h> +#include <asm/uv/uv_hub.h> + +DEFINE_PER_CPU(struct uv_hub_info_s, __uv_hub_info); +EXPORT_PER_CPU_SYMBOL_GPL(__uv_hub_info); + +struct uv_blade_info *uv_blade_info; +EXPORT_SYMBOL_GPL(uv_blade_info); + +short *uv_node_to_blade; +EXPORT_SYMBOL_GPL(uv_node_to_blade); + +short *uv_cpu_to_blade; +EXPORT_SYMBOL_GPL(uv_cpu_to_blade); + +short uv_possible_blades; +EXPORT_SYMBOL_GPL(uv_possible_blades); + +/* Start with all IRQs pointing to boot CPU. IRQ balancing will shift them. */ + +static cpumask_t uv_target_cpus(void) +{ + return cpumask_of_cpu(0); +} + +static cpumask_t uv_vector_allocation_domain(int cpu) +{ + cpumask_t domain = CPU_MASK_NONE; + cpu_set(cpu, domain); + return domain; +} + +int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip) +{ + unsigned long val; + int nasid; + + nasid = uv_apicid_to_nasid(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); + 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); + return 0; +} + +static void uv_send_IPI_one(int cpu, int vector) +{ + unsigned long val, apicid, lapicid; + int nasid; + + apicid = per_cpu(x86_cpu_to_apicid, cpu); /* ZZZ - cache node-local ? */ + lapicid = apicid & 0x3f; /* ZZZ macro needed */ + nasid = uv_apicid_to_nasid(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); +} + +static void uv_send_IPI_mask(cpumask_t mask, int vector) +{ + unsigned int cpu; + + for (cpu = 0; cpu < NR_CPUS; ++cpu) + if (cpu_isset(cpu, mask)) + uv_send_IPI_one(cpu, vector); +} + +static void uv_send_IPI_allbutself(int vector) +{ + cpumask_t mask = cpu_online_map; + + cpu_clear(smp_processor_id(), mask); + + if (!cpus_empty(mask)) + uv_send_IPI_mask(mask, vector); +} + +static void uv_send_IPI_all(int vector) +{ + uv_send_IPI_mask(cpu_online_map, vector); +} + +static int uv_apic_id_registered(void) +{ + return 1; +} + +static unsigned int uv_cpu_mask_to_apicid(cpumask_t cpumask) +{ + int cpu; + + /* + * We're using fixed IRQ delivery, can only return one phys APIC ID. + * May as well be the first. + */ + cpu = first_cpu(cpumask); + if ((unsigned)cpu < NR_CPUS) + return per_cpu(x86_cpu_to_apicid, cpu); + else + return BAD_APICID; +} + +static unsigned int phys_pkg_id(int index_msb) +{ + return GET_APIC_ID(read_apic_id()) >> index_msb; +} + +#ifdef ZZZ /* Needs x2apic patch */ +static void uv_send_IPI_self(int vector) +{ + apic_write(APIC_SELF_IPI, vector); +} +#endif + +struct genapic apic_x2apic_uv_x = { + .name = "UV large system", + .int_delivery_mode = dest_Fixed, + .int_dest_mode = (APIC_DEST_PHYSICAL != 0), + .target_cpus = uv_target_cpus, + .vector_allocation_domain = uv_vector_allocation_domain,/* Fixme ZZZ */ + .apic_id_registered = uv_apic_id_registered, + .send_IPI_all = uv_send_IPI_all, + .send_IPI_allbutself = uv_send_IPI_allbutself, + .send_IPI_mask = uv_send_IPI_mask, + /* ZZZ.send_IPI_self = uv_send_IPI_self, */ + .cpu_mask_to_apicid = uv_cpu_mask_to_apicid, + .phys_pkg_id = phys_pkg_id, /* Fixme ZZZ */ +}; + +static __cpuinit void set_x2apic_extra_bits(int nasid) +{ + __get_cpu_var(x2apic_extra_bits) = ((nasid >> 1) << 6); +} + +/* + * Called on boot cpu. + */ +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; + + m_n_config.v = uv_read_local_mmr(UVH_SI_ADDR_MAP_CONFIG); + 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; + } + 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); + + 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); + + bytes = sizeof(uv_cpu_to_blade[0]) * num_possible_cpus(); + 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; + uv_blade_info[blade].nr_online_cpus = 0; + } + 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; + 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)->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; + + 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); + } +} + +/* + * Called on each cpu to initialize the per_cpu UV data area. + */ +void __cpuinit uv_cpu_init(void) +{ + if (!uv_node_to_blade) + uv_system_init(); + + 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); +} diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c new file mode 100644 index 000000000000..3db059058927 --- /dev/null +++ b/arch/x86/kernel/head32.c @@ -0,0 +1,14 @@ +/* + * linux/arch/i386/kernel/head32.c -- prepare to run common code + * + * Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE + * Copyright (C) 2007 Eric Biederman <ebiederm@xmission.com> + */ + +#include <linux/init.h> +#include <linux/start_kernel.h> + +void __init i386_start_kernel(void) +{ + start_kernel(); +} diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index ad2440832de0..e25c57b8aa84 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -11,6 +11,7 @@ #include <linux/string.h> #include <linux/percpu.h> #include <linux/start_kernel.h> +#include <linux/io.h> #include <asm/processor.h> #include <asm/proto.h> @@ -22,6 +23,7 @@ #include <asm/sections.h> #include <asm/kdebug.h> #include <asm/e820.h> +#include <asm/bios_ebda.h> static void __init zap_identity_mappings(void) { @@ -49,39 +51,91 @@ static void __init copy_bootdata(char *real_mode_data) } } -#define EBDA_ADDR_POINTER 0x40E +#define BIOS_LOWMEM_KILOBYTES 0x413 -static __init void reserve_ebda(void) +/* + * 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 ebda_addr, ebda_size; + 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; - /* - * there is a real-mode segmented pointer pointing to the - * 4K EBDA area at 0x40E - */ - ebda_addr = *(unsigned short *)__va(EBDA_ADDR_POINTER); - ebda_addr <<= 4; + /* end of low (conventional) memory */ + lowmem = *(unsigned short *)__va(BIOS_LOWMEM_KILOBYTES); + lowmem <<= 10; - if (!ebda_addr) - return; + /* 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; - ebda_size = *(unsigned short *)__va(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; - /* Round EBDA up to pages */ - if (ebda_size == 0) - ebda_size = 1; - ebda_size <<= 10; - ebda_size = round_up(ebda_size + (ebda_addr & ~PAGE_MASK), PAGE_SIZE); - if (ebda_size > 64*1024) - ebda_size = 64*1024; + /* Paranoia: should never happen, but... */ + if ((lowmem == 0) || (lowmem >= 0x100000)) + lowmem = 0x9f000; - reserve_early(ebda_addr, ebda_addr + ebda_size, "EBDA"); + /* 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; + /* + * Build-time sanity checks on the kernel image and module + * area mappings. (these are purely build-time and produce no code) + */ + BUILD_BUG_ON(MODULES_VADDR < KERNEL_IMAGE_START); + BUILD_BUG_ON(MODULES_VADDR-KERNEL_IMAGE_START < KERNEL_IMAGE_SIZE); + BUILD_BUG_ON(MODULES_LEN + KERNEL_IMAGE_SIZE > 2*PUD_SIZE); + BUILD_BUG_ON((KERNEL_IMAGE_START & ~PMD_MASK) != 0); + BUILD_BUG_ON((MODULES_VADDR & ~PMD_MASK) != 0); + BUILD_BUG_ON(!(MODULES_VADDR > __START_KERNEL)); + BUILD_BUG_ON(!(((MODULES_END - 1) & PGDIR_MASK) == + (__START_KERNEL & PGDIR_MASK))); + /* clear bss before set_intr_gate with early_idt_handler */ clear_bss(); @@ -91,7 +145,7 @@ void __init x86_64_start_kernel(char * real_mode_data) /* Cleanup the over mapped high alias */ cleanup_highmap(); - for (i = 0; i < IDT_ENTRIES; i++) { + for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) { #ifdef CONFIG_EARLY_PRINTK set_intr_gate(i, &early_idt_handlers[i]); #else @@ -110,6 +164,7 @@ void __init x86_64_start_kernel(char * real_mode_data) 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) { unsigned long ramdisk_image = boot_params.hdr.ramdisk_image; @@ -117,8 +172,10 @@ void __init x86_64_start_kernel(char * real_mode_data) unsigned long ramdisk_end = ramdisk_image + ramdisk_size; reserve_early(ramdisk_image, ramdisk_end, "RAMDISK"); } +#endif - reserve_ebda(); + 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 74d87ea85b5c..b2cc73768a9d 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -1,5 +1,4 @@ /* - * linux/arch/i386/kernel/head.S -- the 32-bit startup code. * * Copyright (C) 1991, 1992 Linus Torvalds * @@ -450,7 +449,7 @@ is386: movl $2,%ecx # set MP jmp initialize_secondary # all other CPUs call initialize_secondary 1: #endif /* CONFIG_SMP */ - jmp start_kernel + jmp i386_start_kernel /* * We depend on ET to be correct. This checks for 287/387. @@ -657,15 +656,16 @@ int_msg: .asciz "Unknown interrupt or fault at EIP %p %p %p\n" fault_msg: - .asciz \ -/* fault info: */ "BUG: Int %d: CR2 %p\n" \ -/* pusha regs: */ " EDI %p ESI %p EBP %p ESP %p\n" \ - " EBX %p EDX %p ECX %p EAX %p\n" \ -/* fault frame: */ " err %p EIP %p CS %p flg %p\n" \ - \ - "Stack: %p %p %p %p %p %p %p %p\n" \ - " %p %p %p %p %p %p %p %p\n" \ - " %p %p %p %p %p %p %p %p\n" +/* fault info: */ + .ascii "BUG: Int %d: CR2 %p\n" +/* pusha regs: */ + .ascii " EDI %p ESI %p EBP %p ESP %p\n" + .ascii " EBX %p EDX %p ECX %p EAX %p\n" +/* fault frame: */ + .ascii " err %p EIP %p CS %p flg %p\n" + .ascii "Stack: %p %p %p %p %p %p %p %p\n" + .ascii " %p %p %p %p %p %p %p %p\n" + .asciz " %p %p %p %p %p %p %p %p\n" #include "../../x86/xen/xen-head.S" diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index a007454133a3..10a1955bb1d1 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -132,10 +132,6 @@ ident_complete: addq %rbp, trampoline_level4_pgt + 0(%rip) addq %rbp, trampoline_level4_pgt + (511*8)(%rip) #endif -#ifdef CONFIG_ACPI_SLEEP - addq %rbp, wakeup_level4_pgt + 0(%rip) - addq %rbp, wakeup_level4_pgt + (511*8)(%rip) -#endif /* Due to ENTRY(), sometimes the empty space gets filled with * zeros. Better take a jmp than relying on empty space being @@ -267,21 +263,16 @@ ENTRY(secondary_startup_64) bad_address: jmp bad_address + .section ".init.text","ax" #ifdef CONFIG_EARLY_PRINTK -.macro early_idt_tramp first, last - .ifgt \last-\first - early_idt_tramp \first, \last-1 - .endif - movl $\last,%esi - jmp early_idt_handler -.endm - .globl early_idt_handlers early_idt_handlers: - early_idt_tramp 0, 63 - early_idt_tramp 64, 127 - early_idt_tramp 128, 191 - early_idt_tramp 192, 255 + i = 0 + .rept NUM_EXCEPTION_VECTORS + movl $i, %esi + jmp early_idt_handler + i = i + 1 + .endr #endif ENTRY(early_idt_handler) @@ -327,6 +318,7 @@ early_idt_msg: early_idt_ripmsg: .asciz "RIP %s\n" #endif /* CONFIG_EARLY_PRINTK */ + .previous .balign PAGE_SIZE @@ -383,12 +375,12 @@ NEXT_PAGE(level2_ident_pgt) NEXT_PAGE(level2_kernel_pgt) /* - * 128 MB kernel mapping. We spend a full page on this pagetable + * 512 MB kernel mapping. We spend a full page on this pagetable * anyway. * * The kernel code+data+bss must not be bigger than that. * - * (NOTE: at +128MB starts the module area, see MODULES_VADDR. + * (NOTE: at +512MB starts the module area, see MODULES_VADDR. * If you want to increase this then increase MODULES_VADDR * too.) */ diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 36652ea1a265..9b5cfcdfc426 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -137,9 +137,10 @@ static void hpet_reserve_platform_timers(unsigned long id) hd.hd_irq[0] = HPET_LEGACY_8254; hd.hd_irq[1] = HPET_LEGACY_RTC; - for (i = 2; i < nrtimers; timer++, i++) - hd.hd_irq[i] = (timer->hpet_config & Tn_INT_ROUTE_CNF_MASK) >> + for (i = 2; i < nrtimers; timer++, i++) { + hd.hd_irq[i] = (readl(&timer->hpet_config) & Tn_INT_ROUTE_CNF_MASK) >> Tn_INT_ROUTE_CNF_SHIFT; + } hpet_alloc(&hd); @@ -218,7 +219,7 @@ static void hpet_legacy_clockevent_register(void) hpet_freq = 1000000000000000ULL; do_div(hpet_freq, hpet_period); hpet_clockevent.mult = div_sc((unsigned long) hpet_freq, - NSEC_PER_SEC, 32); + NSEC_PER_SEC, hpet_clockevent.shift); /* Calculate the min / max delta */ hpet_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF, &hpet_clockevent); diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c index 061627806a2d..deb43785e923 100644 --- a/arch/x86/kernel/i386_ksyms_32.c +++ b/arch/x86/kernel/i386_ksyms_32.c @@ -1,13 +1,8 @@ #include <linux/module.h> -#include <asm/semaphore.h> #include <asm/checksum.h> #include <asm/desc.h> #include <asm/pgtable.h> -EXPORT_SYMBOL(__down_failed); -EXPORT_SYMBOL(__down_failed_interruptible); -EXPORT_SYMBOL(__down_failed_trylock); -EXPORT_SYMBOL(__up_wakeup); /* Networking helper routines. */ EXPORT_SYMBOL(csum_partial_copy_generic); diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index d2e39e69aaf8..db6839b53195 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -5,51 +5,48 @@ * General FPU state handling cleanups * Gareth Hughes <gareth@valinux.com>, May 2000 */ - -#include <linux/sched.h> #include <linux/module.h> #include <linux/regset.h> +#include <linux/sched.h> + +#include <asm/sigcontext.h> #include <asm/processor.h> -#include <asm/i387.h> #include <asm/math_emu.h> -#include <asm/sigcontext.h> -#include <asm/user.h> -#include <asm/ptrace.h> #include <asm/uaccess.h> +#include <asm/ptrace.h> +#include <asm/i387.h> +#include <asm/user.h> #ifdef CONFIG_X86_64 - -#include <asm/sigcontext32.h> -#include <asm/user32.h> - +# include <asm/sigcontext32.h> +# include <asm/user32.h> #else - -#define save_i387_ia32 save_i387 -#define restore_i387_ia32 restore_i387 - -#define _fpstate_ia32 _fpstate -#define user_i387_ia32_struct user_i387_struct -#define user32_fxsr_struct user_fxsr_struct - +# define save_i387_ia32 save_i387 +# define restore_i387_ia32 restore_i387 +# define _fpstate_ia32 _fpstate +# define user_i387_ia32_struct user_i387_struct +# define user32_fxsr_struct user_fxsr_struct #endif #ifdef CONFIG_MATH_EMULATION -#define HAVE_HWFP (boot_cpu_data.hard_math) +# define HAVE_HWFP (boot_cpu_data.hard_math) #else -#define HAVE_HWFP 1 +# define HAVE_HWFP 1 #endif -static unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; +static unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; +unsigned int xstate_size; +static struct i387_fxsave_struct fx_scratch __cpuinitdata; -void mxcsr_feature_mask_init(void) +void __cpuinit mxcsr_feature_mask_init(void) { unsigned long mask = 0; + clts(); if (cpu_has_fxsr) { - memset(¤t->thread.i387.fxsave, 0, - sizeof(struct i387_fxsave_struct)); - asm volatile("fxsave %0" : : "m" (current->thread.i387.fxsave)); - mask = current->thread.i387.fxsave.mxcsr_mask; + memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct)); + asm volatile("fxsave %0" : : "m" (fx_scratch)); + mask = fx_scratch.mxcsr_mask; if (mask == 0) mask = 0x0000ffbf; } @@ -57,6 +54,16 @@ void mxcsr_feature_mask_init(void) stts(); } +void __init init_thread_xstate(void) +{ + if (cpu_has_fxsr) + xstate_size = sizeof(struct i387_fxsave_struct); +#ifdef CONFIG_X86_32 + else + xstate_size = sizeof(struct i387_fsave_struct); +#endif +} + #ifdef CONFIG_X86_64 /* * Called at bootup to set up the initial FPU state that is later cloned @@ -65,14 +72,11 @@ void mxcsr_feature_mask_init(void) void __cpuinit fpu_init(void) { unsigned long oldcr0 = read_cr0(); - extern void __bad_fxsave_alignment(void); - if (offsetof(struct task_struct, thread.i387.fxsave) & 15) - __bad_fxsave_alignment(); set_in_cr4(X86_CR4_OSFXSR); set_in_cr4(X86_CR4_OSXMMEXCPT); - write_cr0(oldcr0 & ~((1UL<<3)|(1UL<<2))); /* clear TS and EM */ + write_cr0(oldcr0 & ~(X86_CR0_TS|X86_CR0_EM)); /* clear TS and EM */ mxcsr_feature_mask_init(); /* clean state in init */ @@ -87,32 +91,44 @@ void __cpuinit fpu_init(void) * value at reset if we support XMM instructions and then * remeber the current task has used the FPU. */ -void init_fpu(struct task_struct *tsk) +int init_fpu(struct task_struct *tsk) { if (tsk_used_math(tsk)) { if (tsk == current) unlazy_fpu(tsk); - return; + return 0; + } + + /* + * Memory allocation at the first usage of the FPU and other state. + */ + if (!tsk->thread.xstate) { + tsk->thread.xstate = kmem_cache_alloc(task_xstate_cachep, + GFP_KERNEL); + if (!tsk->thread.xstate) + return -ENOMEM; } if (cpu_has_fxsr) { - memset(&tsk->thread.i387.fxsave, 0, - sizeof(struct i387_fxsave_struct)); - tsk->thread.i387.fxsave.cwd = 0x37f; + struct i387_fxsave_struct *fx = &tsk->thread.xstate->fxsave; + + memset(fx, 0, xstate_size); + fx->cwd = 0x37f; if (cpu_has_xmm) - tsk->thread.i387.fxsave.mxcsr = MXCSR_DEFAULT; + fx->mxcsr = MXCSR_DEFAULT; } else { - memset(&tsk->thread.i387.fsave, 0, - sizeof(struct i387_fsave_struct)); - tsk->thread.i387.fsave.cwd = 0xffff037fu; - tsk->thread.i387.fsave.swd = 0xffff0000u; - tsk->thread.i387.fsave.twd = 0xffffffffu; - tsk->thread.i387.fsave.fos = 0xffff0000u; + struct i387_fsave_struct *fp = &tsk->thread.xstate->fsave; + memset(fp, 0, xstate_size); + fp->cwd = 0xffff037fu; + fp->swd = 0xffff0000u; + fp->twd = 0xffffffffu; + fp->fos = 0xffff0000u; } /* * Only the device not available exception or ptrace can call init_fpu. */ set_stopped_child_used_math(tsk); + return 0; } int fpregs_active(struct task_struct *target, const struct user_regset *regset) @@ -129,13 +145,17 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { + int ret; + if (!cpu_has_fxsr) return -ENODEV; - init_fpu(target); + ret = init_fpu(target); + if (ret) + return ret; return user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.i387.fxsave, 0, -1); + &target->thread.xstate->fxsave, 0, -1); } int xfpregs_set(struct task_struct *target, const struct user_regset *regset, @@ -147,16 +167,19 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, if (!cpu_has_fxsr) return -ENODEV; - init_fpu(target); + ret = init_fpu(target); + if (ret) + return ret; + set_stopped_child_used_math(target); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.i387.fxsave, 0, -1); + &target->thread.xstate->fxsave, 0, -1); /* * mxcsr reserved bits must be masked to zero for security reasons. */ - target->thread.i387.fxsave.mxcsr &= mxcsr_feature_mask; + target->thread.xstate->fxsave.mxcsr &= mxcsr_feature_mask; return ret; } @@ -178,6 +201,7 @@ static inline unsigned short twd_i387_to_fxsr(unsigned short twd) tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */ tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */ tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */ + return tmp; } @@ -232,10 +256,10 @@ static inline u32 twd_fxsr_to_i387(struct i387_fxsave_struct *fxsave) * FXSR floating point environment conversions. */ -static void convert_from_fxsr(struct user_i387_ia32_struct *env, - struct task_struct *tsk) +static void +convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk) { - struct i387_fxsave_struct *fxsave = &tsk->thread.i387.fxsave; + struct i387_fxsave_struct *fxsave = &tsk->thread.xstate->fxsave; struct _fpreg *to = (struct _fpreg *) &env->st_space[0]; struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0]; int i; @@ -252,10 +276,11 @@ static void convert_from_fxsr(struct user_i387_ia32_struct *env, * should be actually ds/cs at fpu exception time, but * that information is not available in 64bit mode. */ - asm("mov %%ds,%0" : "=r" (env->fos)); - asm("mov %%cs,%0" : "=r" (env->fcs)); + asm("mov %%ds, %[fos]" : [fos] "=r" (env->fos)); + asm("mov %%cs, %[fcs]" : [fcs] "=r" (env->fcs)); } else { struct pt_regs *regs = task_pt_regs(tsk); + env->fos = 0xffff0000 | tsk->thread.ds; env->fcs = regs->cs; } @@ -274,7 +299,7 @@ static void convert_to_fxsr(struct task_struct *tsk, const struct user_i387_ia32_struct *env) { - struct i387_fxsave_struct *fxsave = &tsk->thread.i387.fxsave; + struct i387_fxsave_struct *fxsave = &tsk->thread.xstate->fxsave; struct _fpreg *from = (struct _fpreg *) &env->st_space[0]; struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0]; int i; @@ -303,15 +328,20 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, void *kbuf, void __user *ubuf) { struct user_i387_ia32_struct env; + int ret; if (!HAVE_HWFP) return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); - init_fpu(target); + ret = init_fpu(target); + if (ret) + return ret; - if (!cpu_has_fxsr) + if (!cpu_has_fxsr) { return user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.i387.fsave, 0, -1); + &target->thread.xstate->fsave, 0, + -1); + } if (kbuf && pos == 0 && count == sizeof(env)) { convert_from_fxsr(kbuf, target); @@ -319,6 +349,7 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, } convert_from_fxsr(&env, target); + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &env, 0, -1); } @@ -332,12 +363,16 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, if (!HAVE_HWFP) return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); - init_fpu(target); + ret = init_fpu(target); + if (ret) + return ret; + set_stopped_child_used_math(target); - if (!cpu_has_fxsr) + if (!cpu_has_fxsr) { return user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.i387.fsave, 0, -1); + &target->thread.xstate->fsave, 0, -1); + } if (pos > 0 || count < sizeof(env)) convert_from_fxsr(&env, target); @@ -356,11 +391,11 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, static inline int save_i387_fsave(struct _fpstate_ia32 __user *buf) { struct task_struct *tsk = current; + struct i387_fsave_struct *fp = &tsk->thread.xstate->fsave; unlazy_fpu(tsk); - tsk->thread.i387.fsave.status = tsk->thread.i387.fsave.swd; - if (__copy_to_user(buf, &tsk->thread.i387.fsave, - sizeof(struct i387_fsave_struct))) + fp->status = fp->swd; + if (__copy_to_user(buf, fp, sizeof(struct i387_fsave_struct))) return -1; return 1; } @@ -368,6 +403,7 @@ static inline int save_i387_fsave(struct _fpstate_ia32 __user *buf) static int save_i387_fxsave(struct _fpstate_ia32 __user *buf) { struct task_struct *tsk = current; + struct i387_fxsave_struct *fx = &tsk->thread.xstate->fxsave; struct user_i387_ia32_struct env; int err = 0; @@ -377,12 +413,12 @@ static int save_i387_fxsave(struct _fpstate_ia32 __user *buf) if (__copy_to_user(buf, &env, sizeof(env))) return -1; - err |= __put_user(tsk->thread.i387.fxsave.swd, &buf->status); + err |= __put_user(fx->swd, &buf->status); err |= __put_user(X86_FXSR_MAGIC, &buf->magic); if (err) return -1; - if (__copy_to_user(&buf->_fxsr_env[0], &tsk->thread.i387.fxsave, + if (__copy_to_user(&buf->_fxsr_env[0], fx, sizeof(struct i387_fxsave_struct))) return -1; return 1; @@ -392,46 +428,48 @@ int save_i387_ia32(struct _fpstate_ia32 __user *buf) { if (!used_math()) return 0; - - /* This will cause a "finit" to be triggered by the next + /* + * This will cause a "finit" to be triggered by the next * attempted FPU operation by the 'current' process. */ clear_used_math(); - if (HAVE_HWFP) { - if (cpu_has_fxsr) { - return save_i387_fxsave(buf); - } else { - return save_i387_fsave(buf); - } - } else { + if (!HAVE_HWFP) { return fpregs_soft_get(current, NULL, 0, sizeof(struct user_i387_ia32_struct), NULL, buf) ? -1 : 1; } + + if (cpu_has_fxsr) + return save_i387_fxsave(buf); + else + return save_i387_fsave(buf); } static inline int restore_i387_fsave(struct _fpstate_ia32 __user *buf) { struct task_struct *tsk = current; + clear_fpu(tsk); - return __copy_from_user(&tsk->thread.i387.fsave, buf, + return __copy_from_user(&tsk->thread.xstate->fsave, buf, sizeof(struct i387_fsave_struct)); } static int restore_i387_fxsave(struct _fpstate_ia32 __user *buf) { - int err; struct task_struct *tsk = current; struct user_i387_ia32_struct env; + int err; + clear_fpu(tsk); - err = __copy_from_user(&tsk->thread.i387.fxsave, &buf->_fxsr_env[0], + err = __copy_from_user(&tsk->thread.xstate->fxsave, &buf->_fxsr_env[0], sizeof(struct i387_fxsave_struct)); /* mxcsr reserved bits must be masked to zero for security reasons */ - tsk->thread.i387.fxsave.mxcsr &= mxcsr_feature_mask; + tsk->thread.xstate->fxsave.mxcsr &= mxcsr_feature_mask; if (err || __copy_from_user(&env, buf, sizeof(env))) return 1; convert_to_fxsr(tsk, &env); + return 0; } @@ -440,17 +478,17 @@ int restore_i387_ia32(struct _fpstate_ia32 __user *buf) int err; if (HAVE_HWFP) { - if (cpu_has_fxsr) { + if (cpu_has_fxsr) err = restore_i387_fxsave(buf); - } else { + else err = restore_i387_fsave(buf); - } } else { err = fpregs_soft_set(current, NULL, 0, sizeof(struct user_i387_ia32_struct), NULL, buf) != 0; } set_used_math(); + return err; } @@ -463,8 +501,8 @@ int restore_i387_ia32(struct _fpstate_ia32 __user *buf) */ int dump_fpu(struct pt_regs *regs, struct user_i387_struct *fpu) { - int fpvalid; struct task_struct *tsk = current; + int fpvalid; fpvalid = !!used_math(); if (fpvalid) diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c index 8540abe86ade..c1b5e3ece1f2 100644 --- a/arch/x86/kernel/i8253.c +++ b/arch/x86/kernel/i8253.c @@ -115,7 +115,8 @@ void __init setup_pit_timer(void) * IO_APIC has been initialized. */ pit_clockevent.cpumask = cpumask_of_cpu(smp_processor_id()); - pit_clockevent.mult = div_sc(CLOCK_TICK_RATE, NSEC_PER_SEC, 32); + pit_clockevent.mult = div_sc(CLOCK_TICK_RATE, NSEC_PER_SEC, + pit_clockevent.shift); pit_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFF, &pit_clockevent); pit_clockevent.min_delta_ns = @@ -224,7 +225,8 @@ static int __init init_pit_clocksource(void) pit_clockevent.mode != CLOCK_EVT_MODE_PERIODIC) return 0; - clocksource_pit.mult = clocksource_hz2mult(CLOCK_TICK_RATE, 20); + clocksource_pit.mult = clocksource_hz2mult(CLOCK_TICK_RATE, + clocksource_pit.shift); return clocksource_register(&clocksource_pit); } arch_initcall(init_pit_clocksource); diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c index 4ca548632c8d..a40d54fc1fdd 100644 --- a/arch/x86/kernel/io_apic_32.c +++ b/arch/x86/kernel/io_apic_32.c @@ -71,6 +71,16 @@ 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]; +int nr_ioapics; + +/* MP IRQ source entries */ +struct mpc_config_intsrc mp_irqs[MAX_IRQ_SOURCES]; + +/* # of MP IRQ source entries */ +int mp_irq_entries; + static int disable_timer_pin_1 __initdata; /* @@ -810,10 +820,7 @@ static int __init find_isa_irq_pin(int irq, int type) for (i = 0; i < mp_irq_entries; i++) { int lbus = mp_irqs[i].mpc_srcbus; - if ((mp_bus_id_to_type[lbus] == MP_BUS_ISA || - mp_bus_id_to_type[lbus] == MP_BUS_EISA || - mp_bus_id_to_type[lbus] == MP_BUS_MCA - ) && + if (test_bit(lbus, mp_bus_not_pci) && (mp_irqs[i].mpc_irqtype == type) && (mp_irqs[i].mpc_srcbusirq == irq)) @@ -829,10 +836,7 @@ static int __init find_isa_irq_apic(int irq, int type) for (i = 0; i < mp_irq_entries; i++) { int lbus = mp_irqs[i].mpc_srcbus; - if ((mp_bus_id_to_type[lbus] == MP_BUS_ISA || - mp_bus_id_to_type[lbus] == MP_BUS_EISA || - mp_bus_id_to_type[lbus] == MP_BUS_MCA - ) && + if (test_bit(lbus, mp_bus_not_pci) && (mp_irqs[i].mpc_irqtype == type) && (mp_irqs[i].mpc_srcbusirq == irq)) break; @@ -872,7 +876,7 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin) mp_irqs[i].mpc_dstapic == MP_APIC_ALL) break; - if ((mp_bus_id_to_type[lbus] == MP_BUS_PCI) && + if (!test_bit(lbus, mp_bus_not_pci) && !mp_irqs[i].mpc_irqtype && (bus == lbus) && (slot == ((mp_irqs[i].mpc_srcbusirq >> 2) & 0x1f))) { @@ -921,6 +925,7 @@ void __init setup_ioapic_dest(void) } #endif +#if defined(CONFIG_EISA) || defined(CONFIG_MCA) /* * EISA Edge/Level control register, ELCR */ @@ -934,6 +939,13 @@ static int EISA_ELCR(unsigned int irq) "Broken MPtable reports ISA irq %d\n", irq); return 0; } +#endif + +/* ISA interrupts are always polarity zero edge triggered, + * when listed as conforming in the MP table. */ + +#define default_ISA_trigger(idx) (0) +#define default_ISA_polarity(idx) (0) /* EISA interrupts are always polarity zero and can be edge or level * trigger depending on the ELCR value. If an interrupt is listed as @@ -941,13 +953,7 @@ static int EISA_ELCR(unsigned int irq) * be read in from the ELCR */ #define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].mpc_srcbusirq)) -#define default_EISA_polarity(idx) (0) - -/* ISA interrupts are always polarity zero edge triggered, - * when listed as conforming in the MP table. */ - -#define default_ISA_trigger(idx) (0) -#define default_ISA_polarity(idx) (0) +#define default_EISA_polarity(idx) default_ISA_polarity(idx) /* PCI interrupts are always polarity one level triggered, * when listed as conforming in the MP table. */ @@ -959,7 +965,7 @@ static int EISA_ELCR(unsigned int irq) * when listed as conforming in the MP table. */ #define default_MCA_trigger(idx) (1) -#define default_MCA_polarity(idx) (0) +#define default_MCA_polarity(idx) default_ISA_polarity(idx) static int MPBIOS_polarity(int idx) { @@ -973,35 +979,9 @@ static int MPBIOS_polarity(int idx) { case 0: /* conforms, ie. bus-type dependent polarity */ { - switch (mp_bus_id_to_type[bus]) - { - case MP_BUS_ISA: /* ISA pin */ - { - polarity = default_ISA_polarity(idx); - break; - } - case MP_BUS_EISA: /* EISA pin */ - { - polarity = default_EISA_polarity(idx); - break; - } - case MP_BUS_PCI: /* PCI pin */ - { - polarity = default_PCI_polarity(idx); - break; - } - case MP_BUS_MCA: /* MCA pin */ - { - polarity = default_MCA_polarity(idx); - break; - } - default: - { - 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 */ @@ -1042,11 +1022,15 @@ static int MPBIOS_trigger(int idx) { case 0: /* conforms, ie. bus-type dependent */ { + 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 */ { - trigger = default_ISA_trigger(idx); + /* set before the switch */ break; } case MP_BUS_EISA: /* EISA pin */ @@ -1056,7 +1040,7 @@ static int MPBIOS_trigger(int idx) } case MP_BUS_PCI: /* PCI pin */ { - trigger = default_PCI_trigger(idx); + /* set before the switch */ break; } case MP_BUS_MCA: /* MCA pin */ @@ -1071,6 +1055,7 @@ static int MPBIOS_trigger(int idx) break; } } +#endif break; } case 1: /* edge */ @@ -1120,39 +1105,22 @@ static int pin_2_irq(int idx, int apic, int pin) if (mp_irqs[idx].mpc_dstirq != pin) printk(KERN_ERR "broken BIOS or MPTABLE parser, ayiee!!\n"); - switch (mp_bus_id_to_type[bus]) - { - case MP_BUS_ISA: /* ISA pin */ - case MP_BUS_EISA: - case MP_BUS_MCA: - { - irq = mp_irqs[idx].mpc_srcbusirq; - break; - } - case MP_BUS_PCI: /* PCI pin */ - { - /* - * PCI IRQs are mapped in order - */ - i = irq = 0; - while (i < apic) - irq += nr_ioapic_registers[i++]; - irq += pin; - - /* - * For MPS mode, so far only needed by ES7000 platform - */ - if (ioapic_renumber_irq) - irq = ioapic_renumber_irq(apic, irq); + if (test_bit(bus, mp_bus_not_pci)) + irq = mp_irqs[idx].mpc_srcbusirq; + else { + /* + * PCI IRQs are mapped in order + */ + i = irq = 0; + while (i < apic) + irq += nr_ioapic_registers[i++]; + irq += pin; - break; - } - default: - { - printk(KERN_ERR "unknown bus type %d.\n",bus); - irq = 0; - break; - } + /* + * For MPS mode, so far only needed by ES7000 platform + */ + if (ioapic_renumber_irq) + irq = ioapic_renumber_irq(apic, irq); } /* @@ -1260,7 +1228,6 @@ static void __init setup_IO_APIC_irqs(void) { struct IO_APIC_route_entry entry; int apic, pin, idx, irq, first_notcon = 1, vector; - unsigned long flags; apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n"); @@ -1326,9 +1293,7 @@ static void __init setup_IO_APIC_irqs(void) if (!apic && (irq < 16)) disable_8259A_irq(irq); } - spin_lock_irqsave(&ioapic_lock, flags); - __ioapic_write_entry(apic, pin, entry); - spin_unlock_irqrestore(&ioapic_lock, flags); + ioapic_write_entry(apic, pin, entry); } } @@ -1524,8 +1489,8 @@ 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(v)); + 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); ver = GET_APIC_VERSION(v); @@ -1734,7 +1699,7 @@ void disable_IO_APIC(void) entry.delivery_mode = dest_ExtINT; /* ExtInt */ entry.vector = 0; entry.dest.physical.physical_dest = - GET_APIC_ID(apic_read(APIC_ID)); + GET_APIC_ID(read_apic_id()); /* * Add it to the IO-APIC irq-routing table: @@ -2031,8 +1996,7 @@ static inline void init_IO_APIC_traps(void) * 0x80, because int 0x80 is hm, kind of importantish. ;) */ for (irq = 0; irq < NR_IRQS ; irq++) { - int tmp = irq; - if (IO_APIC_IRQ(tmp) && !irq_vector[tmp]) { + if (IO_APIC_IRQ(irq) && !irq_vector[irq]) { /* * Hmm.. We don't have an entry for this, * so default to an old-fashioned 8259 @@ -2104,7 +2068,7 @@ static void __init setup_nmi(void) * cycles as some i82489DX-based boards have glue logic that keeps the * 8259A interrupt line asserted until INTA. --macro */ -static inline void unlock_ExtINT_logic(void) +static inline void __init unlock_ExtINT_logic(void) { int apic, pin, i; struct IO_APIC_route_entry entry0, entry1; @@ -2156,8 +2120,6 @@ static inline void unlock_ExtINT_logic(void) ioapic_write_entry(apic, pin, entry0); } -int timer_uses_ioapic_pin_0; - /* * This code may look a bit paranoid, but it's supposed to cooperate with * a wide range of boards and BIOS bugs. Fortunately only the timer IRQ @@ -2168,10 +2130,14 @@ static inline void __init check_timer(void) { int apic1, pin1, apic2, pin2; int vector; + unsigned int ver; unsigned long flags; local_irq_save(flags); + ver = apic_read(APIC_LVR); + ver = GET_APIC_VERSION(ver); + /* * get/set the timer IRQ vector: */ @@ -2184,11 +2150,15 @@ static inline void __init check_timer(void) * 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. + * 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. */ apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT); init_8259A(1); - timer_ack = 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); @@ -2197,9 +2167,6 @@ static inline void __init check_timer(void) pin2 = ioapic_i8259.pin; apic2 = ioapic_i8259.apic; - if (pin1 == 0) - timer_uses_ioapic_pin_0 = 1; - printk(KERN_INFO "..TIMER: vector=0x%02X apic1=%d pin1=%d apic2=%d pin2=%d\n", vector, apic1, pin1, apic2, pin2); @@ -2477,6 +2444,7 @@ void destroy_irq(unsigned int irq) dynamic_irq_cleanup(irq); spin_lock_irqsave(&vector_lock, flags); + clear_bit(irq_vector[irq], used_vectors); irq_vector[irq] = 0; spin_unlock_irqrestore(&vector_lock, flags); } @@ -2789,7 +2757,6 @@ 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) { struct IO_APIC_route_entry entry; - unsigned long flags; if (!IO_APIC_IRQ(irq)) { printk(KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n", @@ -2830,9 +2797,7 @@ int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int a if (!ioapic && (irq < 16)) disable_8259A_irq(irq); - spin_lock_irqsave(&ioapic_lock, flags); - __ioapic_write_entry(ioapic, pin, entry); - spin_unlock_irqrestore(&ioapic_lock, flags); + ioapic_write_entry(ioapic, pin, entry); return 0; } diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c index 1627c0d53e0b..ef1a8dfcc529 100644 --- a/arch/x86/kernel/io_apic_64.c +++ b/arch/x86/kernel/io_apic_64.c @@ -43,13 +43,15 @@ #include <asm/smp.h> #include <asm/desc.h> #include <asm/proto.h> -#include <asm/mach_apic.h> #include <asm/acpi.h> #include <asm/dma.h> #include <asm/nmi.h> #include <asm/msidef.h> #include <asm/hypertransport.h> +#include <mach_ipi.h> +#include <mach_apic.h> + struct irq_cfg { cpumask_t domain; cpumask_t old_domain; @@ -101,6 +103,16 @@ DEFINE_SPINLOCK(vector_lock); */ int nr_ioapic_registers[MAX_IO_APICS]; +/* I/O APIC entries */ +struct mpc_config_ioapic mp_ioapics[MAX_IO_APICS]; +int nr_ioapics; + +/* MP IRQ source entries */ +struct mpc_config_intsrc mp_irqs[MAX_IRQ_SOURCES]; + +/* # of MP IRQ source entries */ +int mp_irq_entries; + /* * Rough estimation of how many shared IRQs there are, can * be changed anytime. @@ -155,11 +167,10 @@ static inline void io_apic_modify(unsigned int apic, unsigned int value) writel(value, &io_apic->data); } -static int io_apic_level_ack_pending(unsigned int irq) +static bool io_apic_level_ack_pending(unsigned int irq) { struct irq_pin_list *entry; unsigned long flags; - int pending = 0; spin_lock_irqsave(&ioapic_lock, flags); entry = irq_2_pin + irq; @@ -172,13 +183,17 @@ static int io_apic_level_ack_pending(unsigned int irq) break; reg = io_apic_read(entry->apic, 0x10 + pin*2); /* Is the remote IRR bit set? */ - pending |= (reg >> 14) & 1; + if ((reg >> 14) & 1) { + spin_unlock_irqrestore(&ioapic_lock, flags); + return true; + } if (!entry->next) break; entry = irq_2_pin + entry->next; } spin_unlock_irqrestore(&ioapic_lock, flags); - return pending; + + return false; } /* @@ -770,7 +785,7 @@ static void __clear_irq_vector(int irq) per_cpu(vector_irq, cpu)[vector] = -1; cfg->vector = 0; - cfg->domain = CPU_MASK_NONE; + cpus_clear(cfg->domain); } void __setup_vector_irq(int cpu) @@ -902,9 +917,8 @@ static void __init setup_IO_APIC_irqs(void) static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, int vector) { struct IO_APIC_route_entry entry; - unsigned long flags; - memset(&entry,0,sizeof(entry)); + memset(&entry, 0, sizeof(entry)); disable_8259A_irq(0); @@ -932,10 +946,7 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in /* * Add it to the IO-APIC irq-routing table: */ - spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(apic, 0x11+2*pin, *(((int *)&entry)+1)); - io_apic_write(apic, 0x10+2*pin, *(((int *)&entry)+0)); - spin_unlock_irqrestore(&ioapic_lock, flags); + ioapic_write_entry(apic, pin, entry); enable_8259A_irq(0); } @@ -1066,8 +1077,7 @@ 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(v)); + 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); ver = GET_APIC_VERSION(v); @@ -1261,7 +1271,7 @@ void disable_IO_APIC(void) entry.dest_mode = 0; /* Physical */ entry.delivery_mode = dest_ExtINT; /* ExtInt */ entry.vector = 0; - entry.dest = GET_APIC_ID(apic_read(APIC_ID)); + entry.dest = GET_APIC_ID(read_apic_id()); /* * Add it to the IO-APIC irq-routing table: @@ -1352,9 +1362,7 @@ static int ioapic_retrigger_irq(unsigned int irq) unsigned long flags; spin_lock_irqsave(&vector_lock, flags); - cpus_clear(mask); - cpu_set(first_cpu(cfg->domain), mask); - + mask = cpumask_of_cpu(first_cpu(cfg->domain)); send_IPI_mask(mask, cfg->vector); spin_unlock_irqrestore(&vector_lock, flags); @@ -1517,8 +1525,7 @@ static inline void init_IO_APIC_traps(void) * 0x80, because int 0x80 is hm, kind of importantish. ;) */ for (irq = 0; irq < NR_IRQS ; irq++) { - int tmp = irq; - if (IO_APIC_IRQ(tmp) && !irq_cfg[tmp].vector) { + if (IO_APIC_IRQ(irq) && !irq_cfg[irq].vector) { /* * Hmm.. We don't have an entry for this, * so default to an old-fashioned 8259 @@ -1592,22 +1599,19 @@ static void __init setup_nmi(void) * cycles as some i82489DX-based boards have glue logic that keeps the * 8259A interrupt line asserted until INTA. --macro */ -static inline void unlock_ExtINT_logic(void) +static inline void __init unlock_ExtINT_logic(void) { int apic, pin, i; struct IO_APIC_route_entry entry0, entry1; unsigned char save_control, save_freq_select; - unsigned long flags; pin = find_isa_irq_pin(8, mp_INT); apic = find_isa_irq_apic(8, mp_INT); if (pin == -1) return; - spin_lock_irqsave(&ioapic_lock, flags); - *(((int *)&entry0) + 1) = io_apic_read(apic, 0x11 + 2 * pin); - *(((int *)&entry0) + 0) = io_apic_read(apic, 0x10 + 2 * pin); - spin_unlock_irqrestore(&ioapic_lock, flags); + entry0 = ioapic_read_entry(apic, pin); + clear_IO_APIC_pin(apic, pin); memset(&entry1, 0, sizeof(entry1)); @@ -1620,10 +1624,7 @@ static inline void unlock_ExtINT_logic(void) entry1.trigger = 0; entry1.vector = 0; - spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(apic, 0x11 + 2 * pin, *(((int *)&entry1) + 1)); - io_apic_write(apic, 0x10 + 2 * pin, *(((int *)&entry1) + 0)); - spin_unlock_irqrestore(&ioapic_lock, flags); + ioapic_write_entry(apic, pin, entry1); save_control = CMOS_READ(RTC_CONTROL); save_freq_select = CMOS_READ(RTC_FREQ_SELECT); @@ -1642,10 +1643,7 @@ static inline void unlock_ExtINT_logic(void) CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT); clear_IO_APIC_pin(apic, pin); - spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(apic, 0x11 + 2 * pin, *(((int *)&entry0) + 1)); - io_apic_write(apic, 0x10 + 2 * pin, *(((int *)&entry0) + 0)); - spin_unlock_irqrestore(&ioapic_lock, flags); + ioapic_write_entry(apic, pin, entry0); } /* @@ -2314,7 +2312,6 @@ static struct resource * __init ioapic_setup_resources(void) res = (void *)mem; if (mem != NULL) { - memset(mem, 0, n); mem += sizeof(struct resource) * nr_ioapics; for (i = 0; i < nr_ioapics; i++) { diff --git a/arch/x86/kernel/ipi.c b/arch/x86/kernel/ipi.c new file mode 100644 index 000000000000..c0df7b89ca23 --- /dev/null +++ b/arch/x86/kernel/ipi.c @@ -0,0 +1,178 @@ +#include <linux/cpumask.h> +#include <linux/interrupt.h> +#include <linux/init.h> + +#include <linux/mm.h> +#include <linux/delay.h> +#include <linux/spinlock.h> +#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> + +#include <asm/smp.h> +#include <asm/mtrr.h> +#include <asm/tlbflush.h> +#include <asm/mmu_context.h> +#include <asm/apic.h> +#include <asm/proto.h> + +#ifdef CONFIG_X86_32 +#include <mach_apic.h> +/* + * the following functions deal with sending IPIs between CPUs. + * + * We use 'broadcast', CPU->CPU IPIs and self-IPIs too. + */ + +static inline int __prepare_ICR(unsigned int shortcut, int vector) +{ + unsigned int icr = shortcut | APIC_DEST_LOGICAL; + + switch (vector) { + default: + icr |= APIC_DM_FIXED | vector; + break; + case NMI_VECTOR: + icr |= APIC_DM_NMI; + break; + } + return icr; +} + +static inline int __prepare_ICR2(unsigned int mask) +{ + return SET_APIC_DEST_FIELD(mask); +} + +void __send_IPI_shortcut(unsigned int shortcut, int vector) +{ + /* + * Subtle. In the case of the 'never do double writes' workaround + * we have to lock out interrupts to be safe. As we don't care + * of the value read we use an atomic rmw access to avoid costly + * cli/sti. Otherwise we use an even cheaper single atomic write + * to the APIC. + */ + unsigned int cfg; + + /* + * Wait for idle. + */ + apic_wait_icr_idle(); + + /* + * No need to touch the target chip field + */ + cfg = __prepare_ICR(shortcut, vector); + + /* + * Send the IPI. The write to APIC_ICR fires this off. + */ + apic_write_around(APIC_ICR, cfg); +} + +void send_IPI_self(int vector) +{ + __send_IPI_shortcut(APIC_DEST_SELF, vector); +} + +/* + * This is used to send an IPI with no shorthand notation (the destination is + * specified in bits 56 to 63 of the ICR). + */ +static inline void __send_IPI_dest_field(unsigned long mask, int vector) +{ + unsigned long cfg; + + /* + * Wait for idle. + */ + if (unlikely(vector == NMI_VECTOR)) + safe_apic_wait_icr_idle(); + else + apic_wait_icr_idle(); + + /* + * prepare target chip field + */ + cfg = __prepare_ICR2(mask); + apic_write_around(APIC_ICR2, cfg); + + /* + * program the ICR + */ + cfg = __prepare_ICR(0, vector); + + /* + * Send the IPI. The write to APIC_ICR fires this off. + */ + apic_write_around(APIC_ICR, cfg); +} + +/* + * This is only used on smaller machines. + */ +void send_IPI_mask_bitmask(cpumask_t cpumask, int vector) +{ + unsigned long mask = cpus_addr(cpumask)[0]; + unsigned long flags; + + local_irq_save(flags); + WARN_ON(mask & ~cpus_addr(cpu_online_map)[0]); + __send_IPI_dest_field(mask, vector); + local_irq_restore(flags); +} + +void send_IPI_mask_sequence(cpumask_t mask, int vector) +{ + unsigned long flags; + unsigned int query_cpu; + + /* + * Hack. The clustered APIC addressing mode doesn't allow us to send + * to an arbitrary mask, so I do a unicasts to each CPU instead. This + * should be modified to do 1 message per cluster ID - mbligh + */ + + local_irq_save(flags); + for_each_possible_cpu(query_cpu) { + if (cpu_isset(query_cpu, mask)) { + __send_IPI_dest_field(cpu_to_logical_apicid(query_cpu), + vector); + } + } + local_irq_restore(flags); +} + +/* must come after the send_IPI functions above for inlining */ +#include <mach_ipi.h> +static int convert_apicid_to_cpu(int apic_id) +{ + int i; + + for_each_possible_cpu(i) { + if (per_cpu(x86_cpu_to_apicid, i) == apic_id) + return i; + } + return -1; +} + +int safe_smp_processor_id(void) +{ + int apicid, cpuid; + + if (!boot_cpu_has(X86_FEATURE_APIC)) + return 0; + + apicid = hard_smp_processor_id(); + if (apicid == BAD_APICID) + return 0; + + cpuid = convert_apicid_to_cpu(apicid); + + return cpuid >= 0 ? cpuid : 0; +} +#endif diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index cef054b09d27..147352df28b9 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -79,7 +79,7 @@ unsigned int do_IRQ(struct pt_regs *regs) if (unlikely((unsigned)irq >= NR_IRQS)) { printk(KERN_EMERG "%s: cannot handle IRQ %d\n", - __FUNCTION__, irq); + __func__, irq); BUG(); } @@ -134,7 +134,7 @@ unsigned int do_IRQ(struct pt_regs *regs) : "=a" (arg1), "=d" (arg2), "=b" (bx) : "0" (irq), "1" (desc), "2" (isp), "D" (desc->handle_irq) - : "memory", "cc" + : "memory", "cc", "ecx" ); } else #endif @@ -190,8 +190,6 @@ void irq_ctx_exit(int cpu) hardirq_ctx[cpu] = NULL; } -extern asmlinkage void __do_softirq(void); - asmlinkage void do_softirq(void) { unsigned long flags; diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c index 73354302fda7..c03205991718 100644 --- a/arch/x86/kernel/kdebugfs.c +++ b/arch/x86/kernel/kdebugfs.c @@ -6,23 +6,171 @@ * * This file is released under the GPLv2. */ - #include <linux/debugfs.h> +#include <linux/uaccess.h> #include <linux/stat.h> #include <linux/init.h> +#include <linux/io.h> +#include <linux/mm.h> #include <asm/setup.h> #ifdef CONFIG_DEBUG_BOOT_PARAMS +struct setup_data_node { + u64 paddr; + u32 type; + u32 len; +}; + +static ssize_t +setup_data_read(struct file *file, char __user *user_buf, size_t count, + loff_t *ppos) +{ + struct setup_data_node *node = file->private_data; + unsigned long remain; + loff_t pos = *ppos; + struct page *pg; + void *p; + u64 pa; + + if (pos < 0) + return -EINVAL; + if (pos >= node->len) + return 0; + + if (count > node->len - pos) + count = node->len - pos; + pa = node->paddr + sizeof(struct setup_data) + pos; + pg = pfn_to_page((pa + count - 1) >> PAGE_SHIFT); + if (PageHighMem(pg)) { + p = ioremap_cache(pa, count); + if (!p) + return -ENXIO; + } else { + p = __va(pa); + } + + remain = copy_to_user(user_buf, p, count); + + if (PageHighMem(pg)) + iounmap(p); + + if (remain) + return -EFAULT; + + *ppos = pos + count; + + return count; +} + +static int setup_data_open(struct inode *inode, struct file *file) +{ + file->private_data = inode->i_private; + return 0; +} + +static const struct file_operations fops_setup_data = { + .read = setup_data_read, + .open = setup_data_open, +}; + +static int __init +create_setup_data_node(struct dentry *parent, int no, + struct setup_data_node *node) +{ + struct dentry *d, *type, *data; + char buf[16]; + int error; + + sprintf(buf, "%d", no); + d = debugfs_create_dir(buf, parent); + if (!d) { + error = -ENOMEM; + goto err_return; + } + type = debugfs_create_x32("type", S_IRUGO, d, &node->type); + if (!type) { + error = -ENOMEM; + goto err_dir; + } + data = debugfs_create_file("data", S_IRUGO, d, node, &fops_setup_data); + if (!data) { + error = -ENOMEM; + goto err_type; + } + return 0; + +err_type: + debugfs_remove(type); +err_dir: + debugfs_remove(d); +err_return: + return error; +} + +static int __init create_setup_data_nodes(struct dentry *parent) +{ + struct setup_data_node *node; + struct setup_data *data; + int error, no = 0; + struct dentry *d; + struct page *pg; + u64 pa_data; + + d = debugfs_create_dir("setup_data", parent); + if (!d) { + error = -ENOMEM; + goto err_return; + } + + pa_data = boot_params.hdr.setup_data; + + while (pa_data) { + node = kmalloc(sizeof(*node), GFP_KERNEL); + if (!node) { + error = -ENOMEM; + goto err_dir; + } + pg = pfn_to_page((pa_data+sizeof(*data)-1) >> PAGE_SHIFT); + if (PageHighMem(pg)) { + data = ioremap_cache(pa_data, sizeof(*data)); + if (!data) { + error = -ENXIO; + goto err_dir; + } + } else { + data = __va(pa_data); + } + + node->paddr = pa_data; + node->type = data->type; + node->len = data->len; + error = create_setup_data_node(d, no, node); + pa_data = data->next; + + if (PageHighMem(pg)) + iounmap(data); + if (error) + goto err_dir; + no++; + } + return 0; + +err_dir: + debugfs_remove(d); +err_return: + return error; +} + static struct debugfs_blob_wrapper boot_params_blob = { - .data = &boot_params, - .size = sizeof(boot_params), + .data = &boot_params, + .size = sizeof(boot_params), }; static int __init boot_params_kdebugfs_init(void) { - int error; struct dentry *dbp, *version, *data; + int error; dbp = debugfs_create_dir("boot_params", NULL); if (!dbp) { @@ -41,7 +189,13 @@ static int __init boot_params_kdebugfs_init(void) error = -ENOMEM; goto err_version; } + error = create_setup_data_nodes(dbp); + if (error) + goto err_data; return 0; + +err_data: + debugfs_remove(data); err_version: debugfs_remove(version); err_dir: @@ -61,5 +215,4 @@ static int __init arch_kdebugfs_init(void) return error; } - arch_initcall(arch_kdebugfs_init); diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c new file mode 100644 index 000000000000..f47f0eb886b8 --- /dev/null +++ b/arch/x86/kernel/kgdb.c @@ -0,0 +1,567 @@ +/* + * 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, 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. + * + */ + +/* + * Copyright (C) 2004 Amit S. Kale <amitkale@linsyssoft.com> + * Copyright (C) 2000-2001 VERITAS Software Corporation. + * Copyright (C) 2002 Andi Kleen, SuSE Labs + * Copyright (C) 2004 LinSysSoft Technologies Pvt. Ltd. + * Copyright (C) 2007 MontaVista Software, Inc. + * Copyright (C) 2007-2008 Jason Wessel, Wind River Systems, Inc. + */ +/**************************************************************************** + * Contributor: Lake Stevens Instrument Division$ + * Written by: Glenn Engel $ + * Updated by: Amit Kale<akale@veritas.com> + * Updated by: Tom Rini <trini@kernel.crashing.org> + * Updated by: Jason Wessel <jason.wessel@windriver.com> + * Modified for 386 by Jim Kingdon, Cygnus Support. + * Origianl kgdb, compatibility with 2.1.xx kernel by + * David Grothe <dave@gcom.com> + * Integrated into 2.2.5 kernel by Tigran Aivazian <tigran@sco.com> + * X86_64 changes from Andi Kleen's patch merged by Jim Houston + */ +#include <linux/spinlock.h> +#include <linux/kdebug.h> +#include <linux/string.h> +#include <linux/kernel.h> +#include <linux/ptrace.h> +#include <linux/sched.h> +#include <linux/delay.h> +#include <linux/kgdb.h> +#include <linux/init.h> +#include <linux/smp.h> +#include <linux/nmi.h> + +#include <asm/apicdef.h> +#include <asm/system.h> + +#include <mach_ipi.h> + +/* + * Put the error code here just in case the user cares: + */ +static int gdb_x86errcode; + +/* + * Likewise, the vector number here (since GDB only gets the signal + * number through the usual means, and that's not very specific): + */ +static int gdb_x86vector = -1; + +/** + * pt_regs_to_gdb_regs - Convert ptrace regs to GDB regs + * @gdb_regs: A pointer to hold the registers in the order GDB wants. + * @regs: The &struct pt_regs of the current process. + * + * Convert the pt_regs in @regs into the format for registers that + * GDB expects, stored in @gdb_regs. + */ +void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs) +{ + gdb_regs[GDB_AX] = regs->ax; + gdb_regs[GDB_BX] = regs->bx; + gdb_regs[GDB_CX] = regs->cx; + gdb_regs[GDB_DX] = regs->dx; + gdb_regs[GDB_SI] = regs->si; + gdb_regs[GDB_DI] = regs->di; + gdb_regs[GDB_BP] = regs->bp; + gdb_regs[GDB_PS] = regs->flags; + gdb_regs[GDB_PC] = regs->ip; +#ifdef CONFIG_X86_32 + gdb_regs[GDB_DS] = regs->ds; + gdb_regs[GDB_ES] = regs->es; + gdb_regs[GDB_CS] = regs->cs; + gdb_regs[GDB_SS] = __KERNEL_DS; + gdb_regs[GDB_FS] = 0xFFFF; + gdb_regs[GDB_GS] = 0xFFFF; +#else + gdb_regs[GDB_R8] = regs->r8; + gdb_regs[GDB_R9] = regs->r9; + gdb_regs[GDB_R10] = regs->r10; + gdb_regs[GDB_R11] = regs->r11; + gdb_regs[GDB_R12] = regs->r12; + gdb_regs[GDB_R13] = regs->r13; + gdb_regs[GDB_R14] = regs->r14; + gdb_regs[GDB_R15] = regs->r15; +#endif + gdb_regs[GDB_SP] = regs->sp; +} + +/** + * sleeping_thread_to_gdb_regs - Convert ptrace regs to GDB regs + * @gdb_regs: A pointer to hold the registers in the order GDB wants. + * @p: The &struct task_struct of the desired process. + * + * Convert the register values of the sleeping process in @p to + * the format that GDB expects. + * This function is called when kgdb does not have access to the + * &struct pt_regs and therefore it should fill the gdb registers + * @gdb_regs with what has been saved in &struct thread_struct + * thread field during switch_to. + */ +void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p) +{ + gdb_regs[GDB_AX] = 0; + gdb_regs[GDB_BX] = 0; + gdb_regs[GDB_CX] = 0; + gdb_regs[GDB_DX] = 0; + gdb_regs[GDB_SI] = 0; + gdb_regs[GDB_DI] = 0; + gdb_regs[GDB_BP] = *(unsigned long *)p->thread.sp; +#ifdef CONFIG_X86_32 + gdb_regs[GDB_DS] = __KERNEL_DS; + gdb_regs[GDB_ES] = __KERNEL_DS; + gdb_regs[GDB_PS] = 0; + gdb_regs[GDB_CS] = __KERNEL_CS; + gdb_regs[GDB_PC] = p->thread.ip; + gdb_regs[GDB_SS] = __KERNEL_DS; + gdb_regs[GDB_FS] = 0xFFFF; + gdb_regs[GDB_GS] = 0xFFFF; +#else + gdb_regs[GDB_PS] = *(unsigned long *)(p->thread.sp + 8); + gdb_regs[GDB_PC] = 0; + gdb_regs[GDB_R8] = 0; + gdb_regs[GDB_R9] = 0; + gdb_regs[GDB_R10] = 0; + gdb_regs[GDB_R11] = 0; + gdb_regs[GDB_R12] = 0; + gdb_regs[GDB_R13] = 0; + gdb_regs[GDB_R14] = 0; + gdb_regs[GDB_R15] = 0; +#endif + gdb_regs[GDB_SP] = p->thread.sp; +} + +/** + * gdb_regs_to_pt_regs - Convert GDB regs to ptrace regs. + * @gdb_regs: A pointer to hold the registers we've received from GDB. + * @regs: A pointer to a &struct pt_regs to hold these values in. + * + * Convert the GDB regs in @gdb_regs into the pt_regs, and store them + * in @regs. + */ +void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs) +{ + regs->ax = gdb_regs[GDB_AX]; + regs->bx = gdb_regs[GDB_BX]; + regs->cx = gdb_regs[GDB_CX]; + regs->dx = gdb_regs[GDB_DX]; + regs->si = gdb_regs[GDB_SI]; + regs->di = gdb_regs[GDB_DI]; + regs->bp = gdb_regs[GDB_BP]; + regs->flags = gdb_regs[GDB_PS]; + regs->ip = gdb_regs[GDB_PC]; +#ifdef CONFIG_X86_32 + regs->ds = gdb_regs[GDB_DS]; + regs->es = gdb_regs[GDB_ES]; + regs->cs = gdb_regs[GDB_CS]; +#else + regs->r8 = gdb_regs[GDB_R8]; + regs->r9 = gdb_regs[GDB_R9]; + regs->r10 = gdb_regs[GDB_R10]; + regs->r11 = gdb_regs[GDB_R11]; + regs->r12 = gdb_regs[GDB_R12]; + regs->r13 = gdb_regs[GDB_R13]; + regs->r14 = gdb_regs[GDB_R14]; + regs->r15 = gdb_regs[GDB_R15]; +#endif +} + +static struct hw_breakpoint { + unsigned enabled; + unsigned type; + unsigned len; + unsigned long addr; +} breakinfo[4]; + +static void kgdb_correct_hw_break(void) +{ + unsigned long dr7; + int correctit = 0; + int breakbit; + int breakno; + + get_debugreg(dr7, 7); + for (breakno = 0; breakno < 4; breakno++) { + breakbit = 2 << (breakno << 1); + if (!(dr7 & breakbit) && breakinfo[breakno].enabled) { + correctit = 1; + dr7 |= breakbit; + dr7 &= ~(0xf0000 << (breakno << 2)); + dr7 |= ((breakinfo[breakno].len << 2) | + breakinfo[breakno].type) << + ((breakno << 2) + 16); + if (breakno >= 0 && breakno <= 3) + set_debugreg(breakinfo[breakno].addr, breakno); + + } else { + if ((dr7 & breakbit) && !breakinfo[breakno].enabled) { + correctit = 1; + dr7 &= ~breakbit; + dr7 &= ~(0xf0000 << (breakno << 2)); + } + } + } + if (correctit) + set_debugreg(dr7, 7); +} + +static int +kgdb_remove_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype) +{ + int i; + + for (i = 0; i < 4; i++) + if (breakinfo[i].addr == addr && breakinfo[i].enabled) + break; + if (i == 4) + return -1; + + breakinfo[i].enabled = 0; + + return 0; +} + +static void kgdb_remove_all_hw_break(void) +{ + int i; + + for (i = 0; i < 4; i++) + memset(&breakinfo[i], 0, sizeof(struct hw_breakpoint)); +} + +static int +kgdb_set_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype) +{ + unsigned type; + int i; + + for (i = 0; i < 4; i++) + if (!breakinfo[i].enabled) + break; + if (i == 4) + return -1; + + switch (bptype) { + case BP_HARDWARE_BREAKPOINT: + type = 0; + len = 1; + break; + case BP_WRITE_WATCHPOINT: + type = 1; + break; + case BP_ACCESS_WATCHPOINT: + type = 3; + break; + default: + return -1; + } + + if (len == 1 || len == 2 || len == 4) + breakinfo[i].len = len - 1; + else + return -1; + + breakinfo[i].enabled = 1; + breakinfo[i].addr = addr; + breakinfo[i].type = type; + + return 0; +} + +/** + * kgdb_disable_hw_debug - Disable hardware debugging while we in kgdb. + * @regs: Current &struct pt_regs. + * + * This function will be called if the particular architecture must + * disable hardware debugging while it is processing gdb packets or + * handling exception. + */ +void kgdb_disable_hw_debug(struct pt_regs *regs) +{ + /* Disable hardware debugging while we are in kgdb: */ + set_debugreg(0UL, 7); +} + +/** + * kgdb_post_primary_code - Save error vector/code numbers. + * @regs: Original pt_regs. + * @e_vector: Original error vector. + * @err_code: Original error code. + * + * This is needed on architectures which support SMP and KGDB. + * This function is called after all the slave cpus have been put + * to a know spin state and the primary CPU has control over KGDB. + */ +void kgdb_post_primary_code(struct pt_regs *regs, int e_vector, int err_code) +{ + /* primary processor is completely in the debugger */ + gdb_x86vector = e_vector; + gdb_x86errcode = err_code; +} + +#ifdef CONFIG_SMP +/** + * kgdb_roundup_cpus - Get other CPUs into a holding pattern + * @flags: Current IRQ state + * + * On SMP systems, we need to get the attention of the other CPUs + * and get them be in a known state. This should do what is needed + * to get the other CPUs to call kgdb_wait(). Note that on some arches, + * the NMI approach is not used for rounding up all the CPUs. For example, + * in case of MIPS, smp_call_function() is used to roundup CPUs. In + * this case, we have to make sure that interrupts are enabled before + * calling smp_call_function(). The argument to this function is + * the flags that will be used when restoring the interrupts. There is + * local_irq_save() call before kgdb_roundup_cpus(). + * + * On non-SMP systems, this is not called. + */ +void kgdb_roundup_cpus(unsigned long flags) +{ + send_IPI_allbutself(APIC_DM_NMI); +} +#endif + +/** + * kgdb_arch_handle_exception - Handle architecture specific GDB packets. + * @vector: The error vector of the exception that happened. + * @signo: The signal number of the exception that happened. + * @err_code: The error code of the exception that happened. + * @remcom_in_buffer: The buffer of the packet we have read. + * @remcom_out_buffer: The buffer of %BUFMAX bytes to write a packet into. + * @regs: The &struct pt_regs of the current process. + * + * This function MUST handle the 'c' and 's' command packets, + * as well packets to set / remove a hardware breakpoint, if used. + * If there are additional packets which the hardware needs to handle, + * they are handled here. The code should return -1 if it wants to + * process more packets, and a %0 or %1 if it wants to exit from the + * kgdb callback. + */ +int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, + char *remcomInBuffer, char *remcomOutBuffer, + struct pt_regs *linux_regs) +{ + unsigned long addr; + unsigned long dr6; + char *ptr; + int newPC; + + switch (remcomInBuffer[0]) { + case 'c': + case 's': + /* try to read optional parameter, pc unchanged if no parm */ + ptr = &remcomInBuffer[1]; + if (kgdb_hex2long(&ptr, &addr)) + linux_regs->ip = addr; + case 'D': + case 'k': + newPC = linux_regs->ip; + + /* clear the trace bit */ + linux_regs->flags &= ~X86_EFLAGS_TF; + atomic_set(&kgdb_cpu_doing_single_step, -1); + + /* set the trace bit if we're stepping */ + if (remcomInBuffer[0] == 's') { + linux_regs->flags |= X86_EFLAGS_TF; + kgdb_single_step = 1; + if (kgdb_contthread) { + atomic_set(&kgdb_cpu_doing_single_step, + raw_smp_processor_id()); + } + } + + get_debugreg(dr6, 6); + if (!(dr6 & 0x4000)) { + int breakno; + + for (breakno = 0; breakno < 4; breakno++) { + if (dr6 & (1 << breakno) && + breakinfo[breakno].type == 0) { + /* Set restore flag: */ + linux_regs->flags |= X86_EFLAGS_RF; + break; + } + } + } + set_debugreg(0UL, 6); + kgdb_correct_hw_break(); + + return 0; + } + + /* this means that we do not want to exit from the handler: */ + return -1; +} + +static inline int +single_step_cont(struct pt_regs *regs, struct die_args *args) +{ + /* + * Single step exception from kernel space to user space so + * eat the exception and continue the process: + */ + printk(KERN_ERR "KGDB: trap/step from kernel to user space, " + "resuming...\n"); + kgdb_arch_handle_exception(args->trapnr, args->signr, + args->err, "c", "", regs); + + return NOTIFY_STOP; +} + +static int was_in_debug_nmi[NR_CPUS]; + +static int __kgdb_notify(struct die_args *args, unsigned long cmd) +{ + struct pt_regs *regs = args->regs; + + switch (cmd) { + case DIE_NMI: + if (atomic_read(&kgdb_active) != -1) { + /* KGDB CPU roundup */ + kgdb_nmicallback(raw_smp_processor_id(), regs); + was_in_debug_nmi[raw_smp_processor_id()] = 1; + touch_nmi_watchdog(); + return NOTIFY_STOP; + } + return NOTIFY_DONE; + + case DIE_NMI_IPI: + if (atomic_read(&kgdb_active) != -1) { + /* KGDB CPU roundup */ + kgdb_nmicallback(raw_smp_processor_id(), regs); + was_in_debug_nmi[raw_smp_processor_id()] = 1; + touch_nmi_watchdog(); + } + return NOTIFY_DONE; + + case DIE_NMIUNKNOWN: + if (was_in_debug_nmi[raw_smp_processor_id()]) { + was_in_debug_nmi[raw_smp_processor_id()] = 0; + return NOTIFY_STOP; + } + return NOTIFY_DONE; + + case DIE_NMIWATCHDOG: + if (atomic_read(&kgdb_active) != -1) { + /* KGDB CPU roundup: */ + kgdb_nmicallback(raw_smp_processor_id(), regs); + return NOTIFY_STOP; + } + /* Enter debugger: */ + break; + + case DIE_DEBUG: + if (atomic_read(&kgdb_cpu_doing_single_step) == + raw_smp_processor_id() && + user_mode(regs)) + return single_step_cont(regs, args); + /* fall through */ + default: + if (user_mode(regs)) + return NOTIFY_DONE; + } + + if (kgdb_handle_exception(args->trapnr, args->signr, args->err, regs)) + return NOTIFY_DONE; + + /* Must touch watchdog before return to normal operation */ + touch_nmi_watchdog(); + return NOTIFY_STOP; +} + +static int +kgdb_notify(struct notifier_block *self, unsigned long cmd, void *ptr) +{ + unsigned long flags; + int ret; + + local_irq_save(flags); + ret = __kgdb_notify(ptr, cmd); + local_irq_restore(flags); + + return ret; +} + +static struct notifier_block kgdb_notifier = { + .notifier_call = kgdb_notify, + + /* + * Lowest-prio notifier priority, we want to be notified last: + */ + .priority = -INT_MAX, +}; + +/** + * kgdb_arch_init - Perform any architecture specific initalization. + * + * This function will handle the initalization of any architecture + * specific callbacks. + */ +int kgdb_arch_init(void) +{ + return register_die_notifier(&kgdb_notifier); +} + +/** + * kgdb_arch_exit - Perform any architecture specific uninitalization. + * + * This function will handle the uninitalization of any architecture + * specific callbacks, for dynamic registration and unregistration. + */ +void kgdb_arch_exit(void) +{ + unregister_die_notifier(&kgdb_notifier); +} + +/** + * + * kgdb_skipexception - Bail out of KGDB when we've been triggered. + * @exception: Exception vector number + * @regs: Current &struct pt_regs. + * + * On some architectures we need to skip a breakpoint exception when + * it occurs after a breakpoint has been removed. + * + * Skip an int3 exception when it occurs after a breakpoint has been + * removed. Backtrack eip by 1 since the int3 would have caused it to + * increment by 1. + */ +int kgdb_skipexception(int exception, struct pt_regs *regs) +{ + if (exception == 3 && kgdb_isremovedbreak(regs->ip - 1)) { + regs->ip -= 1; + return 1; + } + return 0; +} + +unsigned long kgdb_arch_pc(int exception, struct pt_regs *regs) +{ + if (exception == 3) + return instruction_pointer(regs) - 1; + return instruction_pointer(regs); +} + +struct kgdb_arch arch_kgdb_ops = { + /* Breakpoint instruction: */ + .gdb_bpt_instr = { 0xcc }, + .flags = KGDB_HW_BREAKPOINT, + .set_hw_breakpoint = kgdb_set_hw_break, + .remove_hw_breakpoint = kgdb_remove_hw_break, + .remove_all_hw_break = kgdb_remove_all_hw_break, + .correct_hw_break = kgdb_correct_hw_break, +}; diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 34a591283f5d..b8c6743a13da 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -410,13 +410,13 @@ static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs, static void __kprobes clear_btf(void) { if (test_thread_flag(TIF_DEBUGCTLMSR)) - wrmsrl(MSR_IA32_DEBUGCTLMSR, 0); + update_debugctlmsr(0); } static void __kprobes restore_btf(void) { if (test_thread_flag(TIF_DEBUGCTLMSR)) - wrmsrl(MSR_IA32_DEBUGCTLMSR, current->thread.debugctlmsr); + update_debugctlmsr(current->thread.debugctlmsr); } static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs) @@ -489,7 +489,7 @@ static int __kprobes reenter_kprobe(struct kprobe *p, struct pt_regs *regs, break; case KPROBE_HIT_SS: if (p == kprobe_running()) { - regs->flags &= ~TF_MASK; + regs->flags &= ~X86_EFLAGS_TF; regs->flags |= kcb->kprobe_saved_flags; return 0; } else { @@ -858,15 +858,15 @@ static int __kprobes post_kprobe_handler(struct pt_regs *regs) if (!cur) return 0; + resume_execution(cur, regs, kcb); + regs->flags |= kcb->kprobe_saved_flags; + trace_hardirqs_fixup_flags(regs->flags); + if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) { kcb->kprobe_status = KPROBE_HIT_SSDONE; cur->post_handler(cur, regs, 0); } - resume_execution(cur, regs, kcb); - regs->flags |= kcb->kprobe_saved_flags; - trace_hardirqs_fixup_flags(regs->flags); - /* Restore back the original saved kprobes variables and continue. */ if (kcb->kprobe_status == KPROBE_REENTER) { restore_previous_kprobe(kcb); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c new file mode 100644 index 000000000000..8b7a3cf37d2b --- /dev/null +++ b/arch/x86/kernel/kvm.c @@ -0,0 +1,248 @@ +/* + * KVM paravirt_ops implementation + * + * 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, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright (C) 2007, Red Hat, Inc., Ingo Molnar <mingo@redhat.com> + * Copyright IBM Corporation, 2007 + * Authors: Anthony Liguori <aliguori@us.ibm.com> + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/kvm_para.h> +#include <linux/cpu.h> +#include <linux/mm.h> +#include <linux/highmem.h> +#include <linux/hardirq.h> + +#define MMU_QUEUE_SIZE 1024 + +struct kvm_para_state { + u8 mmu_queue[MMU_QUEUE_SIZE]; + int mmu_queue_len; + enum paravirt_lazy_mode mode; +}; + +static DEFINE_PER_CPU(struct kvm_para_state, para_state); + +static struct kvm_para_state *kvm_para_state(void) +{ + return &per_cpu(para_state, raw_smp_processor_id()); +} + +/* + * No need for any "IO delay" on KVM + */ +static void kvm_io_delay(void) +{ +} + +static void kvm_mmu_op(void *buffer, unsigned len) +{ + int r; + unsigned long a1, a2; + + do { + a1 = __pa(buffer); + a2 = 0; /* on i386 __pa() always returns <4G */ + r = kvm_hypercall3(KVM_HC_MMU_OP, len, a1, a2); + buffer += r; + len -= r; + } while (len); +} + +static void mmu_queue_flush(struct kvm_para_state *state) +{ + if (state->mmu_queue_len) { + kvm_mmu_op(state->mmu_queue, state->mmu_queue_len); + state->mmu_queue_len = 0; + } +} + +static void kvm_deferred_mmu_op(void *buffer, int len) +{ + struct kvm_para_state *state = kvm_para_state(); + + if (state->mode != PARAVIRT_LAZY_MMU) { + kvm_mmu_op(buffer, len); + return; + } + if (state->mmu_queue_len + len > sizeof state->mmu_queue) + mmu_queue_flush(state); + memcpy(state->mmu_queue + state->mmu_queue_len, buffer, len); + state->mmu_queue_len += len; +} + +static void kvm_mmu_write(void *dest, u64 val) +{ + __u64 pte_phys; + struct kvm_mmu_op_write_pte wpte; + +#ifdef CONFIG_HIGHPTE + struct page *page; + unsigned long dst = (unsigned long) dest; + + page = kmap_atomic_to_page(dest); + pte_phys = page_to_pfn(page); + pte_phys <<= PAGE_SHIFT; + pte_phys += (dst & ~(PAGE_MASK)); +#else + pte_phys = (unsigned long)__pa(dest); +#endif + wpte.header.op = KVM_MMU_OP_WRITE_PTE; + wpte.pte_val = val; + wpte.pte_phys = pte_phys; + + kvm_deferred_mmu_op(&wpte, sizeof wpte); +} + +/* + * We only need to hook operations that are MMU writes. We hook these so that + * we can use lazy MMU mode to batch these operations. We could probably + * improve the performance of the host code if we used some of the information + * here to simplify processing of batched writes. + */ +static void kvm_set_pte(pte_t *ptep, pte_t pte) +{ + kvm_mmu_write(ptep, pte_val(pte)); +} + +static void kvm_set_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ + kvm_mmu_write(ptep, pte_val(pte)); +} + +static void kvm_set_pmd(pmd_t *pmdp, pmd_t pmd) +{ + kvm_mmu_write(pmdp, pmd_val(pmd)); +} + +#if PAGETABLE_LEVELS >= 3 +#ifdef CONFIG_X86_PAE +static void kvm_set_pte_atomic(pte_t *ptep, pte_t pte) +{ + kvm_mmu_write(ptep, pte_val(pte)); +} + +static void kvm_set_pte_present(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ + kvm_mmu_write(ptep, pte_val(pte)); +} + +static void kvm_pte_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + kvm_mmu_write(ptep, 0); +} + +static void kvm_pmd_clear(pmd_t *pmdp) +{ + kvm_mmu_write(pmdp, 0); +} +#endif + +static void kvm_set_pud(pud_t *pudp, pud_t pud) +{ + kvm_mmu_write(pudp, pud_val(pud)); +} + +#if PAGETABLE_LEVELS == 4 +static void kvm_set_pgd(pgd_t *pgdp, pgd_t pgd) +{ + kvm_mmu_write(pgdp, pgd_val(pgd)); +} +#endif +#endif /* PAGETABLE_LEVELS >= 3 */ + +static void kvm_flush_tlb(void) +{ + struct kvm_mmu_op_flush_tlb ftlb = { + .header.op = KVM_MMU_OP_FLUSH_TLB, + }; + + kvm_deferred_mmu_op(&ftlb, sizeof ftlb); +} + +static void kvm_release_pt(u32 pfn) +{ + struct kvm_mmu_op_release_pt rpt = { + .header.op = KVM_MMU_OP_RELEASE_PT, + .pt_phys = (u64)pfn << PAGE_SHIFT, + }; + + kvm_mmu_op(&rpt, sizeof rpt); +} + +static void kvm_enter_lazy_mmu(void) +{ + struct kvm_para_state *state = kvm_para_state(); + + paravirt_enter_lazy_mmu(); + state->mode = paravirt_get_lazy_mode(); +} + +static void kvm_leave_lazy_mmu(void) +{ + struct kvm_para_state *state = kvm_para_state(); + + mmu_queue_flush(state); + paravirt_leave_lazy(paravirt_get_lazy_mode()); + state->mode = paravirt_get_lazy_mode(); +} + +static void paravirt_ops_setup(void) +{ + pv_info.name = "KVM"; + pv_info.paravirt_enabled = 1; + + if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY)) + pv_cpu_ops.io_delay = kvm_io_delay; + + if (kvm_para_has_feature(KVM_FEATURE_MMU_OP)) { + pv_mmu_ops.set_pte = kvm_set_pte; + pv_mmu_ops.set_pte_at = kvm_set_pte_at; + pv_mmu_ops.set_pmd = kvm_set_pmd; +#if PAGETABLE_LEVELS >= 3 +#ifdef CONFIG_X86_PAE + pv_mmu_ops.set_pte_atomic = kvm_set_pte_atomic; + pv_mmu_ops.set_pte_present = kvm_set_pte_present; + pv_mmu_ops.pte_clear = kvm_pte_clear; + pv_mmu_ops.pmd_clear = kvm_pmd_clear; +#endif + pv_mmu_ops.set_pud = kvm_set_pud; +#if PAGETABLE_LEVELS == 4 + pv_mmu_ops.set_pgd = kvm_set_pgd; +#endif +#endif + pv_mmu_ops.flush_tlb_user = kvm_flush_tlb; + pv_mmu_ops.release_pte = kvm_release_pt; + pv_mmu_ops.release_pmd = kvm_release_pt; + pv_mmu_ops.release_pud = kvm_release_pt; + + pv_mmu_ops.lazy_mode.enter = kvm_enter_lazy_mmu; + pv_mmu_ops.lazy_mode.leave = kvm_leave_lazy_mmu; + } +} + +void __init kvm_guest_init(void) +{ + if (!kvm_para_available()) + return; + + paravirt_ops_setup(); +} diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c new file mode 100644 index 000000000000..ddee04043aeb --- /dev/null +++ b/arch/x86/kernel/kvmclock.c @@ -0,0 +1,187 @@ +/* KVM paravirtual clock driver. A clocksource implementation + Copyright (C) 2008 Glauber de Oliveira Costa, Red Hat Inc. + + 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/clocksource.h> +#include <linux/kvm_para.h> +#include <asm/arch_hooks.h> +#include <asm/msr.h> +#include <asm/apic.h> +#include <linux/percpu.h> +#include <asm/reboot.h> + +#define KVM_SCALE 22 + +static int kvmclock = 1; + +static int parse_no_kvmclock(char *arg) +{ + kvmclock = 0; + return 0; +} +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 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 + * that with system time + */ +unsigned long kvm_get_wallclock(void) +{ + u32 wc_sec, wc_nsec; + u64 delta; + struct timespec ts; + int version, nsec; + int low, high; + + low = (int)__pa(&wall_clock); + high = ((u64)__pa(&wall_clock) >> 32); + + delta = kvm_clock_read(); + + 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; +} + +int kvm_set_wallclock(unsigned long now) +{ + return 0; +} + +/* + * 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; + + 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; +} +static struct clocksource kvm_clock = { + .name = "kvm-clock", + .read = kvm_clock_read, + .rating = 400, + .mask = CLOCKSOURCE_MASK(64), + .mult = 1 << KVM_SCALE, + .shift = KVM_SCALE, + .flags = CLOCK_SOURCE_IS_CONTINUOUS, +}; + +static int kvm_register_clock(void) +{ + 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); + + return native_write_msr_safe(MSR_KVM_SYSTEM_TIME, low, high); +} + +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()); + /* ok, done with our trickery, call native */ + setup_secondary_APIC_clock(); +} + +/* + * After the clock is registered, the host will keep writing to the + * registered memory location. If the guest happens to shutdown, this memory + * won't be valid. In cases like kexec, in which you install a new kernel, this + * means a random memory location will be kept being written. So before any + * kind of shutdown from our side, we unregister the clock by writting anything + * that does not have the 'enable' bit set in the msr + */ +#ifdef CONFIG_KEXEC +static void kvm_crash_shutdown(struct pt_regs *regs) +{ + native_write_msr_safe(MSR_KVM_SYSTEM_TIME, 0, 0); + native_machine_crash_shutdown(regs); +} +#endif + +static void kvm_shutdown(void) +{ + native_write_msr_safe(MSR_KVM_SYSTEM_TIME, 0, 0); + native_machine_shutdown(); +} + +void __init kvmclock_init(void) +{ + if (!kvm_para_available()) + return; + + if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) { + if (kvm_register_clock()) + return; + pv_time_ops.get_wallclock = kvm_get_wallclock; + pv_time_ops.set_wallclock = kvm_set_wallclock; + pv_time_ops.sched_clock = kvm_clock_read; + pv_apic_ops.setup_secondary_clock = kvm_setup_secondary_clock; + machine_ops.shutdown = kvm_shutdown; +#ifdef CONFIG_KEXEC + machine_ops.crash_shutdown = kvm_crash_shutdown; +#endif + clocksource_register(&kvm_clock); + } +} diff --git a/arch/x86/kernel/mca_32.c b/arch/x86/kernel/mca_32.c index 9482033ed0fe..2dc183758be3 100644 --- a/arch/x86/kernel/mca_32.c +++ b/arch/x86/kernel/mca_32.c @@ -53,9 +53,9 @@ #include <linux/init.h> #include <asm/arch_hooks.h> -static unsigned char which_scsi = 0; +static unsigned char which_scsi; -int MCA_bus = 0; +int MCA_bus; EXPORT_SYMBOL(MCA_bus); /* @@ -68,15 +68,17 @@ static DEFINE_SPINLOCK(mca_lock); /* Build the status info for the adapter */ -static void mca_configure_adapter_status(struct mca_device *mca_dev) { +static void mca_configure_adapter_status(struct mca_device *mca_dev) +{ mca_dev->status = MCA_ADAPTER_NONE; mca_dev->pos_id = mca_dev->pos[0] + (mca_dev->pos[1] << 8); - if(!mca_dev->pos_id && mca_dev->slot < MCA_MAX_SLOT_NR) { + if (!mca_dev->pos_id && mca_dev->slot < MCA_MAX_SLOT_NR) { - /* id = 0x0000 usually indicates hardware failure, + /* + * id = 0x0000 usually indicates hardware failure, * however, ZP Gu (zpg@castle.net> reports that his 9556 * has 0x0000 as id and everything still works. There * also seem to be an adapter with id = 0x0000; the @@ -87,9 +89,10 @@ static void mca_configure_adapter_status(struct mca_device *mca_dev) { mca_dev->status = MCA_ADAPTER_ERROR; return; - } else if(mca_dev->pos_id != 0xffff) { + } else if (mca_dev->pos_id != 0xffff) { - /* 0xffff usually indicates that there's no adapter, + /* + * 0xffff usually indicates that there's no adapter, * however, some integrated adapters may have 0xffff as * their id and still be valid. Examples are on-board * VGA of the 55sx, the integrated SCSI of the 56 & 57, @@ -99,19 +102,19 @@ static void mca_configure_adapter_status(struct mca_device *mca_dev) { mca_dev->status = MCA_ADAPTER_NORMAL; } - if((mca_dev->pos_id == 0xffff || + if ((mca_dev->pos_id == 0xffff || mca_dev->pos_id == 0x0000) && mca_dev->slot >= MCA_MAX_SLOT_NR) { int j; - for(j = 2; j < 8; j++) { - if(mca_dev->pos[j] != 0xff) { + for (j = 2; j < 8; j++) { + if (mca_dev->pos[j] != 0xff) { mca_dev->status = MCA_ADAPTER_NORMAL; break; } } } - if(!(mca_dev->pos[2] & MCA_ENABLED)) { + if (!(mca_dev->pos[2] & MCA_ENABLED)) { /* enabled bit is in POS 2 */ @@ -133,7 +136,7 @@ static struct resource mca_standard_resources[] = { #define MCA_STANDARD_RESOURCES ARRAY_SIZE(mca_standard_resources) -/** +/* * mca_read_and_store_pos - read the POS registers into a memory buffer * @pos: a char pointer to 8 bytes, contains the POS register value on * successful return @@ -141,12 +144,14 @@ static struct resource mca_standard_resources[] = { * Returns 1 if a card actually exists (i.e. the pos isn't * all 0xff) or 0 otherwise */ -static int mca_read_and_store_pos(unsigned char *pos) { +static int mca_read_and_store_pos(unsigned char *pos) +{ int j; int found = 0; - for(j=0; j<8; j++) { - if((pos[j] = inb_p(MCA_POS_REG(j))) != 0xff) { + for (j = 0; j < 8; j++) { + pos[j] = inb_p(MCA_POS_REG(j)); + if (pos[j] != 0xff) { /* 0xff all across means no device. 0x00 means * something's broken, but a device is * probably there. However, if you get 0x00 @@ -167,11 +172,11 @@ static unsigned char mca_pc_read_pos(struct mca_device *mca_dev, int reg) unsigned char byte; unsigned long flags; - if(reg < 0 || reg >= 8) + if (reg < 0 || reg >= 8) return 0; spin_lock_irqsave(&mca_lock, flags); - if(mca_dev->pos_register) { + if (mca_dev->pos_register) { /* Disable adapter setup, enable motherboard setup */ outb_p(0, MCA_ADAPTER_SETUP_REG); @@ -203,7 +208,7 @@ static void mca_pc_write_pos(struct mca_device *mca_dev, int reg, { unsigned long flags; - if(reg < 0 || reg >= 8) + if (reg < 0 || reg >= 8) return; spin_lock_irqsave(&mca_lock, flags); @@ -227,17 +232,17 @@ static void mca_pc_write_pos(struct mca_device *mca_dev, int reg, } /* for the primary MCA bus, we have identity transforms */ -static int mca_dummy_transform_irq(struct mca_device * mca_dev, int irq) +static int mca_dummy_transform_irq(struct mca_device *mca_dev, int irq) { return irq; } -static int mca_dummy_transform_ioport(struct mca_device * mca_dev, int port) +static int mca_dummy_transform_ioport(struct mca_device *mca_dev, int port) { return port; } -static void *mca_dummy_transform_memory(struct mca_device * mca_dev, void *mem) +static void *mca_dummy_transform_memory(struct mca_device *mca_dev, void *mem) { return mem; } @@ -251,7 +256,8 @@ static int __init mca_init(void) short mca_builtin_scsi_ports[] = {0xf7, 0xfd, 0x00}; struct mca_bus *bus; - /* WARNING: Be careful when making changes here. Putting an adapter + /* + * WARNING: Be careful when making changes here. Putting an adapter * and the motherboard simultaneously into setup mode may result in * damage to chips (according to The Indispensible PC Hardware Book * by Hans-Peter Messmer). Also, we disable system interrupts (so @@ -283,7 +289,7 @@ static int __init mca_init(void) /* get the motherboard device */ mca_dev = kzalloc(sizeof(struct mca_device), GFP_KERNEL); - if(unlikely(!mca_dev)) + if (unlikely(!mca_dev)) goto out_nomem; /* @@ -309,7 +315,7 @@ static int __init mca_init(void) mca_register_device(MCA_PRIMARY_BUS, mca_dev); mca_dev = kzalloc(sizeof(struct mca_device), GFP_ATOMIC); - if(unlikely(!mca_dev)) + if (unlikely(!mca_dev)) goto out_unlock_nomem; /* Put motherboard into video setup mode, read integrated video @@ -326,7 +332,8 @@ static int __init mca_init(void) mca_dev->slot = MCA_INTEGVIDEO; mca_register_device(MCA_PRIMARY_BUS, mca_dev); - /* Put motherboard into scsi setup mode, read integrated scsi + /* + * Put motherboard into scsi setup mode, read integrated scsi * POS registers, and turn motherboard setup off. * * It seems there are two possible SCSI registers. Martin says that @@ -338,18 +345,18 @@ static int __init mca_init(void) * machine. */ - for(i = 0; (which_scsi = mca_builtin_scsi_ports[i]) != 0; i++) { + for (i = 0; (which_scsi = mca_builtin_scsi_ports[i]) != 0; i++) { outb_p(which_scsi, MCA_MOTHERBOARD_SETUP_REG); - if(mca_read_and_store_pos(pos)) + if (mca_read_and_store_pos(pos)) break; } - if(which_scsi) { + if (which_scsi) { /* found a scsi card */ mca_dev = kzalloc(sizeof(struct mca_device), GFP_ATOMIC); - if(unlikely(!mca_dev)) + if (unlikely(!mca_dev)) goto out_unlock_nomem; - for(j = 0; j < 8; j++) + for (j = 0; j < 8; j++) mca_dev->pos[j] = pos[j]; mca_configure_adapter_status(mca_dev); @@ -364,21 +371,22 @@ static int __init mca_init(void) outb_p(0xff, MCA_MOTHERBOARD_SETUP_REG); - /* Now loop over MCA slots: put each adapter into setup mode, and + /* + * Now loop over MCA slots: put each adapter into setup mode, and * read its POS registers. Then put adapter setup off. */ - for(i=0; i<MCA_MAX_SLOT_NR; i++) { + for (i = 0; i < MCA_MAX_SLOT_NR; i++) { outb_p(0x8|(i&0xf), MCA_ADAPTER_SETUP_REG); - if(!mca_read_and_store_pos(pos)) + if (!mca_read_and_store_pos(pos)) continue; mca_dev = kzalloc(sizeof(struct mca_device), GFP_ATOMIC); - if(unlikely(!mca_dev)) + if (unlikely(!mca_dev)) goto out_unlock_nomem; - for(j=0; j<8; j++) - mca_dev->pos[j]=pos[j]; + for (j = 0; j < 8; j++) + mca_dev->pos[j] = pos[j]; mca_dev->driver_loaded = 0; mca_dev->slot = i; @@ -414,20 +422,20 @@ mca_handle_nmi_device(struct mca_device *mca_dev, int check_flag) { int slot = mca_dev->slot; - if(slot == MCA_INTEGSCSI) { + if (slot == MCA_INTEGSCSI) { printk(KERN_CRIT "NMI: caused by MCA integrated SCSI adapter (%s)\n", mca_dev->name); - } else if(slot == MCA_INTEGVIDEO) { + } else if (slot == MCA_INTEGVIDEO) { printk(KERN_CRIT "NMI: caused by MCA integrated video adapter (%s)\n", mca_dev->name); - } else if(slot == MCA_MOTHERBOARD) { + } else if (slot == MCA_MOTHERBOARD) { printk(KERN_CRIT "NMI: caused by motherboard (%s)\n", mca_dev->name); } /* More info available in POS 6 and 7? */ - if(check_flag) { + if (check_flag) { unsigned char pos6, pos7; pos6 = mca_device_read_pos(mca_dev, 6); @@ -447,8 +455,9 @@ static int __kprobes mca_handle_nmi_callback(struct device *dev, void *data) pos5 = mca_device_read_pos(mca_dev, 5); - if(!(pos5 & 0x80)) { - /* Bit 7 of POS 5 is reset when this adapter has a hardware + if (!(pos5 & 0x80)) { + /* + * Bit 7 of POS 5 is reset when this adapter has a hardware * error. Bit 7 it reset if there's error information * available in POS 6 and 7. */ @@ -460,7 +469,8 @@ static int __kprobes mca_handle_nmi_callback(struct device *dev, void *data) void __kprobes mca_handle_nmi(void) { - /* First try - scan the various adapters and see if a specific + /* + * First try - scan the various adapters and see if a specific * adapter was responsible for the error. */ bus_for_each_dev(&mca_bus_type, NULL, NULL, mca_handle_nmi_callback); diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c index b402c0f3f192..3cad17fe026b 100644 --- a/arch/x86/kernel/mfgpt_32.c +++ b/arch/x86/kernel/mfgpt_32.c @@ -63,7 +63,7 @@ static int __init mfgpt_fix(char *s) /* The following udocumented bit resets the MFGPT timers */ val = 0xFF; dummy = 0; - wrmsr(0x5140002B, val, dummy); + wrmsr(MSR_MFGPT_SETUP, val, dummy); return 1; } __setup("mfgptfix", mfgpt_fix); @@ -127,17 +127,17 @@ int geode_mfgpt_toggle_event(int timer, int cmp, int event, int enable) * 6; that is, resets for 7 and 8 will be ignored. Is this * a problem? -dilinger */ - msr = MFGPT_NR_MSR; + msr = MSR_MFGPT_NR; mask = 1 << (timer + 24); break; case MFGPT_EVENT_NMI: - msr = MFGPT_NR_MSR; + msr = MSR_MFGPT_NR; mask = 1 << (timer + shift); break; case MFGPT_EVENT_IRQ: - msr = MFGPT_IRQ_MSR; + msr = MSR_MFGPT_IRQ; mask = 1 << (timer + shift); break; @@ -364,7 +364,8 @@ int __init mfgpt_timer_setup(void) geode_mfgpt_write(mfgpt_event_clock, MFGPT_REG_SETUP, val); /* Set up the clock event */ - mfgpt_clockevent.mult = div_sc(MFGPT_HZ, NSEC_PER_SEC, 32); + mfgpt_clockevent.mult = div_sc(MFGPT_HZ, NSEC_PER_SEC, + mfgpt_clockevent.shift); mfgpt_clockevent.min_delta_ns = clockevent_delta2ns(0xF, &mfgpt_clockevent); mfgpt_clockevent.max_delta_ns = clockevent_delta2ns(0xFFFE, diff --git a/arch/x86/kernel/microcode.c b/arch/x86/kernel/microcode.c index f2702d01b8a8..69729e38b78a 100644 --- a/arch/x86/kernel/microcode.c +++ b/arch/x86/kernel/microcode.c @@ -290,7 +290,7 @@ static int get_maching_microcode(void *mc, int cpu) } return 0; find: - pr_debug("microcode: CPU %d found a matching microcode update with" + pr_debug("microcode: CPU%d found a matching microcode update with" " version 0x%x (current=0x%x)\n", cpu, mc_header->rev,uci->rev); new_mc = vmalloc(total_size); if (!new_mc) { @@ -336,11 +336,11 @@ static void apply_microcode(int cpu) spin_unlock_irqrestore(µcode_update_lock, flags); if (val[1] != uci->mc->hdr.rev) { - printk(KERN_ERR "microcode: CPU%d updated from revision " + printk(KERN_ERR "microcode: CPU%d update from revision " "0x%x to 0x%x failed\n", cpu_num, uci->rev, val[1]); return; } - pr_debug("microcode: CPU%d updated from revision " + printk(KERN_INFO "microcode: CPU%d updated from revision " "0x%x to 0x%x, date = %08x \n", cpu_num, uci->rev, val[1], uci->mc->hdr.date); uci->rev = val[1]; @@ -402,7 +402,7 @@ static int do_microcode_update (void) if (!uci->valid) continue; - set_cpus_allowed(current, cpumask_of_cpu(cpu)); + set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); error = get_maching_microcode(new_mc, cpu); if (error < 0) goto out; @@ -416,7 +416,7 @@ out: vfree(new_mc); if (cursor < 0) error = cursor; - set_cpus_allowed(current, old); + set_cpus_allowed_ptr(current, &old); return error; } @@ -534,7 +534,7 @@ 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("ucode data file %s load failed\n", name); + pr_debug("microcode: ucode data file %s load failed\n", name); return error; } buf = firmware->data; @@ -579,7 +579,7 @@ static int apply_microcode_check_cpu(int cpu) return 0; old = current->cpus_allowed; - set_cpus_allowed(current, cpumask_of_cpu(cpu)); + set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); /* Check if the microcode we have in memory matches the CPU */ if (c->x86_vendor != X86_VENDOR_INTEL || c->x86 < 6 || @@ -610,7 +610,7 @@ static int apply_microcode_check_cpu(int cpu) " sig=0x%x, pf=0x%x, rev=0x%x\n", cpu, uci->sig, uci->pf, uci->rev); - set_cpus_allowed(current, old); + set_cpus_allowed_ptr(current, &old); return err; } @@ -621,13 +621,13 @@ static void microcode_init_cpu(int cpu, int resume) old = current->cpus_allowed; - set_cpus_allowed(current, cpumask_of_cpu(cpu)); + set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); mutex_lock(µcode_mutex); collect_cpu_info(cpu); if (uci->valid && system_state == SYSTEM_RUNNING && !resume) cpu_request_microcode(cpu); mutex_unlock(µcode_mutex); - set_cpus_allowed(current, old); + set_cpus_allowed_ptr(current, &old); } static void microcode_fini_cpu(int cpu) @@ -657,14 +657,14 @@ static ssize_t reload_store(struct sys_device *dev, const char *buf, size_t sz) old = current->cpus_allowed; get_online_cpus(); - set_cpus_allowed(current, cpumask_of_cpu(cpu)); + set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); mutex_lock(µcode_mutex); if (uci->valid) err = cpu_request_microcode(cpu); mutex_unlock(µcode_mutex); put_online_cpus(); - set_cpus_allowed(current, old); + set_cpus_allowed_ptr(current, &old); } if (err) return err; @@ -709,7 +709,7 @@ static int __mc_sysdev_add(struct sys_device *sys_dev, int resume) if (!cpu_online(cpu)) return 0; - pr_debug("Microcode:CPU %d added\n", cpu); + pr_debug("microcode: CPU%d added\n", cpu); memset(uci, 0, sizeof(*uci)); err = sysfs_create_group(&sys_dev->kobj, &mc_attr_group); @@ -733,7 +733,7 @@ static int mc_sysdev_remove(struct sys_device *sys_dev) if (!cpu_online(cpu)) return 0; - pr_debug("Microcode:CPU %d removed\n", cpu); + pr_debug("microcode: CPU%d removed\n", cpu); microcode_fini_cpu(cpu); sysfs_remove_group(&sys_dev->kobj, &mc_attr_group); return 0; @@ -745,7 +745,7 @@ static int mc_sysdev_resume(struct sys_device *dev) if (!cpu_online(cpu)) return 0; - pr_debug("Microcode:CPU %d resumed\n", cpu); + pr_debug("microcode: CPU%d resumed\n", cpu); /* only CPU 0 will apply ucode here */ apply_microcode(0); return 0; @@ -783,7 +783,7 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) } case CPU_DOWN_FAILED_FROZEN: if (sysfs_create_group(&sys_dev->kobj, &mc_attr_group)) - printk(KERN_ERR "Microcode: Failed to create the sysfs " + printk(KERN_ERR "microcode: Failed to create the sysfs " "group for CPU%d\n", cpu); break; case CPU_DOWN_PREPARE: diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c new file mode 100644 index 000000000000..edc5fbfe85c0 --- /dev/null +++ b/arch/x86/kernel/mmconf-fam10h_64.c @@ -0,0 +1,243 @@ +/* + * AMD Family 10h mmconfig enablement + */ + +#include <linux/types.h> +#include <linux/mm.h> +#include <linux/string.h> +#include <linux/pci.h> +#include <linux/dmi.h> +#include <asm/pci-direct.h> +#include <linux/sort.h> +#include <asm/io.h> +#include <asm/msr.h> +#include <asm/acpi.h> + +#include "../pci/pci.h" + +struct pci_hostbridge_probe { + u32 bus; + u32 slot; + u32 vendor; + u32 device; +}; + +static u64 __cpuinitdata fam10h_pci_mmconf_base; +static int __cpuinitdata fam10h_pci_mmconf_base_status; + +static struct pci_hostbridge_probe pci_probes[] __cpuinitdata = { + { 0, 0x18, PCI_VENDOR_ID_AMD, 0x1200 }, + { 0xff, 0, PCI_VENDOR_ID_AMD, 0x1200 }, +}; + +struct range { + u64 start; + u64 end; +}; + +static int __cpuinit cmp_range(const void *x1, const void *x2) +{ + const struct range *r1 = x1; + const struct range *r2 = x2; + int start1, start2; + + start1 = r1->start >> 32; + start2 = r2->start >> 32; + + return start1 - start2; +} + +/*[47:0] */ +/* need to avoid (0xfd<<32) and (0xfe<<32), ht used space */ +#define FAM10H_PCI_MMCONF_BASE (0xfcULL<<32) +#define BASE_VALID(b) ((b != (0xfdULL << 32)) && (b != (0xfeULL << 32))) +static void __cpuinit get_fam10h_pci_mmconf_base(void) +{ + int i; + unsigned bus; + unsigned slot; + int found; + + u64 val; + u32 address; + u64 tom2; + u64 base = FAM10H_PCI_MMCONF_BASE; + + int hi_mmio_num; + struct range range[8]; + + /* only try to get setting from BSP */ + /* -1 or 1 */ + if (fam10h_pci_mmconf_base_status) + return; + + if (!early_pci_allowed()) + goto fail; + + found = 0; + for (i = 0; i < ARRAY_SIZE(pci_probes); i++) { + u32 id; + u16 device; + u16 vendor; + + bus = pci_probes[i].bus; + slot = pci_probes[i].slot; + id = read_pci_config(bus, slot, 0, PCI_VENDOR_ID); + + vendor = id & 0xffff; + device = (id>>16) & 0xffff; + if (pci_probes[i].vendor == vendor && + pci_probes[i].device == device) { + found = 1; + break; + } + } + + if (!found) + goto fail; + + /* SYS_CFG */ + address = MSR_K8_SYSCFG; + rdmsrl(address, val); + + /* TOP_MEM2 is not enabled? */ + if (!(val & (1<<21))) { + tom2 = 0; + } else { + /* TOP_MEM2 */ + address = MSR_K8_TOP_MEM2; + rdmsrl(address, val); + tom2 = val & (0xffffULL<<32); + } + + if (base <= tom2) + base = tom2 + (1ULL<<32); + + /* + * need to check if the range is in the high mmio range that is + * above 4G + */ + hi_mmio_num = 0; + for (i = 0; i < 8; i++) { + u32 reg; + u64 start; + u64 end; + reg = read_pci_config(bus, slot, 1, 0x80 + (i << 3)); + if (!(reg & 3)) + continue; + + start = (((u64)reg) << 8) & (0xffULL << 32); /* 39:16 on 31:8*/ + reg = read_pci_config(bus, slot, 1, 0x84 + (i << 3)); + end = (((u64)reg) << 8) & (0xffULL << 32); /* 39:16 on 31:8*/ + + if (!end) + continue; + + range[hi_mmio_num].start = start; + range[hi_mmio_num].end = end; + hi_mmio_num++; + } + + if (!hi_mmio_num) + goto out; + + /* sort the range */ + sort(range, hi_mmio_num, sizeof(struct range), cmp_range, NULL); + + if (range[hi_mmio_num - 1].end < base) + goto out; + if (range[0].start > base) + goto out; + + /* need to find one window */ + base = range[0].start - (1ULL << 32); + if ((base > tom2) && BASE_VALID(base)) + goto out; + base = range[hi_mmio_num - 1].end + (1ULL << 32); + if ((base > tom2) && BASE_VALID(base)) + goto out; + /* need to find window between ranges */ + if (hi_mmio_num > 1) + for (i = 0; i < hi_mmio_num - 1; i++) { + if (range[i + 1].start > (range[i].end + (1ULL << 32))) { + base = range[i].end + (1ULL << 32); + if ((base > tom2) && BASE_VALID(base)) + goto out; + } + } + +fail: + fam10h_pci_mmconf_base_status = -1; + return; +out: + fam10h_pci_mmconf_base = base; + fam10h_pci_mmconf_base_status = 1; +} + +void __cpuinit fam10h_check_enable_mmcfg(void) +{ + u64 val; + u32 address; + + if (!(pci_probe & PCI_CHECK_ENABLE_AMD_MMCONF)) + return; + + address = MSR_FAM10H_MMIO_CONF_BASE; + rdmsrl(address, val); + + /* try to make sure that AP's setting is identical to BSP setting */ + if (val & FAM10H_MMIO_CONF_ENABLE) { + unsigned busnbits; + busnbits = (val >> FAM10H_MMIO_CONF_BUSRANGE_SHIFT) & + FAM10H_MMIO_CONF_BUSRANGE_MASK; + + /* only trust the one handle 256 buses, if acpi=off */ + if (!acpi_pci_disabled || busnbits >= 8) { + u64 base; + base = val & (0xffffULL << 32); + if (fam10h_pci_mmconf_base_status <= 0) { + fam10h_pci_mmconf_base = base; + fam10h_pci_mmconf_base_status = 1; + return; + } else if (fam10h_pci_mmconf_base == base) + return; + } + } + + /* + * if it is not enabled, try to enable it and assume only one segment + * with 256 buses + */ + get_fam10h_pci_mmconf_base(); + if (fam10h_pci_mmconf_base_status <= 0) + return; + + printk(KERN_INFO "Enable MMCONFIG on AMD Family 10h\n"); + val &= ~((FAM10H_MMIO_CONF_BASE_MASK<<FAM10H_MMIO_CONF_BASE_SHIFT) | + (FAM10H_MMIO_CONF_BUSRANGE_MASK<<FAM10H_MMIO_CONF_BUSRANGE_SHIFT)); + val |= fam10h_pci_mmconf_base | (8 << FAM10H_MMIO_CONF_BUSRANGE_SHIFT) | + FAM10H_MMIO_CONF_ENABLE; + wrmsrl(address, val); +} + +static int __devinit set_check_enable_amd_mmconf(const struct dmi_system_id *d) +{ + pci_probe |= PCI_CHECK_ENABLE_AMD_MMCONF; + return 0; +} + +static struct dmi_system_id __devinitdata mmconf_dmi_table[] = { + { + .callback = set_check_enable_amd_mmconf, + .ident = "Sun Microsystems Machine", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Sun Microsystems"), + }, + }, + {} +}; + +void __init check_enable_amd_mmconf_dmi(void) +{ + dmi_check_system(mmconf_dmi_table); +} diff --git a/arch/x86/kernel/mpparse_32.c b/arch/x86/kernel/mpparse.c index f349e68e45a0..3e2c54dc8b29 100644 --- a/arch/x86/kernel/mpparse_32.c +++ b/arch/x86/kernel/mpparse.c @@ -4,82 +4,56 @@ * * (c) 1995 Alan Cox, Building #3 <alan@redhat.com> * (c) 1998, 1999, 2000 Ingo Molnar <mingo@redhat.com> - * - * Fixes - * Erich Boleyn : MP v1.4 and additional changes. - * Alan Cox : Added EBDA scanning - * Ingo Molnar : various cleanups and rewrites - * Maciej W. Rozycki: Bits for default MP configurations - * Paul Diefenbaugh: Added full ACPI support + * (c) 2008 Alexey Starikovskiy <astarikovskiy@suse.de> */ #include <linux/mm.h> #include <linux/init.h> -#include <linux/acpi.h> #include <linux/delay.h> #include <linux/bootmem.h> #include <linux/kernel_stat.h> #include <linux/mc146818rtc.h> #include <linux/bitops.h> +#include <linux/acpi.h> +#include <linux/module.h> #include <asm/smp.h> -#include <asm/acpi.h> #include <asm/mtrr.h> #include <asm/mpspec.h> +#include <asm/pgalloc.h> #include <asm/io_apic.h> +#include <asm/proto.h> +#include <asm/acpi.h> +#include <asm/bios_ebda.h> #include <mach_apic.h> +#ifdef CONFIG_X86_32 #include <mach_apicdef.h> #include <mach_mpparse.h> -#include <bios_ebda.h> +#endif /* Have we found an MP table */ int smp_found_config; -unsigned int __cpuinitdata maxcpus = NR_CPUS; /* * Various Linux-internal data structures created from the * MP-table. */ -int apic_version [MAX_APICS]; -int mp_bus_id_to_type [MAX_MP_BUSSES]; -int mp_bus_id_to_node [MAX_MP_BUSSES]; -int mp_bus_id_to_local [MAX_MP_BUSSES]; -int quad_local_to_mp_bus_id [NR_CPUS/4][4]; -int mp_bus_id_to_pci_bus [MAX_MP_BUSSES] = { [0 ... MAX_MP_BUSSES-1] = -1 }; -static int mp_current_pci_id; - -/* I/O APIC entries */ -struct mpc_config_ioapic mp_ioapics[MAX_IO_APICS]; - -/* # of MP IRQ source entries */ -struct mpc_config_intsrc mp_irqs[MAX_IRQ_SOURCES]; +#if defined (CONFIG_MCA) || defined (CONFIG_EISA) +int mp_bus_id_to_type[MAX_MP_BUSSES]; +#endif -/* MP IRQ source entries */ -int mp_irq_entries; +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 }; -int nr_ioapics; +static int mp_current_pci_id; int pic_mode; -unsigned long mp_lapic_addr; - -unsigned int def_to_bigsmp = 0; - -/* Processor that is doing the boot up */ -unsigned int boot_cpu_physical_apicid = -1U; -/* Internal processor count */ -unsigned int num_processors; - -/* Bitmask of physically existing CPUs */ -physid_mask_t phys_cpu_present_map; - -u8 bios_cpu_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID }; /* * Intel MP BIOS table parsing routines: */ - /* * Checksum an MP configuration block. */ @@ -94,216 +68,153 @@ static int __init mpf_checksum(unsigned char *mp, int len) return sum & 0xFF; } +#ifdef CONFIG_X86_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 .... */ -static int mpc_record; -static struct mpc_config_translation *translation_table[MAX_MPC_ENTRY] __cpuinitdata; +static int mpc_record; +static struct mpc_config_translation *translation_table[MAX_MPC_ENTRY] + __cpuinitdata; +#endif -static void __cpuinit MP_processor_info (struct mpc_config_processor *m) +static void __cpuinit MP_processor_info(struct mpc_config_processor *m) { - int ver, apicid; - physid_mask_t phys_cpu; - - if (!(m->mpc_cpuflag & CPU_ENABLED)) - return; + int apicid; + char *bootup_cpu = ""; + if (!(m->mpc_cpuflag & CPU_ENABLED)) { + disabled_cpus++; + return; + } +#ifdef CONFIG_X86_NUMAQ apicid = mpc_apic_id(m, translation_table[mpc_record]); - - if (m->mpc_featureflag&(1<<0)) - Dprintk(" Floating point unit present.\n"); - if (m->mpc_featureflag&(1<<7)) - Dprintk(" Machine Exception supported.\n"); - if (m->mpc_featureflag&(1<<8)) - Dprintk(" 64 bit compare & exchange supported.\n"); - if (m->mpc_featureflag&(1<<9)) - Dprintk(" Internal APIC present.\n"); - if (m->mpc_featureflag&(1<<11)) - Dprintk(" SEP present.\n"); - if (m->mpc_featureflag&(1<<12)) - Dprintk(" MTRR present.\n"); - if (m->mpc_featureflag&(1<<13)) - Dprintk(" PGE present.\n"); - if (m->mpc_featureflag&(1<<14)) - Dprintk(" MCA present.\n"); - if (m->mpc_featureflag&(1<<15)) - Dprintk(" CMOV present.\n"); - if (m->mpc_featureflag&(1<<16)) - Dprintk(" PAT present.\n"); - if (m->mpc_featureflag&(1<<17)) - Dprintk(" PSE present.\n"); - if (m->mpc_featureflag&(1<<18)) - Dprintk(" PSN present.\n"); - if (m->mpc_featureflag&(1<<19)) - Dprintk(" Cache Line Flush Instruction present.\n"); - /* 20 Reserved */ - if (m->mpc_featureflag&(1<<21)) - Dprintk(" Debug Trace and EMON Store present.\n"); - if (m->mpc_featureflag&(1<<22)) - Dprintk(" ACPI Thermal Throttle Registers present.\n"); - if (m->mpc_featureflag&(1<<23)) - Dprintk(" MMX present.\n"); - if (m->mpc_featureflag&(1<<24)) - Dprintk(" FXSR present.\n"); - if (m->mpc_featureflag&(1<<25)) - Dprintk(" XMM present.\n"); - if (m->mpc_featureflag&(1<<26)) - Dprintk(" Willamette New Instructions present.\n"); - if (m->mpc_featureflag&(1<<27)) - Dprintk(" Self Snoop present.\n"); - if (m->mpc_featureflag&(1<<28)) - Dprintk(" HT present.\n"); - if (m->mpc_featureflag&(1<<29)) - Dprintk(" Thermal Monitor present.\n"); - /* 30, 31 Reserved */ - - +#else + apicid = m->mpc_apicid; +#endif if (m->mpc_cpuflag & CPU_BOOTPROCESSOR) { - Dprintk(" Bootup CPU\n"); + bootup_cpu = " (Bootup-CPU)"; boot_cpu_physical_apicid = m->mpc_apicid; } - ver = m->mpc_apicver; - - /* - * Validate version - */ - if (ver == 0x0) { - printk(KERN_WARNING "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; - - phys_cpu = apicid_to_cpu_present(apicid); - physids_or(phys_cpu_present_map, phys_cpu_present_map, phys_cpu); - - if (num_processors >= NR_CPUS) { - printk(KERN_WARNING "WARNING: NR_CPUS limit of %i reached." - " Processor ignored.\n", NR_CPUS); - return; - } - - if (num_processors >= maxcpus) { - printk(KERN_WARNING "WARNING: maxcpus limit of %i reached." - " Processor ignored.\n", maxcpus); - return; - } - - cpu_set(num_processors, cpu_possible_map); - num_processors++; - - /* - * Would be preferable to switch to bigsmp when CONFIG_HOTPLUG_CPU=y - * but we need to work other dependencies like SMP_SUSPEND etc - * before this can be done without some confusion. - * if (CPU_HOTPLUG_ENABLED || num_processors > 8) - * - Ashok Raj <ashok.raj@intel.com> - */ - if (num_processors > 8) { - switch (boot_cpu_data.x86_vendor) { - case X86_VENDOR_INTEL: - if (!APIC_XAPIC(ver)) { - def_to_bigsmp = 0; - break; - } - /* If P4 and above fall through */ - case X86_VENDOR_AMD: - def_to_bigsmp = 1; - } - } - bios_cpu_apicid[num_processors - 1] = m->mpc_apicid; + printk(KERN_INFO "Processor #%d%s\n", m->mpc_apicid, bootup_cpu); + generic_processor_info(apicid, m->mpc_apicver); } -static void __init MP_bus_info (struct mpc_config_bus *m) +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]); +#else + Dprintk("Bus #%d is %s\n", m->mpc_busid, str); +#endif #if MAX_MP_BUSSES < 256 if (m->mpc_busid >= MAX_MP_BUSSES) { printk(KERN_WARNING "MP table busid value (%d) for bustype %s " - " is too large, max. supported is %d\n", - m->mpc_busid, str, MAX_MP_BUSSES - 1); + " is too large, max. supported is %d\n", + m->mpc_busid, str, MAX_MP_BUSSES - 1); return; } #endif - if (strncmp(str, BUSTYPE_ISA, sizeof(BUSTYPE_ISA)-1) == 0) { + if (strncmp(str, BUSTYPE_ISA, sizeof(BUSTYPE_ISA) - 1) == 0) { + set_bit(m->mpc_busid, mp_bus_not_pci); +#if defined(CONFIG_EISA) || defined (CONFIG_MCA) mp_bus_id_to_type[m->mpc_busid] = MP_BUS_ISA; - } else if (strncmp(str, BUSTYPE_EISA, sizeof(BUSTYPE_EISA)-1) == 0) { - mp_bus_id_to_type[m->mpc_busid] = MP_BUS_EISA; - } else if (strncmp(str, BUSTYPE_PCI, sizeof(BUSTYPE_PCI)-1) == 0) { +#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]); - mp_bus_id_to_type[m->mpc_busid] = MP_BUS_PCI; +#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++; - } else if (strncmp(str, BUSTYPE_MCA, sizeof(BUSTYPE_MCA)-1) == 0) { +#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) { + mp_bus_id_to_type[m->mpc_busid] = MP_BUS_EISA; + } else if (strncmp(str, BUSTYPE_MCA, sizeof(BUSTYPE_MCA) - 1) == 0) { mp_bus_id_to_type[m->mpc_busid] = MP_BUS_MCA; - } else { +#endif + } else printk(KERN_WARNING "Unknown bustype %s - ignoring\n", str); +} + +#ifdef CONFIG_X86_IO_APIC + +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; } -static void __init MP_ioapic_info (struct mpc_config_ioapic *m) +static void __init MP_ioapic_info(struct mpc_config_ioapic *m) { if (!(m->mpc_flags & MPC_APIC_USABLE)) return; printk(KERN_INFO "I/O APIC #%d Version %d at 0x%X.\n", - m->mpc_apicid, m->mpc_apicver, m->mpc_apicaddr); - if (nr_ioapics >= MAX_IO_APICS) { - printk(KERN_CRIT "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 (!m->mpc_apicaddr) { - printk(KERN_ERR "WARNING: bogus zero I/O APIC address" - " found in MP table, skipping!\n"); + m->mpc_apicid, m->mpc_apicver, m->mpc_apicaddr); + + if (bad_ioapic(m->mpc_apicaddr)) return; - } + mp_ioapics[nr_ioapics] = *m; nr_ioapics++; } -static void __init MP_intsrc_info (struct mpc_config_intsrc *m) +static void __init MP_intsrc_info(struct mpc_config_intsrc *m) { - mp_irqs [mp_irq_entries] = *m; + mp_irqs[mp_irq_entries] = *m; Dprintk("Int: type %d, pol %d, trig %d, bus %d," " 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); + m->mpc_irqtype, m->mpc_irqflag & 3, + (m->mpc_irqflag >> 2) & 3, m->mpc_srcbus, + m->mpc_srcbusirq, m->mpc_dstapic, m->mpc_dstirq); if (++mp_irq_entries == MAX_IRQ_SOURCES) panic("Max # of irq sources exceeded!!\n"); } -static void __init MP_lintsrc_info (struct mpc_config_lintsrc *m) +#endif + +static void __init MP_lintsrc_info(struct mpc_config_lintsrc *m) { Dprintk("Lint: type %d, pol %d, trig %d, bus %d," " IRQ %02x, APIC ID %x, APIC LINT %02x\n", - m->mpc_irqtype, m->mpc_irqflag & 3, - (m->mpc_irqflag >> 2) &3, m->mpc_srcbusid, - m->mpc_srcbusirq, m->mpc_destapic, m->mpc_destapiclint); + m->mpc_irqtype, m->mpc_irqflag & 3, + (m->mpc_irqflag >> 2) & 3, m->mpc_srcbusid, + m->mpc_srcbusirq, m->mpc_destapic, m->mpc_destapiclint); } #ifdef CONFIG_X86_NUMAQ -static void __init MP_translation_info (struct mpc_config_translation *m) +static void __init MP_translation_info(struct mpc_config_translation *m) { - printk(KERN_INFO "Translation: record %d, type %d, quad %d, global %d, local %d\n", mpc_record, m->trans_type, m->trans_quad, m->trans_global, m->trans_local); + printk(KERN_INFO + "Translation: record %d, type %d, quad %d, global %d, local %d\n", + mpc_record, m->trans_type, m->trans_quad, m->trans_global, + m->trans_local); - if (mpc_record >= MAX_MPC_ENTRY) + if (mpc_record >= MAX_MPC_ENTRY) printk(KERN_ERR "MAX_MPC_ENTRY exceeded!\n"); else - translation_table[mpc_record] = m; /* stash this for later */ + translation_table[mpc_record] = m; /* stash this for later */ if (m->trans_quad < MAX_NUMNODES && !node_online(m->trans_quad)) node_set_online(m->trans_quad); } @@ -312,118 +223,124 @@ static void __init MP_translation_info (struct mpc_config_translation *m) * Read/parse the MPC oem tables */ -static void __init smp_read_mpc_oem(struct mp_config_oemtable *oemtable, \ - unsigned short oemsize) +static void __init smp_read_mpc_oem(struct mp_config_oemtable *oemtable, + unsigned short oemsize) { - int count = sizeof (*oemtable); /* the header size */ - unsigned char *oemptr = ((unsigned char *)oemtable)+count; - + int count = sizeof(*oemtable); /* the header size */ + unsigned char *oemptr = ((unsigned char *)oemtable) + count; + mpc_record = 0; - printk(KERN_INFO "Found an OEM MPC table at %8p - parsing it ... \n", oemtable); - if (memcmp(oemtable->oem_signature,MPC_OEM_SIGNATURE,4)) - { - printk(KERN_WARNING "SMP mpc oemtable: bad signature [%c%c%c%c]!\n", - oemtable->oem_signature[0], - oemtable->oem_signature[1], - oemtable->oem_signature[2], - oemtable->oem_signature[3]); + printk(KERN_INFO "Found an OEM MPC table at %8p - parsing it ... \n", + oemtable); + if (memcmp(oemtable->oem_signature, MPC_OEM_SIGNATURE, 4)) { + printk(KERN_WARNING + "SMP mpc oemtable: bad signature [%c%c%c%c]!\n", + oemtable->oem_signature[0], oemtable->oem_signature[1], + oemtable->oem_signature[2], oemtable->oem_signature[3]); return; } - if (mpf_checksum((unsigned char *)oemtable,oemtable->oem_length)) - { + if (mpf_checksum((unsigned char *)oemtable, oemtable->oem_length)) { printk(KERN_WARNING "SMP oem mptable: checksum error!\n"); return; } while (count < oemtable->oem_length) { switch (*oemptr) { - case MP_TRANSLATION: + case MP_TRANSLATION: { - struct mpc_config_translation *m= - (struct mpc_config_translation *)oemptr; + struct mpc_config_translation *m = + (struct mpc_config_translation *)oemptr; MP_translation_info(m); oemptr += sizeof(*m); count += sizeof(*m); ++mpc_record; break; } - default: + default: { - printk(KERN_WARNING "Unrecognised OEM table entry type! - %d\n", (int) *oemptr); + printk(KERN_WARNING + "Unrecognised OEM table entry type! - %d\n", + (int)*oemptr); return; } } - } + } } static inline void mps_oem_check(struct mp_config_table *mpc, char *oem, - char *productid) + char *productid) { if (strncmp(oem, "IBM NUMA", 8)) printk("Warning! May not be a NUMA-Q system!\n"); if (mpc->mpc_oemptr) - smp_read_mpc_oem((struct mp_config_oemtable *) mpc->mpc_oemptr, - mpc->mpc_oemsize); + smp_read_mpc_oem((struct mp_config_oemtable *)mpc->mpc_oemptr, + mpc->mpc_oemsize); } -#endif /* CONFIG_X86_NUMAQ */ +#endif /* CONFIG_X86_NUMAQ */ /* * Read/parse the MPC */ -static int __init smp_read_mpc(struct mp_config_table *mpc) +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; + int count = sizeof(*mpc); + unsigned char *mpt = ((unsigned char *)mpc) + count; - if (memcmp(mpc->mpc_signature,MPC_SIGNATURE,4)) { - printk(KERN_ERR "SMP mptable: bad signature [0x%x]!\n", - *(u32 *)mpc->mpc_signature); + if (memcmp(mpc->mpc_signature, MPC_SIGNATURE, 4)) { + printk(KERN_ERR "MPTABLE: bad signature [%c%c%c%c]!\n", + mpc->mpc_signature[0], mpc->mpc_signature[1], + mpc->mpc_signature[2], mpc->mpc_signature[3]); return 0; } - if (mpf_checksum((unsigned char *)mpc,mpc->mpc_length)) { - printk(KERN_ERR "SMP mptable: checksum error!\n"); + if (mpf_checksum((unsigned char *)mpc, mpc->mpc_length)) { + printk(KERN_ERR "MPTABLE: checksum error!\n"); return 0; } - if (mpc->mpc_spec!=0x01 && mpc->mpc_spec!=0x04) { - printk(KERN_ERR "SMP mptable: bad table version (%d)!!\n", - mpc->mpc_spec); + if (mpc->mpc_spec != 0x01 && mpc->mpc_spec != 0x04) { + printk(KERN_ERR "MPTABLE: bad table version (%d)!!\n", + mpc->mpc_spec); return 0; } if (!mpc->mpc_lapic) { - printk(KERN_ERR "SMP mptable: null local APIC address!\n"); + printk(KERN_ERR "MPTABLE: null local APIC address!\n"); return 0; } - memcpy(oem,mpc->mpc_oem,8); - oem[8]=0; - printk(KERN_INFO "OEM ID: %s ",oem); + memcpy(oem, mpc->mpc_oem, 8); + oem[8] = 0; + printk(KERN_INFO "MPTABLE: OEM ID: %s ", oem); - memcpy(str,mpc->mpc_productid,12); - str[12]=0; - printk("Product ID: %s ",str); + 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("APIC at: 0x%X\n", mpc->mpc_lapic); + printk(KERN_INFO "MPTABLE: APIC at: 0x%X\n", mpc->mpc_lapic); - /* - * Save the local APIC address (it might be non-default) -- but only - * if we're not using ACPI. - */ + /* save the local APIC address, it might be non-default */ if (!acpi_lapic) mp_lapic_addr = mpc->mpc_lapic; + if (early) + return 1; + /* - * Now process the configuration blocks. + * Now process the configuration blocks. */ +#ifdef CONFIG_X86_NUMAQ mpc_record = 0; +#endif while (count < mpc->mpc_length) { - switch(*mpt) { - case MP_PROCESSOR: + switch (*mpt) { + case MP_PROCESSOR: { - struct mpc_config_processor *m= - (struct mpc_config_processor *)mpt; + struct mpc_config_processor *m = + (struct mpc_config_processor *)mpt; /* ACPI may have already provided this data */ if (!acpi_lapic) MP_processor_info(m); @@ -431,57 +348,68 @@ static int __init smp_read_mpc(struct mp_config_table *mpc) count += sizeof(*m); break; } - case MP_BUS: + case MP_BUS: { - struct mpc_config_bus *m= - (struct mpc_config_bus *)mpt; + struct mpc_config_bus *m = + (struct mpc_config_bus *)mpt; MP_bus_info(m); mpt += sizeof(*m); count += sizeof(*m); break; } - case MP_IOAPIC: + case MP_IOAPIC: { - struct mpc_config_ioapic *m= - (struct mpc_config_ioapic *)mpt; +#ifdef CONFIG_X86_IO_APIC + struct mpc_config_ioapic *m = + (struct mpc_config_ioapic *)mpt; MP_ioapic_info(m); - mpt+=sizeof(*m); - count+=sizeof(*m); +#endif + mpt += sizeof(struct mpc_config_ioapic); + count += sizeof(struct mpc_config_ioapic); break; } - case MP_INTSRC: + case MP_INTSRC: { - struct mpc_config_intsrc *m= - (struct mpc_config_intsrc *)mpt; +#ifdef CONFIG_X86_IO_APIC + struct mpc_config_intsrc *m = + (struct mpc_config_intsrc *)mpt; MP_intsrc_info(m); - mpt+=sizeof(*m); - count+=sizeof(*m); +#endif + mpt += sizeof(struct mpc_config_intsrc); + count += sizeof(struct mpc_config_intsrc); break; } - case MP_LINTSRC: + case MP_LINTSRC: { - struct mpc_config_lintsrc *m= - (struct mpc_config_lintsrc *)mpt; + struct mpc_config_lintsrc *m = + (struct mpc_config_lintsrc *)mpt; MP_lintsrc_info(m); - mpt+=sizeof(*m); - count+=sizeof(*m); - break; - } - default: - { - count = mpc->mpc_length; + 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); + count = mpc->mpc_length; + break; } +#ifdef CONFIG_X86_NUMAQ ++mpc_record; +#endif } setup_apic_routing(); if (!num_processors) - printk(KERN_ERR "SMP mptable: no processors registered!\n"); + printk(KERN_ERR "MPTABLE: no processors registered!\n"); return num_processors; } +#ifdef CONFIG_X86_IO_APIC + static int __init ELCR_trigger(unsigned int irq) { unsigned int port; @@ -497,7 +425,7 @@ static void __init construct_default_ioirq_mptable(int mpc_default_type) int ELCR_fallback = 0; intsrc.mpc_type = MP_INTSRC; - intsrc.mpc_irqflag = 0; /* conforming */ + intsrc.mpc_irqflag = 0; /* conforming */ intsrc.mpc_srcbus = 0; intsrc.mpc_dstapic = mp_ioapics[0].mpc_apicid; @@ -512,12 +440,16 @@ static void __init construct_default_ioirq_mptable(int mpc_default_type) * If it does, we assume it's valid. */ if (mpc_default_type == 5) { - printk(KERN_INFO "ISA/PCI bus type with no IRQ information... falling back to ELCR\n"); + printk(KERN_INFO "ISA/PCI bus type with no IRQ information... " + "falling back to ELCR\n"); - if (ELCR_trigger(0) || ELCR_trigger(1) || ELCR_trigger(2) || ELCR_trigger(13)) - printk(KERN_WARNING "ELCR contains invalid data... not using ELCR\n"); + if (ELCR_trigger(0) || ELCR_trigger(1) || ELCR_trigger(2) || + ELCR_trigger(13)) + printk(KERN_ERR "ELCR contains invalid data... " + "not using ELCR\n"); else { - printk(KERN_INFO "Using ELCR to identify PCI interrupts\n"); + printk(KERN_INFO + "Using ELCR to identify PCI interrupts\n"); ELCR_fallback = 1; } } @@ -546,21 +478,25 @@ static void __init construct_default_ioirq_mptable(int mpc_default_type) } intsrc.mpc_srcbusirq = i; - intsrc.mpc_dstirq = i ? i : 2; /* IRQ0 to INTIN2 */ + intsrc.mpc_dstirq = i ? i : 2; /* IRQ0 to INTIN2 */ MP_intsrc_info(&intsrc); } intsrc.mpc_irqtype = mp_ExtINT; intsrc.mpc_srcbusirq = 0; - intsrc.mpc_dstirq = 0; /* 8259A to INTIN0 */ + intsrc.mpc_dstirq = 0; /* 8259A to INTIN0 */ MP_intsrc_info(&intsrc); } +#endif + static inline void __init construct_default_ISA_mptable(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; @@ -578,8 +514,7 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type) 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; + (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; @@ -591,23 +526,22 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type) bus.mpc_type = MP_BUS; bus.mpc_busid = 0; switch (mpc_default_type) { - default: - printk("???\n"); - printk(KERN_ERR "Unknown standard configuration %d\n", - mpc_default_type); - /* fall through */ - case 1: - case 5: - memcpy(bus.mpc_bustype, "ISA ", 6); - break; - case 2: - case 6: - case 3: - memcpy(bus.mpc_bustype, "EISA ", 6); - break; - case 4: - case 7: - memcpy(bus.mpc_bustype, "MCA ", 6); + default: + printk(KERN_ERR "???\nUnknown standard configuration %d\n", + mpc_default_type); + /* fall through */ + case 1: + case 5: + memcpy(bus.mpc_bustype, "ISA ", 6); + break; + case 2: + case 6: + case 3: + memcpy(bus.mpc_bustype, "EISA ", 6); + break; + case 4: + case 7: + memcpy(bus.mpc_bustype, "MCA ", 6); } MP_bus_info(&bus); if (mpc_default_type > 4) { @@ -616,6 +550,7 @@ 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; @@ -627,9 +562,9 @@ 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); - +#endif lintsrc.mpc_type = MP_LINTSRC; - lintsrc.mpc_irqflag = 0; /* conforming */ + lintsrc.mpc_irqflag = 0; /* conforming */ lintsrc.mpc_srcbusid = 0; lintsrc.mpc_srcbusirq = 0; lintsrc.mpc_destapic = MP_APIC_ALL; @@ -645,36 +580,49 @@ static struct intel_mp_floating *mpf_found; /* * Scan the memory blocks for an SMP configuration block. */ -void __init get_smp_config (void) +static void __init __get_smp_config(unsigned early) { struct intel_mp_floating *mpf = mpf_found; + if (acpi_lapic && early) + return; /* - * ACPI supports both logical (e.g. Hyper-Threading) and physical + * ACPI supports both logical (e.g. Hyper-Threading) and physical * processors, where MPS only supports physical. */ if (acpi_lapic && acpi_ioapic) { - printk(KERN_INFO "Using ACPI (MADT) for SMP configuration information\n"); + printk(KERN_INFO "Using ACPI (MADT) for SMP configuration " + "information\n"); return; - } - else if (acpi_lapic) - printk(KERN_INFO "Using ACPI for processor (LAPIC) configuration information\n"); - - printk(KERN_INFO "Intel MultiProcessor Specification v1.%d\n", mpf->mpf_specification); - if (mpf->mpf_feature2 & (1<<7)) { + } else if (acpi_lapic) + printk(KERN_INFO "Using ACPI for processor (LAPIC) " + "configuration information\n"); + + printk(KERN_INFO "Intel MultiProcessor Specification v1.%d\n", + mpf->mpf_specification); +#ifdef CONFIG_X86_32 + if (mpf->mpf_feature2 & (1 << 7)) { printk(KERN_INFO " IMCR and PIC compatibility mode.\n"); pic_mode = 1; } else { printk(KERN_INFO " Virtual Wire compatibility mode.\n"); pic_mode = 0; } - +#endif /* * Now see if we need to read further. */ if (mpf->mpf_feature1 != 0) { + if (early) { + /* + * local APIC has default address + */ + mp_lapic_addr = APIC_DEFAULT_PHYS_BASE; + return; + } - printk(KERN_INFO "Default MP configuration #%d\n", mpf->mpf_feature1); + printk(KERN_INFO "Default MP configuration #%d\n", + mpf->mpf_feature1); construct_default_ISA_mptable(mpf->mpf_feature1); } else if (mpf->mpf_physptr) { @@ -683,12 +631,18 @@ void __init get_smp_config (void) * Read the physical hardware table. Anything here will * override the defaults. */ - if (!smp_read_mpc(phys_to_virt(mpf->mpf_physptr))) { + if (!smp_read_mpc(phys_to_virt(mpf->mpf_physptr), early)) { smp_found_config = 0; - printk(KERN_ERR "BIOS bug, MP table errors detected!...\n"); - printk(KERN_ERR "... disabling SMP support. (tell your hw vendor)\n"); + printk(KERN_ERR + "BIOS bug, MP table errors detected!...\n"); + printk(KERN_ERR "... disabling SMP support. " + "(tell your hw vendor)\n"); return; } + + if (early) + return; +#ifdef CONFIG_X86_IO_APIC /* * If there are no explicit MP IRQ entries, then we are * broken. We set up most of the low 16 IO-APIC pins to @@ -697,7 +651,9 @@ void __init get_smp_config (void) if (!mp_irq_entries) { struct mpc_config_bus bus; - printk(KERN_ERR "BIOS bug, no explicit IRQ entries, using default mptable. (tell your hw vendor)\n"); + printk(KERN_ERR "BIOS bug, no explicit IRQ entries, " + "using default mptable. " + "(tell your hw vendor)\n"); bus.mpc_type = MP_BUS; bus.mpc_busid = 0; @@ -706,36 +662,49 @@ void __init get_smp_config (void) construct_default_ioirq_mptable(0); } - +#endif } else BUG(); - printk(KERN_INFO "Processors: %d\n", num_processors); + if (!early) + printk(KERN_INFO "Processors: %d\n", num_processors); /* * Only use the first configuration found. */ } -static int __init smp_scan_config (unsigned long base, unsigned long length) +void __init early_get_smp_config(void) { - unsigned long *bp = phys_to_virt(base); + __get_smp_config(1); +} + +void __init get_smp_config(void) +{ + __get_smp_config(0); +} + +static int __init smp_scan_config(unsigned long base, unsigned long length, + unsigned reserve) +{ + unsigned int *bp = phys_to_virt(base); struct intel_mp_floating *mpf; - printk(KERN_INFO "Scan SMP from %p for %ld bytes.\n", bp,length); - if (sizeof(*mpf) != 16) - printk("Error: MPF size\n"); + Dprintk("Scan SMP from %p for %ld bytes.\n", bp, length); + BUILD_BUG_ON(sizeof(*mpf) != 16); while (length > 0) { mpf = (struct intel_mp_floating *)bp; if ((*bp == SMP_MAGIC_IDENT) && - (mpf->mpf_length == 1) && - !mpf_checksum((unsigned char *)bp, 16) && - ((mpf->mpf_specification == 1) - || (mpf->mpf_specification == 4)) ) { + (mpf->mpf_length == 1) && + !mpf_checksum((unsigned char *)bp, 16) && + ((mpf->mpf_specification == 1) + || (mpf->mpf_specification == 4))) { smp_found_config = 1; + mpf_found = mpf; +#ifdef CONFIG_X86_32 printk(KERN_INFO "found SMP MP-table at [%p] %08lx\n", - mpf, virt_to_phys(mpf)); + mpf, virt_to_phys(mpf)); reserve_bootmem(virt_to_phys(mpf), PAGE_SIZE, BOOTMEM_DEFAULT); if (mpf->mpf_physptr) { @@ -756,8 +725,16 @@ static int __init smp_scan_config (unsigned long base, unsigned long length) BOOTMEM_DEFAULT); } - mpf_found = mpf; - return 1; +#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; } bp += 4; length -= 16; @@ -765,7 +742,7 @@ static int __init smp_scan_config (unsigned long base, unsigned long length) return 0; } -void __init find_smp_config (void) +static void __init __find_smp_config(unsigned reserve) { unsigned int address; @@ -777,9 +754,9 @@ void __init find_smp_config (void) * 2) Scan the top 1K of base RAM * 3) Scan the 64K of bios */ - if (smp_scan_config(0x0,0x400) || - smp_scan_config(639*0x400,0x400) || - smp_scan_config(0xF0000,0x10000)) + if (smp_scan_config(0x0, 0x400, reserve) || + smp_scan_config(639 * 0x400, 0x400, reserve) || + smp_scan_config(0xF0000, 0x10000, reserve)) return; /* * If it is an SMP machine we should know now, unless the @@ -800,144 +777,112 @@ void __init find_smp_config (void) address = get_bios_ebda(); if (address) - smp_scan_config(address, 0x400); + smp_scan_config(address, 0x400, reserve); } -int es7000_plat; - -/* -------------------------------------------------------------------------- - ACPI-based MP Configuration - -------------------------------------------------------------------------- */ - -#ifdef CONFIG_ACPI - -void __init mp_register_lapic_address(u64 address) +void __init early_find_smp_config(void) { - mp_lapic_addr = (unsigned long) address; - - set_fixmap_nocache(FIX_APIC_BASE, mp_lapic_addr); - - if (boot_cpu_physical_apicid == -1U) - boot_cpu_physical_apicid = GET_APIC_ID(apic_read(APIC_ID)); - - Dprintk("Boot CPU = %d\n", boot_cpu_physical_apicid); + __find_smp_config(0); } -void __cpuinit mp_register_lapic (u8 id, u8 enabled) +void __init find_smp_config(void) { - struct mpc_config_processor processor; - int boot_cpu = 0; - - if (MAX_APICS - id <= 0) { - printk(KERN_WARNING "Processor #%d invalid (max %d)\n", - id, MAX_APICS); - return; - } - - if (id == boot_cpu_physical_apicid) - boot_cpu = 1; + __find_smp_config(1); +} - processor.mpc_type = MP_PROCESSOR; - processor.mpc_apicid = id; - processor.mpc_apicver = GET_APIC_VERSION(apic_read(APIC_LVR)); - processor.mpc_cpuflag = (enabled ? CPU_ENABLED : 0); - processor.mpc_cpuflag |= (boot_cpu ? CPU_BOOTPROCESSOR : 0); - 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; +/* -------------------------------------------------------------------------- + ACPI-based MP Configuration + -------------------------------------------------------------------------- */ - MP_processor_info(&processor); -} +#ifdef CONFIG_ACPI #ifdef CONFIG_X86_IO_APIC #define MP_ISA_BUS 0 -#define MP_MAX_IOAPIC_PIN 127 -static struct mp_ioapic_routing { - int apic_id; - int gsi_base; - int gsi_end; - u32 pin_programmed[4]; -} mp_ioapic_routing[MAX_IO_APICS]; +extern struct mp_ioapic_routing mp_ioapic_routing[MAX_IO_APICS]; -static int mp_find_ioapic (int gsi) +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)) + && (gsi <= mp_ioapic_routing[i].gsi_end)) return i; } printk(KERN_ERR "ERROR: Unable to locate IOAPIC for GSI %d\n", gsi); - return -1; } -void __init mp_register_ioapic(u8 id, u32 address, u32 gsi_base) +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); +#endif +} + +void __init mp_register_ioapic(int id, u32 address, u32 gsi_base) { int idx = 0; - int tmpid; - 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 MADT table, skipping!\n"); + if (bad_ioapic(address)) return; - } - idx = nr_ioapics++; + idx = nr_ioapics; mp_ioapics[idx].mpc_type = MP_IOAPIC; mp_ioapics[idx].mpc_flags = MPC_APIC_USABLE; mp_ioapics[idx].mpc_apicaddr = address; set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address); - if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) - && !APIC_XAPIC(apic_version[boot_cpu_physical_apicid])) - tmpid = io_apic_get_unique_id(idx, id); - else - tmpid = id; - if (tmpid == -1) { - nr_ioapics--; - return; - } - mp_ioapics[idx].mpc_apicid = tmpid; + 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; +#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); + io_apic_get_redir_entries(idx); - printk("IOAPIC[%d]: apic_id %d, version %d, address 0x%x, " + 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); + mp_ioapic_routing[idx].gsi_base, mp_ioapic_routing[idx].gsi_end); + + nr_ioapics++; } -void __init -mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi) +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; + int ioapic = -1; + int pin = -1; - /* + /* * Convert 'gsi' to 'ioapic.pin'. */ ioapic = mp_find_ioapic(gsi); @@ -947,7 +892,7 @@ mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi) /* * TBD: This check is for faulty timer entries, where the override - * erroneously sets the trigger to level, resulting in a HUGE + * erroneously sets the trigger to level, resulting in a HUGE * increase of timer interrupts! */ if ((bus_irq == 0) && (trigger == 3)) @@ -957,30 +902,28 @@ mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi) 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# */ + intsrc.mpc_srcbusirq = bus_irq; /* IRQ */ + intsrc.mpc_dstapic = mp_ioapics[ioapic].mpc_apicid; /* APIC ID */ + intsrc.mpc_dstirq = pin; /* INTIN# */ - Dprintk("Int: type %d, pol %d, trig %d, bus %d, irq %d, %d-%d\n", - intsrc.mpc_irqtype, intsrc.mpc_irqflag & 3, - (intsrc.mpc_irqflag >> 2) & 3, intsrc.mpc_srcbus, - intsrc.mpc_srcbusirq, intsrc.mpc_dstapic, intsrc.mpc_dstirq); - - mp_irqs[mp_irq_entries] = intsrc; - if (++mp_irq_entries == MAX_IRQ_SOURCES) - panic("Max # of irq sources exceeded!\n"); + MP_intsrc_info(&intsrc); } -void __init mp_config_acpi_legacy_irqs (void) +int es7000_plat; + +void __init mp_config_acpi_legacy_irqs(void) { struct mpc_config_intsrc intsrc; int i = 0; int ioapic = -1; - /* +#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); /* @@ -989,19 +932,20 @@ void __init mp_config_acpi_legacy_irqs (void) if (es7000_plat == 1) return; - /* - * Locate the IOAPIC that manages the ISA IRQs (0-15). + /* + * Locate the IOAPIC that manages the ISA IRQs (0-15). */ ioapic = mp_find_ioapic(0); if (ioapic < 0) return; intsrc.mpc_type = MP_INTSRC; - intsrc.mpc_irqflag = 0; /* Conforming */ + intsrc.mpc_irqflag = 0; /* Conforming */ intsrc.mpc_srcbus = MP_ISA_BUS; +#ifdef CONFIG_X86_IO_APIC intsrc.mpc_dstapic = mp_ioapics[ioapic].mpc_apicid; - - /* +#endif + /* * Use the default configuration for the IRQs 0-15. Unless * overridden by (MADT) interrupt source override entries. */ @@ -1012,51 +956,49 @@ void __init mp_config_acpi_legacy_irqs (void) 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) + 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)) + (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 */ + continue; /* IRQ already used */ } intsrc.mpc_irqtype = mp_INT; - intsrc.mpc_srcbusirq = i; /* Identity mapped */ + intsrc.mpc_srcbusirq = i; /* Identity mapped */ intsrc.mpc_dstirq = i; - Dprintk("Int: type %d, pol %d, trig %d, bus %d, irq %d, " - "%d-%d\n", intsrc.mpc_irqtype, intsrc.mpc_irqflag & 3, - (intsrc.mpc_irqflag >> 2) & 3, intsrc.mpc_srcbus, - intsrc.mpc_srcbusirq, intsrc.mpc_dstapic, - intsrc.mpc_dstirq); - - mp_irqs[mp_irq_entries] = intsrc; - if (++mp_irq_entries == MAX_IRQ_SOURCES) - panic("Max # of irq sources exceeded!\n"); + MP_intsrc_info(&intsrc); } } +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 -int mp_register_gsi(u32 gsi, int triggering, int polarity) -{ - int ioapic = -1; - int ioapic_pin = 0; - int idx, bit = 0; 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]; + 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) @@ -1070,35 +1012,39 @@ int mp_register_gsi(u32 gsi, int triggering, int polarity) 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 + /* + * Avoid pin reprogramming. PRTs typically include entries * with redundant pin->gsi mappings (but unique PCI devices); * we only program the IOAPIC on the first. */ - bit = ioapic_pin % 32; - idx = (ioapic_pin < 32) ? 0 : (ioapic_pin / 32); - if (idx > 3) { + 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); + "%d-%d\n", mp_ioapic_routing[ioapic].apic_id, + ioapic_pin); return gsi; } - if ((1<<bit) & mp_ioapic_routing[ioapic].pin_programmed[idx]) { + 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 } - mp_ioapic_routing[ioapic].pin_programmed[idx] |= (1<<bit); - + 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)) { + && (triggering == ACPI_LEVEL_SENSITIVE)) { /* * For PCI devices assign IRQs in order, avoiding gaps * due to unused I/O APIC pins. @@ -1115,8 +1061,7 @@ int mp_register_gsi(u32 gsi, int triggering, int polarity) * So test for this condition, and if necessary, avoid * the pin collision. */ - if (gsi > 15 || (gsi == 0 && !timer_uses_ioapic_pin_0)) - gsi = pci_irq++; + gsi = pci_irq++; /* * Don't assign IRQ used by ACPI SCI */ @@ -1128,10 +1073,10 @@ int mp_register_gsi(u32 gsi, int triggering, int polarity) return gsi; } } - +#endif io_apic_set_pci_routing(ioapic, ioapic_pin, gsi, - triggering == ACPI_EDGE_SENSITIVE ? 0 : 1, - polarity == ACPI_ACTIVE_HIGH ? 0 : 1); + triggering == ACPI_EDGE_SENSITIVE ? 0 : 1, + polarity == ACPI_ACTIVE_HIGH ? 0 : 1); return gsi; } diff --git a/arch/x86/kernel/mpparse_64.c b/arch/x86/kernel/mpparse_64.c deleted file mode 100644 index 72ab1403fed7..000000000000 --- a/arch/x86/kernel/mpparse_64.c +++ /dev/null @@ -1,867 +0,0 @@ -/* - * Intel Multiprocessor Specification 1.1 and 1.4 - * compliant MP-table parsing routines. - * - * (c) 1995 Alan Cox, Building #3 <alan@redhat.com> - * (c) 1998, 1999, 2000 Ingo Molnar <mingo@redhat.com> - * - * Fixes - * Erich Boleyn : MP v1.4 and additional changes. - * Alan Cox : Added EBDA scanning - * Ingo Molnar : various cleanups and rewrites - * Maciej W. Rozycki: Bits for default MP configurations - * Paul Diefenbaugh: Added full ACPI support - */ - -#include <linux/mm.h> -#include <linux/init.h> -#include <linux/delay.h> -#include <linux/bootmem.h> -#include <linux/kernel_stat.h> -#include <linux/mc146818rtc.h> -#include <linux/acpi.h> -#include <linux/module.h> - -#include <asm/smp.h> -#include <asm/mtrr.h> -#include <asm/mpspec.h> -#include <asm/pgalloc.h> -#include <asm/io_apic.h> -#include <asm/proto.h> -#include <asm/acpi.h> - -/* Have we found an MP table */ -int smp_found_config; - -/* - * Various Linux-internal data structures created from the - * MP-table. - */ -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 = 0; -/* I/O APIC entries */ -struct mpc_config_ioapic mp_ioapics[MAX_IO_APICS]; - -/* # of MP IRQ source entries */ -struct mpc_config_intsrc mp_irqs[MAX_IRQ_SOURCES]; - -/* MP IRQ source entries */ -int mp_irq_entries; - -int nr_ioapics; -unsigned long mp_lapic_addr = 0; - - - -/* Processor that is doing the boot up */ -unsigned int boot_cpu_id = -1U; -EXPORT_SYMBOL(boot_cpu_id); - -/* Internal processor count */ -unsigned int num_processors; - -unsigned disabled_cpus __cpuinitdata; - -/* Bitmask of physically existing CPUs */ -physid_mask_t phys_cpu_present_map = PHYSID_MASK_NONE; - -u16 x86_bios_cpu_apicid_init[NR_CPUS] __initdata - = { [0 ... NR_CPUS-1] = BAD_APICID }; -void *x86_bios_cpu_apicid_early_ptr; -DEFINE_PER_CPU(u16, x86_bios_cpu_apicid) = BAD_APICID; -EXPORT_PER_CPU_SYMBOL(x86_bios_cpu_apicid); - - -/* - * Intel MP BIOS table parsing routines: - */ - -/* - * Checksum an MP configuration block. - */ - -static int __init mpf_checksum(unsigned char *mp, int len) -{ - int sum = 0; - - while (len--) - sum += *mp++; - - return sum & 0xFF; -} - -static void __cpuinit MP_processor_info(struct mpc_config_processor *m) -{ - int cpu; - cpumask_t tmp_map; - char *bootup_cpu = ""; - - if (!(m->mpc_cpuflag & CPU_ENABLED)) { - disabled_cpus++; - return; - } - if (m->mpc_cpuflag & CPU_BOOTPROCESSOR) { - bootup_cpu = " (Bootup-CPU)"; - boot_cpu_id = m->mpc_apicid; - } - - printk(KERN_INFO "Processor #%d%s\n", m->mpc_apicid, bootup_cpu); - - if (num_processors >= NR_CPUS) { - printk(KERN_WARNING "WARNING: NR_CPUS limit of %i reached." - " Processor ignored.\n", NR_CPUS); - return; - } - - num_processors++; - cpus_complement(tmp_map, cpu_present_map); - cpu = first_cpu(tmp_map); - - physid_set(m->mpc_apicid, phys_cpu_present_map); - if (m->mpc_cpuflag & CPU_BOOTPROCESSOR) { - /* - * x86_bios_cpu_apicid is required to have processors listed - * in same order as logical cpu numbers. Hence the first - * entry is BSP, and so on. - */ - cpu = 0; - } - /* 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; - - cpu_to_apicid[cpu] = m->mpc_apicid; - bios_cpu_apicid[cpu] = m->mpc_apicid; - } else { - per_cpu(x86_cpu_to_apicid, cpu) = m->mpc_apicid; - per_cpu(x86_bios_cpu_apicid, cpu) = m->mpc_apicid; - } - - cpu_set(cpu, cpu_possible_map); - cpu_set(cpu, cpu_present_map); -} - -static void __init MP_bus_info (struct mpc_config_bus *m) -{ - char str[7]; - - memcpy(str, m->mpc_bustype, 6); - str[6] = 0; - Dprintk("Bus #%d is %s\n", m->mpc_busid, str); - - if (strncmp(str, "ISA", 3) == 0) { - set_bit(m->mpc_busid, mp_bus_not_pci); - } else if (strncmp(str, "PCI", 3) == 0) { - 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++; - } else { - printk(KERN_ERR "Unknown bustype %s\n", str); - } -} - -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; -} - -static void __init MP_ioapic_info (struct mpc_config_ioapic *m) -{ - if (!(m->mpc_flags & MPC_APIC_USABLE)) - return; - - printk("I/O APIC #%d at 0x%X.\n", - m->mpc_apicid, m->mpc_apicaddr); - - if (bad_ioapic(m->mpc_apicaddr)) - return; - - mp_ioapics[nr_ioapics] = *m; - nr_ioapics++; -} - -static void __init MP_intsrc_info (struct mpc_config_intsrc *m) -{ - mp_irqs [mp_irq_entries] = *m; - Dprintk("Int: type %d, pol %d, trig %d, bus %d," - " 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); - if (++mp_irq_entries >= MAX_IRQ_SOURCES) - panic("Max # of irq sources exceeded!!\n"); -} - -static void __init MP_lintsrc_info (struct mpc_config_lintsrc *m) -{ - Dprintk("Lint: type %d, pol %d, trig %d, bus %d," - " IRQ %02x, APIC ID %x, APIC LINT %02x\n", - m->mpc_irqtype, m->mpc_irqflag & 3, - (m->mpc_irqflag >> 2) &3, m->mpc_srcbusid, - m->mpc_srcbusirq, m->mpc_destapic, m->mpc_destapiclint); -} - -/* - * Read/parse the MPC - */ - -static int __init smp_read_mpc(struct mp_config_table *mpc) -{ - char str[16]; - int count=sizeof(*mpc); - unsigned char *mpt=((unsigned char *)mpc)+count; - - if (memcmp(mpc->mpc_signature,MPC_SIGNATURE,4)) { - printk("MPTABLE: bad signature [%c%c%c%c]!\n", - mpc->mpc_signature[0], - mpc->mpc_signature[1], - mpc->mpc_signature[2], - mpc->mpc_signature[3]); - return 0; - } - if (mpf_checksum((unsigned char *)mpc,mpc->mpc_length)) { - printk("MPTABLE: checksum error!\n"); - return 0; - } - if (mpc->mpc_spec!=0x01 && mpc->mpc_spec!=0x04) { - printk(KERN_ERR "MPTABLE: bad table version (%d)!!\n", - mpc->mpc_spec); - return 0; - } - if (!mpc->mpc_lapic) { - printk(KERN_ERR "MPTABLE: null local APIC address!\n"); - return 0; - } - memcpy(str,mpc->mpc_oem,8); - str[8] = 0; - printk(KERN_INFO "MPTABLE: OEM ID: %s ",str); - - memcpy(str,mpc->mpc_productid,12); - str[12] = 0; - printk("MPTABLE: Product ID: %s ",str); - - printk("MPTABLE: APIC at: 0x%X\n",mpc->mpc_lapic); - - /* save the local APIC address, it might be non-default */ - if (!acpi_lapic) - mp_lapic_addr = mpc->mpc_lapic; - - /* - * Now process the configuration blocks. - */ - while (count < mpc->mpc_length) { - switch(*mpt) { - case MP_PROCESSOR: - { - struct mpc_config_processor *m= - (struct mpc_config_processor *)mpt; - if (!acpi_lapic) - MP_processor_info(m); - mpt += sizeof(*m); - count += sizeof(*m); - break; - } - case MP_BUS: - { - struct mpc_config_bus *m= - (struct mpc_config_bus *)mpt; - MP_bus_info(m); - mpt += sizeof(*m); - count += sizeof(*m); - break; - } - case MP_IOAPIC: - { - struct mpc_config_ioapic *m= - (struct mpc_config_ioapic *)mpt; - MP_ioapic_info(m); - mpt += sizeof(*m); - count += sizeof(*m); - break; - } - case MP_INTSRC: - { - struct mpc_config_intsrc *m= - (struct mpc_config_intsrc *)mpt; - - MP_intsrc_info(m); - mpt += sizeof(*m); - count += sizeof(*m); - break; - } - case MP_LINTSRC: - { - struct mpc_config_lintsrc *m= - (struct mpc_config_lintsrc *)mpt; - MP_lintsrc_info(m); - mpt += sizeof(*m); - count += sizeof(*m); - break; - } - } - } - setup_apic_routing(); - if (!num_processors) - printk(KERN_ERR "MPTABLE: no processors registered!\n"); - return num_processors; -} - -static int __init ELCR_trigger(unsigned int irq) -{ - unsigned int port; - - port = 0x4d0 + (irq >> 3); - return (inb(port) >> (irq & 7)) & 1; -} - -static void __init construct_default_ioirq_mptable(int mpc_default_type) -{ - struct mpc_config_intsrc intsrc; - int i; - int ELCR_fallback = 0; - - intsrc.mpc_type = MP_INTSRC; - intsrc.mpc_irqflag = 0; /* conforming */ - intsrc.mpc_srcbus = 0; - intsrc.mpc_dstapic = mp_ioapics[0].mpc_apicid; - - intsrc.mpc_irqtype = mp_INT; - - /* - * If true, we have an ISA/PCI system with no IRQ entries - * in the MP table. To prevent the PCI interrupts from being set up - * incorrectly, we try to use the ELCR. The sanity check to see if - * there is good ELCR data is very simple - IRQ0, 1, 2 and 13 can - * never be level sensitive, so we simply see if the ELCR agrees. - * If it does, we assume it's valid. - */ - if (mpc_default_type == 5) { - printk(KERN_INFO "ISA/PCI bus type with no IRQ information... falling back to ELCR\n"); - - if (ELCR_trigger(0) || ELCR_trigger(1) || ELCR_trigger(2) || ELCR_trigger(13)) - printk(KERN_ERR "ELCR contains invalid data... not using ELCR\n"); - else { - printk(KERN_INFO "Using ELCR to identify PCI interrupts\n"); - ELCR_fallback = 1; - } - } - - for (i = 0; i < 16; i++) { - switch (mpc_default_type) { - case 2: - if (i == 0 || i == 13) - continue; /* IRQ0 & IRQ13 not connected */ - /* fall through */ - default: - if (i == 2) - continue; /* IRQ2 is never connected */ - } - - if (ELCR_fallback) { - /* - * If the ELCR indicates a level-sensitive interrupt, we - * copy that information over to the MP table in the - * irqflag field (level sensitive, active high polarity). - */ - if (ELCR_trigger(i)) - intsrc.mpc_irqflag = 13; - else - intsrc.mpc_irqflag = 0; - } - - intsrc.mpc_srcbusirq = i; - intsrc.mpc_dstirq = i ? i : 2; /* IRQ0 to INTIN2 */ - MP_intsrc_info(&intsrc); - } - - intsrc.mpc_irqtype = mp_ExtINT; - intsrc.mpc_srcbusirq = 0; - intsrc.mpc_dstirq = 0; /* 8259A to INTIN0 */ - MP_intsrc_info(&intsrc); -} - -static inline void __init construct_default_ISA_mptable(int mpc_default_type) -{ - struct mpc_config_processor processor; - struct mpc_config_bus bus; - struct mpc_config_ioapic ioapic; - 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; - processor.mpc_apicver = 0; - processor.mpc_cpuflag = CPU_ENABLED; - processor.mpc_cpufeature = 0; - processor.mpc_featureflag = 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); - } - - bus.mpc_type = MP_BUS; - bus.mpc_busid = 0; - switch (mpc_default_type) { - default: - printk(KERN_ERR "???\nUnknown standard configuration %d\n", - mpc_default_type); - /* fall through */ - case 1: - case 5: - memcpy(bus.mpc_bustype, "ISA ", 6); - break; - } - MP_bus_info(&bus); - if (mpc_default_type > 4) { - bus.mpc_busid = 1; - memcpy(bus.mpc_bustype, "PCI ", 6); - MP_bus_info(&bus); - } - - ioapic.mpc_type = MP_IOAPIC; - ioapic.mpc_apicid = 2; - ioapic.mpc_apicver = 0; - ioapic.mpc_flags = MPC_APIC_USABLE; - ioapic.mpc_apicaddr = 0xFEC00000; - MP_ioapic_info(&ioapic); - - /* - * We set up most of the low 16 IO-APIC pins according to MPS rules. - */ - construct_default_ioirq_mptable(mpc_default_type); - - lintsrc.mpc_type = MP_LINTSRC; - lintsrc.mpc_irqflag = 0; /* conforming */ - lintsrc.mpc_srcbusid = 0; - lintsrc.mpc_srcbusirq = 0; - lintsrc.mpc_destapic = MP_APIC_ALL; - for (i = 0; i < 2; i++) { - lintsrc.mpc_irqtype = linttypes[i]; - lintsrc.mpc_destapiclint = i; - MP_lintsrc_info(&lintsrc); - } -} - -static struct intel_mp_floating *mpf_found; - -/* - * Scan the memory blocks for an SMP configuration block. - */ -void __init get_smp_config (void) -{ - struct intel_mp_floating *mpf = mpf_found; - - /* - * ACPI supports both logical (e.g. Hyper-Threading) and physical - * processors, where MPS only supports physical. - */ - if (acpi_lapic && acpi_ioapic) { - printk(KERN_INFO "Using ACPI (MADT) for SMP configuration information\n"); - return; - } - else if (acpi_lapic) - printk(KERN_INFO "Using ACPI for processor (LAPIC) configuration information\n"); - - printk("Intel MultiProcessor Specification v1.%d\n", mpf->mpf_specification); - - /* - * Now see if we need to read further. - */ - if (mpf->mpf_feature1 != 0) { - - printk(KERN_INFO "Default MP configuration #%d\n", mpf->mpf_feature1); - construct_default_ISA_mptable(mpf->mpf_feature1); - - } else if (mpf->mpf_physptr) { - - /* - * Read the physical hardware table. Anything here will - * override the defaults. - */ - if (!smp_read_mpc(phys_to_virt(mpf->mpf_physptr))) { - smp_found_config = 0; - printk(KERN_ERR "BIOS bug, MP table errors detected!...\n"); - printk(KERN_ERR "... disabling SMP support. (tell your hw vendor)\n"); - return; - } - /* - * If there are no explicit MP IRQ entries, then we are - * broken. We set up most of the low 16 IO-APIC pins to - * ISA defaults and hope it will work. - */ - if (!mp_irq_entries) { - struct mpc_config_bus bus; - - printk(KERN_ERR "BIOS bug, no explicit IRQ entries, using default mptable. (tell your hw vendor)\n"); - - bus.mpc_type = MP_BUS; - bus.mpc_busid = 0; - memcpy(bus.mpc_bustype, "ISA ", 6); - MP_bus_info(&bus); - - construct_default_ioirq_mptable(0); - } - - } else - BUG(); - - printk(KERN_INFO "Processors: %d\n", num_processors); - /* - * Only use the first configuration found. - */ -} - -static int __init smp_scan_config (unsigned long base, unsigned long length) -{ - extern void __bad_mpf_size(void); - unsigned int *bp = phys_to_virt(base); - struct intel_mp_floating *mpf; - - Dprintk("Scan SMP from %p for %ld bytes.\n", bp,length); - if (sizeof(*mpf) != 16) - __bad_mpf_size(); - - while (length > 0) { - mpf = (struct intel_mp_floating *)bp; - if ((*bp == SMP_MAGIC_IDENT) && - (mpf->mpf_length == 1) && - !mpf_checksum((unsigned char *)bp, 16) && - ((mpf->mpf_specification == 1) - || (mpf->mpf_specification == 4)) ) { - - smp_found_config = 1; - reserve_bootmem_generic(virt_to_phys(mpf), PAGE_SIZE); - if (mpf->mpf_physptr) - reserve_bootmem_generic(mpf->mpf_physptr, PAGE_SIZE); - mpf_found = mpf; - return 1; - } - bp += 4; - length -= 16; - } - return 0; -} - -void __init find_smp_config(void) -{ - unsigned int address; - - /* - * FIXME: Linux assumes you have 640K of base ram.. - * this continues the error... - * - * 1) Scan the bottom 1K for a signature - * 2) Scan the top 1K of base RAM - * 3) Scan the 64K of bios - */ - if (smp_scan_config(0x0,0x400) || - smp_scan_config(639*0x400,0x400) || - smp_scan_config(0xF0000,0x10000)) - return; - /* - * If it is an SMP machine we should know now. - * - * there is a real-mode segmented pointer pointing to the - * 4K EBDA area at 0x40E, calculate and scan it here. - * - * NOTE! There are Linux loaders that will corrupt the EBDA - * area, and as such this kind of SMP config may be less - * trustworthy, simply because the SMP table may have been - * stomped on during early boot. These loaders are buggy and - * should be fixed. - */ - - address = *(unsigned short *)phys_to_virt(0x40E); - address <<= 4; - if (smp_scan_config(address, 0x1000)) - return; - - /* If we have come this far, we did not find an MP table */ - printk(KERN_INFO "No mptable found.\n"); -} - -/* -------------------------------------------------------------------------- - ACPI-based MP Configuration - -------------------------------------------------------------------------- */ - -#ifdef CONFIG_ACPI - -void __init mp_register_lapic_address(u64 address) -{ - mp_lapic_addr = (unsigned long) address; - set_fixmap_nocache(FIX_APIC_BASE, mp_lapic_addr); - if (boot_cpu_id == -1U) - boot_cpu_id = GET_APIC_ID(apic_read(APIC_ID)); -} - -void __cpuinit mp_register_lapic (u8 id, u8 enabled) -{ - struct mpc_config_processor processor; - int boot_cpu = 0; - - if (id == boot_cpu_id) - boot_cpu = 1; - - processor.mpc_type = MP_PROCESSOR; - processor.mpc_apicid = id; - processor.mpc_apicver = 0; - processor.mpc_cpuflag = (enabled ? CPU_ENABLED : 0); - processor.mpc_cpuflag |= (boot_cpu ? CPU_BOOTPROCESSOR : 0); - processor.mpc_cpufeature = 0; - processor.mpc_featureflag = 0; - processor.mpc_reserved[0] = 0; - processor.mpc_reserved[1] = 0; - - MP_processor_info(&processor); -} - -#define MP_ISA_BUS 0 -#define MP_MAX_IOAPIC_PIN 127 - -static struct mp_ioapic_routing { - int apic_id; - int gsi_start; - int gsi_end; - u32 pin_programmed[4]; -} 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_start) - && (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 uniq_ioapic_id(u8 id) -{ - 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); -} - -void __init mp_register_ioapic(u8 id, u32 address, u32 gsi_base) -{ - int idx = 0; - - if (bad_ioapic(address)) - return; - - idx = nr_ioapics; - - mp_ioapics[idx].mpc_type = MP_IOAPIC; - mp_ioapics[idx].mpc_flags = MPC_APIC_USABLE; - mp_ioapics[idx].mpc_apicaddr = address; - - set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address); - mp_ioapics[idx].mpc_apicid = uniq_ioapic_id(id); - mp_ioapics[idx].mpc_apicver = 0; - - /* - * Build basic IRQ lookup table to facilitate gsi->io_apic lookups - * and to prevent reprogramming of IOAPIC pins (PCI IRQs). - */ - mp_ioapic_routing[idx].apic_id = mp_ioapics[idx].mpc_apicid; - mp_ioapic_routing[idx].gsi_start = gsi_base; - mp_ioapic_routing[idx].gsi_end = gsi_base + - io_apic_get_redir_entries(idx); - - printk(KERN_INFO "IOAPIC[%d]: apic_id %d, address 0x%x, " - "GSI %d-%d\n", idx, mp_ioapics[idx].mpc_apicid, - mp_ioapics[idx].mpc_apicaddr, - mp_ioapic_routing[idx].gsi_start, - mp_ioapic_routing[idx].gsi_end); - - nr_ioapics++; -} - -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; - - /* - * Convert 'gsi' to 'ioapic.pin'. - */ - ioapic = mp_find_ioapic(gsi); - if (ioapic < 0) - return; - pin = gsi - mp_ioapic_routing[ioapic].gsi_start; - - /* - * 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; - - 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# */ - - Dprintk("Int: type %d, pol %d, trig %d, bus %d, irq %d, %d-%d\n", - intsrc.mpc_irqtype, intsrc.mpc_irqflag & 3, - (intsrc.mpc_irqflag >> 2) & 3, intsrc.mpc_srcbus, - intsrc.mpc_srcbusirq, intsrc.mpc_dstapic, intsrc.mpc_dstirq); - - mp_irqs[mp_irq_entries] = intsrc; - if (++mp_irq_entries == MAX_IRQ_SOURCES) - panic("Max # of irq sources exceeded!\n"); -} - -void __init mp_config_acpi_legacy_irqs(void) -{ - struct mpc_config_intsrc intsrc; - int i = 0; - int ioapic = -1; - - /* - * Fabricate the legacy ISA bus (bus #31). - */ - set_bit(MP_ISA_BUS, mp_bus_not_pci); - - /* - * Locate the IOAPIC that manages the ISA IRQs (0-15). - */ - ioapic = mp_find_ioapic(0); - if (ioapic < 0) - return; - - intsrc.mpc_type = MP_INTSRC; - intsrc.mpc_irqflag = 0; /* Conforming */ - intsrc.mpc_srcbus = MP_ISA_BUS; - intsrc.mpc_dstapic = mp_ioapics[ioapic].mpc_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 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; - - Dprintk("Int: type %d, pol %d, trig %d, bus %d, irq %d, " - "%d-%d\n", intsrc.mpc_irqtype, intsrc.mpc_irqflag & 3, - (intsrc.mpc_irqflag >> 2) & 3, intsrc.mpc_srcbus, - intsrc.mpc_srcbusirq, intsrc.mpc_dstapic, - intsrc.mpc_dstirq); - - mp_irqs[mp_irq_entries] = intsrc; - if (++mp_irq_entries == MAX_IRQ_SOURCES) - panic("Max # of irq sources exceeded!\n"); - } -} - -int mp_register_gsi(u32 gsi, int triggering, int polarity) -{ - int ioapic = -1; - int ioapic_pin = 0; - int idx, bit = 0; - - if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC) - return gsi; - - /* 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_start; - - /* - * Avoid pin reprogramming. PRTs typically include entries - * with redundant pin->gsi mappings (but unique PCI devices); - * we only program the IOAPIC on the first. - */ - bit = ioapic_pin % 32; - idx = (ioapic_pin < 32) ? 0 : (ioapic_pin / 32); - if (idx > 3) { - printk(KERN_ERR "Invalid reference to IOAPIC pin " - "%d-%d\n", mp_ioapic_routing[ioapic].apic_id, - ioapic_pin); - return gsi; - } - if ((1<<bit) & mp_ioapic_routing[ioapic].pin_programmed[idx]) { - Dprintk(KERN_DEBUG "Pin %d-%d already programmed\n", - mp_ioapic_routing[ioapic].apic_id, ioapic_pin); - return gsi; - } - - mp_ioapic_routing[ioapic].pin_programmed[idx] |= (1<<bit); - - io_apic_set_pci_routing(ioapic, ioapic_pin, gsi, - triggering == ACPI_EDGE_SENSITIVE ? 0 : 1, - polarity == ACPI_ACTIVE_HIGH ? 0 : 1); - return gsi; -} -#endif /*CONFIG_ACPI*/ diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index af51ea8400b2..1f3abe048e93 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -65,8 +65,8 @@ static loff_t msr_seek(struct file *file, loff_t offset, int orig) return ret; } -static ssize_t msr_read(struct file *file, char __user * buf, - size_t count, loff_t * ppos) +static ssize_t msr_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) { u32 __user *tmp = (u32 __user *) buf; u32 data[2]; @@ -162,12 +162,10 @@ static int __cpuinit msr_class_cpu_callback(struct notifier_block *nfb, err = msr_device_create(cpu); break; case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: case CPU_DEAD: msr_device_destroy(cpu); break; - case CPU_UP_CANCELED_FROZEN: - destroy_suspended_device(msr_class, MKDEV(MSR_MAJOR, cpu)); - break; } return err ? NOTIFY_BAD : NOTIFY_OK; } diff --git a/arch/x86/kernel/nmi_32.c b/arch/x86/kernel/nmi_32.c index 6a0aa7038685..11b14bbaa61e 100644 --- a/arch/x86/kernel/nmi_32.c +++ b/arch/x86/kernel/nmi_32.c @@ -22,9 +22,11 @@ #include <linux/cpumask.h> #include <linux/kernel_stat.h> #include <linux/kdebug.h> +#include <linux/slab.h> #include <asm/smp.h> #include <asm/nmi.h> +#include <asm/timer.h> #include "mach_traps.h" @@ -67,7 +69,7 @@ static __init void nmi_cpu_busy(void *data) } #endif -static int __init check_nmi_watchdog(void) +int __init check_nmi_watchdog(void) { unsigned int *prev_nmi_count; int cpu; @@ -80,7 +82,7 @@ static int __init check_nmi_watchdog(void) prev_nmi_count = kmalloc(NR_CPUS * sizeof(int), GFP_KERNEL); if (!prev_nmi_count) - return -1; + goto error; printk(KERN_INFO "Testing NMI watchdog ... "); @@ -117,7 +119,7 @@ static int __init check_nmi_watchdog(void) if (!atomic_read(&nmi_active)) { kfree(prev_nmi_count); atomic_set(&nmi_active, -1); - return -1; + goto error; } printk("OK.\n"); @@ -128,9 +130,11 @@ static int __init check_nmi_watchdog(void) kfree(prev_nmi_count); return 0; +error: + timer_ack = !cpu_has_tsc; + + return -1; } -/* This needs to happen later in boot so counters are working */ -late_initcall(check_nmi_watchdog); static int __init setup_nmi_watchdog(char *str) { @@ -317,7 +321,8 @@ EXPORT_SYMBOL(touch_nmi_watchdog); extern void die_nmi(struct pt_regs *, const char *msg); -__kprobes int nmi_watchdog_tick(struct pt_regs * regs, unsigned reason) +notrace __kprobes int +nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) { /* diff --git a/arch/x86/kernel/nmi_64.c b/arch/x86/kernel/nmi_64.c index 9a4fde74bee1..5a29ded994fa 100644 --- a/arch/x86/kernel/nmi_64.c +++ b/arch/x86/kernel/nmi_64.c @@ -26,6 +26,8 @@ #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; @@ -311,7 +313,8 @@ void touch_nmi_watchdog(void) } EXPORT_SYMBOL(touch_nmi_watchdog); -int __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason) +notrace __kprobes int +nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) { int sum; int touched = 0; @@ -382,7 +385,8 @@ int __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason) static unsigned ignore_nmis; -asmlinkage __kprobes void do_nmi(struct pt_regs * regs, long error_code) +asmlinkage notrace __kprobes void +do_nmi(struct pt_regs *regs, long error_code) { nmi_enter(); add_pda(__nmi_count,1); diff --git a/arch/x86/kernel/olpc.c b/arch/x86/kernel/olpc.c new file mode 100644 index 000000000000..3e6672274807 --- /dev/null +++ b/arch/x86/kernel/olpc.c @@ -0,0 +1,260 @@ +/* + * Support for the OLPC DCON and OLPC EC access + * + * Copyright © 2006 Advanced Micro Devices, Inc. + * Copyright © 2007-2008 Andres Salomon <dilinger@debian.org> + * + * 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. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/delay.h> +#include <linux/spinlock.h> +#include <linux/io.h> +#include <linux/string.h> +#include <asm/geode.h> +#include <asm/olpc.h> + +#ifdef CONFIG_OPEN_FIRMWARE +#include <asm/ofw.h> +#endif + +struct olpc_platform_t olpc_platform_info; +EXPORT_SYMBOL_GPL(olpc_platform_info); + +static DEFINE_SPINLOCK(ec_lock); + +/* what the timeout *should* be (in ms) */ +#define EC_BASE_TIMEOUT 20 + +/* the timeout that bugs in the EC might force us to actually use */ +static int ec_timeout = EC_BASE_TIMEOUT; + +static int __init olpc_ec_timeout_set(char *str) +{ + if (get_option(&str, &ec_timeout) != 1) { + ec_timeout = EC_BASE_TIMEOUT; + printk(KERN_ERR "olpc-ec: invalid argument to " + "'olpc_ec_timeout=', ignoring!\n"); + } + printk(KERN_DEBUG "olpc-ec: using %d ms delay for EC commands.\n", + ec_timeout); + return 1; +} +__setup("olpc_ec_timeout=", olpc_ec_timeout_set); + +/* + * These {i,o}bf_status functions return whether the buffers are full or not. + */ + +static inline unsigned int ibf_status(unsigned int port) +{ + return !!(inb(port) & 0x02); +} + +static inline unsigned int obf_status(unsigned int port) +{ + return inb(port) & 0x01; +} + +#define wait_on_ibf(p, d) __wait_on_ibf(__LINE__, (p), (d)) +static int __wait_on_ibf(unsigned int line, unsigned int port, int desired) +{ + unsigned int timeo; + int state = ibf_status(port); + + for (timeo = ec_timeout; state != desired && timeo; timeo--) { + mdelay(1); + state = ibf_status(port); + } + + if ((state == desired) && (ec_timeout > EC_BASE_TIMEOUT) && + timeo < (ec_timeout - EC_BASE_TIMEOUT)) { + printk(KERN_WARNING "olpc-ec: %d: waited %u ms for IBF!\n", + line, ec_timeout - timeo); + } + + return !(state == desired); +} + +#define wait_on_obf(p, d) __wait_on_obf(__LINE__, (p), (d)) +static int __wait_on_obf(unsigned int line, unsigned int port, int desired) +{ + unsigned int timeo; + int state = obf_status(port); + + for (timeo = ec_timeout; state != desired && timeo; timeo--) { + mdelay(1); + state = obf_status(port); + } + + if ((state == desired) && (ec_timeout > EC_BASE_TIMEOUT) && + timeo < (ec_timeout - EC_BASE_TIMEOUT)) { + printk(KERN_WARNING "olpc-ec: %d: waited %u ms for OBF!\n", + line, ec_timeout - timeo); + } + + return !(state == desired); +} + +/* + * This allows the kernel to run Embedded Controller commands. The EC is + * documented at <http://wiki.laptop.org/go/Embedded_controller>, and the + * available EC commands are here: + * <http://wiki.laptop.org/go/Ec_specification>. Unfortunately, while + * OpenFirmware's source is available, the EC's is not. + */ +int olpc_ec_cmd(unsigned char cmd, unsigned char *inbuf, size_t inlen, + unsigned char *outbuf, size_t outlen) +{ + unsigned long flags; + int ret = -EIO; + int i; + + spin_lock_irqsave(&ec_lock, flags); + + /* Clear OBF */ + for (i = 0; i < 10 && (obf_status(0x6c) == 1); i++) + inb(0x68); + if (i == 10) { + printk(KERN_ERR "olpc-ec: timeout while attempting to " + "clear OBF flag!\n"); + goto err; + } + + if (wait_on_ibf(0x6c, 0)) { + printk(KERN_ERR "olpc-ec: timeout waiting for EC to " + "quiesce!\n"); + goto err; + } + +restart: + /* + * Note that if we time out during any IBF checks, that's a failure; + * we have to return. There's no way for the kernel to clear that. + * + * If we time out during an OBF check, we can restart the command; + * reissuing it will clear the OBF flag, and we should be alright. + * The OBF flag will sometimes misbehave due to what we believe + * is a hardware quirk.. + */ + printk(KERN_DEBUG "olpc-ec: running cmd 0x%x\n", cmd); + outb(cmd, 0x6c); + + if (wait_on_ibf(0x6c, 0)) { + printk(KERN_ERR "olpc-ec: timeout waiting for EC to read " + "command!\n"); + goto err; + } + + if (inbuf && inlen) { + /* write data to EC */ + for (i = 0; i < inlen; i++) { + if (wait_on_ibf(0x6c, 0)) { + printk(KERN_ERR "olpc-ec: timeout waiting for" + " EC accept data!\n"); + goto err; + } + printk(KERN_DEBUG "olpc-ec: sending cmd arg 0x%x\n", + inbuf[i]); + outb(inbuf[i], 0x68); + } + } + if (outbuf && outlen) { + /* read data from EC */ + for (i = 0; i < outlen; i++) { + if (wait_on_obf(0x6c, 1)) { + printk(KERN_ERR "olpc-ec: timeout waiting for" + " EC to provide data!\n"); + goto restart; + } + outbuf[i] = inb(0x68); + printk(KERN_DEBUG "olpc-ec: received 0x%x\n", + outbuf[i]); + } + } + + ret = 0; +err: + spin_unlock_irqrestore(&ec_lock, flags); + return ret; +} +EXPORT_SYMBOL_GPL(olpc_ec_cmd); + +#ifdef CONFIG_OPEN_FIRMWARE +static void __init platform_detect(void) +{ + size_t propsize; + u32 rev; + + if (ofw("getprop", 4, 1, NULL, "board-revision-int", &rev, 4, + &propsize) || propsize != 4) { + printk(KERN_ERR "ofw: getprop call failed!\n"); + rev = 0; + } + olpc_platform_info.boardrev = be32_to_cpu(rev); +} +#else +static void __init platform_detect(void) +{ + /* stopgap until OFW support is added to the kernel */ + olpc_platform_info.boardrev = be32_to_cpu(0xc2); +} +#endif + +static int __init olpc_init(void) +{ + unsigned char *romsig; + + /* The ioremap check is dangerous; limit what we run it on */ + if (!is_geode() || geode_has_vsa2()) + return 0; + + spin_lock_init(&ec_lock); + + romsig = ioremap(0xffffffc0, 16); + if (!romsig) + return 0; + + if (strncmp(romsig, "CL1 Q", 7)) + goto unmap; + if (strncmp(romsig+6, romsig+13, 3)) { + printk(KERN_INFO "OLPC BIOS signature looks invalid. " + "Assuming not OLPC\n"); + goto unmap; + } + + printk(KERN_INFO "OLPC board with OpenFirmware %.16s\n", romsig); + olpc_platform_info.flags |= OLPC_F_PRESENT; + + /* get the platform revision */ + platform_detect(); + + /* assume B1 and above models always have a DCON */ + if (olpc_board_at_least(olpc_board(0xb1))) + olpc_platform_info.flags |= OLPC_F_DCON; + + /* get the EC revision */ + olpc_ec_cmd(EC_FIRMWARE_REV, NULL, 0, + (unsigned char *) &olpc_platform_info.ecver, 1); + + /* check to see if the VSA exists */ + if (geode_has_vsa2()) + olpc_platform_info.flags |= OLPC_F_VSA; + + printk(KERN_INFO "OLPC board revision %s%X (EC=%x)\n", + ((olpc_platform_info.boardrev & 0xf) < 8) ? "pre" : "", + olpc_platform_info.boardrev >> 4, + olpc_platform_info.ecver); + +unmap: + iounmap(romsig); + return 0; +} + +postcore_initcall(olpc_init); diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 075962cc75ab..74f0c5ea2a03 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -206,13 +206,6 @@ static struct resource reserve_ioports = { .flags = IORESOURCE_IO | IORESOURCE_BUSY, }; -static struct resource reserve_iomem = { - .start = 0, - .end = -1, - .name = "paravirt-iomem", - .flags = IORESOURCE_MEM | IORESOURCE_BUSY, -}; - /* * Reserve the whole legacy IO space to prevent any legacy drivers * from wasting time probing for their hardware. This is a fairly @@ -222,16 +215,7 @@ static struct resource reserve_iomem = { */ int paravirt_disable_iospace(void) { - int ret; - - ret = request_resource(&ioport_resource, &reserve_ioports); - if (ret == 0) { - ret = request_resource(&iomem_resource, &reserve_iomem); - if (ret) - release_resource(&reserve_ioports); - } - - return ret; + return request_resource(&ioport_resource, &reserve_ioports); } static DEFINE_PER_CPU(enum paravirt_lazy_mode, paravirt_lazy_mode) = PARAVIRT_LAZY_NONE; @@ -382,11 +366,13 @@ struct pv_mmu_ops pv_mmu_ops = { .flush_tlb_single = native_flush_tlb_single, .flush_tlb_others = native_flush_tlb_others, - .alloc_pt = paravirt_nop, - .alloc_pd = paravirt_nop, - .alloc_pd_clone = paravirt_nop, - .release_pt = paravirt_nop, - .release_pd = paravirt_nop, + .alloc_pte = paravirt_nop, + .alloc_pmd = paravirt_nop, + .alloc_pmd_clone = paravirt_nop, + .alloc_pud = paravirt_nop, + .release_pte = paravirt_nop, + .release_pmd = paravirt_nop, + .release_pud = paravirt_nop, .set_pte = native_set_pte, .set_pte_at = native_set_pte_at, diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 1b5464c2434f..e28ec497e142 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -43,6 +43,7 @@ #include <asm/system.h> #include <asm/dma.h> #include <asm/rio.h> +#include <asm/bios_ebda.h> #ifdef CONFIG_CALGARY_IOMMU_ENABLED_BY_DEFAULT int use_calgary __read_mostly = 1; @@ -470,10 +471,11 @@ error: return 0; } -static dma_addr_t calgary_map_single(struct device *dev, void *vaddr, +static dma_addr_t calgary_map_single(struct device *dev, phys_addr_t paddr, size_t size, int direction) { dma_addr_t dma_handle = bad_dma_address; + void *vaddr = phys_to_virt(paddr); unsigned long uaddr; unsigned int npages; struct iommu_table *tbl = find_iommu_table(dev); @@ -1232,8 +1234,7 @@ static int __init calgary_init(void) error: do { - dev = pci_get_device_reverse(PCI_VENDOR_ID_IBM, - PCI_ANY_ID, dev); + dev = pci_get_device(PCI_VENDOR_ID_IBM, PCI_ANY_ID, dev); if (!dev) break; if (!is_cal_pci_dev(dev->device)) diff --git a/arch/x86/kernel/pci-dma_64.c b/arch/x86/kernel/pci-dma.c index 375cb2bc45be..0c37f16b6950 100644 --- a/arch/x86/kernel/pci-dma_64.c +++ b/arch/x86/kernel/pci-dma.c @@ -1,61 +1,370 @@ -/* - * Dynamic DMA mapping support. - */ - -#include <linux/types.h> -#include <linux/mm.h> -#include <linux/string.h> -#include <linux/pci.h> -#include <linux/module.h> +#include <linux/dma-mapping.h> #include <linux/dmar.h> -#include <asm/io.h> +#include <linux/bootmem.h> +#include <linux/pci.h> + +#include <asm/proto.h> +#include <asm/dma.h> #include <asm/gart.h> #include <asm/calgary.h> -int iommu_merge __read_mostly = 0; +int forbid_dac __read_mostly; +EXPORT_SYMBOL(forbid_dac); -dma_addr_t bad_dma_address __read_mostly; -EXPORT_SYMBOL(bad_dma_address); +const struct dma_mapping_ops *dma_ops; +EXPORT_SYMBOL(dma_ops); -/* This tells the BIO block layer to assume merging. Default to off - because we cannot guarantee merging later. */ -int iommu_bio_merge __read_mostly = 0; -EXPORT_SYMBOL(iommu_bio_merge); - -static int iommu_sac_force __read_mostly = 0; +static int iommu_sac_force __read_mostly; -int no_iommu __read_mostly; #ifdef CONFIG_IOMMU_DEBUG int panic_on_overflow __read_mostly = 1; int force_iommu __read_mostly = 1; #else int panic_on_overflow __read_mostly = 0; -int force_iommu __read_mostly= 0; +int force_iommu __read_mostly = 0; #endif +int iommu_merge __read_mostly = 0; + +int no_iommu __read_mostly; /* Set this to 1 if there is a HW IOMMU in the system */ int iommu_detected __read_mostly = 0; +/* This tells the BIO block layer to assume merging. Default to off + because we cannot guarantee merging later. */ +int iommu_bio_merge __read_mostly = 0; +EXPORT_SYMBOL(iommu_bio_merge); + +dma_addr_t bad_dma_address __read_mostly = 0; +EXPORT_SYMBOL(bad_dma_address); + /* Dummy device used for NULL arguments (normally ISA). Better would be probably a smaller DMA mask, but this is bug-to-bug compatible - to i386. */ + to older i386. */ struct device fallback_dev = { .bus_id = "fallback device", .coherent_dma_mask = DMA_32BIT_MASK, .dma_mask = &fallback_dev.coherent_dma_mask, }; +int dma_set_mask(struct device *dev, u64 mask) +{ + if (!dev->dma_mask || !dma_supported(dev, mask)) + return -EIO; + + *dev->dma_mask = mask; + + return 0; +} +EXPORT_SYMBOL(dma_set_mask); + +#ifdef CONFIG_X86_64 +static __initdata void *dma32_bootmem_ptr; +static unsigned long dma32_bootmem_size __initdata = (128ULL<<20); + +static int __init parse_dma32_size_opt(char *p) +{ + if (!p) + return -EINVAL; + dma32_bootmem_size = memparse(p, &p); + return 0; +} +early_param("dma32_size", parse_dma32_size_opt); + +void __init dma32_reserve_bootmem(void) +{ + unsigned long size, align; + if (end_pfn <= MAX_DMA32_PFN) + return; + + align = 64ULL<<20; + size = round_up(dma32_bootmem_size, align); + dma32_bootmem_ptr = __alloc_bootmem_nopanic(size, align, + __pa(MAX_DMA_ADDRESS)); + if (dma32_bootmem_ptr) + dma32_bootmem_size = size; + else + dma32_bootmem_size = 0; +} +static void __init dma32_free_bootmem(void) +{ + int node; + + if (end_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); + + dma32_bootmem_ptr = NULL; + dma32_bootmem_size = 0; +} + +void __init pci_iommu_alloc(void) +{ + /* free the range so iommu could get some range less than 4G */ + dma32_free_bootmem(); + /* + * The order of these functions is important for + * fall-back/fail-over reasons + */ +#ifdef CONFIG_GART_IOMMU + gart_iommu_hole_init(); +#endif + +#ifdef CONFIG_CALGARY_IOMMU + detect_calgary(); +#endif + + detect_intel_iommu(); + +#ifdef CONFIG_SWIOTLB + pci_swiotlb_init(); +#endif +} +#endif + +/* + * See <Documentation/x86_64/boot-options.txt> for the iommu kernel parameter + * documentation. + */ +static __init int iommu_setup(char *p) +{ + iommu_merge = 1; + + if (!p) + return -EINVAL; + + while (*p) { + if (!strncmp(p, "off", 3)) + no_iommu = 1; + /* gart_parse_options has more force support */ + if (!strncmp(p, "force", 5)) + force_iommu = 1; + if (!strncmp(p, "noforce", 7)) { + iommu_merge = 0; + force_iommu = 0; + } + + if (!strncmp(p, "biomerge", 8)) { + iommu_bio_merge = 4096; + iommu_merge = 1; + force_iommu = 1; + } + if (!strncmp(p, "panic", 5)) + panic_on_overflow = 1; + if (!strncmp(p, "nopanic", 7)) + panic_on_overflow = 0; + if (!strncmp(p, "merge", 5)) { + iommu_merge = 1; + force_iommu = 1; + } + if (!strncmp(p, "nomerge", 7)) + iommu_merge = 0; + if (!strncmp(p, "forcesac", 8)) + iommu_sac_force = 1; + if (!strncmp(p, "allowdac", 8)) + forbid_dac = 0; + if (!strncmp(p, "nodac", 5)) + forbid_dac = -1; + if (!strncmp(p, "usedac", 6)) { + forbid_dac = -1; + return 1; + } +#ifdef CONFIG_SWIOTLB + if (!strncmp(p, "soft", 4)) + swiotlb = 1; +#endif + +#ifdef CONFIG_GART_IOMMU + gart_parse_options(p); +#endif + +#ifdef CONFIG_CALGARY_IOMMU + if (!strncmp(p, "calgary", 7)) + use_calgary = 1; +#endif /* CONFIG_CALGARY_IOMMU */ + + p += strcspn(p, ","); + if (*p == ',') + ++p; + } + return 0; +} +early_param("iommu", iommu_setup); + +#ifdef CONFIG_X86_32 +int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr, + dma_addr_t device_addr, size_t size, int flags) +{ + void __iomem *mem_base = NULL; + int pages = size >> PAGE_SHIFT; + int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long); + + if ((flags & (DMA_MEMORY_MAP | DMA_MEMORY_IO)) == 0) + goto out; + if (!size) + goto out; + if (dev->dma_mem) + goto out; + + /* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */ + + mem_base = ioremap(bus_addr, size); + if (!mem_base) + goto out; + + dev->dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL); + if (!dev->dma_mem) + goto out; + dev->dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL); + if (!dev->dma_mem->bitmap) + goto free1_out; + + dev->dma_mem->virt_base = mem_base; + dev->dma_mem->device_base = device_addr; + dev->dma_mem->size = pages; + dev->dma_mem->flags = flags; + + if (flags & DMA_MEMORY_MAP) + return DMA_MEMORY_MAP; + + return DMA_MEMORY_IO; + + free1_out: + kfree(dev->dma_mem); + out: + if (mem_base) + iounmap(mem_base); + return 0; +} +EXPORT_SYMBOL(dma_declare_coherent_memory); + +void dma_release_declared_memory(struct device *dev) +{ + struct dma_coherent_mem *mem = dev->dma_mem; + + if (!mem) + return; + dev->dma_mem = NULL; + iounmap(mem->virt_base); + kfree(mem->bitmap); + kfree(mem); +} +EXPORT_SYMBOL(dma_release_declared_memory); + +void *dma_mark_declared_memory_occupied(struct device *dev, + dma_addr_t device_addr, size_t size) +{ + struct dma_coherent_mem *mem = dev->dma_mem; + int pos, err; + int pages = (size + (device_addr & ~PAGE_MASK) + PAGE_SIZE - 1); + + pages >>= PAGE_SHIFT; + + if (!mem) + return ERR_PTR(-EINVAL); + + pos = (device_addr - mem->device_base) >> PAGE_SHIFT; + err = bitmap_allocate_region(mem->bitmap, pos, get_order(pages)); + if (err != 0) + return ERR_PTR(err); + return mem->virt_base + (pos << PAGE_SHIFT); +} +EXPORT_SYMBOL(dma_mark_declared_memory_occupied); + +static int dma_alloc_from_coherent_mem(struct device *dev, ssize_t size, + dma_addr_t *dma_handle, void **ret) +{ + struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL; + int order = get_order(size); + + if (mem) { + int page = bitmap_find_free_region(mem->bitmap, mem->size, + order); + if (page >= 0) { + *dma_handle = mem->device_base + (page << PAGE_SHIFT); + *ret = mem->virt_base + (page << PAGE_SHIFT); + memset(*ret, 0, size); + } + if (mem->flags & DMA_MEMORY_EXCLUSIVE) + *ret = NULL; + } + return (mem != NULL); +} + +static int dma_release_coherent(struct device *dev, int order, void *vaddr) +{ + struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL; + + if (mem && vaddr >= mem->virt_base && vaddr < + (mem->virt_base + (mem->size << PAGE_SHIFT))) { + int page = (vaddr - mem->virt_base) >> PAGE_SHIFT; + + bitmap_release_region(mem->bitmap, page, order); + return 1; + } + return 0; +} +#else +#define dma_alloc_from_coherent_mem(dev, size, handle, ret) (0) +#define dma_release_coherent(dev, order, vaddr) (0) +#endif /* CONFIG_X86_32 */ + +int dma_supported(struct device *dev, u64 mask) +{ +#ifdef CONFIG_PCI + if (mask > 0xffffffff && forbid_dac > 0) { + printk(KERN_INFO "PCI: Disallowing DAC for device %s\n", + dev->bus_id); + return 0; + } +#endif + + if (dma_ops->dma_supported) + return dma_ops->dma_supported(dev, mask); + + /* Copied from i386. Doesn't make much sense, because it will + only work for pci_alloc_coherent. + The caller just has to use GFP_DMA in this case. */ + if (mask < DMA_24BIT_MASK) + return 0; + + /* Tell the device to use SAC when IOMMU force is on. This + allows the driver to use cheaper accesses in some cases. + + Problem with this is that if we overflow the IOMMU area and + return DAC as fallback address the device may not handle it + correctly. + + As a special case some controllers have a 39bit address + mode that is as efficient as 32bit (aic79xx). Don't force + SAC for these. Assume all masks <= 40 bits are of this + type. Normally this doesn't make any difference, but gives + more gentle handling of IOMMU overflow. */ + if (iommu_sac_force && (mask >= DMA_40BIT_MASK)) { + printk(KERN_INFO "%s: Force SAC with mask %Lx\n", + dev->bus_id, mask); + return 0; + } + + return 1; +} +EXPORT_SYMBOL(dma_supported); + /* Allocate DMA memory on node near device */ -noinline static void * +noinline struct page * dma_alloc_pages(struct device *dev, gfp_t gfp, unsigned order) { - struct page *page; int node; node = dev_to_node(dev); - page = alloc_pages_node(node, gfp, order); - return page ? page_address(page) : NULL; + return alloc_pages_node(node, gfp, order); } /* @@ -65,9 +374,16 @@ void * dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp) { - void *memory; + void *memory = NULL; + struct page *page; unsigned long dma_mask = 0; - u64 bus; + dma_addr_t bus; + + /* ignore region specifiers */ + gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); + + if (dma_alloc_from_coherent_mem(dev, size, dma_handle, &memory)) + return memory; if (!dev) dev = &fallback_dev; @@ -82,26 +398,25 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, /* Don't invoke OOM killer */ gfp |= __GFP_NORETRY; - /* Kludge to make it bug-to-bug compatible with i386. i386 - uses the normal dma_mask for alloc_coherent. */ - dma_mask &= *dev->dma_mask; - +#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_DMA32; +#endif again: - memory = dma_alloc_pages(dev, gfp, get_order(size)); - if (memory == NULL) + page = dma_alloc_pages(dev, gfp, get_order(size)); + if (page == NULL) return NULL; { int high, mmu; - bus = virt_to_bus(memory); - high = (bus + size) >= dma_mask; + bus = page_to_phys(page); + memory = page_address(page); + high = (bus + size) >= dma_mask; mmu = high; if (force_iommu && !(gfp & GFP_DMA)) mmu = 1; @@ -127,7 +442,7 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, memset(memory, 0, size); if (!mmu) { - *dma_handle = virt_to_bus(memory); + *dma_handle = bus; return memory; } } @@ -139,7 +454,7 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, } if (dma_ops->map_simple) { - *dma_handle = dma_ops->map_simple(dev, memory, + *dma_handle = dma_ops->map_simple(dev, virt_to_phys(memory), size, PCI_DMA_BIDIRECTIONAL); if (*dma_handle != bad_dma_address) @@ -147,7 +462,8 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, } if (panic_on_overflow) - panic("dma_alloc_coherent: IOMMU overflow by %lu bytes\n",size); + panic("dma_alloc_coherent: IOMMU overflow by %lu bytes\n", + (unsigned long)size); free_pages((unsigned long)memory, get_order(size)); return NULL; } @@ -160,153 +476,16 @@ EXPORT_SYMBOL(dma_alloc_coherent); void dma_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t bus) { + int order = get_order(size); WARN_ON(irqs_disabled()); /* for portability */ + if (dma_release_coherent(dev, order, vaddr)) + return; if (dma_ops->unmap_single) dma_ops->unmap_single(dev, bus, size, 0); - free_pages((unsigned long)vaddr, get_order(size)); + free_pages((unsigned long)vaddr, order); } EXPORT_SYMBOL(dma_free_coherent); -static int forbid_dac __read_mostly; - -int dma_supported(struct device *dev, u64 mask) -{ -#ifdef CONFIG_PCI - if (mask > 0xffffffff && forbid_dac > 0) { - - - - printk(KERN_INFO "PCI: Disallowing DAC for device %s\n", dev->bus_id); - return 0; - } -#endif - - if (dma_ops->dma_supported) - return dma_ops->dma_supported(dev, mask); - - /* Copied from i386. Doesn't make much sense, because it will - only work for pci_alloc_coherent. - The caller just has to use GFP_DMA in this case. */ - if (mask < DMA_24BIT_MASK) - return 0; - - /* Tell the device to use SAC when IOMMU force is on. This - allows the driver to use cheaper accesses in some cases. - - Problem with this is that if we overflow the IOMMU area and - return DAC as fallback address the device may not handle it - correctly. - - As a special case some controllers have a 39bit address - mode that is as efficient as 32bit (aic79xx). Don't force - SAC for these. Assume all masks <= 40 bits are of this - type. Normally this doesn't make any difference, but gives - more gentle handling of IOMMU overflow. */ - if (iommu_sac_force && (mask >= DMA_40BIT_MASK)) { - printk(KERN_INFO "%s: Force SAC with mask %Lx\n", dev->bus_id,mask); - return 0; - } - - return 1; -} -EXPORT_SYMBOL(dma_supported); - -int dma_set_mask(struct device *dev, u64 mask) -{ - if (!dev->dma_mask || !dma_supported(dev, mask)) - return -EIO; - *dev->dma_mask = mask; - return 0; -} -EXPORT_SYMBOL(dma_set_mask); - -/* - * See <Documentation/x86_64/boot-options.txt> for the iommu kernel parameter - * documentation. - */ -static __init int iommu_setup(char *p) -{ - iommu_merge = 1; - - if (!p) - return -EINVAL; - - while (*p) { - if (!strncmp(p,"off",3)) - no_iommu = 1; - /* gart_parse_options has more force support */ - if (!strncmp(p,"force",5)) - force_iommu = 1; - if (!strncmp(p,"noforce",7)) { - iommu_merge = 0; - force_iommu = 0; - } - - if (!strncmp(p, "biomerge",8)) { - iommu_bio_merge = 4096; - iommu_merge = 1; - force_iommu = 1; - } - if (!strncmp(p, "panic",5)) - panic_on_overflow = 1; - if (!strncmp(p, "nopanic",7)) - panic_on_overflow = 0; - if (!strncmp(p, "merge",5)) { - iommu_merge = 1; - force_iommu = 1; - } - if (!strncmp(p, "nomerge",7)) - iommu_merge = 0; - if (!strncmp(p, "forcesac",8)) - iommu_sac_force = 1; - if (!strncmp(p, "allowdac", 8)) - forbid_dac = 0; - if (!strncmp(p, "nodac", 5)) - forbid_dac = -1; - -#ifdef CONFIG_SWIOTLB - if (!strncmp(p, "soft",4)) - swiotlb = 1; -#endif - -#ifdef CONFIG_GART_IOMMU - gart_parse_options(p); -#endif - -#ifdef CONFIG_CALGARY_IOMMU - if (!strncmp(p, "calgary", 7)) - use_calgary = 1; -#endif /* CONFIG_CALGARY_IOMMU */ - - p += strcspn(p, ","); - if (*p == ',') - ++p; - } - return 0; -} -early_param("iommu", iommu_setup); - -void __init pci_iommu_alloc(void) -{ - /* - * The order of these functions is important for - * fall-back/fail-over reasons - */ -#ifdef CONFIG_GART_IOMMU - gart_iommu_hole_init(); -#endif - -#ifdef CONFIG_CALGARY_IOMMU - detect_calgary(); -#endif - - detect_intel_iommu(); - -#ifdef CONFIG_SWIOTLB - pci_swiotlb_init(); -#endif -} - static int __init pci_iommu_init(void) { #ifdef CONFIG_CALGARY_IOMMU @@ -327,6 +506,8 @@ void pci_iommu_shutdown(void) { gart_iommu_shutdown(); } +/* Must execute after PCI subsystem */ +fs_initcall(pci_iommu_init); #ifdef CONFIG_PCI /* Many VIA bridges seem to corrupt data for DAC. Disable it here */ @@ -334,11 +515,10 @@ void pci_iommu_shutdown(void) static __devinit void via_no_dac(struct pci_dev *dev) { if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && forbid_dac == 0) { - printk(KERN_INFO "PCI: VIA PCI bridge detected. Disabling DAC.\n"); + printk(KERN_INFO "PCI: VIA PCI bridge detected." + "Disabling DAC.\n"); forbid_dac = 1; } } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID, via_no_dac); #endif -/* Must execute after PCI subsystem */ -fs_initcall(pci_iommu_init); diff --git a/arch/x86/kernel/pci-dma_32.c b/arch/x86/kernel/pci-dma_32.c deleted file mode 100644 index 51330321a5d3..000000000000 --- a/arch/x86/kernel/pci-dma_32.c +++ /dev/null @@ -1,177 +0,0 @@ -/* - * Dynamic DMA mapping support. - * - * On i386 there is no hardware dynamic DMA address translation, - * so consistent alloc/free are merely page allocation/freeing. - * The rest of the dynamic DMA mapping interface is implemented - * in asm/pci.h. - */ - -#include <linux/types.h> -#include <linux/mm.h> -#include <linux/string.h> -#include <linux/pci.h> -#include <linux/module.h> -#include <asm/io.h> - -struct dma_coherent_mem { - void *virt_base; - u32 device_base; - int size; - int flags; - unsigned long *bitmap; -}; - -void *dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp) -{ - void *ret; - struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL; - int order = get_order(size); - /* ignore region specifiers */ - gfp &= ~(__GFP_DMA | __GFP_HIGHMEM); - - if (mem) { - int page = bitmap_find_free_region(mem->bitmap, mem->size, - order); - if (page >= 0) { - *dma_handle = mem->device_base + (page << PAGE_SHIFT); - ret = mem->virt_base + (page << PAGE_SHIFT); - memset(ret, 0, size); - return ret; - } - if (mem->flags & DMA_MEMORY_EXCLUSIVE) - return NULL; - } - - if (dev == NULL || (dev->coherent_dma_mask < 0xffffffff)) - gfp |= GFP_DMA; - - ret = (void *)__get_free_pages(gfp, order); - - if (ret != NULL) { - memset(ret, 0, size); - *dma_handle = virt_to_phys(ret); - } - return ret; -} -EXPORT_SYMBOL(dma_alloc_coherent); - -void dma_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle) -{ - struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL; - int order = get_order(size); - - WARN_ON(irqs_disabled()); /* for portability */ - if (mem && vaddr >= mem->virt_base && vaddr < (mem->virt_base + (mem->size << PAGE_SHIFT))) { - int page = (vaddr - mem->virt_base) >> PAGE_SHIFT; - - bitmap_release_region(mem->bitmap, page, order); - } else - free_pages((unsigned long)vaddr, order); -} -EXPORT_SYMBOL(dma_free_coherent); - -int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr, - dma_addr_t device_addr, size_t size, int flags) -{ - void __iomem *mem_base = NULL; - int pages = size >> PAGE_SHIFT; - int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long); - - if ((flags & (DMA_MEMORY_MAP | DMA_MEMORY_IO)) == 0) - goto out; - if (!size) - goto out; - if (dev->dma_mem) - goto out; - - /* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */ - - mem_base = ioremap(bus_addr, size); - if (!mem_base) - goto out; - - dev->dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL); - if (!dev->dma_mem) - goto out; - dev->dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL); - if (!dev->dma_mem->bitmap) - goto free1_out; - - dev->dma_mem->virt_base = mem_base; - dev->dma_mem->device_base = device_addr; - dev->dma_mem->size = pages; - dev->dma_mem->flags = flags; - - if (flags & DMA_MEMORY_MAP) - return DMA_MEMORY_MAP; - - return DMA_MEMORY_IO; - - free1_out: - kfree(dev->dma_mem); - out: - if (mem_base) - iounmap(mem_base); - return 0; -} -EXPORT_SYMBOL(dma_declare_coherent_memory); - -void dma_release_declared_memory(struct device *dev) -{ - struct dma_coherent_mem *mem = dev->dma_mem; - - if(!mem) - return; - dev->dma_mem = NULL; - iounmap(mem->virt_base); - kfree(mem->bitmap); - kfree(mem); -} -EXPORT_SYMBOL(dma_release_declared_memory); - -void *dma_mark_declared_memory_occupied(struct device *dev, - dma_addr_t device_addr, size_t size) -{ - struct dma_coherent_mem *mem = dev->dma_mem; - int pages = (size + (device_addr & ~PAGE_MASK) + PAGE_SIZE - 1) >> PAGE_SHIFT; - int pos, err; - - if (!mem) - return ERR_PTR(-EINVAL); - - pos = (device_addr - mem->device_base) >> PAGE_SHIFT; - err = bitmap_allocate_region(mem->bitmap, pos, get_order(pages)); - if (err != 0) - return ERR_PTR(err); - return mem->virt_base + (pos << PAGE_SHIFT); -} -EXPORT_SYMBOL(dma_mark_declared_memory_occupied); - -#ifdef CONFIG_PCI -/* Many VIA bridges seem to corrupt data for DAC. Disable it here */ - -int forbid_dac; -EXPORT_SYMBOL(forbid_dac); - -static __devinit void via_no_dac(struct pci_dev *dev) -{ - if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && forbid_dac == 0) { - printk(KERN_INFO "PCI: VIA PCI bridge detected. Disabling DAC.\n"); - forbid_dac = 1; - } -} -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID, via_no_dac); - -static int check_iommu(char *s) -{ - if (!strcmp(s, "usedac")) { - forbid_dac = -1; - return 1; - } - return 0; -} -__setup("iommu=", check_iommu); -#endif diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index 700e4647dd30..c07455d1695f 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -264,9 +264,9 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem, } static dma_addr_t -gart_map_simple(struct device *dev, char *buf, size_t size, int dir) +gart_map_simple(struct device *dev, phys_addr_t paddr, size_t size, int dir) { - dma_addr_t map = dma_map_area(dev, virt_to_bus(buf), size, dir); + dma_addr_t map = dma_map_area(dev, paddr, size, dir); flush_gart(); @@ -275,18 +275,17 @@ gart_map_simple(struct device *dev, char *buf, size_t size, int dir) /* Map a single area into the IOMMU */ static dma_addr_t -gart_map_single(struct device *dev, void *addr, size_t size, int dir) +gart_map_single(struct device *dev, phys_addr_t paddr, size_t size, int dir) { - unsigned long phys_mem, bus; + unsigned long bus; if (!dev) dev = &fallback_dev; - phys_mem = virt_to_phys(addr); - if (!need_iommu(dev, phys_mem, size)) - return phys_mem; + if (!need_iommu(dev, paddr, size)) + return paddr; - bus = gart_map_simple(dev, addr, size, dir); + bus = gart_map_simple(dev, paddr, size, dir); return bus; } diff --git a/arch/x86/kernel/pci-nommu_64.c b/arch/x86/kernel/pci-nommu.c index ab08e1832228..aec43d56f49c 100644 --- a/arch/x86/kernel/pci-nommu_64.c +++ b/arch/x86/kernel/pci-nommu.c @@ -14,7 +14,7 @@ static int check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size) { - if (hwdev && bus + size > *hwdev->dma_mask) { + if (hwdev && bus + size > *hwdev->dma_mask) { if (*hwdev->dma_mask >= DMA_32BIT_MASK) printk(KERN_ERR "nommu_%s: overflow %Lx+%zu of device mask %Lx\n", @@ -26,19 +26,17 @@ check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size) } static dma_addr_t -nommu_map_single(struct device *hwdev, void *ptr, size_t size, +nommu_map_single(struct device *hwdev, phys_addr_t paddr, size_t size, int direction) { - dma_addr_t bus = virt_to_bus(ptr); + dma_addr_t bus = paddr; + WARN_ON(size == 0); if (!check_addr("map_single", hwdev, bus, size)) return bad_dma_address; + flush_write_buffers(); return bus; } -static void nommu_unmap_single(struct device *dev, dma_addr_t addr,size_t size, - int direction) -{ -} /* Map a set of buffers described by scatterlist in streaming * mode for DMA. This is the scatter-gather version of the @@ -61,30 +59,34 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg, struct scatterlist *s; int i; + WARN_ON(nents == 0 || sg[0].length == 0); + for_each_sg(sg, s, nents, i) { BUG_ON(!sg_page(s)); - s->dma_address = virt_to_bus(sg_virt(s)); + s->dma_address = sg_phys(s); if (!check_addr("map_sg", hwdev, s->dma_address, s->length)) return 0; s->dma_length = s->length; } + flush_write_buffers(); return nents; } -/* Unmap a set of streaming mode DMA translations. - * Again, cpu read rules concerning calls here are the same as for - * pci_unmap_single() above. - */ -static void nommu_unmap_sg(struct device *dev, struct scatterlist *sg, - int nents, int dir) +/* Make sure we keep the same behaviour */ +static int nommu_mapping_error(dma_addr_t dma_addr) { +#ifdef CONFIG_X86_32 + return 0; +#else + return (dma_addr == bad_dma_address); +#endif } + const struct dma_mapping_ops nommu_dma_ops = { .map_single = nommu_map_single, - .unmap_single = nommu_unmap_single, .map_sg = nommu_map_sg, - .unmap_sg = nommu_unmap_sg, + .mapping_error = nommu_mapping_error, .is_phys = 1, }; diff --git a/arch/x86/kernel/pci-swiotlb_64.c b/arch/x86/kernel/pci-swiotlb_64.c index 82a0a674a003..490da7f4b8d0 100644 --- a/arch/x86/kernel/pci-swiotlb_64.c +++ b/arch/x86/kernel/pci-swiotlb_64.c @@ -11,11 +11,18 @@ int swiotlb __read_mostly; +static dma_addr_t +swiotlb_map_single_phys(struct device *hwdev, phys_addr_t paddr, size_t size, + int direction) +{ + return swiotlb_map_single(hwdev, phys_to_virt(paddr), size, direction); +} + const struct dma_mapping_ops swiotlb_dma_ops = { .mapping_error = swiotlb_dma_mapping_error, .alloc_coherent = swiotlb_alloc_coherent, .free_coherent = swiotlb_free_coherent, - .map_single = swiotlb_map_single, + .map_single = swiotlb_map_single_phys, .unmap_single = swiotlb_unmap_single, .sync_single_for_cpu = swiotlb_sync_single_for_cpu, .sync_single_for_device = swiotlb_sync_single_for_device, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c new file mode 100644 index 000000000000..67e9b4a1e89d --- /dev/null +++ b/arch/x86/kernel/process.c @@ -0,0 +1,161 @@ +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/slab.h> +#include <linux/sched.h> +#include <linux/module.h> +#include <linux/pm.h> + +struct kmem_cache *task_xstate_cachep; + +int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) +{ + *dst = *src; + if (src->thread.xstate) { + dst->thread.xstate = kmem_cache_alloc(task_xstate_cachep, + GFP_KERNEL); + if (!dst->thread.xstate) + return -ENOMEM; + WARN_ON((unsigned long)dst->thread.xstate & 15); + memcpy(dst->thread.xstate, src->thread.xstate, xstate_size); + } + return 0; +} + +void free_thread_xstate(struct task_struct *tsk) +{ + if (tsk->thread.xstate) { + kmem_cache_free(task_xstate_cachep, tsk->thread.xstate); + tsk->thread.xstate = NULL; + } +} + +void free_thread_info(struct thread_info *ti) +{ + free_thread_xstate(ti->task); + free_pages((unsigned long)ti, get_order(THREAD_SIZE)); +} + +void arch_task_cache_init(void) +{ + task_xstate_cachep = + kmem_cache_create("task_xstate", xstate_size, + __alignof__(union thread_xstate), + SLAB_PANIC, NULL); +} + +static void do_nothing(void *unused) +{ +} + +/* + * cpu_idle_wait - Used to ensure that all the CPUs discard old value of + * pm_idle and update to new pm_idle value. Required while changing pm_idle + * handler on SMP systems. + * + * Caller must have changed pm_idle to the new value before the call. Old + * pm_idle value will not be used by any CPU after the return of this function. + */ +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); +} +EXPORT_SYMBOL_GPL(cpu_idle_wait); + +/* + * This uses new MONITOR/MWAIT instructions on P4 processors with PNI, + * which can obviate IPI to trigger checking of need_resched. + * We execute MONITOR against need_resched and enter optimized wait state + * through MWAIT. Whenever someone changes need_resched, we would be woken + * up from MWAIT (without an IPI). + * + * New with Core Duo processors, MWAIT can take some hints based on CPU + * capability. + */ +void mwait_idle_with_hints(unsigned long ax, unsigned long cx) +{ + if (!need_resched()) { + __monitor((void *)¤t_thread_info()->flags, 0, 0); + smp_mb(); + if (!need_resched()) + __mwait(ax, cx); + } +} + +/* Default MONITOR/MWAIT with no hints, used for default C1 state */ +static void mwait_idle(void) +{ + if (!need_resched()) { + __monitor((void *)¤t_thread_info()->flags, 0, 0); + smp_mb(); + if (!need_resched()) + __sti_mwait(0, 0); + else + local_irq_enable(); + } else + local_irq_enable(); +} + + +static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c) +{ + if (force_mwait) + return 1; + /* Any C1 states supported? */ + return c->cpuid_level >= 5 && ((cpuid_edx(5) >> 4) & 0xf) > 0; +} + +/* + * On SMP it's slightly faster (but much more power-consuming!) + * to poll the ->work.need_resched flag instead of waiting for the + * cross-CPU IPI to arrive. Use this option with caution. + */ +static void poll_idle(void) +{ + local_irq_enable(); + cpu_relax(); +} + +void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) +{ + static int selected; + + if (selected) + return; +#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 (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; +} + +static int __init idle_setup(char *str) +{ + if (!strcmp(str, "poll")) { + printk("using polling idle threads.\n"); + pm_idle = poll_idle; + } else if (!strcmp(str, "mwait")) + force_mwait = 1; + else + return -1; + + boot_option_idle_override = 1; + return 0; +} +early_param("idle", idle_setup); + diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 43930e73f657..f8476dfbb60d 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -36,6 +36,7 @@ #include <linux/personality.h> #include <linux/tick.h> #include <linux/percpu.h> +#include <linux/prctl.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -45,7 +46,6 @@ #include <asm/processor.h> #include <asm/i387.h> #include <asm/desc.h> -#include <asm/vm86.h> #ifdef CONFIG_MATH_EMULATION #include <asm/math_emu.h> #endif @@ -111,22 +111,13 @@ void default_idle(void) */ smp_mb(); - local_irq_disable(); - if (!need_resched()) { - ktime_t t0, t1; - u64 t0n, t1n; - - t0 = ktime_get(); - t0n = ktime_to_ns(t0); + if (!need_resched()) safe_halt(); /* enables interrupts racelessly */ - local_irq_disable(); - t1 = ktime_get(); - t1n = ktime_to_ns(t1); - sched_clock_idle_wakeup_event(t1n - t0n); - } - local_irq_enable(); + else + local_irq_enable(); current_thread_info()->status |= TS_POLLING; } else { + local_irq_enable(); /* loop is done by the caller */ cpu_relax(); } @@ -135,16 +126,6 @@ void default_idle(void) EXPORT_SYMBOL(default_idle); #endif -/* - * On SMP it's slightly faster (but much more power-consuming!) - * to poll the ->work.need_resched flag instead of waiting for the - * cross-CPU IPI to arrive. Use this option with caution. - */ -static void poll_idle(void) -{ - cpu_relax(); -} - #ifdef CONFIG_HOTPLUG_CPU #include <asm/nmi.h> /* We don't actually take CPU down, just spin without interrupts. */ @@ -202,6 +183,7 @@ void cpu_idle(void) if (cpu_is_offline(cpu)) play_dead(); + local_irq_disable(); __get_cpu_var(irq_stat).idle_timestamp = jiffies; idle(); } @@ -212,101 +194,6 @@ void cpu_idle(void) } } -static void do_nothing(void *unused) -{ -} - -/* - * cpu_idle_wait - Used to ensure that all the CPUs discard old value of - * pm_idle and update to new pm_idle value. Required while changing pm_idle - * handler on SMP systems. - * - * Caller must have changed pm_idle to the new value before the call. Old - * pm_idle value will not be used by any CPU after the return of this function. - */ -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); -} -EXPORT_SYMBOL_GPL(cpu_idle_wait); - -/* - * This uses new MONITOR/MWAIT instructions on P4 processors with PNI, - * which can obviate IPI to trigger checking of need_resched. - * We execute MONITOR against need_resched and enter optimized wait state - * through MWAIT. Whenever someone changes need_resched, we would be woken - * up from MWAIT (without an IPI). - * - * New with Core Duo processors, MWAIT can take some hints based on CPU - * capability. - */ -void mwait_idle_with_hints(unsigned long ax, unsigned long cx) -{ - if (!need_resched()) { - __monitor((void *)¤t_thread_info()->flags, 0, 0); - smp_mb(); - if (!need_resched()) - __mwait(ax, cx); - } -} - -/* Default MONITOR/MWAIT with no hints, used for default C1 state */ -static void mwait_idle(void) -{ - local_irq_enable(); - mwait_idle_with_hints(0, 0); -} - -static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c) -{ - if (force_mwait) - return 1; - /* Any C1 states supported? */ - return c->cpuid_level >= 5 && ((cpuid_edx(5) >> 4) & 0xf) > 0; -} - -void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) -{ - static int selected; - - if (selected) - return; -#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 (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; -} - -static int __init idle_setup(char *str) -{ - if (!strcmp(str, "poll")) { - printk("using polling idle threads.\n"); - pm_idle = poll_idle; - } else if (!strcmp(str, "mwait")) - force_mwait = 1; - else - return -1; - - boot_option_idle_override = 1; - return 0; -} -early_param("idle", idle_setup); - void __show_registers(struct pt_regs *regs, int all) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L; @@ -332,7 +219,7 @@ void __show_registers(struct pt_regs *regs, int all) init_utsname()->version); printk("EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n", - 0xffff & regs->cs, regs->ip, regs->flags, + (u16)regs->cs, regs->ip, regs->flags, smp_processor_id()); print_symbol("EIP is at %s\n", regs->ip); @@ -341,8 +228,7 @@ void __show_registers(struct pt_regs *regs, int all) printk("ESI: %08lx EDI: %08lx EBP: %08lx ESP: %08lx\n", regs->si, regs->di, regs->bp, sp); printk(" DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x\n", - regs->ds & 0xffff, regs->es & 0xffff, - regs->fs & 0xffff, gs, ss); + (u16)regs->ds, (u16)regs->es, (u16)regs->fs, gs, ss); if (!all) return; @@ -513,11 +399,30 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long sp, return err; } -#ifdef CONFIG_SECCOMP +void +start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) +{ + __asm__("movl %0, %%gs" :: "r"(0)); + regs->fs = 0; + set_fs(USER_DS); + regs->ds = __USER_DS; + regs->es = __USER_DS; + regs->ss = __USER_DS; + regs->cs = __USER_CS; + regs->ip = new_ip; + regs->sp = new_sp; + /* + * Free the old FP and other extended state + */ + free_thread_xstate(current); +} +EXPORT_SYMBOL_GPL(start_thread); + static void hard_disable_TSC(void) { write_cr4(read_cr4() | X86_CR4_TSD); } + void disable_TSC(void) { preempt_disable(); @@ -529,11 +434,47 @@ void disable_TSC(void) hard_disable_TSC(); preempt_enable(); } + static void hard_enable_TSC(void) { write_cr4(read_cr4() & ~X86_CR4_TSD); } -#endif /* CONFIG_SECCOMP */ + +static void enable_TSC(void) +{ + preempt_disable(); + if (test_and_clear_thread_flag(TIF_NOTSC)) + /* + * Must flip the CPU state synchronously with + * TIF_NOTSC in the current running context. + */ + hard_enable_TSC(); + preempt_enable(); +} + +int get_tsc_mode(unsigned long adr) +{ + unsigned int val; + + if (test_thread_flag(TIF_NOTSC)) + val = PR_TSC_SIGSEGV; + else + val = PR_TSC_ENABLE; + + return put_user(val, (unsigned int __user *)adr); +} + +int set_tsc_mode(unsigned int val) +{ + if (val == PR_TSC_SIGSEGV) + disable_TSC(); + else if (val == PR_TSC_ENABLE) + enable_TSC(); + else + return -EINVAL; + + return 0; +} static noinline void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, @@ -550,12 +491,12 @@ __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, /* we clear debugctl to make sure DS * is not in use when we change it */ debugctl = 0; - wrmsrl(MSR_IA32_DEBUGCTLMSR, 0); + update_debugctlmsr(0); wrmsr(MSR_IA32_DS_AREA, next->ds_area_msr, 0); } if (next->debugctlmsr != debugctl) - wrmsr(MSR_IA32_DEBUGCTLMSR, next->debugctlmsr, 0); + update_debugctlmsr(next->debugctlmsr); if (test_tsk_thread_flag(next_p, TIF_DEBUG)) { set_debugreg(next->debugreg0, 0); @@ -567,7 +508,6 @@ __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, set_debugreg(next->debugreg7, 7); } -#ifdef CONFIG_SECCOMP if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^ test_tsk_thread_flag(next_p, TIF_NOTSC)) { /* prev and next are different */ @@ -576,7 +516,6 @@ __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, else hard_enable_TSC(); } -#endif #ifdef X86_BTS if (test_tsk_thread_flag(prev_p, TIF_BTS_TRACE_TS)) @@ -658,7 +597,7 @@ struct task_struct * __switch_to(struct task_struct *prev_p, struct task_struct /* we're going to use this soon, after a few expensive things */ if (next_p->fpu_counter > 5) - prefetch(&next->i387.fxsave); + prefetch(next->xstate); /* * Reload esp0. diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 46c4c546b499..e2319f39988b 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -36,6 +36,7 @@ #include <linux/kprobes.h> #include <linux/kdebug.h> #include <linux/tick.h> +#include <linux/prctl.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -105,34 +106,13 @@ void default_idle(void) * test NEED_RESCHED: */ smp_mb(); - local_irq_disable(); - if (!need_resched()) { - ktime_t t0, t1; - u64 t0n, t1n; - - t0 = ktime_get(); - t0n = ktime_to_ns(t0); + if (!need_resched()) safe_halt(); /* enables interrupts racelessly */ - local_irq_disable(); - t1 = ktime_get(); - t1n = ktime_to_ns(t1); - sched_clock_idle_wakeup_event(t1n - t0n); - } - local_irq_enable(); + else + local_irq_enable(); current_thread_info()->status |= TS_POLLING; } -/* - * On SMP it's slightly faster (but much more power-consuming!) - * to poll the ->need_resched flag instead of waiting for the - * cross-CPU IPI to arrive. Use this option with caution. - */ -static void poll_idle(void) -{ - local_irq_enable(); - cpu_relax(); -} - #ifdef CONFIG_HOTPLUG_CPU DECLARE_PER_CPU(int, cpu_state); @@ -199,110 +179,6 @@ void cpu_idle(void) } } -static void do_nothing(void *unused) -{ -} - -/* - * cpu_idle_wait - Used to ensure that all the CPUs discard old value of - * pm_idle and update to new pm_idle value. Required while changing pm_idle - * handler on SMP systems. - * - * Caller must have changed pm_idle to the new value before the call. Old - * pm_idle value will not be used by any CPU after the return of this function. - */ -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); -} -EXPORT_SYMBOL_GPL(cpu_idle_wait); - -/* - * This uses new MONITOR/MWAIT instructions on P4 processors with PNI, - * which can obviate IPI to trigger checking of need_resched. - * We execute MONITOR against need_resched and enter optimized wait state - * through MWAIT. Whenever someone changes need_resched, we would be woken - * up from MWAIT (without an IPI). - * - * New with Core Duo processors, MWAIT can take some hints based on CPU - * capability. - */ -void mwait_idle_with_hints(unsigned long ax, unsigned long cx) -{ - if (!need_resched()) { - __monitor((void *)¤t_thread_info()->flags, 0, 0); - smp_mb(); - if (!need_resched()) - __mwait(ax, cx); - } -} - -/* Default MONITOR/MWAIT with no hints, used for default C1 state */ -static void mwait_idle(void) -{ - if (!need_resched()) { - __monitor((void *)¤t_thread_info()->flags, 0, 0); - smp_mb(); - if (!need_resched()) - __sti_mwait(0, 0); - else - local_irq_enable(); - } else { - local_irq_enable(); - } -} - - -static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c) -{ - if (force_mwait) - return 1; - /* Any C1 states supported? */ - return c->cpuid_level >= 5 && ((cpuid_edx(5) >> 4) & 0xf) > 0; -} - -void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) -{ - static int selected; - - if (selected) - return; -#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 (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; -} - -static int __init idle_setup(char *str) -{ - if (!strcmp(str, "poll")) { - printk("using polling idle threads.\n"); - pm_idle = poll_idle; - } else if (!strcmp(str, "mwait")) - force_mwait = 1; - else - return -1; - - boot_option_idle_override = 1; - return 0; -} -early_param("idle", idle_setup); - /* Prints also some state that isn't saved in the pt_regs */ void __show_regs(struct pt_regs * regs) { @@ -528,6 +404,83 @@ out: return err; } +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)); + load_gs_index(0); + regs->ip = new_ip; + regs->sp = new_sp; + write_pda(oldrsp, new_sp); + regs->cs = __USER_CS; + regs->ss = __USER_DS; + regs->flags = 0x200; + set_fs(USER_DS); + /* + * Free the old FP and other extended state + */ + free_thread_xstate(current); +} +EXPORT_SYMBOL_GPL(start_thread); + +static void hard_disable_TSC(void) +{ + write_cr4(read_cr4() | X86_CR4_TSD); +} + +void disable_TSC(void) +{ + preempt_disable(); + if (!test_and_set_thread_flag(TIF_NOTSC)) + /* + * Must flip the CPU state synchronously with + * TIF_NOTSC in the current running context. + */ + hard_disable_TSC(); + preempt_enable(); +} + +static void hard_enable_TSC(void) +{ + write_cr4(read_cr4() & ~X86_CR4_TSD); +} + +static void enable_TSC(void) +{ + preempt_disable(); + if (test_and_clear_thread_flag(TIF_NOTSC)) + /* + * Must flip the CPU state synchronously with + * TIF_NOTSC in the current running context. + */ + hard_enable_TSC(); + preempt_enable(); +} + +int get_tsc_mode(unsigned long adr) +{ + unsigned int val; + + if (test_thread_flag(TIF_NOTSC)) + val = PR_TSC_SIGSEGV; + else + val = PR_TSC_ENABLE; + + return put_user(val, (unsigned int __user *)adr); +} + +int set_tsc_mode(unsigned int val) +{ + if (val == PR_TSC_SIGSEGV) + disable_TSC(); + else if (val == PR_TSC_ENABLE) + enable_TSC(); + else + return -EINVAL; + + return 0; +} + /* * This special macro can be used to load a debugging register */ @@ -548,12 +501,12 @@ static inline void __switch_to_xtra(struct task_struct *prev_p, /* we clear debugctl to make sure DS * is not in use when we change it */ debugctl = 0; - wrmsrl(MSR_IA32_DEBUGCTLMSR, 0); + update_debugctlmsr(0); wrmsrl(MSR_IA32_DS_AREA, next->ds_area_msr); } if (next->debugctlmsr != debugctl) - wrmsrl(MSR_IA32_DEBUGCTLMSR, next->debugctlmsr); + update_debugctlmsr(next->debugctlmsr); if (test_tsk_thread_flag(next_p, TIF_DEBUG)) { loaddebug(next, 0); @@ -565,6 +518,15 @@ static inline void __switch_to_xtra(struct task_struct *prev_p, loaddebug(next, 7); } + if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^ + test_tsk_thread_flag(next_p, TIF_NOTSC)) { + /* prev and next are different */ + if (test_tsk_thread_flag(next_p, TIF_NOTSC)) + hard_disable_TSC(); + else + hard_enable_TSC(); + } + if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { /* * Copy the relevant range of the IO bitmap. @@ -607,7 +569,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) /* we're going to use this soon, after a few expensive things */ if (next_p->fpu_counter>5) - prefetch(&next->i387.fxsave); + prefetch(next->xstate); /* * Reload esp0, LDT and the page table pointer: diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index eb92ccbb3502..fb03ef380f0e 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1207,97 +1207,16 @@ static int genregs32_set(struct task_struct *target, return ret; } -static long ptrace32_siginfo(unsigned request, u32 pid, u32 addr, u32 data) +long compat_arch_ptrace(struct task_struct *child, compat_long_t request, + compat_ulong_t caddr, compat_ulong_t cdata) { - siginfo_t __user *si = compat_alloc_user_space(sizeof(siginfo_t)); - compat_siginfo_t __user *si32 = compat_ptr(data); - siginfo_t ssi; - int ret; - - if (request == PTRACE_SETSIGINFO) { - memset(&ssi, 0, sizeof(siginfo_t)); - ret = copy_siginfo_from_user32(&ssi, si32); - if (ret) - return ret; - if (copy_to_user(si, &ssi, sizeof(siginfo_t))) - return -EFAULT; - } - ret = sys_ptrace(request, pid, addr, (unsigned long)si); - if (ret) - return ret; - if (request == PTRACE_GETSIGINFO) { - if (copy_from_user(&ssi, si, sizeof(siginfo_t))) - return -EFAULT; - ret = copy_siginfo_to_user32(si32, &ssi); - } - return ret; -} - -asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data) -{ - struct task_struct *child; - struct pt_regs *childregs; + unsigned long addr = caddr; + unsigned long data = cdata; void __user *datap = compat_ptr(data); int ret; __u32 val; switch (request) { - case PTRACE_TRACEME: - case PTRACE_ATTACH: - case PTRACE_KILL: - case PTRACE_CONT: - case PTRACE_SINGLESTEP: - case PTRACE_SINGLEBLOCK: - case PTRACE_DETACH: - case PTRACE_SYSCALL: - case PTRACE_OLDSETOPTIONS: - case PTRACE_SETOPTIONS: - case PTRACE_SET_THREAD_AREA: - case PTRACE_GET_THREAD_AREA: -#ifdef X86_BTS - case PTRACE_BTS_CONFIG: - case PTRACE_BTS_STATUS: - case PTRACE_BTS_SIZE: - case PTRACE_BTS_GET: - case PTRACE_BTS_CLEAR: - case PTRACE_BTS_DRAIN: -#endif - return sys_ptrace(request, pid, addr, data); - - default: - return -EINVAL; - - case PTRACE_PEEKTEXT: - case PTRACE_PEEKDATA: - case PTRACE_POKEDATA: - case PTRACE_POKETEXT: - case PTRACE_POKEUSR: - case PTRACE_PEEKUSR: - case PTRACE_GETREGS: - case PTRACE_SETREGS: - case PTRACE_SETFPREGS: - case PTRACE_GETFPREGS: - case PTRACE_SETFPXREGS: - case PTRACE_GETFPXREGS: - case PTRACE_GETEVENTMSG: - break; - - case PTRACE_SETSIGINFO: - case PTRACE_GETSIGINFO: - return ptrace32_siginfo(request, pid, addr, data); - } - - child = ptrace_get_task_struct(pid); - if (IS_ERR(child)) - return PTR_ERR(child); - - ret = ptrace_check_attach(child, request == PTRACE_KILL); - if (ret < 0) - goto out; - - childregs = task_pt_regs(child); - - switch (request) { case PTRACE_PEEKUSR: ret = getreg32(child, addr, &val); if (ret == 0) @@ -1343,12 +1262,14 @@ asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data) sizeof(struct user32_fxsr_struct), datap); + case PTRACE_GET_THREAD_AREA: + case PTRACE_SET_THREAD_AREA: + return arch_ptrace(child, request, addr, data); + default: return compat_ptrace_request(child, request, addr, data); } - out: - put_task_struct(child); return ret; } @@ -1456,7 +1377,6 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code) /* notification of system call entry/exit * - triggered by current->work.syscall_trace */ -__attribute__((regparm(3))) int do_syscall_trace(struct pt_regs *regs, int entryexit) { int is_sysemu = test_thread_flag(TIF_SYSCALL_EMU); diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 484c4a80d38a..07c6d42ab5ff 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -1,5 +1,4 @@ #include <linux/module.h> -#include <linux/init.h> #include <linux/reboot.h> #include <linux/init.h> #include <linux/pm.h> @@ -9,6 +8,8 @@ #include <asm/apic.h> #include <asm/desc.h> #include <asm/hpet.h> +#include <asm/pgtable.h> +#include <asm/proto.h> #include <asm/reboot_fixups.h> #include <asm/reboot.h> @@ -16,7 +17,6 @@ # include <linux/dmi.h> # include <linux/ctype.h> # include <linux/mc146818rtc.h> -# include <asm/pgtable.h> #else # include <asm/iommu.h> #endif @@ -276,7 +276,7 @@ void machine_real_restart(unsigned char *code, int length) /* Remap the kernel at virtual address zero, as well as offset zero from the kernel segment. This assumes the kernel segment starts at virtual address PAGE_OFFSET. */ - memcpy(swapper_pg_dir, swapper_pg_dir + USER_PGD_PTRS, + memcpy(swapper_pg_dir, swapper_pg_dir + KERNEL_PGD_BOUNDARY, sizeof(swapper_pg_dir [0]) * KERNEL_PGD_PTRS); /* @@ -400,7 +400,7 @@ static void native_machine_emergency_restart(void) } } -static void native_machine_shutdown(void) +void native_machine_shutdown(void) { /* Stop the cpus and apics */ #ifdef CONFIG_SMP @@ -412,16 +412,16 @@ static void native_machine_shutdown(void) #ifdef CONFIG_X86_32 /* See if there has been given a command line override */ if ((reboot_cpu != -1) && (reboot_cpu < NR_CPUS) && - cpu_isset(reboot_cpu, cpu_online_map)) + cpu_online(reboot_cpu)) reboot_cpu_id = reboot_cpu; #endif /* Make certain the cpu I'm about to reboot on is online */ - if (!cpu_isset(reboot_cpu_id, cpu_online_map)) + if (!cpu_online(reboot_cpu_id)) reboot_cpu_id = smp_processor_id(); /* Make certain I only run on the appropriate processor */ - set_cpus_allowed(current, cpumask_of_cpu(reboot_cpu_id)); + set_cpus_allowed_ptr(current, &cpumask_of_cpu(reboot_cpu_id)); /* O.K Now that I'm on the appropriate processor, * stop all of the others. @@ -471,7 +471,10 @@ struct machine_ops machine_ops = { .shutdown = native_machine_shutdown, .emergency_restart = native_machine_emergency_restart, .restart = native_machine_restart, - .halt = native_machine_halt + .halt = native_machine_halt, +#ifdef CONFIG_KEXEC + .crash_shutdown = native_machine_crash_shutdown, +#endif }; void machine_power_off(void) @@ -499,3 +502,9 @@ void machine_halt(void) machine_ops.halt(); } +#ifdef CONFIG_KEXEC +void machine_crash_shutdown(struct pt_regs *regs) +{ + machine_ops.crash_shutdown(regs); +} +#endif diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S index f151d6fae462..c30fe25d470d 100644 --- a/arch/x86/kernel/relocate_kernel_32.S +++ b/arch/x86/kernel/relocate_kernel_32.S @@ -9,18 +9,19 @@ #include <linux/linkage.h> #include <asm/page.h> #include <asm/kexec.h> +#include <asm/processor-flags.h> +#include <asm/pgtable.h> /* * Must be relocatable PIC code callable as a C function */ #define PTR(x) (x << 2) -#define PAGE_ALIGNED (1 << PAGE_SHIFT) -#define PAGE_ATTR 0x63 /* _PAGE_PRESENT|_PAGE_RW|_PAGE_ACCESSED|_PAGE_DIRTY */ -#define PAE_PGD_ATTR 0x01 /* _PAGE_PRESENT */ +#define PAGE_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY) +#define PAE_PGD_ATTR (_PAGE_PRESENT) .text - .align PAGE_ALIGNED + .align PAGE_SIZE .globl relocate_kernel relocate_kernel: movl 8(%esp), %ebp /* list of pages */ @@ -155,7 +156,7 @@ relocate_new_kernel: movl %eax, %cr3 /* setup a new stack at the end of the physical control page */ - lea 4096(%edi), %esp + lea PAGE_SIZE(%edi), %esp /* jump to identity mapped page */ movl %edi, %eax @@ -168,16 +169,16 @@ identity_mapped: pushl %edx /* Set cr0 to a known state: - * 31 0 == Paging disabled - * 18 0 == Alignment check disabled - * 16 0 == Write protect disabled - * 3 0 == No task switch - * 2 0 == Don't do FP software emulation. - * 0 1 == Proctected mode enabled + * - Paging disabled + * - Alignment check disabled + * - Write protect disabled + * - No task switch + * - Don't do FP software emulation. + * - Proctected mode enabled */ movl %cr0, %eax - andl $~((1<<31)|(1<<18)|(1<<16)|(1<<3)|(1<<2)), %eax - orl $(1<<0), %eax + andl $~(X86_CR0_PG | X86_CR0_AM | X86_CR0_WP | X86_CR0_TS | X86_CR0_EM), %eax + orl $(X86_CR0_PE), %eax movl %eax, %cr0 /* clear cr4 if applicable */ @@ -186,8 +187,7 @@ identity_mapped: /* Set cr4 to a known state: * Setting everything to zero seems safe. */ - movl %cr4, %eax - andl $0, %eax + xorl %eax, %eax movl %eax, %cr4 jmp 1f diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index 14e95872c6a3..f5afe665a82b 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -9,17 +9,18 @@ #include <linux/linkage.h> #include <asm/page.h> #include <asm/kexec.h> +#include <asm/processor-flags.h> +#include <asm/pgtable.h> /* * Must be relocatable PIC code callable as a C function */ #define PTR(x) (x << 3) -#define PAGE_ALIGNED (1 << PAGE_SHIFT) -#define PAGE_ATTR 0x63 /* _PAGE_PRESENT|_PAGE_RW|_PAGE_ACCESSED|_PAGE_DIRTY */ +#define PAGE_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY) .text - .align PAGE_ALIGNED + .align PAGE_SIZE .code64 .globl relocate_kernel relocate_kernel: @@ -160,7 +161,7 @@ relocate_new_kernel: movq %r9, %cr3 /* setup a new stack at the end of the physical control page */ - lea 4096(%r8), %rsp + lea PAGE_SIZE(%r8), %rsp /* jump to identity mapped page */ addq $(identity_mapped - relocate_kernel), %r8 @@ -172,33 +173,22 @@ identity_mapped: pushq %rdx /* Set cr0 to a known state: - * 31 1 == Paging enabled - * 18 0 == Alignment check disabled - * 16 0 == Write protect disabled - * 3 0 == No task switch - * 2 0 == Don't do FP software emulation. - * 0 1 == Proctected mode enabled + * - Paging enabled + * - Alignment check disabled + * - Write protect disabled + * - No task switch + * - Don't do FP software emulation. + * - Proctected mode enabled */ movq %cr0, %rax - andq $~((1<<18)|(1<<16)|(1<<3)|(1<<2)), %rax - orl $((1<<31)|(1<<0)), %eax + andq $~(X86_CR0_AM | X86_CR0_WP | X86_CR0_TS | X86_CR0_EM), %rax + orl $(X86_CR0_PG | X86_CR0_PE), %eax movq %rax, %cr0 /* Set cr4 to a known state: - * 10 0 == xmm exceptions disabled - * 9 0 == xmm registers instructions disabled - * 8 0 == performance monitoring counter disabled - * 7 0 == page global disabled - * 6 0 == machine check exceptions disabled - * 5 1 == physical address extension enabled - * 4 0 == page size extensions disabled - * 3 0 == Debug extensions disabled - * 2 0 == Time stamp disable (disabled) - * 1 0 == Protected mode virtual interrupts disabled - * 0 0 == VME disabled + * - physical address extension enabled */ - - movq $((1<<5)), %rax + movq $X86_CR4_PAE, %rax movq %rax, %cr4 jmp 1f diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index eb9b1a198f5e..9615eee9b775 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -9,7 +9,6 @@ #include <asm/vsyscall.h> #ifdef CONFIG_X86_32 -# define CMOS_YEARS_OFFS 1900 /* * This is a special lock that is owned by the CPU and holds the index * register we are working with. It is required for NMI access to the @@ -17,14 +16,11 @@ */ volatile unsigned long cmos_lock = 0; EXPORT_SYMBOL(cmos_lock); -#else -/* - * x86-64 systems only exists since 2002. - * This will work up to Dec 31, 2100 - */ -# define CMOS_YEARS_OFFS 2000 #endif +/* For two digit years assume time is always after that */ +#define CMOS_YEARS_OFFS 2000 + DEFINE_SPINLOCK(rtc_lock); EXPORT_SYMBOL(rtc_lock); @@ -98,7 +94,7 @@ int mach_set_rtc_mmss(unsigned long nowtime) unsigned long mach_get_cmos_time(void) { - unsigned int year, mon, day, hour, min, sec, century = 0; + unsigned int status, year, mon, day, hour, min, sec, century = 0; /* * If UIP is clear, then we have >= 244 microseconds before @@ -116,14 +112,16 @@ unsigned long mach_get_cmos_time(void) mon = CMOS_READ(RTC_MONTH); year = CMOS_READ(RTC_YEAR); -#if defined(CONFIG_ACPI) && defined(CONFIG_X86_64) - /* CHECKME: Is this really 64bit only ??? */ +#ifdef CONFIG_ACPI if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && acpi_gbl_FADT.century) century = CMOS_READ(acpi_gbl_FADT.century); #endif - if (RTC_ALWAYS_BCD || !(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY)) { + status = CMOS_READ(RTC_CONTROL); + WARN_ON_ONCE(RTC_ALWAYS_BCD && (status & RTC_DM_BINARY)); + + if (RTC_ALWAYS_BCD || !(status & RTC_DM_BINARY)) { BCD_TO_BIN(sec); BCD_TO_BIN(min); BCD_TO_BIN(hour); @@ -136,11 +134,8 @@ unsigned long mach_get_cmos_time(void) BCD_TO_BIN(century); year += century * 100; printk(KERN_INFO "Extended CMOS year: %d\n", century * 100); - } else { + } else year += CMOS_YEARS_OFFS; - if (year < 1970) - year += 100; - } return mktime(year, mon, day, hour, min, sec); } @@ -151,8 +146,8 @@ unsigned char rtc_cmos_read(unsigned char addr) unsigned char val; lock_cmos_prefix(addr); - outb_p(addr, RTC_PORT(0)); - val = inb_p(RTC_PORT(1)); + outb(addr, RTC_PORT(0)); + val = inb(RTC_PORT(1)); lock_cmos_suffix(addr); return val; } @@ -161,8 +156,8 @@ EXPORT_SYMBOL(rtc_cmos_read); void rtc_cmos_write(unsigned char val, unsigned char addr) { lock_cmos_prefix(addr); - outb_p(addr, RTC_PORT(0)); - outb_p(val, RTC_PORT(1)); + outb(addr, RTC_PORT(0)); + outb(val, RTC_PORT(1)); lock_cmos_suffix(addr); } EXPORT_SYMBOL(rtc_cmos_write); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c new file mode 100644 index 000000000000..c0c68c18a788 --- /dev/null +++ b/arch/x86/kernel/setup.c @@ -0,0 +1,137 @@ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/bootmem.h> +#include <linux/percpu.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> + +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); + +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_HAVE_SETUP_PER_CPU_AREA) && defined(CONFIG_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) = 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]; +#endif + } + + /* 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; +#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); +#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) +{ + int i, highest_cpu = 0; + unsigned long size; + +#ifdef CONFIG_HOTPLUG_CPU + prefill_possible_map(); +#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); + + for_each_possible_cpu(i) { + char *ptr; +#ifndef CONFIG_NEED_MULTIPLE_NODES + ptr = alloc_bootmem_pages(size); +#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); +#endif + if (!ptr) + panic("Cannot allocate cpu data for CPU %d\n", i); +#ifdef CONFIG_X86_64 + cpu_pda(i)->data_offset = ptr - __per_cpu_start; +#else + __per_cpu_offset[i] = ptr - __per_cpu_start; +#endif + memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start); + + highest_cpu = i; + } + + nr_cpu_ids = highest_cpu + 1; + printk(KERN_DEBUG "NR_CPUS: %d, nr_cpu_ids: %d\n", NR_CPUS, nr_cpu_ids); + + /* Setup percpu data maps */ + setup_per_cpu_maps(); + + /* Setup cpumask_of_cpu map */ + setup_cpumask_of_cpu(); +} + +#endif diff --git a/arch/x86/kernel/setup64.c b/arch/x86/kernel/setup64.c index e24c45677094..aee0e8200777 100644 --- a/arch/x86/kernel/setup64.c +++ b/arch/x86/kernel/setup64.c @@ -11,6 +11,7 @@ #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> @@ -23,6 +24,7 @@ #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; @@ -72,8 +74,8 @@ int force_personality32 = 0; 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 -off PROT_READ implies PROT_EXEC (default) +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) { @@ -85,83 +87,6 @@ static int __init nonx32_setup(char *str) } __setup("noexec32=", nonx32_setup); -/* - * 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) { -#ifdef CONFIG_SMP - if (per_cpu_offset(cpu)) { -#endif - 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]; -#endif -#ifdef CONFIG_SMP - } - else - printk(KERN_NOTICE "per_cpu_offset zero for cpu %d\n", - cpu); -#endif - } - - /* 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; -#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) -{ - int i; - unsigned long size; - -#ifdef CONFIG_HOTPLUG_CPU - prefill_possible_map(); -#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); - for_each_cpu_mask (i, cpu_possible_map) { - char *ptr; -#ifndef CONFIG_NEED_MULTIPLE_NODES - ptr = alloc_bootmem_pages(size); -#else - int node = early_cpu_to_node(i); - - if (!node_online(node) || !NODE_DATA(node)) - ptr = alloc_bootmem_pages(size); - else - ptr = alloc_bootmem_pages_node(NODE_DATA(node), size); -#endif - if (!ptr) - panic("Cannot allocate cpu data for CPU %d\n", i); - cpu_pda(i)->data_offset = ptr - __per_cpu_start; - memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start); - } - - /* setup percpu data maps early */ - setup_per_cpu_maps(); -} - void pda_init(int cpu) { struct x8664_pda *pda = cpu_pda(cpu); @@ -327,6 +252,17 @@ void __cpuinit cpu_init (void) 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: */ @@ -337,8 +273,15 @@ void __cpuinit cpu_init (void) 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 index 2b3e5d45176b..2283422af794 100644 --- a/arch/x86/kernel/setup_32.c +++ b/arch/x86/kernel/setup_32.c @@ -39,6 +39,7 @@ #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> @@ -46,6 +47,7 @@ #include <linux/pfn.h> #include <linux/pci.h> #include <linux/init_ohci1394_dma.h> +#include <linux/kvm_para.h> #include <video/edid.h> @@ -62,8 +64,9 @@ #include <asm/io.h> #include <asm/vmi.h> #include <setup_arch.h> -#include <bios_ebda.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* @@ -154,6 +157,8 @@ struct cpuinfo_x86 new_cpu_data __cpuinitdata = { 0, 0, 0, 0, -1, 1, 0, 0, -1 }; 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 @@ -189,7 +194,7 @@ EXPORT_SYMBOL(ist_info); extern void early_cpu_init(void); extern int root_mountflags; -unsigned long saved_videomode; +unsigned long saved_video_mode; #define RAMDISK_IMAGE_START_MASK 0x07FF #define RAMDISK_PROMPT_FLAG 0x8000 @@ -227,7 +232,7 @@ static inline void copy_edd(void) } #endif -int __initdata user_defined_memmap = 0; +int __initdata user_defined_memmap; /* * "mem=nopentium" disables the 4MB page tables. @@ -385,19 +390,58 @@ unsigned long __init find_max_low_pfn(void) return max_low_pfn; } +#define BIOS_LOWMEM_KILOBYTES 0x413 + /* - * workaround for Dell systems that neglect to reserve EBDA + * 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 addr; - addr = get_bios_ebda(); - if (addr) - reserve_bootmem(addr, PAGE_SIZE, BOOTMEM_DEFAULT); + 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 -void __init setup_bootmem_allocator(void); +static void __init setup_bootmem_allocator(void); static unsigned long __init setup_memory(void) { /* @@ -432,7 +476,7 @@ static unsigned long __init setup_memory(void) return max_low_pfn; } -void __init zone_sizes_init(void) +static void __init zone_sizes_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES]; memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); @@ -617,16 +661,9 @@ void __init setup_bootmem_allocator(void) */ reserve_bootmem(0, PAGE_SIZE, BOOTMEM_DEFAULT); - /* reserve EBDA region, it's a 4K region */ + /* reserve EBDA region */ reserve_ebda_region(); - /* could be an AMD 768MPX 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. */ - if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD && - boot_cpu_data.x86 == 6) - reserve_bootmem(0xa0000 - 4096, 4096, BOOTMEM_DEFAULT); - #ifdef CONFIG_SMP /* * But first pinch a few for the stack/trampoline stuff @@ -652,6 +689,8 @@ void __init setup_bootmem_allocator(void) #endif numa_kva_reserve(); reserve_crashkernel(); + + reserve_ibft_region(); } /* @@ -687,6 +726,18 @@ 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 @@ -714,7 +765,7 @@ void __init setup_arch(char **cmdline_p) edid_info = boot_params.edid_info; apm_info.bios = boot_params.apm_bios_info; ist_info = boot_params.ist_info; - saved_videomode = boot_params.hdr.vid_mode; + 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]; @@ -763,13 +814,17 @@ void __init setup_arch(char **cmdline_p) efi_init(); /* update e820 for memory not covered by WB MTRRs */ - find_max_pfn(); + propagate_e820_map(); mtrr_bp_init(); if (mtrr_trim_uncached_memory(max_pfn)) - find_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 @@ -777,6 +832,7 @@ void __init setup_arch(char **cmdline_p) */ vmi_init(); #endif + kvm_guest_init(); /* * NOTE: before this point _nobody_ is allowed to allocate @@ -820,6 +876,18 @@ void __init setup_arch(char **cmdline_p) 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 diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c index f4f7ecfb898c..22c14e21c97c 100644 --- a/arch/x86/kernel/setup_64.c +++ b/arch/x86/kernel/setup_64.c @@ -29,18 +29,22 @@ #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> @@ -58,7 +62,6 @@ #include <asm/mmu_context.h> #include <asm/proto.h> #include <asm/setup.h> -#include <asm/mach_apic.h> #include <asm/numa.h> #include <asm/sections.h> #include <asm/dmi.h> @@ -66,7 +69,9 @@ #include <asm/mce.h> #include <asm/ds.h> #include <asm/topology.h> +#include <asm/trampoline.h> +#include <mach_apic.h> #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> #else @@ -114,7 +119,7 @@ extern int root_mountflags; char __initdata command_line[COMMAND_LINE_SIZE]; -struct resource standard_io_resources[] = { +static struct resource standard_io_resources[] = { { .name = "dma1", .start = 0x00, .end = 0x1f, .flags = IORESOURCE_BUSY | IORESOURCE_IO }, { .name = "pic1", .start = 0x20, .end = 0x21, @@ -188,6 +193,7 @@ contig_initmem_init(unsigned long start_pfn, unsigned long end_pfn) 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 @@ -248,6 +254,7 @@ static void __init reserve_crashkernel(void) (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 @@ -261,6 +268,40 @@ 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 * @@ -313,6 +354,8 @@ void __init setup_arch(char **cmdline_p) 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 @@ -322,6 +365,11 @@ void __init setup_arch(char **cmdline_p) 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); @@ -341,14 +389,20 @@ void __init setup_arch(char **cmdline_p) check_efer(); - init_memory_mapping(0, (end_pfn_map << PAGE_SHIFT)); + 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; @@ -387,7 +441,7 @@ void __init setup_arch(char **cmdline_p) contig_initmem_init(0, end_pfn); #endif - early_res_to_bootmem(); + dma32_reserve_bootmem(); #ifdef CONFIG_ACPI_SLEEP /* @@ -411,11 +465,14 @@ void __init setup_arch(char **cmdline_p) unsigned long end_of_mem = end_pfn << PAGE_SHIFT; if (ramdisk_end <= end_of_mem) { - reserve_bootmem_generic(ramdisk_image, ramdisk_size); + /* + * 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 { - /* Assumes everything on node 0 */ free_bootmem(ramdisk_image, ramdisk_size); printk(KERN_ERR "initrd extends beyond end of memory " "(0x%08lx > 0x%08lx)\ndisabling initrd\n", @@ -425,6 +482,9 @@ void __init setup_arch(char **cmdline_p) } #endif reserve_crashkernel(); + + reserve_ibft_region(); + paging_init(); map_vsyscall(); @@ -447,10 +507,12 @@ void __init setup_arch(char **cmdline_p) init_apic_mappings(); ioapic_init_mappings(); + kvm_guest_init(); + /* * We trust e820 completely. No explicit ROM probing in memory. */ - e820_reserve_resources(&code_resource, &data_resource, &bss_resource); + e820_reserve_resources(); e820_mark_nosave_regions(); /* request I/O space for devices used on all i[345]86 PCs */ @@ -467,6 +529,9 @@ void __init setup_arch(char **cmdline_p) 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) @@ -552,9 +617,9 @@ static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c) bits = c->x86_coreid_bits; /* Low order bits define the core id (index of core in socket) */ - c->cpu_core_id = c->phys_proc_id & ((1 << bits)-1); - /* Convert the APIC ID into the socket ID */ - c->phys_proc_id = phys_pkg_id(bits); + 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; @@ -571,7 +636,7 @@ static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c) If that doesn't result in a usable node fall back to the path for the previous case. */ - int ht_nodeid = apicid - (cpu_data(0).phys_proc_id << bits); + int ht_nodeid = c->initial_apicid; if (ht_nodeid >= 0 && apicid_to_node[ht_nodeid] != NUMA_NO_NODE) @@ -677,7 +742,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) /* Bit 31 in normal CPUID used for nonstandard 3DNow ID; 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */ - clear_bit(0*32+31, (unsigned long *)&c->x86_capability); + clear_cpu_cap(c, 0*32+31); /* On C+ stepping K8 rep microcode works well for copy/memset */ level = cpuid_eax(1); @@ -719,8 +784,24 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) /* 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) @@ -813,7 +894,7 @@ 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_bit(X86_FEATURE_CONSTANT_TSC, &c->x86_capability); + set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); } static void __cpuinit init_intel(struct cpuinfo_x86 *c) @@ -856,9 +937,6 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) if (c->x86 == 15) c->x86_cache_alignment = c->x86_clflush_size * 2; - if ((c->x86 == 0xf && c->x86_model >= 0x03) || - (c->x86 == 0x6 && c->x86_model >= 0x0e)) - set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); if (c->x86 == 6) set_cpu_cap(c, X86_FEATURE_REP_GOOD); set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); @@ -867,6 +945,32 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) srat_detect_node(); } +static void __cpuinit early_init_centaur(struct cpuinfo_x86 *c) +{ + if (c->x86 == 0x6 && c->x86_model >= 0xf) + set_bit(X86_FEATURE_CONSTANT_TSC, &c->x86_capability); +} + +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; @@ -875,6 +979,8 @@ static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c) 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; } @@ -922,15 +1028,16 @@ static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c) c->x86 += (tfms >> 20) & 0xff; if (c->x86 >= 0x6) c->x86_model += ((tfms >> 16) & 0xF) << 4; - if (c->x86_capability[0] & (1<<19)) + 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 = (cpuid_ebx(1) >> 24) & 0xff; + c->phys_proc_id = c->initial_apicid; #endif /* AMD-defined flags: level 0x80000001 */ xlvl = cpuid_eax(0x80000000); @@ -956,12 +1063,22 @@ static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c) if (c->extended_cpuid_level >= 0x80000007) c->x86_power = cpuid_edx(0x80000007); + + clear_cpu_cap(c, X86_FEATURE_PAT); + switch (c->x86_vendor) { case X86_VENDOR_AMD: early_init_amd(c); + if (c->x86 >= 0xf && c->x86 <= 0x11) + set_cpu_cap(c, X86_FEATURE_PAT); break; case X86_VENDOR_INTEL: early_init_intel(c); + if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15)) + set_cpu_cap(c, X86_FEATURE_PAT); + break; + case X86_VENDOR_CENTAUR: + early_init_centaur(c); break; } @@ -999,6 +1116,10 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c) init_intel(c); break; + case X86_VENDOR_CENTAUR: + init_centaur(c); + break; + case X86_VENDOR_UNKNOWN: default: display_cacheinfo(c); @@ -1028,14 +1149,24 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c) #endif select_idle_routine(c); - if (c != &boot_cpu_data) - mtrr_ap_init(); #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); @@ -1064,123 +1195,3 @@ static __init int setup_disablecpuid(char *arg) return 1; } __setup("clearcpuid=", setup_disablecpuid); - -/* - * Get CPU information for use by the procfs. - */ - -static int show_cpuinfo(struct seq_file *m, void *v) -{ - struct cpuinfo_x86 *c = v; - int cpu = 0, i; - -#ifdef CONFIG_SMP - cpu = c->cpu_index; -#endif - - seq_printf(m, "processor\t: %u\n" - "vendor_id\t: %s\n" - "cpu family\t: %d\n" - "model\t\t: %d\n" - "model name\t: %s\n", - (unsigned)cpu, - c->x86_vendor_id[0] ? c->x86_vendor_id : "unknown", - c->x86, - (int)c->x86_model, - c->x86_model_id[0] ? c->x86_model_id : "unknown"); - - if (c->x86_mask || c->cpuid_level >= 0) - seq_printf(m, "stepping\t: %d\n", c->x86_mask); - else - seq_printf(m, "stepping\t: unknown\n"); - - if (cpu_has(c, X86_FEATURE_TSC)) { - unsigned int freq = cpufreq_quick_get((unsigned)cpu); - - if (!freq) - freq = cpu_khz; - seq_printf(m, "cpu MHz\t\t: %u.%03u\n", - freq / 1000, (freq % 1000)); - } - - /* Cache size */ - if (c->x86_cache_size >= 0) - seq_printf(m, "cache size\t: %d KB\n", c->x86_cache_size); - -#ifdef CONFIG_SMP - if (smp_num_siblings * c->x86_max_cores > 1) { - seq_printf(m, "physical id\t: %d\n", c->phys_proc_id); - seq_printf(m, "siblings\t: %d\n", - cpus_weight(per_cpu(cpu_core_map, cpu))); - seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id); - seq_printf(m, "cpu cores\t: %d\n", c->booted_cores); - } -#endif - - seq_printf(m, - "fpu\t\t: yes\n" - "fpu_exception\t: yes\n" - "cpuid level\t: %d\n" - "wp\t\t: yes\n" - "flags\t\t:", - c->cpuid_level); - - for (i = 0; i < 32*NCAPINTS; i++) - if (cpu_has(c, i) && x86_cap_flags[i] != NULL) - seq_printf(m, " %s", x86_cap_flags[i]); - - seq_printf(m, "\nbogomips\t: %lu.%02lu\n", - c->loops_per_jiffy/(500000/HZ), - (c->loops_per_jiffy/(5000/HZ)) % 100); - - if (c->x86_tlbsize > 0) - seq_printf(m, "TLB size\t: %d 4K pages\n", c->x86_tlbsize); - seq_printf(m, "clflush size\t: %d\n", c->x86_clflush_size); - seq_printf(m, "cache_alignment\t: %d\n", c->x86_cache_alignment); - - seq_printf(m, "address sizes\t: %u bits physical, %u bits virtual\n", - c->x86_phys_bits, c->x86_virt_bits); - - seq_printf(m, "power management:"); - for (i = 0; i < 32; i++) { - if (c->x86_power & (1 << i)) { - if (i < ARRAY_SIZE(x86_power_flags) && - x86_power_flags[i]) - seq_printf(m, "%s%s", - x86_power_flags[i][0]?" ":"", - x86_power_flags[i]); - else - seq_printf(m, " [%d]", i); - } - } - - seq_printf(m, "\n\n"); - - return 0; -} - -static void *c_start(struct seq_file *m, loff_t *pos) -{ - if (*pos == 0) /* just in case, cpu 0 is not the first */ - *pos = first_cpu(cpu_online_map); - if ((*pos) < NR_CPUS && cpu_online(*pos)) - return &cpu_data(*pos); - return NULL; -} - -static void *c_next(struct seq_file *m, void *v, loff_t *pos) -{ - *pos = next_cpu(*pos, cpu_online_map); - return c_start(m, pos); -} - -static void c_stop(struct seq_file *m, void *v) -{ -} - -const struct seq_operations cpuinfo_op = { - .start = c_start, - .next = c_next, - .stop = c_stop, - .show = show_cpuinfo, -}; diff --git a/arch/x86/kernel/sigframe_32.h b/arch/x86/kernel/sigframe.h index 0b2221711dad..72bbb519d2dc 100644 --- a/arch/x86/kernel/sigframe_32.h +++ b/arch/x86/kernel/sigframe.h @@ -1,5 +1,5 @@ -struct sigframe -{ +#ifdef CONFIG_X86_32 +struct sigframe { char __user *pretcode; int sig; struct sigcontext sc; @@ -8,8 +8,7 @@ struct sigframe char retcode[8]; }; -struct rt_sigframe -{ +struct rt_sigframe { char __user *pretcode; int sig; struct siginfo __user *pinfo; @@ -19,3 +18,10 @@ struct rt_sigframe struct _fpstate fpstate; char retcode[8]; }; +#else +struct rt_sigframe { + char __user *pretcode; + struct ucontext uc; + struct siginfo info; +}; +#endif diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c index 0157a6f0f41f..d92373630963 100644 --- a/arch/x86/kernel/signal_32.c +++ b/arch/x86/kernel/signal_32.c @@ -4,32 +4,44 @@ * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson * 2000-06-20 Pentium III FXSR, SSE support by Gareth Hughes */ +#include <linux/list.h> -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/smp.h> +#include <linux/personality.h> +#include <linux/binfmts.h> +#include <linux/suspend.h> #include <linux/kernel.h> +#include <linux/ptrace.h> #include <linux/signal.h> +#include <linux/stddef.h> +#include <linux/unistd.h> #include <linux/errno.h> +#include <linux/sched.h> #include <linux/wait.h> -#include <linux/unistd.h> -#include <linux/stddef.h> -#include <linux/personality.h> -#include <linux/suspend.h> -#include <linux/ptrace.h> #include <linux/elf.h> -#include <linux/binfmts.h> +#include <linux/smp.h> +#include <linux/mm.h> + #include <asm/processor.h> #include <asm/ucontext.h> #include <asm/uaccess.h> #include <asm/i387.h> #include <asm/vdso.h> -#include "sigframe_32.h" -#define DEBUG_SIG 0 +#include "sigframe.h" #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) +#define __FIX_EFLAGS (X86_EFLAGS_AC | X86_EFLAGS_OF | \ + X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \ + X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \ + X86_EFLAGS_CF) + +#ifdef CONFIG_X86_32 +# define FIX_EFLAGS (__FIX_EFLAGS | X86_EFLAGS_RF) +#else +# define FIX_EFLAGS __FIX_EFLAGS +#endif + /* * Atomically swap in the new signal mask, and wait for a signal. */ @@ -45,11 +57,12 @@ sys_sigsuspend(int history0, int history1, old_sigset_t mask) current->state = TASK_INTERRUPTIBLE; schedule(); - set_thread_flag(TIF_RESTORE_SIGMASK); + set_restore_sigmask(); + return -ERESTARTNOHAND; } -asmlinkage int +asmlinkage int sys_sigaction(int sig, const struct old_sigaction __user *act, struct old_sigaction __user *oact) { @@ -58,10 +71,12 @@ sys_sigaction(int sig, const struct old_sigaction __user *act, if (act) { old_sigset_t mask; + if (!access_ok(VERIFY_READ, act, sizeof(*act)) || __get_user(new_ka.sa.sa_handler, &act->sa_handler) || __get_user(new_ka.sa.sa_restorer, &act->sa_restorer)) return -EFAULT; + __get_user(new_ka.sa.sa_flags, &act->sa_flags); __get_user(mask, &act->sa_mask); siginitset(&new_ka.sa.sa_mask, mask); @@ -74,6 +89,7 @@ sys_sigaction(int sig, const struct old_sigaction __user *act, __put_user(old_ka.sa.sa_handler, &oact->sa_handler) || __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer)) return -EFAULT; + __put_user(old_ka.sa.sa_flags, &oact->sa_flags); __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask); } @@ -81,10 +97,12 @@ sys_sigaction(int sig, const struct old_sigaction __user *act, return ret; } -asmlinkage int -sys_sigaltstack(unsigned long bx) +asmlinkage int sys_sigaltstack(unsigned long bx) { - /* This is needed to make gcc realize it doesn't own the "struct pt_regs" */ + /* + * This is needed to make gcc realize it doesn't own the + * "struct pt_regs" + */ struct pt_regs *regs = (struct pt_regs *)&bx; const stack_t __user *uss = (const stack_t __user *)bx; stack_t __user *uoss = (stack_t __user *)regs->cx; @@ -96,9 +114,9 @@ sys_sigaltstack(unsigned long bx) /* * Do a signal return; undo the signal stack. */ - static int -restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, int *peax) +restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, + unsigned long *pax) { unsigned int err = 0; @@ -120,37 +138,29 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, int *peax #define GET_SEG(seg) \ { unsigned short tmp; \ err |= __get_user(tmp, &sc->seg); \ - loadsegment(seg,tmp); } - -#define FIX_EFLAGS (X86_EFLAGS_AC | X86_EFLAGS_RF | \ - X86_EFLAGS_OF | X86_EFLAGS_DF | \ - X86_EFLAGS_TF | X86_EFLAGS_SF | X86_EFLAGS_ZF | \ - X86_EFLAGS_AF | X86_EFLAGS_PF | X86_EFLAGS_CF) + loadsegment(seg, tmp); } GET_SEG(gs); COPY_SEG(fs); COPY_SEG(es); COPY_SEG(ds); - COPY(di); - COPY(si); - COPY(bp); - COPY(sp); - COPY(bx); - COPY(dx); - COPY(cx); - COPY(ip); + COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx); + COPY(dx); COPY(cx); COPY(ip); COPY_SEG_STRICT(cs); COPY_SEG_STRICT(ss); - + { unsigned int tmpflags; + err |= __get_user(tmpflags, &sc->flags); - regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); + regs->flags = (regs->flags & ~FIX_EFLAGS) | + (tmpflags & FIX_EFLAGS); regs->orig_ax = -1; /* disable syscall checks */ } { - struct _fpstate __user * buf; + struct _fpstate __user *buf; + err |= __get_user(buf, &sc->fpstate); if (buf) { if (!access_ok(VERIFY_READ, buf, sizeof(*buf))) @@ -158,6 +168,7 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, int *peax err |= restore_i387(buf); } else { struct task_struct *me = current; + if (used_math()) { clear_fpu(me); clear_used_math(); @@ -165,24 +176,26 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, int *peax } } - err |= __get_user(*peax, &sc->ax); + err |= __get_user(*pax, &sc->ax); return err; badframe: return 1; } -asmlinkage int sys_sigreturn(unsigned long __unused) +asmlinkage unsigned long sys_sigreturn(unsigned long __unused) { - struct pt_regs *regs = (struct pt_regs *) &__unused; - struct sigframe __user *frame = (struct sigframe __user *)(regs->sp - 8); + struct sigframe __user *frame; + struct pt_regs *regs; + unsigned long ax; sigset_t set; - int ax; + + regs = (struct pt_regs *) &__unused; + frame = (struct sigframe __user *)(regs->sp - 8); if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) goto badframe; - if (__get_user(set.sig[0], &frame->sc.oldmask) - || (_NSIG_WORDS > 1 + if (__get_user(set.sig[0], &frame->sc.oldmask) || (_NSIG_WORDS > 1 && __copy_from_user(&set.sig[1], &frame->extramask, sizeof(frame->extramask)))) goto badframe; @@ -192,33 +205,35 @@ asmlinkage int sys_sigreturn(unsigned long __unused) current->blocked = set; recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); - + if (restore_sigcontext(regs, &frame->sc, &ax)) goto badframe; return ax; badframe: if (show_unhandled_signals && printk_ratelimit()) { - printk("%s%s[%d] bad frame in sigreturn frame:%p ip:%lx" - " sp:%lx oeax:%lx", + printk(KERN_INFO "%s%s[%d] bad frame in sigreturn frame:" + "%p ip:%lx sp:%lx oeax:%lx", task_pid_nr(current) > 1 ? KERN_INFO : KERN_EMERG, current->comm, task_pid_nr(current), frame, regs->ip, regs->sp, regs->orig_ax); print_vma_addr(" in ", regs->ip); - printk("\n"); + printk(KERN_CONT "\n"); } force_sig(SIGSEGV, current); + return 0; -} +} asmlinkage int sys_rt_sigreturn(unsigned long __unused) { - struct pt_regs *regs = (struct pt_regs *) &__unused; - struct rt_sigframe __user *frame = (struct rt_sigframe __user *)(regs->sp - 4); + struct pt_regs *regs = (struct pt_regs *)&__unused; + struct rt_sigframe __user *frame; + unsigned long ax; sigset_t set; - int ax; + frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long)); if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) goto badframe; if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) @@ -229,7 +244,7 @@ asmlinkage int sys_rt_sigreturn(unsigned long __unused) current->blocked = set; recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); - + if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax)) goto badframe; @@ -241,12 +256,11 @@ asmlinkage int sys_rt_sigreturn(unsigned long __unused) badframe: force_sig(SIGSEGV, current); return 0; -} +} /* * Set up a signal frame. */ - static int setup_sigcontext(struct sigcontext __user *sc, struct _fpstate __user *fpstate, struct pt_regs *regs, unsigned long mask) @@ -277,9 +291,9 @@ setup_sigcontext(struct sigcontext __user *sc, struct _fpstate __user *fpstate, tmp = save_i387(fpstate); if (tmp < 0) - err = 1; + err = 1; else - err |= __put_user(tmp ? fpstate : NULL, &sc->fpstate); + err |= __put_user(tmp ? fpstate : NULL, &sc->fpstate); /* non-iBCS2 extensions.. */ err |= __put_user(mask, &sc->oldmask); @@ -292,7 +306,7 @@ setup_sigcontext(struct sigcontext __user *sc, struct _fpstate __user *fpstate, * Determine which stack to use.. */ static inline void __user * -get_sigframe(struct k_sigaction *ka, struct pt_regs * regs, size_t frame_size) +get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size) { unsigned long sp; @@ -310,32 +324,30 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs * regs, size_t frame_size) if (ka->sa.sa_flags & SA_ONSTACK) { if (sas_ss_flags(sp) == 0) sp = current->sas_ss_sp + current->sas_ss_size; - } - - /* This is the legacy signal stack switching. */ - else if ((regs->ss & 0xffff) != __USER_DS && - !(ka->sa.sa_flags & SA_RESTORER) && - ka->sa.sa_restorer) { - sp = (unsigned long) ka->sa.sa_restorer; + } else { + /* This is the legacy signal stack switching. */ + if ((regs->ss & 0xffff) != __USER_DS && + !(ka->sa.sa_flags & SA_RESTORER) && + ka->sa.sa_restorer) + sp = (unsigned long) ka->sa.sa_restorer; } sp -= frame_size; - /* Align the stack pointer according to the i386 ABI, - * i.e. so that on function entry ((sp + 4) & 15) == 0. */ + /* + * Align the stack pointer according to the i386 ABI, + * i.e. so that on function entry ((sp + 4) & 15) == 0. + */ sp = ((sp + 4) & -16ul) - 4; + return (void __user *) sp; } -/* These symbols are defined with the addresses in the vsyscall page. - See vsyscall-sigreturn.S. */ -extern void __user __kernel_sigreturn; -extern void __user __kernel_rt_sigreturn; - -static int setup_frame(int sig, struct k_sigaction *ka, - sigset_t *set, struct pt_regs * regs) +static int +setup_frame(int sig, struct k_sigaction *ka, sigset_t *set, + struct pt_regs *regs) { - void __user *restorer; struct sigframe __user *frame; + void __user *restorer; int err = 0; int usig; @@ -365,7 +377,7 @@ static int setup_frame(int sig, struct k_sigaction *ka, goto give_sigsegv; } - if (current->binfmt->hasvdso) + if (current->mm->context.vdso) restorer = VDSO32_SYMBOL(current->mm->context.vdso, sigreturn); else restorer = &frame->retcode; @@ -374,9 +386,9 @@ static int setup_frame(int sig, struct k_sigaction *ka, /* Set up to return from userspace. */ err |= __put_user(restorer, &frame->pretcode); - + /* - * This is popl %eax ; movl $,%eax ; int $0x80 + * This is popl %eax ; movl $__NR_sigreturn, %eax ; int $0x80 * * WE DO NOT USE IT ANY MORE! It's only left here for historical * reasons and because gdb uses it as a signature to notice @@ -390,32 +402,17 @@ static int setup_frame(int sig, struct k_sigaction *ka, goto give_sigsegv; /* Set up registers for signal handler */ - regs->sp = (unsigned long) frame; - regs->ip = (unsigned long) ka->sa.sa_handler; - regs->ax = (unsigned long) sig; - regs->dx = (unsigned long) 0; - regs->cx = (unsigned long) 0; + regs->sp = (unsigned long)frame; + regs->ip = (unsigned long)ka->sa.sa_handler; + regs->ax = (unsigned long)sig; + regs->dx = 0; + regs->cx = 0; regs->ds = __USER_DS; regs->es = __USER_DS; regs->ss = __USER_DS; regs->cs = __USER_CS; - /* - * Clear TF when entering the signal handler, but - * notify any tracer that was single-stepping it. - * The tracer may want to single-step inside the - * handler too. - */ - regs->flags &= ~(TF_MASK | X86_EFLAGS_DF); - if (test_thread_flag(TIF_SINGLESTEP)) - ptrace_notify(SIGTRAP); - -#if DEBUG_SIG - printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n", - current->comm, current->pid, frame, regs->ip, frame->pretcode); -#endif - return 0; give_sigsegv: @@ -424,10 +421,10 @@ give_sigsegv: } static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, - sigset_t *set, struct pt_regs * regs) + sigset_t *set, struct pt_regs *regs) { - void __user *restorer; struct rt_sigframe __user *frame; + void __user *restorer; int err = 0; int usig; @@ -457,7 +454,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, &frame->uc.uc_stack.ss_flags); err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size); err |= setup_sigcontext(&frame->uc.uc_mcontext, &frame->fpstate, - regs, set->sig[0]); + regs, set->sig[0]); err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); if (err) goto give_sigsegv; @@ -467,9 +464,9 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, if (ka->sa.sa_flags & SA_RESTORER) restorer = ka->sa.sa_restorer; err |= __put_user(restorer, &frame->pretcode); - + /* - * This is movl $,%ax ; int $0x80 + * This is movl $__NR_rt_sigreturn, %ax ; int $0x80 * * WE DO NOT USE IT ANY MORE! It's only left here for historical * reasons and because gdb uses it as a signature to notice @@ -483,32 +480,17 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, goto give_sigsegv; /* Set up registers for signal handler */ - regs->sp = (unsigned long) frame; - regs->ip = (unsigned long) ka->sa.sa_handler; - regs->ax = (unsigned long) usig; - regs->dx = (unsigned long) &frame->info; - regs->cx = (unsigned long) &frame->uc; + regs->sp = (unsigned long)frame; + regs->ip = (unsigned long)ka->sa.sa_handler; + regs->ax = (unsigned long)usig; + regs->dx = (unsigned long)&frame->info; + regs->cx = (unsigned long)&frame->uc; regs->ds = __USER_DS; regs->es = __USER_DS; regs->ss = __USER_DS; regs->cs = __USER_CS; - /* - * Clear TF when entering the signal handler, but - * notify any tracer that was single-stepping it. - * The tracer may want to single-step inside the - * handler too. - */ - regs->flags &= ~(TF_MASK | X86_EFLAGS_DF); - if (test_thread_flag(TIF_SINGLESTEP)) - ptrace_notify(SIGTRAP); - -#if DEBUG_SIG - printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n", - current->comm, current->pid, frame, regs->ip, frame->pretcode); -#endif - return 0; give_sigsegv: @@ -517,33 +499,33 @@ give_sigsegv: } /* - * OK, we're invoking a handler - */ - + * OK, we're invoking a handler: + */ static int handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, - sigset_t *oldset, struct pt_regs * regs) + sigset_t *oldset, struct pt_regs *regs) { int ret; /* Are we from a system call? */ - if (regs->orig_ax >= 0) { + if ((long)regs->orig_ax >= 0) { /* If so, check system call restarting.. */ switch (regs->ax) { - case -ERESTART_RESTARTBLOCK: - case -ERESTARTNOHAND: + case -ERESTART_RESTARTBLOCK: + case -ERESTARTNOHAND: + regs->ax = -EINTR; + break; + + case -ERESTARTSYS: + if (!(ka->sa.sa_flags & SA_RESTART)) { regs->ax = -EINTR; break; - - case -ERESTARTSYS: - if (!(ka->sa.sa_flags & SA_RESTART)) { - regs->ax = -EINTR; - break; - } - /* fallthrough */ - case -ERESTARTNOINTR: - regs->ax = regs->orig_ax; - regs->ip -= 2; + } + /* fallthrough */ + case -ERESTARTNOINTR: + regs->ax = regs->orig_ax; + regs->ip -= 2; + break; } } @@ -561,16 +543,32 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, else ret = setup_frame(sig, ka, oldset, regs); - if (ret == 0) { - spin_lock_irq(¤t->sighand->siglock); - sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); - if (!(ka->sa.sa_flags & SA_NODEFER)) - sigaddset(¤t->blocked,sig); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - } + if (ret) + return ret; - return ret; + /* + * Clear the direction flag as per the ABI for function entry. + */ + regs->flags &= ~X86_EFLAGS_DF; + + /* + * Clear TF when entering the signal handler, but + * notify any tracer that was single-stepping it. + * The tracer may want to single-step inside the + * handler too. + */ + regs->flags &= ~X86_EFLAGS_TF; + if (test_thread_flag(TIF_SINGLESTEP)) + ptrace_notify(SIGTRAP); + + spin_lock_irq(¤t->sighand->siglock); + sigorsets(¤t->blocked, ¤t->blocked, &ka->sa.sa_mask); + if (!(ka->sa.sa_flags & SA_NODEFER)) + sigaddset(¤t->blocked, sig); + recalc_sigpending(); + spin_unlock_irq(¤t->sighand->siglock); + + return 0; } /* @@ -580,52 +578,52 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, */ static void do_signal(struct pt_regs *regs) { + struct k_sigaction ka; siginfo_t info; int signr; - struct k_sigaction ka; sigset_t *oldset; /* - * We want the common case to go fast, which - * is why we may in certain cases get here from - * kernel mode. Just return without doing anything - * if so. vm86 regs switched out by assembly code - * before reaching here, so testing against kernel - * CS suffices. + * We want the common case to go fast, which is why we may in certain + * cases get here from kernel mode. Just return without doing anything + * if so. + * X86_32: vm86 regs switched out by assembly code before reaching + * here, so testing against kernel CS suffices. */ if (!user_mode(regs)) return; - if (test_thread_flag(TIF_RESTORE_SIGMASK)) + if (current_thread_info()->status & TS_RESTORE_SIGMASK) oldset = ¤t->saved_sigmask; else oldset = ¤t->blocked; signr = get_signal_to_deliver(&info, &ka, regs, NULL); if (signr > 0) { - /* Re-enable any watchpoints before delivering the + /* + * Re-enable any watchpoints before delivering the * signal to user space. The processor register will * have been cleared if the watchpoint triggered * inside the kernel. */ - if (unlikely(current->thread.debugreg7)) + if (current->thread.debugreg7) set_debugreg(current->thread.debugreg7, 7); - /* Whee! Actually deliver the signal. */ + /* Whee! Actually deliver the signal. */ if (handle_signal(signr, &info, &ka, oldset, regs) == 0) { - /* a signal was successfully delivered; the saved + /* + * A signal was successfully delivered; the saved * sigmask will have been stored in the signal frame, * and will be restored by sigreturn, so we can simply - * clear the TIF_RESTORE_SIGMASK flag */ - if (test_thread_flag(TIF_RESTORE_SIGMASK)) - clear_thread_flag(TIF_RESTORE_SIGMASK); + * clear the TS_RESTORE_SIGMASK flag. + */ + current_thread_info()->status &= ~TS_RESTORE_SIGMASK; } - return; } /* Did we come from a system call? */ - if (regs->orig_ax >= 0) { + if ((long)regs->orig_ax >= 0) { /* Restart the system call - no handlers present */ switch (regs->ax) { case -ERESTARTNOHAND: @@ -642,10 +640,12 @@ static void do_signal(struct pt_regs *regs) } } - /* if there's no signal to deliver, we just put the saved sigmask - * back */ - if (test_thread_flag(TIF_RESTORE_SIGMASK)) { - clear_thread_flag(TIF_RESTORE_SIGMASK); + /* + * If there's no signal to deliver, we just put the saved sigmask + * back. + */ + if (current_thread_info()->status & TS_RESTORE_SIGMASK) { + current_thread_info()->status &= ~TS_RESTORE_SIGMASK; sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); } } @@ -654,22 +654,21 @@ static void do_signal(struct pt_regs *regs) * notification of userspace execution resumption * - triggered by the TIF_WORK_MASK flags */ -__attribute__((regparm(3))) -void do_notify_resume(struct pt_regs *regs, void *_unused, - __u32 thread_info_flags) +void +do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) { /* Pending single-step? */ if (thread_info_flags & _TIF_SINGLESTEP) { - regs->flags |= TF_MASK; + regs->flags |= X86_EFLAGS_TF; clear_thread_flag(TIF_SINGLESTEP); } /* deal with pending signal delivery */ - if (thread_info_flags & (_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK)) + if (thread_info_flags & _TIF_SIGPENDING) do_signal(regs); if (thread_info_flags & _TIF_HRTICK_RESCHED) hrtick_resched(); - + clear_thread_flag(TIF_IRET); } diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c index 1c83e5124c65..e53b267662e7 100644 --- a/arch/x86/kernel/signal_64.c +++ b/arch/x86/kernel/signal_64.c @@ -19,17 +19,28 @@ #include <linux/stddef.h> #include <linux/personality.h> #include <linux/compiler.h> +#include <asm/processor.h> #include <asm/ucontext.h> #include <asm/uaccess.h> #include <asm/i387.h> #include <asm/proto.h> #include <asm/ia32_unistd.h> #include <asm/mce.h> - -/* #define DEBUG_SIG 1 */ +#include "sigframe.h" #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) +#define __FIX_EFLAGS (X86_EFLAGS_AC | X86_EFLAGS_OF | \ + X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \ + X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \ + X86_EFLAGS_CF) + +#ifdef CONFIG_X86_32 +# define FIX_EFLAGS (__FIX_EFLAGS | X86_EFLAGS_RF) +#else +# define FIX_EFLAGS __FIX_EFLAGS +#endif + int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *set, struct pt_regs * regs); int ia32_setup_frame(int sig, struct k_sigaction *ka, @@ -46,16 +57,9 @@ sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, /* * Do a signal return; undo the signal stack. */ - -struct rt_sigframe -{ - char __user *pretcode; - struct ucontext uc; - struct siginfo info; -}; - static int -restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, unsigned long *prax) +restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, + unsigned long *pax) { unsigned int err = 0; @@ -87,7 +91,7 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, unsigned { unsigned int tmpflags; err |= __get_user(tmpflags, &sc->flags); - regs->flags = (regs->flags & ~0x40DD5) | (tmpflags & 0x40DD5); + regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); regs->orig_ax = -1; /* disable syscall checks */ } @@ -108,7 +112,7 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, unsigned } } - err |= __get_user(*prax, &sc->ax); + err |= __get_user(*pax, &sc->ax); return err; badframe: @@ -121,13 +125,11 @@ asmlinkage long sys_rt_sigreturn(struct pt_regs *regs) sigset_t set; unsigned long ax; - frame = (struct rt_sigframe __user *)(regs->sp - 8); - if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) { + frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long)); + if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) goto badframe; - } - if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) { + if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) goto badframe; - } sigdelsetmask(&set, ~_BLOCKABLE); spin_lock_irq(¤t->sighand->siglock); @@ -138,10 +140,6 @@ asmlinkage long sys_rt_sigreturn(struct pt_regs *regs) if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax)) goto badframe; -#ifdef DEBUG_SIG - printk("%d sigreturn ip:%lx sp:%lx frame:%p ax:%lx\n",current->pid,regs->ip,regs->sp,frame,ax); -#endif - if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->sp) == -EFAULT) goto badframe; @@ -270,10 +268,6 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, if (err) goto give_sigsegv; -#ifdef DEBUG_SIG - printk("%d old ip %lx old sp %lx old ax %lx\n", current->pid,regs->ip,regs->sp,regs->ax); -#endif - /* Set up registers for signal handler */ regs->di = sig; /* In case the signal handler was declared without prototypes */ @@ -291,18 +285,6 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, even if the handler happens to be interrupting 32-bit code. */ regs->cs = __USER_CS; - /* This, by contrast, has nothing to do with segment registers - - see include/asm-x86_64/uaccess.h for details. */ - set_fs(USER_DS); - - regs->flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_DF); - if (test_thread_flag(TIF_SINGLESTEP)) - ptrace_notify(SIGTRAP); -#ifdef DEBUG_SIG - printk("SIG deliver (%s:%d): sp=%p pc=%lx ra=%p\n", - current->comm, current->pid, frame, regs->ip, frame->pretcode); -#endif - return 0; give_sigsegv: @@ -345,35 +327,29 @@ static long current_syscall_ret(struct pt_regs *regs) static int handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, - sigset_t *oldset, struct pt_regs *regs) + sigset_t *oldset, struct pt_regs *regs) { int ret; -#ifdef DEBUG_SIG - printk("handle_signal pid:%d sig:%lu ip:%lx sp:%lx regs=%p\n", - current->pid, sig, - regs->ip, regs->sp, regs); -#endif - /* Are we from a system call? */ if (current_syscall(regs) >= 0) { /* If so, check system call restarting.. */ switch (current_syscall_ret(regs)) { - case -ERESTART_RESTARTBLOCK: - case -ERESTARTNOHAND: - regs->ax = -EINTR; - break; + case -ERESTART_RESTARTBLOCK: + case -ERESTARTNOHAND: + regs->ax = -EINTR; + break; - case -ERESTARTSYS: - if (!(ka->sa.sa_flags & SA_RESTART)) { - regs->ax = -EINTR; - break; - } - /* fallthrough */ - case -ERESTARTNOINTR: - regs->ax = regs->orig_ax; - regs->ip -= 2; + case -ERESTARTSYS: + if (!(ka->sa.sa_flags & SA_RESTART)) { + regs->ax = -EINTR; break; + } + /* fallthrough */ + case -ERESTARTNOINTR: + regs->ax = regs->orig_ax; + regs->ip -= 2; + break; } } @@ -396,6 +372,28 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, ret = setup_rt_frame(sig, ka, info, oldset, regs); if (ret == 0) { + /* + * This has nothing to do with segment registers, + * despite the name. This magic affects uaccess.h + * macros' behavior. Reset it to the normal setting. + */ + set_fs(USER_DS); + + /* + * Clear the direction flag as per the ABI for function entry. + */ + regs->flags &= ~X86_EFLAGS_DF; + + /* + * Clear TF when entering the signal handler, but + * notify any tracer that was single-stepping it. + * The tracer may want to single-step inside the + * handler too. + */ + regs->flags &= ~X86_EFLAGS_TF; + if (test_thread_flag(TIF_SINGLESTEP)) + ptrace_notify(SIGTRAP); + spin_lock_irq(¤t->sighand->siglock); sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); if (!(ka->sa.sa_flags & SA_NODEFER)) @@ -420,15 +418,16 @@ static void do_signal(struct pt_regs *regs) sigset_t *oldset; /* - * We want the common case to go fast, which - * is why we may in certain cases get here from - * kernel mode. Just return without doing anything + * We want the common case to go fast, which is why we may in certain + * cases get here from kernel mode. Just return without doing anything * if so. + * X86_32: vm86 regs switched out by assembly code before reaching + * here, so testing against kernel CS suffices. */ if (!user_mode(regs)) return; - if (test_thread_flag(TIF_RESTORE_SIGMASK)) + if (current_thread_info()->status & TS_RESTORE_SIGMASK) oldset = ¤t->saved_sigmask; else oldset = ¤t->blocked; @@ -445,11 +444,13 @@ static void do_signal(struct pt_regs *regs) /* Whee! Actually deliver the signal. */ if (handle_signal(signr, &info, &ka, oldset, regs) == 0) { - /* a signal was successfully delivered; the saved + /* + * A signal was successfully delivered; the saved * sigmask will have been stored in the signal frame, * and will be restored by sigreturn, so we can simply - * clear the TIF_RESTORE_SIGMASK flag */ - clear_thread_flag(TIF_RESTORE_SIGMASK); + * clear the TS_RESTORE_SIGMASK flag. + */ + current_thread_info()->status &= ~TS_RESTORE_SIGMASK; } return; } @@ -473,22 +474,19 @@ static void do_signal(struct pt_regs *regs) } } - /* if there's no signal to deliver, we just put the saved sigmask - back. */ - if (test_thread_flag(TIF_RESTORE_SIGMASK)) { - clear_thread_flag(TIF_RESTORE_SIGMASK); + /* + * If there's no signal to deliver, we just put the saved sigmask + * back. + */ + if (current_thread_info()->status & TS_RESTORE_SIGMASK) { + current_thread_info()->status &= ~TS_RESTORE_SIGMASK; sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); } } -void -do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) +void do_notify_resume(struct pt_regs *regs, void *unused, + __u32 thread_info_flags) { -#ifdef DEBUG_SIG - printk("do_notify_resume flags:%x ip:%lx sp:%lx caller:%p pending:%x\n", - thread_info_flags, regs->ip, regs->sp, __builtin_return_address(0),signal_pending(current)); -#endif - /* Pending single-step? */ if (thread_info_flags & _TIF_SINGLESTEP) { regs->flags |= X86_EFLAGS_TF; @@ -502,7 +500,7 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) #endif /* CONFIG_X86_MCE */ /* deal with pending signal delivery */ - if (thread_info_flags & (_TIF_SIGPENDING|_TIF_RESTORE_SIGMASK)) + if (thread_info_flags & _TIF_SIGPENDING) do_signal(regs); if (thread_info_flags & _TIF_HRTICK_RESCHED) diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c new file mode 100644 index 000000000000..8f75893a6467 --- /dev/null +++ b/arch/x86/kernel/smp.c @@ -0,0 +1,343 @@ +/* + * Intel SMP support routines. + * + * (c) 1995 Alan Cox, Building #3 <alan@redhat.com> + * (c) 1998-99, 2000 Ingo Molnar <mingo@redhat.com> + * (c) 2002,2003 Andi Kleen, SuSE Labs. + * + * i386 and x86_64 integration by Glauber Costa <gcosta@redhat.com> + * + * This code is released under the GNU General Public License version 2 or + * later. + */ + +#include <linux/init.h> + +#include <linux/mm.h> +#include <linux/delay.h> +#include <linux/spinlock.h> +#include <linux/kernel_stat.h> +#include <linux/mc146818rtc.h> +#include <linux/cache.h> +#include <linux/interrupt.h> +#include <linux/cpu.h> + +#include <asm/mtrr.h> +#include <asm/tlbflush.h> +#include <asm/mmu_context.h> +#include <asm/proto.h> +#include <mach_ipi.h> +#include <mach_apic.h> +/* + * Some notes on x86 processor bugs affecting SMP operation: + * + * Pentium, Pentium Pro, II, III (and all CPUs) have bugs. + * The Linux implications for SMP are handled as follows: + * + * Pentium III / [Xeon] + * None of the E1AP-E3AP errata are visible to the user. + * + * E1AP. see PII A1AP + * E2AP. see PII A2AP + * E3AP. see PII A3AP + * + * Pentium II / [Xeon] + * None of the A1AP-A3AP errata are visible to the user. + * + * A1AP. see PPro 1AP + * A2AP. see PPro 2AP + * A3AP. see PPro 7AP + * + * Pentium Pro + * None of 1AP-9AP errata are visible to the normal user, + * except occasional delivery of 'spurious interrupt' as trap #15. + * This is very rare and a non-problem. + * + * 1AP. Linux maps APIC as non-cacheable + * 2AP. worked around in hardware + * 3AP. fixed in C0 and above steppings microcode update. + * Linux does not use excessive STARTUP_IPIs. + * 4AP. worked around in hardware + * 5AP. symmetric IO mode (normal Linux operation) not affected. + * 'noapic' mode has vector 0xf filled out properly. + * 6AP. 'noapic' mode might be affected - fixed in later steppings + * 7AP. We do not assume writes to the LVT deassering IRQs + * 8AP. We do not enable low power mode (deep sleep) during MP bootup + * 9AP. We do not use mixed mode + * + * Pentium + * There is a marginal case where REP MOVS on 100MHz SMP + * machines with B stepping processors can fail. XXX should provide + * an L1cache=Writethrough or L1cache=off option. + * + * B stepping CPUs may hang. There are hardware work arounds + * for this. We warn about it in case your board doesn't have the work + * arounds. Basically that's so I can tell anyone with a B stepping + * CPU and SMP problems "tough". + * + * Specific items [From Pentium Processor Specification Update] + * + * 1AP. Linux doesn't use remote read + * 2AP. Linux doesn't trust APIC errors + * 3AP. We work around this + * 4AP. Linux never generated 3 interrupts of the same priority + * to cause a lost local interrupt. + * 5AP. Remote read is never used + * 6AP. not affected - worked around in hardware + * 7AP. not affected - worked around in hardware + * 8AP. worked around in hardware - we get explicit CS errors if not + * 9AP. only 'noapic' mode affected. Might generate spurious + * interrupts, we log only the first one and count the + * rest silently. + * 10AP. not affected - worked around in hardware + * 11AP. Linux reads the APIC between writes to avoid this, as per + * the documentation. Make sure you preserve this as it affects + * the C stepping chips too. + * 12AP. not affected - worked around in hardware + * 13AP. not affected - worked around in hardware + * 14AP. we always deassert INIT during bootup + * 15AP. not affected - worked around in hardware + * 16AP. not affected - worked around in hardware + * 17AP. not affected - worked around in hardware + * 18AP. not affected - worked around in hardware + * 19AP. not affected - worked around in BIOS + * + * If this sounds worrying believe me these bugs are either ___RARE___, + * or are signal timing bugs worked around in hardware and there's + * about nothing of note with C stepping upwards. + */ + +/* + * this function sends a 'reschedule' IPI to another CPU. + * it goes straight through and wastes no time serializing + * anything. Worst case is that we lose a reschedule ... + */ +static void native_smp_send_reschedule(int cpu) +{ + if (unlikely(cpu_is_offline(cpu))) { + WARN_ON(1); + return; + } + 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) +{ + 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(); +} + + +/** + * 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) +{ + 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)) + 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) +{ + local_irq_disable(); + /* + * Remove this CPU: + */ + cpu_clear(smp_processor_id(), cpu_online_map); + disable_local_APIC(); + if (hlt_works(smp_processor_id())) + for (;;) halt(); + for (;;); +} + +/* + * this function calls the 'stop' function on all other CPUs in the system. + */ + +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); + 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); +} + +/* + * Reschedule call back. Nothing to do, + * all the work is done automatically when + * we return from the interrupt. + */ +void smp_reschedule_interrupt(struct pt_regs *regs) +{ + ack_APIC_irq(); +#ifdef CONFIG_X86_32 + __get_cpu_var(irq_stat).irq_resched_count++; +#else + add_pda(irq_resched_count, 1); +#endif +} + +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); +#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); + } +} + +struct smp_ops smp_ops = { + .smp_prepare_boot_cpu = native_smp_prepare_boot_cpu, + .smp_prepare_cpus = native_smp_prepare_cpus, + .cpu_up = native_cpu_up, + .smp_cpus_done = native_smp_cpus_done, + + .smp_send_stop = native_smp_send_stop, + .smp_send_reschedule = native_smp_send_reschedule, + .smp_call_function_mask = native_smp_call_function_mask, +}; +EXPORT_SYMBOL_GPL(smp_ops); + diff --git a/arch/x86/kernel/smp_32.c b/arch/x86/kernel/smp_32.c deleted file mode 100644 index dc0cde9d16fb..000000000000 --- a/arch/x86/kernel/smp_32.c +++ /dev/null @@ -1,712 +0,0 @@ -/* - * Intel SMP support routines. - * - * (c) 1995 Alan Cox, Building #3 <alan@redhat.com> - * (c) 1998-99, 2000 Ingo Molnar <mingo@redhat.com> - * - * This code is released under the GNU General Public License version 2 or - * later. - */ - -#include <linux/init.h> - -#include <linux/mm.h> -#include <linux/delay.h> -#include <linux/spinlock.h> -#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> - -#include <asm/mtrr.h> -#include <asm/tlbflush.h> -#include <asm/mmu_context.h> -#include <mach_apic.h> - -/* - * Some notes on x86 processor bugs affecting SMP operation: - * - * Pentium, Pentium Pro, II, III (and all CPUs) have bugs. - * The Linux implications for SMP are handled as follows: - * - * Pentium III / [Xeon] - * None of the E1AP-E3AP errata are visible to the user. - * - * E1AP. see PII A1AP - * E2AP. see PII A2AP - * E3AP. see PII A3AP - * - * Pentium II / [Xeon] - * None of the A1AP-A3AP errata are visible to the user. - * - * A1AP. see PPro 1AP - * A2AP. see PPro 2AP - * A3AP. see PPro 7AP - * - * Pentium Pro - * None of 1AP-9AP errata are visible to the normal user, - * except occasional delivery of 'spurious interrupt' as trap #15. - * This is very rare and a non-problem. - * - * 1AP. Linux maps APIC as non-cacheable - * 2AP. worked around in hardware - * 3AP. fixed in C0 and above steppings microcode update. - * Linux does not use excessive STARTUP_IPIs. - * 4AP. worked around in hardware - * 5AP. symmetric IO mode (normal Linux operation) not affected. - * 'noapic' mode has vector 0xf filled out properly. - * 6AP. 'noapic' mode might be affected - fixed in later steppings - * 7AP. We do not assume writes to the LVT deassering IRQs - * 8AP. We do not enable low power mode (deep sleep) during MP bootup - * 9AP. We do not use mixed mode - * - * Pentium - * There is a marginal case where REP MOVS on 100MHz SMP - * machines with B stepping processors can fail. XXX should provide - * an L1cache=Writethrough or L1cache=off option. - * - * B stepping CPUs may hang. There are hardware work arounds - * for this. We warn about it in case your board doesn't have the work - * arounds. Basically that's so I can tell anyone with a B stepping - * CPU and SMP problems "tough". - * - * Specific items [From Pentium Processor Specification Update] - * - * 1AP. Linux doesn't use remote read - * 2AP. Linux doesn't trust APIC errors - * 3AP. We work around this - * 4AP. Linux never generated 3 interrupts of the same priority - * to cause a lost local interrupt. - * 5AP. Remote read is never used - * 6AP. not affected - worked around in hardware - * 7AP. not affected - worked around in hardware - * 8AP. worked around in hardware - we get explicit CS errors if not - * 9AP. only 'noapic' mode affected. Might generate spurious - * interrupts, we log only the first one and count the - * rest silently. - * 10AP. not affected - worked around in hardware - * 11AP. Linux reads the APIC between writes to avoid this, as per - * the documentation. Make sure you preserve this as it affects - * the C stepping chips too. - * 12AP. not affected - worked around in hardware - * 13AP. not affected - worked around in hardware - * 14AP. we always deassert INIT during bootup - * 15AP. not affected - worked around in hardware - * 16AP. not affected - worked around in hardware - * 17AP. not affected - worked around in hardware - * 18AP. not affected - worked around in hardware - * 19AP. not affected - worked around in BIOS - * - * If this sounds worrying believe me these bugs are either ___RARE___, - * or are signal timing bugs worked around in hardware and there's - * about nothing of note with C stepping upwards. - */ - -DEFINE_PER_CPU(struct tlb_state, cpu_tlbstate) ____cacheline_aligned = { &init_mm, 0, }; - -/* - * the following functions deal with sending IPIs between CPUs. - * - * We use 'broadcast', CPU->CPU IPIs and self-IPIs too. - */ - -static inline int __prepare_ICR (unsigned int shortcut, int vector) -{ - unsigned int icr = shortcut | APIC_DEST_LOGICAL; - - switch (vector) { - default: - icr |= APIC_DM_FIXED | vector; - break; - case NMI_VECTOR: - icr |= APIC_DM_NMI; - break; - } - return icr; -} - -static inline int __prepare_ICR2 (unsigned int mask) -{ - return SET_APIC_DEST_FIELD(mask); -} - -void __send_IPI_shortcut(unsigned int shortcut, int vector) -{ - /* - * Subtle. In the case of the 'never do double writes' workaround - * we have to lock out interrupts to be safe. As we don't care - * of the value read we use an atomic rmw access to avoid costly - * cli/sti. Otherwise we use an even cheaper single atomic write - * to the APIC. - */ - unsigned int cfg; - - /* - * Wait for idle. - */ - apic_wait_icr_idle(); - - /* - * No need to touch the target chip field - */ - cfg = __prepare_ICR(shortcut, vector); - - /* - * Send the IPI. The write to APIC_ICR fires this off. - */ - apic_write_around(APIC_ICR, cfg); -} - -void send_IPI_self(int vector) -{ - __send_IPI_shortcut(APIC_DEST_SELF, vector); -} - -/* - * This is used to send an IPI with no shorthand notation (the destination is - * specified in bits 56 to 63 of the ICR). - */ -static inline void __send_IPI_dest_field(unsigned long mask, int vector) -{ - unsigned long cfg; - - /* - * Wait for idle. - */ - if (unlikely(vector == NMI_VECTOR)) - safe_apic_wait_icr_idle(); - else - apic_wait_icr_idle(); - - /* - * prepare target chip field - */ - cfg = __prepare_ICR2(mask); - apic_write_around(APIC_ICR2, cfg); - - /* - * program the ICR - */ - cfg = __prepare_ICR(0, vector); - - /* - * Send the IPI. The write to APIC_ICR fires this off. - */ - apic_write_around(APIC_ICR, cfg); -} - -/* - * This is only used on smaller machines. - */ -void send_IPI_mask_bitmask(cpumask_t cpumask, int vector) -{ - unsigned long mask = cpus_addr(cpumask)[0]; - unsigned long flags; - - local_irq_save(flags); - WARN_ON(mask & ~cpus_addr(cpu_online_map)[0]); - __send_IPI_dest_field(mask, vector); - local_irq_restore(flags); -} - -void send_IPI_mask_sequence(cpumask_t mask, int vector) -{ - unsigned long flags; - unsigned int query_cpu; - - /* - * Hack. The clustered APIC addressing mode doesn't allow us to send - * to an arbitrary mask, so I do a unicasts to each CPU instead. This - * should be modified to do 1 message per cluster ID - mbligh - */ - - local_irq_save(flags); - for_each_possible_cpu(query_cpu) { - if (cpu_isset(query_cpu, mask)) { - __send_IPI_dest_field(cpu_to_logical_apicid(query_cpu), - vector); - } - } - local_irq_restore(flags); -} - -#include <mach_ipi.h> /* must come after the send_IPI functions above for inlining */ - -/* - * Smarter SMP flushing macros. - * c/o Linus Torvalds. - * - * These mean you can really definitely utterly forget about - * writing to user space from interrupts. (Its not allowed anyway). - * - * Optimizations Manfred Spraul <manfred@colorfullife.com> - */ - -static cpumask_t flush_cpumask; -static struct mm_struct * flush_mm; -static unsigned long flush_va; -static DEFINE_SPINLOCK(tlbstate_lock); - -/* - * We cannot call mmdrop() because we are in interrupt context, - * instead update mm->cpu_vm_mask. - * - * We need to reload %cr3 since the page tables may be going - * away from under us.. - */ -void leave_mm(int cpu) -{ - if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK) - BUG(); - cpu_clear(cpu, per_cpu(cpu_tlbstate, cpu).active_mm->cpu_vm_mask); - load_cr3(swapper_pg_dir); -} -EXPORT_SYMBOL_GPL(leave_mm); - -/* - * - * The flush IPI assumes that a thread switch happens in this order: - * [cpu0: the cpu that switches] - * 1) switch_mm() either 1a) or 1b) - * 1a) thread switch to a different mm - * 1a1) cpu_clear(cpu, old_mm->cpu_vm_mask); - * Stop ipi delivery for the old mm. This is not synchronized with - * the other cpus, but smp_invalidate_interrupt ignore flush ipis - * for the wrong mm, and in the worst case we perform a superfluous - * tlb flush. - * 1a2) set cpu_tlbstate to TLBSTATE_OK - * Now the smp_invalidate_interrupt won't call leave_mm if cpu0 - * was in lazy tlb mode. - * 1a3) update cpu_tlbstate[].active_mm - * Now cpu0 accepts tlb flushes for the new mm. - * 1a4) cpu_set(cpu, new_mm->cpu_vm_mask); - * Now the other cpus will send tlb flush ipis. - * 1a4) change cr3. - * 1b) thread switch without mm change - * cpu_tlbstate[].active_mm is correct, cpu0 already handles - * flush ipis. - * 1b1) set cpu_tlbstate to TLBSTATE_OK - * 1b2) test_and_set the cpu bit in cpu_vm_mask. - * Atomically set the bit [other cpus will start sending flush ipis], - * and test the bit. - * 1b3) if the bit was 0: leave_mm was called, flush the tlb. - * 2) switch %%esp, ie current - * - * The interrupt must handle 2 special cases: - * - cr3 is changed before %%esp, ie. it cannot use current->{active_,}mm. - * - the cpu performs speculative tlb reads, i.e. even if the cpu only - * runs in kernel space, the cpu could load tlb entries for user space - * pages. - * - * The good news is that cpu_tlbstate is local to each cpu, no - * write/read ordering problems. - */ - -/* - * TLB flush IPI: - * - * 1) Flush the tlb entries if the cpu uses the mm that's being flushed. - * 2) Leave the mm if we are in the lazy tlb mode. - */ - -void smp_invalidate_interrupt(struct pt_regs *regs) -{ - unsigned long cpu; - - cpu = get_cpu(); - - if (!cpu_isset(cpu, flush_cpumask)) - goto out; - /* - * This was a BUG() but until someone can quote me the - * line from the intel manual that guarantees an IPI to - * multiple CPUs is retried _only_ on the erroring CPUs - * its staying as a return - * - * BUG(); - */ - - if (flush_mm == per_cpu(cpu_tlbstate, cpu).active_mm) { - if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK) { - if (flush_va == TLB_FLUSH_ALL) - local_flush_tlb(); - else - __flush_tlb_one(flush_va); - } else - leave_mm(cpu); - } - ack_APIC_irq(); - smp_mb__before_clear_bit(); - cpu_clear(cpu, flush_cpumask); - smp_mb__after_clear_bit(); -out: - put_cpu_no_resched(); - __get_cpu_var(irq_stat).irq_tlb_count++; -} - -void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm, - unsigned long va) -{ - cpumask_t cpumask = *cpumaskp; - - /* - * A couple of (to be removed) sanity checks: - * - * - current CPU must not be in mask - * - mask must exist :) - */ - BUG_ON(cpus_empty(cpumask)); - BUG_ON(cpu_isset(smp_processor_id(), cpumask)); - BUG_ON(!mm); - -#ifdef CONFIG_HOTPLUG_CPU - /* If a CPU which we ran on has gone down, OK. */ - cpus_and(cpumask, cpumask, cpu_online_map); - if (unlikely(cpus_empty(cpumask))) - return; -#endif - - /* - * i'm not happy about this global shared spinlock in the - * MM hot path, but we'll see how contended it is. - * AK: x86-64 has a faster method that could be ported. - */ - spin_lock(&tlbstate_lock); - - flush_mm = mm; - flush_va = va; - cpus_or(flush_cpumask, cpumask, flush_cpumask); - /* - * We have to send the IPI only to - * CPUs affected. - */ - send_IPI_mask(cpumask, INVALIDATE_TLB_VECTOR); - - while (!cpus_empty(flush_cpumask)) - /* nothing. lockup detection does not belong here */ - cpu_relax(); - - flush_mm = NULL; - flush_va = 0; - spin_unlock(&tlbstate_lock); -} - -void flush_tlb_current_task(void) -{ - struct mm_struct *mm = current->mm; - cpumask_t cpu_mask; - - preempt_disable(); - cpu_mask = mm->cpu_vm_mask; - cpu_clear(smp_processor_id(), cpu_mask); - - local_flush_tlb(); - if (!cpus_empty(cpu_mask)) - flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL); - preempt_enable(); -} - -void flush_tlb_mm (struct mm_struct * mm) -{ - cpumask_t cpu_mask; - - preempt_disable(); - cpu_mask = mm->cpu_vm_mask; - cpu_clear(smp_processor_id(), cpu_mask); - - if (current->active_mm == mm) { - if (current->mm) - local_flush_tlb(); - else - leave_mm(smp_processor_id()); - } - if (!cpus_empty(cpu_mask)) - flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL); - - preempt_enable(); -} - -void flush_tlb_page(struct vm_area_struct * vma, unsigned long va) -{ - struct mm_struct *mm = vma->vm_mm; - cpumask_t cpu_mask; - - preempt_disable(); - cpu_mask = mm->cpu_vm_mask; - cpu_clear(smp_processor_id(), cpu_mask); - - if (current->active_mm == mm) { - if(current->mm) - __flush_tlb_one(va); - else - leave_mm(smp_processor_id()); - } - - if (!cpus_empty(cpu_mask)) - flush_tlb_others(cpu_mask, mm, va); - - preempt_enable(); -} -EXPORT_SYMBOL(flush_tlb_page); - -static void do_flush_tlb_all(void* info) -{ - unsigned long cpu = smp_processor_id(); - - __flush_tlb_all(); - if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_LAZY) - leave_mm(cpu); -} - -void flush_tlb_all(void) -{ - on_each_cpu(do_flush_tlb_all, NULL, 1, 1); -} - -/* - * this function sends a 'reschedule' IPI to another CPU. - * it goes straight through and wastes no time serializing - * anything. Worst case is that we lose a reschedule ... - */ -static void native_smp_send_reschedule(int cpu) -{ - WARN_ON(cpu_is_offline(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) -{ - 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(); -} - - -/** - * 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) -{ - 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; - mb(); - - /* Send a message to other CPUs */ - if (cpus_equal(mask, allbutself)) - send_IPI_allbutself(CALL_FUNCTION_VECTOR); - else - send_IPI_mask(mask, CALL_FUNCTION_VECTOR); - - /* Wait for response */ - while (atomic_read(&data.started) != cpus) - cpu_relax(); - - if (wait) - while (atomic_read(&data.finished) != cpus) - cpu_relax(); - spin_unlock(&call_lock); - - return 0; -} - -static void stop_this_cpu (void * dummy) -{ - local_irq_disable(); - /* - * Remove this CPU: - */ - cpu_clear(smp_processor_id(), cpu_online_map); - disable_local_APIC(); - if (cpu_data(smp_processor_id()).hlt_works_ok) - for(;;) halt(); - for (;;); -} - -/* - * this function calls the 'stop' function on all other CPUs in the system. - */ - -static void native_smp_send_stop(void) -{ - /* Don't deadlock on the call lock in panic */ - int nolock = !spin_trylock(&call_lock); - unsigned long flags; - - 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); -} - -/* - * Reschedule call back. Nothing to do, - * all the work is done automatically when - * we return from the interrupt. - */ -void smp_reschedule_interrupt(struct pt_regs *regs) -{ - ack_APIC_irq(); - __get_cpu_var(irq_stat).irq_resched_count++; -} - -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); - __get_cpu_var(irq_stat).irq_call_count++; - irq_exit(); - - if (wait) { - mb(); - atomic_inc(&call_data->finished); - } -} - -static int convert_apicid_to_cpu(int apic_id) -{ - int i; - - for_each_possible_cpu(i) { - if (per_cpu(x86_cpu_to_apicid, i) == apic_id) - return i; - } - return -1; -} - -int safe_smp_processor_id(void) -{ - int apicid, cpuid; - - if (!boot_cpu_has(X86_FEATURE_APIC)) - return 0; - - apicid = hard_smp_processor_id(); - if (apicid == BAD_APICID) - return 0; - - cpuid = convert_apicid_to_cpu(apicid); - - return cpuid >= 0 ? cpuid : 0; -} - -struct smp_ops smp_ops = { - .smp_prepare_boot_cpu = native_smp_prepare_boot_cpu, - .smp_prepare_cpus = native_smp_prepare_cpus, - .cpu_up = native_cpu_up, - .smp_cpus_done = native_smp_cpus_done, - - .smp_send_stop = native_smp_send_stop, - .smp_send_reschedule = native_smp_send_reschedule, - .smp_call_function_mask = native_smp_call_function_mask, -}; -EXPORT_SYMBOL_GPL(smp_ops); diff --git a/arch/x86/kernel/smpboot_32.c b/arch/x86/kernel/smpboot.c index 579b9b740c7c..84241a256dc8 100644 --- a/arch/x86/kernel/smpboot_32.c +++ b/arch/x86/kernel/smpboot.c @@ -3,6 +3,7 @@ * * (c) 1995 Alan Cox, Building #3 <alan@redhat.com> * (c) 1998, 1999, 2000 Ingo Molnar <mingo@redhat.com> + * Copyright 2001 Andi Kleen, SuSE Labs. * * Much of the core SMP work is based on previous work by Thomas Radke, to * whom a great many thanks are extended. @@ -29,53 +30,91 @@ * Ingo Molnar : various cleanups and rewrites * Tigran Aivazian : fixed "0.00 in /proc/uptime on SMP" bug. * Maciej W. Rozycki : Bits for genuine 82489DX APICs + * Andi Kleen : Changed for SMP boot into long mode. * Martin J. Bligh : Added support for multi-quad systems * Dave Jones : Report invalid combinations of Athlon CPUs. -* Rusty Russell : Hacked into shape for new "hotplug" boot process. */ + * Rusty Russell : Hacked into shape for new "hotplug" boot process. + * Andi Kleen : Converted to new state machine. + * Ashok Raj : CPU hotplug support + * Glauber Costa : i386 and x86_64 integration + */ -#include <linux/module.h> #include <linux/init.h> -#include <linux/kernel.h> - -#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/module.h> #include <linux/sched.h> -#include <linux/kernel_stat.h> -#include <linux/bootmem.h> -#include <linux/notifier.h> -#include <linux/cpu.h> #include <linux/percpu.h> +#include <linux/bootmem.h> +#include <linux/err.h> #include <linux/nmi.h> -#include <linux/delay.h> -#include <linux/mc146818rtc.h> -#include <asm/tlbflush.h> +#include <asm/acpi.h> #include <asm/desc.h> -#include <asm/arch_hooks.h> #include <asm/nmi.h> +#include <asm/irq.h> +#include <asm/smp.h> +#include <asm/trampoline.h> +#include <asm/cpu.h> +#include <asm/numa.h> +#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> #include <mach_apic.h> #include <mach_wakecpu.h> #include <smpboot_hooks.h> -#include <asm/vmi.h> -#include <asm/mtrr.h> -/* Set if we find a B stepping CPU */ -static int __cpuinitdata smp_b_stepping; +/* + * 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]; +#endif + +/* State of each CPU */ +DEFINE_PER_CPU(int, cpu_state) = { 0 }; + +/* Store all idle threads, this can be reused instead of creating +* a new thread. Also avoids complicated thread destroy functionality +* for idle threads. +*/ +#ifdef CONFIG_HOTPLUG_CPU +/* + * Needed only for CONFIG_HOTPLUG_CPU because __cpuinitdata is + * removed after init for !CONFIG_HOTPLUG_CPU. + */ +static DEFINE_PER_CPU(struct task_struct *, idle_thread_array); +#define get_idle_for_cpu(x) (per_cpu(idle_thread_array, x)) +#define set_idle_for_cpu(x, p) (per_cpu(idle_thread_array, x) = (p)) +#else +struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ; +#define get_idle_for_cpu(x) (idle_thread_array[(x)]) +#define set_idle_for_cpu(x, p) (idle_thread_array[(x)] = (p)) +#endif /* Number of siblings per CPU package */ int smp_num_siblings = 1; EXPORT_SYMBOL(smp_num_siblings); /* Last level cache ID of each logical CPU */ -DEFINE_PER_CPU(u8, cpu_llc_id) = BAD_APICID; - -/* representing HT siblings of each logical CPU */ -DEFINE_PER_CPU(cpumask_t, cpu_sibling_map); -EXPORT_PER_CPU_SYMBOL(cpu_sibling_map); - -/* representing HT and core siblings of each logical CPU */ -DEFINE_PER_CPU(cpumask_t, cpu_core_map); -EXPORT_PER_CPU_SYMBOL(cpu_core_map); +DEFINE_PER_CPU(u16, cpu_llc_id) = BAD_APICID; /* bitmap of online cpus */ cpumask_t cpu_online_map __read_mostly; @@ -85,125 +124,93 @@ cpumask_t cpu_callin_map; cpumask_t cpu_callout_map; cpumask_t cpu_possible_map; EXPORT_SYMBOL(cpu_possible_map); -static cpumask_t smp_commenced_mask; + +/* representing HT siblings of each logical CPU */ +DEFINE_PER_CPU(cpumask_t, cpu_sibling_map); +EXPORT_PER_CPU_SYMBOL(cpu_sibling_map); + +/* representing HT and core siblings of each logical CPU */ +DEFINE_PER_CPU(cpumask_t, cpu_core_map); +EXPORT_PER_CPU_SYMBOL(cpu_core_map); /* Per CPU bogomips and other parameters */ DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info); EXPORT_PER_CPU_SYMBOL(cpu_info); -/* which logical CPU number maps to which CPU (physical APIC ID) */ -u8 x86_cpu_to_apicid_init[NR_CPUS] __initdata = - { [0 ... NR_CPUS-1] = BAD_APICID }; -void *x86_cpu_to_apicid_early_ptr; -DEFINE_PER_CPU(u8, x86_cpu_to_apicid) = BAD_APICID; -EXPORT_PER_CPU_SYMBOL(x86_cpu_to_apicid); - -u8 apicid_2_node[MAX_APICID]; +static atomic_t init_deasserted; -/* - * Trampoline 80x86 program as an array. - */ +static int boot_cpu_logical_apicid; -extern const unsigned char trampoline_data []; -extern const unsigned char trampoline_end []; -static unsigned char *trampoline_base; +/* representing cpus for which sibling maps can be computed */ +static cpumask_t cpu_sibling_setup_map; -static void map_cpu_to_logical_apicid(void); +/* Set if we find a B stepping CPU */ +int __cpuinitdata smp_b_stepping; -/* State of each CPU. */ -DEFINE_PER_CPU(int, cpu_state) = { 0 }; +#if defined(CONFIG_NUMA) && defined(CONFIG_X86_32) -/* - * Currently trivial. Write the real->protected mode - * bootstrap into the page concerned. The caller - * has made sure it's suitably aligned. - */ +/* which logical CPUs are on which nodes */ +cpumask_t node_to_cpumask_map[MAX_NUMNODES] __read_mostly = + { [0 ... MAX_NUMNODES-1] = CPU_MASK_NONE }; +EXPORT_SYMBOL(node_to_cpumask_map); +/* which node each logical CPU is on */ +int cpu_to_node_map[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = 0 }; +EXPORT_SYMBOL(cpu_to_node_map); -static unsigned long __cpuinit setup_trampoline(void) +/* set up a mapping between cpu and node. */ +static void map_cpu_to_node(int cpu, int node) { - memcpy(trampoline_base, trampoline_data, trampoline_end - trampoline_data); - return virt_to_phys(trampoline_base); + printk(KERN_INFO "Mapping cpu %d to node %d\n", cpu, node); + cpu_set(cpu, node_to_cpumask_map[node]); + cpu_to_node_map[cpu] = node; } -/* - * We are called very early to get the low memory for the - * SMP bootup trampoline page. - */ -void __init smp_alloc_memory(void) +/* undo a mapping between cpu and node. */ +static void unmap_cpu_to_node(int cpu) { - 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(); + int node; + + printk(KERN_INFO "Unmapping cpu %d from all nodes\n", cpu); + for (node = 0; node < MAX_NUMNODES; node++) + cpu_clear(cpu, node_to_cpumask_map[node]); + cpu_to_node_map[cpu] = 0; } +#else /* !(CONFIG_NUMA && CONFIG_X86_32) */ +#define map_cpu_to_node(cpu, node) ({}) +#define unmap_cpu_to_node(cpu) ({}) +#endif -/* - * The bootstrap kernel entry code has set these up. Save them for - * a given CPU - */ +#ifdef CONFIG_X86_32 +u8 cpu_2_logical_apicid[NR_CPUS] __read_mostly = + { [0 ... NR_CPUS-1] = BAD_APICID }; -void __cpuinit smp_store_cpu_info(int id) +static void map_cpu_to_logical_apicid(void) { - struct cpuinfo_x86 *c = &cpu_data(id); - - *c = boot_cpu_data; - c->cpu_index = id; - if (id!=0) - identify_secondary_cpu(c); - /* - * Mask B, Pentium, but not Pentium MMX - */ - if (c->x86_vendor == X86_VENDOR_INTEL && - c->x86 == 5 && - c->x86_mask >= 1 && c->x86_mask <= 4 && - c->x86_model <= 3) - /* - * Remember we have B step Pentia with bugs - */ - smp_b_stepping = 1; - - /* - * Certain Athlons might work (for various values of 'work') in SMP - * but they are not certified as MP capable. - */ - if ((c->x86_vendor == X86_VENDOR_AMD) && (c->x86 == 6)) { - - if (num_possible_cpus() == 1) - goto valid_k7; - - /* Athlon 660/661 is valid. */ - if ((c->x86_model==6) && ((c->x86_mask==0) || (c->x86_mask==1))) - goto valid_k7; - - /* Duron 670 is valid */ - if ((c->x86_model==7) && (c->x86_mask==0)) - goto valid_k7; - - /* - * Athlon 662, Duron 671, and Athlon >model 7 have capability bit. - * It's worth noting that the A5 stepping (662) of some Athlon XP's - * have the MP bit set. - * See http://www.heise.de/newsticker/data/jow-18.10.01-000 for more. - */ - if (((c->x86_model==6) && (c->x86_mask>=2)) || - ((c->x86_model==7) && (c->x86_mask>=1)) || - (c->x86_model> 7)) - if (cpu_has_mp) - goto valid_k7; + int cpu = smp_processor_id(); + int apicid = logical_smp_processor_id(); + int node = apicid_to_node(apicid); - /* If we get here, it's not a certified SMP capable AMD system. */ - add_taint(TAINT_UNSAFE_SMP); - } + if (!node_online(node)) + node = first_online_node; -valid_k7: - ; + cpu_2_logical_apicid[cpu] = apicid; + map_cpu_to_node(cpu, node); } -static atomic_t init_deasserted; +static void unmap_cpu_to_logical_apicid(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 +/* + * Report back to the Boot Processor. + * Running on AP. + */ static void __cpuinit smp_callin(void) { int cpuid, phys_id; @@ -220,12 +227,11 @@ static void __cpuinit smp_callin(void) /* * (This works even if the APIC is not enabled.) */ - phys_id = GET_APIC_ID(apic_read(APIC_ID)); + phys_id = GET_APIC_ID(read_apic_id()); cpuid = smp_processor_id(); if (cpu_isset(cpuid, cpu_callin_map)) { - printk("huh, phys CPU#%d, CPU#%d already present??\n", + panic("%s: phys CPU#%d, CPU#%d already present??\n", __func__, phys_id, cpuid); - BUG(); } Dprintk("CPU#%d (phys ID: %d) waiting for CALLOUT\n", cpuid, phys_id); @@ -247,13 +253,12 @@ static void __cpuinit smp_callin(void) */ if (cpu_isset(cpuid, cpu_callout_map)) break; - rep_nop(); + cpu_relax(); } if (!time_before(jiffies, timeout)) { - printk("BUG: CPU%d started up but did not get a callout!\n", - cpuid); - BUG(); + panic("%s: CPU%d started up but did not get a callout!\n", + __func__, cpuid); } /* @@ -266,13 +271,19 @@ static void __cpuinit smp_callin(void) Dprintk("CALLIN, before setup_local_APIC().\n"); smp_callin_clear_local_apic(); setup_local_APIC(); + end_local_APIC_setup(); map_cpu_to_logical_apicid(); /* * Get our bogomips. + * + * Need to enable IRQs because it can take longer and then + * the NMI watchdog might kill us. */ + local_irq_enable(); calibrate_delay(); - Dprintk("Stack at about %p\n",&cpuid); + local_irq_disable(); + Dprintk("Stack at about %p\n", &cpuid); /* * Save our processor parameters @@ -285,91 +296,10 @@ static void __cpuinit smp_callin(void) cpu_set(cpuid, cpu_callin_map); } -static int cpucount; - -/* maps the cpu to the sched domain representing multi-core */ -cpumask_t cpu_coregroup_map(int cpu) -{ - struct cpuinfo_x86 *c = &cpu_data(cpu); - /* - * For perf, we return last level cache shared map. - * And for power savings, we return cpu_core_map - */ - if (sched_mc_power_savings || sched_smt_power_savings) - return per_cpu(cpu_core_map, cpu); - else - return c->llc_shared_map; -} - -/* representing cpus for which sibling maps can be computed */ -static cpumask_t cpu_sibling_setup_map; - -void __cpuinit set_cpu_sibling_map(int cpu) -{ - int i; - struct cpuinfo_x86 *c = &cpu_data(cpu); - - cpu_set(cpu, cpu_sibling_setup_map); - - if (smp_num_siblings > 1) { - for_each_cpu_mask(i, cpu_sibling_setup_map) { - if (c->phys_proc_id == cpu_data(i).phys_proc_id && - c->cpu_core_id == cpu_data(i).cpu_core_id) { - cpu_set(i, per_cpu(cpu_sibling_map, cpu)); - cpu_set(cpu, per_cpu(cpu_sibling_map, i)); - cpu_set(i, per_cpu(cpu_core_map, cpu)); - cpu_set(cpu, per_cpu(cpu_core_map, i)); - cpu_set(i, c->llc_shared_map); - cpu_set(cpu, cpu_data(i).llc_shared_map); - } - } - } else { - cpu_set(cpu, per_cpu(cpu_sibling_map, cpu)); - } - - cpu_set(cpu, c->llc_shared_map); - - if (current_cpu_data.x86_max_cores == 1) { - per_cpu(cpu_core_map, cpu) = per_cpu(cpu_sibling_map, cpu); - c->booted_cores = 1; - return; - } - - for_each_cpu_mask(i, cpu_sibling_setup_map) { - if (per_cpu(cpu_llc_id, cpu) != BAD_APICID && - per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) { - cpu_set(i, c->llc_shared_map); - cpu_set(cpu, cpu_data(i).llc_shared_map); - } - if (c->phys_proc_id == cpu_data(i).phys_proc_id) { - cpu_set(i, per_cpu(cpu_core_map, cpu)); - cpu_set(cpu, per_cpu(cpu_core_map, i)); - /* - * Does this new cpu bringup a new core? - */ - if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1) { - /* - * for each core in package, increment - * the booted_cores for this new cpu - */ - if (first_cpu(per_cpu(cpu_sibling_map, i)) == i) - c->booted_cores++; - /* - * increment the core count for all - * the other cpus in this package - */ - if (i != cpu) - cpu_data(i).booted_cores++; - } else if (i != cpu && !c->booted_cores) - c->booted_cores = cpu_data(i).booted_cores; - } - } -} - /* * Activate a secondary processor. */ -static void __cpuinit start_secondary(void *unused) +void __cpuinit start_secondary(void *unused) { /* * Don't put *anything* before cpu_init(), SMP booting is too @@ -382,24 +312,19 @@ static void __cpuinit start_secondary(void *unused) cpu_init(); preempt_disable(); smp_callin(); - while (!cpu_isset(smp_processor_id(), smp_commenced_mask)) - rep_nop(); + + /* otherwise gcc will move up smp_processor_id before the cpu_init */ + barrier(); /* * Check TSC synchronization with the BP: */ check_tsc_sync_target(); - setup_secondary_clock(); if (nmi_watchdog == NMI_IO_APIC) { disable_8259A_irq(0); enable_NMI_through_LVT0(); enable_8259A_irq(0); } - /* - * low-memory mappings have been cleared, flush them from - * the local TLBs too. - */ - local_flush_tlb(); /* This must be done before setting cpu_online_map */ set_cpu_sibling_map(raw_smp_processor_id()); @@ -414,17 +339,27 @@ static void __cpuinit start_secondary(void *unused) * 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); +#endif cpu_set(smp_processor_id(), cpu_online_map); unlock_ipi_call_lock(); per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; - /* We can take interrupts now: we're officially "up". */ - local_irq_enable(); + setup_secondary_clock(); wmb(); cpu_idle(); } +#ifdef CONFIG_X86_32 /* * Everything has been set up for the secondary * CPUs - they just need to reload everything @@ -442,89 +377,233 @@ void __devinit initialize_secondary(void) "movl %0,%%esp\n\t" "jmp *%1" : - :"m" (current->thread.sp),"m" (current->thread.ip)); + :"m" (current->thread.sp), "m" (current->thread.ip)); } +#endif -/* Static state in head.S used to set up a CPU */ -extern struct { - void * sp; - unsigned short ss; -} stack_start; +static void __cpuinit smp_apply_quirks(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_X86_32 + /* + * Mask B, Pentium, but not Pentium MMX + */ + if (c->x86_vendor == X86_VENDOR_INTEL && + c->x86 == 5 && + c->x86_mask >= 1 && c->x86_mask <= 4 && + c->x86_model <= 3) + /* + * Remember we have B step Pentia with bugs + */ + smp_b_stepping = 1; -#ifdef CONFIG_NUMA + /* + * Certain Athlons might work (for various values of 'work') in SMP + * but they are not certified as MP capable. + */ + if ((c->x86_vendor == X86_VENDOR_AMD) && (c->x86 == 6)) { -/* which logical CPUs are on which nodes */ -cpumask_t node_to_cpumask_map[MAX_NUMNODES] __read_mostly = - { [0 ... MAX_NUMNODES-1] = CPU_MASK_NONE }; -EXPORT_SYMBOL(node_to_cpumask_map); -/* which node each logical CPU is on */ -int cpu_to_node_map[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = 0 }; -EXPORT_SYMBOL(cpu_to_node_map); + if (num_possible_cpus() == 1) + goto valid_k7; -/* set up a mapping between cpu and node. */ -static inline void map_cpu_to_node(int cpu, int node) -{ - printk("Mapping cpu %d to node %d\n", cpu, node); - cpu_set(cpu, node_to_cpumask_map[node]); - cpu_to_node_map[cpu] = node; + /* Athlon 660/661 is valid. */ + if ((c->x86_model == 6) && ((c->x86_mask == 0) || + (c->x86_mask == 1))) + goto valid_k7; + + /* Duron 670 is valid */ + if ((c->x86_model == 7) && (c->x86_mask == 0)) + goto valid_k7; + + /* + * Athlon 662, Duron 671, and Athlon >model 7 have capability + * bit. It's worth noting that the A5 stepping (662) of some + * Athlon XP's have the MP bit set. + * See http://www.heise.de/newsticker/data/jow-18.10.01-000 for + * more. + */ + if (((c->x86_model == 6) && (c->x86_mask >= 2)) || + ((c->x86_model == 7) && (c->x86_mask >= 1)) || + (c->x86_model > 7)) + if (cpu_has_mp) + goto valid_k7; + + /* If we get here, not a certified SMP capable AMD system. */ + add_taint(TAINT_UNSAFE_SMP); + } + +valid_k7: + ; +#endif } -/* undo a mapping between cpu and node. */ -static inline void unmap_cpu_to_node(int cpu) +static void __cpuinit smp_checks(void) { - int node; + if (smp_b_stepping) + printk(KERN_WARNING "WARNING: SMP operation may be unreliable" + "with B stepping processors.\n"); - printk("Unmapping cpu %d from all nodes\n", cpu); - for (node = 0; node < MAX_NUMNODES; node ++) - cpu_clear(cpu, node_to_cpumask_map[node]); - cpu_to_node_map[cpu] = 0; + /* + * Don't taint if we are running SMP kernel on a single non-MP + * approved Athlon + */ + if (tainted & TAINT_UNSAFE_SMP) { + if (num_online_cpus()) + printk(KERN_INFO "WARNING: This combination of AMD" + "processors is not suitable for SMP.\n"); + else + tainted &= ~TAINT_UNSAFE_SMP; + } } -#else /* !CONFIG_NUMA */ -#define map_cpu_to_node(cpu, node) ({}) -#define unmap_cpu_to_node(cpu) ({}) +/* + * The bootstrap kernel entry code has set these up. Save them for + * a given CPU + */ -#endif /* CONFIG_NUMA */ +void __cpuinit smp_store_cpu_info(int id) +{ + struct cpuinfo_x86 *c = &cpu_data(id); -u8 cpu_2_logical_apicid[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = BAD_APICID }; + *c = boot_cpu_data; + c->cpu_index = id; + if (id != 0) + identify_secondary_cpu(c); + smp_apply_quirks(c); +} -static void map_cpu_to_logical_apicid(void) + +void __cpuinit set_cpu_sibling_map(int cpu) { - int cpu = smp_processor_id(); - int apicid = logical_smp_processor_id(); - int node = apicid_to_node(apicid); + int i; + struct cpuinfo_x86 *c = &cpu_data(cpu); - if (!node_online(node)) - node = first_online_node; + cpu_set(cpu, cpu_sibling_setup_map); - cpu_2_logical_apicid[cpu] = apicid; - map_cpu_to_node(cpu, node); + if (smp_num_siblings > 1) { + for_each_cpu_mask(i, cpu_sibling_setup_map) { + if (c->phys_proc_id == cpu_data(i).phys_proc_id && + c->cpu_core_id == cpu_data(i).cpu_core_id) { + cpu_set(i, per_cpu(cpu_sibling_map, cpu)); + cpu_set(cpu, per_cpu(cpu_sibling_map, i)); + cpu_set(i, per_cpu(cpu_core_map, cpu)); + cpu_set(cpu, per_cpu(cpu_core_map, i)); + cpu_set(i, c->llc_shared_map); + cpu_set(cpu, cpu_data(i).llc_shared_map); + } + } + } else { + cpu_set(cpu, per_cpu(cpu_sibling_map, cpu)); + } + + cpu_set(cpu, c->llc_shared_map); + + if (current_cpu_data.x86_max_cores == 1) { + per_cpu(cpu_core_map, cpu) = per_cpu(cpu_sibling_map, cpu); + c->booted_cores = 1; + return; + } + + for_each_cpu_mask(i, cpu_sibling_setup_map) { + if (per_cpu(cpu_llc_id, cpu) != BAD_APICID && + per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) { + cpu_set(i, c->llc_shared_map); + cpu_set(cpu, cpu_data(i).llc_shared_map); + } + if (c->phys_proc_id == cpu_data(i).phys_proc_id) { + cpu_set(i, per_cpu(cpu_core_map, cpu)); + cpu_set(cpu, per_cpu(cpu_core_map, i)); + /* + * Does this new cpu bringup a new core? + */ + if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1) { + /* + * for each core in package, increment + * the booted_cores for this new cpu + */ + if (first_cpu(per_cpu(cpu_sibling_map, i)) == i) + c->booted_cores++; + /* + * increment the core count for all + * the other cpus in this package + */ + if (i != cpu) + cpu_data(i).booted_cores++; + } else if (i != cpu && !c->booted_cores) + c->booted_cores = cpu_data(i).booted_cores; + } + } } -static void unmap_cpu_to_logical_apicid(int cpu) +/* maps the cpu to the sched domain representing multi-core */ +cpumask_t cpu_coregroup_map(int cpu) { - cpu_2_logical_apicid[cpu] = BAD_APICID; - unmap_cpu_to_node(cpu); + struct cpuinfo_x86 *c = &cpu_data(cpu); + /* + * For perf, we return last level cache shared map. + * And for power savings, we return cpu_core_map + */ + if (sched_mc_power_savings || sched_smt_power_savings) + return per_cpu(cpu_core_map, cpu); + else + 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; + unsigned long bogosum = 0; + /* + * Allow the user to impress friends. + */ + Dprintk("Before bogomips.\n"); + for_each_possible_cpu(cpu) + if (cpu_isset(cpu, cpu_callout_map)) + bogosum += cpu_data(cpu).loops_per_jiffy; + printk(KERN_INFO + "Total of %d processors activated (%lu.%02lu BogoMIPS).\n", + num_online_cpus(), + bogosum/(500000/HZ), + (bogosum/(5000/HZ))%100); + + Dprintk("Before bogocount - setting activated=1.\n"); } static inline void __inquire_remote_apic(int apicid) { - int i, regs[] = { APIC_ID >> 4, APIC_LVR >> 4, APIC_SPIV >> 4 }; + unsigned i, regs[] = { APIC_ID >> 4, APIC_LVR >> 4, APIC_SPIV >> 4 }; char *names[] = { "ID", "VERSION", "SPIV" }; int timeout; - unsigned long status; + u32 status; - printk("Inquiring remote APIC #%d...\n", apicid); + printk(KERN_INFO "Inquiring remote APIC #%d...\n", apicid); for (i = 0; i < ARRAY_SIZE(regs); i++) { - printk("... APIC #%d %s: ", apicid, names[i]); + printk(KERN_INFO "... APIC #%d %s: ", apicid, names[i]); /* * Wait for idle. */ status = safe_apic_wait_icr_idle(); if (status) - printk("a previous APIC delivery may have failed\n"); + printk(KERN_CONT + "a previous APIC delivery may have failed\n"); apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(apicid)); apic_write_around(APIC_ICR, APIC_DM_REMRD | regs[i]); @@ -538,16 +617,16 @@ static inline void __inquire_remote_apic(int apicid) switch (status) { case APIC_ICR_RR_VALID: status = apic_read(APIC_RRR); - printk("%lx\n", status); + printk(KERN_CONT "%08x\n", status); break; default: - printk("failed\n"); + printk(KERN_CONT "failed\n"); } } } #ifdef WAKE_SECONDARY_VIA_NMI -/* +/* * Poke the other CPU in the eye via NMI to wake it up. Remember that the normal * INIT, INIT, STARTUP sequence will reset the chip hard for us, and this * won't ... remember to clear down the APIC, etc later. @@ -584,9 +663,9 @@ wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip) Dprintk("NMI sent.\n"); if (send_status) - printk("APIC never delivered???\n"); + printk(KERN_ERR "APIC never delivered???\n"); if (accept_status) - printk("APIC delivery error (%lx).\n", accept_status); + printk(KERN_ERR "APIC delivery error (%lx).\n", accept_status); return (send_status | accept_status); } @@ -599,6 +678,12 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip) unsigned long send_status, accept_status = 0; int maxlvt, num_starts, j; + if (get_uv_system_type() == UV_NON_UNIQUE_APIC) { + send_status = uv_wakeup_secondary(phys_apicid, start_eip); + atomic_set(&init_deasserted, 1); + return send_status; + } + /* * Be paranoid about clearing APIC errors. */ @@ -637,6 +722,7 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip) Dprintk("Waiting for send to finish...\n"); send_status = safe_apic_wait_icr_idle(); + mb(); atomic_set(&init_deasserted, 1); /* @@ -655,7 +741,11 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip) * target processor state. */ startup_ipi_hook(phys_apicid, (unsigned long) start_secondary, - (unsigned long) stack_start.sp); +#ifdef CONFIG_X86_64 + (unsigned long)init_rsp); +#else + (unsigned long)stack_start.sp); +#endif /* * Run STARTUP IPI loop. @@ -665,7 +755,7 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip) maxlvt = lapic_get_maxlvt(); for (j = 1; j <= num_starts; j++) { - Dprintk("Sending STARTUP #%d.\n",j); + Dprintk("Sending STARTUP #%d.\n", j); apic_read_around(APIC_SPIV); apic_write(APIC_ESR, 0); apic_read(APIC_ESR); @@ -711,49 +801,29 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip) Dprintk("After Startup.\n"); if (send_status) - printk("APIC never delivered???\n"); + printk(KERN_ERR "APIC never delivered???\n"); if (accept_status) - printk("APIC delivery error (%lx).\n", accept_status); + printk(KERN_ERR "APIC delivery error (%lx).\n", accept_status); return (send_status | accept_status); } #endif /* WAKE_SECONDARY_VIA_INIT */ -extern cpumask_t cpu_initialized; -static inline int alloc_cpu_id(void) -{ - cpumask_t tmp_map; +struct create_idle { + struct work_struct work; + struct task_struct *idle; + struct completion done; int cpu; - cpus_complement(tmp_map, cpu_present_map); - cpu = first_cpu(tmp_map); - if (cpu >= NR_CPUS) - return -ENODEV; - return cpu; -} +}; -#ifdef CONFIG_HOTPLUG_CPU -static struct task_struct * __cpuinitdata cpu_idle_tasks[NR_CPUS]; -static inline struct task_struct * __cpuinit alloc_idle_task(int cpu) +static void __cpuinit do_fork_idle(struct work_struct *work) { - struct task_struct *idle; - - if ((idle = cpu_idle_tasks[cpu]) != NULL) { - /* initialize thread_struct. we really want to avoid destroy - * idle tread - */ - idle->thread.sp = (unsigned long)task_pt_regs(idle); - init_idle(idle, cpu); - return idle; - } - idle = fork_idle(cpu); + struct create_idle *c_idle = + container_of(work, struct create_idle, work); - if (!IS_ERR(idle)) - cpu_idle_tasks[cpu] = idle; - return idle; + c_idle->idle = fork_idle(c_idle->cpu); + complete(&c_idle->done); } -#else -#define alloc_idle_task(cpu) fork_idle(cpu) -#endif static int __cpuinit do_boot_cpu(int apicid, int cpu) /* @@ -762,45 +832,92 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu) * Returns zero if CPU booted OK, else error code from wakeup_secondary_cpu. */ { - struct task_struct *idle; - unsigned long boot_error; + unsigned long boot_error = 0; int timeout; - unsigned long start_eip; + unsigned long start_ip; unsigned short nmi_high = 0, nmi_low = 0; + struct create_idle c_idle = { + .cpu = 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; + } - /* - * Save current MTRR state in case it was changed since early boot - * (e.g. by the ACPI SMI) to initialize new CPUs with MTRRs in sync: - */ - mtrr_save_state(); + /* 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); + } +#endif + + alternatives_smp_switch(1); + + c_idle.idle = get_idle_for_cpu(cpu); /* * We can't use kernel_thread since we must avoid to * reschedule the child. */ - idle = alloc_idle_task(cpu); - if (IS_ERR(idle)) - panic("failed fork for CPU %d", cpu); + if (c_idle.idle) { + c_idle.idle->thread.sp = (unsigned long) (((struct pt_regs *) + (THREAD_SIZE + task_stack_page(c_idle.idle))) - 1); + init_idle(c_idle.idle, cpu); + goto do_rest; + } + + if (!keventd_up() || current_is_keventd()) + c_idle.work.func(&c_idle.work); + else { + schedule_work(&c_idle.work); + wait_for_completion(&c_idle.done); + } + if (IS_ERR(c_idle.idle)) { + printk("failed fork for CPU %d\n", cpu); + return PTR_ERR(c_idle.idle); + } + + set_idle_for_cpu(cpu, c_idle.idle); +do_rest: +#ifdef CONFIG_X86_32 + per_cpu(current_task, cpu) = c_idle.idle; init_gdt(cpu); - per_cpu(current_task, cpu) = idle; 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 - idle->thread.ip = (unsigned long) start_secondary; - /* start_eip had better be page-aligned! */ - start_eip = setup_trampoline(); - - ++cpucount; - alternatives_smp_switch(1); + /* start_ip had better be page-aligned! */ + start_ip = setup_trampoline(); /* So we see what's up */ - printk("Booting processor %d/%d ip %lx\n", cpu, apicid, start_eip); - /* Stack for startup_32 can be just as for start_secondary onwards */ - stack_start.sp = (void *) idle->thread.sp; + printk(KERN_INFO "Booting processor %d/%d ip %lx\n", + cpu, apicid, start_ip); - irq_ctx_init(cpu); - - per_cpu(x86_cpu_to_apicid, cpu) = apicid; /* * This grunge runs the startup process for * the targeted processor. @@ -808,16 +925,24 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu) atomic_set(&init_deasserted, 0); - Dprintk("Setting warm reset code and vector.\n"); + if (get_uv_system_type() != UV_NON_UNIQUE_APIC) { + + Dprintk("Setting warm reset code and vector.\n"); - store_NMI_vector(&nmi_high, &nmi_low); + store_NMI_vector(&nmi_high, &nmi_low); - smpboot_setup_warm_reset_vector(start_eip); + smpboot_setup_warm_reset_vector(start_ip); + /* + * Be paranoid about clearing APIC errors. + */ + apic_write(APIC_ESR, 0); + apic_read(APIC_ESR); + } /* * Starting actual IPI sequence... */ - boot_error = wakeup_secondary_cpu(apicid, start_eip); + boot_error = wakeup_secondary_cpu(apicid, start_ip); if (!boot_error) { /* @@ -839,175 +964,179 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu) if (cpu_isset(cpu, cpu_callin_map)) { /* number CPUs logically, starting from 1 (BSP is 0) */ Dprintk("OK.\n"); - printk("CPU%d: ", cpu); + printk(KERN_INFO "CPU%d: ", cpu); print_cpu_info(&cpu_data(cpu)); Dprintk("CPU has booted.\n"); } else { - boot_error= 1; + boot_error = 1; if (*((volatile unsigned char *)trampoline_base) == 0xA5) /* trampoline started but...? */ - printk("Stuck ??\n"); + printk(KERN_ERR "Stuck ??\n"); else /* trampoline code not run */ - printk("Not responding.\n"); - inquire_remote_apic(apicid); + printk(KERN_ERR "Not responding.\n"); + if (get_uv_system_type() != UV_NON_UNIQUE_APIC) + inquire_remote_apic(apicid); } } if (boot_error) { /* Try to put things back the way they were before ... */ unmap_cpu_to_logical_apicid(cpu); - cpu_clear(cpu, cpu_callout_map); /* was set here (do_boot_cpu()) */ +#ifdef CONFIG_X86_64 + clear_node_cpumask(cpu); /* was set by numa_add_cpu */ +#endif + cpu_clear(cpu, cpu_callout_map); /* was set by do_boot_cpu() */ cpu_clear(cpu, cpu_initialized); /* was set by cpu_init() */ - cpucount--; - } else { - per_cpu(x86_cpu_to_apicid, cpu) = apicid; - cpu_set(cpu, cpu_present_map); + cpu_clear(cpu, cpu_possible_map); + cpu_clear(cpu, cpu_present_map); + per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID; } /* mark "stuck" area as not stuck */ *((volatile unsigned long *)trampoline_base) = 0; + /* + * Cleanup possible dangling ends... + */ + smpboot_restore_warm_reset_vector(); + return boot_error; } -#ifdef CONFIG_HOTPLUG_CPU -void cpu_exit_clear(void) +int __cpuinit native_cpu_up(unsigned int cpu) { - int cpu = raw_smp_processor_id(); + int apicid = cpu_present_to_apicid(cpu); + unsigned long flags; + int err; - idle_task_exit(); + WARN_ON(irqs_disabled()); - cpucount --; - cpu_uninit(); - irq_ctx_exit(cpu); + Dprintk("++++++++++++++++++++=_---CPU UP %u\n", cpu); - cpu_clear(cpu, cpu_callout_map); - cpu_clear(cpu, cpu_callin_map); + if (apicid == BAD_APICID || apicid == boot_cpu_physical_apicid || + !physid_isset(apicid, phys_cpu_present_map)) { + printk(KERN_ERR "%s: bad cpu %d\n", __func__, cpu); + return -EINVAL; + } - cpu_clear(cpu, smp_commenced_mask); - unmap_cpu_to_logical_apicid(cpu); -} + /* + * Already booted CPU? + */ + if (cpu_isset(cpu, cpu_callin_map)) { + Dprintk("do_boot_cpu %d Already started\n", cpu); + return -ENOSYS; + } -struct warm_boot_cpu_info { - struct completion *complete; - struct work_struct task; - int apicid; - int cpu; -}; + /* + * Save current MTRR state in case it was changed since early boot + * (e.g. by the ACPI SMI) to initialize new CPUs with MTRRs in sync: + */ + mtrr_save_state(); -static void __cpuinit do_warm_boot_cpu(struct work_struct *work) -{ - struct warm_boot_cpu_info *info = - container_of(work, struct warm_boot_cpu_info, task); - do_boot_cpu(info->apicid, info->cpu); - complete(info->complete); -} + per_cpu(cpu_state, cpu) = CPU_UP_PREPARE; -static int __cpuinit __smp_prepare_cpu(int cpu) -{ - DECLARE_COMPLETION_ONSTACK(done); - struct warm_boot_cpu_info info; - int apicid, ret; - - apicid = per_cpu(x86_cpu_to_apicid, cpu); - if (apicid == BAD_APICID) { - ret = -ENODEV; - goto exit; +#ifdef CONFIG_X86_32 + /* init low mem mapping */ + clone_pgd_range(swapper_pg_dir, swapper_pg_dir + KERNEL_PGD_BOUNDARY, + min_t(unsigned long, KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY)); + flush_tlb_all(); +#endif + + err = do_boot_cpu(apicid, cpu); + if (err < 0) { + Dprintk("do_boot_cpu failed %d\n", err); + return err; } - info.complete = &done; - info.apicid = apicid; - info.cpu = cpu; - INIT_WORK(&info.task, do_warm_boot_cpu); + /* + * Check TSC synchronization with the AP (keep irqs disabled + * while doing so): + */ + local_irq_save(flags); + check_tsc_sync_source(cpu); + local_irq_restore(flags); - /* init low mem mapping */ - clone_pgd_range(swapper_pg_dir, swapper_pg_dir + USER_PGD_PTRS, - min_t(unsigned long, KERNEL_PGD_PTRS, USER_PGD_PTRS)); - flush_tlb_all(); - schedule_work(&info.task); - wait_for_completion(&done); + while (!cpu_online(cpu)) { + cpu_relax(); + touch_nmi_watchdog(); + } - zap_low_mappings(); - ret = 0; -exit: - return ret; + return 0; } -#endif /* - * Cycle through the processors sending APIC IPIs to boot each. + * Fall back to non SMP mode after errors. + * + * RED-PEN audit/test this more. I bet there is more state messed up here. */ - -static int boot_cpu_logical_apicid; -/* Where the IO area was mapped on multiquad, always 0 otherwise */ -void *xquad_portio; -#ifdef CONFIG_X86_NUMAQ -EXPORT_SYMBOL(xquad_portio); +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); + else + phys_cpu_present_map = physid_mask_of_physid(0); + map_cpu_to_logical_apicid(); + cpu_set(0, per_cpu(cpu_sibling_map, 0)); + cpu_set(0, per_cpu(cpu_core_map, 0)); +} -static void __init smp_boot_cpus(unsigned int max_cpus) +/* + * Various sanity checks. + */ +static int __init smp_sanity_check(unsigned max_cpus) { - int apicid, cpu, bit, kicked; - unsigned long bogosum = 0; - - /* - * Setup boot CPU information - */ - smp_store_cpu_info(0); /* Final full version of the data */ - printk("CPU%d: ", 0); - print_cpu_info(&cpu_data(0)); - - boot_cpu_physical_apicid = GET_APIC_ID(apic_read(APIC_ID)); - boot_cpu_logical_apicid = logical_smp_processor_id(); - per_cpu(x86_cpu_to_apicid, 0) = boot_cpu_physical_apicid; - - current_thread_info()->cpu = 0; - - set_cpu_sibling_map(0); + preempt_disable(); + if (!physid_isset(hard_smp_processor_id(), phys_cpu_present_map)) { + printk(KERN_WARNING "weird, boot CPU (#%d) not listed" + "by the BIOS.\n", hard_smp_processor_id()); + physid_set(hard_smp_processor_id(), phys_cpu_present_map); + } /* * If we couldn't find an SMP configuration at boot time, * get out of here now! */ if (!smp_found_config && !acpi_lapic) { + preempt_enable(); printk(KERN_NOTICE "SMP motherboard not detected.\n"); - smpboot_clear_io_apic_irqs(); - phys_cpu_present_map = physid_mask_of_physid(0); + disable_smp(); if (APIC_init_uniprocessor()) printk(KERN_NOTICE "Local APIC not detected." " Using dummy APIC emulation.\n"); - map_cpu_to_logical_apicid(); - cpu_set(0, per_cpu(cpu_sibling_map, 0)); - cpu_set(0, per_cpu(cpu_core_map, 0)); - return; + return -1; } /* * Should not be necessary because the MP table should list the boot * CPU too, but we do it for the sake of robustness anyway. - * Makes no sense to do this check in clustered apic mode, so skip it */ if (!check_phys_apicid_present(boot_cpu_physical_apicid)) { - printk("weird, boot CPU (#%d) not listed by the BIOS.\n", - boot_cpu_physical_apicid); + printk(KERN_NOTICE + "weird, boot CPU (#%d) not listed by the BIOS.\n", + boot_cpu_physical_apicid); physid_set(hard_smp_processor_id(), phys_cpu_present_map); } + preempt_enable(); /* * If we couldn't find a local APIC, then get out of here now! */ - if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid]) && !cpu_has_apic) { + if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid]) && + !cpu_has_apic) { printk(KERN_ERR "BIOS bug, local APIC #%d not detected!...\n", boot_cpu_physical_apicid); - printk(KERN_ERR "... forcing use of dummy APIC emulation. (tell your hw vendor)\n"); - smpboot_clear_io_apic_irqs(); - phys_cpu_present_map = physid_mask_of_physid(0); - map_cpu_to_logical_apicid(); - cpu_set(0, per_cpu(cpu_sibling_map, 0)); - cpu_set(0, per_cpu(cpu_core_map, 0)); - return; + printk(KERN_ERR "... forcing use of dummy APIC emulation." + "(tell your hw vendor)\n"); + smpboot_clear_io_apic(); + return -1; } verify_local_APIC(); @@ -1016,138 +1145,145 @@ static void __init smp_boot_cpus(unsigned int max_cpus) * If SMP should be disabled, then really disable it! */ if (!max_cpus) { - smp_found_config = 0; - printk(KERN_INFO "SMP mode deactivated, forcing use of dummy APIC emulation.\n"); - - if (nmi_watchdog == NMI_LOCAL_APIC) { - printk(KERN_INFO "activating minimal APIC for NMI watchdog use.\n"); - connect_bsp_APIC(); - setup_local_APIC(); - } - smpboot_clear_io_apic_irqs(); - phys_cpu_present_map = physid_mask_of_physid(0); - map_cpu_to_logical_apicid(); - cpu_set(0, per_cpu(cpu_sibling_map, 0)); - cpu_set(0, per_cpu(cpu_core_map, 0)); - return; + printk(KERN_INFO "SMP mode deactivated," + "forcing use of dummy APIC emulation.\n"); + smpboot_clear_io_apic(); +#ifdef CONFIG_X86_32 + connect_bsp_APIC(); +#endif + setup_local_APIC(); + end_local_APIC_setup(); + return -1; } - connect_bsp_APIC(); - setup_local_APIC(); - map_cpu_to_logical_apicid(); + return 0; +} +static void __init smp_cpu_index_default(void) +{ + int i; + struct cpuinfo_x86 *c; - setup_portio_remap(); + for_each_possible_cpu(i) { + c = &cpu_data(i); + /* mark all to hotplug */ + c->cpu_index = NR_CPUS; + } +} +/* + * Prepare for SMP bootup. The MP table or ACPI has been read + * earlier. Just do some sanity checking here and enable APIC mode. + */ +void __init native_smp_prepare_cpus(unsigned int max_cpus) +{ + nmi_watchdog_default(); + smp_cpu_index_default(); + current_cpu_data = boot_cpu_data; + cpu_callin_map = cpumask_of_cpu(0); + mb(); /* - * Scan the CPU present map and fire up the other CPUs via do_boot_cpu - * - * In clustered apic mode, phys_cpu_present_map is a constructed thus: - * bits 0-3 are quad0, 4-7 are quad1, etc. A perverse twist on the - * clustered apic ID. + * Setup boot CPU information */ - Dprintk("CPU present map: %lx\n", physids_coerce(phys_cpu_present_map)); - - kicked = 1; - for (bit = 0; kicked < NR_CPUS && bit < MAX_APICS; bit++) { - apicid = cpu_present_to_apicid(bit); - /* - * Don't even attempt to start the boot CPU! - */ - if ((apicid == boot_cpu_apicid) || (apicid == BAD_APICID)) - continue; + smp_store_cpu_info(0); /* Final full version of the data */ + boot_cpu_logical_apicid = logical_smp_processor_id(); + current_thread_info()->cpu = 0; /* needed? */ + set_cpu_sibling_map(0); - if (!check_apicid_present(bit)) - continue; - if (max_cpus <= cpucount+1) - continue; + if (smp_sanity_check(max_cpus) < 0) { + printk(KERN_INFO "SMP disabled\n"); + disable_smp(); + return; + } - if (((cpu = alloc_cpu_id()) <= 0) || do_boot_cpu(apicid, cpu)) - printk("CPU #%d not responding - cannot use it.\n", - apicid); - else - ++kicked; + preempt_disable(); + if (GET_APIC_ID(read_apic_id()) != boot_cpu_physical_apicid) { + panic("Boot APIC ID in local APIC unexpected (%d vs %d)", + GET_APIC_ID(read_apic_id()), boot_cpu_physical_apicid); + /* Or can we switch back to PIC here? */ } + preempt_enable(); +#ifdef CONFIG_X86_32 + connect_bsp_APIC(); +#endif /* - * Cleanup possible dangling ends... + * Switch from PIC to APIC mode. */ - smpboot_restore_warm_reset_vector(); + setup_local_APIC(); +#ifdef CONFIG_X86_64 /* - * Allow the user to impress friends. + * Enable IO APIC before setting up error vector */ - Dprintk("Before bogomips.\n"); - for_each_possible_cpu(cpu) - if (cpu_isset(cpu, cpu_callout_map)) - bogosum += cpu_data(cpu).loops_per_jiffy; - printk(KERN_INFO - "Total of %d processors activated (%lu.%02lu BogoMIPS).\n", - cpucount+1, - bogosum/(500000/HZ), - (bogosum/(5000/HZ))%100); - - Dprintk("Before bogocount - setting activated=1.\n"); - - if (smp_b_stepping) - printk(KERN_WARNING "WARNING: SMP operation may be unreliable with B stepping processors.\n"); + if (!skip_ioapic_setup && nr_ioapics) + enable_IO_APIC(); +#endif + end_local_APIC_setup(); - /* - * Don't taint if we are running SMP kernel on a single non-MP - * approved Athlon - */ - if (tainted & TAINT_UNSAFE_SMP) { - if (cpucount) - printk (KERN_INFO "WARNING: This combination of AMD processors is not suitable for SMP.\n"); - else - tainted &= ~TAINT_UNSAFE_SMP; - } + map_cpu_to_logical_apicid(); - Dprintk("Boot done.\n"); + setup_portio_remap(); + smpboot_setup_io_apic(); /* - * construct cpu_sibling_map, so that we can tell sibling CPUs - * efficiently. + * Set up local APIC timer on boot CPU. */ - for_each_possible_cpu(cpu) { - cpus_clear(per_cpu(cpu_sibling_map, cpu)); - cpus_clear(per_cpu(cpu_core_map, cpu)); - } - - cpu_set(0, per_cpu(cpu_sibling_map, 0)); - cpu_set(0, per_cpu(cpu_core_map, 0)); - - smpboot_setup_io_apic(); + printk(KERN_INFO "CPU%d: ", 0); + print_cpu_info(&cpu_data(0)); setup_boot_clock(); } +/* + * Early setup to make printk work. + */ +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 + /* already set me in cpu_online_map in boot_cpu_init() */ + cpu_set(me, cpu_callout_map); + per_cpu(cpu_state, me) = CPU_ONLINE; +} -/* These are wrappers to interface to the new boot process. Someone - who understands all this stuff should rewrite it properly. --RR 15/Jul/02 */ -void __init native_smp_prepare_cpus(unsigned int max_cpus) +void __init native_smp_cpus_done(unsigned int max_cpus) { - smp_commenced_mask = cpumask_of_cpu(0); - cpu_callin_map = cpumask_of_cpu(0); - mb(); - smp_boot_cpus(max_cpus); + Dprintk("Boot done.\n"); + + impress_friends(); + smp_checks(); +#ifdef CONFIG_X86_IO_APIC + setup_ioapic_dest(); +#endif + check_nmi_watchdog(); +#ifdef CONFIG_X86_32 + zap_low_mappings(); +#endif } -void __init native_smp_prepare_boot_cpu(void) +#ifdef CONFIG_HOTPLUG_CPU + +# ifdef CONFIG_X86_32 +void cpu_exit_clear(void) { - unsigned int cpu = smp_processor_id(); + int cpu = raw_smp_processor_id(); - init_gdt(cpu); - switch_to_new_gdt(); + idle_task_exit(); + + cpu_uninit(); + irq_ctx_exit(cpu); + + cpu_clear(cpu, cpu_callout_map); + cpu_clear(cpu, cpu_callin_map); - cpu_set(cpu, cpu_online_map); - cpu_set(cpu, cpu_callout_map); - cpu_set(cpu, cpu_present_map); - cpu_set(cpu, cpu_possible_map); - __get_cpu_var(cpu_state) = CPU_ONLINE; + unmap_cpu_to_logical_apicid(cpu); } +# endif /* CONFIG_X86_32 */ -#ifdef CONFIG_HOTPLUG_CPU -void remove_siblinginfo(int cpu) +static void remove_siblinginfo(int cpu) { int sibling; struct cpuinfo_x86 *c = &cpu_data(cpu); @@ -1160,7 +1296,7 @@ void remove_siblinginfo(int cpu) if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1) cpu_data(sibling).booted_cores--; } - + for_each_cpu_mask(sibling, per_cpu(cpu_sibling_map, cpu)) cpu_clear(cpu, per_cpu(cpu_sibling_map, sibling)); cpus_clear(per_cpu(cpu_sibling_map, cpu)); @@ -1170,35 +1306,99 @@ void remove_siblinginfo(int cpu) cpu_clear(cpu, cpu_sibling_setup_map); } +int additional_cpus __initdata = -1; + +static __init int setup_additional_cpus(char *s) +{ + return s && get_option(&s, &additional_cpus) ? 0 : -EINVAL; +} +early_param("additional_cpus", setup_additional_cpus); + +/* + * cpu_possible_map should be static, it cannot change as cpu's + * are onlined, or offlined. The reason is per-cpu data-structures + * are allocated by some modules at init time, and dont expect to + * do this dynamically on cpu arrival/departure. + * cpu_present_map on the other hand can change dynamically. + * In case when cpu_hotplug is not compiled, then we resort to current + * behaviour, which is cpu_possible == cpu_present. + * - Ashok Raj + * + * Three ways to find out the number of additional hotplug CPUs: + * - If the BIOS specified disabled CPUs in ACPI/mptables use that. + * - The user can overwrite it with additional_cpus=NUM + * - Otherwise don't reserve additional CPUs. + * We do this because additional CPUs waste a lot of memory. + * -AK + */ +__init void prefill_possible_map(void) +{ + int i; + int possible; + + if (additional_cpus == -1) { + if (disabled_cpus > 0) + additional_cpus = disabled_cpus; + else + additional_cpus = 0; + } + possible = num_processors + additional_cpus; + if (possible > NR_CPUS) + possible = NR_CPUS; + + printk(KERN_INFO "SMP: Allowing %d CPUs, %d hotplug CPUs\n", + possible, max_t(int, possible - num_processors, 0)); + + for (i = 0; i < possible; i++) + cpu_set(i, cpu_possible_map); +} + +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 +} + int __cpu_disable(void) { - cpumask_t map = cpu_online_map; int cpu = smp_processor_id(); /* * Perhaps use cpufreq to drop frequency, but that could go * into generic code. - * + * * We won't take down the boot processor on i386 due to some * interrupts only being able to be serviced by the BSP. * Especially so if we're not using an IOAPIC -zwane */ if (cpu == 0) return -EBUSY; + if (nmi_watchdog == NMI_LOCAL_APIC) stop_apic_nmi_watchdog(NULL); clear_local_APIC(); - /* Allow any queued timer interrupts to get serviced */ + + /* + * HACK: + * Allow any queued timer interrupts to get serviced + * This is only a temporary solution until we cleanup + * fixup_irqs as we do for IA64. + */ local_irq_enable(); mdelay(1); - local_irq_disable(); + local_irq_disable(); remove_siblinginfo(cpu); - cpu_clear(cpu, map); - fixup_irqs(map); /* It's now safe to remove this processor from the online map */ - cpu_clear(cpu, cpu_online_map); + remove_cpu_from_maps(cpu); + fixup_irqs(cpu_online_map); return 0; } @@ -1210,14 +1410,14 @@ void __cpu_die(unsigned int cpu) for (i = 0; i < 10; i++) { /* They ack this in play_dead by setting CPU_DEAD */ if (per_cpu(cpu_state, cpu) == CPU_DEAD) { - printk ("CPU %d is now offline\n", cpu); + printk(KERN_INFO "CPU %d is now offline\n", cpu); if (1 == num_online_cpus()) alternatives_smp_switch(0); return; } msleep(100); } - printk(KERN_ERR "CPU %u didn't die...\n", cpu); + printk(KERN_ERR "CPU %u didn't die...\n", cpu); } #else /* ... !CONFIG_HOTPLUG_CPU */ int __cpu_disable(void) @@ -1230,82 +1430,8 @@ void __cpu_die(unsigned int cpu) /* We said "no" in __cpu_disable */ BUG(); } -#endif /* CONFIG_HOTPLUG_CPU */ - -int __cpuinit native_cpu_up(unsigned int cpu) -{ - unsigned long flags; -#ifdef CONFIG_HOTPLUG_CPU - int ret = 0; - - /* - * We do warm boot only on cpus that had booted earlier - * Otherwise cold boot is all handled from smp_boot_cpus(). - * cpu_callin_map is set during AP kickstart process. Its reset - * when a cpu is taken offline from cpu_exit_clear(). - */ - if (!cpu_isset(cpu, cpu_callin_map)) - ret = __smp_prepare_cpu(cpu); - - if (ret) - return -EIO; #endif - /* In case one didn't come up */ - if (!cpu_isset(cpu, cpu_callin_map)) { - printk(KERN_DEBUG "skipping cpu%d, didn't come online\n", cpu); - return -EIO; - } - - per_cpu(cpu_state, cpu) = CPU_UP_PREPARE; - /* Unleash the CPU! */ - cpu_set(cpu, smp_commenced_mask); - - /* - * Check TSC synchronization with the AP (keep irqs disabled - * while doing so): - */ - local_irq_save(flags); - check_tsc_sync_source(cpu); - local_irq_restore(flags); - - while (!cpu_isset(cpu, cpu_online_map)) { - cpu_relax(); - touch_nmi_watchdog(); - } - - return 0; -} - -void __init native_smp_cpus_done(unsigned int max_cpus) -{ -#ifdef CONFIG_X86_IO_APIC - setup_ioapic_dest(); -#endif - zap_low_mappings(); -} - -void __init smp_intr_init(void) -{ - /* - * IRQ0 must be given a fixed assignment and initialized, - * because it's used before the IO-APIC is set up. - */ - set_intr_gate(FIRST_DEVICE_VECTOR, interrupt[0]); - - /* - * The reschedule interrupt is a CPU-to-CPU reschedule-helper - * IPI, driven by wakeup. - */ - set_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt); - - /* IPI for invalidation */ - set_intr_gate(INVALIDATE_TLB_VECTOR, invalidate_interrupt); - - /* IPI for generic function call */ - set_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt); -} - /* * If the BIOS enumerates physical processors before logical, * maxcpus=N at enumeration-time can be used to disable HT. diff --git a/arch/x86/kernel/smpboot_64.c b/arch/x86/kernel/smpboot_64.c deleted file mode 100644 index 0880f2c388a9..000000000000 --- a/arch/x86/kernel/smpboot_64.c +++ /dev/null @@ -1,1108 +0,0 @@ -/* - * x86 SMP booting functions - * - * (c) 1995 Alan Cox, Building #3 <alan@redhat.com> - * (c) 1998, 1999, 2000 Ingo Molnar <mingo@redhat.com> - * Copyright 2001 Andi Kleen, SuSE Labs. - * - * Much of the core SMP work is based on previous work by Thomas Radke, to - * whom a great many thanks are extended. - * - * Thanks to Intel for making available several different Pentium, - * Pentium Pro and Pentium-II/Xeon MP machines. - * Original development of Linux SMP code supported by Caldera. - * - * This code is released under the GNU General Public License version 2 - * - * Fixes - * Felix Koop : NR_CPUS used properly - * Jose Renau : Handle single CPU case. - * Alan Cox : By repeated request 8) - Total BogoMIP report. - * Greg Wright : Fix for kernel stacks panic. - * Erich Boleyn : MP v1.4 and additional changes. - * Matthias Sattler : Changes for 2.1 kernel map. - * Michel Lespinasse : Changes for 2.1 kernel map. - * Michael Chastain : Change trampoline.S to gnu as. - * Alan Cox : Dumb bug: 'B' step PPro's are fine - * Ingo Molnar : Added APIC timers, based on code - * from Jose Renau - * Ingo Molnar : various cleanups and rewrites - * Tigran Aivazian : fixed "0.00 in /proc/uptime on SMP" bug. - * Maciej W. Rozycki : Bits for genuine 82489DX APICs - * Andi Kleen : Changed for SMP boot into long mode. - * Rusty Russell : Hacked into shape for new "hotplug" boot process. - * Andi Kleen : Converted to new state machine. - * Various cleanups. - * Probably mostly hotplug CPU ready now. - * Ashok Raj : CPU hotplug support - */ - - -#include <linux/init.h> - -#include <linux/mm.h> -#include <linux/kernel_stat.h> -#include <linux/bootmem.h> -#include <linux/thread_info.h> -#include <linux/module.h> -#include <linux/delay.h> -#include <linux/mc146818rtc.h> -#include <linux/smp.h> -#include <linux/kdebug.h> - -#include <asm/mtrr.h> -#include <asm/pgalloc.h> -#include <asm/desc.h> -#include <asm/tlbflush.h> -#include <asm/proto.h> -#include <asm/nmi.h> -#include <asm/irq.h> -#include <asm/hw_irq.h> -#include <asm/numa.h> - -/* Number of siblings per CPU package */ -int smp_num_siblings = 1; -EXPORT_SYMBOL(smp_num_siblings); - -/* Last level cache ID of each logical CPU */ -DEFINE_PER_CPU(u16, cpu_llc_id) = BAD_APICID; - -/* Bitmask of currently online CPUs */ -cpumask_t cpu_online_map __read_mostly; - -EXPORT_SYMBOL(cpu_online_map); - -/* - * Private maps to synchronize booting between AP and BP. - * Probably not needed anymore, but it makes for easier debugging. -AK - */ -cpumask_t cpu_callin_map; -cpumask_t cpu_callout_map; -cpumask_t cpu_possible_map; -EXPORT_SYMBOL(cpu_possible_map); - -/* Per CPU bogomips and other parameters */ -DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info); -EXPORT_PER_CPU_SYMBOL(cpu_info); - -/* Set when the idlers are all forked */ -int smp_threads_ready; - -/* representing HT siblings of each logical CPU */ -DEFINE_PER_CPU(cpumask_t, cpu_sibling_map); -EXPORT_PER_CPU_SYMBOL(cpu_sibling_map); - -/* representing HT and core siblings of each logical CPU */ -DEFINE_PER_CPU(cpumask_t, cpu_core_map); -EXPORT_PER_CPU_SYMBOL(cpu_core_map); - -/* - * Trampoline 80x86 program as an array. - */ - -extern const unsigned char trampoline_data[]; -extern const unsigned char trampoline_end[]; - -/* State of each CPU */ -DEFINE_PER_CPU(int, cpu_state) = { 0 }; - -/* - * Store all idle threads, this can be reused instead of creating - * a new thread. Also avoids complicated thread destroy functionality - * for idle threads. - */ -#ifdef CONFIG_HOTPLUG_CPU -/* - * Needed only for CONFIG_HOTPLUG_CPU because __cpuinitdata is - * removed after init for !CONFIG_HOTPLUG_CPU. - */ -static DEFINE_PER_CPU(struct task_struct *, idle_thread_array); -#define get_idle_for_cpu(x) (per_cpu(idle_thread_array, x)) -#define set_idle_for_cpu(x,p) (per_cpu(idle_thread_array, x) = (p)) -#else -struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ; -#define get_idle_for_cpu(x) (idle_thread_array[(x)]) -#define set_idle_for_cpu(x,p) (idle_thread_array[(x)] = (p)) -#endif - - -/* - * Currently trivial. Write the real->protected mode - * bootstrap into the page concerned. The caller - * has made sure it's suitably aligned. - */ - -static unsigned long __cpuinit setup_trampoline(void) -{ - void *tramp = __va(SMP_TRAMPOLINE_BASE); - memcpy(tramp, trampoline_data, trampoline_end - trampoline_data); - return virt_to_phys(tramp); -} - -/* - * The bootstrap kernel entry code has set these up. Save them for - * a given CPU - */ - -static void __cpuinit smp_store_cpu_info(int id) -{ - struct cpuinfo_x86 *c = &cpu_data(id); - - *c = boot_cpu_data; - c->cpu_index = id; - identify_cpu(c); - print_cpu_info(c); -} - -static atomic_t init_deasserted __cpuinitdata; - -/* - * Report back to the Boot Processor. - * Running on AP. - */ -void __cpuinit smp_callin(void) -{ - int cpuid, phys_id; - unsigned long timeout; - - /* - * If waken up by an INIT in an 82489DX configuration - * we may get here before an INIT-deassert IPI reaches - * our local APIC. We have to wait for the IPI or we'll - * lock up on an APIC access. - */ - while (!atomic_read(&init_deasserted)) - cpu_relax(); - - /* - * (This works even if the APIC is not enabled.) - */ - phys_id = GET_APIC_ID(apic_read(APIC_ID)); - cpuid = smp_processor_id(); - if (cpu_isset(cpuid, cpu_callin_map)) { - panic("smp_callin: phys CPU#%d, CPU#%d already present??\n", - phys_id, cpuid); - } - Dprintk("CPU#%d (phys ID: %d) waiting for CALLOUT\n", cpuid, phys_id); - - /* - * STARTUP IPIs are fragile beasts as they might sometimes - * trigger some glue motherboard logic. Complete APIC bus - * silence for 1 second, this overestimates the time the - * boot CPU is spending to send the up to 2 STARTUP IPIs - * by a factor of two. This should be enough. - */ - - /* - * Waiting 2s total for startup (udelay is not yet working) - */ - timeout = jiffies + 2*HZ; - while (time_before(jiffies, timeout)) { - /* - * Has the boot CPU finished it's STARTUP sequence? - */ - if (cpu_isset(cpuid, cpu_callout_map)) - break; - cpu_relax(); - } - - if (!time_before(jiffies, timeout)) { - panic("smp_callin: CPU%d started up but did not get a callout!\n", - cpuid); - } - - /* - * the boot CPU has finished the init stage and is spinning - * on callin_map until we finish. We are free to set up this - * CPU, first the APIC. (this is probably redundant on most - * boards) - */ - - Dprintk("CALLIN, before setup_local_APIC().\n"); - setup_local_APIC(); - end_local_APIC_setup(); - - /* - * Get our bogomips. - * - * Need to enable IRQs because it can take longer and then - * the NMI watchdog might kill us. - */ - local_irq_enable(); - calibrate_delay(); - local_irq_disable(); - Dprintk("Stack at about %p\n",&cpuid); - - /* - * Save our processor parameters - */ - smp_store_cpu_info(cpuid); - - /* - * Allow the master to continue. - */ - cpu_set(cpuid, cpu_callin_map); -} - -/* maps the cpu to the sched domain representing multi-core */ -cpumask_t cpu_coregroup_map(int cpu) -{ - struct cpuinfo_x86 *c = &cpu_data(cpu); - /* - * For perf, we return last level cache shared map. - * And for power savings, we return cpu_core_map - */ - if (sched_mc_power_savings || sched_smt_power_savings) - return per_cpu(cpu_core_map, cpu); - else - return c->llc_shared_map; -} - -/* representing cpus for which sibling maps can be computed */ -static cpumask_t cpu_sibling_setup_map; - -static inline void set_cpu_sibling_map(int cpu) -{ - int i; - struct cpuinfo_x86 *c = &cpu_data(cpu); - - cpu_set(cpu, cpu_sibling_setup_map); - - if (smp_num_siblings > 1) { - for_each_cpu_mask(i, cpu_sibling_setup_map) { - if (c->phys_proc_id == cpu_data(i).phys_proc_id && - c->cpu_core_id == cpu_data(i).cpu_core_id) { - cpu_set(i, per_cpu(cpu_sibling_map, cpu)); - cpu_set(cpu, per_cpu(cpu_sibling_map, i)); - cpu_set(i, per_cpu(cpu_core_map, cpu)); - cpu_set(cpu, per_cpu(cpu_core_map, i)); - cpu_set(i, c->llc_shared_map); - cpu_set(cpu, cpu_data(i).llc_shared_map); - } - } - } else { - cpu_set(cpu, per_cpu(cpu_sibling_map, cpu)); - } - - cpu_set(cpu, c->llc_shared_map); - - if (current_cpu_data.x86_max_cores == 1) { - per_cpu(cpu_core_map, cpu) = per_cpu(cpu_sibling_map, cpu); - c->booted_cores = 1; - return; - } - - for_each_cpu_mask(i, cpu_sibling_setup_map) { - if (per_cpu(cpu_llc_id, cpu) != BAD_APICID && - per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) { - cpu_set(i, c->llc_shared_map); - cpu_set(cpu, cpu_data(i).llc_shared_map); - } - if (c->phys_proc_id == cpu_data(i).phys_proc_id) { - cpu_set(i, per_cpu(cpu_core_map, cpu)); - cpu_set(cpu, per_cpu(cpu_core_map, i)); - /* - * Does this new cpu bringup a new core? - */ - if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1) { - /* - * for each core in package, increment - * the booted_cores for this new cpu - */ - if (first_cpu(per_cpu(cpu_sibling_map, i)) == i) - c->booted_cores++; - /* - * increment the core count for all - * the other cpus in this package - */ - if (i != cpu) - cpu_data(i).booted_cores++; - } else if (i != cpu && !c->booted_cores) - c->booted_cores = cpu_data(i).booted_cores; - } - } -} - -/* - * Setup code on secondary processor (after comming out of the trampoline) - */ -void __cpuinit start_secondary(void) -{ - /* - * Dont put anything before smp_callin(), SMP - * booting is too fragile that we want to limit the - * things done here to the most necessary things. - */ - cpu_init(); - preempt_disable(); - smp_callin(); - - /* otherwise gcc will move up the smp_processor_id before the cpu_init */ - barrier(); - - /* - * Check TSC sync first: - */ - check_tsc_sync_target(); - - if (nmi_watchdog == NMI_IO_APIC) { - disable_8259A_irq(0); - enable_NMI_through_LVT0(); - enable_8259A_irq(0); - } - - /* - * The sibling maps must be set before turing the online map on for - * this cpu - */ - set_cpu_sibling_map(smp_processor_id()); - - /* - * We need to hold call_lock, so there is no inconsistency - * between the time smp_call_function() determines number of - * IPI recipients, and the time when the determination is made - * for which cpus receive the IPI in genapic_flat.c. Holding this - * lock helps us to not include this cpu in a currently in progress - * smp_call_function(). - */ - lock_ipi_call_lock(); - spin_lock(&vector_lock); - - /* Setup the per cpu irq handling data structures */ - __setup_vector_irq(smp_processor_id()); - /* - * Allow the master to continue. - */ - cpu_set(smp_processor_id(), cpu_online_map); - per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; - spin_unlock(&vector_lock); - - unlock_ipi_call_lock(); - - setup_secondary_clock(); - - cpu_idle(); -} - -extern volatile unsigned long init_rsp; -extern void (*initial_code)(void); - -#ifdef APIC_DEBUG -static void inquire_remote_apic(int apicid) -{ - unsigned i, regs[] = { APIC_ID >> 4, APIC_LVR >> 4, APIC_SPIV >> 4 }; - char *names[] = { "ID", "VERSION", "SPIV" }; - int timeout; - u32 status; - - printk(KERN_INFO "Inquiring remote APIC #%d...\n", apicid); - - for (i = 0; i < ARRAY_SIZE(regs); i++) { - printk(KERN_INFO "... APIC #%d %s: ", apicid, names[i]); - - /* - * Wait for idle. - */ - status = safe_apic_wait_icr_idle(); - if (status) - printk(KERN_CONT - "a previous APIC delivery may have failed\n"); - - apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(apicid)); - apic_write(APIC_ICR, APIC_DM_REMRD | regs[i]); - - timeout = 0; - do { - udelay(100); - status = apic_read(APIC_ICR) & APIC_ICR_RR_MASK; - } while (status == APIC_ICR_RR_INPROG && timeout++ < 1000); - - switch (status) { - case APIC_ICR_RR_VALID: - status = apic_read(APIC_RRR); - printk(KERN_CONT "%08x\n", status); - break; - default: - printk(KERN_CONT "failed\n"); - } - } -} -#endif - -/* - * Kick the secondary to wake up. - */ -static int __cpuinit wakeup_secondary_via_INIT(int phys_apicid, unsigned int start_rip) -{ - unsigned long send_status, accept_status = 0; - int maxlvt, num_starts, j; - - Dprintk("Asserting INIT.\n"); - - /* - * Turn INIT on target chip - */ - apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid)); - - /* - * Send IPI - */ - apic_write(APIC_ICR, APIC_INT_LEVELTRIG | APIC_INT_ASSERT - | APIC_DM_INIT); - - Dprintk("Waiting for send to finish...\n"); - send_status = safe_apic_wait_icr_idle(); - - mdelay(10); - - Dprintk("Deasserting INIT.\n"); - - /* Target chip */ - apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid)); - - /* Send IPI */ - apic_write(APIC_ICR, APIC_INT_LEVELTRIG | APIC_DM_INIT); - - Dprintk("Waiting for send to finish...\n"); - send_status = safe_apic_wait_icr_idle(); - - mb(); - atomic_set(&init_deasserted, 1); - - num_starts = 2; - - /* - * Run STARTUP IPI loop. - */ - Dprintk("#startup loops: %d.\n", num_starts); - - maxlvt = lapic_get_maxlvt(); - - for (j = 1; j <= num_starts; j++) { - Dprintk("Sending STARTUP #%d.\n",j); - apic_write(APIC_ESR, 0); - apic_read(APIC_ESR); - Dprintk("After apic_write.\n"); - - /* - * STARTUP IPI - */ - - /* Target chip */ - apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid)); - - /* Boot on the stack */ - /* Kick the second */ - apic_write(APIC_ICR, APIC_DM_STARTUP | (start_rip >> 12)); - - /* - * Give the other CPU some time to accept the IPI. - */ - udelay(300); - - Dprintk("Startup point 1.\n"); - - Dprintk("Waiting for send to finish...\n"); - send_status = safe_apic_wait_icr_idle(); - - /* - * Give the other CPU some time to accept the IPI. - */ - udelay(200); - /* - * Due to the Pentium erratum 3AP. - */ - if (maxlvt > 3) { - apic_write(APIC_ESR, 0); - } - accept_status = (apic_read(APIC_ESR) & 0xEF); - if (send_status || accept_status) - break; - } - Dprintk("After Startup.\n"); - - if (send_status) - printk(KERN_ERR "APIC never delivered???\n"); - if (accept_status) - printk(KERN_ERR "APIC delivery error (%lx).\n", accept_status); - - return (send_status | accept_status); -} - -struct create_idle { - struct work_struct work; - struct task_struct *idle; - struct completion done; - int cpu; -}; - -static void __cpuinit do_fork_idle(struct work_struct *work) -{ - struct create_idle *c_idle = - container_of(work, struct create_idle, work); - - c_idle->idle = fork_idle(c_idle->cpu); - complete(&c_idle->done); -} - -/* - * Boot one CPU. - */ -static int __cpuinit do_boot_cpu(int cpu, int apicid) -{ - unsigned long boot_error; - int timeout; - unsigned long start_rip; - struct create_idle c_idle = { - .cpu = cpu, - .done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done), - }; - INIT_WORK(&c_idle.work, do_fork_idle); - - /* 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; - } - - /* 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); - } - - alternatives_smp_switch(1); - - c_idle.idle = get_idle_for_cpu(cpu); - - if (c_idle.idle) { - c_idle.idle->thread.sp = (unsigned long) (((struct pt_regs *) - (THREAD_SIZE + task_stack_page(c_idle.idle))) - 1); - init_idle(c_idle.idle, cpu); - goto do_rest; - } - - /* - * During cold boot process, keventd thread is not spun up yet. - * When we do cpu hot-add, we create idle threads on the fly, we should - * not acquire any attributes from the calling context. Hence the clean - * way to create kernel_threads() is to do that from keventd(). - * We do the current_is_keventd() due to the fact that ACPI notifier - * was also queuing to keventd() and when the caller is already running - * in context of keventd(), we would end up with locking up the keventd - * thread. - */ - if (!keventd_up() || current_is_keventd()) - c_idle.work.func(&c_idle.work); - else { - schedule_work(&c_idle.work); - wait_for_completion(&c_idle.done); - } - - if (IS_ERR(c_idle.idle)) { - printk("failed fork for CPU %d\n", cpu); - return PTR_ERR(c_idle.idle); - } - - set_idle_for_cpu(cpu, c_idle.idle); - -do_rest: - - cpu_pda(cpu)->pcurrent = c_idle.idle; - - start_rip = setup_trampoline(); - - init_rsp = c_idle.idle->thread.sp; - load_sp0(&per_cpu(init_tss, cpu), &c_idle.idle->thread); - initial_code = start_secondary; - clear_tsk_thread_flag(c_idle.idle, TIF_FORK); - - printk(KERN_INFO "Booting processor %d/%d APIC 0x%x\n", cpu, - cpus_weight(cpu_present_map), - apicid); - - /* - * This grunge runs the startup process for - * the targeted processor. - */ - - atomic_set(&init_deasserted, 0); - - Dprintk("Setting warm reset code and vector.\n"); - - CMOS_WRITE(0xa, 0xf); - local_flush_tlb(); - Dprintk("1.\n"); - *((volatile unsigned short *) phys_to_virt(0x469)) = start_rip >> 4; - Dprintk("2.\n"); - *((volatile unsigned short *) phys_to_virt(0x467)) = start_rip & 0xf; - Dprintk("3.\n"); - - /* - * Be paranoid about clearing APIC errors. - */ - apic_write(APIC_ESR, 0); - apic_read(APIC_ESR); - - /* - * Status is now clean - */ - boot_error = 0; - - /* - * Starting actual IPI sequence... - */ - boot_error = wakeup_secondary_via_INIT(apicid, start_rip); - - if (!boot_error) { - /* - * allow APs to start initializing. - */ - Dprintk("Before Callout %d.\n", cpu); - cpu_set(cpu, cpu_callout_map); - Dprintk("After Callout %d.\n", cpu); - - /* - * Wait 5s total for a response - */ - for (timeout = 0; timeout < 50000; timeout++) { - if (cpu_isset(cpu, cpu_callin_map)) - break; /* It has booted */ - udelay(100); - } - - if (cpu_isset(cpu, cpu_callin_map)) { - /* number CPUs logically, starting from 1 (BSP is 0) */ - Dprintk("CPU has booted.\n"); - } else { - boot_error = 1; - if (*((volatile unsigned char *)phys_to_virt(SMP_TRAMPOLINE_BASE)) - == 0xA5) - /* trampoline started but...? */ - printk("Stuck ??\n"); - else - /* trampoline code not run */ - printk("Not responding.\n"); -#ifdef APIC_DEBUG - inquire_remote_apic(apicid); -#endif - } - } - if (boot_error) { - cpu_clear(cpu, cpu_callout_map); /* was set here (do_boot_cpu()) */ - clear_bit(cpu, (unsigned long *)&cpu_initialized); /* was set by cpu_init() */ - clear_node_cpumask(cpu); /* was set by numa_add_cpu */ - cpu_clear(cpu, cpu_present_map); - cpu_clear(cpu, cpu_possible_map); - per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID; - return -EIO; - } - - return 0; -} - -cycles_t cacheflush_time; -unsigned long cache_decay_ticks; - -/* - * Cleanup possible dangling ends... - */ -static __cpuinit void smp_cleanup_boot(void) -{ - /* - * Paranoid: Set warm reset code and vector here back - * to default values. - */ - CMOS_WRITE(0, 0xf); - - /* - * Reset trampoline flag - */ - *((volatile int *) phys_to_virt(0x467)) = 0; -} - -/* - * Fall back to non SMP mode after errors. - * - * RED-PEN audit/test this more. I bet there is more state messed up here. - */ -static __init void disable_smp(void) -{ - cpu_present_map = cpumask_of_cpu(0); - cpu_possible_map = cpumask_of_cpu(0); - if (smp_found_config) - phys_cpu_present_map = physid_mask_of_physid(boot_cpu_id); - else - phys_cpu_present_map = physid_mask_of_physid(0); - cpu_set(0, per_cpu(cpu_sibling_map, 0)); - cpu_set(0, per_cpu(cpu_core_map, 0)); -} - -#ifdef CONFIG_HOTPLUG_CPU - -int additional_cpus __initdata = -1; - -/* - * cpu_possible_map should be static, it cannot change as cpu's - * are onlined, or offlined. The reason is per-cpu data-structures - * are allocated by some modules at init time, and dont expect to - * do this dynamically on cpu arrival/departure. - * cpu_present_map on the other hand can change dynamically. - * In case when cpu_hotplug is not compiled, then we resort to current - * behaviour, which is cpu_possible == cpu_present. - * - Ashok Raj - * - * Three ways to find out the number of additional hotplug CPUs: - * - If the BIOS specified disabled CPUs in ACPI/mptables use that. - * - The user can overwrite it with additional_cpus=NUM - * - Otherwise don't reserve additional CPUs. - * We do this because additional CPUs waste a lot of memory. - * -AK - */ -__init void prefill_possible_map(void) -{ - int i; - int possible; - - if (additional_cpus == -1) { - if (disabled_cpus > 0) - additional_cpus = disabled_cpus; - else - additional_cpus = 0; - } - possible = num_processors + additional_cpus; - if (possible > NR_CPUS) - possible = NR_CPUS; - - printk(KERN_INFO "SMP: Allowing %d CPUs, %d hotplug CPUs\n", - possible, - max_t(int, possible - num_processors, 0)); - - for (i = 0; i < possible; i++) - cpu_set(i, cpu_possible_map); -} -#endif - -/* - * Various sanity checks. - */ -static int __init smp_sanity_check(unsigned max_cpus) -{ - if (!physid_isset(hard_smp_processor_id(), phys_cpu_present_map)) { - printk("weird, boot CPU (#%d) not listed by the BIOS.\n", - hard_smp_processor_id()); - physid_set(hard_smp_processor_id(), phys_cpu_present_map); - } - - /* - * If we couldn't find an SMP configuration at boot time, - * get out of here now! - */ - if (!smp_found_config) { - printk(KERN_NOTICE "SMP motherboard not detected.\n"); - disable_smp(); - if (APIC_init_uniprocessor()) - printk(KERN_NOTICE "Local APIC not detected." - " Using dummy APIC emulation.\n"); - return -1; - } - - /* - * Should not be necessary because the MP table should list the boot - * CPU too, but we do it for the sake of robustness anyway. - */ - if (!physid_isset(boot_cpu_id, phys_cpu_present_map)) { - printk(KERN_NOTICE "weird, boot CPU (#%d) not listed by the BIOS.\n", - boot_cpu_id); - physid_set(hard_smp_processor_id(), phys_cpu_present_map); - } - - /* - * If we couldn't find a local APIC, then get out of here now! - */ - if (!cpu_has_apic) { - printk(KERN_ERR "BIOS bug, local APIC #%d not detected!...\n", - boot_cpu_id); - printk(KERN_ERR "... forcing use of dummy APIC emulation. (tell your hw vendor)\n"); - nr_ioapics = 0; - return -1; - } - - /* - * 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"); - nr_ioapics = 0; - return -1; - } - - return 0; -} - -static void __init smp_cpu_index_default(void) -{ - int i; - struct cpuinfo_x86 *c; - - for_each_cpu_mask(i, cpu_possible_map) { - c = &cpu_data(i); - /* mark all to hotplug */ - c->cpu_index = NR_CPUS; - } -} - -/* - * Prepare for SMP bootup. The MP table or ACPI has been read - * earlier. Just do some sanity checking here and enable APIC mode. - */ -void __init smp_prepare_cpus(unsigned int max_cpus) -{ - nmi_watchdog_default(); - smp_cpu_index_default(); - current_cpu_data = boot_cpu_data; - current_thread_info()->cpu = 0; /* needed? */ - set_cpu_sibling_map(0); - - if (smp_sanity_check(max_cpus) < 0) { - printk(KERN_INFO "SMP disabled\n"); - disable_smp(); - return; - } - - - /* - * Switch from PIC to APIC mode. - */ - setup_local_APIC(); - - /* - * Enable IO APIC before setting up error vector - */ - if (!skip_ioapic_setup && nr_ioapics) - enable_IO_APIC(); - end_local_APIC_setup(); - - if (GET_APIC_ID(apic_read(APIC_ID)) != boot_cpu_id) { - panic("Boot APIC ID in local APIC unexpected (%d vs %d)", - GET_APIC_ID(apic_read(APIC_ID)), boot_cpu_id); - /* Or can we switch back to PIC here? */ - } - - /* - * Now start the IO-APICs - */ - if (!skip_ioapic_setup && nr_ioapics) - setup_IO_APIC(); - else - nr_ioapics = 0; - - /* - * Set up local APIC timer on boot CPU. - */ - - setup_boot_clock(); -} - -/* - * Early setup to make printk work. - */ -void __init smp_prepare_boot_cpu(void) -{ - int me = smp_processor_id(); - /* already set me in cpu_online_map in boot_cpu_init() */ - cpu_set(me, cpu_callout_map); - per_cpu(cpu_state, me) = CPU_ONLINE; -} - -/* - * Entry point to boot a CPU. - */ -int __cpuinit __cpu_up(unsigned int cpu) -{ - int apicid = cpu_present_to_apicid(cpu); - unsigned long flags; - int err; - - WARN_ON(irqs_disabled()); - - Dprintk("++++++++++++++++++++=_---CPU UP %u\n", cpu); - - if (apicid == BAD_APICID || apicid == boot_cpu_id || - !physid_isset(apicid, phys_cpu_present_map)) { - printk("__cpu_up: bad cpu %d\n", cpu); - return -EINVAL; - } - - /* - * Already booted CPU? - */ - if (cpu_isset(cpu, cpu_callin_map)) { - Dprintk("do_boot_cpu %d Already started\n", cpu); - return -ENOSYS; - } - - /* - * Save current MTRR state in case it was changed since early boot - * (e.g. by the ACPI SMI) to initialize new CPUs with MTRRs in sync: - */ - mtrr_save_state(); - - per_cpu(cpu_state, cpu) = CPU_UP_PREPARE; - /* Boot it! */ - err = do_boot_cpu(cpu, apicid); - if (err < 0) { - Dprintk("do_boot_cpu failed %d\n", err); - return err; - } - - /* Unleash the CPU! */ - Dprintk("waiting for cpu %d\n", cpu); - - /* - * Make sure and check TSC sync: - */ - local_irq_save(flags); - check_tsc_sync_source(cpu); - local_irq_restore(flags); - - while (!cpu_isset(cpu, cpu_online_map)) - cpu_relax(); - err = 0; - - return err; -} - -/* - * Finish the SMP boot. - */ -void __init smp_cpus_done(unsigned int max_cpus) -{ - smp_cleanup_boot(); - setup_ioapic_dest(); - check_nmi_watchdog(); -} - -#ifdef CONFIG_HOTPLUG_CPU - -static void remove_siblinginfo(int cpu) -{ - int sibling; - struct cpuinfo_x86 *c = &cpu_data(cpu); - - for_each_cpu_mask(sibling, per_cpu(cpu_core_map, cpu)) { - cpu_clear(cpu, per_cpu(cpu_core_map, sibling)); - /* - * last thread sibling in this cpu core going down - */ - if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1) - cpu_data(sibling).booted_cores--; - } - - for_each_cpu_mask(sibling, per_cpu(cpu_sibling_map, cpu)) - cpu_clear(cpu, per_cpu(cpu_sibling_map, sibling)); - cpus_clear(per_cpu(cpu_sibling_map, cpu)); - cpus_clear(per_cpu(cpu_core_map, cpu)); - c->phys_proc_id = 0; - c->cpu_core_id = 0; - cpu_clear(cpu, cpu_sibling_setup_map); -} - -static void __ref remove_cpu_from_maps(void) -{ - int cpu = smp_processor_id(); - - cpu_clear(cpu, cpu_callout_map); - cpu_clear(cpu, cpu_callin_map); - clear_bit(cpu, (unsigned long *)&cpu_initialized); /* was set by cpu_init() */ - clear_node_cpumask(cpu); -} - -int __cpu_disable(void) -{ - int cpu = smp_processor_id(); - - /* - * Perhaps use cpufreq to drop frequency, but that could go - * into generic code. - * - * We won't take down the boot processor on i386 due to some - * interrupts only being able to be serviced by the BSP. - * Especially so if we're not using an IOAPIC -zwane - */ - if (cpu == 0) - return -EBUSY; - - if (nmi_watchdog == NMI_LOCAL_APIC) - stop_apic_nmi_watchdog(NULL); - clear_local_APIC(); - - /* - * HACK: - * Allow any queued timer interrupts to get serviced - * This is only a temporary solution until we cleanup - * fixup_irqs as we do for IA64. - */ - local_irq_enable(); - mdelay(1); - - local_irq_disable(); - remove_siblinginfo(cpu); - - spin_lock(&vector_lock); - /* It's now safe to remove this processor from the online map */ - cpu_clear(cpu, cpu_online_map); - spin_unlock(&vector_lock); - remove_cpu_from_maps(); - fixup_irqs(cpu_online_map); - return 0; -} - -void __cpu_die(unsigned int cpu) -{ - /* We don't do anything here: idle task is faking death itself. */ - unsigned int i; - - for (i = 0; i < 10; i++) { - /* They ack this in play_dead by setting CPU_DEAD */ - if (per_cpu(cpu_state, cpu) == CPU_DEAD) { - printk ("CPU %d is now offline\n", cpu); - if (1 == num_online_cpus()) - alternatives_smp_switch(0); - return; - } - msleep(100); - } - printk(KERN_ERR "CPU %u didn't die...\n", cpu); -} - -static __init int setup_additional_cpus(char *s) -{ - return s && get_option(&s, &additional_cpus) ? 0 : -EINVAL; -} -early_param("additional_cpus", setup_additional_cpus); - -#else /* ... !CONFIG_HOTPLUG_CPU */ - -int __cpu_disable(void) -{ - return -ENOSYS; -} - -void __cpu_die(unsigned int cpu) -{ - /* We said "no" in __cpu_disable */ - BUG(); -} -#endif /* CONFIG_HOTPLUG_CPU */ diff --git a/arch/x86/kernel/smpcommon.c b/arch/x86/kernel/smpcommon.c new file mode 100644 index 000000000000..3449064d141a --- /dev/null +++ b/arch/x86/kernel/smpcommon.c @@ -0,0 +1,83 @@ +/* + * SMP stuff which is common to all sub-architectures. + */ +#include <linux/module.h> +#include <asm/smp.h> + +#ifdef CONFIG_X86_32 +DEFINE_PER_CPU(unsigned long, this_cpu_off); +EXPORT_PER_CPU_SYMBOL(this_cpu_off); + +/* Initialize the CPU's GDT. This is either the boot CPU doing itself + (still using the master per-cpu area), or a CPU doing it for a + secondary which will soon come up. */ +__cpuinit void init_gdt(int cpu) +{ + struct desc_struct *gdt = get_cpu_gdt_table(cpu); + + pack_descriptor(&gdt[GDT_ENTRY_PERCPU], + __per_cpu_offset[cpu], 0xFFFFF, + 0x2 | DESCTYPE_S, 0x8); + + gdt[GDT_ENTRY_PERCPU].s = 1; + + per_cpu(this_cpu_off, cpu) = __per_cpu_offset[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/smpcommon_32.c b/arch/x86/kernel/smpcommon_32.c index 8bc38af29aef..8b137891791f 100644 --- a/arch/x86/kernel/smpcommon_32.c +++ b/arch/x86/kernel/smpcommon_32.c @@ -1,82 +1 @@ -/* - * SMP stuff which is common to all sub-architectures. - */ -#include <linux/module.h> -#include <asm/smp.h> -DEFINE_PER_CPU(unsigned long, this_cpu_off); -EXPORT_PER_CPU_SYMBOL(this_cpu_off); - -/* Initialize the CPU's GDT. This is either the boot CPU doing itself - (still using the master per-cpu area), or a CPU doing it for a - secondary which will soon come up. */ -__cpuinit void init_gdt(int cpu) -{ - struct desc_struct *gdt = get_cpu_gdt_table(cpu); - - pack_descriptor(&gdt[GDT_ENTRY_PERCPU], - __per_cpu_offset[cpu], 0xFFFFF, - 0x2 | DESCTYPE_S, 0x8); - - gdt[GDT_ENTRY_PERCPU].s = 1; - - per_cpu(this_cpu_off, cpu) = __per_cpu_offset[cpu]; - per_cpu(cpu_number, cpu) = cpu; -} - - -/** - * 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/srat_32.c b/arch/x86/kernel/srat_32.c index b72e61359c36..70e4a374b4e8 100644 --- a/arch/x86/kernel/srat_32.c +++ b/arch/x86/kernel/srat_32.c @@ -277,14 +277,14 @@ int __init get_memcfg_from_srat(void) rsdp_address = acpi_os_get_root_pointer(); if (!rsdp_address) { printk("%s: System description tables not found\n", - __FUNCTION__); + __func__); goto out_err; } - printk("%s: assigning address to rsdp\n", __FUNCTION__); + 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", __FUNCTION__); + printk("%s: Didn't find ACPI root!\n", __func__); goto out_err; } @@ -292,7 +292,7 @@ int __init get_memcfg_from_srat(void) rsdp->oem_id); if (strncmp(rsdp->signature, ACPI_SIG_RSDP,strlen(ACPI_SIG_RSDP))) { - printk(KERN_WARNING "%s: RSDP table signature incorrect\n", __FUNCTION__); + printk(KERN_WARNING "%s: RSDP table signature incorrect\n", __func__); goto out_err; } @@ -302,7 +302,7 @@ int __init get_memcfg_from_srat(void) if (!rsdt) { printk(KERN_WARNING "%s: ACPI: Invalid root system description tables (RSDT)\n", - __FUNCTION__); + __func__); goto out_err; } diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 071ff4798236..92c20fee6781 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -148,7 +148,7 @@ static void write_debugctlmsr(struct task_struct *child, unsigned long val) if (child != current) return; - wrmsrl(MSR_IA32_DEBUGCTLMSR, val); + update_debugctlmsr(val); } /* diff --git a/arch/x86/kernel/summit_32.c b/arch/x86/kernel/summit_32.c index 72f463401592..ae751094eba9 100644 --- a/arch/x86/kernel/summit_32.c +++ b/arch/x86/kernel/summit_32.c @@ -29,49 +29,54 @@ #include <linux/mm.h> #include <linux/init.h> #include <asm/io.h> +#include <asm/bios_ebda.h> #include <asm/mach-summit/mach_mpparse.h> 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; +static int mp_bus_id_to_node[MAX_MP_BUSSES] __initdata; + static int __init setup_pci_node_map_for_wpeg(int wpeg_num, int last_bus) { int twister = 0, node = 0; int i, bus, num_buses; - for(i = 0; i < rio_table_hdr->num_rio_dev; i++){ - if (rio_devs[i]->node_id == rio_devs[wpeg_num]->owner_id){ + for (i = 0; i < rio_table_hdr->num_rio_dev; i++) { + if (rio_devs[i]->node_id == rio_devs[wpeg_num]->owner_id) { twister = rio_devs[i]->owner_id; break; } } - if (i == rio_table_hdr->num_rio_dev){ - printk(KERN_ERR "%s: Couldn't find owner Cyclone for Winnipeg!\n", __FUNCTION__); + if (i == rio_table_hdr->num_rio_dev) { + printk(KERN_ERR "%s: Couldn't find owner Cyclone for Winnipeg!\n", __func__); return last_bus; } - for(i = 0; i < rio_table_hdr->num_scal_dev; i++){ - if (scal_devs[i]->node_id == twister){ + for (i = 0; i < rio_table_hdr->num_scal_dev; i++) { + if (scal_devs[i]->node_id == twister) { node = scal_devs[i]->node_id; break; } } - if (i == rio_table_hdr->num_scal_dev){ - printk(KERN_ERR "%s: Couldn't find owner Twister for Cyclone!\n", __FUNCTION__); + if (i == rio_table_hdr->num_scal_dev) { + printk(KERN_ERR "%s: Couldn't find owner Twister for Cyclone!\n", __func__); return last_bus; } - switch (rio_devs[wpeg_num]->type){ + switch (rio_devs[wpeg_num]->type) { case CompatWPEG: - /* The Compatibility Winnipeg controls the 2 legacy buses, + /* + * The Compatibility Winnipeg controls the 2 legacy buses, * the 66MHz PCI bus [2 slots] and the 2 "extra" buses in case * a PCI-PCI bridge card is used in either slot: total 5 buses. */ num_buses = 5; break; case AltWPEG: - /* The Alternate Winnipeg controls the 2 133MHz buses [1 slot + /* + * The Alternate Winnipeg controls the 2 133MHz buses [1 slot * each], their 2 "extra" buses, the 100MHz bus [2 slots] and * the "extra" buses for each of those slots: total 7 buses. */ @@ -79,17 +84,18 @@ static int __init setup_pci_node_map_for_wpeg(int wpeg_num, int last_bus) break; case LookOutAWPEG: case LookOutBWPEG: - /* A Lookout Winnipeg controls 3 100MHz buses [2 slots each] + /* + * A Lookout Winnipeg controls 3 100MHz buses [2 slots each] * & the "extra" buses for each of those slots: total 9 buses. */ num_buses = 9; break; default: - printk(KERN_INFO "%s: Unsupported Winnipeg type!\n", __FUNCTION__); + printk(KERN_INFO "%s: Unsupported Winnipeg type!\n", __func__); return last_bus; } - for(bus = last_bus; bus < last_bus + num_buses; bus++) + for (bus = last_bus; bus < last_bus + num_buses; bus++) mp_bus_id_to_node[bus] = node; return bus; } @@ -99,14 +105,14 @@ static int __init build_detail_arrays(void) unsigned long ptr; int i, scal_detail_size, rio_detail_size; - if (rio_table_hdr->num_scal_dev > MAX_NUMNODES){ - printk(KERN_WARNING "%s: MAX_NUMNODES too low! Defined as %d, but system has %d nodes.\n", __FUNCTION__, MAX_NUMNODES, rio_table_hdr->num_scal_dev); + if (rio_table_hdr->num_scal_dev > MAX_NUMNODES) { + printk(KERN_WARNING "%s: MAX_NUMNODES too low! Defined as %d, but system has %d nodes.\n", __func__, MAX_NUMNODES, rio_table_hdr->num_scal_dev); return 0; } - switch (rio_table_hdr->version){ + switch (rio_table_hdr->version) { default: - printk(KERN_WARNING "%s: Invalid Rio Grande Table Version: %d\n", __FUNCTION__, rio_table_hdr->version); + printk(KERN_WARNING "%s: Invalid Rio Grande Table Version: %d\n", __func__, rio_table_hdr->version); return 0; case 2: scal_detail_size = 11; @@ -119,10 +125,10 @@ static int __init build_detail_arrays(void) } ptr = (unsigned long)rio_table_hdr + 3; - for(i = 0; i < rio_table_hdr->num_scal_dev; i++, ptr += scal_detail_size) + for (i = 0; i < rio_table_hdr->num_scal_dev; i++, ptr += scal_detail_size) scal_devs[i] = (struct scal_detail *)ptr; - for(i = 0; i < rio_table_hdr->num_rio_dev; i++, ptr += rio_detail_size) + for (i = 0; i < rio_table_hdr->num_rio_dev; i++, ptr += rio_detail_size) rio_devs[i] = (struct rio_detail *)ptr; return 1; @@ -135,14 +141,14 @@ void __init setup_summit(void) int i, next_wpeg, next_bus = 0; /* The pointer to the EBDA is stored in the word @ phys 0x40E(40:0E) */ - ptr = *(unsigned short *)phys_to_virt(0x40Eul); - ptr = (unsigned long)phys_to_virt(ptr << 4); + ptr = get_bios_ebda(); + ptr = (unsigned long)phys_to_virt(ptr); rio_table_hdr = NULL; offset = 0x180; - while (offset){ + while (offset) { /* The block id is stored in the 2nd word */ - if (*((unsigned short *)(ptr + offset + 2)) == 0x4752){ + if (*((unsigned short *)(ptr + offset + 2)) == 0x4752) { /* set the pointer past the offset & block id */ rio_table_hdr = (struct rio_table_hdr *)(ptr + offset + 4); break; @@ -150,8 +156,8 @@ void __init setup_summit(void) /* The next offset is stored in the 1st word. 0 means no more */ offset = *((unsigned short *)(ptr + offset)); } - if (!rio_table_hdr){ - printk(KERN_ERR "%s: Unable to locate Rio Grande Table in EBDA - bailing!\n", __FUNCTION__); + if (!rio_table_hdr) { + printk(KERN_ERR "%s: Unable to locate Rio Grande Table in EBDA - bailing!\n", __func__); return; } @@ -161,8 +167,8 @@ void __init setup_summit(void) /* The first Winnipeg we're looking for has an index of 0 */ next_wpeg = 0; do { - for(i = 0; i < rio_table_hdr->num_rio_dev; i++){ - if (is_WPEG(rio_devs[i]) && rio_devs[i]->WP_index == next_wpeg){ + for (i = 0; i < rio_table_hdr->num_rio_dev; i++) { + if (is_WPEG(rio_devs[i]) && rio_devs[i]->WP_index == next_wpeg) { /* It's the Winnipeg we're looking for! */ next_bus = setup_pci_node_map_for_wpeg(i, next_bus); next_wpeg++; diff --git a/arch/x86/kernel/syscall_64.c b/arch/x86/kernel/syscall_64.c index 9d498c2f8eea..170d43c17487 100644 --- a/arch/x86/kernel/syscall_64.c +++ b/arch/x86/kernel/syscall_64.c @@ -1,4 +1,4 @@ -/* System call table for x86-64. */ +/* System call table for x86-64. */ #include <linux/linkage.h> #include <linux/sys.h> @@ -7,20 +7,23 @@ #define __NO_STUBS -#define __SYSCALL(nr, sym) extern asmlinkage void sym(void) ; +#define __SYSCALL(nr, sym) extern asmlinkage void sym(void) ; #undef _ASM_X86_64_UNISTD_H_ #include <asm/unistd_64.h> #undef __SYSCALL -#define __SYSCALL(nr, sym) [ nr ] = sym, +#define __SYSCALL(nr, sym) [nr] = sym, #undef _ASM_X86_64_UNISTD_H_ -typedef void (*sys_call_ptr_t)(void); +typedef void (*sys_call_ptr_t)(void); extern void sys_ni_syscall(void); const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { - /* Smells like a like a compiler bug -- it doesn't work when the & below is removed. */ + /* + *Smells like a like a compiler bug -- it doesn't work + *when the & below is removed. + */ [0 ... __NR_syscall_max] = &sys_ni_syscall, #include <asm/unistd_64.h> }; diff --git a/arch/x86/kernel/test_nx.c b/arch/x86/kernel/test_nx.c index 10b8a6f69f84..787a5e499dd1 100644 --- a/arch/x86/kernel/test_nx.c +++ b/arch/x86/kernel/test_nx.c @@ -11,6 +11,8 @@ */ #include <linux/module.h> #include <linux/sort.h> +#include <linux/slab.h> + #include <asm/uaccess.h> #include <asm/asm.h> diff --git a/arch/x86/kernel/time_32.c b/arch/x86/kernel/time_32.c index 1a89e93f3f1c..2ff21f398934 100644 --- a/arch/x86/kernel/time_32.c +++ b/arch/x86/kernel/time_32.c @@ -115,7 +115,6 @@ irqreturn_t timer_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -extern void (*late_time_init)(void); /* Duplicate of time_init() below, with hpet_enable part added */ void __init hpet_time_init(void) { diff --git a/arch/x86/kernel/tlb_32.c b/arch/x86/kernel/tlb_32.c new file mode 100644 index 000000000000..9bb2363851af --- /dev/null +++ b/arch/x86/kernel/tlb_32.c @@ -0,0 +1,243 @@ +#include <linux/spinlock.h> +#include <linux/cpu.h> +#include <linux/interrupt.h> + +#include <asm/tlbflush.h> + +DEFINE_PER_CPU(struct tlb_state, cpu_tlbstate) + ____cacheline_aligned = { &init_mm, 0, }; + +/* must come after the send_IPI functions above for inlining */ +#include <mach_ipi.h> + +/* + * Smarter SMP flushing macros. + * c/o Linus Torvalds. + * + * These mean you can really definitely utterly forget about + * writing to user space from interrupts. (Its not allowed anyway). + * + * Optimizations Manfred Spraul <manfred@colorfullife.com> + */ + +static cpumask_t flush_cpumask; +static struct mm_struct *flush_mm; +static unsigned long flush_va; +static DEFINE_SPINLOCK(tlbstate_lock); + +/* + * We cannot call mmdrop() because we are in interrupt context, + * instead update mm->cpu_vm_mask. + * + * We need to reload %cr3 since the page tables may be going + * away from under us.. + */ +void leave_mm(int cpu) +{ + if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK) + BUG(); + cpu_clear(cpu, per_cpu(cpu_tlbstate, cpu).active_mm->cpu_vm_mask); + load_cr3(swapper_pg_dir); +} +EXPORT_SYMBOL_GPL(leave_mm); + +/* + * + * The flush IPI assumes that a thread switch happens in this order: + * [cpu0: the cpu that switches] + * 1) switch_mm() either 1a) or 1b) + * 1a) thread switch to a different mm + * 1a1) cpu_clear(cpu, old_mm->cpu_vm_mask); + * Stop ipi delivery for the old mm. This is not synchronized with + * the other cpus, but smp_invalidate_interrupt ignore flush ipis + * for the wrong mm, and in the worst case we perform a superfluous + * tlb flush. + * 1a2) set cpu_tlbstate to TLBSTATE_OK + * Now the smp_invalidate_interrupt won't call leave_mm if cpu0 + * was in lazy tlb mode. + * 1a3) update cpu_tlbstate[].active_mm + * Now cpu0 accepts tlb flushes for the new mm. + * 1a4) cpu_set(cpu, new_mm->cpu_vm_mask); + * Now the other cpus will send tlb flush ipis. + * 1a4) change cr3. + * 1b) thread switch without mm change + * cpu_tlbstate[].active_mm is correct, cpu0 already handles + * flush ipis. + * 1b1) set cpu_tlbstate to TLBSTATE_OK + * 1b2) test_and_set the cpu bit in cpu_vm_mask. + * Atomically set the bit [other cpus will start sending flush ipis], + * and test the bit. + * 1b3) if the bit was 0: leave_mm was called, flush the tlb. + * 2) switch %%esp, ie current + * + * The interrupt must handle 2 special cases: + * - cr3 is changed before %%esp, ie. it cannot use current->{active_,}mm. + * - the cpu performs speculative tlb reads, i.e. even if the cpu only + * runs in kernel space, the cpu could load tlb entries for user space + * pages. + * + * The good news is that cpu_tlbstate is local to each cpu, no + * write/read ordering problems. + */ + +/* + * TLB flush IPI: + * + * 1) Flush the tlb entries if the cpu uses the mm that's being flushed. + * 2) Leave the mm if we are in the lazy tlb mode. + */ + +void smp_invalidate_interrupt(struct pt_regs *regs) +{ + unsigned long cpu; + + cpu = get_cpu(); + + if (!cpu_isset(cpu, flush_cpumask)) + goto out; + /* + * This was a BUG() but until someone can quote me the + * line from the intel manual that guarantees an IPI to + * multiple CPUs is retried _only_ on the erroring CPUs + * its staying as a return + * + * BUG(); + */ + + if (flush_mm == per_cpu(cpu_tlbstate, cpu).active_mm) { + if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK) { + if (flush_va == TLB_FLUSH_ALL) + local_flush_tlb(); + else + __flush_tlb_one(flush_va); + } else + leave_mm(cpu); + } + ack_APIC_irq(); + smp_mb__before_clear_bit(); + cpu_clear(cpu, flush_cpumask); + smp_mb__after_clear_bit(); +out: + put_cpu_no_resched(); + __get_cpu_var(irq_stat).irq_tlb_count++; +} + +void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm, + unsigned long va) +{ + cpumask_t cpumask = *cpumaskp; + + /* + * A couple of (to be removed) sanity checks: + * + * - current CPU must not be in mask + * - mask must exist :) + */ + BUG_ON(cpus_empty(cpumask)); + BUG_ON(cpu_isset(smp_processor_id(), cpumask)); + BUG_ON(!mm); + +#ifdef CONFIG_HOTPLUG_CPU + /* If a CPU which we ran on has gone down, OK. */ + cpus_and(cpumask, cpumask, cpu_online_map); + if (unlikely(cpus_empty(cpumask))) + return; +#endif + + /* + * i'm not happy about this global shared spinlock in the + * MM hot path, but we'll see how contended it is. + * AK: x86-64 has a faster method that could be ported. + */ + spin_lock(&tlbstate_lock); + + flush_mm = mm; + flush_va = va; + cpus_or(flush_cpumask, cpumask, flush_cpumask); + /* + * We have to send the IPI only to + * CPUs affected. + */ + send_IPI_mask(cpumask, INVALIDATE_TLB_VECTOR); + + while (!cpus_empty(flush_cpumask)) + /* nothing. lockup detection does not belong here */ + cpu_relax(); + + flush_mm = NULL; + flush_va = 0; + spin_unlock(&tlbstate_lock); +} + +void flush_tlb_current_task(void) +{ + struct mm_struct *mm = current->mm; + cpumask_t cpu_mask; + + preempt_disable(); + cpu_mask = mm->cpu_vm_mask; + cpu_clear(smp_processor_id(), cpu_mask); + + local_flush_tlb(); + if (!cpus_empty(cpu_mask)) + flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL); + preempt_enable(); +} + +void flush_tlb_mm(struct mm_struct *mm) +{ + cpumask_t cpu_mask; + + preempt_disable(); + cpu_mask = mm->cpu_vm_mask; + cpu_clear(smp_processor_id(), cpu_mask); + + if (current->active_mm == mm) { + if (current->mm) + local_flush_tlb(); + else + leave_mm(smp_processor_id()); + } + if (!cpus_empty(cpu_mask)) + flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL); + + preempt_enable(); +} + +void flush_tlb_page(struct vm_area_struct *vma, unsigned long va) +{ + struct mm_struct *mm = vma->vm_mm; + cpumask_t cpu_mask; + + preempt_disable(); + cpu_mask = mm->cpu_vm_mask; + cpu_clear(smp_processor_id(), cpu_mask); + + if (current->active_mm == mm) { + if (current->mm) + __flush_tlb_one(va); + else + leave_mm(smp_processor_id()); + } + + if (!cpus_empty(cpu_mask)) + flush_tlb_others(cpu_mask, mm, va); + + preempt_enable(); +} +EXPORT_SYMBOL(flush_tlb_page); + +static void do_flush_tlb_all(void *info) +{ + unsigned long cpu = smp_processor_id(); + + __flush_tlb_all(); + if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_LAZY) + leave_mm(cpu); +} + +void flush_tlb_all(void) +{ + on_each_cpu(do_flush_tlb_all, NULL, 1, 1); +} + diff --git a/arch/x86/kernel/smp_64.c b/arch/x86/kernel/tlb_64.c index 2fd74b06db67..a1f07d793202 100644 --- a/arch/x86/kernel/smp_64.c +++ b/arch/x86/kernel/tlb_64.c @@ -1,14 +1,3 @@ -/* - * Intel SMP support routines. - * - * (c) 1995 Alan Cox, Building #3 <alan@redhat.com> - * (c) 1998-99, 2000 Ingo Molnar <mingo@redhat.com> - * (c) 2002,2003 Andi Kleen, SuSE Labs. - * - * This code is released under the GNU General Public License version 2 or - * later. - */ - #include <linux/init.h> #include <linux/mm.h> @@ -22,12 +11,12 @@ #include <asm/mtrr.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> -#include <asm/mach_apic.h> #include <asm/mmu_context.h> #include <asm/proto.h> #include <asm/apicdef.h> #include <asm/idle.h> +#include <mach_ipi.h> /* * Smarter SMP flushing macros. * c/o Linus Torvalds. @@ -202,13 +191,13 @@ void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm, spin_unlock(&f->tlbstate_lock); } -int __cpuinit init_smp_flush(void) +static int __cpuinit init_smp_flush(void) { int i; - for_each_cpu_mask(i, cpu_possible_map) { + for_each_possible_cpu(i) spin_lock_init(&per_cpu(flush_state, i).tlbstate_lock); - } + return 0; } core_initcall(init_smp_flush); @@ -228,7 +217,7 @@ void flush_tlb_current_task(void) preempt_enable(); } -void flush_tlb_mm (struct mm_struct * mm) +void flush_tlb_mm(struct mm_struct *mm) { cpumask_t cpu_mask; @@ -248,7 +237,7 @@ void flush_tlb_mm (struct mm_struct * mm) preempt_enable(); } -void flush_tlb_page(struct vm_area_struct * vma, unsigned long va) +void flush_tlb_page(struct vm_area_struct *vma, unsigned long va) { struct mm_struct *mm = vma->vm_mm; cpumask_t cpu_mask; @@ -258,7 +247,7 @@ void flush_tlb_page(struct vm_area_struct * vma, unsigned long va) cpu_clear(smp_processor_id(), cpu_mask); if (current->active_mm == mm) { - if(current->mm) + if (current->mm) __flush_tlb_one(va); else leave_mm(smp_processor_id()); @@ -270,7 +259,7 @@ void flush_tlb_page(struct vm_area_struct * vma, unsigned long va) preempt_enable(); } -static void do_flush_tlb_all(void* info) +static void do_flush_tlb_all(void *info) { unsigned long cpu = smp_processor_id(); @@ -283,248 +272,3 @@ void flush_tlb_all(void) { on_each_cpu(do_flush_tlb_all, NULL, 1, 1); } - -/* - * this function sends a 'reschedule' IPI to another CPU. - * it goes straight through and wastes no time serializing - * anything. Worst case is that we lose a reschedule ... - */ - -void 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; -}; - -static struct call_data_struct * call_data; - -void lock_ipi_call_lock(void) -{ - spin_lock_irq(&call_lock); -} - -void unlock_ipi_call_lock(void) -{ - spin_unlock_irq(&call_lock); -} - -/* - * this function sends a 'generic call function' IPI to all other CPU - * of the system defined in the mask. - */ -static int __smp_call_function_mask(cpumask_t mask, - void (*func)(void *), void *info, - int wait) -{ - struct call_data_struct data; - cpumask_t allbutself; - int cpus; - - allbutself = cpu_online_map; - cpu_clear(smp_processor_id(), allbutself); - - cpus_and(mask, mask, allbutself); - cpus = cpus_weight(mask); - - if (!cpus) - return 0; - - data.func = func; - data.info = info; - 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)) - send_IPI_allbutself(CALL_FUNCTION_VECTOR); - else - send_IPI_mask(mask, CALL_FUNCTION_VECTOR); - - /* Wait for response */ - while (atomic_read(&data.started) != cpus) - cpu_relax(); - - if (!wait) - return 0; - - while (atomic_read(&data.finished) != cpus) - cpu_relax(); - - return 0; -} -/** - * smp_call_function_mask(): Run a function on a set of other CPUs. - * @mask: The set of cpus to run on. Must not include the current cpu. - * @func: The function to run. This must be fast and non-blocking. - * @info: An arbitrary pointer to pass to the function. - * @wait: If true, wait (atomically) until function has completed on other CPUs. - * - * Returns 0 on success, else a negative status code. - * - * If @wait is true, then returns once @func has returned; otherwise - * it returns just before the target cpu calls @func. - * - * You must not call this function with disabled interrupts or from a - * hardware interrupt handler or from a bottom half handler. - */ -int smp_call_function_mask(cpumask_t mask, - void (*func)(void *), void *info, - int wait) -{ - int ret; - - /* Can deadlock when called with interrupts disabled */ - WARN_ON(irqs_disabled()); - - spin_lock(&call_lock); - ret = __smp_call_function_mask(mask, func, info, wait); - spin_unlock(&call_lock); - return ret; -} -EXPORT_SYMBOL(smp_call_function_mask); - -/* - * smp_call_function_single - Run a function on a specific CPU - * @func: The function to run. This must be fast and non-blocking. - * @info: An arbitrary pointer to pass to the function. - * @nonatomic: Currently unused. - * @wait: If true, wait until function has completed on other CPUs. - * - * Retrurns 0 on success, else a negative status code. - * - * Does not return until the remote CPU is nearly ready to execute <func> - * or is or has executed. - */ - -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, me = get_cpu(); - - /* Can deadlock when called with interrupts disabled */ - WARN_ON(irqs_disabled()); - - 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); - -/* - * 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: currently unused. - * @wait: If true, wait (atomically) until function has completed on other - * CPUs. - * - * Returns 0 on success, else a negative status code. Does not return until - * remote CPUs are nearly ready to execute func or are or have executed. - * - * You must not call this function with disabled interrupts or from a - * hardware interrupt handler or from a bottom half handler. - * Actually there are a few legal cases, like panic. - */ -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); - -static void stop_this_cpu(void *dummy) -{ - local_irq_disable(); - /* - * Remove this CPU: - */ - cpu_clear(smp_processor_id(), cpu_online_map); - disable_local_APIC(); - for (;;) - halt(); -} - -void 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); - local_irq_save(flags); - __smp_call_function_mask(cpu_online_map, stop_this_cpu, NULL, 0); - if (!nolock) - spin_unlock(&call_lock); - disable_local_APIC(); - local_irq_restore(flags); -} - -/* - * Reschedule call back. Nothing to do, - * all the work is done automatically when - * we return from the interrupt. - */ -asmlinkage void smp_reschedule_interrupt(void) -{ - ack_APIC_irq(); - add_pda(irq_resched_count, 1); -} - -asmlinkage void smp_call_function_interrupt(void) -{ - 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 - */ - exit_idle(); - irq_enter(); - (*func)(info); - add_pda(irq_call_count, 1); - irq_exit(); - if (wait) { - mb(); - atomic_inc(&call_data->finished); - } -} - diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c new file mode 100644 index 000000000000..abbf199adebb --- /dev/null +++ b/arch/x86/kernel/trampoline.c @@ -0,0 +1,18 @@ +#include <linux/io.h> + +#include <asm/trampoline.h> + +/* ready for x86_64, no harm for x86, since it will overwrite after alloc */ +unsigned char *trampoline_base = __va(TRAMPOLINE_BASE); + +/* + * Currently trivial. Write the real->protected mode + * bootstrap into the page concerned. The caller + * has made sure it's suitably aligned. + */ +unsigned long setup_trampoline(void) +{ + memcpy(trampoline_base, trampoline_data, + trampoline_end - trampoline_data); + return virt_to_phys(trampoline_base); +} diff --git a/arch/x86/kernel/trampoline_32.S b/arch/x86/kernel/trampoline_32.S index 64580679861e..d8ccc3c6552f 100644 --- a/arch/x86/kernel/trampoline_32.S +++ b/arch/x86/kernel/trampoline_32.S @@ -33,7 +33,7 @@ /* We can free up trampoline after bootup if cpu hotplug is not supported. */ #ifndef CONFIG_HOTPLUG_CPU -.section ".init.data","aw",@progbits +.section ".cpuinit.data","aw",@progbits #else .section .rodata,"a",@progbits #endif diff --git a/arch/x86/kernel/trampoline_64.S b/arch/x86/kernel/trampoline_64.S index 4aedd0bcee4c..894293c598db 100644 --- a/arch/x86/kernel/trampoline_64.S +++ b/arch/x86/kernel/trampoline_64.S @@ -30,12 +30,7 @@ #include <asm/msr.h> #include <asm/segment.h> -/* We can free up trampoline after bootup if cpu hotplug is not supported. */ -#ifndef CONFIG_HOTPLUG_CPU -.section .init.data, "aw", @progbits -#else .section .rodata, "a", @progbits -#endif .code16 diff --git a/arch/x86/kernel/traps_32.c b/arch/x86/kernel/traps_32.c index b22c01e05a18..bde6f63e15d5 100644 --- a/arch/x86/kernel/traps_32.c +++ b/arch/x86/kernel/traps_32.c @@ -9,26 +9,28 @@ * 'Traps.c' handles hardware traps and faults after we have saved some * state in 'asm.s'. */ -#include <linux/sched.h> +#include <linux/interrupt.h> +#include <linux/kallsyms.h> +#include <linux/spinlock.h> +#include <linux/highmem.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/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/highmem.h> -#include <linux/kallsyms.h> -#include <linux/ptrace.h> -#include <linux/utsname.h> -#include <linux/kprobes.h> -#include <linux/kexec.h> -#include <linux/unwind.h> -#include <linux/uaccess.h> -#include <linux/nmi.h> #include <linux/bug.h> +#include <linux/nmi.h> +#include <linux/mm.h> #ifdef CONFIG_EISA #include <linux/ioport.h> @@ -43,21 +45,18 @@ #include <linux/edac.h> #endif +#include <asm/arch_hooks.h> +#include <asm/stacktrace.h> #include <asm/processor.h> -#include <asm/system.h> -#include <asm/io.h> -#include <asm/atomic.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/nmi.h> -#include <asm/unwind.h> #include <asm/smp.h> -#include <asm/arch_hooks.h> -#include <linux/kdebug.h> -#include <asm/stacktrace.h> - -#include <linux/module.h> +#include <asm/io.h> #include "mach_traps.h" @@ -69,7 +68,7 @@ EXPORT_SYMBOL_GPL(used_vectors); asmlinkage int system_call(void); /* Do we ignore FPU interrupts ? */ -char ignore_fpu_irq = 0; +char ignore_fpu_irq; /* * The IDT has to be page-aligned to simplify the Pentium @@ -105,12 +104,13 @@ static unsigned int code_bytes = 64; void printk_address(unsigned long address, int reliable) { #ifdef CONFIG_KALLSYMS - unsigned long offset = 0, symsize; + char namebuf[KSYM_NAME_LEN]; + unsigned long offset = 0; + unsigned long symsize; const char *symname; - char *modname; - char *delim = ":"; - char namebuf[128]; char reliab[4] = ""; + char *delim = ":"; + char *modname; symname = kallsyms_lookup(address, &symsize, &offset, &modname, namebuf); @@ -138,13 +138,14 @@ static inline int valid_stack_ptr(struct thread_info *tinfo, void *p, unsigned s /* 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) +static inline unsigned long +print_context_stack(struct thread_info *tinfo, + unsigned long *stack, unsigned long bp, + const struct stacktrace_ops *ops, void *data) { struct stack_frame *frame = (struct stack_frame *)bp; @@ -166,7 +167,7 @@ static inline unsigned long print_context_stack(struct thread_info *tinfo, return bp; } -#define MSG(msg) ops->warning(data, msg) +#define MSG(msg) ops->warning(data, msg) void dump_trace(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, unsigned long bp, @@ -177,6 +178,7 @@ 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; @@ -186,7 +188,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, if (!bp) { if (task == current) { /* Grab bp right from our regs */ - asm ("movl %%ebp, %0" : "=r" (bp) : ); + asm("movl %%ebp, %0" : "=r" (bp) :); } else { /* bp is the last reg pushed by switch_to */ bp = *(unsigned long *) task->thread.sp; @@ -196,15 +198,18 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, while (1) { struct thread_info *context; + context = (struct thread_info *) ((unsigned long)stack & (~(THREAD_SIZE - 1))); bp = print_context_stack(context, stack, bp, ops, data); - /* Should be after the line below, but somewhere - in early boot context comes out corrupted and we - can't reference it -AK */ + /* + * Should be after the line below, but somewhere + * in early boot context comes out corrupted and we + * can't reference it: + */ if (ops->stack(data, "IRQ") < 0) break; - stack = (unsigned long*)context->previous_esp; + stack = (unsigned long *)context->previous_esp; if (!stack) break; touch_nmi_watchdog(); @@ -243,15 +248,15 @@ 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 show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, char *log_lvl) + unsigned long *stack, unsigned long bp, char *log_lvl) { dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl); printk("%s =======================\n", log_lvl); @@ -263,21 +268,22 @@ void show_trace(struct task_struct *task, struct pt_regs *regs, show_trace_log_lvl(task, regs, stack, bp, ""); } -static void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, unsigned long bp, char *log_lvl) +static void +show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *sp, unsigned long bp, char *log_lvl) { unsigned long *stack; int i; if (sp == NULL) { if (task) - sp = (unsigned long*)task->thread.sp; + 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 (kstack_end(stack)) break; if (i && ((i % 8) == 0)) @@ -285,6 +291,7 @@ static void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, printk("%08lx ", *stack++); } printk("\n%sCall Trace:\n", log_lvl); + show_trace_log_lvl(task, regs, sp, bp, log_lvl); } @@ -299,8 +306,8 @@ void show_stack(struct task_struct *task, unsigned long *sp) */ void dump_stack(void) { - unsigned long stack; unsigned long bp = 0; + unsigned long stack; #ifdef CONFIG_FRAME_POINTER if (!bp) @@ -312,6 +319,7 @@ void dump_stack(void) init_utsname()->release, (int)strcspn(init_utsname()->version, " "), init_utsname()->version); + show_trace(current, NULL, &stack, bp); } @@ -323,6 +331,7 @@ void show_registers(struct pt_regs *regs) print_modules(); __show_registers(regs, 0); + printk(KERN_EMERG "Process %.*s (pid: %d, ti=%p task=%p task.ti=%p)", TASK_COMM_LEN, current->comm, task_pid_nr(current), current_thread_info(), current, task_thread_info(current)); @@ -331,10 +340,10 @@ void show_registers(struct pt_regs *regs) * time of the fault.. */ if (!user_mode_vm(regs)) { - u8 *ip; unsigned int code_prologue = code_bytes * 43 / 64; unsigned int code_len = code_bytes; unsigned char c; + u8 *ip; printk("\n" KERN_EMERG "Stack: "); show_stack_log_lvl(NULL, regs, ®s->sp, 0, KERN_EMERG); @@ -361,7 +370,7 @@ void show_registers(struct pt_regs *regs) } } printk("\n"); -} +} int is_valid_bugaddr(unsigned long ip) { @@ -377,10 +386,10 @@ int is_valid_bugaddr(unsigned long ip) static int die_counter; -int __kprobes __die(const char * str, struct pt_regs * regs, long err) +int __kprobes __die(const char *str, struct pt_regs *regs, long err) { - unsigned long sp; unsigned short ss; + unsigned long sp; printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter); #ifdef CONFIG_PREEMPT @@ -395,8 +404,8 @@ int __kprobes __die(const char * str, struct pt_regs * regs, long err) printk("\n"); if (notify_die(DIE_OOPS, str, regs, err, - current->thread.trap_no, SIGSEGV) != - NOTIFY_STOP) { + current->thread.trap_no, SIGSEGV) != NOTIFY_STOP) { + show_registers(regs); /* Executive summary in case the oops scrolled away */ sp = (unsigned long) (®s->sp); @@ -408,17 +417,18 @@ int __kprobes __die(const char * str, struct pt_regs * regs, long err) printk(KERN_EMERG "EIP: [<%08lx>] ", regs->ip); print_symbol("%s", regs->ip); printk(" SS:ESP %04x:%08lx\n", ss, sp); + return 0; - } else { - return 1; } + + return 1; } /* - * This is gone through when something in the kernel has done something bad and - * is about to be terminated. + * This is gone through when something in the kernel has done something bad + * and is about to be terminated: */ -void die(const char * str, struct pt_regs * regs, long err) +void die(const char *str, struct pt_regs *regs, long err) { static struct { raw_spinlock_t lock; @@ -440,8 +450,9 @@ void die(const char * str, struct pt_regs * regs, long err) die.lock_owner = smp_processor_id(); die.lock_owner_depth = 0; bust_spinlocks(1); - } else + } else { raw_local_irq_save(flags); + } if (++die.lock_owner_depth < 3) { report_bug(regs->ip, regs); @@ -474,19 +485,20 @@ void die(const char * str, struct pt_regs * regs, long err) do_exit(SIGSEGV); } -static inline void die_if_kernel(const char * str, struct pt_regs * regs, long err) +static inline void +die_if_kernel(const char *str, struct pt_regs *regs, long err) { if (!user_mode_vm(regs)) die(str, regs, err); } -static void __kprobes do_trap(int trapnr, int signr, char *str, int vm86, - struct pt_regs * regs, long error_code, - siginfo_t *info) +static void __kprobes +do_trap(int trapnr, int signr, char *str, int vm86, struct pt_regs *regs, + long error_code, siginfo_t *info) { struct task_struct *tsk = current; - if (regs->flags & VM_MASK) { + if (regs->flags & X86_VM_MASK) { if (vm86) goto vm86_trap; goto trap_signal; @@ -495,111 +507,112 @@ static void __kprobes do_trap(int trapnr, int signr, char *str, int vm86, if (!user_mode(regs)) goto kernel_trap; - trap_signal: { - /* - * 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; +trap_signal: + /* + * 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 (info) - force_sig_info(signr, info, tsk); - else - force_sig(signr, tsk); - return; - } + 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; - die(str, regs, error_code); - } - return; +kernel_trap: + if (!fixup_exception(regs)) { + tsk->thread.error_code = error_code; + tsk->thread.trap_no = trapnr; + die(str, regs, error_code); } + return; - vm86_trap: { - int ret = handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, trapnr); - if (ret) goto trap_signal; - return; - } +vm86_trap: + if (handle_vm86_trap((struct kernel_vm86_regs *) regs, + error_code, trapnr)) + goto trap_signal; + return; } -#define DO_ERROR(trapnr, signr, str, name) \ -void do_##name(struct pt_regs * regs, long error_code) \ -{ \ - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ - return; \ - do_trap(trapnr, signr, str, 0, regs, error_code, NULL); \ +#define DO_ERROR(trapnr, signr, str, name) \ +void do_##name(struct pt_regs *regs, long error_code) \ +{ \ + if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ + == NOTIFY_STOP) \ + return; \ + do_trap(trapnr, signr, str, 0, regs, error_code, NULL); \ } -#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr, irq) \ -void do_##name(struct pt_regs * regs, long error_code) \ -{ \ - siginfo_t info; \ - if (irq) \ - local_irq_enable(); \ - info.si_signo = signr; \ - info.si_errno = 0; \ - info.si_code = sicode; \ - info.si_addr = (void __user *)siaddr; \ - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ - return; \ - do_trap(trapnr, signr, str, 0, regs, error_code, &info); \ +#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr, irq) \ +void do_##name(struct pt_regs *regs, long error_code) \ +{ \ + siginfo_t info; \ + if (irq) \ + local_irq_enable(); \ + info.si_signo = signr; \ + info.si_errno = 0; \ + info.si_code = sicode; \ + info.si_addr = (void __user *)siaddr; \ + if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ + == NOTIFY_STOP) \ + return; \ + do_trap(trapnr, signr, str, 0, regs, error_code, &info); \ } -#define DO_VM86_ERROR(trapnr, signr, str, name) \ -void do_##name(struct pt_regs * regs, long error_code) \ -{ \ - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ - return; \ - do_trap(trapnr, signr, str, 1, regs, error_code, NULL); \ +#define DO_VM86_ERROR(trapnr, signr, str, name) \ +void do_##name(struct pt_regs *regs, long error_code) \ +{ \ + if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ + == NOTIFY_STOP) \ + return; \ + do_trap(trapnr, signr, str, 1, regs, error_code, NULL); \ } -#define DO_VM86_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ -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; \ - do_trap(trapnr, signr, str, 1, regs, error_code, &info); \ +#define DO_VM86_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ +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; \ + 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) +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_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(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_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0, 0) -DO_ERROR_INFO(32, SIGSEGV, "iret exception", iret_error, ILL_BADSTK, 0, 1) +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) { - int cpu = get_cpu(); - struct tss_struct *tss = &per_cpu(init_tss, cpu); - struct thread_struct *thread = ¤t->thread; + struct thread_struct *thread; + struct tss_struct *tss; + int cpu; + + cpu = get_cpu(); + tss = &per_cpu(init_tss, cpu); + thread = ¤t->thread; /* * Perform the lazy TSS's I/O bitmap copy. If the TSS has an @@ -616,19 +629,21 @@ void __kprobes do_general_protection(struct pt_regs * regs, * If the previously set map was extending to higher ports * than the current one, pad extra space with 0xff (no access). */ - if (thread->io_bitmap_max < tss->io_bitmap_max) + if (thread->io_bitmap_max < tss->io_bitmap_max) { memset((char *) tss->io_bitmap + thread->io_bitmap_max, 0xff, tss->io_bitmap_max - thread->io_bitmap_max); + } tss->io_bitmap_max = thread->io_bitmap_max; tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET; tss->io_bitmap_owner = thread; put_cpu(); + return; } put_cpu(); - if (regs->flags & VM_MASK) + if (regs->flags & X86_VM_MASK) goto gp_in_vm86; if (!user_mode(regs)) @@ -636,6 +651,7 @@ void __kprobes do_general_protection(struct pt_regs * regs, current->thread.error_code = error_code; current->thread.trap_no = 13; + if (show_unhandled_signals && unhandled_signal(current, SIGSEGV) && printk_ratelimit()) { printk(KERN_INFO @@ -665,22 +681,25 @@ gp_in_kernel: } } -static __kprobes void -mem_parity_error(unsigned char reason, struct pt_regs * regs) +static notrace __kprobes void +mem_parity_error(unsigned char reason, struct pt_regs *regs) { - printk(KERN_EMERG "Uhhuh. NMI received for unknown reason %02x on " - "CPU %d.\n", reason, smp_processor_id()); - printk(KERN_EMERG "You have some hardware problem, likely on the PCI bus.\n"); + printk(KERN_EMERG + "Uhhuh. NMI received for unknown reason %02x on CPU %d.\n", + reason, smp_processor_id()); + + 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; } #endif if (panic_on_unrecovered_nmi) - panic("NMI: Not continuing"); + panic("NMI: Not continuing"); printk(KERN_EMERG "Dazed and confused, but trying to continue\n"); @@ -688,8 +707,8 @@ mem_parity_error(unsigned char reason, struct pt_regs * regs) clear_mem_error(reason); } -static __kprobes void -io_check_error(unsigned char reason, struct pt_regs * regs) +static notrace __kprobes void +io_check_error(unsigned char reason, struct pt_regs *regs) { unsigned long i; @@ -699,44 +718,52 @@ io_check_error(unsigned char reason, struct pt_regs * regs) /* Re-enable the IOCK line, wait for a few seconds */ reason = (reason & 0xf) | 8; outb(reason, 0x61); + i = 2000; - while (--i) udelay(1000); + while (--i) + udelay(1000); + reason &= ~8; outb(reason, 0x61); } -static __kprobes void -unknown_nmi_error(unsigned char reason, struct pt_regs * regs) +static notrace __kprobes void +unknown_nmi_error(unsigned char reason, struct pt_regs *regs) { + if (notify_die(DIE_NMIUNKNOWN, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP) + return; #ifdef CONFIG_MCA - /* Might actually be able to figure out what the guilty party - * is. */ - if( MCA_bus ) { + /* + * Might actually be able to figure out what the guilty party + * is: + */ + if (MCA_bus) { mca_handle_nmi(); return; } #endif - printk(KERN_EMERG "Uhhuh. NMI received for unknown reason %02x on " - "CPU %d.\n", reason, smp_processor_id()); + printk(KERN_EMERG + "Uhhuh. NMI received for unknown reason %02x on CPU %d.\n", + reason, smp_processor_id()); + printk(KERN_EMERG "Do you have a strange power saving mode enabled?\n"); if (panic_on_unrecovered_nmi) - panic("NMI: Not continuing"); + panic("NMI: Not continuing"); printk(KERN_EMERG "Dazed and confused, but trying to continue\n"); } static DEFINE_SPINLOCK(nmi_print_lock); -void __kprobes die_nmi(struct pt_regs *regs, const char *msg) +void notrace __kprobes die_nmi(struct pt_regs *regs, const char *msg) { - if (notify_die(DIE_NMIWATCHDOG, msg, regs, 0, 2, SIGINT) == - NOTIFY_STOP) + if (notify_die(DIE_NMIWATCHDOG, msg, regs, 0, 2, SIGINT) == NOTIFY_STOP) return; spin_lock(&nmi_print_lock); /* * We are in trouble anyway, lets at least try - * to get a message out. + * to get a message out: */ bust_spinlocks(1); printk(KERN_EMERG "%s", msg); @@ -747,9 +774,10 @@ void __kprobes die_nmi(struct pt_regs *regs, const char *msg) spin_unlock(&nmi_print_lock); bust_spinlocks(0); - /* If we are in kernel we are probably nested up pretty bad - * and might aswell get out now while we still can. - */ + /* + * If we are in kernel we are probably nested up pretty bad + * and might aswell get out now while we still can: + */ if (!user_mode_vm(regs)) { current->thread.trap_no = 2; crash_kexec(regs); @@ -758,14 +786,14 @@ void __kprobes die_nmi(struct pt_regs *regs, const char *msg) do_exit(SIGSEGV); } -static __kprobes void default_do_nmi(struct pt_regs * regs) +static notrace __kprobes void default_do_nmi(struct pt_regs *regs) { unsigned char reason = 0; - /* Only the BSP gets external NMIs from the system. */ + /* Only the BSP gets external NMIs from the system: */ if (!smp_processor_id()) reason = get_nmi_reason(); - + if (!(reason & 0xc0)) { if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 2, SIGINT) == NOTIFY_STOP) @@ -778,8 +806,10 @@ static __kprobes void default_do_nmi(struct pt_regs * regs) if (nmi_watchdog_tick(regs, reason)) return; if (!do_nmi_callback(regs, smp_processor_id())) -#endif unknown_nmi_error(reason, regs); +#else + unknown_nmi_error(reason, regs); +#endif return; } @@ -791,14 +821,14 @@ static __kprobes void default_do_nmi(struct pt_regs * regs) io_check_error(reason, regs); /* * Reassert NMI in case it became active meanwhile - * as it's edge-triggered. + * as it's edge-triggered: */ reassert_nmi(); } static int ignore_nmis; -__kprobes void do_nmi(struct pt_regs * regs, long error_code) +notrace __kprobes void do_nmi(struct pt_regs *regs, long error_code) { int cpu; @@ -834,9 +864,12 @@ void __kprobes do_int3(struct pt_regs *regs, long error_code) if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) == NOTIFY_STOP) return; - /* This is an interrupt gate, because kprobes wants interrupts - disabled. Normal trap handlers don't. */ + /* + * This is an interrupt gate, because kprobes wants interrupts + * disabled. Normal trap handlers don't. + */ restore_interrupts(regs); + do_trap(3, SIGTRAP, "int3", 1, regs, error_code, NULL); } #endif @@ -851,7 +884,7 @@ void __kprobes do_int3(struct pt_regs *regs, long error_code) * from user space. Such code must not hold kernel locks (since it * can equally take a page fault), therefore it is safe to call * force_sig_info even though that claims and releases locks. - * + * * Code in ./signal.c ensures that the debug control register * is restored before we deliver any signal, and therefore that * user code runs with the correct debug control register even though @@ -863,10 +896,10 @@ void __kprobes do_int3(struct pt_regs *regs, long error_code) * find every occurrence of the TF bit that could be saved away even * by user code) */ -void __kprobes do_debug(struct pt_regs * regs, long error_code) +void __kprobes do_debug(struct pt_regs *regs, long error_code) { - unsigned int condition; struct task_struct *tsk = current; + unsigned int condition; trace_hardirqs_fixup(); @@ -891,7 +924,7 @@ void __kprobes do_debug(struct pt_regs * regs, long error_code) goto clear_dr7; } - if (regs->flags & VM_MASK) + if (regs->flags & X86_VM_MASK) goto debug_vm86; /* Save debug status register where ptrace can see it */ @@ -914,7 +947,8 @@ void __kprobes do_debug(struct pt_regs * regs, long error_code) /* Ok, finally something we can handle */ send_sigtrap(tsk, regs, error_code); - /* Disable additional traps. They'll be re-enabled when + /* + * Disable additional traps. They'll be re-enabled when * the signal is delivered. */ clear_dr7: @@ -927,7 +961,7 @@ debug_vm86: clear_TF_reenable: set_tsk_thread_flag(tsk, TIF_SINGLESTEP); - regs->flags &= ~TF_MASK; + regs->flags &= ~X86_EFLAGS_TF; return; } @@ -938,9 +972,10 @@ clear_TF_reenable: */ void math_error(void __user *ip) { - struct task_struct * task; + 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. @@ -966,36 +1001,36 @@ void math_error(void __user *ip) cwd = get_fpu_cwd(task); swd = get_fpu_swd(task); switch (swd & ~cwd & 0x3f) { - case 0x000: /* No unmasked exception */ - return; - 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; + case 0x000: /* No unmasked exception */ + return; + 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); } -void do_coprocessor_error(struct pt_regs * regs, long error_code) +void do_coprocessor_error(struct pt_regs *regs, long error_code) { ignore_fpu_irq = 1; math_error((void __user *)regs->ip); @@ -1003,9 +1038,9 @@ void do_coprocessor_error(struct pt_regs * regs, long error_code) static void simd_math_error(void __user *ip) { - struct task_struct * task; - siginfo_t info; + struct task_struct *task; unsigned short mxcsr; + siginfo_t info; /* * Save the info for the exception handler and clear the error. @@ -1026,82 +1061,80 @@ static void simd_math_error(void __user *ip) */ 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); } -void do_simd_coprocessor_error(struct pt_regs * regs, - long error_code) +void do_simd_coprocessor_error(struct pt_regs *regs, long error_code) { if (cpu_has_xmm) { /* Handle SIMD FPU exceptions on PIII+ processors. */ ignore_fpu_irq = 1; simd_math_error((void __user *)regs->ip); - } else { - /* - * Handle strange cache flush from user space exception - * in all other cases. This is undocumented behaviour. - */ - if (regs->flags & VM_MASK) { - handle_vm86_fault((struct kernel_vm86_regs *)regs, - error_code); - return; - } - current->thread.trap_no = 19; - current->thread.error_code = error_code; - die_if_kernel("cache flush denied", regs, error_code); - force_sig(SIGSEGV, current); + return; } + /* + * Handle strange cache flush from user space exception + * in all other cases. This is undocumented behaviour. + */ + if (regs->flags & X86_VM_MASK) { + handle_vm86_fault((struct kernel_vm86_regs *)regs, error_code); + return; + } + current->thread.trap_no = 19; + current->thread.error_code = error_code; + die_if_kernel("cache flush denied", regs, error_code); + force_sig(SIGSEGV, current); } -void do_spurious_interrupt_bug(struct pt_regs * regs, - long error_code) +void do_spurious_interrupt_bug(struct pt_regs *regs, long error_code) { #if 0 /* No need to warn about this any longer. */ - printk("Ignoring P6 Local APIC Spurious Interrupt Bug...\n"); + printk(KERN_INFO "Ignoring P6 Local APIC Spurious Interrupt Bug...\n"); #endif } -unsigned long patch_espfix_desc(unsigned long uesp, - unsigned long kesp) +unsigned long patch_espfix_desc(unsigned long uesp, unsigned long kesp) { struct desc_struct *gdt = __get_cpu_var(gdt_page).gdt; unsigned long base = (kesp - uesp) & -THREAD_SIZE; unsigned long new_kesp = kesp - base; unsigned long lim_pages = (new_kesp | (THREAD_SIZE - 1)) >> PAGE_SHIFT; __u64 desc = *(__u64 *)&gdt[GDT_ENTRY_ESPFIX_SS]; + /* Set up base for espfix segment */ - desc &= 0x00f0ff0000000000ULL; - desc |= ((((__u64)base) << 16) & 0x000000ffffff0000ULL) | + desc &= 0x00f0ff0000000000ULL; + desc |= ((((__u64)base) << 16) & 0x000000ffffff0000ULL) | ((((__u64)base) << 32) & 0xff00000000000000ULL) | ((((__u64)lim_pages) << 32) & 0x000f000000000000ULL) | (lim_pages & 0xffff); *(__u64 *)&gdt[GDT_ENTRY_ESPFIX_SS] = desc; + return new_kesp; } /* - * '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. @@ -1115,9 +1148,22 @@ asmlinkage void math_state_restore(void) struct thread_info *thread = current_thread_info(); struct task_struct *tsk = thread->task; - clts(); /* Allow maths ops (or we recurse) */ - if (!tsk_used_math(tsk)) - init_fpu(tsk); + if (!tsk_used_math(tsk)) { + local_irq_enable(); + /* + * does a slab alloc which can sleep + */ + if (init_fpu(tsk)) { + /* + * ran out of memory! + */ + do_group_exit(SIGKILL); + return; + } + local_irq_disable(); + } + + clts(); /* Allow maths ops (or we recurse) */ restore_fpu(tsk); thread->status |= TS_USEDFPU; /* So we fnsave on switch_to() */ tsk->fpu_counter++; @@ -1128,80 +1174,76 @@ EXPORT_SYMBOL_GPL(math_state_restore); asmlinkage void math_emulate(long arg) { - printk(KERN_EMERG "math-emulation not enabled and no coprocessor found.\n"); - printk(KERN_EMERG "killing %s.\n",current->comm); - force_sig(SIGFPE,current); + printk(KERN_EMERG + "math-emulation not enabled and no coprocessor found.\n"); + printk(KERN_EMERG "killing %s.\n", current->comm); + force_sig(SIGFPE, current); schedule(); } #endif /* CONFIG_MATH_EMULATION */ - void __init trap_init(void) { int i; #ifdef CONFIG_EISA void __iomem *p = early_ioremap(0x0FFFD9, 4); - if (readl(p) == 'E'+('I'<<8)+('S'<<16)+('A'<<24)) { + + if (readl(p) == 'E' + ('I'<<8) + ('S'<<16) + ('A'<<24)) EISA_bus = 1; - } 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_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(10,&invalid_TSS); - set_trap_gate(11,&segment_not_present); - set_trap_gate(12,&stack_segment); - set_trap_gate(13,&general_protection); - set_intr_gate(14,&page_fault); - set_trap_gate(15,&spurious_interrupt_bug); - set_trap_gate(16,&coprocessor_error); - set_trap_gate(17,&alignment_check); + 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(10, &invalid_TSS); + set_trap_gate(11, &segment_not_present); + set_trap_gate(12, &stack_segment); + set_trap_gate(13, &general_protection); + set_intr_gate(14, &page_fault); + set_trap_gate(15, &spurious_interrupt_bug); + set_trap_gate(16, &coprocessor_error); + set_trap_gate(17, &alignment_check); #ifdef CONFIG_X86_MCE - set_trap_gate(18,&machine_check); + set_trap_gate(18, &machine_check); #endif - set_trap_gate(19,&simd_coprocessor_error); + set_trap_gate(19, &simd_coprocessor_error); - /* - * Verify that the FXSAVE/FXRSTOR data will be 16-byte aligned. - * Generate a build-time error if the alignment is wrong. - */ - BUILD_BUG_ON(offsetof(struct task_struct, thread.i387.fxsave) & 15); if (cpu_has_fxsr) { printk(KERN_INFO "Enabling fast FPU save and restore... "); set_in_cr4(X86_CR4_OSFXSR); printk("done.\n"); } if (cpu_has_xmm) { - printk(KERN_INFO "Enabling unmasked SIMD FPU exception " - "support... "); + printk(KERN_INFO + "Enabling unmasked SIMD FPU exception support... "); set_in_cr4(X86_CR4_OSXMMEXCPT); printk("done.\n"); } - set_system_gate(SYSCALL_VECTOR,&system_call); + set_system_gate(SYSCALL_VECTOR, &system_call); - /* Reserve all the builtin and the syscall vector. */ + /* Reserve all the builtin and the syscall vector: */ for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++) set_bit(i, used_vectors); + set_bit(SYSCALL_VECTOR, used_vectors); + init_thread_xstate(); /* - * Should be a barrier for any external CPU state. + * Should be a barrier for any external CPU state: */ cpu_init(); @@ -1211,6 +1253,7 @@ void __init trap_init(void) static int __init kstack_setup(char *s) { kstack_depth_to_print = simple_strtoul(s, NULL, 0); + return 1; } __setup("kstack=", kstack_setup); diff --git a/arch/x86/kernel/traps_64.c b/arch/x86/kernel/traps_64.c index 045466681911..adff76ea97c4 100644 --- a/arch/x86/kernel/traps_64.c +++ b/arch/x86/kernel/traps_64.c @@ -33,6 +33,8 @@ #include <linux/kdebug.h> #include <linux/utsname.h> +#include <mach_traps.h> + #if defined(CONFIG_EDAC) #include <linux/edac.h> #endif @@ -598,10 +600,16 @@ void die(const char * str, struct pt_regs * regs, long err) oops_end(flags, regs, SIGSEGV); } -void __kprobes die_nmi(char *str, struct pt_regs *regs, int do_panic) +notrace __kprobes void +die_nmi(char *str, struct pt_regs *regs, int do_panic) { - unsigned long flags = oops_begin(); + unsigned long flags; + + if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == + NOTIFY_STOP) + return; + flags = oops_begin(); /* * We are in trouble anyway, lets at least try * to get a message out. @@ -765,7 +773,7 @@ asmlinkage void __kprobes do_general_protection(struct pt_regs * regs, die("general protection fault", regs, error_code); } -static __kprobes void +static notrace __kprobes void mem_parity_error(unsigned char reason, struct pt_regs * regs) { printk(KERN_EMERG "Uhhuh. NMI received for unknown reason %02x.\n", @@ -789,7 +797,7 @@ mem_parity_error(unsigned char reason, struct pt_regs * regs) outb(reason, 0x61); } -static __kprobes void +static notrace __kprobes void io_check_error(unsigned char reason, struct pt_regs * regs) { printk("NMI: IOCK error (debug interrupt?)\n"); @@ -803,9 +811,11 @@ io_check_error(unsigned char reason, struct pt_regs * regs) outb(reason, 0x61); } -static __kprobes void +static notrace __kprobes void unknown_nmi_error(unsigned char reason, struct pt_regs * regs) { + if (notify_die(DIE_NMIUNKNOWN, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP) + return; printk(KERN_EMERG "Uhhuh. NMI received for unknown reason %02x.\n", reason); printk(KERN_EMERG "Do you have a strange power saving mode enabled?\n"); @@ -818,7 +828,7 @@ 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 __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; @@ -1114,11 +1124,24 @@ asmlinkage void __attribute__((weak)) mce_threshold_interrupt(void) asmlinkage void math_state_restore(void) { struct task_struct *me = current; - clts(); /* Allow maths ops (or we recurse) */ - if (!used_math()) - init_fpu(me); - restore_fpu_checking(&me->thread.i387.fxsave); + if (!used_math()) { + local_irq_enable(); + /* + * does a slab alloc which can sleep + */ + if (init_fpu(me)) { + /* + * ran out of memory! + */ + do_group_exit(SIGKILL); + return; + } + local_irq_disable(); + } + + clts(); /* Allow maths ops (or we recurse) */ + restore_fpu_checking(&me->thread.xstate->fxsave); task_thread_info(me)->status |= TS_USEDFPU; me->fpu_counter++; } @@ -1154,6 +1177,10 @@ void __init trap_init(void) #endif /* + * initialize the per thread extended state: + */ + init_thread_xstate(); + /* * Should be a barrier for any external CPU state. */ cpu_init(); diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c index c2241e04ea5f..e4790728b224 100644 --- a/arch/x86/kernel/tsc_32.c +++ b/arch/x86/kernel/tsc_32.c @@ -84,8 +84,8 @@ DEFINE_PER_CPU(unsigned long, cyc2ns); static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) { - unsigned long flags, prev_scale, *scale; unsigned long long tsc_now, ns_now; + unsigned long flags, *scale; local_irq_save(flags); sched_clock_idle_sleep_event(); @@ -95,7 +95,6 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) rdtscll(tsc_now); ns_now = __cycles_2_ns(tsc_now); - prev_scale = *scale; if (cpu_khz) *scale = (NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR)/cpu_khz; @@ -222,9 +221,9 @@ EXPORT_SYMBOL(recalibrate_cpu_khz); * 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 = 0; -static unsigned long loops_per_jiffy_ref = 0; -static unsigned long cpu_khz_ref = 0; +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) @@ -284,15 +283,28 @@ core_initcall(cpufreq_tsc); /* clock source code */ -static unsigned long current_tsc_khz = 0; +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; + return ret >= clocksource_tsc.cycle_last ? + ret : clocksource_tsc.cycle_last; } static struct clocksource clocksource_tsc = { @@ -392,13 +404,15 @@ void __init tsc_init(void) int cpu; if (!cpu_has_tsc) - goto out_no_tsc; + return; cpu_khz = calculate_cpu_khz(); tsc_khz = cpu_khz; - if (!cpu_khz) - goto out_no_tsc; + if (!cpu_khz) { + mark_tsc_unstable("could not calculate TSC khz"); + return; + } printk("Detected %lu.%03lu MHz processor.\n", (unsigned long)cpu_khz / 1000, @@ -431,9 +445,4 @@ void __init tsc_init(void) tsc_enabled = 1; clocksource_register(&clocksource_tsc); - - return; - -out_no_tsc: - setup_clear_cpu_cap(X86_FEATURE_TSC); } diff --git a/arch/x86/kernel/tsc_64.c b/arch/x86/kernel/tsc_64.c index d3bebaaad842..fcc16e58609e 100644 --- a/arch/x86/kernel/tsc_64.c +++ b/arch/x86/kernel/tsc_64.c @@ -11,6 +11,7 @@ #include <asm/hpet.h> #include <asm/timex.h> #include <asm/timer.h> +#include <asm/vgtod.h> static int notsc __initdata = 0; @@ -44,8 +45,8 @@ DEFINE_PER_CPU(unsigned long, cyc2ns); static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) { - unsigned long flags, prev_scale, *scale; unsigned long long tsc_now, ns_now; + unsigned long flags, *scale; local_irq_save(flags); sched_clock_idle_sleep_event(); @@ -55,7 +56,6 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) rdtscll(tsc_now); ns_now = __cycles_2_ns(tsc_now); - prev_scale = *scale; if (cpu_khz) *scale = (NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR)/cpu_khz; @@ -288,18 +288,34 @@ int __init notsc_setup(char *s) __setup("notsc", notsc_setup); +static struct clocksource clocksource_tsc; -/* clock source code: */ +/* + * 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; + + 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; + + return ret >= __vsyscall_gtod_data.clock.cycle_last ? + ret : __vsyscall_gtod_data.clock.cycle_last; } static struct clocksource clocksource_tsc = { diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 738c2104df30..38f566fa27d2 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -64,7 +64,7 @@ #define KVM86 ((struct kernel_vm86_struct *)regs) -#define VMPI KVM86->vm86plus +#define VMPI KVM86->vm86plus /* @@ -81,7 +81,7 @@ #define VFLAGS (*(unsigned short *)&(current->thread.v86flags)) #define VEFLAGS (current->thread.v86flags) -#define set_flags(X,new,mask) \ +#define set_flags(X, new, mask) \ ((X) = ((X) & ~(mask)) | ((new) & (mask))) #define SAFE_MASK (0xDD5) @@ -93,8 +93,10 @@ static int copy_vm86_regs_to_user(struct vm86_regs __user *user, { int ret = 0; - /* kernel_vm86_regs is missing gs, so copy everything up to - (but not including) orig_eax, and then rest including orig_eax. */ + /* + * kernel_vm86_regs is missing gs, so copy everything up to + * (but not including) orig_eax, and then rest including orig_eax. + */ ret += copy_to_user(user, regs, offsetof(struct kernel_vm86_regs, pt.orig_ax)); ret += copy_to_user(&user->orig_eax, ®s->pt.orig_ax, sizeof(struct kernel_vm86_regs) - @@ -120,7 +122,7 @@ static int copy_vm86_regs_from_user(struct kernel_vm86_regs *regs, return ret; } -struct pt_regs * save_v86_state(struct kernel_vm86_regs * regs) +struct pt_regs *save_v86_state(struct kernel_vm86_regs *regs) { struct tss_struct *tss; struct pt_regs *ret; @@ -137,9 +139,9 @@ struct pt_regs * save_v86_state(struct kernel_vm86_regs * regs) printk("no vm86_info: BAD\n"); do_exit(SIGSEGV); } - set_flags(regs->pt.flags, VEFLAGS, VIF_MASK | current->thread.v86mask); - tmp = copy_vm86_regs_to_user(¤t->thread.vm86_info->regs,regs); - tmp += put_user(current->thread.screen_bitmap,¤t->thread.vm86_info->screen_bitmap); + set_flags(regs->pt.flags, VEFLAGS, X86_EFLAGS_VIF | current->thread.v86mask); + tmp = copy_vm86_regs_to_user(¤t->thread.vm86_info->regs, regs); + tmp += put_user(current->thread.screen_bitmap, ¤t->thread.vm86_info->screen_bitmap); if (tmp) { printk("vm86: could not access userspace vm86_info\n"); do_exit(SIGSEGV); @@ -237,20 +239,21 @@ asmlinkage int sys_vm86(struct pt_regs regs) tsk = current; switch (regs.bx) { - case VM86_REQUEST_IRQ: - case VM86_FREE_IRQ: - case VM86_GET_IRQ_BITS: - case VM86_GET_AND_RESET_IRQ: - ret = do_vm86_irq_handling(regs.bx, (int)regs.cx); - goto out; - case VM86_PLUS_INSTALL_CHECK: - /* NOTE: on old vm86 stuff this will return the error - from access_ok(), because the subfunction is - interpreted as (invalid) address to vm86_struct. - So the installation check works. - */ - ret = 0; - goto out; + case VM86_REQUEST_IRQ: + case VM86_FREE_IRQ: + case VM86_GET_IRQ_BITS: + case VM86_GET_AND_RESET_IRQ: + ret = do_vm86_irq_handling(regs.bx, (int)regs.cx); + goto out; + case VM86_PLUS_INSTALL_CHECK: + /* + * NOTE: on old vm86 stuff this will return the error + * from access_ok(), because the subfunction is + * interpreted as (invalid) address to vm86_struct. + * So the installation check works. + */ + ret = 0; + goto out; } /* we come here only for functions VM86_ENTER, VM86_ENTER_NO_BYPASS */ @@ -296,21 +299,21 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk VEFLAGS = info->regs.pt.flags; info->regs.pt.flags &= SAFE_MASK; info->regs.pt.flags |= info->regs32->flags & ~SAFE_MASK; - info->regs.pt.flags |= VM_MASK; + info->regs.pt.flags |= X86_VM_MASK; switch (info->cpu_type) { - case CPU_286: - tsk->thread.v86mask = 0; - break; - case CPU_386: - tsk->thread.v86mask = NT_MASK | IOPL_MASK; - break; - case CPU_486: - tsk->thread.v86mask = AC_MASK | NT_MASK | IOPL_MASK; - break; - default: - tsk->thread.v86mask = ID_MASK | AC_MASK | NT_MASK | IOPL_MASK; - break; + case CPU_286: + tsk->thread.v86mask = 0; + break; + case CPU_386: + tsk->thread.v86mask = X86_EFLAGS_NT | X86_EFLAGS_IOPL; + break; + case CPU_486: + tsk->thread.v86mask = X86_EFLAGS_AC | X86_EFLAGS_NT | X86_EFLAGS_IOPL; + break; + default: + tsk->thread.v86mask = X86_EFLAGS_ID | X86_EFLAGS_AC | X86_EFLAGS_NT | X86_EFLAGS_IOPL; + break; } /* @@ -346,9 +349,9 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk /* we never return here */ } -static inline void return_to_32bit(struct kernel_vm86_regs * regs16, int retval) +static inline void return_to_32bit(struct kernel_vm86_regs *regs16, int retval) { - struct pt_regs * regs32; + struct pt_regs *regs32; regs32 = save_v86_state(regs16); regs32->ax = retval; @@ -358,29 +361,30 @@ static inline void return_to_32bit(struct kernel_vm86_regs * regs16, int retval) : : "r" (regs32), "r" (current_thread_info())); } -static inline void set_IF(struct kernel_vm86_regs * regs) +static inline void set_IF(struct kernel_vm86_regs *regs) { - VEFLAGS |= VIF_MASK; - if (VEFLAGS & VIP_MASK) + VEFLAGS |= X86_EFLAGS_VIF; + if (VEFLAGS & X86_EFLAGS_VIP) return_to_32bit(regs, VM86_STI); } -static inline void clear_IF(struct kernel_vm86_regs * regs) +static inline void clear_IF(struct kernel_vm86_regs *regs) { - VEFLAGS &= ~VIF_MASK; + VEFLAGS &= ~X86_EFLAGS_VIF; } -static inline void clear_TF(struct kernel_vm86_regs * regs) +static inline void clear_TF(struct kernel_vm86_regs *regs) { - regs->pt.flags &= ~TF_MASK; + regs->pt.flags &= ~X86_EFLAGS_TF; } -static inline void clear_AC(struct kernel_vm86_regs * regs) +static inline void clear_AC(struct kernel_vm86_regs *regs) { - regs->pt.flags &= ~AC_MASK; + regs->pt.flags &= ~X86_EFLAGS_AC; } -/* It is correct to call set_IF(regs) from the set_vflags_* +/* + * It is correct to call set_IF(regs) from the set_vflags_* * functions. However someone forgot to call clear_IF(regs) * in the opposite case. * After the command sequence CLI PUSHF STI POPF you should @@ -391,41 +395,41 @@ static inline void clear_AC(struct kernel_vm86_regs * regs) * [KD] */ -static inline void set_vflags_long(unsigned long flags, struct kernel_vm86_regs * regs) +static inline void set_vflags_long(unsigned long flags, struct kernel_vm86_regs *regs) { set_flags(VEFLAGS, flags, current->thread.v86mask); set_flags(regs->pt.flags, flags, SAFE_MASK); - if (flags & IF_MASK) + if (flags & X86_EFLAGS_IF) set_IF(regs); else clear_IF(regs); } -static inline void set_vflags_short(unsigned short flags, struct kernel_vm86_regs * regs) +static inline void set_vflags_short(unsigned short flags, struct kernel_vm86_regs *regs) { set_flags(VFLAGS, flags, current->thread.v86mask); set_flags(regs->pt.flags, flags, SAFE_MASK); - if (flags & IF_MASK) + if (flags & X86_EFLAGS_IF) set_IF(regs); else clear_IF(regs); } -static inline unsigned long get_vflags(struct kernel_vm86_regs * regs) +static inline unsigned long get_vflags(struct kernel_vm86_regs *regs) { unsigned long flags = regs->pt.flags & RETURN_MASK; - if (VEFLAGS & VIF_MASK) - flags |= IF_MASK; - flags |= IOPL_MASK; + if (VEFLAGS & X86_EFLAGS_VIF) + flags |= X86_EFLAGS_IF; + flags |= X86_EFLAGS_IOPL; return flags | (VEFLAGS & current->thread.v86mask); } -static inline int is_revectored(int nr, struct revectored_struct * bitmap) +static inline int is_revectored(int nr, struct revectored_struct *bitmap) { __asm__ __volatile__("btl %2,%1\n\tsbbl %0,%0" :"=r" (nr) - :"m" (*bitmap),"r" (nr)); + :"m" (*bitmap), "r" (nr)); return nr; } @@ -437,7 +441,7 @@ static inline int is_revectored(int nr, struct revectored_struct * bitmap) ptr--; \ if (put_user(__val, base + ptr) < 0) \ goto err_label; \ - } while(0) + } while (0) #define pushw(base, ptr, val, err_label) \ do { \ @@ -448,7 +452,7 @@ static inline int is_revectored(int nr, struct revectored_struct * bitmap) ptr--; \ if (put_user(val_byte(__val, 0), base + ptr) < 0) \ goto err_label; \ - } while(0) + } while (0) #define pushl(base, ptr, val, err_label) \ do { \ @@ -465,7 +469,7 @@ static inline int is_revectored(int nr, struct revectored_struct * bitmap) ptr--; \ if (put_user(val_byte(__val, 0), base + ptr) < 0) \ goto err_label; \ - } while(0) + } while (0) #define popb(base, ptr, err_label) \ ({ \ @@ -512,7 +516,7 @@ static inline int is_revectored(int nr, struct revectored_struct * bitmap) * in userspace is always better than an Oops anyway.) [KD] */ static void do_int(struct kernel_vm86_regs *regs, int i, - unsigned char __user * ssp, unsigned short sp) + unsigned char __user *ssp, unsigned short sp) { unsigned long __user *intr_ptr; unsigned long segoffs; @@ -521,7 +525,7 @@ static void do_int(struct kernel_vm86_regs *regs, int i, goto cannot_handle; if (is_revectored(i, &KVM86->int_revectored)) goto cannot_handle; - if (i==0x21 && is_revectored(AH(regs),&KVM86->int21_revectored)) + if (i == 0x21 && is_revectored(AH(regs), &KVM86->int21_revectored)) goto cannot_handle; intr_ptr = (unsigned long __user *) (i << 2); if (get_user(segoffs, intr_ptr)) @@ -543,30 +547,23 @@ cannot_handle: return_to_32bit(regs, VM86_INTx + (i << 8)); } -int handle_vm86_trap(struct kernel_vm86_regs * regs, long error_code, int trapno) +int handle_vm86_trap(struct kernel_vm86_regs *regs, long error_code, int trapno) { if (VMPI.is_vm86pus) { - if ( (trapno==3) || (trapno==1) ) + if ((trapno == 3) || (trapno == 1)) return_to_32bit(regs, VM86_TRAP + (trapno << 8)); do_int(regs, trapno, (unsigned char __user *) (regs->pt.ss << 4), SP(regs)); return 0; } - if (trapno !=1) + if (trapno != 1) return 1; /* we let this handle by the calling routine */ - if (current->ptrace & PT_PTRACED) { - unsigned long flags; - spin_lock_irqsave(¤t->sighand->siglock, flags); - sigdelset(¤t->blocked, SIGTRAP); - recalc_sigpending(); - spin_unlock_irqrestore(¤t->sighand->siglock, flags); - } - send_sig(SIGTRAP, current, 1); current->thread.trap_no = trapno; current->thread.error_code = error_code; + force_sig(SIGTRAP, current); return 0; } -void handle_vm86_fault(struct kernel_vm86_regs * regs, long error_code) +void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code) { unsigned char opcode; unsigned char __user *csp; @@ -576,11 +573,11 @@ void handle_vm86_fault(struct kernel_vm86_regs * regs, long error_code) #define CHECK_IF_IN_TRAP \ if (VMPI.vm86dbg_active && VMPI.vm86dbg_TFpendig) \ - newflags |= TF_MASK + newflags |= X86_EFLAGS_TF #define VM86_FAULT_RETURN do { \ - if (VMPI.force_return_for_pic && (VEFLAGS & (IF_MASK | VIF_MASK))) \ + if (VMPI.force_return_for_pic && (VEFLAGS & (X86_EFLAGS_IF | X86_EFLAGS_VIF))) \ return_to_32bit(regs, VM86_PICRETURN); \ - if (orig_flags & TF_MASK) \ + if (orig_flags & X86_EFLAGS_TF) \ handle_vm86_trap(regs, 0, 1); \ return; } while (0) @@ -595,17 +592,17 @@ void handle_vm86_fault(struct kernel_vm86_regs * regs, long error_code) pref_done = 0; do { switch (opcode = popb(csp, ip, simulate_sigsegv)) { - case 0x66: /* 32-bit data */ data32=1; break; - case 0x67: /* 32-bit address */ break; - case 0x2e: /* CS */ break; - case 0x3e: /* DS */ break; - case 0x26: /* ES */ break; - case 0x36: /* SS */ break; - case 0x65: /* GS */ break; - case 0x64: /* FS */ break; - case 0xf2: /* repnz */ break; - case 0xf3: /* rep */ break; - default: pref_done = 1; + case 0x66: /* 32-bit data */ data32 = 1; break; + case 0x67: /* 32-bit address */ break; + case 0x2e: /* CS */ break; + case 0x3e: /* DS */ break; + case 0x26: /* ES */ break; + case 0x36: /* SS */ break; + case 0x65: /* GS */ break; + case 0x64: /* FS */ break; + case 0xf2: /* repnz */ break; + case 0xf3: /* rep */ break; + default: pref_done = 1; } } while (!pref_done); @@ -628,7 +625,7 @@ void handle_vm86_fault(struct kernel_vm86_regs * regs, long error_code) { unsigned long newflags; if (data32) { - newflags=popl(ssp, sp, simulate_sigsegv); + newflags = popl(ssp, sp, simulate_sigsegv); SP(regs) += 4; } else { newflags = popw(ssp, sp, simulate_sigsegv); @@ -636,20 +633,20 @@ void handle_vm86_fault(struct kernel_vm86_regs * regs, long error_code) } IP(regs) = ip; CHECK_IF_IN_TRAP; - if (data32) { + if (data32) set_vflags_long(newflags, regs); - } else { + else set_vflags_short(newflags, regs); - } + VM86_FAULT_RETURN; } /* int xx */ case 0xcd: { - int intno=popb(csp, ip, simulate_sigsegv); + int intno = popb(csp, ip, simulate_sigsegv); IP(regs) = ip; if (VMPI.vm86dbg_active) { - if ( (1 << (intno &7)) & VMPI.vm86dbg_intxxtab[intno >> 3] ) + if ((1 << (intno & 7)) & VMPI.vm86dbg_intxxtab[intno >> 3]) return_to_32bit(regs, VM86_INTx + (intno << 8)); } do_int(regs, intno, ssp, sp); @@ -663,9 +660,9 @@ void handle_vm86_fault(struct kernel_vm86_regs * regs, long error_code) unsigned long newcs; unsigned long newflags; if (data32) { - newip=popl(ssp, sp, simulate_sigsegv); - newcs=popl(ssp, sp, simulate_sigsegv); - newflags=popl(ssp, sp, simulate_sigsegv); + newip = popl(ssp, sp, simulate_sigsegv); + newcs = popl(ssp, sp, simulate_sigsegv); + newflags = popl(ssp, sp, simulate_sigsegv); SP(regs) += 12; } else { newip = popw(ssp, sp, simulate_sigsegv); @@ -734,18 +731,18 @@ static struct vm86_irqs { static DEFINE_SPINLOCK(irqbits_lock); static int irqbits; -#define ALLOWED_SIGS ( 1 /* 0 = don't send a signal */ \ +#define ALLOWED_SIGS (1 /* 0 = don't send a signal */ \ | (1 << SIGUSR1) | (1 << SIGUSR2) | (1 << SIGIO) | (1 << SIGURG) \ - | (1 << SIGUNUSED) ) - + | (1 << SIGUNUSED)) + static irqreturn_t irq_handler(int intno, void *dev_id) { int irq_bit; unsigned long flags; - spin_lock_irqsave(&irqbits_lock, flags); + spin_lock_irqsave(&irqbits_lock, flags); irq_bit = 1 << intno; - if ((irqbits & irq_bit) || ! vm86_irqs[intno].tsk) + if ((irqbits & irq_bit) || !vm86_irqs[intno].tsk) goto out; irqbits |= irq_bit; if (vm86_irqs[intno].sig) @@ -759,7 +756,7 @@ static irqreturn_t irq_handler(int intno, void *dev_id) return IRQ_HANDLED; out: - spin_unlock_irqrestore(&irqbits_lock, flags); + spin_unlock_irqrestore(&irqbits_lock, flags); return IRQ_NONE; } @@ -770,9 +767,9 @@ static inline void free_vm86_irq(int irqnumber) free_irq(irqnumber, NULL); vm86_irqs[irqnumber].tsk = NULL; - spin_lock_irqsave(&irqbits_lock, flags); + spin_lock_irqsave(&irqbits_lock, flags); irqbits &= ~(1 << irqnumber); - spin_unlock_irqrestore(&irqbits_lock, flags); + spin_unlock_irqrestore(&irqbits_lock, flags); } void release_vm86_irqs(struct task_struct *task) @@ -788,10 +785,10 @@ static inline int get_and_reset_irq(int irqnumber) int bit; unsigned long flags; int ret = 0; - + if (invalid_vm86_irq(irqnumber)) return 0; if (vm86_irqs[irqnumber].tsk != current) return 0; - spin_lock_irqsave(&irqbits_lock, flags); + spin_lock_irqsave(&irqbits_lock, flags); bit = irqbits & (1 << irqnumber); irqbits &= ~bit; if (bit) { @@ -799,7 +796,7 @@ static inline int get_and_reset_irq(int irqnumber) ret = 1; } - spin_unlock_irqrestore(&irqbits_lock, flags); + spin_unlock_irqrestore(&irqbits_lock, flags); return ret; } diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c index 12affe1f9bce..956f38927aa7 100644 --- a/arch/x86/kernel/vmi_32.c +++ b/arch/x86/kernel/vmi_32.c @@ -320,7 +320,7 @@ static void check_zeroed_page(u32 pfn, int type, struct page *page) * pdes need to be zeroed. */ if (type & VMI_PAGE_CLONE) - limit = USER_PTRS_PER_PGD; + limit = KERNEL_PGD_BOUNDARY; for (i = 0; i < limit; i++) BUG_ON(ptr[i]); } @@ -392,13 +392,13 @@ static void *vmi_kmap_atomic_pte(struct page *page, enum km_type type) } #endif -static void vmi_allocate_pt(struct mm_struct *mm, u32 pfn) +static void vmi_allocate_pte(struct mm_struct *mm, u32 pfn) { vmi_set_page_type(pfn, VMI_PAGE_L1); vmi_ops.allocate_page(pfn, VMI_PAGE_L1, 0, 0, 0); } -static void vmi_allocate_pd(struct mm_struct *mm, u32 pfn) +static void vmi_allocate_pmd(struct mm_struct *mm, u32 pfn) { /* * This call comes in very early, before mem_map is setup. @@ -409,20 +409,20 @@ static void vmi_allocate_pd(struct mm_struct *mm, u32 pfn) vmi_ops.allocate_page(pfn, VMI_PAGE_L2, 0, 0, 0); } -static void vmi_allocate_pd_clone(u32 pfn, u32 clonepfn, u32 start, u32 count) +static void vmi_allocate_pmd_clone(u32 pfn, u32 clonepfn, u32 start, u32 count) { vmi_set_page_type(pfn, VMI_PAGE_L2 | VMI_PAGE_CLONE); vmi_check_page_type(clonepfn, VMI_PAGE_L2); vmi_ops.allocate_page(pfn, VMI_PAGE_L2 | VMI_PAGE_CLONE, clonepfn, start, count); } -static void vmi_release_pt(u32 pfn) +static void vmi_release_pte(u32 pfn) { vmi_ops.release_page(pfn, VMI_PAGE_L1); vmi_set_page_type(pfn, VMI_PAGE_NORMAL); } -static void vmi_release_pd(u32 pfn) +static void vmi_release_pmd(u32 pfn) { vmi_ops.release_page(pfn, VMI_PAGE_L2); vmi_set_page_type(pfn, VMI_PAGE_NORMAL); @@ -871,15 +871,15 @@ static inline int __init activate_vmi(void) vmi_ops.allocate_page = vmi_get_function(VMI_CALL_AllocatePage); if (vmi_ops.allocate_page) { - pv_mmu_ops.alloc_pt = vmi_allocate_pt; - pv_mmu_ops.alloc_pd = vmi_allocate_pd; - pv_mmu_ops.alloc_pd_clone = vmi_allocate_pd_clone; + pv_mmu_ops.alloc_pte = vmi_allocate_pte; + pv_mmu_ops.alloc_pmd = vmi_allocate_pmd; + pv_mmu_ops.alloc_pmd_clone = vmi_allocate_pmd_clone; } vmi_ops.release_page = vmi_get_function(VMI_CALL_ReleasePage); if (vmi_ops.release_page) { - pv_mmu_ops.release_pt = vmi_release_pt; - pv_mmu_ops.release_pd = vmi_release_pd; + pv_mmu_ops.release_pte = vmi_release_pte; + pv_mmu_ops.release_pmd = vmi_release_pmd; } /* Set linear is needed in all cases */ diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S index 2ffa9656fe7a..ce5ed083a1e9 100644 --- a/arch/x86/kernel/vmlinux_32.lds.S +++ b/arch/x86/kernel/vmlinux_32.lds.S @@ -149,6 +149,11 @@ SECTIONS *(.con_initcall.init) __con_initcall_end = .; } + .x86cpuvendor.init : AT(ADDR(.x86cpuvendor.init) - LOAD_OFFSET) { + __x86cpuvendor_start = .; + *(.x86cpuvendor.init) + __x86cpuvendor_end = .; + } SECURITY_INIT . = ALIGN(4); .altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) { diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S index fab132299735..fad3674b06a5 100644 --- a/arch/x86/kernel/vmlinux_64.lds.S +++ b/arch/x86/kernel/vmlinux_64.lds.S @@ -177,6 +177,11 @@ SECTIONS *(.con_initcall.init) } __con_initcall_end = .; + __x86cpuvendor_start = .; + .x86cpuvendor.init : AT(ADDR(.x86cpuvendor.init) - LOAD_OFFSET) { + *(.x86cpuvendor.init) + } + __x86cpuvendor_end = .; SECURITY_INIT . = ALIGN(8); @@ -204,12 +209,6 @@ SECTIONS EXIT_DATA } -/* vdso blob that is mapped into user space */ - vdso_start = . ; - .vdso : AT(ADDR(.vdso) - LOAD_OFFSET) { *(.vdso) } - . = ALIGN(PAGE_SIZE); - vdso_end = .; - #ifdef CONFIG_BLK_DEV_INITRD . = ALIGN(PAGE_SIZE); __initramfs_start = .; @@ -247,3 +246,9 @@ SECTIONS DWARF_DEBUG } + +/* + * Build-time check on the image size: + */ +ASSERT((_end - _text <= KERNEL_IMAGE_SIZE), + "kernel image bigger than KERNEL_IMAGE_SIZE") diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index d971210a6d36..ba8c0b75ab0a 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -8,6 +8,8 @@ * * Ravikiran Thirumalai <kiran@scalemp.com>, * Shai Fultheim <shai@scalemp.com> + * Paravirt ops integration: Glauber de Oliveira Costa <gcosta@redhat.com>, + * Ravikiran Thirumalai <kiran@scalemp.com> */ #include <linux/init.h> @@ -15,38 +17,137 @@ #include <linux/pci_regs.h> #include <asm/pci-direct.h> #include <asm/io.h> +#include <asm/paravirt.h> -static int __init vsmp_init(void) +#if defined CONFIG_PCI && defined CONFIG_PARAVIRT +/* + * Interrupt control on vSMPowered systems: + * ~AC is a shadow of IF. If IF is 'on' AC should be 'off' + * and vice versa. + */ + +static unsigned long vsmp_save_fl(void) { - void *address; - unsigned int cap, ctl; + unsigned long flags = native_save_fl(); - if (!early_pci_allowed()) - return 0; + if (!(flags & X86_EFLAGS_IF) || (flags & X86_EFLAGS_AC)) + flags &= ~X86_EFLAGS_IF; + return flags; +} - /* Check if we are running on a ScaleMP vSMP box */ - if ((read_pci_config_16(0, 0x1f, 0, PCI_VENDOR_ID) != - PCI_VENDOR_ID_SCALEMP) || - (read_pci_config_16(0, 0x1f, 0, PCI_DEVICE_ID) != - PCI_DEVICE_ID_SCALEMP_VSMP_CTL)) - return 0; +static void vsmp_restore_fl(unsigned long flags) +{ + if (flags & X86_EFLAGS_IF) + flags &= ~X86_EFLAGS_AC; + else + flags |= X86_EFLAGS_AC; + native_restore_fl(flags); +} + +static void vsmp_irq_disable(void) +{ + unsigned long flags = native_save_fl(); + + native_restore_fl((flags & ~X86_EFLAGS_IF) | X86_EFLAGS_AC); +} + +static void vsmp_irq_enable(void) +{ + unsigned long flags = native_save_fl(); + + native_restore_fl((flags | X86_EFLAGS_IF) & (~X86_EFLAGS_AC)); +} + +static unsigned __init vsmp_patch(u8 type, u16 clobbers, void *ibuf, + unsigned long addr, unsigned len) +{ + switch (type) { + case PARAVIRT_PATCH(pv_irq_ops.irq_enable): + case PARAVIRT_PATCH(pv_irq_ops.irq_disable): + case PARAVIRT_PATCH(pv_irq_ops.save_fl): + case PARAVIRT_PATCH(pv_irq_ops.restore_fl): + return paravirt_patch_default(type, clobbers, ibuf, addr, len); + default: + return native_patch(type, clobbers, ibuf, addr, len); + } + +} + +static void __init set_vsmp_pv_ops(void) +{ + void *address; + unsigned int cap, ctl, cfg; /* set vSMP magic bits to indicate vSMP capable kernel */ - address = ioremap(read_pci_config(0, 0x1f, 0, PCI_BASE_ADDRESS_0), 8); + cfg = read_pci_config(0, 0x1f, 0, PCI_BASE_ADDRESS_0); + address = early_ioremap(cfg, 8); cap = readl(address); ctl = readl(address + 4); printk(KERN_INFO "vSMP CTL: capabilities:0x%08x control:0x%08x\n", cap, ctl); if (cap & ctl & (1 << 4)) { - /* Turn on vSMP IRQ fastpath handling (see system.h) */ + /* Setup irq ops and turn on vSMP IRQ fastpath handling */ + pv_irq_ops.irq_disable = vsmp_irq_disable; + pv_irq_ops.irq_enable = vsmp_irq_enable; + pv_irq_ops.save_fl = vsmp_save_fl; + pv_irq_ops.restore_fl = vsmp_restore_fl; + pv_init_ops.patch = vsmp_patch; + ctl &= ~(1 << 4); writel(ctl, address + 4); ctl = readl(address + 4); printk(KERN_INFO "vSMP CTL: control set to:0x%08x\n", ctl); } - iounmap(address); + early_iounmap(address, 8); +} +#else +static void __init set_vsmp_pv_ops(void) +{ +} +#endif + +#ifdef CONFIG_PCI +static int is_vsmp = -1; + +static void __init detect_vsmp_box(void) +{ + is_vsmp = 0; + + if (!early_pci_allowed()) + return; + + /* Check if we are running on a ScaleMP vSMPowered box */ + if (read_pci_config(0, 0x1f, 0, PCI_VENDOR_ID) == + (PCI_VENDOR_ID_SCALEMP | (PCI_DEVICE_ID_SCALEMP_VSMP_CTL << 16))) + is_vsmp = 1; +} + +int is_vsmp_box(void) +{ + if (is_vsmp != -1) + return is_vsmp; + else { + WARN_ON_ONCE(1); + return 0; + } +} +#else +static void __init detect_vsmp_box(void) +{ +} +int is_vsmp_box(void) +{ return 0; } +#endif -core_initcall(vsmp_init); +void __init vsmp_init(void) +{ + detect_vsmp_box(); + if (!is_vsmp_box()) + return; + + set_vsmp_pv_ops(); + return; +} diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index edff4c985485..61efa2f7d564 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -216,7 +216,7 @@ vgetcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache) return 0; } -long __vsyscall(3) venosys_1(void) +static long __vsyscall(3) venosys_1(void) { return -ENOSYS; } diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index a66e9c1a0537..58882f9f2637 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -4,7 +4,6 @@ #include <linux/module.h> #include <linux/smp.h> -#include <asm/semaphore.h> #include <asm/processor.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -12,11 +11,6 @@ EXPORT_SYMBOL(kernel_thread); -EXPORT_SYMBOL(__down_failed); -EXPORT_SYMBOL(__down_failed_interruptible); -EXPORT_SYMBOL(__down_failed_trylock); -EXPORT_SYMBOL(__up_wakeup); - EXPORT_SYMBOL(__get_user_1); EXPORT_SYMBOL(__get_user_2); EXPORT_SYMBOL(__get_user_4); @@ -35,15 +29,17 @@ EXPORT_SYMBOL(__copy_from_user_inatomic); EXPORT_SYMBOL(copy_page); EXPORT_SYMBOL(clear_page); -/* Export string functions. We normally rely on gcc builtin for most of these, - but gcc sometimes decides not to inline them. */ +/* + * Export string functions. We normally rely on gcc builtin for most of these, + * but gcc sometimes decides not to inline them. + */ #undef memcpy #undef memset #undef memmove -extern void * memset(void *,int,__kernel_size_t); -extern void * memcpy(void *,const void *,__kernel_size_t); -extern void * __memcpy(void *,const void *,__kernel_size_t); +extern void *memset(void *, int, __kernel_size_t); +extern void *memcpy(void *, const void *, __kernel_size_t); +extern void *__memcpy(void *, const void *, __kernel_size_t); EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memcpy); diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 41962e793c0f..8d45fabc5f3b 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -19,7 +19,7 @@ if VIRTUALIZATION config KVM tristate "Kernel-based Virtual Machine (KVM) support" - depends on HAVE_KVM && EXPERIMENTAL + depends on HAVE_KVM select PREEMPT_NOTIFIERS select ANON_INODES ---help--- @@ -50,6 +50,17 @@ config KVM_AMD Provides support for KVM on AMD processors equipped with the AMD-V (SVM) extensions. +config KVM_TRACE + bool "KVM trace support" + depends on KVM && MARKERS && SYSFS + select RELAY + select DEBUG_FS + default n + ---help--- + This option allows reading a trace of kvm-related events through + relayfs. Note the ABI is not considered stable and will be + modified in future updates. + # OK, it's a little counter-intuitive to do this, but it puts it neatly under # the virtualization menu. source drivers/lguest/Kconfig diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index ffdd0b310784..c97d35c218db 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -3,10 +3,14 @@ # common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o) +ifeq ($(CONFIG_KVM_TRACE),y) +common-objs += $(addprefix ../../../virt/kvm/, kvm_trace.o) +endif EXTRA_CFLAGS += -Ivirt/kvm -Iarch/x86/kvm -kvm-objs := $(common-objs) x86.o mmu.o x86_emulate.o i8259.o irq.o lapic.o +kvm-objs := $(common-objs) x86.o mmu.o x86_emulate.o i8259.o irq.o lapic.o \ + i8254.o obj-$(CONFIG_KVM) += kvm.o kvm-intel-objs = vmx.o obj-$(CONFIG_KVM_INTEL) += kvm-intel.o diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c new file mode 100644 index 000000000000..4c943eabacc3 --- /dev/null +++ b/arch/x86/kvm/i8254.c @@ -0,0 +1,611 @@ +/* + * 8253/8254 interval timer emulation + * + * Copyright (c) 2003-2004 Fabrice Bellard + * Copyright (c) 2006 Intel Corporation + * Copyright (c) 2007 Keir Fraser, XenSource Inc + * Copyright (c) 2008 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + * + * Authors: + * Sheng Yang <sheng.yang@intel.com> + * Based on QEMU and Xen. + */ + +#include <linux/kvm_host.h> + +#include "irq.h" +#include "i8254.h" + +#ifndef CONFIG_X86_64 +#define mod_64(x, y) ((x) - (y) * div64_u64(x, y)) +#else +#define mod_64(x, y) ((x) % (y)) +#endif + +#define RW_STATE_LSB 1 +#define RW_STATE_MSB 2 +#define RW_STATE_WORD0 3 +#define RW_STATE_WORD1 4 + +/* Compute with 96 bit intermediate result: (a*b)/c */ +static u64 muldiv64(u64 a, u32 b, u32 c) +{ + union { + u64 ll; + struct { + u32 low, high; + } l; + } u, res; + u64 rl, rh; + + u.ll = a; + rl = (u64)u.l.low * (u64)b; + rh = (u64)u.l.high * (u64)b; + rh += (rl >> 32); + res.l.high = div64_u64(rh, c); + res.l.low = div64_u64(((mod_64(rh, c) << 32) + (rl & 0xffffffff)), c); + return res.ll; +} + +static void pit_set_gate(struct kvm *kvm, int channel, u32 val) +{ + struct kvm_kpit_channel_state *c = + &kvm->arch.vpit->pit_state.channels[channel]; + + WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock)); + + switch (c->mode) { + default: + case 0: + case 4: + /* XXX: just disable/enable counting */ + break; + case 1: + case 2: + case 3: + case 5: + /* Restart counting on rising edge. */ + if (c->gate < val) + c->count_load_time = ktime_get(); + break; + } + + c->gate = val; +} + +int pit_get_gate(struct kvm *kvm, int channel) +{ + WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock)); + + return kvm->arch.vpit->pit_state.channels[channel].gate; +} + +static int pit_get_count(struct kvm *kvm, int channel) +{ + struct kvm_kpit_channel_state *c = + &kvm->arch.vpit->pit_state.channels[channel]; + s64 d, t; + int counter; + + WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock)); + + t = ktime_to_ns(ktime_sub(ktime_get(), c->count_load_time)); + d = muldiv64(t, KVM_PIT_FREQ, NSEC_PER_SEC); + + switch (c->mode) { + case 0: + case 1: + case 4: + case 5: + counter = (c->count - d) & 0xffff; + break; + case 3: + /* XXX: may be incorrect for odd counts */ + counter = c->count - (mod_64((2 * d), c->count)); + break; + default: + counter = c->count - mod_64(d, c->count); + break; + } + return counter; +} + +static int pit_get_out(struct kvm *kvm, int channel) +{ + struct kvm_kpit_channel_state *c = + &kvm->arch.vpit->pit_state.channels[channel]; + s64 d, t; + int out; + + WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock)); + + t = ktime_to_ns(ktime_sub(ktime_get(), c->count_load_time)); + d = muldiv64(t, KVM_PIT_FREQ, NSEC_PER_SEC); + + switch (c->mode) { + default: + case 0: + out = (d >= c->count); + break; + case 1: + out = (d < c->count); + break; + case 2: + out = ((mod_64(d, c->count) == 0) && (d != 0)); + break; + case 3: + out = (mod_64(d, c->count) < ((c->count + 1) >> 1)); + break; + case 4: + case 5: + out = (d == c->count); + break; + } + + return out; +} + +static void pit_latch_count(struct kvm *kvm, int channel) +{ + struct kvm_kpit_channel_state *c = + &kvm->arch.vpit->pit_state.channels[channel]; + + WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock)); + + if (!c->count_latched) { + c->latched_count = pit_get_count(kvm, channel); + c->count_latched = c->rw_mode; + } +} + +static void pit_latch_status(struct kvm *kvm, int channel) +{ + struct kvm_kpit_channel_state *c = + &kvm->arch.vpit->pit_state.channels[channel]; + + WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock)); + + if (!c->status_latched) { + /* TODO: Return NULL COUNT (bit 6). */ + c->status = ((pit_get_out(kvm, channel) << 7) | + (c->rw_mode << 4) | + (c->mode << 1) | + c->bcd); + c->status_latched = 1; + } +} + +int __pit_timer_fn(struct kvm_kpit_state *ps) +{ + struct kvm_vcpu *vcpu0 = ps->pit->kvm->vcpus[0]; + struct kvm_kpit_timer *pt = &ps->pit_timer; + + 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); + } + + pt->timer.expires = ktime_add_ns(pt->timer.expires, pt->period); + pt->scheduled = ktime_to_ns(pt->timer.expires); + + return (pt->period == 0 ? 0 : 1); +} + +int pit_has_pending_timer(struct kvm_vcpu *vcpu) +{ + struct kvm_pit *pit = vcpu->kvm->arch.vpit; + + if (pit && vcpu->vcpu_id == 0) + return atomic_read(&pit->pit_state.pit_timer.pending); + + return 0; +} + +static enum hrtimer_restart pit_timer_fn(struct hrtimer *data) +{ + struct kvm_kpit_state *ps; + int restart_timer = 0; + + ps = container_of(data, struct kvm_kpit_state, pit_timer.timer); + + restart_timer = __pit_timer_fn(ps); + + if (restart_timer) + return HRTIMER_RESTART; + else + return HRTIMER_NORESTART; +} + +static void destroy_pit_timer(struct kvm_kpit_timer *pt) +{ + pr_debug("pit: execute del timer!\n"); + hrtimer_cancel(&pt->timer); +} + +static void create_pit_timer(struct kvm_kpit_timer *pt, u32 val, int is_period) +{ + s64 interval; + + interval = muldiv64(val, NSEC_PER_SEC, KVM_PIT_FREQ); + + pr_debug("pit: create pit timer, interval is %llu nsec\n", interval); + + /* TODO The new value only affected after the retriggered */ + hrtimer_cancel(&pt->timer); + pt->period = (is_period == 0) ? 0 : interval; + pt->timer.function = pit_timer_fn; + atomic_set(&pt->pending, 0); + + hrtimer_start(&pt->timer, ktime_add_ns(ktime_get(), interval), + HRTIMER_MODE_ABS); +} + +static void pit_load_count(struct kvm *kvm, int channel, u32 val) +{ + struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state; + + WARN_ON(!mutex_is_locked(&ps->lock)); + + pr_debug("pit: load_count val is %d, channel is %d\n", val, channel); + + /* + * Though spec said the state of 8254 is undefined after power-up, + * seems some tricky OS like Windows XP depends on IRQ0 interrupt + * when booting up. + * So here setting initialize rate for it, and not a specific number + */ + if (val == 0) + val = 0x10000; + + ps->channels[channel].count_load_time = ktime_get(); + ps->channels[channel].count = val; + + if (channel != 0) + return; + + /* Two types of timer + * mode 1 is one shot, mode 2 is period, otherwise del timer */ + switch (ps->channels[0].mode) { + case 1: + create_pit_timer(&ps->pit_timer, val, 0); + break; + case 2: + create_pit_timer(&ps->pit_timer, val, 1); + break; + default: + destroy_pit_timer(&ps->pit_timer); + } +} + +void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val) +{ + mutex_lock(&kvm->arch.vpit->pit_state.lock); + pit_load_count(kvm, channel, val); + mutex_unlock(&kvm->arch.vpit->pit_state.lock); +} + +static void pit_ioport_write(struct kvm_io_device *this, + gpa_t addr, int len, const void *data) +{ + struct kvm_pit *pit = (struct kvm_pit *)this->private; + struct kvm_kpit_state *pit_state = &pit->pit_state; + struct kvm *kvm = pit->kvm; + int channel, access; + struct kvm_kpit_channel_state *s; + u32 val = *(u32 *) data; + + val &= 0xff; + addr &= KVM_PIT_CHANNEL_MASK; + + mutex_lock(&pit_state->lock); + + if (val != 0) + pr_debug("pit: write addr is 0x%x, len is %d, val is 0x%x\n", + (unsigned int)addr, len, val); + + if (addr == 3) { + channel = val >> 6; + if (channel == 3) { + /* Read-Back Command. */ + for (channel = 0; channel < 3; channel++) { + s = &pit_state->channels[channel]; + if (val & (2 << channel)) { + if (!(val & 0x20)) + pit_latch_count(kvm, channel); + if (!(val & 0x10)) + pit_latch_status(kvm, channel); + } + } + } else { + /* Select Counter <channel>. */ + s = &pit_state->channels[channel]; + access = (val >> 4) & KVM_PIT_CHANNEL_MASK; + if (access == 0) { + pit_latch_count(kvm, channel); + } else { + s->rw_mode = access; + s->read_state = access; + s->write_state = access; + s->mode = (val >> 1) & 7; + if (s->mode > 5) + s->mode -= 4; + s->bcd = val & 1; + } + } + } else { + /* Write Count. */ + s = &pit_state->channels[addr]; + switch (s->write_state) { + default: + case RW_STATE_LSB: + pit_load_count(kvm, addr, val); + break; + case RW_STATE_MSB: + pit_load_count(kvm, addr, val << 8); + break; + case RW_STATE_WORD0: + s->write_latch = val; + s->write_state = RW_STATE_WORD1; + break; + case RW_STATE_WORD1: + pit_load_count(kvm, addr, s->write_latch | (val << 8)); + s->write_state = RW_STATE_WORD0; + break; + } + } + + mutex_unlock(&pit_state->lock); +} + +static void pit_ioport_read(struct kvm_io_device *this, + gpa_t addr, int len, void *data) +{ + struct kvm_pit *pit = (struct kvm_pit *)this->private; + struct kvm_kpit_state *pit_state = &pit->pit_state; + struct kvm *kvm = pit->kvm; + int ret, count; + struct kvm_kpit_channel_state *s; + + addr &= KVM_PIT_CHANNEL_MASK; + s = &pit_state->channels[addr]; + + mutex_lock(&pit_state->lock); + + if (s->status_latched) { + s->status_latched = 0; + ret = s->status; + } else if (s->count_latched) { + switch (s->count_latched) { + default: + case RW_STATE_LSB: + ret = s->latched_count & 0xff; + s->count_latched = 0; + break; + case RW_STATE_MSB: + ret = s->latched_count >> 8; + s->count_latched = 0; + break; + case RW_STATE_WORD0: + ret = s->latched_count & 0xff; + s->count_latched = RW_STATE_MSB; + break; + } + } else { + switch (s->read_state) { + default: + case RW_STATE_LSB: + count = pit_get_count(kvm, addr); + ret = count & 0xff; + break; + case RW_STATE_MSB: + count = pit_get_count(kvm, addr); + ret = (count >> 8) & 0xff; + break; + case RW_STATE_WORD0: + count = pit_get_count(kvm, addr); + ret = count & 0xff; + s->read_state = RW_STATE_WORD1; + break; + case RW_STATE_WORD1: + count = pit_get_count(kvm, addr); + ret = (count >> 8) & 0xff; + s->read_state = RW_STATE_WORD0; + break; + } + } + + if (len > sizeof(ret)) + len = sizeof(ret); + memcpy(data, (char *)&ret, len); + + mutex_unlock(&pit_state->lock); +} + +static int pit_in_range(struct kvm_io_device *this, gpa_t addr) +{ + return ((addr >= KVM_PIT_BASE_ADDRESS) && + (addr < KVM_PIT_BASE_ADDRESS + KVM_PIT_MEM_LENGTH)); +} + +static void speaker_ioport_write(struct kvm_io_device *this, + gpa_t addr, int len, const void *data) +{ + struct kvm_pit *pit = (struct kvm_pit *)this->private; + struct kvm_kpit_state *pit_state = &pit->pit_state; + struct kvm *kvm = pit->kvm; + u32 val = *(u32 *) data; + + mutex_lock(&pit_state->lock); + pit_state->speaker_data_on = (val >> 1) & 1; + pit_set_gate(kvm, 2, val & 1); + mutex_unlock(&pit_state->lock); +} + +static void speaker_ioport_read(struct kvm_io_device *this, + gpa_t addr, int len, void *data) +{ + struct kvm_pit *pit = (struct kvm_pit *)this->private; + struct kvm_kpit_state *pit_state = &pit->pit_state; + struct kvm *kvm = pit->kvm; + unsigned int refresh_clock; + int ret; + + /* Refresh clock toggles at about 15us. We approximate as 2^14ns. */ + refresh_clock = ((unsigned int)ktime_to_ns(ktime_get()) >> 14) & 1; + + mutex_lock(&pit_state->lock); + ret = ((pit_state->speaker_data_on << 1) | pit_get_gate(kvm, 2) | + (pit_get_out(kvm, 2) << 5) | (refresh_clock << 4)); + if (len > sizeof(ret)) + len = sizeof(ret); + memcpy(data, (char *)&ret, len); + mutex_unlock(&pit_state->lock); +} + +static int speaker_in_range(struct kvm_io_device *this, gpa_t addr) +{ + return (addr == KVM_SPEAKER_BASE_ADDRESS); +} + +void kvm_pit_reset(struct kvm_pit *pit) +{ + int i; + struct kvm_kpit_channel_state *c; + + mutex_lock(&pit->pit_state.lock); + for (i = 0; i < 3; i++) { + c = &pit->pit_state.channels[i]; + c->mode = 0xff; + c->gate = (i != 2); + pit_load_count(pit->kvm, i, 0); + } + mutex_unlock(&pit->pit_state.lock); + + atomic_set(&pit->pit_state.pit_timer.pending, 0); + pit->pit_state.inject_pending = 1; +} + +struct kvm_pit *kvm_create_pit(struct kvm *kvm) +{ + struct kvm_pit *pit; + struct kvm_kpit_state *pit_state; + + pit = kzalloc(sizeof(struct kvm_pit), GFP_KERNEL); + if (!pit) + return NULL; + + mutex_init(&pit->pit_state.lock); + mutex_lock(&pit->pit_state.lock); + + /* Initialize PIO device */ + pit->dev.read = pit_ioport_read; + pit->dev.write = pit_ioport_write; + pit->dev.in_range = pit_in_range; + pit->dev.private = pit; + kvm_io_bus_register_dev(&kvm->pio_bus, &pit->dev); + + pit->speaker_dev.read = speaker_ioport_read; + pit->speaker_dev.write = speaker_ioport_write; + pit->speaker_dev.in_range = speaker_in_range; + pit->speaker_dev.private = pit; + kvm_io_bus_register_dev(&kvm->pio_bus, &pit->speaker_dev); + + kvm->arch.vpit = pit; + pit->kvm = kvm; + + pit_state = &pit->pit_state; + pit_state->pit = pit; + hrtimer_init(&pit_state->pit_timer.timer, + CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + mutex_unlock(&pit->pit_state.lock); + + kvm_pit_reset(pit); + + return pit; +} + +void kvm_free_pit(struct kvm *kvm) +{ + struct hrtimer *timer; + + if (kvm->arch.vpit) { + mutex_lock(&kvm->arch.vpit->pit_state.lock); + timer = &kvm->arch.vpit->pit_state.pit_timer.timer; + hrtimer_cancel(timer); + mutex_unlock(&kvm->arch.vpit->pit_state.lock); + kfree(kvm->arch.vpit); + } +} + +void __inject_pit_timer_intr(struct kvm *kvm) +{ + mutex_lock(&kvm->lock); + kvm_ioapic_set_irq(kvm->arch.vioapic, 0, 1); + kvm_ioapic_set_irq(kvm->arch.vioapic, 0, 0); + kvm_pic_set_irq(pic_irqchip(kvm), 0, 1); + kvm_pic_set_irq(pic_irqchip(kvm), 0, 0); + mutex_unlock(&kvm->lock); +} + +void kvm_inject_pit_timer_irqs(struct kvm_vcpu *vcpu) +{ + struct kvm_pit *pit = vcpu->kvm->arch.vpit; + struct kvm *kvm = vcpu->kvm; + struct kvm_kpit_state *ps; + + if (vcpu && pit) { + ps = &pit->pit_state; + + /* Try to inject pending interrupts when: + * 1. Pending exists + * 2. Last interrupt was accepted or waited for too long time*/ + if (atomic_read(&ps->pit_timer.pending) && + (ps->inject_pending || + (jiffies - ps->last_injected_time + >= KVM_MAX_PIT_INTR_INTERVAL))) { + ps->inject_pending = 0; + __inject_pit_timer_intr(kvm); + ps->last_injected_time = jiffies; + } + } +} + +void kvm_pit_timer_intr_post(struct kvm_vcpu *vcpu, int vec) +{ + struct kvm_arch *arch = &vcpu->kvm->arch; + struct kvm_kpit_state *ps; + + if (vcpu && arch->vpit) { + ps = &arch->vpit->pit_state; + if (atomic_read(&ps->pit_timer.pending) && + (((arch->vpic->pics[0].imr & 1) == 0 && + arch->vpic->pics[0].irq_base == vec) || + (arch->vioapic->redirtbl[0].fields.vector == vec && + arch->vioapic->redirtbl[0].fields.mask != 1))) { + ps->inject_pending = 1; + atomic_dec(&ps->pit_timer.pending); + ps->channels[0].count_load_time = ktime_get(); + } + } +} diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h new file mode 100644 index 000000000000..db25c2a6c8c4 --- /dev/null +++ b/arch/x86/kvm/i8254.h @@ -0,0 +1,63 @@ +#ifndef __I8254_H +#define __I8254_H + +#include "iodev.h" + +struct kvm_kpit_timer { + struct hrtimer timer; + int irq; + s64 period; /* unit: ns */ + s64 scheduled; + ktime_t last_update; + atomic_t pending; +}; + +struct kvm_kpit_channel_state { + u32 count; /* can be 65536 */ + u16 latched_count; + u8 count_latched; + u8 status_latched; + u8 status; + u8 read_state; + u8 write_state; + u8 write_latch; + u8 rw_mode; + u8 mode; + u8 bcd; /* not supported */ + u8 gate; /* timer start */ + ktime_t count_load_time; +}; + +struct kvm_kpit_state { + struct kvm_kpit_channel_state channels[3]; + struct kvm_kpit_timer pit_timer; + u32 speaker_data_on; + struct mutex lock; + struct kvm_pit *pit; + bool inject_pending; /* if inject pending interrupts */ + unsigned long last_injected_time; +}; + +struct kvm_pit { + unsigned long base_addresss; + struct kvm_io_device dev; + struct kvm_io_device speaker_dev; + struct kvm *kvm; + struct kvm_kpit_state pit_state; +}; + +#define KVM_PIT_BASE_ADDRESS 0x40 +#define KVM_SPEAKER_BASE_ADDRESS 0x61 +#define KVM_PIT_MEM_LENGTH 4 +#define KVM_PIT_FREQ 1193181 +#define KVM_MAX_PIT_INTR_INTERVAL HZ / 100 +#define KVM_PIT_CHANNEL_MASK 0x3 + +void kvm_inject_pit_timer_irqs(struct kvm_vcpu *vcpu); +void kvm_pit_timer_intr_post(struct kvm_vcpu *vcpu, int vec); +void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val); +struct kvm_pit *kvm_create_pit(struct kvm *kvm); +void kvm_free_pit(struct kvm *kvm); +void kvm_pit_reset(struct kvm_pit *pit); + +#endif diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index e5714759e97f..ce1f583459b1 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -23,6 +23,22 @@ #include <linux/kvm_host.h> #include "irq.h" +#include "i8254.h" + +/* + * check if there are pending timer events + * to be processed. + */ +int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) +{ + int ret; + + ret = pit_has_pending_timer(vcpu); + ret |= apic_has_pending_timer(vcpu); + + return ret; +} +EXPORT_SYMBOL(kvm_cpu_has_pending_timer); /* * check if there is pending interrupt without @@ -66,6 +82,7 @@ EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt); void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu) { kvm_inject_apic_timer_irqs(vcpu); + kvm_inject_pit_timer_irqs(vcpu); /* TODO: PIT, RTC etc. */ } EXPORT_SYMBOL_GPL(kvm_inject_pending_timer_irqs); @@ -73,6 +90,7 @@ EXPORT_SYMBOL_GPL(kvm_inject_pending_timer_irqs); void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec) { kvm_apic_timer_intr_post(vcpu, vec); + kvm_pit_timer_intr_post(vcpu, vec); /* TODO: PIT, RTC etc. */ } EXPORT_SYMBOL_GPL(kvm_timer_intr_post); diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index fa5ed5d59b5d..1802134b836f 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -85,4 +85,7 @@ 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); +int pit_has_pending_timer(struct kvm_vcpu *vcpu); +int apic_has_pending_timer(struct kvm_vcpu *vcpu); + #endif diff --git a/arch/x86/kvm/kvm_svm.h b/arch/x86/kvm/kvm_svm.h index ecdfe97e4635..65ef0fc2c036 100644 --- a/arch/x86/kvm/kvm_svm.h +++ b/arch/x86/kvm/kvm_svm.h @@ -39,6 +39,8 @@ struct vcpu_svm { unsigned long host_db_regs[NUM_DB_REGS]; unsigned long host_dr6; unsigned long host_dr7; + + u32 *msrpm; }; #endif diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 68a6b1511934..36809d79788b 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -25,13 +25,13 @@ #include <linux/hrtimer.h> #include <linux/io.h> #include <linux/module.h> +#include <linux/math64.h> #include <asm/processor.h> #include <asm/msr.h> #include <asm/page.h> #include <asm/current.h> #include <asm/apicdef.h> #include <asm/atomic.h> -#include <asm/div64.h> #include "irq.h" #define PRId64 "d" @@ -338,10 +338,10 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, } else apic_clear_vector(vector, apic->regs + APIC_TMR); - if (vcpu->arch.mp_state == VCPU_MP_STATE_RUNNABLE) + if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE) kvm_vcpu_kick(vcpu); - else if (vcpu->arch.mp_state == VCPU_MP_STATE_HALTED) { - vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE; + else if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) { + vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; if (waitqueue_active(&vcpu->wq)) wake_up_interruptible(&vcpu->wq); } @@ -362,11 +362,11 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, case APIC_DM_INIT: if (level) { - if (vcpu->arch.mp_state == VCPU_MP_STATE_RUNNABLE) + if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE) printk(KERN_DEBUG "INIT on a runnable vcpu %d\n", vcpu->vcpu_id); - vcpu->arch.mp_state = VCPU_MP_STATE_INIT_RECEIVED; + vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED; kvm_vcpu_kick(vcpu); } else { printk(KERN_DEBUG @@ -379,9 +379,9 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, case APIC_DM_STARTUP: printk(KERN_DEBUG "SIPI to vcpu %d vector 0x%02x\n", vcpu->vcpu_id, vector); - if (vcpu->arch.mp_state == VCPU_MP_STATE_INIT_RECEIVED) { + if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { vcpu->arch.sipi_vector = vector; - vcpu->arch.mp_state = VCPU_MP_STATE_SIPI_RECEIVED; + vcpu->arch.mp_state = KVM_MP_STATE_SIPI_RECEIVED; if (waitqueue_active(&vcpu->wq)) wake_up_interruptible(&vcpu->wq); } @@ -526,8 +526,8 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic) } else passed = ktime_sub(now, apic->timer.last_update); - counter_passed = div64_64(ktime_to_ns(passed), - (APIC_BUS_CYCLE_NS * apic->timer.divide_count)); + counter_passed = div64_u64(ktime_to_ns(passed), + (APIC_BUS_CYCLE_NS * apic->timer.divide_count)); if (counter_passed > tmcct) { if (unlikely(!apic_lvtt_period(apic))) { @@ -658,7 +658,7 @@ static void start_apic_timer(struct kvm_lapic *apic) apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016" PRIx64 ", " "timer initial count 0x%x, period %lldns, " - "expire @ 0x%016" PRIx64 ".\n", __FUNCTION__, + "expire @ 0x%016" PRIx64 ".\n", __func__, APIC_BUS_CYCLE_NS, ktime_to_ns(now), apic_get_reg(apic, APIC_TMICT), apic->timer.period, @@ -691,7 +691,7 @@ static void apic_mmio_write(struct kvm_io_device *this, /* too common printing */ if (offset != APIC_EOI) apic_debug("%s: offset 0x%x with length 0x%x, and value is " - "0x%x\n", __FUNCTION__, offset, len, val); + "0x%x\n", __func__, offset, len, val); offset &= 0xff0; @@ -822,6 +822,7 @@ void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8) apic_set_tpr(apic, ((cr8 & 0x0f) << 4) | (apic_get_reg(apic, APIC_TASKPRI) & 4)); } +EXPORT_SYMBOL_GPL(kvm_lapic_set_tpr); u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu) { @@ -869,7 +870,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu) struct kvm_lapic *apic; int i; - apic_debug("%s\n", __FUNCTION__); + apic_debug("%s\n", __func__); ASSERT(vcpu); apic = vcpu->arch.apic; @@ -907,7 +908,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu) apic_update_ppr(apic); apic_debug(KERN_INFO "%s: vcpu=%p, id=%d, base_msr=" - "0x%016" PRIx64 ", base_address=0x%0lx.\n", __FUNCTION__, + "0x%016" PRIx64 ", base_address=0x%0lx.\n", __func__, vcpu, kvm_apic_id(apic), vcpu->arch.apic_base, apic->base_address); } @@ -940,7 +941,7 @@ static int __apic_timer_fn(struct kvm_lapic *apic) atomic_inc(&apic->timer.pending); if (waitqueue_active(q)) { - apic->vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE; + apic->vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; wake_up_interruptible(q); } if (apic_lvtt_period(apic)) { @@ -952,6 +953,16 @@ static int __apic_timer_fn(struct kvm_lapic *apic) return result; } +int apic_has_pending_timer(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *lapic = vcpu->arch.apic; + + if (lapic) + return atomic_read(&lapic->timer.pending); + + return 0; +} + static int __inject_apic_timer_irq(struct kvm_lapic *apic) { int vector; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index e55af12e11b7..2ad6f5481671 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -27,11 +27,22 @@ #include <linux/highmem.h> #include <linux/module.h> #include <linux/swap.h> +#include <linux/hugetlb.h> +#include <linux/compiler.h> #include <asm/page.h> #include <asm/cmpxchg.h> #include <asm/io.h> +/* + * When setting this variable to true it enables Two-Dimensional-Paging + * where the hardware walks 2 page tables: + * 1. the guest-virtual to guest-physical + * 2. while doing 1. it walks guest-physical to host-physical + * If the hardware supports that we don't need to do shadow paging. + */ +bool tdp_enabled = false; + #undef MMU_DEBUG #undef AUDIT @@ -101,8 +112,6 @@ static int dbg = 1; #define PT_FIRST_AVAIL_BITS_SHIFT 9 #define PT64_SECOND_AVAIL_BITS_SHIFT 52 -#define PT_SHADOW_IO_MARK (1ULL << PT_FIRST_AVAIL_BITS_SHIFT) - #define VALID_PAGE(x) ((x) != INVALID_PAGE) #define PT64_LEVEL_BITS 9 @@ -159,6 +168,13 @@ static int dbg = 1; #define ACC_USER_MASK PT_USER_MASK #define ACC_ALL (ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK) +struct kvm_pv_mmu_op_buffer { + void *ptr; + unsigned len; + unsigned processed; + char buf[512] __aligned(sizeof(long)); +}; + struct kvm_rmap_desc { u64 *shadow_ptes[RMAP_EXT]; struct kvm_rmap_desc *more; @@ -200,11 +216,15 @@ static int is_present_pte(unsigned long pte) static int is_shadow_present_pte(u64 pte) { - pte &= ~PT_SHADOW_IO_MARK; return pte != shadow_trap_nonpresent_pte && pte != shadow_notrap_nonpresent_pte; } +static int is_large_pte(u64 pte) +{ + return pte & PT_PAGE_SIZE_MASK; +} + static int is_writeble_pte(unsigned long pte) { return pte & PT_WRITABLE_MASK; @@ -215,14 +235,14 @@ static int is_dirty_pte(unsigned long pte) return pte & PT_DIRTY_MASK; } -static int is_io_pte(unsigned long pte) +static int is_rmap_pte(u64 pte) { - return pte & PT_SHADOW_IO_MARK; + return is_shadow_present_pte(pte); } -static int is_rmap_pte(u64 pte) +static pfn_t spte_to_pfn(u64 pte) { - return is_shadow_present_pte(pte); + return (pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; } static gfn_t pse36_gfn_delta(u32 gpte) @@ -349,16 +369,100 @@ static void mmu_free_rmap_desc(struct kvm_rmap_desc *rd) } /* + * Return the pointer to the largepage write count for a given + * gfn, handling slots that are not large page aligned. + */ +static int *slot_largepage_idx(gfn_t gfn, struct kvm_memory_slot *slot) +{ + unsigned long idx; + + idx = (gfn / KVM_PAGES_PER_HPAGE) - + (slot->base_gfn / KVM_PAGES_PER_HPAGE); + return &slot->lpage_info[idx].write_count; +} + +static void account_shadowed(struct kvm *kvm, gfn_t gfn) +{ + int *write_count; + + write_count = slot_largepage_idx(gfn, gfn_to_memslot(kvm, gfn)); + *write_count += 1; + WARN_ON(*write_count > KVM_PAGES_PER_HPAGE); +} + +static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn) +{ + int *write_count; + + write_count = slot_largepage_idx(gfn, gfn_to_memslot(kvm, gfn)); + *write_count -= 1; + WARN_ON(*write_count < 0); +} + +static int has_wrprotected_page(struct kvm *kvm, gfn_t gfn) +{ + struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); + int *largepage_idx; + + if (slot) { + largepage_idx = slot_largepage_idx(gfn, slot); + return *largepage_idx; + } + + return 1; +} + +static int host_largepage_backed(struct kvm *kvm, gfn_t gfn) +{ + struct vm_area_struct *vma; + unsigned long addr; + + addr = gfn_to_hva(kvm, gfn); + if (kvm_is_error_hva(addr)) + return 0; + + vma = find_vma(current->mm, addr); + if (vma && is_vm_hugetlb_page(vma)) + return 1; + + return 0; +} + +static int is_largepage_backed(struct kvm_vcpu *vcpu, gfn_t large_gfn) +{ + struct kvm_memory_slot *slot; + + if (has_wrprotected_page(vcpu->kvm, large_gfn)) + return 0; + + if (!host_largepage_backed(vcpu->kvm, large_gfn)) + return 0; + + slot = gfn_to_memslot(vcpu->kvm, large_gfn); + if (slot && slot->dirty_bitmap) + return 0; + + return 1; +} + +/* * Take gfn and return the reverse mapping to it. * Note: gfn must be unaliased before this function get called */ -static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn) +static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int lpage) { struct kvm_memory_slot *slot; + unsigned long idx; slot = gfn_to_memslot(kvm, gfn); - return &slot->rmap[gfn - slot->base_gfn]; + if (!lpage) + return &slot->rmap[gfn - slot->base_gfn]; + + idx = (gfn / KVM_PAGES_PER_HPAGE) - + (slot->base_gfn / KVM_PAGES_PER_HPAGE); + + return &slot->lpage_info[idx].rmap_pde; } /* @@ -370,7 +474,7 @@ static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn) * If rmapp bit zero is one, (then rmap & ~1) points to a struct kvm_rmap_desc * containing more mappings. */ -static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) +static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn, int lpage) { struct kvm_mmu_page *sp; struct kvm_rmap_desc *desc; @@ -382,7 +486,7 @@ static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) gfn = unalias_gfn(vcpu->kvm, gfn); sp = page_header(__pa(spte)); sp->gfns[spte - sp->spt] = gfn; - rmapp = gfn_to_rmap(vcpu->kvm, gfn); + rmapp = gfn_to_rmap(vcpu->kvm, gfn, lpage); if (!*rmapp) { rmap_printk("rmap_add: %p %llx 0->1\n", spte, *spte); *rmapp = (unsigned long)spte; @@ -435,20 +539,21 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) struct kvm_rmap_desc *desc; struct kvm_rmap_desc *prev_desc; struct kvm_mmu_page *sp; - struct page *page; + pfn_t pfn; unsigned long *rmapp; int i; if (!is_rmap_pte(*spte)) return; sp = page_header(__pa(spte)); - page = pfn_to_page((*spte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT); - mark_page_accessed(page); + pfn = spte_to_pfn(*spte); + if (*spte & PT_ACCESSED_MASK) + kvm_set_pfn_accessed(pfn); if (is_writeble_pte(*spte)) - kvm_release_page_dirty(page); + kvm_release_pfn_dirty(pfn); else - kvm_release_page_clean(page); - rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt]); + kvm_release_pfn_clean(pfn); + rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt], is_large_pte(*spte)); if (!*rmapp) { printk(KERN_ERR "rmap_remove: %p %llx 0->BUG\n", spte, *spte); BUG(); @@ -514,7 +619,7 @@ static void rmap_write_protect(struct kvm *kvm, u64 gfn) int write_protected = 0; gfn = unalias_gfn(kvm, gfn); - rmapp = gfn_to_rmap(kvm, gfn); + rmapp = gfn_to_rmap(kvm, gfn, 0); spte = rmap_next(kvm, rmapp, NULL); while (spte) { @@ -527,8 +632,35 @@ static void rmap_write_protect(struct kvm *kvm, u64 gfn) } spte = rmap_next(kvm, rmapp, spte); } + if (write_protected) { + pfn_t pfn; + + spte = rmap_next(kvm, rmapp, NULL); + pfn = spte_to_pfn(*spte); + kvm_set_pfn_dirty(pfn); + } + + /* check for huge page mappings */ + rmapp = gfn_to_rmap(kvm, gfn, 1); + spte = rmap_next(kvm, rmapp, NULL); + while (spte) { + BUG_ON(!spte); + BUG_ON(!(*spte & PT_PRESENT_MASK)); + BUG_ON((*spte & (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK)) != (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK)); + pgprintk("rmap_write_protect(large): spte %p %llx %lld\n", spte, *spte, gfn); + if (is_writeble_pte(*spte)) { + rmap_remove(kvm, spte); + --kvm->stat.lpages; + set_shadow_pte(spte, shadow_trap_nonpresent_pte); + write_protected = 1; + } + spte = rmap_next(kvm, rmapp, spte); + } + if (write_protected) kvm_flush_remote_tlbs(kvm); + + account_shadowed(kvm, gfn); } #ifdef MMU_DEBUG @@ -538,8 +670,8 @@ static int is_empty_shadow_page(u64 *spt) u64 *end; for (pos = spt, end = pos + PAGE_SIZE / sizeof(u64); pos != end; pos++) - if ((*pos & ~PT_SHADOW_IO_MARK) != shadow_trap_nonpresent_pte) { - printk(KERN_ERR "%s: %p %llx\n", __FUNCTION__, + if (*pos != shadow_trap_nonpresent_pte) { + printk(KERN_ERR "%s: %p %llx\n", __func__, pos, *pos); return 0; } @@ -559,7 +691,7 @@ static void kvm_mmu_free_page(struct kvm *kvm, struct kvm_mmu_page *sp) static unsigned kvm_page_table_hashfn(gfn_t gfn) { - return gfn; + return gfn & ((1 << KVM_MMU_HASH_SHIFT) - 1); } static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, @@ -662,13 +794,14 @@ static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn) struct kvm_mmu_page *sp; struct hlist_node *node; - pgprintk("%s: looking for gfn %lx\n", __FUNCTION__, gfn); - index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES; + pgprintk("%s: looking for gfn %lx\n", __func__, gfn); + index = kvm_page_table_hashfn(gfn); bucket = &kvm->arch.mmu_page_hash[index]; hlist_for_each_entry(sp, node, bucket, hash_link) - if (sp->gfn == gfn && !sp->role.metaphysical) { + if (sp->gfn == gfn && !sp->role.metaphysical + && !sp->role.invalid) { pgprintk("%s: found role %x\n", - __FUNCTION__, sp->role.word); + __func__, sp->role.word); return sp; } return NULL; @@ -699,27 +832,27 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1; role.quadrant = quadrant; } - pgprintk("%s: looking gfn %lx role %x\n", __FUNCTION__, + pgprintk("%s: looking gfn %lx role %x\n", __func__, gfn, role.word); - index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES; + index = kvm_page_table_hashfn(gfn); bucket = &vcpu->kvm->arch.mmu_page_hash[index]; hlist_for_each_entry(sp, node, bucket, hash_link) if (sp->gfn == gfn && sp->role.word == role.word) { mmu_page_add_parent_pte(vcpu, sp, parent_pte); - pgprintk("%s: found\n", __FUNCTION__); + pgprintk("%s: found\n", __func__); return sp; } ++vcpu->kvm->stat.mmu_cache_miss; sp = kvm_mmu_alloc_page(vcpu, parent_pte); if (!sp) return sp; - pgprintk("%s: adding gfn %lx role %x\n", __FUNCTION__, gfn, role.word); + pgprintk("%s: adding gfn %lx role %x\n", __func__, gfn, role.word); sp->gfn = gfn; sp->role = role; hlist_add_head(&sp->hash_link, bucket); - vcpu->arch.mmu.prefetch_page(vcpu, sp); if (!metaphysical) rmap_write_protect(vcpu->kvm, gfn); + vcpu->arch.mmu.prefetch_page(vcpu, sp); return sp; } @@ -745,11 +878,17 @@ static void kvm_mmu_page_unlink_children(struct kvm *kvm, for (i = 0; i < PT64_ENT_PER_PAGE; ++i) { ent = pt[i]; + if (is_shadow_present_pte(ent)) { + if (!is_large_pte(ent)) { + ent &= PT64_BASE_ADDR_MASK; + mmu_page_remove_parent_pte(page_header(ent), + &pt[i]); + } else { + --kvm->stat.lpages; + rmap_remove(kvm, &pt[i]); + } + } pt[i] = shadow_trap_nonpresent_pte; - if (!is_shadow_present_pte(ent)) - continue; - ent &= PT64_BASE_ADDR_MASK; - mmu_page_remove_parent_pte(page_header(ent), &pt[i]); } kvm_flush_remote_tlbs(kvm); } @@ -789,10 +928,15 @@ static void kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp) } kvm_mmu_page_unlink_children(kvm, sp); if (!sp->root_count) { + if (!sp->role.metaphysical) + unaccount_shadowed(kvm, sp->gfn); hlist_del(&sp->hash_link); kvm_mmu_free_page(kvm, sp); - } else + } else { list_move(&sp->link, &kvm->arch.active_mmu_pages); + sp->role.invalid = 1; + kvm_reload_remote_mmus(kvm); + } kvm_mmu_reset_last_pte_updated(kvm); } @@ -838,13 +982,13 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) struct hlist_node *node, *n; int r; - pgprintk("%s: looking for gfn %lx\n", __FUNCTION__, gfn); + pgprintk("%s: looking for gfn %lx\n", __func__, gfn); r = 0; - index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES; + index = kvm_page_table_hashfn(gfn); bucket = &kvm->arch.mmu_page_hash[index]; hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) if (sp->gfn == gfn && !sp->role.metaphysical) { - pgprintk("%s: gfn %lx role %x\n", __FUNCTION__, gfn, + pgprintk("%s: gfn %lx role %x\n", __func__, gfn, sp->role.word); kvm_mmu_zap_page(kvm, sp); r = 1; @@ -857,7 +1001,7 @@ static void mmu_unshadow(struct kvm *kvm, gfn_t gfn) struct kvm_mmu_page *sp; while ((sp = kvm_mmu_lookup_page(kvm, gfn)) != NULL) { - pgprintk("%s: zap %lx %x\n", __FUNCTION__, gfn, sp->role.word); + pgprintk("%s: zap %lx %x\n", __func__, gfn, sp->role.word); kvm_mmu_zap_page(kvm, sp); } } @@ -889,26 +1033,39 @@ struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva) static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, unsigned pt_access, unsigned pte_access, int user_fault, int write_fault, int dirty, - int *ptwrite, gfn_t gfn, struct page *page) + int *ptwrite, int largepage, gfn_t gfn, + pfn_t pfn, bool speculative) { u64 spte; int was_rmapped = 0; int was_writeble = is_writeble_pte(*shadow_pte); - hfn_t host_pfn = (*shadow_pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; pgprintk("%s: spte %llx access %x write_fault %d" " user_fault %d gfn %lx\n", - __FUNCTION__, *shadow_pte, pt_access, + __func__, *shadow_pte, pt_access, write_fault, user_fault, gfn); if (is_rmap_pte(*shadow_pte)) { - if (host_pfn != page_to_pfn(page)) { + /* + * If we overwrite a PTE page pointer with a 2MB PMD, unlink + * the parent of the now unreachable PTE. + */ + if (largepage && !is_large_pte(*shadow_pte)) { + struct kvm_mmu_page *child; + u64 pte = *shadow_pte; + + child = page_header(pte & PT64_BASE_ADDR_MASK); + mmu_page_remove_parent_pte(child, shadow_pte); + } else if (pfn != spte_to_pfn(*shadow_pte)) { pgprintk("hfn old %lx new %lx\n", - host_pfn, page_to_pfn(page)); + spte_to_pfn(*shadow_pte), pfn); rmap_remove(vcpu->kvm, shadow_pte); + } else { + if (largepage) + was_rmapped = is_large_pte(*shadow_pte); + else + was_rmapped = 1; } - else - was_rmapped = 1; } /* @@ -917,6 +1074,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, * demand paging). */ spte = PT_PRESENT_MASK | PT_DIRTY_MASK; + if (!speculative) + pte_access |= PT_ACCESSED_MASK; if (!dirty) pte_access &= ~ACC_WRITE_MASK; if (!(pte_access & ACC_EXEC_MASK)) @@ -925,15 +1084,10 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, spte |= PT_PRESENT_MASK; if (pte_access & ACC_USER_MASK) spte |= PT_USER_MASK; + if (largepage) + spte |= PT_PAGE_SIZE_MASK; - if (is_error_page(page)) { - set_shadow_pte(shadow_pte, - shadow_trap_nonpresent_pte | PT_SHADOW_IO_MARK); - kvm_release_page_clean(page); - return; - } - - spte |= page_to_phys(page); + spte |= (u64)pfn << PAGE_SHIFT; if ((pte_access & ACC_WRITE_MASK) || (write_fault && !is_write_protection(vcpu) && !user_fault)) { @@ -946,9 +1100,10 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, } shadow = kvm_mmu_lookup_page(vcpu->kvm, gfn); - if (shadow) { + if (shadow || + (largepage && has_wrprotected_page(vcpu->kvm, gfn))) { pgprintk("%s: found shadow page for %lx, marking ro\n", - __FUNCTION__, gfn); + __func__, gfn); pte_access &= ~ACC_WRITE_MASK; if (is_writeble_pte(spte)) { spte &= ~PT_WRITABLE_MASK; @@ -964,18 +1119,25 @@ unshadowed: if (pte_access & ACC_WRITE_MASK) mark_page_dirty(vcpu->kvm, gfn); - pgprintk("%s: setting spte %llx\n", __FUNCTION__, spte); + pgprintk("%s: setting spte %llx\n", __func__, spte); + pgprintk("instantiating %s PTE (%s) at %d (%llx) addr %llx\n", + (spte&PT_PAGE_SIZE_MASK)? "2MB" : "4kB", + (spte&PT_WRITABLE_MASK)?"RW":"R", gfn, spte, shadow_pte); set_shadow_pte(shadow_pte, spte); + if (!was_rmapped && (spte & PT_PAGE_SIZE_MASK) + && (spte & PT_PRESENT_MASK)) + ++vcpu->kvm->stat.lpages; + page_header_update_slot(vcpu->kvm, shadow_pte, gfn); if (!was_rmapped) { - rmap_add(vcpu, shadow_pte, gfn); + rmap_add(vcpu, shadow_pte, gfn, largepage); if (!is_rmap_pte(*shadow_pte)) - kvm_release_page_clean(page); + kvm_release_pfn_clean(pfn); } else { if (was_writeble) - kvm_release_page_dirty(page); + kvm_release_pfn_dirty(pfn); else - kvm_release_page_clean(page); + kvm_release_pfn_clean(pfn); } if (!ptwrite || !*ptwrite) vcpu->arch.last_pte_updated = shadow_pte; @@ -985,10 +1147,10 @@ static void nonpaging_new_cr3(struct kvm_vcpu *vcpu) { } -static int __nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, - gfn_t gfn, struct page *page) +static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, + int largepage, gfn_t gfn, pfn_t pfn, + int level) { - int level = PT32E_ROOT_LEVEL; hpa_t table_addr = vcpu->arch.mmu.root_hpa; int pt_write = 0; @@ -1001,8 +1163,14 @@ static int __nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, if (level == 1) { mmu_set_spte(vcpu, &table[index], ACC_ALL, ACC_ALL, - 0, write, 1, &pt_write, gfn, page); - return pt_write || is_io_pte(table[index]); + 0, write, 1, &pt_write, 0, gfn, pfn, false); + return pt_write; + } + + if (largepage && level == 2) { + mmu_set_spte(vcpu, &table[index], ACC_ALL, ACC_ALL, + 0, write, 1, &pt_write, 1, gfn, pfn, false); + return pt_write; } if (table[index] == shadow_trap_nonpresent_pte) { @@ -1016,7 +1184,7 @@ static int __nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, 1, ACC_ALL, &table[index]); if (!new_table) { pgprintk("nonpaging_map: ENOMEM\n"); - kvm_release_page_clean(page); + kvm_release_pfn_clean(pfn); return -ENOMEM; } @@ -1030,21 +1198,30 @@ static int __nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn) { int r; - - struct page *page; - - down_read(&vcpu->kvm->slots_lock); + int largepage = 0; + pfn_t pfn; down_read(¤t->mm->mmap_sem); - page = gfn_to_page(vcpu->kvm, gfn); + if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) { + gfn &= ~(KVM_PAGES_PER_HPAGE-1); + largepage = 1; + } + + pfn = gfn_to_pfn(vcpu->kvm, gfn); up_read(¤t->mm->mmap_sem); + /* mmio */ + if (is_error_pfn(pfn)) { + kvm_release_pfn_clean(pfn); + return 1; + } + spin_lock(&vcpu->kvm->mmu_lock); kvm_mmu_free_some_pages(vcpu); - r = __nonpaging_map(vcpu, v, write, gfn, page); + r = __direct_map(vcpu, v, write, largepage, gfn, pfn, + PT32E_ROOT_LEVEL); spin_unlock(&vcpu->kvm->mmu_lock); - up_read(&vcpu->kvm->slots_lock); return r; } @@ -1073,6 +1250,8 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu) sp = page_header(root); --sp->root_count; + if (!sp->root_count && sp->role.invalid) + kvm_mmu_zap_page(vcpu->kvm, sp); vcpu->arch.mmu.root_hpa = INVALID_PAGE; spin_unlock(&vcpu->kvm->mmu_lock); return; @@ -1085,6 +1264,8 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu) root &= PT64_BASE_ADDR_MASK; sp = page_header(root); --sp->root_count; + if (!sp->root_count && sp->role.invalid) + kvm_mmu_zap_page(vcpu->kvm, sp); } vcpu->arch.mmu.pae_root[i] = INVALID_PAGE; } @@ -1097,6 +1278,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu) int i; gfn_t root_gfn; struct kvm_mmu_page *sp; + int metaphysical = 0; root_gfn = vcpu->arch.cr3 >> PAGE_SHIFT; @@ -1105,14 +1287,20 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu) hpa_t root = vcpu->arch.mmu.root_hpa; ASSERT(!VALID_PAGE(root)); + if (tdp_enabled) + metaphysical = 1; sp = kvm_mmu_get_page(vcpu, root_gfn, 0, - PT64_ROOT_LEVEL, 0, ACC_ALL, NULL); + PT64_ROOT_LEVEL, metaphysical, + ACC_ALL, NULL); root = __pa(sp->spt); ++sp->root_count; vcpu->arch.mmu.root_hpa = root; return; } #endif + metaphysical = !is_paging(vcpu); + if (tdp_enabled) + metaphysical = 1; for (i = 0; i < 4; ++i) { hpa_t root = vcpu->arch.mmu.pae_root[i]; @@ -1126,7 +1314,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu) } else if (vcpu->arch.mmu.root_level == 0) root_gfn = 0; sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, - PT32_ROOT_LEVEL, !is_paging(vcpu), + PT32_ROOT_LEVEL, metaphysical, ACC_ALL, NULL); root = __pa(sp->spt); ++sp->root_count; @@ -1146,7 +1334,7 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn; int r; - pgprintk("%s: gva %lx error %x\n", __FUNCTION__, gva, error_code); + pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code); r = mmu_topup_memory_caches(vcpu); if (r) return r; @@ -1160,6 +1348,41 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, error_code & PFERR_WRITE_MASK, gfn); } +static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, + u32 error_code) +{ + pfn_t pfn; + int r; + int largepage = 0; + gfn_t gfn = gpa >> PAGE_SHIFT; + + ASSERT(vcpu); + ASSERT(VALID_PAGE(vcpu->arch.mmu.root_hpa)); + + r = mmu_topup_memory_caches(vcpu); + if (r) + return r; + + down_read(¤t->mm->mmap_sem); + if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) { + gfn &= ~(KVM_PAGES_PER_HPAGE-1); + largepage = 1; + } + pfn = gfn_to_pfn(vcpu->kvm, gfn); + up_read(¤t->mm->mmap_sem); + if (is_error_pfn(pfn)) { + kvm_release_pfn_clean(pfn); + return 1; + } + spin_lock(&vcpu->kvm->mmu_lock); + kvm_mmu_free_some_pages(vcpu); + r = __direct_map(vcpu, gpa, error_code & PFERR_WRITE_MASK, + largepage, gfn, pfn, TDP_ROOT_LEVEL); + spin_unlock(&vcpu->kvm->mmu_lock); + + return r; +} + static void nonpaging_free(struct kvm_vcpu *vcpu) { mmu_free_roots(vcpu); @@ -1188,7 +1411,7 @@ void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu) static void paging_new_cr3(struct kvm_vcpu *vcpu) { - pgprintk("%s: cr3 %lx\n", __FUNCTION__, vcpu->arch.cr3); + pgprintk("%s: cr3 %lx\n", __func__, vcpu->arch.cr3); mmu_free_roots(vcpu); } @@ -1253,7 +1476,35 @@ static int paging32E_init_context(struct kvm_vcpu *vcpu) return paging64_init_context_common(vcpu, PT32E_ROOT_LEVEL); } -static int init_kvm_mmu(struct kvm_vcpu *vcpu) +static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) +{ + struct kvm_mmu *context = &vcpu->arch.mmu; + + context->new_cr3 = nonpaging_new_cr3; + context->page_fault = tdp_page_fault; + context->free = nonpaging_free; + context->prefetch_page = nonpaging_prefetch_page; + context->shadow_root_level = TDP_ROOT_LEVEL; + context->root_hpa = INVALID_PAGE; + + if (!is_paging(vcpu)) { + context->gva_to_gpa = nonpaging_gva_to_gpa; + context->root_level = 0; + } else if (is_long_mode(vcpu)) { + context->gva_to_gpa = paging64_gva_to_gpa; + context->root_level = PT64_ROOT_LEVEL; + } else if (is_pae(vcpu)) { + context->gva_to_gpa = paging64_gva_to_gpa; + context->root_level = PT32E_ROOT_LEVEL; + } else { + context->gva_to_gpa = paging32_gva_to_gpa; + context->root_level = PT32_ROOT_LEVEL; + } + + return 0; +} + +static int init_kvm_softmmu(struct kvm_vcpu *vcpu) { ASSERT(vcpu); ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); @@ -1268,6 +1519,16 @@ static int init_kvm_mmu(struct kvm_vcpu *vcpu) return paging32_init_context(vcpu); } +static int init_kvm_mmu(struct kvm_vcpu *vcpu) +{ + vcpu->arch.update_pte.pfn = bad_pfn; + + if (tdp_enabled) + return init_kvm_tdp_mmu(vcpu); + else + return init_kvm_softmmu(vcpu); +} + static void destroy_kvm_mmu(struct kvm_vcpu *vcpu) { ASSERT(vcpu); @@ -1316,7 +1577,8 @@ static void mmu_pte_write_zap_pte(struct kvm_vcpu *vcpu, pte = *spte; if (is_shadow_present_pte(pte)) { - if (sp->role.level == PT_PAGE_TABLE_LEVEL) + if (sp->role.level == PT_PAGE_TABLE_LEVEL || + is_large_pte(pte)) rmap_remove(vcpu->kvm, spte); else { child = page_header(pte & PT64_BASE_ADDR_MASK); @@ -1324,24 +1586,26 @@ static void mmu_pte_write_zap_pte(struct kvm_vcpu *vcpu, } } set_shadow_pte(spte, shadow_trap_nonpresent_pte); + if (is_large_pte(pte)) + --vcpu->kvm->stat.lpages; } static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, - const void *new, int bytes, - int offset_in_pte) + const void *new) { - if (sp->role.level != PT_PAGE_TABLE_LEVEL) { + if ((sp->role.level != PT_PAGE_TABLE_LEVEL) + && !vcpu->arch.update_pte.largepage) { ++vcpu->kvm->stat.mmu_pde_zapped; return; } ++vcpu->kvm->stat.mmu_pte_updated; if (sp->role.glevels == PT32_ROOT_LEVEL) - paging32_update_pte(vcpu, sp, spte, new, bytes, offset_in_pte); + paging32_update_pte(vcpu, sp, spte, new); else - paging64_update_pte(vcpu, sp, spte, new, bytes, offset_in_pte); + paging64_update_pte(vcpu, sp, spte, new); } static bool need_remote_flush(u64 old, u64 new) @@ -1378,7 +1642,9 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, gfn_t gfn; int r; u64 gpte = 0; - struct page *page; + pfn_t pfn; + + vcpu->arch.update_pte.largepage = 0; if (bytes != 4 && bytes != 8) return; @@ -1408,11 +1674,19 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, gfn = (gpte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; down_read(¤t->mm->mmap_sem); - page = gfn_to_page(vcpu->kvm, gfn); + if (is_large_pte(gpte) && is_largepage_backed(vcpu, gfn)) { + gfn &= ~(KVM_PAGES_PER_HPAGE-1); + vcpu->arch.update_pte.largepage = 1; + } + pfn = gfn_to_pfn(vcpu->kvm, gfn); up_read(¤t->mm->mmap_sem); + if (is_error_pfn(pfn)) { + kvm_release_pfn_clean(pfn); + return; + } vcpu->arch.update_pte.gfn = gfn; - vcpu->arch.update_pte.page = page; + vcpu->arch.update_pte.pfn = pfn; } void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, @@ -1423,7 +1697,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, struct hlist_node *node, *n; struct hlist_head *bucket; unsigned index; - u64 entry; + u64 entry, gentry; u64 *spte; unsigned offset = offset_in_page(gpa); unsigned pte_size; @@ -1433,8 +1707,9 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, int level; int flooded = 0; int npte; + int r; - pgprintk("%s: gpa %llx bytes %d\n", __FUNCTION__, gpa, bytes); + pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes); mmu_guess_page_from_pte_write(vcpu, gpa, new, bytes); spin_lock(&vcpu->kvm->mmu_lock); kvm_mmu_free_some_pages(vcpu); @@ -1450,7 +1725,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, vcpu->arch.last_pt_write_count = 1; vcpu->arch.last_pte_updated = NULL; } - index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES; + index = kvm_page_table_hashfn(gfn); bucket = &vcpu->kvm->arch.mmu_page_hash[index]; hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) { if (sp->gfn != gfn || sp->role.metaphysical) @@ -1496,20 +1771,29 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, continue; } spte = &sp->spt[page_offset / sizeof(*spte)]; + if ((gpa & (pte_size - 1)) || (bytes < pte_size)) { + gentry = 0; + r = kvm_read_guest_atomic(vcpu->kvm, + gpa & ~(u64)(pte_size - 1), + &gentry, pte_size); + new = (const void *)&gentry; + if (r < 0) + new = NULL; + } while (npte--) { entry = *spte; mmu_pte_write_zap_pte(vcpu, sp, spte); - mmu_pte_write_new_pte(vcpu, sp, spte, new, bytes, - page_offset & (pte_size - 1)); + if (new) + mmu_pte_write_new_pte(vcpu, sp, spte, new); mmu_pte_write_flush_tlb(vcpu, entry, *spte); ++spte; } } kvm_mmu_audit(vcpu, "post pte write"); spin_unlock(&vcpu->kvm->mmu_lock); - if (vcpu->arch.update_pte.page) { - kvm_release_page_clean(vcpu->arch.update_pte.page); - vcpu->arch.update_pte.page = NULL; + if (!is_error_pfn(vcpu->arch.update_pte.pfn)) { + kvm_release_pfn_clean(vcpu->arch.update_pte.pfn); + vcpu->arch.update_pte.pfn = bad_pfn; } } @@ -1518,9 +1802,7 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) gpa_t gpa; int r; - down_read(&vcpu->kvm->slots_lock); gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gva); - up_read(&vcpu->kvm->slots_lock); spin_lock(&vcpu->kvm->mmu_lock); r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT); @@ -1577,6 +1859,12 @@ out: } EXPORT_SYMBOL_GPL(kvm_mmu_page_fault); +void kvm_enable_tdp(void) +{ + tdp_enabled = true; +} +EXPORT_SYMBOL_GPL(kvm_enable_tdp); + static void free_mmu_pages(struct kvm_vcpu *vcpu) { struct kvm_mmu_page *sp; @@ -1677,7 +1965,53 @@ void kvm_mmu_zap_all(struct kvm *kvm) kvm_flush_remote_tlbs(kvm); } -void kvm_mmu_module_exit(void) +void kvm_mmu_remove_one_alloc_mmu_page(struct kvm *kvm) +{ + struct kvm_mmu_page *page; + + page = container_of(kvm->arch.active_mmu_pages.prev, + struct kvm_mmu_page, link); + kvm_mmu_zap_page(kvm, page); +} + +static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask) +{ + struct kvm *kvm; + struct kvm *kvm_freed = NULL; + int cache_count = 0; + + spin_lock(&kvm_lock); + + list_for_each_entry(kvm, &vm_list, vm_list) { + int npages; + + spin_lock(&kvm->mmu_lock); + npages = kvm->arch.n_alloc_mmu_pages - + kvm->arch.n_free_mmu_pages; + cache_count += npages; + if (!kvm_freed && nr_to_scan > 0 && npages > 0) { + kvm_mmu_remove_one_alloc_mmu_page(kvm); + cache_count--; + kvm_freed = kvm; + } + nr_to_scan--; + + spin_unlock(&kvm->mmu_lock); + } + if (kvm_freed) + list_move_tail(&kvm_freed->vm_list, &vm_list); + + spin_unlock(&kvm_lock); + + return cache_count; +} + +static struct shrinker mmu_shrinker = { + .shrink = mmu_shrink, + .seeks = DEFAULT_SEEKS * 10, +}; + +void mmu_destroy_caches(void) { if (pte_chain_cache) kmem_cache_destroy(pte_chain_cache); @@ -1687,6 +2021,12 @@ void kvm_mmu_module_exit(void) kmem_cache_destroy(mmu_page_header_cache); } +void kvm_mmu_module_exit(void) +{ + mmu_destroy_caches(); + unregister_shrinker(&mmu_shrinker); +} + int kvm_mmu_module_init(void) { pte_chain_cache = kmem_cache_create("kvm_pte_chain", @@ -1706,10 +2046,12 @@ int kvm_mmu_module_init(void) if (!mmu_page_header_cache) goto nomem; + register_shrinker(&mmu_shrinker); + return 0; nomem: - kvm_mmu_module_exit(); + mmu_destroy_caches(); return -ENOMEM; } @@ -1732,6 +2074,127 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm) return nr_mmu_pages; } +static void *pv_mmu_peek_buffer(struct kvm_pv_mmu_op_buffer *buffer, + unsigned len) +{ + if (len > buffer->len) + return NULL; + return buffer->ptr; +} + +static void *pv_mmu_read_buffer(struct kvm_pv_mmu_op_buffer *buffer, + unsigned len) +{ + void *ret; + + ret = pv_mmu_peek_buffer(buffer, len); + if (!ret) + return ret; + buffer->ptr += len; + buffer->len -= len; + buffer->processed += len; + return ret; +} + +static int kvm_pv_mmu_write(struct kvm_vcpu *vcpu, + gpa_t addr, gpa_t value) +{ + int bytes = 8; + int r; + + if (!is_long_mode(vcpu) && !is_pae(vcpu)) + bytes = 4; + + r = mmu_topup_memory_caches(vcpu); + if (r) + return r; + + if (!emulator_write_phys(vcpu, addr, &value, bytes)) + return -EFAULT; + + return 1; +} + +static int kvm_pv_mmu_flush_tlb(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops->tlb_flush(vcpu); + return 1; +} + +static int kvm_pv_mmu_release_pt(struct kvm_vcpu *vcpu, gpa_t addr) +{ + spin_lock(&vcpu->kvm->mmu_lock); + mmu_unshadow(vcpu->kvm, addr >> PAGE_SHIFT); + spin_unlock(&vcpu->kvm->mmu_lock); + return 1; +} + +static int kvm_pv_mmu_op_one(struct kvm_vcpu *vcpu, + struct kvm_pv_mmu_op_buffer *buffer) +{ + struct kvm_mmu_op_header *header; + + header = pv_mmu_peek_buffer(buffer, sizeof *header); + if (!header) + return 0; + switch (header->op) { + case KVM_MMU_OP_WRITE_PTE: { + struct kvm_mmu_op_write_pte *wpte; + + wpte = pv_mmu_read_buffer(buffer, sizeof *wpte); + if (!wpte) + return 0; + return kvm_pv_mmu_write(vcpu, wpte->pte_phys, + wpte->pte_val); + } + case KVM_MMU_OP_FLUSH_TLB: { + struct kvm_mmu_op_flush_tlb *ftlb; + + ftlb = pv_mmu_read_buffer(buffer, sizeof *ftlb); + if (!ftlb) + return 0; + return kvm_pv_mmu_flush_tlb(vcpu); + } + case KVM_MMU_OP_RELEASE_PT: { + struct kvm_mmu_op_release_pt *rpt; + + rpt = pv_mmu_read_buffer(buffer, sizeof *rpt); + if (!rpt) + return 0; + return kvm_pv_mmu_release_pt(vcpu, rpt->pt_phys); + } + default: return 0; + } +} + +int kvm_pv_mmu_op(struct kvm_vcpu *vcpu, unsigned long bytes, + gpa_t addr, unsigned long *ret) +{ + int r; + struct kvm_pv_mmu_op_buffer buffer; + + buffer.ptr = buffer.buf; + buffer.len = min_t(unsigned long, bytes, sizeof buffer.buf); + buffer.processed = 0; + + r = kvm_read_guest(vcpu->kvm, addr, buffer.buf, buffer.len); + if (r) + goto out; + + while (buffer.len) { + r = kvm_pv_mmu_op_one(vcpu, &buffer); + if (r < 0) + goto out; + if (r == 0) + break; + } + + r = 1; +out: + *ret = buffer.processed; + return r; +} + #ifdef AUDIT static const char *audit_msg; @@ -1768,8 +2231,7 @@ static void audit_mappings_page(struct kvm_vcpu *vcpu, u64 page_pte, audit_mappings_page(vcpu, ent, va, level - 1); } else { gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, va); - struct page *page = gpa_to_page(vcpu, gpa); - hpa_t hpa = page_to_phys(page); + hpa_t hpa = (hpa_t)gpa_to_pfn(vcpu, gpa) << PAGE_SHIFT; if (is_shadow_present_pte(ent) && (ent & PT64_BASE_ADDR_MASK) != hpa) @@ -1782,7 +2244,7 @@ static void audit_mappings_page(struct kvm_vcpu *vcpu, u64 page_pte, && !is_error_hpa(hpa)) printk(KERN_ERR "audit: (%s) notrap shadow," " valid guest gva %lx\n", audit_msg, va); - kvm_release_page_clean(page); + kvm_release_pfn_clean(pfn); } } @@ -1867,7 +2329,7 @@ static void audit_rmap(struct kvm_vcpu *vcpu) if (n_rmap != n_actual) printk(KERN_ERR "%s: (%s) rmap %d actual %d\n", - __FUNCTION__, audit_msg, n_rmap, n_actual); + __func__, audit_msg, n_rmap, n_actual); } static void audit_write_protection(struct kvm_vcpu *vcpu) @@ -1887,7 +2349,7 @@ static void audit_write_protection(struct kvm_vcpu *vcpu) if (*rmapp) printk(KERN_ERR "%s: (%s) shadow page has writable" " mappings: gfn %lx role %x\n", - __FUNCTION__, audit_msg, sp->gfn, + __func__, audit_msg, sp->gfn, sp->role.word); } } diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 1fce19ec7a23..e64e9f56a65e 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -3,6 +3,12 @@ #include <linux/kvm_host.h> +#ifdef CONFIG_X86_64 +#define TDP_ROOT_LEVEL PT64_ROOT_LEVEL +#else +#define TDP_ROOT_LEVEL PT32E_ROOT_LEVEL +#endif + static inline void kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu) { if (unlikely(vcpu->kvm->arch.n_free_mmu_pages < KVM_MIN_FREE_MMU_PAGES)) diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index ecc0856268c4..156fe10288ae 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -130,7 +130,7 @@ static int FNAME(walk_addr)(struct guest_walker *walker, unsigned index, pt_access, pte_access; gpa_t pte_gpa; - pgprintk("%s: addr %lx\n", __FUNCTION__, addr); + pgprintk("%s: addr %lx\n", __func__, addr); walk: walker->level = vcpu->arch.mmu.root_level; pte = vcpu->arch.cr3; @@ -155,7 +155,7 @@ walk: pte_gpa += index * sizeof(pt_element_t); walker->table_gfn[walker->level - 1] = table_gfn; walker->pte_gpa[walker->level - 1] = pte_gpa; - pgprintk("%s: table_gfn[%d] %lx\n", __FUNCTION__, + pgprintk("%s: table_gfn[%d] %lx\n", __func__, walker->level - 1, table_gfn); kvm_read_guest(vcpu->kvm, pte_gpa, &pte, sizeof(pte)); @@ -222,7 +222,7 @@ walk: walker->pt_access = pt_access; walker->pte_access = pte_access; pgprintk("%s: pte %llx pte_access %x pt_access %x\n", - __FUNCTION__, (u64)pte, pt_access, pte_access); + __func__, (u64)pte, pt_access, pte_access); return 1; not_present: @@ -243,31 +243,30 @@ err: } static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page, - u64 *spte, const void *pte, int bytes, - int offset_in_pte) + u64 *spte, const void *pte) { pt_element_t gpte; unsigned pte_access; - struct page *npage; + pfn_t pfn; + int largepage = vcpu->arch.update_pte.largepage; gpte = *(const pt_element_t *)pte; if (~gpte & (PT_PRESENT_MASK | PT_ACCESSED_MASK)) { - if (!offset_in_pte && !is_present_pte(gpte)) + if (!is_present_pte(gpte)) set_shadow_pte(spte, shadow_notrap_nonpresent_pte); return; } - if (bytes < sizeof(pt_element_t)) - return; - pgprintk("%s: gpte %llx spte %p\n", __FUNCTION__, (u64)gpte, spte); + pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte); pte_access = page->role.access & FNAME(gpte_access)(vcpu, gpte); if (gpte_to_gfn(gpte) != vcpu->arch.update_pte.gfn) return; - npage = vcpu->arch.update_pte.page; - if (!npage) + pfn = vcpu->arch.update_pte.pfn; + if (is_error_pfn(pfn)) return; - get_page(npage); + kvm_get_pfn(pfn); mmu_set_spte(vcpu, spte, page->role.access, pte_access, 0, 0, - gpte & PT_DIRTY_MASK, NULL, gpte_to_gfn(gpte), npage); + gpte & PT_DIRTY_MASK, NULL, largepage, gpte_to_gfn(gpte), + pfn, true); } /* @@ -275,8 +274,8 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page, */ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, struct guest_walker *walker, - int user_fault, int write_fault, int *ptwrite, - struct page *page) + int user_fault, int write_fault, int largepage, + int *ptwrite, pfn_t pfn) { hpa_t shadow_addr; int level; @@ -304,11 +303,19 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, shadow_ent = ((u64 *)__va(shadow_addr)) + index; if (level == PT_PAGE_TABLE_LEVEL) break; - if (is_shadow_present_pte(*shadow_ent)) { + + if (largepage && level == PT_DIRECTORY_LEVEL) + break; + + if (is_shadow_present_pte(*shadow_ent) + && !is_large_pte(*shadow_ent)) { shadow_addr = *shadow_ent & PT64_BASE_ADDR_MASK; continue; } + if (is_large_pte(*shadow_ent)) + rmap_remove(vcpu->kvm, shadow_ent); + if (level - 1 == PT_PAGE_TABLE_LEVEL && walker->level == PT_DIRECTORY_LEVEL) { metaphysical = 1; @@ -329,7 +336,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, walker->pte_gpa[level - 2], &curr_pte, sizeof(curr_pte)); if (r || curr_pte != walker->ptes[level - 2]) { - kvm_release_page_clean(page); + kvm_release_pfn_clean(pfn); return NULL; } } @@ -342,7 +349,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, mmu_set_spte(vcpu, shadow_ent, access, walker->pte_access & access, user_fault, write_fault, walker->ptes[walker->level-1] & PT_DIRTY_MASK, - ptwrite, walker->gfn, page); + ptwrite, largepage, walker->gfn, pfn, false); return shadow_ent; } @@ -371,16 +378,16 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u64 *shadow_pte; int write_pt = 0; int r; - struct page *page; + pfn_t pfn; + int largepage = 0; - pgprintk("%s: addr %lx err %x\n", __FUNCTION__, addr, error_code); + pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code); kvm_mmu_audit(vcpu, "pre page fault"); r = mmu_topup_memory_caches(vcpu); if (r) return r; - down_read(&vcpu->kvm->slots_lock); /* * Look up the shadow pte for the faulting address. */ @@ -391,40 +398,45 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, * The page is not mapped by the guest. Let the guest handle it. */ if (!r) { - pgprintk("%s: guest page fault\n", __FUNCTION__); + pgprintk("%s: guest page fault\n", __func__); inject_page_fault(vcpu, addr, walker.error_code); vcpu->arch.last_pt_write_count = 0; /* reset fork detector */ - up_read(&vcpu->kvm->slots_lock); return 0; } down_read(¤t->mm->mmap_sem); - page = gfn_to_page(vcpu->kvm, walker.gfn); + if (walker.level == PT_DIRECTORY_LEVEL) { + gfn_t large_gfn; + large_gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE-1); + if (is_largepage_backed(vcpu, large_gfn)) { + walker.gfn = large_gfn; + largepage = 1; + } + } + pfn = gfn_to_pfn(vcpu->kvm, walker.gfn); up_read(¤t->mm->mmap_sem); + /* mmio */ + if (is_error_pfn(pfn)) { + pgprintk("gfn %x is mmio\n", walker.gfn); + kvm_release_pfn_clean(pfn); + return 1; + } + spin_lock(&vcpu->kvm->mmu_lock); kvm_mmu_free_some_pages(vcpu); shadow_pte = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault, - &write_pt, page); - pgprintk("%s: shadow pte %p %llx ptwrite %d\n", __FUNCTION__, + largepage, &write_pt, pfn); + + pgprintk("%s: shadow pte %p %llx ptwrite %d\n", __func__, shadow_pte, *shadow_pte, write_pt); if (!write_pt) vcpu->arch.last_pt_write_count = 0; /* reset fork detector */ - /* - * mmio: emulate if accessible, otherwise its a guest fault. - */ - if (shadow_pte && is_io_pte(*shadow_pte)) { - spin_unlock(&vcpu->kvm->mmu_lock); - up_read(&vcpu->kvm->slots_lock); - return 1; - } - ++vcpu->stat.pf_fixed; kvm_mmu_audit(vcpu, "post page fault (fixed)"); spin_unlock(&vcpu->kvm->mmu_lock); - up_read(&vcpu->kvm->slots_lock); return write_pt; } diff --git a/arch/x86/kvm/segment_descriptor.h b/arch/x86/kvm/segment_descriptor.h deleted file mode 100644 index 56fc4c873389..000000000000 --- a/arch/x86/kvm/segment_descriptor.h +++ /dev/null @@ -1,29 +0,0 @@ -#ifndef __SEGMENT_DESCRIPTOR_H -#define __SEGMENT_DESCRIPTOR_H - -struct segment_descriptor { - u16 limit_low; - u16 base_low; - u8 base_mid; - u8 type : 4; - u8 system : 1; - u8 dpl : 2; - u8 present : 1; - u8 limit_high : 4; - u8 avl : 1; - u8 long_mode : 1; - u8 default_op : 1; - u8 granularity : 1; - u8 base_high; -} __attribute__((packed)); - -#ifdef CONFIG_X86_64 -/* LDT or TSS descriptor in the GDT. 16 bytes. */ -struct segment_descriptor_64 { - struct segment_descriptor s; - u32 base_higher; - u32 pad_zero; -}; - -#endif -#endif diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 1a582f1090e8..89e0be2c10d0 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -47,6 +47,18 @@ MODULE_LICENSE("GPL"); #define SVM_FEATURE_LBRV (1 << 1) #define SVM_DEATURE_SVML (1 << 2) +#define DEBUGCTL_RESERVED_BITS (~(0x3fULL)) + +/* enable NPT for AMD64 and X86 with PAE */ +#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) +static bool npt_enabled = true; +#else +static bool npt_enabled = false; +#endif +static int npt = 1; + +module_param(npt, int, S_IRUGO); + static void kvm_reput_irq(struct vcpu_svm *svm); static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu) @@ -54,8 +66,7 @@ static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu) return container_of(vcpu, struct vcpu_svm, vcpu); } -unsigned long iopm_base; -unsigned long msrpm_base; +static unsigned long iopm_base; struct kvm_ldttss_desc { u16 limit0; @@ -182,7 +193,7 @@ static inline void flush_guest_tlb(struct kvm_vcpu *vcpu) static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) { - if (!(efer & EFER_LMA)) + if (!npt_enabled && !(efer & EFER_LMA)) efer &= ~EFER_LME; to_svm(vcpu)->vmcb->save.efer = efer | MSR_EFER_SVME_MASK; @@ -219,12 +230,12 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); if (!svm->next_rip) { - printk(KERN_DEBUG "%s: NOP\n", __FUNCTION__); + printk(KERN_DEBUG "%s: NOP\n", __func__); return; } if (svm->next_rip - svm->vmcb->save.rip > MAX_INST_SIZE) printk(KERN_ERR "%s: ip 0x%llx next 0x%llx\n", - __FUNCTION__, + __func__, svm->vmcb->save.rip, svm->next_rip); @@ -279,11 +290,7 @@ static void svm_hardware_enable(void *garbage) struct svm_cpu_data *svm_data; uint64_t efer; -#ifdef CONFIG_X86_64 - struct desc_ptr gdt_descr; -#else struct desc_ptr gdt_descr; -#endif struct desc_struct *gdt; int me = raw_smp_processor_id(); @@ -302,7 +309,6 @@ static void svm_hardware_enable(void *garbage) svm_data->asid_generation = 1; svm_data->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1; svm_data->next_asid = svm_data->max_asid + 1; - svm_features = cpuid_edx(SVM_CPUID_FUNC); asm volatile ("sgdt %0" : "=m"(gdt_descr)); gdt = (struct desc_struct *)gdt_descr.address; @@ -361,12 +367,51 @@ static void set_msr_interception(u32 *msrpm, unsigned msr, BUG(); } +static void svm_vcpu_init_msrpm(u32 *msrpm) +{ + memset(msrpm, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER)); + +#ifdef CONFIG_X86_64 + set_msr_interception(msrpm, MSR_GS_BASE, 1, 1); + set_msr_interception(msrpm, MSR_FS_BASE, 1, 1); + set_msr_interception(msrpm, MSR_KERNEL_GS_BASE, 1, 1); + set_msr_interception(msrpm, MSR_LSTAR, 1, 1); + set_msr_interception(msrpm, MSR_CSTAR, 1, 1); + set_msr_interception(msrpm, MSR_SYSCALL_MASK, 1, 1); +#endif + set_msr_interception(msrpm, MSR_K6_STAR, 1, 1); + set_msr_interception(msrpm, MSR_IA32_SYSENTER_CS, 1, 1); + set_msr_interception(msrpm, MSR_IA32_SYSENTER_ESP, 1, 1); + set_msr_interception(msrpm, MSR_IA32_SYSENTER_EIP, 1, 1); +} + +static void svm_enable_lbrv(struct vcpu_svm *svm) +{ + u32 *msrpm = svm->msrpm; + + svm->vmcb->control.lbr_ctl = 1; + set_msr_interception(msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1); + set_msr_interception(msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1); + set_msr_interception(msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); + set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 1, 1); +} + +static void svm_disable_lbrv(struct vcpu_svm *svm) +{ + u32 *msrpm = svm->msrpm; + + svm->vmcb->control.lbr_ctl = 0; + set_msr_interception(msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0); + set_msr_interception(msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0); + set_msr_interception(msrpm, MSR_IA32_LASTINTFROMIP, 0, 0); + set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0); +} + static __init int svm_hardware_setup(void) { int cpu; struct page *iopm_pages; - struct page *msrpm_pages; - void *iopm_va, *msrpm_va; + void *iopm_va; int r; iopm_pages = alloc_pages(GFP_KERNEL, IOPM_ALLOC_ORDER); @@ -379,41 +424,33 @@ static __init int svm_hardware_setup(void) clear_bit(0x80, iopm_va); /* allow direct access to PC debug port */ iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT; + if (boot_cpu_has(X86_FEATURE_NX)) + kvm_enable_efer_bits(EFER_NX); - msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER); + for_each_online_cpu(cpu) { + r = svm_cpu_init(cpu); + if (r) + goto err; + } - r = -ENOMEM; - if (!msrpm_pages) - goto err_1; + svm_features = cpuid_edx(SVM_CPUID_FUNC); - msrpm_va = page_address(msrpm_pages); - memset(msrpm_va, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER)); - msrpm_base = page_to_pfn(msrpm_pages) << PAGE_SHIFT; + if (!svm_has(SVM_FEATURE_NPT)) + npt_enabled = false; -#ifdef CONFIG_X86_64 - set_msr_interception(msrpm_va, MSR_GS_BASE, 1, 1); - set_msr_interception(msrpm_va, MSR_FS_BASE, 1, 1); - set_msr_interception(msrpm_va, MSR_KERNEL_GS_BASE, 1, 1); - set_msr_interception(msrpm_va, MSR_LSTAR, 1, 1); - set_msr_interception(msrpm_va, MSR_CSTAR, 1, 1); - set_msr_interception(msrpm_va, MSR_SYSCALL_MASK, 1, 1); -#endif - set_msr_interception(msrpm_va, MSR_K6_STAR, 1, 1); - set_msr_interception(msrpm_va, MSR_IA32_SYSENTER_CS, 1, 1); - set_msr_interception(msrpm_va, MSR_IA32_SYSENTER_ESP, 1, 1); - set_msr_interception(msrpm_va, MSR_IA32_SYSENTER_EIP, 1, 1); + if (npt_enabled && !npt) { + printk(KERN_INFO "kvm: Nested Paging disabled\n"); + npt_enabled = false; + } - for_each_online_cpu(cpu) { - r = svm_cpu_init(cpu); - if (r) - goto err_2; + if (npt_enabled) { + printk(KERN_INFO "kvm: Nested Paging enabled\n"); + kvm_enable_tdp(); } + return 0; -err_2: - __free_pages(msrpm_pages, MSRPM_ALLOC_ORDER); - msrpm_base = 0; -err_1: +err: __free_pages(iopm_pages, IOPM_ALLOC_ORDER); iopm_base = 0; return r; @@ -421,9 +458,8 @@ err_1: static __exit void svm_hardware_unsetup(void) { - __free_pages(pfn_to_page(msrpm_base >> PAGE_SHIFT), MSRPM_ALLOC_ORDER); __free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER); - iopm_base = msrpm_base = 0; + iopm_base = 0; } static void init_seg(struct vmcb_seg *seg) @@ -443,15 +479,14 @@ static void init_sys_seg(struct vmcb_seg *seg, uint32_t type) seg->base = 0; } -static void init_vmcb(struct vmcb *vmcb) +static void init_vmcb(struct vcpu_svm *svm) { - struct vmcb_control_area *control = &vmcb->control; - struct vmcb_save_area *save = &vmcb->save; + struct vmcb_control_area *control = &svm->vmcb->control; + struct vmcb_save_area *save = &svm->vmcb->save; control->intercept_cr_read = INTERCEPT_CR0_MASK | INTERCEPT_CR3_MASK | - INTERCEPT_CR4_MASK | - INTERCEPT_CR8_MASK; + INTERCEPT_CR4_MASK; control->intercept_cr_write = INTERCEPT_CR0_MASK | INTERCEPT_CR3_MASK | @@ -471,23 +506,13 @@ static void init_vmcb(struct vmcb *vmcb) INTERCEPT_DR7_MASK; control->intercept_exceptions = (1 << PF_VECTOR) | - (1 << UD_VECTOR); + (1 << UD_VECTOR) | + (1 << MC_VECTOR); control->intercept = (1ULL << INTERCEPT_INTR) | (1ULL << INTERCEPT_NMI) | (1ULL << INTERCEPT_SMI) | - /* - * selective cr0 intercept bug? - * 0: 0f 22 d8 mov %eax,%cr3 - * 3: 0f 20 c0 mov %cr0,%eax - * 6: 0d 00 00 00 80 or $0x80000000,%eax - * b: 0f 22 c0 mov %eax,%cr0 - * set cr3 ->interception - * get cr0 ->interception - * set cr0 -> no interception - */ - /* (1ULL << INTERCEPT_SELECTIVE_CR0) | */ (1ULL << INTERCEPT_CPUID) | (1ULL << INTERCEPT_INVD) | (1ULL << INTERCEPT_HLT) | @@ -508,7 +533,7 @@ static void init_vmcb(struct vmcb *vmcb) (1ULL << INTERCEPT_MWAIT); control->iopm_base_pa = iopm_base; - control->msrpm_base_pa = msrpm_base; + control->msrpm_base_pa = __pa(svm->msrpm); control->tsc_offset = 0; control->int_ctl = V_INTR_MASKING_MASK; @@ -550,13 +575,30 @@ static void init_vmcb(struct vmcb *vmcb) save->cr0 = 0x00000010 | X86_CR0_PG | X86_CR0_WP; save->cr4 = X86_CR4_PAE; /* rdx = ?? */ + + if (npt_enabled) { + /* Setup VMCB for Nested Paging */ + control->nested_ctl = 1; + control->intercept &= ~(1ULL << INTERCEPT_TASK_SWITCH); + control->intercept_exceptions &= ~(1 << PF_VECTOR); + control->intercept_cr_read &= ~(INTERCEPT_CR0_MASK| + INTERCEPT_CR3_MASK); + control->intercept_cr_write &= ~(INTERCEPT_CR0_MASK| + INTERCEPT_CR3_MASK); + save->g_pat = 0x0007040600070406ULL; + /* enable caching because the QEMU Bios doesn't enable it */ + save->cr0 = X86_CR0_ET; + save->cr3 = 0; + save->cr4 = 0; + } + force_new_asid(&svm->vcpu); } static int svm_vcpu_reset(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - init_vmcb(svm->vmcb); + init_vmcb(svm); if (vcpu->vcpu_id != 0) { svm->vmcb->save.rip = 0; @@ -571,6 +613,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) { struct vcpu_svm *svm; struct page *page; + struct page *msrpm_pages; int err; svm = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); @@ -589,12 +632,19 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) goto uninit; } + err = -ENOMEM; + msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER); + if (!msrpm_pages) + goto uninit; + svm->msrpm = page_address(msrpm_pages); + svm_vcpu_init_msrpm(svm->msrpm); + svm->vmcb = page_address(page); clear_page(svm->vmcb); svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT; svm->asid_generation = 0; memset(svm->db_regs, 0, sizeof(svm->db_regs)); - init_vmcb(svm->vmcb); + init_vmcb(svm); fx_init(&svm->vcpu); svm->vcpu.fpu_active = 1; @@ -617,6 +667,7 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); __free_page(pfn_to_page(svm->vmcb_pa >> PAGE_SHIFT)); + __free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, svm); } @@ -731,6 +782,13 @@ static void svm_get_segment(struct kvm_vcpu *vcpu, var->unusable = !var->present; } +static int svm_get_cpl(struct kvm_vcpu *vcpu) +{ + struct vmcb_save_area *save = &to_svm(vcpu)->vmcb->save; + + return save->cpl; +} + static void svm_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) { struct vcpu_svm *svm = to_svm(vcpu); @@ -784,6 +842,9 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) } } #endif + if (npt_enabled) + goto set; + if ((vcpu->arch.cr0 & X86_CR0_TS) && !(cr0 & X86_CR0_TS)) { svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR); vcpu->fpu_active = 1; @@ -791,18 +852,29 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) vcpu->arch.cr0 = cr0; cr0 |= X86_CR0_PG | X86_CR0_WP; - cr0 &= ~(X86_CR0_CD | X86_CR0_NW); if (!vcpu->fpu_active) { svm->vmcb->control.intercept_exceptions |= (1 << NM_VECTOR); cr0 |= X86_CR0_TS; } +set: + /* + * re-enable caching here because the QEMU bios + * does not do it - this results in some delay at + * reboot + */ + cr0 &= ~(X86_CR0_CD | X86_CR0_NW); svm->vmcb->save.cr0 = cr0; } static void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { - vcpu->arch.cr4 = cr4; - to_svm(vcpu)->vmcb->save.cr4 = cr4 | X86_CR4_PAE; + unsigned long host_cr4_mce = read_cr4() & X86_CR4_MCE; + + vcpu->arch.cr4 = cr4; + if (!npt_enabled) + cr4 |= X86_CR4_PAE; + cr4 |= host_cr4_mce; + to_svm(vcpu)->vmcb->save.cr4 = cr4; } static void svm_set_segment(struct kvm_vcpu *vcpu, @@ -833,13 +905,6 @@ static void svm_set_segment(struct kvm_vcpu *vcpu, } -/* FIXME: - - svm(vcpu)->vmcb->control.int_ctl &= ~V_TPR_MASK; - svm(vcpu)->vmcb->control.int_ctl |= (sregs->cr8 & V_TPR_MASK); - -*/ - static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg) { return -EOPNOTSUPP; @@ -920,7 +985,7 @@ static void svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value, } default: printk(KERN_DEBUG "%s: unexpected dr %u\n", - __FUNCTION__, dr); + __func__, dr); *exception = UD_VECTOR; return; } @@ -962,6 +1027,19 @@ static int nm_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } +static int mc_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + /* + * On an #MC intercept the MCE handler is not called automatically in + * the host. So do it by hand here. + */ + asm volatile ( + "int $0x12\n"); + /* not sure if we ever come back to this point */ + + return 1; +} + static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) { /* @@ -969,7 +1047,7 @@ static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) * so reinitialize it. */ clear_page(svm->vmcb); - init_vmcb(svm->vmcb); + init_vmcb(svm); kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; return 0; @@ -1033,9 +1111,18 @@ static int invalid_op_interception(struct vcpu_svm *svm, static int task_switch_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) { - pr_unimpl(&svm->vcpu, "%s: task switch is unsupported\n", __FUNCTION__); - kvm_run->exit_reason = KVM_EXIT_UNKNOWN; - return 0; + u16 tss_selector; + + tss_selector = (u16)svm->vmcb->control.exit_info_1; + if (svm->vmcb->control.exit_info_2 & + (1ULL << SVM_EXITINFOSHIFT_TS_REASON_IRET)) + return kvm_task_switch(&svm->vcpu, tss_selector, + TASK_SWITCH_IRET); + if (svm->vmcb->control.exit_info_2 & + (1ULL << SVM_EXITINFOSHIFT_TS_REASON_JMP)) + return kvm_task_switch(&svm->vcpu, tss_selector, + TASK_SWITCH_JMP); + return kvm_task_switch(&svm->vcpu, tss_selector, TASK_SWITCH_CALL); } static int cpuid_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) @@ -1049,7 +1136,7 @@ static int emulate_on_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) { if (emulate_instruction(&svm->vcpu, NULL, 0, 0, 0) != EMULATE_DONE) - pr_unimpl(&svm->vcpu, "%s: failed\n", __FUNCTION__); + pr_unimpl(&svm->vcpu, "%s: failed\n", __func__); return 1; } @@ -1179,8 +1266,19 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) svm->vmcb->save.sysenter_esp = data; break; case MSR_IA32_DEBUGCTLMSR: - pr_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n", - __FUNCTION__, data); + if (!svm_has(SVM_FEATURE_LBRV)) { + pr_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTL 0x%llx, nop\n", + __func__, data); + break; + } + if (data & DEBUGCTL_RESERVED_BITS) + return 1; + + svm->vmcb->save.dbgctl = data; + if (data & (1ULL<<0)) + svm_enable_lbrv(svm); + else + svm_disable_lbrv(svm); break; case MSR_K7_EVNTSEL0: case MSR_K7_EVNTSEL1: @@ -1265,6 +1363,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm, [SVM_EXIT_EXCP_BASE + UD_VECTOR] = ud_interception, [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception, [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception, + [SVM_EXIT_EXCP_BASE + MC_VECTOR] = mc_interception, [SVM_EXIT_INTR] = nop_on_interception, [SVM_EXIT_NMI] = nop_on_interception, [SVM_EXIT_SMI] = nop_on_interception, @@ -1290,14 +1389,34 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm, [SVM_EXIT_WBINVD] = emulate_on_interception, [SVM_EXIT_MONITOR] = invalid_op_interception, [SVM_EXIT_MWAIT] = invalid_op_interception, + [SVM_EXIT_NPF] = pf_interception, }; - static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); u32 exit_code = svm->vmcb->control.exit_code; + if (npt_enabled) { + int mmu_reload = 0; + if ((vcpu->arch.cr0 ^ svm->vmcb->save.cr0) & X86_CR0_PG) { + svm_set_cr0(vcpu, svm->vmcb->save.cr0); + mmu_reload = 1; + } + vcpu->arch.cr0 = svm->vmcb->save.cr0; + vcpu->arch.cr3 = svm->vmcb->save.cr3; + if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) { + if (!load_pdptrs(vcpu, vcpu->arch.cr3)) { + kvm_inject_gp(vcpu, 0); + return 1; + } + } + if (mmu_reload) { + kvm_mmu_reset_context(vcpu); + kvm_mmu_load(vcpu); + } + } + kvm_reput_irq(svm); if (svm->vmcb->control.exit_code == SVM_EXIT_ERR) { @@ -1308,10 +1427,11 @@ static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) } if (is_external_interrupt(svm->vmcb->control.exit_int_info) && - exit_code != SVM_EXIT_EXCP_BASE + PF_VECTOR) + exit_code != SVM_EXIT_EXCP_BASE + PF_VECTOR && + exit_code != SVM_EXIT_NPF) printk(KERN_ERR "%s: unexpected exit_ini_info 0x%x " "exit_code 0x%x\n", - __FUNCTION__, svm->vmcb->control.exit_int_info, + __func__, svm->vmcb->control.exit_int_info, exit_code); if (exit_code >= ARRAY_SIZE(svm_exit_handlers) @@ -1364,6 +1484,27 @@ static void svm_set_irq(struct kvm_vcpu *vcpu, int irq) svm_inject_irq(svm, irq); } +static void update_cr8_intercept(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb *vmcb = svm->vmcb; + int max_irr, tpr; + + if (!irqchip_in_kernel(vcpu->kvm) || vcpu->arch.apic->vapic_addr) + return; + + vmcb->control.intercept_cr_write &= ~INTERCEPT_CR8_MASK; + + max_irr = kvm_lapic_find_highest_irr(vcpu); + if (max_irr == -1) + return; + + tpr = kvm_lapic_get_cr8(vcpu) << 4; + + if (tpr >= (max_irr & 0xf0)) + vmcb->control.intercept_cr_write |= INTERCEPT_CR8_MASK; +} + static void svm_intr_assist(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1376,14 +1517,14 @@ static void svm_intr_assist(struct kvm_vcpu *vcpu) SVM_EVTINJ_VEC_MASK; vmcb->control.exit_int_info = 0; svm_inject_irq(svm, intr_vector); - return; + goto out; } if (vmcb->control.int_ctl & V_IRQ_MASK) - return; + goto out; if (!kvm_cpu_has_interrupt(vcpu)) - return; + goto out; if (!(vmcb->save.rflags & X86_EFLAGS_IF) || (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) || @@ -1391,12 +1532,14 @@ static void svm_intr_assist(struct kvm_vcpu *vcpu) /* unable to deliver irq, set pending irq */ vmcb->control.intercept |= (1ULL << INTERCEPT_VINTR); svm_inject_irq(svm, 0x0); - return; + goto out; } /* Okay, we can deliver the interrupt: grab it and update PIC state. */ intr_vector = kvm_cpu_get_interrupt(vcpu); svm_inject_irq(svm, intr_vector); kvm_timer_intr_post(vcpu, intr_vector); +out: + update_cr8_intercept(vcpu); } static void kvm_reput_irq(struct vcpu_svm *svm) @@ -1482,6 +1625,29 @@ static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu) { } +static inline void sync_cr8_to_lapic(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR8_MASK)) { + int cr8 = svm->vmcb->control.int_ctl & V_TPR_MASK; + kvm_lapic_set_tpr(vcpu, cr8); + } +} + +static inline void sync_lapic_to_cr8(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u64 cr8; + + if (!irqchip_in_kernel(vcpu->kvm)) + return; + + cr8 = kvm_get_cr8(vcpu); + svm->vmcb->control.int_ctl &= ~V_TPR_MASK; + svm->vmcb->control.int_ctl |= cr8 & V_TPR_MASK; +} + static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1491,6 +1657,8 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) pre_svm_run(svm); + sync_lapic_to_cr8(vcpu); + save_host_msrs(vcpu); fs_selector = read_fs(); gs_selector = read_gs(); @@ -1499,6 +1667,9 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) svm->host_dr6 = read_dr6(); svm->host_dr7 = read_dr7(); svm->vmcb->save.cr2 = vcpu->arch.cr2; + /* required for live migration with NPT */ + if (npt_enabled) + svm->vmcb->save.cr3 = vcpu->arch.cr3; if (svm->vmcb->save.dr7 & 0xff) { write_dr7(0); @@ -1635,6 +1806,8 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) stgi(); + sync_cr8_to_lapic(vcpu); + svm->next_rip = 0; } @@ -1642,6 +1815,12 @@ static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root) { struct vcpu_svm *svm = to_svm(vcpu); + if (npt_enabled) { + svm->vmcb->control.nested_cr3 = root; + force_new_asid(vcpu); + return; + } + svm->vmcb->save.cr3 = root; force_new_asid(vcpu); @@ -1709,6 +1888,7 @@ static struct kvm_x86_ops svm_x86_ops = { .get_segment_base = svm_get_segment_base, .get_segment = svm_get_segment, .set_segment = svm_set_segment, + .get_cpl = svm_get_cpl, .get_cs_db_l_bits = kvm_get_cs_db_l_bits, .decache_cr4_guest_bits = svm_decache_cr4_guest_bits, .set_cr0 = svm_set_cr0, diff --git a/arch/x86/kvm/svm.h b/arch/x86/kvm/svm.h index 5fd50491b555..1b8afa78e869 100644 --- a/arch/x86/kvm/svm.h +++ b/arch/x86/kvm/svm.h @@ -238,6 +238,9 @@ struct __attribute__ ((__packed__)) vmcb { #define SVM_EXITINTINFO_VALID SVM_EVTINJ_VALID #define SVM_EXITINTINFO_VALID_ERR SVM_EVTINJ_VALID_ERR +#define SVM_EXITINFOSHIFT_TS_REASON_IRET 36 +#define SVM_EXITINFOSHIFT_TS_REASON_JMP 38 + #define SVM_EXIT_READ_CR0 0x000 #define SVM_EXIT_READ_CR3 0x003 #define SVM_EXIT_READ_CR4 0x004 diff --git a/arch/x86/kvm/tss.h b/arch/x86/kvm/tss.h new file mode 100644 index 000000000000..622aa10f692f --- /dev/null +++ b/arch/x86/kvm/tss.h @@ -0,0 +1,59 @@ +#ifndef __TSS_SEGMENT_H +#define __TSS_SEGMENT_H + +struct tss_segment_32 { + u32 prev_task_link; + u32 esp0; + u32 ss0; + u32 esp1; + u32 ss1; + u32 esp2; + u32 ss2; + u32 cr3; + u32 eip; + u32 eflags; + u32 eax; + u32 ecx; + u32 edx; + u32 ebx; + u32 esp; + u32 ebp; + u32 esi; + u32 edi; + u32 es; + u32 cs; + u32 ss; + u32 ds; + u32 fs; + u32 gs; + u32 ldt_selector; + u16 t; + u16 io_map; +}; + +struct tss_segment_16 { + u16 prev_task_link; + u16 sp0; + u16 ss0; + u16 sp1; + u16 ss1; + u16 sp2; + u16 ss2; + u16 ip; + u16 flag; + u16 ax; + u16 cx; + u16 dx; + u16 bx; + u16 sp; + u16 bp; + u16 si; + u16 di; + u16 es; + u16 cs; + u16 ss; + u16 ds; + u16 ldt; +}; + +#endif diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 8e1462880d1f..8e5d6645b90d 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -17,7 +17,6 @@ #include "irq.h" #include "vmx.h" -#include "segment_descriptor.h" #include "mmu.h" #include <linux/kvm_host.h> @@ -37,6 +36,12 @@ MODULE_LICENSE("GPL"); static int bypass_guest_pf = 1; module_param(bypass_guest_pf, bool, 0); +static int enable_vpid = 1; +module_param(enable_vpid, bool, 0); + +static int flexpriority_enabled = 1; +module_param(flexpriority_enabled, bool, 0); + struct vmcs { u32 revision_id; u32 abort; @@ -71,6 +76,7 @@ struct vcpu_vmx { unsigned rip; } irq; } rmode; + int vpid; }; static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) @@ -85,6 +91,10 @@ static DEFINE_PER_CPU(struct vmcs *, current_vmcs); static struct page *vmx_io_bitmap_a; static struct page *vmx_io_bitmap_b; +static struct page *vmx_msr_bitmap; + +static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS); +static DEFINE_SPINLOCK(vmx_vpid_lock); static struct vmcs_config { int size; @@ -176,6 +186,11 @@ static inline int is_external_interrupt(u32 intr_info) == (INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK); } +static inline int cpu_has_vmx_msr_bitmap(void) +{ + return (vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS); +} + static inline int cpu_has_vmx_tpr_shadow(void) { return (vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW); @@ -194,8 +209,9 @@ static inline int cpu_has_secondary_exec_ctrls(void) static inline bool cpu_has_vmx_virtualize_apic_accesses(void) { - return (vmcs_config.cpu_based_2nd_exec_ctrl & - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES); + return flexpriority_enabled + && (vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES); } static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm) @@ -204,6 +220,12 @@ static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm) (irqchip_in_kernel(kvm))); } +static inline int cpu_has_vmx_vpid(void) +{ + return (vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_ENABLE_VPID); +} + static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr) { int i; @@ -214,6 +236,20 @@ static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr) return -1; } +static inline void __invvpid(int ext, u16 vpid, gva_t gva) +{ + struct { + u64 vpid : 16; + u64 rsvd : 48; + u64 gva; + } operand = { vpid, 0, gva }; + + asm volatile (ASM_VMX_INVVPID + /* CF==1 or ZF==1 --> rc = -1 */ + "; ja 1f ; ud2 ; 1:" + : : "a"(&operand), "c"(ext) : "cc", "memory"); +} + static struct kvm_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr) { int i; @@ -257,6 +293,14 @@ static void vcpu_clear(struct vcpu_vmx *vmx) vmx->launched = 0; } +static inline void vpid_sync_vcpu_all(struct vcpu_vmx *vmx) +{ + if (vmx->vpid == 0) + return; + + __invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vmx->vpid, 0); +} + static unsigned long vmcs_readl(unsigned long field) { unsigned long value; @@ -353,7 +397,7 @@ static void reload_tss(void) * VT restores TR but not its size. Useless. */ struct descriptor_table gdt; - struct segment_descriptor *descs; + struct desc_struct *descs; get_gdt(&gdt); descs = (void *)gdt.base; @@ -485,11 +529,12 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u64 phys_addr = __pa(vmx->vmcs); - u64 tsc_this, delta; + u64 tsc_this, delta, new_offset; if (vcpu->cpu != cpu) { vcpu_clear(vmx); kvm_migrate_apic_timer(vcpu); + vpid_sync_vcpu_all(vmx); } if (per_cpu(current_vmcs, cpu) != vmx->vmcs) { @@ -524,8 +569,11 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) * Make sure the time stamp counter is monotonous. */ rdtscll(tsc_this); - delta = vcpu->arch.host_tsc - tsc_this; - vmcs_write64(TSC_OFFSET, vmcs_read64(TSC_OFFSET) + delta); + if (tsc_this < vcpu->arch.host_tsc) { + delta = vcpu->arch.host_tsc - tsc_this; + new_offset = vmcs_read64(TSC_OFFSET) + delta; + vmcs_write64(TSC_OFFSET, new_offset); + } } } @@ -596,7 +644,7 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, { vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, nr | INTR_TYPE_EXCEPTION - | (has_error_code ? INTR_INFO_DELIEVER_CODE_MASK : 0) + | (has_error_code ? INTR_INFO_DELIVER_CODE_MASK : 0) | INTR_INFO_VALID_MASK); if (has_error_code) vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code); @@ -959,6 +1007,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) CPU_BASED_MOV_DR_EXITING | CPU_BASED_USE_TSC_OFFSETING; opt = CPU_BASED_TPR_SHADOW | + CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS, &_cpu_based_exec_control) < 0) @@ -971,7 +1020,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) { min = 0; opt = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | - SECONDARY_EXEC_WBINVD_EXITING; + SECONDARY_EXEC_WBINVD_EXITING | + SECONDARY_EXEC_ENABLE_VPID; if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS2, &_cpu_based_2nd_exec_control) < 0) return -EIO; @@ -1080,6 +1130,10 @@ static __init int hardware_setup(void) { if (setup_vmcs_config(&vmcs_config) < 0) return -EIO; + + if (boot_cpu_has(X86_FEATURE_NX)) + kvm_enable_efer_bits(EFER_NX); + return alloc_kvm_area(); } @@ -1214,7 +1268,7 @@ static void enter_lmode(struct kvm_vcpu *vcpu) guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES); if ((guest_tr_ar & AR_TYPE_MASK) != AR_TYPE_BUSY_64_TSS) { printk(KERN_DEBUG "%s: tss fixup for long mode. \n", - __FUNCTION__); + __func__); vmcs_write32(GUEST_TR_AR_BYTES, (guest_tr_ar & ~AR_TYPE_MASK) | AR_TYPE_BUSY_64_TSS); @@ -1239,6 +1293,11 @@ static void exit_lmode(struct kvm_vcpu *vcpu) #endif +static void vmx_flush_tlb(struct kvm_vcpu *vcpu) +{ + vpid_sync_vcpu_all(to_vmx(vcpu)); +} + static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) { vcpu->arch.cr4 &= KVM_GUEST_CR4_MASK; @@ -1275,6 +1334,7 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { + vmx_flush_tlb(vcpu); vmcs_writel(GUEST_CR3, cr3); if (vcpu->arch.cr0 & X86_CR0_PE) vmx_fpu_deactivate(vcpu); @@ -1288,14 +1348,14 @@ static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) vcpu->arch.cr4 = cr4; } -#ifdef CONFIG_X86_64 - static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_msr_entry *msr = find_msr_entry(vmx, MSR_EFER); vcpu->arch.shadow_efer = efer; + if (!msr) + return; if (efer & EFER_LMA) { vmcs_write32(VM_ENTRY_CONTROLS, vmcs_read32(VM_ENTRY_CONTROLS) | @@ -1312,8 +1372,6 @@ static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) setup_msrs(vmx); } -#endif - static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) { struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; @@ -1344,6 +1402,20 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu, var->unusable = (ar >> 16) & 1; } +static int vmx_get_cpl(struct kvm_vcpu *vcpu) +{ + struct kvm_segment kvm_seg; + + if (!(vcpu->arch.cr0 & X86_CR0_PE)) /* if real mode */ + return 0; + + if (vmx_get_rflags(vcpu) & X86_EFLAGS_VM) /* if virtual 8086 */ + return 3; + + vmx_get_segment(vcpu, &kvm_seg, VCPU_SREG_CS); + return kvm_seg.selector & 3; +} + static u32 vmx_segment_access_rights(struct kvm_segment *var) { u32 ar; @@ -1433,7 +1505,6 @@ static int init_rmode_tss(struct kvm *kvm) int ret = 0; int r; - down_read(&kvm->slots_lock); r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE); if (r < 0) goto out; @@ -1456,7 +1527,6 @@ static int init_rmode_tss(struct kvm *kvm) ret = 1; out: - up_read(&kvm->slots_lock); return ret; } @@ -1494,6 +1564,46 @@ out: return r; } +static void allocate_vpid(struct vcpu_vmx *vmx) +{ + int vpid; + + vmx->vpid = 0; + if (!enable_vpid || !cpu_has_vmx_vpid()) + return; + spin_lock(&vmx_vpid_lock); + vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS); + if (vpid < VMX_NR_VPIDS) { + vmx->vpid = vpid; + __set_bit(vpid, vmx_vpid_bitmap); + } + spin_unlock(&vmx_vpid_lock); +} + +void vmx_disable_intercept_for_msr(struct page *msr_bitmap, u32 msr) +{ + void *va; + + if (!cpu_has_vmx_msr_bitmap()) + return; + + /* + * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals + * have the write-low and read-high bitmap offsets the wrong way round. + * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff. + */ + va = kmap(msr_bitmap); + if (msr <= 0x1fff) { + __clear_bit(msr, va + 0x000); /* read-low */ + __clear_bit(msr, va + 0x800); /* write-low */ + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { + msr &= 0x1fff; + __clear_bit(msr, va + 0x400); /* read-high */ + __clear_bit(msr, va + 0xc00); /* write-high */ + } + kunmap(msr_bitmap); +} + /* * Sets up the vmcs for emulated real mode. */ @@ -1511,6 +1621,9 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write64(IO_BITMAP_A, page_to_phys(vmx_io_bitmap_a)); vmcs_write64(IO_BITMAP_B, page_to_phys(vmx_io_bitmap_b)); + if (cpu_has_vmx_msr_bitmap()) + vmcs_write64(MSR_BITMAP, page_to_phys(vmx_msr_bitmap)); + vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */ /* Control */ @@ -1532,6 +1645,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) if (!vm_need_virtualize_apic_accesses(vmx->vcpu.kvm)) exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + if (vmx->vpid == 0) + exec_control &= ~SECONDARY_EXEC_ENABLE_VPID; vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); } @@ -1613,6 +1728,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) u64 msr; int ret; + down_read(&vcpu->kvm->slots_lock); if (!init_rmode_tss(vmx->vcpu.kvm)) { ret = -ENOMEM; goto out; @@ -1621,7 +1737,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmx->vcpu.arch.rmode.active = 0; vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); - set_cr8(&vmx->vcpu, 0); + kvm_set_cr8(&vmx->vcpu, 0); msr = 0xfee00000 | MSR_IA32_APICBASE_ENABLE; if (vmx->vcpu.vcpu_id == 0) msr |= MSR_IA32_APICBASE_BSP; @@ -1704,18 +1820,22 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_write64(APIC_ACCESS_ADDR, page_to_phys(vmx->vcpu.kvm->arch.apic_access_page)); + if (vmx->vpid != 0) + vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); + vmx->vcpu.arch.cr0 = 0x60000010; vmx_set_cr0(&vmx->vcpu, vmx->vcpu.arch.cr0); /* enter rmode */ vmx_set_cr4(&vmx->vcpu, 0); -#ifdef CONFIG_X86_64 vmx_set_efer(&vmx->vcpu, 0); -#endif vmx_fpu_activate(&vmx->vcpu); update_exception_bitmap(&vmx->vcpu); - return 0; + vpid_sync_vcpu_all(vmx); + + ret = 0; out: + up_read(&vcpu->kvm->slots_lock); return ret; } @@ -1723,6 +1843,8 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu, int irq) { struct vcpu_vmx *vmx = to_vmx(vcpu); + KVMTRACE_1D(INJ_VIRQ, vcpu, (u32)irq, handler); + if (vcpu->arch.rmode.active) { vmx->rmode.irq.pending = true; vmx->rmode.irq.vector = irq; @@ -1844,7 +1966,7 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if ((vect_info & VECTORING_INFO_VALID_MASK) && !is_page_fault(intr_info)) printk(KERN_ERR "%s: unexpected, vectoring info 0x%x " - "intr info 0x%x\n", __FUNCTION__, vect_info, intr_info); + "intr info 0x%x\n", __func__, vect_info, intr_info); if (!irqchip_in_kernel(vcpu->kvm) && is_external_interrupt(vect_info)) { int irq = vect_info & VECTORING_INFO_VECTOR_MASK; @@ -1869,10 +1991,12 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) error_code = 0; rip = vmcs_readl(GUEST_RIP); - if (intr_info & INTR_INFO_DELIEVER_CODE_MASK) + if (intr_info & INTR_INFO_DELIVER_CODE_MASK) error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE); if (is_page_fault(intr_info)) { cr2 = vmcs_readl(EXIT_QUALIFICATION); + KVMTRACE_3D(PAGE_FAULT, vcpu, error_code, (u32)cr2, + (u32)((u64)cr2 >> 32), handler); return kvm_mmu_page_fault(vcpu, cr2, error_code); } @@ -1901,6 +2025,7 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { ++vcpu->stat.irq_exits; + KVMTRACE_1D(INTR, vcpu, vmcs_read32(VM_EXIT_INTR_INFO), handler); return 1; } @@ -1958,25 +2083,27 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) reg = (exit_qualification >> 8) & 15; switch ((exit_qualification >> 4) & 3) { case 0: /* mov to cr */ + KVMTRACE_3D(CR_WRITE, vcpu, (u32)cr, (u32)vcpu->arch.regs[reg], + (u32)((u64)vcpu->arch.regs[reg] >> 32), handler); switch (cr) { case 0: vcpu_load_rsp_rip(vcpu); - set_cr0(vcpu, vcpu->arch.regs[reg]); + kvm_set_cr0(vcpu, vcpu->arch.regs[reg]); skip_emulated_instruction(vcpu); return 1; case 3: vcpu_load_rsp_rip(vcpu); - set_cr3(vcpu, vcpu->arch.regs[reg]); + kvm_set_cr3(vcpu, vcpu->arch.regs[reg]); skip_emulated_instruction(vcpu); return 1; case 4: vcpu_load_rsp_rip(vcpu); - set_cr4(vcpu, vcpu->arch.regs[reg]); + kvm_set_cr4(vcpu, vcpu->arch.regs[reg]); skip_emulated_instruction(vcpu); return 1; case 8: vcpu_load_rsp_rip(vcpu); - set_cr8(vcpu, vcpu->arch.regs[reg]); + kvm_set_cr8(vcpu, vcpu->arch.regs[reg]); skip_emulated_instruction(vcpu); if (irqchip_in_kernel(vcpu->kvm)) return 1; @@ -1990,6 +2117,7 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vcpu->arch.cr0 &= ~X86_CR0_TS; vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0); vmx_fpu_activate(vcpu); + KVMTRACE_0D(CLTS, vcpu, handler); skip_emulated_instruction(vcpu); return 1; case 1: /*mov from cr*/ @@ -1998,18 +2126,24 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vcpu_load_rsp_rip(vcpu); vcpu->arch.regs[reg] = vcpu->arch.cr3; vcpu_put_rsp_rip(vcpu); + KVMTRACE_3D(CR_READ, vcpu, (u32)cr, + (u32)vcpu->arch.regs[reg], + (u32)((u64)vcpu->arch.regs[reg] >> 32), + handler); skip_emulated_instruction(vcpu); return 1; case 8: vcpu_load_rsp_rip(vcpu); - vcpu->arch.regs[reg] = get_cr8(vcpu); + vcpu->arch.regs[reg] = kvm_get_cr8(vcpu); vcpu_put_rsp_rip(vcpu); + KVMTRACE_2D(CR_READ, vcpu, (u32)cr, + (u32)vcpu->arch.regs[reg], handler); skip_emulated_instruction(vcpu); return 1; } break; case 3: /* lmsw */ - lmsw(vcpu, (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f); + kvm_lmsw(vcpu, (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f); skip_emulated_instruction(vcpu); return 1; @@ -2049,6 +2183,7 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) val = 0; } vcpu->arch.regs[reg] = val; + KVMTRACE_2D(DR_READ, vcpu, (u32)dr, (u32)val, handler); } else { /* mov to dr */ } @@ -2073,6 +2208,9 @@ static int handle_rdmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } + KVMTRACE_3D(MSR_READ, vcpu, ecx, (u32)data, (u32)(data >> 32), + handler); + /* FIXME: handling of bits 32:63 of rax, rdx */ vcpu->arch.regs[VCPU_REGS_RAX] = data & -1u; vcpu->arch.regs[VCPU_REGS_RDX] = (data >> 32) & -1u; @@ -2086,6 +2224,9 @@ static int handle_wrmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) u64 data = (vcpu->arch.regs[VCPU_REGS_RAX] & -1u) | ((u64)(vcpu->arch.regs[VCPU_REGS_RDX] & -1u) << 32); + KVMTRACE_3D(MSR_WRITE, vcpu, ecx, (u32)data, (u32)(data >> 32), + handler); + if (vmx_set_msr(vcpu, ecx, data) != 0) { kvm_inject_gp(vcpu, 0); return 1; @@ -2110,6 +2251,9 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu, cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING; vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); + + KVMTRACE_0D(PEND_INTR, vcpu, handler); + /* * If the user space waits to inject interrupts, exit as soon as * possible @@ -2152,6 +2296,8 @@ static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) exit_qualification = vmcs_read64(EXIT_QUALIFICATION); offset = exit_qualification & 0xffful; + KVMTRACE_1D(APIC_ACCESS, vcpu, (u32)offset, handler); + er = emulate_instruction(vcpu, kvm_run, 0, 0, 0); if (er != EMULATE_DONE) { @@ -2163,6 +2309,20 @@ static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } +static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + unsigned long exit_qualification; + u16 tss_selector; + int reason; + + exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + + reason = (u32)exit_qualification >> 30; + tss_selector = exit_qualification; + + return kvm_task_switch(vcpu, tss_selector, reason); +} + /* * The exit handlers return 1 if the exit was handled fully and guest execution * may resume. Otherwise they set the kvm_run parameter to indicate what needs @@ -2185,6 +2345,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu, [EXIT_REASON_TPR_BELOW_THRESHOLD] = handle_tpr_below_threshold, [EXIT_REASON_APIC_ACCESS] = handle_apic_access, [EXIT_REASON_WBINVD] = handle_wbinvd, + [EXIT_REASON_TASK_SWITCH] = handle_task_switch, }; static const int kvm_vmx_max_exit_handlers = @@ -2200,6 +2361,9 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); u32 vectoring_info = vmx->idt_vectoring_info; + KVMTRACE_3D(VMEXIT, vcpu, exit_reason, (u32)vmcs_readl(GUEST_RIP), + (u32)((u64)vmcs_readl(GUEST_RIP) >> 32), entryexit); + if (unlikely(vmx->fail)) { kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY; kvm_run->fail_entry.hardware_entry_failure_reason @@ -2210,7 +2374,7 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) if ((vectoring_info & VECTORING_INFO_VALID_MASK) && exit_reason != EXIT_REASON_EXCEPTION_NMI) printk(KERN_WARNING "%s: unexpected, valid vectoring info and " - "exit reason is 0x%x\n", __FUNCTION__, exit_reason); + "exit reason is 0x%x\n", __func__, exit_reason); if (exit_reason < kvm_vmx_max_exit_handlers && kvm_vmx_exit_handlers[exit_reason]) return kvm_vmx_exit_handlers[exit_reason](vcpu, kvm_run); @@ -2221,10 +2385,6 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) return 0; } -static void vmx_flush_tlb(struct kvm_vcpu *vcpu) -{ -} - static void update_tpr_threshold(struct kvm_vcpu *vcpu) { int max_irr, tpr; @@ -2285,11 +2445,13 @@ static void vmx_intr_assist(struct kvm_vcpu *vcpu) return; } + KVMTRACE_1D(REDELIVER_EVT, vcpu, idtv_info_field, handler); + vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, idtv_info_field); vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, vmcs_read32(VM_EXIT_INSTRUCTION_LEN)); - if (unlikely(idtv_info_field & INTR_INFO_DELIEVER_CODE_MASK)) + if (unlikely(idtv_info_field & INTR_INFO_DELIVER_CODE_MASK)) vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, vmcs_read32(IDT_VECTORING_ERROR_CODE)); if (unlikely(has_ext_irq)) @@ -2470,8 +2632,10 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) intr_info = vmcs_read32(VM_EXIT_INTR_INFO); /* We need to handle NMIs before interrupts are enabled */ - if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == 0x200) /* nmi */ + if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == 0x200) { /* nmi */ + KVMTRACE_0D(NMI, vcpu, handler); asm("int $2"); + } } static void vmx_free_vmcs(struct kvm_vcpu *vcpu) @@ -2489,6 +2653,10 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + spin_lock(&vmx_vpid_lock); + if (vmx->vpid != 0) + __clear_bit(vmx->vpid, vmx_vpid_bitmap); + spin_unlock(&vmx_vpid_lock); vmx_free_vmcs(vcpu); kfree(vmx->host_msrs); kfree(vmx->guest_msrs); @@ -2505,6 +2673,8 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (!vmx) return ERR_PTR(-ENOMEM); + allocate_vpid(vmx); + err = kvm_vcpu_init(&vmx->vcpu, kvm, id); if (err) goto free_vcpu; @@ -2591,14 +2761,13 @@ static struct kvm_x86_ops vmx_x86_ops = { .get_segment_base = vmx_get_segment_base, .get_segment = vmx_get_segment, .set_segment = vmx_set_segment, + .get_cpl = vmx_get_cpl, .get_cs_db_l_bits = vmx_get_cs_db_l_bits, .decache_cr4_guest_bits = vmx_decache_cr4_guest_bits, .set_cr0 = vmx_set_cr0, .set_cr3 = vmx_set_cr3, .set_cr4 = vmx_set_cr4, -#ifdef CONFIG_X86_64 .set_efer = vmx_set_efer, -#endif .get_idt = vmx_get_idt, .set_idt = vmx_set_idt, .get_gdt = vmx_get_gdt, @@ -2626,7 +2795,7 @@ static struct kvm_x86_ops vmx_x86_ops = { static int __init vmx_init(void) { - void *iova; + void *va; int r; vmx_io_bitmap_a = alloc_page(GFP_KERNEL | __GFP_HIGHMEM); @@ -2639,28 +2808,48 @@ static int __init vmx_init(void) goto out; } + vmx_msr_bitmap = alloc_page(GFP_KERNEL | __GFP_HIGHMEM); + if (!vmx_msr_bitmap) { + r = -ENOMEM; + goto out1; + } + /* * Allow direct access to the PC debug port (it is often used for I/O * delays, but the vmexits simply slow things down). */ - iova = kmap(vmx_io_bitmap_a); - memset(iova, 0xff, PAGE_SIZE); - clear_bit(0x80, iova); + va = kmap(vmx_io_bitmap_a); + memset(va, 0xff, PAGE_SIZE); + clear_bit(0x80, va); kunmap(vmx_io_bitmap_a); - iova = kmap(vmx_io_bitmap_b); - memset(iova, 0xff, PAGE_SIZE); + va = kmap(vmx_io_bitmap_b); + memset(va, 0xff, PAGE_SIZE); kunmap(vmx_io_bitmap_b); + va = kmap(vmx_msr_bitmap); + memset(va, 0xff, PAGE_SIZE); + kunmap(vmx_msr_bitmap); + + set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ + r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), THIS_MODULE); if (r) - goto out1; + goto out2; + + vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_FS_BASE); + vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_GS_BASE); + vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_CS); + vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_ESP); + vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_EIP); if (bypass_guest_pf) kvm_mmu_set_nonpresent_ptes(~0xffeull, 0ull); return 0; +out2: + __free_page(vmx_msr_bitmap); out1: __free_page(vmx_io_bitmap_b); out: @@ -2670,6 +2859,7 @@ out: static void __exit vmx_exit(void) { + __free_page(vmx_msr_bitmap); __free_page(vmx_io_bitmap_b); __free_page(vmx_io_bitmap_a); diff --git a/arch/x86/kvm/vmx.h b/arch/x86/kvm/vmx.h index d52ae8d7303d..5dff4606b988 100644 --- a/arch/x86/kvm/vmx.h +++ b/arch/x86/kvm/vmx.h @@ -49,6 +49,7 @@ * Definitions of Secondary Processor-Based VM-Execution Controls. */ #define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001 +#define SECONDARY_EXEC_ENABLE_VPID 0x00000020 #define SECONDARY_EXEC_WBINVD_EXITING 0x00000040 @@ -65,6 +66,7 @@ /* VMCS Encodings */ enum vmcs_field { + VIRTUAL_PROCESSOR_ID = 0x00000000, GUEST_ES_SELECTOR = 0x00000800, GUEST_CS_SELECTOR = 0x00000802, GUEST_SS_SELECTOR = 0x00000804, @@ -231,12 +233,12 @@ enum vmcs_field { */ #define INTR_INFO_VECTOR_MASK 0xff /* 7:0 */ #define INTR_INFO_INTR_TYPE_MASK 0x700 /* 10:8 */ -#define INTR_INFO_DELIEVER_CODE_MASK 0x800 /* 11 */ +#define INTR_INFO_DELIVER_CODE_MASK 0x800 /* 11 */ #define INTR_INFO_VALID_MASK 0x80000000 /* 31 */ #define VECTORING_INFO_VECTOR_MASK INTR_INFO_VECTOR_MASK #define VECTORING_INFO_TYPE_MASK INTR_INFO_INTR_TYPE_MASK -#define VECTORING_INFO_DELIEVER_CODE_MASK INTR_INFO_DELIEVER_CODE_MASK +#define VECTORING_INFO_DELIVER_CODE_MASK INTR_INFO_DELIVER_CODE_MASK #define VECTORING_INFO_VALID_MASK INTR_INFO_VALID_MASK #define INTR_TYPE_EXT_INTR (0 << 8) /* external interrupt */ @@ -321,4 +323,8 @@ enum vmcs_field { #define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT 9 +#define VMX_NR_VPIDS (1 << 16) +#define VMX_VPID_EXTENT_SINGLE_CONTEXT 1 +#define VMX_VPID_EXTENT_ALL_CONTEXT 2 + #endif diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6b01552bd1f1..0ce556372a4d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -15,10 +15,12 @@ */ #include <linux/kvm_host.h> -#include "segment_descriptor.h" #include "irq.h" #include "mmu.h" +#include "i8254.h" +#include "tss.h" +#include <linux/clocksource.h> #include <linux/kvm.h> #include <linux/fs.h> #include <linux/vmalloc.h> @@ -28,6 +30,7 @@ #include <asm/uaccess.h> #include <asm/msr.h> +#include <asm/desc.h> #define MAX_IO_MSRS 256 #define CR0_RESERVED_BITS \ @@ -41,7 +44,15 @@ | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE)) #define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR) -#define EFER_RESERVED_BITS 0xfffffffffffff2fe +/* EFER defaults: + * - enable syscall per default because its emulated by KVM + * - enable LME and LMA per default on 64 bit KVM + */ +#ifdef CONFIG_X86_64 +static u64 __read_mostly efer_reserved_bits = 0xfffffffffffffafeULL; +#else +static u64 __read_mostly efer_reserved_bits = 0xfffffffffffffffeULL; +#endif #define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU @@ -63,6 +74,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "irq_window", VCPU_STAT(irq_window_exits) }, { "halt_exits", VCPU_STAT(halt_exits) }, { "halt_wakeup", VCPU_STAT(halt_wakeup) }, + { "hypercalls", VCPU_STAT(hypercalls) }, { "request_irq", VCPU_STAT(request_irq_exits) }, { "irq_exits", VCPU_STAT(irq_exits) }, { "host_state_reload", VCPU_STAT(host_state_reload) }, @@ -78,6 +90,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "mmu_recycled", VM_STAT(mmu_recycled) }, { "mmu_cache_miss", VM_STAT(mmu_cache_miss) }, { "remote_tlb_flush", VM_STAT(remote_tlb_flush) }, + { "largepages", VM_STAT(lpages) }, { NULL } }; @@ -85,7 +98,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { unsigned long segment_base(u16 selector) { struct descriptor_table gdt; - struct segment_descriptor *d; + struct desc_struct *d; unsigned long table_base; unsigned long v; @@ -101,13 +114,12 @@ unsigned long segment_base(u16 selector) asm("sldt %0" : "=g"(ldt_selector)); table_base = segment_base(ldt_selector); } - d = (struct segment_descriptor *)(table_base + (selector & ~7)); - v = d->base_low | ((unsigned long)d->base_mid << 16) | - ((unsigned long)d->base_high << 24); + d = (struct desc_struct *)(table_base + (selector & ~7)); + v = d->base0 | ((unsigned long)d->base1 << 16) | + ((unsigned long)d->base2 << 24); #ifdef CONFIG_X86_64 - if (d->system == 0 && (d->type == 2 || d->type == 9 || d->type == 11)) - v |= ((unsigned long) \ - ((struct segment_descriptor_64 *)d)->base_higher) << 32; + if (d->s == 0 && (d->type == 2 || d->type == 9 || d->type == 11)) + v |= ((unsigned long)((struct ldttss_desc64 *)d)->base3) << 32; #endif return v; } @@ -145,11 +157,16 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long addr, u32 error_code) { ++vcpu->stat.pf_guest; - if (vcpu->arch.exception.pending && vcpu->arch.exception.nr == PF_VECTOR) { - printk(KERN_DEBUG "kvm: inject_page_fault:" - " double fault 0x%lx\n", addr); - vcpu->arch.exception.nr = DF_VECTOR; - vcpu->arch.exception.error_code = 0; + if (vcpu->arch.exception.pending) { + if (vcpu->arch.exception.nr == PF_VECTOR) { + printk(KERN_DEBUG "kvm: inject_page_fault:" + " double fault 0x%lx\n", addr); + vcpu->arch.exception.nr = DF_VECTOR; + vcpu->arch.exception.error_code = 0; + } else if (vcpu->arch.exception.nr == DF_VECTOR) { + /* triple fault -> shutdown */ + set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests); + } return; } vcpu->arch.cr2 = addr; @@ -184,7 +201,6 @@ int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3) int ret; u64 pdpte[ARRAY_SIZE(vcpu->arch.pdptrs)]; - down_read(&vcpu->kvm->slots_lock); ret = kvm_read_guest_page(vcpu->kvm, pdpt_gfn, pdpte, offset * sizeof(u64), sizeof(pdpte)); if (ret < 0) { @@ -201,10 +217,10 @@ int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3) memcpy(vcpu->arch.pdptrs, pdpte, sizeof(vcpu->arch.pdptrs)); out: - up_read(&vcpu->kvm->slots_lock); return ret; } +EXPORT_SYMBOL_GPL(load_pdptrs); static bool pdptrs_changed(struct kvm_vcpu *vcpu) { @@ -215,18 +231,16 @@ static bool pdptrs_changed(struct kvm_vcpu *vcpu) if (is_long_mode(vcpu) || !is_pae(vcpu)) return false; - down_read(&vcpu->kvm->slots_lock); r = kvm_read_guest(vcpu->kvm, vcpu->arch.cr3 & ~31u, pdpte, sizeof(pdpte)); if (r < 0) goto out; changed = memcmp(pdpte, vcpu->arch.pdptrs, sizeof(pdpte)) != 0; out: - up_read(&vcpu->kvm->slots_lock); return changed; } -void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) +void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { if (cr0 & CR0_RESERVED_BITS) { printk(KERN_DEBUG "set_cr0: 0x%lx #GP, reserved bits 0x%lx\n", @@ -284,15 +298,18 @@ void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) kvm_mmu_reset_context(vcpu); return; } -EXPORT_SYMBOL_GPL(set_cr0); +EXPORT_SYMBOL_GPL(kvm_set_cr0); -void lmsw(struct kvm_vcpu *vcpu, unsigned long msw) +void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw) { - set_cr0(vcpu, (vcpu->arch.cr0 & ~0x0ful) | (msw & 0x0f)); + kvm_set_cr0(vcpu, (vcpu->arch.cr0 & ~0x0ful) | (msw & 0x0f)); + KVMTRACE_1D(LMSW, vcpu, + (u32)((vcpu->arch.cr0 & ~0x0ful) | (msw & 0x0f)), + handler); } -EXPORT_SYMBOL_GPL(lmsw); +EXPORT_SYMBOL_GPL(kvm_lmsw); -void set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { if (cr4 & CR4_RESERVED_BITS) { printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n"); @@ -323,9 +340,9 @@ void set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) vcpu->arch.cr4 = cr4; kvm_mmu_reset_context(vcpu); } -EXPORT_SYMBOL_GPL(set_cr4); +EXPORT_SYMBOL_GPL(kvm_set_cr4); -void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) +void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { if (cr3 == vcpu->arch.cr3 && !pdptrs_changed(vcpu)) { kvm_mmu_flush_tlb(vcpu); @@ -359,7 +376,6 @@ void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) */ } - down_read(&vcpu->kvm->slots_lock); /* * Does the new cr3 value map to physical memory? (Note, we * catch an invalid cr3 even in real-mode, because it would @@ -375,11 +391,10 @@ void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) vcpu->arch.cr3 = cr3; vcpu->arch.mmu.new_cr3(vcpu); } - up_read(&vcpu->kvm->slots_lock); } -EXPORT_SYMBOL_GPL(set_cr3); +EXPORT_SYMBOL_GPL(kvm_set_cr3); -void set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8) +void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8) { if (cr8 & CR8_RESERVED_BITS) { printk(KERN_DEBUG "set_cr8: #GP, reserved bits 0x%lx\n", cr8); @@ -391,16 +406,16 @@ void set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8) else vcpu->arch.cr8 = cr8; } -EXPORT_SYMBOL_GPL(set_cr8); +EXPORT_SYMBOL_GPL(kvm_set_cr8); -unsigned long get_cr8(struct kvm_vcpu *vcpu) +unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu) { if (irqchip_in_kernel(vcpu->kvm)) return kvm_lapic_get_cr8(vcpu); else return vcpu->arch.cr8; } -EXPORT_SYMBOL_GPL(get_cr8); +EXPORT_SYMBOL_GPL(kvm_get_cr8); /* * List of msr numbers which we expose to userspace through KVM_GET_MSRS @@ -415,7 +430,8 @@ static u32 msrs_to_save[] = { #ifdef CONFIG_X86_64 MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif - MSR_IA32_TIME_STAMP_COUNTER, + MSR_IA32_TIME_STAMP_COUNTER, MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, + MSR_IA32_PERF_STATUS, }; static unsigned num_msrs_to_save; @@ -424,11 +440,9 @@ static u32 emulated_msrs[] = { MSR_IA32_MISC_ENABLE, }; -#ifdef CONFIG_X86_64 - static void set_efer(struct kvm_vcpu *vcpu, u64 efer) { - if (efer & EFER_RESERVED_BITS) { + if (efer & efer_reserved_bits) { printk(KERN_DEBUG "set_efer: 0x%llx #GP, reserved bits\n", efer); kvm_inject_gp(vcpu, 0); @@ -450,7 +464,12 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer) vcpu->arch.shadow_efer = efer; } -#endif +void kvm_enable_efer_bits(u64 mask) +{ + efer_reserved_bits &= ~mask; +} +EXPORT_SYMBOL_GPL(kvm_enable_efer_bits); + /* * Writes msr value into into the appropriate "register". @@ -470,26 +489,86 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) return kvm_set_msr(vcpu, index, *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; + + if (!wall_clock) + return; + + version++; + + 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; + + kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc)); + + version++; + kvm_write_guest(kvm, wall_clock, &version, sizeof(version)); +} + +static void kvm_write_guest_time(struct kvm_vcpu *v) +{ + struct timespec ts; + unsigned long flags; + struct kvm_vcpu_arch *vcpu = &v->arch; + void *shared_kaddr; + + if ((!vcpu->time_page)) + return; + + /* Keep irq disabled to prevent changes to the clock */ + local_irq_save(flags); + kvm_get_msr(v, MSR_IA32_TIME_STAMP_COUNTER, + &vcpu->hv_clock.tsc_timestamp); + ktime_get_ts(&ts); + local_irq_restore(flags); + + /* With all the info we got, fill in the values */ + + vcpu->hv_clock.system_time = ts.tv_nsec + + (NSEC_PER_SEC * (u64)ts.tv_sec); + /* + * 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 + */ + 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)); + + kunmap_atomic(shared_kaddr, KM_USER0); + + mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT); +} + int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) { switch (msr) { -#ifdef CONFIG_X86_64 case MSR_EFER: set_efer(vcpu, data); break; -#endif case MSR_IA32_MC0_STATUS: pr_unimpl(vcpu, "%s: MSR_IA32_MC0_STATUS 0x%llx, nop\n", - __FUNCTION__, data); + __func__, data); break; case MSR_IA32_MCG_STATUS: pr_unimpl(vcpu, "%s: MSR_IA32_MCG_STATUS 0x%llx, nop\n", - __FUNCTION__, data); + __func__, data); break; case MSR_IA32_MCG_CTL: pr_unimpl(vcpu, "%s: MSR_IA32_MCG_CTL 0x%llx, nop\n", - __FUNCTION__, data); + __func__, data); break; case MSR_IA32_UCODE_REV: case MSR_IA32_UCODE_WRITE: @@ -501,6 +580,42 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) case MSR_IA32_MISC_ENABLE: vcpu->arch.ia32_misc_enable_msr = data; break; + case MSR_KVM_WALL_CLOCK: + vcpu->kvm->arch.wall_clock = data; + kvm_write_wall_clock(vcpu->kvm, data); + break; + case MSR_KVM_SYSTEM_TIME: { + if (vcpu->arch.time_page) { + kvm_release_page_dirty(vcpu->arch.time_page); + vcpu->arch.time_page = NULL; + } + + vcpu->arch.time = data; + + /* we verify if the enable bit is set... */ + if (!(data & 1)) + break; + + /* ...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); + up_read(¤t->mm->mmap_sem); + + if (is_error_page(vcpu->arch.time_page)) { + kvm_release_page_clean(vcpu->arch.time_page); + vcpu->arch.time_page = NULL; + } + + kvm_write_guest_time(vcpu); + break; + } default: pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", msr, data); return 1; @@ -540,7 +655,6 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_IA32_MC0_MISC+12: case MSR_IA32_MC0_MISC+16: case MSR_IA32_UCODE_REV: - case MSR_IA32_PERF_STATUS: case MSR_IA32_EBL_CR_POWERON: /* MTRR registers */ case 0xfe: @@ -556,11 +670,21 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_IA32_MISC_ENABLE: data = vcpu->arch.ia32_misc_enable_msr; break; -#ifdef CONFIG_X86_64 + case MSR_IA32_PERF_STATUS: + /* TSC increment by tick */ + data = 1000ULL; + /* CPU multiplier */ + data |= (((uint64_t)4ULL) << 40); + break; case MSR_EFER: data = vcpu->arch.shadow_efer; break; -#endif + case MSR_KVM_WALL_CLOCK: + data = vcpu->kvm->arch.wall_clock; + break; + case MSR_KVM_SYSTEM_TIME: + data = vcpu->arch.time; + break; default: pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr); return 1; @@ -584,9 +708,11 @@ static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs, vcpu_load(vcpu); + down_read(&vcpu->kvm->slots_lock); for (i = 0; i < msrs->nmsrs; ++i) if (do_msr(vcpu, entries[i].index, &entries[i].data)) break; + up_read(&vcpu->kvm->slots_lock); vcpu_put(vcpu); @@ -688,11 +814,24 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_USER_MEMORY: case KVM_CAP_SET_TSS_ADDR: case KVM_CAP_EXT_CPUID: + case KVM_CAP_CLOCKSOURCE: + case KVM_CAP_PIT: + case KVM_CAP_NOP_IO_DELAY: + case KVM_CAP_MP_STATE: r = 1; break; case KVM_CAP_VAPIC: r = !kvm_x86_ops->cpu_has_accelerated_tpr(); break; + case KVM_CAP_NR_VCPUS: + r = KVM_MAX_VCPUS; + break; + case KVM_CAP_NR_MEMSLOTS: + r = KVM_MEMORY_SLOTS; + break; + case KVM_CAP_PV_MMU: + r = !tdp_enabled; + break; default: r = 0; break; @@ -763,6 +902,7 @@ out: void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { kvm_x86_ops->vcpu_load(vcpu, cpu); + kvm_write_guest_time(vcpu); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) @@ -958,32 +1098,32 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, } /* function 4 and 0xb have additional index. */ case 4: { - int index, cache_type; + int i, cache_type; entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; /* read more entries until cache_type is zero */ - for (index = 1; *nent < maxnent; ++index) { - cache_type = entry[index - 1].eax & 0x1f; + for (i = 1; *nent < maxnent; ++i) { + cache_type = entry[i - 1].eax & 0x1f; if (!cache_type) break; - do_cpuid_1_ent(&entry[index], function, index); - entry[index].flags |= + do_cpuid_1_ent(&entry[i], function, i); + entry[i].flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; ++*nent; } break; } case 0xb: { - int index, level_type; + int i, level_type; entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; /* read more entries until level_type is zero */ - for (index = 1; *nent < maxnent; ++index) { - level_type = entry[index - 1].ecx & 0xff; + for (i = 1; *nent < maxnent; ++i) { + level_type = entry[i - 1].ecx & 0xff; if (!level_type) break; - do_cpuid_1_ent(&entry[index], function, index); - entry[index].flags |= + do_cpuid_1_ent(&entry[i], function, i); + entry[i].flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; ++*nent; } @@ -1365,6 +1505,23 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) return r; } +static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps) +{ + int r = 0; + + memcpy(ps, &kvm->arch.vpit->pit_state, sizeof(struct kvm_pit_state)); + return r; +} + +static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps) +{ + int r = 0; + + memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state)); + kvm_pit_load_count(kvm, 0, ps->channels[0].count); + return r; +} + /* * Get (and clear) the dirty memory log for a memory slot. */ @@ -1457,6 +1614,12 @@ long kvm_arch_vm_ioctl(struct file *filp, } else goto out; break; + case KVM_CREATE_PIT: + r = -ENOMEM; + kvm->arch.vpit = kvm_create_pit(kvm); + if (kvm->arch.vpit) + r = 0; + break; case KVM_IRQ_LINE: { struct kvm_irq_level irq_event; @@ -1512,6 +1675,37 @@ long kvm_arch_vm_ioctl(struct file *filp, r = 0; break; } + case KVM_GET_PIT: { + struct kvm_pit_state ps; + r = -EFAULT; + if (copy_from_user(&ps, argp, sizeof ps)) + goto out; + r = -ENXIO; + if (!kvm->arch.vpit) + goto out; + r = kvm_vm_ioctl_get_pit(kvm, &ps); + if (r) + goto out; + r = -EFAULT; + if (copy_to_user(argp, &ps, sizeof ps)) + goto out; + r = 0; + break; + } + case KVM_SET_PIT: { + struct kvm_pit_state ps; + r = -EFAULT; + if (copy_from_user(&ps, argp, sizeof ps)) + goto out; + r = -ENXIO; + if (!kvm->arch.vpit) + goto out; + r = kvm_vm_ioctl_set_pit(kvm, &ps); + if (r) + goto out; + r = 0; + break; + } default: ; } @@ -1570,7 +1764,6 @@ int emulator_read_std(unsigned long addr, void *data = val; int r = X86EMUL_CONTINUE; - down_read(&vcpu->kvm->slots_lock); while (bytes) { gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); unsigned offset = addr & (PAGE_SIZE-1); @@ -1592,7 +1785,6 @@ int emulator_read_std(unsigned long addr, addr += tocopy; } out: - up_read(&vcpu->kvm->slots_lock); return r; } EXPORT_SYMBOL_GPL(emulator_read_std); @@ -1611,9 +1803,7 @@ static int emulator_read_emulated(unsigned long addr, return X86EMUL_CONTINUE; } - down_read(&vcpu->kvm->slots_lock); gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); - up_read(&vcpu->kvm->slots_lock); /* For APIC access vmexit */ if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) @@ -1646,19 +1836,15 @@ mmio: return X86EMUL_UNHANDLEABLE; } -static int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, - const void *val, int bytes) +int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, + const void *val, int bytes) { int ret; - down_read(&vcpu->kvm->slots_lock); ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes); - if (ret < 0) { - up_read(&vcpu->kvm->slots_lock); + if (ret < 0) return 0; - } kvm_mmu_pte_write(vcpu, gpa, val, bytes); - up_read(&vcpu->kvm->slots_lock); return 1; } @@ -1670,9 +1856,7 @@ static int emulator_write_emulated_onepage(unsigned long addr, struct kvm_io_device *mmio_dev; gpa_t gpa; - down_read(&vcpu->kvm->slots_lock); gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); - up_read(&vcpu->kvm->slots_lock); if (gpa == UNMAPPED_GVA) { kvm_inject_page_fault(vcpu, addr, 2); @@ -1749,7 +1933,6 @@ static int emulator_cmpxchg_emulated(unsigned long addr, char *kaddr; u64 val; - down_read(&vcpu->kvm->slots_lock); gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); if (gpa == UNMAPPED_GVA || @@ -1769,9 +1952,8 @@ static int emulator_cmpxchg_emulated(unsigned long addr, set_64bit((u64 *)(kaddr + offset_in_page(gpa)), val); kunmap_atomic(kaddr, KM_USER0); kvm_release_page_dirty(page); - emul_write: - up_read(&vcpu->kvm->slots_lock); } +emul_write: #endif return emulator_write_emulated(addr, new, bytes, vcpu); @@ -1802,7 +1984,7 @@ int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest) *dest = kvm_x86_ops->get_dr(vcpu, dr); return X86EMUL_CONTINUE; default: - pr_unimpl(vcpu, "%s: unexpected dr %u\n", __FUNCTION__, dr); + pr_unimpl(vcpu, "%s: unexpected dr %u\n", __func__, dr); return X86EMUL_UNHANDLEABLE; } } @@ -1840,7 +2022,7 @@ void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context) } EXPORT_SYMBOL_GPL(kvm_report_emulation_failure); -struct x86_emulate_ops emulate_ops = { +static struct x86_emulate_ops emulate_ops = { .read_std = emulator_read_std, .read_emulated = emulator_read_emulated, .write_emulated = emulator_write_emulated, @@ -2091,6 +2273,13 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, vcpu->arch.pio.guest_page_offset = 0; vcpu->arch.pio.rep = 0; + if (vcpu->run->io.direction == KVM_EXIT_IO_IN) + KVMTRACE_2D(IO_READ, vcpu, vcpu->run->io.port, (u32)size, + handler); + else + KVMTRACE_2D(IO_WRITE, vcpu, vcpu->run->io.port, (u32)size, + handler); + kvm_x86_ops->cache_regs(vcpu); memcpy(vcpu->arch.pio_data, &vcpu->arch.regs[VCPU_REGS_RAX], 4); kvm_x86_ops->decache_regs(vcpu); @@ -2129,6 +2318,13 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, vcpu->arch.pio.guest_page_offset = offset_in_page(address); vcpu->arch.pio.rep = rep; + if (vcpu->run->io.direction == KVM_EXIT_IO_IN) + KVMTRACE_2D(IO_READ, vcpu, vcpu->run->io.port, (u32)size, + handler); + else + KVMTRACE_2D(IO_WRITE, vcpu, vcpu->run->io.port, (u32)size, + handler); + if (!count) { kvm_x86_ops->skip_emulated_instruction(vcpu); return 1; @@ -2163,10 +2359,8 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, kvm_x86_ops->skip_emulated_instruction(vcpu); for (i = 0; i < nr_pages; ++i) { - down_read(&vcpu->kvm->slots_lock); page = gva_to_page(vcpu, address + i * PAGE_SIZE); vcpu->arch.pio.guest_pages[i] = page; - up_read(&vcpu->kvm->slots_lock); if (!page) { kvm_inject_gp(vcpu, 0); free_pio_guest_pages(vcpu); @@ -2238,10 +2432,13 @@ void kvm_arch_exit(void) int kvm_emulate_halt(struct kvm_vcpu *vcpu) { ++vcpu->stat.halt_exits; + KVMTRACE_0D(HLT, vcpu, handler); if (irqchip_in_kernel(vcpu->kvm)) { - vcpu->arch.mp_state = VCPU_MP_STATE_HALTED; + vcpu->arch.mp_state = KVM_MP_STATE_HALTED; + up_read(&vcpu->kvm->slots_lock); kvm_vcpu_block(vcpu); - if (vcpu->arch.mp_state != VCPU_MP_STATE_RUNNABLE) + down_read(&vcpu->kvm->slots_lock); + if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE) return -EINTR; return 1; } else { @@ -2251,9 +2448,19 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_emulate_halt); +static inline gpa_t hc_gpa(struct kvm_vcpu *vcpu, unsigned long a0, + unsigned long a1) +{ + if (is_long_mode(vcpu)) + return a0; + else + return a0 | ((gpa_t)a1 << 32); +} + int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) { unsigned long nr, a0, a1, a2, a3, ret; + int r = 1; kvm_x86_ops->cache_regs(vcpu); @@ -2263,6 +2470,8 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) a2 = vcpu->arch.regs[VCPU_REGS_RDX]; a3 = vcpu->arch.regs[VCPU_REGS_RSI]; + KVMTRACE_1D(VMMCALL, vcpu, (u32)nr, handler); + if (!is_long_mode(vcpu)) { nr &= 0xFFFFFFFF; a0 &= 0xFFFFFFFF; @@ -2275,13 +2484,17 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) case KVM_HC_VAPIC_POLL_IRQ: ret = 0; break; + case KVM_HC_MMU_OP: + r = kvm_pv_mmu_op(vcpu, a0, hc_gpa(vcpu, a1, a2), &ret); + break; default: ret = -KVM_ENOSYS; break; } vcpu->arch.regs[VCPU_REGS_RAX] = ret; kvm_x86_ops->decache_regs(vcpu); - return 0; + ++vcpu->stat.hypercalls; + return r; } EXPORT_SYMBOL_GPL(kvm_emulate_hypercall); @@ -2329,7 +2542,7 @@ void realmode_lidt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base) void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw, unsigned long *rflags) { - lmsw(vcpu, msw); + kvm_lmsw(vcpu, msw); *rflags = kvm_x86_ops->get_rflags(vcpu); } @@ -2346,9 +2559,9 @@ unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr) case 4: return vcpu->arch.cr4; case 8: - return get_cr8(vcpu); + return kvm_get_cr8(vcpu); default: - vcpu_printf(vcpu, "%s: unexpected cr %u\n", __FUNCTION__, cr); + vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr); return 0; } } @@ -2358,23 +2571,23 @@ void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val, { switch (cr) { case 0: - set_cr0(vcpu, mk_cr_64(vcpu->arch.cr0, val)); + kvm_set_cr0(vcpu, mk_cr_64(vcpu->arch.cr0, val)); *rflags = kvm_x86_ops->get_rflags(vcpu); break; case 2: vcpu->arch.cr2 = val; break; case 3: - set_cr3(vcpu, val); + kvm_set_cr3(vcpu, val); break; case 4: - set_cr4(vcpu, mk_cr_64(vcpu->arch.cr4, val)); + kvm_set_cr4(vcpu, mk_cr_64(vcpu->arch.cr4, val)); break; case 8: - set_cr8(vcpu, val & 0xfUL); + kvm_set_cr8(vcpu, val & 0xfUL); break; default: - vcpu_printf(vcpu, "%s: unexpected cr %u\n", __FUNCTION__, cr); + vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr); } } @@ -2447,6 +2660,11 @@ void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) } kvm_x86_ops->decache_regs(vcpu); kvm_x86_ops->skip_emulated_instruction(vcpu); + KVMTRACE_5D(CPUID, vcpu, function, + (u32)vcpu->arch.regs[VCPU_REGS_RAX], + (u32)vcpu->arch.regs[VCPU_REGS_RBX], + (u32)vcpu->arch.regs[VCPU_REGS_RCX], + (u32)vcpu->arch.regs[VCPU_REGS_RDX], handler); } EXPORT_SYMBOL_GPL(kvm_emulate_cpuid); @@ -2469,7 +2687,7 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { kvm_run->if_flag = (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF) != 0; - kvm_run->cr8 = get_cr8(vcpu); + kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); if (irqchip_in_kernel(vcpu->kvm)) kvm_run->ready_for_interrupt_injection = 1; @@ -2509,16 +2727,17 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { int r; - if (unlikely(vcpu->arch.mp_state == VCPU_MP_STATE_SIPI_RECEIVED)) { + if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED)) { pr_debug("vcpu %d received sipi with vector # %x\n", vcpu->vcpu_id, vcpu->arch.sipi_vector); kvm_lapic_reset(vcpu); r = kvm_x86_ops->vcpu_reset(vcpu); if (r) return r; - vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE; + vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; } + down_read(&vcpu->kvm->slots_lock); vapic_enter(vcpu); preempted: @@ -2526,6 +2745,10 @@ preempted: kvm_x86_ops->guest_debug_pre(vcpu); again: + if (vcpu->requests) + if (test_and_clear_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests)) + kvm_mmu_unload(vcpu); + r = kvm_mmu_reload(vcpu); if (unlikely(r)) goto out; @@ -2539,6 +2762,11 @@ again: r = 0; goto out; } + if (test_and_clear_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests)) { + kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; + r = 0; + goto out; + } } kvm_inject_pending_timer_irqs(vcpu); @@ -2557,6 +2785,14 @@ again: 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(); @@ -2566,6 +2802,13 @@ again: goto out; } + vcpu->guest_mode = 1; + /* + * Make sure that guest_mode assignment won't happen after + * testing the pending IRQ vector bitmap. + */ + smp_wmb(); + if (vcpu->arch.exception.pending) __queue_exception(vcpu); else if (irqchip_in_kernel(vcpu->kvm)) @@ -2575,13 +2818,15 @@ again: kvm_lapic_sync_to_vapic(vcpu); - vcpu->guest_mode = 1; + up_read(&vcpu->kvm->slots_lock); + 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); vcpu->guest_mode = 0; @@ -2601,6 +2846,8 @@ again: preempt_enable(); + down_read(&vcpu->kvm->slots_lock); + /* * Profile KVM exit RIPs: */ @@ -2628,14 +2875,18 @@ again: } out: + up_read(&vcpu->kvm->slots_lock); if (r > 0) { kvm_resched(vcpu); + down_read(&vcpu->kvm->slots_lock); goto preempted; } post_kvm_run_save(vcpu, kvm_run); + down_read(&vcpu->kvm->slots_lock); vapic_exit(vcpu); + up_read(&vcpu->kvm->slots_lock); return r; } @@ -2647,7 +2898,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vcpu_load(vcpu); - if (unlikely(vcpu->arch.mp_state == VCPU_MP_STATE_UNINITIALIZED)) { + if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) { kvm_vcpu_block(vcpu); vcpu_put(vcpu); return -EAGAIN; @@ -2658,7 +2909,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) /* re-sync apic's tpr */ if (!irqchip_in_kernel(vcpu->kvm)) - set_cr8(vcpu, kvm_run->cr8); + kvm_set_cr8(vcpu, kvm_run->cr8); if (vcpu->arch.pio.cur_count) { r = complete_pio(vcpu); @@ -2670,9 +2921,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8); vcpu->mmio_read_completed = 1; vcpu->mmio_needed = 0; + + down_read(&vcpu->kvm->slots_lock); r = emulate_instruction(vcpu, kvm_run, vcpu->arch.mmio_fault_cr2, 0, EMULTYPE_NO_DECODE); + up_read(&vcpu->kvm->slots_lock); if (r == EMULATE_DO_MMIO) { /* * Read-modify-write. Back to userspace. @@ -2773,7 +3027,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) static void get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { - return kvm_x86_ops->get_segment(vcpu, var, seg); + kvm_x86_ops->get_segment(vcpu, var, seg); } void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) @@ -2816,7 +3070,7 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, sregs->cr2 = vcpu->arch.cr2; sregs->cr3 = vcpu->arch.cr3; sregs->cr4 = vcpu->arch.cr4; - sregs->cr8 = get_cr8(vcpu); + sregs->cr8 = kvm_get_cr8(vcpu); sregs->efer = vcpu->arch.shadow_efer; sregs->apic_base = kvm_get_apic_base(vcpu); @@ -2836,12 +3090,438 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, return 0; } +int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state) +{ + vcpu_load(vcpu); + mp_state->mp_state = vcpu->arch.mp_state; + vcpu_put(vcpu); + return 0; +} + +int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state) +{ + vcpu_load(vcpu); + vcpu->arch.mp_state = mp_state->mp_state; + vcpu_put(vcpu); + return 0; +} + static void set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { - return kvm_x86_ops->set_segment(vcpu, var, seg); + kvm_x86_ops->set_segment(vcpu, var, seg); +} + +static void seg_desct_to_kvm_desct(struct desc_struct *seg_desc, u16 selector, + struct kvm_segment *kvm_desct) +{ + kvm_desct->base = seg_desc->base0; + kvm_desct->base |= seg_desc->base1 << 16; + kvm_desct->base |= seg_desc->base2 << 24; + kvm_desct->limit = seg_desc->limit0; + kvm_desct->limit |= seg_desc->limit << 16; + kvm_desct->selector = selector; + kvm_desct->type = seg_desc->type; + kvm_desct->present = seg_desc->p; + kvm_desct->dpl = seg_desc->dpl; + kvm_desct->db = seg_desc->d; + kvm_desct->s = seg_desc->s; + kvm_desct->l = seg_desc->l; + kvm_desct->g = seg_desc->g; + kvm_desct->avl = seg_desc->avl; + if (!selector) + kvm_desct->unusable = 1; + else + kvm_desct->unusable = 0; + kvm_desct->padding = 0; +} + +static void get_segment_descritptor_dtable(struct kvm_vcpu *vcpu, + u16 selector, + struct descriptor_table *dtable) +{ + if (selector & 1 << 2) { + struct kvm_segment kvm_seg; + + get_segment(vcpu, &kvm_seg, VCPU_SREG_LDTR); + + if (kvm_seg.unusable) + dtable->limit = 0; + else + dtable->limit = kvm_seg.limit; + dtable->base = kvm_seg.base; + } + else + kvm_x86_ops->get_gdt(vcpu, dtable); +} + +/* allowed just for 8 bytes segments */ +static int load_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, + struct desc_struct *seg_desc) +{ + struct descriptor_table dtable; + u16 index = selector >> 3; + + get_segment_descritptor_dtable(vcpu, selector, &dtable); + + if (dtable.limit < index * 8 + 7) { + kvm_queue_exception_e(vcpu, GP_VECTOR, selector & 0xfffc); + return 1; + } + return kvm_read_guest(vcpu->kvm, dtable.base + index * 8, seg_desc, 8); +} + +/* allowed just for 8 bytes segments */ +static int save_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, + struct desc_struct *seg_desc) +{ + struct descriptor_table dtable; + u16 index = selector >> 3; + + get_segment_descritptor_dtable(vcpu, selector, &dtable); + + if (dtable.limit < index * 8 + 7) + return 1; + return kvm_write_guest(vcpu->kvm, dtable.base + index * 8, seg_desc, 8); +} + +static u32 get_tss_base_addr(struct kvm_vcpu *vcpu, + struct desc_struct *seg_desc) +{ + u32 base_addr; + + base_addr = seg_desc->base0; + base_addr |= (seg_desc->base1 << 16); + base_addr |= (seg_desc->base2 << 24); + + return base_addr; +} + +static int load_tss_segment32(struct kvm_vcpu *vcpu, + struct desc_struct *seg_desc, + struct tss_segment_32 *tss) +{ + u32 base_addr; + + base_addr = get_tss_base_addr(vcpu, seg_desc); + + return kvm_read_guest(vcpu->kvm, base_addr, tss, + sizeof(struct tss_segment_32)); +} + +static int save_tss_segment32(struct kvm_vcpu *vcpu, + struct desc_struct *seg_desc, + struct tss_segment_32 *tss) +{ + u32 base_addr; + + base_addr = get_tss_base_addr(vcpu, seg_desc); + + return kvm_write_guest(vcpu->kvm, base_addr, tss, + sizeof(struct tss_segment_32)); +} + +static int load_tss_segment16(struct kvm_vcpu *vcpu, + struct desc_struct *seg_desc, + struct tss_segment_16 *tss) +{ + u32 base_addr; + + base_addr = get_tss_base_addr(vcpu, seg_desc); + + return kvm_read_guest(vcpu->kvm, base_addr, tss, + sizeof(struct tss_segment_16)); +} + +static int save_tss_segment16(struct kvm_vcpu *vcpu, + struct desc_struct *seg_desc, + struct tss_segment_16 *tss) +{ + u32 base_addr; + + base_addr = get_tss_base_addr(vcpu, seg_desc); + + return kvm_write_guest(vcpu->kvm, base_addr, tss, + sizeof(struct tss_segment_16)); +} + +static u16 get_segment_selector(struct kvm_vcpu *vcpu, int seg) +{ + struct kvm_segment kvm_seg; + + get_segment(vcpu, &kvm_seg, seg); + return kvm_seg.selector; +} + +static int load_segment_descriptor_to_kvm_desct(struct kvm_vcpu *vcpu, + u16 selector, + struct kvm_segment *kvm_seg) +{ + struct desc_struct seg_desc; + + if (load_guest_segment_descriptor(vcpu, selector, &seg_desc)) + return 1; + seg_desct_to_kvm_desct(&seg_desc, selector, kvm_seg); + return 0; +} + +static int load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, + int type_bits, int seg) +{ + struct kvm_segment kvm_seg; + + if (load_segment_descriptor_to_kvm_desct(vcpu, selector, &kvm_seg)) + return 1; + kvm_seg.type |= type_bits; + + if (seg != VCPU_SREG_SS && seg != VCPU_SREG_CS && + seg != VCPU_SREG_LDTR) + if (!kvm_seg.s) + kvm_seg.unusable = 1; + + set_segment(vcpu, &kvm_seg, seg); + return 0; +} + +static void save_state_to_tss32(struct kvm_vcpu *vcpu, + struct tss_segment_32 *tss) +{ + tss->cr3 = vcpu->arch.cr3; + tss->eip = vcpu->arch.rip; + tss->eflags = kvm_x86_ops->get_rflags(vcpu); + tss->eax = vcpu->arch.regs[VCPU_REGS_RAX]; + tss->ecx = vcpu->arch.regs[VCPU_REGS_RCX]; + tss->edx = vcpu->arch.regs[VCPU_REGS_RDX]; + tss->ebx = vcpu->arch.regs[VCPU_REGS_RBX]; + tss->esp = vcpu->arch.regs[VCPU_REGS_RSP]; + tss->ebp = vcpu->arch.regs[VCPU_REGS_RBP]; + tss->esi = vcpu->arch.regs[VCPU_REGS_RSI]; + tss->edi = vcpu->arch.regs[VCPU_REGS_RDI]; + + tss->es = get_segment_selector(vcpu, VCPU_SREG_ES); + tss->cs = get_segment_selector(vcpu, VCPU_SREG_CS); + tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS); + tss->ds = get_segment_selector(vcpu, VCPU_SREG_DS); + tss->fs = get_segment_selector(vcpu, VCPU_SREG_FS); + tss->gs = get_segment_selector(vcpu, VCPU_SREG_GS); + tss->ldt_selector = get_segment_selector(vcpu, VCPU_SREG_LDTR); + tss->prev_task_link = get_segment_selector(vcpu, VCPU_SREG_TR); +} + +static int load_state_from_tss32(struct kvm_vcpu *vcpu, + struct tss_segment_32 *tss) +{ + kvm_set_cr3(vcpu, tss->cr3); + + vcpu->arch.rip = tss->eip; + kvm_x86_ops->set_rflags(vcpu, tss->eflags | 2); + + vcpu->arch.regs[VCPU_REGS_RAX] = tss->eax; + vcpu->arch.regs[VCPU_REGS_RCX] = tss->ecx; + vcpu->arch.regs[VCPU_REGS_RDX] = tss->edx; + vcpu->arch.regs[VCPU_REGS_RBX] = tss->ebx; + vcpu->arch.regs[VCPU_REGS_RSP] = tss->esp; + vcpu->arch.regs[VCPU_REGS_RBP] = tss->ebp; + vcpu->arch.regs[VCPU_REGS_RSI] = tss->esi; + vcpu->arch.regs[VCPU_REGS_RDI] = tss->edi; + + if (load_segment_descriptor(vcpu, tss->ldt_selector, 0, VCPU_SREG_LDTR)) + return 1; + + if (load_segment_descriptor(vcpu, tss->es, 1, VCPU_SREG_ES)) + return 1; + + if (load_segment_descriptor(vcpu, tss->cs, 9, VCPU_SREG_CS)) + return 1; + + if (load_segment_descriptor(vcpu, tss->ss, 1, VCPU_SREG_SS)) + return 1; + + if (load_segment_descriptor(vcpu, tss->ds, 1, VCPU_SREG_DS)) + return 1; + + if (load_segment_descriptor(vcpu, tss->fs, 1, VCPU_SREG_FS)) + return 1; + + if (load_segment_descriptor(vcpu, tss->gs, 1, VCPU_SREG_GS)) + return 1; + return 0; +} + +static void save_state_to_tss16(struct kvm_vcpu *vcpu, + struct tss_segment_16 *tss) +{ + tss->ip = vcpu->arch.rip; + tss->flag = kvm_x86_ops->get_rflags(vcpu); + tss->ax = vcpu->arch.regs[VCPU_REGS_RAX]; + tss->cx = vcpu->arch.regs[VCPU_REGS_RCX]; + tss->dx = vcpu->arch.regs[VCPU_REGS_RDX]; + tss->bx = vcpu->arch.regs[VCPU_REGS_RBX]; + tss->sp = vcpu->arch.regs[VCPU_REGS_RSP]; + tss->bp = vcpu->arch.regs[VCPU_REGS_RBP]; + tss->si = vcpu->arch.regs[VCPU_REGS_RSI]; + tss->di = vcpu->arch.regs[VCPU_REGS_RDI]; + + tss->es = get_segment_selector(vcpu, VCPU_SREG_ES); + tss->cs = get_segment_selector(vcpu, VCPU_SREG_CS); + tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS); + tss->ds = get_segment_selector(vcpu, VCPU_SREG_DS); + tss->ldt = get_segment_selector(vcpu, VCPU_SREG_LDTR); + tss->prev_task_link = get_segment_selector(vcpu, VCPU_SREG_TR); +} + +static int load_state_from_tss16(struct kvm_vcpu *vcpu, + struct tss_segment_16 *tss) +{ + vcpu->arch.rip = tss->ip; + kvm_x86_ops->set_rflags(vcpu, tss->flag | 2); + vcpu->arch.regs[VCPU_REGS_RAX] = tss->ax; + vcpu->arch.regs[VCPU_REGS_RCX] = tss->cx; + vcpu->arch.regs[VCPU_REGS_RDX] = tss->dx; + vcpu->arch.regs[VCPU_REGS_RBX] = tss->bx; + vcpu->arch.regs[VCPU_REGS_RSP] = tss->sp; + vcpu->arch.regs[VCPU_REGS_RBP] = tss->bp; + vcpu->arch.regs[VCPU_REGS_RSI] = tss->si; + vcpu->arch.regs[VCPU_REGS_RDI] = tss->di; + + if (load_segment_descriptor(vcpu, tss->ldt, 0, VCPU_SREG_LDTR)) + return 1; + + if (load_segment_descriptor(vcpu, tss->es, 1, VCPU_SREG_ES)) + return 1; + + if (load_segment_descriptor(vcpu, tss->cs, 9, VCPU_SREG_CS)) + return 1; + + if (load_segment_descriptor(vcpu, tss->ss, 1, VCPU_SREG_SS)) + return 1; + + if (load_segment_descriptor(vcpu, tss->ds, 1, VCPU_SREG_DS)) + return 1; + return 0; +} + +int kvm_task_switch_16(struct kvm_vcpu *vcpu, u16 tss_selector, + struct desc_struct *cseg_desc, + struct desc_struct *nseg_desc) +{ + struct tss_segment_16 tss_segment_16; + int ret = 0; + + if (load_tss_segment16(vcpu, cseg_desc, &tss_segment_16)) + goto out; + + save_state_to_tss16(vcpu, &tss_segment_16); + save_tss_segment16(vcpu, cseg_desc, &tss_segment_16); + + if (load_tss_segment16(vcpu, nseg_desc, &tss_segment_16)) + goto out; + if (load_state_from_tss16(vcpu, &tss_segment_16)) + goto out; + + ret = 1; +out: + return ret; +} + +int kvm_task_switch_32(struct kvm_vcpu *vcpu, u16 tss_selector, + struct desc_struct *cseg_desc, + struct desc_struct *nseg_desc) +{ + struct tss_segment_32 tss_segment_32; + int ret = 0; + + if (load_tss_segment32(vcpu, cseg_desc, &tss_segment_32)) + goto out; + + save_state_to_tss32(vcpu, &tss_segment_32); + save_tss_segment32(vcpu, cseg_desc, &tss_segment_32); + + if (load_tss_segment32(vcpu, nseg_desc, &tss_segment_32)) + goto out; + if (load_state_from_tss32(vcpu, &tss_segment_32)) + goto out; + + ret = 1; +out: + return ret; } +int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) +{ + struct kvm_segment tr_seg; + struct desc_struct cseg_desc; + struct desc_struct nseg_desc; + int ret = 0; + + get_segment(vcpu, &tr_seg, VCPU_SREG_TR); + + if (load_guest_segment_descriptor(vcpu, tss_selector, &nseg_desc)) + goto out; + + if (load_guest_segment_descriptor(vcpu, tr_seg.selector, &cseg_desc)) + goto out; + + + if (reason != TASK_SWITCH_IRET) { + int cpl; + + cpl = kvm_x86_ops->get_cpl(vcpu); + if ((tss_selector & 3) > nseg_desc.dpl || cpl > nseg_desc.dpl) { + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return 1; + } + } + + if (!nseg_desc.p || (nseg_desc.limit0 | nseg_desc.limit << 16) < 0x67) { + kvm_queue_exception_e(vcpu, TS_VECTOR, tss_selector & 0xfffc); + return 1; + } + + if (reason == TASK_SWITCH_IRET || reason == TASK_SWITCH_JMP) { + cseg_desc.type &= ~(1 << 8); //clear the B flag + save_guest_segment_descriptor(vcpu, tr_seg.selector, + &cseg_desc); + } + + if (reason == TASK_SWITCH_IRET) { + u32 eflags = kvm_x86_ops->get_rflags(vcpu); + kvm_x86_ops->set_rflags(vcpu, eflags & ~X86_EFLAGS_NT); + } + + kvm_x86_ops->skip_emulated_instruction(vcpu); + kvm_x86_ops->cache_regs(vcpu); + + if (nseg_desc.type & 8) + ret = kvm_task_switch_32(vcpu, tss_selector, &cseg_desc, + &nseg_desc); + else + ret = kvm_task_switch_16(vcpu, tss_selector, &cseg_desc, + &nseg_desc); + + if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) { + u32 eflags = kvm_x86_ops->get_rflags(vcpu); + kvm_x86_ops->set_rflags(vcpu, eflags | X86_EFLAGS_NT); + } + + if (reason != TASK_SWITCH_IRET) { + nseg_desc.type |= (1 << 8); + save_guest_segment_descriptor(vcpu, tss_selector, + &nseg_desc); + } + + kvm_x86_ops->set_cr0(vcpu, vcpu->arch.cr0 | X86_CR0_TS); + seg_desct_to_kvm_desct(&nseg_desc, tss_selector, &tr_seg); + tr_seg.type = 11; + set_segment(vcpu, &tr_seg, VCPU_SREG_TR); +out: + kvm_x86_ops->decache_regs(vcpu); + return ret; +} +EXPORT_SYMBOL_GPL(kvm_task_switch); + int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { @@ -2862,12 +3542,10 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, mmu_reset_needed |= vcpu->arch.cr3 != sregs->cr3; vcpu->arch.cr3 = sregs->cr3; - set_cr8(vcpu, sregs->cr8); + kvm_set_cr8(vcpu, sregs->cr8); mmu_reset_needed |= vcpu->arch.shadow_efer != sregs->efer; -#ifdef CONFIG_X86_64 kvm_x86_ops->set_efer(vcpu, sregs->efer); -#endif kvm_set_apic_base(vcpu, sregs->apic_base); kvm_x86_ops->decache_cr4_guest_bits(vcpu); @@ -3141,9 +3819,9 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) vcpu->arch.mmu.root_hpa = INVALID_PAGE; if (!irqchip_in_kernel(kvm) || vcpu->vcpu_id == 0) - vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE; + vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else - vcpu->arch.mp_state = VCPU_MP_STATE_UNINITIALIZED; + vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED; page = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!page) { @@ -3175,7 +3853,9 @@ fail: void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) { kvm_free_lapic(vcpu); + down_read(&vcpu->kvm->slots_lock); kvm_mmu_destroy(vcpu); + up_read(&vcpu->kvm->slots_lock); free_page((unsigned long)vcpu->arch.pio_data); } @@ -3219,10 +3899,13 @@ static void kvm_free_vcpus(struct kvm *kvm) void kvm_arch_destroy_vm(struct kvm *kvm) { + kvm_free_pit(kvm); kfree(kvm->arch.vpic); kfree(kvm->arch.vioapic); kvm_free_vcpus(kvm); kvm_free_physmem(kvm); + if (kvm->arch.apic_access_page) + put_page(kvm->arch.apic_access_page); kfree(kvm); } @@ -3278,8 +3961,8 @@ int kvm_arch_set_memory_region(struct kvm *kvm, int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { - return vcpu->arch.mp_state == VCPU_MP_STATE_RUNNABLE - || vcpu->arch.mp_state == VCPU_MP_STATE_SIPI_RECEIVED; + return vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE + || vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED; } static void vcpu_kick_intr(void *info) @@ -3293,11 +3976,17 @@ static void vcpu_kick_intr(void *info) void kvm_vcpu_kick(struct kvm_vcpu *vcpu) { int ipi_pcpu = vcpu->cpu; + int cpu = get_cpu(); if (waitqueue_active(&vcpu->wq)) { wake_up_interruptible(&vcpu->wq); ++vcpu->stat.halt_wakeup; } - if (vcpu->guest_mode) + /* + * We may be called synchronously with irqs disabled in guest mode, + * 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); + put_cpu(); } diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c index 79586003397a..2ca08386f993 100644 --- a/arch/x86/kvm/x86_emulate.c +++ b/arch/x86/kvm/x86_emulate.c @@ -65,6 +65,14 @@ #define MemAbs (1<<9) /* Memory operand is absolute displacement */ #define String (1<<10) /* String instruction (rep capable) */ #define Stack (1<<11) /* Stack instruction (push/pop) */ +#define Group (1<<14) /* Bits 3:5 of modrm byte extend opcode */ +#define GroupDual (1<<15) /* Alternate decoding of mod == 3 */ +#define GroupMask 0xff /* Group number stored in bits 0:7 */ + +enum { + Group1_80, Group1_81, Group1_82, Group1_83, + Group1A, Group3_Byte, Group3, Group4, Group5, Group7, +}; static u16 opcode_table[256] = { /* 0x00 - 0x07 */ @@ -123,14 +131,14 @@ static u16 opcode_table[256] = { ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, /* 0x80 - 0x87 */ - ByteOp | DstMem | SrcImm | ModRM, DstMem | SrcImm | ModRM, - ByteOp | DstMem | SrcImm | ModRM, DstMem | SrcImmByte | ModRM, + Group | Group1_80, Group | Group1_81, + Group | Group1_82, Group | Group1_83, ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, /* 0x88 - 0x8F */ ByteOp | DstMem | SrcReg | ModRM | Mov, DstMem | SrcReg | ModRM | Mov, ByteOp | DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov, - 0, ModRM | DstReg, 0, DstMem | SrcNone | ModRM | Mov | Stack, + 0, ModRM | DstReg, 0, Group | Group1A, /* 0x90 - 0x9F */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ImplicitOps | Stack, ImplicitOps | Stack, 0, 0, @@ -164,16 +172,15 @@ static u16 opcode_table[256] = { 0, 0, 0, 0, /* 0xF0 - 0xF7 */ 0, 0, 0, 0, - ImplicitOps, ImplicitOps, - ByteOp | DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM, + ImplicitOps, ImplicitOps, Group | Group3_Byte, Group | Group3, /* 0xF8 - 0xFF */ ImplicitOps, 0, ImplicitOps, ImplicitOps, - 0, 0, ByteOp | DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM + 0, 0, Group | Group4, Group | Group5, }; static u16 twobyte_table[256] = { /* 0x00 - 0x0F */ - 0, SrcMem | ModRM | DstReg, 0, 0, 0, 0, ImplicitOps, 0, + 0, Group | GroupDual | Group7, 0, 0, 0, 0, ImplicitOps, 0, ImplicitOps, ImplicitOps, 0, 0, 0, ImplicitOps | ModRM, 0, 0, /* 0x10 - 0x1F */ 0, 0, 0, 0, 0, 0, 0, 0, ImplicitOps | ModRM, 0, 0, 0, 0, 0, 0, 0, @@ -229,6 +236,56 @@ static u16 twobyte_table[256] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }; +static u16 group_table[] = { + [Group1_80*8] = + ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM, + ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM, + ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM, + ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM, + [Group1_81*8] = + DstMem | SrcImm | ModRM, DstMem | SrcImm | ModRM, + DstMem | SrcImm | ModRM, DstMem | SrcImm | ModRM, + DstMem | SrcImm | ModRM, DstMem | SrcImm | ModRM, + DstMem | SrcImm | ModRM, DstMem | SrcImm | ModRM, + [Group1_82*8] = + ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM, + ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM, + ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM, + ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM, + [Group1_83*8] = + DstMem | SrcImmByte | ModRM, DstMem | SrcImmByte | ModRM, + DstMem | SrcImmByte | ModRM, DstMem | SrcImmByte | ModRM, + DstMem | SrcImmByte | ModRM, DstMem | SrcImmByte | ModRM, + DstMem | SrcImmByte | ModRM, DstMem | SrcImmByte | ModRM, + [Group1A*8] = + DstMem | SrcNone | ModRM | Mov | Stack, 0, 0, 0, 0, 0, 0, 0, + [Group3_Byte*8] = + ByteOp | SrcImm | DstMem | ModRM, 0, + ByteOp | DstMem | SrcNone | ModRM, ByteOp | DstMem | SrcNone | ModRM, + 0, 0, 0, 0, + [Group3*8] = + DstMem | SrcImm | ModRM | SrcImm, 0, + DstMem | SrcNone | ModRM, ByteOp | DstMem | SrcNone | ModRM, + 0, 0, 0, 0, + [Group4*8] = + ByteOp | DstMem | SrcNone | ModRM, ByteOp | DstMem | SrcNone | ModRM, + 0, 0, 0, 0, 0, 0, + [Group5*8] = + DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM, 0, 0, + SrcMem | ModRM, 0, SrcMem | ModRM | Stack, 0, + [Group7*8] = + 0, 0, ModRM | SrcMem, ModRM | SrcMem, + SrcNone | ModRM | DstMem | Mov, 0, + SrcMem16 | ModRM | Mov, SrcMem | ModRM | ByteOp, +}; + +static u16 group2_table[] = { + [Group7*8] = + SrcNone | ModRM, 0, 0, 0, + SrcNone | ModRM | DstMem | Mov, 0, + SrcMem16 | ModRM | Mov, 0, +}; + /* EFLAGS bit definitions. */ #define EFLG_OF (1<<11) #define EFLG_DF (1<<10) @@ -317,7 +374,7 @@ static u16 twobyte_table[256] = { #define __emulate_2op(_op,_src,_dst,_eflags,_bx,_by,_wx,_wy,_lx,_ly,_qx,_qy) \ do { \ - unsigned long _tmp; \ + unsigned long __tmp; \ switch ((_dst).bytes) { \ case 1: \ __asm__ __volatile__ ( \ @@ -325,7 +382,7 @@ static u16 twobyte_table[256] = { _op"b %"_bx"3,%1; " \ _POST_EFLAGS("0", "4", "2") \ : "=m" (_eflags), "=m" ((_dst).val), \ - "=&r" (_tmp) \ + "=&r" (__tmp) \ : _by ((_src).val), "i" (EFLAGS_MASK)); \ break; \ default: \ @@ -426,29 +483,40 @@ static u16 twobyte_table[256] = { (_type)_x; \ }) +static inline unsigned long ad_mask(struct decode_cache *c) +{ + return (1UL << (c->ad_bytes << 3)) - 1; +} + /* Access/update address held in a register, based on addressing mode. */ -#define address_mask(reg) \ - ((c->ad_bytes == sizeof(unsigned long)) ? \ - (reg) : ((reg) & ((1UL << (c->ad_bytes << 3)) - 1))) -#define register_address(base, reg) \ - ((base) + address_mask(reg)) -#define register_address_increment(reg, inc) \ - do { \ - /* signed type ensures sign extension to long */ \ - int _inc = (inc); \ - if (c->ad_bytes == sizeof(unsigned long)) \ - (reg) += _inc; \ - else \ - (reg) = ((reg) & \ - ~((1UL << (c->ad_bytes << 3)) - 1)) | \ - (((reg) + _inc) & \ - ((1UL << (c->ad_bytes << 3)) - 1)); \ - } while (0) +static inline unsigned long +address_mask(struct decode_cache *c, unsigned long reg) +{ + if (c->ad_bytes == sizeof(unsigned long)) + return reg; + else + return reg & ad_mask(c); +} -#define JMP_REL(rel) \ - do { \ - register_address_increment(c->eip, rel); \ - } while (0) +static inline unsigned long +register_address(struct decode_cache *c, unsigned long base, unsigned long reg) +{ + return base + address_mask(c, reg); +} + +static inline void +register_address_increment(struct decode_cache *c, unsigned long *reg, int inc) +{ + if (c->ad_bytes == sizeof(unsigned long)) + *reg += inc; + else + *reg = (*reg & ~ad_mask(c)) | ((*reg + inc) & ad_mask(c)); +} + +static inline void jmp_rel(struct decode_cache *c, int rel) +{ + register_address_increment(c, &c->eip, rel); +} static int do_fetch_insn_byte(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops, @@ -763,7 +831,7 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) struct decode_cache *c = &ctxt->decode; int rc = 0; int mode = ctxt->mode; - int def_op_bytes, def_ad_bytes; + int def_op_bytes, def_ad_bytes, group; /* Shadow copy of register state. Committed on successful emulation. */ @@ -864,12 +932,24 @@ done_prefixes: c->b = insn_fetch(u8, 1, c->eip); c->d = twobyte_table[c->b]; } + } - /* Unrecognised? */ - if (c->d == 0) { - DPRINTF("Cannot emulate %02x\n", c->b); - return -1; - } + if (c->d & Group) { + group = c->d & GroupMask; + c->modrm = insn_fetch(u8, 1, c->eip); + --c->eip; + + group = (group << 3) + ((c->modrm >> 3) & 7); + if ((c->d & GroupDual) && (c->modrm >> 6) == 3) + c->d = group2_table[group]; + else + c->d = group_table[group]; + } + + /* Unrecognised? */ + if (c->d == 0) { + DPRINTF("Cannot emulate %02x\n", c->b); + return -1; } if (mode == X86EMUL_MODE_PROT64 && (c->d & Stack)) @@ -924,6 +1004,7 @@ done_prefixes: */ if ((c->d & ModRM) && c->modrm_mod == 3) { c->src.type = OP_REG; + c->src.val = c->modrm_val; break; } c->src.type = OP_MEM; @@ -967,6 +1048,7 @@ done_prefixes: case DstMem: if ((c->d & ModRM) && c->modrm_mod == 3) { c->dst.type = OP_REG; + c->dst.val = c->dst.orig_val = c->modrm_val; break; } c->dst.type = OP_MEM; @@ -984,8 +1066,8 @@ static inline void emulate_push(struct x86_emulate_ctxt *ctxt) c->dst.type = OP_MEM; c->dst.bytes = c->op_bytes; c->dst.val = c->src.val; - register_address_increment(c->regs[VCPU_REGS_RSP], -c->op_bytes); - c->dst.ptr = (void *) register_address(ctxt->ss_base, + register_address_increment(c, &c->regs[VCPU_REGS_RSP], -c->op_bytes); + c->dst.ptr = (void *) register_address(c, ctxt->ss_base, c->regs[VCPU_REGS_RSP]); } @@ -995,13 +1077,13 @@ static inline int emulate_grp1a(struct x86_emulate_ctxt *ctxt, struct decode_cache *c = &ctxt->decode; int rc; - rc = ops->read_std(register_address(ctxt->ss_base, + rc = ops->read_std(register_address(c, ctxt->ss_base, c->regs[VCPU_REGS_RSP]), &c->dst.val, c->dst.bytes, ctxt->vcpu); if (rc != 0) return rc; - register_address_increment(c->regs[VCPU_REGS_RSP], c->dst.bytes); + register_address_increment(c, &c->regs[VCPU_REGS_RSP], c->dst.bytes); return 0; } @@ -1043,26 +1125,6 @@ static inline int emulate_grp3(struct x86_emulate_ctxt *ctxt, switch (c->modrm_reg) { case 0 ... 1: /* test */ - /* - * Special case in Grp3: test has an immediate - * source operand. - */ - c->src.type = OP_IMM; - c->src.ptr = (unsigned long *)c->eip; - c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; - if (c->src.bytes == 8) - c->src.bytes = 4; - switch (c->src.bytes) { - case 1: - c->src.val = insn_fetch(s8, 1, c->eip); - break; - case 2: - c->src.val = insn_fetch(s16, 2, c->eip); - break; - case 4: - c->src.val = insn_fetch(s32, 4, c->eip); - break; - } emulate_2op_SrcV("test", c->src, c->dst, ctxt->eflags); break; case 2: /* not */ @@ -1076,7 +1138,6 @@ static inline int emulate_grp3(struct x86_emulate_ctxt *ctxt, rc = X86EMUL_UNHANDLEABLE; break; } -done: return rc; } @@ -1084,7 +1145,6 @@ static inline int emulate_grp45(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - int rc; switch (c->modrm_reg) { case 0: /* inc */ @@ -1094,36 +1154,11 @@ static inline int emulate_grp45(struct x86_emulate_ctxt *ctxt, emulate_1op("dec", c->dst, ctxt->eflags); break; case 4: /* jmp abs */ - if (c->b == 0xff) - c->eip = c->dst.val; - else { - DPRINTF("Cannot emulate %02x\n", c->b); - return X86EMUL_UNHANDLEABLE; - } + c->eip = c->src.val; break; case 6: /* push */ - - /* 64-bit mode: PUSH always pushes a 64-bit operand. */ - - if (ctxt->mode == X86EMUL_MODE_PROT64) { - c->dst.bytes = 8; - rc = ops->read_std((unsigned long)c->dst.ptr, - &c->dst.val, 8, ctxt->vcpu); - if (rc != 0) - return rc; - } - register_address_increment(c->regs[VCPU_REGS_RSP], - -c->dst.bytes); - rc = ops->write_emulated(register_address(ctxt->ss_base, - c->regs[VCPU_REGS_RSP]), &c->dst.val, - c->dst.bytes, ctxt->vcpu); - if (rc != 0) - return rc; - c->dst.type = OP_NONE; + emulate_push(ctxt); break; - default: - DPRINTF("Cannot emulate %02x\n", c->b); - return X86EMUL_UNHANDLEABLE; } return 0; } @@ -1361,19 +1396,19 @@ special_insn: c->dst.type = OP_MEM; c->dst.bytes = c->op_bytes; c->dst.val = c->src.val; - register_address_increment(c->regs[VCPU_REGS_RSP], + register_address_increment(c, &c->regs[VCPU_REGS_RSP], -c->op_bytes); c->dst.ptr = (void *) register_address( - ctxt->ss_base, c->regs[VCPU_REGS_RSP]); + c, ctxt->ss_base, c->regs[VCPU_REGS_RSP]); break; case 0x58 ... 0x5f: /* pop reg */ pop_instruction: - if ((rc = ops->read_std(register_address(ctxt->ss_base, + if ((rc = ops->read_std(register_address(c, ctxt->ss_base, c->regs[VCPU_REGS_RSP]), c->dst.ptr, c->op_bytes, ctxt->vcpu)) != 0) goto done; - register_address_increment(c->regs[VCPU_REGS_RSP], + register_address_increment(c, &c->regs[VCPU_REGS_RSP], c->op_bytes); c->dst.type = OP_NONE; /* Disable writeback. */ break; @@ -1393,9 +1428,9 @@ special_insn: 1, (c->d & ByteOp) ? 1 : c->op_bytes, c->rep_prefix ? - address_mask(c->regs[VCPU_REGS_RCX]) : 1, + address_mask(c, c->regs[VCPU_REGS_RCX]) : 1, (ctxt->eflags & EFLG_DF), - register_address(ctxt->es_base, + register_address(c, ctxt->es_base, c->regs[VCPU_REGS_RDI]), c->rep_prefix, c->regs[VCPU_REGS_RDX]) == 0) { @@ -1409,9 +1444,9 @@ special_insn: 0, (c->d & ByteOp) ? 1 : c->op_bytes, c->rep_prefix ? - address_mask(c->regs[VCPU_REGS_RCX]) : 1, + address_mask(c, c->regs[VCPU_REGS_RCX]) : 1, (ctxt->eflags & EFLG_DF), - register_address(c->override_base ? + register_address(c, c->override_base ? *c->override_base : ctxt->ds_base, c->regs[VCPU_REGS_RSI]), @@ -1425,7 +1460,7 @@ special_insn: int rel = insn_fetch(s8, 1, c->eip); if (test_cc(c->b, ctxt->eflags)) - JMP_REL(rel); + jmp_rel(c, rel); break; } case 0x80 ... 0x83: /* Grp1 */ @@ -1477,7 +1512,7 @@ special_insn: case 0x88 ... 0x8b: /* mov */ goto mov; case 0x8d: /* lea r16/r32, m */ - c->dst.val = c->modrm_val; + c->dst.val = c->modrm_ea; break; case 0x8f: /* pop (sole member of Grp1a) */ rc = emulate_grp1a(ctxt, ops); @@ -1501,27 +1536,27 @@ special_insn: case 0xa4 ... 0xa5: /* movs */ c->dst.type = OP_MEM; c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; - c->dst.ptr = (unsigned long *)register_address( + c->dst.ptr = (unsigned long *)register_address(c, ctxt->es_base, c->regs[VCPU_REGS_RDI]); - if ((rc = ops->read_emulated(register_address( + if ((rc = ops->read_emulated(register_address(c, c->override_base ? *c->override_base : ctxt->ds_base, c->regs[VCPU_REGS_RSI]), &c->dst.val, c->dst.bytes, ctxt->vcpu)) != 0) goto done; - register_address_increment(c->regs[VCPU_REGS_RSI], + register_address_increment(c, &c->regs[VCPU_REGS_RSI], (ctxt->eflags & EFLG_DF) ? -c->dst.bytes : c->dst.bytes); - register_address_increment(c->regs[VCPU_REGS_RDI], + register_address_increment(c, &c->regs[VCPU_REGS_RDI], (ctxt->eflags & EFLG_DF) ? -c->dst.bytes : c->dst.bytes); break; case 0xa6 ... 0xa7: /* cmps */ c->src.type = OP_NONE; /* Disable writeback. */ c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; - c->src.ptr = (unsigned long *)register_address( + c->src.ptr = (unsigned long *)register_address(c, c->override_base ? *c->override_base : ctxt->ds_base, c->regs[VCPU_REGS_RSI]); @@ -1533,7 +1568,7 @@ special_insn: c->dst.type = OP_NONE; /* Disable writeback. */ c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; - c->dst.ptr = (unsigned long *)register_address( + c->dst.ptr = (unsigned long *)register_address(c, ctxt->es_base, c->regs[VCPU_REGS_RDI]); if ((rc = ops->read_emulated((unsigned long)c->dst.ptr, @@ -1546,10 +1581,10 @@ special_insn: emulate_2op_SrcV("cmp", c->src, c->dst, ctxt->eflags); - register_address_increment(c->regs[VCPU_REGS_RSI], + register_address_increment(c, &c->regs[VCPU_REGS_RSI], (ctxt->eflags & EFLG_DF) ? -c->src.bytes : c->src.bytes); - register_address_increment(c->regs[VCPU_REGS_RDI], + register_address_increment(c, &c->regs[VCPU_REGS_RDI], (ctxt->eflags & EFLG_DF) ? -c->dst.bytes : c->dst.bytes); @@ -1557,11 +1592,11 @@ special_insn: case 0xaa ... 0xab: /* stos */ c->dst.type = OP_MEM; c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; - c->dst.ptr = (unsigned long *)register_address( + c->dst.ptr = (unsigned long *)register_address(c, ctxt->es_base, c->regs[VCPU_REGS_RDI]); c->dst.val = c->regs[VCPU_REGS_RAX]; - register_address_increment(c->regs[VCPU_REGS_RDI], + register_address_increment(c, &c->regs[VCPU_REGS_RDI], (ctxt->eflags & EFLG_DF) ? -c->dst.bytes : c->dst.bytes); break; @@ -1569,7 +1604,7 @@ special_insn: c->dst.type = OP_REG; c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; c->dst.ptr = (unsigned long *)&c->regs[VCPU_REGS_RAX]; - if ((rc = ops->read_emulated(register_address( + if ((rc = ops->read_emulated(register_address(c, c->override_base ? *c->override_base : ctxt->ds_base, c->regs[VCPU_REGS_RSI]), @@ -1577,7 +1612,7 @@ special_insn: c->dst.bytes, ctxt->vcpu)) != 0) goto done; - register_address_increment(c->regs[VCPU_REGS_RSI], + register_address_increment(c, &c->regs[VCPU_REGS_RSI], (ctxt->eflags & EFLG_DF) ? -c->dst.bytes : c->dst.bytes); break; @@ -1616,14 +1651,14 @@ special_insn: goto cannot_emulate; } c->src.val = (unsigned long) c->eip; - JMP_REL(rel); + jmp_rel(c, rel); c->op_bytes = c->ad_bytes; emulate_push(ctxt); break; } case 0xe9: /* jmp rel */ case 0xeb: /* jmp rel short */ - JMP_REL(c->src.val); + jmp_rel(c, c->src.val); c->dst.type = OP_NONE; /* Disable writeback. */ break; case 0xf4: /* hlt */ @@ -1690,6 +1725,8 @@ twobyte_insn: goto done; kvm_emulate_hypercall(ctxt->vcpu); + /* Disable writeback. */ + c->dst.type = OP_NONE; break; case 2: /* lgdt */ rc = read_descriptor(ctxt, ops, c->src.ptr, @@ -1697,6 +1734,8 @@ twobyte_insn: if (rc) goto done; realmode_lgdt(ctxt->vcpu, size, address); + /* Disable writeback. */ + c->dst.type = OP_NONE; break; case 3: /* lidt/vmmcall */ if (c->modrm_mod == 3 && c->modrm_rm == 1) { @@ -1712,27 +1751,25 @@ twobyte_insn: goto done; realmode_lidt(ctxt->vcpu, size, address); } + /* Disable writeback. */ + c->dst.type = OP_NONE; break; case 4: /* smsw */ - if (c->modrm_mod != 3) - goto cannot_emulate; - *(u16 *)&c->regs[c->modrm_rm] - = realmode_get_cr(ctxt->vcpu, 0); + c->dst.bytes = 2; + c->dst.val = realmode_get_cr(ctxt->vcpu, 0); break; case 6: /* lmsw */ - if (c->modrm_mod != 3) - goto cannot_emulate; - realmode_lmsw(ctxt->vcpu, (u16)c->modrm_val, - &ctxt->eflags); + realmode_lmsw(ctxt->vcpu, (u16)c->src.val, + &ctxt->eflags); break; case 7: /* invlpg*/ emulate_invlpg(ctxt->vcpu, memop); + /* Disable writeback. */ + c->dst.type = OP_NONE; break; default: goto cannot_emulate; } - /* Disable writeback. */ - c->dst.type = OP_NONE; break; case 0x06: emulate_clts(ctxt->vcpu); @@ -1823,7 +1860,7 @@ twobyte_insn: goto cannot_emulate; } if (test_cc(c->b, ctxt->eflags)) - JMP_REL(rel); + jmp_rel(c, rel); c->dst.type = OP_NONE; break; } diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 3335b4595efd..af65b2da3ba0 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -661,7 +661,7 @@ static int lguest_clockevent_set_next_event(unsigned long delta, if (delta < LG_CLOCK_MIN_DELTA) { if (printk_ratelimit()) printk(KERN_DEBUG "%s: small delta %lu ns\n", - __FUNCTION__, delta); + __func__, delta); return -ETIME; } diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 25df1c1989fe..76f60f52a885 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -11,7 +11,7 @@ lib-y += memcpy_$(BITS).o ifeq ($(CONFIG_X86_32),y) lib-y += checksum_32.o lib-y += strstr_32.o - lib-y += bitops_32.o semaphore_32.o string_32.o + lib-y += semaphore_32.o string_32.o lib-$(CONFIG_X86_USE_3DNOW) += mmx_32.o else @@ -21,7 +21,6 @@ else lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o lib-y += thunk_64.o clear_page_64.o copy_page_64.o - lib-y += bitops_64.o lib-y += memmove_64.o memset_64.o lib-y += copy_user_64.o rwlock_64.o copy_user_nocache_64.o endif diff --git a/arch/x86/lib/bitops_32.c b/arch/x86/lib/bitops_32.c deleted file mode 100644 index b65440459859..000000000000 --- a/arch/x86/lib/bitops_32.c +++ /dev/null @@ -1,70 +0,0 @@ -#include <linux/bitops.h> -#include <linux/module.h> - -/** - * find_next_bit - find the next set bit in a memory region - * @addr: The address to base the search on - * @offset: The bitnumber to start searching at - * @size: The maximum size to search - */ -int find_next_bit(const unsigned long *addr, int size, int offset) -{ - const unsigned long *p = addr + (offset >> 5); - int set = 0, bit = offset & 31, res; - - if (bit) { - /* - * Look for nonzero in the first 32 bits: - */ - __asm__("bsfl %1,%0\n\t" - "jne 1f\n\t" - "movl $32, %0\n" - "1:" - : "=r" (set) - : "r" (*p >> bit)); - if (set < (32 - bit)) - return set + offset; - set = 32 - bit; - p++; - } - /* - * No set bit yet, search remaining full words for a bit - */ - res = find_first_bit (p, size - 32 * (p - addr)); - return (offset + set + res); -} -EXPORT_SYMBOL(find_next_bit); - -/** - * find_next_zero_bit - find the first zero bit in a memory region - * @addr: The address to base the search on - * @offset: The bitnumber to start searching at - * @size: The maximum size to search - */ -int find_next_zero_bit(const unsigned long *addr, int size, int offset) -{ - const unsigned long *p = addr + (offset >> 5); - int set = 0, bit = offset & 31, res; - - if (bit) { - /* - * Look for zero in the first 32 bits. - */ - __asm__("bsfl %1,%0\n\t" - "jne 1f\n\t" - "movl $32, %0\n" - "1:" - : "=r" (set) - : "r" (~(*p >> bit))); - if (set < (32 - bit)) - return set + offset; - set = 32 - bit; - p++; - } - /* - * No zero yet, search remaining full bytes for a zero - */ - res = find_first_zero_bit(p, size - 32 * (p - addr)); - return (offset + set + res); -} -EXPORT_SYMBOL(find_next_zero_bit); diff --git a/arch/x86/lib/bitops_64.c b/arch/x86/lib/bitops_64.c deleted file mode 100644 index 0e8f491e6ccc..000000000000 --- a/arch/x86/lib/bitops_64.c +++ /dev/null @@ -1,175 +0,0 @@ -#include <linux/bitops.h> - -#undef find_first_zero_bit -#undef find_next_zero_bit -#undef find_first_bit -#undef find_next_bit - -static inline long -__find_first_zero_bit(const unsigned long * addr, unsigned long size) -{ - long d0, d1, d2; - long res; - - /* - * We must test the size in words, not in bits, because - * otherwise incoming sizes in the range -63..-1 will not run - * any scasq instructions, and then the flags used by the je - * instruction will have whatever random value was in place - * before. Nobody should call us like that, but - * find_next_zero_bit() does when offset and size are at the - * same word and it fails to find a zero itself. - */ - size += 63; - size >>= 6; - if (!size) - return 0; - asm volatile( - " repe; scasq\n" - " je 1f\n" - " xorq -8(%%rdi),%%rax\n" - " subq $8,%%rdi\n" - " bsfq %%rax,%%rdx\n" - "1: subq %[addr],%%rdi\n" - " shlq $3,%%rdi\n" - " addq %%rdi,%%rdx" - :"=d" (res), "=&c" (d0), "=&D" (d1), "=&a" (d2) - :"0" (0ULL), "1" (size), "2" (addr), "3" (-1ULL), - [addr] "S" (addr) : "memory"); - /* - * Any register would do for [addr] above, but GCC tends to - * prefer rbx over rsi, even though rsi is readily available - * and doesn't have to be saved. - */ - return res; -} - -/** - * find_first_zero_bit - find the first zero bit in a memory region - * @addr: The address to start the search at - * @size: The maximum size to search - * - * Returns the bit-number of the first zero bit, not the number of the byte - * containing a bit. - */ -long find_first_zero_bit(const unsigned long * addr, unsigned long size) -{ - return __find_first_zero_bit (addr, size); -} - -/** - * find_next_zero_bit - find the next zero bit in a memory region - * @addr: The address to base the search on - * @offset: The bitnumber to start searching at - * @size: The maximum size to search - */ -long find_next_zero_bit (const unsigned long * addr, long size, long offset) -{ - const unsigned long * p = addr + (offset >> 6); - unsigned long set = 0; - unsigned long res, bit = offset&63; - - if (bit) { - /* - * Look for zero in first word - */ - asm("bsfq %1,%0\n\t" - "cmoveq %2,%0" - : "=r" (set) - : "r" (~(*p >> bit)), "r"(64L)); - if (set < (64 - bit)) - return set + offset; - set = 64 - bit; - p++; - } - /* - * No zero yet, search remaining full words for a zero - */ - res = __find_first_zero_bit (p, size - 64 * (p - addr)); - - return (offset + set + res); -} - -static inline long -__find_first_bit(const unsigned long * addr, unsigned long size) -{ - long d0, d1; - long res; - - /* - * We must test the size in words, not in bits, because - * otherwise incoming sizes in the range -63..-1 will not run - * any scasq instructions, and then the flags used by the jz - * instruction will have whatever random value was in place - * before. Nobody should call us like that, but - * find_next_bit() does when offset and size are at the same - * word and it fails to find a one itself. - */ - size += 63; - size >>= 6; - if (!size) - return 0; - asm volatile( - " repe; scasq\n" - " jz 1f\n" - " subq $8,%%rdi\n" - " bsfq (%%rdi),%%rax\n" - "1: subq %[addr],%%rdi\n" - " shlq $3,%%rdi\n" - " addq %%rdi,%%rax" - :"=a" (res), "=&c" (d0), "=&D" (d1) - :"0" (0ULL), "1" (size), "2" (addr), - [addr] "r" (addr) : "memory"); - return res; -} - -/** - * find_first_bit - find the first set bit in a memory region - * @addr: The address to start the search at - * @size: The maximum size to search - * - * Returns the bit-number of the first set bit, not the number of the byte - * containing a bit. - */ -long find_first_bit(const unsigned long * addr, unsigned long size) -{ - return __find_first_bit(addr,size); -} - -/** - * find_next_bit - find the first set bit in a memory region - * @addr: The address to base the search on - * @offset: The bitnumber to start searching at - * @size: The maximum size to search - */ -long find_next_bit(const unsigned long * addr, long size, long offset) -{ - const unsigned long * p = addr + (offset >> 6); - unsigned long set = 0, bit = offset & 63, res; - - if (bit) { - /* - * Look for nonzero in the first 64 bits: - */ - asm("bsfq %1,%0\n\t" - "cmoveq %2,%0\n\t" - : "=r" (set) - : "r" (*p >> bit), "r" (64L)); - if (set < (64 - bit)) - return set + offset; - set = 64 - bit; - p++; - } - /* - * No set bit yet, search remaining full words for a bit - */ - res = __find_first_bit (p, size - 64 * (p - addr)); - return (offset + set + res); -} - -#include <linux/module.h> - -EXPORT_SYMBOL(find_next_bit); -EXPORT_SYMBOL(find_first_bit); -EXPORT_SYMBOL(find_first_zero_bit); -EXPORT_SYMBOL(find_next_zero_bit); diff --git a/arch/x86/lib/memcpy_32.c b/arch/x86/lib/memcpy_32.c index 37756b6fb329..5415a9d06f53 100644 --- a/arch/x86/lib/memcpy_32.c +++ b/arch/x86/lib/memcpy_32.c @@ -25,7 +25,7 @@ void *memmove(void *dest, const void *src, size_t n) int d0, d1, d2; if (dest < src) { - memcpy(dest,src,n); + memcpy(dest, src, n); } else { __asm__ __volatile__( "std\n\t" diff --git a/arch/x86/lib/memmove_64.c b/arch/x86/lib/memmove_64.c index 80175e47b190..0a33909bf122 100644 --- a/arch/x86/lib/memmove_64.c +++ b/arch/x86/lib/memmove_64.c @@ -6,10 +6,10 @@ #include <linux/module.h> #undef memmove -void *memmove(void * dest,const void *src,size_t count) +void *memmove(void *dest, const void *src, size_t count) { - if (dest < src) { - return memcpy(dest,src,count); + if (dest < src) { + return memcpy(dest, src, count); } else { char *p = dest + count; const char *s = src + count; @@ -17,5 +17,5 @@ void *memmove(void * dest,const void *src,size_t count) *--p = *--s; } return dest; -} +} EXPORT_SYMBOL(memmove); diff --git a/arch/x86/lib/mmx_32.c b/arch/x86/lib/mmx_32.c index cc9b4a4450f3..c9f2d9ba8dd8 100644 --- a/arch/x86/lib/mmx_32.c +++ b/arch/x86/lib/mmx_32.c @@ -1,32 +1,30 @@ -#include <linux/types.h> -#include <linux/string.h> -#include <linux/sched.h> -#include <linux/hardirq.h> -#include <linux/module.h> - -#include <asm/asm.h> -#include <asm/i387.h> - - /* * MMX 3DNow! library helper functions * * To do: - * We can use MMX just for prefetch in IRQ's. This may be a win. + * We can use MMX just for prefetch in IRQ's. This may be a win. * (reported so on K6-III) * We should use a better code neutral filler for the short jump * leal ebx. [ebx] is apparently best for K6-2, but Cyrix ?? * We also want to clobber the filler register so we don't get any - * register forwarding stalls on the filler. + * register forwarding stalls on the filler. * * Add *user handling. Checksums are not a win with MMX on any CPU * tested so far for any MMX solution figured. * - * 22/09/2000 - Arjan van de Ven - * Improved for non-egineering-sample Athlons + * 22/09/2000 - Arjan van de Ven + * Improved for non-egineering-sample Athlons * */ - +#include <linux/hardirq.h> +#include <linux/string.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/types.h> + +#include <asm/i387.h> +#include <asm/asm.h> + void *_mmx_memcpy(void *to, const void *from, size_t len) { void *p; @@ -51,12 +49,10 @@ void *_mmx_memcpy(void *to, const void *from, size_t len) "3: movw $0x1AEB, 1b\n" /* jmp on 26 bytes */ " jmp 2b\n" ".previous\n" - _ASM_EXTABLE(1b,3b) - : : "r" (from) ); - - - for(; i>5; i--) - { + _ASM_EXTABLE(1b, 3b) + : : "r" (from)); + + for ( ; i > 5; i--) { __asm__ __volatile__ ( "1: prefetch 320(%0)\n" "2: movq (%0), %%mm0\n" @@ -79,14 +75,14 @@ void *_mmx_memcpy(void *to, const void *from, size_t len) "3: movw $0x05EB, 1b\n" /* jmp on 5 bytes */ " jmp 2b\n" ".previous\n" - _ASM_EXTABLE(1b,3b) - : : "r" (from), "r" (to) : "memory"); - from+=64; - to+=64; + _ASM_EXTABLE(1b, 3b) + : : "r" (from), "r" (to) : "memory"); + + from += 64; + to += 64; } - for(; i>0; i--) - { + for ( ; i > 0; i--) { __asm__ __volatile__ ( " movq (%0), %%mm0\n" " movq 8(%0), %%mm1\n" @@ -104,17 +100,20 @@ void *_mmx_memcpy(void *to, const void *from, size_t len) " movq %%mm1, 40(%1)\n" " movq %%mm2, 48(%1)\n" " movq %%mm3, 56(%1)\n" - : : "r" (from), "r" (to) : "memory"); - from+=64; - to+=64; + : : "r" (from), "r" (to) : "memory"); + + from += 64; + to += 64; } /* - * Now do the tail of the block + * Now do the tail of the block: */ - __memcpy(to, from, len&63); + __memcpy(to, from, len & 63); kernel_fpu_end(); + return p; } +EXPORT_SYMBOL(_mmx_memcpy); #ifdef CONFIG_MK7 @@ -128,13 +127,12 @@ static void fast_clear_page(void *page) int i; kernel_fpu_begin(); - + __asm__ __volatile__ ( " pxor %%mm0, %%mm0\n" : : ); - for(i=0;i<4096/64;i++) - { + for (i = 0; i < 4096/64; i++) { __asm__ __volatile__ ( " movntq %%mm0, (%0)\n" " movntq %%mm0, 8(%0)\n" @@ -145,14 +143,15 @@ static void fast_clear_page(void *page) " movntq %%mm0, 48(%0)\n" " movntq %%mm0, 56(%0)\n" : : "r" (page) : "memory"); - page+=64; + page += 64; } - /* since movntq is weakly-ordered, a "sfence" is needed to become - * ordered again. + + /* + * Since movntq is weakly-ordered, a "sfence" is needed to become + * ordered again: */ - __asm__ __volatile__ ( - " sfence \n" : : - ); + __asm__ __volatile__("sfence\n"::); + kernel_fpu_end(); } @@ -162,10 +161,11 @@ static void fast_copy_page(void *to, void *from) kernel_fpu_begin(); - /* maybe the prefetch stuff can go before the expensive fnsave... + /* + * maybe the prefetch stuff can go before the expensive fnsave... * but that is for later. -AV */ - __asm__ __volatile__ ( + __asm__ __volatile__( "1: prefetch (%0)\n" " prefetch 64(%0)\n" " prefetch 128(%0)\n" @@ -176,11 +176,9 @@ static void fast_copy_page(void *to, void *from) "3: movw $0x1AEB, 1b\n" /* jmp on 26 bytes */ " jmp 2b\n" ".previous\n" - _ASM_EXTABLE(1b,3b) - : : "r" (from) ); + _ASM_EXTABLE(1b, 3b) : : "r" (from)); - for(i=0; i<(4096-320)/64; i++) - { + for (i = 0; i < (4096-320)/64; i++) { __asm__ __volatile__ ( "1: prefetch 320(%0)\n" "2: movq (%0), %%mm0\n" @@ -203,13 +201,13 @@ static void fast_copy_page(void *to, void *from) "3: movw $0x05EB, 1b\n" /* jmp on 5 bytes */ " jmp 2b\n" ".previous\n" - _ASM_EXTABLE(1b,3b) - : : "r" (from), "r" (to) : "memory"); - from+=64; - to+=64; + _ASM_EXTABLE(1b, 3b) : : "r" (from), "r" (to) : "memory"); + + from += 64; + to += 64; } - for(i=(4096-320)/64; i<4096/64; i++) - { + + for (i = (4096-320)/64; i < 4096/64; i++) { __asm__ __volatile__ ( "2: movq (%0), %%mm0\n" " movntq %%mm0, (%1)\n" @@ -227,37 +225,34 @@ static void fast_copy_page(void *to, void *from) " movntq %%mm6, 48(%1)\n" " movq 56(%0), %%mm7\n" " movntq %%mm7, 56(%1)\n" - : : "r" (from), "r" (to) : "memory"); - from+=64; - to+=64; + : : "r" (from), "r" (to) : "memory"); + from += 64; + to += 64; } - /* since movntq is weakly-ordered, a "sfence" is needed to become - * ordered again. + /* + * Since movntq is weakly-ordered, a "sfence" is needed to become + * ordered again: */ - __asm__ __volatile__ ( - " sfence \n" : : - ); + __asm__ __volatile__("sfence \n"::); kernel_fpu_end(); } -#else +#else /* CONFIG_MK7 */ /* * Generic MMX implementation without K7 specific streaming */ - static void fast_clear_page(void *page) { int i; - + kernel_fpu_begin(); - + __asm__ __volatile__ ( " pxor %%mm0, %%mm0\n" : : ); - for(i=0;i<4096/128;i++) - { + for (i = 0; i < 4096/128; i++) { __asm__ __volatile__ ( " movq %%mm0, (%0)\n" " movq %%mm0, 8(%0)\n" @@ -275,8 +270,8 @@ static void fast_clear_page(void *page) " movq %%mm0, 104(%0)\n" " movq %%mm0, 112(%0)\n" " movq %%mm0, 120(%0)\n" - : : "r" (page) : "memory"); - page+=128; + : : "r" (page) : "memory"); + page += 128; } kernel_fpu_end(); @@ -285,8 +280,7 @@ static void fast_clear_page(void *page) static void fast_copy_page(void *to, void *from) { int i; - - + kernel_fpu_begin(); __asm__ __volatile__ ( @@ -300,11 +294,9 @@ static void fast_copy_page(void *to, void *from) "3: movw $0x1AEB, 1b\n" /* jmp on 26 bytes */ " jmp 2b\n" ".previous\n" - _ASM_EXTABLE(1b,3b) - : : "r" (from) ); + _ASM_EXTABLE(1b, 3b) : : "r" (from)); - for(i=0; i<4096/64; i++) - { + for (i = 0; i < 4096/64; i++) { __asm__ __volatile__ ( "1: prefetch 320(%0)\n" "2: movq (%0), %%mm0\n" @@ -327,60 +319,59 @@ static void fast_copy_page(void *to, void *from) "3: movw $0x05EB, 1b\n" /* jmp on 5 bytes */ " jmp 2b\n" ".previous\n" - _ASM_EXTABLE(1b,3b) - : : "r" (from), "r" (to) : "memory"); - from+=64; - to+=64; + _ASM_EXTABLE(1b, 3b) + : : "r" (from), "r" (to) : "memory"); + + from += 64; + to += 64; } kernel_fpu_end(); } - -#endif +#endif /* !CONFIG_MK7 */ /* - * Favour MMX for page clear and copy. + * Favour MMX for page clear and copy: */ - -static void slow_zero_page(void * page) +static void slow_zero_page(void *page) { int d0, d1; - __asm__ __volatile__( \ - "cld\n\t" \ - "rep ; stosl" \ - : "=&c" (d0), "=&D" (d1) - :"a" (0),"1" (page),"0" (1024) - :"memory"); + + __asm__ __volatile__( + "cld\n\t" + "rep ; stosl" + + : "=&c" (d0), "=&D" (d1) + :"a" (0), "1" (page), "0" (1024) + :"memory"); } - -void mmx_clear_page(void * page) + +void mmx_clear_page(void *page) { - if(unlikely(in_interrupt())) + if (unlikely(in_interrupt())) slow_zero_page(page); else fast_clear_page(page); } +EXPORT_SYMBOL(mmx_clear_page); static void slow_copy_page(void *to, void *from) { int d0, d1, d2; - __asm__ __volatile__( \ - "cld\n\t" \ - "rep ; movsl" \ - : "=&c" (d0), "=&D" (d1), "=&S" (d2) \ - : "0" (1024),"1" ((long) to),"2" ((long) from) \ + + __asm__ __volatile__( + "cld\n\t" + "rep ; movsl" + : "=&c" (d0), "=&D" (d1), "=&S" (d2) + : "0" (1024), "1" ((long) to), "2" ((long) from) : "memory"); } - void mmx_copy_page(void *to, void *from) { - if(unlikely(in_interrupt())) + if (unlikely(in_interrupt())) slow_copy_page(to, from); else fast_copy_page(to, from); } - -EXPORT_SYMBOL(_mmx_memcpy); -EXPORT_SYMBOL(mmx_clear_page); EXPORT_SYMBOL(mmx_copy_page); diff --git a/arch/x86/lib/semaphore_32.S b/arch/x86/lib/semaphore_32.S index 3899bd37fdf0..648fe4741782 100644 --- a/arch/x86/lib/semaphore_32.S +++ b/arch/x86/lib/semaphore_32.S @@ -30,89 +30,6 @@ * value or just clobbered.. */ .section .sched.text, "ax" -ENTRY(__down_failed) - CFI_STARTPROC - FRAME - pushl %edx - CFI_ADJUST_CFA_OFFSET 4 - CFI_REL_OFFSET edx,0 - pushl %ecx - CFI_ADJUST_CFA_OFFSET 4 - CFI_REL_OFFSET ecx,0 - call __down - popl %ecx - CFI_ADJUST_CFA_OFFSET -4 - CFI_RESTORE ecx - popl %edx - CFI_ADJUST_CFA_OFFSET -4 - CFI_RESTORE edx - ENDFRAME - ret - CFI_ENDPROC - ENDPROC(__down_failed) - -ENTRY(__down_failed_interruptible) - CFI_STARTPROC - FRAME - pushl %edx - CFI_ADJUST_CFA_OFFSET 4 - CFI_REL_OFFSET edx,0 - pushl %ecx - CFI_ADJUST_CFA_OFFSET 4 - CFI_REL_OFFSET ecx,0 - call __down_interruptible - popl %ecx - CFI_ADJUST_CFA_OFFSET -4 - CFI_RESTORE ecx - popl %edx - CFI_ADJUST_CFA_OFFSET -4 - CFI_RESTORE edx - ENDFRAME - ret - CFI_ENDPROC - ENDPROC(__down_failed_interruptible) - -ENTRY(__down_failed_trylock) - CFI_STARTPROC - FRAME - pushl %edx - CFI_ADJUST_CFA_OFFSET 4 - CFI_REL_OFFSET edx,0 - pushl %ecx - CFI_ADJUST_CFA_OFFSET 4 - CFI_REL_OFFSET ecx,0 - call __down_trylock - popl %ecx - CFI_ADJUST_CFA_OFFSET -4 - CFI_RESTORE ecx - popl %edx - CFI_ADJUST_CFA_OFFSET -4 - CFI_RESTORE edx - ENDFRAME - ret - CFI_ENDPROC - ENDPROC(__down_failed_trylock) - -ENTRY(__up_wakeup) - CFI_STARTPROC - FRAME - pushl %edx - CFI_ADJUST_CFA_OFFSET 4 - CFI_REL_OFFSET edx,0 - pushl %ecx - CFI_ADJUST_CFA_OFFSET 4 - CFI_REL_OFFSET ecx,0 - call __up - popl %ecx - CFI_ADJUST_CFA_OFFSET -4 - CFI_RESTORE ecx - popl %edx - CFI_ADJUST_CFA_OFFSET -4 - CFI_RESTORE edx - ENDFRAME - ret - CFI_ENDPROC - ENDPROC(__up_wakeup) /* * rw spinlock fallbacks diff --git a/arch/x86/lib/string_32.c b/arch/x86/lib/string_32.c index c2c0504a3071..94972e7c094d 100644 --- a/arch/x86/lib/string_32.c +++ b/arch/x86/lib/string_32.c @@ -14,25 +14,25 @@ #include <linux/module.h> #ifdef __HAVE_ARCH_STRCPY -char *strcpy(char * dest,const char *src) +char *strcpy(char *dest, const char *src) { int d0, d1, d2; - asm volatile( "1:\tlodsb\n\t" + asm volatile("1:\tlodsb\n\t" "stosb\n\t" "testb %%al,%%al\n\t" "jne 1b" : "=&S" (d0), "=&D" (d1), "=&a" (d2) - :"0" (src),"1" (dest) : "memory"); + :"0" (src), "1" (dest) : "memory"); return dest; } EXPORT_SYMBOL(strcpy); #endif #ifdef __HAVE_ARCH_STRNCPY -char *strncpy(char * dest,const char *src,size_t count) +char *strncpy(char *dest, const char *src, size_t count) { int d0, d1, d2, d3; - asm volatile( "1:\tdecl %2\n\t" + asm volatile("1:\tdecl %2\n\t" "js 2f\n\t" "lodsb\n\t" "stosb\n\t" @@ -42,17 +42,17 @@ char *strncpy(char * dest,const char *src,size_t count) "stosb\n" "2:" : "=&S" (d0), "=&D" (d1), "=&c" (d2), "=&a" (d3) - :"0" (src),"1" (dest),"2" (count) : "memory"); + :"0" (src), "1" (dest), "2" (count) : "memory"); return dest; } EXPORT_SYMBOL(strncpy); #endif #ifdef __HAVE_ARCH_STRCAT -char *strcat(char * dest,const char * src) +char *strcat(char *dest, const char *src) { int d0, d1, d2, d3; - asm volatile( "repne\n\t" + asm volatile("repne\n\t" "scasb\n\t" "decl %1\n" "1:\tlodsb\n\t" @@ -67,10 +67,10 @@ EXPORT_SYMBOL(strcat); #endif #ifdef __HAVE_ARCH_STRNCAT -char *strncat(char * dest,const char * src,size_t count) +char *strncat(char *dest, const char *src, size_t count) { int d0, d1, d2, d3; - asm volatile( "repne\n\t" + asm volatile("repne\n\t" "scasb\n\t" "decl %1\n\t" "movl %8,%3\n" @@ -83,7 +83,7 @@ char *strncat(char * dest,const char * src,size_t count) "2:\txorl %2,%2\n\t" "stosb" : "=&S" (d0), "=&D" (d1), "=&a" (d2), "=&c" (d3) - : "0" (src),"1" (dest),"2" (0),"3" (0xffffffffu), "g" (count) + : "0" (src), "1" (dest), "2" (0), "3" (0xffffffffu), "g" (count) : "memory"); return dest; } @@ -91,11 +91,11 @@ EXPORT_SYMBOL(strncat); #endif #ifdef __HAVE_ARCH_STRCMP -int strcmp(const char * cs,const char * ct) +int strcmp(const char *cs, const char *ct) { int d0, d1; int res; - asm volatile( "1:\tlodsb\n\t" + asm volatile("1:\tlodsb\n\t" "scasb\n\t" "jne 2f\n\t" "testb %%al,%%al\n\t" @@ -106,7 +106,7 @@ int strcmp(const char * cs,const char * ct) "orb $1,%%al\n" "3:" :"=a" (res), "=&S" (d0), "=&D" (d1) - :"1" (cs),"2" (ct) + :"1" (cs), "2" (ct) :"memory"); return res; } @@ -114,11 +114,11 @@ EXPORT_SYMBOL(strcmp); #endif #ifdef __HAVE_ARCH_STRNCMP -int strncmp(const char * cs,const char * ct,size_t count) +int strncmp(const char *cs, const char *ct, size_t count) { int res; int d0, d1, d2; - asm volatile( "1:\tdecl %3\n\t" + asm volatile("1:\tdecl %3\n\t" "js 2f\n\t" "lodsb\n\t" "scasb\n\t" @@ -131,7 +131,7 @@ int strncmp(const char * cs,const char * ct,size_t count) "orb $1,%%al\n" "4:" :"=a" (res), "=&S" (d0), "=&D" (d1), "=&c" (d2) - :"1" (cs),"2" (ct),"3" (count) + :"1" (cs), "2" (ct), "3" (count) :"memory"); return res; } @@ -139,11 +139,11 @@ EXPORT_SYMBOL(strncmp); #endif #ifdef __HAVE_ARCH_STRCHR -char *strchr(const char * s, int c) +char *strchr(const char *s, int c) { int d0; - char * res; - asm volatile( "movb %%al,%%ah\n" + char *res; + asm volatile("movb %%al,%%ah\n" "1:\tlodsb\n\t" "cmpb %%ah,%%al\n\t" "je 2f\n\t" @@ -153,7 +153,7 @@ char *strchr(const char * s, int c) "2:\tmovl %1,%0\n\t" "decl %0" :"=a" (res), "=&S" (d0) - :"1" (s),"0" (c) + :"1" (s), "0" (c) :"memory"); return res; } @@ -161,16 +161,16 @@ EXPORT_SYMBOL(strchr); #endif #ifdef __HAVE_ARCH_STRLEN -size_t strlen(const char * s) +size_t strlen(const char *s) { int d0; int res; - asm volatile( "repne\n\t" + asm volatile("repne\n\t" "scasb\n\t" "notl %0\n\t" "decl %0" :"=c" (res), "=&D" (d0) - :"1" (s),"a" (0), "0" (0xffffffffu) + :"1" (s), "a" (0), "0" (0xffffffffu) :"memory"); return res; } @@ -178,19 +178,19 @@ EXPORT_SYMBOL(strlen); #endif #ifdef __HAVE_ARCH_MEMCHR -void *memchr(const void *cs,int c,size_t count) +void *memchr(const void *cs, int c, size_t count) { int d0; void *res; if (!count) return NULL; - asm volatile( "repne\n\t" + asm volatile("repne\n\t" "scasb\n\t" "je 1f\n\t" "movl $1,%0\n" "1:\tdecl %0" :"=D" (res), "=&c" (d0) - :"a" (c),"0" (cs),"1" (count) + :"a" (c), "0" (cs), "1" (count) :"memory"); return res; } @@ -198,7 +198,7 @@ EXPORT_SYMBOL(memchr); #endif #ifdef __HAVE_ARCH_MEMSCAN -void *memscan(void * addr, int c, size_t size) +void *memscan(void *addr, int c, size_t size) { if (!size) return addr; @@ -219,7 +219,7 @@ size_t strnlen(const char *s, size_t count) { int d0; int res; - asm volatile( "movl %2,%0\n\t" + asm volatile("movl %2,%0\n\t" "jmp 2f\n" "1:\tcmpb $0,(%0)\n\t" "je 3f\n\t" @@ -229,7 +229,7 @@ size_t strnlen(const char *s, size_t count) "jne 1b\n" "3:\tsubl %2,%0" :"=a" (res), "=&d" (d0) - :"c" (s),"1" (count) + :"c" (s), "1" (count) :"memory"); return res; } diff --git a/arch/x86/lib/strstr_32.c b/arch/x86/lib/strstr_32.c index a3dafbf59dae..42e8a50303f3 100644 --- a/arch/x86/lib/strstr_32.c +++ b/arch/x86/lib/strstr_32.c @@ -1,9 +1,9 @@ #include <linux/string.h> -char * strstr(const char * cs,const char * ct) +char *strstr(const char *cs, const char *ct) { int d0, d1; -register char * __res; +register char *__res; __asm__ __volatile__( "movl %6,%%edi\n\t" "repne\n\t" diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/lib/thunk_64.S index 8b92d428ab02..e009251d4e9f 100644 --- a/arch/x86/lib/thunk_64.S +++ b/arch/x86/lib/thunk_64.S @@ -41,11 +41,6 @@ thunk rwsem_downgrade_thunk,rwsem_downgrade_wake #endif - thunk __down_failed,__down - thunk_retrax __down_failed_interruptible,__down_interruptible - thunk_retrax __down_failed_trylock,__down_trylock - thunk __up_wakeup,__up - #ifdef CONFIG_TRACE_IRQFLAGS thunk trace_hardirqs_on_thunk,trace_hardirqs_on thunk trace_hardirqs_off_thunk,trace_hardirqs_off diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index e849b9998b0e..24e60944971a 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -1,4 +1,4 @@ -/* +/* * User address space access functions. * The non inlined parts of asm-i386/uaccess.h are here. * @@ -22,14 +22,14 @@ static inline int __movsl_is_ok(unsigned long a1, unsigned long a2, unsigned lon #endif return 1; } -#define movsl_is_ok(a1,a2,n) \ - __movsl_is_ok((unsigned long)(a1),(unsigned long)(a2),(n)) +#define movsl_is_ok(a1, a2, n) \ + __movsl_is_ok((unsigned long)(a1), (unsigned long)(a2), (n)) /* * Copy a null terminated string from userspace. */ -#define __do_strncpy_from_user(dst,src,count,res) \ +#define __do_strncpy_from_user(dst, src, count, res) \ do { \ int __d0, __d1, __d2; \ might_sleep(); \ @@ -61,7 +61,7 @@ do { \ * least @count bytes long. * @src: Source address, in user space. * @count: Maximum number of bytes to copy, including the trailing NUL. - * + * * Copies a NUL-terminated string from userspace to kernel space. * Caller must check the specified block with access_ok() before calling * this function. @@ -90,7 +90,7 @@ EXPORT_SYMBOL(__strncpy_from_user); * least @count bytes long. * @src: Source address, in user space. * @count: Maximum number of bytes to copy, including the trailing NUL. - * + * * Copies a NUL-terminated string from userspace to kernel space. * * On success, returns the length of the string (not including the trailing @@ -120,7 +120,7 @@ EXPORT_SYMBOL(strncpy_from_user); do { \ int __d0; \ might_sleep(); \ - __asm__ __volatile__( \ + __asm__ __volatile__( \ "0: rep; stosl\n" \ " movl %2,%0\n" \ "1: rep; stosb\n" \ @@ -333,17 +333,17 @@ __copy_user_zeroing_intel(void *to, const void __user *from, unsigned long size) __asm__ __volatile__( " .align 2,0x90\n" "0: movl 32(%4), %%eax\n" - " cmpl $67, %0\n" - " jbe 2f\n" + " cmpl $67, %0\n" + " jbe 2f\n" "1: movl 64(%4), %%eax\n" - " .align 2,0x90\n" - "2: movl 0(%4), %%eax\n" - "21: movl 4(%4), %%edx\n" - " movl %%eax, 0(%3)\n" - " movl %%edx, 4(%3)\n" - "3: movl 8(%4), %%eax\n" - "31: movl 12(%4),%%edx\n" - " movl %%eax, 8(%3)\n" + " .align 2,0x90\n" + "2: movl 0(%4), %%eax\n" + "21: movl 4(%4), %%edx\n" + " movl %%eax, 0(%3)\n" + " movl %%edx, 4(%3)\n" + "3: movl 8(%4), %%eax\n" + "31: movl 12(%4),%%edx\n" + " movl %%eax, 8(%3)\n" " movl %%edx, 12(%3)\n" "4: movl 16(%4), %%eax\n" "41: movl 20(%4), %%edx\n" @@ -369,38 +369,38 @@ __copy_user_zeroing_intel(void *to, const void __user *from, unsigned long size) "91: movl 60(%4), %%edx\n" " movl %%eax, 56(%3)\n" " movl %%edx, 60(%3)\n" - " addl $-64, %0\n" - " addl $64, %4\n" - " addl $64, %3\n" - " cmpl $63, %0\n" - " ja 0b\n" - "5: movl %0, %%eax\n" - " shrl $2, %0\n" - " andl $3, %%eax\n" - " cld\n" - "6: rep; movsl\n" + " addl $-64, %0\n" + " addl $64, %4\n" + " addl $64, %3\n" + " cmpl $63, %0\n" + " ja 0b\n" + "5: movl %0, %%eax\n" + " shrl $2, %0\n" + " andl $3, %%eax\n" + " cld\n" + "6: rep; movsl\n" " movl %%eax,%0\n" - "7: rep; movsb\n" - "8:\n" + "7: rep; movsb\n" + "8:\n" ".section .fixup,\"ax\"\n" - "9: lea 0(%%eax,%0,4),%0\n" - "16: pushl %0\n" - " pushl %%eax\n" + "9: lea 0(%%eax,%0,4),%0\n" + "16: pushl %0\n" + " pushl %%eax\n" " xorl %%eax,%%eax\n" - " rep; stosb\n" - " popl %%eax\n" - " popl %0\n" - " jmp 8b\n" - ".previous\n" + " rep; stosb\n" + " popl %%eax\n" + " popl %0\n" + " jmp 8b\n" + ".previous\n" ".section __ex_table,\"a\"\n" - " .align 4\n" - " .long 0b,16b\n" + " .align 4\n" + " .long 0b,16b\n" " .long 1b,16b\n" " .long 2b,16b\n" " .long 21b,16b\n" - " .long 3b,16b\n" + " .long 3b,16b\n" " .long 31b,16b\n" - " .long 4b,16b\n" + " .long 4b,16b\n" " .long 41b,16b\n" " .long 10b,16b\n" " .long 51b,16b\n" @@ -412,9 +412,9 @@ __copy_user_zeroing_intel(void *to, const void __user *from, unsigned long size) " .long 81b,16b\n" " .long 14b,16b\n" " .long 91b,16b\n" - " .long 6b,9b\n" - " .long 7b,16b\n" - ".previous" + " .long 6b,9b\n" + " .long 7b,16b\n" + ".previous" : "=&c"(size), "=&D" (d0), "=&S" (d1) : "1"(to), "2"(from), "0"(size) : "eax", "edx", "memory"); @@ -429,7 +429,7 @@ __copy_user_zeroing_intel(void *to, const void __user *from, unsigned long size) static unsigned long __copy_user_zeroing_intel_nocache(void *to, const void __user *from, unsigned long size) { - int d0, d1; + int d0, d1; __asm__ __volatile__( " .align 2,0x90\n" @@ -526,7 +526,7 @@ static unsigned long __copy_user_zeroing_intel_nocache(void *to, static unsigned long __copy_user_intel_nocache(void *to, const void __user *from, unsigned long size) { - int d0, d1; + int d0, d1; __asm__ __volatile__( " .align 2,0x90\n" @@ -629,7 +629,7 @@ unsigned long __copy_user_zeroing_intel_nocache(void *to, #endif /* CONFIG_X86_INTEL_USERCOPY */ /* Generic arbitrary sized copy. */ -#define __copy_user(to,from,size) \ +#define __copy_user(to, from, size) \ do { \ int __d0, __d1, __d2; \ __asm__ __volatile__( \ @@ -665,7 +665,7 @@ do { \ : "memory"); \ } while (0) -#define __copy_user_zeroing(to,from,size) \ +#define __copy_user_zeroing(to, from, size) \ do { \ int __d0, __d1, __d2; \ __asm__ __volatile__( \ @@ -712,7 +712,7 @@ unsigned long __copy_to_user_ll(void __user *to, const void *from, { #ifndef CONFIG_X86_WP_WORKS_OK if (unlikely(boot_cpu_data.wp_works_ok == 0) && - ((unsigned long )to) < TASK_SIZE) { + ((unsigned long)to) < TASK_SIZE) { /* * When we are in an atomic section (see * mm/filemap.c:file_read_actor), return the full @@ -721,26 +721,26 @@ unsigned long __copy_to_user_ll(void __user *to, const void *from, if (in_atomic()) return n; - /* + /* * CPU does not honor the WP bit when writing * from supervisory mode, and due to preemption or SMP, * the page tables can change at any time. * Do it manually. Manfred <manfred@colorfullife.com> */ while (n) { - unsigned long offset = ((unsigned long)to)%PAGE_SIZE; + unsigned long offset = ((unsigned long)to)%PAGE_SIZE; unsigned long len = PAGE_SIZE - offset; int retval; struct page *pg; void *maddr; - + if (len > n) len = n; survive: down_read(¤t->mm->mmap_sem); retval = get_user_pages(current, current->mm, - (unsigned long )to, 1, 1, 0, &pg, NULL); + (unsigned long)to, 1, 1, 0, &pg, NULL); if (retval == -ENOMEM && is_global_init(current)) { up_read(¤t->mm->mmap_sem); @@ -750,8 +750,8 @@ survive: if (retval != 1) { up_read(¤t->mm->mmap_sem); - break; - } + break; + } maddr = kmap_atomic(pg, KM_USER0); memcpy(maddr + offset, from, len); @@ -802,12 +802,12 @@ unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from, unsigned long n) { #ifdef CONFIG_X86_INTEL_USERCOPY - if ( n > 64 && cpu_has_xmm2) - n = __copy_user_zeroing_intel_nocache(to, from, n); + if (n > 64 && cpu_has_xmm2) + n = __copy_user_zeroing_intel_nocache(to, from, n); else __copy_user_zeroing(to, from, n); #else - __copy_user_zeroing(to, from, n); + __copy_user_zeroing(to, from, n); #endif return n; } @@ -817,12 +817,12 @@ unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *fr unsigned long n) { #ifdef CONFIG_X86_INTEL_USERCOPY - if ( n > 64 && cpu_has_xmm2) - n = __copy_user_intel_nocache(to, from, n); + if (n > 64 && cpu_has_xmm2) + n = __copy_user_intel_nocache(to, from, n); else __copy_user(to, from, n); #else - __copy_user(to, from, n); + __copy_user(to, from, n); #endif return n; } diff --git a/arch/x86/mach-generic/bigsmp.c b/arch/x86/mach-generic/bigsmp.c index 292a225edabe..95fc463056d0 100644 --- a/arch/x86/mach-generic/bigsmp.c +++ b/arch/x86/mach-generic/bigsmp.c @@ -1,4 +1,4 @@ -/* +/* * APIC driver for "bigsmp" XAPIC machines with more than 8 virtual CPUs. * Drives the local APIC in "clustered mode". */ @@ -32,26 +32,26 @@ static int hp_ht_bigsmp(const struct dmi_system_id *d) static const struct dmi_system_id bigsmp_dmi_table[] = { - { hp_ht_bigsmp, "HP ProLiant DL760 G2", { - DMI_MATCH(DMI_BIOS_VENDOR, "HP"), - DMI_MATCH(DMI_BIOS_VERSION, "P44-"), - }}, - - { hp_ht_bigsmp, "HP ProLiant DL740", { - DMI_MATCH(DMI_BIOS_VENDOR, "HP"), - DMI_MATCH(DMI_BIOS_VERSION, "P47-"), - }}, + { hp_ht_bigsmp, "HP ProLiant DL760 G2", + { DMI_MATCH(DMI_BIOS_VENDOR, "HP"), + DMI_MATCH(DMI_BIOS_VERSION, "P44-"),} + }, + + { hp_ht_bigsmp, "HP ProLiant DL740", + { DMI_MATCH(DMI_BIOS_VENDOR, "HP"), + DMI_MATCH(DMI_BIOS_VERSION, "P47-"),} + }, { } }; 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; -} + return dmi_bigsmp; +} -struct genapic apic_bigsmp = APIC_INIT("bigsmp", probe_bigsmp); +struct genapic apic_bigsmp = APIC_INIT("bigsmp", probe_bigsmp); diff --git a/arch/x86/mach-generic/default.c b/arch/x86/mach-generic/default.c index 1af0cc7648f0..9e835a11a13a 100644 --- a/arch/x86/mach-generic/default.c +++ b/arch/x86/mach-generic/default.c @@ -1,4 +1,4 @@ -/* +/* * Default generic APIC driver. This handles up to 8 CPUs. */ #define APIC_DEFINITION 1 @@ -19,8 +19,8 @@ /* should be called last. */ static int probe_default(void) -{ +{ return 1; -} +} -struct genapic apic_default = APIC_INIT("default", probe_default); +struct genapic apic_default = APIC_INIT("default", probe_default); diff --git a/arch/x86/mach-generic/probe.c b/arch/x86/mach-generic/probe.c index f410d3cb5659..c5ae751b994a 100644 --- a/arch/x86/mach-generic/probe.c +++ b/arch/x86/mach-generic/probe.c @@ -1,8 +1,9 @@ -/* Copyright 2003 Andi Kleen, SuSE Labs. - * Subject to the GNU Public License, v.2 - * +/* + * Copyright 2003 Andi Kleen, SuSE Labs. + * Subject to the GNU Public License, v.2 + * * Generic x86 APIC driver probe layer. - */ + */ #include <linux/threads.h> #include <linux/cpumask.h> #include <linux/string.h> @@ -24,7 +25,7 @@ struct genapic *genapic = &apic_default; static struct genapic *apic_probe[] __initdata = { &apic_summit, - &apic_bigsmp, + &apic_bigsmp, &apic_es7000, &apic_default, /* must be last */ NULL, @@ -69,7 +70,7 @@ void __init generic_bigsmp_probe(void) } void __init generic_apic_probe(void) -{ +{ if (!cmdline_apic) { int i; for (i = 0; apic_probe[i]; i++) { @@ -83,40 +84,40 @@ void __init generic_apic_probe(void) panic("Didn't find an APIC driver"); } printk(KERN_INFO "Using APIC driver %s\n", genapic->name); -} +} /* 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 i; - for (i = 0; apic_probe[i]; ++i) { - if (apic_probe[i]->mps_oem_check(mpc,oem,productid)) { + for (i = 0; apic_probe[i]; ++i) { + if (apic_probe[i]->mps_oem_check(mpc, oem, productid)) { if (!cmdline_apic) { genapic = apic_probe[i]; printk(KERN_INFO "Switched to APIC driver `%s'.\n", genapic->name); } return 1; - } - } + } + } return 0; -} +} int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id) { int i; - for (i = 0; apic_probe[i]; ++i) { - if (apic_probe[i]->acpi_madt_oem_check(oem_id, oem_table_id)) { + for (i = 0; apic_probe[i]; ++i) { + if (apic_probe[i]->acpi_madt_oem_check(oem_id, oem_table_id)) { if (!cmdline_apic) { genapic = apic_probe[i]; printk(KERN_INFO "Switched to APIC driver `%s'.\n", genapic->name); } return 1; - } - } - return 0; + } + } + return 0; } int hard_smp_processor_id(void) diff --git a/arch/x86/mach-generic/summit.c b/arch/x86/mach-generic/summit.c index 74883ccb8f73..a97ea0f35b1e 100644 --- a/arch/x86/mach-generic/summit.c +++ b/arch/x86/mach-generic/summit.c @@ -1,4 +1,4 @@ -/* +/* * APIC driver for the IBM "Summit" chipset. */ #define APIC_DEFINITION 1 @@ -19,9 +19,9 @@ #include <asm/mach-summit/mach_mpparse.h> static int probe_summit(void) -{ +{ /* probed later in mptable/ACPI hooks */ return 0; -} +} -struct genapic apic_summit = APIC_INIT("summit", probe_summit); +struct genapic apic_summit = APIC_INIT("summit", probe_summit); diff --git a/arch/x86/mach-rdc321x/Makefile b/arch/x86/mach-rdc321x/Makefile index 1faac8125e3d..8325b4ca431c 100644 --- a/arch/x86/mach-rdc321x/Makefile +++ b/arch/x86/mach-rdc321x/Makefile @@ -1,5 +1,5 @@ # # Makefile for the RDC321x specific parts of the kernel # -obj-$(CONFIG_X86_RDC321X) := gpio.o platform.o wdt.o +obj-$(CONFIG_X86_RDC321X) := gpio.o platform.o diff --git a/arch/x86/mach-rdc321x/wdt.c b/arch/x86/mach-rdc321x/wdt.c deleted file mode 100644 index ec5625ae7061..000000000000 --- a/arch/x86/mach-rdc321x/wdt.c +++ /dev/null @@ -1,275 +0,0 @@ -/* - * RDC321x watchdog driver - * - * Copyright (C) 2007 Florian Fainelli <florian@openwrt.org> - * - * This driver is highly inspired from the cpu5_wdt driver - * - * 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., 675 Mass Ave, Cambridge, MA 02139, USA. - * - */ - -#include <linux/module.h> -#include <linux/moduleparam.h> -#include <linux/types.h> -#include <linux/errno.h> -#include <linux/miscdevice.h> -#include <linux/fs.h> -#include <linux/init.h> -#include <linux/ioport.h> -#include <linux/timer.h> -#include <linux/completion.h> -#include <linux/jiffies.h> -#include <linux/platform_device.h> -#include <linux/watchdog.h> -#include <linux/io.h> -#include <linux/uaccess.h> - -#include <asm/mach-rdc321x/rdc321x_defs.h> - -#define RDC_WDT_MASK 0x80000000 /* Mask */ -#define RDC_WDT_EN 0x00800000 /* Enable bit */ -#define RDC_WDT_WTI 0x00200000 /* Generate CPU reset/NMI/WDT on timeout */ -#define RDC_WDT_RST 0x00100000 /* Reset bit */ -#define RDC_WDT_WIF 0x00040000 /* WDT IRQ Flag */ -#define RDC_WDT_IRT 0x00000100 /* IRQ Routing table */ -#define RDC_WDT_CNT 0x00000001 /* WDT count */ - -#define RDC_CLS_TMR 0x80003844 /* Clear timer */ - -#define RDC_WDT_INTERVAL (HZ/10+1) - -int nowayout = WATCHDOG_NOWAYOUT; -module_param(nowayout, int, 0); -MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); - -static int ticks = 1000; - -/* some device data */ - -static struct { - struct completion stop; - volatile int running; - struct timer_list timer; - volatile int queue; - int default_ticks; - unsigned long inuse; -} rdc321x_wdt_device; - -/* generic helper functions */ - -static void rdc321x_wdt_trigger(unsigned long unused) -{ - if (rdc321x_wdt_device.running) - ticks--; - - /* keep watchdog alive */ - outl(RDC_WDT_EN|inl(RDC3210_CFGREG_DATA), RDC3210_CFGREG_DATA); - - /* requeue?? */ - if (rdc321x_wdt_device.queue && ticks) - mod_timer(&rdc321x_wdt_device.timer, - jiffies + RDC_WDT_INTERVAL); - else { - /* ticks doesn't matter anyway */ - complete(&rdc321x_wdt_device.stop); - } - -} - -static void rdc321x_wdt_reset(void) -{ - ticks = rdc321x_wdt_device.default_ticks; -} - -static void rdc321x_wdt_start(void) -{ - if (!rdc321x_wdt_device.queue) { - rdc321x_wdt_device.queue = 1; - - /* Clear the timer */ - outl(RDC_CLS_TMR, RDC3210_CFGREG_ADDR); - - /* Enable watchdog and set the timeout to 81.92 us */ - outl(RDC_WDT_EN|RDC_WDT_CNT, RDC3210_CFGREG_DATA); - - mod_timer(&rdc321x_wdt_device.timer, - jiffies + RDC_WDT_INTERVAL); - } - - /* if process dies, counter is not decremented */ - rdc321x_wdt_device.running++; -} - -static int rdc321x_wdt_stop(void) -{ - if (rdc321x_wdt_device.running) - rdc321x_wdt_device.running = 0; - - ticks = rdc321x_wdt_device.default_ticks; - - return -EIO; -} - -/* filesystem operations */ - -static int rdc321x_wdt_open(struct inode *inode, struct file *file) -{ - if (test_and_set_bit(0, &rdc321x_wdt_device.inuse)) - return -EBUSY; - - return nonseekable_open(inode, file); -} - -static int rdc321x_wdt_release(struct inode *inode, struct file *file) -{ - clear_bit(0, &rdc321x_wdt_device.inuse); - return 0; -} - -static int rdc321x_wdt_ioctl(struct inode *inode, struct file *file, - unsigned int cmd, unsigned long arg) -{ - void __user *argp = (void __user *)arg; - unsigned int value; - static struct watchdog_info ident = { - .options = WDIOF_CARDRESET, - .identity = "RDC321x WDT", - }; - - switch (cmd) { - case WDIOC_KEEPALIVE: - rdc321x_wdt_reset(); - break; - case WDIOC_GETSTATUS: - /* Read the value from the DATA register */ - value = inl(RDC3210_CFGREG_DATA); - if (copy_to_user(argp, &value, sizeof(int))) - return -EFAULT; - break; - case WDIOC_GETSUPPORT: - if (copy_to_user(argp, &ident, sizeof(ident))) - return -EFAULT; - break; - case WDIOC_SETOPTIONS: - if (copy_from_user(&value, argp, sizeof(int))) - return -EFAULT; - switch (value) { - case WDIOS_ENABLECARD: - rdc321x_wdt_start(); - break; - case WDIOS_DISABLECARD: - return rdc321x_wdt_stop(); - default: - return -EINVAL; - } - break; - default: - return -ENOTTY; - } - return 0; -} - -static ssize_t rdc321x_wdt_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) -{ - if (!count) - return -EIO; - - rdc321x_wdt_reset(); - - return count; -} - -static const struct file_operations rdc321x_wdt_fops = { - .owner = THIS_MODULE, - .llseek = no_llseek, - .ioctl = rdc321x_wdt_ioctl, - .open = rdc321x_wdt_open, - .write = rdc321x_wdt_write, - .release = rdc321x_wdt_release, -}; - -static struct miscdevice rdc321x_wdt_misc = { - .minor = WATCHDOG_MINOR, - .name = "watchdog", - .fops = &rdc321x_wdt_fops, -}; - -static int __devinit rdc321x_wdt_probe(struct platform_device *pdev) -{ - int err; - - err = misc_register(&rdc321x_wdt_misc); - if (err < 0) { - printk(KERN_ERR PFX "watchdog misc_register failed\n"); - return err; - } - - /* Reset the watchdog */ - outl(RDC_WDT_RST, RDC3210_CFGREG_DATA); - - init_completion(&rdc321x_wdt_device.stop); - rdc321x_wdt_device.queue = 0; - - clear_bit(0, &rdc321x_wdt_device.inuse); - - setup_timer(&rdc321x_wdt_device.timer, rdc321x_wdt_trigger, 0); - - rdc321x_wdt_device.default_ticks = ticks; - - printk(KERN_INFO PFX "watchdog init success\n"); - - return 0; -} - -static int rdc321x_wdt_remove(struct platform_device *pdev) -{ - if (rdc321x_wdt_device.queue) { - rdc321x_wdt_device.queue = 0; - wait_for_completion(&rdc321x_wdt_device.stop); - } - - misc_deregister(&rdc321x_wdt_misc); - - return 0; -} - -static struct platform_driver rdc321x_wdt_driver = { - .probe = rdc321x_wdt_probe, - .remove = rdc321x_wdt_remove, - .driver = { - .owner = THIS_MODULE, - .name = "rdc321x-wdt", - }, -}; - -static int __init rdc321x_wdt_init(void) -{ - return platform_driver_register(&rdc321x_wdt_driver); -} - -static void __exit rdc321x_wdt_exit(void) -{ - platform_driver_unregister(&rdc321x_wdt_driver); -} - -module_init(rdc321x_wdt_init); -module_exit(rdc321x_wdt_exit); - -MODULE_AUTHOR("Florian Fainelli <florian@openwrt.org>"); -MODULE_DESCRIPTION("RDC321x watchdog driver"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR); diff --git a/arch/x86/mach-visws/mpparse.c b/arch/x86/mach-visws/mpparse.c index 2a8456a1f44f..57484e91ab90 100644 --- a/arch/x86/mach-visws/mpparse.c +++ b/arch/x86/mach-visws/mpparse.c @@ -11,22 +11,9 @@ /* Have we found an MP table */ int smp_found_config; -/* - * Various Linux-internal data structures created from the - * MP-table. - */ -int apic_version [MAX_APICS]; - int pic_mode; -unsigned long mp_lapic_addr; - -/* Processor that is doing the boot up */ -unsigned int boot_cpu_physical_apicid = -1U; - -/* Bitmask of physically existing CPUs */ -physid_mask_t phys_cpu_present_map; -unsigned int __initdata maxcpus = NR_CPUS; +extern unsigned int __cpuinitdata maxcpus; /* * The Visual Workstation is Intel MP compliant in the hardware diff --git a/arch/x86/mach-visws/visws_apic.c b/arch/x86/mach-visws/visws_apic.c index 710faf71a650..cef9cb1d15ac 100644 --- a/arch/x86/mach-visws/visws_apic.c +++ b/arch/x86/mach-visws/visws_apic.c @@ -1,6 +1,4 @@ /* - * linux/arch/i386/mach-visws/visws_apic.c - * * Copyright (C) 1999 Bent Hagemark, Ingo Molnar * * SGI Visual Workstation interrupt controller diff --git a/arch/x86/mach-voyager/voyager_basic.c b/arch/x86/mach-voyager/voyager_basic.c index 6a949e4edde8..46d6f8067690 100644 --- a/arch/x86/mach-voyager/voyager_basic.c +++ b/arch/x86/mach-voyager/voyager_basic.c @@ -2,8 +2,6 @@ * * Author: J.E.J.Bottomley@HansenPartnership.com * - * linux/arch/i386/kernel/voyager.c - * * This file contains all the voyager specific routines for getting * initialisation of the architecture to function. For additional * features see: diff --git a/arch/x86/mach-voyager/voyager_cat.c b/arch/x86/mach-voyager/voyager_cat.c index 17a7904f75b1..2ad598c104af 100644 --- a/arch/x86/mach-voyager/voyager_cat.c +++ b/arch/x86/mach-voyager/voyager_cat.c @@ -4,8 +4,6 @@ * * Author: J.E.J.Bottomley@HansenPartnership.com * - * linux/arch/i386/kernel/voyager_cat.c - * * This file contains all the logic for manipulating the CAT bus * in a level 5 machine. * @@ -879,7 +877,7 @@ void __init voyager_cat_init(void) request_resource(&iomem_resource, res); } - qic_addr = (unsigned long)ioremap(qic_addr, 0x400); + qic_addr = (unsigned long)ioremap_cache(qic_addr, 0x400); for (j = 0; j < 4; j++) { __u8 cpu; diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c index 3cc8eb2f36a9..8acbf0cdf1a5 100644 --- a/arch/x86/mach-voyager/voyager_smp.c +++ b/arch/x86/mach-voyager/voyager_smp.c @@ -4,8 +4,6 @@ * * Author: J.E.J.Bottomley@HansenPartnership.com * - * linux/arch/i386/kernel/voyager_smp.c - * * This file provides all the same external entries as smp.c but uses * the voyager hal to provide the functionality */ @@ -27,6 +25,7 @@ #include <asm/pgalloc.h> #include <asm/tlbflush.h> #include <asm/arch_hooks.h> +#include <asm/trampoline.h> /* TLB state -- visible externally, indexed physically */ DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = { &init_mm, 0 }; @@ -114,7 +113,7 @@ static inline void send_QIC_CPI(__u32 cpuset, __u8 cpi) for_each_online_cpu(cpu) { if (cpuset & (1 << cpu)) { #ifdef VOYAGER_DEBUG - if (!cpu_isset(cpu, cpu_online_map)) + if (!cpu_online(cpu)) VDEBUG(("CPU%d sending cpi %d to CPU%d not in " "cpu_online_map\n", hard_smp_processor_id(), cpi, cpu)); @@ -207,11 +206,6 @@ static struct irq_chip vic_chip = { /* used to count up as CPUs are brought on line (starts at 0) */ static int cpucount = 0; -/* steal a page from the bottom of memory for the trampoline and - * squirrel its address away here. This will be in kernel virtual - * space */ -static __u32 trampoline_base; - /* The per cpu profile stuff - used in smp_local_timer_interrupt */ static DEFINE_PER_CPU(int, prof_multiplier) = 1; static DEFINE_PER_CPU(int, prof_old_multiplier) = 1; @@ -428,18 +422,6 @@ void __init smp_store_cpu_info(int id) identify_secondary_cpu(c); } -/* set up the trampoline and return the physical address of the code */ -static __u32 __init setup_trampoline(void) -{ - /* these two are global symbols in trampoline.S */ - extern const __u8 trampoline_end[]; - extern const __u8 trampoline_data[]; - - memcpy((__u8 *) trampoline_base, trampoline_data, - trampoline_end - trampoline_data); - return virt_to_phys((__u8 *) trampoline_base); -} - /* Routine initially called when a non-boot CPU is brought online */ static void __init start_secondary(void *unused) { @@ -520,13 +502,6 @@ static void __init do_boot_cpu(__u8 cpu) & ~(voyager_extended_vic_processors & voyager_allowed_boot_processors); - /* This is an area in head.S which was used to set up the - * initial kernel stack. We need to alter this to give the - * booting CPU a new stack (taken from its idle process) */ - extern struct { - __u8 *sp; - unsigned short ss; - } stack_start; /* This is the format of the CPI IDT gate (in real mode) which * we're hijacking to boot the CPU */ union IDTFormat { @@ -568,8 +543,8 @@ static void __init do_boot_cpu(__u8 cpu) hijack_source.idt.Offset, stack_start.sp)); /* init lowmem identity mapping */ - clone_pgd_range(swapper_pg_dir, swapper_pg_dir + USER_PGD_PTRS, - min_t(unsigned long, KERNEL_PGD_PTRS, USER_PGD_PTRS)); + clone_pgd_range(swapper_pg_dir, swapper_pg_dir + KERNEL_PGD_BOUNDARY, + min_t(unsigned long, KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY)); flush_tlb_all(); if (quad_boot) { @@ -708,9 +683,9 @@ void __init smp_boot_cpus(void) * Code added from smpboot.c */ { unsigned long bogosum = 0; - for (i = 0; i < NR_CPUS; i++) - if (cpu_isset(i, cpu_online_map)) - bogosum += cpu_data(i).loops_per_jiffy; + + for_each_online_cpu(i) + bogosum += cpu_data(i).loops_per_jiffy; printk(KERN_INFO "Total of %d processors activated " "(%lu.%02lu BogoMIPS).\n", cpucount + 1, bogosum / (500000 / HZ), @@ -1166,7 +1141,7 @@ void flush_tlb_all(void) * is sorted out */ void __init smp_alloc_memory(void) { - trampoline_base = (__u32) alloc_bootmem_low_pages(PAGE_SIZE); + trampoline_base = alloc_bootmem_low_pages(PAGE_SIZE); if (__pa(trampoline_base) >= 0x93000) BUG(); } @@ -1863,7 +1838,7 @@ static int __cpuinit voyager_cpu_up(unsigned int cpu) return -EIO; /* Unleash the CPU! */ cpu_set(cpu, smp_commenced_mask); - while (!cpu_isset(cpu, cpu_online_map)) + while (!cpu_online(cpu)) mb(); return 0; } diff --git a/arch/x86/mach-voyager/voyager_thread.c b/arch/x86/mach-voyager/voyager_thread.c index c69c931818ed..15464a20fb38 100644 --- a/arch/x86/mach-voyager/voyager_thread.c +++ b/arch/x86/mach-voyager/voyager_thread.c @@ -4,8 +4,6 @@ * * Author: J.E.J.Bottomley@HansenPartnership.com * - * linux/arch/i386/kernel/voyager_thread.c - * * This module provides the machine status monitor thread for the * voyager architecture. This allows us to monitor the machine * environment (temp, voltage, fan function) and the front panel and diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c index 760baeea5f07..6e38d877ea77 100644 --- a/arch/x86/math-emu/fpu_entry.c +++ b/arch/x86/math-emu/fpu_entry.c @@ -276,6 +276,7 @@ asmlinkage void math_emulate(long arg) entry_sel_off.offset = FPU_ORIG_EIP; entry_sel_off.selector = FPU_CS; entry_sel_off.opcode = (byte1 << 8) | FPU_modrm; + entry_sel_off.empty = 0; FPU_rm = FPU_modrm & 7; @@ -677,7 +678,7 @@ int fpregs_soft_set(struct task_struct *target, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - struct i387_soft_struct *s387 = &target->thread.i387.soft; + struct i387_soft_struct *s387 = &target->thread.xstate->soft; void *space = s387->st_space; int ret; int offset, other, i, tags, regnr, tag, newtop; @@ -729,7 +730,7 @@ int fpregs_soft_get(struct task_struct *target, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - struct i387_soft_struct *s387 = &target->thread.i387.soft; + struct i387_soft_struct *s387 = &target->thread.xstate->soft; const void *space = s387->st_space; int ret; int offset = (S387->ftop & 7) * 10, other = 80 - offset; diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h index a3ae28c49ddd..13488fa153e0 100644 --- a/arch/x86/math-emu/fpu_system.h +++ b/arch/x86/math-emu/fpu_system.h @@ -35,8 +35,8 @@ #define SEG_EXPAND_DOWN(s) (((s).b & ((1 << 11) | (1 << 10))) \ == (1 << 10)) -#define I387 (current->thread.i387) -#define FPU_info (I387.soft.info) +#define I387 (current->thread.xstate) +#define FPU_info (I387->soft.info) #define FPU_CS (*(unsigned short *) &(FPU_info->___cs)) #define FPU_SS (*(unsigned short *) &(FPU_info->___ss)) @@ -46,25 +46,25 @@ #define FPU_EIP (FPU_info->___eip) #define FPU_ORIG_EIP (FPU_info->___orig_eip) -#define FPU_lookahead (I387.soft.lookahead) +#define FPU_lookahead (I387->soft.lookahead) /* nz if ip_offset and cs_selector are not to be set for the current instruction. */ -#define no_ip_update (*(u_char *)&(I387.soft.no_update)) -#define FPU_rm (*(u_char *)&(I387.soft.rm)) +#define no_ip_update (*(u_char *)&(I387->soft.no_update)) +#define FPU_rm (*(u_char *)&(I387->soft.rm)) /* Number of bytes of data which can be legally accessed by the current instruction. This only needs to hold a number <= 108, so a byte will do. */ -#define access_limit (*(u_char *)&(I387.soft.alimit)) +#define access_limit (*(u_char *)&(I387->soft.alimit)) -#define partial_status (I387.soft.swd) -#define control_word (I387.soft.cwd) -#define fpu_tag_word (I387.soft.twd) -#define registers (I387.soft.st_space) -#define top (I387.soft.ftop) +#define partial_status (I387->soft.swd) +#define control_word (I387->soft.cwd) +#define fpu_tag_word (I387->soft.twd) +#define registers (I387->soft.st_space) +#define top (I387->soft.ftop) -#define instruction_address (*(struct address *)&I387.soft.fip) -#define operand_address (*(struct address *)&I387.soft.foo) +#define instruction_address (*(struct address *)&I387->soft.fip) +#define operand_address (*(struct address *)&I387->soft.foo) #define FPU_access_ok(x,y,z) if ( !access_ok(x,y,z) ) \ math_abort(FPU_info,SIGSEGV) diff --git a/arch/x86/math-emu/reg_ld_str.c b/arch/x86/math-emu/reg_ld_str.c index 799d4af5be66..d597fe7423c9 100644 --- a/arch/x86/math-emu/reg_ld_str.c +++ b/arch/x86/math-emu/reg_ld_str.c @@ -383,15 +383,15 @@ int FPU_store_double(FPU_REG *st0_ptr, u_char st0_tag, double __user *dfloat) int exp; FPU_REG tmp; + l[0] = 0; + l[1] = 0; if (st0_tag == TAG_Valid) { reg_copy(st0_ptr, &tmp); exp = exponent(&tmp); if (exp < DOUBLE_Emin) { /* It may be a denormal */ addexponent(&tmp, -DOUBLE_Emin + 52); /* largest exp to be 51 */ - - denormal_arg: - +denormal_arg: if ((precision_loss = FPU_round_to_int(&tmp, st0_tag))) { #ifdef PECULIAR_486 /* Did it round to a non-denormal ? */ @@ -477,8 +477,7 @@ int FPU_store_double(FPU_REG *st0_ptr, u_char st0_tag, double __user *dfloat) /* This is a special case: see sec 16.2.5.1 of the 80486 book */ /* Overflow to infinity */ - l[0] = 0x00000000; /* Set to */ - l[1] = 0x7ff00000; /* + INF */ + l[1] = 0x7ff00000; /* Set to + INF */ } else { if (precision_loss) { if (increment) @@ -492,8 +491,6 @@ int FPU_store_double(FPU_REG *st0_ptr, u_char st0_tag, double __user *dfloat) } } else if (st0_tag == TAG_Zero) { /* Number is zero */ - l[0] = 0; - l[1] = 0; } else if (st0_tag == TAG_Special) { st0_tag = FPU_Special(st0_ptr); if (st0_tag == TW_Denormal) { @@ -508,7 +505,6 @@ int FPU_store_double(FPU_REG *st0_ptr, u_char st0_tag, double __user *dfloat) reg_copy(st0_ptr, &tmp); goto denormal_arg; } else if (st0_tag == TW_Infinity) { - l[0] = 0; l[1] = 0x7ff00000; } else if (st0_tag == TW_NaN) { /* Is it really a NaN ? */ @@ -532,7 +528,6 @@ int FPU_store_double(FPU_REG *st0_ptr, u_char st0_tag, double __user *dfloat) EXCEPTION(EX_Invalid); if (!(control_word & CW_Invalid)) return 0; - l[0] = 0; l[1] = 0xfff80000; } } @@ -1185,8 +1180,8 @@ u_char __user *fstenv(fpu_addr_modes addr_modes, u_char __user *d) control_word |= 0xffff0040; partial_status = status_word() | 0xffff0000; fpu_tag_word |= 0xffff0000; - I387.soft.fcs &= ~0xf8000000; - I387.soft.fos |= 0xffff0000; + I387->soft.fcs &= ~0xf8000000; + I387->soft.fos |= 0xffff0000; #endif /* PECULIAR_486 */ if (__copy_to_user(d, &control_word, 7 * 4)) FPU_abort; diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 983291096848..b7b3e4c7cfc9 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -1,5 +1,17 @@ +obj-y := init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ + pat.o pgtable.o + +obj-$(CONFIG_X86_32) += pgtable_32.o + +obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o +obj-$(CONFIG_X86_PTDUMP) += dump_pagetables.o + +obj-$(CONFIG_HIGHMEM) += highmem_32.o + ifeq ($(CONFIG_X86_32),y) -include ${srctree}/arch/x86/mm/Makefile_32 +obj-$(CONFIG_NUMA) += discontig_32.o else -include ${srctree}/arch/x86/mm/Makefile_64 +obj-$(CONFIG_NUMA) += numa_64.o +obj-$(CONFIG_K8_NUMA) += k8topology_64.o +obj-$(CONFIG_ACPI_NUMA) += srat_64.o endif diff --git a/arch/x86/mm/Makefile_32 b/arch/x86/mm/Makefile_32 deleted file mode 100644 index c36ae88bb543..000000000000 --- a/arch/x86/mm/Makefile_32 +++ /dev/null @@ -1,9 +0,0 @@ -# -# Makefile for the linux i386-specific parts of the memory manager. -# - -obj-y := init_32.o pgtable_32.o fault.o ioremap.o extable.o pageattr.o mmap.o - -obj-$(CONFIG_NUMA) += discontig_32.o -obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o -obj-$(CONFIG_HIGHMEM) += highmem_32.o diff --git a/arch/x86/mm/Makefile_64 b/arch/x86/mm/Makefile_64 deleted file mode 100644 index 688c8c28ac8f..000000000000 --- a/arch/x86/mm/Makefile_64 +++ /dev/null @@ -1,9 +0,0 @@ -# -# Makefile for the linux x86_64-specific parts of the memory manager. -# - -obj-y := init_64.o fault.o ioremap.o extable.o pageattr.o mmap.o -obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o -obj-$(CONFIG_NUMA) += numa_64.o -obj-$(CONFIG_K8_NUMA) += k8topology_64.o -obj-$(CONFIG_ACPI_NUMA) += srat_64.o diff --git a/arch/x86/mm/discontig_32.c b/arch/x86/mm/discontig_32.c index 8e25e06ff730..18378850e25a 100644 --- a/arch/x86/mm/discontig_32.c +++ b/arch/x86/mm/discontig_32.c @@ -37,7 +37,7 @@ #include <asm/e820.h> #include <asm/setup.h> #include <asm/mmzone.h> -#include <bios_ebda.h> +#include <asm/bios_ebda.h> struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); @@ -120,7 +120,7 @@ int __init get_memcfg_numa_flat(void) printk("NUMA - single node, flat memory mode\n"); /* Run the memory configuration and find the top of memory. */ - find_max_pfn(); + propagate_e820_map(); node_start_pfn[0] = 0; node_end_pfn[0] = max_pfn; memory_present(0, 0, max_pfn); @@ -134,7 +134,7 @@ int __init get_memcfg_numa_flat(void) /* * Find the highest page frame number we have available for the node */ -static void __init find_max_pfn_node(int nid) +static void __init propagate_e820_map_node(int nid) { if (node_end_pfn[nid] > max_pfn) node_end_pfn[nid] = max_pfn; @@ -379,7 +379,7 @@ unsigned long __init setup_memory(void) printk("High memory starts at vaddr %08lx\n", (ulong) pfn_to_kaddr(highstart_pfn)); for_each_online_node(nid) - find_max_pfn_node(nid); + propagate_e820_map_node(nid); memset(NODE_DATA(0), 0, sizeof(struct pglist_data)); NODE_DATA(0)->bdata = &node0_bdata; diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c new file mode 100644 index 000000000000..2c24bea92c66 --- /dev/null +++ b/arch/x86/mm/dump_pagetables.c @@ -0,0 +1,354 @@ +/* + * Debug helper to dump the current kernel pagetables of the system + * so that we can see what the various memory ranges are set to. + * + * (C) Copyright 2008 Intel Corporation + * + * Author: Arjan van de Ven <arjan@linux.intel.com> + * + * 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; version 2 + * of the License. + */ + +#include <linux/debugfs.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/seq_file.h> + +#include <asm/pgtable.h> + +/* + * The dumper groups pagetable entries of the same type into one, and for + * that it needs to keep some state when walking, and flush this state + * when a "break" in the continuity is found. + */ +struct pg_state { + int level; + pgprot_t current_prot; + unsigned long start_address; + unsigned long current_address; + const struct addr_marker *marker; +}; + +struct addr_marker { + unsigned long start_address; + const char *name; +}; + +/* Address space markers hints */ +static struct addr_marker address_markers[] = { + { 0, "User Space" }, +#ifdef CONFIG_X86_64 + { 0x8000000000000000UL, "Kernel Space" }, + { 0xffff810000000000UL, "Low Kernel Mapping" }, + { VMALLOC_START, "vmalloc() Area" }, + { VMEMMAP_START, "Vmemmap" }, + { __START_KERNEL_map, "High Kernel Mapping" }, + { MODULES_VADDR, "Modules" }, + { MODULES_END, "End Modules" }, +#else + { PAGE_OFFSET, "Kernel Mapping" }, + { 0/* VMALLOC_START */, "vmalloc() Area" }, + { 0/*VMALLOC_END*/, "vmalloc() End" }, +# ifdef CONFIG_HIGHMEM + { 0/*PKMAP_BASE*/, "Persisent kmap() Area" }, +# endif + { 0/*FIXADDR_START*/, "Fixmap Area" }, +#endif + { -1, NULL } /* End of list */ +}; + +/* Multipliers for offsets within the PTEs */ +#define PTE_LEVEL_MULT (PAGE_SIZE) +#define PMD_LEVEL_MULT (PTRS_PER_PTE * PTE_LEVEL_MULT) +#define PUD_LEVEL_MULT (PTRS_PER_PMD * PMD_LEVEL_MULT) +#define PGD_LEVEL_MULT (PTRS_PER_PUD * PUD_LEVEL_MULT) + +/* + * Print a readable form of a pgprot_t to the seq_file + */ +static void printk_prot(struct seq_file *m, pgprot_t prot, int level) +{ + pgprotval_t pr = pgprot_val(prot); + static const char * const level_name[] = + { "cr3", "pgd", "pud", "pmd", "pte" }; + + if (!pgprot_val(prot)) { + /* Not present */ + seq_printf(m, " "); + } else { + if (pr & _PAGE_USER) + seq_printf(m, "USR "); + else + seq_printf(m, " "); + if (pr & _PAGE_RW) + seq_printf(m, "RW "); + else + seq_printf(m, "ro "); + if (pr & _PAGE_PWT) + seq_printf(m, "PWT "); + else + seq_printf(m, " "); + if (pr & _PAGE_PCD) + seq_printf(m, "PCD "); + else + seq_printf(m, " "); + + /* Bit 9 has a different meaning on level 3 vs 4 */ + if (level <= 3) { + if (pr & _PAGE_PSE) + seq_printf(m, "PSE "); + else + seq_printf(m, " "); + } else { + if (pr & _PAGE_PAT) + seq_printf(m, "pat "); + else + seq_printf(m, " "); + } + if (pr & _PAGE_GLOBAL) + seq_printf(m, "GLB "); + else + seq_printf(m, " "); + if (pr & _PAGE_NX) + seq_printf(m, "NX "); + else + seq_printf(m, "x "); + } + seq_printf(m, "%s\n", level_name[level]); +} + +/* + * On 64 bits, sign-extend the 48 bit address to 64 bit + */ +static unsigned long normalize_addr(unsigned long u) +{ +#ifdef CONFIG_X86_64 + return (signed long)(u << 16) >> 16; +#else + return u; +#endif +} + +/* + * This function gets called on a break in a continuous series + * of PTE entries; the next one is different so we need to + * print what we collected so far. + */ +static void note_page(struct seq_file *m, struct pg_state *st, + pgprot_t new_prot, int level) +{ + pgprotval_t prot, cur; + static const char units[] = "KMGTPE"; + + /* + * If we have a "break" in the series, we need to flush the state that + * we have now. "break" is either changing perms, levels or + * address space marker. + */ + prot = pgprot_val(new_prot) & ~(PTE_MASK); + cur = pgprot_val(st->current_prot) & ~(PTE_MASK); + + if (!st->level) { + /* First entry */ + st->current_prot = new_prot; + st->level = level; + st->marker = address_markers; + seq_printf(m, "---[ %s ]---\n", st->marker->name); + } else if (prot != cur || level != st->level || + st->current_address >= st->marker[1].start_address) { + const char *unit = units; + unsigned long delta; + + /* + * Now print the actual finished series + */ + seq_printf(m, "0x%p-0x%p ", + (void *)st->start_address, + (void *)st->current_address); + + delta = (st->current_address - st->start_address) >> 10; + while (!(delta & 1023) && unit[1]) { + delta >>= 10; + unit++; + } + seq_printf(m, "%9lu%c ", delta, *unit); + printk_prot(m, st->current_prot, st->level); + + /* + * We print markers for special areas of address space, + * such as the start of vmalloc space etc. + * This helps in the interpretation. + */ + if (st->current_address >= st->marker[1].start_address) { + st->marker++; + seq_printf(m, "---[ %s ]---\n", st->marker->name); + } + + st->start_address = st->current_address; + st->current_prot = new_prot; + st->level = level; + } +} + +static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr, + unsigned long P) +{ + int i; + pte_t *start; + + start = (pte_t *) pmd_page_vaddr(addr); + for (i = 0; i < PTRS_PER_PTE; i++) { + pgprot_t prot = pte_pgprot(*start); + + st->current_address = normalize_addr(P + i * PTE_LEVEL_MULT); + note_page(m, st, prot, 4); + start++; + } +} + +#if PTRS_PER_PMD > 1 + +static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr, + unsigned long P) +{ + int i; + pmd_t *start; + + start = (pmd_t *) pud_page_vaddr(addr); + for (i = 0; i < PTRS_PER_PMD; i++) { + st->current_address = normalize_addr(P + i * PMD_LEVEL_MULT); + if (!pmd_none(*start)) { + pgprotval_t prot = pmd_val(*start) & ~PTE_MASK; + + if (pmd_large(*start) || !pmd_present(*start)) + note_page(m, st, __pgprot(prot), 3); + else + walk_pte_level(m, st, *start, + P + i * PMD_LEVEL_MULT); + } else + note_page(m, st, __pgprot(0), 3); + start++; + } +} + +#else +#define walk_pmd_level(m,s,a,p) walk_pte_level(m,s,__pmd(pud_val(a)),p) +#define pud_large(a) pmd_large(__pmd(pud_val(a))) +#define pud_none(a) pmd_none(__pmd(pud_val(a))) +#endif + +#if PTRS_PER_PUD > 1 + +static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr, + unsigned long P) +{ + int i; + pud_t *start; + + start = (pud_t *) pgd_page_vaddr(addr); + + for (i = 0; i < PTRS_PER_PUD; i++) { + st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT); + if (!pud_none(*start)) { + pgprotval_t prot = pud_val(*start) & ~PTE_MASK; + + if (pud_large(*start) || !pud_present(*start)) + note_page(m, st, __pgprot(prot), 2); + else + walk_pmd_level(m, st, *start, + P + i * PUD_LEVEL_MULT); + } else + note_page(m, st, __pgprot(0), 2); + + start++; + } +} + +#else +#define walk_pud_level(m,s,a,p) walk_pmd_level(m,s,__pud(pgd_val(a)),p) +#define pgd_large(a) pud_large(__pud(pgd_val(a))) +#define pgd_none(a) pud_none(__pud(pgd_val(a))) +#endif + +static void walk_pgd_level(struct seq_file *m) +{ +#ifdef CONFIG_X86_64 + pgd_t *start = (pgd_t *) &init_level4_pgt; +#else + pgd_t *start = swapper_pg_dir; +#endif + int i; + struct pg_state st; + + memset(&st, 0, sizeof(st)); + + for (i = 0; i < PTRS_PER_PGD; i++) { + st.current_address = normalize_addr(i * PGD_LEVEL_MULT); + if (!pgd_none(*start)) { + pgprotval_t prot = pgd_val(*start) & ~PTE_MASK; + + if (pgd_large(*start) || !pgd_present(*start)) + note_page(m, &st, __pgprot(prot), 1); + else + walk_pud_level(m, &st, *start, + i * PGD_LEVEL_MULT); + } else + note_page(m, &st, __pgprot(0), 1); + + start++; + } + + /* Flush out the last page */ + st.current_address = normalize_addr(PTRS_PER_PGD*PGD_LEVEL_MULT); + note_page(m, &st, __pgprot(0), 0); +} + +static int ptdump_show(struct seq_file *m, void *v) +{ + walk_pgd_level(m); + return 0; +} + +static int ptdump_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, ptdump_show, NULL); +} + +static const struct file_operations ptdump_fops = { + .open = ptdump_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int pt_dump_init(void) +{ + struct dentry *pe; + +#ifdef CONFIG_X86_32 + /* Not a compile-time constant on x86-32 */ + address_markers[2].start_address = VMALLOC_START; + address_markers[3].start_address = VMALLOC_END; +# ifdef CONFIG_HIGHMEM + address_markers[4].start_address = PKMAP_BASE; + address_markers[5].start_address = FIXADDR_START; +# else + address_markers[4].start_address = FIXADDR_START; +# endif +#endif + + pe = debugfs_create_file("kernel_page_tables", 0600, NULL, NULL, + &ptdump_fops); + if (!pe) + return -ENOMEM; + + return 0; +} + +__initcall(pt_dump_init); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>"); +MODULE_DESCRIPTION("Kernel debugging helper that dumps pagetables"); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index ec08d8389850..fd7e1798c75a 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -639,7 +639,7 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) #ifdef CONFIG_X86_32 /* It's safe to allow irq's after cr2 has been saved and the vmalloc fault has been handled. */ - if (regs->flags & (X86_EFLAGS_IF|VM_MASK)) + if (regs->flags & (X86_EFLAGS_IF | X86_VM_MASK)) local_irq_enable(); /* @@ -976,9 +976,5 @@ void vmalloc_sync_all(void) if (address == start) start = address + PGDIR_SIZE; } - /* Check that there is no need to do the same for the modules area. */ - BUILD_BUG_ON(!(MODULES_VADDR > __START_KERNEL)); - BUILD_BUG_ON(!(((MODULES_END - 1) & PGDIR_MASK) == - (__START_KERNEL & PGDIR_MASK))); #endif } diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index 9cf33d3ee5bc..165c871ba9af 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -155,4 +155,3 @@ EXPORT_SYMBOL(kmap); EXPORT_SYMBOL(kunmap); EXPORT_SYMBOL(kmap_atomic); EXPORT_SYMBOL(kunmap_atomic); -EXPORT_SYMBOL(kmap_atomic_to_page); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index ee1091a46964..de236e419cb5 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -1,5 +1,4 @@ /* - * linux/arch/i386/mm/init.c * * Copyright (C) 1995 Linus Torvalds * @@ -51,6 +50,8 @@ unsigned int __VMALLOC_RESERVE = 128 << 20; +unsigned long max_pfn_mapped; + DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); unsigned long highstart_pfn, highend_pfn; @@ -70,7 +71,7 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd) if (!(pgd_val(*pgd) & _PAGE_PRESENT)) { pmd_table = (pmd_t *) alloc_bootmem_low_pages(PAGE_SIZE); - paravirt_alloc_pd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT); + paravirt_alloc_pmd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT); set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT)); pud = pud_offset(pgd, 0); BUG_ON(pmd_table != pmd_offset(pud, 0)); @@ -99,7 +100,7 @@ static pte_t * __init one_page_table_init(pmd_t *pmd) (pte_t *)alloc_bootmem_low_pages(PAGE_SIZE); } - paravirt_alloc_pt(&init_mm, __pa(page_table) >> PAGE_SHIFT); + paravirt_alloc_pte(&init_mm, __pa(page_table) >> PAGE_SHIFT); set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE)); BUG_ON(page_table != pte_offset_kernel(pmd, 0)); } @@ -179,8 +180,13 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base) /* * 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) { + if (cpu_has_pse && !(pgd_idx == 0 && pmd_idx == 0)) { unsigned int addr2; pgprot_t prot = PAGE_KERNEL_LARGE; @@ -194,6 +200,7 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base) set_pmd(pmd, pfn_pmd(pfn, prot)); pfn += PTRS_PER_PTE; + max_pfn_mapped = pfn; continue; } pte = one_page_table_init(pmd); @@ -208,6 +215,7 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base) set_pte(pte, pfn_pte(pfn, prot)); } + max_pfn_mapped = pfn; } } } @@ -219,6 +227,25 @@ static inline int page_kills_ppro(unsigned long pagenr) return 0; } +/* + * devmem_is_allowed() checks to see if /dev/mem access to a certain address + * is valid. The argument is a physical page number. + * + * + * On x86, access has to be given to the first megabyte of ram because that area + * contains bios code and data regions used by X and dosemu and similar apps. + * Access has to be given to non-kernel-ram areas as well, these contain the PCI + * mmio resources as well as potential bios/acpi data regions. + */ +int devmem_is_allowed(unsigned long pagenr) +{ + if (pagenr <= 256) + return 1; + if (!page_is_ram(pagenr)) + return 1; + return 0; +} + #ifdef CONFIG_HIGHMEM pte_t *kmap_pte; pgprot_t kmap_prot; @@ -260,47 +287,17 @@ static void __init permanent_kmaps_init(pgd_t *pgd_base) pkmap_page_table = pte; } -static void __meminit free_new_highpage(struct page *page) -{ - init_page_count(page); - __free_page(page); - totalhigh_pages++; -} - void __init add_one_highpage_init(struct page *page, int pfn, int bad_ppro) { if (page_is_ram(pfn) && !(bad_ppro && page_kills_ppro(pfn))) { ClearPageReserved(page); - free_new_highpage(page); + init_page_count(page); + __free_page(page); + totalhigh_pages++; } else SetPageReserved(page); } -static int __meminit -add_one_highpage_hotplug(struct page *page, unsigned long pfn) -{ - free_new_highpage(page); - totalram_pages++; -#ifdef CONFIG_FLATMEM - max_mapnr = max(pfn, max_mapnr); -#endif - num_physpages++; - - return 0; -} - -/* - * Not currently handling the NUMA case. - * Assuming single node and all memory that - * has been added dynamically that would be - * onlined here is in HIGHMEM. - */ -void __meminit online_page(struct page *page) -{ - ClearPageReserved(page); - add_one_highpage_hotplug(page, page_to_pfn(page)); -} - #ifndef CONFIG_NUMA static void __init set_highmem_pages_init(int bad_ppro) { @@ -357,7 +354,7 @@ void __init native_pagetable_setup_start(pgd_t *base) pte_clear(NULL, va, pte); } - paravirt_alloc_pd(&init_mm, __pa(base) >> PAGE_SHIFT); + paravirt_alloc_pmd(&init_mm, __pa(base) >> PAGE_SHIFT); } void __init native_pagetable_setup_done(pgd_t *base) @@ -449,7 +446,7 @@ void zap_low_mappings(void) * Note that "pgd_clear()" doesn't do it for * us, because pgd_clear() is a no-op on i386. */ - for (i = 0; i < USER_PTRS_PER_PGD; i++) { + for (i = 0; i < KERNEL_PGD_BOUNDARY; i++) { #ifdef CONFIG_X86_PAE set_pgd(swapper_pg_dir+i, __pgd(1 + __pa(empty_zero_page))); #else @@ -539,9 +536,9 @@ void __init paging_init(void) /* * Test if the WP bit works in supervisor mode. It isn't supported on 386's - * and also on some strange 486's (NexGen etc.). All 586+'s are OK. This - * used to involve black magic jumps to work around some nasty CPU bugs, - * but fortunately the switch to using exceptions got rid of all that. + * and also on some strange 486's. All 586+'s are OK. This used to involve + * black magic jumps to work around some nasty CPU bugs, but fortunately the + * switch to using exceptions got rid of all that. */ static void __init test_wp_bit(void) { @@ -723,25 +720,17 @@ void mark_rodata_ro(void) unsigned long start = PFN_ALIGN(_text); unsigned long size = PFN_ALIGN(_etext) - start; -#ifndef CONFIG_KPROBES -#ifdef CONFIG_HOTPLUG_CPU - /* It must still be possible to apply SMP alternatives. */ - if (num_possible_cpus() <= 1) -#endif - { - set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); - printk(KERN_INFO "Write protecting the kernel text: %luk\n", - size >> 10); + set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); + printk(KERN_INFO "Write protecting the kernel text: %luk\n", + size >> 10); #ifdef CONFIG_CPA_DEBUG - printk(KERN_INFO "Testing CPA: Reverting %lx-%lx\n", - start, start+size); - set_pages_rw(virt_to_page(start), size>>PAGE_SHIFT); + printk(KERN_INFO "Testing CPA: Reverting %lx-%lx\n", + start, start+size); + set_pages_rw(virt_to_page(start), size>>PAGE_SHIFT); - printk(KERN_INFO "Testing CPA: write protecting again\n"); - set_pages_ro(virt_to_page(start), size>>PAGE_SHIFT); -#endif - } + printk(KERN_INFO "Testing CPA: write protecting again\n"); + set_pages_ro(virt_to_page(start), size>>PAGE_SHIFT); #endif start += size; size = (unsigned long)__end_rodata - start; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index a02a14f0f324..32ba13b0f818 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -47,13 +47,30 @@ #include <asm/numa.h> #include <asm/cacheflush.h> -const struct dma_mapping_ops *dma_ops; -EXPORT_SYMBOL(dma_ops); - static unsigned long dma_reserve __initdata; DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); +int direct_gbpages __meminitdata +#ifdef CONFIG_DIRECT_GBPAGES + = 1 +#endif +; + +static int __init parse_direct_gbpages_off(char *arg) +{ + direct_gbpages = 0; + return 0; +} +early_param("nogbpages", parse_direct_gbpages_off); + +static int __init parse_direct_gbpages_on(char *arg) +{ + direct_gbpages = 1; + return 0; +} +early_param("gbpages", parse_direct_gbpages_on); + /* * NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the * physical space so we can cache the place of the first one and move @@ -69,9 +86,6 @@ void show_mem(void) printk(KERN_INFO "Mem-info:\n"); show_free_areas(); - printk(KERN_INFO "Free swap: %6ldkB\n", - nr_swap_pages << (PAGE_SHIFT-10)); - for_each_online_pgdat(pgdat) { for (i = 0; i < pgdat->node_spanned_pages; ++i) { /* @@ -121,7 +135,7 @@ static __init void *spp_getpage(void) return ptr; } -static __init void +static void set_pte_phys(unsigned long vaddr, unsigned long phys, pgprot_t prot) { pgd_t *pgd; @@ -159,7 +173,7 @@ set_pte_phys(unsigned long vaddr, unsigned long phys, pgprot_t prot) new_pte = pfn_pte(phys >> PAGE_SHIFT, prot); pte = pte_offset_kernel(pmd, vaddr); - if (!pte_none(*pte) && + if (!pte_none(*pte) && pte_val(new_pte) && pte_val(*pte) != (pte_val(new_pte) & __supported_pte_mask)) pte_ERROR(*pte); set_pte(pte, new_pte); @@ -200,8 +214,7 @@ void __init cleanup_highmap(void) } /* NOTE: this is meant to be run only at boot */ -void __init -__set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t prot) +void __set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t prot) { unsigned long address = __fix_to_virt(idx); @@ -296,7 +309,7 @@ __meminit void early_iounmap(void *addr, unsigned long size) __flush_tlb_all(); } -static void __meminit +static unsigned long __meminit phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end) { int i = pmd_index(address); @@ -318,21 +331,26 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end) set_pte((pte_t *)pmd, pfn_pte(address >> PAGE_SHIFT, PAGE_KERNEL_LARGE)); } + return address; } -static void __meminit +static unsigned long __meminit phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end) { pmd_t *pmd = pmd_offset(pud, 0); + unsigned long last_map_addr; + spin_lock(&init_mm.page_table_lock); - phys_pmd_init(pmd, address, end); + last_map_addr = phys_pmd_init(pmd, address, end); spin_unlock(&init_mm.page_table_lock); __flush_tlb_all(); + return last_map_addr; } -static void __meminit +static unsigned long __meminit phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end) { + unsigned long last_map_addr = end; int i = pud_index(addr); for (; i < PTRS_PER_PUD; i++, addr = (addr & PUD_MASK) + PUD_SIZE) { @@ -350,7 +368,15 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end) } if (pud_val(*pud)) { - phys_pmd_update(pud, addr, end); + if (!pud_large(*pud)) + last_map_addr = phys_pmd_update(pud, addr, end); + continue; + } + + if (direct_gbpages) { + set_pte((pte_t *)pud, + pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL_LARGE)); + last_map_addr = (addr & PUD_MASK) + PUD_SIZE; continue; } @@ -358,12 +384,14 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end) spin_lock(&init_mm.page_table_lock); set_pud(pud, __pud(pmd_phys | _KERNPG_TABLE)); - phys_pmd_init(pmd, addr, end); + last_map_addr = phys_pmd_init(pmd, addr, end); spin_unlock(&init_mm.page_table_lock); unmap_low_page(pmd); } __flush_tlb_all(); + + return last_map_addr >> PAGE_SHIFT; } static void __init find_early_table_space(unsigned long end) @@ -371,9 +399,11 @@ static void __init find_early_table_space(unsigned long end) unsigned long puds, pmds, tables, start; puds = (end + PUD_SIZE - 1) >> PUD_SHIFT; - pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT; - tables = round_up(puds * sizeof(pud_t), PAGE_SIZE) + - round_up(pmds * sizeof(pmd_t), PAGE_SIZE); + tables = round_up(puds * sizeof(pud_t), PAGE_SIZE); + if (!direct_gbpages) { + pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT; + tables += round_up(pmds * sizeof(pmd_t), PAGE_SIZE); + } /* * RED-PEN putting page tables only on node 0 could @@ -393,16 +423,135 @@ static void __init find_early_table_space(unsigned long end) (table_start << PAGE_SHIFT) + tables); } +static void __init init_gbpages(void) +{ + if (direct_gbpages && cpu_has_gbpages) + printk(KERN_INFO "Using GB pages for direct mapping\n"); + else + direct_gbpages = 0; +} + +#ifdef CONFIG_MEMTEST_BOOTPARAM + +static void __init memtest(unsigned long start_phys, unsigned long size, + unsigned pattern) +{ + unsigned long i; + unsigned long *start; + unsigned long start_bad; + unsigned long last_bad; + unsigned long val; + unsigned long start_phys_aligned; + unsigned long count; + unsigned long incr; + + switch (pattern) { + case 0: + val = 0UL; + break; + case 1: + val = -1UL; + break; + case 2: + val = 0x5555555555555555UL; + break; + case 3: + val = 0xaaaaaaaaaaaaaaaaUL; + break; + default: + return; + } + + incr = sizeof(unsigned long); + start_phys_aligned = ALIGN(start_phys, incr); + count = (size - (start_phys_aligned - start_phys))/incr; + start = __va(start_phys_aligned); + start_bad = 0; + last_bad = 0; + + for (i = 0; i < count; i++) + start[i] = val; + for (i = 0; i < count; i++, start++, start_phys_aligned += incr) { + if (*start != val) { + if (start_phys_aligned == last_bad + incr) { + last_bad += incr; + } else { + if (start_bad) { + printk(KERN_CONT "\n %016lx bad mem addr %016lx - %016lx reserved", + val, start_bad, last_bad + incr); + reserve_early(start_bad, last_bad - start_bad, "BAD RAM"); + } + start_bad = last_bad = start_phys_aligned; + } + } + } + if (start_bad) { + printk(KERN_CONT "\n %016lx bad mem addr %016lx - %016lx reserved", + val, start_bad, last_bad + incr); + reserve_early(start_bad, last_bad - start_bad, "BAD RAM"); + } + +} + +static int memtest_pattern __initdata = CONFIG_MEMTEST_BOOTPARAM_VALUE; + +static int __init parse_memtest(char *arg) +{ + if (arg) + memtest_pattern = simple_strtoul(arg, NULL, 0); + return 0; +} + +early_param("memtest", parse_memtest); + +static void __init early_memtest(unsigned long start, unsigned long end) +{ + unsigned long t_start, t_size; + unsigned pattern; + + if (!memtest_pattern) + return; + + printk(KERN_INFO "early_memtest: pattern num %d", memtest_pattern); + for (pattern = 0; pattern < memtest_pattern; pattern++) { + t_start = start; + t_size = 0; + while (t_start < end) { + t_start = find_e820_area_size(t_start, &t_size, 1); + + /* done ? */ + if (t_start >= end) + break; + 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); + + memtest(t_start, t_size, pattern); + + t_start += t_size; + } + } + printk(KERN_CONT "\n"); +} +#else +static void __init early_memtest(unsigned long start, unsigned long end) +{ +} +#endif + /* * 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. */ -void __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; + unsigned long next, last_map_addr = end; + unsigned long start_phys = start, end_phys = end; - pr_debug("init_memory_mapping\n"); + printk(KERN_INFO "init_memory_mapping\n"); /* * Find space for the kernel direct mapping tables. @@ -411,8 +560,10 @@ void __init_refok init_memory_mapping(unsigned long start, unsigned long end) * 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); + } start = (unsigned long)__va(start); end = (unsigned long)__va(end); @@ -430,7 +581,7 @@ void __init_refok init_memory_mapping(unsigned long start, unsigned long end) next = start + PGDIR_SIZE; if (next > end) next = end; - phys_pud_init(pud, __pa(start), __pa(next)); + 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); @@ -443,6 +594,11 @@ void __init_refok init_memory_mapping(unsigned long start, unsigned long end) if (!after_bootmem) reserve_early(table_start << PAGE_SHIFT, table_end << PAGE_SHIFT, "PGTABLE"); + + if (!after_bootmem) + early_memtest(start_phys, end_phys); + + return last_map_addr; } #ifndef CONFIG_NUMA @@ -464,15 +620,6 @@ void __init paging_init(void) /* * Memory hotplug specific functions */ -void online_page(struct page *page) -{ - ClearPageReserved(page); - init_page_count(page); - __free_page(page); - totalram_pages++; - num_physpages++; -} - #ifdef CONFIG_MEMORY_HOTPLUG /* * Memory is added always to NORMAL zone. This means you will never get @@ -482,11 +629,13 @@ int arch_add_memory(int nid, u64 start, u64 size) { struct pglist_data *pgdat = NODE_DATA(nid); struct zone *zone = pgdat->node_zones + ZONE_NORMAL; - unsigned long start_pfn = start >> PAGE_SHIFT; + unsigned long last_mapped_pfn, start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; int ret; - init_memory_mapping(start, start + size-1); + last_mapped_pfn = init_memory_mapping(start, start + size-1); + if (last_mapped_pfn > max_pfn_mapped) + max_pfn_mapped = last_mapped_pfn; ret = __add_pages(zone, start_pfn, nr_pages); WARN_ON(1); @@ -505,6 +654,26 @@ EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif /* CONFIG_MEMORY_HOTPLUG */ +/* + * devmem_is_allowed() checks to see if /dev/mem access to a certain address + * is valid. The argument is a physical page number. + * + * + * On x86, access has to be given to the first megabyte of ram because that area + * contains bios code and data regions used by X and dosemu and similar apps. + * Access has to be given to non-kernel-ram areas as well, these contain the PCI + * mmio resources as well as potential bios/acpi data regions. + */ +int devmem_is_allowed(unsigned long pagenr) +{ + if (pagenr <= 256) + return 1; + if (!page_is_ram(pagenr)) + return 1; + return 0; +} + + static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel, kcore_modules, kcore_vsyscall; @@ -596,24 +765,7 @@ EXPORT_SYMBOL_GPL(rodata_test_data); void mark_rodata_ro(void) { - unsigned long start = (unsigned long)_stext, end; - -#ifdef CONFIG_HOTPLUG_CPU - /* It must still be possible to apply SMP alternatives. */ - if (num_possible_cpus() > 1) - start = (unsigned long)_etext; -#endif - -#ifdef CONFIG_KPROBES - start = (unsigned long)__start_rodata; -#endif - - end = (unsigned long)__end_rodata; - start = (start + PAGE_SIZE - 1) & PAGE_MASK; - end &= PAGE_MASK; - if (end <= start) - return; - + unsigned long start = PFN_ALIGN(_stext), end = PFN_ALIGN(__end_rodata); printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n", (end - start) >> 10); @@ -636,6 +788,7 @@ void mark_rodata_ro(void) set_memory_ro(start, (end-start) >> PAGE_SHIFT); #endif } + #endif #ifdef CONFIG_BLK_DEV_INITRD @@ -648,7 +801,7 @@ void free_initrd_mem(unsigned long start, unsigned long end) void __init reserve_bootmem_generic(unsigned long phys, unsigned len) { #ifdef CONFIG_NUMA - int nid = phys_to_nid(phys); + int nid, next_nid; #endif unsigned long pfn = phys >> PAGE_SHIFT; @@ -657,7 +810,7 @@ void __init reserve_bootmem_generic(unsigned long phys, unsigned len) * This can happen with kdump kernels when accessing * firmware tables: */ - if (pfn < end_pfn_map) + if (pfn < max_pfn_mapped) return; printk(KERN_ERR "reserve_bootmem: illegal reserve %lx %u\n", @@ -667,10 +820,16 @@ void __init reserve_bootmem_generic(unsigned long phys, unsigned len) /* Should check here against the e820 map to avoid double free */ #ifdef CONFIG_NUMA - reserve_bootmem_node(NODE_DATA(nid), phys, len, BOOTMEM_DEFAULT); + 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); + else + reserve_bootmem(phys, len, BOOTMEM_DEFAULT); #else reserve_bootmem(phys, len, BOOTMEM_DEFAULT); #endif + if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) { dma_reserve += len / PAGE_SIZE; set_dma_reserve(dma_reserve); @@ -764,6 +923,10 @@ const char *arch_vma_name(struct vm_area_struct *vma) /* * Initialise the sparsemem vmemmap using huge-pages at the PMD level. */ +static long __meminitdata addr_start, addr_end; +static void __meminitdata *p_start, *p_end; +static int __meminitdata node_start; + int __meminit vmemmap_populate(struct page *start_page, unsigned long size, int node) { @@ -798,12 +961,32 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node) PAGE_KERNEL_LARGE); set_pmd(pmd, __pmd(pte_val(entry))); - printk(KERN_DEBUG " [%lx-%lx] PMD ->%p on node %d\n", - addr, addr + PMD_SIZE - 1, p, node); + /* 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; } + +void __meminit vmemmap_populate_print_last(void) +{ + 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); + p_start = NULL; + p_end = NULL; + node_start = 0; + } +} #endif diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 794895c6dcc9..71bb3159031a 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -19,11 +19,7 @@ #include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/pgalloc.h> - -enum ioremap_mode { - IOR_MODE_UNCACHED, - IOR_MODE_CACHED, -}; +#include <asm/pat.h> #ifdef CONFIG_X86_64 @@ -35,11 +31,23 @@ unsigned long __phys_addr(unsigned long x) } EXPORT_SYMBOL(__phys_addr); +static inline int phys_addr_valid(unsigned long addr) +{ + return addr < (1UL << boot_cpu_data.x86_phys_bits); +} + +#else + +static inline int phys_addr_valid(unsigned long addr) +{ + return 1; +} + #endif int page_is_ram(unsigned long pagenr) { - unsigned long addr, end; + resource_size_t addr, end; int i; /* @@ -78,19 +86,22 @@ int page_is_ram(unsigned long pagenr) * Fix up the linear direct mapping of the kernel to avoid cache attribute * conflicts. */ -static int ioremap_change_attr(unsigned long vaddr, unsigned long size, - enum ioremap_mode mode) +int ioremap_change_attr(unsigned long vaddr, unsigned long size, + unsigned long prot_val) { unsigned long nrpages = size >> PAGE_SHIFT; int err; - switch (mode) { - case IOR_MODE_UNCACHED: + switch (prot_val) { + case _PAGE_CACHE_UC: default: - err = set_memory_uc(vaddr, nrpages); + err = _set_memory_uc(vaddr, nrpages); break; - case IOR_MODE_CACHED: - err = set_memory_wb(vaddr, nrpages); + case _PAGE_CACHE_WC: + err = _set_memory_wc(vaddr, nrpages); + break; + case _PAGE_CACHE_WB: + err = _set_memory_wb(vaddr, nrpages); break; } @@ -106,18 +117,28 @@ static int ioremap_change_attr(unsigned long vaddr, unsigned long size, * have to convert them into an offset in a page-aligned mapping, but the * caller shouldn't need to know that small detail. */ -static void __iomem *__ioremap(resource_size_t phys_addr, unsigned long size, - enum ioremap_mode mode) +static void __iomem *__ioremap_caller(resource_size_t phys_addr, + unsigned long size, unsigned long prot_val, void *caller) { - unsigned long pfn, offset, last_addr, vaddr; + unsigned long pfn, offset, vaddr; + resource_size_t last_addr; struct vm_struct *area; + unsigned long new_prot_val; pgprot_t prot; + int retval; /* Don't allow wraparound or zero size */ last_addr = phys_addr + size - 1; if (!size || last_addr < phys_addr) return NULL; + if (!phys_addr_valid(phys_addr)) { + printk(KERN_WARNING "ioremap: invalid physical address %llx\n", + (unsigned long long)phys_addr); + WARN_ON_ONCE(1); + return NULL; + } + /* * Don't remap the low PCI/ISA area, it's always mapped.. */ @@ -127,48 +148,87 @@ static void __iomem *__ioremap(resource_size_t phys_addr, unsigned long size, /* * Don't allow anybody to remap normal RAM that we're using.. */ - for (pfn = phys_addr >> PAGE_SHIFT; pfn < max_pfn_mapped && - (pfn << PAGE_SHIFT) < last_addr; pfn++) { - if (page_is_ram(pfn) && pfn_valid(pfn) && - !PageReserved(pfn_to_page(pfn))) + for (pfn = phys_addr >> PAGE_SHIFT; + (pfn << PAGE_SHIFT) < (last_addr & PAGE_MASK); + pfn++) { + + int is_ram = page_is_ram(pfn); + + if (is_ram && pfn_valid(pfn) && !PageReserved(pfn_to_page(pfn))) return NULL; + WARN_ON_ONCE(is_ram); } - switch (mode) { - case IOR_MODE_UNCACHED: - default: + /* + * Mappings have to be page-aligned + */ + offset = phys_addr & ~PAGE_MASK; + phys_addr &= PAGE_MASK; + size = PAGE_ALIGN(last_addr+1) - phys_addr; + + retval = reserve_memtype(phys_addr, phys_addr + size, + prot_val, &new_prot_val); + if (retval) { + pr_debug("Warning: reserve_memtype returned %d\n", retval); + return NULL; + } + + if (prot_val != new_prot_val) { /* - * FIXME: we will use UC MINUS for now, as video fb drivers - * depend on it. Upcoming ioremap_wc() will fix this behavior. + * Do not fallback to certain memory types with certain + * requested type: + * - request is uc-, return cannot be write-back + * - request is uc-, return cannot be write-combine + * - request is write-combine, return cannot be write-back */ + if ((prot_val == _PAGE_CACHE_UC_MINUS && + (new_prot_val == _PAGE_CACHE_WB || + new_prot_val == _PAGE_CACHE_WC)) || + (prot_val == _PAGE_CACHE_WC && + new_prot_val == _PAGE_CACHE_WB)) { + pr_debug( + "ioremap error for 0x%llx-0x%llx, requested 0x%lx, got 0x%lx\n", + (unsigned long long)phys_addr, + (unsigned long long)(phys_addr + size), + prot_val, new_prot_val); + free_memtype(phys_addr, phys_addr + size); + return NULL; + } + prot_val = new_prot_val; + } + + switch (prot_val) { + case _PAGE_CACHE_UC: + default: + prot = PAGE_KERNEL_NOCACHE; + break; + case _PAGE_CACHE_UC_MINUS: prot = PAGE_KERNEL_UC_MINUS; break; - case IOR_MODE_CACHED: + case _PAGE_CACHE_WC: + prot = PAGE_KERNEL_WC; + break; + case _PAGE_CACHE_WB: prot = PAGE_KERNEL; break; } /* - * Mappings have to be page-aligned - */ - offset = phys_addr & ~PAGE_MASK; - phys_addr &= PAGE_MASK; - size = PAGE_ALIGN(last_addr+1) - phys_addr; - - /* * Ok, go for it.. */ - area = get_vm_area(size, VM_IOREMAP); + area = get_vm_area_caller(size, VM_IOREMAP, caller); if (!area) return NULL; area->phys_addr = phys_addr; vaddr = (unsigned long) area->addr; if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot)) { + free_memtype(phys_addr, phys_addr + size); free_vm_area(area); return NULL; } - if (ioremap_change_attr(vaddr, size, mode) < 0) { + if (ioremap_change_attr(vaddr, size, prot_val) < 0) { + free_memtype(phys_addr, phys_addr + size); vunmap(area->addr); return NULL; } @@ -199,13 +259,44 @@ static void __iomem *__ioremap(resource_size_t phys_addr, unsigned long size, */ void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size) { - return __ioremap(phys_addr, size, IOR_MODE_UNCACHED); + /* + * Ideally, this should be: + * pat_wc_enabled ? _PAGE_CACHE_UC : _PAGE_CACHE_UC_MINUS; + * + * Till we fix all X drivers to use ioremap_wc(), we will use + * UC MINUS. + */ + unsigned long val = _PAGE_CACHE_UC_MINUS; + + return __ioremap_caller(phys_addr, size, val, + __builtin_return_address(0)); } EXPORT_SYMBOL(ioremap_nocache); +/** + * ioremap_wc - map memory into CPU space write combined + * @offset: bus address of the memory + * @size: size of the resource to map + * + * This version of ioremap ensures that the memory is marked write combining. + * Write combining allows faster writes to some hardware devices. + * + * Must be freed with iounmap. + */ +void __iomem *ioremap_wc(unsigned long phys_addr, unsigned long size) +{ + if (pat_wc_enabled) + return __ioremap_caller(phys_addr, size, _PAGE_CACHE_WC, + __builtin_return_address(0)); + else + return ioremap_nocache(phys_addr, size); +} +EXPORT_SYMBOL(ioremap_wc); + void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size) { - return __ioremap(phys_addr, size, IOR_MODE_CACHED); + return __ioremap_caller(phys_addr, size, _PAGE_CACHE_WB, + __builtin_return_address(0)); } EXPORT_SYMBOL(ioremap_cache); @@ -252,6 +343,8 @@ void iounmap(volatile void __iomem *addr) return; } + free_memtype(p->phys_addr, p->phys_addr + get_vm_area_size(p)); + /* Finally remove it */ o = remove_vm_area((void *)addr); BUG_ON(p != o || o == NULL); @@ -259,6 +352,35 @@ void iounmap(volatile void __iomem *addr) } EXPORT_SYMBOL(iounmap); +/* + * Convert a physical pointer to a virtual kernel pointer for /dev/mem + * access + */ +void *xlate_dev_mem_ptr(unsigned long phys) +{ + void *addr; + unsigned long start = phys & PAGE_MASK; + + /* If page is RAM, we can use __va. Otherwise ioremap and unmap. */ + if (page_is_ram(start >> PAGE_SHIFT)) + return __va(phys); + + addr = (void *)ioremap(start, PAGE_SIZE); + if (addr) + addr = (void *)((unsigned long)addr | (phys & ~PAGE_MASK)); + + return addr; +} + +void unxlate_dev_mem_ptr(unsigned long phys, void *addr) +{ + if (page_is_ram(phys >> PAGE_SHIFT)) + return; + + iounmap((void __iomem *)((unsigned long)addr & PAGE_MASK)); + return; +} + #ifdef CONFIG_X86_32 int __initdata early_ioremap_debug; @@ -272,8 +394,8 @@ 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 __initdata pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] - __attribute__((aligned(PAGE_SIZE))); +static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] + __section(.bss.page_aligned); static inline pmd_t * __init early_ioremap_pmd(unsigned long addr) { @@ -330,7 +452,7 @@ void __init early_ioremap_clear(void) pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)); pmd_clear(pmd); - paravirt_release_pt(__pa(bm_pte) >> PAGE_SHIFT); + paravirt_release_pte(__pa(bm_pte) >> PAGE_SHIFT); __flush_tlb_all(); } diff --git a/arch/x86/mm/k8topology_64.c b/arch/x86/mm/k8topology_64.c index 7a2ebce87df5..1f476e477844 100644 --- a/arch/x86/mm/k8topology_64.c +++ b/arch/x86/mm/k8topology_64.c @@ -13,12 +13,15 @@ #include <linux/nodemask.h> #include <asm/io.h> #include <linux/pci_ids.h> +#include <linux/acpi.h> #include <asm/types.h> #include <asm/mmzone.h> #include <asm/proto.h> #include <asm/e820.h> #include <asm/pci-direct.h> #include <asm/numa.h> +#include <asm/mpspec.h> +#include <asm/apic.h> static __init int find_northbridge(void) { @@ -44,6 +47,30 @@ static __init int find_northbridge(void) return -1; } +static __init void early_get_boot_cpu_id(void) +{ + /* + * need to get boot_cpu_id so can use that to create apicid_to_node + * in k8_scan_nodes() + */ + /* + * Find possible boot-time SMP configuration: + */ + early_find_smp_config(); +#ifdef CONFIG_ACPI + /* + * Read APIC information from ACPI tables. + */ + early_acpi_boot_init(); +#endif + /* + * get boot-time SMP configuration: + */ + if (smp_found_config) + early_get_smp_config(); + early_init_lapic_mapping(); +} + int __init k8_scan_nodes(unsigned long start, unsigned long end) { unsigned long prevbase; @@ -56,6 +83,7 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end) unsigned cores; unsigned bits; int j; + unsigned apicid_base; if (!early_pci_allowed()) return -1; @@ -164,7 +192,7 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end) if (!found) return -1; - memnode_shift = compute_hash_shift(nodes, 8); + memnode_shift = compute_hash_shift(nodes, 8, NULL); if (memnode_shift < 0) { printk(KERN_ERR "No NUMA node hash function found. Contact maintainer\n"); return -1; @@ -174,11 +202,19 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end) /* use the coreid bits from early_identify_cpu */ bits = boot_cpu_data.x86_coreid_bits; cores = (1<<bits); + apicid_base = 0; + /* need to get boot_cpu_id early for system with apicid lifting */ + early_get_boot_cpu_id(); + if (boot_cpu_physical_apicid > 0) { + printk(KERN_INFO "BSP APIC ID: %02x\n", + boot_cpu_physical_apicid); + apicid_base = boot_cpu_physical_apicid; + } for (i = 0; i < 8; i++) { if (nodes[i].start != nodes[i].end) { nodeid = nodeids[i]; - for (j = 0; j < cores; j++) + for (j = apicid_base; j < cores + apicid_base; j++) apicid_to_node[(nodeid << bits) + j] = i; setup_node_bootmem(i, nodes[i].start, nodes[i].end); } diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 16b82ad34b96..c5066d519e5d 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -31,13 +31,15 @@ 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); -EXPORT_SYMBOL(x86_cpu_to_node_map_early_ptr); s16 apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = { [0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE @@ -58,7 +60,7 @@ unsigned long __initdata nodemap_size; * -1 if node overlap or lost ram (shift too big) */ static int __init populate_memnodemap(const struct bootnode *nodes, - int numnodes, int shift) + int numnodes, int shift, int *nodeids) { unsigned long addr, end; int i, res = -1; @@ -74,7 +76,12 @@ static int __init populate_memnodemap(const struct bootnode *nodes, do { if (memnodemap[addr >> shift] != NUMA_NO_NODE) return -1; - memnodemap[addr >> shift] = i; + + if (!nodeids) + memnodemap[addr >> shift] = i; + else + memnodemap[addr >> shift] = nodeids[i]; + addr += (1UL << shift); } while (addr < end); res = 1; @@ -137,7 +144,8 @@ static int __init extract_lsb_from_nodes(const struct bootnode *nodes, return i; } -int __init compute_hash_shift(struct bootnode *nodes, int numnodes) +int __init compute_hash_shift(struct bootnode *nodes, int numnodes, + int *nodeids) { int shift; @@ -147,7 +155,7 @@ int __init compute_hash_shift(struct bootnode *nodes, int numnodes) printk(KERN_DEBUG "NUMA: Using %d for the hash shift.\n", shift); - if (populate_memnodemap(nodes, numnodes, shift) != 1) { + if (populate_memnodemap(nodes, numnodes, shift, nodeids) != 1) { printk(KERN_INFO "Your memory is not aligned you need to " "rebuild your kernel with a bigger NODEMAPSIZE " "shift=%d\n", shift); @@ -188,6 +196,7 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long bootmap_start, nodedata_phys; void *bootmap; const int pgdat_size = round_up(sizeof(pg_data_t), PAGE_SIZE); + int nid; start = round_up(start, ZONE_ALIGN); @@ -210,9 +219,19 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, NODE_DATA(nodeid)->node_start_pfn = start_pfn; NODE_DATA(nodeid)->node_spanned_pages = end_pfn - start_pfn; - /* Find a place for the bootmem map */ + /* + * Find a place for the bootmem map + * nodedata_phys could be on other nodes by alloc_bootmem, + * so need to sure bootmap_start not to be small, otherwise + * 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_start = round_up(nodedata_phys + pgdat_size, PAGE_SIZE); + 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 * to use that to align to PAGE_SIZE @@ -237,10 +256,29 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, free_bootmem_with_active_regions(nodeid, end); - reserve_bootmem_node(NODE_DATA(nodeid), nodedata_phys, pgdat_size, - BOOTMEM_DEFAULT); - reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start, - bootmap_pages<<PAGE_SHIFT, BOOTMEM_DEFAULT); + /* + * convert early reserve to bootmem reserve earlier + * otherwise early_node_mem could use early reserved mem + * on previous node + */ + early_res_to_bootmem(start, end); + + /* + * in some case early_node_mem could use alloc_bootmem + * to get range on other node, don't reserve that again + */ + if (nid != nodeid) + printk(KERN_INFO " NODE_DATA(%d) on node %d\n", nodeid, nid); + else + reserve_bootmem_node(NODE_DATA(nodeid), nodedata_phys, + pgdat_size, BOOTMEM_DEFAULT); + nid = phys_to_nid(bootmap_start); + if (nid != nodeid) + printk(KERN_INFO " bootmap(%d) on node %d\n", nodeid, nid); + else + reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start, + bootmap_pages<<PAGE_SHIFT, BOOTMEM_DEFAULT); + #ifdef CONFIG_ACPI_NUMA srat_reserve_add_area(nodeid); #endif @@ -378,9 +416,10 @@ 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 * 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) { - struct bootnode nodes[MAX_NUMNODES]; u64 size, addr = start_pfn << PAGE_SHIFT; u64 max_addr = end_pfn << PAGE_SHIFT; int num_nodes = 0, num = 0, coeff_flag, coeff = -1, i; @@ -460,7 +499,7 @@ done: } } out: - memnode_shift = compute_hash_shift(nodes, num_nodes); + memnode_shift = compute_hash_shift(nodes, num_nodes, NULL); if (memnode_shift < 0) { memnode_shift = 0; printk(KERN_ERR "No NUMA hash function found. NUMA emulation " @@ -548,8 +587,6 @@ void __cpuinit numa_set_node(int cpu, int node) { int *cpu_to_node_map = x86_cpu_to_node_map_early_ptr; - cpu_pda(cpu)->nodenumber = node; - if(cpu_to_node_map) cpu_to_node_map[cpu] = node; else if(per_cpu_offset(cpu)) diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 7b79f6be4e7d..60bcb5b6a37e 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -9,6 +9,8 @@ #include <linux/slab.h> #include <linux/mm.h> #include <linux/interrupt.h> +#include <linux/seq_file.h> +#include <linux/debugfs.h> #include <asm/e820.h> #include <asm/processor.h> @@ -17,6 +19,7 @@ #include <asm/uaccess.h> #include <asm/pgalloc.h> #include <asm/proto.h> +#include <asm/pat.h> /* * The current flushing context - we pass it instead of 5 arguments: @@ -28,6 +31,7 @@ struct cpa_data { int numpages; int flushtlb; unsigned long pfn; + unsigned force_split : 1; }; #ifdef CONFIG_X86_64 @@ -259,6 +263,9 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, int i, do_split = 1; unsigned int level; + if (cpa->force_split) + return 1; + spin_lock_irqsave(&pgd_lock, flags); /* * Check for races, another CPU might have split this page @@ -476,9 +483,7 @@ static int split_large_page(pte_t *kpte, unsigned long address) goto out_unlock; pbase = (pte_t *)page_address(base); -#ifdef CONFIG_X86_32 - paravirt_alloc_pt(&init_mm, page_to_pfn(base)); -#endif + paravirt_alloc_pte(&init_mm, page_to_pfn(base)); ref_prot = pte_pgprot(pte_clrhuge(*kpte)); #ifdef CONFIG_X86_64 @@ -535,7 +540,7 @@ static int __change_page_attr(struct cpa_data *cpa, int primary) repeat: kpte = lookup_address(address, &level); if (!kpte) - return primary ? -EINVAL : 0; + return 0; old_pte = *kpte; if (!pte_val(old_pte)) { @@ -693,7 +698,8 @@ static inline int cache_attr(pgprot_t attr) } static int change_page_attr_set_clr(unsigned long addr, int numpages, - pgprot_t mask_set, pgprot_t mask_clr) + pgprot_t mask_set, pgprot_t mask_clr, + int force_split) { struct cpa_data cpa; int ret, cache, checkalias; @@ -704,7 +710,7 @@ static int change_page_attr_set_clr(unsigned long addr, int numpages, */ mask_set = canon_pgprot(mask_set); mask_clr = canon_pgprot(mask_clr); - if (!pgprot_val(mask_set) && !pgprot_val(mask_clr)) + if (!pgprot_val(mask_set) && !pgprot_val(mask_clr) && !force_split) return 0; /* Ensure we are PAGE_SIZE aligned */ @@ -721,6 +727,7 @@ static int change_page_attr_set_clr(unsigned long addr, int numpages, cpa.mask_set = mask_set; cpa.mask_clr = mask_clr; cpa.flushtlb = 0; + cpa.force_split = force_split; /* No alias checking for _NX bit modifications */ checkalias = (pgprot_val(mask_set) | pgprot_val(mask_clr)) != _PAGE_NX; @@ -759,26 +766,67 @@ out: static inline int change_page_attr_set(unsigned long addr, int numpages, pgprot_t mask) { - return change_page_attr_set_clr(addr, numpages, mask, __pgprot(0)); + return change_page_attr_set_clr(addr, numpages, mask, __pgprot(0), 0); } static inline int change_page_attr_clear(unsigned long addr, int numpages, pgprot_t mask) { - return change_page_attr_set_clr(addr, numpages, __pgprot(0), mask); + return change_page_attr_set_clr(addr, numpages, __pgprot(0), mask, 0); } -int set_memory_uc(unsigned long addr, int numpages) +int _set_memory_uc(unsigned long addr, int numpages) { + /* + * for now UC MINUS. see comments in ioremap_nocache() + */ return change_page_attr_set(addr, numpages, - __pgprot(_PAGE_PCD)); + __pgprot(_PAGE_CACHE_UC_MINUS)); +} + +int set_memory_uc(unsigned long addr, int numpages) +{ + /* + * for now UC MINUS. see comments in ioremap_nocache() + */ + if (reserve_memtype(addr, addr + numpages * PAGE_SIZE, + _PAGE_CACHE_UC_MINUS, NULL)) + return -EINVAL; + + return _set_memory_uc(addr, numpages); } EXPORT_SYMBOL(set_memory_uc); -int set_memory_wb(unsigned long addr, int numpages) +int _set_memory_wc(unsigned long addr, int numpages) +{ + return change_page_attr_set(addr, numpages, + __pgprot(_PAGE_CACHE_WC)); +} + +int set_memory_wc(unsigned long addr, int numpages) +{ + if (!pat_wc_enabled) + return set_memory_uc(addr, numpages); + + if (reserve_memtype(addr, addr + numpages * PAGE_SIZE, + _PAGE_CACHE_WC, NULL)) + return -EINVAL; + + return _set_memory_wc(addr, numpages); +} +EXPORT_SYMBOL(set_memory_wc); + +int _set_memory_wb(unsigned long addr, int numpages) { return change_page_attr_clear(addr, numpages, - __pgprot(_PAGE_PCD | _PAGE_PWT)); + __pgprot(_PAGE_CACHE_MASK)); +} + +int set_memory_wb(unsigned long addr, int numpages) +{ + free_memtype(addr, addr + numpages * PAGE_SIZE); + + return _set_memory_wb(addr, numpages); } EXPORT_SYMBOL(set_memory_wb); @@ -809,6 +857,12 @@ int set_memory_np(unsigned long addr, int numpages) return change_page_attr_clear(addr, numpages, __pgprot(_PAGE_PRESENT)); } +int set_memory_4k(unsigned long addr, int numpages) +{ + return change_page_attr_set_clr(addr, numpages, __pgprot(0), + __pgprot(0), 1); +} + int set_pages_uc(struct page *page, int numpages) { unsigned long addr = (unsigned long)page_address(page); @@ -918,6 +972,45 @@ void kernel_map_pages(struct page *page, int numpages, int enable) cpa_fill_pool(NULL); } +#ifdef CONFIG_DEBUG_FS +static int dpa_show(struct seq_file *m, void *v) +{ + seq_puts(m, "DEBUG_PAGEALLOC\n"); + seq_printf(m, "pool_size : %lu\n", pool_size); + seq_printf(m, "pool_pages : %lu\n", pool_pages); + seq_printf(m, "pool_low : %lu\n", pool_low); + seq_printf(m, "pool_used : %lu\n", pool_used); + seq_printf(m, "pool_failed : %lu\n", pool_failed); + + return 0; +} + +static int dpa_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, dpa_show, NULL); +} + +static const struct file_operations dpa_fops = { + .open = dpa_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init debug_pagealloc_proc_init(void) +{ + struct dentry *de; + + de = debugfs_create_file("debug_pagealloc", 0600, NULL, NULL, + &dpa_fops); + if (!de) + return -ENOMEM; + + return 0; +} +__initcall(debug_pagealloc_proc_init); +#endif + #ifdef CONFIG_HIBERNATION bool kernel_page_present(struct page *page) diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c new file mode 100644 index 000000000000..277446cd30b6 --- /dev/null +++ b/arch/x86/mm/pat.c @@ -0,0 +1,596 @@ +/* + * Handle caching attributes in page tables (PAT) + * + * Authors: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> + * Suresh B Siddha <suresh.b.siddha@intel.com> + * + * Loosely based on earlier PAT patchset from Eric Biederman and Andi Kleen. + */ + +#include <linux/mm.h> +#include <linux/kernel.h> +#include <linux/gfp.h> +#include <linux/fs.h> +#include <linux/bootmem.h> + +#include <asm/msr.h> +#include <asm/tlbflush.h> +#include <asm/processor.h> +#include <asm/page.h> +#include <asm/pgtable.h> +#include <asm/pat.h> +#include <asm/e820.h> +#include <asm/cacheflush.h> +#include <asm/fcntl.h> +#include <asm/mtrr.h> +#include <asm/io.h> + +int pat_wc_enabled = 1; + +static u64 __read_mostly boot_pat_state; + +static int nopat(char *str) +{ + pat_wc_enabled = 0; + printk(KERN_INFO "x86: PAT support disabled.\n"); + + return 0; +} +early_param("nopat", nopat); + +static int pat_known_cpu(void) +{ + if (!pat_wc_enabled) + return 0; + + if (cpu_has_pat) + return 1; + + pat_wc_enabled = 0; + printk(KERN_INFO "CPU and/or kernel does not support PAT.\n"); + return 0; +} + +enum { + PAT_UC = 0, /* uncached */ + PAT_WC = 1, /* Write combining */ + PAT_WT = 4, /* Write Through */ + PAT_WP = 5, /* Write Protected */ + PAT_WB = 6, /* Write Back (default) */ + PAT_UC_MINUS = 7, /* UC, but can be overriden by MTRR */ +}; + +#define PAT(x,y) ((u64)PAT_ ## y << ((x)*8)) + +void pat_init(void) +{ + u64 pat; + +#ifndef CONFIG_X86_PAT + nopat(NULL); +#endif + + /* Boot CPU enables PAT based on CPU feature */ + if (!smp_processor_id() && !pat_known_cpu()) + return; + + /* APs enable PAT iff boot CPU has enabled it before */ + if (smp_processor_id() && !pat_wc_enabled) + return; + + /* Set PWT to Write-Combining. All other bits stay the same */ + /* + * PTE encoding used in Linux: + * PAT + * |PCD + * ||PWT + * ||| + * 000 WB _PAGE_CACHE_WB + * 001 WC _PAGE_CACHE_WC + * 010 UC- _PAGE_CACHE_UC_MINUS + * 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); + + /* Boot CPU check */ + if (!smp_processor_id()) { + rdmsrl(MSR_IA32_CR_PAT, boot_pat_state); + } + + wrmsrl(MSR_IA32_CR_PAT, pat); + printk(KERN_INFO "x86 PAT enabled: cpu %d, old 0x%Lx, new 0x%Lx\n", + smp_processor_id(), boot_pat_state, pat); +} + +#undef PAT + +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"; + } +} + +/* + * The global memtype list keeps track of memory type for specific + * physical memory areas. Conflicting memory types in different + * mappings can cause CPU cache corruption. To avoid this we keep track. + * + * The list is sorted based on starting address and can contain multiple + * entries for each address (this allows reference counting for overlapping + * areas). All the aliases have the same cache attributes of course. + * Zero attributes are represented as holes. + * + * Currently the data structure is a list because the number of mappings + * are expected to be relatively small. If this should be a problem + * it could be changed to a rbtree or similar. + * + * memtype_lock protects the whole list. + */ + +struct memtype { + u64 start; + u64 end; + unsigned long type; + struct list_head nd; +}; + +static LIST_HEAD(memtype_list); +static DEFINE_SPINLOCK(memtype_lock); /* protects memtype list */ + +/* + * Does intersection of PAT memory type and MTRR memory type and returns + * the resulting memory type as PAT understands it. + * (Type in pat and mtrr will not have same value) + * 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) +{ + 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; + } + + 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 0; +} + +/* + * req_type typically has one of the: + * - _PAGE_CACHE_WB + * - _PAGE_CACHE_WC + * - _PAGE_CACHE_UC_MINUS + * - _PAGE_CACHE_UC + * + * 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 + * it will return a negative return value. + */ +int reserve_memtype(u64 start, u64 end, unsigned long req_type, + unsigned long *ret_type) +{ + struct memtype *new_entry = NULL; + struct memtype *parse; + unsigned long actual_type; + int err = 0; + + /* Only track when pat_wc_enabled */ + if (!pat_wc_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; + } + } + 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; + + 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. + */ + 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; + actual_type = _PAGE_CACHE_WB; + } else { + req_type = _PAGE_CACHE_UC_MINUS; + actual_type = _PAGE_CACHE_UC_MINUS; + } + } else { + req_type &= _PAGE_CACHE_MASK; + err = pat_x_mtrr_type(start, end, req_type, &actual_type); + } + + if (err) { + if (ret_type) + *ret_type = actual_type; + + return -EINVAL; + } + + new_entry = kmalloc(sizeof(struct memtype), GFP_KERNEL); + if (!new_entry) + return -ENOMEM; + + new_entry->start = start; + new_entry->end = end; + new_entry->type = actual_type; + + if (ret_type) + *ret_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; + 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; + } + } + + 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; + } + + 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); + 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)); + } + + spin_unlock(&memtype_lock); + return err; +} + +int free_memtype(u64 start, u64 end) +{ + struct memtype *ml; + int err = -EINVAL; + + /* Only track when pat_wc_enabled */ + if (!pat_wc_enabled) { + return 0; + } + + /* Low ISA region is always mapped WB. No need to track */ + if (start >= ISA_START_ADDRESS && end <= ISA_END_ADDRESS) { + 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); + err = 0; + break; + } + } + spin_unlock(&memtype_lock); + + if (err) { + printk(KERN_INFO "%s:%d freeing invalid memtype %Lx-%Lx\n", + current->comm, current->pid, start, end); + } + + pr_debug("free_memtype request 0x%Lx-0x%Lx\n", start, end); + return err; +} + + +/* + * /dev/mem mmap interface. The memtype used for mapping varies: + * - Use UC for mappings with O_SYNC flag + * - Without O_SYNC flag, if there is any conflict in reserve_memtype, + * inherit the memtype from existing mapping. + * - Else use UC_MINUS memtype (for backward compatibility with existing + * X drivers. + */ +pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t vma_prot) +{ + return vma_prot; +} + +#ifdef CONFIG_NONPROMISC_DEVMEM +/* This check is done in drivers/char/mem.c in case of NONPROMISC_DEVMEM*/ +static inline int range_is_allowed(unsigned long pfn, unsigned long size) +{ + return 1; +} +#else +static inline int range_is_allowed(unsigned long pfn, unsigned long size) +{ + u64 from = ((u64)pfn) << PAGE_SHIFT; + u64 to = from + size; + u64 cursor = from; + + while (cursor < to) { + if (!devmem_is_allowed(pfn)) { + printk(KERN_INFO + "Program %s tried to access /dev/mem between %Lx->%Lx.\n", + current->comm, from, to); + return 0; + } + cursor += PAGE_SIZE; + pfn++; + } + return 1; +} +#endif /* CONFIG_NONPROMISC_DEVMEM */ + +int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t *vma_prot) +{ + u64 offset = ((u64) pfn) << PAGE_SHIFT; + unsigned long flags = _PAGE_CACHE_UC_MINUS; + int retval; + + if (!range_is_allowed(pfn, size)) + return 0; + + if (file->f_flags & O_SYNC) { + flags = _PAGE_CACHE_UC; + } + +#ifdef CONFIG_X86_32 + /* + * On the PPro and successors, the MTRRs are used to set + * memory types for physical addresses outside main memory, + * so blindly setting UC or PWT on those pages is wrong. + * For Pentiums and earlier, the surround logic should disable + * 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)) { + flags = _PAGE_CACHE_UC; + } +#endif + + /* + * With O_SYNC, we can only take UC mapping. Fail if we cannot. + * Without O_SYNC, we want to get + * - 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 + */ + if (flags != _PAGE_CACHE_UC_MINUS) { + retval = reserve_memtype(offset, offset + size, flags, NULL); + } else { + retval = reserve_memtype(offset, offset + size, -1, &flags); + } + + if (retval < 0) + return 0; + + if (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", + current->comm, current->pid, + cattr_name(flags), + offset, offset + size); + return 0; + } + + *vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) | + flags); + return 1; +} + +void map_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot) +{ + u64 addr = (u64)pfn << PAGE_SHIFT; + unsigned long flags; + unsigned long want_flags = (pgprot_val(vma_prot) & _PAGE_CACHE_MASK); + + reserve_memtype(addr, addr + size, want_flags, &flags); + if (flags != want_flags) { + printk(KERN_INFO + "%s:%d /dev/mem expected mapping type %s for %Lx-%Lx, got %s\n", + current->comm, current->pid, + cattr_name(want_flags), + addr, addr + size, + cattr_name(flags)); + } +} + +void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot) +{ + u64 addr = (u64)pfn << PAGE_SHIFT; + + free_memtype(addr, addr + size); +} + diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c new file mode 100644 index 000000000000..50159764f694 --- /dev/null +++ b/arch/x86/mm/pgtable.c @@ -0,0 +1,276 @@ +#include <linux/mm.h> +#include <asm/pgalloc.h> +#include <asm/pgtable.h> +#include <asm/tlb.h> + +pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) +{ + return (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); +} + +pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) +{ + struct page *pte; + +#ifdef CONFIG_HIGHPTE + pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT|__GFP_ZERO, 0); +#else + pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0); +#endif + if (pte) + pgtable_page_ctor(pte); + return pte; +} + +void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte) +{ + pgtable_page_dtor(pte); + paravirt_release_pte(page_to_pfn(pte)); + tlb_remove_page(tlb, pte); +} + +#if PAGETABLE_LEVELS > 2 +void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) +{ + paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT); + tlb_remove_page(tlb, virt_to_page(pmd)); +} + +#if PAGETABLE_LEVELS > 3 +void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud) +{ + paravirt_release_pud(__pa(pud) >> PAGE_SHIFT); + tlb_remove_page(tlb, virt_to_page(pud)); +} +#endif /* PAGETABLE_LEVELS > 3 */ +#endif /* PAGETABLE_LEVELS > 2 */ + +static inline void pgd_list_add(pgd_t *pgd) +{ + struct page *page = virt_to_page(pgd); + + list_add(&page->lru, &pgd_list); +} + +static inline void pgd_list_del(pgd_t *pgd) +{ + struct page *page = virt_to_page(pgd); + + list_del(&page->lru); +} + +#define UNSHARED_PTRS_PER_PGD \ + (SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_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 + references from swapper_pg_dir. */ + if (PAGETABLE_LEVELS == 2 || + (PAGETABLE_LEVELS == 3 && SHARED_KERNEL_PMD) || + PAGETABLE_LEVELS == 4) { + clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY, + swapper_pg_dir + KERNEL_PGD_BOUNDARY, + KERNEL_PGD_PTRS); + paravirt_alloc_pmd_clone(__pa(pgd) >> PAGE_SHIFT, + __pa(swapper_pg_dir) >> PAGE_SHIFT, + KERNEL_PGD_BOUNDARY, + KERNEL_PGD_PTRS); + } + + /* 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) +{ + unsigned long flags; /* can be called from interrupt context */ + + if (SHARED_KERNEL_PMD) + return; + + spin_lock_irqsave(&pgd_lock, flags); + pgd_list_del(pgd); + spin_unlock_irqrestore(&pgd_lock, flags); +} + +/* + * List of all pgd's needed for non-PAE so it can invalidate entries + * in both cached and uncached pgd's; not needed for PAE since the + * kernel pmd is shared. If PAE were not to share the pmd a similar + * tactic would be needed. This is essentially codepath-based locking + * against pageattr.c; it is the unique case in which a valid change + * of kernel pagetables can't be lazily synchronized by vmalloc faults. + * vmalloc faults work because attached pagetables are never freed. + * -- wli + */ + +#ifdef CONFIG_X86_PAE +/* + * 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 + * freed manually. + */ +static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) +{ + int i; + + for(i = 0; i < UNSHARED_PTRS_PER_PGD; i++) { + pgd_t pgd = pgdp[i]; + + if (pgd_val(pgd) != 0) { + pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd); + + pgdp[i] = native_make_pgd(0); + + paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT); + pmd_free(mm, pmd); + } + } +} + +/* + * 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) +{ + 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; + } + + if (i >= KERNEL_PGD_BOUNDARY) + memcpy(pmd, (pmd_t *)pgd_page_vaddr(swapper_pg_dir[i]), + sizeof(pmd_t) * PTRS_PER_PMD); + + pud_populate(mm, pud, pmd); + } + + return 1; +} + +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. */ +static int pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd) +{ + return 1; +} + +static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgd) +{ +} +#endif /* CONFIG_X86_PAE */ + +pgd_t *pgd_alloc(struct mm_struct *mm) +{ + pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); + + /* so that alloc_pmd can use it */ + mm->pgd = pgd; + if (pgd) + pgd_ctor(pgd); + + if (pgd && !pgd_prepopulate_pmd(mm, pgd)) { + pgd_dtor(pgd); + free_page((unsigned long)pgd); + pgd = NULL; + } + + return pgd; +} + +void pgd_free(struct mm_struct *mm, pgd_t *pgd) +{ + pgd_mop_up_pmds(mm, pgd); + pgd_dtor(pgd); + free_page((unsigned long)pgd); +} + +int ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, + pte_t entry, int dirty) +{ + int changed = !pte_same(*ptep, entry); + + if (changed && dirty) { + *ptep = entry; + pte_update_defer(vma->vm_mm, address, ptep); + flush_tlb_page(vma, address); + } + + return changed; +} + +int ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ + int ret = 0; + + if (pte_young(*ptep)) + ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, + &ptep->pte); + + if (ret) + pte_update(vma->vm_mm, addr, ptep); + + return ret; +} + +int ptep_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) +{ + int young; + + young = ptep_test_and_clear_young(vma, address, ptep); + if (young) + flush_tlb_page(vma, address); + + return young; +} diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index 2f9e9afcb9f4..9ee007be9142 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -1,7 +1,3 @@ -/* - * linux/arch/i386/mm/pgtable.c - */ - #include <linux/sched.h> #include <linux/kernel.h> #include <linux/errno.h> @@ -36,7 +32,6 @@ void show_mem(void) printk(KERN_INFO "Mem-info:\n"); show_free_areas(); - printk(KERN_INFO "Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10)); for_each_online_pgdat(pgdat) { pgdat_resize_lock(pgdat, &flags); for (i = 0; i < pgdat->node_spanned_pages; ++i) { @@ -178,206 +173,9 @@ void reserve_top_address(unsigned long reserve) __VMALLOC_RESERVE += reserve; } -pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) -{ - return (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); -} - -pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) +int pmd_bad(pmd_t pmd) { - struct page *pte; + WARN_ON_ONCE(pmd_bad_v1(pmd) != pmd_bad_v2(pmd)); -#ifdef CONFIG_HIGHPTE - pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT|__GFP_ZERO, 0); -#else - pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0); -#endif - if (pte) - pgtable_page_ctor(pte); - return pte; + return pmd_bad_v1(pmd); } - -/* - * List of all pgd's needed for non-PAE so it can invalidate entries - * in both cached and uncached pgd's; not needed for PAE since the - * kernel pmd is shared. If PAE were not to share the pmd a similar - * tactic would be needed. This is essentially codepath-based locking - * against pageattr.c; it is the unique case in which a valid change - * of kernel pagetables can't be lazily synchronized by vmalloc faults. - * vmalloc faults work because attached pagetables are never freed. - * -- wli - */ -static inline void pgd_list_add(pgd_t *pgd) -{ - struct page *page = virt_to_page(pgd); - - list_add(&page->lru, &pgd_list); -} - -static inline void pgd_list_del(pgd_t *pgd) -{ - struct page *page = virt_to_page(pgd); - - list_del(&page->lru); -} - -#define UNSHARED_PTRS_PER_PGD \ - (SHARED_KERNEL_PMD ? USER_PTRS_PER_PGD : PTRS_PER_PGD) - -static void pgd_ctor(void *p) -{ - pgd_t *pgd = p; - unsigned long flags; - - /* Clear usermode parts of PGD */ - memset(pgd, 0, USER_PTRS_PER_PGD*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 - references from swapper_pg_dir. */ - if (PAGETABLE_LEVELS == 2 || - (PAGETABLE_LEVELS == 3 && SHARED_KERNEL_PMD)) { - clone_pgd_range(pgd + USER_PTRS_PER_PGD, - swapper_pg_dir + USER_PTRS_PER_PGD, - KERNEL_PGD_PTRS); - paravirt_alloc_pd_clone(__pa(pgd) >> PAGE_SHIFT, - __pa(swapper_pg_dir) >> PAGE_SHIFT, - USER_PTRS_PER_PGD, - KERNEL_PGD_PTRS); - } - - /* 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) -{ - unsigned long flags; /* can be called from interrupt context */ - - if (SHARED_KERNEL_PMD) - return; - - spin_lock_irqsave(&pgd_lock, flags); - pgd_list_del(pgd); - spin_unlock_irqrestore(&pgd_lock, flags); -} - -#ifdef CONFIG_X86_PAE -/* - * 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 - * freed manually. - */ -static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) -{ - int i; - - for(i = 0; i < UNSHARED_PTRS_PER_PGD; i++) { - pgd_t pgd = pgdp[i]; - - if (pgd_val(pgd) != 0) { - pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd); - - pgdp[i] = native_make_pgd(0); - - paravirt_release_pd(pgd_val(pgd) >> PAGE_SHIFT); - pmd_free(mm, pmd); - } - } -} - -/* - * 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) -{ - 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; - } - - if (i >= USER_PTRS_PER_PGD) - memcpy(pmd, (pmd_t *)pgd_page_vaddr(swapper_pg_dir[i]), - sizeof(pmd_t) * PTRS_PER_PMD); - - pud_populate(mm, pud, pmd); - } - - return 1; -} -#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; -} - -static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) -{ -} -#endif /* CONFIG_X86_PAE */ - -pgd_t *pgd_alloc(struct mm_struct *mm) -{ - pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); - - /* so that alloc_pd can use it */ - mm->pgd = pgd; - if (pgd) - pgd_ctor(pgd); - - if (pgd && !pgd_prepopulate_pmd(mm, pgd)) { - pgd_dtor(pgd); - free_page((unsigned long)pgd); - pgd = NULL; - } - - return pgd; -} - -void pgd_free(struct mm_struct *mm, pgd_t *pgd) -{ - pgd_mop_up_pmds(mm, pgd); - pgd_dtor(pgd); - free_page((unsigned long)pgd); -} - -void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte) -{ - pgtable_page_dtor(pte); - paravirt_release_pt(page_to_pfn(pte)); - tlb_remove_page(tlb, pte); -} - -#ifdef CONFIG_X86_PAE - -void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) -{ - paravirt_release_pd(__pa(pmd) >> PAGE_SHIFT); - tlb_remove_page(tlb, virt_to_page(pmd)); -} - -#endif diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index 845001c617cc..3890234e5b26 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -20,6 +20,7 @@ #include <asm/proto.h> #include <asm/numa.h> #include <asm/e820.h> +#include <asm/genapic.h> int acpi_numa __initdata; @@ -31,6 +32,10 @@ static struct bootnode nodes_add[MAX_NUMNODES]; static int found_add_area __initdata; int hotadd_percent __initdata = 0; +static int num_node_memblks __initdata; +static struct bootnode node_memblk_range[NR_NODE_MEMBLKS] __initdata; +static int memblk_nodeid[NR_NODE_MEMBLKS] __initdata; + /* Too small nodes confuse the VM badly. Usually they result from BIOS bugs. */ #define NODE_MIN_SIZE (4*1024*1024) @@ -40,17 +45,17 @@ static __init int setup_node(int pxm) return acpi_map_pxm_to_node(pxm); } -static __init int conflicting_nodes(unsigned long start, unsigned long end) +static __init int conflicting_memblks(unsigned long start, unsigned long end) { int i; - for_each_node_mask(i, nodes_parsed) { - struct bootnode *nd = &nodes[i]; + for (i = 0; i < num_node_memblks; i++) { + struct bootnode *nd = &node_memblk_range[i]; if (nd->start == nd->end) continue; if (nd->end > start && nd->start < end) - return i; + return memblk_nodeid[i]; if (nd->end == end && nd->start == start) - return i; + return memblk_nodeid[i]; } return -1; } @@ -132,7 +137,6 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) int pxm, node; int apic_id; - apic_id = pa->apic_id; if (srat_disabled()) return; if (pa->header.length != sizeof(struct acpi_srat_cpu_affinity)) { @@ -148,13 +152,18 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) bad_srat(); return; } + + if (is_uv_system()) + apic_id = (pa->apic_id << 8) | pa->local_sapic_eid; + else + apic_id = pa->apic_id; apicid_to_node[apic_id] = node; acpi_numa = 1; printk(KERN_INFO "SRAT: PXM %u -> APIC %u -> Node %u\n", pxm, apic_id, node); } -int update_end_of_memory(unsigned long end) {return -1;} +static int update_end_of_memory(unsigned long end) {return -1;} static int hotadd_enough_memory(struct bootnode *nd) {return 1;} #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE static inline int save_add_info(void) {return 1;} @@ -253,7 +262,7 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) bad_srat(); return; } - i = conflicting_nodes(start, end); + i = conflicting_memblks(start, end); if (i == node) { printk(KERN_WARNING "SRAT: Warning: PXM %d (%lx-%lx) overlaps with itself (%Lx-%Lx)\n", @@ -278,10 +287,10 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) nd->end = end; } - printk(KERN_INFO "SRAT: Node %u PXM %u %Lx-%Lx\n", node, pxm, - nd->start, nd->end); - e820_register_active_regions(node, nd->start >> PAGE_SHIFT, - nd->end >> PAGE_SHIFT); + printk(KERN_INFO "SRAT: Node %u PXM %u %lx-%lx\n", node, pxm, + start, end); + e820_register_active_regions(node, start >> PAGE_SHIFT, + end >> PAGE_SHIFT); push_node_boundaries(node, nd->start >> PAGE_SHIFT, nd->end >> PAGE_SHIFT); @@ -293,6 +302,11 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) if ((nd->start | nd->end) == 0) node_clear(node, nodes_parsed); } + + node_memblk_range[num_node_memblks].start = start; + node_memblk_range[num_node_memblks].end = end; + memblk_nodeid[num_node_memblks] = node; + num_node_memblks++; } /* Sanity check to catch more bad SRATs (they are amazingly common). @@ -363,7 +377,8 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end) return -1; } - memnode_shift = compute_hash_shift(nodes, MAX_NUMNODES); + memnode_shift = compute_hash_shift(node_memblk_range, num_node_memblks, + memblk_nodeid); if (memnode_shift < 0) { printk(KERN_ERR "SRAT: No NUMA node hash function found. Contact maintainer\n"); diff --git a/arch/x86/oprofile/init.c b/arch/x86/oprofile/init.c index 5341d481d92f..cdfe4c54deca 100644 --- a/arch/x86/oprofile/init.c +++ b/arch/x86/oprofile/init.c @@ -10,18 +10,19 @@ #include <linux/oprofile.h> #include <linux/init.h> #include <linux/errno.h> - -/* We support CPUs that have performance counters like the Pentium Pro + +/* + * We support CPUs that have performance counters like the Pentium Pro * with the NMI mode driver. */ - -extern int op_nmi_init(struct oprofile_operations * ops); -extern int op_nmi_timer_init(struct oprofile_operations * ops); + +extern int op_nmi_init(struct oprofile_operations *ops); +extern int op_nmi_timer_init(struct oprofile_operations *ops); extern void op_nmi_exit(void); extern void x86_backtrace(struct pt_regs * const regs, unsigned int depth); -int __init oprofile_arch_init(struct oprofile_operations * ops) +int __init oprofile_arch_init(struct oprofile_operations *ops) { int ret; diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 1f11cf0a307f..cc48d3fde545 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -23,8 +23,8 @@ #include "op_x86_model.h" static struct op_x86_model_spec const *model; -static struct op_msrs cpu_msrs[NR_CPUS]; -static unsigned long saved_lvtpc[NR_CPUS]; +static DEFINE_PER_CPU(struct op_msrs, cpu_msrs); +static DEFINE_PER_CPU(unsigned long, saved_lvtpc); static int nmi_start(void); static void nmi_stop(void); @@ -89,7 +89,7 @@ static int profile_exceptions_notify(struct notifier_block *self, switch (val) { case DIE_NMI: - if (model->check_ctrs(args->regs, &cpu_msrs[cpu])) + if (model->check_ctrs(args->regs, &per_cpu(cpu_msrs, cpu))) ret = NOTIFY_STOP; break; default: @@ -126,7 +126,7 @@ static void nmi_cpu_save_registers(struct op_msrs *msrs) static void nmi_save_registers(void *dummy) { int cpu = smp_processor_id(); - struct op_msrs *msrs = &cpu_msrs[cpu]; + struct op_msrs *msrs = &per_cpu(cpu_msrs, cpu); nmi_cpu_save_registers(msrs); } @@ -134,10 +134,10 @@ static void free_msrs(void) { int i; for_each_possible_cpu(i) { - kfree(cpu_msrs[i].counters); - cpu_msrs[i].counters = NULL; - kfree(cpu_msrs[i].controls); - cpu_msrs[i].controls = NULL; + kfree(per_cpu(cpu_msrs, i).counters); + per_cpu(cpu_msrs, i).counters = NULL; + kfree(per_cpu(cpu_msrs, i).controls); + per_cpu(cpu_msrs, i).controls = NULL; } } @@ -149,13 +149,15 @@ static int allocate_msrs(void) int i; for_each_possible_cpu(i) { - cpu_msrs[i].counters = kmalloc(counters_size, GFP_KERNEL); - if (!cpu_msrs[i].counters) { + per_cpu(cpu_msrs, i).counters = kmalloc(counters_size, + GFP_KERNEL); + if (!per_cpu(cpu_msrs, i).counters) { success = 0; break; } - cpu_msrs[i].controls = kmalloc(controls_size, GFP_KERNEL); - if (!cpu_msrs[i].controls) { + per_cpu(cpu_msrs, i).controls = kmalloc(controls_size, + GFP_KERNEL); + if (!per_cpu(cpu_msrs, i).controls) { success = 0; break; } @@ -170,11 +172,11 @@ static int allocate_msrs(void) static void nmi_cpu_setup(void *dummy) { int cpu = smp_processor_id(); - struct op_msrs *msrs = &cpu_msrs[cpu]; + struct op_msrs *msrs = &per_cpu(cpu_msrs, cpu); spin_lock(&oprofilefs_lock); model->setup_ctrs(msrs); spin_unlock(&oprofilefs_lock); - saved_lvtpc[cpu] = apic_read(APIC_LVTPC); + per_cpu(saved_lvtpc, cpu) = apic_read(APIC_LVTPC); apic_write(APIC_LVTPC, APIC_DM_NMI); } @@ -203,13 +205,15 @@ static int nmi_setup(void) */ /* Assume saved/restored counters are the same on all CPUs */ - model->fill_in_addresses(&cpu_msrs[0]); + model->fill_in_addresses(&per_cpu(cpu_msrs, 0)); for_each_possible_cpu(cpu) { if (cpu != 0) { - memcpy(cpu_msrs[cpu].counters, cpu_msrs[0].counters, + memcpy(per_cpu(cpu_msrs, cpu).counters, + per_cpu(cpu_msrs, 0).counters, sizeof(struct op_msr) * model->num_counters); - memcpy(cpu_msrs[cpu].controls, cpu_msrs[0].controls, + memcpy(per_cpu(cpu_msrs, cpu).controls, + per_cpu(cpu_msrs, 0).controls, sizeof(struct op_msr) * model->num_controls); } @@ -249,7 +253,7 @@ static void nmi_cpu_shutdown(void *dummy) { unsigned int v; int cpu = smp_processor_id(); - struct op_msrs *msrs = &cpu_msrs[cpu]; + struct op_msrs *msrs = &__get_cpu_var(cpu_msrs); /* restoring APIC_LVTPC can trigger an apic error because the delivery * mode and vector nr combination can be illegal. That's by design: on @@ -258,23 +262,24 @@ static void nmi_cpu_shutdown(void *dummy) */ v = apic_read(APIC_LVTERR); apic_write(APIC_LVTERR, v | APIC_LVT_MASKED); - apic_write(APIC_LVTPC, saved_lvtpc[cpu]); + apic_write(APIC_LVTPC, per_cpu(saved_lvtpc, cpu)); apic_write(APIC_LVTERR, v); nmi_restore_registers(msrs); } static void nmi_shutdown(void) { + struct op_msrs *msrs = &__get_cpu_var(cpu_msrs); nmi_enabled = 0; on_each_cpu(nmi_cpu_shutdown, NULL, 0, 1); unregister_die_notifier(&profile_exceptions_nb); - model->shutdown(cpu_msrs); + model->shutdown(msrs); free_msrs(); } static void nmi_cpu_start(void *dummy) { - struct op_msrs const *msrs = &cpu_msrs[smp_processor_id()]; + struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs); model->start(msrs); } @@ -286,7 +291,7 @@ static int nmi_start(void) static void nmi_cpu_stop(void *dummy) { - struct op_msrs const *msrs = &cpu_msrs[smp_processor_id()]; + struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs); model->stop(msrs); } diff --git a/arch/x86/oprofile/nmi_timer_int.c b/arch/x86/oprofile/nmi_timer_int.c index 1418e36ae7ab..e3ecb71b5790 100644 --- a/arch/x86/oprofile/nmi_timer_int.c +++ b/arch/x86/oprofile/nmi_timer_int.c @@ -17,14 +17,14 @@ #include <asm/nmi.h> #include <asm/apic.h> #include <asm/ptrace.h> - + static int profile_timer_exceptions_notify(struct notifier_block *self, unsigned long val, void *data) { struct die_args *args = (struct die_args *)data; int ret = NOTIFY_DONE; - switch(val) { + switch (val) { case DIE_NMI: oprofile_add_sample(args->regs, 0); ret = NOTIFY_STOP; @@ -56,7 +56,7 @@ static void timer_stop(void) } -int __init op_nmi_timer_init(struct oprofile_operations * ops) +int __init op_nmi_timer_init(struct oprofile_operations *ops) { if ((nmi_watchdog != NMI_IO_APIC) || (atomic_read(&nmi_active) <= 0)) return -ENODEV; diff --git a/arch/x86/oprofile/op_model_athlon.c b/arch/x86/oprofile/op_model_athlon.c index c3ee43333f26..3d534879a9dc 100644 --- a/arch/x86/oprofile/op_model_athlon.c +++ b/arch/x86/oprofile/op_model_athlon.c @@ -1,4 +1,4 @@ -/** +/* * @file op_model_athlon.h * athlon / K7 / K8 / Family 10h model-specific MSR operations * @@ -14,28 +14,28 @@ #include <asm/ptrace.h> #include <asm/msr.h> #include <asm/nmi.h> - + #include "op_x86_model.h" #include "op_counter.h" #define NUM_COUNTERS 4 #define NUM_CONTROLS 4 -#define CTR_IS_RESERVED(msrs,c) (msrs->counters[(c)].addr ? 1 : 0) -#define CTR_READ(l,h,msrs,c) do {rdmsr(msrs->counters[(c)].addr, (l), (h));} while (0) -#define CTR_WRITE(l,msrs,c) do {wrmsr(msrs->counters[(c)].addr, -(unsigned int)(l), -1);} while (0) +#define CTR_IS_RESERVED(msrs, c) (msrs->counters[(c)].addr ? 1 : 0) +#define CTR_READ(l, h, msrs, c) do {rdmsr(msrs->counters[(c)].addr, (l), (h)); } while (0) +#define CTR_WRITE(l, msrs, c) do {wrmsr(msrs->counters[(c)].addr, -(unsigned int)(l), -1); } while (0) #define CTR_OVERFLOWED(n) (!((n) & (1U<<31))) -#define CTRL_IS_RESERVED(msrs,c) (msrs->controls[(c)].addr ? 1 : 0) -#define CTRL_READ(l,h,msrs,c) do {rdmsr(msrs->controls[(c)].addr, (l), (h));} while (0) -#define CTRL_WRITE(l,h,msrs,c) do {wrmsr(msrs->controls[(c)].addr, (l), (h));} while (0) +#define CTRL_IS_RESERVED(msrs, c) (msrs->controls[(c)].addr ? 1 : 0) +#define CTRL_READ(l, h, msrs, c) do {rdmsr(msrs->controls[(c)].addr, (l), (h)); } while (0) +#define CTRL_WRITE(l, h, msrs, c) do {wrmsr(msrs->controls[(c)].addr, (l), (h)); } while (0) #define CTRL_SET_ACTIVE(n) (n |= (1<<22)) #define CTRL_SET_INACTIVE(n) (n &= ~(1<<22)) #define CTRL_CLEAR_LO(x) (x &= (1<<21)) #define CTRL_CLEAR_HI(x) (x &= 0xfffffcf0) #define CTRL_SET_ENABLE(val) (val |= 1<<20) -#define CTRL_SET_USR(val,u) (val |= ((u & 1) << 16)) -#define CTRL_SET_KERN(val,k) (val |= ((k & 1) << 17)) +#define CTRL_SET_USR(val, u) (val |= ((u & 1) << 16)) +#define CTRL_SET_KERN(val, k) (val |= ((k & 1) << 17)) #define CTRL_SET_UM(val, m) (val |= (m << 8)) #define CTRL_SET_EVENT_LOW(val, e) (val |= (e & 0xff)) #define CTRL_SET_EVENT_HIGH(val, e) (val |= ((e >> 8) & 0xf)) @@ -43,19 +43,19 @@ #define CTRL_SET_GUEST_ONLY(val, h) (val |= ((h & 1) << 8)) static unsigned long reset_value[NUM_COUNTERS]; - + static void athlon_fill_in_addresses(struct op_msrs * const msrs) { int i; - for (i=0; i < NUM_COUNTERS; i++) { + for (i = 0; i < NUM_COUNTERS; i++) { if (reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i)) msrs->counters[i].addr = MSR_K7_PERFCTR0 + i; else msrs->counters[i].addr = 0; } - for (i=0; i < NUM_CONTROLS; i++) { + for (i = 0; i < NUM_CONTROLS; i++) { if (reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i)) msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i; else @@ -63,15 +63,15 @@ static void athlon_fill_in_addresses(struct op_msrs * const msrs) } } - + static void athlon_setup_ctrs(struct op_msrs const * const msrs) { unsigned int low, high; int i; - + /* clear all counters */ for (i = 0 ; i < NUM_CONTROLS; ++i) { - if (unlikely(!CTRL_IS_RESERVED(msrs,i))) + if (unlikely(!CTRL_IS_RESERVED(msrs, i))) continue; CTRL_READ(low, high, msrs, i); CTRL_CLEAR_LO(low); @@ -81,14 +81,14 @@ static void athlon_setup_ctrs(struct op_msrs const * const msrs) /* avoid a false detection of ctr overflows in NMI handler */ for (i = 0; i < NUM_COUNTERS; ++i) { - if (unlikely(!CTR_IS_RESERVED(msrs,i))) + if (unlikely(!CTR_IS_RESERVED(msrs, i))) continue; CTR_WRITE(1, msrs, i); } /* enable active counters */ for (i = 0; i < NUM_COUNTERS; ++i) { - if ((counter_config[i].enabled) && (CTR_IS_RESERVED(msrs,i))) { + if ((counter_config[i].enabled) && (CTR_IS_RESERVED(msrs, i))) { reset_value[i] = counter_config[i].count; CTR_WRITE(counter_config[i].count, msrs, i); @@ -112,7 +112,7 @@ static void athlon_setup_ctrs(struct op_msrs const * const msrs) } } - + static int athlon_check_ctrs(struct pt_regs * const regs, struct op_msrs const * const msrs) { @@ -133,7 +133,7 @@ static int athlon_check_ctrs(struct pt_regs * const regs, return 1; } - + static void athlon_start(struct op_msrs const * const msrs) { unsigned int low, high; @@ -150,7 +150,7 @@ static void athlon_start(struct op_msrs const * const msrs) static void athlon_stop(struct op_msrs const * const msrs) { - unsigned int low,high; + unsigned int low, high; int i; /* Subtle: stop on all counters to avoid race with @@ -169,11 +169,11 @@ static void athlon_shutdown(struct op_msrs const * const msrs) int i; for (i = 0 ; i < NUM_COUNTERS ; ++i) { - if (CTR_IS_RESERVED(msrs,i)) + if (CTR_IS_RESERVED(msrs, i)) release_perfctr_nmi(MSR_K7_PERFCTR0 + i); } for (i = 0 ; i < NUM_CONTROLS ; ++i) { - if (CTRL_IS_RESERVED(msrs,i)) + if (CTRL_IS_RESERVED(msrs, i)) release_evntsel_nmi(MSR_K7_EVNTSEL0 + i); } } diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c index c554f52cb808..eff431f6c57b 100644 --- a/arch/x86/oprofile/op_model_ppro.c +++ b/arch/x86/oprofile/op_model_ppro.c @@ -1,4 +1,4 @@ -/** +/* * @file op_model_ppro.h * pentium pro / P6 model-specific MSR operations * @@ -15,45 +15,45 @@ #include <asm/msr.h> #include <asm/apic.h> #include <asm/nmi.h> - + #include "op_x86_model.h" #include "op_counter.h" #define NUM_COUNTERS 2 #define NUM_CONTROLS 2 -#define CTR_IS_RESERVED(msrs,c) (msrs->counters[(c)].addr ? 1 : 0) -#define CTR_READ(l,h,msrs,c) do {rdmsr(msrs->counters[(c)].addr, (l), (h));} while (0) -#define CTR_32BIT_WRITE(l,msrs,c) \ - do {wrmsr(msrs->counters[(c)].addr, -(u32)(l), 0);} while (0) +#define CTR_IS_RESERVED(msrs, c) (msrs->counters[(c)].addr ? 1 : 0) +#define CTR_READ(l, h, msrs, c) do {rdmsr(msrs->counters[(c)].addr, (l), (h)); } while (0) +#define CTR_32BIT_WRITE(l, msrs, c) \ + do {wrmsr(msrs->counters[(c)].addr, -(u32)(l), 0); } while (0) #define CTR_OVERFLOWED(n) (!((n) & (1U<<31))) -#define CTRL_IS_RESERVED(msrs,c) (msrs->controls[(c)].addr ? 1 : 0) -#define CTRL_READ(l,h,msrs,c) do {rdmsr((msrs->controls[(c)].addr), (l), (h));} while (0) -#define CTRL_WRITE(l,h,msrs,c) do {wrmsr((msrs->controls[(c)].addr), (l), (h));} while (0) +#define CTRL_IS_RESERVED(msrs, c) (msrs->controls[(c)].addr ? 1 : 0) +#define CTRL_READ(l, h, msrs, c) do {rdmsr((msrs->controls[(c)].addr), (l), (h)); } while (0) +#define CTRL_WRITE(l, h, msrs, c) do {wrmsr((msrs->controls[(c)].addr), (l), (h)); } while (0) #define CTRL_SET_ACTIVE(n) (n |= (1<<22)) #define CTRL_SET_INACTIVE(n) (n &= ~(1<<22)) #define CTRL_CLEAR(x) (x &= (1<<21)) #define CTRL_SET_ENABLE(val) (val |= 1<<20) -#define CTRL_SET_USR(val,u) (val |= ((u & 1) << 16)) -#define CTRL_SET_KERN(val,k) (val |= ((k & 1) << 17)) +#define CTRL_SET_USR(val, u) (val |= ((u & 1) << 16)) +#define CTRL_SET_KERN(val, k) (val |= ((k & 1) << 17)) #define CTRL_SET_UM(val, m) (val |= (m << 8)) #define CTRL_SET_EVENT(val, e) (val |= e) static unsigned long reset_value[NUM_COUNTERS]; - + static void ppro_fill_in_addresses(struct op_msrs * const msrs) { int i; - for (i=0; i < NUM_COUNTERS; i++) { + for (i = 0; i < NUM_COUNTERS; i++) { if (reserve_perfctr_nmi(MSR_P6_PERFCTR0 + i)) msrs->counters[i].addr = MSR_P6_PERFCTR0 + i; else msrs->counters[i].addr = 0; } - - for (i=0; i < NUM_CONTROLS; i++) { + + for (i = 0; i < NUM_CONTROLS; i++) { if (reserve_evntsel_nmi(MSR_P6_EVNTSEL0 + i)) msrs->controls[i].addr = MSR_P6_EVNTSEL0 + i; else @@ -69,23 +69,23 @@ static void ppro_setup_ctrs(struct op_msrs const * const msrs) /* clear all counters */ for (i = 0 ; i < NUM_CONTROLS; ++i) { - if (unlikely(!CTRL_IS_RESERVED(msrs,i))) + if (unlikely(!CTRL_IS_RESERVED(msrs, i))) continue; CTRL_READ(low, high, msrs, i); CTRL_CLEAR(low); CTRL_WRITE(low, high, msrs, i); } - + /* avoid a false detection of ctr overflows in NMI handler */ for (i = 0; i < NUM_COUNTERS; ++i) { - if (unlikely(!CTR_IS_RESERVED(msrs,i))) + if (unlikely(!CTR_IS_RESERVED(msrs, i))) continue; CTR_32BIT_WRITE(1, msrs, i); } /* enable active counters */ for (i = 0; i < NUM_COUNTERS; ++i) { - if ((counter_config[i].enabled) && (CTR_IS_RESERVED(msrs,i))) { + if ((counter_config[i].enabled) && (CTR_IS_RESERVED(msrs, i))) { reset_value[i] = counter_config[i].count; CTR_32BIT_WRITE(counter_config[i].count, msrs, i); @@ -104,13 +104,13 @@ static void ppro_setup_ctrs(struct op_msrs const * const msrs) } } - + static int ppro_check_ctrs(struct pt_regs * const regs, struct op_msrs const * const msrs) { unsigned int low, high; int i; - + for (i = 0 ; i < NUM_COUNTERS; ++i) { if (!reset_value[i]) continue; @@ -135,10 +135,10 @@ static int ppro_check_ctrs(struct pt_regs * const regs, return 1; } - + static void ppro_start(struct op_msrs const * const msrs) { - unsigned int low,high; + unsigned int low, high; int i; for (i = 0; i < NUM_COUNTERS; ++i) { @@ -153,7 +153,7 @@ static void ppro_start(struct op_msrs const * const msrs) static void ppro_stop(struct op_msrs const * const msrs) { - unsigned int low,high; + unsigned int low, high; int i; for (i = 0; i < NUM_COUNTERS; ++i) { @@ -170,11 +170,11 @@ static void ppro_shutdown(struct op_msrs const * const msrs) int i; for (i = 0 ; i < NUM_COUNTERS ; ++i) { - if (CTR_IS_RESERVED(msrs,i)) + if (CTR_IS_RESERVED(msrs, i)) release_perfctr_nmi(MSR_P6_PERFCTR0 + i); } for (i = 0 ; i < NUM_CONTROLS ; ++i) { - if (CTRL_IS_RESERVED(msrs,i)) + if (CTRL_IS_RESERVED(msrs, i)) release_evntsel_nmi(MSR_P6_EVNTSEL0 + i); } } diff --git a/arch/x86/pci/Makefile_32 b/arch/x86/pci/Makefile_32 index cdd6828b5abb..7fa519868d70 100644 --- a/arch/x86/pci/Makefile_32 +++ b/arch/x86/pci/Makefile_32 @@ -3,12 +3,14 @@ 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-$(CONFIG_PCI_OLPC) += olpc.o pci-y := fixup.o pci-$(CONFIG_ACPI) += acpi.o pci-y += legacy.o irq.o -pci-$(CONFIG_X86_VISWS) := visws.o fixup.o -pci-$(CONFIG_X86_NUMAQ) := numa.o irq.o +pci-$(CONFIG_X86_VISWS) += visws.o fixup.o +pci-$(CONFIG_X86_NUMAQ) += numa.o irq.o +pci-$(CONFIG_NUMA) += mp_bus_to_node.o obj-y += $(pci-y) common.o early.o diff --git a/arch/x86/pci/Makefile_64 b/arch/x86/pci/Makefile_64 index 7d8c467bf143..8fbd19832cf6 100644 --- a/arch/x86/pci/Makefile_64 +++ b/arch/x86/pci/Makefile_64 @@ -13,5 +13,5 @@ obj-y += legacy.o irq.o common.o early.o # mmconfig has a 64bit special obj-$(CONFIG_PCI_MMCONFIG) += mmconfig_64.o direct.o mmconfig-shared.o -obj-$(CONFIG_NUMA) += k8-bus_64.o +obj-y += k8-bus_64.o diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 378136fb5044..1a9c0c6a1a18 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -151,7 +151,7 @@ adjust_transparent_bridge_resources(struct pci_bus *bus) static void get_current_resources(struct acpi_device *device, int busnum, - struct pci_bus *bus) + int domain, struct pci_bus *bus) { struct pci_root_info info; size_t size; @@ -168,10 +168,10 @@ get_current_resources(struct acpi_device *device, int busnum, if (!info.res) goto res_alloc_fail; - info.name = kmalloc(12, GFP_KERNEL); + info.name = kmalloc(16, GFP_KERNEL); if (!info.name) goto name_alloc_fail; - sprintf(info.name, "PCI Bus #%02x", busnum); + sprintf(info.name, "PCI Bus %04x:%02x", domain, busnum); info.res_num = 0; acpi_walk_resources(device->handle, METHOD_NAME__CRS, setup_resource, @@ -191,7 +191,10 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do { struct pci_bus *bus; struct pci_sysdata *sd; + int node; +#ifdef CONFIG_ACPI_NUMA int pxm; +#endif dmi_check_system(acpi_pciprobe_dmi_table); @@ -201,6 +204,17 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do return NULL; } + node = -1; +#ifdef CONFIG_ACPI_NUMA + pxm = acpi_get_pxm(device->handle); + if (pxm >= 0) + node = pxm_to_node(pxm); + if (node != -1) + set_mp_bus_to_node(busnum, node); + else + node = get_mp_bus_to_node(busnum); +#endif + /* Allocate per-root-bus (not per bus) arch-specific data. * TODO: leak; this memory is never freed. * It's arguable whether it's worth the trouble to care. @@ -212,13 +226,7 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do } sd->domain = domain; - sd->node = -1; - - pxm = acpi_get_pxm(device->handle); -#ifdef CONFIG_ACPI_NUMA - if (pxm >= 0) - sd->node = pxm_to_node(pxm); -#endif + sd->node = node; /* * Maybe the desired pci bus has been already scanned. In such case * it is unnecessary to scan the pci bus with the given domain,busnum. @@ -238,17 +246,16 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do kfree(sd); #ifdef CONFIG_ACPI_NUMA - if (bus != NULL) { + if (bus) { if (pxm >= 0) { - printk("bus %d -> pxm %d -> node %d\n", + printk(KERN_DEBUG "bus %02x -> pxm %d -> node %d\n", busnum, pxm, pxm_to_node(pxm)); } } #endif if (bus && (pci_probe & PCI_USE__CRS)) - get_current_resources(device, busnum, bus); - + get_current_resources(device, busnum, domain, bus); return bus; } @@ -278,8 +285,7 @@ static int __init pci_acpi_init(void) printk(KERN_INFO "PCI: Routing PCI interrupts for all devices because \"pci=routeirq\" specified\n"); for_each_pci_dev(dev) acpi_pci_irq_enable(dev); - } else - printk(KERN_INFO "PCI: If a device doesn't work, try \"pci=routeirq\". If it helps, post a report\n"); + } #ifdef CONFIG_X86_IO_APIC if (acpi_ioapic) diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 7b6e3bb9b28c..2a4d751818b7 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -77,59 +77,6 @@ int pcibios_scanned; */ DEFINE_SPINLOCK(pci_config_lock); -/* - * Several buggy motherboards address only 16 devices and mirror - * them to next 16 IDs. We try to detect this `feature' on all - * primary buses (those containing host bridges as they are - * expected to be unique) and remove the ghost devices. - */ - -static void __devinit pcibios_fixup_ghosts(struct pci_bus *b) -{ - struct list_head *ln, *mn; - struct pci_dev *d, *e; - int mirror = PCI_DEVFN(16,0); - int seen_host_bridge = 0; - int i; - - DBG("PCI: Scanning for ghost devices on bus %d\n", b->number); - list_for_each(ln, &b->devices) { - d = pci_dev_b(ln); - if ((d->class >> 8) == PCI_CLASS_BRIDGE_HOST) - seen_host_bridge++; - for (mn=ln->next; mn != &b->devices; mn=mn->next) { - e = pci_dev_b(mn); - if (e->devfn != d->devfn + mirror || - e->vendor != d->vendor || - e->device != d->device || - e->class != d->class) - continue; - for(i=0; i<PCI_NUM_RESOURCES; i++) - if (e->resource[i].start != d->resource[i].start || - e->resource[i].end != d->resource[i].end || - e->resource[i].flags != d->resource[i].flags) - continue; - break; - } - if (mn == &b->devices) - return; - } - if (!seen_host_bridge) - return; - printk(KERN_WARNING "PCI: Ignoring ghost devices on bus %02x\n", b->number); - - ln = &b->devices; - while (ln->next != &b->devices) { - d = pci_dev_b(ln->next); - if (d->devfn >= mirror) { - list_del(&d->global_list); - list_del(&d->bus_list); - kfree(d); - } else - ln = ln->next; - } -} - static void __devinit pcibios_fixup_device_resources(struct pci_dev *dev) { struct resource *rom_r = &dev->resource[PCI_ROM_RESOURCE]; @@ -152,7 +99,6 @@ void __devinit pcibios_fixup_bus(struct pci_bus *b) { struct pci_dev *dev; - pcibios_fixup_ghosts(b); pci_read_bridge_bases(b); list_for_each_entry(dev, &b->devices, bus_list) pcibios_fixup_device_resources(dev); @@ -396,9 +342,14 @@ struct pci_bus * __devinit pcibios_scan_root(int busnum) return NULL; } + sd->node = get_mp_bus_to_node(busnum); + printk(KERN_DEBUG "PCI: Probing PCI hardware (bus %02x)\n", busnum); + bus = pci_scan_bus_parented(NULL, busnum, &pci_root_ops, sd); + if (!bus) + kfree(sd); - return pci_scan_bus_parented(NULL, busnum, &pci_root_ops, sd); + return bus; } extern u8 pci_cache_line_size; @@ -427,10 +378,6 @@ static int __init pcibios_init(void) if (pci_bf_sort >= pci_force_bf) pci_sort_breadthfirst(); -#ifdef CONFIG_PCI_BIOS - if ((pci_probe & PCI_BIOS_SORT) && !(pci_probe & PCI_NO_SORT)) - pcibios_sort(); -#endif return 0; } @@ -455,9 +402,6 @@ char * __devinit pcibios_setup(char *str) } else if (!strcmp(str, "nobios")) { pci_probe &= ~PCI_PROBE_BIOS; return NULL; - } else if (!strcmp(str, "nosort")) { - pci_probe |= PCI_NO_SORT; - return NULL; } else if (!strcmp(str, "biosirq")) { pci_probe |= PCI_BIOS_IRQ_SCAN; return NULL; @@ -481,6 +425,10 @@ char * __devinit pcibios_setup(char *str) pci_probe &= ~PCI_PROBE_MMCONF; return NULL; } + else if (!strcmp(str, "check_enable_amd_mmconf")) { + pci_probe |= PCI_CHECK_ENABLE_AMD_MMCONF; + return NULL; + } #endif else if (!strcmp(str, "noacpi")) { acpi_noirq_set(); @@ -527,7 +475,7 @@ int pcibios_enable_device(struct pci_dev *dev, int mask) { int err; - if ((err = pcibios_enable_resources(dev, mask)) < 0) + if ((err = pci_enable_resources(dev, mask)) < 0) return err; if (!dev->msi_enabled) @@ -541,7 +489,7 @@ void pcibios_disable_device (struct pci_dev *dev) pcibios_disable_irq(dev); } -struct pci_bus *__devinit pci_scan_bus_with_sysdata(int busno) +struct pci_bus *pci_scan_bus_on_node(int busno, struct pci_ops *ops, int node) { struct pci_bus *bus = NULL; struct pci_sysdata *sd; @@ -556,10 +504,15 @@ struct pci_bus *__devinit pci_scan_bus_with_sysdata(int busno) printk(KERN_ERR "PCI: OOM, skipping PCI bus %02x\n", busno); return NULL; } - sd->node = -1; - bus = pci_scan_bus(busno, &pci_root_ops, sd); + sd->node = node; + bus = pci_scan_bus(busno, ops, sd); if (!bus) kfree(sd); return bus; } + +struct pci_bus *pci_scan_bus_with_sysdata(int busno) +{ + return pci_scan_bus_on_node(busno, &pci_root_ops, -1); +} diff --git a/arch/x86/pci/direct.c b/arch/x86/pci/direct.c index 42f3e4cad179..21d1e0e0d535 100644 --- a/arch/x86/pci/direct.c +++ b/arch/x86/pci/direct.c @@ -258,7 +258,8 @@ void __init pci_direct_init(int type) { if (type == 0) return; - printk(KERN_INFO "PCI: Using configuration type %d\n", type); + printk(KERN_INFO "PCI: Using configuration type %d for base access\n", + type); if (type == 1) raw_pci_ops = &pci_direct_conf1; else @@ -275,8 +276,10 @@ int __init pci_direct_probe(void) if (!region) goto type2; - if (pci_check_type1()) + if (pci_check_type1()) { + raw_pci_ops = &pci_direct_conf1; return 1; + } release_resource(region); type2: @@ -290,7 +293,6 @@ int __init pci_direct_probe(void) goto fail2; if (pci_check_type2()) { - printk(KERN_INFO "PCI: Using configuration type 2\n"); raw_pci_ops = &pci_direct_conf2; return 2; } diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index a5ef5f551373..b60b2abd480c 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -493,3 +493,20 @@ static void __devinit pci_siemens_interrupt_controller(struct pci_dev *dev) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SIEMENS, 0x0015, pci_siemens_interrupt_controller); + +/* + * Regular PCI devices have 256 bytes, but AMD Family 10h Opteron ext config + * have 4096 bytes. Even if the device is capable, that doesn't mean we can + * access it. Maybe we don't have a way to generate extended config space + * accesses. So check it + */ +static void fam10h_pci_cfg_space_size(struct pci_dev *dev) +{ + dev->cfg_size = pci_cfg_space_size_ext(dev, 0); +} + +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1200, fam10h_pci_cfg_space_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1201, fam10h_pci_cfg_space_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1202, fam10h_pci_cfg_space_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1203, fam10h_pci_cfg_space_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1204, fam10h_pci_cfg_space_size); diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 103b9dff1213..8af0f0bae2af 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -30,6 +30,9 @@ #include <linux/init.h> #include <linux/ioport.h> #include <linux/errno.h> +#include <linux/bootmem.h> + +#include <asm/pat.h> #include "pci.h" @@ -238,44 +241,6 @@ void __init pcibios_resource_survey(void) */ fs_initcall(pcibios_assign_resources); -int pcibios_enable_resources(struct pci_dev *dev, int mask) -{ - u16 cmd, old_cmd; - int idx; - struct resource *r; - - pci_read_config_word(dev, PCI_COMMAND, &cmd); - old_cmd = cmd; - for (idx = 0; idx < PCI_NUM_RESOURCES; idx++) { - /* Only set up the requested stuff */ - if (!(mask & (1 << idx))) - continue; - - r = &dev->resource[idx]; - if (!(r->flags & (IORESOURCE_IO | IORESOURCE_MEM))) - continue; - if ((idx == PCI_ROM_RESOURCE) && - (!(r->flags & IORESOURCE_ROM_ENABLE))) - continue; - if (!r->start && r->end) { - printk(KERN_ERR "PCI: Device %s not available " - "because of resource %d collisions\n", - pci_name(dev), idx); - return -EINVAL; - } - if (r->flags & IORESOURCE_IO) - cmd |= PCI_COMMAND_IO; - if (r->flags & IORESOURCE_MEM) - cmd |= PCI_COMMAND_MEMORY; - } - if (cmd != old_cmd) { - printk("PCI: Enabling device %s (%04x -> %04x)\n", - pci_name(dev), old_cmd, cmd); - pci_write_config_word(dev, PCI_COMMAND, cmd); - } - return 0; -} - /* * If we set up a device for bus mastering, we need to check the latency * timer as certain crappy BIOSes forget to set it properly. @@ -297,10 +262,35 @@ void pcibios_set_master(struct pci_dev *dev) pci_write_config_byte(dev, PCI_LATENCY_TIMER, lat); } +static void pci_unmap_page_range(struct vm_area_struct *vma) +{ + u64 addr = (u64)vma->vm_pgoff << PAGE_SHIFT; + free_memtype(addr, addr + vma->vm_end - vma->vm_start); +} + +static void pci_track_mmap_page_range(struct vm_area_struct *vma) +{ + u64 addr = (u64)vma->vm_pgoff << PAGE_SHIFT; + unsigned long flags = pgprot_val(vma->vm_page_prot) + & _PAGE_CACHE_MASK; + + reserve_memtype(addr, addr + vma->vm_end - vma->vm_start, flags, NULL); +} + +static struct vm_operations_struct pci_mmap_ops = { + .open = pci_track_mmap_page_range, + .close = pci_unmap_page_range, +}; + int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, enum pci_mmap_state mmap_state, int write_combine) { unsigned long prot; + u64 addr = vma->vm_pgoff << PAGE_SHIFT; + unsigned long len = vma->vm_end - vma->vm_start; + unsigned long flags; + unsigned long new_flags; + int retval; /* I/O space cannot be accessed via normal processor loads and * stores on this platform. @@ -308,21 +298,56 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, if (mmap_state == pci_mmap_io) return -EINVAL; - /* Leave vm_pgoff as-is, the PCI space address is the physical - * address on this platform. - */ prot = pgprot_val(vma->vm_page_prot); - if (boot_cpu_data.x86 > 3) - prot |= _PAGE_PCD | _PAGE_PWT; + if (pat_wc_enabled && write_combine) + prot |= _PAGE_CACHE_WC; + else if (pat_wc_enabled) + /* + * ioremap() and ioremap_nocache() defaults to UC MINUS for now. + * To avoid attribute conflicts, request UC MINUS here + * aswell. + */ + prot |= _PAGE_CACHE_UC_MINUS; + else if (boot_cpu_data.x86 > 3) + prot |= _PAGE_CACHE_UC; + vma->vm_page_prot = __pgprot(prot); - /* Write-combine setting is ignored, it is changed via the mtrr - * interfaces on this platform. - */ + flags = pgprot_val(vma->vm_page_prot) & _PAGE_CACHE_MASK; + retval = reserve_memtype(addr, addr + len, flags, &new_flags); + if (retval) + return retval; + + if (flags != new_flags) { + /* + * Do not fallback to certain memory types with certain + * requested type: + * - request is uncached, return cannot be write-back + * - request is uncached, return cannot be write-combine + * - request is write-combine, return cannot be write-back + */ + if ((flags == _PAGE_CACHE_UC_MINUS && + (new_flags == _PAGE_CACHE_WB)) || + (flags == _PAGE_CACHE_WC && + new_flags == _PAGE_CACHE_WB)) { + free_memtype(addr, addr+len); + return -EINVAL; + } + flags = new_flags; + } + + if (vma->vm_pgoff <= max_pfn_mapped && + ioremap_change_attr((unsigned long)__va(addr), len, flags)) { + free_memtype(addr, addr + len); + return -EINVAL; + } + if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, vma->vm_end - vma->vm_start, vma->vm_page_prot)) return -EAGAIN; + vma->vm_ops = &pci_mmap_ops; + return 0; } diff --git a/arch/x86/pci/init.c b/arch/x86/pci/init.c index 3de9f9ba2da6..dd30c6076b5d 100644 --- a/arch/x86/pci/init.c +++ b/arch/x86/pci/init.c @@ -6,16 +6,17 @@ in the right sequence from here. */ static __init int pci_access_init(void) { - int type __maybe_unused = 0; - #ifdef CONFIG_PCI_DIRECT + int type = 0; + type = pci_direct_probe(); #endif -#ifdef CONFIG_PCI_MMCONFIG - pci_mmcfg_init(type); + + pci_mmcfg_early_init(); + +#ifdef CONFIG_PCI_OLPC + pci_olpc_init(); #endif - if (raw_pci_ops) - return 0; #ifdef CONFIG_PCI_BIOS pci_pcbios_init(); #endif @@ -28,7 +29,7 @@ static __init int pci_access_init(void) #ifdef CONFIG_PCI_DIRECT pci_direct_init(type); #endif - if (!raw_pci_ops) + if (!raw_pci_ops && !raw_pci_ext_ops) printk(KERN_ERR "PCI: Fatal: No config space access function found\n"); diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index a8715861877e..0908fca901bf 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -136,9 +136,11 @@ static void __init pirq_peer_trick(void) busmap[e->bus] = 1; } for(i = 1; i < 256; i++) { + int node; if (!busmap[i] || pci_find_bus(0, i)) continue; - if (pci_scan_bus_with_sysdata(i)) + node = get_mp_bus_to_node(i); + if (pci_scan_bus_on_node(i, &pci_root_ops, node)) printk(KERN_INFO "PCI: Discovered primary peer " "bus %02x [IRQ]\n", i); } @@ -200,7 +202,7 @@ static int pirq_ali_get(struct pci_dev *router, struct pci_dev *dev, int pirq) { static const unsigned char irqmap[16] = { 0, 9, 3, 10, 4, 5, 7, 6, 1, 11, 0, 12, 0, 14, 0, 15 }; - WARN_ON_ONCE(pirq >= 16); + WARN_ON_ONCE(pirq > 16); return irqmap[read_config_nybble(router, 0x48, pirq-1)]; } @@ -209,7 +211,7 @@ static int pirq_ali_set(struct pci_dev *router, struct pci_dev *dev, int pirq, i static const unsigned char irqmap[16] = { 0, 8, 0, 2, 4, 5, 7, 6, 0, 1, 3, 9, 11, 0, 13, 15 }; unsigned int val = irqmap[irq]; - WARN_ON_ONCE(pirq >= 16); + WARN_ON_ONCE(pirq > 16); if (val) { write_config_nybble(router, 0x48, pirq-1, val); return 1; @@ -260,7 +262,7 @@ static int pirq_via586_get(struct pci_dev *router, struct pci_dev *dev, int pirq { static const unsigned int pirqmap[5] = { 3, 2, 5, 1, 1 }; - WARN_ON_ONCE(pirq >= 5); + WARN_ON_ONCE(pirq > 5); return read_config_nybble(router, 0x55, pirqmap[pirq-1]); } @@ -268,7 +270,7 @@ static int pirq_via586_set(struct pci_dev *router, struct pci_dev *dev, int pirq { static const unsigned int pirqmap[5] = { 3, 2, 5, 1, 1 }; - WARN_ON_ONCE(pirq >= 5); + WARN_ON_ONCE(pirq > 5); write_config_nybble(router, 0x55, pirqmap[pirq-1], irq); return 1; } @@ -282,7 +284,7 @@ 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); + WARN_ON_ONCE(pirq > 4); return read_config_nybble(router,0x43, pirqmap[pirq-1]); } @@ -290,7 +292,7 @@ static int pirq_ite_set(struct pci_dev *router, struct pci_dev *dev, int pirq, i { static const unsigned char pirqmap[4] = { 1, 0, 2, 3 }; - WARN_ON_ONCE(pirq >= 4); + WARN_ON_ONCE(pirq > 4); write_config_nybble(router, 0x43, pirqmap[pirq-1], irq); return 1; } diff --git a/arch/x86/pci/k8-bus_64.c b/arch/x86/pci/k8-bus_64.c index 9cc813e29706..ab6d4b18a88f 100644 --- a/arch/x86/pci/k8-bus_64.c +++ b/arch/x86/pci/k8-bus_64.c @@ -1,83 +1,536 @@ #include <linux/init.h> #include <linux/pci.h> +#include <asm/pci-direct.h> #include <asm/mpspec.h> #include <linux/cpumask.h> +#include <linux/topology.h> /* * This discovers the pcibus <-> node mapping on AMD K8. - * - * RED-PEN need to call this again on PCI hotplug - * RED-PEN empty cpus get reported wrong + * also get peer root bus resource for io,mmio */ -#define NODE_ID_REGISTER 0x60 -#define NODE_ID(dword) (dword & 0x07) -#define LDT_BUS_NUMBER_REGISTER_0 0x94 -#define LDT_BUS_NUMBER_REGISTER_1 0xB4 -#define LDT_BUS_NUMBER_REGISTER_2 0xD4 -#define NR_LDT_BUS_NUMBER_REGISTERS 3 -#define SECONDARY_LDT_BUS_NUMBER(dword) ((dword >> 8) & 0xFF) -#define SUBORDINATE_LDT_BUS_NUMBER(dword) ((dword >> 16) & 0xFF) -#define PCI_DEVICE_ID_K8HTCONFIG 0x1100 + +/* + * 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 + +static int 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] = node; +} + +int get_mp_bus_to_node(int busnum) +{ + int node = -1; + + if (busnum < 0 || busnum > (BUS_NR - 1)) + return node; + + node = mp_bus_to_node[busnum]; + + /* + * let numa_node_id to decide it later in dma_alloc_pages + * if there is no ram on that node + */ + if (node != -1 && !node_online(node)) + node = -1; + + return node; +} +#endif + +void set_pci_bus_resources_arch_default(struct pci_bus *b) +{ + int i; + int j; + struct pci_root_info *info; + + /* if only one root bus, don't need to anything */ + if (pci_root_num < 2) + return; + + for (i = 0; i < pci_root_num; i++) { + if (pci_root_info[i].bus_min == b->number) + break; + } + + if (i == pci_root_num) + return; + + info = &pci_root_info[i]; + for (j = 0; j < info->res_num; j++) { + struct resource *res; + struct resource *root; + + res = &info->res[j]; + b->resource[j] = res; + if (res->flags & IORESOURCE_IO) + root = &ioport_resource; + else + root = &iomem_resource; + insert_resource(root, res); + } +} + +#define RANGE_NUM 16 + +struct res_range { + size_t start; + size_t end; +}; + +static void __init update_range(struct res_range *range, size_t start, + size_t end) +{ + int i; + int 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 void __init update_res(struct pci_root_info *info, size_t start, + size_t end, unsigned long flags, int merge) +{ + int i; + struct resource *res; + + if (!merge) + goto addit; + + /* try to merge it with old one */ + for (i = 0; i < info->res_num; i++) { + size_t final_start, final_end; + size_t common_start, common_end; + + res = &info->res[i]; + if (res->flags != flags) + continue; + + common_start = max((size_t)res->start, start); + common_end = min((size_t)res->end, end); + if (common_start > common_end + 1) + continue; + + final_start = min((size_t)res->start, start); + final_end = max((size_t)res->end, end); + + res->start = final_start; + res->end = final_end; + return; + } + +addit: + + /* need to add that */ + if (info->res_num >= RES_NUM) + return; + + res = &info->res[info->res_num]; + res->name = info->name; + res->flags = flags; + res->start = start; + res->end = end; + res->child = NULL; + info->res_num++; +} + +struct pci_hostbridge_probe { + u32 bus; + u32 slot; + u32 vendor; + u32 device; +}; + +static struct pci_hostbridge_probe pci_probes[] __initdata = { + { 0, 0x18, PCI_VENDOR_ID_AMD, 0x1100 }, + { 0, 0x18, PCI_VENDOR_ID_AMD, 0x1200 }, + { 0xff, 0, PCI_VENDOR_ID_AMD, 0x1200 }, + { 0, 0x18, PCI_VENDOR_ID_AMD, 0x1300 }, +}; + +static u64 __initdata fam10h_mmconf_start; +static u64 __initdata fam10h_mmconf_end; +static void __init get_pci_mmcfg_amd_fam10h_range(void) +{ + u32 address; + u64 base, msr; + unsigned segn_busn_bits; + + /* assume all cpus from fam10h have mmconf */ + if (boot_cpu_data.x86 < 0x10) + return; + + address = MSR_FAM10H_MMIO_CONF_BASE; + rdmsrl(address, msr); + + /* mmconfig is not enable */ + if (!(msr & FAM10H_MMIO_CONF_ENABLE)) + return; + + base = msr & (FAM10H_MMIO_CONF_BASE_MASK<<FAM10H_MMIO_CONF_BASE_SHIFT); + + segn_busn_bits = (msr >> FAM10H_MMIO_CONF_BUSRANGE_SHIFT) & + FAM10H_MMIO_CONF_BUSRANGE_MASK; + + fam10h_mmconf_start = base; + fam10h_mmconf_end = base + (1ULL<<(segn_busn_bits + 20)) - 1; +} /** - * fill_mp_bus_to_cpumask() + * early_fill_mp_bus_to_node() + * called before pcibios_scan_root and pci_scan_bus * fills the mp_bus_to_cpumask array based according to the LDT Bus Number * Registers found in the K8 northbridge */ -__init static int -fill_mp_bus_to_cpumask(void) +static int __init early_fill_mp_bus_info(void) { - struct pci_dev *nb_dev = NULL; - int i, j; - u32 ldtbus, nid; - static int lbnr[3] = { - LDT_BUS_NUMBER_REGISTER_0, - LDT_BUS_NUMBER_REGISTER_1, - LDT_BUS_NUMBER_REGISTER_2 - }; - - while ((nb_dev = pci_get_device(PCI_VENDOR_ID_AMD, - PCI_DEVICE_ID_K8HTCONFIG, nb_dev))) { - pci_read_config_dword(nb_dev, NODE_ID_REGISTER, &nid); - - for (i = 0; i < NR_LDT_BUS_NUMBER_REGISTERS; i++) { - pci_read_config_dword(nb_dev, lbnr[i], &ldtbus); - /* - * if there are no busses hanging off of the current - * ldt link then both the secondary and subordinate - * bus number fields are set to 0. - * - * RED-PEN - * This is slightly broken because it assumes - * HT node IDs == Linux node ids, which is not always - * true. However it is probably mostly true. - */ - if (!(SECONDARY_LDT_BUS_NUMBER(ldtbus) == 0 - && SUBORDINATE_LDT_BUS_NUMBER(ldtbus) == 0)) { - for (j = SECONDARY_LDT_BUS_NUMBER(ldtbus); - j <= SUBORDINATE_LDT_BUS_NUMBER(ldtbus); - j++) { - struct pci_bus *bus; - struct pci_sysdata *sd; - - long node = NODE_ID(nid); - /* Algorithm a bit dumb, but - it shouldn't matter here */ - bus = pci_find_bus(0, j); - if (!bus) - continue; - if (!node_online(node)) - node = 0; - - sd = bus->sysdata; - sd->node = node; - } + int i; + int j; + unsigned bus; + unsigned slot; + int found; + int node; + int link; + int def_node; + int def_link; + struct pci_root_info *info; + u32 reg; + struct resource *res; + size_t start; + size_t end; + struct res_range range[RANGE_NUM]; + u64 val; + u32 address; + +#ifdef CONFIG_NUMA + for (i = 0; i < BUS_NR; i++) + mp_bus_to_node[i] = -1; +#endif + + if (!early_pci_allowed()) + return -1; + + found = 0; + for (i = 0; i < ARRAY_SIZE(pci_probes); i++) { + u32 id; + u16 device; + u16 vendor; + + bus = pci_probes[i].bus; + slot = pci_probes[i].slot; + id = read_pci_config(bus, slot, 0, PCI_VENDOR_ID); + + vendor = id & 0xffff; + device = (id>>16) & 0xffff; + if (pci_probes[i].vendor == vendor && + pci_probes[i].device == device) { + found = 1; + break; + } + } + + if (!found) + return 0; + + pci_root_num = 0; + for (i = 0; i < 4; i++) { + int min_bus; + int max_bus; + reg = read_pci_config(bus, slot, 1, 0xe0 + (i << 2)); + + /* Check if that register is enabled for bus range */ + if ((reg & 7) != 3) + continue; + + min_bus = (reg >> 16) & 0xff; + max_bus = (reg >> 24) & 0xff; + node = (reg >> 4) & 0x07; +#ifdef CONFIG_NUMA + for (j = min_bus; j <= max_bus; j++) + mp_bus_to_node[j] = (unsigned char) node; +#endif + link = (reg >> 8) & 0x03; + + info = &pci_root_info[pci_root_num]; + info->bus_min = min_bus; + info->bus_max = max_bus; + info->node = node; + info->link = link; + sprintf(info->name, "PCI Bus #%02x", min_bus); + pci_root_num++; + } + + /* get the default node and link for left over res */ + reg = read_pci_config(bus, slot, 0, 0x60); + def_node = (reg >> 8) & 0x07; + reg = read_pci_config(bus, slot, 0, 0x64); + def_link = (reg >> 8) & 0x03; + + memset(range, 0, sizeof(range)); + range[0].end = 0xffff; + /* io port resource */ + for (i = 0; i < 4; i++) { + reg = read_pci_config(bus, slot, 1, 0xc0 + (i << 3)); + if (!(reg & 3)) + continue; + + start = reg & 0xfff000; + reg = read_pci_config(bus, slot, 1, 0xc4 + (i << 3)); + node = reg & 0x07; + link = (reg >> 4) & 0x03; + end = (reg & 0xfff000) | 0xfff; + + /* find the position */ + for (j = 0; j < pci_root_num; j++) { + info = &pci_root_info[j]; + if (info->node == node && info->link == link) + break; + } + if (j == pci_root_num) + continue; /* not found */ + + info = &pci_root_info[j]; + printk(KERN_DEBUG "node %d link %d: io port [%llx, %llx]\n", + node, link, (u64)start, (u64)end); + + /* kernel only handle 16 bit only */ + if (end > 0xffff) + end = 0xffff; + update_res(info, start, end, IORESOURCE_IO, 1); + update_range(range, start, end); + } + /* add left over io port range to def node/link, [0, 0xffff] */ + /* find the position */ + for (j = 0; j < pci_root_num; j++) { + info = &pci_root_info[j]; + if (info->node == def_node && info->link == def_link) + break; + } + if (j < pci_root_num) { + info = &pci_root_info[j]; + for (i = 0; i < RANGE_NUM; i++) { + if (!range[i].end) + continue; + + update_res(info, range[i].start, range[i].end, + IORESOURCE_IO, 1); + } + } + + memset(range, 0, sizeof(range)); + /* 0xfd00000000-0xffffffffff for HT */ + range[0].end = (0xfdULL<<32) - 1; + + /* need to take out [0, TOM) for RAM*/ + address = MSR_K8_TOP_MEM1; + rdmsrl(address, val); + end = (val & 0xffffff8000000ULL); + printk(KERN_INFO "TOM: %016lx aka %ldM\n", end, end>>20); + if (end < (1ULL<<32)) + update_range(range, 0, end - 1); + + /* get mmconfig */ + get_pci_mmcfg_amd_fam10h_range(); + /* need to take out mmconf range */ + if (fam10h_mmconf_end) { + printk(KERN_DEBUG "Fam 10h mmconf [%llx, %llx]\n", fam10h_mmconf_start, fam10h_mmconf_end); + update_range(range, fam10h_mmconf_start, fam10h_mmconf_end); + } + + /* mmio resource */ + for (i = 0; i < 8; i++) { + reg = read_pci_config(bus, slot, 1, 0x80 + (i << 3)); + if (!(reg & 3)) + continue; + + start = reg & 0xffffff00; /* 39:16 on 31:8*/ + start <<= 8; + reg = read_pci_config(bus, slot, 1, 0x84 + (i << 3)); + node = reg & 0x07; + link = (reg >> 4) & 0x03; + end = (reg & 0xffffff00); + end <<= 8; + end |= 0xffff; + + /* find the position */ + for (j = 0; j < pci_root_num; j++) { + info = &pci_root_info[j]; + if (info->node == node && info->link == link) + break; + } + if (j == pci_root_num) + continue; /* not found */ + + info = &pci_root_info[j]; + + printk(KERN_DEBUG "node %d link %d: mmio [%llx, %llx]", + node, link, (u64)start, (u64)end); + /* + * some sick allocation would have range overlap with fam10h + * mmconf range, so need to update start and end. + */ + if (fam10h_mmconf_end) { + int changed = 0; + u64 endx = 0; + if (start >= fam10h_mmconf_start && + start <= fam10h_mmconf_end) { + start = fam10h_mmconf_end + 1; + changed = 1; + } + + if (end >= fam10h_mmconf_start && + end <= fam10h_mmconf_end) { + end = fam10h_mmconf_start - 1; + changed = 1; + } + + if (start < fam10h_mmconf_start && + end > fam10h_mmconf_end) { + /* we got a hole */ + endx = fam10h_mmconf_start - 1; + update_res(info, start, endx, IORESOURCE_MEM, 0); + update_range(range, start, endx); + printk(KERN_CONT " ==> [%llx, %llx]", (u64)start, endx); + start = fam10h_mmconf_end + 1; + changed = 1; + } + if (changed) { + if (start <= end) { + printk(KERN_CONT " %s [%llx, %llx]", endx?"and":"==>", (u64)start, (u64)end); + } else { + printk(KERN_CONT "%s\n", endx?"":" ==> none"); + continue; + } } } + + update_res(info, start, end, IORESOURCE_MEM, 1); + update_range(range, start, end); + printk(KERN_CONT "\n"); + } + + /* need to take out [4G, TOM2) for RAM*/ + /* SYS_CFG */ + address = MSR_K8_SYSCFG; + rdmsrl(address, val); + /* TOP_MEM2 is enabled? */ + if (val & (1<<21)) { + /* TOP_MEM2 */ + address = MSR_K8_TOP_MEM2; + rdmsrl(address, val); + end = (val & 0xffffff8000000ULL); + printk(KERN_INFO "TOM2: %016lx aka %ldM\n", end, end>>20); + update_range(range, 1ULL<<32, end - 1); + } + + /* + * add left over mmio range to def node/link ? + * that is tricky, just record range in from start_min to 4G + */ + for (j = 0; j < pci_root_num; j++) { + info = &pci_root_info[j]; + if (info->node == def_node && info->link == def_link) + break; + } + if (j < pci_root_num) { + info = &pci_root_info[j]; + + for (i = 0; i < RANGE_NUM; i++) { + if (!range[i].end) + continue; + + update_res(info, range[i].start, range[i].end, + IORESOURCE_MEM, 1); + } + } + +#ifdef CONFIG_NUMA + for (i = 0; i < BUS_NR; i++) { + node = mp_bus_to_node[i]; + if (node >= 0) + printk(KERN_DEBUG "bus: %02x to node: %02x\n", i, node); + } +#endif + + for (i = 0; i < pci_root_num; i++) { + int res_num; + int busnum; + + info = &pci_root_info[i]; + res_num = info->res_num; + busnum = info->bus_min; + printk(KERN_DEBUG "bus: [%02x,%02x] on node %x link %x\n", + info->bus_min, info->bus_max, info->node, info->link); + for (j = 0; j < res_num; j++) { + res = &info->res[j]; + printk(KERN_DEBUG "bus: %02x index %x %s: [%llx, %llx]\n", + busnum, j, + (res->flags & IORESOURCE_IO)?"io port":"mmio", + res->start, res->end); + } } return 0; } -fs_initcall(fill_mp_bus_to_cpumask); +postcore_initcall(early_fill_mp_bus_info); diff --git a/arch/x86/pci/legacy.c b/arch/x86/pci/legacy.c index e041ced0ce13..a67921ce60af 100644 --- a/arch/x86/pci/legacy.c +++ b/arch/x86/pci/legacy.c @@ -12,6 +12,7 @@ static void __devinit pcibios_fixup_peer_bridges(void) { int n, devfn; + long node; if (pcibios_last_bus <= 0 || pcibios_last_bus >= 0xff) return; @@ -21,12 +22,13 @@ static void __devinit pcibios_fixup_peer_bridges(void) u32 l; if (pci_find_bus(0, n)) continue; + node = get_mp_bus_to_node(n); for (devfn = 0; devfn < 256; devfn += 8) { if (!raw_pci_read(0, n, devfn, PCI_VENDOR_ID, 2, &l) && l != 0x0000 && l != 0xffff) { DBG("Found device at %02x:%02x [%04x]\n", n, devfn, l); printk(KERN_INFO "PCI: Discovered peer bus %02x\n", n); - pci_scan_bus_with_sysdata(n); + pci_scan_bus_on_node(n, &pci_root_ops, node); break; } } diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 8d54df4dfaad..0cfebecf2a8f 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -28,7 +28,7 @@ static int __initdata pci_mmcfg_resources_inserted; static const char __init *pci_mmcfg_e7520(void) { u32 win; - pci_direct_conf1.read(0, 0, PCI_DEVFN(0,0), 0xce, 2, &win); + raw_pci_ops->read(0, 0, PCI_DEVFN(0, 0), 0xce, 2, &win); win = win & 0xf000; if(win == 0x0000 || win == 0xf000) @@ -53,7 +53,7 @@ static const char __init *pci_mmcfg_intel_945(void) pci_mmcfg_config_num = 1; - pci_direct_conf1.read(0, 0, PCI_DEVFN(0,0), 0x48, 4, &pciexbar); + raw_pci_ops->read(0, 0, PCI_DEVFN(0, 0), 0x48, 4, &pciexbar); /* Enable bit */ if (!(pciexbar & 1)) @@ -100,33 +100,102 @@ static const char __init *pci_mmcfg_intel_945(void) return "Intel Corporation 945G/GZ/P/PL Express Memory Controller Hub"; } +static const char __init *pci_mmcfg_amd_fam10h(void) +{ + u32 low, high, address; + u64 base, msr; + int i; + unsigned segnbits = 0, busnbits; + + if (!(pci_probe & PCI_CHECK_ENABLE_AMD_MMCONF)) + return NULL; + + address = MSR_FAM10H_MMIO_CONF_BASE; + if (rdmsr_safe(address, &low, &high)) + return NULL; + + msr = high; + msr <<= 32; + msr |= low; + + /* mmconfig is not enable */ + if (!(msr & FAM10H_MMIO_CONF_ENABLE)) + return NULL; + + base = msr & (FAM10H_MMIO_CONF_BASE_MASK<<FAM10H_MMIO_CONF_BASE_SHIFT); + + busnbits = (msr >> FAM10H_MMIO_CONF_BUSRANGE_SHIFT) & + FAM10H_MMIO_CONF_BUSRANGE_MASK; + + /* + * only handle bus 0 ? + * need to skip it + */ + if (!busnbits) + return NULL; + + if (busnbits > 8) { + segnbits = busnbits - 8; + busnbits = 8; + } + + pci_mmcfg_config_num = (1 << segnbits); + pci_mmcfg_config = kzalloc(sizeof(pci_mmcfg_config[0]) * + pci_mmcfg_config_num, GFP_KERNEL); + if (!pci_mmcfg_config) + return NULL; + + for (i = 0; i < (1 << segnbits); i++) { + pci_mmcfg_config[i].address = base + (1<<28) * i; + pci_mmcfg_config[i].pci_segment = i; + pci_mmcfg_config[i].start_bus_number = 0; + pci_mmcfg_config[i].end_bus_number = (1 << busnbits) - 1; + } + + return "AMD Family 10h NB"; +} + struct pci_mmcfg_hostbridge_probe { + u32 bus; + u32 devfn; u32 vendor; u32 device; const char *(*probe)(void); }; static struct pci_mmcfg_hostbridge_probe pci_mmcfg_probes[] __initdata = { - { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E7520_MCH, pci_mmcfg_e7520 }, - { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82945G_HB, pci_mmcfg_intel_945 }, + { 0, PCI_DEVFN(0, 0), PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_E7520_MCH, pci_mmcfg_e7520 }, + { 0, PCI_DEVFN(0, 0), PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_82945G_HB, pci_mmcfg_intel_945 }, + { 0, PCI_DEVFN(0x18, 0), PCI_VENDOR_ID_AMD, + 0x1200, pci_mmcfg_amd_fam10h }, + { 0xff, PCI_DEVFN(0, 0), PCI_VENDOR_ID_AMD, + 0x1200, pci_mmcfg_amd_fam10h }, }; static int __init pci_mmcfg_check_hostbridge(void) { u32 l; + u32 bus, devfn; u16 vendor, device; int i; const char *name; - pci_direct_conf1.read(0, 0, PCI_DEVFN(0,0), 0, 4, &l); - vendor = l & 0xffff; - device = (l >> 16) & 0xffff; + if (!raw_pci_ops) + return 0; pci_mmcfg_config_num = 0; pci_mmcfg_config = NULL; name = NULL; for (i = 0; !name && i < ARRAY_SIZE(pci_mmcfg_probes); i++) { + bus = pci_mmcfg_probes[i].bus; + devfn = pci_mmcfg_probes[i].devfn; + raw_pci_ops->read(0, bus, devfn, 0, 4, &l); + vendor = l & 0xffff; + device = (l >> 16) & 0xffff; + if (pci_mmcfg_probes[i].vendor == vendor && pci_mmcfg_probes[i].device == device) name = pci_mmcfg_probes[i].probe(); @@ -173,9 +242,78 @@ static void __init pci_mmcfg_insert_resources(unsigned long resource_flags) pci_mmcfg_resources_inserted = 1; } -static void __init pci_mmcfg_reject_broken(int type) +static acpi_status __init check_mcfg_resource(struct acpi_resource *res, + void *data) +{ + struct resource *mcfg_res = data; + struct acpi_resource_address64 address; + acpi_status status; + + if (res->type == ACPI_RESOURCE_TYPE_FIXED_MEMORY32) { + struct acpi_resource_fixed_memory32 *fixmem32 = + &res->data.fixed_memory32; + if (!fixmem32) + return AE_OK; + if ((mcfg_res->start >= fixmem32->address) && + (mcfg_res->end < (fixmem32->address + + fixmem32->address_length))) { + mcfg_res->flags = 1; + return AE_CTRL_TERMINATE; + } + } + if ((res->type != ACPI_RESOURCE_TYPE_ADDRESS32) && + (res->type != ACPI_RESOURCE_TYPE_ADDRESS64)) + return AE_OK; + + status = acpi_resource_to_address64(res, &address); + if (ACPI_FAILURE(status) || + (address.address_length <= 0) || + (address.resource_type != ACPI_MEMORY_RANGE)) + return AE_OK; + + if ((mcfg_res->start >= address.minimum) && + (mcfg_res->end < (address.minimum + address.address_length))) { + mcfg_res->flags = 1; + return AE_CTRL_TERMINATE; + } + return AE_OK; +} + +static acpi_status __init find_mboard_resource(acpi_handle handle, u32 lvl, + void *context, void **rv) +{ + struct resource *mcfg_res = context; + + acpi_walk_resources(handle, METHOD_NAME__CRS, + check_mcfg_resource, context); + + if (mcfg_res->flags) + return AE_CTRL_TERMINATE; + + return AE_OK; +} + +static int __init is_acpi_reserved(unsigned long start, unsigned long end) +{ + struct resource mcfg_res; + + mcfg_res.start = start; + mcfg_res.end = end; + mcfg_res.flags = 0; + + acpi_get_devices("PNP0C01", find_mboard_resource, &mcfg_res, NULL); + + if (!mcfg_res.flags) + acpi_get_devices("PNP0C02", find_mboard_resource, &mcfg_res, + NULL); + + return mcfg_res.flags; +} + +static void __init pci_mmcfg_reject_broken(int early) { typeof(pci_mmcfg_config[0]) *cfg; + int i; if ((pci_mmcfg_config_num == 0) || (pci_mmcfg_config == NULL) || @@ -184,51 +322,80 @@ static void __init pci_mmcfg_reject_broken(int type) cfg = &pci_mmcfg_config[0]; - /* - * Handle more broken MCFG tables on Asus etc. - * They only contain a single entry for bus 0-0. - */ - if (pci_mmcfg_config_num == 1 && - cfg->pci_segment == 0 && - (cfg->start_bus_number | cfg->end_bus_number) == 0) { - printk(KERN_ERR "PCI: start and end of bus number is 0. " - "Rejected as broken MCFG.\n"); - goto reject; + for (i = 0; i < pci_mmcfg_config_num; i++) { + int valid = 0; + u32 size = (cfg->end_bus_number + 1) << 20; + cfg = &pci_mmcfg_config[i]; + printk(KERN_NOTICE "PCI: MCFG configuration %d: base %lx " + "segment %hu buses %u - %u\n", + i, (unsigned long)cfg->address, cfg->pci_segment, + (unsigned int)cfg->start_bus_number, + (unsigned int)cfg->end_bus_number); + + if (!early && + is_acpi_reserved(cfg->address, cfg->address + size - 1)) { + printk(KERN_NOTICE "PCI: MCFG area at %Lx reserved " + "in ACPI motherboard resources\n", + cfg->address); + valid = 1; + } + + if (valid) + continue; + + if (!early) + printk(KERN_ERR "PCI: BIOS Bug: MCFG area at %Lx is not" + " reserved in ACPI motherboard resources\n", + cfg->address); + /* Don't try to do this check unless configuration + type 1 is available. how about type 2 ?*/ + if (raw_pci_ops && e820_all_mapped(cfg->address, + cfg->address + size - 1, + E820_RESERVED)) { + printk(KERN_NOTICE + "PCI: MCFG area at %Lx reserved in E820\n", + cfg->address); + valid = 1; + } + + if (!valid) + goto reject; } - /* - * Only do this check when type 1 works. If it doesn't work - * assume we run on a Mac and always use MCFG - */ - if (type == 1 && !e820_all_mapped(cfg->address, - cfg->address + MMCONFIG_APER_MIN, - E820_RESERVED)) { - printk(KERN_ERR "PCI: BIOS Bug: MCFG area at %Lx is not" - " E820-reserved\n", cfg->address); - goto reject; - } return; reject: printk(KERN_ERR "PCI: Not using MMCONFIG.\n"); + pci_mmcfg_arch_free(); kfree(pci_mmcfg_config); pci_mmcfg_config = NULL; pci_mmcfg_config_num = 0; } -void __init pci_mmcfg_init(int type) -{ - int known_bridge = 0; +static int __initdata known_bridge; +void __init __pci_mmcfg_init(int early) +{ + /* MMCONFIG disabled */ if ((pci_probe & PCI_PROBE_MMCONF) == 0) return; - if (type == 1 && pci_mmcfg_check_hostbridge()) - known_bridge = 1; + /* MMCONFIG already enabled */ + if (!early && !(pci_probe & PCI_PROBE_MASK & ~PCI_PROBE_MMCONF)) + return; + + /* for late to exit */ + if (known_bridge) + return; + + if (early) { + if (pci_mmcfg_check_hostbridge()) + known_bridge = 1; + } if (!known_bridge) { acpi_table_parse(ACPI_SIG_MCFG, acpi_parse_mcfg); - pci_mmcfg_reject_broken(type); + pci_mmcfg_reject_broken(early); } if ((pci_mmcfg_config_num == 0) || @@ -249,6 +416,16 @@ void __init pci_mmcfg_init(int type) } } +void __init pci_mmcfg_early_init(void) +{ + __pci_mmcfg_init(1); +} + +void __init pci_mmcfg_late_init(void) +{ + __pci_mmcfg_init(0); +} + static int __init pci_mmcfg_late_insert_resources(void) { /* diff --git a/arch/x86/pci/mmconfig_32.c b/arch/x86/pci/mmconfig_32.c index 081816ada057..f3c761dce695 100644 --- a/arch/x86/pci/mmconfig_32.c +++ b/arch/x86/pci/mmconfig_32.c @@ -136,3 +136,7 @@ int __init pci_mmcfg_arch_init(void) raw_pci_ext_ops = &pci_mmcfg; return 1; } + +void __init pci_mmcfg_arch_free(void) +{ +} diff --git a/arch/x86/pci/mmconfig_64.c b/arch/x86/pci/mmconfig_64.c index 9207fd49233c..a1994163c99d 100644 --- a/arch/x86/pci/mmconfig_64.c +++ b/arch/x86/pci/mmconfig_64.c @@ -127,7 +127,7 @@ static void __iomem * __init mcfg_ioremap(struct acpi_mcfg_allocation *cfg) int __init pci_mmcfg_arch_init(void) { int i; - pci_mmcfg_virt = kmalloc(sizeof(*pci_mmcfg_virt) * + pci_mmcfg_virt = kzalloc(sizeof(*pci_mmcfg_virt) * pci_mmcfg_config_num, GFP_KERNEL); if (pci_mmcfg_virt == NULL) { printk(KERN_ERR "PCI: Can not allocate memory for mmconfig structures\n"); @@ -141,9 +141,29 @@ int __init pci_mmcfg_arch_init(void) printk(KERN_ERR "PCI: Cannot map mmconfig aperture for " "segment %d\n", pci_mmcfg_config[i].pci_segment); + pci_mmcfg_arch_free(); return 0; } } raw_pci_ext_ops = &pci_mmcfg; return 1; } + +void __init pci_mmcfg_arch_free(void) +{ + int i; + + if (pci_mmcfg_virt == NULL) + return; + + for (i = 0; i < pci_mmcfg_config_num; ++i) { + if (pci_mmcfg_virt[i].virt) { + iounmap(pci_mmcfg_virt[i].virt); + pci_mmcfg_virt[i].virt = NULL; + pci_mmcfg_virt[i].cfg = NULL; + } + } + + kfree(pci_mmcfg_virt); + pci_mmcfg_virt = NULL; +} diff --git a/arch/x86/pci/mp_bus_to_node.c b/arch/x86/pci/mp_bus_to_node.c new file mode 100644 index 000000000000..022943999b84 --- /dev/null +++ b/arch/x86/pci/mp_bus_to_node.c @@ -0,0 +1,23 @@ +#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 55270c26237c..d9afbae5092b 100644 --- a/arch/x86/pci/numa.c +++ b/arch/x86/pci/numa.c @@ -11,11 +11,41 @@ #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 -extern void *xquad_portio; /* Where the IO area was mapped */ #define XQUAD_PORT_ADDR(port, quad) (xquad_portio + (XQUAD_PORTIO_QUAD*quad) + port) #define PCI_CONF1_MQ_ADDRESS(bus, devfn, reg) \ diff --git a/arch/x86/pci/olpc.c b/arch/x86/pci/olpc.c new file mode 100644 index 000000000000..5e7636558c02 --- /dev/null +++ b/arch/x86/pci/olpc.c @@ -0,0 +1,313 @@ +/* + * Low-level PCI config space access for OLPC systems who lack the VSA + * PCI virtualization software. + * + * Copyright © 2006 Advanced Micro Devices, Inc. + * + * 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. + * + * The AMD Geode chipset (ie: GX2 processor, cs5536 I/O companion device) + * has some I/O functions (display, southbridge, sound, USB HCIs, etc) + * that more or less behave like PCI devices, but the hardware doesn't + * directly implement the PCI configuration space headers. AMD provides + * "VSA" (Virtual System Architecture) software that emulates PCI config + * space for these devices, by trapping I/O accesses to PCI config register + * (CF8/CFC) and running some code in System Management Mode interrupt state. + * On the OLPC platform, we don't want to use that VSA code because + * (a) it slows down suspend/resume, and (b) recompiling it requires special + * compilers that are hard to get. So instead of letting the complex VSA + * code simulate the PCI config registers for the on-chip devices, we + * just simulate them the easy way, by inserting the code into the + * pci_write_config and pci_read_config path. Most of the config registers + * are read-only anyway, so the bulk of the simulation is just table lookup. + */ + +#include <linux/pci.h> +#include <linux/init.h> +#include <asm/olpc.h> +#include <asm/geode.h> +#include "pci.h" + +/* + * In the tables below, the first two line (8 longwords) are the + * size masks that are used when the higher level PCI code determines + * the size of the region by writing ~0 to a base address register + * and reading back the result. + * + * The following lines are the values that are read during normal + * PCI config access cycles, i.e. not after just having written + * ~0 to a base address register. + */ + +static const uint32_t lxnb_hdr[] = { /* dev 1 function 0 - devfn = 8 */ + 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, + + 0x281022, 0x2200005, 0x6000021, 0x80f808, /* AMD Vendor ID */ + 0x0, 0x0, 0x0, 0x0, /* No virtual registers, hence no BAR */ + 0x0, 0x0, 0x0, 0x28100b, + 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, +}; + +static const uint32_t gxnb_hdr[] = { /* dev 1 function 0 - devfn = 8 */ + 0xfffffffd, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, + + 0x28100b, 0x2200005, 0x6000021, 0x80f808, /* NSC Vendor ID */ + 0xac1d, 0x0, 0x0, 0x0, /* I/O BAR - base of virtual registers */ + 0x0, 0x0, 0x0, 0x28100b, + 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, +}; + +static const uint32_t lxfb_hdr[] = { /* dev 1 function 1 - devfn = 9 */ + 0xff000008, 0xffffc000, 0xffffc000, 0xffffc000, + 0xffffc000, 0x0, 0x0, 0x0, + + 0x20811022, 0x2200003, 0x3000000, 0x0, /* AMD Vendor ID */ + 0xfd000000, 0xfe000000, 0xfe004000, 0xfe008000, /* FB, GP, VG, DF */ + 0xfe00c000, 0x0, 0x0, 0x30100b, /* VIP */ + 0x0, 0x0, 0x0, 0x10e, /* INTA, IRQ14 for graphics accel */ + 0x0, 0x0, 0x0, 0x0, + 0x3d0, 0x3c0, 0xa0000, 0x0, /* VG IO, VG IO, EGA FB, MONO FB */ + 0x0, 0x0, 0x0, 0x0, +}; + +static const uint32_t gxfb_hdr[] = { /* dev 1 function 1 - devfn = 9 */ + 0xff800008, 0xffffc000, 0xffffc000, 0xffffc000, + 0x0, 0x0, 0x0, 0x0, + + 0x30100b, 0x2200003, 0x3000000, 0x0, /* NSC Vendor ID */ + 0xfd000000, 0xfe000000, 0xfe004000, 0xfe008000, /* FB, GP, VG, DF */ + 0x0, 0x0, 0x0, 0x30100b, + 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, + 0x3d0, 0x3c0, 0xa0000, 0x0, /* VG IO, VG IO, EGA FB, MONO FB */ + 0x0, 0x0, 0x0, 0x0, +}; + +static const uint32_t aes_hdr[] = { /* dev 1 function 2 - devfn = 0xa */ + 0xffffc000, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, + + 0x20821022, 0x2a00006, 0x10100000, 0x8, /* NSC Vendor ID */ + 0xfe010000, 0x0, 0x0, 0x0, /* AES registers */ + 0x0, 0x0, 0x0, 0x20821022, + 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, +}; + + +static const uint32_t isa_hdr[] = { /* dev f function 0 - devfn = 78 */ + 0xfffffff9, 0xffffff01, 0xffffffc1, 0xffffffe1, + 0xffffff81, 0xffffffc1, 0x0, 0x0, + + 0x20901022, 0x2a00049, 0x6010003, 0x802000, + 0x18b1, 0x1001, 0x1801, 0x1881, /* SMB-8 GPIO-256 MFGPT-64 IRQ-32 */ + 0x1401, 0x1841, 0x0, 0x20901022, /* PMS-128 ACPI-64 */ + 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0xaa5b, /* IRQ steering */ + 0x0, 0x0, 0x0, 0x0, +}; + +static const uint32_t ac97_hdr[] = { /* dev f function 3 - devfn = 7b */ + 0xffffff81, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, + + 0x20931022, 0x2a00041, 0x4010001, 0x0, + 0x1481, 0x0, 0x0, 0x0, /* I/O BAR-128 */ + 0x0, 0x0, 0x0, 0x20931022, + 0x0, 0x0, 0x0, 0x205, /* IntB, IRQ5 */ + 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, +}; + +static const uint32_t ohci_hdr[] = { /* dev f function 4 - devfn = 7c */ + 0xfffff000, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, + + 0x20941022, 0x2300006, 0xc031002, 0x0, + 0xfe01a000, 0x0, 0x0, 0x0, /* MEMBAR-1000 */ + 0x0, 0x0, 0x0, 0x20941022, + 0x0, 0x40, 0x0, 0x40a, /* CapPtr INT-D, IRQA */ + 0xc8020001, 0x0, 0x0, 0x0, /* Capabilities - 40 is R/O, + 44 is mask 8103 (power control) */ + 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, +}; + +static const uint32_t ehci_hdr[] = { /* dev f function 4 - devfn = 7d */ + 0xfffff000, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, + + 0x20951022, 0x2300006, 0xc032002, 0x0, + 0xfe01b000, 0x0, 0x0, 0x0, /* MEMBAR-1000 */ + 0x0, 0x0, 0x0, 0x20951022, + 0x0, 0x40, 0x0, 0x40a, /* CapPtr INT-D, IRQA */ + 0xc8020001, 0x0, 0x0, 0x0, /* Capabilities - 40 is R/O, 44 is + mask 8103 (power control) */ +#if 0 + 0x1, 0x40080000, 0x0, 0x0, /* EECP - see EHCI spec section 2.1.7 */ +#endif + 0x01000001, 0x0, 0x0, 0x0, /* EECP - see EHCI spec section 2.1.7 */ + 0x2020, 0x0, 0x0, 0x0, /* (EHCI page 8) 60 SBRN (R/O), + 61 FLADJ (R/W), PORTWAKECAP */ +}; + +static uint32_t ff_loc = ~0; +static uint32_t zero_loc; +static int bar_probing; /* Set after a write of ~0 to a BAR */ +static int is_lx; + +#define NB_SLOT 0x1 /* Northbridge - GX chip - Device 1 */ +#define SB_SLOT 0xf /* Southbridge - CS5536 chip - Device F */ + +static int is_simulated(unsigned int bus, unsigned int devfn) +{ + return (!bus && ((PCI_SLOT(devfn) == NB_SLOT) || + (PCI_SLOT(devfn) == SB_SLOT))); +} + +static uint32_t *hdr_addr(const uint32_t *hdr, int reg) +{ + uint32_t addr; + + /* + * This is a little bit tricky. The header maps consist of + * 0x20 bytes of size masks, followed by 0x70 bytes of header data. + * In the normal case, when not probing a BAR's size, we want + * to access the header data, so we add 0x20 to the reg offset, + * thus skipping the size mask area. + * In the BAR probing case, we want to access the size mask for + * the BAR, so we subtract 0x10 (the config header offset for + * BAR0), and don't skip the size mask area. + */ + + addr = (uint32_t)hdr + reg + (bar_probing ? -0x10 : 0x20); + + bar_probing = 0; + return (uint32_t *)addr; +} + +static int pci_olpc_read(unsigned int seg, unsigned int bus, + unsigned int devfn, int reg, int len, uint32_t *value) +{ + uint32_t *addr; + + /* Use the hardware mechanism for non-simulated devices */ + if (!is_simulated(bus, devfn)) + return pci_direct_conf1.read(seg, bus, devfn, reg, len, value); + + /* + * No device has config registers past 0x70, so we save table space + * by not storing entries for the nonexistent registers + */ + if (reg >= 0x70) + addr = &zero_loc; + else { + switch (devfn) { + case 0x8: + addr = hdr_addr(is_lx ? lxnb_hdr : gxnb_hdr, reg); + break; + case 0x9: + addr = hdr_addr(is_lx ? lxfb_hdr : gxfb_hdr, reg); + break; + case 0xa: + addr = is_lx ? hdr_addr(aes_hdr, reg) : &ff_loc; + break; + case 0x78: + addr = hdr_addr(isa_hdr, reg); + break; + case 0x7b: + addr = hdr_addr(ac97_hdr, reg); + break; + case 0x7c: + addr = hdr_addr(ohci_hdr, reg); + break; + case 0x7d: + addr = hdr_addr(ehci_hdr, reg); + break; + default: + addr = &ff_loc; + break; + } + } + switch (len) { + case 1: + *value = *(uint8_t *)addr; + break; + case 2: + *value = *(uint16_t *)addr; + break; + case 4: + *value = *addr; + break; + default: + BUG(); + } + + return 0; +} + +static int pci_olpc_write(unsigned int seg, unsigned int bus, + unsigned int devfn, int reg, int len, uint32_t value) +{ + /* Use the hardware mechanism for non-simulated devices */ + if (!is_simulated(bus, devfn)) + return pci_direct_conf1.write(seg, bus, devfn, reg, len, value); + + /* XXX we may want to extend this to simulate EHCI power management */ + + /* + * Mostly we just discard writes, but if the write is a size probe + * (i.e. writing ~0 to a BAR), we remember it and arrange to return + * the appropriate size mask on the next read. This is cheating + * to some extent, because it depends on the fact that the next + * access after such a write will always be a read to the same BAR. + */ + + if ((reg >= 0x10) && (reg < 0x2c)) { + /* write is to a BAR */ + if (value == ~0) + bar_probing = 1; + } else { + /* + * No warning on writes to ROM BAR, CMD, LATENCY_TIMER, + * CACHE_LINE_SIZE, or PM registers. + */ + if ((reg != PCI_ROM_ADDRESS) && (reg != PCI_COMMAND_MASTER) && + (reg != PCI_LATENCY_TIMER) && + (reg != PCI_CACHE_LINE_SIZE) && (reg != 0x44)) + printk(KERN_WARNING "OLPC PCI: Config write to devfn" + " %x reg %x value %x\n", devfn, reg, value); + } + + return 0; +} + +static struct pci_raw_ops pci_olpc_conf = { + .read = pci_olpc_read, + .write = pci_olpc_write, +}; + +void __init pci_olpc_init(void) +{ + if (!machine_is_olpc() || olpc_has_vsa()) + return; + + printk(KERN_INFO "PCI: Using configuration type OLPC\n"); + raw_pci_ops = &pci_olpc_conf; + is_lx = is_geode_lx(); +} diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index 2f7109ac4c15..37472fc6f729 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -152,28 +152,6 @@ static int __devinit check_pcibios(void) return 0; } -static int __devinit pci_bios_find_device (unsigned short vendor, unsigned short device_id, - unsigned short index, unsigned char *bus, unsigned char *device_fn) -{ - unsigned short bx; - unsigned short ret; - - __asm__("lcall *(%%edi); cld\n\t" - "jc 1f\n\t" - "xor %%ah, %%ah\n" - "1:" - : "=b" (bx), - "=a" (ret) - : "1" (PCIBIOS_FIND_PCI_DEVICE), - "c" (device_id), - "d" (vendor), - "S" ((int) index), - "D" (&pci_indirect)); - *bus = (bx >> 8) & 0xff; - *device_fn = bx & 0xff; - return (int) (ret & 0xff00) >> 8; -} - static int pci_bios_read(unsigned int seg, unsigned int bus, unsigned int devfn, int reg, int len, u32 *value) { @@ -364,55 +342,6 @@ static struct pci_raw_ops * __devinit pci_find_bios(void) } /* - * Sort the device list according to PCI BIOS. Nasty hack, but since some - * fool forgot to define the `correct' device order in the PCI BIOS specs - * and we want to be (possibly bug-to-bug ;-]) compatible with older kernels - * which used BIOS ordering, we are bound to do this... - */ - -void __devinit pcibios_sort(void) -{ - LIST_HEAD(sorted_devices); - struct list_head *ln; - struct pci_dev *dev, *d; - int idx, found; - unsigned char bus, devfn; - - DBG("PCI: Sorting device list...\n"); - while (!list_empty(&pci_devices)) { - ln = pci_devices.next; - dev = pci_dev_g(ln); - idx = found = 0; - while (pci_bios_find_device(dev->vendor, dev->device, idx, &bus, &devfn) == PCIBIOS_SUCCESSFUL) { - idx++; - list_for_each(ln, &pci_devices) { - d = pci_dev_g(ln); - if (d->bus->number == bus && d->devfn == devfn) { - list_move_tail(&d->global_list, &sorted_devices); - if (d == dev) - found = 1; - break; - } - } - if (ln == &pci_devices) { - printk(KERN_WARNING "PCI: BIOS reporting unknown device %02x:%02x\n", bus, devfn); - /* - * We must not continue scanning as several buggy BIOSes - * return garbage after the last device. Grr. - */ - break; - } - } - if (!found) { - printk(KERN_WARNING "PCI: Device %s not found by BIOS\n", - pci_name(dev)); - list_move_tail(&dev->global_list, &sorted_devices); - } - } - list_splice(&sorted_devices, &pci_devices); -} - -/* * BIOS Functions for IRQ Routing */ @@ -495,7 +424,6 @@ void __init pci_pcbios_init(void) { if ((pci_probe & PCI_PROBE_BIOS) && ((raw_pci_ops = pci_find_bios()))) { - pci_probe |= PCI_BIOS_SORT; pci_bios_present = 1; } } diff --git a/arch/x86/pci/pci.h b/arch/x86/pci/pci.h index 3431518d921a..c58805a92db5 100644 --- a/arch/x86/pci/pci.h +++ b/arch/x86/pci/pci.h @@ -19,8 +19,6 @@ #define PCI_PROBE_MASK 0x000f #define PCI_PROBE_NOEARLY 0x0010 -#define PCI_NO_SORT 0x0100 -#define PCI_BIOS_SORT 0x0200 #define PCI_NO_CHECKS 0x0400 #define PCI_USE_PIRQ_MASK 0x0800 #define PCI_ASSIGN_ROMS 0x1000 @@ -28,6 +26,7 @@ #define PCI_ASSIGN_ALL_BUSSES 0x4000 #define PCI_CAN_SKIP_ISA_ALIGN 0x8000 #define PCI_USE__CRS 0x10000 +#define PCI_CHECK_ENABLE_AMD_MMCONF 0x20000 extern unsigned int pci_probe; extern unsigned long pirq_table_addr; @@ -44,7 +43,6 @@ enum pci_bf_sort_state { extern unsigned int pcibios_max_latency; void pcibios_resource_survey(void); -int pcibios_enable_resources(struct pci_dev *, int); /* pci-pc.c */ @@ -100,12 +98,12 @@ extern struct pci_raw_ops pci_direct_conf1; extern int pci_direct_probe(void); extern void pci_direct_init(int type); extern void pci_pcbios_init(void); -extern void pci_mmcfg_init(int type); -extern void pcibios_sort(void); +extern void pci_olpc_init(void); /* pci-mmconfig.c */ extern int __init pci_mmcfg_arch_init(void); +extern void __init pci_mmcfg_arch_free(void); /* * AMD Fam10h CPUs are buggy, and cannot access MMIO config space diff --git a/arch/x86/power/cpu_32.c b/arch/x86/power/cpu_32.c index 7f9c6da04a4c..7dc5d5cf50a2 100644 --- a/arch/x86/power/cpu_32.c +++ b/arch/x86/power/cpu_32.c @@ -27,17 +27,17 @@ static void __save_processor_state(struct saved_context *ctxt) /* * descriptor tables */ - store_gdt(&ctxt->gdt); - store_idt(&ctxt->idt); - store_tr(ctxt->tr); + store_gdt(&ctxt->gdt); + store_idt(&ctxt->idt); + store_tr(ctxt->tr); /* * segment registers */ - savesegment(es, ctxt->es); - savesegment(fs, ctxt->fs); - savesegment(gs, ctxt->gs); - savesegment(ss, ctxt->ss); + savesegment(es, ctxt->es); + savesegment(fs, ctxt->fs); + savesegment(gs, ctxt->gs); + savesegment(ss, ctxt->ss); /* * control registers @@ -48,10 +48,12 @@ static void __save_processor_state(struct saved_context *ctxt) ctxt->cr4 = read_cr4(); } +/* Needed by apm.c */ void save_processor_state(void) { __save_processor_state(&saved_context); } +EXPORT_SYMBOL(save_processor_state); static void do_fpu_end(void) { @@ -64,9 +66,14 @@ static void do_fpu_end(void) static void fix_processor_context(void) { int cpu = smp_processor_id(); - struct tss_struct * t = &per_cpu(init_tss, cpu); + struct tss_struct *t = &per_cpu(init_tss, cpu); - set_tss_desc(cpu,t); /* This just modifies memory; should not be necessary. But... This is necessary, because 386 hardware has concept of busy TSS or some similar stupidity. */ + set_tss_desc(cpu, t); /* + * This just modifies memory; should not be + * necessary. But... This is necessary, because + * 386 hardware has concept of busy TSS or some + * similar stupidity. + */ load_TR_desc(); /* This does ltr */ load_LDT(¤t->active_mm->context); /* This does lldt */ @@ -100,16 +107,16 @@ static void __restore_processor_state(struct saved_context *ctxt) * now restore the descriptor tables to their proper values * ltr is done i fix_processor_context(). */ - load_gdt(&ctxt->gdt); - load_idt(&ctxt->idt); + load_gdt(&ctxt->gdt); + load_idt(&ctxt->idt); /* * segment registers */ - loadsegment(es, ctxt->es); - loadsegment(fs, ctxt->fs); - loadsegment(gs, ctxt->gs); - loadsegment(ss, ctxt->ss); + loadsegment(es, ctxt->es); + loadsegment(fs, ctxt->fs); + loadsegment(gs, ctxt->gs); + loadsegment(ss, ctxt->ss); /* * sysenter MSRs @@ -123,11 +130,9 @@ static void __restore_processor_state(struct saved_context *ctxt) mcheck_init(&boot_cpu_data); } +/* Needed by apm.c */ void restore_processor_state(void) { __restore_processor_state(&saved_context); } - -/* Needed by apm.c */ -EXPORT_SYMBOL(save_processor_state); EXPORT_SYMBOL(restore_processor_state); diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index 0a8f4742ef51..b7ad9f89d21f 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -37,9 +37,10 @@ $(obj)/%.so: OBJCOPYFLAGS := -S $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) -CFL := $(PROFILING) -mcmodel=small -fPIC -g0 -O2 -fasynchronous-unwind-tables -m64 +CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \ + $(filter -g%,$(KBUILD_CFLAGS)) -$(vobjs): KBUILD_CFLAGS = $(CFL) +$(vobjs): KBUILD_CFLAGS += $(CFL) targets += vdso-syms.lds obj-$(VDSO64-y) += vdso-syms.lds diff --git a/arch/x86/vdso/vdso.S b/arch/x86/vdso/vdso.S index 4b1620a1529e..1d3aa6b87181 100644 --- a/arch/x86/vdso/vdso.S +++ b/arch/x86/vdso/vdso.S @@ -1,2 +1,10 @@ - .section ".vdso","a" +#include <linux/init.h> + +__INITDATA + + .globl vdso_start, vdso_end +vdso_start: .incbin "arch/x86/vdso/vdso.so" +vdso_end: + +__FINIT diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c index 348f1341e1c8..4dceeb1fc5e0 100644 --- a/arch/x86/vdso/vdso32-setup.c +++ b/arch/x86/vdso/vdso32-setup.c @@ -210,8 +210,12 @@ static int use_sysenter __read_mostly = -1; /* May not be __init: called during resume */ void syscall32_cpu_init(void) { - if (use_sysenter < 0) - use_sysenter = (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL); + 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. */ @@ -299,8 +303,6 @@ int __init sysenter_setup(void) #ifdef CONFIG_X86_32 gate_vma_init(); - - printk("Compat vDSO mapped to %08lx.\n", __fix_to_virt(FIX_VDSO)); #endif if (!vdso32_sysenter()) { @@ -325,6 +327,9 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int exstack) int ret = 0; bool compat; + if (vdso_enabled == VDSO_DISABLED) + return 0; + down_write(&mm->mmap_sem); /* Test compat mode once here, in case someone diff --git a/arch/x86/video/fbdev.c b/arch/x86/video/fbdev.c index 48fb38d7d2c0..4db42bff8c60 100644 --- a/arch/x86/video/fbdev.c +++ b/arch/x86/video/fbdev.c @@ -1,5 +1,4 @@ /* - * arch/i386/video/fbdev.c - i386 Framebuffer * * Copyright (C) 2007 Antonino Daplas <adaplas@gmail.com> * diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 4d5f2649bee4..2e641be2737e 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -6,7 +6,7 @@ config XEN bool "Xen guest support" select PARAVIRT depends on X86_32 - depends on X86_CMPXCHG && X86_TSC && !NEED_MULTIPLE_NODES && !(X86_VISWS || X86_VOYAGER) + depends on X86_CMPXCHG && X86_TSC && !(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 diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 343df246bd3e..3d8df981d5fd 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -1,4 +1,4 @@ -obj-y := enlighten.o setup.o features.o multicalls.o mmu.o \ - events.o time.o manage.o xen-asm.o +obj-y := enlighten.o setup.o multicalls.o mmu.o \ + time.o manage.o xen-asm.o grant-table.o obj-$(CONFIG_SMP) += smp.o diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 27ee26aedf94..c8a56e457d61 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -25,6 +25,7 @@ #include <linux/mm.h> #include <linux/page-flags.h> #include <linux/highmem.h> +#include <linux/console.h> #include <xen/interface/xen.h> #include <xen/interface/physdev.h> @@ -154,7 +155,8 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, if (*ax == 1) maskedx = ~((1 << X86_FEATURE_APIC) | /* disable APIC */ (1 << X86_FEATURE_ACPI) | /* disable ACPI */ - (1 << X86_FEATURE_SEP) | /* disable SEP */ + (1 << X86_FEATURE_MCE) | /* disable MCE */ + (1 << X86_FEATURE_MCA) | /* disable MCA */ (1 << X86_FEATURE_ACC)); /* thermal monitoring */ asm(XEN_EMULATE_PREFIX "cpuid" @@ -530,26 +532,37 @@ static void xen_apic_write(unsigned long reg, u32 val) static void xen_flush_tlb(void) { struct mmuext_op *op; - struct multicall_space mcs = xen_mc_entry(sizeof(*op)); + struct multicall_space mcs; + + preempt_disable(); + + mcs = xen_mc_entry(sizeof(*op)); op = mcs.args; op->cmd = MMUEXT_TLB_FLUSH_LOCAL; MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF); xen_mc_issue(PARAVIRT_LAZY_MMU); + + preempt_enable(); } static void xen_flush_tlb_single(unsigned long addr) { struct mmuext_op *op; - struct multicall_space mcs = xen_mc_entry(sizeof(*op)); + struct multicall_space mcs; + + preempt_disable(); + mcs = xen_mc_entry(sizeof(*op)); op = mcs.args; op->cmd = MMUEXT_INVLPG_LOCAL; op->arg1.linear_addr = addr & PAGE_MASK; MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF); xen_mc_issue(PARAVIRT_LAZY_MMU); + + preempt_enable(); } static void xen_flush_tlb_others(const cpumask_t *cpus, struct mm_struct *mm, @@ -654,15 +667,17 @@ static void xen_write_cr3(unsigned long cr3) /* Early in boot, while setting up the initial pagetable, assume everything is pinned. */ -static __init void xen_alloc_pt_init(struct mm_struct *mm, u32 pfn) +static __init void xen_alloc_pte_init(struct mm_struct *mm, u32 pfn) { +#ifdef CONFIG_FLATMEM BUG_ON(mem_map); /* should only be used early */ +#endif make_lowmem_page_readonly(__va(PFN_PHYS(pfn))); } -/* Early release_pt assumes that all pts are pinned, since there's +/* Early release_pte assumes that all pts are pinned, since there's only init_mm and anything attached to that is pinned. */ -static void xen_release_pt_init(u32 pfn) +static void xen_release_pte_init(u32 pfn) { make_lowmem_page_readwrite(__va(PFN_PHYS(pfn))); } @@ -696,12 +711,12 @@ static void xen_alloc_ptpage(struct mm_struct *mm, u32 pfn, unsigned level) } } -static void xen_alloc_pt(struct mm_struct *mm, u32 pfn) +static void xen_alloc_pte(struct mm_struct *mm, u32 pfn) { xen_alloc_ptpage(mm, pfn, PT_PTE); } -static void xen_alloc_pd(struct mm_struct *mm, u32 pfn) +static void xen_alloc_pmd(struct mm_struct *mm, u32 pfn) { xen_alloc_ptpage(mm, pfn, PT_PMD); } @@ -721,12 +736,12 @@ static void xen_release_ptpage(u32 pfn, unsigned level) } } -static void xen_release_pt(u32 pfn) +static void xen_release_pte(u32 pfn) { xen_release_ptpage(pfn, PT_PTE); } -static void xen_release_pd(u32 pfn) +static void xen_release_pmd(u32 pfn) { xen_release_ptpage(pfn, PT_PMD); } @@ -848,10 +863,10 @@ static __init void xen_pagetable_setup_done(pgd_t *base) { /* This will work as long as patching hasn't happened yet (which it hasn't) */ - pv_mmu_ops.alloc_pt = xen_alloc_pt; - pv_mmu_ops.alloc_pd = xen_alloc_pd; - pv_mmu_ops.release_pt = xen_release_pt; - pv_mmu_ops.release_pd = xen_release_pd; + pv_mmu_ops.alloc_pte = xen_alloc_pte; + pv_mmu_ops.alloc_pmd = xen_alloc_pmd; + pv_mmu_ops.release_pte = xen_release_pte; + pv_mmu_ops.release_pmd = xen_release_pmd; pv_mmu_ops.set_pte = xen_set_pte; setup_shared_info(); @@ -889,7 +904,6 @@ void __init xen_setup_vcpu_info_placement(void) pv_irq_ops.irq_disable = xen_irq_disable_direct; pv_irq_ops.irq_enable = xen_irq_enable_direct; pv_mmu_ops.read_cr2 = xen_read_cr2_direct; - pv_cpu_ops.iret = xen_iret_direct; } } @@ -993,8 +1007,8 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = { .read_tsc = native_read_tsc, .read_pmc = native_read_pmc, - .iret = (void *)&hypercall_page[__HYPERVISOR_iret], - .irq_enable_syscall_ret = NULL, /* never called */ + .iret = xen_iret, + .irq_enable_syscall_ret = xen_sysexit, .load_tr_desc = paravirt_nop, .set_ldt = xen_set_ldt, @@ -1059,11 +1073,11 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = { .pte_update = paravirt_nop, .pte_update_defer = paravirt_nop, - .alloc_pt = xen_alloc_pt_init, - .release_pt = xen_release_pt_init, - .alloc_pd = xen_alloc_pt_init, - .alloc_pd_clone = paravirt_nop, - .release_pd = xen_release_pt_init, + .alloc_pte = xen_alloc_pte_init, + .release_pte = xen_release_pte_init, + .alloc_pmd = xen_alloc_pte_init, + .alloc_pmd_clone = paravirt_nop, + .release_pmd = xen_release_pte_init, #ifdef CONFIG_HIGHPTE .kmap_atomic_pte = xen_kmap_atomic_pte, @@ -1228,6 +1242,9 @@ 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()) + add_preferred_console("hvc", 0, NULL); + /* Start the world */ start_kernel(); } diff --git a/arch/x86/xen/events.c b/arch/x86/xen/events.c deleted file mode 100644 index dcf613e17581..000000000000 --- a/arch/x86/xen/events.c +++ /dev/null @@ -1,591 +0,0 @@ -/* - * Xen event channels - * - * Xen models interrupts with abstract event channels. Because each - * domain gets 1024 event channels, but NR_IRQ is not that large, we - * must dynamically map irqs<->event channels. The event channels - * interface with the rest of the kernel by defining a xen interrupt - * chip. When an event is recieved, it is mapped to an irq and sent - * through the normal interrupt processing path. - * - * There are four kinds of events which can be mapped to an event - * channel: - * - * 1. Inter-domain notifications. This includes all the virtual - * device events, since they're driven by front-ends in another domain - * (typically dom0). - * 2. VIRQs, typically used for timers. These are per-cpu events. - * 3. IPIs. - * 4. Hardware interrupts. Not supported at present. - * - * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007 - */ - -#include <linux/linkage.h> -#include <linux/interrupt.h> -#include <linux/irq.h> -#include <linux/module.h> -#include <linux/string.h> - -#include <asm/ptrace.h> -#include <asm/irq.h> -#include <asm/sync_bitops.h> -#include <asm/xen/hypercall.h> -#include <asm/xen/hypervisor.h> - -#include <xen/events.h> -#include <xen/interface/xen.h> -#include <xen/interface/event_channel.h> - -#include "xen-ops.h" - -/* - * This lock protects updates to the following mapping and reference-count - * arrays. The lock does not need to be acquired to read the mapping tables. - */ -static DEFINE_SPINLOCK(irq_mapping_update_lock); - -/* IRQ <-> VIRQ mapping. */ -static DEFINE_PER_CPU(int, virq_to_irq[NR_VIRQS]) = {[0 ... NR_VIRQS-1] = -1}; - -/* IRQ <-> IPI mapping */ -static DEFINE_PER_CPU(int, ipi_to_irq[XEN_NR_IPIS]) = {[0 ... XEN_NR_IPIS-1] = -1}; - -/* Packed IRQ information: binding type, sub-type index, and event channel. */ -struct packed_irq -{ - unsigned short evtchn; - unsigned char index; - unsigned char type; -}; - -static struct packed_irq irq_info[NR_IRQS]; - -/* Binding types. */ -enum { - IRQT_UNBOUND, - IRQT_PIRQ, - IRQT_VIRQ, - IRQT_IPI, - IRQT_EVTCHN -}; - -/* Convenient shorthand for packed representation of an unbound IRQ. */ -#define IRQ_UNBOUND mk_irq_info(IRQT_UNBOUND, 0, 0) - -static int evtchn_to_irq[NR_EVENT_CHANNELS] = { - [0 ... NR_EVENT_CHANNELS-1] = -1 -}; -static unsigned long cpu_evtchn_mask[NR_CPUS][NR_EVENT_CHANNELS/BITS_PER_LONG]; -static u8 cpu_evtchn[NR_EVENT_CHANNELS]; - -/* Reference counts for bindings to IRQs. */ -static int irq_bindcount[NR_IRQS]; - -/* Xen will never allocate port zero for any purpose. */ -#define VALID_EVTCHN(chn) ((chn) != 0) - -/* - * Force a proper event-channel callback from Xen after clearing the - * callback mask. We do this in a very simple manner, by making a call - * down into Xen. The pending flag will be checked by Xen on return. - */ -void force_evtchn_callback(void) -{ - (void)HYPERVISOR_xen_version(0, NULL); -} -EXPORT_SYMBOL_GPL(force_evtchn_callback); - -static struct irq_chip xen_dynamic_chip; - -/* Constructor for packed IRQ information. */ -static inline struct packed_irq mk_irq_info(u32 type, u32 index, u32 evtchn) -{ - return (struct packed_irq) { evtchn, index, type }; -} - -/* - * Accessors for packed IRQ information. - */ -static inline unsigned int evtchn_from_irq(int irq) -{ - return irq_info[irq].evtchn; -} - -static inline unsigned int index_from_irq(int irq) -{ - return irq_info[irq].index; -} - -static inline unsigned int type_from_irq(int irq) -{ - return irq_info[irq].type; -} - -static inline unsigned long active_evtchns(unsigned int cpu, - struct shared_info *sh, - unsigned int idx) -{ - return (sh->evtchn_pending[idx] & - cpu_evtchn_mask[cpu][idx] & - ~sh->evtchn_mask[idx]); -} - -static void bind_evtchn_to_cpu(unsigned int chn, unsigned int cpu) -{ - int irq = evtchn_to_irq[chn]; - - BUG_ON(irq == -1); -#ifdef CONFIG_SMP - irq_desc[irq].affinity = cpumask_of_cpu(cpu); -#endif - - __clear_bit(chn, cpu_evtchn_mask[cpu_evtchn[chn]]); - __set_bit(chn, cpu_evtchn_mask[cpu]); - - cpu_evtchn[chn] = cpu; -} - -static void init_evtchn_cpu_bindings(void) -{ -#ifdef CONFIG_SMP - int i; - /* By default all event channels notify CPU#0. */ - for (i = 0; i < NR_IRQS; i++) - irq_desc[i].affinity = cpumask_of_cpu(0); -#endif - - memset(cpu_evtchn, 0, sizeof(cpu_evtchn)); - memset(cpu_evtchn_mask[0], ~0, sizeof(cpu_evtchn_mask[0])); -} - -static inline unsigned int cpu_from_evtchn(unsigned int evtchn) -{ - return cpu_evtchn[evtchn]; -} - -static inline void clear_evtchn(int port) -{ - struct shared_info *s = HYPERVISOR_shared_info; - sync_clear_bit(port, &s->evtchn_pending[0]); -} - -static inline void set_evtchn(int port) -{ - struct shared_info *s = HYPERVISOR_shared_info; - sync_set_bit(port, &s->evtchn_pending[0]); -} - - -/** - * notify_remote_via_irq - send event to remote end of event channel via irq - * @irq: irq of event channel to send event to - * - * Unlike notify_remote_via_evtchn(), this is safe to use across - * save/restore. Notifications on a broken connection are silently - * dropped. - */ -void notify_remote_via_irq(int irq) -{ - int evtchn = evtchn_from_irq(irq); - - if (VALID_EVTCHN(evtchn)) - notify_remote_via_evtchn(evtchn); -} -EXPORT_SYMBOL_GPL(notify_remote_via_irq); - -static void mask_evtchn(int port) -{ - struct shared_info *s = HYPERVISOR_shared_info; - sync_set_bit(port, &s->evtchn_mask[0]); -} - -static void unmask_evtchn(int port) -{ - struct shared_info *s = HYPERVISOR_shared_info; - unsigned int cpu = get_cpu(); - - BUG_ON(!irqs_disabled()); - - /* Slow path (hypercall) if this is a non-local port. */ - if (unlikely(cpu != cpu_from_evtchn(port))) { - struct evtchn_unmask unmask = { .port = port }; - (void)HYPERVISOR_event_channel_op(EVTCHNOP_unmask, &unmask); - } else { - struct vcpu_info *vcpu_info = __get_cpu_var(xen_vcpu); - - sync_clear_bit(port, &s->evtchn_mask[0]); - - /* - * The following is basically the equivalent of - * 'hw_resend_irq'. Just like a real IO-APIC we 'lose - * the interrupt edge' if the channel is masked. - */ - if (sync_test_bit(port, &s->evtchn_pending[0]) && - !sync_test_and_set_bit(port / BITS_PER_LONG, - &vcpu_info->evtchn_pending_sel)) - vcpu_info->evtchn_upcall_pending = 1; - } - - put_cpu(); -} - -static int find_unbound_irq(void) -{ - int irq; - - /* Only allocate from dynirq range */ - for (irq = 0; irq < NR_IRQS; irq++) - if (irq_bindcount[irq] == 0) - break; - - if (irq == NR_IRQS) - panic("No available IRQ to bind to: increase NR_IRQS!\n"); - - return irq; -} - -int bind_evtchn_to_irq(unsigned int evtchn) -{ - int irq; - - spin_lock(&irq_mapping_update_lock); - - irq = evtchn_to_irq[evtchn]; - - if (irq == -1) { - irq = find_unbound_irq(); - - dynamic_irq_init(irq); - set_irq_chip_and_handler_name(irq, &xen_dynamic_chip, - handle_level_irq, "event"); - - evtchn_to_irq[evtchn] = irq; - irq_info[irq] = mk_irq_info(IRQT_EVTCHN, 0, evtchn); - } - - irq_bindcount[irq]++; - - spin_unlock(&irq_mapping_update_lock); - - return irq; -} -EXPORT_SYMBOL_GPL(bind_evtchn_to_irq); - -static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu) -{ - struct evtchn_bind_ipi bind_ipi; - int evtchn, irq; - - spin_lock(&irq_mapping_update_lock); - - irq = per_cpu(ipi_to_irq, cpu)[ipi]; - if (irq == -1) { - irq = find_unbound_irq(); - if (irq < 0) - goto out; - - dynamic_irq_init(irq); - set_irq_chip_and_handler_name(irq, &xen_dynamic_chip, - handle_level_irq, "ipi"); - - bind_ipi.vcpu = cpu; - if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_ipi, - &bind_ipi) != 0) - BUG(); - evtchn = bind_ipi.port; - - evtchn_to_irq[evtchn] = irq; - irq_info[irq] = mk_irq_info(IRQT_IPI, ipi, evtchn); - - per_cpu(ipi_to_irq, cpu)[ipi] = irq; - - bind_evtchn_to_cpu(evtchn, cpu); - } - - irq_bindcount[irq]++; - - out: - spin_unlock(&irq_mapping_update_lock); - return irq; -} - - -static int bind_virq_to_irq(unsigned int virq, unsigned int cpu) -{ - struct evtchn_bind_virq bind_virq; - int evtchn, irq; - - spin_lock(&irq_mapping_update_lock); - - irq = per_cpu(virq_to_irq, cpu)[virq]; - - if (irq == -1) { - bind_virq.virq = virq; - bind_virq.vcpu = cpu; - if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq, - &bind_virq) != 0) - BUG(); - evtchn = bind_virq.port; - - irq = find_unbound_irq(); - - dynamic_irq_init(irq); - set_irq_chip_and_handler_name(irq, &xen_dynamic_chip, - handle_level_irq, "virq"); - - evtchn_to_irq[evtchn] = irq; - irq_info[irq] = mk_irq_info(IRQT_VIRQ, virq, evtchn); - - per_cpu(virq_to_irq, cpu)[virq] = irq; - - bind_evtchn_to_cpu(evtchn, cpu); - } - - irq_bindcount[irq]++; - - spin_unlock(&irq_mapping_update_lock); - - return irq; -} - -static void unbind_from_irq(unsigned int irq) -{ - struct evtchn_close close; - int evtchn = evtchn_from_irq(irq); - - spin_lock(&irq_mapping_update_lock); - - if (VALID_EVTCHN(evtchn) && (--irq_bindcount[irq] == 0)) { - close.port = evtchn; - if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0) - BUG(); - - switch (type_from_irq(irq)) { - case IRQT_VIRQ: - per_cpu(virq_to_irq, cpu_from_evtchn(evtchn)) - [index_from_irq(irq)] = -1; - break; - default: - break; - } - - /* Closed ports are implicitly re-bound to VCPU0. */ - bind_evtchn_to_cpu(evtchn, 0); - - evtchn_to_irq[evtchn] = -1; - irq_info[irq] = IRQ_UNBOUND; - - dynamic_irq_init(irq); - } - - spin_unlock(&irq_mapping_update_lock); -} - -int bind_evtchn_to_irqhandler(unsigned int evtchn, - irq_handler_t handler, - unsigned long irqflags, - const char *devname, void *dev_id) -{ - unsigned int irq; - int retval; - - irq = bind_evtchn_to_irq(evtchn); - retval = request_irq(irq, handler, irqflags, devname, dev_id); - if (retval != 0) { - unbind_from_irq(irq); - return retval; - } - - return irq; -} -EXPORT_SYMBOL_GPL(bind_evtchn_to_irqhandler); - -int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu, - irq_handler_t handler, - unsigned long irqflags, const char *devname, void *dev_id) -{ - unsigned int irq; - int retval; - - irq = bind_virq_to_irq(virq, cpu); - retval = request_irq(irq, handler, irqflags, devname, dev_id); - if (retval != 0) { - unbind_from_irq(irq); - return retval; - } - - return irq; -} -EXPORT_SYMBOL_GPL(bind_virq_to_irqhandler); - -int bind_ipi_to_irqhandler(enum ipi_vector ipi, - unsigned int cpu, - irq_handler_t handler, - unsigned long irqflags, - const char *devname, - void *dev_id) -{ - int irq, retval; - - irq = bind_ipi_to_irq(ipi, cpu); - if (irq < 0) - return irq; - - retval = request_irq(irq, handler, irqflags, devname, dev_id); - if (retval != 0) { - unbind_from_irq(irq); - return retval; - } - - return irq; -} - -void unbind_from_irqhandler(unsigned int irq, void *dev_id) -{ - free_irq(irq, dev_id); - unbind_from_irq(irq); -} -EXPORT_SYMBOL_GPL(unbind_from_irqhandler); - -void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector) -{ - int irq = per_cpu(ipi_to_irq, cpu)[vector]; - BUG_ON(irq < 0); - notify_remote_via_irq(irq); -} - - -/* - * Search the CPUs pending events bitmasks. For each one found, map - * the event number to an irq, and feed it into do_IRQ() for - * handling. - * - * Xen uses a two-level bitmap to speed searching. The first level is - * a bitset of words which contain pending event bits. The second - * level is a bitset of pending events themselves. - */ -void xen_evtchn_do_upcall(struct pt_regs *regs) -{ - int cpu = get_cpu(); - struct shared_info *s = HYPERVISOR_shared_info; - struct vcpu_info *vcpu_info = __get_cpu_var(xen_vcpu); - unsigned long pending_words; - - vcpu_info->evtchn_upcall_pending = 0; - - /* NB. No need for a barrier here -- XCHG is a barrier on x86. */ - pending_words = xchg(&vcpu_info->evtchn_pending_sel, 0); - while (pending_words != 0) { - unsigned long pending_bits; - int word_idx = __ffs(pending_words); - pending_words &= ~(1UL << word_idx); - - while ((pending_bits = active_evtchns(cpu, s, word_idx)) != 0) { - int bit_idx = __ffs(pending_bits); - int port = (word_idx * BITS_PER_LONG) + bit_idx; - int irq = evtchn_to_irq[port]; - - if (irq != -1) { - regs->orig_ax = ~irq; - do_IRQ(regs); - } - } - } - - put_cpu(); -} - -/* Rebind an evtchn so that it gets delivered to a specific cpu */ -static void rebind_irq_to_cpu(unsigned irq, unsigned tcpu) -{ - struct evtchn_bind_vcpu bind_vcpu; - int evtchn = evtchn_from_irq(irq); - - if (!VALID_EVTCHN(evtchn)) - return; - - /* Send future instances of this interrupt to other vcpu. */ - bind_vcpu.port = evtchn; - bind_vcpu.vcpu = tcpu; - - /* - * If this fails, it usually just indicates that we're dealing with a - * virq or IPI channel, which don't actually need to be rebound. Ignore - * it, but don't do the xenlinux-level rebind in that case. - */ - if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0) - bind_evtchn_to_cpu(evtchn, tcpu); -} - - -static void set_affinity_irq(unsigned irq, cpumask_t dest) -{ - unsigned tcpu = first_cpu(dest); - rebind_irq_to_cpu(irq, tcpu); -} - -static void enable_dynirq(unsigned int irq) -{ - int evtchn = evtchn_from_irq(irq); - - if (VALID_EVTCHN(evtchn)) - unmask_evtchn(evtchn); -} - -static void disable_dynirq(unsigned int irq) -{ - int evtchn = evtchn_from_irq(irq); - - if (VALID_EVTCHN(evtchn)) - mask_evtchn(evtchn); -} - -static void ack_dynirq(unsigned int irq) -{ - int evtchn = evtchn_from_irq(irq); - - move_native_irq(irq); - - if (VALID_EVTCHN(evtchn)) - clear_evtchn(evtchn); -} - -static int retrigger_dynirq(unsigned int irq) -{ - int evtchn = evtchn_from_irq(irq); - int ret = 0; - - if (VALID_EVTCHN(evtchn)) { - set_evtchn(evtchn); - ret = 1; - } - - return ret; -} - -static struct irq_chip xen_dynamic_chip __read_mostly = { - .name = "xen-dyn", - .mask = disable_dynirq, - .unmask = enable_dynirq, - .ack = ack_dynirq, - .set_affinity = set_affinity_irq, - .retrigger = retrigger_dynirq, -}; - -void __init xen_init_IRQ(void) -{ - int i; - - init_evtchn_cpu_bindings(); - - /* No event channels are 'live' right now. */ - for (i = 0; i < NR_EVENT_CHANNELS; i++) - mask_evtchn(i); - - /* Dynamic IRQ space is currently unbound. Zero the refcnts. */ - for (i = 0; i < NR_IRQS; i++) - irq_bindcount[i] = 0; - - irq_ctx_init(smp_processor_id()); -} diff --git a/arch/x86/xen/features.c b/arch/x86/xen/features.c deleted file mode 100644 index 0707714e40d6..000000000000 --- a/arch/x86/xen/features.c +++ /dev/null @@ -1,29 +0,0 @@ -/****************************************************************************** - * features.c - * - * Xen feature flags. - * - * Copyright (c) 2006, Ian Campbell, XenSource Inc. - */ -#include <linux/types.h> -#include <linux/cache.h> -#include <linux/module.h> -#include <asm/xen/hypervisor.h> -#include <xen/features.h> - -u8 xen_features[XENFEAT_NR_SUBMAPS * 32] __read_mostly; -EXPORT_SYMBOL_GPL(xen_features); - -void xen_setup_features(void) -{ - struct xen_feature_info fi; - int i, j; - - for (i = 0; i < XENFEAT_NR_SUBMAPS; i++) { - fi.submap_idx = i; - if (HYPERVISOR_xen_version(XENVER_get_features, &fi) < 0) - break; - for (j = 0; j < 32; j++) - xen_features[i * 32 + j] = !!(fi.submap & 1<<j); - } -} diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c new file mode 100644 index 000000000000..49ba9b5224d1 --- /dev/null +++ b/arch/x86/xen/grant-table.c @@ -0,0 +1,91 @@ +/****************************************************************************** + * grant_table.c + * x86 specific part + * + * Granting foreign access to our memory reservation. + * + * Copyright (c) 2005-2006, Christopher Clark + * Copyright (c) 2004-2005, K A Fraser + * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp> + * VA Linux Systems Japan. Split out x86 specific part. + * + * 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; or, when distributed + * separately from the Linux kernel or incorporated into other + * software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/vmalloc.h> + +#include <xen/interface/xen.h> +#include <xen/page.h> +#include <xen/grant_table.h> + +#include <asm/pgtable.h> + +static int map_pte_fn(pte_t *pte, struct page *pmd_page, + unsigned long addr, void *data) +{ + unsigned long **frames = (unsigned long **)data; + + set_pte_at(&init_mm, addr, pte, mfn_pte((*frames)[0], PAGE_KERNEL)); + (*frames)++; + return 0; +} + +static int unmap_pte_fn(pte_t *pte, struct page *pmd_page, + unsigned long addr, void *data) +{ + + set_pte_at(&init_mm, addr, pte, __pte(0)); + return 0; +} + +int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes, + unsigned long max_nr_gframes, + struct grant_entry **__shared) +{ + int rc; + struct grant_entry *shared = *__shared; + + if (shared == NULL) { + struct vm_struct *area = + xen_alloc_vm_area(PAGE_SIZE * max_nr_gframes); + BUG_ON(area == NULL); + shared = area->addr; + *__shared = shared; + } + + rc = apply_to_page_range(&init_mm, (unsigned long)shared, + PAGE_SIZE * nr_gframes, + map_pte_fn, &frames); + return rc; +} + +void arch_gnttab_unmap_shared(struct grant_entry *shared, + unsigned long nr_gframes) +{ + apply_to_page_range(&init_mm, (unsigned long)shared, + PAGE_SIZE * nr_gframes, unmap_pte_fn, NULL); +} diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 2a054ef2a3da..126766d43aea 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -156,6 +156,10 @@ void set_pte_mfn(unsigned long vaddr, unsigned long mfn, pgprot_t flags) void xen_set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pteval) { + /* updates to init_mm may be done without lock */ + if (mm == &init_mm) + preempt_disable(); + if (mm == current->mm || mm == &init_mm) { if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) { struct multicall_space mcs; @@ -163,14 +167,61 @@ void xen_set_pte_at(struct mm_struct *mm, unsigned long addr, MULTI_update_va_mapping(mcs.mc, addr, pteval, 0); xen_mc_issue(PARAVIRT_LAZY_MMU); - return; + goto out; } else if (HYPERVISOR_update_va_mapping(addr, pteval, 0) == 0) - return; + goto out; } xen_set_pte(ptep, pteval); + +out: + if (mm == &init_mm) + preempt_enable(); +} + +pteval_t xen_pte_val(pte_t pte) +{ + pteval_t ret = pte.pte; + + if (ret & _PAGE_PRESENT) + ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT; + + return ret; +} + +pgdval_t xen_pgd_val(pgd_t pgd) +{ + pgdval_t ret = pgd.pgd; + if (ret & _PAGE_PRESENT) + ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT; + return ret; +} + +pte_t xen_make_pte(pteval_t pte) +{ + if (pte & _PAGE_PRESENT) { + pte = phys_to_machine(XPADDR(pte)).maddr; + pte &= ~(_PAGE_PCD | _PAGE_PWT); + } + + return (pte_t){ .pte = pte }; } +pgd_t xen_make_pgd(pgdval_t pgd) +{ + if (pgd & _PAGE_PRESENT) + pgd = phys_to_machine(XPADDR(pgd)).maddr; + + return (pgd_t){ 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; +} #ifdef CONFIG_X86_PAE void xen_set_pud(pud_t *ptr, pud_t val) { @@ -214,100 +265,18 @@ void xen_pmd_clear(pmd_t *pmdp) xen_set_pmd(pmdp, __pmd(0)); } -unsigned long long xen_pte_val(pte_t pte) +pmd_t xen_make_pmd(pmdval_t pmd) { - unsigned long long ret = 0; - - if (pte.pte_low) { - ret = ((unsigned long long)pte.pte_high << 32) | pte.pte_low; - ret = machine_to_phys(XMADDR(ret)).paddr | 1; - } - - return ret; -} - -unsigned long long xen_pmd_val(pmd_t pmd) -{ - unsigned long long ret = pmd.pmd; - if (ret) - ret = machine_to_phys(XMADDR(ret)).paddr | 1; - return ret; -} - -unsigned long long xen_pgd_val(pgd_t pgd) -{ - unsigned long long ret = pgd.pgd; - if (ret) - ret = machine_to_phys(XMADDR(ret)).paddr | 1; - return ret; -} - -pte_t xen_make_pte(unsigned long long pte) -{ - if (pte & _PAGE_PRESENT) { - pte = phys_to_machine(XPADDR(pte)).maddr; - pte &= ~(_PAGE_PCD | _PAGE_PWT); - } - - return (pte_t){ .pte = pte }; -} - -pmd_t xen_make_pmd(unsigned long long pmd) -{ - if (pmd & 1) + if (pmd & _PAGE_PRESENT) pmd = phys_to_machine(XPADDR(pmd)).maddr; - return (pmd_t){ pmd }; -} - -pgd_t xen_make_pgd(unsigned long long pgd) -{ - if (pgd & _PAGE_PRESENT) - pgd = phys_to_machine(XPADDR(pgd)).maddr; - - return (pgd_t){ pgd }; + return native_make_pmd(pmd); } #else /* !PAE */ void xen_set_pte(pte_t *ptep, pte_t pte) { *ptep = pte; } - -unsigned long xen_pte_val(pte_t pte) -{ - unsigned long ret = pte.pte_low; - - if (ret & _PAGE_PRESENT) - ret = machine_to_phys(XMADDR(ret)).paddr; - - return ret; -} - -unsigned long xen_pgd_val(pgd_t pgd) -{ - unsigned long ret = pgd.pgd; - if (ret) - ret = machine_to_phys(XMADDR(ret)).paddr | 1; - return ret; -} - -pte_t xen_make_pte(unsigned long pte) -{ - if (pte & _PAGE_PRESENT) { - pte = phys_to_machine(XPADDR(pte)).maddr; - pte &= ~(_PAGE_PCD | _PAGE_PWT); - } - - return (pte_t){ pte }; -} - -pgd_t xen_make_pgd(unsigned long pgd) -{ - if (pgd & _PAGE_PRESENT) - pgd = phys_to_machine(XPADDR(pgd)).maddr; - - return (pgd_t){ pgd }; -} #endif /* CONFIG_X86_PAE */ /* @@ -418,7 +387,7 @@ static void xen_do_pin(unsigned level, unsigned long pfn) static int pin_page(struct page *page, enum pt_level level) { - unsigned pgfl = test_and_set_bit(PG_pinned, &page->flags); + unsigned pgfl = TestSetPagePinned(page); int flush; if (pgfl) @@ -499,7 +468,7 @@ void __init xen_mark_init_mm_pinned(void) static int unpin_page(struct page *page, enum pt_level level) { - unsigned pgfl = test_and_clear_bit(PG_pinned, &page->flags); + unsigned pgfl = TestClearPagePinned(page); if (pgfl && !PageHighMem(page)) { void *pt = lowmem_page_address(page); diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c index 5e6f36f6d876..5791eb2e3750 100644 --- a/arch/x86/xen/multicalls.c +++ b/arch/x86/xen/multicalls.c @@ -76,7 +76,7 @@ void xen_mc_flush(void) if (ret) { printk(KERN_ERR "%d multicall(s) failed: cpu %d\n", ret, smp_processor_id()); - for(i = 0; i < b->mcidx; i++) { + for (i = 0; i < b->mcidx; i++) { printk(" call %2d/%d: op=%lu arg=[%lx] result=%ld\n", i+1, b->mcidx, b->debug[i].op, @@ -93,7 +93,7 @@ void xen_mc_flush(void) local_irq_restore(flags); - for(i = 0; i < b->cbidx; i++) { + for (i = 0; i < b->cbidx; i++) { struct callback *cb = &b->callbacks[i]; (*cb->fn)(cb->data); diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 2341492bf7a0..82517e4a752a 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -16,6 +16,7 @@ #include <asm/xen/hypervisor.h> #include <asm/xen/hypercall.h> +#include <xen/interface/callback.h> #include <xen/interface/physdev.h> #include <xen/features.h> @@ -68,6 +69,24 @@ static void __init fiddle_vdso(void) *mask |= 1 << VDSO_NOTE_NONEGSEG_BIT; } +void xen_enable_sysenter(void) +{ + int cpu = smp_processor_id(); + extern void xen_sysenter_target(void); + /* Mask events on entry, even though they get enabled immediately */ + static struct callback_register sysenter = { + .type = CALLBACKTYPE_sysenter, + .address = { __KERNEL_CS, (unsigned long)xen_sysenter_target }, + .flags = CALLBACKF_mask_events, + }; + + if (!boot_cpu_has(X86_FEATURE_SEP) || + HYPERVISOR_callback_op(CALLBACKOP_register, &sysenter) != 0) { + clear_cpu_cap(&cpu_data(cpu), X86_FEATURE_SEP); + clear_cpu_cap(&boot_cpu_data, X86_FEATURE_SEP); + } +} + void __init xen_arch_setup(void) { struct physdev_set_iopl set_iopl; @@ -82,6 +101,8 @@ void __init xen_arch_setup(void) HYPERVISOR_set_callbacks(__KERNEL_CS, (unsigned long)xen_hypervisor_callback, __KERNEL_CS, (unsigned long)xen_failsafe_callback); + xen_enable_sysenter(); + set_iopl.iopl = 1; rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl); if (rc != 0) diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index aafc54437403..94e69000f982 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -35,9 +35,10 @@ #include "xen-ops.h" #include "mmu.h" -static cpumask_t cpu_initialized_map; -static DEFINE_PER_CPU(int, resched_irq); -static DEFINE_PER_CPU(int, callfunc_irq); +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 @@ -72,6 +73,7 @@ static __cpuinit void cpu_bringup_and_idle(void) int cpu = smp_processor_id(); cpu_init(); + xen_enable_sysenter(); preempt_disable(); per_cpu(cpu_state, cpu) = CPU_ONLINE; @@ -88,9 +90,7 @@ static __cpuinit void cpu_bringup_and_idle(void) static int xen_smp_intr_init(unsigned int cpu) { int rc; - const char *resched_name, *callfunc_name; - - per_cpu(resched_irq, cpu) = per_cpu(callfunc_irq, cpu) = -1; + const char *resched_name, *callfunc_name, *debug_name; resched_name = kasprintf(GFP_KERNEL, "resched%d", cpu); rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR, @@ -114,6 +114,14 @@ static int xen_smp_intr_init(unsigned int cpu) goto fail; per_cpu(callfunc_irq, cpu) = rc; + debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu); + rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu, xen_debug_interrupt, + IRQF_DISABLED | IRQF_PERCPU | IRQF_NOBALANCING, + debug_name, NULL); + if (rc < 0) + goto fail; + per_cpu(debug_irq, cpu) = rc; + return 0; fail: @@ -121,6 +129,8 @@ static int xen_smp_intr_init(unsigned int cpu) unbind_from_irqhandler(per_cpu(resched_irq, cpu), NULL); if (per_cpu(callfunc_irq, cpu) >= 0) 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); return rc; } @@ -179,11 +189,11 @@ void __init xen_smp_prepare_cpus(unsigned int max_cpus) if (xen_smp_intr_init(0)) BUG(); - cpu_initialized_map = cpumask_of_cpu(0); + xen_cpu_initialized_map = cpumask_of_cpu(0); /* Restrict the possible_map according to max_cpus. */ while ((num_possible_cpus() > 1) && (num_possible_cpus() > max_cpus)) { - for (cpu = NR_CPUS-1; !cpu_isset(cpu, cpu_possible_map); cpu--) + for (cpu = NR_CPUS - 1; !cpu_possible(cpu); cpu--) continue; cpu_clear(cpu, cpu_possible_map); } @@ -210,7 +220,7 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) struct vcpu_guest_context *ctxt; struct gdt_page *gdt = &per_cpu(gdt_page, cpu); - if (cpu_test_and_set(cpu, cpu_initialized_map)) + if (cpu_test_and_set(cpu, xen_cpu_initialized_map)) return 0; ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 6b7190449d07..2497a30f41de 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -108,6 +108,20 @@ ENDPATCH(xen_restore_fl_direct) RELOC(xen_restore_fl_direct, 2b+1) /* + We can't use sysexit directly, because we're not running in ring0. + But we can easily fake it up using iret. Assuming xen_sysexit + is jumped to with a standard stack frame, we can just strip it + back to a standard iret frame and use iret. + */ +ENTRY(xen_sysexit) + movl PT_EAX(%esp), %eax /* Shouldn't be necessary? */ + orl $X86_EFLAGS_IF, PT_EFLAGS(%esp) + lea PT_EIP(%esp), %esp + + jmp xen_iret +ENDPROC(xen_sysexit) + +/* This is run where a normal iret would be run, with the same stack setup: 8: eflags 4: cs @@ -135,13 +149,8 @@ ENDPATCH(xen_restore_fl_direct) current stack state in whatever form its in, we keep things simple by only using a single register which is pushed/popped on the stack. - - Non-direct iret could be done in the same way, but it would - require an annoying amount of code duplication. We'll assume - that direct mode will be the common case once the hypervisor - support becomes commonplace. */ -ENTRY(xen_iret_direct) +ENTRY(xen_iret) /* test eflags for special cases */ testl $(X86_EFLAGS_VM | XEN_EFLAGS_NMI), 8(%esp) jnz hyper_iret @@ -155,9 +164,9 @@ ENTRY(xen_iret_direct) GET_THREAD_INFO(%eax) movl TI_cpu(%eax),%eax movl __per_cpu_offset(,%eax,4),%eax - lea per_cpu__xen_vcpu_info(%eax),%eax + mov per_cpu__xen_vcpu(%eax),%eax #else - movl $per_cpu__xen_vcpu_info, %eax + movl per_cpu__xen_vcpu, %eax #endif /* check IF state we're restoring */ @@ -189,8 +198,12 @@ iret_restore_end: region is OK. */ je xen_hypervisor_callback - iret +1: iret xen_iret_end_crit: +.section __ex_table,"a" + .align 4 + .long 1b,iret_exc +.previous hyper_iret: /* put this out of line since its very rarely used */ @@ -224,9 +237,7 @@ hyper_iret: ds } SAVE_ALL state eax } : : - ebx } - ---------------- - return addr <- esp + ebx }<- esp ---------------- In order to deliver the nested exception properly, we need to shift @@ -241,10 +252,8 @@ hyper_iret: it's usermode state which we eventually need to restore. */ ENTRY(xen_iret_crit_fixup) - /* offsets +4 for return address */ - /* - Paranoia: Make sure we're really coming from userspace. + Paranoia: Make sure we're really coming from kernel space. One could imagine a case where userspace jumps into the critical range address, but just before the CPU delivers a GP, it decides to deliver an interrupt instead. Unlikely? @@ -253,32 +262,32 @@ ENTRY(xen_iret_crit_fixup) jump instruction itself, not the destination, but some virtual environments get this wrong. */ - movl PT_CS+4(%esp), %ecx + movl PT_CS(%esp), %ecx andl $SEGMENT_RPL_MASK, %ecx cmpl $USER_RPL, %ecx je 2f - lea PT_ORIG_EAX+4(%esp), %esi - lea PT_EFLAGS+4(%esp), %edi + lea PT_ORIG_EAX(%esp), %esi + lea PT_EFLAGS(%esp), %edi /* If eip is before iret_restore_end then stack hasn't been restored yet. */ cmp $iret_restore_end, %eax jae 1f - movl 0+4(%edi),%eax /* copy EAX */ - movl %eax, PT_EAX+4(%esp) + movl 0+4(%edi),%eax /* copy EAX (just above top of frame) */ + movl %eax, PT_EAX(%esp) lea ESP_OFFSET(%edi),%edi /* move dest up over saved regs */ /* set up the copy */ 1: std - mov $(PT_EIP+4) / 4, %ecx /* copy ret+saved regs up to orig_eax */ + mov $PT_EIP / 4, %ecx /* saved regs up to orig_eax */ rep movsl cld lea 4(%edi),%esp /* point esp to new frame */ -2: ret +2: jmp xen_do_upcall /* diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index b02a909bfd4c..f1063ae08037 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -2,6 +2,8 @@ #define XEN_OPS_H #include <linux/init.h> +#include <linux/irqreturn.h> +#include <xen/xen-ops.h> /* These are code, but not functions. Defined in entry.S */ extern const char xen_hypervisor_callback[]; @@ -9,7 +11,6 @@ extern const char xen_failsafe_callback[]; void xen_copy_trap_info(struct trap_info *traps); -DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu); DECLARE_PER_CPU(unsigned long, xen_cr3); DECLARE_PER_CPU(unsigned long, xen_current_cr3); @@ -19,6 +20,7 @@ extern struct shared_info *HYPERVISOR_shared_info; 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_setup_timer(int cpu); void xen_setup_cpu_clockevents(void); @@ -28,6 +30,8 @@ unsigned long xen_get_wallclock(void); int xen_set_wallclock(unsigned long time); unsigned long long xen_sched_clock(void); +irqreturn_t xen_debug_interrupt(int irq, void *dev_id); + bool xen_vcpu_stolen(int vcpu); void xen_mark_init_mm_pinned(void); @@ -63,5 +67,7 @@ DECL_ASM(void, xen_irq_disable_direct, void); DECL_ASM(unsigned long, xen_save_fl_direct, void); DECL_ASM(void, xen_restore_fl_direct, unsigned long); -void xen_iret_direct(void); +void xen_iret(void); +void xen_sysexit(void); + #endif /* XEN_OPS_H */ |