diff options
| author | Linus Torvalds <torvalds@g5.osdl.org> | 2006-09-26 13:07:55 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@g5.osdl.org> | 2006-09-26 13:07:55 -0700 |
| commit | b278240839e20fa9384ea430df463b367b90e04e (patch) | |
| tree | f99f0c8cdd4cc7f177cd75440e6bd181cded7fb3 /arch | |
| parent | dd77a4ee0f3981693d4229aa1d57cea9e526ff47 (diff) | |
| parent | 3f75f42d7733e73aca5c78326489efd4189e0111 (diff) | |
| download | op-kernel-dev-b278240839e20fa9384ea430df463b367b90e04e.zip op-kernel-dev-b278240839e20fa9384ea430df463b367b90e04e.tar.gz | |
Merge branch 'for-linus' of git://one.firstfloor.org/home/andi/git/linux-2.6
* 'for-linus' of git://one.firstfloor.org/home/andi/git/linux-2.6: (225 commits)
[PATCH] Don't set calgary iommu as default y
[PATCH] i386/x86-64: New Intel feature flags
[PATCH] x86: Add a cumulative thermal throttle event counter.
[PATCH] i386: Make the jiffies compares use the 64bit safe macros.
[PATCH] x86: Refactor thermal throttle processing
[PATCH] Add 64bit jiffies compares (for use with get_jiffies_64)
[PATCH] Fix unwinder warning in traps.c
[PATCH] x86: Allow disabling early pci scans with pci=noearly or disallowing conf1
[PATCH] x86: Move direct PCI scanning functions out of line
[PATCH] i386/x86-64: Make all early PCI scans dependent on CONFIG_PCI
[PATCH] Don't leak NT bit into next task
[PATCH] i386/x86-64: Work around gcc bug with noreturn functions in unwinder
[PATCH] Fix some broken white space in ia32_signal.c
[PATCH] Initialize argument registers for 32bit signal handlers.
[PATCH] Remove all traces of signal number conversion
[PATCH] Don't synchronize time reading on single core AMD systems
[PATCH] Remove outdated comment in x86-64 mmconfig code
[PATCH] Use string instructions for Core2 copy/clear
[PATCH] x86: - restore i8259A eoi status on resume
[PATCH] i386: Split multi-line printk in oops output.
...
Diffstat (limited to 'arch')
143 files changed, 5735 insertions, 4477 deletions
diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig index 6189b0c..758044f 100644 --- a/arch/i386/Kconfig +++ b/arch/i386/Kconfig @@ -166,7 +166,6 @@ config X86_VISWS config X86_GENERICARCH bool "Generic architecture (Summit, bigsmp, ES7000, default)" - depends on SMP help This option compiles in the Summit, bigsmp, ES7000, default subarchitectures. It is intended for a generic binary kernel. @@ -263,7 +262,7 @@ source "kernel/Kconfig.preempt" config X86_UP_APIC bool "Local APIC support on uniprocessors" - depends on !SMP && !(X86_VISWS || X86_VOYAGER) + depends on !SMP && !(X86_VISWS || X86_VOYAGER || X86_GENERICARCH) help A local APIC (Advanced Programmable Interrupt Controller) is an integrated interrupt controller in the CPU. If you have a single-CPU @@ -288,12 +287,12 @@ config X86_UP_IOAPIC config X86_LOCAL_APIC bool - depends on X86_UP_APIC || ((X86_VISWS || SMP) && !X86_VOYAGER) + depends on X86_UP_APIC || ((X86_VISWS || SMP) && !X86_VOYAGER) || X86_GENERICARCH default y config X86_IO_APIC bool - depends on X86_UP_IOAPIC || (SMP && !(X86_VISWS || X86_VOYAGER)) + depends on X86_UP_IOAPIC || (SMP && !(X86_VISWS || X86_VOYAGER)) || X86_GENERICARCH default y config X86_VISWS_APIC @@ -741,8 +740,7 @@ config SECCOMP source kernel/Kconfig.hz config KEXEC - bool "kexec system call (EXPERIMENTAL)" - depends on EXPERIMENTAL + bool "kexec system call" 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 @@ -763,6 +761,13 @@ config CRASH_DUMP depends on HIGHMEM help Generate crash dump after being started by kexec. + This should be normally only set in special crash dump kernels + which are loaded in the main kernel with kexec-tools into + a specially reserved region and then later executed after + a crash by kdump/kexec. The crash dump kernel must be compiled + to a memory address not used by the main kernel or BIOS using + PHYSICAL_START. + For more details see Documentation/kdump/kdump.txt config PHYSICAL_START hex "Physical address where the kernel is loaded" if (EMBEDDED || CRASH_DUMP) diff --git a/arch/i386/Makefile b/arch/i386/Makefile index 3e4adb1..7cc0b18 100644 --- a/arch/i386/Makefile +++ b/arch/i386/Makefile @@ -46,6 +46,14 @@ cflags-y += -ffreestanding # a lot more stack due to the lack of sharing of stacklots: CFLAGS += $(shell if [ $(call cc-version) -lt 0400 ] ; then echo $(call cc-option,-fno-unit-at-a-time); fi ;) +# do binutils support CFI? +cflags-y += $(call as-instr,.cfi_startproc\n.cfi_endproc,-DCONFIG_AS_CFI=1,) +AFLAGS += $(call as-instr,.cfi_startproc\n.cfi_endproc,-DCONFIG_AS_CFI=1,) + +# is .cfi_signal_frame supported too? +cflags-y += $(call as-instr,.cfi_startproc\n.cfi_endproc,-DCONFIG_AS_CFI=1,) +AFLAGS += $(call as-instr,.cfi_startproc\n.cfi_endproc,-DCONFIG_AS_CFI=1,) + CFLAGS += $(cflags-y) # Default subarch .c files diff --git a/arch/i386/boot/edd.S b/arch/i386/boot/edd.S index 4b84ea2..3432136 100644 --- a/arch/i386/boot/edd.S +++ b/arch/i386/boot/edd.S @@ -15,42 +15,95 @@ #include <asm/setup.h> #if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE) + +# It is assumed that %ds == INITSEG here + movb $0, (EDD_MBR_SIG_NR_BUF) movb $0, (EDDNR) -# Check the command line for two options: +# Check the command line for options: # edd=of disables EDD completely (edd=off) # edd=sk skips the MBR test (edd=skipmbr) +# edd=on re-enables EDD (edd=on) + pushl %esi - cmpl $0, %cs:cmd_line_ptr - jz done_cl + movw $edd_mbr_sig_start, %di # Default to edd=on + movl %cs:(cmd_line_ptr), %esi -# ds:esi has the pointer to the command line now - movl $(COMMAND_LINE_SIZE-7), %ecx -# loop through kernel command line one byte at a time -cl_loop: - cmpl $EDD_CL_EQUALS, (%si) + andl %esi, %esi + jz old_cl # Old boot protocol? + +# Convert to a real-mode pointer in fs:si + movl %esi, %eax + shrl $4, %eax + movw %ax, %fs + andw $0xf, %si + jmp have_cl_pointer + +# Old-style boot protocol? +old_cl: + push %ds # aka INITSEG + pop %fs + + cmpw $0xa33f, (0x20) + jne done_cl # No command line at all? + movw (0x22), %si # Pointer relative to INITSEG + +# fs:si has the pointer to the command line now +have_cl_pointer: + +# Loop through kernel command line one byte at a time. Just in +# case the loader is buggy and failed to null-terminate the command line +# terminate if we get close enough to the end of the segment that we +# cannot fit "edd=XX"... +cl_atspace: + cmpw $-5, %si # Watch for segment wraparound + jae done_cl + movl %fs:(%si), %eax + andb %al, %al # End of line? + jz done_cl + cmpl $EDD_CL_EQUALS, %eax jz found_edd_equals - incl %esi - loop cl_loop - jmp done_cl + cmpb $0x20, %al # <= space consider whitespace + ja cl_skipword + incw %si + jmp cl_atspace + +cl_skipword: + cmpw $-5, %si # Watch for segment wraparound + jae done_cl + movb %fs:(%si), %al # End of string? + andb %al, %al + jz done_cl + cmpb $0x20, %al + jbe cl_atspace + incw %si + jmp cl_skipword + found_edd_equals: # only looking at first two characters after equals - addl $4, %esi - cmpw $EDD_CL_OFF, (%si) # edd=of - jz do_edd_off - cmpw $EDD_CL_SKIP, (%si) # edd=sk - jz do_edd_skipmbr - jmp done_cl +# late overrides early on the command line, so keep going after finding something + movw %fs:4(%si), %ax + cmpw $EDD_CL_OFF, %ax # edd=of + je do_edd_off + cmpw $EDD_CL_SKIP, %ax # edd=sk + je do_edd_skipmbr + cmpw $EDD_CL_ON, %ax # edd=on + je do_edd_on + jmp cl_skipword do_edd_skipmbr: - popl %esi - jmp edd_start + movw $edd_start, %di + jmp cl_skipword do_edd_off: - popl %esi - jmp edd_done + movw $edd_done, %di + jmp cl_skipword +do_edd_on: + movw $edd_mbr_sig_start, %di + jmp cl_skipword + done_cl: popl %esi - + jmpw *%di # Read the first sector of each BIOS disk device and store the 4-byte signature edd_mbr_sig_start: diff --git a/arch/i386/boot/setup.S b/arch/i386/boot/setup.S index d2b684c..3aec4538 100644 --- a/arch/i386/boot/setup.S +++ b/arch/i386/boot/setup.S @@ -494,12 +494,12 @@ no_voyager: movw %cs, %ax # aka SETUPSEG subw $DELTA_INITSEG, %ax # aka INITSEG movw %ax, %ds - movw $0, (0x1ff) # default is no pointing device + movb $0, (0x1ff) # default is no pointing device int $0x11 # int 0x11: equipment list testb $0x04, %al # check if mouse installed jz no_psmouse - movw $0xAA, (0x1ff) # device present + movb $0xAA, (0x1ff) # device present no_psmouse: #if defined(CONFIG_X86_SPEEDSTEP_SMI) || defined(CONFIG_X86_SPEEDSTEP_SMI_MODULE) diff --git a/arch/i386/defconfig b/arch/i386/defconfig index 89ebb7a..1a29bfa 100644 --- a/arch/i386/defconfig +++ b/arch/i386/defconfig @@ -1,41 +1,51 @@ # # Automatically generated make config: don't edit +# Linux kernel version: 2.6.18-git5 +# Tue Sep 26 09:30:47 2006 # CONFIG_X86_32=y +CONFIG_GENERIC_TIME=y +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_STACKTRACE_SUPPORT=y CONFIG_SEMAPHORE_SLEEPERS=y CONFIG_X86=y CONFIG_MMU=y CONFIG_GENERIC_ISA_DMA=y CONFIG_GENERIC_IOMAP=y +CONFIG_GENERIC_HWEIGHT=y CONFIG_ARCH_MAY_HAVE_PC_FDC=y CONFIG_DMI=y +CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # # Code maturity level options # CONFIG_EXPERIMENTAL=y -CONFIG_BROKEN_ON_SMP=y +CONFIG_LOCK_KERNEL=y CONFIG_INIT_ENV_ARG_LIMIT=32 # # General setup # CONFIG_LOCALVERSION="" -# CONFIG_LOCALVERSION_AUTO is not set +CONFIG_LOCALVERSION_AUTO=y CONFIG_SWAP=y CONFIG_SYSVIPC=y -# CONFIG_POSIX_MQUEUE is not set +CONFIG_POSIX_MQUEUE=y # CONFIG_BSD_PROCESS_ACCT is not set -CONFIG_SYSCTL=y +# CONFIG_TASKSTATS is not set # CONFIG_AUDIT is not set CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y +# CONFIG_CPUSETS is not set +# CONFIG_RELAY is not set CONFIG_INITRAMFS_SOURCE="" -CONFIG_UID16=y -CONFIG_VM86=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_EMBEDDED is not set +CONFIG_UID16=y +CONFIG_SYSCTL=y CONFIG_KALLSYMS=y +CONFIG_KALLSYMS_ALL=y # CONFIG_KALLSYMS_EXTRA_PASS is not set CONFIG_HOTPLUG=y CONFIG_PRINTK=y @@ -45,11 +55,9 @@ CONFIG_BASE_FULL=y CONFIG_FUTEX=y CONFIG_EPOLL=y CONFIG_SHMEM=y -CONFIG_CC_ALIGN_FUNCTIONS=0 -CONFIG_CC_ALIGN_LABELS=0 -CONFIG_CC_ALIGN_LOOPS=0 -CONFIG_CC_ALIGN_JUMPS=0 CONFIG_SLAB=y +CONFIG_VM_EVENT_COUNTERS=y +CONFIG_RT_MUTEXES=y # CONFIG_TINY_SHMEM is not set CONFIG_BASE_SMALL=0 # CONFIG_SLOB is not set @@ -60,41 +68,45 @@ CONFIG_BASE_SMALL=0 CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y -CONFIG_OBSOLETE_MODPARM=y # CONFIG_MODVERSIONS is not set # CONFIG_MODULE_SRCVERSION_ALL is not set # CONFIG_KMOD is not set +CONFIG_STOP_MACHINE=y # # Block layer # -# CONFIG_LBD is not set +CONFIG_LBD=y +# CONFIG_BLK_DEV_IO_TRACE is not set +# CONFIG_LSF is not set # # IO Schedulers # CONFIG_IOSCHED_NOOP=y -# CONFIG_IOSCHED_AS is not set -# CONFIG_IOSCHED_DEADLINE is not set +CONFIG_IOSCHED_AS=y +CONFIG_IOSCHED_DEADLINE=y CONFIG_IOSCHED_CFQ=y -# CONFIG_DEFAULT_AS is not set +CONFIG_DEFAULT_AS=y # CONFIG_DEFAULT_DEADLINE is not set -CONFIG_DEFAULT_CFQ=y +# CONFIG_DEFAULT_CFQ is not set # CONFIG_DEFAULT_NOOP is not set -CONFIG_DEFAULT_IOSCHED="cfq" +CONFIG_DEFAULT_IOSCHED="anticipatory" # # Processor type and features # -CONFIG_X86_PC=y +CONFIG_SMP=y +# CONFIG_X86_PC is not set # CONFIG_X86_ELAN is not set # CONFIG_X86_VOYAGER is not set # CONFIG_X86_NUMAQ is not set # CONFIG_X86_SUMMIT is not set # CONFIG_X86_BIGSMP is not set # CONFIG_X86_VISWS is not set -# CONFIG_X86_GENERICARCH is not set +CONFIG_X86_GENERICARCH=y # CONFIG_X86_ES7000 is not set +CONFIG_X86_CYCLONE_TIMER=y # CONFIG_M386 is not set # CONFIG_M486 is not set # CONFIG_M586 is not set @@ -102,11 +114,11 @@ CONFIG_X86_PC=y # CONFIG_M586MMX is not set # CONFIG_M686 is not set # CONFIG_MPENTIUMII is not set -# CONFIG_MPENTIUMIII is not set +CONFIG_MPENTIUMIII=y # CONFIG_MPENTIUMM is not set # CONFIG_MPENTIUM4 is not set # CONFIG_MK6 is not set -CONFIG_MK7=y +# CONFIG_MK7 is not set # CONFIG_MK8 is not set # CONFIG_MCRUSOE is not set # CONFIG_MEFFICEON is not set @@ -117,10 +129,10 @@ CONFIG_MK7=y # CONFIG_MGEODE_LX is not set # CONFIG_MCYRIXIII is not set # CONFIG_MVIAC3_2 is not set -# CONFIG_X86_GENERIC is not set +CONFIG_X86_GENERIC=y CONFIG_X86_CMPXCHG=y CONFIG_X86_XADD=y -CONFIG_X86_L1_CACHE_SHIFT=6 +CONFIG_X86_L1_CACHE_SHIFT=7 CONFIG_RWSEM_XCHGADD_ALGORITHM=y CONFIG_GENERIC_CALIBRATE_DELAY=y CONFIG_X86_WP_WORKS_OK=y @@ -131,26 +143,28 @@ CONFIG_X86_CMPXCHG64=y CONFIG_X86_GOOD_APIC=y CONFIG_X86_INTEL_USERCOPY=y CONFIG_X86_USE_PPRO_CHECKSUM=y -CONFIG_X86_USE_3DNOW=y CONFIG_X86_TSC=y -# CONFIG_HPET_TIMER is not set -# CONFIG_SMP is not set -CONFIG_PREEMPT_NONE=y -# CONFIG_PREEMPT_VOLUNTARY is not set +CONFIG_HPET_TIMER=y +CONFIG_HPET_EMULATE_RTC=y +CONFIG_NR_CPUS=32 +CONFIG_SCHED_SMT=y +CONFIG_SCHED_MC=y +# CONFIG_PREEMPT_NONE is not set +CONFIG_PREEMPT_VOLUNTARY=y # CONFIG_PREEMPT is not set -CONFIG_X86_UP_APIC=y -CONFIG_X86_UP_IOAPIC=y +CONFIG_PREEMPT_BKL=y CONFIG_X86_LOCAL_APIC=y CONFIG_X86_IO_APIC=y CONFIG_X86_MCE=y CONFIG_X86_MCE_NONFATAL=y -# CONFIG_X86_MCE_P4THERMAL is not set +CONFIG_X86_MCE_P4THERMAL=y +CONFIG_VM86=y # CONFIG_TOSHIBA is not set # CONFIG_I8K is not set # CONFIG_X86_REBOOTFIXUPS is not set -# CONFIG_MICROCODE is not set -# CONFIG_X86_MSR is not set -# CONFIG_X86_CPUID is not set +CONFIG_MICROCODE=y +CONFIG_X86_MSR=y +CONFIG_X86_CPUID=y # # Firmware Drivers @@ -158,68 +172,67 @@ CONFIG_X86_MCE_NONFATAL=y # CONFIG_EDD is not set # CONFIG_DELL_RBU is not set # CONFIG_DCDBAS is not set -CONFIG_NOHIGHMEM=y -# CONFIG_HIGHMEM4G is not set +# CONFIG_NOHIGHMEM is not set +CONFIG_HIGHMEM4G=y # CONFIG_HIGHMEM64G is not set -CONFIG_VMSPLIT_3G=y -# CONFIG_VMSPLIT_3G_OPT is not set -# CONFIG_VMSPLIT_2G is not set -# CONFIG_VMSPLIT_1G is not set CONFIG_PAGE_OFFSET=0xC0000000 -CONFIG_ARCH_FLATMEM_ENABLE=y -CONFIG_ARCH_SPARSEMEM_ENABLE=y -CONFIG_ARCH_SELECT_MEMORY_MODEL=y +CONFIG_HIGHMEM=y CONFIG_SELECT_MEMORY_MODEL=y CONFIG_FLATMEM_MANUAL=y # CONFIG_DISCONTIGMEM_MANUAL is not set # CONFIG_SPARSEMEM_MANUAL is not set CONFIG_FLATMEM=y CONFIG_FLAT_NODE_MEM_MAP=y -CONFIG_SPARSEMEM_STATIC=y +# CONFIG_SPARSEMEM_STATIC is not set CONFIG_SPLIT_PTLOCK_CPUS=4 +CONFIG_RESOURCES_64BIT=y +# CONFIG_HIGHPTE is not set # CONFIG_MATH_EMULATION is not set CONFIG_MTRR=y # CONFIG_EFI is not set +# CONFIG_IRQBALANCE is not set CONFIG_REGPARM=y -# CONFIG_SECCOMP is not set -CONFIG_HZ_100=y -# CONFIG_HZ_250 is not set +CONFIG_SECCOMP=y +# CONFIG_HZ_100 is not set +CONFIG_HZ_250=y # CONFIG_HZ_1000 is not set -CONFIG_HZ=100 +CONFIG_HZ=250 # CONFIG_KEXEC is not set +# CONFIG_CRASH_DUMP is not set CONFIG_PHYSICAL_START=0x100000 -CONFIG_DOUBLEFAULT=y +# CONFIG_HOTPLUG_CPU is not set +CONFIG_COMPAT_VDSO=y +CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y # # Power management options (ACPI, APM) # CONFIG_PM=y -# CONFIG_PM_LEGACY is not set +CONFIG_PM_LEGACY=y # CONFIG_PM_DEBUG is not set -CONFIG_SOFTWARE_SUSPEND=y -CONFIG_PM_STD_PARTITION="" # # ACPI (Advanced Configuration and Power Interface) Support # CONFIG_ACPI=y -# CONFIG_ACPI_SLEEP is not set -# CONFIG_ACPI_AC is not set -# CONFIG_ACPI_BATTERY is not set -# CONFIG_ACPI_BUTTON is not set +CONFIG_ACPI_AC=y +CONFIG_ACPI_BATTERY=y +CONFIG_ACPI_BUTTON=y # CONFIG_ACPI_VIDEO is not set # CONFIG_ACPI_HOTKEY is not set -# CONFIG_ACPI_FAN is not set -# CONFIG_ACPI_PROCESSOR is not set +CONFIG_ACPI_FAN=y +# CONFIG_ACPI_DOCK is not set +CONFIG_ACPI_PROCESSOR=y +CONFIG_ACPI_THERMAL=y # CONFIG_ACPI_ASUS is not set # CONFIG_ACPI_IBM is not set # CONFIG_ACPI_TOSHIBA is not set -CONFIG_ACPI_BLACKLIST_YEAR=0 -# CONFIG_ACPI_DEBUG is not set +CONFIG_ACPI_BLACKLIST_YEAR=2001 +CONFIG_ACPI_DEBUG=y CONFIG_ACPI_EC=y CONFIG_ACPI_POWER=y CONFIG_ACPI_SYSTEM=y -# CONFIG_X86_PM_TIMER is not set +CONFIG_X86_PM_TIMER=y # CONFIG_ACPI_CONTAINER is not set # @@ -230,7 +243,41 @@ CONFIG_ACPI_SYSTEM=y # # CPU Frequency scaling # -# CONFIG_CPU_FREQ is not set +CONFIG_CPU_FREQ=y +CONFIG_CPU_FREQ_TABLE=y +CONFIG_CPU_FREQ_DEBUG=y +CONFIG_CPU_FREQ_STAT=y +# CONFIG_CPU_FREQ_STAT_DETAILS is not set +CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y +# CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set +CONFIG_CPU_FREQ_GOV_PERFORMANCE=y +# CONFIG_CPU_FREQ_GOV_POWERSAVE is not set +CONFIG_CPU_FREQ_GOV_USERSPACE=y +CONFIG_CPU_FREQ_GOV_ONDEMAND=y +# CONFIG_CPU_FREQ_GOV_CONSERVATIVE is not set + +# +# CPUFreq processor drivers +# +CONFIG_X86_ACPI_CPUFREQ=y +# CONFIG_X86_POWERNOW_K6 is not set +# CONFIG_X86_POWERNOW_K7 is not set +CONFIG_X86_POWERNOW_K8=y +CONFIG_X86_POWERNOW_K8_ACPI=y +# CONFIG_X86_GX_SUSPMOD is not set +# CONFIG_X86_SPEEDSTEP_CENTRINO is not set +# CONFIG_X86_SPEEDSTEP_ICH is not set +# CONFIG_X86_SPEEDSTEP_SMI is not set +# CONFIG_X86_P4_CLOCKMOD is not set +# CONFIG_X86_CPUFREQ_NFORCE2 is not set +# CONFIG_X86_LONGRUN is not set +# CONFIG_X86_LONGHAUL is not set + +# +# shared options +# +CONFIG_X86_ACPI_CPUFREQ_PROC_INTF=y +# CONFIG_X86_SPEEDSTEP_LIB is not set # # Bus options (PCI, PCMCIA, EISA, MCA, ISA) @@ -244,12 +291,13 @@ CONFIG_PCI_BIOS=y CONFIG_PCI_DIRECT=y CONFIG_PCI_MMCONFIG=y # CONFIG_PCIEPORTBUS is not set -# CONFIG_PCI_MSI is not set -# CONFIG_PCI_LEGACY_PROC is not set +CONFIG_PCI_MSI=y +# CONFIG_PCI_DEBUG is not set CONFIG_ISA_DMA_API=y # CONFIG_ISA is not set # CONFIG_MCA is not set # CONFIG_SCx200 is not set +CONFIG_K8_NB=y # # PCCARD (PCMCIA/CardBus) support @@ -278,93 +326,54 @@ CONFIG_NET=y # # CONFIG_NETDEBUG is not set CONFIG_PACKET=y -CONFIG_PACKET_MMAP=y +# CONFIG_PACKET_MMAP is not set CONFIG_UNIX=y +CONFIG_XFRM=y +# CONFIG_XFRM_USER is not set +# CONFIG_XFRM_SUB_POLICY is not set # CONFIG_NET_KEY is not set CONFIG_INET=y -# CONFIG_IP_MULTICAST is not set +CONFIG_IP_MULTICAST=y # CONFIG_IP_ADVANCED_ROUTER is not set CONFIG_IP_FIB_HASH=y -# CONFIG_IP_PNP is not set +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +# CONFIG_IP_PNP_BOOTP is not set +# CONFIG_IP_PNP_RARP is not set # CONFIG_NET_IPIP is not set # CONFIG_NET_IPGRE is not set +# CONFIG_IP_MROUTE is not set # CONFIG_ARPD is not set # CONFIG_SYN_COOKIES is not set # CONFIG_INET_AH is not set # CONFIG_INET_ESP is not set # CONFIG_INET_IPCOMP is not set +# CONFIG_INET_XFRM_TUNNEL is not set # CONFIG_INET_TUNNEL is not set -# CONFIG_INET_DIAG is not set +CONFIG_INET_XFRM_MODE_TRANSPORT=y +CONFIG_INET_XFRM_MODE_TUNNEL=y +CONFIG_INET_DIAG=y +CONFIG_INET_TCP_DIAG=y # CONFIG_TCP_CONG_ADVANCED is not set -CONFIG_TCP_CONG_BIC=y - -# -# IP: Virtual Server Configuration -# -# CONFIG_IP_VS is not set -# CONFIG_IPV6 is not set -CONFIG_NETFILTER=y -# CONFIG_NETFILTER_DEBUG is not set - -# -# Core Netfilter Configuration -# -# CONFIG_NETFILTER_NETLINK is not set -CONFIG_NETFILTER_XTABLES=y -# CONFIG_NETFILTER_XT_TARGET_CLASSIFY is not set -# CONFIG_NETFILTER_XT_TARGET_MARK is not set -# CONFIG_NETFILTER_XT_TARGET_NFQUEUE is not set -# CONFIG_NETFILTER_XT_MATCH_COMMENT is not set -# CONFIG_NETFILTER_XT_MATCH_CONNTRACK is not set -# CONFIG_NETFILTER_XT_MATCH_DCCP is not set -# CONFIG_NETFILTER_XT_MATCH_HELPER is not set -# CONFIG_NETFILTER_XT_MATCH_LENGTH is not set -CONFIG_NETFILTER_XT_MATCH_LIMIT=y -CONFIG_NETFILTER_XT_MATCH_MAC=y -# CONFIG_NETFILTER_XT_MATCH_MARK is not set -# CONFIG_NETFILTER_XT_MATCH_PKTTYPE is not set -# CONFIG_NETFILTER_XT_MATCH_REALM is not set -# CONFIG_NETFILTER_XT_MATCH_SCTP is not set -CONFIG_NETFILTER_XT_MATCH_STATE=y -# CONFIG_NETFILTER_XT_MATCH_STRING is not set -# CONFIG_NETFILTER_XT_MATCH_TCPMSS is not set - -# -# IP: Netfilter Configuration -# -CONFIG_IP_NF_CONNTRACK=y -# CONFIG_IP_NF_CT_ACCT is not set -# CONFIG_IP_NF_CONNTRACK_MARK is not set -# CONFIG_IP_NF_CONNTRACK_EVENTS is not set -# CONFIG_IP_NF_CT_PROTO_SCTP is not set -CONFIG_IP_NF_FTP=y -# CONFIG_IP_NF_IRC is not set -# CONFIG_IP_NF_NETBIOS_NS is not set -# CONFIG_IP_NF_TFTP is not set -# CONFIG_IP_NF_AMANDA is not set -# CONFIG_IP_NF_PPTP is not set -# CONFIG_IP_NF_QUEUE is not set -CONFIG_IP_NF_IPTABLES=y -# CONFIG_IP_NF_MATCH_IPRANGE is not set -# CONFIG_IP_NF_MATCH_MULTIPORT is not set -# CONFIG_IP_NF_MATCH_TOS is not set -# CONFIG_IP_NF_MATCH_RECENT is not set -# CONFIG_IP_NF_MATCH_ECN is not set -# CONFIG_IP_NF_MATCH_DSCP is not set -# CONFIG_IP_NF_MATCH_AH_ESP is not set -# CONFIG_IP_NF_MATCH_TTL is not set -# CONFIG_IP_NF_MATCH_OWNER is not set -# CONFIG_IP_NF_MATCH_ADDRTYPE is not set -# CONFIG_IP_NF_MATCH_HASHLIMIT is not set -CONFIG_IP_NF_FILTER=y -# CONFIG_IP_NF_TARGET_REJECT is not set -CONFIG_IP_NF_TARGET_LOG=y -# CONFIG_IP_NF_TARGET_ULOG is not set -# CONFIG_IP_NF_TARGET_TCPMSS is not set -# CONFIG_IP_NF_NAT is not set -# CONFIG_IP_NF_MANGLE is not set -# CONFIG_IP_NF_RAW is not set -# CONFIG_IP_NF_ARPTABLES is not set +CONFIG_TCP_CONG_CUBIC=y +CONFIG_DEFAULT_TCP_CONG="cubic" +CONFIG_IPV6=y +# CONFIG_IPV6_PRIVACY is not set +# CONFIG_IPV6_ROUTER_PREF is not set +# CONFIG_INET6_AH is not set +# CONFIG_INET6_ESP is not set +# CONFIG_INET6_IPCOMP is not set +# CONFIG_IPV6_MIP6 is not set +# CONFIG_INET6_XFRM_TUNNEL is not set +# CONFIG_INET6_TUNNEL is not set +CONFIG_INET6_XFRM_MODE_TRANSPORT=y +CONFIG_INET6_XFRM_MODE_TUNNEL=y +# CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION is not set +# CONFIG_IPV6_TUNNEL is not set +# CONFIG_IPV6_SUBTREES is not set +# CONFIG_IPV6_MULTIPLE_TABLES is not set +# CONFIG_NETWORK_SECMARK is not set +# CONFIG_NETFILTER is not set # # DCCP Configuration (EXPERIMENTAL) @@ -389,7 +398,6 @@ CONFIG_IP_NF_TARGET_LOG=y # CONFIG_ATALK is not set # CONFIG_X25 is not set # CONFIG_LAPB is not set -# CONFIG_NET_DIVERT is not set # CONFIG_ECONET is not set # CONFIG_WAN_ROUTER is not set @@ -402,6 +410,7 @@ CONFIG_IP_NF_TARGET_LOG=y # Network testing # # CONFIG_NET_PKTGEN is not set +# CONFIG_NET_TCPPROBE is not set # CONFIG_HAMRADIO is not set # CONFIG_IRDA is not set # CONFIG_BT is not set @@ -416,7 +425,9 @@ CONFIG_IP_NF_TARGET_LOG=y # CONFIG_STANDALONE=y CONFIG_PREVENT_FIRMWARE_BUILD=y -# CONFIG_FW_LOADER is not set +CONFIG_FW_LOADER=y +# CONFIG_DEBUG_DRIVER is not set +# CONFIG_SYS_HYPERVISOR is not set # # Connector - unified userspace <-> kernelspace linker @@ -431,13 +442,7 @@ CONFIG_PREVENT_FIRMWARE_BUILD=y # # Parallel port support # -CONFIG_PARPORT=y -CONFIG_PARPORT_PC=y -# CONFIG_PARPORT_SERIAL is not set -# CONFIG_PARPORT_PC_FIFO is not set -# CONFIG_PARPORT_PC_SUPERIO is not set -# CONFIG_PARPORT_GSC is not set -CONFIG_PARPORT_1284=y +# CONFIG_PARPORT is not set # # Plug and Play support @@ -447,8 +452,7 @@ CONFIG_PARPORT_1284=y # # Block devices # -# CONFIG_BLK_DEV_FD is not set -# CONFIG_PARIDE is not set +CONFIG_BLK_DEV_FD=y # CONFIG_BLK_CPQ_DA is not set # CONFIG_BLK_CPQ_CISS_DA is not set # CONFIG_BLK_DEV_DAC960 is not set @@ -459,8 +463,11 @@ CONFIG_BLK_DEV_LOOP=y # CONFIG_BLK_DEV_NBD is not set # CONFIG_BLK_DEV_SX8 is not set # CONFIG_BLK_DEV_UB is not set -# CONFIG_BLK_DEV_RAM is not set +CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_COUNT=16 +CONFIG_BLK_DEV_RAM_SIZE=4096 +CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024 +CONFIG_BLK_DEV_INITRD=y # CONFIG_CDROM_PKTCDVD is not set # CONFIG_ATA_OVER_ETH is not set @@ -476,7 +483,7 @@ CONFIG_BLK_DEV_IDE=y # CONFIG_BLK_DEV_IDE_SATA is not set # CONFIG_BLK_DEV_HD_IDE is not set CONFIG_BLK_DEV_IDEDISK=y -# CONFIG_IDEDISK_MULTI_MODE is not set +CONFIG_IDEDISK_MULTI_MODE=y CONFIG_BLK_DEV_IDECD=y # CONFIG_BLK_DEV_IDETAPE is not set # CONFIG_BLK_DEV_IDEFLOPPY is not set @@ -486,10 +493,10 @@ CONFIG_BLK_DEV_IDECD=y # # IDE chipset support/bugfixes # -# CONFIG_IDE_GENERIC is not set +CONFIG_IDE_GENERIC=y # CONFIG_BLK_DEV_CMD640 is not set CONFIG_BLK_DEV_IDEPCI=y -CONFIG_IDEPCI_SHARE_IRQ=y +# CONFIG_IDEPCI_SHARE_IRQ is not set # CONFIG_BLK_DEV_OFFBOARD is not set # CONFIG_BLK_DEV_GENERIC is not set # CONFIG_BLK_DEV_OPTI621 is not set @@ -500,7 +507,7 @@ CONFIG_IDEDMA_PCI_AUTO=y # CONFIG_IDEDMA_ONLYDISK is not set # CONFIG_BLK_DEV_AEC62XX is not set # CONFIG_BLK_DEV_ALI15X3 is not set -# CONFIG_BLK_DEV_AMD74XX is not set +CONFIG_BLK_DEV_AMD74XX=y # CONFIG_BLK_DEV_ATIIXP is not set # CONFIG_BLK_DEV_CMD64X is not set # CONFIG_BLK_DEV_TRIFLEX is not set @@ -511,7 +518,7 @@ CONFIG_IDEDMA_PCI_AUTO=y # CONFIG_BLK_DEV_HPT34X is not set # CONFIG_BLK_DEV_HPT366 is not set # CONFIG_BLK_DEV_SC1200 is not set -# CONFIG_BLK_DEV_PIIX is not set +CONFIG_BLK_DEV_PIIX=y # CONFIG_BLK_DEV_IT821X is not set # CONFIG_BLK_DEV_NS87415 is not set # CONFIG_BLK_DEV_PDC202XX_OLD is not set @@ -521,7 +528,7 @@ CONFIG_IDEDMA_PCI_AUTO=y # CONFIG_BLK_DEV_SIS5513 is not set # CONFIG_BLK_DEV_SLC90E66 is not set # CONFIG_BLK_DEV_TRM290 is not set -CONFIG_BLK_DEV_VIA82CXXX=y +# CONFIG_BLK_DEV_VIA82CXXX is not set # CONFIG_IDE_ARM is not set CONFIG_BLK_DEV_IDEDMA=y # CONFIG_IDEDMA_IVB is not set @@ -533,6 +540,7 @@ CONFIG_IDEDMA_AUTO=y # # CONFIG_RAID_ATTRS is not set CONFIG_SCSI=y +CONFIG_SCSI_NETLINK=y # CONFIG_SCSI_PROC_FS is not set # @@ -541,8 +549,9 @@ CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y # CONFIG_CHR_DEV_ST is not set # CONFIG_CHR_DEV_OSST is not set -# CONFIG_BLK_DEV_SR is not set -# CONFIG_CHR_DEV_SG is not set +CONFIG_BLK_DEV_SR=y +# CONFIG_BLK_DEV_SR_VENDOR is not set +CONFIG_CHR_DEV_SG=y # CONFIG_CHR_DEV_SCH is not set # @@ -553,29 +562,44 @@ CONFIG_BLK_DEV_SD=y # CONFIG_SCSI_LOGGING is not set # -# SCSI Transport Attributes +# SCSI Transports # -# CONFIG_SCSI_SPI_ATTRS is not set -# CONFIG_SCSI_FC_ATTRS is not set +CONFIG_SCSI_SPI_ATTRS=y +CONFIG_SCSI_FC_ATTRS=y # CONFIG_SCSI_ISCSI_ATTRS is not set # CONFIG_SCSI_SAS_ATTRS is not set +# CONFIG_SCSI_SAS_LIBSAS is not set # # SCSI low-level drivers # # CONFIG_ISCSI_TCP is not set -# CONFIG_BLK_DEV_3W_XXXX_RAID is not set +CONFIG_BLK_DEV_3W_XXXX_RAID=y # CONFIG_SCSI_3W_9XXX is not set # CONFIG_SCSI_ACARD is not set # CONFIG_SCSI_AACRAID is not set -# CONFIG_SCSI_AIC7XXX is not set +CONFIG_SCSI_AIC7XXX=y +CONFIG_AIC7XXX_CMDS_PER_DEVICE=32 +CONFIG_AIC7XXX_RESET_DELAY_MS=5000 +CONFIG_AIC7XXX_DEBUG_ENABLE=y +CONFIG_AIC7XXX_DEBUG_MASK=0 +CONFIG_AIC7XXX_REG_PRETTY_PRINT=y # CONFIG_SCSI_AIC7XXX_OLD is not set -# CONFIG_SCSI_AIC79XX is not set +CONFIG_SCSI_AIC79XX=y +CONFIG_AIC79XX_CMDS_PER_DEVICE=32 +CONFIG_AIC79XX_RESET_DELAY_MS=4000 +# CONFIG_AIC79XX_ENABLE_RD_STRM is not set +# CONFIG_AIC79XX_DEBUG_ENABLE is not set +CONFIG_AIC79XX_DEBUG_MASK=0 +# CONFIG_AIC79XX_REG_PRETTY_PRINT is not set +# CONFIG_SCSI_AIC94XX is not set # CONFIG_SCSI_DPT_I2O is not set +# CONFIG_SCSI_ADVANSYS is not set +# CONFIG_SCSI_ARCMSR is not set # CONFIG_MEGARAID_NEWGEN is not set # CONFIG_MEGARAID_LEGACY is not set # CONFIG_MEGARAID_SAS is not set -# CONFIG_SCSI_SATA is not set +# CONFIG_SCSI_HPTIOP is not set # CONFIG_SCSI_BUSLOGIC is not set # CONFIG_SCSI_DMX3191D is not set # CONFIG_SCSI_EATA is not set @@ -584,11 +608,9 @@ CONFIG_BLK_DEV_SD=y # CONFIG_SCSI_IPS is not set # CONFIG_SCSI_INITIO is not set # CONFIG_SCSI_INIA100 is not set -# CONFIG_SCSI_PPA is not set -# CONFIG_SCSI_IMM is not set +# CONFIG_SCSI_STEX is not set # CONFIG_SCSI_SYM53C8XX_2 is not set # CONFIG_SCSI_IPR is not set -# CONFIG_SCSI_QLOGIC_FC is not set # CONFIG_SCSI_QLOGIC_1280 is not set # CONFIG_SCSI_QLA_FC is not set # CONFIG_SCSI_LPFC is not set @@ -598,22 +620,114 @@ CONFIG_BLK_DEV_SD=y # CONFIG_SCSI_DEBUG is not set # +# Serial ATA (prod) and Parallel ATA (experimental) drivers +# +CONFIG_ATA=y +CONFIG_SATA_AHCI=y +CONFIG_SATA_SVW=y +CONFIG_ATA_PIIX=y +# CONFIG_SATA_MV is not set +CONFIG_SATA_NV=y +# CONFIG_PDC_ADMA is not set +# CONFIG_SATA_QSTOR is not set +# CONFIG_SATA_PROMISE is not set +# CONFIG_SATA_SX4 is not set +CONFIG_SATA_SIL=y +# CONFIG_SATA_SIL24 is not set +# CONFIG_SATA_SIS is not set +# CONFIG_SATA_ULI is not set +CONFIG_SATA_VIA=y +# CONFIG_SATA_VITESSE is not set +CONFIG_SATA_INTEL_COMBINED=y +# CONFIG_PATA_ALI is not set +# CONFIG_PATA_AMD is not set +# CONFIG_PATA_ARTOP is not set +# CONFIG_PATA_ATIIXP is not set +# CONFIG_PATA_CMD64X is not set +# CONFIG_PATA_CS5520 is not set +# CONFIG_PATA_CS5530 is not set +# CONFIG_PATA_CS5535 is not set +# CONFIG_PATA_CYPRESS is not set +# CONFIG_PATA_EFAR is not set +# CONFIG_ATA_GENERIC is not set +# CONFIG_PATA_HPT366 is not set +# CONFIG_PATA_HPT37X is not set +# CONFIG_PATA_HPT3X2N is not set +# CONFIG_PATA_HPT3X3 is not set +# CONFIG_PATA_IT821X is not set +# CONFIG_PATA_JMICRON is not set +# CONFIG_PATA_LEGACY is not set +# CONFIG_PATA_TRIFLEX is not set +# CONFIG_PATA_MPIIX is not set +# CONFIG_PATA_OLDPIIX is not set +# CONFIG_PATA_NETCELL is not set +# CONFIG_PATA_NS87410 is not set +# CONFIG_PATA_OPTI is not set +# CONFIG_PATA_OPTIDMA is not set +# CONFIG_PATA_PDC_OLD is not set +# CONFIG_PATA_QDI is not set +# CONFIG_PATA_RADISYS is not set +# CONFIG_PATA_RZ1000 is not set +# CONFIG_PATA_SC1200 is not set +# CONFIG_PATA_SERVERWORKS is not set +# CONFIG_PATA_PDC2027X is not set +# CONFIG_PATA_SIL680 is not set +# CONFIG_PATA_SIS is not set +# CONFIG_PATA_VIA is not set +# CONFIG_PATA_WINBOND is not set + +# # Multi-device support (RAID and LVM) # -# CONFIG_MD is not set +CONFIG_MD=y +# CONFIG_BLK_DEV_MD is not set +CONFIG_BLK_DEV_DM=y +# CONFIG_DM_CRYPT is not set +# CONFIG_DM_SNAPSHOT is not set +# CONFIG_DM_MIRROR is not set +# CONFIG_DM_ZERO is not set +# CONFIG_DM_MULTIPATH is not set # # Fusion MPT device support # -# CONFIG_FUSION is not set -# CONFIG_FUSION_SPI is not set +CONFIG_FUSION=y +CONFIG_FUSION_SPI=y # CONFIG_FUSION_FC is not set # CONFIG_FUSION_SAS is not set +CONFIG_FUSION_MAX_SGE=128 +# CONFIG_FUSION_CTL is not set # # IEEE 1394 (FireWire) support # -# CONFIG_IEEE1394 is not set +CONFIG_IEEE1394=y + +# +# Subsystem Options +# +# CONFIG_IEEE1394_VERBOSEDEBUG is not set +# CONFIG_IEEE1394_OUI_DB is not set +# CONFIG_IEEE1394_EXTRA_CONFIG_ROMS is not set +# CONFIG_IEEE1394_EXPORT_FULL_API is not set + +# +# Device Drivers +# + +# +# Texas Instruments PCILynx requires I2C +# +CONFIG_IEEE1394_OHCI1394=y + +# +# Protocol Drivers +# +# CONFIG_IEEE1394_VIDEO1394 is not set +# CONFIG_IEEE1394_SBP2 is not set +# CONFIG_IEEE1394_ETH1394 is not set +# CONFIG_IEEE1394_DV1394 is not set +CONFIG_IEEE1394_RAWIO=y # # I2O device support @@ -652,46 +766,63 @@ CONFIG_MII=y # # Tulip family network device support # -# CONFIG_NET_TULIP is not set +CONFIG_NET_TULIP=y +# CONFIG_DE2104X is not set +CONFIG_TULIP=y +# CONFIG_TULIP_MWI is not set +# CONFIG_TULIP_MMIO is not set +# CONFIG_TULIP_NAPI is not set +# CONFIG_DE4X5 is not set +# CONFIG_WINBOND_840 is not set +# CONFIG_DM9102 is not set +# CONFIG_ULI526X is not set # CONFIG_HP100 is not set CONFIG_NET_PCI=y # CONFIG_PCNET32 is not set # CONFIG_AMD8111_ETH is not set # CONFIG_ADAPTEC_STARFIRE is not set -# CONFIG_B44 is not set -# CONFIG_FORCEDETH is not set +CONFIG_B44=y +CONFIG_FORCEDETH=y +# CONFIG_FORCEDETH_NAPI is not set # CONFIG_DGRS is not set # CONFIG_EEPRO100 is not set CONFIG_E100=y # CONFIG_FEALNX is not set # CONFIG_NATSEMI is not set # CONFIG_NE2K_PCI is not set -# CONFIG_8139CP is not set -# CONFIG_8139TOO is not set +CONFIG_8139CP=y +CONFIG_8139TOO=y +# CONFIG_8139TOO_PIO is not set +# CONFIG_8139TOO_TUNE_TWISTER is not set +# CONFIG_8139TOO_8129 is not set +# CONFIG_8139_OLD_RX_RESET is not set # CONFIG_SIS900 is not set # CONFIG_EPIC100 is not set # CONFIG_SUNDANCE is not set # CONFIG_TLAN is not set # CONFIG_VIA_RHINE is not set -# CONFIG_NET_POCKET is not set # # Ethernet (1000 Mbit) # # CONFIG_ACENIC is not set # CONFIG_DL2K is not set -# CONFIG_E1000 is not set +CONFIG_E1000=y +# CONFIG_E1000_NAPI is not set +# CONFIG_E1000_DISABLE_PACKET_SPLIT is not set # CONFIG_NS83820 is not set # CONFIG_HAMACHI is not set # CONFIG_YELLOWFIN is not set -# CONFIG_R8169 is not set +CONFIG_R8169=y +# CONFIG_R8169_NAPI is not set # CONFIG_SIS190 is not set # CONFIG_SKGE is not set -# CONFIG_SKY2 is not set +CONFIG_SKY2=y # CONFIG_SK98LIN is not set # CONFIG_VIA_VELOCITY is not set -# CONFIG_TIGON3 is not set -# CONFIG_BNX2 is not set +CONFIG_TIGON3=y +CONFIG_BNX2=y +# CONFIG_QLA3XXX is not set # # Ethernet (10000 Mbit) @@ -699,6 +830,7 @@ CONFIG_E100=y # CONFIG_CHELSIO_T1 is not set # CONFIG_IXGB is not set # CONFIG_S2IO is not set +# CONFIG_MYRI10GE is not set # # Token Ring devices @@ -716,14 +848,15 @@ CONFIG_E100=y # CONFIG_WAN is not set # CONFIG_FDDI is not set # CONFIG_HIPPI is not set -# CONFIG_PLIP is not set # CONFIG_PPP is not set # CONFIG_SLIP is not set # CONFIG_NET_FC is not set # CONFIG_SHAPER is not set -# CONFIG_NETCONSOLE is not set -# CONFIG_NETPOLL is not set -# CONFIG_NET_POLL_CONTROLLER is not set +CONFIG_NETCONSOLE=y +CONFIG_NETPOLL=y +# CONFIG_NETPOLL_RX is not set +# CONFIG_NETPOLL_TRAP is not set +CONFIG_NET_POLL_CONTROLLER=y # # ISDN subsystem @@ -745,8 +878,8 @@ CONFIG_INPUT=y # CONFIG_INPUT_MOUSEDEV=y CONFIG_INPUT_MOUSEDEV_PSAUX=y -CONFIG_INPUT_MOUSEDEV_SCREEN_X=1280 -CONFIG_INPUT_MOUSEDEV_SCREEN_Y=1024 +CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024 +CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768 # CONFIG_INPUT_JOYDEV is not set # CONFIG_INPUT_TSDEV is not set CONFIG_INPUT_EVDEV=y @@ -776,7 +909,6 @@ CONFIG_SERIO=y CONFIG_SERIO_I8042=y # CONFIG_SERIO_SERPORT is not set # CONFIG_SERIO_CT82C710 is not set -# CONFIG_SERIO_PARKBD is not set # CONFIG_SERIO_PCIPS2 is not set CONFIG_SERIO_LIBPS2=y # CONFIG_SERIO_RAW is not set @@ -788,14 +920,15 @@ CONFIG_SERIO_LIBPS2=y CONFIG_VT=y CONFIG_VT_CONSOLE=y CONFIG_HW_CONSOLE=y +# CONFIG_VT_HW_CONSOLE_BINDING is not set # CONFIG_SERIAL_NONSTANDARD is not set # # Serial drivers # CONFIG_SERIAL_8250=y -# CONFIG_SERIAL_8250_CONSOLE is not set -# CONFIG_SERIAL_8250_ACPI is not set +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_PCI=y CONFIG_SERIAL_8250_NR_UARTS=4 CONFIG_SERIAL_8250_RUNTIME_UARTS=4 # CONFIG_SERIAL_8250_EXTENDED is not set @@ -804,14 +937,11 @@ CONFIG_SERIAL_8250_RUNTIME_UARTS=4 # Non-8250 serial port support # CONFIG_SERIAL_CORE=y +CONFIG_SERIAL_CORE_CONSOLE=y # CONFIG_SERIAL_JSM is not set CONFIG_UNIX98_PTYS=y CONFIG_LEGACY_PTYS=y CONFIG_LEGACY_PTY_COUNT=256 -CONFIG_PRINTER=y -# CONFIG_LP_CONSOLE is not set -# CONFIG_PPDEV is not set -# CONFIG_TIPAR is not set # # IPMI @@ -822,8 +952,12 @@ CONFIG_PRINTER=y # Watchdog Cards # # CONFIG_WATCHDOG is not set -# CONFIG_HW_RANDOM is not set -CONFIG_NVRAM=y +CONFIG_HW_RANDOM=y +CONFIG_HW_RANDOM_INTEL=y +CONFIG_HW_RANDOM_AMD=y +CONFIG_HW_RANDOM_GEODE=y +CONFIG_HW_RANDOM_VIA=y +# CONFIG_NVRAM is not set CONFIG_RTC=y # CONFIG_DTLK is not set # CONFIG_R3964 is not set @@ -833,31 +967,28 @@ CONFIG_RTC=y # # Ftape, the floppy tape device driver # -# CONFIG_FTAPE is not set CONFIG_AGP=y # CONFIG_AGP_ALI is not set # CONFIG_AGP_ATI is not set # CONFIG_AGP_AMD is not set -# CONFIG_AGP_AMD64 is not set -# CONFIG_AGP_INTEL is not set +CONFIG_AGP_AMD64=y +CONFIG_AGP_INTEL=y # CONFIG_AGP_NVIDIA is not set # CONFIG_AGP_SIS is not set # CONFIG_AGP_SWORKS is not set -CONFIG_AGP_VIA=y +# CONFIG_AGP_VIA is not set # CONFIG_AGP_EFFICEON is not set -CONFIG_DRM=y -# CONFIG_DRM_TDFX is not set -# CONFIG_DRM_R128 is not set -CONFIG_DRM_RADEON=y -# CONFIG_DRM_MGA is not set -# CONFIG_DRM_SIS is not set -# CONFIG_DRM_VIA is not set -# CONFIG_DRM_SAVAGE is not set +# CONFIG_DRM is not set # CONFIG_MWAVE is not set +# CONFIG_PC8736x_GPIO is not set +# CONFIG_NSC_GPIO is not set # CONFIG_CS5535_GPIO is not set -# CONFIG_RAW_DRIVER is not set -# CONFIG_HPET is not set -# CONFIG_HANGCHECK_TIMER is not set +CONFIG_RAW_DRIVER=y +CONFIG_MAX_RAW_DEVS=256 +CONFIG_HPET=y +# CONFIG_HPET_RTC_IRQ is not set +CONFIG_HPET_MMAP=y +CONFIG_HANGCHECK_TIMER=y # # TPM devices @@ -868,59 +999,7 @@ CONFIG_DRM_RADEON=y # # I2C support # -CONFIG_I2C=y -CONFIG_I2C_CHARDEV=y - -# -# I2C Algorithms -# -CONFIG_I2C_ALGOBIT=y -# CONFIG_I2C_ALGOPCF is not set -# CONFIG_I2C_ALGOPCA is not set - -# -# I2C Hardware Bus support -# -# CONFIG_I2C_ALI1535 is not set -# CONFIG_I2C_ALI1563 is not set -# CONFIG_I2C_ALI15X3 is not set -# CONFIG_I2C_AMD756 is not set -# CONFIG_I2C_AMD8111 is not set -# CONFIG_I2C_I801 is not set -# CONFIG_I2C_I810 is not set -# CONFIG_I2C_PIIX4 is not set -CONFIG_I2C_ISA=y -# CONFIG_I2C_NFORCE2 is not set -# CONFIG_I2C_PARPORT is not set -# CONFIG_I2C_PARPORT_LIGHT is not set -# CONFIG_I2C_PROSAVAGE is not set -# CONFIG_I2C_SAVAGE4 is not set -# CONFIG_SCx200_ACB is not set -# CONFIG_I2C_SIS5595 is not set -# CONFIG_I2C_SIS630 is not set -# CONFIG_I2C_SIS96X is not set -# CONFIG_I2C_STUB is not set -# CONFIG_I2C_VIA is not set -CONFIG_I2C_VIAPRO=y -# CONFIG_I2C_VOODOO3 is not set -# CONFIG_I2C_PCA_ISA is not set - -# -# Miscellaneous I2C Chip support -# -# CONFIG_SENSORS_DS1337 is not set -# CONFIG_SENSORS_DS1374 is not set -# CONFIG_SENSORS_EEPROM is not set -# CONFIG_SENSORS_PCF8574 is not set -# CONFIG_SENSORS_PCA9539 is not set -# CONFIG_SENSORS_PCF8591 is not set -# CONFIG_SENSORS_RTC8564 is not set -# CONFIG_SENSORS_MAX6875 is not set -# CONFIG_RTC_X1205_I2C is not set -# CONFIG_I2C_DEBUG_CORE is not set -# CONFIG_I2C_DEBUG_ALGO is not set -# CONFIG_I2C_DEBUG_BUS is not set -# CONFIG_I2C_DEBUG_CHIP is not set +# CONFIG_I2C is not set # # SPI support @@ -931,51 +1010,12 @@ CONFIG_I2C_VIAPRO=y # # Dallas's 1-wire bus # -# CONFIG_W1 is not set # # Hardware Monitoring support # -CONFIG_HWMON=y -CONFIG_HWMON_VID=y -# CONFIG_SENSORS_ADM1021 is not set -# CONFIG_SENSORS_ADM1025 is not set -# CONFIG_SENSORS_ADM1026 is not set -# CONFIG_SENSORS_ADM1031 is not set -# CONFIG_SENSORS_ADM9240 is not set -# CONFIG_SENSORS_ASB100 is not set -# CONFIG_SENSORS_ATXP1 is not set -# CONFIG_SENSORS_DS1621 is not set -# CONFIG_SENSORS_F71805F is not set -# CONFIG_SENSORS_FSCHER is not set -# CONFIG_SENSORS_FSCPOS is not set -# CONFIG_SENSORS_GL518SM is not set -# CONFIG_SENSORS_GL520SM is not set -CONFIG_SENSORS_IT87=y -# CONFIG_SENSORS_LM63 is not set -# CONFIG_SENSORS_LM75 is not set -# CONFIG_SENSORS_LM77 is not set -# CONFIG_SENSORS_LM78 is not set -# CONFIG_SENSORS_LM80 is not set -# CONFIG_SENSORS_LM83 is not set -# CONFIG_SENSORS_LM85 is not set -# CONFIG_SENSORS_LM87 is not set -# CONFIG_SENSORS_LM90 is not set -# CONFIG_SENSORS_LM92 is not set -# CONFIG_SENSORS_MAX1619 is not set -# CONFIG_SENSORS_PC87360 is not set -# CONFIG_SENSORS_SIS5595 is not set -# CONFIG_SENSORS_SMSC47M1 is not set -# CONFIG_SENSORS_SMSC47B397 is not set -# CONFIG_SENSORS_VIA686A is not set -# CONFIG_SENSORS_VT8231 is not set -# CONFIG_SENSORS_W83781D is not set -# CONFIG_SENSORS_W83792D is not set -# CONFIG_SENSORS_W83L785TS is not set -# CONFIG_SENSORS_W83627HF is not set -# CONFIG_SENSORS_W83627EHF is not set -# CONFIG_SENSORS_HDAPS is not set -# CONFIG_HWMON_DEBUG_CHIP is not set +# CONFIG_HWMON is not set +# CONFIG_HWMON_VID is not set # # Misc devices @@ -983,117 +1023,31 @@ CONFIG_SENSORS_IT87=y # CONFIG_IBM_ASM is not set # -# Multimedia Capabilities Port drivers -# - -# # Multimedia devices # -CONFIG_VIDEO_DEV=y - -# -# Video For Linux -# - -# -# Video Adapters -# -# CONFIG_VIDEO_ADV_DEBUG is not set -# CONFIG_VIDEO_BT848 is not set -# CONFIG_VIDEO_BWQCAM is not set -# CONFIG_VIDEO_CQCAM is not set -# CONFIG_VIDEO_W9966 is not set -# CONFIG_VIDEO_CPIA is not set -# CONFIG_VIDEO_SAA5246A is not set -# CONFIG_VIDEO_SAA5249 is not set -# CONFIG_TUNER_3036 is not set -# CONFIG_VIDEO_STRADIS is not set -# CONFIG_VIDEO_ZORAN is not set -CONFIG_VIDEO_SAA7134=y -# CONFIG_VIDEO_SAA7134_ALSA is not set -# CONFIG_VIDEO_MXB is not set -# CONFIG_VIDEO_DPC is not set -# CONFIG_VIDEO_HEXIUM_ORION is not set -# CONFIG_VIDEO_HEXIUM_GEMINI is not set -# CONFIG_VIDEO_CX88 is not set -# CONFIG_VIDEO_EM28XX is not set -# CONFIG_VIDEO_OVCAMCHIP is not set -# CONFIG_VIDEO_AUDIO_DECODER is not set -# CONFIG_VIDEO_DECODER is not set - -# -# Radio Adapters -# -# CONFIG_RADIO_GEMTEK_PCI is not set -# CONFIG_RADIO_MAXIRADIO is not set -# CONFIG_RADIO_MAESTRO is not set +# CONFIG_VIDEO_DEV is not set +CONFIG_VIDEO_V4L2=y # # Digital Video Broadcasting Devices # # CONFIG_DVB is not set -CONFIG_VIDEO_TUNER=y -CONFIG_VIDEO_BUF=y -CONFIG_VIDEO_IR=y +# CONFIG_USB_DABUSB is not set # # Graphics support # -CONFIG_FB=y -CONFIG_FB_CFB_FILLRECT=y -CONFIG_FB_CFB_COPYAREA=y -CONFIG_FB_CFB_IMAGEBLIT=y -# CONFIG_FB_MACMODES is not set -CONFIG_FB_MODE_HELPERS=y -# CONFIG_FB_TILEBLITTING is not set -# CONFIG_FB_CIRRUS is not set -# CONFIG_FB_PM2 is not set -# CONFIG_FB_CYBER2000 is not set -# CONFIG_FB_ARC is not set -# CONFIG_FB_ASILIANT is not set -# CONFIG_FB_IMSTT is not set -# CONFIG_FB_VGA16 is not set -# CONFIG_FB_VESA is not set -CONFIG_VIDEO_SELECT=y -# CONFIG_FB_HGA is not set -# CONFIG_FB_S1D13XXX is not set -# CONFIG_FB_NVIDIA is not set -# CONFIG_FB_RIVA is not set -# CONFIG_FB_I810 is not set -# CONFIG_FB_INTEL is not set -# CONFIG_FB_MATROX is not set -# CONFIG_FB_RADEON_OLD is not set -CONFIG_FB_RADEON=y -CONFIG_FB_RADEON_I2C=y -# CONFIG_FB_RADEON_DEBUG is not set -# CONFIG_FB_ATY128 is not set -# CONFIG_FB_ATY is not set -# CONFIG_FB_SAVAGE is not set -# CONFIG_FB_SIS is not set -# CONFIG_FB_NEOMAGIC is not set -# CONFIG_FB_KYRO is not set -# CONFIG_FB_3DFX is not set -# CONFIG_FB_VOODOO1 is not set -# CONFIG_FB_CYBLA is not set -# CONFIG_FB_TRIDENT is not set -# CONFIG_FB_GEODE is not set -# CONFIG_FB_VIRTUAL is not set +CONFIG_FIRMWARE_EDID=y +# CONFIG_FB is not set # # Console display driver support # CONFIG_VGA_CONSOLE=y +CONFIG_VGACON_SOFT_SCROLLBACK=y +CONFIG_VGACON_SOFT_SCROLLBACK_SIZE=128 +CONFIG_VIDEO_SELECT=y CONFIG_DUMMY_CONSOLE=y -CONFIG_FRAMEBUFFER_CONSOLE=y -# CONFIG_FRAMEBUFFER_CONSOLE_ROTATION is not set -# CONFIG_FONTS is not set -CONFIG_FONT_8x8=y -CONFIG_FONT_8x16=y - -# -# Logo configuration -# -# CONFIG_LOGO is not set # CONFIG_BACKLIGHT_LCD_SUPPORT is not set # @@ -1104,97 +1058,30 @@ CONFIG_SOUND=y # # Advanced Linux Sound Architecture # -CONFIG_SND=y -CONFIG_SND_TIMER=y -CONFIG_SND_PCM=y -CONFIG_SND_RAWMIDI=y -CONFIG_SND_SEQUENCER=y -# CONFIG_SND_SEQ_DUMMY is not set -# CONFIG_SND_MIXER_OSS is not set -# CONFIG_SND_PCM_OSS is not set -# CONFIG_SND_SEQUENCER_OSS is not set -CONFIG_SND_RTCTIMER=y -CONFIG_SND_SEQ_RTCTIMER_DEFAULT=y -# CONFIG_SND_DYNAMIC_MINORS is not set -# CONFIG_SND_SUPPORT_OLD_API is not set -# CONFIG_SND_VERBOSE_PRINTK is not set -# CONFIG_SND_DEBUG is not set - -# -# Generic devices -# -CONFIG_SND_MPU401_UART=y -CONFIG_SND_AC97_CODEC=y -CONFIG_SND_AC97_BUS=y -# CONFIG_SND_DUMMY is not set -# CONFIG_SND_VIRMIDI is not set -# CONFIG_SND_MTPAV is not set -# CONFIG_SND_SERIAL_U16550 is not set -# CONFIG_SND_MPU401 is not set - -# -# PCI devices -# -# CONFIG_SND_AD1889 is not set -# CONFIG_SND_ALS4000 is not set -# CONFIG_SND_ALI5451 is not set -# CONFIG_SND_ATIIXP is not set -# CONFIG_SND_ATIIXP_MODEM is not set -# CONFIG_SND_AU8810 is not set -# CONFIG_SND_AU8820 is not set -# CONFIG_SND_AU8830 is not set -# CONFIG_SND_AZT3328 is not set -# CONFIG_SND_BT87X is not set -# CONFIG_SND_CA0106 is not set -# CONFIG_SND_CMIPCI is not set -# CONFIG_SND_CS4281 is not set -# CONFIG_SND_CS46XX is not set -# CONFIG_SND_CS5535AUDIO is not set -# CONFIG_SND_EMU10K1 is not set -# CONFIG_SND_EMU10K1X is not set -# CONFIG_SND_ENS1370 is not set -# CONFIG_SND_ENS1371 is not set -# CONFIG_SND_ES1938 is not set -# CONFIG_SND_ES1968 is not set -# CONFIG_SND_FM801 is not set -# CONFIG_SND_HDA_INTEL is not set -# CONFIG_SND_HDSP is not set -# CONFIG_SND_HDSPM is not set -# CONFIG_SND_ICE1712 is not set -# CONFIG_SND_ICE1724 is not set -# CONFIG_SND_INTEL8X0 is not set -# CONFIG_SND_INTEL8X0M is not set -# CONFIG_SND_KORG1212 is not set -# CONFIG_SND_MAESTRO3 is not set -# CONFIG_SND_MIXART is not set -# CONFIG_SND_NM256 is not set -# CONFIG_SND_PCXHR is not set -# CONFIG_SND_RME32 is not set -# CONFIG_SND_RME96 is not set -# CONFIG_SND_RME9652 is not set -# CONFIG_SND_SONICVIBES is not set -# CONFIG_SND_TRIDENT is not set -CONFIG_SND_VIA82XX=y -# CONFIG_SND_VIA82XX_MODEM is not set -# CONFIG_SND_VX222 is not set -# CONFIG_SND_YMFPCI is not set - -# -# USB devices -# -# CONFIG_SND_USB_AUDIO is not set -# CONFIG_SND_USB_USX2Y is not set +# CONFIG_SND is not set # # Open Sound System # -# CONFIG_SOUND_PRIME is not set +CONFIG_SOUND_PRIME=y +CONFIG_OSS_OBSOLETE_DRIVER=y +# CONFIG_SOUND_BT878 is not set +# CONFIG_SOUND_EMU10K1 is not set +# CONFIG_SOUND_FUSION is not set +# CONFIG_SOUND_ES1371 is not set +CONFIG_SOUND_ICH=y +# CONFIG_SOUND_TRIDENT is not set +# CONFIG_SOUND_MSNDCLAS is not set +# CONFIG_SOUND_MSNDPIN is not set +# CONFIG_SOUND_VIA82CXXX is not set +# CONFIG_SOUND_OSS is not set # # USB support # CONFIG_USB_ARCH_HAS_HCD=y CONFIG_USB_ARCH_HAS_OHCI=y +CONFIG_USB_ARCH_HAS_EHCI=y CONFIG_USB=y # CONFIG_USB_DEBUG is not set @@ -1213,17 +1100,19 @@ CONFIG_USB_DEVICEFS=y CONFIG_USB_EHCI_HCD=y # CONFIG_USB_EHCI_SPLIT_ISO is not set # CONFIG_USB_EHCI_ROOT_HUB_TT is not set +# CONFIG_USB_EHCI_TT_NEWSCHED is not set # CONFIG_USB_ISP116X_HCD is not set -# CONFIG_USB_OHCI_HCD is not set +CONFIG_USB_OHCI_HCD=y +# CONFIG_USB_OHCI_BIG_ENDIAN is not set +CONFIG_USB_OHCI_LITTLE_ENDIAN=y CONFIG_USB_UHCI_HCD=y # CONFIG_USB_SL811_HCD is not set # # USB Device Class drivers # -# CONFIG_OBSOLETE_OSS_USB_DRIVER is not set # CONFIG_USB_ACM is not set -# CONFIG_USB_PRINTER is not set +CONFIG_USB_PRINTER=y # # NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' @@ -1248,21 +1137,17 @@ CONFIG_USB_STORAGE=y # # USB Input Devices # -# CONFIG_USB_HID is not set - -# -# USB HID Boot Protocol drivers -# -# CONFIG_USB_KBD is not set -# CONFIG_USB_MOUSE is not set +CONFIG_USB_HID=y +CONFIG_USB_HIDINPUT=y +# CONFIG_USB_HIDINPUT_POWERBOOK is not set +# CONFIG_HID_FF is not set +# CONFIG_USB_HIDDEV is not set # CONFIG_USB_AIPTEK is not set # CONFIG_USB_WACOM is not set # CONFIG_USB_ACECAD is not set # CONFIG_USB_KBTAB is not set # CONFIG_USB_POWERMATE is not set -# CONFIG_USB_MTOUCH is not set -# CONFIG_USB_ITMTOUCH is not set -# CONFIG_USB_EGALAX is not set +# CONFIG_USB_TOUCHSCREEN is not set # CONFIG_USB_YEALINK is not set # CONFIG_USB_XPAD is not set # CONFIG_USB_ATI_REMOTE is not set @@ -1277,21 +1162,6 @@ CONFIG_USB_STORAGE=y # CONFIG_USB_MICROTEK is not set # -# USB Multimedia devices -# -# CONFIG_USB_DABUSB is not set -# CONFIG_USB_VICAM is not set -# CONFIG_USB_DSBR is not set -# CONFIG_USB_ET61X251 is not set -# CONFIG_USB_IBMCAM is not set -# CONFIG_USB_KONICAWC is not set -# CONFIG_USB_OV511 is not set -# CONFIG_USB_SE401 is not set -# CONFIG_USB_SN9C102 is not set -# CONFIG_USB_STV680 is not set -# CONFIG_USB_PWC is not set - -# # USB Network Adapters # # CONFIG_USB_CATC is not set @@ -1299,12 +1169,11 @@ CONFIG_USB_STORAGE=y # CONFIG_USB_PEGASUS is not set # CONFIG_USB_RTL8150 is not set # CONFIG_USB_USBNET is not set -# CONFIG_USB_MON is not set +CONFIG_USB_MON=y # # USB port drivers # -# CONFIG_USB_USS720 is not set # # USB Serial Converter support @@ -1321,10 +1190,12 @@ CONFIG_USB_STORAGE=y # CONFIG_USB_LEGOTOWER is not set # CONFIG_USB_LCD is not set # CONFIG_USB_LED is not set +# CONFIG_USB_CYPRESS_CY7C63 is not set # CONFIG_USB_CYTHERM is not set # CONFIG_USB_PHIDGETKIT is not set # CONFIG_USB_PHIDGETSERVO is not set # CONFIG_USB_IDMOUSE is not set +# CONFIG_USB_APPLEDISPLAY is not set # CONFIG_USB_SISUSBVGA is not set # CONFIG_USB_LD is not set # CONFIG_USB_TEST is not set @@ -1344,56 +1215,96 @@ CONFIG_USB_STORAGE=y # CONFIG_MMC is not set # +# LED devices +# +# CONFIG_NEW_LEDS is not set + +# +# LED drivers +# + +# +# LED Triggers +# + +# # InfiniBand support # # CONFIG_INFINIBAND is not set # -# SN Devices +# EDAC - error detection and reporting (RAS) (EXPERIMENTAL) +# +# CONFIG_EDAC is not set + +# +# Real Time Clock # +# CONFIG_RTC_CLASS is not set # -# EDAC - error detection and reporting (RAS) +# DMA Engine support +# +# CONFIG_DMA_ENGINE is not set + +# +# DMA Clients +# + +# +# DMA Devices # -# CONFIG_EDAC is not set # # File systems # CONFIG_EXT2_FS=y -# CONFIG_EXT2_FS_XATTR is not set +CONFIG_EXT2_FS_XATTR=y +CONFIG_EXT2_FS_POSIX_ACL=y +# CONFIG_EXT2_FS_SECURITY is not set # CONFIG_EXT2_FS_XIP is not set -# CONFIG_EXT3_FS is not set -# CONFIG_REISERFS_FS is not set +CONFIG_EXT3_FS=y +CONFIG_EXT3_FS_XATTR=y +CONFIG_EXT3_FS_POSIX_ACL=y +# CONFIG_EXT3_FS_SECURITY is not set +CONFIG_JBD=y +# CONFIG_JBD_DEBUG is not set +CONFIG_FS_MBCACHE=y +CONFIG_REISERFS_FS=y +# CONFIG_REISERFS_CHECK is not set +# CONFIG_REISERFS_PROC_INFO is not set +CONFIG_REISERFS_FS_XATTR=y +CONFIG_REISERFS_FS_POSIX_ACL=y +# CONFIG_REISERFS_FS_SECURITY is not set # CONFIG_JFS_FS is not set -# CONFIG_FS_POSIX_ACL is not set +CONFIG_FS_POSIX_ACL=y # CONFIG_XFS_FS is not set # CONFIG_OCFS2_FS is not set # CONFIG_MINIX_FS is not set # CONFIG_ROMFS_FS is not set -# CONFIG_INOTIFY is not set +CONFIG_INOTIFY=y +CONFIG_INOTIFY_USER=y # CONFIG_QUOTA is not set CONFIG_DNOTIFY=y # CONFIG_AUTOFS_FS is not set -# CONFIG_AUTOFS4_FS is not set +CONFIG_AUTOFS4_FS=y # CONFIG_FUSE_FS is not set # # CD-ROM/DVD Filesystems # CONFIG_ISO9660_FS=y -CONFIG_JOLIET=y -CONFIG_ZISOFS=y -CONFIG_ZISOFS_FS=y +# CONFIG_JOLIET is not set +# CONFIG_ZISOFS is not set # CONFIG_UDF_FS is not set # # DOS/FAT/NT Filesystems # CONFIG_FAT_FS=y -# CONFIG_MSDOS_FS is not set +CONFIG_MSDOS_FS=y CONFIG_VFAT_FS=y -CONFIG_FAT_DEFAULT_CODEPAGE=850 +CONFIG_FAT_DEFAULT_CODEPAGE=437 CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1" # CONFIG_NTFS_FS is not set @@ -1404,10 +1315,9 @@ CONFIG_PROC_FS=y CONFIG_PROC_KCORE=y CONFIG_SYSFS=y CONFIG_TMPFS=y -# CONFIG_HUGETLBFS is not set -# CONFIG_HUGETLB_PAGE is not set +CONFIG_HUGETLBFS=y +CONFIG_HUGETLB_PAGE=y CONFIG_RAMFS=y -# CONFIG_RELAYFS_FS is not set # CONFIG_CONFIGFS_FS is not set # @@ -1430,13 +1340,26 @@ CONFIG_RAMFS=y # # Network File Systems # -# CONFIG_NFS_FS is not set -# CONFIG_NFSD is not set +CONFIG_NFS_FS=y +CONFIG_NFS_V3=y +# CONFIG_NFS_V3_ACL is not set +# CONFIG_NFS_V4 is not set +# CONFIG_NFS_DIRECTIO is not set +CONFIG_NFSD=y +CONFIG_NFSD_V3=y +# CONFIG_NFSD_V3_ACL is not set +# CONFIG_NFSD_V4 is not set +CONFIG_NFSD_TCP=y +CONFIG_ROOT_NFS=y +CONFIG_LOCKD=y +CONFIG_LOCKD_V4=y +CONFIG_EXPORTFS=y +CONFIG_NFS_COMMON=y +CONFIG_SUNRPC=y +# CONFIG_RPCSEC_GSS_KRB5 is not set +# CONFIG_RPCSEC_GSS_SPKM3 is not set # CONFIG_SMB_FS is not set -CONFIG_CIFS=y -# CONFIG_CIFS_STATS is not set -# CONFIG_CIFS_XATTR is not set -# CONFIG_CIFS_EXPERIMENTAL is not set +# CONFIG_CIFS is not set # CONFIG_NCP_FS is not set # CONFIG_CODA_FS is not set # CONFIG_AFS_FS is not set @@ -1445,33 +1368,18 @@ CONFIG_CIFS=y # # Partition Types # -CONFIG_PARTITION_ADVANCED=y -# CONFIG_ACORN_PARTITION is not set -# CONFIG_OSF_PARTITION is not set -# CONFIG_AMIGA_PARTITION is not set -# CONFIG_ATARI_PARTITION is not set -# CONFIG_MAC_PARTITION is not set +# CONFIG_PARTITION_ADVANCED is not set CONFIG_MSDOS_PARTITION=y -# CONFIG_BSD_DISKLABEL is not set -# CONFIG_MINIX_SUBPARTITION is not set -# CONFIG_SOLARIS_X86_PARTITION is not set -# CONFIG_UNIXWARE_DISKLABEL is not set -# CONFIG_LDM_PARTITION is not set -# CONFIG_SGI_PARTITION is not set -# CONFIG_ULTRIX_PARTITION is not set -# CONFIG_SUN_PARTITION is not set -# CONFIG_KARMA_PARTITION is not set -# CONFIG_EFI_PARTITION is not set # # Native Language Support # CONFIG_NLS=y -CONFIG_NLS_DEFAULT="iso8859-15" -# CONFIG_NLS_CODEPAGE_437 is not set +CONFIG_NLS_DEFAULT="iso8859-1" +CONFIG_NLS_CODEPAGE_437=y # CONFIG_NLS_CODEPAGE_737 is not set # CONFIG_NLS_CODEPAGE_775 is not set -CONFIG_NLS_CODEPAGE_850=y +# CONFIG_NLS_CODEPAGE_850 is not set # CONFIG_NLS_CODEPAGE_852 is not set # CONFIG_NLS_CODEPAGE_855 is not set # CONFIG_NLS_CODEPAGE_857 is not set @@ -1491,7 +1399,7 @@ CONFIG_NLS_CODEPAGE_850=y # CONFIG_NLS_ISO8859_8 is not set # CONFIG_NLS_CODEPAGE_1250 is not set # CONFIG_NLS_CODEPAGE_1251 is not set -# CONFIG_NLS_ASCII is not set +CONFIG_NLS_ASCII=y CONFIG_NLS_ISO8859_1=y # CONFIG_NLS_ISO8859_2 is not set # CONFIG_NLS_ISO8859_3 is not set @@ -1510,20 +1418,50 @@ CONFIG_NLS_UTF8=y # # Instrumentation Support # -# CONFIG_PROFILING is not set -# CONFIG_KPROBES is not set +CONFIG_PROFILING=y +CONFIG_OPROFILE=y +CONFIG_KPROBES=y # # Kernel hacking # +CONFIG_TRACE_IRQFLAGS_SUPPORT=y # CONFIG_PRINTK_TIME is not set CONFIG_MAGIC_SYSRQ=y -# CONFIG_DEBUG_KERNEL is not set -CONFIG_LOG_BUF_SHIFT=14 +CONFIG_UNUSED_SYMBOLS=y +CONFIG_DEBUG_KERNEL=y +CONFIG_LOG_BUF_SHIFT=18 +CONFIG_DETECT_SOFTLOCKUP=y +# CONFIG_SCHEDSTATS is not set +# CONFIG_DEBUG_SLAB is not set +# CONFIG_DEBUG_RT_MUTEXES is not set +# CONFIG_RT_MUTEX_TESTER is not set +# CONFIG_DEBUG_SPINLOCK is not set +# CONFIG_DEBUG_MUTEXES is not set +# CONFIG_DEBUG_RWSEMS is not set +# CONFIG_DEBUG_LOCK_ALLOC is not set +# CONFIG_PROVE_LOCKING is not set +# CONFIG_DEBUG_SPINLOCK_SLEEP is not set +# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set +# CONFIG_DEBUG_KOBJECT is not set +# CONFIG_DEBUG_HIGHMEM is not set CONFIG_DEBUG_BUGVERBOSE=y +# CONFIG_DEBUG_INFO is not set +# CONFIG_DEBUG_FS is not set +# CONFIG_DEBUG_VM is not set +# CONFIG_FRAME_POINTER is not set +CONFIG_UNWIND_INFO=y +CONFIG_STACK_UNWIND=y +# CONFIG_FORCED_INLINING is not set +# CONFIG_RCU_TORTURE_TEST is not set CONFIG_EARLY_PRINTK=y +CONFIG_DEBUG_STACKOVERFLOW=y +# CONFIG_DEBUG_STACK_USAGE is not set +# CONFIG_DEBUG_RODATA is not set +# CONFIG_4KSTACKS is not set CONFIG_X86_FIND_SMP_CONFIG=y CONFIG_X86_MPPARSE=y +CONFIG_DOUBLEFAULT=y # # Security options @@ -1537,10 +1475,6 @@ CONFIG_X86_MPPARSE=y # CONFIG_CRYPTO is not set # -# Hardware crypto devices -# - -# # Library routines # # CONFIG_CRC_CCITT is not set @@ -1548,7 +1482,12 @@ CONFIG_X86_MPPARSE=y CONFIG_CRC32=y # CONFIG_LIBCRC32C is not set CONFIG_ZLIB_INFLATE=y +CONFIG_PLIST=y CONFIG_GENERIC_HARDIRQS=y CONFIG_GENERIC_IRQ_PROBE=y +CONFIG_GENERIC_PENDING_IRQ=y +CONFIG_X86_SMP=y +CONFIG_X86_HT=y CONFIG_X86_BIOS_REBOOT=y +CONFIG_X86_TRAMPOLINE=y CONFIG_KTIME_SCALAR=y diff --git a/arch/i386/kernel/Makefile b/arch/i386/kernel/Makefile index 5427a84..1a884b6 100644 --- a/arch/i386/kernel/Makefile +++ b/arch/i386/kernel/Makefile @@ -4,7 +4,7 @@ extra-y := head.o init_task.o vmlinux.lds -obj-y := process.o semaphore.o signal.o entry.o traps.o irq.o \ +obj-y := process.o signal.o entry.o traps.o irq.o \ ptrace.o time.o ioport.o ldt.o setup.o i8259.o sys_i386.o \ pci-dma.o i386_ksyms.o i387.o bootflag.o \ quirks.o i8237.o topology.o alternative.o i8253.o tsc.o @@ -81,4 +81,5 @@ $(obj)/vsyscall-syms.o: $(src)/vsyscall.lds \ $(call if_changed,syscall) k8-y += ../../x86_64/kernel/k8.o +stacktrace-y += ../../x86_64/kernel/stacktrace.o diff --git a/arch/i386/kernel/acpi/Makefile b/arch/i386/kernel/acpi/Makefile index 7e9ac99..7f7be01 100644 --- a/arch/i386/kernel/acpi/Makefile +++ b/arch/i386/kernel/acpi/Makefile @@ -1,5 +1,7 @@ obj-$(CONFIG_ACPI) += boot.o +ifneq ($(CONFIG_PCI),) obj-$(CONFIG_X86_IO_APIC) += earlyquirk.o +endif obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup.o ifneq ($(CONFIG_ACPI_PROCESSOR),) diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c index ee003bc..1aaea6a 100644 --- a/arch/i386/kernel/acpi/boot.c +++ b/arch/i386/kernel/acpi/boot.c @@ -26,9 +26,12 @@ #include <linux/init.h> #include <linux/acpi.h> #include <linux/efi.h> +#include <linux/cpumask.h> #include <linux/module.h> #include <linux/dmi.h> #include <linux/irq.h> +#include <linux/bootmem.h> +#include <linux/ioport.h> #include <asm/pgtable.h> #include <asm/io_apic.h> @@ -36,11 +39,17 @@ #include <asm/io.h> #include <asm/mpspec.h> -#ifdef CONFIG_X86_64 +static int __initdata acpi_force = 0; -extern void __init clustered_apic_check(void); +#ifdef CONFIG_ACPI +int acpi_disabled = 0; +#else +int acpi_disabled = 1; +#endif +EXPORT_SYMBOL(acpi_disabled); + +#ifdef CONFIG_X86_64 -extern int gsi_irq_sharing(int gsi); #include <asm/proto.h> static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id) { return 0; } @@ -506,16 +515,76 @@ EXPORT_SYMBOL(acpi_register_gsi); #ifdef CONFIG_ACPI_HOTPLUG_CPU int acpi_map_lsapic(acpi_handle handle, int *pcpu) { - /* TBD */ - return -EINVAL; + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + union acpi_object *obj; + struct acpi_table_lapic *lapic; + cpumask_t tmp_map, new_map; + u8 physid; + int cpu; + + if (ACPI_FAILURE(acpi_evaluate_object(handle, "_MAT", NULL, &buffer))) + return -EINVAL; + + if (!buffer.length || !buffer.pointer) + return -EINVAL; + + obj = buffer.pointer; + if (obj->type != ACPI_TYPE_BUFFER || + obj->buffer.length < sizeof(*lapic)) { + kfree(buffer.pointer); + return -EINVAL; + } + + lapic = (struct acpi_table_lapic *)obj->buffer.pointer; + + if ((lapic->header.type != ACPI_MADT_LAPIC) || + (!lapic->flags.enabled)) { + kfree(buffer.pointer); + return -EINVAL; + } + + physid = lapic->id; + + kfree(buffer.pointer); + buffer.length = ACPI_ALLOCATE_BUFFER; + buffer.pointer = NULL; + + tmp_map = cpu_present_map; + mp_register_lapic(physid, lapic->flags.enabled); + + /* + * If mp_register_lapic successfully generates a new logical cpu + * number, then the following will get us exactly what was mapped + */ + cpus_andnot(new_map, cpu_present_map, tmp_map); + if (cpus_empty(new_map)) { + printk ("Unable to map lapic to logical cpu number\n"); + return -EINVAL; + } + + cpu = first_cpu(new_map); + + *pcpu = cpu; + return 0; } EXPORT_SYMBOL(acpi_map_lsapic); int acpi_unmap_lsapic(int cpu) { - /* TBD */ - return -EINVAL; + int i; + + for_each_possible_cpu(i) { + if (x86_acpiid_to_apicid[i] == x86_cpu_to_apicid[cpu]) { + x86_acpiid_to_apicid[i] = -1; + break; + } + } + x86_cpu_to_apicid[cpu] = -1; + cpu_clear(cpu, cpu_present_map); + num_processors--; + + return (0); } EXPORT_SYMBOL(acpi_unmap_lsapic); @@ -579,6 +648,8 @@ static int __init acpi_parse_sbf(unsigned long phys_addr, unsigned long size) static int __init acpi_parse_hpet(unsigned long phys, unsigned long size) { struct acpi_table_hpet *hpet_tbl; + struct resource *hpet_res; + resource_size_t res_start; if (!phys || !size) return -EINVAL; @@ -594,12 +665,26 @@ static int __init acpi_parse_hpet(unsigned long phys, unsigned long size) "memory.\n"); return -1; } + +#define HPET_RESOURCE_NAME_SIZE 9 + hpet_res = alloc_bootmem(sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE); + if (hpet_res) { + memset(hpet_res, 0, sizeof(*hpet_res)); + hpet_res->name = (void *)&hpet_res[1]; + hpet_res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + snprintf((char *)hpet_res->name, HPET_RESOURCE_NAME_SIZE, + "HPET %u", hpet_tbl->number); + hpet_res->end = (1 * 1024) - 1; + } + #ifdef CONFIG_X86_64 vxtime.hpet_address = hpet_tbl->addr.addrl | ((long)hpet_tbl->addr.addrh << 32); printk(KERN_INFO PREFIX "HPET id: %#x base: %#lx\n", hpet_tbl->id, vxtime.hpet_address); + + res_start = vxtime.hpet_address; #else /* X86 */ { extern unsigned long hpet_address; @@ -607,9 +692,17 @@ static int __init acpi_parse_hpet(unsigned long phys, unsigned long size) hpet_address = hpet_tbl->addr.addrl; printk(KERN_INFO PREFIX "HPET id: %#x base: %#lx\n", hpet_tbl->id, hpet_address); + + res_start = hpet_address; } #endif /* X86 */ + if (hpet_res) { + hpet_res->start = res_start; + hpet_res->end += res_start; + insert_resource(&iomem_resource, hpet_res); + } + return 0; } #else @@ -860,8 +953,6 @@ static void __init acpi_process_madt(void) return; } -extern int acpi_force; - #ifdef __i386__ static int __init disable_acpi_irq(struct dmi_system_id *d) @@ -1163,3 +1254,75 @@ int __init acpi_boot_init(void) return 0; } + +static int __init parse_acpi(char *arg) +{ + if (!arg) + return -EINVAL; + + /* "acpi=off" disables both ACPI table parsing and interpreter */ + if (strcmp(arg, "off") == 0) { + disable_acpi(); + } + /* acpi=force to over-ride black-list */ + else if (strcmp(arg, "force") == 0) { + acpi_force = 1; + acpi_ht = 1; + acpi_disabled = 0; + } + /* acpi=strict disables out-of-spec workarounds */ + else if (strcmp(arg, "strict") == 0) { + acpi_strict = 1; + } + /* Limit ACPI just to boot-time to enable HT */ + else if (strcmp(arg, "ht") == 0) { + if (!acpi_force) + disable_acpi(); + acpi_ht = 1; + } + /* "acpi=noirq" disables ACPI interrupt routing */ + else if (strcmp(arg, "noirq") == 0) { + acpi_noirq_set(); + } else { + /* Core will printk when we return error. */ + return -EINVAL; + } + return 0; +} +early_param("acpi", parse_acpi); + +/* FIXME: Using pci= for an ACPI parameter is a travesty. */ +static int __init parse_pci(char *arg) +{ + if (arg && strcmp(arg, "noacpi") == 0) + acpi_disable_pci(); + return 0; +} +early_param("pci", parse_pci); + +#ifdef CONFIG_X86_IO_APIC +static int __init parse_acpi_skip_timer_override(char *arg) +{ + acpi_skip_timer_override = 1; + return 0; +} +early_param("acpi_skip_timer_override", parse_acpi_skip_timer_override); +#endif /* CONFIG_X86_IO_APIC */ + +static int __init setup_acpi_sci(char *s) +{ + if (!s) + return -EINVAL; + if (!strcmp(s, "edge")) + acpi_sci_flags.trigger = 1; + else if (!strcmp(s, "level")) + acpi_sci_flags.trigger = 3; + else if (!strcmp(s, "high")) + acpi_sci_flags.polarity = 1; + else if (!strcmp(s, "low")) + acpi_sci_flags.polarity = 3; + else + return -EINVAL; + return 0; +} +early_param("acpi_sci", setup_acpi_sci); diff --git a/arch/i386/kernel/acpi/earlyquirk.c b/arch/i386/kernel/acpi/earlyquirk.c index 1649a17..fe799b1 100644 --- a/arch/i386/kernel/acpi/earlyquirk.c +++ b/arch/i386/kernel/acpi/earlyquirk.c @@ -48,7 +48,11 @@ void __init check_acpi_pci(void) int num, slot, func; /* Assume the machine supports type 1. If not it will - always read ffffffff and should not have any side effect. */ + always read ffffffff and should not have any side effect. + Actually a few buggy systems can machine check. Allow the user + to disable it by command line option at least -AK */ + if (!early_pci_allowed()) + return; /* Poor man's PCI discovery */ for (num = 0; num < 32; num++) { diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c index 8c844d0..90faae5 100644 --- a/arch/i386/kernel/apic.c +++ b/arch/i386/kernel/apic.c @@ -52,7 +52,18 @@ static cpumask_t timer_bcast_ipi; /* * Knob to control our willingness to enable the local APIC. */ -int enable_local_apic __initdata = 0; /* -1=force-disable, +1=force-enable */ +static int enable_local_apic __initdata = 0; /* -1=force-disable, +1=force-enable */ + +static inline void lapic_disable(void) +{ + enable_local_apic = -1; + clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability); +} + +static inline void lapic_enable(void) +{ + enable_local_apic = 1; +} /* * Debug level @@ -586,8 +597,7 @@ void __devinit setup_local_APIC(void) printk("No ESR for 82489DX.\n"); } - if (nmi_watchdog == NMI_LOCAL_APIC) - setup_apic_nmi_watchdog(); + setup_apic_nmi_watchdog(NULL); apic_pm_activate(); } @@ -1373,3 +1383,18 @@ int __init APIC_init_uniprocessor (void) return 0; } + +static int __init parse_lapic(char *arg) +{ + lapic_enable(); + return 0; +} +early_param("lapic", parse_lapic); + +static int __init parse_nolapic(char *arg) +{ + lapic_disable(); + return 0; +} +early_param("nolapic", parse_nolapic); + diff --git a/arch/i386/kernel/cpu/amd.c b/arch/i386/kernel/cpu/amd.c index e6a2d6b..e475809 100644 --- a/arch/i386/kernel/cpu/amd.c +++ b/arch/i386/kernel/cpu/amd.c @@ -22,7 +22,7 @@ extern void vide(void); __asm__(".align 4\nvide: ret"); -static void __init init_amd(struct cpuinfo_x86 *c) +static void __cpuinit init_amd(struct cpuinfo_x86 *c) { u32 l, h; int mbytes = num_physpages >> (20-PAGE_SHIFT); @@ -246,7 +246,7 @@ static void __init init_amd(struct cpuinfo_x86 *c) num_cache_leaves = 3; } -static unsigned int 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)) { @@ -259,7 +259,7 @@ static unsigned int amd_size_cache(struct cpuinfo_x86 * c, unsigned int size) return size; } -static struct cpu_dev amd_cpu_dev __initdata = { +static struct cpu_dev amd_cpu_dev __cpuinitdata = { .c_vendor = "AMD", .c_ident = { "AuthenticAMD" }, .c_models = { @@ -275,7 +275,6 @@ static struct cpu_dev amd_cpu_dev __initdata = { }, }, .c_init = init_amd, - .c_identify = generic_identify, .c_size_cache = amd_size_cache, }; diff --git a/arch/i386/kernel/cpu/centaur.c b/arch/i386/kernel/cpu/centaur.c index bd75629..8c25047 100644 --- a/arch/i386/kernel/cpu/centaur.c +++ b/arch/i386/kernel/cpu/centaur.c @@ -9,7 +9,7 @@ #ifdef CONFIG_X86_OOSTORE -static u32 __init power2(u32 x) +static u32 __cpuinit power2(u32 x) { u32 s=1; while(s<=x) @@ -22,7 +22,7 @@ static u32 __init power2(u32 x) * Set up an actual MCR */ -static void __init centaur_mcr_insert(int reg, u32 base, u32 size, int key) +static void __cpuinit centaur_mcr_insert(int reg, u32 base, u32 size, int key) { u32 lo, hi; @@ -40,7 +40,7 @@ static void __init centaur_mcr_insert(int reg, u32 base, u32 size, int key) * Shortcut: We know you can't put 4Gig of RAM on a winchip */ -static u32 __init ramtop(void) /* 16388 */ +static u32 __cpuinit ramtop(void) /* 16388 */ { int i; u32 top = 0; @@ -91,7 +91,7 @@ static u32 __init ramtop(void) /* 16388 */ * Compute a set of MCR's to give maximum coverage */ -static int __init centaur_mcr_compute(int nr, int key) +static int __cpuinit centaur_mcr_compute(int nr, int key) { u32 mem = ramtop(); u32 root = power2(mem); @@ -166,7 +166,7 @@ static int __init centaur_mcr_compute(int nr, int key) return ct; } -static void __init centaur_create_optimal_mcr(void) +static void __cpuinit centaur_create_optimal_mcr(void) { int i; /* @@ -189,7 +189,7 @@ static void __init centaur_create_optimal_mcr(void) wrmsr(MSR_IDT_MCR0+i, 0, 0); } -static void __init winchip2_create_optimal_mcr(void) +static void __cpuinit winchip2_create_optimal_mcr(void) { u32 lo, hi; int i; @@ -227,7 +227,7 @@ static void __init winchip2_create_optimal_mcr(void) * Handle the MCR key on the Winchip 2. */ -static void __init winchip2_unprotect_mcr(void) +static void __cpuinit winchip2_unprotect_mcr(void) { u32 lo, hi; u32 key; @@ -239,7 +239,7 @@ static void __init winchip2_unprotect_mcr(void) wrmsr(MSR_IDT_MCR_CTRL, lo, hi); } -static void __init winchip2_protect_mcr(void) +static void __cpuinit winchip2_protect_mcr(void) { u32 lo, hi; @@ -257,7 +257,7 @@ static void __init winchip2_protect_mcr(void) #define RNG_ENABLED (1 << 3) #define RNG_ENABLE (1 << 6) /* MSR_VIA_RNG */ -static void __init init_c3(struct cpuinfo_x86 *c) +static void __cpuinit init_c3(struct cpuinfo_x86 *c) { u32 lo, hi; @@ -303,7 +303,7 @@ static void __init init_c3(struct cpuinfo_x86 *c) display_cacheinfo(c); } -static void __init init_centaur(struct cpuinfo_x86 *c) +static void __cpuinit init_centaur(struct cpuinfo_x86 *c) { enum { ECX8=1<<1, @@ -442,7 +442,7 @@ static void __init init_centaur(struct cpuinfo_x86 *c) } } -static unsigned int 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))) @@ -457,7 +457,7 @@ static unsigned int centaur_size_cache(struct cpuinfo_x86 * c, unsigned int size return size; } -static struct cpu_dev centaur_cpu_dev __initdata = { +static struct cpu_dev centaur_cpu_dev __cpuinitdata = { .c_vendor = "Centaur", .c_ident = { "CentaurHauls" }, .c_init = init_centaur, diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c index 70c87de..2799baa 100644 --- a/arch/i386/kernel/cpu/common.c +++ b/arch/i386/kernel/cpu/common.c @@ -36,7 +36,7 @@ struct cpu_dev * cpu_devs[X86_VENDOR_NUM] = {}; extern int disable_pse; -static void 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 */ @@ -49,7 +49,7 @@ static void default_init(struct cpuinfo_x86 * c) } } -static struct cpu_dev default_cpu = { +static struct cpu_dev __cpuinitdata default_cpu = { .c_init = default_init, .c_vendor = "Unknown", }; @@ -265,7 +265,7 @@ static void __init early_cpu_detect(void) } } -void __cpuinit generic_identify(struct cpuinfo_x86 * c) +static void __cpuinit generic_identify(struct cpuinfo_x86 * c) { u32 tfms, xlvl; int ebx; @@ -675,7 +675,7 @@ old_gdt: #endif /* Clear %fs and %gs. */ - asm volatile ("xorl %eax, %eax; movl %eax, %fs; movl %eax, %gs"); + asm volatile ("movl %0, %%fs; movl %0, %%gs" : : "r" (0)); /* Clear all 6 debug registers: */ set_debugreg(0, 0); diff --git a/arch/i386/kernel/cpu/cpu.h b/arch/i386/kernel/cpu/cpu.h index 5a1d4f1..2f6432c 100644 --- a/arch/i386/kernel/cpu/cpu.h +++ b/arch/i386/kernel/cpu/cpu.h @@ -24,7 +24,5 @@ extern struct cpu_dev * cpu_devs [X86_VENDOR_NUM]; extern int get_model_name(struct cpuinfo_x86 *c); extern void display_cacheinfo(struct cpuinfo_x86 *c); -extern void generic_identify(struct cpuinfo_x86 * c); - extern void early_intel_workaround(struct cpuinfo_x86 *c); diff --git a/arch/i386/kernel/cpu/cyrix.c b/arch/i386/kernel/cpu/cyrix.c index f03b7f9..c0c3b59 100644 --- a/arch/i386/kernel/cpu/cyrix.c +++ b/arch/i386/kernel/cpu/cyrix.c @@ -12,7 +12,7 @@ /* * Read NSC/Cyrix DEVID registers (DIR) to get more detailed info. about the CPU */ -static void __init do_cyrix_devid(unsigned char *dir0, unsigned char *dir1) +static void __cpuinit do_cyrix_devid(unsigned char *dir0, unsigned char *dir1) { unsigned char ccr2, ccr3; unsigned long flags; @@ -52,25 +52,25 @@ static void __init do_cyrix_devid(unsigned char *dir0, unsigned char *dir1) * Actually since bugs.h doesn't even reference this perhaps someone should * fix the documentation ??? */ -static unsigned char Cx86_dir0_msb __initdata = 0; +static unsigned char Cx86_dir0_msb __cpuinitdata = 0; -static char Cx86_model[][9] __initdata = { +static char Cx86_model[][9] __cpuinitdata = { "Cx486", "Cx486", "5x86 ", "6x86", "MediaGX ", "6x86MX ", "M II ", "Unknown" }; -static char Cx486_name[][5] __initdata = { +static char Cx486_name[][5] __cpuinitdata = { "SLC", "DLC", "SLC2", "DLC2", "SRx", "DRx", "SRx2", "DRx2" }; -static char Cx486S_name[][4] __initdata = { +static char Cx486S_name[][4] __cpuinitdata = { "S", "S2", "Se", "S2e" }; -static char Cx486D_name[][4] __initdata = { +static char Cx486D_name[][4] __cpuinitdata = { "DX", "DX2", "?", "?", "?", "DX4" }; -static char Cx86_cb[] __initdata = "?.5x Core/Bus Clock"; -static char cyrix_model_mult1[] __initdata = "12??43"; -static char cyrix_model_mult2[] __initdata = "12233445"; +static char Cx86_cb[] __cpuinitdata = "?.5x Core/Bus Clock"; +static char cyrix_model_mult1[] __cpuinitdata = "12??43"; +static char cyrix_model_mult2[] __cpuinitdata = "12233445"; /* * Reset the slow-loop (SLOP) bit on the 686(L) which is set by some old @@ -82,7 +82,7 @@ static char cyrix_model_mult2[] __initdata = "12233445"; extern void calibrate_delay(void) __init; -static void __init check_cx686_slop(struct cpuinfo_x86 *c) +static void __cpuinit check_cx686_slop(struct cpuinfo_x86 *c) { unsigned long flags; @@ -107,7 +107,7 @@ static void __init check_cx686_slop(struct cpuinfo_x86 *c) } -static void __init set_cx86_reorder(void) +static void __cpuinit set_cx86_reorder(void) { u8 ccr3; @@ -122,7 +122,7 @@ static void __init set_cx86_reorder(void) setCx86(CX86_CCR3, ccr3); } -static void __init set_cx86_memwb(void) +static void __cpuinit set_cx86_memwb(void) { u32 cr0; @@ -137,7 +137,7 @@ static void __init set_cx86_memwb(void) setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x14 ); } -static void __init set_cx86_inc(void) +static void __cpuinit set_cx86_inc(void) { unsigned char ccr3; @@ -158,7 +158,7 @@ static void __init set_cx86_inc(void) * Configure later MediaGX and/or Geode processor. */ -static void __init geode_configure(void) +static void __cpuinit geode_configure(void) { unsigned long flags; u8 ccr3, ccr4; @@ -184,14 +184,14 @@ static void __init geode_configure(void) #ifdef CONFIG_PCI -static struct pci_device_id __initdata cyrix_55x0[] = { +static struct pci_device_id __cpuinitdata cyrix_55x0[] = { { PCI_DEVICE(PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5510) }, { PCI_DEVICE(PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5520) }, { }, }; #endif -static void __init init_cyrix(struct cpuinfo_x86 *c) +static void __cpuinit init_cyrix(struct cpuinfo_x86 *c) { unsigned char dir0, dir0_msn, dir0_lsn, dir1 = 0; char *buf = c->x86_model_id; @@ -346,7 +346,7 @@ static void __init init_cyrix(struct cpuinfo_x86 *c) /* * Handle National Semiconductor branded processors */ -static void __init init_nsc(struct cpuinfo_x86 *c) +static void __cpuinit init_nsc(struct cpuinfo_x86 *c) { /* There may be GX1 processors in the wild that are branded * NSC and not Cyrix. @@ -394,7 +394,7 @@ static inline int test_cyrix_52div(void) return (unsigned char) (test >> 8) == 0x02; } -static void 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() ) { @@ -427,10 +427,9 @@ static void cyrix_identify(struct cpuinfo_x86 * c) local_irq_restore(flags); } } - generic_identify(c); } -static struct cpu_dev cyrix_cpu_dev __initdata = { +static struct cpu_dev cyrix_cpu_dev __cpuinitdata = { .c_vendor = "Cyrix", .c_ident = { "CyrixInstead" }, .c_init = init_cyrix, @@ -453,11 +452,10 @@ static int __init cyrix_exit_cpu(void) late_initcall(cyrix_exit_cpu); -static struct cpu_dev nsc_cpu_dev __initdata = { +static struct cpu_dev nsc_cpu_dev __cpuinitdata = { .c_vendor = "NSC", .c_ident = { "Geode by NSC" }, .c_init = init_nsc, - .c_identify = generic_identify, }; int __init nsc_init_cpu(void) diff --git a/arch/i386/kernel/cpu/intel.c b/arch/i386/kernel/cpu/intel.c index 5a2e270..94a95aa 100644 --- a/arch/i386/kernel/cpu/intel.c +++ b/arch/i386/kernel/cpu/intel.c @@ -198,7 +198,7 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) } -static unsigned int 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. * One has 256kb of cache, the other 512. We have no way @@ -263,7 +263,6 @@ static struct cpu_dev intel_cpu_dev __cpuinitdata = { }, }, .c_init = init_intel, - .c_identify = generic_identify, .c_size_cache = intel_size_cache, }; diff --git a/arch/i386/kernel/cpu/mcheck/Makefile b/arch/i386/kernel/cpu/mcheck/Makefile index 30808f3..f1ebe1c 100644 --- a/arch/i386/kernel/cpu/mcheck/Makefile +++ b/arch/i386/kernel/cpu/mcheck/Makefile @@ -1,2 +1,2 @@ -obj-y = mce.o k7.o p4.o p5.o p6.o winchip.o +obj-y = mce.o k7.o p4.o p5.o p6.o winchip.o therm_throt.o obj-$(CONFIG_X86_MCE_NONFATAL) += non-fatal.o diff --git a/arch/i386/kernel/cpu/mcheck/p4.c b/arch/i386/kernel/cpu/mcheck/p4.c index b95f1b3d..504434a 100644 --- a/arch/i386/kernel/cpu/mcheck/p4.c +++ b/arch/i386/kernel/cpu/mcheck/p4.c @@ -13,6 +13,8 @@ #include <asm/msr.h> #include <asm/apic.h> +#include <asm/therm_throt.h> + #include "mce.h" /* as supported by the P4/Xeon family */ @@ -44,25 +46,12 @@ static void unexpected_thermal_interrupt(struct pt_regs *regs) /* P4/Xeon Thermal transition interrupt handler */ static void intel_thermal_interrupt(struct pt_regs *regs) { - u32 l, h; - unsigned int cpu = smp_processor_id(); - static unsigned long next[NR_CPUS]; + __u64 msr_val; ack_APIC_irq(); - if (time_after(next[cpu], jiffies)) - return; - - next[cpu] = jiffies + HZ*5; - rdmsr(MSR_IA32_THERM_STATUS, l, h); - if (l & 0x1) { - printk(KERN_EMERG "CPU%d: Temperature above threshold\n", cpu); - printk(KERN_EMERG "CPU%d: Running in modulated clock mode\n", - cpu); - add_taint(TAINT_MACHINE_CHECK); - } else { - printk(KERN_INFO "CPU%d: Temperature/speed normal\n", cpu); - } + rdmsrl(MSR_IA32_THERM_STATUS, msr_val); + therm_throt_process(msr_val & 0x1); } /* Thermal interrupt handler for this CPU setup */ @@ -122,10 +111,13 @@ static void intel_init_thermal(struct cpuinfo_x86 *c) rdmsr (MSR_IA32_MISC_ENABLE, l, h); wrmsr (MSR_IA32_MISC_ENABLE, l | (1<<3), h); - + l = apic_read (APIC_LVTTHMR); apic_write_around (APIC_LVTTHMR, l & ~APIC_LVT_MASKED); printk (KERN_INFO "CPU%d: Thermal monitoring enabled\n", cpu); + + /* enable thermal throttle processing */ + atomic_set(&therm_throt_en, 1); return; } #endif /* CONFIG_X86_MCE_P4THERMAL */ diff --git a/arch/i386/kernel/cpu/mcheck/therm_throt.c b/arch/i386/kernel/cpu/mcheck/therm_throt.c new file mode 100644 index 0000000..4f43047 --- /dev/null +++ b/arch/i386/kernel/cpu/mcheck/therm_throt.c @@ -0,0 +1,180 @@ +/* + * linux/arch/i386/kerne/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). + * This allows consistent reporting of CPU thermal throttle events. + * + * Maintains a counter in /sys that keeps track of the number of thermal + * events, such that the user knows how bad the thermal problem might be + * (since the logging to syslog and mcelog is rate limited). + * + * Author: Dmitriy Zavin (dmitriyz@google.com) + * + * Credits: Adapted from Zwane Mwaikambo's original code in mce_intel.c. + * Inspired by Ross Biro's and Al Borchers' counter code. + */ + +#include <linux/percpu.h> +#include <linux/sysdev.h> +#include <linux/cpu.h> +#include <asm/cpu.h> +#include <linux/notifier.h> +#include <asm/therm_throt.h> + +/* How long to wait between reporting thermal events */ +#define CHECK_INTERVAL (300 * HZ) + +static DEFINE_PER_CPU(__u64, next_check) = INITIAL_JIFFIES; +static DEFINE_PER_CPU(unsigned long, thermal_throttle_count); +atomic_t therm_throt_en = ATOMIC_INIT(0); + +#ifdef CONFIG_SYSFS +#define define_therm_throt_sysdev_one_ro(_name) \ + static SYSDEV_ATTR(_name, 0444, therm_throt_sysdev_show_##_name, NULL) + +#define define_therm_throt_sysdev_show_func(name) \ +static ssize_t therm_throt_sysdev_show_##name(struct sys_device *dev, \ + char *buf) \ +{ \ + unsigned int cpu = dev->id; \ + ssize_t ret; \ + \ + preempt_disable(); /* CPU hotplug */ \ + if (cpu_online(cpu)) \ + ret = sprintf(buf, "%lu\n", \ + per_cpu(thermal_throttle_##name, cpu)); \ + else \ + ret = 0; \ + preempt_enable(); \ + \ + return ret; \ +} + +define_therm_throt_sysdev_show_func(count); +define_therm_throt_sysdev_one_ro(count); + +static struct attribute *thermal_throttle_attrs[] = { + &attr_count.attr, + NULL +}; + +static struct attribute_group thermal_throttle_attr_group = { + .attrs = thermal_throttle_attrs, + .name = "thermal_throttle" +}; +#endif /* CONFIG_SYSFS */ + +/*** + * therm_throt_process - Process thermal throttling event from interrupt + * @curr: Whether the condition is current or not (boolean), since the + * thermal interrupt normally gets called both when the thermal + * event begins and once the event has ended. + * + * This function is called by the thermal interrupt after the + * IRQ has been acknowledged. + * + * It will take care of rate limiting and printing messages to the syslog. + * + * Returns: 0 : Event should NOT be further logged, i.e. still in + * "timeout" from previous log message. + * 1 : Event should be logged further, and a message has been + * printed to the syslog. + */ +int therm_throt_process(int curr) +{ + unsigned int cpu = smp_processor_id(); + __u64 tmp_jiffs = get_jiffies_64(); + + if (curr) + __get_cpu_var(thermal_throttle_count)++; + + if (time_before64(tmp_jiffs, __get_cpu_var(next_check))) + return 0; + + __get_cpu_var(next_check) = tmp_jiffs + CHECK_INTERVAL; + + /* if we just entered the thermal event */ + if (curr) { + printk(KERN_CRIT "CPU%d: Temperature above threshold, " + "cpu clock throttled (total events = %lu)\n", cpu, + __get_cpu_var(thermal_throttle_count)); + + add_taint(TAINT_MACHINE_CHECK); + } else { + printk(KERN_CRIT "CPU%d: Temperature/speed normal\n", cpu); + } + + return 1; +} + +#ifdef CONFIG_SYSFS +/* Add/Remove thermal_throttle interface for CPU device */ +static __cpuinit int thermal_throttle_add_dev(struct sys_device * sys_dev) +{ + sysfs_create_group(&sys_dev->kobj, &thermal_throttle_attr_group); + return 0; +} + +#ifdef CONFIG_HOTPLUG_CPU +static __cpuinit int thermal_throttle_remove_dev(struct sys_device * sys_dev) +{ + sysfs_remove_group(&sys_dev->kobj, &thermal_throttle_attr_group); + return 0; +} + +/* Mutex protecting device creation against CPU hotplug */ +static DEFINE_MUTEX(therm_cpu_lock); + +/* Get notified when a cpu comes on/off. Be hotplug friendly. */ +static __cpuinit int thermal_throttle_cpu_callback(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + unsigned int cpu = (unsigned long)hcpu; + struct sys_device *sys_dev; + + sys_dev = get_cpu_sysdev(cpu); + mutex_lock(&therm_cpu_lock); + switch (action) { + case CPU_ONLINE: + thermal_throttle_add_dev(sys_dev); + break; + case CPU_DEAD: + thermal_throttle_remove_dev(sys_dev); + break; + } + mutex_unlock(&therm_cpu_lock); + return NOTIFY_OK; +} + +static struct notifier_block thermal_throttle_cpu_notifier = +{ + .notifier_call = thermal_throttle_cpu_callback, +}; +#endif /* CONFIG_HOTPLUG_CPU */ + +static __init int thermal_throttle_init_device(void) +{ + unsigned int cpu = 0; + + if (!atomic_read(&therm_throt_en)) + return 0; + + register_hotcpu_notifier(&thermal_throttle_cpu_notifier); + +#ifdef CONFIG_HOTPLUG_CPU + mutex_lock(&therm_cpu_lock); +#endif + /* connect live CPUs to sysfs */ + for_each_online_cpu(cpu) + thermal_throttle_add_dev(get_cpu_sysdev(cpu)); +#ifdef CONFIG_HOTPLUG_CPU + mutex_unlock(&therm_cpu_lock); +#endif + + return 0; +} + +device_initcall(thermal_throttle_init_device); +#endif /* CONFIG_SYSFS */ diff --git a/arch/i386/kernel/cpu/nexgen.c b/arch/i386/kernel/cpu/nexgen.c index ad87fa5..8bf23cc 100644 --- a/arch/i386/kernel/cpu/nexgen.c +++ b/arch/i386/kernel/cpu/nexgen.c @@ -10,7 +10,7 @@ * to have CPUID. (Thanks to Herbert Oppmann) */ -static int __init deep_magic_nexgen_probe(void) +static int __cpuinit deep_magic_nexgen_probe(void) { int ret; @@ -27,21 +27,20 @@ static int __init deep_magic_nexgen_probe(void) return ret; } -static void __init init_nexgen(struct cpuinfo_x86 * c) +static void __cpuinit init_nexgen(struct cpuinfo_x86 * c) { c->x86_cache_size = 256; /* A few had 1 MB... */ } -static void __init nexgen_identify(struct cpuinfo_x86 * c) +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"); } - generic_identify(c); } -static struct cpu_dev nexgen_cpu_dev __initdata = { +static struct cpu_dev nexgen_cpu_dev __cpuinitdata = { .c_vendor = "Nexgen", .c_ident = { "NexGenDriven" }, .c_models = { diff --git a/arch/i386/kernel/cpu/proc.c b/arch/i386/kernel/cpu/proc.c index f54a152..76aac08 100644 --- a/arch/i386/kernel/cpu/proc.c +++ b/arch/i386/kernel/cpu/proc.c @@ -46,8 +46,8 @@ static int show_cpuinfo(struct seq_file *m, void *v) /* Intel-defined (#2) */ "pni", NULL, NULL, "monitor", "ds_cpl", "vmx", "smx", "est", - "tm2", NULL, "cid", NULL, NULL, "cx16", "xtpr", NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + "tm2", "ssse3", "cid", NULL, NULL, "cx16", "xtpr", NULL, + NULL, NULL, "dca", NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, /* VIA/Cyrix/Centaur-defined */ diff --git a/arch/i386/kernel/cpu/rise.c b/arch/i386/kernel/cpu/rise.c index d08d5a2..9317f74 100644 --- a/arch/i386/kernel/cpu/rise.c +++ b/arch/i386/kernel/cpu/rise.c @@ -5,7 +5,7 @@ #include "cpu.h" -static void __init init_rise(struct cpuinfo_x86 *c) +static void __cpuinit init_rise(struct cpuinfo_x86 *c) { printk("CPU: Rise iDragon"); if (c->x86_model > 2) @@ -28,7 +28,7 @@ static void __init init_rise(struct cpuinfo_x86 *c) set_bit(X86_FEATURE_CX8, c->x86_capability); } -static struct cpu_dev rise_cpu_dev __initdata = { +static struct cpu_dev rise_cpu_dev __cpuinitdata = { .c_vendor = "Rise", .c_ident = { "RiseRiseRise" }, .c_models = { diff --git a/arch/i386/kernel/cpu/transmeta.c b/arch/i386/kernel/cpu/transmeta.c index 7214c9b..4056fb7 100644 --- a/arch/i386/kernel/cpu/transmeta.c +++ b/arch/i386/kernel/cpu/transmeta.c @@ -5,7 +5,7 @@ #include <asm/msr.h> #include "cpu.h" -static void __init init_transmeta(struct cpuinfo_x86 *c) +static void __cpuinit init_transmeta(struct cpuinfo_x86 *c) { unsigned int cap_mask, uk, max, dummy; unsigned int cms_rev1, cms_rev2; @@ -85,10 +85,9 @@ static void __init init_transmeta(struct cpuinfo_x86 *c) #endif } -static void __init transmeta_identify(struct cpuinfo_x86 * c) +static void __cpuinit transmeta_identify(struct cpuinfo_x86 * c) { u32 xlvl; - generic_identify(c); /* Transmeta-defined flags: level 0x80860001 */ xlvl = cpuid_eax(0x80860000); @@ -98,7 +97,7 @@ static void __init transmeta_identify(struct cpuinfo_x86 * c) } } -static struct cpu_dev transmeta_cpu_dev __initdata = { +static struct cpu_dev transmeta_cpu_dev __cpuinitdata = { .c_vendor = "Transmeta", .c_ident = { "GenuineTMx86", "TransmetaCPU" }, .c_init = init_transmeta, diff --git a/arch/i386/kernel/cpu/umc.c b/arch/i386/kernel/cpu/umc.c index 2cd988f..1bf3f87 100644 --- a/arch/i386/kernel/cpu/umc.c +++ b/arch/i386/kernel/cpu/umc.c @@ -5,12 +5,8 @@ /* UMC chips appear to be only either 386 or 486, so no special init takes place. */ -static void __init init_umc(struct cpuinfo_x86 * c) -{ - -} -static struct cpu_dev umc_cpu_dev __initdata = { +static struct cpu_dev umc_cpu_dev __cpuinitdata = { .c_vendor = "UMC", .c_ident = { "UMC UMC UMC" }, .c_models = { @@ -21,7 +17,6 @@ static struct cpu_dev umc_cpu_dev __initdata = { } }, }, - .c_init = init_umc, }; int __init umc_init_cpu(void) diff --git a/arch/i386/kernel/crash.c b/arch/i386/kernel/crash.c index 5b96f03..67d297d 100644 --- a/arch/i386/kernel/crash.c +++ b/arch/i386/kernel/crash.c @@ -22,6 +22,8 @@ #include <asm/nmi.h> #include <asm/hw_irq.h> #include <asm/apic.h> +#include <asm/kdebug.h> + #include <mach_ipi.h> @@ -93,16 +95,25 @@ static void crash_save_self(struct pt_regs *regs) #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC) static atomic_t waiting_for_crash_ipi; -static int crash_nmi_callback(struct pt_regs *regs, int cpu) +static int crash_nmi_callback(struct notifier_block *self, + unsigned long val, void *data) { + struct pt_regs *regs; struct pt_regs fixed_regs; + int cpu; + + if (val != DIE_NMI_IPI) + return NOTIFY_OK; + + regs = ((struct die_args *)data)->regs; + cpu = raw_smp_processor_id(); /* Don't do anything if this handler is invoked on crashing cpu. * Otherwise, system will completely hang. Crashing cpu can get * an NMI if system was initially booted with nmi_watchdog parameter. */ if (cpu == crashing_cpu) - return 1; + return NOTIFY_STOP; local_irq_disable(); if (!user_mode_vm(regs)) { @@ -125,13 +136,18 @@ static void smp_send_nmi_allbutself(void) send_IPI_allbutself(NMI_VECTOR); } +static struct notifier_block crash_nmi_nb = { + .notifier_call = crash_nmi_callback, +}; + static void nmi_shootdown_cpus(void) { unsigned long msecs; atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1); /* Would it be better to replace the trap vector here? */ - set_nmi_callback(crash_nmi_callback); + if (register_die_notifier(&crash_nmi_nb)) + return; /* return what? */ /* Ensure the new callback function is set before sending * out the NMI */ diff --git a/arch/i386/kernel/entry.S b/arch/i386/kernel/entry.S index 87f9f60..5a63d6f 100644 --- a/arch/i386/kernel/entry.S +++ b/arch/i386/kernel/entry.S @@ -76,8 +76,15 @@ DF_MASK = 0x00000400 NT_MASK = 0x00004000 VM_MASK = 0x00020000 +/* These are replaces for paravirtualization */ +#define DISABLE_INTERRUPTS cli +#define ENABLE_INTERRUPTS sti +#define ENABLE_INTERRUPTS_SYSEXIT sti; sysexit +#define INTERRUPT_RETURN iret +#define GET_CR0_INTO_EAX movl %cr0, %eax + #ifdef CONFIG_PREEMPT -#define preempt_stop cli; TRACE_IRQS_OFF +#define preempt_stop DISABLE_INTERRUPTS; TRACE_IRQS_OFF #else #define preempt_stop #define resume_kernel restore_nocheck @@ -176,18 +183,21 @@ VM_MASK = 0x00020000 #define RING0_INT_FRAME \ CFI_STARTPROC simple;\ + CFI_SIGNAL_FRAME;\ CFI_DEF_CFA esp, 3*4;\ /*CFI_OFFSET cs, -2*4;*/\ CFI_OFFSET eip, -3*4 #define RING0_EC_FRAME \ CFI_STARTPROC simple;\ + CFI_SIGNAL_FRAME;\ CFI_DEF_CFA esp, 4*4;\ /*CFI_OFFSET cs, -2*4;*/\ CFI_OFFSET eip, -3*4 #define RING0_PTREGS_FRAME \ CFI_STARTPROC simple;\ + CFI_SIGNAL_FRAME;\ CFI_DEF_CFA esp, OLDESP-EBX;\ /*CFI_OFFSET cs, CS-OLDESP;*/\ CFI_OFFSET eip, EIP-OLDESP;\ @@ -233,10 +243,11 @@ ret_from_intr: check_userspace: movl EFLAGS(%esp), %eax # mix EFLAGS and CS movb CS(%esp), %al - testl $(VM_MASK | 3), %eax - jz resume_kernel + andl $(VM_MASK | SEGMENT_RPL_MASK), %eax + cmpl $USER_RPL, %eax + jb resume_kernel # not returning to v8086 or userspace ENTRY(resume_userspace) - cli # make sure we don't miss an interrupt + DISABLE_INTERRUPTS # make sure we don't miss an interrupt # setting need_resched or sigpending # between sampling and the iret movl TI_flags(%ebp), %ecx @@ -247,7 +258,7 @@ ENTRY(resume_userspace) #ifdef CONFIG_PREEMPT ENTRY(resume_kernel) - cli + DISABLE_INTERRUPTS cmpl $0,TI_preempt_count(%ebp) # non-zero preempt_count ? jnz restore_nocheck need_resched: @@ -267,6 +278,7 @@ need_resched: # sysenter call handler stub ENTRY(sysenter_entry) CFI_STARTPROC simple + CFI_SIGNAL_FRAME CFI_DEF_CFA esp, 0 CFI_REGISTER esp, ebp movl TSS_sysenter_esp0(%esp),%esp @@ -275,7 +287,7 @@ sysenter_past_esp: * No need to follow this irqs on/off section: the syscall * disabled irqs and here we enable it straight after entry: */ - sti + ENABLE_INTERRUPTS pushl $(__USER_DS) CFI_ADJUST_CFA_OFFSET 4 /*CFI_REL_OFFSET ss, 0*/ @@ -320,7 +332,7 @@ sysenter_past_esp: jae syscall_badsys call *sys_call_table(,%eax,4) movl %eax,EAX(%esp) - cli + DISABLE_INTERRUPTS TRACE_IRQS_OFF movl TI_flags(%ebp), %ecx testw $_TIF_ALLWORK_MASK, %cx @@ -330,8 +342,7 @@ sysenter_past_esp: movl OLDESP(%esp), %ecx xorl %ebp,%ebp TRACE_IRQS_ON - sti - sysexit + ENABLE_INTERRUPTS_SYSEXIT CFI_ENDPROC @@ -356,7 +367,7 @@ syscall_call: call *sys_call_table(,%eax,4) movl %eax,EAX(%esp) # store the return value syscall_exit: - cli # make sure we don't miss an interrupt + DISABLE_INTERRUPTS # make sure we don't miss an interrupt # setting need_resched or sigpending # between sampling and the iret TRACE_IRQS_OFF @@ -371,8 +382,8 @@ restore_all: # See comments in process.c:copy_thread() for details. movb OLDSS(%esp), %ah movb CS(%esp), %al - andl $(VM_MASK | (4 << 8) | 3), %eax - cmpl $((4 << 8) | 3), %eax + andl $(VM_MASK | (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 restore_nocheck: @@ -381,11 +392,11 @@ restore_nocheck_notrace: RESTORE_REGS addl $4, %esp CFI_ADJUST_CFA_OFFSET -4 -1: iret +1: INTERRUPT_RETURN .section .fixup,"ax" iret_exc: TRACE_IRQS_ON - sti + ENABLE_INTERRUPTS pushl $0 # no error code pushl $do_iret_error jmp error_code @@ -409,7 +420,7 @@ ldt_ss: * dosemu and wine happy. */ subl $8, %esp # reserve space for switch16 pointer CFI_ADJUST_CFA_OFFSET 8 - cli + DISABLE_INTERRUPTS TRACE_IRQS_OFF movl %esp, %eax /* Set up the 16bit stack frame with switch32 pointer on top, @@ -419,7 +430,7 @@ ldt_ss: TRACE_IRQS_IRET RESTORE_REGS lss 20+4(%esp), %esp # switch to 16bit stack -1: iret +1: INTERRUPT_RETURN .section __ex_table,"a" .align 4 .long 1b,iret_exc @@ -434,7 +445,7 @@ work_pending: jz work_notifysig work_resched: call schedule - cli # make sure we don't miss an interrupt + DISABLE_INTERRUPTS # make sure we don't miss an interrupt # setting need_resched or sigpending # between sampling and the iret TRACE_IRQS_OFF @@ -490,7 +501,7 @@ syscall_exit_work: testb $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP), %cl jz work_pending TRACE_IRQS_ON - sti # could let do_syscall_trace() call + ENABLE_INTERRUPTS # could let do_syscall_trace() call # schedule() instead movl %esp, %eax movl $1, %edx @@ -591,11 +602,9 @@ ENTRY(name) \ /* The include is where all of the SMP etc. interrupts come from */ #include "entry_arch.h" -ENTRY(divide_error) - RING0_INT_FRAME - pushl $0 # no error code - CFI_ADJUST_CFA_OFFSET 4 - pushl $do_divide_error +KPROBE_ENTRY(page_fault) + RING0_EC_FRAME + pushl $do_page_fault CFI_ADJUST_CFA_OFFSET 4 ALIGN error_code: @@ -645,6 +654,7 @@ error_code: call *%edi jmp ret_from_exception CFI_ENDPROC +KPROBE_END(page_fault) ENTRY(coprocessor_error) RING0_INT_FRAME @@ -669,7 +679,7 @@ ENTRY(device_not_available) pushl $-1 # mark this as an int CFI_ADJUST_CFA_OFFSET 4 SAVE_ALL - movl %cr0, %eax + GET_CR0_INTO_EAX testl $0x4, %eax # EM (math emulation bit) jne device_not_available_emulate preempt_stop @@ -702,9 +712,15 @@ device_not_available_emulate: jne ok; \ label: \ movl TSS_sysenter_esp0+offset(%esp),%esp; \ + CFI_DEF_CFA esp, 0; \ + CFI_UNDEFINED eip; \ pushfl; \ + CFI_ADJUST_CFA_OFFSET 4; \ pushl $__KERNEL_CS; \ - pushl $sysenter_past_esp + CFI_ADJUST_CFA_OFFSET 4; \ + pushl $sysenter_past_esp; \ + CFI_ADJUST_CFA_OFFSET 4; \ + CFI_REL_OFFSET eip, 0 KPROBE_ENTRY(debug) RING0_INT_FRAME @@ -720,7 +736,8 @@ debug_stack_correct: call do_debug jmp ret_from_exception CFI_ENDPROC - .previous .text +KPROBE_END(debug) + /* * NMI is doubly nasty. It can happen _while_ we're handling * a debug fault, and the debug fault hasn't yet been able to @@ -729,7 +746,7 @@ debug_stack_correct: * check whether we got an NMI on the debug path where the debug * fault happened on the sysenter path. */ -ENTRY(nmi) +KPROBE_ENTRY(nmi) RING0_INT_FRAME pushl %eax CFI_ADJUST_CFA_OFFSET 4 @@ -754,6 +771,7 @@ ENTRY(nmi) cmpl $sysenter_entry,12(%esp) je nmi_debug_stack_check nmi_stack_correct: + /* We have a RING0_INT_FRAME here */ pushl %eax CFI_ADJUST_CFA_OFFSET 4 SAVE_ALL @@ -764,9 +782,12 @@ nmi_stack_correct: CFI_ENDPROC nmi_stack_fixup: + RING0_INT_FRAME FIX_STACK(12,nmi_stack_correct, 1) jmp nmi_stack_correct + nmi_debug_stack_check: + /* We have a RING0_INT_FRAME here */ cmpw $__KERNEL_CS,16(%esp) jne nmi_stack_correct cmpl $debug,(%esp) @@ -777,8 +798,10 @@ nmi_debug_stack_check: jmp nmi_stack_correct nmi_16bit_stack: - RING0_INT_FRAME - /* create the pointer to lss back */ + /* We have a RING0_INT_FRAME here. + * + * create the pointer to lss back + */ pushl %ss CFI_ADJUST_CFA_OFFSET 4 pushl %esp @@ -799,12 +822,13 @@ nmi_16bit_stack: call do_nmi RESTORE_REGS lss 12+4(%esp), %esp # back to 16bit stack -1: iret +1: INTERRUPT_RETURN CFI_ENDPROC .section __ex_table,"a" .align 4 .long 1b,iret_exc .previous +KPROBE_END(nmi) KPROBE_ENTRY(int3) RING0_INT_FRAME @@ -816,7 +840,7 @@ KPROBE_ENTRY(int3) call do_int3 jmp ret_from_exception CFI_ENDPROC - .previous .text +KPROBE_END(int3) ENTRY(overflow) RING0_INT_FRAME @@ -881,7 +905,7 @@ KPROBE_ENTRY(general_protection) CFI_ADJUST_CFA_OFFSET 4 jmp error_code CFI_ENDPROC - .previous .text +KPROBE_END(general_protection) ENTRY(alignment_check) RING0_EC_FRAME @@ -890,13 +914,14 @@ ENTRY(alignment_check) jmp error_code CFI_ENDPROC -KPROBE_ENTRY(page_fault) - RING0_EC_FRAME - pushl $do_page_fault +ENTRY(divide_error) + RING0_INT_FRAME + pushl $0 # no error code + CFI_ADJUST_CFA_OFFSET 4 + pushl $do_divide_error CFI_ADJUST_CFA_OFFSET 4 jmp error_code CFI_ENDPROC - .previous .text #ifdef CONFIG_X86_MCE ENTRY(machine_check) @@ -949,6 +974,19 @@ ENTRY(arch_unwind_init_running) ENDPROC(arch_unwind_init_running) #endif +ENTRY(kernel_thread_helper) + pushl $0 # fake return address for unwinder + CFI_STARTPROC + movl %edx,%eax + push %edx + CFI_ADJUST_CFA_OFFSET 4 + call *%ebx + push %eax + CFI_ADJUST_CFA_OFFSET 4 + call do_exit + CFI_ENDPROC +ENDPROC(kernel_thread_helper) + .section .rodata,"a" #include "syscall_table.S" diff --git a/arch/i386/kernel/head.S b/arch/i386/kernel/head.S index a6b8bd8..be9d883 100644 --- a/arch/i386/kernel/head.S +++ b/arch/i386/kernel/head.S @@ -371,8 +371,65 @@ rp_sidt: addl $8,%edi dec %ecx jne rp_sidt + +.macro set_early_handler handler,trapno + lea \handler,%edx + movl $(__KERNEL_CS << 16),%eax + movw %dx,%ax + movw $0x8E00,%dx /* interrupt gate - dpl=0, present */ + lea idt_table,%edi + movl %eax,8*\trapno(%edi) + movl %edx,8*\trapno+4(%edi) +.endm + + set_early_handler handler=early_divide_err,trapno=0 + set_early_handler handler=early_illegal_opcode,trapno=6 + set_early_handler handler=early_protection_fault,trapno=13 + set_early_handler handler=early_page_fault,trapno=14 + ret +early_divide_err: + xor %edx,%edx + pushl $0 /* fake errcode */ + jmp early_fault + +early_illegal_opcode: + movl $6,%edx + pushl $0 /* fake errcode */ + jmp early_fault + +early_protection_fault: + movl $13,%edx + jmp early_fault + +early_page_fault: + movl $14,%edx + jmp early_fault + +early_fault: + cld +#ifdef CONFIG_PRINTK + movl $(__KERNEL_DS),%eax + movl %eax,%ds + movl %eax,%es + cmpl $2,early_recursion_flag + je hlt_loop + incl early_recursion_flag + movl %cr2,%eax + pushl %eax + pushl %edx /* trapno */ + pushl $fault_msg +#ifdef CONFIG_EARLY_PRINTK + call early_printk +#else + call printk +#endif +#endif +hlt_loop: + hlt + jmp hlt_loop + /* This is the default interrupt "handler" :-) */ ALIGN ignore_int: @@ -386,6 +443,9 @@ ignore_int: movl $(__KERNEL_DS),%eax movl %eax,%ds movl %eax,%es + cmpl $2,early_recursion_flag + je hlt_loop + incl early_recursion_flag pushl 16(%esp) pushl 24(%esp) pushl 32(%esp) @@ -431,9 +491,16 @@ ENTRY(stack_start) ready: .byte 0 +early_recursion_flag: + .long 0 + int_msg: .asciz "Unknown interrupt or fault at EIP %p %p %p\n" +fault_msg: + .ascii "Int %d: CR2 %p err %p EIP %p CS %p flags %p\n" + .asciz "Stack: %p %p %p %p %p %p %p %p\n" + /* * The IDT and GDT 'descriptors' are a strange 48-bit object * only used by the lidt and lgdt instructions. They are not diff --git a/arch/i386/kernel/i8259.c b/arch/i386/kernel/i8259.c index d4756d1..ea5f4e7 100644 --- a/arch/i386/kernel/i8259.c +++ b/arch/i386/kernel/i8259.c @@ -45,6 +45,8 @@ static void end_8259A_irq (unsigned int irq) #define shutdown_8259A_irq disable_8259A_irq +static int i8259A_auto_eoi; + static void mask_and_ack_8259A(unsigned int); unsigned int startup_8259A_irq(unsigned int irq) @@ -253,7 +255,7 @@ static void save_ELCR(char *trigger) static int i8259A_resume(struct sys_device *dev) { - init_8259A(0); + init_8259A(i8259A_auto_eoi); restore_ELCR(irq_trigger); return 0; } @@ -301,6 +303,8 @@ void init_8259A(int auto_eoi) { unsigned long flags; + i8259A_auto_eoi = auto_eoi; + spin_lock_irqsave(&i8259A_lock, flags); outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */ diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c index 4fb32c5..fd0df75 100644 --- a/arch/i386/kernel/io_apic.c +++ b/arch/i386/kernel/io_apic.c @@ -40,6 +40,7 @@ #include <asm/nmi.h> #include <mach_apic.h> +#include <mach_apicdef.h> #include "io_ports.h" @@ -65,7 +66,7 @@ int sis_apic_bug = -1; */ int nr_ioapic_registers[MAX_IO_APICS]; -int disable_timer_pin_1 __initdata; +static int disable_timer_pin_1 __initdata; /* * Rough estimation of how many shared IRQs there are, can @@ -93,6 +94,34 @@ int vector_irq[NR_VECTORS] __read_mostly = { [0 ... NR_VECTORS - 1] = -1}; #define vector_to_irq(vector) (vector) #endif + +union entry_union { + struct { u32 w1, w2; }; + struct IO_APIC_route_entry entry; +}; + +static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin) +{ + union entry_union eu; + unsigned long flags; + spin_lock_irqsave(&ioapic_lock, flags); + eu.w1 = io_apic_read(apic, 0x10 + 2 * pin); + eu.w2 = io_apic_read(apic, 0x11 + 2 * pin); + spin_unlock_irqrestore(&ioapic_lock, flags); + return eu.entry; +} + +static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e) +{ + unsigned long flags; + union entry_union eu; + eu.entry = e; + spin_lock_irqsave(&ioapic_lock, flags); + io_apic_write(apic, 0x10 + 2*pin, eu.w1); + io_apic_write(apic, 0x11 + 2*pin, eu.w2); + spin_unlock_irqrestore(&ioapic_lock, flags); +} + /* * The common case is 1:1 IRQ<->pin mappings. Sometimes there are * shared ISA-space IRQs, so we have to support them. We are super @@ -200,13 +229,9 @@ static void unmask_IO_APIC_irq (unsigned int irq) static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) { struct IO_APIC_route_entry entry; - unsigned long flags; /* Check delivery_mode to be sure we're not clearing an SMI pin */ - spin_lock_irqsave(&ioapic_lock, flags); - *(((int*)&entry) + 0) = io_apic_read(apic, 0x10 + 2 * pin); - *(((int*)&entry) + 1) = io_apic_read(apic, 0x11 + 2 * pin); - spin_unlock_irqrestore(&ioapic_lock, flags); + entry = ioapic_read_entry(apic, pin); if (entry.delivery_mode == dest_SMI) return; @@ -215,10 +240,7 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) */ memset(&entry, 0, sizeof(entry)); entry.mask = 1; - spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(apic, 0x10 + 2 * pin, *(((int *)&entry) + 0)); - io_apic_write(apic, 0x11 + 2 * pin, *(((int *)&entry) + 1)); - spin_unlock_irqrestore(&ioapic_lock, flags); + ioapic_write_entry(apic, pin, entry); } static void clear_IO_APIC (void) @@ -1283,9 +1305,8 @@ static void __init setup_IO_APIC_irqs(void) if (!apic && (irq < 16)) disable_8259A_irq(irq); } + ioapic_write_entry(apic, pin, entry); 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)); set_native_irq_info(irq, TARGET_CPUS); spin_unlock_irqrestore(&ioapic_lock, flags); } @@ -1301,7 +1322,6 @@ 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)); @@ -1331,10 +1351,7 @@ 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); } @@ -1444,10 +1461,7 @@ void __init print_IO_APIC(void) for (i = 0; i <= reg_01.bits.entries; i++) { struct IO_APIC_route_entry entry; - spin_lock_irqsave(&ioapic_lock, flags); - *(((int *)&entry)+0) = io_apic_read(apic, 0x10+i*2); - *(((int *)&entry)+1) = io_apic_read(apic, 0x11+i*2); - spin_unlock_irqrestore(&ioapic_lock, flags); + entry = ioapic_read_entry(apic, i); printk(KERN_DEBUG " %02x %03X %02X ", i, @@ -1666,10 +1680,7 @@ static void __init enable_IO_APIC(void) /* See if any of the pins is in ExtINT mode */ for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) { struct IO_APIC_route_entry entry; - spin_lock_irqsave(&ioapic_lock, flags); - *(((int *)&entry) + 0) = io_apic_read(apic, 0x10 + 2 * pin); - *(((int *)&entry) + 1) = io_apic_read(apic, 0x11 + 2 * pin); - spin_unlock_irqrestore(&ioapic_lock, flags); + entry = ioapic_read_entry(apic, pin); /* If the interrupt line is enabled and in ExtInt mode @@ -1726,7 +1737,6 @@ void disable_IO_APIC(void) */ if (ioapic_i8259.pin != -1) { struct IO_APIC_route_entry entry; - unsigned long flags; memset(&entry, 0, sizeof(entry)); entry.mask = 0; /* Enabled */ @@ -1743,12 +1753,7 @@ void disable_IO_APIC(void) /* * Add it to the IO-APIC irq-routing table: */ - spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(ioapic_i8259.apic, 0x11+2*ioapic_i8259.pin, - *(((int *)&entry)+1)); - io_apic_write(ioapic_i8259.apic, 0x10+2*ioapic_i8259.pin, - *(((int *)&entry)+0)); - spin_unlock_irqrestore(&ioapic_lock, flags); + ioapic_write_entry(ioapic_i8259.apic, ioapic_i8259.pin, entry); } disconnect_bsp_APIC(ioapic_i8259.pin != -1); } @@ -2213,17 +2218,13 @@ static inline void 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)); @@ -2236,10 +2237,7 @@ 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); @@ -2258,10 +2256,7 @@ 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); } int timer_uses_ioapic_pin_0; @@ -2461,17 +2456,12 @@ static int ioapic_suspend(struct sys_device *dev, pm_message_t state) { struct IO_APIC_route_entry *entry; struct sysfs_ioapic_data *data; - unsigned long flags; int i; data = container_of(dev, struct sysfs_ioapic_data, dev); entry = data->entry; - spin_lock_irqsave(&ioapic_lock, flags); - for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ ) { - *(((int *)entry) + 1) = io_apic_read(dev->id, 0x11 + 2 * i); - *(((int *)entry) + 0) = io_apic_read(dev->id, 0x10 + 2 * i); - } - spin_unlock_irqrestore(&ioapic_lock, flags); + for (i = 0; i < nr_ioapic_registers[dev->id]; i ++) + entry[i] = ioapic_read_entry(dev->id, i); return 0; } @@ -2493,11 +2483,9 @@ static int ioapic_resume(struct sys_device *dev) reg_00.bits.ID = mp_ioapics[dev->id].mpc_apicid; io_apic_write(dev->id, 0, reg_00.raw); } - for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ ) { - io_apic_write(dev->id, 0x11+2*i, *(((int *)entry)+1)); - io_apic_write(dev->id, 0x10+2*i, *(((int *)entry)+0)); - } spin_unlock_irqrestore(&ioapic_lock, flags); + for (i = 0; i < nr_ioapic_registers[dev->id]; i ++) + ioapic_write_entry(dev->id, i, entry[i]); return 0; } @@ -2694,9 +2682,8 @@ 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); + ioapic_write_entry(ioapic, pin, entry); spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(ioapic, 0x11+2*pin, *(((int *)&entry)+1)); - io_apic_write(ioapic, 0x10+2*pin, *(((int *)&entry)+0)); set_native_irq_info(use_pci_vector() ? entry.vector : irq, TARGET_CPUS); spin_unlock_irqrestore(&ioapic_lock, flags); @@ -2704,3 +2691,25 @@ int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int a } #endif /* CONFIG_ACPI */ + +static int __init parse_disable_timer_pin_1(char *arg) +{ + disable_timer_pin_1 = 1; + return 0; +} +early_param("disable_timer_pin_1", parse_disable_timer_pin_1); + +static int __init parse_enable_timer_pin_1(char *arg) +{ + disable_timer_pin_1 = -1; + return 0; +} +early_param("enable_timer_pin_1", parse_enable_timer_pin_1); + +static int __init parse_noapic(char *arg) +{ + /* disable IO-APIC */ + disable_ioapic_setup(); + return 0; +} +early_param("noapic", parse_noapic); diff --git a/arch/i386/kernel/machine_kexec.c b/arch/i386/kernel/machine_kexec.c index 6b1ae6b..91966ba 100644 --- a/arch/i386/kernel/machine_kexec.c +++ b/arch/i386/kernel/machine_kexec.c @@ -9,6 +9,7 @@ #include <linux/mm.h> #include <linux/kexec.h> #include <linux/delay.h> +#include <linux/init.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> @@ -20,70 +21,13 @@ #include <asm/system.h> #define PAGE_ALIGNED __attribute__ ((__aligned__(PAGE_SIZE))) - -#define L0_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY) -#define L1_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY) -#define L2_ATTR (_PAGE_PRESENT) - -#define LEVEL0_SIZE (1UL << 12UL) - -#ifndef CONFIG_X86_PAE -#define LEVEL1_SIZE (1UL << 22UL) -static u32 pgtable_level1[1024] PAGE_ALIGNED; - -static void identity_map_page(unsigned long address) -{ - unsigned long level1_index, level2_index; - u32 *pgtable_level2; - - /* Find the current page table */ - pgtable_level2 = __va(read_cr3()); - - /* Find the indexes of the physical address to identity map */ - level1_index = (address % LEVEL1_SIZE)/LEVEL0_SIZE; - level2_index = address / LEVEL1_SIZE; - - /* Identity map the page table entry */ - pgtable_level1[level1_index] = address | L0_ATTR; - pgtable_level2[level2_index] = __pa(pgtable_level1) | L1_ATTR; - - /* Flush the tlb so the new mapping takes effect. - * Global tlb entries are not flushed but that is not an issue. - */ - load_cr3(pgtable_level2); -} - -#else -#define LEVEL1_SIZE (1UL << 21UL) -#define LEVEL2_SIZE (1UL << 30UL) -static u64 pgtable_level1[512] PAGE_ALIGNED; -static u64 pgtable_level2[512] PAGE_ALIGNED; - -static void identity_map_page(unsigned long address) -{ - unsigned long level1_index, level2_index, level3_index; - u64 *pgtable_level3; - - /* Find the current page table */ - pgtable_level3 = __va(read_cr3()); - - /* Find the indexes of the physical address to identity map */ - level1_index = (address % LEVEL1_SIZE)/LEVEL0_SIZE; - level2_index = (address % LEVEL2_SIZE)/LEVEL1_SIZE; - level3_index = address / LEVEL2_SIZE; - - /* Identity map the page table entry */ - pgtable_level1[level1_index] = address | L0_ATTR; - pgtable_level2[level2_index] = __pa(pgtable_level1) | L1_ATTR; - set_64bit(&pgtable_level3[level3_index], - __pa(pgtable_level2) | L2_ATTR); - - /* Flush the tlb so the new mapping takes effect. - * Global tlb entries are not flushed but that is not an issue. - */ - load_cr3(pgtable_level3); -} +static u32 kexec_pgd[1024] PAGE_ALIGNED; +#ifdef CONFIG_X86_PAE +static u32 kexec_pmd0[1024] PAGE_ALIGNED; +static u32 kexec_pmd1[1024] PAGE_ALIGNED; #endif +static u32 kexec_pte0[1024] PAGE_ALIGNED; +static u32 kexec_pte1[1024] PAGE_ALIGNED; static void set_idt(void *newidt, __u16 limit) { @@ -127,16 +71,6 @@ static void load_segments(void) #undef __STR } -typedef asmlinkage NORET_TYPE void (*relocate_new_kernel_t)( - unsigned long indirection_page, - unsigned long reboot_code_buffer, - unsigned long start_address, - unsigned int has_pae) ATTRIB_NORET; - -extern const unsigned char relocate_new_kernel[]; -extern void relocate_new_kernel_end(void); -extern const unsigned int relocate_new_kernel_size; - /* * A architecture hook called to validate the * proposed image and prepare the control pages @@ -169,25 +103,29 @@ void machine_kexec_cleanup(struct kimage *image) */ NORET_TYPE void machine_kexec(struct kimage *image) { - unsigned long page_list; - unsigned long reboot_code_buffer; - - relocate_new_kernel_t rnk; + unsigned long page_list[PAGES_NR]; + void *control_page; /* Interrupts aren't acceptable while we reboot */ local_irq_disable(); - /* Compute some offsets */ - reboot_code_buffer = page_to_pfn(image->control_code_page) - << PAGE_SHIFT; - page_list = image->head; - - /* Set up an identity mapping for the reboot_code_buffer */ - identity_map_page(reboot_code_buffer); - - /* copy it out */ - memcpy((void *)reboot_code_buffer, relocate_new_kernel, - relocate_new_kernel_size); + control_page = page_address(image->control_code_page); + memcpy(control_page, relocate_kernel, PAGE_SIZE); + + page_list[PA_CONTROL_PAGE] = __pa(control_page); + page_list[VA_CONTROL_PAGE] = (unsigned long)relocate_kernel; + page_list[PA_PGD] = __pa(kexec_pgd); + page_list[VA_PGD] = (unsigned long)kexec_pgd; +#ifdef CONFIG_X86_PAE + page_list[PA_PMD_0] = __pa(kexec_pmd0); + page_list[VA_PMD_0] = (unsigned long)kexec_pmd0; + page_list[PA_PMD_1] = __pa(kexec_pmd1); + page_list[VA_PMD_1] = (unsigned long)kexec_pmd1; +#endif + page_list[PA_PTE_0] = __pa(kexec_pte0); + page_list[VA_PTE_0] = (unsigned long)kexec_pte0; + page_list[PA_PTE_1] = __pa(kexec_pte1); + page_list[VA_PTE_1] = (unsigned long)kexec_pte1; /* The segment registers are funny things, they have both a * visible and an invisible part. Whenever the visible part is @@ -206,6 +144,28 @@ NORET_TYPE void machine_kexec(struct kimage *image) set_idt(phys_to_virt(0),0); /* now call it */ - rnk = (relocate_new_kernel_t) reboot_code_buffer; - (*rnk)(page_list, reboot_code_buffer, image->start, cpu_has_pae); + relocate_kernel((unsigned long)image->head, (unsigned long)page_list, + image->start, cpu_has_pae); +} + +/* crashkernel=size@addr specifies the location to reserve for + * a crash kernel. By reserving this memory we guarantee + * that linux never sets it up as a DMA target. + * Useful for holding code to do something appropriate + * after a kernel panic. + */ +static int __init parse_crashkernel(char *arg) +{ + unsigned long size, base; + size = memparse(arg, &arg); + if (*arg == '@') { + base = memparse(arg+1, &arg); + /* FIXME: Do I want a sanity check + * to validate the memory range? + */ + crashk_res.start = base; + crashk_res.end = base + size - 1; + } + return 0; } +early_param("crashkernel", parse_crashkernel); diff --git a/arch/i386/kernel/mca.c b/arch/i386/kernel/mca.c index cd5456f..eb57a85 100644 --- a/arch/i386/kernel/mca.c +++ b/arch/i386/kernel/mca.c @@ -42,6 +42,7 @@ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/mca.h> +#include <linux/kprobes.h> #include <asm/system.h> #include <asm/io.h> #include <linux/proc_fs.h> @@ -414,7 +415,8 @@ subsys_initcall(mca_init); /*--------------------------------------------------------------------*/ -static void mca_handle_nmi_device(struct mca_device *mca_dev, int check_flag) +static __kprobes void +mca_handle_nmi_device(struct mca_device *mca_dev, int check_flag) { int slot = mca_dev->slot; @@ -444,7 +446,7 @@ static void mca_handle_nmi_device(struct mca_device *mca_dev, int check_flag) /*--------------------------------------------------------------------*/ -static int mca_handle_nmi_callback(struct device *dev, void *data) +static int __kprobes mca_handle_nmi_callback(struct device *dev, void *data) { struct mca_device *mca_dev = to_mca_device(dev); unsigned char pos5; @@ -462,7 +464,7 @@ static int mca_handle_nmi_callback(struct device *dev, void *data) return 0; } -void mca_handle_nmi(void) +void __kprobes mca_handle_nmi(void) { /* First try - scan the various adapters and see if a specific * adapter was responsible for the error. diff --git a/arch/i386/kernel/mpparse.c b/arch/i386/kernel/mpparse.c index a70b5fa..442aaf8 100644 --- a/arch/i386/kernel/mpparse.c +++ b/arch/i386/kernel/mpparse.c @@ -30,6 +30,7 @@ #include <asm/io_apic.h> #include <mach_apic.h> +#include <mach_apicdef.h> #include <mach_mpparse.h> #include <bios_ebda.h> @@ -68,7 +69,7 @@ unsigned int def_to_bigsmp = 0; /* Processor that is doing the boot up */ unsigned int boot_cpu_physical_apicid = -1U; /* Internal processor count */ -static unsigned int __devinitdata num_processors; +unsigned int __cpuinitdata num_processors; /* Bitmask of physically existing CPUs */ physid_mask_t phys_cpu_present_map; @@ -228,12 +229,14 @@ static void __init MP_bus_info (struct mpc_config_bus *m) mpc_oem_bus_info(m, str, translation_table[mpc_record]); +#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); return; } +#endif if (strncmp(str, BUSTYPE_ISA, sizeof(BUSTYPE_ISA)-1) == 0) { mp_bus_id_to_type[m->mpc_busid] = MP_BUS_ISA; @@ -293,19 +296,6 @@ static void __init MP_lintsrc_info (struct mpc_config_lintsrc *m) m->mpc_irqtype, m->mpc_irqflag & 3, (m->mpc_irqflag >> 2) &3, m->mpc_srcbusid, m->mpc_srcbusirq, m->mpc_destapic, m->mpc_destapiclint); - /* - * Well it seems all SMP boards in existence - * use ExtINT/LVT1 == LINT0 and - * NMI/LVT2 == LINT1 - the following check - * will show us if this assumptions is false. - * Until then we do not have to add baggage. - */ - if ((m->mpc_irqtype == mp_ExtINT) && - (m->mpc_destapiclint != 0)) - BUG(); - if ((m->mpc_irqtype == mp_NMI) && - (m->mpc_destapiclint != 1)) - BUG(); } #ifdef CONFIG_X86_NUMAQ @@ -822,8 +812,7 @@ int es7000_plat; #ifdef CONFIG_ACPI -void __init mp_register_lapic_address ( - u64 address) +void __init mp_register_lapic_address(u64 address) { mp_lapic_addr = (unsigned long) address; @@ -835,13 +824,10 @@ void __init mp_register_lapic_address ( Dprintk("Boot CPU = %d\n", boot_cpu_physical_apicid); } - -void __devinit mp_register_lapic ( - u8 id, - u8 enabled) +void __devinit mp_register_lapic (u8 id, u8 enabled) { struct mpc_config_processor processor; - int boot_cpu = 0; + int boot_cpu = 0; if (MAX_APICS - id <= 0) { printk(KERN_WARNING "Processor #%d invalid (max %d)\n", @@ -878,11 +864,9 @@ static struct mp_ioapic_routing { u32 pin_programmed[4]; } mp_ioapic_routing[MAX_IO_APICS]; - -static int mp_find_ioapic ( - int gsi) +static int mp_find_ioapic (int gsi) { - int i = 0; + int i = 0; /* Find the IOAPIC that manages this GSI. */ for (i = 0; i < nr_ioapics; i++) { @@ -895,15 +879,11 @@ static int mp_find_ioapic ( return -1; } - -void __init mp_register_ioapic ( - u8 id, - u32 address, - u32 gsi_base) +void __init mp_register_ioapic(u8 id, u32 address, u32 gsi_base) { - int idx = 0; - int tmpid; + int idx = 0; + int tmpid; if (nr_ioapics >= MAX_IO_APICS) { printk(KERN_ERR "ERROR: Max # of I/O APICs (%d) exceeded " @@ -949,16 +929,10 @@ void __init mp_register_ioapic ( mp_ioapics[idx].mpc_apicver, mp_ioapics[idx].mpc_apicaddr, mp_ioapic_routing[idx].gsi_base, mp_ioapic_routing[idx].gsi_end); - - return; } - -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; @@ -996,15 +970,13 @@ void __init mp_override_legacy_irq ( mp_irqs[mp_irq_entries] = intsrc; if (++mp_irq_entries == MAX_IRQ_SOURCES) panic("Max # of irq sources exceeded!\n"); - - return; } void __init mp_config_acpi_legacy_irqs (void) { struct mpc_config_intsrc intsrc; - int i = 0; - int ioapic = -1; + int i = 0; + int ioapic = -1; /* * Fabricate the legacy ISA bus (bus #31). @@ -1073,12 +1045,12 @@ void __init mp_config_acpi_legacy_irqs (void) #define MAX_GSI_NUM 4096 -int mp_register_gsi (u32 gsi, int triggering, int polarity) +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 = 16; + int ioapic = -1; + int ioapic_pin = 0; + int idx, bit = 0; + static int pci_irq = 16; /* * Mapping between Global System Interrups, which * represent all possible interrupts, and IRQs diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c index acb3514..dbda706 100644 --- a/arch/i386/kernel/nmi.c +++ b/arch/i386/kernel/nmi.c @@ -21,83 +21,174 @@ #include <linux/sysdev.h> #include <linux/sysctl.h> #include <linux/percpu.h> +#include <linux/dmi.h> +#include <linux/kprobes.h> #include <asm/smp.h> #include <asm/nmi.h> +#include <asm/kdebug.h> #include <asm/intel_arch_perfmon.h> #include "mach_traps.h" -unsigned int nmi_watchdog = NMI_NONE; -extern int unknown_nmi_panic; -static unsigned int nmi_hz = HZ; -static unsigned int nmi_perfctr_msr; /* the MSR to reset in NMI handler */ -static unsigned int nmi_p4_cccr_val; -extern void show_registers(struct pt_regs *regs); +/* perfctr_nmi_owner tracks the ownership of the perfctr registers: + * evtsel_nmi_owner tracks the ownership of the event selection + * - different performance counters/ event selection may be reserved for + * different subsystems this reservation system just tries to coordinate + * things a little + */ +static DEFINE_PER_CPU(unsigned long, perfctr_nmi_owner); +static DEFINE_PER_CPU(unsigned long, evntsel_nmi_owner[3]); -/* - * lapic_nmi_owner tracks the ownership of the lapic NMI hardware: - * - it may be reserved by some other driver, or not - * - when not reserved by some other driver, it may be used for - * the NMI watchdog, or not - * - * This is maintained separately from nmi_active because the NMI - * watchdog may also be driven from the I/O APIC timer. +/* this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's + * offset from MSR_P4_BSU_ESCR0. It will be the max for all platforms (for now) */ -static DEFINE_SPINLOCK(lapic_nmi_owner_lock); -static unsigned int lapic_nmi_owner; -#define LAPIC_NMI_WATCHDOG (1<<0) -#define LAPIC_NMI_RESERVED (1<<1) +#define NMI_MAX_COUNTER_BITS 66 /* nmi_active: - * +1: the lapic NMI watchdog is active, but can be disabled - * 0: the lapic NMI watchdog has not been set up, and cannot + * >0: the lapic NMI watchdog is active, but can be disabled + * <0: the lapic NMI watchdog has not been set up, and cannot * be enabled - * -1: the lapic NMI watchdog is disabled, but can be enabled + * 0: the lapic NMI watchdog is disabled, but can be enabled */ -int nmi_active; +atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */ -#define K7_EVNTSEL_ENABLE (1 << 22) -#define K7_EVNTSEL_INT (1 << 20) -#define K7_EVNTSEL_OS (1 << 17) -#define K7_EVNTSEL_USR (1 << 16) -#define K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING 0x76 -#define K7_NMI_EVENT K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING +unsigned int nmi_watchdog = NMI_DEFAULT; +static unsigned int nmi_hz = HZ; -#define P6_EVNTSEL0_ENABLE (1 << 22) -#define P6_EVNTSEL_INT (1 << 20) -#define P6_EVNTSEL_OS (1 << 17) -#define P6_EVNTSEL_USR (1 << 16) -#define P6_EVENT_CPU_CLOCKS_NOT_HALTED 0x79 -#define P6_NMI_EVENT P6_EVENT_CPU_CLOCKS_NOT_HALTED +struct nmi_watchdog_ctlblk { + int enabled; + u64 check_bit; + unsigned int cccr_msr; + unsigned int perfctr_msr; /* the MSR to reset in NMI handler */ + unsigned int evntsel_msr; /* the MSR to select the events to handle */ +}; +static DEFINE_PER_CPU(struct nmi_watchdog_ctlblk, nmi_watchdog_ctlblk); -#define MSR_P4_MISC_ENABLE 0x1A0 -#define MSR_P4_MISC_ENABLE_PERF_AVAIL (1<<7) -#define MSR_P4_MISC_ENABLE_PEBS_UNAVAIL (1<<12) -#define MSR_P4_PERFCTR0 0x300 -#define MSR_P4_CCCR0 0x360 -#define P4_ESCR_EVENT_SELECT(N) ((N)<<25) -#define P4_ESCR_OS (1<<3) -#define P4_ESCR_USR (1<<2) -#define P4_CCCR_OVF_PMI0 (1<<26) -#define P4_CCCR_OVF_PMI1 (1<<27) -#define P4_CCCR_THRESHOLD(N) ((N)<<20) -#define P4_CCCR_COMPLEMENT (1<<19) -#define P4_CCCR_COMPARE (1<<18) -#define P4_CCCR_REQUIRED (3<<16) -#define P4_CCCR_ESCR_SELECT(N) ((N)<<13) -#define P4_CCCR_ENABLE (1<<12) -/* Set up IQ_COUNTER0 to behave like a clock, by having IQ_CCCR0 filter - CRU_ESCR0 (with any non-null event selector) through a complemented - max threshold. [IA32-Vol3, Section 14.9.9] */ -#define MSR_P4_IQ_COUNTER0 0x30C -#define P4_NMI_CRU_ESCR0 (P4_ESCR_EVENT_SELECT(0x3F)|P4_ESCR_OS|P4_ESCR_USR) -#define P4_NMI_IQ_CCCR0 \ - (P4_CCCR_OVF_PMI0|P4_CCCR_THRESHOLD(15)|P4_CCCR_COMPLEMENT| \ - P4_CCCR_COMPARE|P4_CCCR_REQUIRED|P4_CCCR_ESCR_SELECT(4)|P4_CCCR_ENABLE) +/* local prototypes */ +static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu); -#define ARCH_PERFMON_NMI_EVENT_SEL ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL -#define ARCH_PERFMON_NMI_EVENT_UMASK ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK +extern void show_registers(struct pt_regs *regs); +extern int unknown_nmi_panic; + +/* converts an msr to an appropriate reservation bit */ +static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr) +{ + /* returns the bit offset of the performance counter register */ + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_AMD: + return (msr - MSR_K7_PERFCTR0); + case X86_VENDOR_INTEL: + if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) + return (msr - MSR_ARCH_PERFMON_PERFCTR0); + + switch (boot_cpu_data.x86) { + case 6: + return (msr - MSR_P6_PERFCTR0); + case 15: + return (msr - MSR_P4_BPU_PERFCTR0); + } + } + return 0; +} + +/* converts an msr to an appropriate reservation bit */ +static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr) +{ + /* returns the bit offset of the event selection register */ + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_AMD: + return (msr - MSR_K7_EVNTSEL0); + case X86_VENDOR_INTEL: + if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) + return (msr - MSR_ARCH_PERFMON_EVENTSEL0); + + switch (boot_cpu_data.x86) { + case 6: + return (msr - MSR_P6_EVNTSEL0); + case 15: + return (msr - MSR_P4_BSU_ESCR0); + } + } + return 0; +} + +/* checks for a bit availability (hack for oprofile) */ +int avail_to_resrv_perfctr_nmi_bit(unsigned int counter) +{ + BUG_ON(counter > NMI_MAX_COUNTER_BITS); + + return (!test_bit(counter, &__get_cpu_var(perfctr_nmi_owner))); +} + +/* checks the an msr for availability */ +int avail_to_resrv_perfctr_nmi(unsigned int msr) +{ + unsigned int counter; + + counter = nmi_perfctr_msr_to_bit(msr); + BUG_ON(counter > NMI_MAX_COUNTER_BITS); + + return (!test_bit(counter, &__get_cpu_var(perfctr_nmi_owner))); +} + +int reserve_perfctr_nmi(unsigned int msr) +{ + unsigned int counter; + + counter = nmi_perfctr_msr_to_bit(msr); + BUG_ON(counter > NMI_MAX_COUNTER_BITS); + + if (!test_and_set_bit(counter, &__get_cpu_var(perfctr_nmi_owner))) + return 1; + return 0; +} + +void release_perfctr_nmi(unsigned int msr) +{ + unsigned int counter; + + counter = nmi_perfctr_msr_to_bit(msr); + BUG_ON(counter > NMI_MAX_COUNTER_BITS); + + clear_bit(counter, &__get_cpu_var(perfctr_nmi_owner)); +} + +int reserve_evntsel_nmi(unsigned int msr) +{ + unsigned int counter; + + counter = nmi_evntsel_msr_to_bit(msr); + BUG_ON(counter > NMI_MAX_COUNTER_BITS); + + if (!test_and_set_bit(counter, &__get_cpu_var(evntsel_nmi_owner)[0])) + return 1; + return 0; +} + +void release_evntsel_nmi(unsigned int msr) +{ + unsigned int counter; + + counter = nmi_evntsel_msr_to_bit(msr); + BUG_ON(counter > NMI_MAX_COUNTER_BITS); + + clear_bit(counter, &__get_cpu_var(evntsel_nmi_owner)[0]); +} + +static __cpuinit inline int nmi_known_cpu(void) +{ + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_AMD: + return ((boot_cpu_data.x86 == 15) || (boot_cpu_data.x86 == 6)); + case X86_VENDOR_INTEL: + if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) + return 1; + else + return ((boot_cpu_data.x86 == 15) || (boot_cpu_data.x86 == 6)); + } + return 0; +} #ifdef CONFIG_SMP /* The performance counters used by NMI_LOCAL_APIC don't trigger when @@ -125,7 +216,18 @@ static int __init check_nmi_watchdog(void) unsigned int *prev_nmi_count; int cpu; - if (nmi_watchdog == NMI_NONE) + /* Enable NMI watchdog for newer systems. + Actually it should be safe for most systems before 2004 too except + for some IBM systems that corrupt registers when NMI happens + during SMM. Unfortunately we don't have more exact information + on these and use this coarse check. */ + if (nmi_watchdog == NMI_DEFAULT && dmi_get_year(DMI_BIOS_DATE) >= 2004) + nmi_watchdog = NMI_LOCAL_APIC; + + if ((nmi_watchdog == NMI_NONE) || (nmi_watchdog == NMI_DEFAULT)) + return 0; + + if (!atomic_read(&nmi_active)) return 0; prev_nmi_count = kmalloc(NR_CPUS * sizeof(int), GFP_KERNEL); @@ -149,25 +251,45 @@ static int __init check_nmi_watchdog(void) if (!cpu_isset(cpu, cpu_callin_map)) continue; #endif + if (!per_cpu(nmi_watchdog_ctlblk, cpu).enabled) + continue; if (nmi_count(cpu) - prev_nmi_count[cpu] <= 5) { - endflag = 1; printk("CPU#%d: NMI appears to be stuck (%d->%d)!\n", cpu, prev_nmi_count[cpu], nmi_count(cpu)); - nmi_active = 0; - lapic_nmi_owner &= ~LAPIC_NMI_WATCHDOG; - kfree(prev_nmi_count); - return -1; + per_cpu(nmi_watchdog_ctlblk, cpu).enabled = 0; + atomic_dec(&nmi_active); } } + if (!atomic_read(&nmi_active)) { + kfree(prev_nmi_count); + atomic_set(&nmi_active, -1); + return -1; + } endflag = 1; printk("OK.\n"); /* now that we know it works we can reduce NMI frequency to something more reasonable; makes a difference in some configs */ - if (nmi_watchdog == NMI_LOCAL_APIC) + if (nmi_watchdog == NMI_LOCAL_APIC) { + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); + nmi_hz = 1; + /* + * On Intel CPUs with ARCH_PERFMON only 32 bits in the counter + * are writable, with higher bits sign extending from bit 31. + * So, we can only program the counter with 31 bit values and + * 32nd bit should be 1, for 33.. to be 1. + * Find the appropriate nmi_hz + */ + if (wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0 && + ((u64)cpu_khz * 1000) > 0x7fffffffULL) { + u64 count = (u64)cpu_khz * 1000; + do_div(count, 0x7fffffffUL); + nmi_hz = count + 1; + } + } kfree(prev_nmi_count); return 0; @@ -181,124 +303,70 @@ static int __init setup_nmi_watchdog(char *str) get_option(&str, &nmi); - if (nmi >= NMI_INVALID) + if ((nmi >= NMI_INVALID) || (nmi < NMI_NONE)) return 0; - if (nmi == NMI_NONE) - nmi_watchdog = nmi; /* * If any other x86 CPU has a local APIC, then * please test the NMI stuff there and send me the * missing bits. Right now Intel P6/P4 and AMD K7 only. */ - if ((nmi == NMI_LOCAL_APIC) && - (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && - (boot_cpu_data.x86 == 6 || boot_cpu_data.x86 == 15)) - nmi_watchdog = nmi; - if ((nmi == NMI_LOCAL_APIC) && - (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && - (boot_cpu_data.x86 == 6 || boot_cpu_data.x86 == 15)) - nmi_watchdog = nmi; - /* - * We can enable the IO-APIC watchdog - * unconditionally. - */ - if (nmi == NMI_IO_APIC) { - nmi_active = 1; - nmi_watchdog = nmi; - } + if ((nmi == NMI_LOCAL_APIC) && (nmi_known_cpu() == 0)) + return 0; /* no lapic support */ + nmi_watchdog = nmi; return 1; } __setup("nmi_watchdog=", setup_nmi_watchdog); -static void disable_intel_arch_watchdog(void); - static void disable_lapic_nmi_watchdog(void) { - if (nmi_active <= 0) + BUG_ON(nmi_watchdog != NMI_LOCAL_APIC); + + if (atomic_read(&nmi_active) <= 0) return; - switch (boot_cpu_data.x86_vendor) { - case X86_VENDOR_AMD: - wrmsr(MSR_K7_EVNTSEL0, 0, 0); - break; - case X86_VENDOR_INTEL: - if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { - disable_intel_arch_watchdog(); - break; - } - switch (boot_cpu_data.x86) { - case 6: - if (boot_cpu_data.x86_model > 0xd) - break; - wrmsr(MSR_P6_EVNTSEL0, 0, 0); - break; - case 15: - if (boot_cpu_data.x86_model > 0x4) - break; + on_each_cpu(stop_apic_nmi_watchdog, NULL, 0, 1); - wrmsr(MSR_P4_IQ_CCCR0, 0, 0); - wrmsr(MSR_P4_CRU_ESCR0, 0, 0); - break; - } - break; - } - nmi_active = -1; - /* tell do_nmi() and others that we're not active any more */ - nmi_watchdog = 0; + BUG_ON(atomic_read(&nmi_active) != 0); } static void enable_lapic_nmi_watchdog(void) { - if (nmi_active < 0) { - nmi_watchdog = NMI_LOCAL_APIC; - setup_apic_nmi_watchdog(); - } -} + BUG_ON(nmi_watchdog != NMI_LOCAL_APIC); -int reserve_lapic_nmi(void) -{ - unsigned int old_owner; - - spin_lock(&lapic_nmi_owner_lock); - old_owner = lapic_nmi_owner; - lapic_nmi_owner |= LAPIC_NMI_RESERVED; - spin_unlock(&lapic_nmi_owner_lock); - if (old_owner & LAPIC_NMI_RESERVED) - return -EBUSY; - if (old_owner & LAPIC_NMI_WATCHDOG) - disable_lapic_nmi_watchdog(); - return 0; -} + /* are we already enabled */ + if (atomic_read(&nmi_active) != 0) + return; -void release_lapic_nmi(void) -{ - unsigned int new_owner; + /* are we lapic aware */ + if (nmi_known_cpu() <= 0) + return; - spin_lock(&lapic_nmi_owner_lock); - new_owner = lapic_nmi_owner & ~LAPIC_NMI_RESERVED; - lapic_nmi_owner = new_owner; - spin_unlock(&lapic_nmi_owner_lock); - if (new_owner & LAPIC_NMI_WATCHDOG) - enable_lapic_nmi_watchdog(); + on_each_cpu(setup_apic_nmi_watchdog, NULL, 0, 1); + touch_nmi_watchdog(); } void disable_timer_nmi_watchdog(void) { - if ((nmi_watchdog != NMI_IO_APIC) || (nmi_active <= 0)) + BUG_ON(nmi_watchdog != NMI_IO_APIC); + + if (atomic_read(&nmi_active) <= 0) return; - unset_nmi_callback(); - nmi_active = -1; - nmi_watchdog = NMI_NONE; + disable_irq(0); + on_each_cpu(stop_apic_nmi_watchdog, NULL, 0, 1); + + BUG_ON(atomic_read(&nmi_active) != 0); } void enable_timer_nmi_watchdog(void) { - if (nmi_active < 0) { - nmi_watchdog = NMI_IO_APIC; + BUG_ON(nmi_watchdog != NMI_IO_APIC); + + if (atomic_read(&nmi_active) == 0) { touch_nmi_watchdog(); - nmi_active = 1; + on_each_cpu(setup_apic_nmi_watchdog, NULL, 0, 1); + enable_irq(0); } } @@ -308,15 +376,20 @@ static int nmi_pm_active; /* nmi_active before suspend */ static int lapic_nmi_suspend(struct sys_device *dev, pm_message_t state) { - nmi_pm_active = nmi_active; - disable_lapic_nmi_watchdog(); + /* only CPU0 goes here, other CPUs should be offline */ + nmi_pm_active = atomic_read(&nmi_active); + stop_apic_nmi_watchdog(NULL); + BUG_ON(atomic_read(&nmi_active) != 0); return 0; } static int lapic_nmi_resume(struct sys_device *dev) { - if (nmi_pm_active > 0) - enable_lapic_nmi_watchdog(); + /* only CPU0 goes here, other CPUs should be offline */ + if (nmi_pm_active > 0) { + setup_apic_nmi_watchdog(NULL); + touch_nmi_watchdog(); + } return 0; } @@ -336,7 +409,13 @@ static int __init init_lapic_nmi_sysfs(void) { int error; - if (nmi_active == 0 || nmi_watchdog != NMI_LOCAL_APIC) + /* should really be a BUG_ON but b/c this is an + * init call, it just doesn't work. -dcz + */ + if (nmi_watchdog != NMI_LOCAL_APIC) + return 0; + + if ( atomic_read(&nmi_active) < 0 ) return 0; error = sysdev_class_register(&nmi_sysclass); @@ -354,138 +433,269 @@ late_initcall(init_lapic_nmi_sysfs); * Original code written by Keith Owens. */ -static void clear_msr_range(unsigned int base, unsigned int n) -{ - unsigned int i; - - for(i = 0; i < n; ++i) - wrmsr(base+i, 0, 0); -} - -static void write_watchdog_counter(const char *descr) +static void write_watchdog_counter(unsigned int perfctr_msr, const char *descr) { u64 count = (u64)cpu_khz * 1000; do_div(count, nmi_hz); if(descr) Dprintk("setting %s to -0x%08Lx\n", descr, count); - wrmsrl(nmi_perfctr_msr, 0 - count); + wrmsrl(perfctr_msr, 0 - count); } -static void setup_k7_watchdog(void) +/* Note that these events don't tick when the CPU idles. This means + the frequency varies with CPU load. */ + +#define K7_EVNTSEL_ENABLE (1 << 22) +#define K7_EVNTSEL_INT (1 << 20) +#define K7_EVNTSEL_OS (1 << 17) +#define K7_EVNTSEL_USR (1 << 16) +#define K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING 0x76 +#define K7_NMI_EVENT K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING + +static int setup_k7_watchdog(void) { + unsigned int perfctr_msr, evntsel_msr; unsigned int evntsel; + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); + + perfctr_msr = MSR_K7_PERFCTR0; + evntsel_msr = MSR_K7_EVNTSEL0; + if (!reserve_perfctr_nmi(perfctr_msr)) + goto fail; - nmi_perfctr_msr = MSR_K7_PERFCTR0; + if (!reserve_evntsel_nmi(evntsel_msr)) + goto fail1; - clear_msr_range(MSR_K7_EVNTSEL0, 4); - clear_msr_range(MSR_K7_PERFCTR0, 4); + wrmsrl(perfctr_msr, 0UL); evntsel = K7_EVNTSEL_INT | K7_EVNTSEL_OS | K7_EVNTSEL_USR | K7_NMI_EVENT; - wrmsr(MSR_K7_EVNTSEL0, evntsel, 0); - write_watchdog_counter("K7_PERFCTR0"); + /* setup the timer */ + wrmsr(evntsel_msr, evntsel, 0); + write_watchdog_counter(perfctr_msr, "K7_PERFCTR0"); apic_write(APIC_LVTPC, APIC_DM_NMI); evntsel |= K7_EVNTSEL_ENABLE; - wrmsr(MSR_K7_EVNTSEL0, evntsel, 0); + wrmsr(evntsel_msr, evntsel, 0); + + wd->perfctr_msr = perfctr_msr; + wd->evntsel_msr = evntsel_msr; + wd->cccr_msr = 0; //unused + wd->check_bit = 1ULL<<63; + return 1; +fail1: + release_perfctr_nmi(perfctr_msr); +fail: + return 0; +} + +static void stop_k7_watchdog(void) +{ + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); + + wrmsr(wd->evntsel_msr, 0, 0); + + release_evntsel_nmi(wd->evntsel_msr); + release_perfctr_nmi(wd->perfctr_msr); } -static void setup_p6_watchdog(void) +#define P6_EVNTSEL0_ENABLE (1 << 22) +#define P6_EVNTSEL_INT (1 << 20) +#define P6_EVNTSEL_OS (1 << 17) +#define P6_EVNTSEL_USR (1 << 16) +#define P6_EVENT_CPU_CLOCKS_NOT_HALTED 0x79 +#define P6_NMI_EVENT P6_EVENT_CPU_CLOCKS_NOT_HALTED + +static int setup_p6_watchdog(void) { + unsigned int perfctr_msr, evntsel_msr; unsigned int evntsel; + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); + + perfctr_msr = MSR_P6_PERFCTR0; + evntsel_msr = MSR_P6_EVNTSEL0; + if (!reserve_perfctr_nmi(perfctr_msr)) + goto fail; - nmi_perfctr_msr = MSR_P6_PERFCTR0; + if (!reserve_evntsel_nmi(evntsel_msr)) + goto fail1; - clear_msr_range(MSR_P6_EVNTSEL0, 2); - clear_msr_range(MSR_P6_PERFCTR0, 2); + wrmsrl(perfctr_msr, 0UL); evntsel = P6_EVNTSEL_INT | P6_EVNTSEL_OS | P6_EVNTSEL_USR | P6_NMI_EVENT; - wrmsr(MSR_P6_EVNTSEL0, evntsel, 0); - write_watchdog_counter("P6_PERFCTR0"); + /* setup the timer */ + wrmsr(evntsel_msr, evntsel, 0); + write_watchdog_counter(perfctr_msr, "P6_PERFCTR0"); apic_write(APIC_LVTPC, APIC_DM_NMI); evntsel |= P6_EVNTSEL0_ENABLE; - wrmsr(MSR_P6_EVNTSEL0, evntsel, 0); + wrmsr(evntsel_msr, evntsel, 0); + + wd->perfctr_msr = perfctr_msr; + wd->evntsel_msr = evntsel_msr; + wd->cccr_msr = 0; //unused + wd->check_bit = 1ULL<<39; + return 1; +fail1: + release_perfctr_nmi(perfctr_msr); +fail: + return 0; +} + +static void stop_p6_watchdog(void) +{ + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); + + wrmsr(wd->evntsel_msr, 0, 0); + + release_evntsel_nmi(wd->evntsel_msr); + release_perfctr_nmi(wd->perfctr_msr); } +/* Note that these events don't tick when the CPU idles. This means + the frequency varies with CPU load. */ + +#define MSR_P4_MISC_ENABLE_PERF_AVAIL (1<<7) +#define P4_ESCR_EVENT_SELECT(N) ((N)<<25) +#define P4_ESCR_OS (1<<3) +#define P4_ESCR_USR (1<<2) +#define P4_CCCR_OVF_PMI0 (1<<26) +#define P4_CCCR_OVF_PMI1 (1<<27) +#define P4_CCCR_THRESHOLD(N) ((N)<<20) +#define P4_CCCR_COMPLEMENT (1<<19) +#define P4_CCCR_COMPARE (1<<18) +#define P4_CCCR_REQUIRED (3<<16) +#define P4_CCCR_ESCR_SELECT(N) ((N)<<13) +#define P4_CCCR_ENABLE (1<<12) +#define P4_CCCR_OVF (1<<31) +/* Set up IQ_COUNTER0 to behave like a clock, by having IQ_CCCR0 filter + CRU_ESCR0 (with any non-null event selector) through a complemented + max threshold. [IA32-Vol3, Section 14.9.9] */ + static int setup_p4_watchdog(void) { + unsigned int perfctr_msr, evntsel_msr, cccr_msr; + unsigned int evntsel, cccr_val; unsigned int misc_enable, dummy; + unsigned int ht_num; + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - rdmsr(MSR_P4_MISC_ENABLE, misc_enable, dummy); + rdmsr(MSR_IA32_MISC_ENABLE, misc_enable, dummy); if (!(misc_enable & MSR_P4_MISC_ENABLE_PERF_AVAIL)) return 0; - nmi_perfctr_msr = MSR_P4_IQ_COUNTER0; - nmi_p4_cccr_val = P4_NMI_IQ_CCCR0; #ifdef CONFIG_SMP - if (smp_num_siblings == 2) - nmi_p4_cccr_val |= P4_CCCR_OVF_PMI1; + /* detect which hyperthread we are on */ + if (smp_num_siblings == 2) { + unsigned int ebx, apicid; + + ebx = cpuid_ebx(1); + apicid = (ebx >> 24) & 0xff; + ht_num = apicid & 1; + } else #endif + ht_num = 0; - if (!(misc_enable & MSR_P4_MISC_ENABLE_PEBS_UNAVAIL)) - clear_msr_range(0x3F1, 2); - /* MSR 0x3F0 seems to have a default value of 0xFC00, but current - docs doesn't fully define it, so leave it alone for now. */ - if (boot_cpu_data.x86_model >= 0x3) { - /* MSR_P4_IQ_ESCR0/1 (0x3ba/0x3bb) removed */ - clear_msr_range(0x3A0, 26); - clear_msr_range(0x3BC, 3); + /* performance counters are shared resources + * assign each hyperthread its own set + * (re-use the ESCR0 register, seems safe + * and keeps the cccr_val the same) + */ + if (!ht_num) { + /* logical cpu 0 */ + perfctr_msr = MSR_P4_IQ_PERFCTR0; + evntsel_msr = MSR_P4_CRU_ESCR0; + cccr_msr = MSR_P4_IQ_CCCR0; + cccr_val = P4_CCCR_OVF_PMI0 | P4_CCCR_ESCR_SELECT(4); } else { - clear_msr_range(0x3A0, 31); + /* logical cpu 1 */ + perfctr_msr = MSR_P4_IQ_PERFCTR1; + evntsel_msr = MSR_P4_CRU_ESCR0; + cccr_msr = MSR_P4_IQ_CCCR1; + cccr_val = P4_CCCR_OVF_PMI1 | P4_CCCR_ESCR_SELECT(4); } - clear_msr_range(0x3C0, 6); - clear_msr_range(0x3C8, 6); - clear_msr_range(0x3E0, 2); - clear_msr_range(MSR_P4_CCCR0, 18); - clear_msr_range(MSR_P4_PERFCTR0, 18); - - wrmsr(MSR_P4_CRU_ESCR0, P4_NMI_CRU_ESCR0, 0); - wrmsr(MSR_P4_IQ_CCCR0, P4_NMI_IQ_CCCR0 & ~P4_CCCR_ENABLE, 0); - write_watchdog_counter("P4_IQ_COUNTER0"); + + if (!reserve_perfctr_nmi(perfctr_msr)) + goto fail; + + if (!reserve_evntsel_nmi(evntsel_msr)) + goto fail1; + + evntsel = P4_ESCR_EVENT_SELECT(0x3F) + | P4_ESCR_OS + | P4_ESCR_USR; + + cccr_val |= P4_CCCR_THRESHOLD(15) + | P4_CCCR_COMPLEMENT + | P4_CCCR_COMPARE + | P4_CCCR_REQUIRED; + + wrmsr(evntsel_msr, evntsel, 0); + wrmsr(cccr_msr, cccr_val, 0); + write_watchdog_counter(perfctr_msr, "P4_IQ_COUNTER0"); apic_write(APIC_LVTPC, APIC_DM_NMI); - wrmsr(MSR_P4_IQ_CCCR0, nmi_p4_cccr_val, 0); + cccr_val |= P4_CCCR_ENABLE; + wrmsr(cccr_msr, cccr_val, 0); + wd->perfctr_msr = perfctr_msr; + wd->evntsel_msr = evntsel_msr; + wd->cccr_msr = cccr_msr; + wd->check_bit = 1ULL<<39; return 1; +fail1: + release_perfctr_nmi(perfctr_msr); +fail: + return 0; } -static void disable_intel_arch_watchdog(void) +static void stop_p4_watchdog(void) { - unsigned ebx; + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - /* - * Check whether the Architectural PerfMon supports - * Unhalted Core Cycles Event or not. - * NOTE: Corresponding bit = 0 in ebp indicates event present. - */ - ebx = cpuid_ebx(10); - if (!(ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT)) - wrmsr(MSR_ARCH_PERFMON_EVENTSEL0, 0, 0); + wrmsr(wd->cccr_msr, 0, 0); + wrmsr(wd->evntsel_msr, 0, 0); + + release_evntsel_nmi(wd->evntsel_msr); + release_perfctr_nmi(wd->perfctr_msr); } +#define ARCH_PERFMON_NMI_EVENT_SEL ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL +#define ARCH_PERFMON_NMI_EVENT_UMASK ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK + static int setup_intel_arch_watchdog(void) { + unsigned int ebx; + union cpuid10_eax eax; + unsigned int unused; + unsigned int perfctr_msr, evntsel_msr; unsigned int evntsel; - unsigned ebx; + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); /* * Check whether the Architectural PerfMon supports * Unhalted Core Cycles Event or not. - * NOTE: Corresponding bit = 0 in ebp indicates event present. + * NOTE: Corresponding bit = 0 in ebx indicates event present. */ - ebx = cpuid_ebx(10); - if ((ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT)) - return 0; + cpuid(10, &(eax.full), &ebx, &unused, &unused); + if ((eax.split.mask_length < (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX+1)) || + (ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT)) + goto fail; + + perfctr_msr = MSR_ARCH_PERFMON_PERFCTR0; + evntsel_msr = MSR_ARCH_PERFMON_EVENTSEL0; - nmi_perfctr_msr = MSR_ARCH_PERFMON_PERFCTR0; + if (!reserve_perfctr_nmi(perfctr_msr)) + goto fail; - clear_msr_range(MSR_ARCH_PERFMON_EVENTSEL0, 2); - clear_msr_range(MSR_ARCH_PERFMON_PERFCTR0, 2); + if (!reserve_evntsel_nmi(evntsel_msr)) + goto fail1; + + wrmsrl(perfctr_msr, 0UL); evntsel = ARCH_PERFMON_EVENTSEL_INT | ARCH_PERFMON_EVENTSEL_OS @@ -493,51 +703,145 @@ static int setup_intel_arch_watchdog(void) | ARCH_PERFMON_NMI_EVENT_SEL | ARCH_PERFMON_NMI_EVENT_UMASK; - wrmsr(MSR_ARCH_PERFMON_EVENTSEL0, evntsel, 0); - write_watchdog_counter("INTEL_ARCH_PERFCTR0"); + /* setup the timer */ + wrmsr(evntsel_msr, evntsel, 0); + write_watchdog_counter(perfctr_msr, "INTEL_ARCH_PERFCTR0"); apic_write(APIC_LVTPC, APIC_DM_NMI); evntsel |= ARCH_PERFMON_EVENTSEL0_ENABLE; - wrmsr(MSR_ARCH_PERFMON_EVENTSEL0, evntsel, 0); + wrmsr(evntsel_msr, evntsel, 0); + + wd->perfctr_msr = perfctr_msr; + wd->evntsel_msr = evntsel_msr; + wd->cccr_msr = 0; //unused + wd->check_bit = 1ULL << (eax.split.bit_width - 1); return 1; +fail1: + release_perfctr_nmi(perfctr_msr); +fail: + return 0; } -void setup_apic_nmi_watchdog (void) +static void stop_intel_arch_watchdog(void) { - switch (boot_cpu_data.x86_vendor) { - case X86_VENDOR_AMD: - if (boot_cpu_data.x86 != 6 && boot_cpu_data.x86 != 15) - return; - setup_k7_watchdog(); - break; - case X86_VENDOR_INTEL: - if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { - if (!setup_intel_arch_watchdog()) + unsigned int ebx; + union cpuid10_eax eax; + unsigned int unused; + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); + + /* + * Check whether the Architectural PerfMon supports + * Unhalted Core Cycles Event or not. + * NOTE: Corresponding bit = 0 in ebx indicates event present. + */ + cpuid(10, &(eax.full), &ebx, &unused, &unused); + if ((eax.split.mask_length < (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX+1)) || + (ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT)) + return; + + wrmsr(wd->evntsel_msr, 0, 0); + release_evntsel_nmi(wd->evntsel_msr); + release_perfctr_nmi(wd->perfctr_msr); +} + +void setup_apic_nmi_watchdog (void *unused) +{ + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); + + /* only support LOCAL and IO APICs for now */ + if ((nmi_watchdog != NMI_LOCAL_APIC) && + (nmi_watchdog != NMI_IO_APIC)) + return; + + if (wd->enabled == 1) + return; + + /* cheap hack to support suspend/resume */ + /* if cpu0 is not active neither should the other cpus */ + if ((smp_processor_id() != 0) && (atomic_read(&nmi_active) <= 0)) + return; + + if (nmi_watchdog == NMI_LOCAL_APIC) { + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_AMD: + if (boot_cpu_data.x86 != 6 && boot_cpu_data.x86 != 15) return; - break; - } - switch (boot_cpu_data.x86) { - case 6: - if (boot_cpu_data.x86_model > 0xd) + if (!setup_k7_watchdog()) return; - - setup_p6_watchdog(); break; - case 15: - if (boot_cpu_data.x86_model > 0x4) - return; + case X86_VENDOR_INTEL: + if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { + if (!setup_intel_arch_watchdog()) + return; + break; + } + switch (boot_cpu_data.x86) { + case 6: + if (boot_cpu_data.x86_model > 0xd) + return; + + if (!setup_p6_watchdog()) + return; + break; + case 15: + if (boot_cpu_data.x86_model > 0x4) + return; - if (!setup_p4_watchdog()) + if (!setup_p4_watchdog()) + return; + break; + default: return; + } break; default: return; } - break; - default: + } + wd->enabled = 1; + atomic_inc(&nmi_active); +} + +void stop_apic_nmi_watchdog(void *unused) +{ + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); + + /* only support LOCAL and IO APICs for now */ + if ((nmi_watchdog != NMI_LOCAL_APIC) && + (nmi_watchdog != NMI_IO_APIC)) + return; + + if (wd->enabled == 0) return; + + if (nmi_watchdog == NMI_LOCAL_APIC) { + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_AMD: + stop_k7_watchdog(); + break; + case X86_VENDOR_INTEL: + if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { + stop_intel_arch_watchdog(); + break; + } + switch (boot_cpu_data.x86) { + case 6: + if (boot_cpu_data.x86_model > 0xd) + break; + stop_p6_watchdog(); + break; + case 15: + if (boot_cpu_data.x86_model > 0x4) + break; + stop_p4_watchdog(); + break; + } + break; + default: + return; + } } - lapic_nmi_owner = LAPIC_NMI_WATCHDOG; - nmi_active = 1; + wd->enabled = 0; + atomic_dec(&nmi_active); } /* @@ -579,7 +883,7 @@ EXPORT_SYMBOL(touch_nmi_watchdog); extern void die_nmi(struct pt_regs *, const char *msg); -void nmi_watchdog_tick (struct pt_regs * regs) +__kprobes int nmi_watchdog_tick(struct pt_regs * regs, unsigned reason) { /* @@ -588,11 +892,23 @@ void nmi_watchdog_tick (struct pt_regs * regs) * smp_processor_id(). */ unsigned int sum; + int touched = 0; int cpu = smp_processor_id(); + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); + u64 dummy; + int rc=0; + + /* check for other users first */ + if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) + == NOTIFY_STOP) { + rc = 1; + touched = 1; + } sum = per_cpu(irq_stat, cpu).apic_timer_irqs; - if (last_irq_sums[cpu] == sum) { + /* if the apic timer isn't firing, this cpu isn't doing much */ + if (!touched && last_irq_sums[cpu] == sum) { /* * Ayiee, looks like this CPU is stuck ... * wait a few IRQs (5 seconds) before doing the oops ... @@ -607,27 +923,59 @@ void nmi_watchdog_tick (struct pt_regs * regs) last_irq_sums[cpu] = sum; alert_counter[cpu] = 0; } - if (nmi_perfctr_msr) { - if (nmi_perfctr_msr == MSR_P4_IQ_COUNTER0) { - /* - * P4 quirks: - * - An overflown perfctr will assert its interrupt - * until the OVF flag in its CCCR is cleared. - * - LVTPC is masked on interrupt and must be - * unmasked by the LVTPC handler. + /* see if the nmi watchdog went off */ + if (wd->enabled) { + if (nmi_watchdog == NMI_LOCAL_APIC) { + rdmsrl(wd->perfctr_msr, dummy); + if (dummy & wd->check_bit){ + /* this wasn't a watchdog timer interrupt */ + goto done; + } + + /* only Intel P4 uses the cccr msr */ + if (wd->cccr_msr != 0) { + /* + * P4 quirks: + * - An overflown perfctr will assert its interrupt + * until the OVF flag in its CCCR is cleared. + * - LVTPC is masked on interrupt and must be + * unmasked by the LVTPC handler. + */ + rdmsrl(wd->cccr_msr, dummy); + dummy &= ~P4_CCCR_OVF; + wrmsrl(wd->cccr_msr, dummy); + apic_write(APIC_LVTPC, APIC_DM_NMI); + } + else if (wd->perfctr_msr == MSR_P6_PERFCTR0 || + wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0) { + /* P6 based Pentium M need to re-unmask + * the apic vector but it doesn't hurt + * other P6 variant. + * ArchPerfom/Core Duo also needs this */ + apic_write(APIC_LVTPC, APIC_DM_NMI); + } + /* start the cycle over again */ + write_watchdog_counter(wd->perfctr_msr, NULL); + rc = 1; + } else if (nmi_watchdog == NMI_IO_APIC) { + /* don't know how to accurately check for this. + * just assume it was a watchdog timer interrupt + * This matches the old behaviour. */ - wrmsr(MSR_P4_IQ_CCCR0, nmi_p4_cccr_val, 0); - apic_write(APIC_LVTPC, APIC_DM_NMI); + rc = 1; } - else if (nmi_perfctr_msr == MSR_P6_PERFCTR0 || - nmi_perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0) { - /* Only P6 based Pentium M need to re-unmask - * the apic vector but it doesn't hurt - * other P6 variant */ - apic_write(APIC_LVTPC, APIC_DM_NMI); - } - write_watchdog_counter(NULL); } +done: + return rc; +} + +int do_nmi_callback(struct pt_regs * regs, int cpu) +{ +#ifdef CONFIG_SYSCTL + if (unknown_nmi_panic) + return unknown_nmi_panic_callback(regs, cpu); +#endif + return 0; } #ifdef CONFIG_SYSCTL @@ -637,36 +985,46 @@ static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu) unsigned char reason = get_nmi_reason(); char buf[64]; - if (!(reason & 0xc0)) { - sprintf(buf, "NMI received for unknown reason %02x\n", reason); - die_nmi(regs, buf); - } + sprintf(buf, "NMI received for unknown reason %02x\n", reason); + die_nmi(regs, buf); return 0; } /* - * proc handler for /proc/sys/kernel/unknown_nmi_panic + * proc handler for /proc/sys/kernel/nmi */ -int proc_unknown_nmi_panic(ctl_table *table, int write, struct file *file, +int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file, void __user *buffer, size_t *length, loff_t *ppos) { int old_state; - old_state = unknown_nmi_panic; + nmi_watchdog_enabled = (atomic_read(&nmi_active) > 0) ? 1 : 0; + old_state = nmi_watchdog_enabled; proc_dointvec(table, write, file, buffer, length, ppos); - if (!!old_state == !!unknown_nmi_panic) + if (!!old_state == !!nmi_watchdog_enabled) return 0; - if (unknown_nmi_panic) { - if (reserve_lapic_nmi() < 0) { - unknown_nmi_panic = 0; - return -EBUSY; - } else { - set_nmi_callback(unknown_nmi_panic_callback); - } + if (atomic_read(&nmi_active) < 0) { + printk( KERN_WARNING "NMI watchdog is permanently disabled\n"); + return -EIO; + } + + if (nmi_watchdog == NMI_DEFAULT) { + if (nmi_known_cpu() > 0) + nmi_watchdog = NMI_LOCAL_APIC; + else + nmi_watchdog = NMI_IO_APIC; + } + + if (nmi_watchdog == NMI_LOCAL_APIC) { + if (nmi_watchdog_enabled) + enable_lapic_nmi_watchdog(); + else + disable_lapic_nmi_watchdog(); } else { - release_lapic_nmi(); - unset_nmi_callback(); + printk( KERN_WARNING + "NMI watchdog doesn't know what hardware to touch\n"); + return -EIO; } return 0; } @@ -675,7 +1033,11 @@ int proc_unknown_nmi_panic(ctl_table *table, int write, struct file *file, EXPORT_SYMBOL(nmi_active); EXPORT_SYMBOL(nmi_watchdog); -EXPORT_SYMBOL(reserve_lapic_nmi); -EXPORT_SYMBOL(release_lapic_nmi); +EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi); +EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi_bit); +EXPORT_SYMBOL(reserve_perfctr_nmi); +EXPORT_SYMBOL(release_perfctr_nmi); +EXPORT_SYMBOL(reserve_evntsel_nmi); +EXPORT_SYMBOL(release_evntsel_nmi); EXPORT_SYMBOL(disable_timer_nmi_watchdog); EXPORT_SYMBOL(enable_timer_nmi_watchdog); diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c index 8657c73..8c190ca 100644 --- a/arch/i386/kernel/process.c +++ b/arch/i386/kernel/process.c @@ -37,6 +37,7 @@ #include <linux/kallsyms.h> #include <linux/ptrace.h> #include <linux/random.h> +#include <linux/personality.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -320,15 +321,6 @@ void show_regs(struct pt_regs * regs) * the "args". */ extern void kernel_thread_helper(void); -__asm__(".section .text\n" - ".align 4\n" - "kernel_thread_helper:\n\t" - "movl %edx,%eax\n\t" - "pushl %edx\n\t" - "call *%ebx\n\t" - "pushl %eax\n\t" - "call do_exit\n" - ".previous"); /* * Create a kernel thread @@ -346,7 +338,7 @@ int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) regs.xes = __USER_DS; regs.orig_eax = -1; regs.eip = (unsigned long) kernel_thread_helper; - regs.xcs = __KERNEL_CS; + regs.xcs = __KERNEL_CS | get_kernel_rpl(); regs.eflags = X86_EFLAGS_IF | X86_EFLAGS_SF | X86_EFLAGS_PF | 0x2; /* Ok, create the new process.. */ @@ -905,7 +897,7 @@ asmlinkage int sys_get_thread_area(struct user_desc __user *u_info) unsigned long arch_align_stack(unsigned long sp) { - if (randomize_va_space) + if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space) sp -= get_random_int() % 8192; return sp & ~0xf; } diff --git a/arch/i386/kernel/ptrace.c b/arch/i386/kernel/ptrace.c index d3db03f..775f50e 100644 --- a/arch/i386/kernel/ptrace.c +++ b/arch/i386/kernel/ptrace.c @@ -185,17 +185,17 @@ static unsigned long convert_eip_to_linear(struct task_struct *child, struct pt_ return addr; } -static inline int is_at_popf(struct task_struct *child, struct pt_regs *regs) +static inline int is_setting_trap_flag(struct task_struct *child, struct pt_regs *regs) { int i, copied; - unsigned char opcode[16]; + unsigned char opcode[15]; unsigned long addr = convert_eip_to_linear(child, regs); copied = access_process_vm(child, addr, opcode, sizeof(opcode), 0); for (i = 0; i < copied; i++) { switch (opcode[i]) { - /* popf */ - case 0x9d: + /* popf and iret */ + case 0x9d: case 0xcf: return 1; /* opcode and address size prefixes */ case 0x66: case 0x67: @@ -247,7 +247,7 @@ static void set_singlestep(struct task_struct *child) * don't mark it as being "us" that set it, so that we * won't clear it by hand later. */ - if (is_at_popf(child, regs)) + if (is_setting_trap_flag(child, regs)) return; child->ptrace |= PT_DTRACE; diff --git a/arch/i386/kernel/relocate_kernel.S b/arch/i386/kernel/relocate_kernel.S index d312616..f151d6f 100644 --- a/arch/i386/kernel/relocate_kernel.S +++ b/arch/i386/kernel/relocate_kernel.S @@ -7,16 +7,138 @@ */ #include <linux/linkage.h> +#include <asm/page.h> +#include <asm/kexec.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 */ + + .text + .align PAGE_ALIGNED + .globl relocate_kernel +relocate_kernel: + movl 8(%esp), %ebp /* list of pages */ + +#ifdef CONFIG_X86_PAE + /* map the control page at its virtual address */ + + movl PTR(VA_PGD)(%ebp), %edi + movl PTR(VA_CONTROL_PAGE)(%ebp), %eax + andl $0xc0000000, %eax + shrl $27, %eax + addl %edi, %eax + + movl PTR(PA_PMD_0)(%ebp), %edx + orl $PAE_PGD_ATTR, %edx + movl %edx, (%eax) + + movl PTR(VA_PMD_0)(%ebp), %edi + movl PTR(VA_CONTROL_PAGE)(%ebp), %eax + andl $0x3fe00000, %eax + shrl $18, %eax + addl %edi, %eax + + movl PTR(PA_PTE_0)(%ebp), %edx + orl $PAGE_ATTR, %edx + movl %edx, (%eax) + + movl PTR(VA_PTE_0)(%ebp), %edi + movl PTR(VA_CONTROL_PAGE)(%ebp), %eax + andl $0x001ff000, %eax + shrl $9, %eax + addl %edi, %eax + + movl PTR(PA_CONTROL_PAGE)(%ebp), %edx + orl $PAGE_ATTR, %edx + movl %edx, (%eax) + + /* identity map the control page at its physical address */ + + movl PTR(VA_PGD)(%ebp), %edi + movl PTR(PA_CONTROL_PAGE)(%ebp), %eax + andl $0xc0000000, %eax + shrl $27, %eax + addl %edi, %eax + + movl PTR(PA_PMD_1)(%ebp), %edx + orl $PAE_PGD_ATTR, %edx + movl %edx, (%eax) + + movl PTR(VA_PMD_1)(%ebp), %edi + movl PTR(PA_CONTROL_PAGE)(%ebp), %eax + andl $0x3fe00000, %eax + shrl $18, %eax + addl %edi, %eax + + movl PTR(PA_PTE_1)(%ebp), %edx + orl $PAGE_ATTR, %edx + movl %edx, (%eax) + + movl PTR(VA_PTE_1)(%ebp), %edi + movl PTR(PA_CONTROL_PAGE)(%ebp), %eax + andl $0x001ff000, %eax + shrl $9, %eax + addl %edi, %eax + + movl PTR(PA_CONTROL_PAGE)(%ebp), %edx + orl $PAGE_ATTR, %edx + movl %edx, (%eax) +#else + /* map the control page at its virtual address */ + + movl PTR(VA_PGD)(%ebp), %edi + movl PTR(VA_CONTROL_PAGE)(%ebp), %eax + andl $0xffc00000, %eax + shrl $20, %eax + addl %edi, %eax + + movl PTR(PA_PTE_0)(%ebp), %edx + orl $PAGE_ATTR, %edx + movl %edx, (%eax) + + movl PTR(VA_PTE_0)(%ebp), %edi + movl PTR(VA_CONTROL_PAGE)(%ebp), %eax + andl $0x003ff000, %eax + shrl $10, %eax + addl %edi, %eax + + movl PTR(PA_CONTROL_PAGE)(%ebp), %edx + orl $PAGE_ATTR, %edx + movl %edx, (%eax) + + /* identity map the control page at its physical address */ + + movl PTR(VA_PGD)(%ebp), %edi + movl PTR(PA_CONTROL_PAGE)(%ebp), %eax + andl $0xffc00000, %eax + shrl $20, %eax + addl %edi, %eax + + movl PTR(PA_PTE_1)(%ebp), %edx + orl $PAGE_ATTR, %edx + movl %edx, (%eax) + + movl PTR(VA_PTE_1)(%ebp), %edi + movl PTR(PA_CONTROL_PAGE)(%ebp), %eax + andl $0x003ff000, %eax + shrl $10, %eax + addl %edi, %eax + + movl PTR(PA_CONTROL_PAGE)(%ebp), %edx + orl $PAGE_ATTR, %edx + movl %edx, (%eax) +#endif - /* - * Must be relocatable PIC code callable as a C function, that once - * it starts can not use the previous processes stack. - */ - .globl relocate_new_kernel relocate_new_kernel: /* read the arguments and say goodbye to the stack */ movl 4(%esp), %ebx /* page_list */ - movl 8(%esp), %ebp /* reboot_code_buffer */ + movl 8(%esp), %ebp /* list of pages */ movl 12(%esp), %edx /* start address */ movl 16(%esp), %ecx /* cpu_has_pae */ @@ -24,11 +146,26 @@ relocate_new_kernel: pushl $0 popfl - /* set a new stack at the bottom of our page... */ - lea 4096(%ebp), %esp + /* get physical address of control page now */ + /* this is impossible after page table switch */ + movl PTR(PA_CONTROL_PAGE)(%ebp), %edi - /* store the parameters back on the stack */ - pushl %edx /* store the start address */ + /* switch to new set of page tables */ + movl PTR(PA_PGD)(%ebp), %eax + movl %eax, %cr3 + + /* setup a new stack at the end of the physical control page */ + lea 4096(%edi), %esp + + /* jump to identity mapped page */ + movl %edi, %eax + addl $(identity_mapped - relocate_kernel), %eax + pushl %eax + ret + +identity_mapped: + /* store the start address on the stack */ + pushl %edx /* Set cr0 to a known state: * 31 0 == Paging disabled @@ -113,8 +250,3 @@ relocate_new_kernel: xorl %edi, %edi xorl %ebp, %ebp ret -relocate_new_kernel_end: - - .globl relocate_new_kernel_size -relocate_new_kernel_size: - .long relocate_new_kernel_end - relocate_new_kernel diff --git a/arch/i386/kernel/semaphore.c b/arch/i386/kernel/semaphore.c deleted file mode 100644 index 98352c3..0000000 --- a/arch/i386/kernel/semaphore.c +++ /dev/null @@ -1,134 +0,0 @@ -/* - * i386 semaphore implementation. - * - * (C) Copyright 1999 Linus Torvalds - * - * Portions Copyright 1999 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. - * - * rw semaphores implemented November 1999 by Benjamin LaHaise <bcrl@kvack.org> - */ -#include <asm/semaphore.h> - -/* - * The semaphore operations have a special calling sequence that - * allow us to do a simpler in-line version of them. These routines - * need to convert that sequence back into the C sequence when - * there is contention on the semaphore. - * - * %eax contains the semaphore pointer on entry. Save the C-clobbered - * registers (%eax, %edx and %ecx) except %eax whish is either a return - * value or just clobbered.. - */ -asm( -".section .sched.text\n" -".align 4\n" -".globl __down_failed\n" -"__down_failed:\n\t" -#if defined(CONFIG_FRAME_POINTER) - "pushl %ebp\n\t" - "movl %esp,%ebp\n\t" -#endif - "pushl %edx\n\t" - "pushl %ecx\n\t" - "call __down\n\t" - "popl %ecx\n\t" - "popl %edx\n\t" -#if defined(CONFIG_FRAME_POINTER) - "movl %ebp,%esp\n\t" - "popl %ebp\n\t" -#endif - "ret" -); - -asm( -".section .sched.text\n" -".align 4\n" -".globl __down_failed_interruptible\n" -"__down_failed_interruptible:\n\t" -#if defined(CONFIG_FRAME_POINTER) - "pushl %ebp\n\t" - "movl %esp,%ebp\n\t" -#endif - "pushl %edx\n\t" - "pushl %ecx\n\t" - "call __down_interruptible\n\t" - "popl %ecx\n\t" - "popl %edx\n\t" -#if defined(CONFIG_FRAME_POINTER) - "movl %ebp,%esp\n\t" - "popl %ebp\n\t" -#endif - "ret" -); - -asm( -".section .sched.text\n" -".align 4\n" -".globl __down_failed_trylock\n" -"__down_failed_trylock:\n\t" -#if defined(CONFIG_FRAME_POINTER) - "pushl %ebp\n\t" - "movl %esp,%ebp\n\t" -#endif - "pushl %edx\n\t" - "pushl %ecx\n\t" - "call __down_trylock\n\t" - "popl %ecx\n\t" - "popl %edx\n\t" -#if defined(CONFIG_FRAME_POINTER) - "movl %ebp,%esp\n\t" - "popl %ebp\n\t" -#endif - "ret" -); - -asm( -".section .sched.text\n" -".align 4\n" -".globl __up_wakeup\n" -"__up_wakeup:\n\t" - "pushl %edx\n\t" - "pushl %ecx\n\t" - "call __up\n\t" - "popl %ecx\n\t" - "popl %edx\n\t" - "ret" -); - -/* - * rw spinlock fallbacks - */ -#if defined(CONFIG_SMP) -asm( -".section .sched.text\n" -".align 4\n" -".globl __write_lock_failed\n" -"__write_lock_failed:\n\t" - LOCK_PREFIX "addl $" RW_LOCK_BIAS_STR ",(%eax)\n" -"1: rep; nop\n\t" - "cmpl $" RW_LOCK_BIAS_STR ",(%eax)\n\t" - "jne 1b\n\t" - LOCK_PREFIX "subl $" RW_LOCK_BIAS_STR ",(%eax)\n\t" - "jnz __write_lock_failed\n\t" - "ret" -); - -asm( -".section .sched.text\n" -".align 4\n" -".globl __read_lock_failed\n" -"__read_lock_failed:\n\t" - LOCK_PREFIX "incl (%eax)\n" -"1: rep; nop\n\t" - "cmpl $1,(%eax)\n\t" - "js 1b\n\t" - LOCK_PREFIX "decl (%eax)\n\t" - "js __read_lock_failed\n\t" - "ret" -); -#endif diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c index 16d9944..76a524b 100644 --- a/arch/i386/kernel/setup.c +++ b/arch/i386/kernel/setup.c @@ -90,18 +90,6 @@ EXPORT_SYMBOL(boot_cpu_data); unsigned long mmu_cr4_features; -#ifdef CONFIG_ACPI - int acpi_disabled = 0; -#else - int acpi_disabled = 1; -#endif -EXPORT_SYMBOL(acpi_disabled); - -#ifdef CONFIG_ACPI -int __initdata acpi_force = 0; -extern acpi_interrupt_flags acpi_sci_flags; -#endif - /* for MCA, but anyone else can use it if they want */ unsigned int machine_id; #ifdef CONFIG_MCA @@ -149,7 +137,6 @@ EXPORT_SYMBOL(ist_info); struct e820map e820; extern void early_cpu_init(void); -extern void generic_apic_probe(char *); extern int root_mountflags; unsigned long saved_videomode; @@ -701,238 +688,132 @@ static inline void copy_edd(void) } #endif -static void __init parse_cmdline_early (char ** cmdline_p) -{ - char c = ' ', *to = command_line, *from = saved_command_line; - int len = 0; - int userdef = 0; +static int __initdata user_defined_memmap = 0; - /* Save unparsed command line copy for /proc/cmdline */ - saved_command_line[COMMAND_LINE_SIZE-1] = '\0'; +/* + * "mem=nopentium" disables the 4MB page tables. + * "mem=XXX[kKmM]" defines a memory region from HIGH_MEM + * to <mem>, overriding the bios size. + * "memmap=XXX[KkmM]@XXX[KkmM]" defines a memory region from + * <start> to <start>+<mem>, overriding the bios size. + * + * HPA tells me bootloaders need to parse mem=, so no new + * option should be mem= [also see Documentation/i386/boot.txt] + */ +static int __init parse_mem(char *arg) +{ + if (!arg) + return -EINVAL; - for (;;) { - if (c != ' ') - goto next_char; - /* - * "mem=nopentium" disables the 4MB page tables. - * "mem=XXX[kKmM]" defines a memory region from HIGH_MEM - * to <mem>, overriding the bios size. - * "memmap=XXX[KkmM]@XXX[KkmM]" defines a memory region from - * <start> to <start>+<mem>, overriding the bios size. - * - * HPA tells me bootloaders need to parse mem=, so no new - * option should be mem= [also see Documentation/i386/boot.txt] + if (strcmp(arg, "nopentium") == 0) { + clear_bit(X86_FEATURE_PSE, boot_cpu_data.x86_capability); + disable_pse = 1; + } else { + /* If the user specifies memory size, we + * limit the BIOS-provided memory map to + * that size. exactmap can be used to specify + * the exact map. mem=number can be used to + * trim the existing memory map. */ - if (!memcmp(from, "mem=", 4)) { - if (to != command_line) - to--; - if (!memcmp(from+4, "nopentium", 9)) { - from += 9+4; - clear_bit(X86_FEATURE_PSE, boot_cpu_data.x86_capability); - disable_pse = 1; - } else { - /* If the user specifies memory size, we - * limit the BIOS-provided memory map to - * that size. exactmap can be used to specify - * the exact map. mem=number can be used to - * trim the existing memory map. - */ - unsigned long long mem_size; + unsigned long long mem_size; - mem_size = memparse(from+4, &from); - limit_regions(mem_size); - userdef=1; - } - } - - else if (!memcmp(from, "memmap=", 7)) { - if (to != command_line) - to--; - if (!memcmp(from+7, "exactmap", 8)) { -#ifdef CONFIG_CRASH_DUMP - /* If we are doing a crash dump, we - * still need to know the real mem - * size before original memory map is - * reset. - */ - find_max_pfn(); - saved_max_pfn = max_pfn; -#endif - from += 8+7; - e820.nr_map = 0; - userdef = 1; - } else { - /* If the user specifies memory size, we - * limit the BIOS-provided memory map to - * that size. exactmap can be used to specify - * the exact map. mem=number can be used to - * trim the existing memory map. - */ - unsigned long long start_at, mem_size; - - mem_size = memparse(from+7, &from); - if (*from == '@') { - start_at = memparse(from+1, &from); - add_memory_region(start_at, mem_size, E820_RAM); - } else if (*from == '#') { - start_at = memparse(from+1, &from); - add_memory_region(start_at, mem_size, E820_ACPI); - } else if (*from == '$') { - start_at = memparse(from+1, &from); - add_memory_region(start_at, mem_size, E820_RESERVED); - } else { - limit_regions(mem_size); - userdef=1; - } - } - } - - else if (!memcmp(from, "noexec=", 7)) - noexec_setup(from + 7); + mem_size = memparse(arg, &arg); + limit_regions(mem_size); + user_defined_memmap = 1; + } + return 0; +} +early_param("mem", parse_mem); +static int __init parse_memmap(char *arg) +{ + if (!arg) + return -EINVAL; -#ifdef CONFIG_X86_SMP - /* - * If the BIOS enumerates physical processors before logical, - * maxcpus=N at enumeration-time can be used to disable HT. + if (strcmp(arg, "exactmap") == 0) { +#ifdef CONFIG_CRASH_DUMP + /* If we are doing a crash dump, we + * still need to know the real mem + * size before original memory map is + * reset. */ - else if (!memcmp(from, "maxcpus=", 8)) { - extern unsigned int maxcpus; - - maxcpus = simple_strtoul(from + 8, NULL, 0); - } + find_max_pfn(); + saved_max_pfn = max_pfn; #endif - -#ifdef CONFIG_ACPI - /* "acpi=off" disables both ACPI table parsing and interpreter */ - else if (!memcmp(from, "acpi=off", 8)) { - disable_acpi(); - } - - /* acpi=force to over-ride black-list */ - else if (!memcmp(from, "acpi=force", 10)) { - acpi_force = 1; - acpi_ht = 1; - acpi_disabled = 0; - } - - /* acpi=strict disables out-of-spec workarounds */ - else if (!memcmp(from, "acpi=strict", 11)) { - acpi_strict = 1; - } - - /* Limit ACPI just to boot-time to enable HT */ - else if (!memcmp(from, "acpi=ht", 7)) { - if (!acpi_force) - disable_acpi(); - acpi_ht = 1; - } - - /* "pci=noacpi" disable ACPI IRQ routing and PCI scan */ - else if (!memcmp(from, "pci=noacpi", 10)) { - acpi_disable_pci(); - } - /* "acpi=noirq" disables ACPI interrupt routing */ - else if (!memcmp(from, "acpi=noirq", 10)) { - acpi_noirq_set(); + e820.nr_map = 0; + user_defined_memmap = 1; + } else { + /* If the user specifies memory size, we + * limit the BIOS-provided memory map to + * that size. exactmap can be used to specify + * the exact map. mem=number can be used to + * trim the existing memory map. + */ + unsigned long long start_at, mem_size; + + mem_size = memparse(arg, &arg); + if (*arg == '@') { + start_at = memparse(arg+1, &arg); + add_memory_region(start_at, mem_size, E820_RAM); + } else if (*arg == '#') { + start_at = memparse(arg+1, &arg); + add_memory_region(start_at, mem_size, E820_ACPI); + } else if (*arg == '$') { + start_at = memparse(arg+1, &arg); + add_memory_region(start_at, mem_size, E820_RESERVED); + } else { + limit_regions(mem_size); + user_defined_memmap = 1; } + } + return 0; +} +early_param("memmap", parse_memmap); - else if (!memcmp(from, "acpi_sci=edge", 13)) - acpi_sci_flags.trigger = 1; - - else if (!memcmp(from, "acpi_sci=level", 14)) - acpi_sci_flags.trigger = 3; - - else if (!memcmp(from, "acpi_sci=high", 13)) - acpi_sci_flags.polarity = 1; - - else if (!memcmp(from, "acpi_sci=low", 12)) - acpi_sci_flags.polarity = 3; - -#ifdef CONFIG_X86_IO_APIC - else if (!memcmp(from, "acpi_skip_timer_override", 24)) - acpi_skip_timer_override = 1; - - if (!memcmp(from, "disable_timer_pin_1", 19)) - disable_timer_pin_1 = 1; - if (!memcmp(from, "enable_timer_pin_1", 18)) - disable_timer_pin_1 = -1; +#ifdef CONFIG_PROC_VMCORE +/* elfcorehdr= specifies the location of elf core header + * stored by the crashed kernel. + */ +static int __init parse_elfcorehdr(char *arg) +{ + if (!arg) + return -EINVAL; - /* disable IO-APIC */ - else if (!memcmp(from, "noapic", 6)) - disable_ioapic_setup(); -#endif /* CONFIG_X86_IO_APIC */ -#endif /* CONFIG_ACPI */ + elfcorehdr_addr = memparse(arg, &arg); + return 0; +} +early_param("elfcorehdr", parse_elfcorehdr); +#endif /* CONFIG_PROC_VMCORE */ -#ifdef CONFIG_X86_LOCAL_APIC - /* enable local APIC */ - else if (!memcmp(from, "lapic", 5)) - lapic_enable(); +/* + * highmem=size forces highmem to be exactly 'size' bytes. + * This works even on boxes that have no highmem otherwise. + * This also works to reduce highmem size on bigger boxes. + */ +static int __init parse_highmem(char *arg) +{ + if (!arg) + return -EINVAL; - /* disable local APIC */ - else if (!memcmp(from, "nolapic", 6)) - lapic_disable(); -#endif /* CONFIG_X86_LOCAL_APIC */ + highmem_pages = memparse(arg, &arg) >> PAGE_SHIFT; + return 0; +} +early_param("highmem", parse_highmem); -#ifdef CONFIG_KEXEC - /* crashkernel=size@addr specifies the location to reserve for - * a crash kernel. By reserving this memory we guarantee - * that linux never set's it up as a DMA target. - * Useful for holding code to do something appropriate - * after a kernel panic. - */ - else if (!memcmp(from, "crashkernel=", 12)) { - unsigned long size, base; - size = memparse(from+12, &from); - if (*from == '@') { - base = memparse(from+1, &from); - /* FIXME: Do I want a sanity check - * to validate the memory range? - */ - crashk_res.start = base; - crashk_res.end = base + size - 1; - } - } -#endif -#ifdef CONFIG_PROC_VMCORE - /* elfcorehdr= specifies the location of elf core header - * stored by the crashed kernel. - */ - else if (!memcmp(from, "elfcorehdr=", 11)) - elfcorehdr_addr = memparse(from+11, &from); -#endif +/* + * vmalloc=size forces the vmalloc area to be exactly 'size' + * bytes. This can be used to increase (or decrease) the + * vmalloc area - the default is 128m. + */ +static int __init parse_vmalloc(char *arg) +{ + if (!arg) + return -EINVAL; - /* - * highmem=size forces highmem to be exactly 'size' bytes. - * This works even on boxes that have no highmem otherwise. - * This also works to reduce highmem size on bigger boxes. - */ - else if (!memcmp(from, "highmem=", 8)) - highmem_pages = memparse(from+8, &from) >> PAGE_SHIFT; - - /* - * vmalloc=size forces the vmalloc area to be exactly 'size' - * bytes. This can be used to increase (or decrease) the - * vmalloc area - the default is 128m. - */ - else if (!memcmp(from, "vmalloc=", 8)) - __VMALLOC_RESERVE = memparse(from+8, &from); - - next_char: - c = *(from++); - if (!c) - break; - if (COMMAND_LINE_SIZE <= ++len) - break; - *(to++) = c; - } - *to = '\0'; - *cmdline_p = command_line; - if (userdef) { - printk(KERN_INFO "user-defined physical RAM map:\n"); - print_memory_map("user"); - } + __VMALLOC_RESERVE = memparse(arg, &arg); + return 0; } +early_param("vmalloc", parse_vmalloc); /* * reservetop=size reserves a hole at the top of the kernel address space which @@ -1189,6 +1070,14 @@ static unsigned long __init setup_memory(void) } printk(KERN_NOTICE "%ldMB HIGHMEM available.\n", pages_to_mb(highend_pfn - highstart_pfn)); + num_physpages = highend_pfn; + high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1; +#else + num_physpages = max_low_pfn; + high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1; +#endif +#ifdef CONFIG_FLATMEM + max_mapnr = num_physpages; #endif printk(KERN_NOTICE "%ldMB LOWMEM available.\n", pages_to_mb(max_low_pfn)); @@ -1518,17 +1407,15 @@ void __init setup_arch(char **cmdline_p) data_resource.start = virt_to_phys(_etext); data_resource.end = virt_to_phys(_edata)-1; - parse_cmdline_early(cmdline_p); + parse_early_param(); -#ifdef CONFIG_EARLY_PRINTK - { - char *s = strstr(*cmdline_p, "earlyprintk="); - if (s) { - setup_early_printk(strchr(s, '=') + 1); - printk("early console enabled\n"); - } + if (user_defined_memmap) { + printk(KERN_INFO "user-defined physical RAM map:\n"); + print_memory_map("user"); } -#endif + + strlcpy(command_line, saved_command_line, COMMAND_LINE_SIZE); + *cmdline_p = command_line; max_low_pfn = setup_memory(); @@ -1557,7 +1444,7 @@ void __init setup_arch(char **cmdline_p) dmi_scan_machine(); #ifdef CONFIG_X86_GENERICARCH - generic_apic_probe(*cmdline_p); + generic_apic_probe(); #endif if (efi_enabled) efi_map_memmap(); @@ -1569,9 +1456,11 @@ void __init setup_arch(char **cmdline_p) acpi_boot_table_init(); #endif +#ifdef CONFIG_PCI #ifdef CONFIG_X86_IO_APIC check_acpi_pci(); /* Checks more than just ACPI actually */ #endif +#endif #ifdef CONFIG_ACPI acpi_boot_init(); diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c index efe0799..020d873 100644 --- a/arch/i386/kernel/smpboot.c +++ b/arch/i386/kernel/smpboot.c @@ -177,6 +177,9 @@ static void __devinit smp_store_cpu_info(int id) */ 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; @@ -1376,7 +1379,8 @@ int __cpu_disable(void) */ 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 */ local_irq_enable(); @@ -1490,3 +1494,16 @@ void __init smp_intr_init(void) /* 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. + */ +static int __init parse_maxcpus(char *arg) +{ + extern unsigned int maxcpus; + + maxcpus = simple_strtoul(arg, NULL, 0); + return 0; +} +early_param("maxcpus", parse_maxcpus); diff --git a/arch/i386/kernel/stacktrace.c b/arch/i386/kernel/stacktrace.c deleted file mode 100644 index e62a037..0000000 --- a/arch/i386/kernel/stacktrace.c +++ /dev/null @@ -1,98 +0,0 @@ -/* - * arch/i386/kernel/stacktrace.c - * - * Stack trace management functions - * - * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> - */ -#include <linux/sched.h> -#include <linux/stacktrace.h> - -static inline int valid_stack_ptr(struct thread_info *tinfo, void *p) -{ - return p > (void *)tinfo && - p < (void *)tinfo + THREAD_SIZE - 3; -} - -/* - * Save stack-backtrace addresses into a stack_trace buffer: - */ -static inline unsigned long -save_context_stack(struct stack_trace *trace, unsigned int skip, - struct thread_info *tinfo, unsigned long *stack, - unsigned long ebp) -{ - unsigned long addr; - -#ifdef CONFIG_FRAME_POINTER - while (valid_stack_ptr(tinfo, (void *)ebp)) { - addr = *(unsigned long *)(ebp + 4); - if (!skip) - trace->entries[trace->nr_entries++] = addr; - else - skip--; - if (trace->nr_entries >= trace->max_entries) - break; - /* - * break out of recursive entries (such as - * end_of_stack_stop_unwind_function): - */ - if (ebp == *(unsigned long *)ebp) - break; - - ebp = *(unsigned long *)ebp; - } -#else - while (valid_stack_ptr(tinfo, stack)) { - addr = *stack++; - if (__kernel_text_address(addr)) { - if (!skip) - trace->entries[trace->nr_entries++] = addr; - else - skip--; - if (trace->nr_entries >= trace->max_entries) - break; - } - } -#endif - - return ebp; -} - -/* - * Save stack-backtrace addresses into a stack_trace buffer. - * If all_contexts is set, all contexts (hardirq, softirq and process) - * are saved. If not set then only the current context is saved. - */ -void save_stack_trace(struct stack_trace *trace, - struct task_struct *task, int all_contexts, - unsigned int skip) -{ - unsigned long ebp; - unsigned long *stack = &ebp; - - WARN_ON(trace->nr_entries || !trace->max_entries); - - if (!task || task == current) { - /* Grab ebp right from our regs: */ - asm ("movl %%ebp, %0" : "=r" (ebp)); - } else { - /* ebp is the last reg pushed by switch_to(): */ - ebp = *(unsigned long *) task->thread.esp; - } - - while (1) { - struct thread_info *context = (struct thread_info *) - ((unsigned long)stack & (~(THREAD_SIZE - 1))); - - ebp = save_context_stack(trace, skip, context, stack, ebp); - stack = (unsigned long *)context->previous_esp; - if (!all_contexts || !stack || - trace->nr_entries >= trace->max_entries) - break; - trace->entries[trace->nr_entries++] = ULONG_MAX; - if (trace->nr_entries >= trace->max_entries) - break; - } -} - diff --git a/arch/i386/kernel/syscall_table.S b/arch/i386/kernel/syscall_table.S index dd63d47..7e639f7 100644 --- a/arch/i386/kernel/syscall_table.S +++ b/arch/i386/kernel/syscall_table.S @@ -317,3 +317,4 @@ ENTRY(sys_call_table) .long sys_tee /* 315 */ .long sys_vmsplice .long sys_move_pages + .long sys_getcpu diff --git a/arch/i386/kernel/time.c b/arch/i386/kernel/time.c index 1302e4a..86944ac 100644 --- a/arch/i386/kernel/time.c +++ b/arch/i386/kernel/time.c @@ -130,18 +130,33 @@ static int set_rtc_mmss(unsigned long nowtime) int timer_ack; -#if defined(CONFIG_SMP) && defined(CONFIG_FRAME_POINTER) unsigned long profile_pc(struct pt_regs *regs) { unsigned long pc = instruction_pointer(regs); - if (!user_mode_vm(regs) && in_lock_functions(pc)) +#ifdef CONFIG_SMP + if (!user_mode_vm(regs) && in_lock_functions(pc)) { +#ifdef CONFIG_FRAME_POINTER return *(unsigned long *)(regs->ebp + 4); - +#else + unsigned long *sp; + if ((regs->xcs & 3) == 0) + sp = (unsigned long *)®s->esp; + else + sp = (unsigned long *)regs->esp; + /* Return address is either directly at stack pointer + or above a saved eflags. Eflags has bits 22-31 zero, + kernel addresses don't. */ + if (sp[0] >> 22) + return sp[0]; + if (sp[1] >> 22) + return sp[1]; +#endif + } +#endif return pc; } EXPORT_SYMBOL(profile_pc); -#endif /* * This is the same as the above, except we _also_ save the current diff --git a/arch/i386/kernel/topology.c b/arch/i386/kernel/topology.c index e2e281d..07d6da3 100644 --- a/arch/i386/kernel/topology.c +++ b/arch/i386/kernel/topology.c @@ -28,6 +28,7 @@ #include <linux/init.h> #include <linux/smp.h> #include <linux/nodemask.h> +#include <linux/mmzone.h> #include <asm/cpu.h> static struct i386_cpu cpu_devices[NR_CPUS]; @@ -55,34 +56,18 @@ EXPORT_SYMBOL(arch_register_cpu); EXPORT_SYMBOL(arch_unregister_cpu); #endif /*CONFIG_HOTPLUG_CPU*/ - - -#ifdef CONFIG_NUMA -#include <linux/mmzone.h> - static int __init topology_init(void) { int i; +#ifdef CONFIG_NUMA for_each_online_node(i) register_one_node(i); +#endif /* CONFIG_NUMA */ for_each_present_cpu(i) arch_register_cpu(i); return 0; } -#else /* !CONFIG_NUMA */ - -static int __init topology_init(void) -{ - int i; - - for_each_present_cpu(i) - arch_register_cpu(i); - return 0; -} - -#endif /* CONFIG_NUMA */ - subsys_initcall(topology_init); diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c index 4fcc6690..21aa1cd 100644 --- a/arch/i386/kernel/traps.c +++ b/arch/i386/kernel/traps.c @@ -51,6 +51,7 @@ #include <asm/smp.h> #include <asm/arch_hooks.h> #include <asm/kdebug.h> +#include <asm/stacktrace.h> #include <linux/module.h> @@ -118,26 +119,16 @@ static inline int valid_stack_ptr(struct thread_info *tinfo, void *p) p < (void *)tinfo + THREAD_SIZE - 3; } -/* - * Print one address/symbol entries per line. - */ -static inline void print_addr_and_symbol(unsigned long addr, char *log_lvl) -{ - printk(" [<%08lx>] ", addr); - - print_symbol("%s\n", addr); -} - static inline unsigned long print_context_stack(struct thread_info *tinfo, unsigned long *stack, unsigned long ebp, - char *log_lvl) + struct stacktrace_ops *ops, void *data) { unsigned long addr; #ifdef CONFIG_FRAME_POINTER while (valid_stack_ptr(tinfo, (void *)ebp)) { addr = *(unsigned long *)(ebp + 4); - print_addr_and_symbol(addr, log_lvl); + ops->address(data, addr); /* * break out of recursive entries (such as * end_of_stack_stop_unwind_function): @@ -150,30 +141,37 @@ static inline unsigned long print_context_stack(struct thread_info *tinfo, while (valid_stack_ptr(tinfo, stack)) { addr = *stack++; if (__kernel_text_address(addr)) - print_addr_and_symbol(addr, log_lvl); + ops->address(data, addr); } #endif return ebp; } +struct ops_and_data { + struct stacktrace_ops *ops; + void *data; +}; + static asmlinkage int -show_trace_unwind(struct unwind_frame_info *info, void *log_lvl) +dump_trace_unwind(struct unwind_frame_info *info, void *data) { + struct ops_and_data *oad = (struct ops_and_data *)data; int n = 0; while (unwind(info) == 0 && UNW_PC(info)) { n++; - print_addr_and_symbol(UNW_PC(info), log_lvl); + oad->ops->address(oad->data, UNW_PC(info)); if (arch_unw_user_mode(info)) break; } return n; } -static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, char *log_lvl) +void dump_trace(struct task_struct *task, struct pt_regs *regs, + unsigned long *stack, + struct stacktrace_ops *ops, void *data) { - unsigned long ebp; + unsigned long ebp = 0; if (!task) task = current; @@ -181,54 +179,116 @@ static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, if (call_trace >= 0) { int unw_ret = 0; struct unwind_frame_info info; + struct ops_and_data oad = { .ops = ops, .data = data }; if (regs) { if (unwind_init_frame_info(&info, task, regs) == 0) - unw_ret = show_trace_unwind(&info, log_lvl); + unw_ret = dump_trace_unwind(&info, &oad); } else if (task == current) - unw_ret = unwind_init_running(&info, show_trace_unwind, log_lvl); + unw_ret = unwind_init_running(&info, dump_trace_unwind, &oad); else { if (unwind_init_blocked(&info, task) == 0) - unw_ret = show_trace_unwind(&info, log_lvl); + unw_ret = dump_trace_unwind(&info, &oad); } if (unw_ret > 0) { if (call_trace == 1 && !arch_unw_user_mode(&info)) { - print_symbol("DWARF2 unwinder stuck at %s\n", + ops->warning_symbol(data, "DWARF2 unwinder stuck at %s\n", UNW_PC(&info)); if (UNW_SP(&info) >= PAGE_OFFSET) { - printk("Leftover inexact backtrace:\n"); + ops->warning(data, "Leftover inexact backtrace:\n"); stack = (void *)UNW_SP(&info); + if (!stack) + return; + ebp = UNW_FP(&info); } else - printk("Full inexact backtrace again:\n"); + ops->warning(data, "Full inexact backtrace again:\n"); } else if (call_trace >= 1) return; else - printk("Full inexact backtrace again:\n"); + ops->warning(data, "Full inexact backtrace again:\n"); } else - printk("Inexact backtrace:\n"); + ops->warning(data, "Inexact backtrace:\n"); + } + if (!stack) { + unsigned long dummy; + stack = &dummy; + if (task && task != current) + stack = (unsigned long *)task->thread.esp; } - if (task == current) { - /* Grab ebp right from our regs */ - asm ("movl %%ebp, %0" : "=r" (ebp) : ); - } else { - /* ebp is the last reg pushed by switch_to */ - ebp = *(unsigned long *) task->thread.esp; +#ifdef CONFIG_FRAME_POINTER + if (!ebp) { + if (task == current) { + /* Grab ebp right from our regs */ + asm ("movl %%ebp, %0" : "=r" (ebp) : ); + } else { + /* ebp is the last reg pushed by switch_to */ + ebp = *(unsigned long *) task->thread.esp; + } } +#endif while (1) { struct thread_info *context; context = (struct thread_info *) ((unsigned long)stack & (~(THREAD_SIZE - 1))); - ebp = print_context_stack(context, stack, ebp, log_lvl); + ebp = print_context_stack(context, stack, ebp, ops, data); + /* Should be after the line below, but somewhere + in early boot context comes out corrupted and we + can't reference it -AK */ + if (ops->stack(data, "IRQ") < 0) + break; stack = (unsigned long*)context->previous_esp; if (!stack) break; - printk("%s =======================\n", log_lvl); } } +EXPORT_SYMBOL(dump_trace); + +static void +print_trace_warning_symbol(void *data, char *msg, unsigned long symbol) +{ + printk(data); + print_symbol(msg, symbol); + printk("\n"); +} + +static void print_trace_warning(void *data, char *msg) +{ + printk("%s%s\n", (char *)data, msg); +} + +static int print_trace_stack(void *data, char *name) +{ + return 0; +} + +/* + * Print one address/symbol entries per line. + */ +static void print_trace_address(void *data, unsigned long addr) +{ + printk("%s [<%08lx>] ", (char *)data, addr); + print_symbol("%s\n", addr); +} + +static struct stacktrace_ops print_trace_ops = { + .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, char *log_lvl) +{ + dump_trace(task, regs, stack, &print_trace_ops, log_lvl); + printk("%s =======================\n", log_lvl); +} -void show_trace(struct task_struct *task, struct pt_regs *regs, unsigned long * stack) +void show_trace(struct task_struct *task, struct pt_regs *regs, + unsigned long * stack) { show_trace_log_lvl(task, regs, stack, ""); } @@ -291,8 +351,9 @@ void show_registers(struct pt_regs *regs) ss = regs->xss & 0xffff; } print_modules(); - printk(KERN_EMERG "CPU: %d\nEIP: %04x:[<%08lx>] %s VLI\n" - "EFLAGS: %08lx (%s %.*s) \n", + printk(KERN_EMERG "CPU: %d\n" + KERN_EMERG "EIP: %04x:[<%08lx>] %s VLI\n" + KERN_EMERG "EFLAGS: %08lx (%s %.*s)\n", smp_processor_id(), 0xffff & regs->xcs, regs->eip, print_tainted(), regs->eflags, system_utsname.release, (int)strcspn(system_utsname.version, " "), @@ -634,18 +695,24 @@ gp_in_kernel: } } -static void mem_parity_error(unsigned char reason, struct pt_regs * regs) +static __kprobes void +mem_parity_error(unsigned char reason, struct pt_regs * regs) { - printk(KERN_EMERG "Uhhuh. NMI received. Dazed and confused, but trying " - "to continue\n"); + printk(KERN_EMERG "Uhhuh. NMI received for unknown reason %02x on " + "CPU %d.\n", reason, smp_processor_id()); printk(KERN_EMERG "You probably have a hardware problem with your RAM " "chips\n"); + if (panic_on_unrecovered_nmi) + panic("NMI: Not continuing"); + + printk(KERN_EMERG "Dazed and confused, but trying to continue\n"); /* Clear and disable the memory parity error line. */ clear_mem_error(reason); } -static void io_check_error(unsigned char reason, struct pt_regs * regs) +static __kprobes void +io_check_error(unsigned char reason, struct pt_regs * regs) { unsigned long i; @@ -661,7 +728,8 @@ static void io_check_error(unsigned char reason, struct pt_regs * regs) outb(reason, 0x61); } -static void unknown_nmi_error(unsigned char reason, struct pt_regs * regs) +static __kprobes void +unknown_nmi_error(unsigned char reason, struct pt_regs * regs) { #ifdef CONFIG_MCA /* Might actually be able to figure out what the guilty party @@ -671,15 +739,18 @@ static void unknown_nmi_error(unsigned char reason, struct pt_regs * regs) return; } #endif - printk("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n", - reason, smp_processor_id()); - printk("Dazed and confused, but trying to continue\n"); - printk("Do you have a strange power saving mode enabled?\n"); + 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"); + + printk(KERN_EMERG "Dazed and confused, but trying to continue\n"); } static DEFINE_SPINLOCK(nmi_print_lock); -void die_nmi (struct pt_regs *regs, const char *msg) +void __kprobes die_nmi(struct pt_regs *regs, const char *msg) { if (notify_die(DIE_NMIWATCHDOG, msg, regs, 0, 2, SIGINT) == NOTIFY_STOP) @@ -711,7 +782,7 @@ void die_nmi (struct pt_regs *regs, const char *msg) do_exit(SIGSEGV); } -static void default_do_nmi(struct pt_regs * regs) +static __kprobes void default_do_nmi(struct pt_regs * regs) { unsigned char reason = 0; @@ -728,12 +799,12 @@ static void default_do_nmi(struct pt_regs * regs) * Ok, so this is none of the documented NMI sources, * so it must be the NMI watchdog. */ - if (nmi_watchdog) { - nmi_watchdog_tick(regs); + if (nmi_watchdog_tick(regs, reason)) return; - } + if (!do_nmi_callback(regs, smp_processor_id())) #endif - unknown_nmi_error(reason, regs); + unknown_nmi_error(reason, regs); + return; } if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP) @@ -749,14 +820,7 @@ static void default_do_nmi(struct pt_regs * regs) reassert_nmi(); } -static int dummy_nmi_callback(struct pt_regs * regs, int cpu) -{ - return 0; -} - -static nmi_callback_t nmi_callback = dummy_nmi_callback; - -fastcall void do_nmi(struct pt_regs * regs, long error_code) +fastcall __kprobes void do_nmi(struct pt_regs * regs, long error_code) { int cpu; @@ -766,25 +830,11 @@ fastcall void do_nmi(struct pt_regs * regs, long error_code) ++nmi_count(cpu); - if (!rcu_dereference(nmi_callback)(regs, cpu)) - default_do_nmi(regs); + default_do_nmi(regs); nmi_exit(); } -void set_nmi_callback(nmi_callback_t callback) -{ - vmalloc_sync_all(); - rcu_assign_pointer(nmi_callback, callback); -} -EXPORT_SYMBOL_GPL(set_nmi_callback); - -void unset_nmi_callback(void) -{ - nmi_callback = dummy_nmi_callback; -} -EXPORT_SYMBOL_GPL(unset_nmi_callback); - #ifdef CONFIG_KPROBES fastcall void __kprobes do_int3(struct pt_regs *regs, long error_code) { @@ -1124,20 +1174,6 @@ void __init trap_init_f00f_bug(void) } #endif -#define _set_gate(gate_addr,type,dpl,addr,seg) \ -do { \ - int __d0, __d1; \ - __asm__ __volatile__ ("movw %%dx,%%ax\n\t" \ - "movw %4,%%dx\n\t" \ - "movl %%eax,%0\n\t" \ - "movl %%edx,%1" \ - :"=m" (*((long *) (gate_addr))), \ - "=m" (*(1+(long *) (gate_addr))), "=&a" (__d0), "=&d" (__d1) \ - :"i" ((short) (0x8000+(dpl<<13)+(type<<8))), \ - "3" ((char *) (addr)),"2" ((seg) << 16)); \ -} while (0) - - /* * This needs to use 'idt_table' rather than 'idt', and * thus use the _nonmapped_ version of the IDT, as the @@ -1146,7 +1182,7 @@ do { \ */ void set_intr_gate(unsigned int n, void *addr) { - _set_gate(idt_table+n,14,0,addr,__KERNEL_CS); + _set_gate(n, DESCTYPE_INT, addr, __KERNEL_CS); } /* @@ -1154,22 +1190,22 @@ void set_intr_gate(unsigned int n, void *addr) */ static inline void set_system_intr_gate(unsigned int n, void *addr) { - _set_gate(idt_table+n, 14, 3, addr, __KERNEL_CS); + _set_gate(n, DESCTYPE_INT | DESCTYPE_DPL3, addr, __KERNEL_CS); } static void __init set_trap_gate(unsigned int n, void *addr) { - _set_gate(idt_table+n,15,0,addr,__KERNEL_CS); + _set_gate(n, DESCTYPE_TRAP, addr, __KERNEL_CS); } static void __init set_system_gate(unsigned int n, void *addr) { - _set_gate(idt_table+n,15,3,addr,__KERNEL_CS); + _set_gate(n, DESCTYPE_TRAP | DESCTYPE_DPL3, addr, __KERNEL_CS); } static void __init set_task_gate(unsigned int n, unsigned int gdt_entry) { - _set_gate(idt_table+n,5,0,0,(gdt_entry<<3)); + _set_gate(n, DESCTYPE_TASK, (void *)0, (gdt_entry<<3)); } diff --git a/arch/i386/kernel/tsc.c b/arch/i386/kernel/tsc.c index 7e0d8da..b8fa0a8 100644 --- a/arch/i386/kernel/tsc.c +++ b/arch/i386/kernel/tsc.c @@ -192,7 +192,7 @@ int recalibrate_cpu_khz(void) EXPORT_SYMBOL(recalibrate_cpu_khz); -void tsc_init(void) +void __init tsc_init(void) { if (!cpu_has_tsc || tsc_disable) return; diff --git a/arch/i386/lib/Makefile b/arch/i386/lib/Makefile index 914933e..d86a548 100644 --- a/arch/i386/lib/Makefile +++ b/arch/i386/lib/Makefile @@ -4,6 +4,6 @@ lib-y = checksum.o delay.o usercopy.o getuser.o putuser.o memcpy.o strstr.o \ - bitops.o + bitops.o semaphore.o lib-$(CONFIG_X86_USE_3DNOW) += mmx.o diff --git a/arch/i386/lib/semaphore.S b/arch/i386/lib/semaphore.S new file mode 100644 index 0000000..01f80b5 --- /dev/null +++ b/arch/i386/lib/semaphore.S @@ -0,0 +1,217 @@ +/* + * i386 semaphore implementation. + * + * (C) Copyright 1999 Linus Torvalds + * + * Portions Copyright 1999 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. + * + * rw semaphores implemented November 1999 by Benjamin LaHaise <bcrl@kvack.org> + */ + +#include <linux/config.h> +#include <linux/linkage.h> +#include <asm/rwlock.h> +#include <asm/alternative-asm.i> +#include <asm/frame.i> +#include <asm/dwarf2.h> + +/* + * The semaphore operations have a special calling sequence that + * allow us to do a simpler in-line version of them. These routines + * need to convert that sequence back into the C sequence when + * there is contention on the semaphore. + * + * %eax contains the semaphore pointer on entry. Save the C-clobbered + * registers (%eax, %edx and %ecx) except %eax whish is either a return + * value or just clobbered.. + */ + .section .sched.text +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 + END(__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 + END(__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 + END(__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 + END(__up_wakeup) + +/* + * rw spinlock fallbacks + */ +#ifdef CONFIG_SMP +ENTRY(__write_lock_failed) + CFI_STARTPROC simple + FRAME +2: LOCK_PREFIX + addl $ RW_LOCK_BIAS,(%eax) +1: rep; nop + cmpl $ RW_LOCK_BIAS,(%eax) + jne 1b + LOCK_PREFIX + subl $ RW_LOCK_BIAS,(%eax) + jnz 2b + ENDFRAME + ret + CFI_ENDPROC + END(__write_lock_failed) + +ENTRY(__read_lock_failed) + CFI_STARTPROC + FRAME +2: LOCK_PREFIX + incl (%eax) +1: rep; nop + cmpl $1,(%eax) + js 1b + LOCK_PREFIX + decl (%eax) + js 2b + ENDFRAME + ret + CFI_ENDPROC + END(__read_lock_failed) + +#endif + +/* Fix up special calling conventions */ +ENTRY(call_rwsem_down_read_failed) + CFI_STARTPROC + push %ecx + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET ecx,0 + push %edx + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET edx,0 + call rwsem_down_read_failed + pop %edx + CFI_ADJUST_CFA_OFFSET -4 + pop %ecx + CFI_ADJUST_CFA_OFFSET -4 + ret + CFI_ENDPROC + END(call_rwsem_down_read_failed) + +ENTRY(call_rwsem_down_write_failed) + CFI_STARTPROC + push %ecx + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET ecx,0 + calll rwsem_down_write_failed + pop %ecx + CFI_ADJUST_CFA_OFFSET -4 + ret + CFI_ENDPROC + END(call_rwsem_down_write_failed) + +ENTRY(call_rwsem_wake) + CFI_STARTPROC + decw %dx /* do nothing if still outstanding active readers */ + jnz 1f + push %ecx + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET ecx,0 + call rwsem_wake + pop %ecx + CFI_ADJUST_CFA_OFFSET -4 +1: ret + CFI_ENDPROC + END(call_rwsem_wake) + +/* Fix up special calling conventions */ +ENTRY(call_rwsem_downgrade_wake) + CFI_STARTPROC + push %ecx + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET ecx,0 + push %edx + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET edx,0 + call rwsem_downgrade_wake + pop %edx + CFI_ADJUST_CFA_OFFSET -4 + pop %ecx + CFI_ADJUST_CFA_OFFSET -4 + ret + CFI_ENDPROC + END(call_rwsem_downgrade_wake) + diff --git a/arch/i386/mach-generic/bigsmp.c b/arch/i386/mach-generic/bigsmp.c index ef7a6e6..33d9f93 100644 --- a/arch/i386/mach-generic/bigsmp.c +++ b/arch/i386/mach-generic/bigsmp.c @@ -5,6 +5,7 @@ #define APIC_DEFINITION 1 #include <linux/threads.h> #include <linux/cpumask.h> +#include <asm/smp.h> #include <asm/mpspec.h> #include <asm/genapic.h> #include <asm/fixmap.h> diff --git a/arch/i386/mach-generic/es7000.c b/arch/i386/mach-generic/es7000.c index 845cdd0..aa144d8 100644 --- a/arch/i386/mach-generic/es7000.c +++ b/arch/i386/mach-generic/es7000.c @@ -4,6 +4,7 @@ #define APIC_DEFINITION 1 #include <linux/threads.h> #include <linux/cpumask.h> +#include <asm/smp.h> #include <asm/mpspec.h> #include <asm/genapic.h> #include <asm/fixmap.h> diff --git a/arch/i386/mach-generic/probe.c b/arch/i386/mach-generic/probe.c index bcd1bcf..94b1fd9 100644 --- a/arch/i386/mach-generic/probe.c +++ b/arch/i386/mach-generic/probe.c @@ -9,6 +9,7 @@ #include <linux/kernel.h> #include <linux/ctype.h> #include <linux/init.h> +#include <linux/errno.h> #include <asm/fixmap.h> #include <asm/mpspec.h> #include <asm/apicdef.h> @@ -29,7 +30,24 @@ struct genapic *apic_probe[] __initdata = { NULL, }; -static int cmdline_apic; +static int cmdline_apic __initdata; +static int __init parse_apic(char *arg) +{ + int i; + + if (!arg) + return -EINVAL; + + for (i = 0; apic_probe[i]; i++) { + if (!strcmp(apic_probe[i]->name, arg)) { + genapic = apic_probe[i]; + cmdline_apic = 1; + return 0; + } + } + return -ENOENT; +} +early_param("apic", parse_apic); void __init generic_bigsmp_probe(void) { @@ -48,40 +66,20 @@ void __init generic_bigsmp_probe(void) } } -void __init generic_apic_probe(char *command_line) +void __init generic_apic_probe(void) { - char *s; - int i; - int changed = 0; - - s = strstr(command_line, "apic="); - if (s && (s == command_line || isspace(s[-1]))) { - char *p = strchr(s, ' '), old; - if (!p) - p = strchr(s, '\0'); - old = *p; - *p = 0; - for (i = 0; !changed && apic_probe[i]; i++) { - if (!strcmp(apic_probe[i]->name, s+5)) { - changed = 1; + if (!cmdline_apic) { + int i; + for (i = 0; apic_probe[i]; i++) { + if (apic_probe[i]->probe()) { genapic = apic_probe[i]; + break; } } - if (!changed) - printk(KERN_ERR "Unknown genapic `%s' specified.\n", s); - *p = old; - cmdline_apic = changed; - } - for (i = 0; !changed && apic_probe[i]; i++) { - if (apic_probe[i]->probe()) { - changed = 1; - genapic = apic_probe[i]; - } + /* Not visible without early console */ + if (!apic_probe[i]) + panic("Didn't find an APIC driver"); } - /* Not visible without early console */ - if (!changed) - panic("Didn't find an APIC driver"); - printk(KERN_INFO "Using APIC driver %s\n", genapic->name); } @@ -119,7 +117,9 @@ int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id) return 0; } +#ifdef CONFIG_SMP int hard_smp_processor_id(void) { return genapic->get_apic_id(*(unsigned long *)(APIC_BASE+APIC_ID)); } +#endif diff --git a/arch/i386/mach-generic/summit.c b/arch/i386/mach-generic/summit.c index b73501d..f7e5d66 100644 --- a/arch/i386/mach-generic/summit.c +++ b/arch/i386/mach-generic/summit.c @@ -4,6 +4,7 @@ #define APIC_DEFINITION 1 #include <linux/threads.h> #include <linux/cpumask.h> +#include <asm/smp.h> #include <asm/mpspec.h> #include <asm/genapic.h> #include <asm/fixmap.h> diff --git a/arch/i386/mm/discontig.c b/arch/i386/mm/discontig.c index fb5d8b7..941d1a5 100644 --- a/arch/i386/mm/discontig.c +++ b/arch/i386/mm/discontig.c @@ -322,6 +322,11 @@ unsigned long __init setup_memory(void) highstart_pfn = system_max_low_pfn; printk(KERN_NOTICE "%ldMB HIGHMEM available.\n", pages_to_mb(highend_pfn - highstart_pfn)); + num_physpages = highend_pfn; + high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1; +#else + num_physpages = system_max_low_pfn; + high_memory = (void *) __va(system_max_low_pfn * PAGE_SIZE - 1) + 1; #endif printk(KERN_NOTICE "%ldMB LOWMEM available.\n", pages_to_mb(system_max_low_pfn)); diff --git a/arch/i386/mm/extable.c b/arch/i386/mm/extable.c index de03c54..0ce4f22 100644 --- a/arch/i386/mm/extable.c +++ b/arch/i386/mm/extable.c @@ -11,7 +11,7 @@ int fixup_exception(struct pt_regs *regs) const struct exception_table_entry *fixup; #ifdef CONFIG_PNPBIOS - if (unlikely((regs->xcs & ~15) == (GDT_ENTRY_PNPBIOS_BASE << 3))) + if (unlikely(SEGMENT_IS_PNP_CODE(regs->xcs))) { extern u32 pnp_bios_fault_eip, pnp_bios_fault_esp; extern u32 pnp_bios_is_utter_crap; diff --git a/arch/i386/mm/fault.c b/arch/i386/mm/fault.c index f727946..5e17a3f 100644 --- a/arch/i386/mm/fault.c +++ b/arch/i386/mm/fault.c @@ -27,21 +27,24 @@ #include <asm/uaccess.h> #include <asm/desc.h> #include <asm/kdebug.h> +#include <asm/segment.h> extern void die(const char *,struct pt_regs *,long); -#ifdef CONFIG_KPROBES -ATOMIC_NOTIFIER_HEAD(notify_page_fault_chain); +static ATOMIC_NOTIFIER_HEAD(notify_page_fault_chain); + int register_page_fault_notifier(struct notifier_block *nb) { vmalloc_sync_all(); return atomic_notifier_chain_register(¬ify_page_fault_chain, nb); } +EXPORT_SYMBOL_GPL(register_page_fault_notifier); int unregister_page_fault_notifier(struct notifier_block *nb) { return atomic_notifier_chain_unregister(¬ify_page_fault_chain, nb); } +EXPORT_SYMBOL_GPL(unregister_page_fault_notifier); static inline int notify_page_fault(enum die_val val, const char *str, struct pt_regs *regs, long err, int trap, int sig) @@ -55,14 +58,6 @@ static inline int notify_page_fault(enum die_val val, const char *str, }; return atomic_notifier_call_chain(¬ify_page_fault_chain, val, &args); } -#else -static inline int notify_page_fault(enum die_val val, const char *str, - struct pt_regs *regs, long err, int trap, int sig) -{ - return NOTIFY_DONE; -} -#endif - /* * Unlock any spinlocks which will prevent us from getting the @@ -119,10 +114,10 @@ static inline unsigned long get_segment_eip(struct pt_regs *regs, } /* The standard kernel/user address space limit. */ - *eip_limit = (seg & 3) ? USER_DS.seg : KERNEL_DS.seg; + *eip_limit = user_mode(regs) ? USER_DS.seg : KERNEL_DS.seg; /* By far the most common cases. */ - if (likely(seg == __USER_CS || seg == __KERNEL_CS)) + if (likely(SEGMENT_IS_FLAT_CODE(seg))) return eip; /* Check the segment exists, is within the current LDT/GDT size, @@ -436,11 +431,7 @@ good_area: write = 0; switch (error_code & 3) { default: /* 3: write, present */ -#ifdef TEST_VERIFY_AREA - if (regs->cs == KERNEL_CS) - printk("WP fault at %08lx\n", regs->eip); -#endif - /* fall through */ + /* fall through */ case 2: /* write, not present */ if (!(vma->vm_flags & VM_WRITE)) goto bad_area; diff --git a/arch/i386/mm/highmem.c b/arch/i386/mm/highmem.c index b6eb4dc..ba44000 100644 --- a/arch/i386/mm/highmem.c +++ b/arch/i386/mm/highmem.c @@ -54,7 +54,7 @@ void kunmap_atomic(void *kvaddr, enum km_type type) unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK; enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id(); - if (vaddr < FIXADDR_START) { // FIXME + if (vaddr >= PAGE_OFFSET && vaddr < (unsigned long)high_memory) { dec_preempt_count(); preempt_check_resched(); return; diff --git a/arch/i386/mm/init.c b/arch/i386/mm/init.c index efd0bcd..4a5a914 100644 --- a/arch/i386/mm/init.c +++ b/arch/i386/mm/init.c @@ -435,16 +435,22 @@ u64 __supported_pte_mask __read_mostly = ~_PAGE_NX; * on Enable * off Disable */ -void __init noexec_setup(const char *str) +static int __init noexec_setup(char *str) { - if (!strncmp(str, "on",2) && cpu_has_nx) { - __supported_pte_mask |= _PAGE_NX; - disable_nx = 0; - } else if (!strncmp(str,"off",3)) { + if (!str || !strcmp(str, "on")) { + if (cpu_has_nx) { + __supported_pte_mask |= _PAGE_NX; + disable_nx = 0; + } + } else if (!strcmp(str,"off")) { disable_nx = 1; __supported_pte_mask &= ~_PAGE_NX; - } + } else + return -EINVAL; + + return 0; } +early_param("noexec", noexec_setup); int nx_enabled = 0; #ifdef CONFIG_X86_PAE @@ -552,18 +558,6 @@ static void __init test_wp_bit(void) } } -static void __init set_max_mapnr_init(void) -{ -#ifdef CONFIG_HIGHMEM - num_physpages = highend_pfn; -#else - num_physpages = max_low_pfn; -#endif -#ifdef CONFIG_FLATMEM - max_mapnr = num_physpages; -#endif -} - static struct kcore_list kcore_mem, kcore_vmalloc; void __init mem_init(void) @@ -590,14 +584,6 @@ void __init mem_init(void) } #endif - set_max_mapnr_init(); - -#ifdef CONFIG_HIGHMEM - high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1; -#else - high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1; -#endif - /* this will put all low memory onto the freelists */ totalram_pages += free_all_bootmem(); diff --git a/arch/i386/oprofile/nmi_int.c b/arch/i386/oprofile/nmi_int.c index 5f8dc8a..3700eef 100644 --- a/arch/i386/oprofile/nmi_int.c +++ b/arch/i386/oprofile/nmi_int.c @@ -17,14 +17,15 @@ #include <asm/nmi.h> #include <asm/msr.h> #include <asm/apic.h> +#include <asm/kdebug.h> #include "op_counter.h" #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 int nmi_start(void); static void nmi_stop(void); @@ -82,13 +83,24 @@ static void exit_driverfs(void) #define exit_driverfs() do { } while (0) #endif /* CONFIG_PM */ - -static int nmi_callback(struct pt_regs * regs, int cpu) +static int profile_exceptions_notify(struct notifier_block *self, + unsigned long val, void *data) { - return model->check_ctrs(regs, &cpu_msrs[cpu]); + struct die_args *args = (struct die_args *)data; + int ret = NOTIFY_DONE; + int cpu = smp_processor_id(); + + switch(val) { + case DIE_NMI: + if (model->check_ctrs(args->regs, &cpu_msrs[cpu])) + ret = NOTIFY_STOP; + break; + default: + break; + } + return ret; } - - + static void nmi_cpu_save_registers(struct op_msrs * msrs) { unsigned int const nr_ctrs = model->num_counters; @@ -98,15 +110,19 @@ static void nmi_cpu_save_registers(struct op_msrs * msrs) unsigned int i; for (i = 0; i < nr_ctrs; ++i) { - rdmsr(counters[i].addr, - counters[i].saved.low, - counters[i].saved.high); + if (counters[i].addr){ + rdmsr(counters[i].addr, + counters[i].saved.low, + counters[i].saved.high); + } } for (i = 0; i < nr_ctrls; ++i) { - rdmsr(controls[i].addr, - controls[i].saved.low, - controls[i].saved.high); + if (controls[i].addr){ + rdmsr(controls[i].addr, + controls[i].saved.low, + controls[i].saved.high); + } } } @@ -170,27 +186,29 @@ static void nmi_cpu_setup(void * dummy) apic_write(APIC_LVTPC, APIC_DM_NMI); } +static struct notifier_block profile_exceptions_nb = { + .notifier_call = profile_exceptions_notify, + .next = NULL, + .priority = 0 +}; static int nmi_setup(void) { + int err=0; + if (!allocate_msrs()) return -ENOMEM; - /* We walk a thin line between law and rape here. - * We need to be careful to install our NMI handler - * without actually triggering any NMIs as this will - * break the core code horrifically. - */ - if (reserve_lapic_nmi() < 0) { + if ((err = register_die_notifier(&profile_exceptions_nb))){ free_msrs(); - return -EBUSY; + return err; } + /* We need to serialize save and setup for HT because the subset * of msrs are distinct for save and setup operations */ on_each_cpu(nmi_save_registers, NULL, 0, 1); on_each_cpu(nmi_cpu_setup, NULL, 0, 1); - set_nmi_callback(nmi_callback); nmi_enabled = 1; return 0; } @@ -205,15 +223,19 @@ static void nmi_restore_registers(struct op_msrs * msrs) unsigned int i; for (i = 0; i < nr_ctrls; ++i) { - wrmsr(controls[i].addr, - controls[i].saved.low, - controls[i].saved.high); + if (controls[i].addr){ + wrmsr(controls[i].addr, + controls[i].saved.low, + controls[i].saved.high); + } } for (i = 0; i < nr_ctrs; ++i) { - wrmsr(counters[i].addr, - counters[i].saved.low, - counters[i].saved.high); + if (counters[i].addr){ + wrmsr(counters[i].addr, + counters[i].saved.low, + counters[i].saved.high); + } } } @@ -234,6 +256,7 @@ static void nmi_cpu_shutdown(void * dummy) apic_write(APIC_LVTPC, saved_lvtpc[cpu]); apic_write(APIC_LVTERR, v); nmi_restore_registers(msrs); + model->shutdown(msrs); } @@ -241,8 +264,7 @@ static void nmi_shutdown(void) { nmi_enabled = 0; on_each_cpu(nmi_cpu_shutdown, NULL, 0, 1); - unset_nmi_callback(); - release_lapic_nmi(); + unregister_die_notifier(&profile_exceptions_nb); free_msrs(); } @@ -284,6 +306,14 @@ static int nmi_create_files(struct super_block * sb, struct dentry * root) struct dentry * dir; char buf[4]; + /* quick little hack to _not_ expose a counter if it is not + * available for use. This should protect userspace app. + * NOTE: assumes 1:1 mapping here (that counters are organized + * sequentially in their struct assignment). + */ + if (unlikely(!avail_to_resrv_perfctr_nmi_bit(i))) + continue; + snprintf(buf, sizeof(buf), "%d", i); dir = oprofilefs_mkdir(sb, root, buf); oprofilefs_create_ulong(sb, dir, "enabled", &counter_config[i].enabled); diff --git a/arch/i386/oprofile/nmi_timer_int.c b/arch/i386/oprofile/nmi_timer_int.c index 930a112..abf0ba5 100644 --- a/arch/i386/oprofile/nmi_timer_int.c +++ b/arch/i386/oprofile/nmi_timer_int.c @@ -17,34 +17,49 @@ #include <asm/nmi.h> #include <asm/apic.h> #include <asm/ptrace.h> +#include <asm/kdebug.h> -static int nmi_timer_callback(struct pt_regs * regs, int cpu) +static int profile_timer_exceptions_notify(struct notifier_block *self, + unsigned long val, void *data) { - oprofile_add_sample(regs, 0); - return 1; + struct die_args *args = (struct die_args *)data; + int ret = NOTIFY_DONE; + + switch(val) { + case DIE_NMI: + oprofile_add_sample(args->regs, 0); + ret = NOTIFY_STOP; + break; + default: + break; + } + return ret; } +static struct notifier_block profile_timer_exceptions_nb = { + .notifier_call = profile_timer_exceptions_notify, + .next = NULL, + .priority = 0 +}; + static int timer_start(void) { - disable_timer_nmi_watchdog(); - set_nmi_callback(nmi_timer_callback); + if (register_die_notifier(&profile_timer_exceptions_nb)) + return 1; return 0; } static void timer_stop(void) { - enable_timer_nmi_watchdog(); - unset_nmi_callback(); + unregister_die_notifier(&profile_timer_exceptions_nb); synchronize_sched(); /* Allow already-started NMIs to complete. */ } int __init op_nmi_timer_init(struct oprofile_operations * ops) { - extern int nmi_active; - - if (nmi_active <= 0) + if ((nmi_watchdog != NMI_IO_APIC) || (atomic_read(&nmi_active) <= 0)) return -ENODEV; ops->start = timer_start; diff --git a/arch/i386/oprofile/op_model_athlon.c b/arch/i386/oprofile/op_model_athlon.c index 693bdea..3057a19 100644 --- a/arch/i386/oprofile/op_model_athlon.c +++ b/arch/i386/oprofile/op_model_athlon.c @@ -21,10 +21,12 @@ #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_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_SET_ACTIVE(n) (n |= (1<<22)) @@ -40,15 +42,21 @@ static unsigned long reset_value[NUM_COUNTERS]; static void athlon_fill_in_addresses(struct op_msrs * const msrs) { - msrs->counters[0].addr = MSR_K7_PERFCTR0; - msrs->counters[1].addr = MSR_K7_PERFCTR1; - msrs->counters[2].addr = MSR_K7_PERFCTR2; - msrs->counters[3].addr = MSR_K7_PERFCTR3; - - msrs->controls[0].addr = MSR_K7_EVNTSEL0; - msrs->controls[1].addr = MSR_K7_EVNTSEL1; - msrs->controls[2].addr = MSR_K7_EVNTSEL2; - msrs->controls[3].addr = MSR_K7_EVNTSEL3; + int 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++) { + if (reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i)) + msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i; + else + msrs->controls[i].addr = 0; + } } @@ -59,19 +67,23 @@ static void athlon_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))) + 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))) + continue; CTR_WRITE(1, msrs, i); } /* enable active counters */ for (i = 0; i < NUM_COUNTERS; ++i) { - if (counter_config[i].enabled) { + 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); @@ -98,6 +110,8 @@ static int athlon_check_ctrs(struct pt_regs * const regs, int i; for (i = 0 ; i < NUM_COUNTERS; ++i) { + if (!reset_value[i]) + continue; CTR_READ(low, high, msrs, i); if (CTR_OVERFLOWED(low)) { oprofile_add_sample(regs, i); @@ -132,12 +146,27 @@ static void athlon_stop(struct op_msrs const * const msrs) /* Subtle: stop on all counters to avoid race with * setting our pm callback */ for (i = 0 ; i < NUM_COUNTERS ; ++i) { + if (!reset_value[i]) + continue; CTRL_READ(low, high, msrs, i); CTRL_SET_INACTIVE(low); CTRL_WRITE(low, high, msrs, i); } } +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)) + release_perfctr_nmi(MSR_K7_PERFCTR0 + i); + } + for (i = 0 ; i < NUM_CONTROLS ; ++i) { + if (CTRL_IS_RESERVED(msrs,i)) + release_evntsel_nmi(MSR_K7_EVNTSEL0 + i); + } +} struct op_x86_model_spec const op_athlon_spec = { .num_counters = NUM_COUNTERS, @@ -146,5 +175,6 @@ struct op_x86_model_spec const op_athlon_spec = { .setup_ctrs = &athlon_setup_ctrs, .check_ctrs = &athlon_check_ctrs, .start = &athlon_start, - .stop = &athlon_stop + .stop = &athlon_stop, + .shutdown = &athlon_shutdown }; diff --git a/arch/i386/oprofile/op_model_p4.c b/arch/i386/oprofile/op_model_p4.c index 7c61d35..4792592 100644 --- a/arch/i386/oprofile/op_model_p4.c +++ b/arch/i386/oprofile/op_model_p4.c @@ -32,7 +32,7 @@ #define NUM_CONTROLS_HT2 (NUM_ESCRS_HT2 + NUM_CCCRS_HT2) static unsigned int num_counters = NUM_COUNTERS_NON_HT; - +static unsigned int num_controls = NUM_CONTROLS_NON_HT; /* this has to be checked dynamically since the hyper-threadedness of a chip is discovered at @@ -40,8 +40,10 @@ static unsigned int num_counters = NUM_COUNTERS_NON_HT; static inline void setup_num_counters(void) { #ifdef CONFIG_SMP - if (smp_num_siblings == 2) + if (smp_num_siblings == 2){ num_counters = NUM_COUNTERS_HT2; + num_controls = NUM_CONTROLS_HT2; + } #endif } @@ -97,15 +99,6 @@ static struct p4_counter_binding p4_counters [NUM_COUNTERS_NON_HT] = { #define NUM_UNUSED_CCCRS NUM_CCCRS_NON_HT - NUM_COUNTERS_NON_HT -/* All cccr we don't use. */ -static int p4_unused_cccr[NUM_UNUSED_CCCRS] = { - MSR_P4_BPU_CCCR1, MSR_P4_BPU_CCCR3, - MSR_P4_MS_CCCR1, MSR_P4_MS_CCCR3, - MSR_P4_FLAME_CCCR1, MSR_P4_FLAME_CCCR3, - MSR_P4_IQ_CCCR0, MSR_P4_IQ_CCCR1, - MSR_P4_IQ_CCCR2, MSR_P4_IQ_CCCR3 -}; - /* p4 event codes in libop/op_event.h are indices into this table. */ static struct p4_event_binding p4_events[NUM_EVENTS] = { @@ -372,6 +365,8 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = { #define CCCR_OVF_P(cccr) ((cccr) & (1U<<31)) #define CCCR_CLEAR_OVF(cccr) ((cccr) &= (~(1U<<31))) +#define CTRL_IS_RESERVED(msrs,c) (msrs->controls[(c)].addr ? 1 : 0) +#define CTR_IS_RESERVED(msrs,c) (msrs->counters[(c)].addr ? 1 : 0) #define CTR_READ(l,h,i) do {rdmsr(p4_counters[(i)].counter_address, (l), (h));} while (0) #define CTR_WRITE(l,i) do {wrmsr(p4_counters[(i)].counter_address, -(u32)(l), -1);} while (0) #define CTR_OVERFLOW_P(ctr) (!((ctr) & 0x80000000)) @@ -401,29 +396,34 @@ static unsigned long reset_value[NUM_COUNTERS_NON_HT]; static void p4_fill_in_addresses(struct op_msrs * const msrs) { unsigned int i; - unsigned int addr, stag; + unsigned int addr, cccraddr, stag; setup_num_counters(); stag = get_stagger(); - /* the counter registers we pay attention to */ + /* initialize some registers */ for (i = 0; i < num_counters; ++i) { - msrs->counters[i].addr = - p4_counters[VIRT_CTR(stag, i)].counter_address; + msrs->counters[i].addr = 0; } - - /* FIXME: bad feeling, we don't save the 10 counters we don't use. */ - - /* 18 CCCR registers */ - for (i = 0, addr = MSR_P4_BPU_CCCR0 + stag; - addr <= MSR_P4_IQ_CCCR5; ++i, addr += addr_increment()) { - msrs->controls[i].addr = addr; + for (i = 0; i < num_controls; ++i) { + msrs->controls[i].addr = 0; } + /* the counter & cccr registers we pay attention to */ + for (i = 0; i < num_counters; ++i) { + addr = p4_counters[VIRT_CTR(stag, i)].counter_address; + cccraddr = p4_counters[VIRT_CTR(stag, i)].cccr_address; + if (reserve_perfctr_nmi(addr)){ + msrs->counters[i].addr = addr; + msrs->controls[i].addr = cccraddr; + } + } + /* 43 ESCR registers in three or four discontiguous group */ for (addr = MSR_P4_BSU_ESCR0 + stag; addr < MSR_P4_IQ_ESCR0; ++i, addr += addr_increment()) { - msrs->controls[i].addr = addr; + if (reserve_evntsel_nmi(addr)) + msrs->controls[i].addr = addr; } /* no IQ_ESCR0/1 on some models, we save a seconde time BSU_ESCR0/1 @@ -431,47 +431,57 @@ static void p4_fill_in_addresses(struct op_msrs * const msrs) if (boot_cpu_data.x86_model >= 0x3) { for (addr = MSR_P4_BSU_ESCR0 + stag; addr <= MSR_P4_BSU_ESCR1; ++i, addr += addr_increment()) { - msrs->controls[i].addr = addr; + if (reserve_evntsel_nmi(addr)) + msrs->controls[i].addr = addr; } } else { for (addr = MSR_P4_IQ_ESCR0 + stag; addr <= MSR_P4_IQ_ESCR1; ++i, addr += addr_increment()) { - msrs->controls[i].addr = addr; + if (reserve_evntsel_nmi(addr)) + msrs->controls[i].addr = addr; } } for (addr = MSR_P4_RAT_ESCR0 + stag; addr <= MSR_P4_SSU_ESCR0; ++i, addr += addr_increment()) { - msrs->controls[i].addr = addr; + if (reserve_evntsel_nmi(addr)) + msrs->controls[i].addr = addr; } for (addr = MSR_P4_MS_ESCR0 + stag; addr <= MSR_P4_TC_ESCR1; ++i, addr += addr_increment()) { - msrs->controls[i].addr = addr; + if (reserve_evntsel_nmi(addr)) + msrs->controls[i].addr = addr; } for (addr = MSR_P4_IX_ESCR0 + stag; addr <= MSR_P4_CRU_ESCR3; ++i, addr += addr_increment()) { - msrs->controls[i].addr = addr; + if (reserve_evntsel_nmi(addr)) + msrs->controls[i].addr = addr; } /* there are 2 remaining non-contiguously located ESCRs */ if (num_counters == NUM_COUNTERS_NON_HT) { /* standard non-HT CPUs handle both remaining ESCRs*/ - msrs->controls[i++].addr = MSR_P4_CRU_ESCR5; - msrs->controls[i++].addr = MSR_P4_CRU_ESCR4; + if (reserve_evntsel_nmi(MSR_P4_CRU_ESCR5)) + msrs->controls[i++].addr = MSR_P4_CRU_ESCR5; + if (reserve_evntsel_nmi(MSR_P4_CRU_ESCR4)) + msrs->controls[i++].addr = MSR_P4_CRU_ESCR4; } else if (stag == 0) { /* HT CPUs give the first remainder to the even thread, as the 32nd control register */ - msrs->controls[i++].addr = MSR_P4_CRU_ESCR4; + if (reserve_evntsel_nmi(MSR_P4_CRU_ESCR4)) + msrs->controls[i++].addr = MSR_P4_CRU_ESCR4; } else { /* and two copies of the second to the odd thread, for the 22st and 23nd control registers */ - msrs->controls[i++].addr = MSR_P4_CRU_ESCR5; - msrs->controls[i++].addr = MSR_P4_CRU_ESCR5; + if (reserve_evntsel_nmi(MSR_P4_CRU_ESCR5)) { + msrs->controls[i++].addr = MSR_P4_CRU_ESCR5; + msrs->controls[i++].addr = MSR_P4_CRU_ESCR5; + } } } @@ -544,7 +554,6 @@ static void p4_setup_ctrs(struct op_msrs const * const msrs) { unsigned int i; unsigned int low, high; - unsigned int addr; unsigned int stag; stag = get_stagger(); @@ -557,59 +566,24 @@ static void p4_setup_ctrs(struct op_msrs const * const msrs) /* clear the cccrs we will use */ for (i = 0 ; i < num_counters ; i++) { + if (unlikely(!CTRL_IS_RESERVED(msrs,i))) + continue; rdmsr(p4_counters[VIRT_CTR(stag, i)].cccr_address, low, high); CCCR_CLEAR(low); CCCR_SET_REQUIRED_BITS(low); wrmsr(p4_counters[VIRT_CTR(stag, i)].cccr_address, low, high); } - /* clear cccrs outside our concern */ - for (i = stag ; i < NUM_UNUSED_CCCRS ; i += addr_increment()) { - rdmsr(p4_unused_cccr[i], low, high); - CCCR_CLEAR(low); - CCCR_SET_REQUIRED_BITS(low); - wrmsr(p4_unused_cccr[i], low, high); - } - /* clear all escrs (including those outside our concern) */ - for (addr = MSR_P4_BSU_ESCR0 + stag; - addr < MSR_P4_IQ_ESCR0; addr += addr_increment()) { - wrmsr(addr, 0, 0); - } - - /* On older models clear also MSR_P4_IQ_ESCR0/1 */ - if (boot_cpu_data.x86_model < 0x3) { - wrmsr(MSR_P4_IQ_ESCR0, 0, 0); - wrmsr(MSR_P4_IQ_ESCR1, 0, 0); - } - - for (addr = MSR_P4_RAT_ESCR0 + stag; - addr <= MSR_P4_SSU_ESCR0; ++i, addr += addr_increment()) { - wrmsr(addr, 0, 0); - } - - for (addr = MSR_P4_MS_ESCR0 + stag; - addr <= MSR_P4_TC_ESCR1; addr += addr_increment()){ - wrmsr(addr, 0, 0); - } - - for (addr = MSR_P4_IX_ESCR0 + stag; - addr <= MSR_P4_CRU_ESCR3; addr += addr_increment()){ - wrmsr(addr, 0, 0); + for (i = num_counters; i < num_controls; i++) { + if (unlikely(!CTRL_IS_RESERVED(msrs,i))) + continue; + wrmsr(msrs->controls[i].addr, 0, 0); } - if (num_counters == NUM_COUNTERS_NON_HT) { - wrmsr(MSR_P4_CRU_ESCR4, 0, 0); - wrmsr(MSR_P4_CRU_ESCR5, 0, 0); - } else if (stag == 0) { - wrmsr(MSR_P4_CRU_ESCR4, 0, 0); - } else { - wrmsr(MSR_P4_CRU_ESCR5, 0, 0); - } - /* setup all counters */ for (i = 0 ; i < num_counters ; ++i) { - if (counter_config[i].enabled) { + if ((counter_config[i].enabled) && (CTRL_IS_RESERVED(msrs,i))) { reset_value[i] = counter_config[i].count; pmc_setup_one_p4_counter(i); CTR_WRITE(counter_config[i].count, VIRT_CTR(stag, i)); @@ -696,12 +670,32 @@ static void p4_stop(struct op_msrs const * const msrs) stag = get_stagger(); for (i = 0; i < num_counters; ++i) { + if (!reset_value[i]) + continue; CCCR_READ(low, high, VIRT_CTR(stag, i)); CCCR_SET_DISABLE(low); CCCR_WRITE(low, high, VIRT_CTR(stag, i)); } } +static void p4_shutdown(struct op_msrs const * const msrs) +{ + int i; + + for (i = 0 ; i < num_counters ; ++i) { + if (CTR_IS_RESERVED(msrs,i)) + release_perfctr_nmi(msrs->counters[i].addr); + } + /* some of the control registers are specially reserved in + * conjunction with the counter registers (hence the starting offset). + * This saves a few bits. + */ + for (i = num_counters ; i < num_controls ; ++i) { + if (CTRL_IS_RESERVED(msrs,i)) + release_evntsel_nmi(msrs->controls[i].addr); + } +} + #ifdef CONFIG_SMP struct op_x86_model_spec const op_p4_ht2_spec = { @@ -711,7 +705,8 @@ struct op_x86_model_spec const op_p4_ht2_spec = { .setup_ctrs = &p4_setup_ctrs, .check_ctrs = &p4_check_ctrs, .start = &p4_start, - .stop = &p4_stop + .stop = &p4_stop, + .shutdown = &p4_shutdown }; #endif @@ -722,5 +717,6 @@ struct op_x86_model_spec const op_p4_spec = { .setup_ctrs = &p4_setup_ctrs, .check_ctrs = &p4_check_ctrs, .start = &p4_start, - .stop = &p4_stop + .stop = &p4_stop, + .shutdown = &p4_shutdown }; diff --git a/arch/i386/oprofile/op_model_ppro.c b/arch/i386/oprofile/op_model_ppro.c index 5c3ab4b..f88e05b 100644 --- a/arch/i386/oprofile/op_model_ppro.c +++ b/arch/i386/oprofile/op_model_ppro.c @@ -22,10 +22,12 @@ #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_WRITE(l,msrs,c) do {wrmsr(msrs->counters[(c)].addr, -(u32)(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_SET_ACTIVE(n) (n |= (1<<22)) @@ -41,11 +43,21 @@ static unsigned long reset_value[NUM_COUNTERS]; static void ppro_fill_in_addresses(struct op_msrs * const msrs) { - msrs->counters[0].addr = MSR_P6_PERFCTR0; - msrs->counters[1].addr = MSR_P6_PERFCTR1; + int 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; + } - msrs->controls[0].addr = MSR_P6_EVNTSEL0; - msrs->controls[1].addr = MSR_P6_EVNTSEL1; + for (i=0; i < NUM_CONTROLS; i++) { + if (reserve_evntsel_nmi(MSR_P6_EVNTSEL0 + i)) + msrs->controls[i].addr = MSR_P6_EVNTSEL0 + i; + else + msrs->controls[i].addr = 0; + } } @@ -56,6 +68,8 @@ 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))) + continue; CTRL_READ(low, high, msrs, i); CTRL_CLEAR(low); CTRL_WRITE(low, high, msrs, i); @@ -63,12 +77,14 @@ static void ppro_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))) + continue; CTR_WRITE(1, msrs, i); } /* enable active counters */ for (i = 0; i < NUM_COUNTERS; ++i) { - if (counter_config[i].enabled) { + 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); @@ -81,6 +97,8 @@ static void ppro_setup_ctrs(struct op_msrs const * const msrs) CTRL_SET_UM(low, counter_config[i].unit_mask); CTRL_SET_EVENT(low, counter_config[i].event); CTRL_WRITE(low, high, msrs, i); + } else { + reset_value[i] = 0; } } } @@ -93,6 +111,8 @@ static int ppro_check_ctrs(struct pt_regs * const regs, int i; for (i = 0 ; i < NUM_COUNTERS; ++i) { + if (!reset_value[i]) + continue; CTR_READ(low, high, msrs, i); if (CTR_OVERFLOWED(low)) { oprofile_add_sample(regs, i); @@ -118,18 +138,38 @@ static int ppro_check_ctrs(struct pt_regs * const regs, static void ppro_start(struct op_msrs const * const msrs) { unsigned int low,high; - CTRL_READ(low, high, msrs, 0); - CTRL_SET_ACTIVE(low); - CTRL_WRITE(low, high, msrs, 0); + + if (reset_value[0]) { + CTRL_READ(low, high, msrs, 0); + CTRL_SET_ACTIVE(low); + CTRL_WRITE(low, high, msrs, 0); + } } static void ppro_stop(struct op_msrs const * const msrs) { unsigned int low,high; - CTRL_READ(low, high, msrs, 0); - CTRL_SET_INACTIVE(low); - CTRL_WRITE(low, high, msrs, 0); + + if (reset_value[0]) { + CTRL_READ(low, high, msrs, 0); + CTRL_SET_INACTIVE(low); + CTRL_WRITE(low, high, msrs, 0); + } +} + +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)) + release_perfctr_nmi(MSR_P6_PERFCTR0 + i); + } + for (i = 0 ; i < NUM_CONTROLS ; ++i) { + if (CTRL_IS_RESERVED(msrs,i)) + release_evntsel_nmi(MSR_P6_EVNTSEL0 + i); + } } @@ -140,5 +180,6 @@ struct op_x86_model_spec const op_ppro_spec = { .setup_ctrs = &ppro_setup_ctrs, .check_ctrs = &ppro_check_ctrs, .start = &ppro_start, - .stop = &ppro_stop + .stop = &ppro_stop, + .shutdown = &ppro_shutdown }; diff --git a/arch/i386/oprofile/op_x86_model.h b/arch/i386/oprofile/op_x86_model.h index 123b7e9..abb1aa9 100644 --- a/arch/i386/oprofile/op_x86_model.h +++ b/arch/i386/oprofile/op_x86_model.h @@ -40,6 +40,7 @@ struct op_x86_model_spec { struct op_msrs const * const msrs); void (*start)(struct op_msrs const * const msrs); void (*stop)(struct op_msrs const * const msrs); + void (*shutdown)(struct op_msrs const * const msrs); }; extern struct op_x86_model_spec const op_ppro_spec; diff --git a/arch/i386/pci/Makefile b/arch/i386/pci/Makefile index 62ad75c..1594d2f 100644 --- a/arch/i386/pci/Makefile +++ b/arch/i386/pci/Makefile @@ -11,4 +11,4 @@ pci-y += legacy.o irq.o pci-$(CONFIG_X86_VISWS) := visws.o fixup.o pci-$(CONFIG_X86_NUMAQ) := numa.o irq.o -obj-y += $(pci-y) common.o +obj-y += $(pci-y) common.o early.o diff --git a/arch/i386/pci/common.c b/arch/i386/pci/common.c index 0a362e3..68bce194 100644 --- a/arch/i386/pci/common.c +++ b/arch/i386/pci/common.c @@ -242,6 +242,10 @@ char * __devinit pcibios_setup(char *str) acpi_noirq_set(); return NULL; } + else if (!strcmp(str, "noearly")) { + pci_probe |= PCI_PROBE_NOEARLY; + return NULL; + } #ifndef CONFIG_X86_VISWS else if (!strcmp(str, "usepirqmask")) { pci_probe |= PCI_USE_PIRQ_MASK; diff --git a/arch/i386/pci/direct.c b/arch/i386/pci/direct.c index 5d81fb5..5acf0b4 100644 --- a/arch/i386/pci/direct.c +++ b/arch/i386/pci/direct.c @@ -254,7 +254,16 @@ static int __init pci_check_type2(void) return works; } -void __init pci_direct_init(void) +void __init pci_direct_init(int type) +{ + printk(KERN_INFO "PCI: Using configuration type %d\n", type); + if (type == 1) + raw_pci_ops = &pci_direct_conf1; + else + raw_pci_ops = &pci_direct_conf2; +} + +int __init pci_direct_probe(void) { struct resource *region, *region2; @@ -264,19 +273,16 @@ void __init pci_direct_init(void) if (!region) goto type2; - if (pci_check_type1()) { - printk(KERN_INFO "PCI: Using configuration type 1\n"); - raw_pci_ops = &pci_direct_conf1; - return; - } + if (pci_check_type1()) + return 1; release_resource(region); type2: if ((pci_probe & PCI_PROBE_CONF2) == 0) - return; + return 0; region = request_region(0xCF8, 4, "PCI conf2"); if (!region) - return; + return 0; region2 = request_region(0xC000, 0x1000, "PCI conf2"); if (!region2) goto fail2; @@ -284,10 +290,11 @@ void __init pci_direct_init(void) if (pci_check_type2()) { printk(KERN_INFO "PCI: Using configuration type 2\n"); raw_pci_ops = &pci_direct_conf2; - return; + return 2; } release_resource(region2); fail2: release_resource(region); + return 0; } diff --git a/arch/i386/pci/early.c b/arch/i386/pci/early.c new file mode 100644 index 0000000..713d6c8 --- /dev/null +++ b/arch/i386/pci/early.c @@ -0,0 +1,52 @@ +#include <linux/kernel.h> +#include <linux/pci.h> +#include <asm/pci-direct.h> +#include <asm/io.h> +#include "pci.h" + +/* Direct PCI access. This is used for PCI accesses in early boot before + the PCI subsystem works. */ + +#define PDprintk(x...) + +u32 read_pci_config(u8 bus, u8 slot, u8 func, u8 offset) +{ + u32 v; + outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8); + v = inl(0xcfc); + if (v != 0xffffffff) + PDprintk("%x reading 4 from %x: %x\n", slot, offset, v); + return v; +} + +u8 read_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset) +{ + u8 v; + outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8); + v = inb(0xcfc + (offset&3)); + PDprintk("%x reading 1 from %x: %x\n", slot, offset, v); + return v; +} + +u16 read_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset) +{ + u16 v; + outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8); + v = inw(0xcfc + (offset&2)); + PDprintk("%x reading 2 from %x: %x\n", slot, offset, v); + return v; +} + +void write_pci_config(u8 bus, u8 slot, u8 func, u8 offset, + u32 val) +{ + PDprintk("%x writing to %x: %x\n", slot, offset, val); + outl(0x80000000 | (bus<<16) | (slot<<11) | (func<<8) | offset, 0xcf8); + outl(val, 0xcfc); +} + +int early_pci_allowed(void) +{ + return (pci_probe & (PCI_PROBE_CONF1|PCI_PROBE_NOEARLY)) == + PCI_PROBE_CONF1; +} diff --git a/arch/i386/pci/init.c b/arch/i386/pci/init.c index 51087a9..d028e1b 100644 --- a/arch/i386/pci/init.c +++ b/arch/i386/pci/init.c @@ -6,8 +6,13 @@ in the right sequence from here. */ static __init int pci_access_init(void) { + int type = 0; + +#ifdef CONFIG_PCI_DIRECT + type = pci_direct_probe(); +#endif #ifdef CONFIG_PCI_MMCONFIG - pci_mmcfg_init(); + pci_mmcfg_init(type); #endif if (raw_pci_ops) return 0; @@ -21,7 +26,7 @@ static __init int pci_access_init(void) * fails. */ #ifdef CONFIG_PCI_DIRECT - pci_direct_init(); + pci_direct_init(type); #endif return 0; } diff --git a/arch/i386/pci/mmconfig.c b/arch/i386/pci/mmconfig.c index 972180f..05be8db 100644 --- a/arch/i386/pci/mmconfig.c +++ b/arch/i386/pci/mmconfig.c @@ -151,6 +151,38 @@ static struct pci_raw_ops pci_mmcfg = { .write = pci_mmcfg_write, }; + +static __init void pci_mmcfg_insert_resources(void) +{ +#define PCI_MMCFG_RESOURCE_NAME_LEN 19 + int i; + struct resource *res; + char *names; + unsigned num_buses; + + res = kcalloc(PCI_MMCFG_RESOURCE_NAME_LEN + sizeof(*res), + pci_mmcfg_config_num, GFP_KERNEL); + + if (!res) { + printk(KERN_ERR "PCI: Unable to allocate MMCONFIG resources\n"); + return; + } + + names = (void *)&res[pci_mmcfg_config_num]; + for (i = 0; i < pci_mmcfg_config_num; i++, res++) { + num_buses = pci_mmcfg_config[i].end_bus_number - + pci_mmcfg_config[i].start_bus_number + 1; + res->name = names; + snprintf(names, PCI_MMCFG_RESOURCE_NAME_LEN, "PCI MMCONFIG %u", + pci_mmcfg_config[i].pci_segment_group_number); + res->start = pci_mmcfg_config[i].base_address; + res->end = res->start + (num_buses << 20) - 1; + res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + insert_resource(&iomem_resource, res); + names += PCI_MMCFG_RESOURCE_NAME_LEN; + } +} + /* K8 systems have some devices (typically in the builtin northbridge) that are only accessible using type1 Normally this can be expressed in the MCFG by not listing them @@ -187,7 +219,9 @@ static __init void unreachable_devices(void) } } -void __init pci_mmcfg_init(void) + + +void __init pci_mmcfg_init(int type) { if ((pci_probe & PCI_PROBE_MMCONF) == 0) return; @@ -198,7 +232,9 @@ void __init pci_mmcfg_init(void) (pci_mmcfg_config[0].base_address == 0)) return; - if (!e820_all_mapped(pci_mmcfg_config[0].base_address, + /* 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(pci_mmcfg_config[0].base_address, pci_mmcfg_config[0].base_address + MMCONFIG_APER_MIN, E820_RESERVED)) { printk(KERN_ERR "PCI: BIOS Bug: MCFG area at %x is not E820-reserved\n", @@ -212,4 +248,5 @@ void __init pci_mmcfg_init(void) pci_probe = (pci_probe & ~PCI_PROBE_MASK) | PCI_PROBE_MMCONF; unreachable_devices(); + pci_mmcfg_insert_resources(); } diff --git a/arch/i386/pci/pci.h b/arch/i386/pci/pci.h index bf4e793..1814f74 100644 --- a/arch/i386/pci/pci.h +++ b/arch/i386/pci/pci.h @@ -17,6 +17,7 @@ #define PCI_PROBE_CONF2 0x0004 #define PCI_PROBE_MMCONF 0x0008 #define PCI_PROBE_MASK 0x000f +#define PCI_PROBE_NOEARLY 0x0010 #define PCI_NO_SORT 0x0100 #define PCI_BIOS_SORT 0x0200 @@ -81,7 +82,9 @@ extern int pci_conf1_write(unsigned int seg, unsigned int bus, extern int pci_conf1_read(unsigned int seg, unsigned int bus, unsigned int devfn, int reg, int len, u32 *value); -extern void pci_direct_init(void); +extern int pci_direct_probe(void); +extern void pci_direct_init(int type); extern void pci_pcbios_init(void); -extern void pci_mmcfg_init(void); +extern void pci_mmcfg_init(int type); extern void pcibios_sort(void); + diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c index de83f38..d9428a0 100644 --- a/arch/s390/kernel/stacktrace.c +++ b/arch/s390/kernel/stacktrace.c @@ -59,9 +59,7 @@ static inline unsigned long save_context_stack(struct stack_trace *trace, } } -void save_stack_trace(struct stack_trace *trace, - struct task_struct *task, int all_contexts, - unsigned int skip) +void save_stack_trace(struct stack_trace *trace, struct task_struct *task) { register unsigned long sp asm ("15"); unsigned long orig_sp; @@ -69,22 +67,23 @@ void save_stack_trace(struct stack_trace *trace, sp &= PSW_ADDR_INSN; orig_sp = sp; - sp = save_context_stack(trace, &skip, sp, + sp = save_context_stack(trace, &trace->skip, sp, S390_lowcore.panic_stack - PAGE_SIZE, S390_lowcore.panic_stack); - if ((sp != orig_sp) && !all_contexts) + if ((sp != orig_sp) && !trace->all_contexts) return; - sp = save_context_stack(trace, &skip, sp, + sp = save_context_stack(trace, &trace->skip, sp, S390_lowcore.async_stack - ASYNC_SIZE, S390_lowcore.async_stack); - if ((sp != orig_sp) && !all_contexts) + if ((sp != orig_sp) && !trace->all_contexts) return; if (task) - save_context_stack(trace, &skip, sp, + save_context_stack(trace, &trace->skip, sp, (unsigned long) task_stack_page(task), (unsigned long) task_stack_page(task) + THREAD_SIZE); else - save_context_stack(trace, &skip, sp, S390_lowcore.thread_info, + save_context_stack(trace, &trace->skip, sp, + S390_lowcore.thread_info, S390_lowcore.thread_info + THREAD_SIZE); return; } diff --git a/arch/um/sys-i386/Makefile b/arch/um/sys-i386/Makefile index 59cc702..0e32adf 100644 --- a/arch/um/sys-i386/Makefile +++ b/arch/um/sys-i386/Makefile @@ -4,7 +4,7 @@ obj-y = bugs.o checksum.o delay.o fault.o ksyms.o ldt.o ptrace.o \ obj-$(CONFIG_MODE_SKAS) += stub.o stub_segv.o -subarch-obj-y = lib/bitops.o kernel/semaphore.o +subarch-obj-y = lib/bitops.o lib/semaphore.o subarch-obj-$(CONFIG_HIGHMEM) += mm/highmem.o subarch-obj-$(CONFIG_MODULES) += kernel/module.o diff --git a/arch/x86_64/Kconfig b/arch/x86_64/Kconfig index 581ce9a..efe249e 100644 --- a/arch/x86_64/Kconfig +++ b/arch/x86_64/Kconfig @@ -109,6 +109,7 @@ config X86_PC config X86_VSMP bool "Support for ScaleMP vSMP" + depends on PCI help Support for ScaleMP vSMP systems. Say 'Y' here if this kernel is supposed to run on these EM64T-based machines. Only choose this option @@ -295,7 +296,7 @@ config NUMA config K8_NUMA bool "Old style AMD Opteron NUMA detection" - depends on NUMA + depends on NUMA && PCI default y help Enable K8 NUMA node topology detection. You should say Y here if @@ -425,7 +426,6 @@ config IOMMU config CALGARY_IOMMU bool "IBM Calgary IOMMU support" - default y select SWIOTLB depends on PCI && EXPERIMENTAL help @@ -472,8 +472,7 @@ config X86_MCE_AMD the DRAM Error Threshold. config KEXEC - bool "kexec system call (EXPERIMENTAL)" - depends on EXPERIMENTAL + bool "kexec system call" 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 @@ -492,7 +491,14 @@ config CRASH_DUMP bool "kernel crash dumps (EXPERIMENTAL)" depends on EXPERIMENTAL help - Generate crash dump after being started by kexec. + Generate crash dump after being started by kexec. + This should be normally only set in special crash dump kernels + which are loaded in the main kernel with kexec-tools into + a specially reserved region and then later executed after + a crash by kdump/kexec. The crash dump kernel must be compiled + to a memory address not used by the main kernel or BIOS using + PHYSICAL_START. + For more details see Documentation/kdump/kdump.txt config PHYSICAL_START hex "Physical address where the kernel is loaded" if (EMBEDDED || CRASH_DUMP) @@ -530,6 +536,30 @@ config SECCOMP If unsure, say Y. Only embedded should say N here. +config CC_STACKPROTECTOR + bool "Enable -fstack-protector buffer overflow detection (EXPRIMENTAL)" + depends on EXPERIMENTAL + help + This option turns on the -fstack-protector GCC feature. This + feature puts, at the beginning of critical functions, a canary + value on the stack just before the return address, and validates + the value just before actually returning. Stack based buffer + overflows (that need to overwrite this return address) now also + overwrite the canary, which gets detected and the attack is then + neutralized via a kernel panic. + + This feature requires gcc version 4.2 or above, or a distribution + gcc with the feature backported. Older versions are automatically + detected and for those versions, this configuration option is ignored. + +config CC_STACKPROTECTOR_ALL + bool "Use stack-protector for all functions" + depends on CC_STACKPROTECTOR + help + Normally, GCC only inserts the canary value protection for + functions that use large-ish on-stack buffers. By enabling + this option, GCC will be asked to do this for ALL functions. + source kernel/Kconfig.hz config REORDER diff --git a/arch/x86_64/Makefile b/arch/x86_64/Makefile index 431bb4b..1c0f18d 100644 --- a/arch/x86_64/Makefile +++ b/arch/x86_64/Makefile @@ -54,6 +54,16 @@ endif cflags-y += $(call cc-option,-funit-at-a-time) # prevent gcc from generating any FP code by mistake cflags-y += $(call cc-option,-mno-sse -mno-mmx -mno-sse2 -mno-3dnow,) +# do binutils support CFI? +cflags-y += $(call as-instr,.cfi_startproc\n.cfi_endproc,-DCONFIG_AS_CFI=1,) +AFLAGS += $(call as-instr,.cfi_startproc\n.cfi_endproc,-DCONFIG_AS_CFI=1,) + +# is .cfi_signal_frame supported too? +cflags-y += $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1,) +AFLAGS += $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1,) + +cflags-$(CONFIG_CC_STACKPROTECTOR) += $(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-x86_64-has-stack-protector.sh $(CC) -fstack-protector ) +cflags-$(CONFIG_CC_STACKPROTECTOR_ALL) += $(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-x86_64-has-stack-protector.sh $(CC) -fstack-protector-all ) CFLAGS += $(cflags-y) CFLAGS_KERNEL += $(cflags-kernel-y) diff --git a/arch/x86_64/boot/compressed/Makefile b/arch/x86_64/boot/compressed/Makefile index f89d96f..e70fa6e 100644 --- a/arch/x86_64/boot/compressed/Makefile +++ b/arch/x86_64/boot/compressed/Makefile @@ -7,7 +7,8 @@ # targets := vmlinux vmlinux.bin vmlinux.bin.gz head.o misc.o piggy.o -EXTRA_AFLAGS := -traditional -m32 +EXTRA_AFLAGS := -traditional +AFLAGS := $(subst -m64,-m32,$(AFLAGS)) # cannot use EXTRA_CFLAGS because base CFLAGS contains -mkernel which conflicts with # -m32 diff --git a/arch/x86_64/boot/setup.S b/arch/x86_64/boot/setup.S index a50b631..c3bfd22 100644 --- a/arch/x86_64/boot/setup.S +++ b/arch/x86_64/boot/setup.S @@ -526,12 +526,12 @@ is_disk1: movw %cs, %ax # aka SETUPSEG subw $DELTA_INITSEG, %ax # aka INITSEG movw %ax, %ds - movw $0, (0x1ff) # default is no pointing device + movb $0, (0x1ff) # default is no pointing device int $0x11 # int 0x11: equipment list testb $0x04, %al # check if mouse installed jz no_psmouse - movw $0xAA, (0x1ff) # device present + movb $0xAA, (0x1ff) # device present no_psmouse: #include "../../i386/boot/edd.S" diff --git a/arch/x86_64/defconfig b/arch/x86_64/defconfig index 5fb9707..647610e 100644 --- a/arch/x86_64/defconfig +++ b/arch/x86_64/defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.18-rc4 -# Thu Aug 24 21:05:55 2006 +# Linux kernel version: 2.6.18-git5 +# Tue Sep 26 09:30:47 2006 # CONFIG_X86_64=y CONFIG_64BIT=y @@ -19,6 +19,7 @@ CONFIG_GENERIC_ISA_DMA=y CONFIG_GENERIC_IOMAP=y CONFIG_ARCH_MAY_HAVE_PC_FDC=y CONFIG_DMI=y +CONFIG_AUDIT_ARCH=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -38,16 +39,16 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y # CONFIG_BSD_PROCESS_ACCT is not set # CONFIG_TASKSTATS is not set -CONFIG_SYSCTL=y # CONFIG_AUDIT is not set CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y # CONFIG_CPUSETS is not set # CONFIG_RELAY is not set CONFIG_INITRAMFS_SOURCE="" -CONFIG_UID16=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_EMBEDDED is not set +CONFIG_UID16=y +CONFIG_SYSCTL=y CONFIG_KALLSYMS=y CONFIG_KALLSYMS_ALL=y # CONFIG_KALLSYMS_EXTRA_PASS is not set @@ -56,12 +57,12 @@ CONFIG_PRINTK=y CONFIG_BUG=y CONFIG_ELF_CORE=y CONFIG_BASE_FULL=y -CONFIG_RT_MUTEXES=y CONFIG_FUTEX=y CONFIG_EPOLL=y CONFIG_SHMEM=y CONFIG_SLAB=y CONFIG_VM_EVENT_COUNTERS=y +CONFIG_RT_MUTEXES=y # CONFIG_TINY_SHMEM is not set CONFIG_BASE_SMALL=0 # CONFIG_SLOB is not set @@ -160,6 +161,7 @@ CONFIG_X86_MCE_AMD=y # CONFIG_CRASH_DUMP is not set CONFIG_PHYSICAL_START=0x200000 CONFIG_SECCOMP=y +# CONFIG_CC_STACKPROTECTOR is not set # CONFIG_HZ_100 is not set CONFIG_HZ_250=y # CONFIG_HZ_1000 is not set @@ -307,18 +309,23 @@ CONFIG_IP_PNP_DHCP=y CONFIG_INET_DIAG=y CONFIG_INET_TCP_DIAG=y # CONFIG_TCP_CONG_ADVANCED is not set -CONFIG_TCP_CONG_BIC=y +CONFIG_TCP_CONG_CUBIC=y +CONFIG_DEFAULT_TCP_CONG="cubic" CONFIG_IPV6=y # CONFIG_IPV6_PRIVACY is not set # CONFIG_IPV6_ROUTER_PREF is not set # CONFIG_INET6_AH is not set # CONFIG_INET6_ESP is not set # CONFIG_INET6_IPCOMP is not set +# CONFIG_IPV6_MIP6 is not set # CONFIG_INET6_XFRM_TUNNEL is not set # CONFIG_INET6_TUNNEL is not set # CONFIG_INET6_XFRM_MODE_TRANSPORT is not set # CONFIG_INET6_XFRM_MODE_TUNNEL is not set +# CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION is not set # CONFIG_IPV6_TUNNEL is not set +# CONFIG_IPV6_SUBTREES is not set +# CONFIG_IPV6_MULTIPLE_TABLES is not set # CONFIG_NETWORK_SECMARK is not set # CONFIG_NETFILTER is not set @@ -345,7 +352,6 @@ CONFIG_IPV6=y # CONFIG_ATALK is not set # CONFIG_X25 is not set # CONFIG_LAPB is not set -# CONFIG_NET_DIVERT is not set # CONFIG_ECONET is not set # CONFIG_WAN_ROUTER is not set @@ -487,6 +493,7 @@ CONFIG_IDEDMA_AUTO=y # # CONFIG_RAID_ATTRS is not set CONFIG_SCSI=y +CONFIG_SCSI_NETLINK=y # CONFIG_SCSI_PROC_FS is not set # @@ -508,12 +515,13 @@ CONFIG_SCSI_CONSTANTS=y # CONFIG_SCSI_LOGGING is not set # -# SCSI Transport Attributes +# SCSI Transports # CONFIG_SCSI_SPI_ATTRS=y CONFIG_SCSI_FC_ATTRS=y # CONFIG_SCSI_ISCSI_ATTRS is not set CONFIG_SCSI_SAS_ATTRS=y +# CONFIG_SCSI_SAS_LIBSAS is not set # # SCSI low-level drivers @@ -532,29 +540,14 @@ CONFIG_AIC79XX_RESET_DELAY_MS=4000 # CONFIG_AIC79XX_DEBUG_ENABLE is not set CONFIG_AIC79XX_DEBUG_MASK=0 # CONFIG_AIC79XX_REG_PRETTY_PRINT is not set +# CONFIG_SCSI_AIC94XX is not set +# CONFIG_SCSI_ARCMSR is not set CONFIG_MEGARAID_NEWGEN=y CONFIG_MEGARAID_MM=y CONFIG_MEGARAID_MAILBOX=y # CONFIG_MEGARAID_LEGACY is not set CONFIG_MEGARAID_SAS=y -CONFIG_SCSI_SATA=y -CONFIG_SCSI_SATA_AHCI=y -CONFIG_SCSI_SATA_SVW=y -CONFIG_SCSI_ATA_PIIX=y -# CONFIG_SCSI_SATA_MV is not set -CONFIG_SCSI_SATA_NV=y -# CONFIG_SCSI_PDC_ADMA is not set # CONFIG_SCSI_HPTIOP is not set -# CONFIG_SCSI_SATA_QSTOR is not set -# CONFIG_SCSI_SATA_PROMISE is not set -# CONFIG_SCSI_SATA_SX4 is not set -CONFIG_SCSI_SATA_SIL=y -# CONFIG_SCSI_SATA_SIL24 is not set -# CONFIG_SCSI_SATA_SIS is not set -# CONFIG_SCSI_SATA_ULI is not set -CONFIG_SCSI_SATA_VIA=y -# CONFIG_SCSI_SATA_VITESSE is not set -CONFIG_SCSI_SATA_INTEL_COMBINED=y # CONFIG_SCSI_BUSLOGIC is not set # CONFIG_SCSI_DMX3191D is not set # CONFIG_SCSI_EATA is not set @@ -563,6 +556,7 @@ CONFIG_SCSI_SATA_INTEL_COMBINED=y # CONFIG_SCSI_IPS is not set # CONFIG_SCSI_INITIO is not set # CONFIG_SCSI_INIA100 is not set +# CONFIG_SCSI_STEX is not set # CONFIG_SCSI_SYM53C8XX_2 is not set # CONFIG_SCSI_IPR is not set # CONFIG_SCSI_QLOGIC_1280 is not set @@ -573,6 +567,62 @@ CONFIG_SCSI_SATA_INTEL_COMBINED=y # CONFIG_SCSI_DEBUG is not set # +# Serial ATA (prod) and Parallel ATA (experimental) drivers +# +CONFIG_ATA=y +CONFIG_SATA_AHCI=y +CONFIG_SATA_SVW=y +CONFIG_ATA_PIIX=y +# CONFIG_SATA_MV is not set +CONFIG_SATA_NV=y +# CONFIG_PDC_ADMA is not set +# CONFIG_SATA_QSTOR is not set +# CONFIG_SATA_PROMISE is not set +# CONFIG_SATA_SX4 is not set +CONFIG_SATA_SIL=y +# CONFIG_SATA_SIL24 is not set +# CONFIG_SATA_SIS is not set +# CONFIG_SATA_ULI is not set +CONFIG_SATA_VIA=y +# CONFIG_SATA_VITESSE is not set +CONFIG_SATA_INTEL_COMBINED=y +# CONFIG_PATA_ALI is not set +# CONFIG_PATA_AMD is not set +# CONFIG_PATA_ARTOP is not set +# CONFIG_PATA_ATIIXP is not set +# CONFIG_PATA_CMD64X is not set +# CONFIG_PATA_CS5520 is not set +# CONFIG_PATA_CS5530 is not set +# CONFIG_PATA_CYPRESS is not set +# CONFIG_PATA_EFAR is not set +# CONFIG_ATA_GENERIC is not set +# CONFIG_PATA_HPT366 is not set +# CONFIG_PATA_HPT37X is not set +# CONFIG_PATA_HPT3X2N is not set +# CONFIG_PATA_HPT3X3 is not set +# CONFIG_PATA_IT821X is not set +# CONFIG_PATA_JMICRON is not set +# CONFIG_PATA_LEGACY is not set +# CONFIG_PATA_TRIFLEX is not set +# CONFIG_PATA_MPIIX is not set +# CONFIG_PATA_OLDPIIX is not set +# CONFIG_PATA_NETCELL is not set +# CONFIG_PATA_NS87410 is not set +# CONFIG_PATA_OPTI is not set +# CONFIG_PATA_OPTIDMA is not set +# CONFIG_PATA_PDC_OLD is not set +# CONFIG_PATA_QDI is not set +# CONFIG_PATA_RADISYS is not set +# CONFIG_PATA_RZ1000 is not set +# CONFIG_PATA_SC1200 is not set +# CONFIG_PATA_SERVERWORKS is not set +# CONFIG_PATA_PDC2027X is not set +# CONFIG_PATA_SIL680 is not set +# CONFIG_PATA_SIS is not set +# CONFIG_PATA_VIA is not set +# CONFIG_PATA_WINBOND is not set + +# # Multi-device support (RAID and LVM) # CONFIG_MD=y @@ -678,6 +728,7 @@ CONFIG_NET_PCI=y # CONFIG_ADAPTEC_STARFIRE is not set CONFIG_B44=y CONFIG_FORCEDETH=y +# CONFIG_FORCEDETH_NAPI is not set # CONFIG_DGRS is not set # CONFIG_EEPRO100 is not set CONFIG_E100=y @@ -714,6 +765,7 @@ CONFIG_E1000=y # CONFIG_VIA_VELOCITY is not set CONFIG_TIGON3=y CONFIG_BNX2=y +# CONFIG_QLA3XXX is not set # # Ethernet (10000 Mbit) @@ -1036,6 +1088,7 @@ CONFIG_SOUND=y # Open Sound System # CONFIG_SOUND_PRIME=y +CONFIG_OSS_OBSOLETE_DRIVER=y # CONFIG_SOUND_BT878 is not set # CONFIG_SOUND_EMU10K1 is not set # CONFIG_SOUND_FUSION is not set @@ -1046,7 +1099,6 @@ CONFIG_SOUND_ICH=y # CONFIG_SOUND_MSNDPIN is not set # CONFIG_SOUND_VIA82CXXX is not set # CONFIG_SOUND_OSS is not set -# CONFIG_SOUND_TVMIXER is not set # # USB support @@ -1203,7 +1255,6 @@ CONFIG_USB_MON=y # InfiniBand support # # CONFIG_INFINIBAND is not set -# CONFIG_IPATH_CORE is not set # # EDAC - error detection and reporting (RAS) (EXPERIMENTAL) @@ -1449,10 +1500,6 @@ CONFIG_DEBUG_STACKOVERFLOW=y # CONFIG_CRYPTO is not set # -# Hardware crypto devices -# - -# # Library routines # # CONFIG_CRC_CCITT is not set diff --git a/arch/x86_64/ia32/ia32_aout.c b/arch/x86_64/ia32/ia32_aout.c index 3bf58af..396d3c1 100644 --- a/arch/x86_64/ia32/ia32_aout.c +++ b/arch/x86_64/ia32/ia32_aout.c @@ -333,7 +333,8 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs) return error; } - error = bprm->file->f_op->read(bprm->file, (char *)text_addr, + error = bprm->file->f_op->read(bprm->file, + (char __user *)text_addr, ex.a_text+ex.a_data, &pos); if ((signed long)error < 0) { send_sig(SIGKILL, current, 0); @@ -366,7 +367,8 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs) down_write(¤t->mm->mmap_sem); do_brk(N_TXTADDR(ex), ex.a_text+ex.a_data); up_write(¤t->mm->mmap_sem); - bprm->file->f_op->read(bprm->file,(char *)N_TXTADDR(ex), + bprm->file->f_op->read(bprm->file, + (char __user *)N_TXTADDR(ex), ex.a_text+ex.a_data, &pos); flush_icache_range((unsigned long) N_TXTADDR(ex), (unsigned long) N_TXTADDR(ex) + @@ -477,7 +479,7 @@ static int load_aout_library(struct file *file) do_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss); up_write(¤t->mm->mmap_sem); - file->f_op->read(file, (char *)start_addr, + file->f_op->read(file, (char __user *)start_addr, ex.a_text + ex.a_data, &pos); flush_icache_range((unsigned long) start_addr, (unsigned long) start_addr + ex.a_text + ex.a_data); diff --git a/arch/x86_64/ia32/ia32_signal.c b/arch/x86_64/ia32/ia32_signal.c index 25e5ca2..a6ba995 100644 --- a/arch/x86_64/ia32/ia32_signal.c +++ b/arch/x86_64/ia32/ia32_signal.c @@ -113,25 +113,19 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) } asmlinkage long -sys32_sigsuspend(int history0, int history1, old_sigset_t mask, - struct pt_regs *regs) +sys32_sigsuspend(int history0, int history1, old_sigset_t mask) { - sigset_t saveset; - mask &= _BLOCKABLE; spin_lock_irq(¤t->sighand->siglock); - saveset = current->blocked; + current->saved_sigmask = current->blocked; siginitset(¤t->blocked, mask); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); - regs->rax = -EINTR; - while (1) { - current->state = TASK_INTERRUPTIBLE; - schedule(); - if (do_signal(regs, &saveset)) - return -EINTR; - } + current->state = TASK_INTERRUPTIBLE; + schedule(); + set_thread_flag(TIF_RESTORE_SIGMASK); + return -ERESTARTNOHAND; } asmlinkage long @@ -437,15 +431,7 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka, if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) goto give_sigsegv; - { - struct exec_domain *ed = current_thread_info()->exec_domain; - err |= __put_user((ed - && ed->signal_invmap - && sig < 32 - ? ed->signal_invmap[sig] - : sig), - &frame->sig); - } + err |= __put_user(sig, &frame->sig); if (err) goto give_sigsegv; @@ -492,6 +478,11 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka, regs->rsp = (unsigned long) frame; regs->rip = (unsigned long) ka->sa.sa_handler; + /* Make -mregparm=3 work */ + regs->rax = sig; + regs->rdx = 0; + regs->rcx = 0; + asm volatile("movl %0,%%ds" :: "r" (__USER32_DS)); asm volatile("movl %0,%%es" :: "r" (__USER32_DS)); @@ -499,20 +490,20 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka, regs->ss = __USER32_DS; set_fs(USER_DS); - regs->eflags &= ~TF_MASK; - if (test_thread_flag(TIF_SINGLESTEP)) - ptrace_notify(SIGTRAP); + regs->eflags &= ~TF_MASK; + 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->rip, frame->pretcode); #endif - return 1; + return 0; give_sigsegv: force_sigsegv(sig, current); - return 0; + return -EFAULT; } int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, @@ -595,18 +586,18 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, regs->ss = __USER32_DS; set_fs(USER_DS); - regs->eflags &= ~TF_MASK; - if (test_thread_flag(TIF_SINGLESTEP)) - ptrace_notify(SIGTRAP); + regs->eflags &= ~TF_MASK; + 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->rip, frame->pretcode); #endif - return 1; + return 0; give_sigsegv: force_sigsegv(sig, current); - return 0; + return -EFAULT; } diff --git a/arch/x86_64/ia32/ia32entry.S b/arch/x86_64/ia32/ia32entry.S index 5d4a7d1..b4aa875 100644 --- a/arch/x86_64/ia32/ia32entry.S +++ b/arch/x86_64/ia32/ia32entry.S @@ -71,6 +71,7 @@ */ ENTRY(ia32_sysenter_target) CFI_STARTPROC32 simple + CFI_SIGNAL_FRAME CFI_DEF_CFA rsp,0 CFI_REGISTER rsp,rbp swapgs @@ -186,6 +187,7 @@ ENDPROC(ia32_sysenter_target) */ ENTRY(ia32_cstar_target) CFI_STARTPROC32 simple + CFI_SIGNAL_FRAME CFI_DEF_CFA rsp,PDA_STACKOFFSET CFI_REGISTER rip,rcx /*CFI_REGISTER rflags,r11*/ @@ -293,6 +295,7 @@ ia32_badarg: ENTRY(ia32_syscall) CFI_STARTPROC simple + CFI_SIGNAL_FRAME CFI_DEF_CFA rsp,SS+8-RIP /*CFI_REL_OFFSET ss,SS-RIP*/ CFI_REL_OFFSET rsp,RSP-RIP @@ -370,6 +373,7 @@ ENTRY(ia32_ptregs_common) popq %r11 CFI_ENDPROC CFI_STARTPROC32 simple + CFI_SIGNAL_FRAME CFI_DEF_CFA rsp,SS+8-ARGOFFSET CFI_REL_OFFSET rax,RAX-ARGOFFSET CFI_REL_OFFSET rcx,RCX-ARGOFFSET @@ -703,8 +707,8 @@ ia32_sys_call_table: .quad sys_readlinkat /* 305 */ .quad sys_fchmodat .quad sys_faccessat - .quad quiet_ni_syscall /* pselect6 for now */ - .quad quiet_ni_syscall /* ppoll for now */ + .quad compat_sys_pselect6 + .quad compat_sys_ppoll .quad sys_unshare /* 310 */ .quad compat_sys_set_robust_list .quad compat_sys_get_robust_list @@ -713,4 +717,5 @@ ia32_sys_call_table: .quad sys_tee .quad compat_sys_vmsplice .quad compat_sys_move_pages + .quad sys_getcpu ia32_syscall_end: diff --git a/arch/x86_64/ia32/ptrace32.c b/arch/x86_64/ia32/ptrace32.c index 659c072..d18198e 100644 --- a/arch/x86_64/ia32/ptrace32.c +++ b/arch/x86_64/ia32/ptrace32.c @@ -117,6 +117,10 @@ static int putreg32(struct task_struct *child, unsigned regno, u32 val) if ((0x5454 >> ((val >> (16 + 4*i)) & 0xf)) & 1) return -EIO; child->thread.debugreg7 = val; + if (val) + set_tsk_thread_flag(child, TIF_DEBUG); + else + clear_tsk_thread_flag(child, TIF_DEBUG); break; default: @@ -371,8 +375,10 @@ asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data) ret = -EIO; if (!access_ok(VERIFY_READ, u, sizeof(*u))) break; - /* no checking to be bug-to-bug compatible with i386 */ - __copy_from_user(&child->thread.i387.fxsave, u, sizeof(*u)); + /* no checking to be bug-to-bug compatible with i386. */ + /* but silence warning */ + if (__copy_from_user(&child->thread.i387.fxsave, u, sizeof(*u))) + ; set_stopped_child_used_math(child); child->thread.i387.fxsave.mxcsr &= mxcsr_feature_mask; ret = 0; diff --git a/arch/x86_64/ia32/sys_ia32.c b/arch/x86_64/ia32/sys_ia32.c index 9c13099..b0e82c7 100644 --- a/arch/x86_64/ia32/sys_ia32.c +++ b/arch/x86_64/ia32/sys_ia32.c @@ -60,6 +60,7 @@ #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> @@ -389,7 +390,9 @@ sys32_rt_sigprocmask(int how, compat_sigset_t __user *set, } } set_fs (KERNEL_DS); - ret = sys_rt_sigprocmask(how, set ? &s : NULL, oset ? &s : NULL, + ret = sys_rt_sigprocmask(how, + set ? (sigset_t __user *)&s : NULL, + oset ? (sigset_t __user *)&s : NULL, sigsetsize); set_fs (old_fs); if (ret) return ret; @@ -541,7 +544,7 @@ sys32_sysinfo(struct sysinfo32 __user *info) int bitcount = 0; set_fs (KERNEL_DS); - ret = sys_sysinfo(&s); + ret = sys_sysinfo((struct sysinfo __user *)&s); set_fs (old_fs); /* Check to see if any memory value is too large for 32-bit and scale @@ -589,7 +592,7 @@ sys32_sched_rr_get_interval(compat_pid_t pid, struct compat_timespec __user *int mm_segment_t old_fs = get_fs (); set_fs (KERNEL_DS); - ret = sys_sched_rr_get_interval(pid, &t); + ret = sys_sched_rr_get_interval(pid, (struct timespec __user *)&t); set_fs (old_fs); if (put_compat_timespec(&t, interval)) return -EFAULT; @@ -605,7 +608,7 @@ sys32_rt_sigpending(compat_sigset_t __user *set, compat_size_t sigsetsize) mm_segment_t old_fs = get_fs(); set_fs (KERNEL_DS); - ret = sys_rt_sigpending(&s, sigsetsize); + ret = sys_rt_sigpending((sigset_t __user *)&s, sigsetsize); set_fs (old_fs); if (!ret) { switch (_NSIG_WORDS) { @@ -630,7 +633,7 @@ sys32_rt_sigqueueinfo(int pid, int sig, compat_siginfo_t __user *uinfo) if (copy_siginfo_from_user32(&info, uinfo)) return -EFAULT; set_fs (KERNEL_DS); - ret = sys_rt_sigqueueinfo(pid, sig, &info); + ret = sys_rt_sigqueueinfo(pid, sig, (siginfo_t __user *)&info); set_fs (old_fs); return ret; } @@ -666,9 +669,6 @@ sys32_sysctl(struct sysctl_ia32 __user *args32) size_t oldlen; int __user *namep; long ret; - extern int do_sysctl(int *name, int nlen, void *oldval, size_t *oldlenp, - void *newval, size_t newlen); - if (copy_from_user(&a32, args32, sizeof (a32))) return -EFAULT; @@ -692,7 +692,8 @@ sys32_sysctl(struct sysctl_ia32 __user *args32) set_fs(KERNEL_DS); lock_kernel(); - ret = do_sysctl(namep, a32.nlen, oldvalp, &oldlen, newvalp, (size_t) a32.newlen); + ret = do_sysctl(namep, a32.nlen, oldvalp, (size_t __user *)&oldlen, + newvalp, (size_t) a32.newlen); unlock_kernel(); set_fs(old_fs); @@ -743,7 +744,8 @@ sys32_sendfile(int out_fd, int in_fd, compat_off_t __user *offset, s32 count) return -EFAULT; set_fs(KERNEL_DS); - ret = sys_sendfile(out_fd, in_fd, offset ? &of : NULL, count); + ret = sys_sendfile(out_fd, in_fd, offset ? (off_t __user *)&of : NULL, + count); set_fs(old_fs); if (offset && put_user(of, offset)) @@ -778,7 +780,7 @@ asmlinkage long sys32_mmap2(unsigned long addr, unsigned long len, asmlinkage long sys32_olduname(struct oldold_utsname __user * name) { - int error; + int err; if (!name) return -EFAULT; @@ -787,27 +789,31 @@ asmlinkage long sys32_olduname(struct oldold_utsname __user * name) down_read(&uts_sem); - error = __copy_to_user(&name->sysname,&system_utsname.sysname,__OLD_UTS_LEN); - __put_user(0,name->sysname+__OLD_UTS_LEN); - __copy_to_user(&name->nodename,&system_utsname.nodename,__OLD_UTS_LEN); - __put_user(0,name->nodename+__OLD_UTS_LEN); - __copy_to_user(&name->release,&system_utsname.release,__OLD_UTS_LEN); - __put_user(0,name->release+__OLD_UTS_LEN); - __copy_to_user(&name->version,&system_utsname.version,__OLD_UTS_LEN); - __put_user(0,name->version+__OLD_UTS_LEN); + err = __copy_to_user(&name->sysname,&system_utsname.sysname, + __OLD_UTS_LEN); + err |= __put_user(0,name->sysname+__OLD_UTS_LEN); + err |= __copy_to_user(&name->nodename,&system_utsname.nodename, + __OLD_UTS_LEN); + err |= __put_user(0,name->nodename+__OLD_UTS_LEN); + err |= __copy_to_user(&name->release,&system_utsname.release, + __OLD_UTS_LEN); + err |= __put_user(0,name->release+__OLD_UTS_LEN); + err |= __copy_to_user(&name->version,&system_utsname.version, + __OLD_UTS_LEN); + err |= __put_user(0,name->version+__OLD_UTS_LEN); { char *arch = "x86_64"; if (personality(current->personality) == PER_LINUX32) arch = "i686"; - __copy_to_user(&name->machine,arch,strlen(arch)+1); + err |= __copy_to_user(&name->machine,arch,strlen(arch)+1); } up_read(&uts_sem); - error = error ? -EFAULT : 0; + err = err ? -EFAULT : 0; - return error; + return err; } long sys32_uname(struct old_utsname __user * name) @@ -831,7 +837,7 @@ long sys32_ustat(unsigned dev, struct ustat32 __user *u32p) seg = get_fs(); set_fs(KERNEL_DS); - ret = sys_ustat(dev,&u); + ret = sys_ustat(dev, (struct ustat __user *)&u); set_fs(seg); if (ret >= 0) { if (!access_ok(VERIFY_WRITE,u32p,sizeof(struct ustat32)) || diff --git a/arch/x86_64/kernel/Makefile b/arch/x86_64/kernel/Makefile index b5aaeaf..3c7cbff 100644 --- a/arch/x86_64/kernel/Makefile +++ b/arch/x86_64/kernel/Makefile @@ -11,7 +11,7 @@ obj-y := process.o signal.o entry.o traps.o irq.o \ pci-dma.o pci-nommu.o alternative.o obj-$(CONFIG_STACKTRACE) += stacktrace.o -obj-$(CONFIG_X86_MCE) += mce.o +obj-$(CONFIG_X86_MCE) += mce.o therm_throt.o obj-$(CONFIG_X86_MCE_INTEL) += mce_intel.o obj-$(CONFIG_X86_MCE_AMD) += mce_amd.o obj-$(CONFIG_MTRR) += ../../i386/kernel/cpu/mtrr/ @@ -20,8 +20,8 @@ obj-$(CONFIG_X86_MSR) += msr.o obj-$(CONFIG_MICROCODE) += microcode.o obj-$(CONFIG_X86_CPUID) += cpuid.o obj-$(CONFIG_SMP) += smp.o smpboot.o trampoline.o -obj-$(CONFIG_X86_LOCAL_APIC) += apic.o nmi.o -obj-$(CONFIG_X86_IO_APIC) += io_apic.o mpparse.o \ +obj-y += apic.o nmi.o +obj-y += io_apic.o mpparse.o \ genapic.o genapic_cluster.o genapic_flat.o obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o @@ -39,12 +39,14 @@ obj-$(CONFIG_K8_NB) += k8.o obj-$(CONFIG_AUDIT) += audit.o obj-$(CONFIG_MODULES) += module.o +obj-$(CONFIG_PCI) += early-quirks.o obj-y += topology.o obj-y += intel_cacheinfo.o CFLAGS_vsyscall.o := $(PROFILING) -g0 +therm_throt-y += ../../i386/kernel/cpu/mcheck/therm_throt.o bootflag-y += ../../i386/kernel/bootflag.o cpuid-$(subst m,y,$(CONFIG_X86_CPUID)) += ../../i386/kernel/cpuid.o topology-y += ../../i386/kernel/topology.o @@ -54,4 +56,3 @@ quirks-y += ../../i386/kernel/quirks.o i8237-y += ../../i386/kernel/i8237.o msr-$(subst m,y,$(CONFIG_X86_MSR)) += ../../i386/kernel/msr.o alternative-y += ../../i386/kernel/alternative.o - diff --git a/arch/x86_64/kernel/aperture.c b/arch/x86_64/kernel/aperture.c index 58af8e7..b487396 100644 --- a/arch/x86_64/kernel/aperture.c +++ b/arch/x86_64/kernel/aperture.c @@ -17,6 +17,7 @@ #include <linux/pci_ids.h> #include <linux/pci.h> #include <linux/bitops.h> +#include <linux/ioport.h> #include <asm/e820.h> #include <asm/io.h> #include <asm/proto.h> @@ -33,6 +34,18 @@ int fallback_aper_force __initdata = 0; int fix_aperture __initdata = 1; +static struct resource gart_resource = { + .name = "GART", + .flags = IORESOURCE_MEM, +}; + +static void __init insert_aperture_resource(u32 aper_base, u32 aper_size) +{ + gart_resource.start = aper_base; + gart_resource.end = aper_base + aper_size - 1; + insert_resource(&iomem_resource, &gart_resource); +} + /* This code runs before the PCI subsystem is initialized, so just access the northbridge directly. */ @@ -48,7 +61,7 @@ static u32 __init allocate_aperture(void) /* * Aperture has to be naturally aligned. This means an 2GB aperture won't - * have much chances to find a place in the lower 4GB of memory. + * have much chance of finding a place in the lower 4GB of memory. * Unfortunately we cannot move it up because that would make the * IOMMU useless. */ @@ -62,6 +75,7 @@ static u32 __init allocate_aperture(void) } printk("Mapping aperture over %d KB of RAM @ %lx\n", aper_size >> 10, __pa(p)); + insert_aperture_resource((u32)__pa(p), aper_size); return (u32)__pa(p); } @@ -198,7 +212,7 @@ void __init iommu_hole_init(void) u64 aper_base, last_aper_base = 0; int valid_agp = 0; - if (iommu_aperture_disabled || !fix_aperture) + if (iommu_aperture_disabled || !fix_aperture || !early_pci_allowed()) return; printk("Checking aperture...\n"); @@ -233,8 +247,13 @@ void __init iommu_hole_init(void) last_aper_base = aper_base; } - if (!fix && !fallback_aper_force) + if (!fix && !fallback_aper_force) { + if (last_aper_base) { + unsigned long n = (32 * 1024 * 1024) << last_aper_order; + insert_aperture_resource((u32)last_aper_base, n); + } return; + } if (!fallback_aper_force) aper_alloc = search_agp_bridge(&aper_order, &valid_agp); diff --git a/arch/x86_64/kernel/apic.c b/arch/x86_64/kernel/apic.c index 2b8cef0..135ff25 100644 --- a/arch/x86_64/kernel/apic.c +++ b/arch/x86_64/kernel/apic.c @@ -25,6 +25,7 @@ #include <linux/kernel_stat.h> #include <linux/sysdev.h> #include <linux/module.h> +#include <linux/ioport.h> #include <asm/atomic.h> #include <asm/smp.h> @@ -36,13 +37,20 @@ #include <asm/idle.h> #include <asm/proto.h> #include <asm/timex.h> +#include <asm/apic.h> +int apic_mapped; int apic_verbosity; int apic_runs_main_timer; int apic_calibrate_pmtmr __initdata; int disable_apic_timer __initdata; +static struct resource lapic_resource = { + .name = "Local APIC", + .flags = IORESOURCE_MEM | IORESOURCE_BUSY, +}; + /* * cpu_mask that denotes the CPUs that needs timer interrupt coming in as * IPIs in place of local APIC timers @@ -136,72 +144,40 @@ void clear_local_APIC(void) apic_read(APIC_ESR); } -void __init connect_bsp_APIC(void) -{ - if (pic_mode) { - /* - * Do not trust the local APIC being empty at bootup. - */ - clear_local_APIC(); - /* - * PIC mode, enable APIC mode in the IMCR, i.e. - * connect BSP's local APIC to INT and NMI lines. - */ - apic_printk(APIC_VERBOSE, "leaving PIC mode, enabling APIC mode.\n"); - outb(0x70, 0x22); - outb(0x01, 0x23); - } -} - void disconnect_bsp_APIC(int virt_wire_setup) { - if (pic_mode) { - /* - * Put the board back into PIC mode (has an effect - * only on certain older boards). Note that APIC - * interrupts, including IPIs, won't work beyond - * this point! The only exception are INIT IPIs. - */ - apic_printk(APIC_QUIET, "disabling APIC mode, entering PIC mode.\n"); - outb(0x70, 0x22); - outb(0x00, 0x23); - } - else { - /* Go back to Virtual Wire compatibility mode */ - unsigned long value; - - /* For the spurious interrupt use vector F, and enable it */ - value = apic_read(APIC_SPIV); - value &= ~APIC_VECTOR_MASK; - value |= APIC_SPIV_APIC_ENABLED; - value |= 0xf; - apic_write(APIC_SPIV, value); - - if (!virt_wire_setup) { - /* For LVT0 make it edge triggered, active high, external and enabled */ - value = apic_read(APIC_LVT0); - value &= ~(APIC_MODE_MASK | APIC_SEND_PENDING | - APIC_INPUT_POLARITY | APIC_LVT_REMOTE_IRR | - APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED ); - value |= APIC_LVT_REMOTE_IRR | APIC_SEND_PENDING; - value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_EXTINT); - apic_write(APIC_LVT0, value); - } - else { - /* Disable LVT0 */ - apic_write(APIC_LVT0, APIC_LVT_MASKED); - } + /* Go back to Virtual Wire compatibility mode */ + unsigned long value; + + /* For the spurious interrupt use vector F, and enable it */ + value = apic_read(APIC_SPIV); + value &= ~APIC_VECTOR_MASK; + value |= APIC_SPIV_APIC_ENABLED; + value |= 0xf; + apic_write(APIC_SPIV, value); - /* For LVT1 make it edge triggered, active high, nmi and enabled */ - value = apic_read(APIC_LVT1); - value &= ~( - APIC_MODE_MASK | APIC_SEND_PENDING | + if (!virt_wire_setup) { + /* For LVT0 make it edge triggered, active high, external and enabled */ + value = apic_read(APIC_LVT0); + value &= ~(APIC_MODE_MASK | APIC_SEND_PENDING | APIC_INPUT_POLARITY | APIC_LVT_REMOTE_IRR | - APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED); + APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED ); value |= APIC_LVT_REMOTE_IRR | APIC_SEND_PENDING; - value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_NMI); - apic_write(APIC_LVT1, value); + value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_EXTINT); + apic_write(APIC_LVT0, value); + } else { + /* Disable LVT0 */ + apic_write(APIC_LVT0, APIC_LVT_MASKED); } + + /* For LVT1 make it edge triggered, active high, nmi and enabled */ + value = apic_read(APIC_LVT1); + value &= ~(APIC_MODE_MASK | APIC_SEND_PENDING | + APIC_INPUT_POLARITY | APIC_LVT_REMOTE_IRR | + APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED); + value |= APIC_LVT_REMOTE_IRR | APIC_SEND_PENDING; + value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_NMI); + apic_write(APIC_LVT1, value); } void disable_local_APIC(void) @@ -297,8 +273,6 @@ void __init sync_Arb_IDs(void) | APIC_DM_INIT); } -extern void __error_in_apic_c (void); - /* * An initial setup of the virtual wire mode. */ @@ -345,8 +319,7 @@ void __cpuinit setup_local_APIC (void) value = apic_read(APIC_LVR); - if ((SPURIOUS_APIC_VECTOR & 0x0f) != 0x0f) - __error_in_apic_c(); + BUILD_BUG_ON((SPURIOUS_APIC_VECTOR & 0x0f) != 0x0f); /* * Double-check whether this APIC is really registered. @@ -399,32 +372,8 @@ void __cpuinit setup_local_APIC (void) */ value |= APIC_SPIV_APIC_ENABLED; - /* - * Some unknown Intel IO/APIC (or APIC) errata is biting us with - * certain networking cards. If high frequency interrupts are - * happening on a particular IOAPIC pin, plus the IOAPIC routing - * entry is masked/unmasked at a high rate as well then sooner or - * later IOAPIC line gets 'stuck', no more interrupts are received - * from the device. If focus CPU is disabled then the hang goes - * away, oh well :-( - * - * [ This bug can be reproduced easily with a level-triggered - * PCI Ne2000 networking cards and PII/PIII processors, dual - * BX chipset. ] - */ - /* - * Actually disabling the focus CPU check just makes the hang less - * frequent as it makes the interrupt distributon model be more - * like LRU than MRU (the short-term load is more even across CPUs). - * See also the comment in end_level_ioapic_irq(). --macro - */ -#if 1 - /* Enable focus processor (bit==0) */ - value &= ~APIC_SPIV_FOCUS_DISABLED; -#else - /* Disable focus processor (bit==1) */ - value |= APIC_SPIV_FOCUS_DISABLED; -#endif + /* We always use processor focus */ + /* * Set spurious IRQ vector */ @@ -442,7 +391,7 @@ void __cpuinit setup_local_APIC (void) * TODO: set up through-local-APIC from through-I/O-APIC? --macro */ value = apic_read(APIC_LVT0) & APIC_LVT_MASKED; - if (!smp_processor_id() && (pic_mode || !value)) { + if (!smp_processor_id() && !value) { value = APIC_DM_EXTINT; apic_printk(APIC_VERBOSE, "enabled ExtINT on CPU#%d\n", smp_processor_id()); } else { @@ -479,8 +428,7 @@ void __cpuinit setup_local_APIC (void) } nmi_watchdog_default(); - if (nmi_watchdog == NMI_LOCAL_APIC) - setup_apic_nmi_watchdog(); + setup_apic_nmi_watchdog(NULL); apic_pm_activate(); } @@ -527,8 +475,7 @@ static int lapic_suspend(struct sys_device *dev, pm_message_t state) apic_pm_state.apic_tmict = apic_read(APIC_TMICT); apic_pm_state.apic_tdcr = apic_read(APIC_TDCR); apic_pm_state.apic_thmr = apic_read(APIC_LVTTHMR); - local_save_flags(flags); - local_irq_disable(); + local_irq_save(flags); disable_local_APIC(); local_irq_restore(flags); return 0; @@ -606,18 +553,24 @@ static void apic_pm_activate(void) { } static int __init apic_set_verbosity(char *str) { + if (str == NULL) { + skip_ioapic_setup = 0; + ioapic_force = 1; + return 0; + } if (strcmp("debug", str) == 0) apic_verbosity = APIC_DEBUG; else if (strcmp("verbose", str) == 0) apic_verbosity = APIC_VERBOSE; - else + else { printk(KERN_WARNING "APIC Verbosity level %s not recognised" - " use apic=verbose or apic=debug", str); + " use apic=verbose or apic=debug\n", str); + return -EINVAL; + } - return 1; + return 0; } - -__setup("apic=", apic_set_verbosity); +early_param("apic", apic_set_verbosity); /* * Detect and enable local APICs on non-SMP boards. @@ -638,6 +591,40 @@ static int __init detect_init_APIC (void) return 0; } +#ifdef CONFIG_X86_IO_APIC +static struct resource * __init ioapic_setup_resources(void) +{ +#define IOAPIC_RESOURCE_NAME_SIZE 11 + unsigned long n; + struct resource *res; + char *mem; + int i; + + if (nr_ioapics <= 0) + return NULL; + + n = IOAPIC_RESOURCE_NAME_SIZE + sizeof(struct resource); + n *= nr_ioapics; + + res = alloc_bootmem(n); + + if (!res) + return NULL; + + memset(res, 0, n); + mem = (void *)&res[nr_ioapics]; + + for (i = 0; i < nr_ioapics; i++) { + res[i].name = mem; + res[i].flags = IORESOURCE_MEM | IORESOURCE_BUSY; + snprintf(mem, IOAPIC_RESOURCE_NAME_SIZE, "IOAPIC %u", i); + mem += IOAPIC_RESOURCE_NAME_SIZE; + } + + return res; +} +#endif + void __init init_apic_mappings(void) { unsigned long apic_phys; @@ -654,19 +641,26 @@ void __init init_apic_mappings(void) apic_phys = mp_lapic_addr; set_fixmap_nocache(FIX_APIC_BASE, apic_phys); + apic_mapped = 1; 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)); -#ifdef CONFIG_X86_IO_APIC { unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0; int i; + struct resource *ioapic_res; + ioapic_res = ioapic_setup_resources(); for (i = 0; i < nr_ioapics; i++) { if (smp_found_config) { ioapic_phys = mp_ioapics[i].mpc_apicaddr; @@ -678,9 +672,15 @@ void __init init_apic_mappings(void) apic_printk(APIC_VERBOSE,"mapped IOAPIC to %016lx (%016lx)\n", __fix_to_virt(idx), ioapic_phys); idx++; + + if (ioapic_res) { + ioapic_res->start = ioapic_phys; + ioapic_res->end = ioapic_phys + (4 * 1024) - 1; + insert_resource(&iomem_resource, ioapic_res); + ioapic_res++; + } } } -#endif } /* @@ -951,7 +951,7 @@ void smp_local_timer_interrupt(struct pt_regs *regs) * We take the 'long' return path, and there every subsystem * grabs the appropriate locks (kernel lock/ irq lock). * - * we might want to decouple profiling from the 'long path', + * We might want to decouple profiling from the 'long path', * and do the profiling totally in assembly. * * Currently this isn't too much of an issue (performance wise), @@ -1123,19 +1123,15 @@ int __init APIC_init_uniprocessor (void) verify_local_APIC(); - connect_bsp_APIC(); - phys_cpu_present_map = physid_mask_of_physid(boot_cpu_id); apic_write(APIC_ID, SET_APIC_ID(boot_cpu_id)); setup_local_APIC(); -#ifdef CONFIG_X86_IO_APIC if (smp_found_config && !skip_ioapic_setup && nr_ioapics) - setup_IO_APIC(); + setup_IO_APIC(); else nr_ioapics = 0; -#endif setup_boot_APIC_clock(); check_nmi_watchdog(); return 0; @@ -1144,14 +1140,17 @@ int __init APIC_init_uniprocessor (void) static __init int setup_disableapic(char *str) { disable_apic = 1; - return 1; -} + clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability); + return 0; +} +early_param("disableapic", setup_disableapic); +/* same as disableapic, for compatibility */ static __init int setup_nolapic(char *str) { - disable_apic = 1; - return 1; + return setup_disableapic(str); } +early_param("nolapic", setup_nolapic); static __init int setup_noapictimer(char *str) { @@ -1184,11 +1183,5 @@ static __init int setup_apicpmtimer(char *s) } __setup("apicpmtimer", setup_apicpmtimer); -/* dummy parsing: see setup.c */ - -__setup("disableapic", setup_disableapic); -__setup("nolapic", setup_nolapic); /* same as disableapic, for compatibility */ - __setup("noapictimer", setup_noapictimer); -/* no "lapic" flag - we only use the lapic when the BIOS tells us so. */ diff --git a/arch/x86_64/kernel/crash.c b/arch/x86_64/kernel/crash.c index d8d5750..3525f88 100644 --- a/arch/x86_64/kernel/crash.c +++ b/arch/x86_64/kernel/crash.c @@ -23,6 +23,7 @@ #include <asm/nmi.h> #include <asm/hw_irq.h> #include <asm/mach_apic.h> +#include <asm/kdebug.h> /* This keeps a track of which one is crashing cpu. */ static int crashing_cpu; @@ -68,7 +69,7 @@ static void crash_save_this_cpu(struct pt_regs *regs, int cpu) * for the data I pass, and I need tags * on the data to indicate what information I have * squirrelled away. ELF notes happen to provide - * all of that that no need to invent something new. + * all of that, no need to invent something new. */ buf = (u32*)per_cpu_ptr(crash_notes, cpu); @@ -95,15 +96,25 @@ static void crash_save_self(struct pt_regs *regs) #ifdef CONFIG_SMP static atomic_t waiting_for_crash_ipi; -static int crash_nmi_callback(struct pt_regs *regs, int cpu) +static int crash_nmi_callback(struct notifier_block *self, + unsigned long val, void *data) { + struct pt_regs *regs; + int cpu; + + if (val != DIE_NMI_IPI) + return NOTIFY_OK; + + regs = ((struct die_args *)data)->regs; + cpu = raw_smp_processor_id(); + /* * Don't do anything if this handler is invoked on crashing cpu. * Otherwise, system will completely hang. Crashing cpu can get * an NMI if system was initially booted with nmi_watchdog parameter. */ if (cpu == crashing_cpu) - return 1; + return NOTIFY_STOP; local_irq_disable(); crash_save_this_cpu(regs, cpu); @@ -127,12 +138,17 @@ static void smp_send_nmi_allbutself(void) * cpu hotplug shouldn't matter. */ +static struct notifier_block crash_nmi_nb = { + .notifier_call = crash_nmi_callback, +}; + static void nmi_shootdown_cpus(void) { unsigned long msecs; atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1); - set_nmi_callback(crash_nmi_callback); + if (register_die_notifier(&crash_nmi_nb)) + return; /* return what? */ /* * Ensure the new callback function is set before sending @@ -178,9 +194,7 @@ void machine_crash_shutdown(struct pt_regs *regs) if(cpu_has_apic) disable_local_APIC(); -#if defined(CONFIG_X86_IO_APIC) disable_IO_APIC(); -#endif crash_save_self(regs); } diff --git a/arch/x86_64/kernel/e820.c b/arch/x86_64/kernel/e820.c index 708a3cd..c0af382 100644 --- a/arch/x86_64/kernel/e820.c +++ b/arch/x86_64/kernel/e820.c @@ -25,6 +25,8 @@ #include <asm/bootsetup.h> #include <asm/sections.h> +struct e820map e820 __initdata; + /* * PFN of last memory page. */ @@ -41,7 +43,7 @@ unsigned long end_pfn_map; /* * Last pfn which the user wants to use. */ -unsigned long end_user_pfn = MAXMEM>>PAGE_SHIFT; +static unsigned long __initdata end_user_pfn = MAXMEM>>PAGE_SHIFT; extern struct resource code_resource, data_resource; @@ -70,12 +72,7 @@ static inline int bad_addr(unsigned long *addrp, unsigned long size) return 1; } #endif - /* kernel code + 640k memory hole (later should not be needed, but - be paranoid for now) */ - if (last >= 640*1024 && addr < 1024*1024) { - *addrp = 1024*1024; - return 1; - } + /* kernel code */ if (last >= __pa_symbol(&_text) && last < __pa_symbol(&_end)) { *addrp = __pa_symbol(&_end); return 1; @@ -565,13 +562,6 @@ static int __init sanitize_e820_map(struct e820entry * biosmap, char * pnr_map) * If we're lucky and live on a modern system, the setup code * will have given us a memory map that we can use to properly * set up memory. If we aren't, we'll fake a memory map. - * - * We check to see that the memory map contains at least 2 elements - * before we'll use it, because the detection code in setup.S may - * not be perfect and most every PC known to man has two memory - * regions: one from 0 to 640k, and one from 1mb up. (The IBM - * thinkpad 560x, for example, does not cooperate with the memory - * detection code.) */ static int __init copy_e820_map(struct e820entry * biosmap, int nr_map) { @@ -589,34 +579,19 @@ static int __init copy_e820_map(struct e820entry * biosmap, int nr_map) if (start > end) return -1; - /* - * Some BIOSes claim RAM in the 640k - 1M region. - * Not right. Fix it up. - * - * This should be removed on Hammer which is supposed to not - * have non e820 covered ISA mappings there, but I had some strange - * problems so it stays for now. -AK - */ - 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); return 0; } -void __init setup_memory_region(void) +void early_panic(char *msg) { - char *who = "BIOS-e820"; + early_printk(msg); + panic(msg); +} +void __init setup_memory_region(void) +{ /* * Try to copy the BIOS-supplied E820-map. * @@ -624,51 +599,70 @@ void __init setup_memory_region(void) * the next section from 1mb->appropriate_mem_k */ sanitize_e820_map(E820_MAP, &E820_MAP_NR); - if (copy_e820_map(E820_MAP, E820_MAP_NR) < 0) { - unsigned long mem_size; - - /* compare results from other methods and take the greater */ - if (ALT_MEM_K < EXT_MEM_K) { - mem_size = EXT_MEM_K; - who = "BIOS-88"; - } else { - mem_size = ALT_MEM_K; - who = "BIOS-e801"; - } - - e820.nr_map = 0; - add_memory_region(0, LOWMEMSIZE(), E820_RAM); - add_memory_region(HIGH_MEMORY, mem_size << 10, E820_RAM); - } + if (copy_e820_map(E820_MAP, E820_MAP_NR) < 0) + early_panic("Cannot find a valid memory map"); printk(KERN_INFO "BIOS-provided physical RAM map:\n"); - e820_print_map(who); + e820_print_map("BIOS-e820"); } -void __init parse_memopt(char *p, char **from) -{ - end_user_pfn = memparse(p, from); +static int __init parse_memopt(char *p) +{ + if (!p) + return -EINVAL; + end_user_pfn = memparse(p, &p); end_user_pfn >>= PAGE_SHIFT; + return 0; } +early_param("mem", parse_memopt); -void __init parse_memmapopt(char *p, char **from) +static int userdef __initdata; + +static int __init parse_memmap_opt(char *p) { + char *oldp; unsigned long long start_at, mem_size; - mem_size = memparse(p, from); - p = *from; + if (!strcmp(p, "exactmap")) { +#ifdef CONFIG_CRASH_DUMP + /* If we are doing a crash dump, we + * still need to know the real mem + * size before original memory map is + * reset. + */ + saved_max_pfn = e820_end_of_ram(); +#endif + end_pfn_map = 0; + e820.nr_map = 0; + userdef = 1; + return 0; + } + + oldp = p; + mem_size = memparse(p, &p); + if (p == oldp) + return -EINVAL; if (*p == '@') { - start_at = memparse(p+1, from); + start_at = memparse(p+1, &p); add_memory_region(start_at, mem_size, E820_RAM); } else if (*p == '#') { - start_at = memparse(p+1, from); + start_at = memparse(p+1, &p); add_memory_region(start_at, mem_size, E820_ACPI); } else if (*p == '$') { - start_at = memparse(p+1, from); + start_at = memparse(p+1, &p); add_memory_region(start_at, mem_size, E820_RESERVED); } else { end_user_pfn = (mem_size >> PAGE_SHIFT); } - p = *from; + return *p == '\0' ? 0 : -EINVAL; +} +early_param("memmap", parse_memmap_opt); + +void finish_e820_parsing(void) +{ + if (userdef) { + printk(KERN_INFO "user-defined physical RAM map:\n"); + e820_print_map("user"); + } } unsigned long pci_mem_start = 0xaeedbabe; diff --git a/arch/x86_64/kernel/early-quirks.c b/arch/x86_64/kernel/early-quirks.c new file mode 100644 index 0000000..208e38a --- /dev/null +++ b/arch/x86_64/kernel/early-quirks.c @@ -0,0 +1,122 @@ +/* Various workarounds for chipset bugs. + This code runs very early and can't use the regular PCI subsystem + The entries are keyed to PCI bridges which usually identify chipsets + uniquely. + This is only for whole classes of chipsets with specific problems which + need early invasive action (e.g. before the timers are initialized). + Most PCI device specific workarounds can be done later and should be + in standard PCI quirks + Mainboard specific bugs should be handled by DMI entries. + CPU specific bugs in setup.c */ + +#include <linux/pci.h> +#include <linux/acpi.h> +#include <linux/pci_ids.h> +#include <asm/pci-direct.h> +#include <asm/proto.h> +#include <asm/dma.h> + +static void via_bugs(void) +{ +#ifdef CONFIG_IOMMU + if ((end_pfn > MAX_DMA32_PFN || force_iommu) && + !iommu_aperture_allowed) { + printk(KERN_INFO + "Looks like a VIA chipset. Disabling IOMMU. Override with iommu=allowed\n"); + iommu_aperture_disabled = 1; + } +#endif +} + +#ifdef CONFIG_ACPI + +static int nvidia_hpet_detected __initdata; + +static int __init nvidia_hpet_check(unsigned long phys, unsigned long size) +{ + nvidia_hpet_detected = 1; + return 0; +} +#endif + +static void nvidia_bugs(void) +{ +#ifdef CONFIG_ACPI + /* + * All timer overrides on Nvidia are + * wrong unless HPET is enabled. + */ + nvidia_hpet_detected = 0; + acpi_table_parse(ACPI_HPET, nvidia_hpet_check); + if (nvidia_hpet_detected == 0) { + acpi_skip_timer_override = 1; + printk(KERN_INFO "Nvidia board " + "detected. Ignoring ACPI " + "timer override.\n"); + } +#endif + /* RED-PEN skip them on mptables too? */ + +} + +static void ati_bugs(void) +{ +#if 1 /* for testing */ + printk("ATI board detected\n"); +#endif + /* No bugs right now */ +} + +struct chipset { + u16 vendor; + void (*f)(void); +}; + +static struct chipset early_qrk[] = { + { PCI_VENDOR_ID_NVIDIA, nvidia_bugs }, + { PCI_VENDOR_ID_VIA, via_bugs }, + { PCI_VENDOR_ID_ATI, ati_bugs }, + {} +}; + +void __init early_quirks(void) +{ + int num, slot, func; + + if (!early_pci_allowed()) + return; + + /* Poor man's PCI discovery */ + for (num = 0; num < 32; num++) { + for (slot = 0; slot < 32; slot++) { + for (func = 0; func < 8; func++) { + u32 class; + u32 vendor; + u8 type; + int i; + class = read_pci_config(num,slot,func, + PCI_CLASS_REVISION); + if (class == 0xffffffff) + break; + + if ((class >> 16) != PCI_CLASS_BRIDGE_PCI) + continue; + + vendor = read_pci_config(num, slot, func, + PCI_VENDOR_ID); + vendor &= 0xffff; + + for (i = 0; early_qrk[i].f; i++) + if (early_qrk[i].vendor == vendor) { + early_qrk[i].f(); + return; + } + + type = read_pci_config_byte(num, slot, func, + PCI_HEADER_TYPE); + if (!(type & 0x80)) + break; + } + } + } +} diff --git a/arch/x86_64/kernel/early_printk.c b/arch/x86_64/kernel/early_printk.c index 140051e..e22ecd5 100644 --- a/arch/x86_64/kernel/early_printk.c +++ b/arch/x86_64/kernel/early_printk.c @@ -215,20 +215,16 @@ void early_printk(const char *fmt, ...) static int __initdata keep_early; -int __init setup_early_printk(char *opt) +static int __init setup_early_printk(char *buf) { - char *space; - char buf[256]; + if (!buf) + return 0; if (early_console_initialized) - return 1; - - strlcpy(buf,opt,sizeof(buf)); - space = strchr(buf, ' '); - if (space) - *space = 0; + return 0; + early_console_initialized = 1; - if (strstr(buf,"keep")) + if (!strcmp(buf,"keep")) keep_early = 1; if (!strncmp(buf, "serial", 6)) { @@ -248,11 +244,12 @@ int __init setup_early_printk(char *opt) early_console = &simnow_console; keep_early = 1; } - early_console_initialized = 1; register_console(early_console); return 0; } +early_param("earlyprintk", setup_early_printk); + void __init disable_early_printk(void) { if (!early_console_initialized || !early_console) @@ -266,4 +263,3 @@ void __init disable_early_printk(void) } } -__setup("earlyprintk=", setup_early_printk); diff --git a/arch/x86_64/kernel/entry.S b/arch/x86_64/kernel/entry.S index aa8d893..2802524 100644 --- a/arch/x86_64/kernel/entry.S +++ b/arch/x86_64/kernel/entry.S @@ -4,8 +4,6 @@ * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs * Copyright (C) 2000 Pavel Machek <pavel@suse.cz> - * - * $Id$ */ /* @@ -22,15 +20,25 @@ * at the top of the kernel process stack. * - partial stack frame: partially saved registers upto R11. * - full stack frame: Like partial stack frame, but all register saved. - * - * TODO: - * - schedule it carefully for the final hardware. + * + * Some macro usage: + * - CFI macros are used to generate dwarf2 unwind information for better + * backtraces. They don't change any code. + * - SAVE_ALL/RESTORE_ALL - Save/restore all registers + * - SAVE_ARGS/RESTORE_ARGS - Save/restore registers that C functions modify. + * There are unfortunately lots of special cases where some registers + * not touched. The macro is a big mess that should be cleaned up. + * - SAVE_REST/RESTORE_REST - Handle the registers not saved by SAVE_ARGS. + * Gives a full stack frame. + * - ENTRY/END Define functions in the symbol table. + * - FIXUP_TOP_OF_STACK/RESTORE_TOP_OF_STACK - Fix up the hardware stack + * frame that is otherwise undefined after a SYSCALL + * - TRACE_IRQ_* - Trace hard interrupt state for lock debugging. + * - errorentry/paranoidentry/zeroentry - Define exception entry points. */ -#define ASSEMBLY 1 #include <linux/linkage.h> #include <asm/segment.h> -#include <asm/smp.h> #include <asm/cache.h> #include <asm/errno.h> #include <asm/dwarf2.h> @@ -115,6 +123,7 @@ .macro CFI_DEFAULT_STACK start=1 .if \start CFI_STARTPROC simple + CFI_SIGNAL_FRAME CFI_DEF_CFA rsp,SS+8 .else CFI_DEF_CFA_OFFSET SS+8 @@ -146,6 +155,10 @@ /* rdi: prev */ ENTRY(ret_from_fork) CFI_DEFAULT_STACK + push kernel_eflags(%rip) + CFI_ADJUST_CFA_OFFSET 4 + popf # reset kernel eflags + CFI_ADJUST_CFA_OFFSET -4 call schedule_tail GET_THREAD_INFO(%rcx) testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),threadinfo_flags(%rcx) @@ -199,6 +212,7 @@ END(ret_from_fork) ENTRY(system_call) CFI_STARTPROC simple + CFI_SIGNAL_FRAME CFI_DEF_CFA rsp,PDA_STACKOFFSET CFI_REGISTER rip,rcx /*CFI_REGISTER rflags,r11*/ @@ -316,6 +330,7 @@ END(system_call) */ ENTRY(int_ret_from_sys_call) CFI_STARTPROC simple + CFI_SIGNAL_FRAME CFI_DEF_CFA rsp,SS+8-ARGOFFSET /*CFI_REL_OFFSET ss,SS-ARGOFFSET*/ CFI_REL_OFFSET rsp,RSP-ARGOFFSET @@ -476,6 +491,7 @@ END(stub_rt_sigreturn) */ .macro _frame ref CFI_STARTPROC simple + CFI_SIGNAL_FRAME CFI_DEF_CFA rsp,SS+8-\ref /*CFI_REL_OFFSET ss,SS-\ref*/ CFI_REL_OFFSET rsp,RSP-\ref @@ -511,7 +527,12 @@ END(stub_rt_sigreturn) testl $3,CS(%rdi) je 1f swapgs -1: incl %gs:pda_irqcount # RED-PEN should check preempt count + /* irqcount is used to check if a CPU is already on an interrupt + stack or not. While this is essentially redundant with preempt_count + it is a little cheaper to use a separate counter in the PDA + (short of moving irq_enter into assembly, which would be too + much work) */ +1: incl %gs:pda_irqcount cmoveq %gs:pda_irqstackptr,%rsp push %rbp # backlink for old unwinder /* @@ -619,8 +640,7 @@ retint_signal: #ifdef CONFIG_PREEMPT /* Returning to kernel space. Check if we need preemption */ /* rcx: threadinfo. interrupts off. */ - .p2align -retint_kernel: +ENTRY(retint_kernel) cmpl $0,threadinfo_preempt_count(%rcx) jnz retint_restore_args bt $TIF_NEED_RESCHED,threadinfo_flags(%rcx) @@ -679,7 +699,6 @@ ENTRY(call_function_interrupt) END(call_function_interrupt) #endif -#ifdef CONFIG_X86_LOCAL_APIC ENTRY(apic_timer_interrupt) apicinterrupt LOCAL_TIMER_VECTOR,smp_apic_timer_interrupt END(apic_timer_interrupt) @@ -691,7 +710,6 @@ END(error_interrupt) ENTRY(spurious_interrupt) apicinterrupt SPURIOUS_APIC_VECTOR,smp_spurious_interrupt END(spurious_interrupt) -#endif /* * Exception entry points. @@ -768,7 +786,9 @@ paranoid_exit\trace: testl $3,CS(%rsp) jnz paranoid_userspace\trace paranoid_swapgs\trace: + .if \trace TRACE_IRQS_IRETQ 0 + .endif swapgs paranoid_restore\trace: RESTORE_ALL 8 @@ -814,7 +834,7 @@ paranoid_schedule\trace: * Exception entry point. This expects an error code/orig_rax on the stack * and the exception handler in %rax. */ -ENTRY(error_entry) +KPROBE_ENTRY(error_entry) _frame RDI /* rdi slot contains rax, oldrax contains error code */ cld @@ -898,7 +918,7 @@ error_kernelspace: cmpq $gs_change,RIP(%rsp) je error_swapgs jmp error_sti -END(error_entry) +KPROBE_END(error_entry) /* Reload gs selector with exception handling */ /* edi: new selector */ @@ -1020,8 +1040,7 @@ ENDPROC(execve) KPROBE_ENTRY(page_fault) errorentry do_page_fault -END(page_fault) - .previous .text +KPROBE_END(page_fault) ENTRY(coprocessor_error) zeroentry do_coprocessor_error @@ -1042,8 +1061,7 @@ KPROBE_ENTRY(debug) CFI_ADJUST_CFA_OFFSET 8 paranoidentry do_debug, DEBUG_STACK paranoidexit -END(debug) - .previous .text +KPROBE_END(debug) /* runs on exception stack */ KPROBE_ENTRY(nmi) @@ -1057,8 +1075,7 @@ KPROBE_ENTRY(nmi) jmp paranoid_exit1 CFI_ENDPROC #endif -END(nmi) - .previous .text +KPROBE_END(nmi) KPROBE_ENTRY(int3) INTR_FRAME @@ -1067,8 +1084,7 @@ KPROBE_ENTRY(int3) paranoidentry do_int3, DEBUG_STACK jmp paranoid_exit1 CFI_ENDPROC -END(int3) - .previous .text +KPROBE_END(int3) ENTRY(overflow) zeroentry do_overflow @@ -1116,8 +1132,7 @@ END(stack_segment) KPROBE_ENTRY(general_protection) errorentry do_general_protection -END(general_protection) - .previous .text +KPROBE_END(general_protection) ENTRY(alignment_check) errorentry do_alignment_check diff --git a/arch/x86_64/kernel/genapic_cluster.c b/arch/x86_64/kernel/genapic_cluster.c index 3020917..cdb90e6 100644 --- a/arch/x86_64/kernel/genapic_cluster.c +++ b/arch/x86_64/kernel/genapic_cluster.c @@ -118,7 +118,6 @@ struct genapic apic_cluster = { .name = "clustered", .int_delivery_mode = dest_Fixed, .int_dest_mode = (APIC_DEST_PHYSICAL != 0), - .int_delivery_dest = APIC_DEST_PHYSICAL | APIC_DM_FIXED, .target_cpus = cluster_target_cpus, .apic_id_registered = cluster_apic_id_registered, .init_apic_ldr = cluster_init_apic_ldr, diff --git a/arch/x86_64/kernel/genapic_flat.c b/arch/x86_64/kernel/genapic_flat.c index eb86d37..50ad153 100644 --- a/arch/x86_64/kernel/genapic_flat.c +++ b/arch/x86_64/kernel/genapic_flat.c @@ -49,8 +49,7 @@ static void flat_send_IPI_mask(cpumask_t cpumask, int vector) unsigned long cfg; unsigned long flags; - local_save_flags(flags); - local_irq_disable(); + local_irq_save(flags); /* * Wait for idle. @@ -121,7 +120,6 @@ struct genapic apic_flat = { .name = "flat", .int_delivery_mode = dest_LowestPrio, .int_dest_mode = (APIC_DEST_LOGICAL != 0), - .int_delivery_dest = APIC_DEST_LOGICAL | APIC_DM_LOWEST, .target_cpus = flat_target_cpus, .apic_id_registered = flat_apic_id_registered, .init_apic_ldr = flat_init_apic_ldr, @@ -180,7 +178,6 @@ struct genapic apic_physflat = { .name = "physical flat", .int_delivery_mode = dest_Fixed, .int_dest_mode = (APIC_DEST_PHYSICAL != 0), - .int_delivery_dest = APIC_DEST_PHYSICAL | APIC_DM_FIXED, .target_cpus = physflat_target_cpus, .apic_id_registered = flat_apic_id_registered, .init_apic_ldr = flat_init_apic_ldr,/*not needed, but shouldn't hurt*/ diff --git a/arch/x86_64/kernel/head.S b/arch/x86_64/kernel/head.S index c9739ca..1e6f808 100644 --- a/arch/x86_64/kernel/head.S +++ b/arch/x86_64/kernel/head.S @@ -5,8 +5,6 @@ * Copyright (C) 2000 Pavel Machek <pavel@suse.cz> * Copyright (C) 2000 Karsten Keil <kkeil@suse.de> * Copyright (C) 2001,2002 Andi Kleen <ak@suse.de> - * - * $Id: head.S,v 1.49 2002/03/19 17:39:25 ak Exp $ */ @@ -187,12 +185,15 @@ startup_64: /* Finally jump to run C code and to be on real kernel address * Since we are running on identity-mapped space we have to jump - * to the full 64bit address , this is only possible as indirect - * jump + * to the full 64bit address, this is only possible as indirect + * jump. In addition we need to ensure %cs is set so we make this + * a far return. */ movq initial_code(%rip),%rax - pushq $0 # fake return address - jmp *%rax + pushq $0 # fake return address to stop unwinder + pushq $__KERNEL_CS # set correct cs + pushq %rax # target address in negative space + lretq /* SMP bootup changes these two */ .align 8 @@ -371,7 +372,7 @@ ENTRY(cpu_gdt_table) .quad 0,0 /* TSS */ .quad 0,0 /* LDT */ .quad 0,0,0 /* three TLS descriptors */ - .quad 0 /* unused */ + .quad 0x0000f40000000000 /* node/CPU stored in limit */ gdt_end: /* asm/segment.h:GDT_ENTRIES must match this */ /* This should be a multiple of the cache line size */ diff --git a/arch/x86_64/kernel/head64.c b/arch/x86_64/kernel/head64.c index 36647ce..9561eb3 100644 --- a/arch/x86_64/kernel/head64.c +++ b/arch/x86_64/kernel/head64.c @@ -45,38 +45,16 @@ static void __init copy_bootdata(char *real_mode_data) new_data = *(int *) (x86_boot_params + NEW_CL_POINTER); if (!new_data) { if (OLD_CL_MAGIC != * (u16 *) OLD_CL_MAGIC_ADDR) { - printk("so old bootloader that it does not support commandline?!\n"); return; } new_data = OLD_CL_BASE_ADDR + * (u16 *) OLD_CL_OFFSET; - printk("old bootloader convention, maybe loadlin?\n"); } command_line = (char *) ((u64)(new_data)); memcpy(saved_command_line, command_line, COMMAND_LINE_SIZE); - printk("Bootdata ok (command line is %s)\n", saved_command_line); -} - -static void __init setup_boot_cpu_data(void) -{ - unsigned int dummy, eax; - - /* get vendor info */ - cpuid(0, (unsigned int *)&boot_cpu_data.cpuid_level, - (unsigned int *)&boot_cpu_data.x86_vendor_id[0], - (unsigned int *)&boot_cpu_data.x86_vendor_id[8], - (unsigned int *)&boot_cpu_data.x86_vendor_id[4]); - - /* get cpu type */ - cpuid(1, &eax, &dummy, &dummy, - (unsigned int *) &boot_cpu_data.x86_capability); - boot_cpu_data.x86 = (eax >> 8) & 0xf; - boot_cpu_data.x86_model = (eax >> 4) & 0xf; - boot_cpu_data.x86_mask = eax & 0xf; } void __init x86_64_start_kernel(char * real_mode_data) { - char *s; int i; for (i = 0; i < 256; i++) @@ -84,10 +62,7 @@ void __init x86_64_start_kernel(char * real_mode_data) asm volatile("lidt %0" :: "m" (idt_descr)); clear_bss(); - /* - * This must be called really, really early: - */ - lockdep_init(); + early_printk("Kernel alive\n"); /* * switch to init_level4_pgt from boot_level4_pgt @@ -103,22 +78,5 @@ void __init x86_64_start_kernel(char * real_mode_data) #ifdef CONFIG_SMP cpu_set(0, cpu_online_map); #endif - s = strstr(saved_command_line, "earlyprintk="); - if (s != NULL) - setup_early_printk(strchr(s, '=') + 1); -#ifdef CONFIG_NUMA - s = strstr(saved_command_line, "numa="); - if (s != NULL) - numa_setup(s+5); -#endif -#ifdef CONFIG_X86_IO_APIC - if (strstr(saved_command_line, "disableapic")) - disable_apic = 1; -#endif - /* You need early console to see that */ - if (__pa_symbol(&_end) >= KERNEL_TEXT_SIZE) - panic("Kernel too big for kernel mapping\n"); - - setup_boot_cpu_data(); start_kernel(); } diff --git a/arch/x86_64/kernel/i8259.c b/arch/x86_64/kernel/i8259.c index 0434b1f..2dd51f3 100644 --- a/arch/x86_64/kernel/i8259.c +++ b/arch/x86_64/kernel/i8259.c @@ -55,7 +55,6 @@ */ BUILD_16_IRQS(0x0) -#ifdef CONFIG_X86_LOCAL_APIC /* * The IO-APIC gives us many more interrupt sources. Most of these * are unused but an SMP system is supposed to have enough memory ... @@ -75,8 +74,6 @@ BUILD_16_IRQS(0xc) BUILD_16_IRQS(0xd) BUILD_15_IRQS(0xe) #endif -#endif - #undef BUILD_16_IRQS #undef BUILD_15_IRQS #undef BI @@ -100,7 +97,6 @@ BUILD_16_IRQS(0xc) BUILD_16_IRQS(0xd) void (*interrupt[NR_IRQS])(void) = { IRQLIST_16(0x0), -#ifdef CONFIG_X86_IO_APIC IRQLIST_16(0x1), IRQLIST_16(0x2), IRQLIST_16(0x3), IRQLIST_16(0x4), IRQLIST_16(0x5), IRQLIST_16(0x6), IRQLIST_16(0x7), IRQLIST_16(0x8), IRQLIST_16(0x9), IRQLIST_16(0xa), IRQLIST_16(0xb), @@ -110,7 +106,6 @@ void (*interrupt[NR_IRQS])(void) = { , IRQLIST_15(0xe) #endif -#endif }; #undef IRQ @@ -128,6 +123,8 @@ void (*interrupt[NR_IRQS])(void) = { DEFINE_SPINLOCK(i8259A_lock); +static int i8259A_auto_eoi; + static void end_8259A_irq (unsigned int irq) { if (irq > 256) { @@ -341,6 +338,8 @@ void init_8259A(int auto_eoi) { unsigned long flags; + i8259A_auto_eoi = auto_eoi; + spin_lock_irqsave(&i8259A_lock, flags); outb(0xff, 0x21); /* mask all of 8259A-1 */ @@ -399,7 +398,7 @@ static void save_ELCR(char *trigger) static int i8259A_resume(struct sys_device *dev) { - init_8259A(0); + init_8259A(i8259A_auto_eoi); restore_ELCR(irq_trigger); return 0; } @@ -453,9 +452,7 @@ void __init init_ISA_irqs (void) { int i; -#ifdef CONFIG_X86_LOCAL_APIC init_bsp_APIC(); -#endif init_8259A(0); for (i = 0; i < NR_IRQS; i++) { @@ -581,14 +578,12 @@ void __init init_IRQ(void) set_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt); set_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt); -#ifdef CONFIG_X86_LOCAL_APIC /* self generated IPI for local APIC timer */ set_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt); /* IPI vectors for APIC spurious and error interrupts */ set_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt); set_intr_gate(ERROR_APIC_VECTOR, error_interrupt); -#endif /* * Set the clock to HZ Hz, we already have a valid diff --git a/arch/x86_64/kernel/io_apic.c b/arch/x86_64/kernel/io_apic.c index 924a4a3..0491019 100644 --- a/arch/x86_64/kernel/io_apic.c +++ b/arch/x86_64/kernel/io_apic.c @@ -48,7 +48,7 @@ int sis_apic_bug; /* not actually supported, dummy for compile */ static int no_timer_check; -int disable_timer_pin_1 __initdata; +static int disable_timer_pin_1 __initdata; int timer_over_8254 __initdata = 0; @@ -111,6 +111,33 @@ int vector_irq[NR_VECTORS] __read_mostly = { [0 ... NR_VECTORS - 1] = -1}; FINAL; \ } +union entry_union { + struct { u32 w1, w2; }; + struct IO_APIC_route_entry entry; +}; + +static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin) +{ + union entry_union eu; + unsigned long flags; + spin_lock_irqsave(&ioapic_lock, flags); + eu.w1 = io_apic_read(apic, 0x10 + 2 * pin); + eu.w2 = io_apic_read(apic, 0x11 + 2 * pin); + spin_unlock_irqrestore(&ioapic_lock, flags); + return eu.entry; +} + +static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e) +{ + unsigned long flags; + union entry_union eu; + eu.entry = e; + spin_lock_irqsave(&ioapic_lock, flags); + io_apic_write(apic, 0x10 + 2*pin, eu.w1); + io_apic_write(apic, 0x11 + 2*pin, eu.w2); + spin_unlock_irqrestore(&ioapic_lock, flags); +} + #ifdef CONFIG_SMP static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask) { @@ -196,13 +223,9 @@ static void unmask_IO_APIC_irq (unsigned int irq) static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) { struct IO_APIC_route_entry entry; - unsigned long flags; /* Check delivery_mode to be sure we're not clearing an SMI pin */ - spin_lock_irqsave(&ioapic_lock, flags); - *(((int*)&entry) + 0) = io_apic_read(apic, 0x10 + 2 * pin); - *(((int*)&entry) + 1) = io_apic_read(apic, 0x11 + 2 * pin); - spin_unlock_irqrestore(&ioapic_lock, flags); + entry = ioapic_read_entry(apic, pin); if (entry.delivery_mode == dest_SMI) return; /* @@ -210,10 +233,7 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) */ memset(&entry, 0, sizeof(entry)); entry.mask = 1; - spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(apic, 0x10 + 2 * pin, *(((int *)&entry) + 0)); - io_apic_write(apic, 0x11 + 2 * pin, *(((int *)&entry) + 1)); - spin_unlock_irqrestore(&ioapic_lock, flags); + ioapic_write_entry(apic, pin, entry); } static void clear_IO_APIC (void) @@ -225,14 +245,6 @@ static void clear_IO_APIC (void) clear_IO_APIC_pin(apic, pin); } -/* - * support for broken MP BIOSs, enables hand-redirection of PIRQ0-7 to - * specific CPU-side IRQs. - */ - -#define MAX_PIRQS 8 -static int pirq_entries [MAX_PIRQS]; -static int pirqs_enabled; int skip_ioapic_setup; int ioapic_force; @@ -241,18 +253,17 @@ int ioapic_force; static int __init disable_ioapic_setup(char *str) { skip_ioapic_setup = 1; - return 1; + return 0; } +early_param("noapic", disable_ioapic_setup); -static int __init enable_ioapic_setup(char *str) +/* Actually the next is obsolete, but keep it for paranoid reasons -AK */ +static int __init disable_timer_pin_setup(char *arg) { - ioapic_force = 1; - skip_ioapic_setup = 0; + disable_timer_pin_1 = 1; return 1; } - -__setup("noapic", disable_ioapic_setup); -__setup("apic", enable_ioapic_setup); +__setup("disable_timer_pin_1", disable_timer_pin_setup); static int __init setup_disable_8254_timer(char *s) { @@ -268,135 +279,6 @@ static int __init setup_enable_8254_timer(char *s) __setup("disable_8254_timer", setup_disable_8254_timer); __setup("enable_8254_timer", setup_enable_8254_timer); -#include <asm/pci-direct.h> -#include <linux/pci_ids.h> -#include <linux/pci.h> - - -#ifdef CONFIG_ACPI - -static int nvidia_hpet_detected __initdata; - -static int __init nvidia_hpet_check(unsigned long phys, unsigned long size) -{ - nvidia_hpet_detected = 1; - return 0; -} -#endif - -/* Temporary Hack. Nvidia and VIA boards currently only work with IO-APIC - off. Check for an Nvidia or VIA PCI bridge and turn it off. - Use pci direct infrastructure because this runs before the PCI subsystem. - - Can be overwritten with "apic" - - And another hack to disable the IOMMU on VIA chipsets. - - ... and others. Really should move this somewhere else. - - Kludge-O-Rama. */ -void __init check_ioapic(void) -{ - int num,slot,func; - /* Poor man's PCI discovery */ - for (num = 0; num < 32; num++) { - for (slot = 0; slot < 32; slot++) { - for (func = 0; func < 8; func++) { - u32 class; - u32 vendor; - u8 type; - class = read_pci_config(num,slot,func, - PCI_CLASS_REVISION); - if (class == 0xffffffff) - break; - - if ((class >> 16) != PCI_CLASS_BRIDGE_PCI) - continue; - - vendor = read_pci_config(num, slot, func, - PCI_VENDOR_ID); - vendor &= 0xffff; - switch (vendor) { - case PCI_VENDOR_ID_VIA: -#ifdef CONFIG_IOMMU - if ((end_pfn > MAX_DMA32_PFN || - force_iommu) && - !iommu_aperture_allowed) { - printk(KERN_INFO - "Looks like a VIA chipset. Disabling IOMMU. Override with \"iommu=allowed\"\n"); - iommu_aperture_disabled = 1; - } -#endif - return; - case PCI_VENDOR_ID_NVIDIA: -#ifdef CONFIG_ACPI - /* - * All timer overrides on Nvidia are - * wrong unless HPET is enabled. - */ - nvidia_hpet_detected = 0; - acpi_table_parse(ACPI_HPET, - nvidia_hpet_check); - if (nvidia_hpet_detected == 0) { - acpi_skip_timer_override = 1; - printk(KERN_INFO "Nvidia board " - "detected. Ignoring ACPI " - "timer override.\n"); - } -#endif - /* RED-PEN skip them on mptables too? */ - return; - - /* This should be actually default, but - for 2.6.16 let's do it for ATI only where - it's really needed. */ - case PCI_VENDOR_ID_ATI: - if (timer_over_8254 == 1) { - timer_over_8254 = 0; - printk(KERN_INFO - "ATI board detected. Disabling timer routing over 8254.\n"); - } - return; - } - - - /* No multi-function device? */ - type = read_pci_config_byte(num,slot,func, - PCI_HEADER_TYPE); - if (!(type & 0x80)) - break; - } - } - } -} - -static int __init ioapic_pirq_setup(char *str) -{ - int i, max; - int ints[MAX_PIRQS+1]; - - get_options(str, ARRAY_SIZE(ints), ints); - - for (i = 0; i < MAX_PIRQS; i++) - pirq_entries[i] = -1; - - pirqs_enabled = 1; - apic_printk(APIC_VERBOSE, "PIRQ redirection, working around broken MP-BIOS.\n"); - max = MAX_PIRQS; - if (ints[0] < MAX_PIRQS) - max = ints[0]; - - for (i = 0; i < max; i++) { - apic_printk(APIC_VERBOSE, "... PIRQ%d -> IRQ %d\n", i, ints[i+1]); - /* - * PIRQs are mapped upside down, usually. - */ - pirq_entries[MAX_PIRQS-i-1] = ints[i+1]; - } - return 1; -} - -__setup("pirq=", ioapic_pirq_setup); /* * Find the IRQ entry number of a certain pin. @@ -425,9 +307,7 @@ 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)) @@ -443,9 +323,7 @@ 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; @@ -485,7 +363,7 @@ 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))) { @@ -508,27 +386,6 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin) return best_guess; } -/* - * EISA Edge/Level control register, ELCR - */ -static int EISA_ELCR(unsigned int irq) -{ - if (irq < 16) { - unsigned int port = 0x4d0 + (irq >> 3); - return (inb(port) >> (irq & 7)) & 1; - } - apic_printk(APIC_VERBOSE, "Broken MPtable reports ISA irq %d\n", irq); - return 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 - * EISA conforming in the MP table, that means its trigger type must - * be read in from the ELCR */ - -#define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].mpc_srcbusirq)) -#define default_EISA_polarity(idx) (0) - /* ISA interrupts are always polarity zero edge triggered, * when listed as conforming in the MP table. */ @@ -541,12 +398,6 @@ static int EISA_ELCR(unsigned int irq) #define default_PCI_trigger(idx) (1) #define default_PCI_polarity(idx) (1) -/* MCA interrupts are always polarity zero level triggered, - * when listed as conforming in the MP table. */ - -#define default_MCA_trigger(idx) (1) -#define default_MCA_polarity(idx) (0) - static int __init MPBIOS_polarity(int idx) { int bus = mp_irqs[idx].mpc_srcbus; @@ -558,38 +409,11 @@ static int __init MPBIOS_polarity(int idx) switch (mp_irqs[idx].mpc_irqflag & 3) { 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; - } - } + if (test_bit(bus, mp_bus_not_pci)) + polarity = default_ISA_polarity(idx); + else + polarity = default_PCI_polarity(idx); break; - } case 1: /* high active */ { polarity = 0; @@ -627,38 +451,11 @@ static int MPBIOS_trigger(int idx) switch ((mp_irqs[idx].mpc_irqflag>>2) & 3) { case 0: /* conforms, ie. bus-type dependent */ - { - switch (mp_bus_id_to_type[bus]) - { - case MP_BUS_ISA: /* ISA pin */ - { - trigger = default_ISA_trigger(idx); - break; - } - case MP_BUS_EISA: /* EISA pin */ - { - trigger = default_EISA_trigger(idx); - break; - } - case MP_BUS_PCI: /* PCI pin */ - { - trigger = default_PCI_trigger(idx); - break; - } - case MP_BUS_MCA: /* MCA pin */ - { - trigger = default_MCA_trigger(idx); - break; - } - default: - { - printk(KERN_WARNING "broken BIOS!!\n"); - trigger = 1; - break; - } - } + if (test_bit(bus, mp_bus_not_pci)) + trigger = default_ISA_trigger(idx); + else + trigger = default_PCI_trigger(idx); break; - } case 1: /* edge */ { trigger = 0; @@ -764,49 +561,17 @@ 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; - irq = gsi_irq_sharing(irq); - break; - } - default: - { - printk(KERN_ERR "unknown bus type %d.\n",bus); - irq = 0; - break; - } - } - BUG_ON(irq >= NR_IRQS); - - /* - * PCI IRQ command line redirection. Yes, limits are hardcoded. - */ - if ((pin >= 16) && (pin <= 23)) { - if (pirq_entries[pin-16] != -1) { - if (!pirq_entries[pin-16]) { - apic_printk(APIC_VERBOSE, "disabling PIRQ%d\n", pin-16); - } else { - irq = pirq_entries[pin-16]; - apic_printk(APIC_VERBOSE, "using PIRQ%d -> IRQ %d\n", - pin-16, 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; + irq = gsi_irq_sharing(irq); } BUG_ON(irq >= NR_IRQS); return irq; @@ -943,9 +708,9 @@ static void __init setup_IO_APIC_irqs(void) if (!apic && (irq < 16)) disable_8259A_irq(irq); } + ioapic_write_entry(apic, pin, entry); + 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)); set_native_irq_info(irq, TARGET_CPUS); spin_unlock_irqrestore(&ioapic_lock, flags); } @@ -1083,10 +848,7 @@ void __apicdebuginit print_IO_APIC(void) for (i = 0; i <= reg_01.bits.entries; i++) { struct IO_APIC_route_entry entry; - spin_lock_irqsave(&ioapic_lock, flags); - *(((int *)&entry)+0) = io_apic_read(apic, 0x10+i*2); - *(((int *)&entry)+1) = io_apic_read(apic, 0x11+i*2); - spin_unlock_irqrestore(&ioapic_lock, flags); + entry = ioapic_read_entry(apic, i); printk(KERN_DEBUG " %02x %03X %02X ", i, @@ -1281,9 +1043,6 @@ static void __init enable_IO_APIC(void) irq_2_pin[i].pin = -1; irq_2_pin[i].next = 0; } - if (!pirqs_enabled) - for (i = 0; i < MAX_PIRQS; i++) - pirq_entries[i] = -1; /* * The number of IO-APIC IRQ registers (== #pins): @@ -1299,11 +1058,7 @@ static void __init enable_IO_APIC(void) /* See if any of the pins is in ExtINT mode */ for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) { struct IO_APIC_route_entry entry; - spin_lock_irqsave(&ioapic_lock, flags); - *(((int *)&entry) + 0) = io_apic_read(apic, 0x10 + 2 * pin); - *(((int *)&entry) + 1) = io_apic_read(apic, 0x11 + 2 * pin); - spin_unlock_irqrestore(&ioapic_lock, flags); - + entry = ioapic_read_entry(apic, pin); /* If the interrupt line is enabled and in ExtInt mode * I have found the pin where the i8259 is connected. @@ -1355,7 +1110,6 @@ void disable_IO_APIC(void) */ if (ioapic_i8259.pin != -1) { struct IO_APIC_route_entry entry; - unsigned long flags; memset(&entry, 0, sizeof(entry)); entry.mask = 0; /* Enabled */ @@ -1372,84 +1126,13 @@ void disable_IO_APIC(void) /* * Add it to the IO-APIC irq-routing table: */ - spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(ioapic_i8259.apic, 0x11+2*ioapic_i8259.pin, - *(((int *)&entry)+1)); - io_apic_write(ioapic_i8259.apic, 0x10+2*ioapic_i8259.pin, - *(((int *)&entry)+0)); - spin_unlock_irqrestore(&ioapic_lock, flags); + ioapic_write_entry(ioapic_i8259.apic, ioapic_i8259.pin, entry); } disconnect_bsp_APIC(ioapic_i8259.pin != -1); } /* - * function to set the IO-APIC physical IDs based on the - * values stored in the MPC table. - * - * by Matt Domsch <Matt_Domsch@dell.com> Tue Dec 21 12:25:05 CST 1999 - */ - -static void __init setup_ioapic_ids_from_mpc (void) -{ - union IO_APIC_reg_00 reg_00; - int apic; - int i; - unsigned char old_id; - unsigned long flags; - - /* - * Set the IOAPIC ID to the value stored in the MPC table. - */ - for (apic = 0; apic < nr_ioapics; apic++) { - - /* Read the register 0 value */ - spin_lock_irqsave(&ioapic_lock, flags); - reg_00.raw = io_apic_read(apic, 0); - spin_unlock_irqrestore(&ioapic_lock, flags); - - old_id = mp_ioapics[apic].mpc_apicid; - - - printk(KERN_INFO "Using IO-APIC %d\n", mp_ioapics[apic].mpc_apicid); - - - /* - * We need to adjust the IRQ routing table - * if the ID changed. - */ - if (old_id != mp_ioapics[apic].mpc_apicid) - for (i = 0; i < mp_irq_entries; i++) - if (mp_irqs[i].mpc_dstapic == old_id) - mp_irqs[i].mpc_dstapic - = mp_ioapics[apic].mpc_apicid; - - /* - * Read the right value from the MPC table and - * write it into the ID register. - */ - apic_printk(APIC_VERBOSE,KERN_INFO "...changing IO-APIC physical APIC ID to %d ...", - mp_ioapics[apic].mpc_apicid); - - reg_00.bits.ID = mp_ioapics[apic].mpc_apicid; - spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(apic, 0, reg_00.raw); - spin_unlock_irqrestore(&ioapic_lock, flags); - - /* - * Sanity check - */ - spin_lock_irqsave(&ioapic_lock, flags); - reg_00.raw = io_apic_read(apic, 0); - spin_unlock_irqrestore(&ioapic_lock, flags); - if (reg_00.bits.ID != mp_ioapics[apic].mpc_apicid) - printk("could not set ID!\n"); - else - apic_printk(APIC_VERBOSE," ok.\n"); - } -} - -/* * There is a nasty bug in some older SMP boards, their mptable lies * about the timer IRQ. We do the following to work around the situation: * @@ -1964,11 +1647,6 @@ void __init setup_IO_APIC(void) apic_printk(APIC_VERBOSE, "ENABLING IO-APIC IRQs\n"); - /* - * Set up the IO-APIC IRQ routing table. - */ - if (!acpi_ioapic) - setup_ioapic_ids_from_mpc(); sync_Arb_IDs(); setup_IO_APIC_irqs(); init_IO_APIC_traps(); @@ -1987,17 +1665,12 @@ static int ioapic_suspend(struct sys_device *dev, pm_message_t state) { struct IO_APIC_route_entry *entry; struct sysfs_ioapic_data *data; - unsigned long flags; int i; data = container_of(dev, struct sysfs_ioapic_data, dev); entry = data->entry; - spin_lock_irqsave(&ioapic_lock, flags); - for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ ) { - *(((int *)entry) + 1) = io_apic_read(dev->id, 0x11 + 2 * i); - *(((int *)entry) + 0) = io_apic_read(dev->id, 0x10 + 2 * i); - } - spin_unlock_irqrestore(&ioapic_lock, flags); + for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ ) + *entry = ioapic_read_entry(dev->id, i); return 0; } @@ -2019,11 +1692,9 @@ static int ioapic_resume(struct sys_device *dev) reg_00.bits.ID = mp_ioapics[dev->id].mpc_apicid; io_apic_write(dev->id, 0, reg_00.raw); } - for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ ) { - io_apic_write(dev->id, 0x11+2*i, *(((int *)entry)+1)); - io_apic_write(dev->id, 0x10+2*i, *(((int *)entry)+0)); - } spin_unlock_irqrestore(&ioapic_lock, flags); + for (i = 0; i < nr_ioapic_registers[dev->id]; i++) + ioapic_write_entry(dev->id, i, entry[i]); return 0; } @@ -2077,19 +1748,6 @@ device_initcall(ioapic_init_sysfs); #define IO_APIC_MAX_ID 0xFE -int __init io_apic_get_version (int ioapic) -{ - union IO_APIC_reg_01 reg_01; - unsigned long flags; - - spin_lock_irqsave(&ioapic_lock, flags); - reg_01.raw = io_apic_read(ioapic, 1); - spin_unlock_irqrestore(&ioapic_lock, flags); - - return reg_01.bits.version; -} - - int __init io_apic_get_redir_entries (int ioapic) { union IO_APIC_reg_01 reg_01; @@ -2148,10 +1806,10 @@ int io_apic_set_pci_routing (int ioapic, int pin, int irq, int triggering, int p if (!ioapic && (irq < 16)) disable_8259A_irq(irq); + ioapic_write_entry(ioapic, pin, entry); + spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(ioapic, 0x11+2*pin, *(((int *)&entry)+1)); - io_apic_write(ioapic, 0x10+2*pin, *(((int *)&entry)+0)); - set_native_irq_info(use_pci_vector() ? entry.vector : irq, TARGET_CPUS); + set_native_irq_info(use_pci_vector() ? entry.vector : irq, TARGET_CPUS); spin_unlock_irqrestore(&ioapic_lock, flags); return 0; diff --git a/arch/x86_64/kernel/ioport.c b/arch/x86_64/kernel/ioport.c index b816149..fe063d3 100644 --- a/arch/x86_64/kernel/ioport.c +++ b/arch/x86_64/kernel/ioport.c @@ -56,6 +56,7 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) memset(bitmap, 0xff, IO_BITMAP_BYTES); t->io_bitmap_ptr = bitmap; + set_thread_flag(TIF_IO_BITMAP); } /* diff --git a/arch/x86_64/kernel/irq.c b/arch/x86_64/kernel/irq.c index 5221a53..b3677e6 100644 --- a/arch/x86_64/kernel/irq.c +++ b/arch/x86_64/kernel/irq.c @@ -20,11 +20,6 @@ #include <asm/idle.h> atomic_t irq_err_count; -#ifdef CONFIG_X86_IO_APIC -#ifdef APIC_MISMATCH_DEBUG -atomic_t irq_mis_count; -#endif -#endif #ifdef CONFIG_DEBUG_STACKOVERFLOW /* @@ -92,18 +87,11 @@ skip: for_each_online_cpu(j) seq_printf(p, "%10u ", cpu_pda(j)->__nmi_count); seq_putc(p, '\n'); -#ifdef CONFIG_X86_LOCAL_APIC seq_printf(p, "LOC: "); for_each_online_cpu(j) seq_printf(p, "%10u ", cpu_pda(j)->apic_timer_irqs); seq_putc(p, '\n'); -#endif seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count)); -#ifdef CONFIG_X86_IO_APIC -#ifdef APIC_MISMATCH_DEBUG - seq_printf(p, "MIS: %10u\n", atomic_read(&irq_mis_count)); -#endif -#endif } return 0; } diff --git a/arch/x86_64/kernel/machine_kexec.c b/arch/x86_64/kernel/machine_kexec.c index 106076b..0497e3b 100644 --- a/arch/x86_64/kernel/machine_kexec.c +++ b/arch/x86_64/kernel/machine_kexec.c @@ -15,6 +15,15 @@ #include <asm/mmu_context.h> #include <asm/io.h> +#define PAGE_ALIGNED __attribute__ ((__aligned__(PAGE_SIZE))) +static u64 kexec_pgd[512] PAGE_ALIGNED; +static u64 kexec_pud0[512] PAGE_ALIGNED; +static u64 kexec_pmd0[512] PAGE_ALIGNED; +static u64 kexec_pte0[512] PAGE_ALIGNED; +static u64 kexec_pud1[512] PAGE_ALIGNED; +static u64 kexec_pmd1[512] PAGE_ALIGNED; +static u64 kexec_pte1[512] PAGE_ALIGNED; + static void init_level2_page(pmd_t *level2p, unsigned long addr) { unsigned long end_addr; @@ -144,32 +153,19 @@ static void load_segments(void) ); } -typedef NORET_TYPE void (*relocate_new_kernel_t)(unsigned long indirection_page, - unsigned long control_code_buffer, - unsigned long start_address, - unsigned long pgtable) ATTRIB_NORET; - -extern const unsigned char relocate_new_kernel[]; -extern const unsigned long relocate_new_kernel_size; - int machine_kexec_prepare(struct kimage *image) { - unsigned long start_pgtable, control_code_buffer; + unsigned long start_pgtable; int result; /* Calculate the offsets */ start_pgtable = page_to_pfn(image->control_code_page) << PAGE_SHIFT; - control_code_buffer = start_pgtable + PAGE_SIZE; /* Setup the identity mapped 64bit page table */ result = init_pgtable(image, start_pgtable); if (result) return result; - /* Place the code in the reboot code buffer */ - memcpy(__va(control_code_buffer), relocate_new_kernel, - relocate_new_kernel_size); - return 0; } @@ -184,28 +180,34 @@ void machine_kexec_cleanup(struct kimage *image) */ NORET_TYPE void machine_kexec(struct kimage *image) { - unsigned long page_list; - unsigned long control_code_buffer; - unsigned long start_pgtable; - relocate_new_kernel_t rnk; + unsigned long page_list[PAGES_NR]; + void *control_page; /* Interrupts aren't acceptable while we reboot */ local_irq_disable(); - /* Calculate the offsets */ - page_list = image->head; - start_pgtable = page_to_pfn(image->control_code_page) << PAGE_SHIFT; - control_code_buffer = start_pgtable + PAGE_SIZE; - - /* Set the low half of the page table to my identity mapped - * page table for kexec. Leave the high half pointing at the - * kernel pages. Don't bother to flush the global pages - * as that will happen when I fully switch to my identity mapped - * page table anyway. - */ - memcpy(__va(read_cr3()), __va(start_pgtable), PAGE_SIZE/2); - __flush_tlb(); - + control_page = page_address(image->control_code_page) + PAGE_SIZE; + memcpy(control_page, relocate_kernel, PAGE_SIZE); + + page_list[PA_CONTROL_PAGE] = __pa(control_page); + page_list[VA_CONTROL_PAGE] = (unsigned long)relocate_kernel; + page_list[PA_PGD] = __pa(kexec_pgd); + page_list[VA_PGD] = (unsigned long)kexec_pgd; + page_list[PA_PUD_0] = __pa(kexec_pud0); + page_list[VA_PUD_0] = (unsigned long)kexec_pud0; + page_list[PA_PMD_0] = __pa(kexec_pmd0); + page_list[VA_PMD_0] = (unsigned long)kexec_pmd0; + page_list[PA_PTE_0] = __pa(kexec_pte0); + page_list[VA_PTE_0] = (unsigned long)kexec_pte0; + page_list[PA_PUD_1] = __pa(kexec_pud1); + page_list[VA_PUD_1] = (unsigned long)kexec_pud1; + page_list[PA_PMD_1] = __pa(kexec_pmd1); + page_list[VA_PMD_1] = (unsigned long)kexec_pmd1; + page_list[PA_PTE_1] = __pa(kexec_pte1); + page_list[VA_PTE_1] = (unsigned long)kexec_pte1; + + page_list[PA_TABLE_PAGE] = + (unsigned long)__pa(page_address(image->control_code_page)); /* The segment registers are funny things, they have both a * visible and an invisible part. Whenever the visible part is @@ -222,7 +224,36 @@ NORET_TYPE void machine_kexec(struct kimage *image) */ set_gdt(phys_to_virt(0),0); set_idt(phys_to_virt(0),0); + /* now call it */ - rnk = (relocate_new_kernel_t) control_code_buffer; - (*rnk)(page_list, control_code_buffer, image->start, start_pgtable); + relocate_kernel((unsigned long)image->head, (unsigned long)page_list, + image->start); } + +/* crashkernel=size@addr specifies the location to reserve for + * a crash kernel. By reserving this memory we guarantee + * that linux never set's it up as a DMA target. + * Useful for holding code to do something appropriate + * after a kernel panic. + */ +static int __init setup_crashkernel(char *arg) +{ + unsigned long size, base; + char *p; + if (!arg) + return -EINVAL; + size = memparse(arg, &p); + if (arg == p) + return -EINVAL; + if (*p == '@') { + base = memparse(p+1, &p); + /* FIXME: Do I want a sanity check to validate the + * memory range? Yes you do, but it's too early for + * e820 -AK */ + crashk_res.start = base; + crashk_res.end = base + size - 1; + } + return 0; +} +early_param("crashkernel", setup_crashkernel); + diff --git a/arch/x86_64/kernel/mce.c b/arch/x86_64/kernel/mce.c index 4e017fb..bbea888 100644 --- a/arch/x86_64/kernel/mce.c +++ b/arch/x86_64/kernel/mce.c @@ -182,7 +182,7 @@ void do_machine_check(struct pt_regs * regs, long error_code) goto out2; memset(&m, 0, sizeof(struct mce)); - m.cpu = safe_smp_processor_id(); + m.cpu = smp_processor_id(); rdmsrl(MSR_IA32_MCG_STATUS, m.mcgstatus); if (!(m.mcgstatus & MCG_STATUS_RIPV)) kill_it = 1; @@ -274,6 +274,33 @@ void do_machine_check(struct pt_regs * regs, long error_code) atomic_dec(&mce_entry); } +#ifdef CONFIG_X86_MCE_INTEL +/*** + * mce_log_therm_throt_event - Logs the thermal throttling event to mcelog + * @cpu: The CPU on which the event occured. + * @status: Event status information + * + * This function should be called by the thermal interrupt after the + * event has been processed and the decision was made to log the event + * further. + * + * The status parameter will be saved to the 'status' field of 'struct mce' + * and historically has been the register value of the + * MSR_IA32_THERMAL_STATUS (Intel) msr. + */ +void mce_log_therm_throt_event(unsigned int cpu, __u64 status) +{ + struct mce m; + + memset(&m, 0, sizeof(m)); + m.cpu = cpu; + m.bank = MCE_THERMAL_BANK; + m.status = status; + rdtscll(m.tsc); + mce_log(&m); +} +#endif /* CONFIG_X86_MCE_INTEL */ + /* * Periodic polling timer for "silent" machine check errors. */ diff --git a/arch/x86_64/kernel/mce_intel.c b/arch/x86_64/kernel/mce_intel.c index 8f533d2..6551505 100644 --- a/arch/x86_64/kernel/mce_intel.c +++ b/arch/x86_64/kernel/mce_intel.c @@ -11,36 +11,21 @@ #include <asm/mce.h> #include <asm/hw_irq.h> #include <asm/idle.h> - -static DEFINE_PER_CPU(unsigned long, next_check); +#include <asm/therm_throt.h> asmlinkage void smp_thermal_interrupt(void) { - struct mce m; + __u64 msr_val; ack_APIC_irq(); exit_idle(); irq_enter(); - if (time_before(jiffies, __get_cpu_var(next_check))) - goto done; - - __get_cpu_var(next_check) = jiffies + HZ*300; - memset(&m, 0, sizeof(m)); - m.cpu = smp_processor_id(); - m.bank = MCE_THERMAL_BANK; - rdtscll(m.tsc); - rdmsrl(MSR_IA32_THERM_STATUS, m.status); - if (m.status & 0x1) { - printk(KERN_EMERG - "CPU%d: Temperature above threshold, cpu clock throttled\n", m.cpu); - add_taint(TAINT_MACHINE_CHECK); - } else { - printk(KERN_EMERG "CPU%d: Temperature/speed normal\n", m.cpu); - } - mce_log(&m); -done: + rdmsrl(MSR_IA32_THERM_STATUS, msr_val); + if (therm_throt_process(msr_val & 1)) + mce_log_therm_throt_event(smp_processor_id(), msr_val); + irq_exit(); } @@ -92,6 +77,9 @@ static void __cpuinit intel_init_thermal(struct cpuinfo_x86 *c) apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED); printk(KERN_INFO "CPU%d: Thermal monitoring enabled (%s)\n", cpu, tm2 ? "TM2" : "TM1"); + + /* enable thermal throttle processing */ + atomic_set(&therm_throt_en, 1); return; } diff --git a/arch/x86_64/kernel/mpparse.c b/arch/x86_64/kernel/mpparse.c index a1ab419..20e88f4 100644 --- a/arch/x86_64/kernel/mpparse.c +++ b/arch/x86_64/kernel/mpparse.c @@ -41,8 +41,7 @@ int acpi_found_madt; * Various Linux-internal data structures created from the * MP-table. */ -unsigned char apic_version [MAX_APICS]; -unsigned char mp_bus_id_to_type [MAX_MP_BUSSES] = { [0 ... MAX_MP_BUSSES-1] = -1 }; +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; @@ -56,7 +55,6 @@ struct mpc_config_intsrc mp_irqs[MAX_IRQ_SOURCES]; int mp_irq_entries; int nr_ioapics; -int pic_mode; unsigned long mp_lapic_addr = 0; @@ -71,19 +69,6 @@ unsigned disabled_cpus __initdata; /* Bitmask of physically existing CPUs */ physid_mask_t phys_cpu_present_map = PHYSID_MASK_NONE; -/* ACPI MADT entry parsing functions */ -#ifdef CONFIG_ACPI -extern struct acpi_boot_flags acpi_boot; -#ifdef CONFIG_X86_LOCAL_APIC -extern int acpi_parse_lapic (acpi_table_entry_header *header); -extern int acpi_parse_lapic_addr_ovr (acpi_table_entry_header *header); -extern int acpi_parse_lapic_nmi (acpi_table_entry_header *header); -#endif /*CONFIG_X86_LOCAL_APIC*/ -#ifdef CONFIG_X86_IO_APIC -extern int acpi_parse_ioapic (acpi_table_entry_header *header); -#endif /*CONFIG_X86_IO_APIC*/ -#endif /*CONFIG_ACPI*/ - u8 bios_cpu_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID }; @@ -108,24 +93,20 @@ static int __init mpf_checksum(unsigned char *mp, int len) static void __cpuinit MP_processor_info (struct mpc_config_processor *m) { int cpu; - unsigned char ver; cpumask_t tmp_map; + char *bootup_cpu = ""; if (!(m->mpc_cpuflag & CPU_ENABLED)) { disabled_cpus++; return; } - - printk(KERN_INFO "Processor #%d %d:%d APIC version %d\n", - m->mpc_apicid, - (m->mpc_cpufeature & CPU_FAMILY_MASK)>>8, - (m->mpc_cpufeature & CPU_MODEL_MASK)>>4, - m->mpc_apicver); - if (m->mpc_cpuflag & CPU_BOOTPROCESSOR) { - Dprintk(" Bootup CPU\n"); + 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); @@ -136,24 +117,7 @@ static void __cpuinit MP_processor_info (struct mpc_config_processor *m) cpus_complement(tmp_map, cpu_present_map); cpu = first_cpu(tmp_map); -#if MAX_APICS < 255 - if ((int)m->mpc_apicid > MAX_APICS) { - printk(KERN_ERR "Processor #%d INVALID. (Max ID: %d).\n", - m->mpc_apicid, MAX_APICS); - return; - } -#endif - ver = m->mpc_apicver; - physid_set(m->mpc_apicid, phys_cpu_present_map); - /* - * Validate version - */ - if (ver == 0x0) { - printk(KERN_ERR "BIOS bug, APIC version is 0 for CPU#%d! fixing up to 0x10. (tell your hw vendor)\n", m->mpc_apicid); - ver = 0x10; - } - apic_version[m->mpc_apicid] = ver; if (m->mpc_cpuflag & CPU_BOOTPROCESSOR) { /* * bios_cpu_apicid is required to have processors listed @@ -178,15 +142,11 @@ static void __init MP_bus_info (struct mpc_config_bus *m) Dprintk("Bus #%d is %s\n", m->mpc_busid, str); if (strncmp(str, "ISA", 3) == 0) { - mp_bus_id_to_type[m->mpc_busid] = MP_BUS_ISA; - } else if (strncmp(str, "EISA", 4) == 0) { - mp_bus_id_to_type[m->mpc_busid] = MP_BUS_EISA; + set_bit(m->mpc_busid, mp_bus_not_pci); } else if (strncmp(str, "PCI", 3) == 0) { - mp_bus_id_to_type[m->mpc_busid] = MP_BUS_PCI; + 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, "MCA", 3) == 0) { - mp_bus_id_to_type[m->mpc_busid] = MP_BUS_MCA; } else { printk(KERN_ERR "Unknown bustype %s\n", str); } @@ -197,8 +157,8 @@ static void __init MP_ioapic_info (struct mpc_config_ioapic *m) if (!(m->mpc_flags & MPC_APIC_USABLE)) return; - printk("I/O APIC #%d Version %d at 0x%X.\n", - m->mpc_apicid, m->mpc_apicver, m->mpc_apicaddr); + printk("I/O APIC #%d at 0x%X.\n", + m->mpc_apicid, m->mpc_apicaddr); if (nr_ioapics >= MAX_IO_APICS) { printk(KERN_ERR "Max # of I/O APICs (%d) exceeded (found %d).\n", MAX_IO_APICS, nr_ioapics); @@ -232,19 +192,6 @@ static void __init MP_lintsrc_info (struct mpc_config_lintsrc *m) m->mpc_irqtype, m->mpc_irqflag & 3, (m->mpc_irqflag >> 2) &3, m->mpc_srcbusid, m->mpc_srcbusirq, m->mpc_destapic, m->mpc_destapiclint); - /* - * Well it seems all SMP boards in existence - * use ExtINT/LVT1 == LINT0 and - * NMI/LVT2 == LINT1 - the following check - * will show us if this assumptions is false. - * Until then we do not have to add baggage. - */ - if ((m->mpc_irqtype == mp_ExtINT) && - (m->mpc_destapiclint != 0)) - BUG(); - if ((m->mpc_irqtype == mp_NMI) && - (m->mpc_destapiclint != 1)) - BUG(); } /* @@ -258,7 +205,7 @@ static int __init smp_read_mpc(struct mp_config_table *mpc) unsigned char *mpt=((unsigned char *)mpc)+count; if (memcmp(mpc->mpc_signature,MPC_SIGNATURE,4)) { - printk("SMP mptable: bad signature [%c%c%c%c]!\n", + printk("MPTABLE: bad signature [%c%c%c%c]!\n", mpc->mpc_signature[0], mpc->mpc_signature[1], mpc->mpc_signature[2], @@ -266,31 +213,31 @@ static int __init smp_read_mpc(struct mp_config_table *mpc) return 0; } if (mpf_checksum((unsigned char *)mpc,mpc->mpc_length)) { - printk("SMP mptable: checksum error!\n"); + printk("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", + 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(str,mpc->mpc_oem,8); - str[8]=0; - printk(KERN_INFO "OEM ID: %s ",str); + str[8] = 0; + printk(KERN_INFO "MPTABLE: OEM ID: %s ",str); memcpy(str,mpc->mpc_productid,12); - str[12]=0; - printk("Product ID: %s ",str); + str[12] = 0; + printk("MPTABLE: Product ID: %s ",str); - printk("APIC at: 0x%X\n",mpc->mpc_lapic); + 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; + mp_lapic_addr = mpc->mpc_lapic; /* * Now process the configuration blocks. @@ -302,7 +249,7 @@ static int __init smp_read_mpc(struct mp_config_table *mpc) struct mpc_config_processor *m= (struct mpc_config_processor *)mpt; if (!acpi_lapic) - MP_processor_info(m); + MP_processor_info(m); mpt += sizeof(*m); count += sizeof(*m); break; @@ -321,8 +268,8 @@ static int __init smp_read_mpc(struct mp_config_table *mpc) struct mpc_config_ioapic *m= (struct mpc_config_ioapic *)mpt; MP_ioapic_info(m); - mpt+=sizeof(*m); - count+=sizeof(*m); + mpt += sizeof(*m); + count += sizeof(*m); break; } case MP_INTSRC: @@ -331,8 +278,8 @@ static int __init smp_read_mpc(struct mp_config_table *mpc) (struct mpc_config_intsrc *)mpt; MP_intsrc_info(m); - mpt+=sizeof(*m); - count+=sizeof(*m); + mpt += sizeof(*m); + count += sizeof(*m); break; } case MP_LINTSRC: @@ -340,15 +287,15 @@ static int __init smp_read_mpc(struct mp_config_table *mpc) struct mpc_config_lintsrc *m= (struct mpc_config_lintsrc *)mpt; MP_lintsrc_info(m); - mpt+=sizeof(*m); - count+=sizeof(*m); + mpt += sizeof(*m); + count += sizeof(*m); break; } } } clustered_apic_check(); if (!num_processors) - printk(KERN_ERR "SMP mptable: no processors registered!\n"); + printk(KERN_ERR "MPTABLE: no processors registered!\n"); return num_processors; } @@ -444,13 +391,10 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type) * 2 CPUs, numbered 0 & 1. */ processor.mpc_type = MP_PROCESSOR; - /* Either an integrated APIC or a discrete 82489DX. */ - processor.mpc_apicver = mpc_default_type > 4 ? 0x10 : 0x01; + processor.mpc_apicver = 0; processor.mpc_cpuflag = CPU_ENABLED; - processor.mpc_cpufeature = (boot_cpu_data.x86 << 8) | - (boot_cpu_data.x86_model << 4) | - boot_cpu_data.x86_mask; - processor.mpc_featureflag = boot_cpu_data.x86_capability[0]; + processor.mpc_cpufeature = 0; + processor.mpc_featureflag = 0; processor.mpc_reserved[0] = 0; processor.mpc_reserved[1] = 0; for (i = 0; i < 2; i++) { @@ -469,14 +413,6 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type) 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) { @@ -487,7 +423,7 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type) ioapic.mpc_type = MP_IOAPIC; ioapic.mpc_apicid = 2; - ioapic.mpc_apicver = mpc_default_type > 4 ? 0x10 : 0x01; + ioapic.mpc_apicver = 0; ioapic.mpc_flags = MPC_APIC_USABLE; ioapic.mpc_apicaddr = 0xFEC00000; MP_ioapic_info(&ioapic); @@ -530,13 +466,6 @@ void __init get_smp_config (void) printk(KERN_INFO "Using ACPI for processor (LAPIC) configuration information\n"); printk("Intel MultiProcessor Specification v1.%d\n", mpf->mpf_specification); - 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; - } /* * Now see if we need to read further. @@ -616,7 +545,7 @@ static int __init smp_scan_config (unsigned long base, unsigned long length) return 0; } -void __init find_intel_smp (void) +void __init find_smp_config(void) { unsigned int address; @@ -633,9 +562,7 @@ void __init find_intel_smp (void) smp_scan_config(0xF0000,0x10000)) return; /* - * If it is an SMP machine we should know now, unless the - * configuration is in an EISA/MCA bus machine with an - * extended bios data area. + * 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. @@ -656,69 +583,41 @@ void __init find_intel_smp (void) printk(KERN_INFO "No mptable found.\n"); } -/* - * - Intel MP Configuration Table - */ -void __init find_smp_config (void) -{ -#ifdef CONFIG_X86_LOCAL_APIC - find_intel_smp(); -#endif -} - - /* -------------------------------------------------------------------------- ACPI-based MP Configuration -------------------------------------------------------------------------- */ #ifdef CONFIG_ACPI -void __init mp_register_lapic_address ( - u64 address) +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)); - - Dprintk("Boot CPU = %d\n", boot_cpu_physical_apicid); } - -void __cpuinit mp_register_lapic ( - u8 id, - u8 enabled) +void __cpuinit mp_register_lapic (u8 id, u8 enabled) { struct mpc_config_processor processor; int boot_cpu = 0; - if (id >= MAX_APICS) { - printk(KERN_WARNING "Processor #%d invalid (max %d)\n", - id, MAX_APICS); - return; - } - - if (id == boot_cpu_physical_apicid) + if (id == boot_cpu_id) boot_cpu = 1; processor.mpc_type = MP_PROCESSOR; processor.mpc_apicid = id; - processor.mpc_apicver = GET_APIC_VERSION(apic_read(APIC_LVR)); + processor.mpc_apicver = 0; 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_cpufeature = 0; + processor.mpc_featureflag = 0; processor.mpc_reserved[0] = 0; processor.mpc_reserved[1] = 0; MP_processor_info(&processor); } -#ifdef CONFIG_X86_IO_APIC - #define MP_ISA_BUS 0 #define MP_MAX_IOAPIC_PIN 127 @@ -729,11 +628,9 @@ static struct mp_ioapic_routing { u32 pin_programmed[4]; } mp_ioapic_routing[MAX_IO_APICS]; - -static int mp_find_ioapic ( - int gsi) +static int mp_find_ioapic(int gsi) { - int i = 0; + int i = 0; /* Find the IOAPIC that manages this GSI. */ for (i = 0; i < nr_ioapics; i++) { @@ -743,17 +640,12 @@ static int mp_find_ioapic ( } 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) +void __init mp_register_ioapic(u8 id, u32 address, u32 gsi_base) { - int idx = 0; + int idx = 0; if (nr_ioapics >= MAX_IO_APICS) { printk(KERN_ERR "ERROR: Max # of I/O APICs (%d) exceeded " @@ -774,7 +666,7 @@ void __init mp_register_ioapic ( set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address); mp_ioapics[idx].mpc_apicid = id; - mp_ioapics[idx].mpc_apicver = io_apic_get_version(idx); + mp_ioapics[idx].mpc_apicver = 0; /* * Build basic IRQ lookup table to facilitate gsi->io_apic lookups @@ -785,21 +677,15 @@ void __init mp_register_ioapic ( mp_ioapic_routing[idx].gsi_end = gsi_base + io_apic_get_redir_entries(idx); - printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%x, " + 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_apicver, mp_ioapics[idx].mpc_apicaddr, + mp_ioapics[idx].mpc_apicaddr, mp_ioapic_routing[idx].gsi_start, mp_ioapic_routing[idx].gsi_end); - - return; } - -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; @@ -837,22 +723,18 @@ void __init mp_override_legacy_irq ( mp_irqs[mp_irq_entries] = intsrc; if (++mp_irq_entries == MAX_IRQ_SOURCES) panic("Max # of irq sources exceeded!\n"); - - return; } - -void __init mp_config_acpi_legacy_irqs (void) +void __init mp_config_acpi_legacy_irqs(void) { struct mpc_config_intsrc intsrc; - int i = 0; - int ioapic = -1; + int i = 0; + int ioapic = -1; /* * Fabricate the legacy ISA bus (bus #31). */ - mp_bus_id_to_type[MP_ISA_BUS] = MP_BUS_ISA; - Dprintk("Bus #%d is ISA\n", MP_ISA_BUS); + set_bit(MP_ISA_BUS, mp_bus_not_pci); /* * Locate the IOAPIC that manages the ISA IRQs (0-15). @@ -905,24 +787,22 @@ void __init mp_config_acpi_legacy_irqs (void) if (++mp_irq_entries == MAX_IRQ_SOURCES) panic("Max # of irq sources exceeded!\n"); } - - return; } #define MAX_GSI_NUM 4096 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 = 16; + int ioapic = -1; + int ioapic_pin = 0; + int idx, bit = 0; + static int pci_irq = 16; /* * Mapping between Global System Interrupts, which * represent all possible interrupts, to the IRQs * assigned to actual devices. */ - static int gsi_to_irq[MAX_GSI_NUM]; + static int gsi_to_irq[MAX_GSI_NUM]; if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC) return gsi; @@ -996,6 +876,4 @@ int mp_register_gsi(u32 gsi, int triggering, int polarity) polarity == ACPI_ACTIVE_HIGH ? 0 : 1); return gsi; } - -#endif /*CONFIG_X86_IO_APIC*/ #endif /*CONFIG_ACPI*/ diff --git a/arch/x86_64/kernel/nmi.c b/arch/x86_64/kernel/nmi.c index 5baa0c7..4d6fb04 100644 --- a/arch/x86_64/kernel/nmi.c +++ b/arch/x86_64/kernel/nmi.c @@ -28,71 +28,138 @@ #include <asm/mce.h> #include <asm/intel_arch_perfmon.h> -/* - * lapic_nmi_owner tracks the ownership of the lapic NMI hardware: - * - it may be reserved by some other driver, or not - * - when not reserved by some other driver, it may be used for - * the NMI watchdog, or not - * - * This is maintained separately from nmi_active because the NMI - * watchdog may also be driven from the I/O APIC timer. +/* perfctr_nmi_owner tracks the ownership of the perfctr registers: + * evtsel_nmi_owner tracks the ownership of the event selection + * - different performance counters/ event selection may be reserved for + * different subsystems this reservation system just tries to coordinate + * things a little */ -static DEFINE_SPINLOCK(lapic_nmi_owner_lock); -static unsigned int lapic_nmi_owner; -#define LAPIC_NMI_WATCHDOG (1<<0) -#define LAPIC_NMI_RESERVED (1<<1) +static DEFINE_PER_CPU(unsigned, perfctr_nmi_owner); +static DEFINE_PER_CPU(unsigned, evntsel_nmi_owner[2]); + +/* this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's + * offset from MSR_P4_BSU_ESCR0. It will be the max for all platforms (for now) + */ +#define NMI_MAX_COUNTER_BITS 66 /* nmi_active: - * +1: the lapic NMI watchdog is active, but can be disabled - * 0: the lapic NMI watchdog has not been set up, and cannot + * >0: the lapic NMI watchdog is active, but can be disabled + * <0: the lapic NMI watchdog has not been set up, and cannot * be enabled - * -1: the lapic NMI watchdog is disabled, but can be enabled + * 0: the lapic NMI watchdog is disabled, but can be enabled */ -int nmi_active; /* oprofile uses this */ +atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */ int panic_on_timeout; unsigned int nmi_watchdog = NMI_DEFAULT; static unsigned int nmi_hz = HZ; -static unsigned int nmi_perfctr_msr; /* the MSR to reset in NMI handler */ -static unsigned int nmi_p4_cccr_val; -/* Note that these events don't tick when the CPU idles. This means - the frequency varies with CPU load. */ +struct nmi_watchdog_ctlblk { + int enabled; + u64 check_bit; + unsigned int cccr_msr; + unsigned int perfctr_msr; /* the MSR to reset in NMI handler */ + unsigned int evntsel_msr; /* the MSR to select the events to handle */ +}; +static DEFINE_PER_CPU(struct nmi_watchdog_ctlblk, nmi_watchdog_ctlblk); -#define K7_EVNTSEL_ENABLE (1 << 22) -#define K7_EVNTSEL_INT (1 << 20) -#define K7_EVNTSEL_OS (1 << 17) -#define K7_EVNTSEL_USR (1 << 16) -#define K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING 0x76 -#define K7_NMI_EVENT K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING +/* local prototypes */ +static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu); -#define ARCH_PERFMON_NMI_EVENT_SEL ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL -#define ARCH_PERFMON_NMI_EVENT_UMASK ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK +/* converts an msr to an appropriate reservation bit */ +static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr) +{ + /* returns the bit offset of the performance counter register */ + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_AMD: + return (msr - MSR_K7_PERFCTR0); + case X86_VENDOR_INTEL: + if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) + return (msr - MSR_ARCH_PERFMON_PERFCTR0); + else + return (msr - MSR_P4_BPU_PERFCTR0); + } + return 0; +} -#define MSR_P4_MISC_ENABLE 0x1A0 -#define MSR_P4_MISC_ENABLE_PERF_AVAIL (1<<7) -#define MSR_P4_MISC_ENABLE_PEBS_UNAVAIL (1<<12) -#define MSR_P4_PERFCTR0 0x300 -#define MSR_P4_CCCR0 0x360 -#define P4_ESCR_EVENT_SELECT(N) ((N)<<25) -#define P4_ESCR_OS (1<<3) -#define P4_ESCR_USR (1<<2) -#define P4_CCCR_OVF_PMI0 (1<<26) -#define P4_CCCR_OVF_PMI1 (1<<27) -#define P4_CCCR_THRESHOLD(N) ((N)<<20) -#define P4_CCCR_COMPLEMENT (1<<19) -#define P4_CCCR_COMPARE (1<<18) -#define P4_CCCR_REQUIRED (3<<16) -#define P4_CCCR_ESCR_SELECT(N) ((N)<<13) -#define P4_CCCR_ENABLE (1<<12) -/* Set up IQ_COUNTER0 to behave like a clock, by having IQ_CCCR0 filter - CRU_ESCR0 (with any non-null event selector) through a complemented - max threshold. [IA32-Vol3, Section 14.9.9] */ -#define MSR_P4_IQ_COUNTER0 0x30C -#define P4_NMI_CRU_ESCR0 (P4_ESCR_EVENT_SELECT(0x3F)|P4_ESCR_OS|P4_ESCR_USR) -#define P4_NMI_IQ_CCCR0 \ - (P4_CCCR_OVF_PMI0|P4_CCCR_THRESHOLD(15)|P4_CCCR_COMPLEMENT| \ - P4_CCCR_COMPARE|P4_CCCR_REQUIRED|P4_CCCR_ESCR_SELECT(4)|P4_CCCR_ENABLE) +/* converts an msr to an appropriate reservation bit */ +static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr) +{ + /* returns the bit offset of the event selection register */ + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_AMD: + return (msr - MSR_K7_EVNTSEL0); + case X86_VENDOR_INTEL: + if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) + return (msr - MSR_ARCH_PERFMON_EVENTSEL0); + else + return (msr - MSR_P4_BSU_ESCR0); + } + return 0; +} + +/* checks for a bit availability (hack for oprofile) */ +int avail_to_resrv_perfctr_nmi_bit(unsigned int counter) +{ + BUG_ON(counter > NMI_MAX_COUNTER_BITS); + + return (!test_bit(counter, &__get_cpu_var(perfctr_nmi_owner))); +} + +/* checks the an msr for availability */ +int avail_to_resrv_perfctr_nmi(unsigned int msr) +{ + unsigned int counter; + + counter = nmi_perfctr_msr_to_bit(msr); + BUG_ON(counter > NMI_MAX_COUNTER_BITS); + + return (!test_bit(counter, &__get_cpu_var(perfctr_nmi_owner))); +} + +int reserve_perfctr_nmi(unsigned int msr) +{ + unsigned int counter; + + counter = nmi_perfctr_msr_to_bit(msr); + BUG_ON(counter > NMI_MAX_COUNTER_BITS); + + if (!test_and_set_bit(counter, &__get_cpu_var(perfctr_nmi_owner))) + return 1; + return 0; +} + +void release_perfctr_nmi(unsigned int msr) +{ + unsigned int counter; + + counter = nmi_perfctr_msr_to_bit(msr); + BUG_ON(counter > NMI_MAX_COUNTER_BITS); + + clear_bit(counter, &__get_cpu_var(perfctr_nmi_owner)); +} + +int reserve_evntsel_nmi(unsigned int msr) +{ + unsigned int counter; + + counter = nmi_evntsel_msr_to_bit(msr); + BUG_ON(counter > NMI_MAX_COUNTER_BITS); + + if (!test_and_set_bit(counter, &__get_cpu_var(evntsel_nmi_owner))) + return 1; + return 0; +} + +void release_evntsel_nmi(unsigned int msr) +{ + unsigned int counter; + + counter = nmi_evntsel_msr_to_bit(msr); + BUG_ON(counter > NMI_MAX_COUNTER_BITS); + + clear_bit(counter, &__get_cpu_var(evntsel_nmi_owner)); +} static __cpuinit inline int nmi_known_cpu(void) { @@ -109,7 +176,7 @@ static __cpuinit inline int nmi_known_cpu(void) } /* Run after command line and cpu_init init, but before all other checks */ -void __cpuinit nmi_watchdog_default(void) +void nmi_watchdog_default(void) { if (nmi_watchdog != NMI_DEFAULT) return; @@ -145,6 +212,12 @@ int __init check_nmi_watchdog (void) int *counts; int cpu; + if ((nmi_watchdog == NMI_NONE) || (nmi_watchdog == NMI_DEFAULT)) + return 0; + + if (!atomic_read(&nmi_active)) + return 0; + counts = kmalloc(NR_CPUS * sizeof(int), GFP_KERNEL); if (!counts) return -1; @@ -162,26 +235,43 @@ int __init check_nmi_watchdog (void) mdelay((10*1000)/nmi_hz); // wait 10 ticks for_each_online_cpu(cpu) { + if (!per_cpu(nmi_watchdog_ctlblk, cpu).enabled) + continue; if (cpu_pda(cpu)->__nmi_count - counts[cpu] <= 5) { - endflag = 1; printk("CPU#%d: NMI appears to be stuck (%d->%d)!\n", cpu, counts[cpu], cpu_pda(cpu)->__nmi_count); - nmi_active = 0; - lapic_nmi_owner &= ~LAPIC_NMI_WATCHDOG; - nmi_perfctr_msr = 0; - kfree(counts); - return -1; + per_cpu(nmi_watchdog_ctlblk, cpu).enabled = 0; + atomic_dec(&nmi_active); } } + if (!atomic_read(&nmi_active)) { + kfree(counts); + atomic_set(&nmi_active, -1); + return -1; + } endflag = 1; printk("OK.\n"); /* now that we know it works we can reduce NMI frequency to something more reasonable; makes a difference in some configs */ - if (nmi_watchdog == NMI_LOCAL_APIC) + if (nmi_watchdog == NMI_LOCAL_APIC) { + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); + nmi_hz = 1; + /* + * On Intel CPUs with ARCH_PERFMON only 32 bits in the counter + * are writable, with higher bits sign extending from bit 31. + * So, we can only program the counter with 31 bit values and + * 32nd bit should be 1, for 33.. to be 1. + * Find the appropriate nmi_hz + */ + if (wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0 && + ((u64)cpu_khz * 1000) > 0x7fffffffULL) { + nmi_hz = ((u64)cpu_khz * 1000) / 0x7fffffffUL + 1; + } + } kfree(counts); return 0; @@ -201,91 +291,65 @@ int __init setup_nmi_watchdog(char *str) get_option(&str, &nmi); - if (nmi >= NMI_INVALID) + if ((nmi >= NMI_INVALID) || (nmi < NMI_NONE)) return 0; + + if ((nmi == NMI_LOCAL_APIC) && (nmi_known_cpu() == 0)) + return 0; /* no lapic support */ nmi_watchdog = nmi; return 1; } __setup("nmi_watchdog=", setup_nmi_watchdog); -static void disable_intel_arch_watchdog(void); - static void disable_lapic_nmi_watchdog(void) { - if (nmi_active <= 0) + BUG_ON(nmi_watchdog != NMI_LOCAL_APIC); + + if (atomic_read(&nmi_active) <= 0) return; - switch (boot_cpu_data.x86_vendor) { - case X86_VENDOR_AMD: - wrmsr(MSR_K7_EVNTSEL0, 0, 0); - break; - case X86_VENDOR_INTEL: - if (boot_cpu_data.x86 == 15) { - wrmsr(MSR_P4_IQ_CCCR0, 0, 0); - wrmsr(MSR_P4_CRU_ESCR0, 0, 0); - } else if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { - disable_intel_arch_watchdog(); - } - break; - } - nmi_active = -1; - /* tell do_nmi() and others that we're not active any more */ - nmi_watchdog = 0; -} -static void enable_lapic_nmi_watchdog(void) -{ - if (nmi_active < 0) { - nmi_watchdog = NMI_LOCAL_APIC; - touch_nmi_watchdog(); - setup_apic_nmi_watchdog(); - } + on_each_cpu(stop_apic_nmi_watchdog, NULL, 0, 1); + + BUG_ON(atomic_read(&nmi_active) != 0); } -int reserve_lapic_nmi(void) +static void enable_lapic_nmi_watchdog(void) { - unsigned int old_owner; + BUG_ON(nmi_watchdog != NMI_LOCAL_APIC); - spin_lock(&lapic_nmi_owner_lock); - old_owner = lapic_nmi_owner; - lapic_nmi_owner |= LAPIC_NMI_RESERVED; - spin_unlock(&lapic_nmi_owner_lock); - if (old_owner & LAPIC_NMI_RESERVED) - return -EBUSY; - if (old_owner & LAPIC_NMI_WATCHDOG) - disable_lapic_nmi_watchdog(); - return 0; -} + /* are we already enabled */ + if (atomic_read(&nmi_active) != 0) + return; -void release_lapic_nmi(void) -{ - unsigned int new_owner; + /* are we lapic aware */ + if (nmi_known_cpu() <= 0) + return; - spin_lock(&lapic_nmi_owner_lock); - new_owner = lapic_nmi_owner & ~LAPIC_NMI_RESERVED; - lapic_nmi_owner = new_owner; - spin_unlock(&lapic_nmi_owner_lock); - if (new_owner & LAPIC_NMI_WATCHDOG) - enable_lapic_nmi_watchdog(); + on_each_cpu(setup_apic_nmi_watchdog, NULL, 0, 1); + touch_nmi_watchdog(); } void disable_timer_nmi_watchdog(void) { - if ((nmi_watchdog != NMI_IO_APIC) || (nmi_active <= 0)) + BUG_ON(nmi_watchdog != NMI_IO_APIC); + + if (atomic_read(&nmi_active) <= 0) return; disable_irq(0); - unset_nmi_callback(); - nmi_active = -1; - nmi_watchdog = NMI_NONE; + on_each_cpu(stop_apic_nmi_watchdog, NULL, 0, 1); + + BUG_ON(atomic_read(&nmi_active) != 0); } void enable_timer_nmi_watchdog(void) { - if (nmi_active < 0) { - nmi_watchdog = NMI_IO_APIC; + BUG_ON(nmi_watchdog != NMI_IO_APIC); + + if (atomic_read(&nmi_active) == 0) { touch_nmi_watchdog(); - nmi_active = 1; + on_each_cpu(setup_apic_nmi_watchdog, NULL, 0, 1); enable_irq(0); } } @@ -296,15 +360,20 @@ static int nmi_pm_active; /* nmi_active before suspend */ static int lapic_nmi_suspend(struct sys_device *dev, pm_message_t state) { - nmi_pm_active = nmi_active; - disable_lapic_nmi_watchdog(); + /* only CPU0 goes here, other CPUs should be offline */ + nmi_pm_active = atomic_read(&nmi_active); + stop_apic_nmi_watchdog(NULL); + BUG_ON(atomic_read(&nmi_active) != 0); return 0; } static int lapic_nmi_resume(struct sys_device *dev) { - if (nmi_pm_active > 0) - enable_lapic_nmi_watchdog(); + /* only CPU0 goes here, other CPUs should be offline */ + if (nmi_pm_active > 0) { + setup_apic_nmi_watchdog(NULL); + touch_nmi_watchdog(); + } return 0; } @@ -323,7 +392,13 @@ static int __init init_lapic_nmi_sysfs(void) { int error; - if (nmi_active == 0 || nmi_watchdog != NMI_LOCAL_APIC) + /* should really be a BUG_ON but b/c this is an + * init call, it just doesn't work. -dcz + */ + if (nmi_watchdog != NMI_LOCAL_APIC) + return 0; + + if ( atomic_read(&nmi_active) < 0 ) return 0; error = sysdev_class_register(&nmi_sysclass); @@ -341,74 +416,209 @@ late_initcall(init_lapic_nmi_sysfs); * Original code written by Keith Owens. */ -static void clear_msr_range(unsigned int base, unsigned int n) -{ - unsigned int i; +/* Note that these events don't tick when the CPU idles. This means + the frequency varies with CPU load. */ - for(i = 0; i < n; ++i) - wrmsr(base+i, 0, 0); -} +#define K7_EVNTSEL_ENABLE (1 << 22) +#define K7_EVNTSEL_INT (1 << 20) +#define K7_EVNTSEL_OS (1 << 17) +#define K7_EVNTSEL_USR (1 << 16) +#define K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING 0x76 +#define K7_NMI_EVENT K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING -static void setup_k7_watchdog(void) +static int setup_k7_watchdog(void) { - int i; + unsigned int perfctr_msr, evntsel_msr; unsigned int evntsel; + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - nmi_perfctr_msr = MSR_K7_PERFCTR0; + perfctr_msr = MSR_K7_PERFCTR0; + evntsel_msr = MSR_K7_EVNTSEL0; + if (!reserve_perfctr_nmi(perfctr_msr)) + goto fail; - for(i = 0; i < 4; ++i) { - /* Simulator may not support it */ - if (checking_wrmsrl(MSR_K7_EVNTSEL0+i, 0UL)) { - nmi_perfctr_msr = 0; - return; - } - wrmsrl(MSR_K7_PERFCTR0+i, 0UL); - } + if (!reserve_evntsel_nmi(evntsel_msr)) + goto fail1; + + /* Simulator may not support it */ + if (checking_wrmsrl(evntsel_msr, 0UL)) + goto fail2; + wrmsrl(perfctr_msr, 0UL); evntsel = K7_EVNTSEL_INT | K7_EVNTSEL_OS | K7_EVNTSEL_USR | K7_NMI_EVENT; - wrmsr(MSR_K7_EVNTSEL0, evntsel, 0); - wrmsrl(MSR_K7_PERFCTR0, -((u64)cpu_khz * 1000 / nmi_hz)); + /* setup the timer */ + wrmsr(evntsel_msr, evntsel, 0); + wrmsrl(perfctr_msr, -((u64)cpu_khz * 1000 / nmi_hz)); apic_write(APIC_LVTPC, APIC_DM_NMI); evntsel |= K7_EVNTSEL_ENABLE; - wrmsr(MSR_K7_EVNTSEL0, evntsel, 0); + wrmsr(evntsel_msr, evntsel, 0); + + wd->perfctr_msr = perfctr_msr; + wd->evntsel_msr = evntsel_msr; + wd->cccr_msr = 0; //unused + wd->check_bit = 1ULL<<63; + return 1; +fail2: + release_evntsel_nmi(evntsel_msr); +fail1: + release_perfctr_nmi(perfctr_msr); +fail: + return 0; } -static void disable_intel_arch_watchdog(void) +static void stop_k7_watchdog(void) { - unsigned ebx; + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - /* - * Check whether the Architectural PerfMon supports - * Unhalted Core Cycles Event or not. - * NOTE: Corresponding bit = 0 in ebp indicates event present. + wrmsr(wd->evntsel_msr, 0, 0); + + release_evntsel_nmi(wd->evntsel_msr); + release_perfctr_nmi(wd->perfctr_msr); +} + +/* Note that these events don't tick when the CPU idles. This means + the frequency varies with CPU load. */ + +#define MSR_P4_MISC_ENABLE_PERF_AVAIL (1<<7) +#define P4_ESCR_EVENT_SELECT(N) ((N)<<25) +#define P4_ESCR_OS (1<<3) +#define P4_ESCR_USR (1<<2) +#define P4_CCCR_OVF_PMI0 (1<<26) +#define P4_CCCR_OVF_PMI1 (1<<27) +#define P4_CCCR_THRESHOLD(N) ((N)<<20) +#define P4_CCCR_COMPLEMENT (1<<19) +#define P4_CCCR_COMPARE (1<<18) +#define P4_CCCR_REQUIRED (3<<16) +#define P4_CCCR_ESCR_SELECT(N) ((N)<<13) +#define P4_CCCR_ENABLE (1<<12) +#define P4_CCCR_OVF (1<<31) +/* Set up IQ_COUNTER0 to behave like a clock, by having IQ_CCCR0 filter + CRU_ESCR0 (with any non-null event selector) through a complemented + max threshold. [IA32-Vol3, Section 14.9.9] */ + +static int setup_p4_watchdog(void) +{ + unsigned int perfctr_msr, evntsel_msr, cccr_msr; + unsigned int evntsel, cccr_val; + unsigned int misc_enable, dummy; + unsigned int ht_num; + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); + + rdmsr(MSR_IA32_MISC_ENABLE, misc_enable, dummy); + if (!(misc_enable & MSR_P4_MISC_ENABLE_PERF_AVAIL)) + return 0; + +#ifdef CONFIG_SMP + /* detect which hyperthread we are on */ + if (smp_num_siblings == 2) { + unsigned int ebx, apicid; + + ebx = cpuid_ebx(1); + apicid = (ebx >> 24) & 0xff; + ht_num = apicid & 1; + } else +#endif + ht_num = 0; + + /* performance counters are shared resources + * assign each hyperthread its own set + * (re-use the ESCR0 register, seems safe + * and keeps the cccr_val the same) */ - ebx = cpuid_ebx(10); - if (!(ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT)) - wrmsr(MSR_ARCH_PERFMON_EVENTSEL0, 0, 0); + if (!ht_num) { + /* logical cpu 0 */ + perfctr_msr = MSR_P4_IQ_PERFCTR0; + evntsel_msr = MSR_P4_CRU_ESCR0; + cccr_msr = MSR_P4_IQ_CCCR0; + cccr_val = P4_CCCR_OVF_PMI0 | P4_CCCR_ESCR_SELECT(4); + } else { + /* logical cpu 1 */ + perfctr_msr = MSR_P4_IQ_PERFCTR1; + evntsel_msr = MSR_P4_CRU_ESCR0; + cccr_msr = MSR_P4_IQ_CCCR1; + cccr_val = P4_CCCR_OVF_PMI1 | P4_CCCR_ESCR_SELECT(4); + } + + if (!reserve_perfctr_nmi(perfctr_msr)) + goto fail; + + if (!reserve_evntsel_nmi(evntsel_msr)) + goto fail1; + + evntsel = P4_ESCR_EVENT_SELECT(0x3F) + | P4_ESCR_OS + | P4_ESCR_USR; + + cccr_val |= P4_CCCR_THRESHOLD(15) + | P4_CCCR_COMPLEMENT + | P4_CCCR_COMPARE + | P4_CCCR_REQUIRED; + + wrmsr(evntsel_msr, evntsel, 0); + wrmsr(cccr_msr, cccr_val, 0); + wrmsrl(perfctr_msr, -((u64)cpu_khz * 1000 / nmi_hz)); + apic_write(APIC_LVTPC, APIC_DM_NMI); + cccr_val |= P4_CCCR_ENABLE; + wrmsr(cccr_msr, cccr_val, 0); + + wd->perfctr_msr = perfctr_msr; + wd->evntsel_msr = evntsel_msr; + wd->cccr_msr = cccr_msr; + wd->check_bit = 1ULL<<39; + return 1; +fail1: + release_perfctr_nmi(perfctr_msr); +fail: + return 0; +} + +static void stop_p4_watchdog(void) +{ + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); + + wrmsr(wd->cccr_msr, 0, 0); + wrmsr(wd->evntsel_msr, 0, 0); + + release_evntsel_nmi(wd->evntsel_msr); + release_perfctr_nmi(wd->perfctr_msr); } +#define ARCH_PERFMON_NMI_EVENT_SEL ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL +#define ARCH_PERFMON_NMI_EVENT_UMASK ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK + static int setup_intel_arch_watchdog(void) { + unsigned int ebx; + union cpuid10_eax eax; + unsigned int unused; + unsigned int perfctr_msr, evntsel_msr; unsigned int evntsel; - unsigned ebx; + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); /* * Check whether the Architectural PerfMon supports * Unhalted Core Cycles Event or not. - * NOTE: Corresponding bit = 0 in ebp indicates event present. + * NOTE: Corresponding bit = 0 in ebx indicates event present. */ - ebx = cpuid_ebx(10); - if ((ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT)) - return 0; + cpuid(10, &(eax.full), &ebx, &unused, &unused); + if ((eax.split.mask_length < (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX+1)) || + (ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT)) + goto fail; + + perfctr_msr = MSR_ARCH_PERFMON_PERFCTR0; + evntsel_msr = MSR_ARCH_PERFMON_EVENTSEL0; - nmi_perfctr_msr = MSR_ARCH_PERFMON_PERFCTR0; + if (!reserve_perfctr_nmi(perfctr_msr)) + goto fail; - clear_msr_range(MSR_ARCH_PERFMON_EVENTSEL0, 2); - clear_msr_range(MSR_ARCH_PERFMON_PERFCTR0, 2); + if (!reserve_evntsel_nmi(evntsel_msr)) + goto fail1; + + wrmsrl(perfctr_msr, 0UL); evntsel = ARCH_PERFMON_EVENTSEL_INT | ARCH_PERFMON_EVENTSEL_OS @@ -416,84 +626,122 @@ static int setup_intel_arch_watchdog(void) | ARCH_PERFMON_NMI_EVENT_SEL | ARCH_PERFMON_NMI_EVENT_UMASK; - wrmsr(MSR_ARCH_PERFMON_EVENTSEL0, evntsel, 0); - wrmsrl(MSR_ARCH_PERFMON_PERFCTR0, -((u64)cpu_khz * 1000 / nmi_hz)); + /* setup the timer */ + wrmsr(evntsel_msr, evntsel, 0); + wrmsrl(perfctr_msr, -((u64)cpu_khz * 1000 / nmi_hz)); + apic_write(APIC_LVTPC, APIC_DM_NMI); evntsel |= ARCH_PERFMON_EVENTSEL0_ENABLE; - wrmsr(MSR_ARCH_PERFMON_EVENTSEL0, evntsel, 0); + wrmsr(evntsel_msr, evntsel, 0); + + wd->perfctr_msr = perfctr_msr; + wd->evntsel_msr = evntsel_msr; + wd->cccr_msr = 0; //unused + wd->check_bit = 1ULL << (eax.split.bit_width - 1); return 1; +fail1: + release_perfctr_nmi(perfctr_msr); +fail: + return 0; } - -static int setup_p4_watchdog(void) +static void stop_intel_arch_watchdog(void) { - unsigned int misc_enable, dummy; + unsigned int ebx; + union cpuid10_eax eax; + unsigned int unused; + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - rdmsr(MSR_P4_MISC_ENABLE, misc_enable, dummy); - if (!(misc_enable & MSR_P4_MISC_ENABLE_PERF_AVAIL)) - return 0; + /* + * Check whether the Architectural PerfMon supports + * Unhalted Core Cycles Event or not. + * NOTE: Corresponding bit = 0 in ebx indicates event present. + */ + cpuid(10, &(eax.full), &ebx, &unused, &unused); + if ((eax.split.mask_length < (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX+1)) || + (ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT)) + return; - nmi_perfctr_msr = MSR_P4_IQ_COUNTER0; - nmi_p4_cccr_val = P4_NMI_IQ_CCCR0; -#ifdef CONFIG_SMP - if (smp_num_siblings == 2) - nmi_p4_cccr_val |= P4_CCCR_OVF_PMI1; -#endif + wrmsr(wd->evntsel_msr, 0, 0); - if (!(misc_enable & MSR_P4_MISC_ENABLE_PEBS_UNAVAIL)) - clear_msr_range(0x3F1, 2); - /* MSR 0x3F0 seems to have a default value of 0xFC00, but current - docs doesn't fully define it, so leave it alone for now. */ - if (boot_cpu_data.x86_model >= 0x3) { - /* MSR_P4_IQ_ESCR0/1 (0x3ba/0x3bb) removed */ - clear_msr_range(0x3A0, 26); - clear_msr_range(0x3BC, 3); - } else { - clear_msr_range(0x3A0, 31); - } - clear_msr_range(0x3C0, 6); - clear_msr_range(0x3C8, 6); - clear_msr_range(0x3E0, 2); - clear_msr_range(MSR_P4_CCCR0, 18); - clear_msr_range(MSR_P4_PERFCTR0, 18); - - wrmsr(MSR_P4_CRU_ESCR0, P4_NMI_CRU_ESCR0, 0); - wrmsr(MSR_P4_IQ_CCCR0, P4_NMI_IQ_CCCR0 & ~P4_CCCR_ENABLE, 0); - Dprintk("setting P4_IQ_COUNTER0 to 0x%08lx\n", -(cpu_khz * 1000UL / nmi_hz)); - wrmsrl(MSR_P4_IQ_COUNTER0, -((u64)cpu_khz * 1000 / nmi_hz)); - apic_write(APIC_LVTPC, APIC_DM_NMI); - wrmsr(MSR_P4_IQ_CCCR0, nmi_p4_cccr_val, 0); - return 1; + release_evntsel_nmi(wd->evntsel_msr); + release_perfctr_nmi(wd->perfctr_msr); } -void setup_apic_nmi_watchdog(void) +void setup_apic_nmi_watchdog(void *unused) { - switch (boot_cpu_data.x86_vendor) { - case X86_VENDOR_AMD: - if (boot_cpu_data.x86 != 15) - return; - if (strstr(boot_cpu_data.x86_model_id, "Screwdriver")) - return; - setup_k7_watchdog(); - break; - case X86_VENDOR_INTEL: - if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { - if (!setup_intel_arch_watchdog()) + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); + + /* only support LOCAL and IO APICs for now */ + if ((nmi_watchdog != NMI_LOCAL_APIC) && + (nmi_watchdog != NMI_IO_APIC)) + return; + + if (wd->enabled == 1) + return; + + /* cheap hack to support suspend/resume */ + /* if cpu0 is not active neither should the other cpus */ + if ((smp_processor_id() != 0) && (atomic_read(&nmi_active) <= 0)) + return; + + if (nmi_watchdog == NMI_LOCAL_APIC) { + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_AMD: + if (strstr(boot_cpu_data.x86_model_id, "Screwdriver")) return; - } else if (boot_cpu_data.x86 == 15) { + if (!setup_k7_watchdog()) + return; + break; + case X86_VENDOR_INTEL: + if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { + if (!setup_intel_arch_watchdog()) + return; + break; + } if (!setup_p4_watchdog()) return; - } else { + break; + default: return; } + } + wd->enabled = 1; + atomic_inc(&nmi_active); +} + +void stop_apic_nmi_watchdog(void *unused) +{ + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - break; + /* only support LOCAL and IO APICs for now */ + if ((nmi_watchdog != NMI_LOCAL_APIC) && + (nmi_watchdog != NMI_IO_APIC)) + return; - default: + if (wd->enabled == 0) return; + + if (nmi_watchdog == NMI_LOCAL_APIC) { + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_AMD: + if (strstr(boot_cpu_data.x86_model_id, "Screwdriver")) + return; + stop_k7_watchdog(); + break; + case X86_VENDOR_INTEL: + if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { + stop_intel_arch_watchdog(); + break; + } + stop_p4_watchdog(); + break; + default: + return; + } } - lapic_nmi_owner = LAPIC_NMI_WATCHDOG; - nmi_active = 1; + wd->enabled = 0; + atomic_dec(&nmi_active); } /* @@ -526,93 +774,109 @@ void touch_nmi_watchdog (void) touch_softlockup_watchdog(); } -void __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason) +int __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason) { int sum; int touched = 0; + struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); + u64 dummy; + int rc=0; + + /* check for other users first */ + if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) + == NOTIFY_STOP) { + rc = 1; + touched = 1; + } sum = read_pda(apic_timer_irqs); if (__get_cpu_var(nmi_touch)) { __get_cpu_var(nmi_touch) = 0; touched = 1; } + #ifdef CONFIG_X86_MCE /* Could check oops_in_progress here too, but it's safer not too */ if (atomic_read(&mce_entry) > 0) touched = 1; #endif + /* if the apic timer isn't firing, this cpu isn't doing much */ if (!touched && __get_cpu_var(last_irq_sum) == sum) { /* * Ayiee, looks like this CPU is stuck ... * wait a few IRQs (5 seconds) before doing the oops ... */ local_inc(&__get_cpu_var(alert_counter)); - if (local_read(&__get_cpu_var(alert_counter)) == 5*nmi_hz) { - if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) - == NOTIFY_STOP) { - local_set(&__get_cpu_var(alert_counter), 0); - return; - } - die_nmi("NMI Watchdog detected LOCKUP on CPU %d\n", regs); - } + if (local_read(&__get_cpu_var(alert_counter)) == 5*nmi_hz) + die_nmi("NMI Watchdog detected LOCKUP on CPU %d\n", regs, + panic_on_timeout); } else { __get_cpu_var(last_irq_sum) = sum; local_set(&__get_cpu_var(alert_counter), 0); } - if (nmi_perfctr_msr) { - if (nmi_perfctr_msr == MSR_P4_IQ_COUNTER0) { - /* - * P4 quirks: - * - An overflown perfctr will assert its interrupt - * until the OVF flag in its CCCR is cleared. - * - LVTPC is masked on interrupt and must be - * unmasked by the LVTPC handler. - */ - wrmsr(MSR_P4_IQ_CCCR0, nmi_p4_cccr_val, 0); - apic_write(APIC_LVTPC, APIC_DM_NMI); - } else if (nmi_perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0) { - /* - * For Intel based architectural perfmon - * - LVTPC is masked on interrupt and must be - * unmasked by the LVTPC handler. + + /* see if the nmi watchdog went off */ + if (wd->enabled) { + if (nmi_watchdog == NMI_LOCAL_APIC) { + rdmsrl(wd->perfctr_msr, dummy); + if (dummy & wd->check_bit){ + /* this wasn't a watchdog timer interrupt */ + goto done; + } + + /* only Intel uses the cccr msr */ + if (wd->cccr_msr != 0) { + /* + * P4 quirks: + * - An overflown perfctr will assert its interrupt + * until the OVF flag in its CCCR is cleared. + * - LVTPC is masked on interrupt and must be + * unmasked by the LVTPC handler. + */ + rdmsrl(wd->cccr_msr, dummy); + dummy &= ~P4_CCCR_OVF; + wrmsrl(wd->cccr_msr, dummy); + apic_write(APIC_LVTPC, APIC_DM_NMI); + } else if (wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0) { + /* + * ArchPerfom/Core Duo needs to re-unmask + * the apic vector + */ + apic_write(APIC_LVTPC, APIC_DM_NMI); + } + /* start the cycle over again */ + wrmsrl(wd->perfctr_msr, -((u64)cpu_khz * 1000 / nmi_hz)); + rc = 1; + } else if (nmi_watchdog == NMI_IO_APIC) { + /* don't know how to accurately check for this. + * just assume it was a watchdog timer interrupt + * This matches the old behaviour. */ - apic_write(APIC_LVTPC, APIC_DM_NMI); - } - wrmsrl(nmi_perfctr_msr, -((u64)cpu_khz * 1000 / nmi_hz)); + rc = 1; + } else + printk(KERN_WARNING "Unknown enabled NMI hardware?!\n"); } +done: + return rc; } -static __kprobes int dummy_nmi_callback(struct pt_regs * regs, int cpu) -{ - return 0; -} - -static nmi_callback_t nmi_callback = dummy_nmi_callback; - asmlinkage __kprobes void do_nmi(struct pt_regs * regs, long error_code) { - int cpu = safe_smp_processor_id(); - nmi_enter(); add_pda(__nmi_count,1); - if (!rcu_dereference(nmi_callback)(regs, cpu)) - default_do_nmi(regs); + default_do_nmi(regs); nmi_exit(); } -void set_nmi_callback(nmi_callback_t callback) +int do_nmi_callback(struct pt_regs * regs, int cpu) { - vmalloc_sync_all(); - rcu_assign_pointer(nmi_callback, callback); -} -EXPORT_SYMBOL_GPL(set_nmi_callback); - -void unset_nmi_callback(void) -{ - nmi_callback = dummy_nmi_callback; +#ifdef CONFIG_SYSCTL + if (unknown_nmi_panic) + return unknown_nmi_panic_callback(regs, cpu); +#endif + return 0; } -EXPORT_SYMBOL_GPL(unset_nmi_callback); #ifdef CONFIG_SYSCTL @@ -621,36 +885,42 @@ static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu) unsigned char reason = get_nmi_reason(); char buf[64]; - if (!(reason & 0xc0)) { - sprintf(buf, "NMI received for unknown reason %02x\n", reason); - die_nmi(buf,regs); - } + sprintf(buf, "NMI received for unknown reason %02x\n", reason); + die_nmi(buf, regs, 1); /* Always panic here */ return 0; } /* - * proc handler for /proc/sys/kernel/unknown_nmi_panic + * proc handler for /proc/sys/kernel/nmi */ -int proc_unknown_nmi_panic(struct ctl_table *table, int write, struct file *file, +int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file, void __user *buffer, size_t *length, loff_t *ppos) { int old_state; - old_state = unknown_nmi_panic; + nmi_watchdog_enabled = (atomic_read(&nmi_active) > 0) ? 1 : 0; + old_state = nmi_watchdog_enabled; proc_dointvec(table, write, file, buffer, length, ppos); - if (!!old_state == !!unknown_nmi_panic) + if (!!old_state == !!nmi_watchdog_enabled) return 0; - if (unknown_nmi_panic) { - if (reserve_lapic_nmi() < 0) { - unknown_nmi_panic = 0; - return -EBUSY; - } else { - set_nmi_callback(unknown_nmi_panic_callback); - } + if (atomic_read(&nmi_active) < 0) { + printk( KERN_WARNING "NMI watchdog is permanently disabled\n"); + return -EIO; + } + + /* if nmi_watchdog is not set yet, then set it */ + nmi_watchdog_default(); + + if (nmi_watchdog == NMI_LOCAL_APIC) { + if (nmi_watchdog_enabled) + enable_lapic_nmi_watchdog(); + else + disable_lapic_nmi_watchdog(); } else { - release_lapic_nmi(); - unset_nmi_callback(); + printk( KERN_WARNING + "NMI watchdog doesn't know what hardware to touch\n"); + return -EIO; } return 0; } @@ -659,8 +929,12 @@ int proc_unknown_nmi_panic(struct ctl_table *table, int write, struct file *file EXPORT_SYMBOL(nmi_active); EXPORT_SYMBOL(nmi_watchdog); -EXPORT_SYMBOL(reserve_lapic_nmi); -EXPORT_SYMBOL(release_lapic_nmi); +EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi); +EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi_bit); +EXPORT_SYMBOL(reserve_perfctr_nmi); +EXPORT_SYMBOL(release_perfctr_nmi); +EXPORT_SYMBOL(reserve_evntsel_nmi); +EXPORT_SYMBOL(release_evntsel_nmi); EXPORT_SYMBOL(disable_timer_nmi_watchdog); EXPORT_SYMBOL(enable_timer_nmi_watchdog); EXPORT_SYMBOL(touch_nmi_watchdog); diff --git a/arch/x86_64/kernel/pci-calgary.c b/arch/x86_64/kernel/pci-calgary.c index 146924b..cfb09b0 100644 --- a/arch/x86_64/kernel/pci-calgary.c +++ b/arch/x86_64/kernel/pci-calgary.c @@ -86,7 +86,8 @@ #define MAX_NUM_OF_PHBS 8 /* how many PHBs in total? */ #define MAX_NUM_CHASSIS 8 /* max number of chassis */ -#define MAX_PHB_BUS_NUM (MAX_NUM_OF_PHBS * MAX_NUM_CHASSIS * 2) /* max dev->bus->number */ +/* MAX_PHB_BUS_NUM is the maximal possible dev->bus->number */ +#define MAX_PHB_BUS_NUM (MAX_NUM_OF_PHBS * MAX_NUM_CHASSIS * 2) #define PHBS_PER_CALGARY 4 /* register offsets in Calgary's internal register space */ @@ -111,31 +112,49 @@ static const unsigned long phb_offsets[] = { 0xB000 /* PHB3 */ }; -static char bus_to_phb[MAX_PHB_BUS_NUM]; -void* tce_table_kva[MAX_PHB_BUS_NUM]; unsigned int specified_table_size = TCE_TABLE_SIZE_UNSPECIFIED; static int translate_empty_slots __read_mostly = 0; static int calgary_detected __read_mostly = 0; -/* - * the bitmap of PHBs the user requested that we disable - * translation on. - */ -static DECLARE_BITMAP(translation_disabled, MAX_PHB_BUS_NUM); +struct calgary_bus_info { + void *tce_space; + unsigned char translation_disabled; + signed char phbid; +}; + +static struct calgary_bus_info bus_info[MAX_PHB_BUS_NUM] = { { NULL, 0, 0 }, }; static void tce_cache_blast(struct iommu_table *tbl); /* enable this to stress test the chip's TCE cache */ #ifdef CONFIG_IOMMU_DEBUG -static inline void tce_cache_blast_stress(struct iommu_table *tbl) +int debugging __read_mostly = 1; + +static inline unsigned long verify_bit_range(unsigned long* bitmap, + int expected, unsigned long start, unsigned long end) { - tce_cache_blast(tbl); + unsigned long idx = start; + + BUG_ON(start >= end); + + while (idx < end) { + if (!!test_bit(idx, bitmap) != expected) + return idx; + ++idx; + } + + /* all bits have the expected value */ + return ~0UL; } -#else -static inline void tce_cache_blast_stress(struct iommu_table *tbl) +#else /* debugging is disabled */ +int debugging __read_mostly = 0; + +static inline unsigned long verify_bit_range(unsigned long* bitmap, + int expected, unsigned long start, unsigned long end) { + return ~0UL; } -#endif /* BLAST_TCE_CACHE_ON_UNMAP */ +#endif /* CONFIG_IOMMU_DEBUG */ static inline unsigned int num_dma_pages(unsigned long dma, unsigned int dmalen) { @@ -149,7 +168,7 @@ static inline unsigned int num_dma_pages(unsigned long dma, unsigned int dmalen) static inline int translate_phb(struct pci_dev* dev) { - int disabled = test_bit(dev->bus->number, translation_disabled); + int disabled = bus_info[dev->bus->number].translation_disabled; return !disabled; } @@ -158,6 +177,7 @@ static void iommu_range_reserve(struct iommu_table *tbl, { unsigned long index; unsigned long end; + unsigned long badbit; index = start_addr >> PAGE_SHIFT; @@ -169,14 +189,15 @@ static void iommu_range_reserve(struct iommu_table *tbl, if (end > tbl->it_size) /* don't go off the table */ end = tbl->it_size; - while (index < end) { - if (test_bit(index, tbl->it_map)) + badbit = verify_bit_range(tbl->it_map, 0, index, end); + if (badbit != ~0UL) { + if (printk_ratelimit()) printk(KERN_ERR "Calgary: entry already allocated at " "0x%lx tbl %p dma 0x%lx npages %u\n", - index, tbl, start_addr, npages); - ++index; + badbit, tbl, start_addr, npages); } - set_bit_string(tbl->it_map, start_addr >> PAGE_SHIFT, npages); + + set_bit_string(tbl->it_map, index, npages); } static unsigned long iommu_range_alloc(struct iommu_table *tbl, @@ -243,7 +264,7 @@ static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, unsigned int npages) { unsigned long entry; - unsigned long i; + unsigned long badbit; entry = dma_addr >> PAGE_SHIFT; @@ -251,16 +272,15 @@ static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, tce_free(tbl, entry, npages); - for (i = 0; i < npages; ++i) { - if (!test_bit(entry + i, tbl->it_map)) + badbit = verify_bit_range(tbl->it_map, 1, entry, entry + npages); + if (badbit != ~0UL) { + if (printk_ratelimit()) printk(KERN_ERR "Calgary: bit is off at 0x%lx " "tbl %p dma 0x%Lx entry 0x%lx npages %u\n", - entry + i, tbl, dma_addr, entry, npages); + badbit, tbl, dma_addr, entry, npages); } __clear_bit_string(tbl->it_map, entry, npages); - - tce_cache_blast_stress(tbl); } static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, @@ -454,7 +474,7 @@ static struct dma_mapping_ops calgary_dma_ops = { static inline int busno_to_phbid(unsigned char num) { - return bus_to_phb[num]; + return bus_info[num].phbid; } static inline unsigned long split_queue_offset(unsigned char num) @@ -631,6 +651,10 @@ static int __init calgary_setup_tar(struct pci_dev *dev, void __iomem *bbar) if (ret) return ret; + tbl = dev->sysdata; + tbl->it_base = (unsigned long)bus_info[dev->bus->number].tce_space; + tce_free(tbl, 0, tbl->it_size); + calgary_reserve_regions(dev); /* set TARs for each PHB */ @@ -654,11 +678,12 @@ static int __init calgary_setup_tar(struct pci_dev *dev, void __iomem *bbar) return 0; } -static void __init calgary_free_tar(struct pci_dev *dev) +static void __init calgary_free_bus(struct pci_dev *dev) { u64 val64; struct iommu_table *tbl = dev->sysdata; void __iomem *target; + unsigned int bitmapsz; target = calgary_reg(tbl->bbar, tar_offset(dev->bus->number)); val64 = be64_to_cpu(readq(target)); @@ -666,8 +691,15 @@ static void __init calgary_free_tar(struct pci_dev *dev) writeq(cpu_to_be64(val64), target); readq(target); /* flush */ + bitmapsz = tbl->it_size / BITS_PER_BYTE; + free_pages((unsigned long)tbl->it_map, get_order(bitmapsz)); + tbl->it_map = NULL; + kfree(tbl); dev->sysdata = NULL; + + /* Can't free bootmem allocated memory after system is up :-( */ + bus_info[dev->bus->number].tce_space = NULL; } static void calgary_watchdog(unsigned long data) @@ -772,12 +804,11 @@ static inline unsigned int __init locate_register_space(struct pci_dev *dev) return address; } -static int __init calgary_init_one_nontraslated(struct pci_dev *dev) +static void __init calgary_init_one_nontraslated(struct pci_dev *dev) { + pci_dev_get(dev); dev->sysdata = NULL; dev->bus->self = dev; - - return 0; } static int __init calgary_init_one(struct pci_dev *dev) @@ -798,6 +829,7 @@ static int __init calgary_init_one(struct pci_dev *dev) if (ret) goto iounmap; + pci_dev_get(dev); dev->bus->self = dev; calgary_enable_translation(dev); @@ -824,10 +856,9 @@ static int __init calgary_init(void) calgary_init_one_nontraslated(dev); continue; } - if (!tce_table_kva[dev->bus->number] && !translate_empty_slots) { - pci_dev_put(dev); + if (!bus_info[dev->bus->number].tce_space && !translate_empty_slots) continue; - } + ret = calgary_init_one(dev); if (ret) goto error; @@ -840,15 +871,18 @@ error: dev = pci_find_device_reverse(PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CALGARY, dev); + if (!dev) + break; if (!translate_phb(dev)) { pci_dev_put(dev); continue; } - if (!tce_table_kva[dev->bus->number] && !translate_empty_slots) + if (!bus_info[dev->bus->number].tce_space && !translate_empty_slots) continue; + calgary_disable_translation(dev); - calgary_free_tar(dev); - pci_dev_put(dev); + calgary_free_bus(dev); + pci_dev_put(dev); /* Undo calgary_init_one()'s pci_dev_get() */ } return ret; @@ -890,13 +924,15 @@ void __init detect_calgary(void) if (swiotlb || no_iommu || iommu_detected) return; + if (!early_pci_allowed()) + return; + specified_table_size = determine_tce_table_size(end_pfn * PAGE_SIZE); for (bus = 0; bus < MAX_PHB_BUS_NUM; bus++) { int dev; - - tce_table_kva[bus] = NULL; - bus_to_phb[bus] = -1; + struct calgary_bus_info *info = &bus_info[bus]; + info->phbid = -1; if (read_pci_config(bus, 0, 0, 0) != PCI_VENDOR_DEVICE_ID_CALGARY) continue; @@ -907,12 +943,9 @@ void __init detect_calgary(void) */ phb = (phb + 1) % PHBS_PER_CALGARY; - if (test_bit(bus, translation_disabled)) { - printk(KERN_INFO "Calgary: translation is disabled for " - "PHB 0x%x\n", bus); - /* skip this phb, don't allocate a tbl for it */ + if (info->translation_disabled) continue; - } + /* * Scan the slots of the PCI bus to see if there is a device present. * The parent bus will be the zero-ith device, so start at 1. @@ -923,8 +956,8 @@ void __init detect_calgary(void) tbl = alloc_tce_table(); if (!tbl) goto cleanup; - tce_table_kva[bus] = tbl; - bus_to_phb[bus] = phb; + info->tce_space = tbl; + info->phbid = phb; calgary_found = 1; break; } @@ -934,15 +967,20 @@ void __init detect_calgary(void) if (calgary_found) { iommu_detected = 1; calgary_detected = 1; - printk(KERN_INFO "PCI-DMA: Calgary IOMMU detected. " - "TCE table spec is %d.\n", specified_table_size); + printk(KERN_INFO "PCI-DMA: Calgary IOMMU detected.\n"); + printk(KERN_INFO "PCI-DMA: Calgary TCE table spec is %d, " + "CONFIG_IOMMU_DEBUG is %s.\n", specified_table_size, + debugging ? "enabled" : "disabled"); } return; cleanup: - for (--bus; bus >= 0; --bus) - if (tce_table_kva[bus]) - free_tce_table(tce_table_kva[bus]); + for (--bus; bus >= 0; --bus) { + struct calgary_bus_info *info = &bus_info[bus]; + + if (info->tce_space) + free_tce_table(info->tce_space); + } } int __init calgary_iommu_init(void) @@ -1016,7 +1054,7 @@ static int __init calgary_parse_options(char *p) if (bridge < MAX_PHB_BUS_NUM) { printk(KERN_INFO "Calgary: disabling " "translation for PHB 0x%x\n", bridge); - set_bit(bridge, translation_disabled); + bus_info[bridge].translation_disabled = 1; } } diff --git a/arch/x86_64/kernel/pci-dma.c b/arch/x86_64/kernel/pci-dma.c index 9c44f4f..4dcb671 100644 --- a/arch/x86_64/kernel/pci-dma.c +++ b/arch/x86_64/kernel/pci-dma.c @@ -236,6 +236,9 @@ __init int iommu_setup(char *p) { iommu_merge = 1; + if (!p) + return -EINVAL; + while (*p) { if (!strncmp(p,"off",3)) no_iommu = 1; @@ -278,9 +281,9 @@ __init int iommu_setup(char *p) if (*p == ',') ++p; } - return 1; + return 0; } -__setup("iommu=", iommu_setup); +early_param("iommu", iommu_setup); void __init pci_iommu_alloc(void) { diff --git a/arch/x86_64/kernel/pci-gart.c b/arch/x86_64/kernel/pci-gart.c index 6d3e61b..16261a8 100644 --- a/arch/x86_64/kernel/pci-gart.c +++ b/arch/x86_64/kernel/pci-gart.c @@ -239,8 +239,6 @@ dma_addr_t gart_map_single(struct device *dev, void *addr, size_t size, int dir) { unsigned long phys_mem, bus; - BUG_ON(dir == DMA_NONE); - if (!dev) dev = &fallback_dev; @@ -383,7 +381,6 @@ int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) unsigned long pages = 0; int need = 0, nextneed; - BUG_ON(dir == DMA_NONE); if (nents == 0) return 0; diff --git a/arch/x86_64/kernel/pci-nommu.c b/arch/x86_64/kernel/pci-nommu.c index aad7609..df09ab0 100644 --- a/arch/x86_64/kernel/pci-nommu.c +++ b/arch/x86_64/kernel/pci-nommu.c @@ -59,7 +59,6 @@ int nommu_map_sg(struct device *hwdev, struct scatterlist *sg, { int i; - BUG_ON(direction == DMA_NONE); for (i = 0; i < nents; i++ ) { struct scatterlist *s = &sg[i]; BUG_ON(!s->page); diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c index bb6745d..458006a 100644 --- a/arch/x86_64/kernel/process.c +++ b/arch/x86_64/kernel/process.c @@ -80,25 +80,25 @@ void idle_notifier_unregister(struct notifier_block *n) } EXPORT_SYMBOL(idle_notifier_unregister); -enum idle_state { CPU_IDLE, CPU_NOT_IDLE }; -static DEFINE_PER_CPU(enum idle_state, idle_state) = CPU_NOT_IDLE; - void enter_idle(void) { - __get_cpu_var(idle_state) = CPU_IDLE; + write_pda(isidle, 1); atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL); } static void __exit_idle(void) { - __get_cpu_var(idle_state) = CPU_NOT_IDLE; + if (read_pda(isidle) == 0) + return; + write_pda(isidle, 0); atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL); } /* Called from interrupts to signify idle end */ void exit_idle(void) { - if (current->pid | read_pda(irqcount)) + /* idle loop has pid 0 */ + if (current->pid) return; __exit_idle(); } @@ -220,6 +220,9 @@ void cpu_idle (void) play_dead(); enter_idle(); idle(); + /* In many cases the interrupt that ended idle + has already called exit_idle. But some idle + loops can be woken up without interrupt. */ __exit_idle(); } @@ -350,6 +353,7 @@ void exit_thread(void) kfree(t->io_bitmap_ptr); t->io_bitmap_ptr = NULL; + clear_thread_flag(TIF_IO_BITMAP); /* * Careful, clear this in the TSS too: */ @@ -369,6 +373,7 @@ void flush_thread(void) if (t->flags & _TIF_IA32) current_thread_info()->status |= TS_COMPAT; } + t->flags &= ~_TIF_DEBUG; tsk->thread.debugreg0 = 0; tsk->thread.debugreg1 = 0; @@ -461,7 +466,7 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long rsp, asm("mov %%es,%0" : "=m" (p->thread.es)); asm("mov %%ds,%0" : "=m" (p->thread.ds)); - if (unlikely(me->thread.io_bitmap_ptr != NULL)) { + if (unlikely(test_tsk_thread_flag(me, TIF_IO_BITMAP))) { p->thread.io_bitmap_ptr = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL); if (!p->thread.io_bitmap_ptr) { p->thread.io_bitmap_max = 0; @@ -469,6 +474,7 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long rsp, } memcpy(p->thread.io_bitmap_ptr, me->thread.io_bitmap_ptr, IO_BITMAP_BYTES); + set_tsk_thread_flag(p, TIF_IO_BITMAP); } /* @@ -498,6 +504,40 @@ out: */ #define loaddebug(thread,r) set_debugreg(thread->debugreg ## r, r) +static inline void __switch_to_xtra(struct task_struct *prev_p, + struct task_struct *next_p, + struct tss_struct *tss) +{ + struct thread_struct *prev, *next; + + prev = &prev_p->thread, + next = &next_p->thread; + + if (test_tsk_thread_flag(next_p, TIF_DEBUG)) { + loaddebug(next, 0); + loaddebug(next, 1); + loaddebug(next, 2); + loaddebug(next, 3); + /* no 4 and 5 */ + loaddebug(next, 6); + loaddebug(next, 7); + } + + if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { + /* + * Copy the relevant range of the IO bitmap. + * Normally this is 128 bytes or less: + */ + memcpy(tss->io_bitmap, next->io_bitmap_ptr, + max(prev->io_bitmap_max, next->io_bitmap_max)); + } else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) { + /* + * Clear any possible leftover bits: + */ + memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); + } +} + /* * switch_to(x,y) should switch tasks from x to y. * @@ -515,6 +555,10 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(init_tss, cpu); + /* we're going to use this soon, after a few expensive things */ + if (next_p->fpu_counter>5) + prefetch(&next->i387.fxsave); + /* * Reload esp0, LDT and the page table pointer: */ @@ -583,41 +627,29 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) And the AMD workaround requires it to be after DS reload. */ unlazy_fpu(prev_p); write_pda(kernelstack, - task_stack_page(next_p) + THREAD_SIZE - PDA_STACKOFFSET); - + (unsigned long)task_stack_page(next_p) + THREAD_SIZE - PDA_STACKOFFSET); +#ifdef CONFIG_CC_STACKPROTECTOR + write_pda(stack_canary, next_p->stack_canary); /* - * Now maybe reload the debug registers + * Build time only check to make sure the stack_canary is at + * offset 40 in the pda; this is a gcc ABI requirement */ - if (unlikely(next->debugreg7)) { - loaddebug(next, 0); - loaddebug(next, 1); - loaddebug(next, 2); - loaddebug(next, 3); - /* no 4 and 5 */ - loaddebug(next, 6); - loaddebug(next, 7); - } - + BUILD_BUG_ON(offsetof(struct x8664_pda, stack_canary) != 40); +#endif - /* - * Handle the IO bitmap - */ - if (unlikely(prev->io_bitmap_ptr || next->io_bitmap_ptr)) { - if (next->io_bitmap_ptr) - /* - * Copy the relevant range of the IO bitmap. - * Normally this is 128 bytes or less: - */ - memcpy(tss->io_bitmap, next->io_bitmap_ptr, - max(prev->io_bitmap_max, next->io_bitmap_max)); - else { - /* - * Clear any possible leftover bits: - */ - memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); - } - } + /* + * Now maybe reload the debug registers and handle I/O bitmaps + */ + if (unlikely((task_thread_info(next_p)->flags & _TIF_WORK_CTXSW)) + || test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) + __switch_to_xtra(prev_p, next_p, tss); + /* If the task has used fpu the last 5 timeslices, just do a full + * restore of the math state immediately to avoid the trap; the + * chances of needing FPU soon are obviously high now + */ + if (next_p->fpu_counter>5) + math_state_restore(); return prev_p; } @@ -834,7 +866,7 @@ int dump_task_regs(struct task_struct *tsk, elf_gregset_t *regs) unsigned long arch_align_stack(unsigned long sp) { - if (randomize_va_space) + if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space) sp -= get_random_int() % 8192; return sp & ~0xf; } diff --git a/arch/x86_64/kernel/ptrace.c b/arch/x86_64/kernel/ptrace.c index 2d50024..addc14a 100644 --- a/arch/x86_64/kernel/ptrace.c +++ b/arch/x86_64/kernel/ptrace.c @@ -116,17 +116,17 @@ unsigned long convert_rip_to_linear(struct task_struct *child, struct pt_regs *r return addr; } -static int is_at_popf(struct task_struct *child, struct pt_regs *regs) +static int is_setting_trap_flag(struct task_struct *child, struct pt_regs *regs) { int i, copied; - unsigned char opcode[16]; + unsigned char opcode[15]; unsigned long addr = convert_rip_to_linear(child, regs); copied = access_process_vm(child, addr, opcode, sizeof(opcode), 0); for (i = 0; i < copied; i++) { switch (opcode[i]) { - /* popf */ - case 0x9d: + /* popf and iret */ + case 0x9d: case 0xcf: return 1; /* CHECKME: 64 65 */ @@ -138,14 +138,17 @@ static int is_at_popf(struct task_struct *child, struct pt_regs *regs) case 0x26: case 0x2e: case 0x36: case 0x3e: case 0x64: case 0x65: - case 0xf0: case 0xf2: case 0xf3: + case 0xf2: case 0xf3: continue; - /* REX prefixes */ case 0x40 ... 0x4f: + if (regs->cs != __USER_CS) + /* 32-bit mode: register increment */ + return 0; + /* 64-bit mode: REX prefix */ continue; - /* CHECKME: f0, f2, f3 */ + /* CHECKME: f2, f3 */ /* * pushf: NOTE! We should probably not let @@ -186,10 +189,8 @@ static void set_singlestep(struct task_struct *child) * ..but if TF is changed by the instruction we will trace, * don't mark it as being "us" that set it, so that we * won't clear it by hand later. - * - * AK: this is not enough, LAHF and IRET can change TF in user space too. */ - if (is_at_popf(child, regs)) + if (is_setting_trap_flag(child, regs)) return; child->ptrace |= PT_DTRACE; @@ -420,9 +421,13 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) if ((0x5554 >> ((data >> (16 + 4*i)) & 0xf)) & 1) break; if (i == 4) { - child->thread.debugreg7 = data; + child->thread.debugreg7 = data; + if (data) + set_tsk_thread_flag(child, TIF_DEBUG); + else + clear_tsk_thread_flag(child, TIF_DEBUG); ret = 0; - } + } break; } break; diff --git a/arch/x86_64/kernel/relocate_kernel.S b/arch/x86_64/kernel/relocate_kernel.S index d24fa9b..14e9587 100644 --- a/arch/x86_64/kernel/relocate_kernel.S +++ b/arch/x86_64/kernel/relocate_kernel.S @@ -7,31 +7,169 @@ */ #include <linux/linkage.h> +#include <asm/page.h> +#include <asm/kexec.h> - /* - * Must be relocatable PIC code callable as a C function, that once - * it starts can not use the previous processes stack. - */ - .globl relocate_new_kernel +/* + * 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 */ + + .text + .align PAGE_ALIGNED .code64 + .globl relocate_kernel +relocate_kernel: + /* %rdi indirection_page + * %rsi page_list + * %rdx start address + */ + + /* map the control page at its virtual address */ + + movq $0x0000ff8000000000, %r10 /* mask */ + mov $(39 - 3), %cl /* bits to shift */ + movq PTR(VA_CONTROL_PAGE)(%rsi), %r11 /* address to map */ + + movq %r11, %r9 + andq %r10, %r9 + shrq %cl, %r9 + + movq PTR(VA_PGD)(%rsi), %r8 + addq %r8, %r9 + movq PTR(PA_PUD_0)(%rsi), %r8 + orq $PAGE_ATTR, %r8 + movq %r8, (%r9) + + shrq $9, %r10 + sub $9, %cl + + movq %r11, %r9 + andq %r10, %r9 + shrq %cl, %r9 + + movq PTR(VA_PUD_0)(%rsi), %r8 + addq %r8, %r9 + movq PTR(PA_PMD_0)(%rsi), %r8 + orq $PAGE_ATTR, %r8 + movq %r8, (%r9) + + shrq $9, %r10 + sub $9, %cl + + movq %r11, %r9 + andq %r10, %r9 + shrq %cl, %r9 + + movq PTR(VA_PMD_0)(%rsi), %r8 + addq %r8, %r9 + movq PTR(PA_PTE_0)(%rsi), %r8 + orq $PAGE_ATTR, %r8 + movq %r8, (%r9) + + shrq $9, %r10 + sub $9, %cl + + movq %r11, %r9 + andq %r10, %r9 + shrq %cl, %r9 + + movq PTR(VA_PTE_0)(%rsi), %r8 + addq %r8, %r9 + movq PTR(PA_CONTROL_PAGE)(%rsi), %r8 + orq $PAGE_ATTR, %r8 + movq %r8, (%r9) + + /* identity map the control page at its physical address */ + + movq $0x0000ff8000000000, %r10 /* mask */ + mov $(39 - 3), %cl /* bits to shift */ + movq PTR(PA_CONTROL_PAGE)(%rsi), %r11 /* address to map */ + + movq %r11, %r9 + andq %r10, %r9 + shrq %cl, %r9 + + movq PTR(VA_PGD)(%rsi), %r8 + addq %r8, %r9 + movq PTR(PA_PUD_1)(%rsi), %r8 + orq $PAGE_ATTR, %r8 + movq %r8, (%r9) + + shrq $9, %r10 + sub $9, %cl + + movq %r11, %r9 + andq %r10, %r9 + shrq %cl, %r9 + + movq PTR(VA_PUD_1)(%rsi), %r8 + addq %r8, %r9 + movq PTR(PA_PMD_1)(%rsi), %r8 + orq $PAGE_ATTR, %r8 + movq %r8, (%r9) + + shrq $9, %r10 + sub $9, %cl + + movq %r11, %r9 + andq %r10, %r9 + shrq %cl, %r9 + + movq PTR(VA_PMD_1)(%rsi), %r8 + addq %r8, %r9 + movq PTR(PA_PTE_1)(%rsi), %r8 + orq $PAGE_ATTR, %r8 + movq %r8, (%r9) + + shrq $9, %r10 + sub $9, %cl + + movq %r11, %r9 + andq %r10, %r9 + shrq %cl, %r9 + + movq PTR(VA_PTE_1)(%rsi), %r8 + addq %r8, %r9 + movq PTR(PA_CONTROL_PAGE)(%rsi), %r8 + orq $PAGE_ATTR, %r8 + movq %r8, (%r9) + relocate_new_kernel: - /* %rdi page_list - * %rsi reboot_code_buffer + /* %rdi indirection_page + * %rsi page_list * %rdx start address - * %rcx page_table - * %r8 arg5 - * %r9 arg6 */ /* zero out flags, and disable interrupts */ pushq $0 popfq - /* set a new stack at the bottom of our page... */ - lea 4096(%rsi), %rsp + /* get physical address of control page now */ + /* this is impossible after page table switch */ + movq PTR(PA_CONTROL_PAGE)(%rsi), %r8 + + /* get physical address of page table now too */ + movq PTR(PA_TABLE_PAGE)(%rsi), %rcx - /* store the parameters back on the stack */ - pushq %rdx /* store the start address */ + /* switch to new set of page tables */ + movq PTR(PA_PGD)(%rsi), %r9 + movq %r9, %cr3 + + /* setup a new stack at the end of the physical control page */ + lea 4096(%r8), %rsp + + /* jump to identity mapped page */ + addq $(identity_mapped - relocate_kernel), %r8 + pushq %r8 + ret + +identity_mapped: + /* store the start address on the stack */ + pushq %rdx /* Set cr0 to a known state: * 31 1 == Paging enabled @@ -136,8 +274,3 @@ relocate_new_kernel: xorq %r15, %r15 ret -relocate_new_kernel_end: - - .globl relocate_new_kernel_size -relocate_new_kernel_size: - .quad relocate_new_kernel_end - relocate_new_kernel diff --git a/arch/x86_64/kernel/setup.c b/arch/x86_64/kernel/setup.c index 4b39f0d..f98e48c 100644 --- a/arch/x86_64/kernel/setup.c +++ b/arch/x86_64/kernel/setup.c @@ -74,16 +74,6 @@ EXPORT_SYMBOL(boot_cpu_data); unsigned long mmu_cr4_features; -int acpi_disabled; -EXPORT_SYMBOL(acpi_disabled); -#ifdef CONFIG_ACPI -extern int __initdata acpi_ht; -extern acpi_interrupt_flags acpi_sci_flags; -int __initdata acpi_force = 0; -#endif - -int acpi_numa __initdata; - /* Boot loader ID as an integer, for the benefit of proc_dointvec */ int bootloader_type; @@ -107,7 +97,6 @@ struct sys_desc_table_struct { struct edid_info edid_info; EXPORT_SYMBOL_GPL(edid_info); -struct e820map e820; extern int root_mountflags; @@ -276,185 +265,22 @@ static void __init probe_roms(void) } } -/* Check for full argument with no trailing characters */ -static int fullarg(char *p, char *arg) +#ifdef CONFIG_PROC_VMCORE +/* elfcorehdr= specifies the location of elf core header + * stored by the crashed kernel. This option will be passed + * by kexec loader to the capture kernel. + */ +static int __init setup_elfcorehdr(char *arg) { - int l = strlen(arg); - return !memcmp(p, arg, l) && (p[l] == 0 || isspace(p[l])); + char *end; + if (!arg) + return -EINVAL; + elfcorehdr_addr = memparse(arg, &end); + return end > arg ? 0 : -EINVAL; } - -static __init void parse_cmdline_early (char ** cmdline_p) -{ - char c = ' ', *to = command_line, *from = COMMAND_LINE; - int len = 0; - int userdef = 0; - - for (;;) { - if (c != ' ') - goto next_char; - -#ifdef CONFIG_SMP - /* - * If the BIOS enumerates physical processors before logical, - * maxcpus=N at enumeration-time can be used to disable HT. - */ - else if (!memcmp(from, "maxcpus=", 8)) { - extern unsigned int maxcpus; - - maxcpus = simple_strtoul(from + 8, NULL, 0); - } -#endif -#ifdef CONFIG_ACPI - /* "acpi=off" disables both ACPI table parsing and interpreter init */ - if (fullarg(from,"acpi=off")) - disable_acpi(); - - if (fullarg(from, "acpi=force")) { - /* add later when we do DMI horrors: */ - acpi_force = 1; - acpi_disabled = 0; - } - - /* acpi=ht just means: do ACPI MADT parsing - at bootup, but don't enable the full ACPI interpreter */ - if (fullarg(from, "acpi=ht")) { - if (!acpi_force) - disable_acpi(); - acpi_ht = 1; - } - else if (fullarg(from, "pci=noacpi")) - acpi_disable_pci(); - else if (fullarg(from, "acpi=noirq")) - acpi_noirq_set(); - - else if (fullarg(from, "acpi_sci=edge")) - acpi_sci_flags.trigger = 1; - else if (fullarg(from, "acpi_sci=level")) - acpi_sci_flags.trigger = 3; - else if (fullarg(from, "acpi_sci=high")) - acpi_sci_flags.polarity = 1; - else if (fullarg(from, "acpi_sci=low")) - acpi_sci_flags.polarity = 3; - - /* acpi=strict disables out-of-spec workarounds */ - else if (fullarg(from, "acpi=strict")) { - acpi_strict = 1; - } -#ifdef CONFIG_X86_IO_APIC - else if (fullarg(from, "acpi_skip_timer_override")) - acpi_skip_timer_override = 1; -#endif -#endif - - if (fullarg(from, "disable_timer_pin_1")) - disable_timer_pin_1 = 1; - if (fullarg(from, "enable_timer_pin_1")) - disable_timer_pin_1 = -1; - - if (fullarg(from, "nolapic") || fullarg(from, "disableapic")) { - clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability); - disable_apic = 1; - } - - if (fullarg(from, "noapic")) - skip_ioapic_setup = 1; - - if (fullarg(from,"apic")) { - skip_ioapic_setup = 0; - ioapic_force = 1; - } - - if (!memcmp(from, "mem=", 4)) - parse_memopt(from+4, &from); - - if (!memcmp(from, "memmap=", 7)) { - /* exactmap option is for used defined memory */ - if (!memcmp(from+7, "exactmap", 8)) { -#ifdef CONFIG_CRASH_DUMP - /* If we are doing a crash dump, we - * still need to know the real mem - * size before original memory map is - * reset. - */ - saved_max_pfn = e820_end_of_ram(); -#endif - from += 8+7; - end_pfn_map = 0; - e820.nr_map = 0; - userdef = 1; - } - else { - parse_memmapopt(from+7, &from); - userdef = 1; - } - } - -#ifdef CONFIG_NUMA - if (!memcmp(from, "numa=", 5)) - numa_setup(from+5); -#endif - - if (!memcmp(from,"iommu=",6)) { - iommu_setup(from+6); - } - - if (fullarg(from,"oops=panic")) - panic_on_oops = 1; - - if (!memcmp(from, "noexec=", 7)) - nonx_setup(from + 7); - -#ifdef CONFIG_KEXEC - /* crashkernel=size@addr specifies the location to reserve for - * a crash kernel. By reserving this memory we guarantee - * that linux never set's it up as a DMA target. - * Useful for holding code to do something appropriate - * after a kernel panic. - */ - else if (!memcmp(from, "crashkernel=", 12)) { - unsigned long size, base; - size = memparse(from+12, &from); - if (*from == '@') { - base = memparse(from+1, &from); - /* FIXME: Do I want a sanity check - * to validate the memory range? - */ - crashk_res.start = base; - crashk_res.end = base + size - 1; - } - } -#endif - -#ifdef CONFIG_PROC_VMCORE - /* elfcorehdr= specifies the location of elf core header - * stored by the crashed kernel. This option will be passed - * by kexec loader to the capture kernel. - */ - else if(!memcmp(from, "elfcorehdr=", 11)) - elfcorehdr_addr = memparse(from+11, &from); -#endif - -#ifdef CONFIG_HOTPLUG_CPU - else if (!memcmp(from, "additional_cpus=", 16)) - setup_additional_cpus(from+16); +early_param("elfcorehdr", setup_elfcorehdr); #endif - next_char: - c = *(from++); - if (!c) - break; - if (COMMAND_LINE_SIZE <= ++len) - break; - *(to++) = c; - } - if (userdef) { - printk(KERN_INFO "user-defined physical RAM map:\n"); - e820_print_map("user"); - } - *to = '\0'; - *cmdline_p = command_line; -} - #ifndef CONFIG_NUMA static void __init contig_initmem_init(unsigned long start_pfn, unsigned long end_pfn) @@ -521,6 +347,8 @@ static void discover_ebda(void) void __init setup_arch(char **cmdline_p) { + printk(KERN_INFO "Command line: %s\n", saved_command_line); + ROOT_DEV = old_decode_dev(ORIG_ROOT_DEV); screen_info = SCREEN_INFO; edid_info = EDID_INFO; @@ -547,16 +375,21 @@ void __init setup_arch(char **cmdline_p) data_resource.start = virt_to_phys(&_etext); data_resource.end = virt_to_phys(&_edata)-1; - parse_cmdline_early(cmdline_p); - early_identify_cpu(&boot_cpu_data); + strlcpy(command_line, saved_command_line, COMMAND_LINE_SIZE); + *cmdline_p = command_line; + + parse_early_param(); + + finish_e820_parsing(); + /* * partially used pages are not usable - thus * we are rounding upwards: */ end_pfn = e820_end_of_ram(); - num_physpages = end_pfn; /* for pfn_valid */ + num_physpages = end_pfn; check_efer(); @@ -576,6 +409,11 @@ void __init setup_arch(char **cmdline_p) acpi_boot_table_init(); #endif + /* How many end-of-memory variables you have, grandma! */ + max_low_pfn = end_pfn; + max_pfn = end_pfn; + high_memory = (void *)__va(end_pfn * PAGE_SIZE - 1) + 1; + #ifdef CONFIG_ACPI_NUMA /* * Parse SRAT to discover nodes. @@ -625,12 +463,10 @@ void __init setup_arch(char **cmdline_p) */ acpi_reserve_bootmem(); #endif -#ifdef CONFIG_X86_LOCAL_APIC /* * Find and reserve possible boot-time SMP configuration: */ find_smp_config(); -#endif #ifdef CONFIG_BLK_DEV_INITRD if (LOADER_TYPE && INITRD_START) { if (INITRD_START + INITRD_SIZE <= (end_pfn << PAGE_SHIFT)) { @@ -657,7 +493,9 @@ void __init setup_arch(char **cmdline_p) paging_init(); - check_ioapic(); +#ifdef CONFIG_PCI + early_quirks(); +#endif /* * set this early, so we dont allocate cpu0 @@ -674,14 +512,12 @@ void __init setup_arch(char **cmdline_p) init_cpu_to_node(); -#ifdef CONFIG_X86_LOCAL_APIC /* * get boot-time SMP configuration: */ if (smp_found_config) get_smp_config(); init_apic_mappings(); -#endif /* * Request address space for all standard RAM and ROM resources @@ -839,7 +675,7 @@ static void __init amd_detect_cmp(struct cpuinfo_x86 *c) #endif } -static void __init init_amd(struct cpuinfo_x86 *c) +static void __cpuinit init_amd(struct cpuinfo_x86 *c) { unsigned level; @@ -895,6 +731,12 @@ static void __init init_amd(struct cpuinfo_x86 *c) /* Fix cpuid4 emulation for more */ num_cache_leaves = 3; + + /* When there is only one core no need to synchronize RDTSC */ + if (num_possible_cpus() == 1) + set_bit(X86_FEATURE_SYNC_RDTSC, &c->x86_capability); + else + clear_bit(X86_FEATURE_SYNC_RDTSC, &c->x86_capability); } static void __cpuinit detect_ht(struct cpuinfo_x86 *c) @@ -976,8 +818,7 @@ static void srat_detect_node(void) node = first_node(node_online_map); numa_set_node(cpu, node); - if (acpi_numa > 0) - printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node); + printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node); #endif } @@ -1011,6 +852,8 @@ static void __cpuinit 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); + if (c->x86 == 6) + set_bit(X86_FEATURE_REP_GOOD, &c->x86_capability); set_bit(X86_FEATURE_SYNC_RDTSC, &c->x86_capability); c->x86_max_cores = intel_num_cpu_cores(c); @@ -1229,8 +1072,8 @@ static int show_cpuinfo(struct seq_file *m, void *v) /* Intel-defined (#2) */ "pni", NULL, NULL, "monitor", "ds_cpl", "vmx", "smx", "est", - "tm2", NULL, "cid", NULL, NULL, "cx16", "xtpr", NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + "tm2", "ssse3", "cid", NULL, NULL, "cx16", "xtpr", NULL, + NULL, NULL, "dca", NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, /* VIA/Cyrix/Centaur-defined */ diff --git a/arch/x86_64/kernel/setup64.c b/arch/x86_64/kernel/setup64.c index 417de56..8c4b80f 100644 --- a/arch/x86_64/kernel/setup64.c +++ b/arch/x86_64/kernel/setup64.c @@ -24,7 +24,7 @@ #include <asm/proto.h> #include <asm/sections.h> -char x86_boot_params[BOOT_PARAM_SIZE] __initdata = {0,}; +char x86_boot_params[BOOT_PARAM_SIZE] __initdata; cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE; @@ -46,8 +46,10 @@ Control non executable mappings for 64bit processes. on Enable(default) off Disable */ -int __init nonx_setup(char *str) +static int __init nonx_setup(char *str) { + if (!str) + return -EINVAL; if (!strncmp(str, "on", 2)) { __supported_pte_mask |= _PAGE_NX; do_not_nx = 0; @@ -55,9 +57,9 @@ int __init nonx_setup(char *str) do_not_nx = 1; __supported_pte_mask &= ~_PAGE_NX; } - return 1; + return 0; } -__setup("noexec=", nonx_setup); /* parsed early actually */ +early_param("noexec", nonx_setup); int force_personality32 = 0; @@ -93,12 +95,9 @@ void __init setup_per_cpu_areas(void) #endif /* Copy section for each CPU (we discard the original) */ - size = ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES); -#ifdef CONFIG_MODULES - if (size < PERCPU_ENOUGH_ROOM) - size = PERCPU_ENOUGH_ROOM; -#endif + 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; @@ -122,7 +121,10 @@ void pda_init(int cpu) /* Setup up data that may be needed in __get_free_pages early */ asm volatile("movl %0,%%fs ; movl %0,%%gs" :: "r" (0)); + /* Memory clobbers used to order PDA accessed */ + mb(); wrmsrl(MSR_GS_BASE, pda); + mb(); pda->cpunumber = cpu; pda->irqcount = -1; @@ -178,6 +180,8 @@ void __cpuinit check_efer(void) } } +unsigned long kernel_eflags; + /* * cpu_init() initializes state that is per-CPU. Some data is already * initialized (naturally) in the bootstrap process, such as the GDT @@ -235,28 +239,17 @@ void __cpuinit cpu_init (void) * set up and load the per-CPU TSS */ for (v = 0; v < N_EXCEPTION_STACKS; v++) { + static const unsigned int order[N_EXCEPTION_STACKS] = { + [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STACK_ORDER, + [DEBUG_STACK - 1] = DEBUG_STACK_ORDER + }; if (cpu) { - static const unsigned int order[N_EXCEPTION_STACKS] = { - [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STACK_ORDER, - [DEBUG_STACK - 1] = DEBUG_STACK_ORDER - }; - estacks = (char *)__get_free_pages(GFP_ATOMIC, order[v]); if (!estacks) panic("Cannot allocate exception stack %ld %d\n", v, cpu); } - switch (v + 1) { -#if DEBUG_STKSZ > EXCEPTION_STKSZ - case DEBUG_STACK: - cpu_pda(cpu)->debugstack = (unsigned long)estacks; - estacks += DEBUG_STKSZ; - break; -#endif - default: - estacks += EXCEPTION_STKSZ; - break; - } + estacks += PAGE_SIZE << order[v]; orig_ist->ist[v] = t->ist[v] = (unsigned long)estacks; } @@ -290,4 +283,6 @@ void __cpuinit cpu_init (void) set_debugreg(0UL, 7); fpu_init(); + + raw_local_save_flags(kernel_eflags); } diff --git a/arch/x86_64/kernel/signal.c b/arch/x86_64/kernel/signal.c index 2816117..49ec324 100644 --- a/arch/x86_64/kernel/signal.c +++ b/arch/x86_64/kernel/signal.c @@ -38,37 +38,6 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka, sigset_t *set, struct pt_regs * regs); asmlinkage long -sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize, struct pt_regs *regs) -{ - sigset_t saveset, newset; - - /* XXX: Don't preclude handling different sized sigset_t's. */ - if (sigsetsize != sizeof(sigset_t)) - return -EINVAL; - - if (copy_from_user(&newset, unewset, sizeof(newset))) - return -EFAULT; - sigdelsetmask(&newset, ~_BLOCKABLE); - - spin_lock_irq(¤t->sighand->siglock); - saveset = current->blocked; - current->blocked = newset; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); -#ifdef DEBUG_SIG - printk("rt_sigsuspend savset(%lx) newset(%lx) regs(%p) rip(%lx)\n", - saveset, newset, regs, regs->rip); -#endif - regs->rax = -EINTR; - while (1) { - current->state = TASK_INTERRUPTIBLE; - schedule(); - if (do_signal(regs, &saveset)) - return -EINTR; - } -} - -asmlinkage long sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, struct pt_regs *regs) { @@ -308,11 +277,6 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, #endif /* Set up registers for signal handler */ - { - struct exec_domain *ed = current_thread_info()->exec_domain; - if (unlikely(ed && ed->signal_invmap && sig < 32)) - sig = ed->signal_invmap[sig]; - } regs->rdi = sig; /* In case the signal handler was declared without prototypes */ regs->rax = 0; @@ -341,11 +305,11 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, current->comm, current->pid, frame, regs->rip, frame->pretcode); #endif - return 1; + return 0; give_sigsegv: force_sigsegv(sig, current); - return 0; + return -EFAULT; } /* @@ -408,7 +372,7 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, #endif ret = setup_rt_frame(sig, ka, info, oldset, regs); - if (ret) { + 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)) @@ -425,11 +389,12 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, * want to handle. Thus you cannot kill init even with a SIGKILL even by * mistake. */ -int do_signal(struct pt_regs *regs, sigset_t *oldset) +static void do_signal(struct pt_regs *regs) { struct k_sigaction ka; siginfo_t info; int signr; + sigset_t *oldset; /* * We want the common case to go fast, which @@ -438,9 +403,11 @@ int do_signal(struct pt_regs *regs, sigset_t *oldset) * if so. */ if (!user_mode(regs)) - return 1; + return; - if (!oldset) + if (test_thread_flag(TIF_RESTORE_SIGMASK)) + oldset = ¤t->saved_sigmask; + else oldset = ¤t->blocked; signr = get_signal_to_deliver(&info, &ka, regs, NULL); @@ -454,30 +421,46 @@ int do_signal(struct pt_regs *regs, sigset_t *oldset) set_debugreg(current->thread.debugreg7, 7); /* Whee! Actually deliver the signal. */ - return handle_signal(signr, &info, &ka, oldset, regs); + if (handle_signal(signr, &info, &ka, oldset, regs) == 0) { + /* 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); + } + return; } /* Did we come from a system call? */ if ((long)regs->orig_rax >= 0) { /* Restart the system call - no handlers present */ long res = regs->rax; - if (res == -ERESTARTNOHAND || - res == -ERESTARTSYS || - res == -ERESTARTNOINTR) { + switch (res) { + case -ERESTARTNOHAND: + case -ERESTARTSYS: + case -ERESTARTNOINTR: regs->rax = regs->orig_rax; regs->rip -= 2; - } - if (regs->rax == (unsigned long)-ERESTART_RESTARTBLOCK) { + break; + case -ERESTART_RESTARTBLOCK: regs->rax = test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall : __NR_restart_syscall; regs->rip -= 2; + break; } } - return 0; + + /* 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); + sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); + } } -void do_notify_resume(struct pt_regs *regs, sigset_t *oldset, __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 rip:%lx rsp:%lx caller:%lx pending:%lx\n", @@ -491,8 +474,8 @@ void do_notify_resume(struct pt_regs *regs, sigset_t *oldset, __u32 thread_info_ } /* deal with pending signal delivery */ - if (thread_info_flags & _TIF_SIGPENDING) - do_signal(regs,oldset); + if (thread_info_flags & (_TIF_SIGPENDING|_TIF_RESTORE_SIGMASK)) + do_signal(regs); } void signal_fault(struct pt_regs *regs, void __user *frame, char *where) diff --git a/arch/x86_64/kernel/smp.c b/arch/x86_64/kernel/smp.c index 06af6ca..4f67697 100644 --- a/arch/x86_64/kernel/smp.c +++ b/arch/x86_64/kernel/smp.c @@ -522,26 +522,3 @@ asmlinkage void smp_call_function_interrupt(void) } } -int safe_smp_processor_id(void) -{ - unsigned apicid, i; - - if (disable_apic) - return 0; - - apicid = hard_smp_processor_id(); - if (apicid < NR_CPUS && x86_cpu_to_apicid[apicid] == apicid) - return apicid; - - for (i = 0; i < NR_CPUS; ++i) { - if (x86_cpu_to_apicid[i] == apicid) - return i; - } - - /* No entries in x86_cpu_to_apicid? Either no MPS|ACPI, - * or called too early. Either way, we must be CPU 0. */ - if (x86_cpu_to_apicid[0] == BAD_APICID) - return 0; - - return 0; /* Should not happen */ -} diff --git a/arch/x86_64/kernel/smpboot.c b/arch/x86_64/kernel/smpboot.c index 3ae9ffd..7b7a687 100644 --- a/arch/x86_64/kernel/smpboot.c +++ b/arch/x86_64/kernel/smpboot.c @@ -1091,7 +1091,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus) /* * Switch from PIC to APIC mode. */ - connect_bsp_APIC(); setup_local_APIC(); if (GET_APIC_ID(apic_read(APIC_ID)) != boot_cpu_id) { @@ -1176,12 +1175,9 @@ int __cpuinit __cpu_up(unsigned int cpu) void __init smp_cpus_done(unsigned int max_cpus) { smp_cleanup_boot(); - -#ifdef CONFIG_X86_IO_APIC setup_ioapic_dest(); -#endif - check_nmi_watchdog(); + time_init_gtod(); } #ifdef CONFIG_HOTPLUG_CPU @@ -1234,6 +1230,8 @@ int __cpu_disable(void) if (cpu == 0) return -EBUSY; + if (nmi_watchdog == NMI_LOCAL_APIC) + stop_apic_nmi_watchdog(NULL); clear_local_APIC(); /* @@ -1273,11 +1271,11 @@ void __cpu_die(unsigned int cpu) printk(KERN_ERR "CPU %u didn't die...\n", cpu); } -__init int setup_additional_cpus(char *s) +static __init int setup_additional_cpus(char *s) { - return get_option(&s, &additional_cpus); + return s && get_option(&s, &additional_cpus) ? 0 : -EINVAL; } -__setup("additional_cpus=", setup_additional_cpus); +early_param("additional_cpus", setup_additional_cpus); #else /* ... !CONFIG_HOTPLUG_CPU */ diff --git a/arch/x86_64/kernel/stacktrace.c b/arch/x86_64/kernel/stacktrace.c index 32cf55e..6026b31 100644 --- a/arch/x86_64/kernel/stacktrace.c +++ b/arch/x86_64/kernel/stacktrace.c @@ -7,215 +7,49 @@ */ #include <linux/sched.h> #include <linux/stacktrace.h> +#include <linux/module.h> +#include <asm/stacktrace.h> -#include <asm/smp.h> - -static inline int -in_range(unsigned long start, unsigned long addr, unsigned long end) +static void save_stack_warning(void *data, char *msg) { - return addr >= start && addr <= end; } -static unsigned long -get_stack_end(struct task_struct *task, unsigned long stack) +static void +save_stack_warning_symbol(void *data, char *msg, unsigned long symbol) { - unsigned long stack_start, stack_end, flags; - int i, cpu; - - /* - * The most common case is that we are in the task stack: - */ - stack_start = (unsigned long)task->thread_info; - stack_end = stack_start + THREAD_SIZE; - - if (in_range(stack_start, stack, stack_end)) - return stack_end; - - /* - * We are in an interrupt if irqstackptr is set: - */ - raw_local_irq_save(flags); - cpu = safe_smp_processor_id(); - stack_end = (unsigned long)cpu_pda(cpu)->irqstackptr; - - if (stack_end) { - stack_start = stack_end & ~(IRQSTACKSIZE-1); - if (in_range(stack_start, stack, stack_end)) - goto out_restore; - /* - * We get here if we are in an IRQ context but we - * are also in an exception stack. - */ - } - - /* - * Iterate over all exception stacks, and figure out whether - * 'stack' is in one of them: - */ - for (i = 0; i < N_EXCEPTION_STACKS; i++) { - /* - * set 'end' to the end of the exception stack. - */ - stack_end = per_cpu(init_tss, cpu).ist[i]; - stack_start = stack_end - EXCEPTION_STKSZ; - - /* - * Is 'stack' above this exception frame's end? - * If yes then skip to the next frame. - */ - if (stack >= stack_end) - continue; - /* - * Is 'stack' above this exception frame's start address? - * If yes then we found the right frame. - */ - if (stack >= stack_start) - goto out_restore; - - /* - * If this is a debug stack, and if it has a larger size than - * the usual exception stacks, then 'stack' might still - * be within the lower portion of the debug stack: - */ -#if DEBUG_STKSZ > EXCEPTION_STKSZ - if (i == DEBUG_STACK - 1 && stack >= stack_end - DEBUG_STKSZ) { - /* - * Black magic. A large debug stack is composed of - * multiple exception stack entries, which we - * iterate through now. Dont look: - */ - do { - stack_end -= EXCEPTION_STKSZ; - stack_start -= EXCEPTION_STKSZ; - } while (stack < stack_start); - - goto out_restore; - } -#endif - } - /* - * Ok, 'stack' is not pointing to any of the system stacks. - */ - stack_end = 0; - -out_restore: - raw_local_irq_restore(flags); - - return stack_end; } - -/* - * Save stack-backtrace addresses into a stack_trace buffer: - */ -static inline unsigned long -save_context_stack(struct stack_trace *trace, unsigned int skip, - unsigned long stack, unsigned long stack_end) +static int save_stack_stack(void *data, char *name) { - unsigned long addr; - -#ifdef CONFIG_FRAME_POINTER - unsigned long prev_stack = 0; + struct stack_trace *trace = (struct stack_trace *)data; + return trace->all_contexts ? 0 : -1; +} - while (in_range(prev_stack, stack, stack_end)) { - pr_debug("stack: %p\n", (void *)stack); - addr = (unsigned long)(((unsigned long *)stack)[1]); - pr_debug("addr: %p\n", (void *)addr); - if (!skip) - trace->entries[trace->nr_entries++] = addr-1; - else - skip--; - if (trace->nr_entries >= trace->max_entries) - break; - if (!addr) - return 0; - /* - * Stack frames must go forwards (otherwise a loop could - * happen if the stackframe is corrupted), so we move - * prev_stack forwards: - */ - prev_stack = stack; - stack = (unsigned long)(((unsigned long *)stack)[0]); - } - pr_debug("invalid: %p\n", (void *)stack); -#else - while (stack < stack_end) { - addr = ((unsigned long *)stack)[0]; - stack += sizeof(long); - if (__kernel_text_address(addr)) { - if (!skip) - trace->entries[trace->nr_entries++] = addr-1; - else - skip--; - if (trace->nr_entries >= trace->max_entries) - break; - } +static void save_stack_address(void *data, unsigned long addr) +{ + struct stack_trace *trace = (struct stack_trace *)data; + if (trace->skip > 0) { + trace->skip--; + return; } -#endif - return stack; + if (trace->nr_entries < trace->max_entries - 1) + trace->entries[trace->nr_entries++] = addr; } -#define MAX_STACKS 10 +static struct stacktrace_ops save_stack_ops = { + .warning = save_stack_warning, + .warning_symbol = save_stack_warning_symbol, + .stack = save_stack_stack, + .address = save_stack_address, +}; /* * Save stack-backtrace addresses into a stack_trace buffer. - * If all_contexts is set, all contexts (hardirq, softirq and process) - * are saved. If not set then only the current context is saved. */ -void save_stack_trace(struct stack_trace *trace, - struct task_struct *task, int all_contexts, - unsigned int skip) +void save_stack_trace(struct stack_trace *trace, struct task_struct *task) { - unsigned long stack = (unsigned long)&stack; - int i, nr_stacks = 0, stacks_done[MAX_STACKS]; - - WARN_ON(trace->nr_entries || !trace->max_entries); - - if (!task) - task = current; - - pr_debug("task: %p, ti: %p\n", task, task->thread_info); - - if (!task || task == current) { - /* Grab rbp right from our regs: */ - asm ("mov %%rbp, %0" : "=r" (stack)); - pr_debug("rbp: %p\n", (void *)stack); - } else { - /* rbp is the last reg pushed by switch_to(): */ - stack = task->thread.rsp; - pr_debug("other task rsp: %p\n", (void *)stack); - stack = (unsigned long)(((unsigned long *)stack)[0]); - pr_debug("other task rbp: %p\n", (void *)stack); - } - - while (1) { - unsigned long stack_end = get_stack_end(task, stack); - - pr_debug("stack: %p\n", (void *)stack); - pr_debug("stack end: %p\n", (void *)stack_end); - - /* - * Invalid stack addres? - */ - if (!stack_end) - return; - /* - * Were we in this stack already? (recursion) - */ - for (i = 0; i < nr_stacks; i++) - if (stacks_done[i] == stack_end) - return; - stacks_done[nr_stacks] = stack_end; - - stack = save_context_stack(trace, skip, stack, stack_end); - if (!all_contexts || !stack || - trace->nr_entries >= trace->max_entries) - return; - trace->entries[trace->nr_entries++] = ULONG_MAX; - if (trace->nr_entries >= trace->max_entries) - return; - if (++nr_stacks >= MAX_STACKS) - return; - } + dump_trace(task, NULL, NULL, &save_stack_ops, trace); + trace->entries[trace->nr_entries++] = ULONG_MAX; } +EXPORT_SYMBOL(save_stack_trace); diff --git a/arch/x86_64/kernel/tce.c b/arch/x86_64/kernel/tce.c index 5530dda..cbabfdf 100644 --- a/arch/x86_64/kernel/tce.c +++ b/arch/x86_64/kernel/tce.c @@ -1,4 +1,6 @@ /* + * This file manages the translation entries for the IBM Calgary IOMMU. + * * Derived from arch/powerpc/platforms/pseries/iommu.c * * Copyright (C) IBM Corporation, 2006 @@ -104,14 +106,6 @@ static int tce_table_setparms(struct pci_dev *dev, struct iommu_table *tbl) /* set the tce table size - measured in entries */ tbl->it_size = table_size_to_number_of_entries(specified_table_size); - tbl->it_base = (unsigned long)tce_table_kva[dev->bus->number]; - if (!tbl->it_base) { - printk(KERN_ERR "Calgary: iommu_table_setparms: " - "no table allocated?!\n"); - ret = -ENOMEM; - goto done; - } - /* * number of bytes needed for the bitmap size in number of * entries; we need one bit per entry @@ -160,8 +154,6 @@ int build_tce_table(struct pci_dev *dev, void __iomem *bbar) if (ret) goto free_tbl; - tce_free(tbl, 0, tbl->it_size); - tbl->bbar = bbar; /* diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c index 7700e6c..1c255ee 100644 --- a/arch/x86_64/kernel/time.c +++ b/arch/x86_64/kernel/time.c @@ -24,6 +24,8 @@ #include <linux/device.h> #include <linux/sysdev.h> #include <linux/bcd.h> +#include <linux/notifier.h> +#include <linux/cpu.h> #include <linux/kallsyms.h> #include <linux/acpi.h> #ifdef CONFIG_ACPI @@ -39,9 +41,7 @@ #include <asm/sections.h> #include <linux/cpufreq.h> #include <linux/hpet.h> -#ifdef CONFIG_X86_LOCAL_APIC #include <asm/apic.h> -#endif #ifdef CONFIG_CPU_FREQ static void cpufreq_delayed_get(void); @@ -49,7 +49,7 @@ static void cpufreq_delayed_get(void); extern void i8254_timer_resume(void); extern int using_apic_timer; -static char *time_init_gtod(void); +static char *timename = NULL; DEFINE_SPINLOCK(rtc_lock); EXPORT_SYMBOL(rtc_lock); @@ -187,20 +187,15 @@ unsigned long profile_pc(struct pt_regs *regs) { unsigned long pc = instruction_pointer(regs); - /* Assume the lock function has either no stack frame or only a single - word. This checks if the address on the stack looks like a kernel - text address. - There is a small window for false hits, but in that case the tick - is just accounted to the spinlock function. - Better would be to write these functions in assembler again - and check exactly. */ + /* Assume the lock function has either no stack frame or a copy + of eflags from PUSHF + Eflags always has bits 22 and up cleared unlike kernel addresses. */ if (!user_mode(regs) && in_lock_functions(pc)) { - char *v = *(char **)regs->rsp; - if ((v >= _stext && v <= _etext) || - (v >= _sinittext && v <= _einittext) || - (v >= (char *)MODULES_VADDR && v <= (char *)MODULES_END)) - return (unsigned long)v; - return ((unsigned long *)regs->rsp)[1]; + unsigned long *sp = (unsigned long *)regs->rsp; + if (sp[0] >> 22) + return sp[0]; + if (sp[1] >> 22) + return sp[1]; } return pc; } @@ -281,6 +276,7 @@ static void set_rtc_mmss(unsigned long nowtime) * Note: This function is required to return accurate * time even in the absence of multiple timer ticks. */ +static inline unsigned long long cycles_2_ns(unsigned long long cyc); unsigned long long monotonic_clock(void) { unsigned long seq; @@ -305,8 +301,7 @@ unsigned long long monotonic_clock(void) base = monotonic_base; } while (read_seqretry(&xtime_lock, seq)); this_offset = get_cycles_sync(); - /* FIXME: 1000 or 1000000? */ - offset = (this_offset - last_offset)*1000 / cpu_khz; + offset = cycles_2_ns(this_offset - last_offset); } return base + offset; } @@ -410,8 +405,7 @@ void main_timer_handler(struct pt_regs *regs) offset %= USEC_PER_TICK; } - /* FIXME: 1000 or 1000000? */ - monotonic_base += (tsc - vxtime.last_tsc) * 1000000 / cpu_khz; + monotonic_base += cycles_2_ns(tsc - vxtime.last_tsc); vxtime.last_tsc = tsc - vxtime.quot * delay / vxtime.tsc_quot; @@ -441,12 +435,8 @@ void main_timer_handler(struct pt_regs *regs) * have to call the local interrupt handler. */ -#ifndef CONFIG_X86_LOCAL_APIC - profile_tick(CPU_PROFILING, regs); -#else if (!using_apic_timer) smp_local_timer_interrupt(regs); -#endif /* * If we have an externally synchronized Linux clock, then update CMOS clock @@ -470,10 +460,8 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) if (apic_runs_main_timer > 1) return IRQ_HANDLED; main_timer_handler(regs); -#ifdef CONFIG_X86_LOCAL_APIC if (using_apic_timer) smp_send_timer_broadcast_ipi(); -#endif return IRQ_HANDLED; } @@ -893,11 +881,17 @@ static struct irqaction irq0 = { timer_interrupt, IRQF_DISABLED, CPU_MASK_NONE, "timer", NULL, NULL }; -void __init time_init(void) +static int __cpuinit +time_cpu_notifier(struct notifier_block *nb, unsigned long action, void *hcpu) { - char *timename; - char *gtod; + unsigned cpu = (unsigned long) hcpu; + if (action == CPU_ONLINE) + vsyscall_set_cpu(cpu); + return NOTIFY_DONE; +} +void __init time_init(void) +{ if (nohpet) vxtime.hpet_address = 0; @@ -931,18 +925,17 @@ void __init time_init(void) } vxtime.mode = VXTIME_TSC; - gtod = time_init_gtod(); - - printk(KERN_INFO "time.c: Using %ld.%06ld MHz WALL %s GTOD %s timer.\n", - vxtime_hz / 1000000, vxtime_hz % 1000000, timename, gtod); - printk(KERN_INFO "time.c: Detected %d.%03d MHz processor.\n", - cpu_khz / 1000, cpu_khz % 1000); vxtime.quot = (USEC_PER_SEC << US_SCALE) / vxtime_hz; vxtime.tsc_quot = (USEC_PER_MSEC << US_SCALE) / cpu_khz; vxtime.last_tsc = get_cycles_sync(); + set_cyc2ns_scale(cpu_khz); setup_irq(0, &irq0); + hotcpu_notifier(time_cpu_notifier, 0); + time_cpu_notifier(NULL, CPU_ONLINE, (void *)(long)smp_processor_id()); - set_cyc2ns_scale(cpu_khz); +#ifndef CONFIG_SMP + time_init_gtod(); +#endif } /* @@ -973,12 +966,18 @@ __cpuinit int unsynchronized_tsc(void) /* * Decide what mode gettimeofday should use. */ -__init static char *time_init_gtod(void) +void time_init_gtod(void) { char *timetype; if (unsynchronized_tsc()) notsc = 1; + + if (cpu_has(&boot_cpu_data, X86_FEATURE_RDTSCP)) + vgetcpu_mode = VGETCPU_RDTSCP; + else + vgetcpu_mode = VGETCPU_LSL; + if (vxtime.hpet_address && notsc) { timetype = hpet_use_timer ? "HPET" : "PIT/HPET"; if (hpet_use_timer) @@ -1001,7 +1000,16 @@ __init static char *time_init_gtod(void) timetype = hpet_use_timer ? "HPET/TSC" : "PIT/TSC"; vxtime.mode = VXTIME_TSC; } - return timetype; + + printk(KERN_INFO "time.c: Using %ld.%06ld MHz WALL %s GTOD %s timer.\n", + vxtime_hz / 1000000, vxtime_hz % 1000000, timename, timetype); + printk(KERN_INFO "time.c: Detected %d.%03d MHz processor.\n", + cpu_khz / 1000, cpu_khz % 1000); + vxtime.quot = (USEC_PER_SEC << US_SCALE) / vxtime_hz; + vxtime.tsc_quot = (USEC_PER_MSEC << US_SCALE) / cpu_khz; + vxtime.last_tsc = get_cycles_sync(); + + set_cyc2ns_scale(cpu_khz); } __setup("report_lost_ticks", time_setup); @@ -1031,8 +1039,16 @@ static int timer_resume(struct sys_device *dev) unsigned long flags; unsigned long sec; unsigned long ctime = get_cmos_time(); - unsigned long sleep_length = (ctime - sleep_start) * HZ; + long sleep_length = (ctime - sleep_start) * HZ; + if (sleep_length < 0) { + printk(KERN_WARNING "Time skew detected in timer resume!\n"); + /* The time after the resume must not be earlier than the time + * before the suspend or some nasty things will happen + */ + sleep_length = 0; + ctime = sleep_start; + } if (vxtime.hpet_address) hpet_reenable(); else diff --git a/arch/x86_64/kernel/trampoline.S b/arch/x86_64/kernel/trampoline.S index 23a03eb9..c79b99a 100644 --- a/arch/x86_64/kernel/trampoline.S +++ b/arch/x86_64/kernel/trampoline.S @@ -64,7 +64,7 @@ idt_48: .word 0, 0 # idt base = 0L gdt_48: - .short __KERNEL32_CS + 7 # gdt limit + .short GDT_ENTRIES*8 - 1 # gdt limit .long cpu_gdt_table-__START_KERNEL_map .globl trampoline_end diff --git a/arch/x86_64/kernel/traps.c b/arch/x86_64/kernel/traps.c index b124977..01f2a8d 100644 --- a/arch/x86_64/kernel/traps.c +++ b/arch/x86_64/kernel/traps.c @@ -45,6 +45,7 @@ #include <asm/pda.h> #include <asm/proto.h> #include <asm/nmi.h> +#include <asm/stacktrace.h> asmlinkage void divide_error(void); asmlinkage void debug(void); @@ -142,7 +143,7 @@ void printk_address(unsigned long address) #endif static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack, - unsigned *usedp, const char **idp) + unsigned *usedp, char **idp) { static char ids[][8] = { [DEBUG_STACK - 1] = "#DB", @@ -161,26 +162,7 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack, * 'stack' is in one of them: */ for (k = 0; k < N_EXCEPTION_STACKS; k++) { - unsigned long end; - - /* - * set 'end' to the end of the exception stack. - */ - switch (k + 1) { - /* - * TODO: this block is not needed i think, because - * setup64.c:cpu_init() sets up t->ist[DEBUG_STACK] - * properly too. - */ -#if DEBUG_STKSZ > EXCEPTION_STKSZ - case DEBUG_STACK: - end = cpu_pda(cpu)->debugstack + DEBUG_STKSZ; - break; -#endif - default: - end = per_cpu(orig_ist, cpu).ist[k]; - break; - } + unsigned long end = per_cpu(orig_ist, cpu).ist[k]; /* * Is 'stack' above this exception frame's end? * If yes then skip to the next frame. @@ -234,13 +216,19 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack, return NULL; } -static int show_trace_unwind(struct unwind_frame_info *info, void *context) +struct ops_and_data { + struct stacktrace_ops *ops; + void *data; +}; + +static int dump_trace_unwind(struct unwind_frame_info *info, void *context) { + struct ops_and_data *oad = (struct ops_and_data *)context; int n = 0; while (unwind(info) == 0 && UNW_PC(info)) { n++; - printk_address(UNW_PC(info)); + oad->ops->address(oad->data, UNW_PC(info)); if (arch_unw_user_mode(info)) break; } @@ -254,45 +242,53 @@ static int show_trace_unwind(struct unwind_frame_info *info, void *context) * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack */ -void show_trace(struct task_struct *tsk, struct pt_regs *regs, unsigned long * stack) +void dump_trace(struct task_struct *tsk, struct pt_regs *regs, unsigned long * stack, + struct stacktrace_ops *ops, void *data) { - const unsigned cpu = safe_smp_processor_id(); + const unsigned cpu = smp_processor_id(); unsigned long *irqstack_end = (unsigned long *)cpu_pda(cpu)->irqstackptr; unsigned used = 0; - printk("\nCall Trace:\n"); - if (!tsk) tsk = current; if (call_trace >= 0) { int unw_ret = 0; struct unwind_frame_info info; + struct ops_and_data oad = { .ops = ops, .data = data }; if (regs) { if (unwind_init_frame_info(&info, tsk, regs) == 0) - unw_ret = show_trace_unwind(&info, NULL); + unw_ret = dump_trace_unwind(&info, &oad); } else if (tsk == current) - unw_ret = unwind_init_running(&info, show_trace_unwind, NULL); + unw_ret = unwind_init_running(&info, dump_trace_unwind, &oad); else { if (unwind_init_blocked(&info, tsk) == 0) - unw_ret = show_trace_unwind(&info, NULL); + unw_ret = dump_trace_unwind(&info, &oad); } if (unw_ret > 0) { if (call_trace == 1 && !arch_unw_user_mode(&info)) { - print_symbol("DWARF2 unwinder stuck at %s\n", + ops->warning_symbol(data, "DWARF2 unwinder stuck at %s\n", UNW_PC(&info)); if ((long)UNW_SP(&info) < 0) { - printk("Leftover inexact backtrace:\n"); + ops->warning(data, "Leftover inexact backtrace:\n"); stack = (unsigned long *)UNW_SP(&info); + if (!stack) + return; } else - printk("Full inexact backtrace again:\n"); + ops->warning(data, "Full inexact backtrace again:\n"); } else if (call_trace >= 1) return; else - printk("Full inexact backtrace again:\n"); + ops->warning(data, "Full inexact backtrace again:\n"); } else - printk("Inexact backtrace:\n"); + ops->warning(data, "Inexact backtrace:\n"); + } + if (!stack) { + unsigned long dummy; + stack = &dummy; + if (tsk && tsk != current) + stack = (unsigned long *)tsk->thread.rsp; } /* @@ -303,7 +299,9 @@ void show_trace(struct task_struct *tsk, struct pt_regs *regs, unsigned long * s #define HANDLE_STACK(cond) \ do while (cond) { \ unsigned long addr = *stack++; \ - if (kernel_text_address(addr)) { \ + if (oops_in_progress ? \ + __kernel_text_address(addr) : \ + kernel_text_address(addr)) { \ /* \ * If the address is either in the text segment of the \ * kernel, or in the region which contains vmalloc'ed \ @@ -312,7 +310,7 @@ void show_trace(struct task_struct *tsk, struct pt_regs *regs, unsigned long * s * down the cause of the crash will be able to figure \ * out the call path that was taken. \ */ \ - printk_address(addr); \ + ops->address(data, addr); \ } \ } while (0) @@ -321,16 +319,17 @@ void show_trace(struct task_struct *tsk, struct pt_regs *regs, unsigned long * s * current stack address. If the stacks consist of nested * exceptions */ - for ( ; ; ) { - const char *id; + for (;;) { + char *id; unsigned long *estack_end; estack_end = in_exception_stack(cpu, (unsigned long)stack, &used, &id); if (estack_end) { - printk(" <%s>", id); + if (ops->stack(data, id) < 0) + break; HANDLE_STACK (stack < estack_end); - printk(" <EOE>"); + ops->stack(data, "<EOE>"); /* * We link to the next stack via the * second-to-last pointer (index -2 to end) in the @@ -345,7 +344,8 @@ void show_trace(struct task_struct *tsk, struct pt_regs *regs, unsigned long * s (IRQSTACKSIZE - 64) / sizeof(*irqstack); if (stack >= irqstack && stack < irqstack_end) { - printk(" <IRQ>"); + if (ops->stack(data, "IRQ") < 0) + break; HANDLE_STACK (stack < irqstack_end); /* * We link to the next stack (which would be @@ -354,7 +354,7 @@ void show_trace(struct task_struct *tsk, struct pt_regs *regs, unsigned long * s */ stack = (unsigned long *) (irqstack_end[-1]); irqstack_end = NULL; - printk(" <EOI>"); + ops->stack(data, "EOI"); continue; } } @@ -362,19 +362,57 @@ void show_trace(struct task_struct *tsk, struct pt_regs *regs, unsigned long * s } /* - * This prints the process stack: + * This handles the process stack: */ HANDLE_STACK (((long) stack & (THREAD_SIZE-1)) != 0); #undef HANDLE_STACK +} +EXPORT_SYMBOL(dump_trace); + +static void +print_trace_warning_symbol(void *data, char *msg, unsigned long symbol) +{ + print_symbol(msg, symbol); + printk("\n"); +} + +static void print_trace_warning(void *data, char *msg) +{ + printk("%s\n", msg); +} + +static int print_trace_stack(void *data, char *name) +{ + printk(" <%s> ", name); + return 0; +} + +static void print_trace_address(void *data, unsigned long addr) +{ + printk_address(addr); +} + +static struct stacktrace_ops print_trace_ops = { + .warning = print_trace_warning, + .warning_symbol = print_trace_warning_symbol, + .stack = print_trace_stack, + .address = print_trace_address, +}; +void +show_trace(struct task_struct *tsk, struct pt_regs *regs, unsigned long *stack) +{ + printk("\nCall Trace:\n"); + dump_trace(tsk, regs, stack, &print_trace_ops, NULL); printk("\n"); } -static void _show_stack(struct task_struct *tsk, struct pt_regs *regs, unsigned long * rsp) +static void +_show_stack(struct task_struct *tsk, struct pt_regs *regs, unsigned long *rsp) { unsigned long *stack; int i; - const int cpu = safe_smp_processor_id(); + const int cpu = smp_processor_id(); unsigned long *irqstack_end = (unsigned long *) (cpu_pda(cpu)->irqstackptr); unsigned long *irqstack = (unsigned long *) (cpu_pda(cpu)->irqstackptr - IRQSTACKSIZE); @@ -428,7 +466,7 @@ void show_registers(struct pt_regs *regs) int i; int in_kernel = !user_mode(regs); unsigned long rsp; - const int cpu = safe_smp_processor_id(); + const int cpu = smp_processor_id(); struct task_struct *cur = cpu_pda(cpu)->pcurrent; rsp = regs->rsp; @@ -503,9 +541,11 @@ static unsigned int die_nest_count; unsigned __kprobes long oops_begin(void) { - int cpu = safe_smp_processor_id(); + int cpu = smp_processor_id(); unsigned long flags; + oops_enter(); + /* racy, but better than risking deadlock. */ local_irq_save(flags); if (!spin_trylock(&die_lock)) { @@ -534,6 +574,7 @@ void __kprobes oops_end(unsigned long flags) spin_unlock_irqrestore(&die_lock, flags); if (panic_on_oops) panic("Fatal exception"); + oops_exit(); } void __kprobes __die(const char * str, struct pt_regs * regs, long err) @@ -570,7 +611,7 @@ void die(const char * str, struct pt_regs * regs, long err) do_exit(SIGSEGV); } -void __kprobes die_nmi(char *str, struct pt_regs *regs) +void __kprobes die_nmi(char *str, struct pt_regs *regs, int do_panic) { unsigned long flags = oops_begin(); @@ -578,13 +619,12 @@ void __kprobes die_nmi(char *str, struct pt_regs *regs) * We are in trouble anyway, lets at least try * to get a message out. */ - printk(str, safe_smp_processor_id()); + printk(str, smp_processor_id()); show_registers(regs); if (kexec_should_crash(current)) crash_kexec(regs); - if (panic_on_timeout || panic_on_oops) - panic("nmi watchdog"); - printk("console shuts up ...\n"); + if (do_panic || panic_on_oops) + panic("Non maskable interrupt"); oops_end(flags); nmi_exit(); local_irq_enable(); @@ -730,8 +770,15 @@ asmlinkage void __kprobes do_general_protection(struct pt_regs * regs, static __kprobes void mem_parity_error(unsigned char reason, struct pt_regs * regs) { - printk("Uhhuh. NMI received. Dazed and confused, but trying to continue\n"); - printk("You probably have a hardware problem with your RAM chips\n"); + printk(KERN_EMERG "Uhhuh. NMI received for unknown reason %02x.\n", + reason); + printk(KERN_EMERG "You probably have a hardware problem with your " + "RAM chips\n"); + + if (panic_on_unrecovered_nmi) + panic("NMI: Not continuing"); + + printk(KERN_EMERG "Dazed and confused, but trying to continue\n"); /* Clear and disable the memory parity error line. */ reason = (reason & 0xf) | 4; @@ -754,9 +801,15 @@ io_check_error(unsigned char reason, struct pt_regs * regs) static __kprobes void unknown_nmi_error(unsigned char reason, struct pt_regs * regs) -{ printk("Uhhuh. NMI received for unknown reason %02x.\n", reason); - printk("Dazed and confused, but trying to continue\n"); - printk("Do you have a strange power saving mode enabled?\n"); +{ + 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"); + + if (panic_on_unrecovered_nmi) + panic("NMI: Not continuing"); + + printk(KERN_EMERG "Dazed and confused, but trying to continue\n"); } /* Runs on IST stack. This code must keep interrupts off all the time. @@ -776,17 +829,15 @@ asmlinkage __kprobes void default_do_nmi(struct pt_regs *regs) if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 2, SIGINT) == NOTIFY_STOP) return; -#ifdef CONFIG_X86_LOCAL_APIC /* * Ok, so this is none of the documented NMI sources, * so it must be the NMI watchdog. */ - if (nmi_watchdog > 0) { - nmi_watchdog_tick(regs,reason); + if (nmi_watchdog_tick(regs,reason)) return; - } -#endif - unknown_nmi_error(reason, regs); + if (!do_nmi_callback(regs,cpu)) + unknown_nmi_error(reason, regs); + return; } if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP) @@ -1071,6 +1122,7 @@ asmlinkage void math_state_restore(void) init_fpu(me); restore_fpu_checking(&me->thread.i387.fxsave); task_thread_info(me)->status |= TS_USEDFPU; + me->fpu_counter++; } void __init trap_init(void) @@ -1109,24 +1161,30 @@ void __init trap_init(void) } -/* Actual parsing is done early in setup.c. */ -static int __init oops_dummy(char *s) +static int __init oops_setup(char *s) { - panic_on_oops = 1; - return 1; + if (!s) + return -EINVAL; + if (!strcmp(s, "panic")) + panic_on_oops = 1; + return 0; } -__setup("oops=", oops_dummy); +early_param("oops", oops_setup); static int __init kstack_setup(char *s) { + if (!s) + return -EINVAL; kstack_depth_to_print = simple_strtoul(s,NULL,0); - return 1; + return 0; } -__setup("kstack=", kstack_setup); +early_param("kstack", kstack_setup); #ifdef CONFIG_STACK_UNWIND static int __init call_trace_setup(char *s) { + if (!s) + return -EINVAL; if (strcmp(s, "old") == 0) call_trace = -1; else if (strcmp(s, "both") == 0) @@ -1135,7 +1193,7 @@ static int __init call_trace_setup(char *s) call_trace = 1; else if (strcmp(s, "new") == 0) call_trace = 2; - return 1; + return 0; } -__setup("call_trace=", call_trace_setup); +early_param("call_trace", call_trace_setup); #endif diff --git a/arch/x86_64/kernel/vmlinux.lds.S b/arch/x86_64/kernel/vmlinux.lds.S index 7c4de31..d0564f1 100644 --- a/arch/x86_64/kernel/vmlinux.lds.S +++ b/arch/x86_64/kernel/vmlinux.lds.S @@ -13,6 +13,12 @@ OUTPUT_FORMAT("elf64-x86-64", "elf64-x86-64", "elf64-x86-64") OUTPUT_ARCH(i386:x86-64) ENTRY(phys_startup_64) jiffies_64 = jiffies; +PHDRS { + text PT_LOAD FLAGS(5); /* R_E */ + data PT_LOAD FLAGS(7); /* RWE */ + user PT_LOAD FLAGS(7); /* RWE */ + note PT_NOTE FLAGS(4); /* R__ */ +} SECTIONS { . = __START_KERNEL; @@ -31,7 +37,7 @@ SECTIONS KPROBES_TEXT *(.fixup) *(.gnu.warning) - } = 0x9090 + } :text = 0x9090 /* out-of-line lock text */ .text.lock : AT(ADDR(.text.lock) - LOAD_OFFSET) { *(.text.lock) } @@ -57,7 +63,7 @@ SECTIONS .data : AT(ADDR(.data) - LOAD_OFFSET) { *(.data) CONSTRUCTORS - } + } :data _edata = .; /* End of data section */ @@ -89,7 +95,7 @@ SECTIONS #define VVIRT(x) (ADDR(x) - VVIRT_OFFSET) . = VSYSCALL_ADDR; - .vsyscall_0 : AT(VSYSCALL_PHYS_ADDR) { *(.vsyscall_0) } + .vsyscall_0 : AT(VSYSCALL_PHYS_ADDR) { *(.vsyscall_0) } :user __vsyscall_0 = VSYSCALL_VIRT_ADDR; . = ALIGN(CONFIG_X86_L1_CACHE_BYTES); @@ -99,6 +105,9 @@ SECTIONS .vxtime : AT(VLOAD(.vxtime)) { *(.vxtime) } vxtime = VVIRT(.vxtime); + .vgetcpu_mode : AT(VLOAD(.vgetcpu_mode)) { *(.vgetcpu_mode) } + vgetcpu_mode = VVIRT(.vgetcpu_mode); + .wall_jiffies : AT(VLOAD(.wall_jiffies)) { *(.wall_jiffies) } wall_jiffies = VVIRT(.wall_jiffies); @@ -132,7 +141,7 @@ SECTIONS . = ALIGN(8192); /* init_task */ .data.init_task : AT(ADDR(.data.init_task) - LOAD_OFFSET) { *(.data.init_task) - } + } :data . = ALIGN(4096); .data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) { @@ -207,14 +216,12 @@ SECTIONS __initramfs_start = .; .init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) { *(.init.ramfs) } __initramfs_end = .; - /* temporary here to work around NR_CPUS. If you see this comment in 2.6.17+ - complain */ - . = ALIGN(4096); - __init_end = .; - . = ALIGN(CONFIG_X86_L1_CACHE_BYTES); + . = ALIGN(CONFIG_X86_L1_CACHE_BYTES); __per_cpu_start = .; .data.percpu : AT(ADDR(.data.percpu) - LOAD_OFFSET) { *(.data.percpu) } __per_cpu_end = .; + . = ALIGN(4096); + __init_end = .; . = ALIGN(4096); __nosave_begin = .; diff --git a/arch/x86_64/kernel/vsmp.c b/arch/x86_64/kernel/vsmp.c index 92f70c7..044e852 100644 --- a/arch/x86_64/kernel/vsmp.c +++ b/arch/x86_64/kernel/vsmp.c @@ -20,6 +20,9 @@ static int __init vsmp_init(void) void *address; unsigned int cap, ctl; + if (!early_pci_allowed()) + return 0; + /* 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)) diff --git a/arch/x86_64/kernel/vsyscall.c b/arch/x86_64/kernel/vsyscall.c index f603037..ac48c38 100644 --- a/arch/x86_64/kernel/vsyscall.c +++ b/arch/x86_64/kernel/vsyscall.c @@ -26,6 +26,7 @@ #include <linux/seqlock.h> #include <linux/jiffies.h> #include <linux/sysctl.h> +#include <linux/getcpu.h> #include <asm/vsyscall.h> #include <asm/pgtable.h> @@ -33,11 +34,15 @@ #include <asm/fixmap.h> #include <asm/errno.h> #include <asm/io.h> +#include <asm/segment.h> +#include <asm/desc.h> +#include <asm/topology.h> #define __vsyscall(nr) __attribute__ ((unused,__section__(".vsyscall_" #nr))) int __sysctl_vsyscall __section_sysctl_vsyscall = 1; seqlock_t __xtime_lock __section_xtime_lock = SEQLOCK_UNLOCKED; +int __vgetcpu_mode __section_vgetcpu_mode; #include <asm/unistd.h> @@ -72,7 +77,8 @@ static __always_inline void do_vgettimeofday(struct timeval * tv) __vxtime.tsc_quot) >> 32; /* See comment in x86_64 do_gettimeofday. */ } else { - usec += ((readl((void *)fix_to_virt(VSYSCALL_HPET) + 0xf0) - + usec += ((readl((void __iomem *) + fix_to_virt(VSYSCALL_HPET) + 0xf0) - __vxtime.last) * __vxtime.quot) >> 32; } } while (read_seqretry(&__xtime_lock, sequence)); @@ -127,9 +133,46 @@ time_t __vsyscall(1) vtime(time_t *t) return __xtime.tv_sec; } -long __vsyscall(2) venosys_0(void) +/* Fast way to get current CPU and node. + This helps to do per node and per CPU caches in user space. + The result is not guaranteed without CPU affinity, but usually + works out because the scheduler tries to keep a thread on the same + CPU. + + tcache must point to a two element sized long array. + All arguments can be NULL. */ +long __vsyscall(2) +vgetcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache) { - return -ENOSYS; + unsigned int dummy, p; + unsigned long j = 0; + + /* Fast cache - only recompute value once per jiffies and avoid + relatively costly rdtscp/cpuid otherwise. + This works because the scheduler usually keeps the process + on the same CPU and this syscall doesn't guarantee its + results anyways. + We do this here because otherwise user space would do it on + its own in a likely inferior way (no access to jiffies). + If you don't like it pass NULL. */ + if (tcache && tcache->t0 == (j = __jiffies)) { + p = tcache->t1; + } else if (__vgetcpu_mode == VGETCPU_RDTSCP) { + /* Load per CPU data from RDTSCP */ + rdtscp(dummy, dummy, p); + } else { + /* Load per CPU data from GDT */ + asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG)); + } + if (tcache) { + tcache->t0 = j; + tcache->t1 = p; + } + if (cpu) + *cpu = p & 0xfff; + if (node) + *node = p >> 12; + return 0; } long __vsyscall(3) venosys_1(void) @@ -149,7 +192,8 @@ static int vsyscall_sysctl_change(ctl_table *ctl, int write, struct file * filp, void __user *buffer, size_t *lenp, loff_t *ppos) { extern u16 vsysc1, vsysc2; - u16 *map1, *map2; + u16 __iomem *map1; + u16 __iomem *map2; int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); if (!write) return ret; @@ -164,11 +208,11 @@ static int vsyscall_sysctl_change(ctl_table *ctl, int write, struct file * filp, goto out; } if (!sysctl_vsyscall) { - *map1 = SYSCALL; - *map2 = SYSCALL; + writew(SYSCALL, map1); + writew(SYSCALL, map2); } else { - *map1 = NOP2; - *map2 = NOP2; + writew(NOP2, map1); + writew(NOP2, map2); } iounmap(map2); out: @@ -200,6 +244,43 @@ static ctl_table kernel_root_table2[] = { #endif +static void __cpuinit write_rdtscp_cb(void *info) +{ + write_rdtscp_aux((unsigned long)info); +} + +void __cpuinit vsyscall_set_cpu(int cpu) +{ + unsigned long *d; + unsigned long node = 0; +#ifdef CONFIG_NUMA + node = cpu_to_node[cpu]; +#endif + if (cpu_has(&cpu_data[cpu], X86_FEATURE_RDTSCP)) { + void *info = (void *)((node << 12) | cpu); + /* Can happen on preemptive kernel */ + if (get_cpu() == cpu) + write_rdtscp_cb(info); +#ifdef CONFIG_SMP + else { + /* the notifier is unfortunately not executed on the + target CPU */ + smp_call_function_single(cpu,write_rdtscp_cb,info,0,1); + } +#endif + put_cpu(); + } + + /* Store cpu number in limit so that it can be loaded quickly + in user space in vgetcpu. + 12 bits for the CPU and 8 bits for the node. */ + d = (unsigned long *)(cpu_gdt(cpu) + GDT_ENTRY_PER_CPU); + *d = 0x0f40000000000ULL; + *d |= cpu; + *d |= (node & 0xf) << 12; + *d |= (node >> 4) << 48; +} + static void __init map_vsyscall(void) { extern char __vsyscall_0; @@ -214,6 +295,7 @@ static int __init vsyscall_init(void) VSYSCALL_ADDR(__NR_vgettimeofday))); BUG_ON((unsigned long) &vtime != VSYSCALL_ADDR(__NR_vtime)); BUG_ON((VSYSCALL_ADDR(0) != __fix_to_virt(VSYSCALL_FIRST_PAGE))); + BUG_ON((unsigned long) &vgetcpu != VSYSCALL_ADDR(__NR_vgetcpu)); map_vsyscall(); #ifdef CONFIG_SYSCTL register_sysctl_table(kernel_root_table2, 0); diff --git a/arch/x86_64/kernel/x8664_ksyms.c b/arch/x86_64/kernel/x8664_ksyms.c index 370952c..c3454af 100644 --- a/arch/x86_64/kernel/x8664_ksyms.c +++ b/arch/x86_64/kernel/x8664_ksyms.c @@ -29,6 +29,7 @@ EXPORT_SYMBOL(__put_user_8); EXPORT_SYMBOL(copy_user_generic); EXPORT_SYMBOL(copy_from_user); EXPORT_SYMBOL(copy_to_user); +EXPORT_SYMBOL(__copy_from_user_inatomic); EXPORT_SYMBOL(copy_page); EXPORT_SYMBOL(clear_page); diff --git a/arch/x86_64/lib/Makefile b/arch/x86_64/lib/Makefile index ccef6ae..b78d417 100644 --- a/arch/x86_64/lib/Makefile +++ b/arch/x86_64/lib/Makefile @@ -9,4 +9,4 @@ obj-y := io.o iomap_copy.o lib-y := csum-partial.o csum-copy.o csum-wrappers.o delay.o \ usercopy.o getuser.o putuser.o \ thunk.o clear_page.o copy_page.o bitstr.o bitops.o -lib-y += memcpy.o memmove.o memset.o copy_user.o +lib-y += memcpy.o memmove.o memset.o copy_user.o rwlock.o diff --git a/arch/x86_64/lib/clear_page.S b/arch/x86_64/lib/clear_page.S index 1f81b79..9a10a78 100644 --- a/arch/x86_64/lib/clear_page.S +++ b/arch/x86_64/lib/clear_page.S @@ -1,10 +1,22 @@ +#include <linux/linkage.h> +#include <asm/dwarf2.h> + /* * Zero a page. * rdi page */ - .globl clear_page - .p2align 4 -clear_page: + ALIGN +clear_page_c: + CFI_STARTPROC + movl $4096/8,%ecx + xorl %eax,%eax + rep stosq + ret + CFI_ENDPROC +ENDPROC(clear_page) + +ENTRY(clear_page) + CFI_STARTPROC xorl %eax,%eax movl $4096/64,%ecx .p2align 4 @@ -23,28 +35,25 @@ clear_page: jnz .Lloop nop ret -clear_page_end: + CFI_ENDPROC +.Lclear_page_end: +ENDPROC(clear_page) /* Some CPUs run faster using the string instructions. It is also a lot simpler. Use this when possible */ #include <asm/cpufeature.h> + .section .altinstr_replacement,"ax" +1: .byte 0xeb /* jmp <disp8> */ + .byte (clear_page_c - clear_page) - (2f - 1b) /* offset */ +2: + .previous .section .altinstructions,"a" .align 8 - .quad clear_page - .quad clear_page_c - .byte X86_FEATURE_REP_GOOD - .byte clear_page_end-clear_page - .byte clear_page_c_end-clear_page_c - .previous - - .section .altinstr_replacement,"ax" -clear_page_c: - movl $4096/8,%ecx - xorl %eax,%eax - rep - stosq - ret -clear_page_c_end: + .quad clear_page + .quad 1b + .byte X86_FEATURE_REP_GOOD + .byte .Lclear_page_end - clear_page + .byte 2b - 1b .previous diff --git a/arch/x86_64/lib/copy_page.S b/arch/x86_64/lib/copy_page.S index 8fa19d9..0ebb03b 100644 --- a/arch/x86_64/lib/copy_page.S +++ b/arch/x86_64/lib/copy_page.S @@ -1,17 +1,33 @@ /* Written 2003 by Andi Kleen, based on a kernel by Evandro Menezes */ +#include <linux/config.h> +#include <linux/linkage.h> +#include <asm/dwarf2.h> + + ALIGN +copy_page_c: + CFI_STARTPROC + movl $4096/8,%ecx + rep movsq + ret + CFI_ENDPROC +ENDPROC(copy_page_c) + /* Don't use streaming store because it's better when the target ends up in cache. */ /* Could vary the prefetch distance based on SMP/UP */ - .globl copy_page - .p2align 4 -copy_page: +ENTRY(copy_page) + CFI_STARTPROC subq $3*8,%rsp + CFI_ADJUST_CFA_OFFSET 3*8 movq %rbx,(%rsp) + CFI_REL_OFFSET rbx, 0 movq %r12,1*8(%rsp) + CFI_REL_OFFSET r12, 1*8 movq %r13,2*8(%rsp) + CFI_REL_OFFSET r13, 2*8 movl $(4096/64)-5,%ecx .p2align 4 @@ -72,30 +88,33 @@ copy_page: jnz .Loop2 movq (%rsp),%rbx + CFI_RESTORE rbx movq 1*8(%rsp),%r12 + CFI_RESTORE r12 movq 2*8(%rsp),%r13 + CFI_RESTORE r13 addq $3*8,%rsp + CFI_ADJUST_CFA_OFFSET -3*8 ret +.Lcopy_page_end: + CFI_ENDPROC +ENDPROC(copy_page) /* Some CPUs run faster using the string copy instructions. It is also a lot simpler. Use this when possible */ #include <asm/cpufeature.h> + .section .altinstr_replacement,"ax" +1: .byte 0xeb /* jmp <disp8> */ + .byte (copy_page_c - copy_page) - (2f - 1b) /* offset */ +2: + .previous .section .altinstructions,"a" .align 8 - .quad copy_page - .quad copy_page_c - .byte X86_FEATURE_REP_GOOD - .byte copy_page_c_end-copy_page_c - .byte copy_page_c_end-copy_page_c - .previous - - .section .altinstr_replacement,"ax" -copy_page_c: - movl $4096/8,%ecx - rep - movsq - ret -copy_page_c_end: + .quad copy_page + .quad 1b + .byte X86_FEATURE_REP_GOOD + .byte .Lcopy_page_end - copy_page + .byte 2b - 1b .previous diff --git a/arch/x86_64/lib/copy_user.S b/arch/x86_64/lib/copy_user.S index f64569b..70bebd3 100644 --- a/arch/x86_64/lib/copy_user.S +++ b/arch/x86_64/lib/copy_user.S @@ -4,56 +4,78 @@ * Functions to copy from and to user space. */ +#include <linux/linkage.h> +#include <asm/dwarf2.h> + #define FIX_ALIGNMENT 1 - #include <asm/current.h> - #include <asm/asm-offsets.h> - #include <asm/thread_info.h> - #include <asm/cpufeature.h> +#include <asm/current.h> +#include <asm/asm-offsets.h> +#include <asm/thread_info.h> +#include <asm/cpufeature.h> -/* Standard copy_to_user with segment limit checking */ - .globl copy_to_user - .p2align 4 -copy_to_user: - GET_THREAD_INFO(%rax) - movq %rdi,%rcx - addq %rdx,%rcx - jc bad_to_user - cmpq threadinfo_addr_limit(%rax),%rcx - jae bad_to_user -2: + .macro ALTERNATIVE_JUMP feature,orig,alt +0: .byte 0xe9 /* 32bit jump */ - .long .Lcug-1f + .long \orig-1f /* by default jump to orig */ 1: - .section .altinstr_replacement,"ax" -3: .byte 0xe9 /* replacement jmp with 8 bit immediate */ - .long copy_user_generic_c-1b /* offset */ +2: .byte 0xe9 /* near jump with 32bit immediate */ + .long \alt-1b /* offset */ /* or alternatively to alt */ .previous .section .altinstructions,"a" .align 8 + .quad 0b .quad 2b - .quad 3b - .byte X86_FEATURE_REP_GOOD + .byte \feature /* when feature is set */ .byte 5 .byte 5 .previous + .endm + +/* Standard copy_to_user with segment limit checking */ +ENTRY(copy_to_user) + CFI_STARTPROC + GET_THREAD_INFO(%rax) + movq %rdi,%rcx + addq %rdx,%rcx + jc bad_to_user + cmpq threadinfo_addr_limit(%rax),%rcx + jae bad_to_user + xorl %eax,%eax /* clear zero flag */ + ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string + CFI_ENDPROC + +ENTRY(copy_user_generic) + CFI_STARTPROC + movl $1,%ecx /* set zero flag */ + ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string + CFI_ENDPROC + +ENTRY(__copy_from_user_inatomic) + CFI_STARTPROC + xorl %ecx,%ecx /* clear zero flag */ + ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string + CFI_ENDPROC /* Standard copy_from_user with segment limit checking */ - .globl copy_from_user - .p2align 4 -copy_from_user: +ENTRY(copy_from_user) + CFI_STARTPROC GET_THREAD_INFO(%rax) movq %rsi,%rcx addq %rdx,%rcx jc bad_from_user cmpq threadinfo_addr_limit(%rax),%rcx jae bad_from_user - /* FALL THROUGH to copy_user_generic */ + movl $1,%ecx /* set zero flag */ + ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string + CFI_ENDPROC +ENDPROC(copy_from_user) .section .fixup,"ax" /* must zero dest */ bad_from_user: + CFI_STARTPROC movl %edx,%ecx xorl %eax,%eax rep @@ -61,40 +83,32 @@ bad_from_user: bad_to_user: movl %edx,%eax ret + CFI_ENDPROC +END(bad_from_user) .previous /* - * copy_user_generic - memory copy with exception handling. + * copy_user_generic_unrolled - memory copy with exception handling. + * This version is for CPUs like P4 that don't have efficient micro code for rep movsq * * Input: * rdi destination * rsi source * rdx count + * ecx zero flag -- if true zero destination on error * * Output: * eax uncopied bytes or 0 if successful. */ - .globl copy_user_generic - .p2align 4 -copy_user_generic: - .byte 0x66,0x66,0x90 /* 5 byte nop for replacement jump */ - .byte 0x66,0x90 -1: - .section .altinstr_replacement,"ax" -2: .byte 0xe9 /* near jump with 32bit immediate */ - .long copy_user_generic_c-1b /* offset */ - .previous - .section .altinstructions,"a" - .align 8 - .quad copy_user_generic - .quad 2b - .byte X86_FEATURE_REP_GOOD - .byte 5 - .byte 5 - .previous -.Lcug: +ENTRY(copy_user_generic_unrolled) + CFI_STARTPROC pushq %rbx + CFI_ADJUST_CFA_OFFSET 8 + CFI_REL_OFFSET rbx, 0 + pushq %rcx + CFI_ADJUST_CFA_OFFSET 8 + CFI_REL_OFFSET rcx, 0 xorl %eax,%eax /*zero for the exception handler */ #ifdef FIX_ALIGNMENT @@ -168,9 +182,16 @@ copy_user_generic: decl %ecx jnz .Lloop_1 + CFI_REMEMBER_STATE .Lende: + popq %rcx + CFI_ADJUST_CFA_OFFSET -8 + CFI_RESTORE rcx popq %rbx + CFI_ADJUST_CFA_OFFSET -8 + CFI_RESTORE rbx ret + CFI_RESTORE_STATE #ifdef FIX_ALIGNMENT /* align destination */ @@ -252,6 +273,8 @@ copy_user_generic: addl %ecx,%edx /* edx: bytes to zero, rdi: dest, eax:zero */ .Lzero_rest: + cmpl $0,(%rsp) + jz .Le_zero movq %rdx,%rcx .Le_byte: xorl %eax,%eax @@ -261,6 +284,9 @@ copy_user_generic: .Le_zero: movq %rdx,%rax jmp .Lende + CFI_ENDPROC +ENDPROC(copy_user_generic) + /* Some CPUs run faster using the string copy instructions. This is also a lot simpler. Use them when possible. @@ -270,6 +296,7 @@ copy_user_generic: /* rdi destination * rsi source * rdx count + * ecx zero flag * * Output: * eax uncopied bytes or 0 if successfull. @@ -280,22 +307,48 @@ copy_user_generic: * And more would be dangerous because both Intel and AMD have * errata with rep movsq > 4GB. If someone feels the need to fix * this please consider this. - */ -copy_user_generic_c: + */ +ENTRY(copy_user_generic_string) + CFI_STARTPROC + movl %ecx,%r8d /* save zero flag */ movl %edx,%ecx shrl $3,%ecx andl $7,%edx + jz 10f 1: rep movsq movl %edx,%ecx 2: rep movsb -4: movl %ecx,%eax +9: movl %ecx,%eax ret -3: lea (%rdx,%rcx,8),%rax + + /* multiple of 8 byte */ +10: rep + movsq + xor %eax,%eax ret + /* exception handling */ +3: lea (%rdx,%rcx,8),%rax /* exception on quad loop */ + jmp 6f +5: movl %ecx,%eax /* exception on byte loop */ + /* eax: left over bytes */ +6: testl %r8d,%r8d /* zero flag set? */ + jz 7f + movl %eax,%ecx /* initialize x86 loop counter */ + push %rax + xorl %eax,%eax +8: rep + stosb /* zero the rest */ +11: pop %rax +7: ret + CFI_ENDPROC +END(copy_user_generic_c) + .section __ex_table,"a" .quad 1b,3b - .quad 2b,4b + .quad 2b,5b + .quad 8b,11b + .quad 10b,3b .previous diff --git a/arch/x86_64/lib/csum-copy.S b/arch/x86_64/lib/csum-copy.S index 72fd55e..f0dba36 100644 --- a/arch/x86_64/lib/csum-copy.S +++ b/arch/x86_64/lib/csum-copy.S @@ -5,8 +5,9 @@ * License. See the file COPYING in the main directory of this archive * for more details. No warranty for anything given at all. */ - #include <linux/linkage.h> - #include <asm/errno.h> +#include <linux/linkage.h> +#include <asm/dwarf2.h> +#include <asm/errno.h> /* * Checksum copy with exception handling. @@ -53,19 +54,24 @@ .endm - .globl csum_partial_copy_generic - .p2align 4 -csum_partial_copy_generic: +ENTRY(csum_partial_copy_generic) + CFI_STARTPROC cmpl $3*64,%edx jle .Lignore .Lignore: subq $7*8,%rsp + CFI_ADJUST_CFA_OFFSET 7*8 movq %rbx,2*8(%rsp) + CFI_REL_OFFSET rbx, 2*8 movq %r12,3*8(%rsp) + CFI_REL_OFFSET r12, 3*8 movq %r14,4*8(%rsp) + CFI_REL_OFFSET r14, 4*8 movq %r13,5*8(%rsp) + CFI_REL_OFFSET r13, 5*8 movq %rbp,6*8(%rsp) + CFI_REL_OFFSET rbp, 6*8 movq %r8,(%rsp) movq %r9,1*8(%rsp) @@ -208,14 +214,22 @@ csum_partial_copy_generic: addl %ebx,%eax adcl %r9d,%eax /* carry */ + CFI_REMEMBER_STATE .Lende: movq 2*8(%rsp),%rbx + CFI_RESTORE rbx movq 3*8(%rsp),%r12 + CFI_RESTORE r12 movq 4*8(%rsp),%r14 + CFI_RESTORE r14 movq 5*8(%rsp),%r13 + CFI_RESTORE r13 movq 6*8(%rsp),%rbp + CFI_RESTORE rbp addq $7*8,%rsp + CFI_ADJUST_CFA_OFFSET -7*8 ret + CFI_RESTORE_STATE /* Exception handlers. Very simple, zeroing is done in the wrappers */ .Lbad_source: @@ -231,3 +245,5 @@ csum_partial_copy_generic: jz .Lende movl $-EFAULT,(%rax) jmp .Lende + CFI_ENDPROC +ENDPROC(csum_partial_copy_generic) diff --git a/arch/x86_64/lib/getuser.S b/arch/x86_64/lib/getuser.S index 3844d5e..5448876 100644 --- a/arch/x86_64/lib/getuser.S +++ b/arch/x86_64/lib/getuser.S @@ -27,25 +27,26 @@ */ #include <linux/linkage.h> +#include <asm/dwarf2.h> #include <asm/page.h> #include <asm/errno.h> #include <asm/asm-offsets.h> #include <asm/thread_info.h> .text - .p2align 4 -.globl __get_user_1 -__get_user_1: +ENTRY(__get_user_1) + CFI_STARTPROC GET_THREAD_INFO(%r8) cmpq threadinfo_addr_limit(%r8),%rcx jae bad_get_user 1: movzb (%rcx),%edx xorl %eax,%eax ret + CFI_ENDPROC +ENDPROC(__get_user_1) - .p2align 4 -.globl __get_user_2 -__get_user_2: +ENTRY(__get_user_2) + CFI_STARTPROC GET_THREAD_INFO(%r8) addq $1,%rcx jc 20f @@ -57,10 +58,11 @@ __get_user_2: ret 20: decq %rcx jmp bad_get_user + CFI_ENDPROC +ENDPROC(__get_user_2) - .p2align 4 -.globl __get_user_4 -__get_user_4: +ENTRY(__get_user_4) + CFI_STARTPROC GET_THREAD_INFO(%r8) addq $3,%rcx jc 30f @@ -72,10 +74,11 @@ __get_user_4: ret 30: subq $3,%rcx jmp bad_get_user + CFI_ENDPROC +ENDPROC(__get_user_4) - .p2align 4 -.globl __get_user_8 -__get_user_8: +ENTRY(__get_user_8) + CFI_STARTPROC GET_THREAD_INFO(%r8) addq $7,%rcx jc 40f @@ -87,11 +90,16 @@ __get_user_8: ret 40: subq $7,%rcx jmp bad_get_user + CFI_ENDPROC +ENDPROC(__get_user_8) bad_get_user: + CFI_STARTPROC xorl %edx,%edx movq $(-EFAULT),%rax ret + CFI_ENDPROC +END(bad_get_user) .section __ex_table,"a" .quad 1b,bad_get_user diff --git a/arch/x86_64/lib/iomap_copy.S b/arch/x86_64/lib/iomap_copy.S index 8bbade5..05a95e7 100644 --- a/arch/x86_64/lib/iomap_copy.S +++ b/arch/x86_64/lib/iomap_copy.S @@ -15,12 +15,16 @@ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA. */ +#include <linux/linkage.h> +#include <asm/dwarf2.h> + /* * override generic version in lib/iomap_copy.c */ - .globl __iowrite32_copy - .p2align 4 -__iowrite32_copy: +ENTRY(__iowrite32_copy) + CFI_STARTPROC movl %edx,%ecx rep movsd ret + CFI_ENDPROC +ENDPROC(__iowrite32_copy) diff --git a/arch/x86_64/lib/memcpy.S b/arch/x86_64/lib/memcpy.S index 5554948..967b22f 100644 --- a/arch/x86_64/lib/memcpy.S +++ b/arch/x86_64/lib/memcpy.S @@ -1,6 +1,10 @@ /* Copyright 2002 Andi Kleen */ - #include <asm/cpufeature.h> +#include <linux/config.h> +#include <linux/linkage.h> +#include <asm/dwarf2.h> +#include <asm/cpufeature.h> + /* * memcpy - Copy a memory block. * @@ -13,12 +17,26 @@ * rax original destination */ - .globl __memcpy - .globl memcpy - .p2align 4 -__memcpy: -memcpy: + ALIGN +memcpy_c: + CFI_STARTPROC + movq %rdi,%rax + movl %edx,%ecx + shrl $3,%ecx + andl $7,%edx + rep movsq + movl %edx,%ecx + rep movsb + ret + CFI_ENDPROC +ENDPROC(memcpy_c) + +ENTRY(__memcpy) +ENTRY(memcpy) + CFI_STARTPROC pushq %rbx + CFI_ADJUST_CFA_OFFSET 8 + CFI_REL_OFFSET rbx, 0 movq %rdi,%rax movl %edx,%ecx @@ -86,36 +104,27 @@ memcpy: .Lende: popq %rbx + CFI_ADJUST_CFA_OFFSET -8 + CFI_RESTORE rbx ret .Lfinal: + CFI_ENDPROC +ENDPROC(memcpy) +ENDPROC(__memcpy) /* Some CPUs run faster using the string copy instructions. It is also a lot simpler. Use this when possible */ + .section .altinstr_replacement,"ax" +1: .byte 0xeb /* jmp <disp8> */ + .byte (memcpy_c - memcpy) - (2f - 1b) /* offset */ +2: + .previous .section .altinstructions,"a" .align 8 - .quad memcpy - .quad memcpy_c - .byte X86_FEATURE_REP_GOOD - .byte .Lfinal-memcpy - .byte memcpy_c_end-memcpy_c - .previous - - .section .altinstr_replacement,"ax" - /* rdi destination - * rsi source - * rdx count - */ -memcpy_c: - movq %rdi,%rax - movl %edx,%ecx - shrl $3,%ecx - andl $7,%edx - rep - movsq - movl %edx,%ecx - rep - movsb - ret -memcpy_c_end: + .quad memcpy + .quad 1b + .byte X86_FEATURE_REP_GOOD + .byte .Lfinal - memcpy + .byte 2b - 1b .previous diff --git a/arch/x86_64/lib/memset.S b/arch/x86_64/lib/memset.S index ad397f2..09ed1f6 100644 --- a/arch/x86_64/lib/memset.S +++ b/arch/x86_64/lib/memset.S @@ -1,4 +1,9 @@ /* Copyright 2002 Andi Kleen, SuSE Labs */ + +#include <linux/config.h> +#include <linux/linkage.h> +#include <asm/dwarf2.h> + /* * ISO C memset - set a memory block to a byte value. * @@ -8,11 +13,29 @@ * * rax original destination */ - .globl __memset - .globl memset - .p2align 4 -memset: -__memset: + ALIGN +memset_c: + CFI_STARTPROC + movq %rdi,%r9 + movl %edx,%r8d + andl $7,%r8d + movl %edx,%ecx + shrl $3,%ecx + /* expand byte value */ + movzbl %sil,%esi + movabs $0x0101010101010101,%rax + mulq %rsi /* with rax, clobbers rdx */ + rep stosq + movl %r8d,%ecx + rep stosb + movq %r9,%rax + ret + CFI_ENDPROC +ENDPROC(memset_c) + +ENTRY(memset) +ENTRY(__memset) + CFI_STARTPROC movq %rdi,%r10 movq %rdx,%r11 @@ -25,6 +48,7 @@ __memset: movl %edi,%r9d andl $7,%r9d jnz .Lbad_alignment + CFI_REMEMBER_STATE .Lafter_bad_alignment: movl %r11d,%ecx @@ -75,6 +99,7 @@ __memset: movq %r10,%rax ret + CFI_RESTORE_STATE .Lbad_alignment: cmpq $7,%r11 jbe .Lhandle_7 @@ -84,42 +109,26 @@ __memset: addq %r8,%rdi subq %r8,%r11 jmp .Lafter_bad_alignment +.Lfinal: + CFI_ENDPROC +ENDPROC(memset) +ENDPROC(__memset) /* Some CPUs run faster using the string instructions. It is also a lot simpler. Use this when possible */ #include <asm/cpufeature.h> + .section .altinstr_replacement,"ax" +1: .byte 0xeb /* jmp <disp8> */ + .byte (memset_c - memset) - (2f - 1b) /* offset */ +2: + .previous .section .altinstructions,"a" .align 8 - .quad memset - .quad memset_c - .byte X86_FEATURE_REP_GOOD - .byte memset_c_end-memset_c - .byte memset_c_end-memset_c - .previous - - .section .altinstr_replacement,"ax" - /* rdi destination - * rsi value - * rdx count - */ -memset_c: - movq %rdi,%r9 - movl %edx,%r8d - andl $7,%r8d - movl %edx,%ecx - shrl $3,%ecx - /* expand byte value */ - movzbl %sil,%esi - movabs $0x0101010101010101,%rax - mulq %rsi /* with rax, clobbers rdx */ - rep - stosq - movl %r8d,%ecx - rep - stosb - movq %r9,%rax - ret -memset_c_end: + .quad memset + .quad 1b + .byte X86_FEATURE_REP_GOOD + .byte .Lfinal - memset + .byte 2b - 1b .previous diff --git a/arch/x86_64/lib/putuser.S b/arch/x86_64/lib/putuser.S index 7f55939..4989f5a 100644 --- a/arch/x86_64/lib/putuser.S +++ b/arch/x86_64/lib/putuser.S @@ -25,25 +25,26 @@ */ #include <linux/linkage.h> +#include <asm/dwarf2.h> #include <asm/page.h> #include <asm/errno.h> #include <asm/asm-offsets.h> #include <asm/thread_info.h> .text - .p2align 4 -.globl __put_user_1 -__put_user_1: +ENTRY(__put_user_1) + CFI_STARTPROC GET_THREAD_INFO(%r8) cmpq threadinfo_addr_limit(%r8),%rcx jae bad_put_user 1: movb %dl,(%rcx) xorl %eax,%eax ret + CFI_ENDPROC +ENDPROC(__put_user_1) - .p2align 4 -.globl __put_user_2 -__put_user_2: +ENTRY(__put_user_2) + CFI_STARTPROC GET_THREAD_INFO(%r8) addq $1,%rcx jc 20f @@ -55,10 +56,11 @@ __put_user_2: ret 20: decq %rcx jmp bad_put_user + CFI_ENDPROC +ENDPROC(__put_user_2) - .p2align 4 -.globl __put_user_4 -__put_user_4: +ENTRY(__put_user_4) + CFI_STARTPROC GET_THREAD_INFO(%r8) addq $3,%rcx jc 30f @@ -70,10 +72,11 @@ __put_user_4: ret 30: subq $3,%rcx jmp bad_put_user + CFI_ENDPROC +ENDPROC(__put_user_4) - .p2align 4 -.globl __put_user_8 -__put_user_8: +ENTRY(__put_user_8) + CFI_STARTPROC GET_THREAD_INFO(%r8) addq $7,%rcx jc 40f @@ -85,10 +88,15 @@ __put_user_8: ret 40: subq $7,%rcx jmp bad_put_user + CFI_ENDPROC +ENDPROC(__put_user_8) bad_put_user: + CFI_STARTPROC movq $(-EFAULT),%rax ret + CFI_ENDPROC +END(bad_put_user) .section __ex_table,"a" .quad 1b,bad_put_user diff --git a/arch/x86_64/lib/rwlock.S b/arch/x86_64/lib/rwlock.S new file mode 100644 index 0000000..0cde1f8 --- /dev/null +++ b/arch/x86_64/lib/rwlock.S @@ -0,0 +1,38 @@ +/* Slow paths of read/write spinlocks. */ + +#include <linux/linkage.h> +#include <asm/rwlock.h> +#include <asm/alternative-asm.i> +#include <asm/dwarf2.h> + +/* rdi: pointer to rwlock_t */ +ENTRY(__write_lock_failed) + CFI_STARTPROC + LOCK_PREFIX + addl $RW_LOCK_BIAS,(%rdi) +1: rep + nop + cmpl $RW_LOCK_BIAS,(%rdi) + jne 1b + LOCK_PREFIX + subl $RW_LOCK_BIAS,(%rdi) + jnz __write_lock_failed + ret + CFI_ENDPROC +END(__write_lock_failed) + +/* rdi: pointer to rwlock_t */ +ENTRY(__read_lock_failed) + CFI_STARTPROC + LOCK_PREFIX + incl (%rdi) +1: rep + nop + cmpl $1,(%rdi) + js 1b + LOCK_PREFIX + decl (%rdi) + js __read_lock_failed + ret + CFI_ENDPROC +END(__read_lock_failed) diff --git a/arch/x86_64/lib/thunk.S b/arch/x86_64/lib/thunk.S index 332ea5d..0025535 100644 --- a/arch/x86_64/lib/thunk.S +++ b/arch/x86_64/lib/thunk.S @@ -1,10 +1,9 @@ - /* - * Save registers before calling assembly functions. This avoids - * disturbance of register allocation in some inline assembly constructs. - * Copyright 2001,2002 by Andi Kleen, SuSE Labs. - * Subject to the GNU public license, v.2. No warranty of any kind. - * $Id: thunk.S,v 1.2 2002/03/13 20:06:58 ak Exp $ - */ +/* + * Save registers before calling assembly functions. This avoids + * disturbance of register allocation in some inline assembly constructs. + * Copyright 2001,2002 by Andi Kleen, SuSE Labs. + * Subject to the GNU public license, v.2. No warranty of any kind. + */ #include <linux/config.h> #include <linux/linkage.h> @@ -67,33 +66,3 @@ restore_norax: RESTORE_ARGS 1 ret CFI_ENDPROC - -#ifdef CONFIG_SMP -/* Support for read/write spinlocks. */ - .text -/* rax: pointer to rwlock_t */ -ENTRY(__write_lock_failed) - lock - addl $RW_LOCK_BIAS,(%rax) -1: rep - nop - cmpl $RW_LOCK_BIAS,(%rax) - jne 1b - lock - subl $RW_LOCK_BIAS,(%rax) - jnz __write_lock_failed - ret - -/* rax: pointer to rwlock_t */ -ENTRY(__read_lock_failed) - lock - incl (%rax) -1: rep - nop - cmpl $1,(%rax) - js 1b - lock - decl (%rax) - js __read_lock_failed - ret -#endif diff --git a/arch/x86_64/mm/fault.c b/arch/x86_64/mm/fault.c index 4198798..1a17b07 100644 --- a/arch/x86_64/mm/fault.c +++ b/arch/x86_64/mm/fault.c @@ -40,8 +40,7 @@ #define PF_RSVD (1<<3) #define PF_INSTR (1<<4) -#ifdef CONFIG_KPROBES -ATOMIC_NOTIFIER_HEAD(notify_page_fault_chain); +static ATOMIC_NOTIFIER_HEAD(notify_page_fault_chain); /* Hook to register for page fault notifications */ int register_page_fault_notifier(struct notifier_block *nb) @@ -49,11 +48,13 @@ int register_page_fault_notifier(struct notifier_block *nb) vmalloc_sync_all(); return atomic_notifier_chain_register(¬ify_page_fault_chain, nb); } +EXPORT_SYMBOL_GPL(register_page_fault_notifier); int unregister_page_fault_notifier(struct notifier_block *nb) { return atomic_notifier_chain_unregister(¬ify_page_fault_chain, nb); } +EXPORT_SYMBOL_GPL(unregister_page_fault_notifier); static inline int notify_page_fault(enum die_val val, const char *str, struct pt_regs *regs, long err, int trap, int sig) @@ -67,13 +68,6 @@ static inline int notify_page_fault(enum die_val val, const char *str, }; return atomic_notifier_call_chain(¬ify_page_fault_chain, val, &args); } -#else -static inline int notify_page_fault(enum die_val val, const char *str, - struct pt_regs *regs, long err, int trap, int sig) -{ - return NOTIFY_DONE; -} -#endif void bust_spinlocks(int yes) { @@ -102,7 +96,7 @@ void bust_spinlocks(int yes) static noinline int is_prefetch(struct pt_regs *regs, unsigned long addr, unsigned long error_code) { - unsigned char *instr; + unsigned char __user *instr; int scan_more = 1; int prefetch = 0; unsigned char *max_instr; @@ -111,7 +105,7 @@ static noinline int is_prefetch(struct pt_regs *regs, unsigned long addr, if (error_code & PF_INSTR) return 0; - instr = (unsigned char *)convert_rip_to_linear(current, regs); + instr = (unsigned char __user *)convert_rip_to_linear(current, regs); max_instr = instr + 15; if (user_mode(regs) && instr >= (unsigned char *)TASK_SIZE) @@ -122,7 +116,7 @@ static noinline int is_prefetch(struct pt_regs *regs, unsigned long addr, unsigned char instr_hi; unsigned char instr_lo; - if (__get_user(opcode, instr)) + if (__get_user(opcode, (char __user *)instr)) break; instr_hi = opcode & 0xf0; @@ -160,7 +154,7 @@ static noinline int is_prefetch(struct pt_regs *regs, unsigned long addr, case 0x00: /* Prefetch instruction is 0x0F0D or 0x0F18 */ scan_more = 0; - if (__get_user(opcode, instr)) + if (__get_user(opcode, (char __user *)instr)) break; prefetch = (instr_lo == 0xF) && (opcode == 0x0D || opcode == 0x18); @@ -176,7 +170,7 @@ static noinline int is_prefetch(struct pt_regs *regs, unsigned long addr, static int bad_address(void *p) { unsigned long dummy; - return __get_user(dummy, (unsigned long *)p); + return __get_user(dummy, (unsigned long __user *)p); } void dump_pagetable(unsigned long address) diff --git a/arch/x86_64/mm/init.c b/arch/x86_64/mm/init.c index 52fd42c..1e4669f 100644 --- a/arch/x86_64/mm/init.c +++ b/arch/x86_64/mm/init.c @@ -229,7 +229,6 @@ __init void *early_ioremap(unsigned long addr, unsigned long size) /* actually usually some more */ if (size >= LARGE_PAGE_SIZE) { - printk("SMBIOS area too long %lu\n", size); return NULL; } set_pmd(temp_mappings[0].pmd, __pmd(map | _KERNPG_TABLE | _PAGE_PSE)); @@ -250,12 +249,13 @@ __init void early_iounmap(void *addr, unsigned long size) } static void __meminit -phys_pmd_init(pmd_t *pmd, unsigned long address, unsigned long end) +phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end) { - int i; + int i = pmd_index(address); - for (i = 0; i < PTRS_PER_PMD; pmd++, i++, address += PMD_SIZE) { + for (; i < PTRS_PER_PMD; i++, address += PMD_SIZE) { unsigned long entry; + pmd_t *pmd = pmd_page + pmd_index(address); if (address >= end) { if (!after_bootmem) @@ -263,6 +263,10 @@ phys_pmd_init(pmd_t *pmd, unsigned long address, unsigned long end) set_pmd(pmd, __pmd(0)); break; } + + if (pmd_val(*pmd)) + continue; + entry = _PAGE_NX|_PAGE_PSE|_KERNPG_TABLE|_PAGE_GLOBAL|address; entry &= __supported_pte_mask; set_pmd(pmd, __pmd(entry)); @@ -272,45 +276,41 @@ phys_pmd_init(pmd_t *pmd, unsigned long address, unsigned long end) static void __meminit phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end) { - pmd_t *pmd = pmd_offset(pud, (unsigned long)__va(address)); - - if (pmd_none(*pmd)) { - spin_lock(&init_mm.page_table_lock); - phys_pmd_init(pmd, address, end); - spin_unlock(&init_mm.page_table_lock); - __flush_tlb_all(); - } + pmd_t *pmd = pmd_offset(pud,0); + spin_lock(&init_mm.page_table_lock); + phys_pmd_init(pmd, address, end); + spin_unlock(&init_mm.page_table_lock); + __flush_tlb_all(); } -static void __meminit phys_pud_init(pud_t *pud, unsigned long address, unsigned long end) +static void __meminit phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end) { - long i = pud_index(address); - - pud = pud + i; + int i = pud_index(addr); - if (after_bootmem && pud_val(*pud)) { - phys_pmd_update(pud, address, end); - return; - } - for (; i < PTRS_PER_PUD; pud++, i++) { + for (; i < PTRS_PER_PUD; i++, addr = (addr & PUD_MASK) + PUD_SIZE ) { int map; - unsigned long paddr, pmd_phys; + unsigned long pmd_phys; + pud_t *pud = pud_page + pud_index(addr); pmd_t *pmd; - paddr = (address & PGDIR_MASK) + i*PUD_SIZE; - if (paddr >= end) + if (addr >= end) break; - if (!after_bootmem && !e820_any_mapped(paddr, paddr+PUD_SIZE, 0)) { + if (!after_bootmem && !e820_any_mapped(addr,addr+PUD_SIZE,0)) { set_pud(pud, __pud(0)); continue; } + if (pud_val(*pud)) { + phys_pmd_update(pud, addr, end); + continue; + } + pmd = alloc_low_page(&map, &pmd_phys); spin_lock(&init_mm.page_table_lock); set_pud(pud, __pud(pmd_phys | _KERNPG_TABLE)); - phys_pmd_init(pmd, paddr, end); + phys_pmd_init(pmd, addr, end); spin_unlock(&init_mm.page_table_lock); unmap_low_page(map); } @@ -597,12 +597,6 @@ void __init mem_init(void) pci_iommu_alloc(); - /* How many end-of-memory variables you have, grandma! */ - max_low_pfn = end_pfn; - max_pfn = end_pfn; - num_physpages = end_pfn; - high_memory = (void *) __va(end_pfn * PAGE_SIZE); - /* clear the zero-page */ memset(empty_zero_page, 0, PAGE_SIZE); diff --git a/arch/x86_64/mm/k8topology.c b/arch/x86_64/mm/k8topology.c index 7c45c2d..5cf594f 100644 --- a/arch/x86_64/mm/k8topology.c +++ b/arch/x86_64/mm/k8topology.c @@ -54,6 +54,9 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end) nodes_clear(nodes_parsed); + if (!early_pci_allowed()) + return -1; + nb = find_northbridge(); if (nb < 0) return nb; diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c index b2fac14..322bf45 100644 --- a/arch/x86_64/mm/numa.c +++ b/arch/x86_64/mm/numa.c @@ -225,7 +225,7 @@ void __init numa_init_array(void) int numa_fake __initdata = 0; /* Numa emulation */ -static int numa_emulation(unsigned long start_pfn, unsigned long end_pfn) +static int __init numa_emulation(unsigned long start_pfn, unsigned long end_pfn) { int i; struct bootnode nodes[MAX_NUMNODES]; @@ -348,9 +348,10 @@ void __init paging_init(void) } } -/* [numa=off] */ -__init int numa_setup(char *opt) +static __init int numa_setup(char *opt) { + if (!opt) + return -EINVAL; if (!strncmp(opt,"off",3)) numa_off = 1; #ifdef CONFIG_NUMA_EMU @@ -366,9 +367,11 @@ __init int numa_setup(char *opt) if (!strncmp(opt,"hotadd=", 7)) hotadd_percent = simple_strtoul(opt+7, NULL, 10); #endif - return 1; + return 0; } +early_param("numa", numa_setup); + /* * Setup early cpu_to_node. * diff --git a/arch/x86_64/mm/pageattr.c b/arch/x86_64/mm/pageattr.c index 2685b1f..3e231d76 100644 --- a/arch/x86_64/mm/pageattr.c +++ b/arch/x86_64/mm/pageattr.c @@ -108,8 +108,8 @@ static void revert_page(unsigned long address, pgprot_t ref_prot) BUG_ON(pud_none(*pud)); pmd = pmd_offset(pud, address); BUG_ON(pmd_val(*pmd) & _PAGE_PSE); - pgprot_val(ref_prot) |= _PAGE_PSE; large_pte = mk_pte_phys(__pa(address) & LARGE_PAGE_MASK, ref_prot); + large_pte = pte_mkhuge(large_pte); set_pte((pte_t *)pmd, large_pte); } @@ -119,32 +119,28 @@ __change_page_attr(unsigned long address, unsigned long pfn, pgprot_t prot, { pte_t *kpte; struct page *kpte_page; - unsigned kpte_flags; pgprot_t ref_prot2; kpte = lookup_address(address); if (!kpte) return 0; kpte_page = virt_to_page(((unsigned long)kpte) & PAGE_MASK); - kpte_flags = pte_val(*kpte); if (pgprot_val(prot) != pgprot_val(ref_prot)) { - if ((kpte_flags & _PAGE_PSE) == 0) { + if (!pte_huge(*kpte)) { set_pte(kpte, pfn_pte(pfn, prot)); } else { /* * split_large_page will take the reference for this * change_page_attr on the split page. */ - struct page *split; - ref_prot2 = __pgprot(pgprot_val(pte_pgprot(*lookup_address(address))) & ~(1<<_PAGE_BIT_PSE)); - + ref_prot2 = pte_pgprot(pte_clrhuge(*kpte)); split = split_large_page(address, prot, ref_prot2); if (!split) return -ENOMEM; - set_pte(kpte,mk_pte(split, ref_prot2)); + set_pte(kpte, mk_pte(split, ref_prot2)); kpte_page = split; - } + } page_private(kpte_page)++; - } else if ((kpte_flags & _PAGE_PSE) == 0) { + } else if (!pte_huge(*kpte)) { set_pte(kpte, pfn_pte(pfn, ref_prot)); BUG_ON(page_private(kpte_page) == 0); page_private(kpte_page)--; @@ -190,10 +186,12 @@ int change_page_attr_addr(unsigned long address, int numpages, pgprot_t prot) * lowmem */ if (__pa(address) < KERNEL_TEXT_SIZE) { unsigned long addr2; - pgprot_t prot2 = prot; + pgprot_t prot2; addr2 = __START_KERNEL_map + __pa(address); - pgprot_val(prot2) &= ~_PAGE_NX; - err = __change_page_attr(addr2, pfn, prot2, PAGE_KERNEL_EXEC); + /* Make sure the kernel mappings stay executable */ + prot2 = pte_pgprot(pte_mkexec(pfn_pte(0, prot))); + err = __change_page_attr(addr2, pfn, prot2, + PAGE_KERNEL_EXEC); } } up_write(&init_mm.mmap_sem); diff --git a/arch/x86_64/mm/srat.c b/arch/x86_64/mm/srat.c index 502fce6..ca10701 100644 --- a/arch/x86_64/mm/srat.c +++ b/arch/x86_64/mm/srat.c @@ -21,6 +21,8 @@ #include <asm/numa.h> #include <asm/e820.h> +int acpi_numa __initdata; + #if (defined(CONFIG_ACPI_HOTPLUG_MEMORY) || \ defined(CONFIG_ACPI_HOTPLUG_MEMORY_MODULE)) \ && !defined(CONFIG_MEMORY_HOTPLUG) diff --git a/arch/x86_64/pci/Makefile b/arch/x86_64/pci/Makefile index a3f6ad5..1eb18f4 100644 --- a/arch/x86_64/pci/Makefile +++ b/arch/x86_64/pci/Makefile @@ -9,7 +9,7 @@ obj-y := i386.o obj-$(CONFIG_PCI_DIRECT)+= direct.o obj-y += fixup.o init.o obj-$(CONFIG_ACPI) += acpi.o -obj-y += legacy.o irq.o common.o +obj-y += legacy.o irq.o common.o early.o # mmconfig has a 64bit special obj-$(CONFIG_PCI_MMCONFIG) += mmconfig.o direct.o @@ -23,3 +23,4 @@ common-y += ../../i386/pci/common.o fixup-y += ../../i386/pci/fixup.o i386-y += ../../i386/pci/i386.o init-y += ../../i386/pci/init.o +early-y += ../../i386/pci/early.o diff --git a/arch/x86_64/pci/mmconfig.c b/arch/x86_64/pci/mmconfig.c index 3c55c76..7732f42 100644 --- a/arch/x86_64/pci/mmconfig.c +++ b/arch/x86_64/pci/mmconfig.c @@ -156,15 +156,45 @@ static __init void unreachable_devices(void) addr = pci_dev_base(0, k, PCI_DEVFN(i, 0)); if (addr == NULL|| readl(addr) != val1) { set_bit(i + 32*k, fallback_slots); - printk(KERN_NOTICE - "PCI: No mmconfig possible on device %x:%x\n", - k, i); + printk(KERN_NOTICE "PCI: No mmconfig possible" + " on device %02x:%02x\n", k, i); } } } } -void __init pci_mmcfg_init(void) +static __init void pci_mmcfg_insert_resources(void) +{ +#define PCI_MMCFG_RESOURCE_NAME_LEN 19 + int i; + struct resource *res; + char *names; + unsigned num_buses; + + res = kcalloc(PCI_MMCFG_RESOURCE_NAME_LEN + sizeof(*res), + pci_mmcfg_config_num, GFP_KERNEL); + + if (!res) { + printk(KERN_ERR "PCI: Unable to allocate MMCONFIG resources\n"); + return; + } + + names = (void *)&res[pci_mmcfg_config_num]; + for (i = 0; i < pci_mmcfg_config_num; i++, res++) { + num_buses = pci_mmcfg_config[i].end_bus_number - + pci_mmcfg_config[i].start_bus_number + 1; + res->name = names; + snprintf(names, PCI_MMCFG_RESOURCE_NAME_LEN, "PCI MMCONFIG %u", + pci_mmcfg_config[i].pci_segment_group_number); + res->start = pci_mmcfg_config[i].base_address; + res->end = res->start + (num_buses << 20) - 1; + res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + insert_resource(&iomem_resource, res); + names += PCI_MMCFG_RESOURCE_NAME_LEN; + } +} + +void __init pci_mmcfg_init(int type) { int i; @@ -177,7 +207,9 @@ void __init pci_mmcfg_init(void) (pci_mmcfg_config[0].base_address == 0)) return; - if (!e820_all_mapped(pci_mmcfg_config[0].base_address, + /* 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(pci_mmcfg_config[0].base_address, pci_mmcfg_config[0].base_address + MMCONFIG_APER_MIN, E820_RESERVED)) { printk(KERN_ERR "PCI: BIOS Bug: MCFG area at %x is not E820-reserved\n", @@ -186,7 +218,6 @@ void __init pci_mmcfg_init(void) return; } - /* RED-PEN i386 doesn't do _nocache right now */ pci_mmcfg_virt = kmalloc(sizeof(*pci_mmcfg_virt) * pci_mmcfg_config_num, GFP_KERNEL); if (pci_mmcfg_virt == NULL) { printk("PCI: Can not allocate memory for mmconfig structures\n"); @@ -205,6 +236,7 @@ void __init pci_mmcfg_init(void) } unreachable_devices(); + pci_mmcfg_insert_resources(); raw_pci_ops = &pci_mmcfg; pci_probe = (pci_probe & ~PCI_PROBE_MASK) | PCI_PROBE_MMCONF; |
