diff options
| author | André Fabian Silva Delgado <emulatorman@parabola.nu> | 2015-09-08 01:01:14 -0300 |
|---|---|---|
| committer | André Fabian Silva Delgado <emulatorman@parabola.nu> | 2015-09-08 01:01:14 -0300 |
| commit | e5fd91f1ef340da553f7a79da9540c3db711c937 (patch) | |
| tree | b11842027dc6641da63f4bcc524f8678263304a3 /arch/x86 | |
| parent | 2a9b0348e685a63d97486f6749622b61e9e3292f (diff) | |
Linux-libre 4.2-gnu
Diffstat (limited to 'arch/x86')
381 files changed, 15554 insertions, 11974 deletions
diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild index 3942f74c9..1538562cc 100644 --- a/arch/x86/Kbuild +++ b/arch/x86/Kbuild @@ -1,3 +1,6 @@ + +obj-y += entry/ + obj-$(CONFIG_KVM) += kvm/ # Xen paravirtualization support @@ -11,7 +14,7 @@ obj-y += kernel/ obj-y += mm/ obj-y += crypto/ -obj-y += vdso/ + obj-$(CONFIG_IA32_EMULATION) += ia32/ obj-y += platform/ diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 773dac7e8..b3a1a5d77 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -9,140 +9,147 @@ config 64BIT config X86_32 def_bool y depends on !64BIT - select CLKSRC_I8253 - select HAVE_UID16 config X86_64 def_bool y depends on 64BIT - select X86_DEV_DMA_OPS - select ARCH_USE_CMPXCHG_LOCKREF - select HAVE_LIVEPATCH ### Arch settings config X86 def_bool y - select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI - select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI + select ACPI_LEGACY_TABLES_LOOKUP if ACPI + select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI + select ANON_INODES + select ARCH_CLOCKSOURCE_DATA + select ARCH_DISCARD_MEMBLOCK + select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS + select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FAST_MULTIPLIER select ARCH_HAS_GCOV_PROFILE_ALL + select ARCH_HAS_PMEM_API + select ARCH_HAS_SG_CHAIN + select ARCH_HAVE_NMI_SAFE_CMPXCHG + select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO - select HAVE_AOUT if X86_32 - select HAVE_UNSTABLE_SCHED_CLOCK - select ARCH_SUPPORTS_NUMA_BALANCING if X86_64 - select ARCH_SUPPORTS_INT128 if X86_64 - select HAVE_IDE - select HAVE_OPROFILE - select HAVE_PCSPKR_PLATFORM - select HAVE_PERF_EVENTS - select HAVE_IOREMAP_PROT - select HAVE_KPROBES - select HAVE_MEMBLOCK - select HAVE_MEMBLOCK_NODE_MAP - select ARCH_DISCARD_MEMBLOCK - select ARCH_WANT_OPTIONAL_GPIOLIB + select ARCH_SUPPORTS_ATOMIC_RMW + select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT + select ARCH_SUPPORTS_INT128 if X86_64 + select ARCH_SUPPORTS_NUMA_BALANCING if X86_64 + select ARCH_USE_BUILTIN_BSWAP + select ARCH_USE_CMPXCHG_LOCKREF if X86_64 + select ARCH_USE_QUEUED_RWLOCKS + select ARCH_USE_QUEUED_SPINLOCKS + select ARCH_WANTS_DYNAMIC_TASK_STRUCT select ARCH_WANT_FRAME_POINTERS - select HAVE_DMA_ATTRS - select HAVE_DMA_CONTIGUOUS - select HAVE_KRETPROBES + select ARCH_WANT_IPC_PARSE_VERSION if X86_32 + select ARCH_WANT_OPTIONAL_GPIOLIB + select BUILDTIME_EXTABLE_SORT + select CLKEVT_I8253 + select CLKSRC_I8253 if X86_32 + select CLOCKSOURCE_VALIDATE_LAST_CYCLE + select CLOCKSOURCE_WATCHDOG + select CLONE_BACKWARDS if X86_32 + select COMPAT_OLD_SIGACTION if IA32_EMULATION + select DCACHE_WORD_ACCESS + select EDAC_ATOMIC_SCRUB + select EDAC_SUPPORT + select GENERIC_CLOCKEVENTS + select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC) + select GENERIC_CLOCKEVENTS_MIN_ADJUST + select GENERIC_CMOS_UPDATE + select GENERIC_CPU_AUTOPROBE select GENERIC_EARLY_IOREMAP - select HAVE_OPTPROBES - select HAVE_KPROBES_ON_FTRACE - select HAVE_FTRACE_MCOUNT_RECORD - select HAVE_FENTRY if X86_64 + select GENERIC_FIND_FIRST_BIT + select GENERIC_IOMAP + select GENERIC_IRQ_PROBE + select GENERIC_IRQ_SHOW + select GENERIC_PENDING_IRQ if SMP + select GENERIC_SMP_IDLE_THREAD + select GENERIC_STRNCPY_FROM_USER + select GENERIC_STRNLEN_USER + select GENERIC_TIME_VSYSCALL + select HAVE_ACPI_APEI if ACPI + select HAVE_ACPI_APEI_NMI if ACPI + select HAVE_ALIGNED_STRUCT_PAGE if SLUB + select HAVE_AOUT if X86_32 + select HAVE_ARCH_AUDITSYSCALL + select HAVE_ARCH_HUGE_VMAP if X86_64 || X86_PAE + select HAVE_ARCH_JUMP_LABEL + select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP + select HAVE_ARCH_KGDB + select HAVE_ARCH_KMEMCHECK + select HAVE_ARCH_SECCOMP_FILTER + select HAVE_ARCH_SOFT_DIRTY if X86_64 + select HAVE_ARCH_TRACEHOOK + select HAVE_ARCH_TRANSPARENT_HUGEPAGE + select HAVE_BPF_JIT if X86_64 + select HAVE_CC_STACKPROTECTOR + select HAVE_CMPXCHG_DOUBLE + select HAVE_CMPXCHG_LOCAL + select HAVE_CONTEXT_TRACKING if X86_64 + select HAVE_COPY_THREAD_TLS select HAVE_C_RECORDMCOUNT + select HAVE_DEBUG_KMEMLEAK + select HAVE_DEBUG_STACKOVERFLOW + select HAVE_DMA_API_DEBUG + select HAVE_DMA_ATTRS + select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS - select HAVE_FUNCTION_TRACER - select HAVE_FUNCTION_GRAPH_TRACER - select HAVE_FUNCTION_GRAPH_FP_TEST - select HAVE_SYSCALL_TRACEPOINTS - select SYSCTL_EXCEPTION_TRACE - select HAVE_KVM - select HAVE_ARCH_KGDB - select HAVE_ARCH_TRACEHOOK - select HAVE_GENERIC_DMA_COHERENT if X86_32 select HAVE_EFFICIENT_UNALIGNED_ACCESS - select USER_STACKTRACE_SUPPORT - select HAVE_REGS_AND_STACK_ACCESS_API - select HAVE_DMA_API_DEBUG - select HAVE_KERNEL_GZIP + select HAVE_FENTRY if X86_64 + select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_FUNCTION_GRAPH_FP_TEST + select HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FUNCTION_TRACER + select HAVE_GENERIC_DMA_COHERENT if X86_32 + select HAVE_HW_BREAKPOINT + select HAVE_IDE + select HAVE_IOREMAP_PROT + select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64 + select HAVE_IRQ_TIME_ACCOUNTING select HAVE_KERNEL_BZIP2 + select HAVE_KERNEL_GZIP + select HAVE_KERNEL_LZ4 select HAVE_KERNEL_LZMA - select HAVE_KERNEL_XZ select HAVE_KERNEL_LZO - select HAVE_KERNEL_LZ4 - select HAVE_HW_BREAKPOINT + select HAVE_KERNEL_XZ + select HAVE_KPROBES + select HAVE_KPROBES_ON_FTRACE + select HAVE_KRETPROBES + select HAVE_KVM + select HAVE_LIVEPATCH if X86_64 + select HAVE_MEMBLOCK + select HAVE_MEMBLOCK_NODE_MAP select HAVE_MIXED_BREAKPOINTS_REGS - select PERF_EVENTS + select HAVE_OPROFILE + select HAVE_OPTPROBES + select HAVE_PCSPKR_PLATFORM + select HAVE_PERF_EVENTS select HAVE_PERF_EVENTS_NMI select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP - select HAVE_DEBUG_KMEMLEAK - select ANON_INODES - select HAVE_ALIGNED_STRUCT_PAGE if SLUB - select HAVE_CMPXCHG_LOCAL - select HAVE_CMPXCHG_DOUBLE - select HAVE_ARCH_KMEMCHECK - select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP + select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_SYSCALL_TRACEPOINTS + select HAVE_UID16 if X86_32 + select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_USER_RETURN_NOTIFIER - select ARCH_HAS_ELF_RANDOMIZE - select HAVE_ARCH_JUMP_LABEL - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE - select SPARSE_IRQ - select GENERIC_FIND_FIRST_BIT - select GENERIC_IRQ_PROBE - select GENERIC_PENDING_IRQ if SMP - select GENERIC_IRQ_SHOW - select GENERIC_CLOCKEVENTS_MIN_ADJUST select IRQ_FORCED_THREADING - select HAVE_BPF_JIT if X86_64 - select HAVE_ARCH_TRANSPARENT_HUGEPAGE - select HAVE_ARCH_HUGE_VMAP if X86_64 || (X86_32 && X86_PAE) - select ARCH_HAS_SG_CHAIN - select CLKEVT_I8253 - select ARCH_HAVE_NMI_SAFE_CMPXCHG - select GENERIC_IOMAP - select DCACHE_WORD_ACCESS - select GENERIC_SMP_IDLE_THREAD - select ARCH_WANT_IPC_PARSE_VERSION if X86_32 - select HAVE_ARCH_SECCOMP_FILTER - select BUILDTIME_EXTABLE_SORT - select GENERIC_CMOS_UPDATE - select HAVE_ARCH_SOFT_DIRTY if X86_64 - select CLOCKSOURCE_WATCHDOG - select GENERIC_CLOCKEVENTS - select ARCH_CLOCKSOURCE_DATA - select CLOCKSOURCE_VALIDATE_LAST_CYCLE - select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC) - select GENERIC_TIME_VSYSCALL - select GENERIC_STRNCPY_FROM_USER - select GENERIC_STRNLEN_USER - select HAVE_CONTEXT_TRACKING if X86_64 - select HAVE_IRQ_TIME_ACCOUNTING - select VIRT_TO_BUS - select MODULES_USE_ELF_REL if X86_32 - select MODULES_USE_ELF_RELA if X86_64 - select CLONE_BACKWARDS if X86_32 - select ARCH_USE_BUILTIN_BSWAP - select ARCH_USE_QUEUE_RWLOCK - select OLD_SIGSUSPEND3 if X86_32 || IA32_EMULATION - select OLD_SIGACTION if X86_32 - select COMPAT_OLD_SIGACTION if IA32_EMULATION + select MODULES_USE_ELF_RELA if X86_64 + select MODULES_USE_ELF_REL if X86_32 + select OLD_SIGACTION if X86_32 + select OLD_SIGSUSPEND3 if X86_32 || IA32_EMULATION + select PERF_EVENTS select RTC_LIB - select HAVE_DEBUG_STACKOVERFLOW - select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64 - select HAVE_CC_STACKPROTECTOR - select GENERIC_CPU_AUTOPROBE - select HAVE_ARCH_AUDITSYSCALL - select ARCH_SUPPORTS_ATOMIC_RMW - select HAVE_ACPI_APEI if ACPI - select HAVE_ACPI_APEI_NMI if ACPI - select ACPI_LEGACY_TABLES_LOOKUP if ACPI - select X86_FEATURE_NAMES if PROC_FS + select SPARSE_IRQ select SRCU + select SYSCTL_EXCEPTION_TRACE + select USER_STACKTRACE_SUPPORT + select VIRT_TO_BUS + select X86_DEV_DMA_OPS if X86_64 + select X86_FEATURE_NAMES if PROC_FS config INSTRUCTION_DECODER def_bool y @@ -248,6 +255,11 @@ config ARCH_SUPPORTS_OPTIMIZED_INLINING config ARCH_SUPPORTS_DEBUG_PAGEALLOC def_bool y +config KASAN_SHADOW_OFFSET + hex + depends on KASAN + default 0xdffffc0000000000 + config HAVE_INTEL_TXT def_bool y depends on INTEL_IOMMU && ACPI @@ -260,10 +272,6 @@ config X86_64_SMP def_bool y depends on X86_64 && SMP -config X86_HT - def_bool y - depends on SMP - config X86_32_LAZY_GS def_bool y depends on X86_32 && !CC_STACKPROTECTOR @@ -341,7 +349,7 @@ config X86_FEATURE_NAMES config X86_X2APIC bool "Support x2apic" - depends on X86_LOCAL_APIC && X86_64 && IRQ_REMAP + depends on X86_LOCAL_APIC && X86_64 && (IRQ_REMAP || HYPERVISOR_GUEST) ---help--- This enables x2apic support on CPUs that have this feature. @@ -441,6 +449,7 @@ config X86_UV depends on X86_EXTENDED_PLATFORM depends on NUMA depends on X86_X2APIC + depends on PCI ---help--- This option is needed in order to support SGI Ultraviolet systems. If you don't have one of these, you should say N here. @@ -466,7 +475,6 @@ config X86_INTEL_CE select X86_REBOOTFIXUPS select OF select OF_EARLY_FLATTREE - select IRQ_DOMAIN ---help--- Select for the Intel CE media processor (CE4100) SOC. This option compiles in support for the CE4100 SOC for settop @@ -666,7 +674,7 @@ config PARAVIRT_DEBUG config PARAVIRT_SPINLOCKS bool "Paravirtualization layer for spinlocks" depends on PARAVIRT && SMP - select UNINLINE_SPIN_UNLOCK + select UNINLINE_SPIN_UNLOCK if !QUEUED_SPINLOCKS ---help--- Paravirtualized spinlocks allow a pvops backend to replace the spinlock implementation with something virtualization-friendly @@ -851,11 +859,12 @@ config NR_CPUS default "1" if !SMP default "8192" if MAXSMP default "32" if SMP && X86_BIGSMP - default "8" if SMP + default "8" if SMP && X86_32 + default "64" if SMP ---help--- This allows you to specify the maximum number of CPUs which this kernel will support. If CPUMASK_OFFSTACK is enabled, the maximum - supported value is 4096, otherwise the maximum value is 512. The + supported value is 8192, otherwise the maximum value is 512. The minimum value which makes sense is 2. This is purely to save memory - each supported CPU adds @@ -863,33 +872,17 @@ config NR_CPUS config SCHED_SMT bool "SMT (Hyperthreading) scheduler support" - depends on X86_HT + depends on SMP ---help--- SMT scheduler support improves the CPU scheduler's decision making - when dealing with Intel P4/Core 2 chips with HyperThreading at a + when dealing with Intel Pentium 4 chips with HyperThreading at a cost of slightly increased overhead in some places. If unsure say N here. -config SMT_NICE - bool "SMT (Hyperthreading) aware nice priority and policy support" - depends on X86_HT && SCHED_BFS && SCHED_SMT - default y - ---help--- - Enabling Hyperthreading on Intel CPUs decreases the effectiveness - of the use of 'nice' levels and different scheduling policies - (e.g. realtime) due to sharing of CPU power between hyperthreads. - SMT nice support makes each logical CPU aware of what is running on - its hyperthread siblings, maintaining appropriate distribution of - CPU according to nice levels and scheduling policies at the expense - of slightly increased overhead. - - If unsure say Y here. - - config SCHED_MC def_bool y prompt "Multi-core scheduler support" - depends on X86_HT + depends on SMP ---help--- Multi-core scheduler support improves the CPU scheduler's decision making when dealing with multi-core CPU chips at a cost of slightly @@ -930,12 +923,12 @@ config X86_UP_IOAPIC config X86_LOCAL_APIC def_bool y depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI - select GENERIC_IRQ_LEGACY_ALLOC_HWIRQ + select IRQ_DOMAIN_HIERARCHY + select PCI_MSI_IRQ_DOMAIN if PCI_MSI config X86_IO_APIC def_bool y depends on X86_LOCAL_APIC || X86_UP_IOAPIC - select IRQ_DOMAIN config X86_REROUTE_FOR_BROKEN_BOOT_IRQS bool "Reroute for broken boot IRQs" @@ -1071,24 +1064,19 @@ config TOSHIBA Say N otherwise. config I8K - tristate "Dell laptop support" + tristate "Dell i8k legacy laptop support" select HWMON + select SENSORS_DELL_SMM ---help--- - This adds a driver to safely access the System Management Mode - of the CPU on the Dell Inspiron 8000. The System Management Mode - is used to read cpu temperature and cooling fan status and to - control the fans on the I8K portables. - - This driver has been tested only on the Inspiron 8000 but it may - also work with other Dell laptops. You can force loading on other - models by passing the parameter `force=1' to the module. Use at - your own risk. - - For information on utilities to make use of this driver see the - I8K Linux utilities web site at: - <http://people.debian.org/~dz/i8k/> + This option enables legacy /proc/i8k userspace interface in hwmon + dell-smm-hwmon driver. Character file /proc/i8k reports bios version, + temperature and allows controlling fan speeds of Dell laptops via + System Management Mode. For old Dell laptops (like Dell Inspiron 8000) + it reports also power and hotkey status. For fan speed control is + needed userspace package i8kutils. - Say Y if you intend to run this kernel on a Dell Inspiron 8000. + Say Y if you intend to run this kernel on old Dell laptops or want to + use userspace package i8kutils. Say N otherwise. config X86_REBOOTFIXUPS @@ -1440,6 +1428,9 @@ source "mm/Kconfig" config X86_PMEM_LEGACY bool "Support non-standard NVDIMMs and ADR protected memory" + depends on PHYS_ADDR_T_64BIT + depends on BLK_DEV + select LIBNVDIMM help Treat memory marked using the non-standard e820 type of 12 as used by the Intel Sandy Bridge-EP reference BIOS as protected memory. @@ -1953,7 +1944,7 @@ config HOTPLUG_CPU config BOOTPARAM_HOTPLUG_CPU0 bool "Set default setting of cpu0_hotpluggable" default n - depends on HOTPLUG_CPU && !SCHED_BFS + depends on HOTPLUG_CPU ---help--- Set whether default state of cpu0_hotpluggable is on or off. @@ -1982,7 +1973,7 @@ config BOOTPARAM_HOTPLUG_CPU0 config DEBUG_HOTPLUG_CPU0 def_bool n prompt "Debug CPU0 hotplug" - depends on HOTPLUG_CPU && !SCHED_BFS + depends on HOTPLUG_CPU ---help--- Enabling this option offlines CPU0 (if CPU0 can be offlined) as soon as possible and boots up userspace with CPU0 offlined. User @@ -2030,7 +2021,7 @@ config CMDLINE_BOOL To compile command line arguments into the kernel, set this option to 'Y', then fill in the - the boot arguments in CONFIG_CMDLINE. + boot arguments in CONFIG_CMDLINE. Systems with fully functional boot loaders (i.e. non-embedded) should leave this option set to 'N'. diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 72484a645..d8c0d3266 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -297,6 +297,18 @@ config OPTIMIZE_INLINING If unsure, say N. +config DEBUG_ENTRY + bool "Debug low-level entry code" + depends on DEBUG_KERNEL + ---help--- + This option enables sanity checks in x86's low-level entry code. + Some of these sanity checks may slow down kernel entries and + exits or otherwise impact performance. + + This is currently used to help test NMI code. + + If unsure, say N. + config DEBUG_NMI_SELFTEST bool "NMI Selftest" depends on DEBUG_KERNEL && X86_LOCAL_APIC @@ -332,4 +344,27 @@ config X86_DEBUG_STATIC_CPU_HAS If unsure, say N. +config X86_DEBUG_FPU + bool "Debug the x86 FPU code" + depends on DEBUG_KERNEL + default y + ---help--- + If this option is enabled then there will be extra sanity + checks and (boot time) debug printouts added to the kernel. + This debugging adds some small amount of runtime overhead + to the kernel. + + If unsure, say N. + +config PUNIT_ATOM_DEBUG + tristate "ATOM Punit debug driver" + select DEBUG_FS + select IOSF_MBI + ---help--- + This is a debug driver, which gets the power states + of all Punit North Complex devices. The power states of + each device is exposed as part of the debugfs interface. + The current power state can be read from + /sys/kernel/debug/punit_atom/dev_power_state + endmenu diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 85b3c2f4f..d8102ac3a 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -77,6 +77,12 @@ else KBUILD_AFLAGS += -m64 KBUILD_CFLAGS += -m64 + # Align jump targets to 1 byte, not the default 16 bytes: + KBUILD_CFLAGS += -falign-jumps=1 + + # Pack loops tightly as well: + KBUILD_CFLAGS += -falign-loops=1 + # Don't autogenerate traditional x87 instructions KBUILD_CFLAGS += $(call cc-option,-mno-80387) KBUILD_CFLAGS += $(call cc-option,-mno-fp-ret-in-387) @@ -84,6 +90,9 @@ else # Use -mpreferred-stack-boundary=3 if supported. KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3) + # Use -mskip-rax-setup if supported. + KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup) + # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu) cflags-$(CONFIG_MNATIVE) += $(call cc-option,-march=native) cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8) @@ -162,12 +171,6 @@ endif sp-$(CONFIG_X86_32) := esp sp-$(CONFIG_X86_64) := rsp -# do binutils support CFI? -cfi := $(call as-instr,.cfi_startproc\n.cfi_rel_offset $(sp-y)$(comma)0\n.cfi_endproc,-DCONFIG_AS_CFI=1) -# is .cfi_signal_frame supported too? -cfi-sigframe := $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1) -cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTIONS=1) - # does binutils support specific instructions? asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1) asinstr += $(call as-instr,pshufb %xmm0$(comma)%xmm0,-DCONFIG_AS_SSSE3=1) @@ -175,8 +178,8 @@ asinstr += $(call as-instr,crc32l %eax$(comma)%eax,-DCONFIG_AS_CRC32=1) avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1) avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1) -KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) -KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) +KBUILD_AFLAGS += $(asinstr) $(avx_instr) $(avx2_instr) +KBUILD_CFLAGS += $(asinstr) $(avx_instr) $(avx2_instr) LDFLAGS := -m elf_$(UTS_MACHINE) @@ -200,7 +203,7 @@ archscripts: scripts_basic # Syscall table generation archheaders: - $(Q)$(MAKE) $(build)=arch/x86/syscalls all + $(Q)$(MAKE) $(build)=arch/x86/entry/syscalls all archprepare: ifeq ($(CONFIG_KEXEC_FILE),y) @@ -263,7 +266,7 @@ install: PHONY += vdso_install vdso_install: - $(Q)$(MAKE) $(build)=arch/x86/vdso $@ + $(Q)$(MAKE) $(build)=arch/x86/entry/vdso $@ archclean: $(Q)rm -rf $(objtree)/arch/i386 diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 0cdc154a2..7d69afd8b 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -1228,6 +1228,10 @@ static efi_status_t setup_e820(struct boot_params *params, e820_type = E820_NVS; break; + case EFI_PERSISTENT_MEMORY: + e820_type = E820_PMEM; + break; + default: continue; } diff --git a/arch/x86/configs/xen.config b/arch/x86/configs/xen.config new file mode 100644 index 000000000..d9fc7139f --- /dev/null +++ b/arch/x86/configs/xen.config @@ -0,0 +1,28 @@ +# global x86 required specific stuff +# On 32-bit HIGHMEM4G is not allowed +CONFIG_HIGHMEM64G=y +CONFIG_64BIT=y + +# These enable us to allow some of the +# not so generic stuff below +CONFIG_HYPERVISOR_GUEST=y +CONFIG_PCI=y +CONFIG_PCI_MSI=y +CONFIG_X86_MCE=y +CONFIG_ACPI_PROCESSOR=y +CONFIG_CPU_FREQ=y + +# x86 xen specific config options +CONFIG_XEN_PVH=y +CONFIG_XEN_MAX_DOMAIN_MEMORY=500 +CONFIG_XEN_SAVE_RESTORE=y +# CONFIG_XEN_DEBUG_FS is not set +CONFIG_XEN_MCE_LOG=y +CONFIG_XEN_ACPI_PROCESSOR=m +# x86 specific backend drivers +CONFIG_XEN_PCIDEV_BACKEND=m +# x86 specific frontend drivers +CONFIG_XEN_PCIDEV_FRONTEND=m +# depends on MEMORY_HOTPLUG, arm64 doesn't enable this yet, +# move to generic config if it ever does. +CONFIG_XEN_BALLOON_MEMORY_HOTPLUG=y diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 112cefacf..dccad38b5 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -32,7 +32,7 @@ #include <crypto/lrw.h> #include <crypto/xts.h> #include <asm/cpu_device_id.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #include <asm/crypto/aes.h> #include <crypto/ablk_helper.h> #include <crypto/scatterwalk.h> @@ -44,15 +44,19 @@ #endif +#define AESNI_ALIGN 16 +#define AES_BLOCK_MASK (~(AES_BLOCK_SIZE - 1)) +#define RFC4106_HASH_SUBKEY_SIZE 16 + /* This data is stored at the end of the crypto_tfm struct. * It's a type of per "session" data storage location. * This needs to be 16 byte aligned. */ struct aesni_rfc4106_gcm_ctx { - u8 hash_subkey[16]; - struct crypto_aes_ctx aes_key_expanded; + u8 hash_subkey[16] __attribute__ ((__aligned__(AESNI_ALIGN))); + struct crypto_aes_ctx aes_key_expanded + __attribute__ ((__aligned__(AESNI_ALIGN))); u8 nonce[4]; - struct cryptd_aead *cryptd_tfm; }; struct aesni_gcm_set_hash_subkey_result { @@ -66,10 +70,6 @@ struct aesni_hash_subkey_req_data { struct scatterlist sg; }; -#define AESNI_ALIGN (16) -#define AES_BLOCK_MASK (~(AES_BLOCK_SIZE-1)) -#define RFC4106_HASH_SUBKEY_SIZE 16 - struct aesni_lrw_ctx { struct lrw_table_ctx lrw_table; u8 raw_aes_ctx[sizeof(struct crypto_aes_ctx) + AESNI_ALIGN - 1]; @@ -283,10 +283,11 @@ static void (*aesni_gcm_dec_tfm)(void *ctx, u8 *out, static inline struct aesni_rfc4106_gcm_ctx *aesni_rfc4106_gcm_ctx_get(struct crypto_aead *tfm) { - return - (struct aesni_rfc4106_gcm_ctx *) - PTR_ALIGN((u8 *) - crypto_tfm_ctx(crypto_aead_tfm(tfm)), AESNI_ALIGN); + unsigned long align = AESNI_ALIGN; + + if (align <= crypto_tfm_ctx_alignment()) + align = 1; + return PTR_ALIGN(crypto_aead_ctx(tfm), align); } #endif @@ -790,36 +791,30 @@ static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, #endif #ifdef CONFIG_X86_64 -static int rfc4106_init(struct crypto_tfm *tfm) +static int rfc4106_init(struct crypto_aead *aead) { struct cryptd_aead *cryptd_tfm; - struct aesni_rfc4106_gcm_ctx *ctx = (struct aesni_rfc4106_gcm_ctx *) - PTR_ALIGN((u8 *)crypto_tfm_ctx(tfm), AESNI_ALIGN); - struct crypto_aead *cryptd_child; - struct aesni_rfc4106_gcm_ctx *child_ctx; + struct cryptd_aead **ctx = crypto_aead_ctx(aead); + cryptd_tfm = cryptd_alloc_aead("__driver-gcm-aes-aesni", CRYPTO_ALG_INTERNAL, CRYPTO_ALG_INTERNAL); if (IS_ERR(cryptd_tfm)) return PTR_ERR(cryptd_tfm); - cryptd_child = cryptd_aead_child(cryptd_tfm); - child_ctx = aesni_rfc4106_gcm_ctx_get(cryptd_child); - memcpy(child_ctx, ctx, sizeof(*ctx)); - ctx->cryptd_tfm = cryptd_tfm; - tfm->crt_aead.reqsize = sizeof(struct aead_request) - + crypto_aead_reqsize(&cryptd_tfm->base); + *ctx = cryptd_tfm; + crypto_aead_set_reqsize( + aead, + sizeof(struct aead_request) + + crypto_aead_reqsize(&cryptd_tfm->base)); return 0; } -static void rfc4106_exit(struct crypto_tfm *tfm) +static void rfc4106_exit(struct crypto_aead *aead) { - struct aesni_rfc4106_gcm_ctx *ctx = - (struct aesni_rfc4106_gcm_ctx *) - PTR_ALIGN((u8 *)crypto_tfm_ctx(tfm), AESNI_ALIGN); - if (!IS_ERR(ctx->cryptd_tfm)) - cryptd_free_aead(ctx->cryptd_tfm); - return; + struct cryptd_aead **ctx = crypto_aead_ctx(aead); + + cryptd_free_aead(*ctx); } static void @@ -845,8 +840,6 @@ rfc4106_set_hash_subkey(u8 *hash_subkey, const u8 *key, unsigned int key_len) if (IS_ERR(ctr_tfm)) return PTR_ERR(ctr_tfm); - crypto_ablkcipher_clear_flags(ctr_tfm, ~0); - ret = crypto_ablkcipher_setkey(ctr_tfm, key, key_len); if (ret) goto out_free_ablkcipher; @@ -895,73 +888,29 @@ out_free_ablkcipher: static int common_rfc4106_set_key(struct crypto_aead *aead, const u8 *key, unsigned int key_len) { - int ret = 0; - struct crypto_tfm *tfm = crypto_aead_tfm(aead); struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(aead); - u8 *new_key_align, *new_key_mem = NULL; if (key_len < 4) { - crypto_tfm_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); + crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN); return -EINVAL; } /*Account for 4 byte nonce at the end.*/ key_len -= 4; - if (key_len != AES_KEYSIZE_128 && key_len != AES_KEYSIZE_192 && - key_len != AES_KEYSIZE_256) { - crypto_tfm_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); - return -EINVAL; - } memcpy(ctx->nonce, key + key_len, sizeof(ctx->nonce)); - /*This must be on a 16 byte boundary!*/ - if ((unsigned long)(&(ctx->aes_key_expanded.key_enc[0])) % AESNI_ALIGN) - return -EINVAL; - - if ((unsigned long)key % AESNI_ALIGN) { - /*key is not aligned: use an auxuliar aligned pointer*/ - new_key_mem = kmalloc(key_len+AESNI_ALIGN, GFP_KERNEL); - if (!new_key_mem) - return -ENOMEM; - - new_key_align = PTR_ALIGN(new_key_mem, AESNI_ALIGN); - memcpy(new_key_align, key, key_len); - key = new_key_align; - } - if (!irq_fpu_usable()) - ret = crypto_aes_expand_key(&(ctx->aes_key_expanded), - key, key_len); - else { - kernel_fpu_begin(); - ret = aesni_set_key(&(ctx->aes_key_expanded), key, key_len); - kernel_fpu_end(); - } - /*This must be on a 16 byte boundary!*/ - if ((unsigned long)(&(ctx->hash_subkey[0])) % AESNI_ALIGN) { - ret = -EINVAL; - goto exit; - } - ret = rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len); -exit: - kfree(new_key_mem); - return ret; + return aes_set_key_common(crypto_aead_tfm(aead), + &ctx->aes_key_expanded, key, key_len) ?: + rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len); } static int rfc4106_set_key(struct crypto_aead *parent, const u8 *key, unsigned int key_len) { - struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(parent); - struct crypto_aead *child = cryptd_aead_child(ctx->cryptd_tfm); - struct aesni_rfc4106_gcm_ctx *c_ctx = aesni_rfc4106_gcm_ctx_get(child); - struct cryptd_aead *cryptd_tfm = ctx->cryptd_tfm; - int ret; + struct cryptd_aead **ctx = crypto_aead_ctx(parent); + struct cryptd_aead *cryptd_tfm = *ctx; - ret = crypto_aead_setkey(child, key, key_len); - if (!ret) { - memcpy(ctx, c_ctx, sizeof(*ctx)); - ctx->cryptd_tfm = cryptd_tfm; - } - return ret; + return crypto_aead_setkey(&cryptd_tfm->base, key, key_len); } static int common_rfc4106_set_authsize(struct crypto_aead *aead, @@ -975,7 +924,7 @@ static int common_rfc4106_set_authsize(struct crypto_aead *aead, default: return -EINVAL; } - crypto_aead_crt(aead)->authsize = authsize; + return 0; } @@ -984,30 +933,23 @@ static int common_rfc4106_set_authsize(struct crypto_aead *aead, static int rfc4106_set_authsize(struct crypto_aead *parent, unsigned int authsize) { - struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(parent); - struct crypto_aead *child = cryptd_aead_child(ctx->cryptd_tfm); - int ret; + struct cryptd_aead **ctx = crypto_aead_ctx(parent); + struct cryptd_aead *cryptd_tfm = *ctx; - ret = crypto_aead_setauthsize(child, authsize); - if (!ret) - crypto_aead_crt(parent)->authsize = authsize; - return ret; + return crypto_aead_setauthsize(&cryptd_tfm->base, authsize); } -static int __driver_rfc4106_encrypt(struct aead_request *req) +static int helper_rfc4106_encrypt(struct aead_request *req) { u8 one_entry_in_sg = 0; u8 *src, *dst, *assoc; __be32 counter = cpu_to_be32(1); struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); - u32 key_len = ctx->aes_key_expanded.key_length; void *aes_ctx = &(ctx->aes_key_expanded); unsigned long auth_tag_len = crypto_aead_authsize(tfm); - u8 iv_tab[16+AESNI_ALIGN]; - u8* iv = (u8 *) PTR_ALIGN((u8 *)iv_tab, AESNI_ALIGN); + u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN))); struct scatter_walk src_sg_walk; - struct scatter_walk assoc_sg_walk; struct scatter_walk dst_sg_walk; unsigned int i; @@ -1016,12 +958,6 @@ static int __driver_rfc4106_encrypt(struct aead_request *req) /* to 8 or 12 bytes */ if (unlikely(req->assoclen != 8 && req->assoclen != 12)) return -EINVAL; - if (unlikely(auth_tag_len != 8 && auth_tag_len != 12 && auth_tag_len != 16)) - return -EINVAL; - if (unlikely(key_len != AES_KEYSIZE_128 && - key_len != AES_KEYSIZE_192 && - key_len != AES_KEYSIZE_256)) - return -EINVAL; /* IV below built */ for (i = 0; i < 4; i++) @@ -1030,55 +966,57 @@ static int __driver_rfc4106_encrypt(struct aead_request *req) *(iv+4+i) = req->iv[i]; *((__be32 *)(iv+12)) = counter; - if ((sg_is_last(req->src)) && (sg_is_last(req->assoc))) { + if (sg_is_last(req->src) && + req->src->offset + req->src->length <= PAGE_SIZE && + sg_is_last(req->dst) && + req->dst->offset + req->dst->length <= PAGE_SIZE) { one_entry_in_sg = 1; scatterwalk_start(&src_sg_walk, req->src); - scatterwalk_start(&assoc_sg_walk, req->assoc); - src = scatterwalk_map(&src_sg_walk); - assoc = scatterwalk_map(&assoc_sg_walk); + assoc = scatterwalk_map(&src_sg_walk); + src = assoc + req->assoclen; dst = src; if (unlikely(req->src != req->dst)) { scatterwalk_start(&dst_sg_walk, req->dst); - dst = scatterwalk_map(&dst_sg_walk); + dst = scatterwalk_map(&dst_sg_walk) + req->assoclen; } - } else { /* Allocate memory for src, dst, assoc */ - src = kmalloc(req->cryptlen + auth_tag_len + req->assoclen, + assoc = kmalloc(req->cryptlen + auth_tag_len + req->assoclen, GFP_ATOMIC); - if (unlikely(!src)) + if (unlikely(!assoc)) return -ENOMEM; - assoc = (src + req->cryptlen + auth_tag_len); - scatterwalk_map_and_copy(src, req->src, 0, req->cryptlen, 0); - scatterwalk_map_and_copy(assoc, req->assoc, 0, - req->assoclen, 0); + scatterwalk_map_and_copy(assoc, req->src, 0, + req->assoclen + req->cryptlen, 0); + src = assoc + req->assoclen; dst = src; } + kernel_fpu_begin(); aesni_gcm_enc_tfm(aes_ctx, dst, src, (unsigned long)req->cryptlen, iv, ctx->hash_subkey, assoc, (unsigned long)req->assoclen, dst + ((unsigned long)req->cryptlen), auth_tag_len); + kernel_fpu_end(); /* The authTag (aka the Integrity Check Value) needs to be written * back to the packet. */ if (one_entry_in_sg) { if (unlikely(req->src != req->dst)) { - scatterwalk_unmap(dst); - scatterwalk_done(&dst_sg_walk, 0, 0); + scatterwalk_unmap(dst - req->assoclen); + scatterwalk_advance(&dst_sg_walk, req->dst->length); + scatterwalk_done(&dst_sg_walk, 1, 0); } - scatterwalk_unmap(src); scatterwalk_unmap(assoc); - scatterwalk_done(&src_sg_walk, 0, 0); - scatterwalk_done(&assoc_sg_walk, 0, 0); + scatterwalk_advance(&src_sg_walk, req->src->length); + scatterwalk_done(&src_sg_walk, req->src == req->dst, 0); } else { - scatterwalk_map_and_copy(dst, req->dst, 0, - req->cryptlen + auth_tag_len, 1); - kfree(src); + scatterwalk_map_and_copy(dst, req->dst, req->assoclen, + req->cryptlen + auth_tag_len, 1); + kfree(assoc); } return 0; } -static int __driver_rfc4106_decrypt(struct aead_request *req) +static int helper_rfc4106_decrypt(struct aead_request *req) { u8 one_entry_in_sg = 0; u8 *src, *dst, *assoc; @@ -1087,26 +1025,16 @@ static int __driver_rfc4106_decrypt(struct aead_request *req) int retval = 0; struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); - u32 key_len = ctx->aes_key_expanded.key_length; void *aes_ctx = &(ctx->aes_key_expanded); unsigned long auth_tag_len = crypto_aead_authsize(tfm); - u8 iv_and_authTag[32+AESNI_ALIGN]; - u8 *iv = (u8 *) PTR_ALIGN((u8 *)iv_and_authTag, AESNI_ALIGN); - u8 *authTag = iv + 16; + u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN))); + u8 authTag[16]; struct scatter_walk src_sg_walk; - struct scatter_walk assoc_sg_walk; struct scatter_walk dst_sg_walk; unsigned int i; - if (unlikely((req->cryptlen < auth_tag_len) || - (req->assoclen != 8 && req->assoclen != 12))) + if (unlikely(req->assoclen != 8 && req->assoclen != 12)) return -EINVAL; - if (unlikely(auth_tag_len != 8 && auth_tag_len != 12 && auth_tag_len != 16)) - return -EINVAL; - if (unlikely(key_len != AES_KEYSIZE_128 && - key_len != AES_KEYSIZE_192 && - key_len != AES_KEYSIZE_256)) - return -EINVAL; /* Assuming we are supporting rfc4106 64-bit extended */ /* sequence numbers We need to have the AAD length */ @@ -1120,33 +1048,36 @@ static int __driver_rfc4106_decrypt(struct aead_request *req) *(iv+4+i) = req->iv[i]; *((__be32 *)(iv+12)) = counter; - if ((sg_is_last(req->src)) && (sg_is_last(req->assoc))) { + if (sg_is_last(req->src) && + req->src->offset + req->src->length <= PAGE_SIZE && + sg_is_last(req->dst) && + req->dst->offset + req->dst->length <= PAGE_SIZE) { one_entry_in_sg = 1; scatterwalk_start(&src_sg_walk, req->src); - scatterwalk_start(&assoc_sg_walk, req->assoc); - src = scatterwalk_map(&src_sg_walk); - assoc = scatterwalk_map(&assoc_sg_walk); + assoc = scatterwalk_map(&src_sg_walk); + src = assoc + req->assoclen; dst = src; if (unlikely(req->src != req->dst)) { scatterwalk_start(&dst_sg_walk, req->dst); - dst = scatterwalk_map(&dst_sg_walk); + dst = scatterwalk_map(&dst_sg_walk) + req->assoclen; } } else { /* Allocate memory for src, dst, assoc */ - src = kmalloc(req->cryptlen + req->assoclen, GFP_ATOMIC); - if (!src) + assoc = kmalloc(req->cryptlen + req->assoclen, GFP_ATOMIC); + if (!assoc) return -ENOMEM; - assoc = (src + req->cryptlen); - scatterwalk_map_and_copy(src, req->src, 0, req->cryptlen, 0); - scatterwalk_map_and_copy(assoc, req->assoc, 0, - req->assoclen, 0); + scatterwalk_map_and_copy(assoc, req->src, 0, + req->assoclen + req->cryptlen, 0); + src = assoc + req->assoclen; dst = src; } + kernel_fpu_begin(); aesni_gcm_dec_tfm(aes_ctx, dst, src, tempCipherLen, iv, ctx->hash_subkey, assoc, (unsigned long)req->assoclen, authTag, auth_tag_len); + kernel_fpu_end(); /* Compare generated tag with passed in tag. */ retval = crypto_memneq(src + tempCipherLen, authTag, auth_tag_len) ? @@ -1154,90 +1085,59 @@ static int __driver_rfc4106_decrypt(struct aead_request *req) if (one_entry_in_sg) { if (unlikely(req->src != req->dst)) { - scatterwalk_unmap(dst); - scatterwalk_done(&dst_sg_walk, 0, 0); + scatterwalk_unmap(dst - req->assoclen); + scatterwalk_advance(&dst_sg_walk, req->dst->length); + scatterwalk_done(&dst_sg_walk, 1, 0); } - scatterwalk_unmap(src); scatterwalk_unmap(assoc); - scatterwalk_done(&src_sg_walk, 0, 0); - scatterwalk_done(&assoc_sg_walk, 0, 0); + scatterwalk_advance(&src_sg_walk, req->src->length); + scatterwalk_done(&src_sg_walk, req->src == req->dst, 0); } else { - scatterwalk_map_and_copy(dst, req->dst, 0, tempCipherLen, 1); - kfree(src); + scatterwalk_map_and_copy(dst, req->dst, req->assoclen, + tempCipherLen, 1); + kfree(assoc); } return retval; } static int rfc4106_encrypt(struct aead_request *req) { - int ret; struct crypto_aead *tfm = crypto_aead_reqtfm(req); - struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); + struct cryptd_aead **ctx = crypto_aead_ctx(tfm); + struct cryptd_aead *cryptd_tfm = *ctx; + struct aead_request *subreq = aead_request_ctx(req); - if (!irq_fpu_usable()) { - struct aead_request *cryptd_req = - (struct aead_request *) aead_request_ctx(req); + aead_request_set_tfm(subreq, irq_fpu_usable() ? + cryptd_aead_child(cryptd_tfm) : + &cryptd_tfm->base); - memcpy(cryptd_req, req, sizeof(*req)); - aead_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base); - ret = crypto_aead_encrypt(cryptd_req); - } else { - kernel_fpu_begin(); - ret = __driver_rfc4106_encrypt(req); - kernel_fpu_end(); - } - return ret; + aead_request_set_callback(subreq, req->base.flags, + req->base.complete, req->base.data); + aead_request_set_crypt(subreq, req->src, req->dst, + req->cryptlen, req->iv); + aead_request_set_ad(subreq, req->assoclen); + + return crypto_aead_encrypt(subreq); } static int rfc4106_decrypt(struct aead_request *req) { - int ret; struct crypto_aead *tfm = crypto_aead_reqtfm(req); - struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); + struct cryptd_aead **ctx = crypto_aead_ctx(tfm); + struct cryptd_aead *cryptd_tfm = *ctx; + struct aead_request *subreq = aead_request_ctx(req); - if (!irq_fpu_usable()) { - struct aead_request *cryptd_req = - (struct aead_request *) aead_request_ctx(req); + aead_request_set_tfm(subreq, irq_fpu_usable() ? + cryptd_aead_child(cryptd_tfm) : + &cryptd_tfm->base); - memcpy(cryptd_req, req, sizeof(*req)); - aead_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base); - ret = crypto_aead_decrypt(cryptd_req); - } else { - kernel_fpu_begin(); - ret = __driver_rfc4106_decrypt(req); - kernel_fpu_end(); - } - return ret; -} - -static int helper_rfc4106_encrypt(struct aead_request *req) -{ - int ret; - - if (unlikely(!irq_fpu_usable())) { - WARN_ONCE(1, "__gcm-aes-aesni alg used in invalid context"); - ret = -EINVAL; - } else { - kernel_fpu_begin(); - ret = __driver_rfc4106_encrypt(req); - kernel_fpu_end(); - } - return ret; -} - -static int helper_rfc4106_decrypt(struct aead_request *req) -{ - int ret; + aead_request_set_callback(subreq, req->base.flags, + req->base.complete, req->base.data); + aead_request_set_crypt(subreq, req->src, req->dst, + req->cryptlen, req->iv); + aead_request_set_ad(subreq, req->assoclen); - if (unlikely(!irq_fpu_usable())) { - WARN_ONCE(1, "__gcm-aes-aesni alg used in invalid context"); - ret = -EINVAL; - } else { - kernel_fpu_begin(); - ret = __driver_rfc4106_decrypt(req); - kernel_fpu_end(); - } - return ret; + return crypto_aead_decrypt(subreq); } #endif @@ -1410,51 +1310,6 @@ static struct crypto_alg aesni_algs[] = { { .geniv = "chainiv", }, }, -}, { - .cra_name = "__gcm-aes-aesni", - .cra_driver_name = "__driver-gcm-aes-aesni", - .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_INTERNAL, - .cra_blocksize = 1, - .cra_ctxsize = sizeof(struct aesni_rfc4106_gcm_ctx) + - AESNI_ALIGN, - .cra_alignmask = 0, - .cra_type = &crypto_aead_type, - .cra_module = THIS_MODULE, - .cra_u = { - .aead = { - .setkey = common_rfc4106_set_key, - .setauthsize = common_rfc4106_set_authsize, - .encrypt = helper_rfc4106_encrypt, - .decrypt = helper_rfc4106_decrypt, - .ivsize = 8, - .maxauthsize = 16, - }, - }, -}, { - .cra_name = "rfc4106(gcm(aes))", - .cra_driver_name = "rfc4106-gcm-aesni", - .cra_priority = 400, - .cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC, - .cra_blocksize = 1, - .cra_ctxsize = sizeof(struct aesni_rfc4106_gcm_ctx) + - AESNI_ALIGN, - .cra_alignmask = 0, - .cra_type = &crypto_nivaead_type, - .cra_module = THIS_MODULE, - .cra_init = rfc4106_init, - .cra_exit = rfc4106_exit, - .cra_u = { - .aead = { - .setkey = rfc4106_set_key, - .setauthsize = rfc4106_set_authsize, - .encrypt = rfc4106_encrypt, - .decrypt = rfc4106_decrypt, - .geniv = "seqiv", - .ivsize = 8, - .maxauthsize = 16, - }, - }, #endif #if IS_ENABLED(CONFIG_CRYPTO_PCBC) }, { @@ -1569,6 +1424,46 @@ static struct crypto_alg aesni_algs[] = { { }, } }; +#ifdef CONFIG_X86_64 +static struct aead_alg aesni_aead_algs[] = { { + .setkey = common_rfc4106_set_key, + .setauthsize = common_rfc4106_set_authsize, + .encrypt = helper_rfc4106_encrypt, + .decrypt = helper_rfc4106_decrypt, + .ivsize = 8, + .maxauthsize = 16, + .base = { + .cra_name = "__gcm-aes-aesni", + .cra_driver_name = "__driver-gcm-aes-aesni", + .cra_flags = CRYPTO_ALG_INTERNAL, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct aesni_rfc4106_gcm_ctx), + .cra_alignmask = AESNI_ALIGN - 1, + .cra_module = THIS_MODULE, + }, +}, { + .init = rfc4106_init, + .exit = rfc4106_exit, + .setkey = rfc4106_set_key, + .setauthsize = rfc4106_set_authsize, + .encrypt = rfc4106_encrypt, + .decrypt = rfc4106_decrypt, + .ivsize = 8, + .maxauthsize = 16, + .base = { + .cra_name = "rfc4106(gcm(aes))", + .cra_driver_name = "rfc4106-gcm-aesni", + .cra_priority = 400, + .cra_flags = CRYPTO_ALG_ASYNC, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct cryptd_aead *), + .cra_module = THIS_MODULE, + }, +} }; +#else +static struct aead_alg aesni_aead_algs[0]; +#endif + static const struct x86_cpu_id aesni_cpu_id[] = { X86_FEATURE_MATCH(X86_FEATURE_AES), @@ -1616,17 +1511,33 @@ static int __init aesni_init(void) if (err) return err; - return crypto_register_algs(aesni_algs, ARRAY_SIZE(aesni_algs)); + err = crypto_register_algs(aesni_algs, ARRAY_SIZE(aesni_algs)); + if (err) + goto fpu_exit; + + err = crypto_register_aeads(aesni_aead_algs, + ARRAY_SIZE(aesni_aead_algs)); + if (err) + goto unregister_algs; + + return err; + +unregister_algs: + crypto_unregister_algs(aesni_algs, ARRAY_SIZE(aesni_algs)); +fpu_exit: + crypto_fpu_exit(); + return err; } static void __exit aesni_exit(void) { + crypto_unregister_aeads(aesni_aead_algs, ARRAY_SIZE(aesni_aead_algs)); crypto_unregister_algs(aesni_algs, ARRAY_SIZE(aesni_algs)); crypto_fpu_exit(); } -module_init(aesni_init); +late_initcall(aesni_init); module_exit(aesni_exit); MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, Intel AES-NI instructions optimized"); diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c index baf0ac21a..4c65c70e6 100644 --- a/arch/x86/crypto/camellia_aesni_avx2_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c @@ -19,8 +19,7 @@ #include <crypto/ctr.h> #include <crypto/lrw.h> #include <crypto/xts.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <asm/crypto/camellia.h> #include <asm/crypto/glue_helper.h> @@ -561,16 +560,15 @@ static struct crypto_alg cmll_algs[10] = { { static int __init camellia_aesni_init(void) { - u64 xcr0; + const char *feature_name; if (!cpu_has_avx2 || !cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) { pr_info("AVX2 or AES-NI instructions are not detected.\n"); return -ENODEV; } - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX2 detected but unusable.\n"); + if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c index 78818a1e7..80a0e4389 100644 --- a/arch/x86/crypto/camellia_aesni_avx_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx_glue.c @@ -19,8 +19,7 @@ #include <crypto/ctr.h> #include <crypto/lrw.h> #include <crypto/xts.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <asm/crypto/camellia.h> #include <asm/crypto/glue_helper.h> @@ -553,16 +552,10 @@ static struct crypto_alg cmll_algs[10] = { { static int __init camellia_aesni_init(void) { - u64 xcr0; + const char *feature_name; - if (!cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) { - pr_info("AVX or AES-NI instructions are not detected.\n"); - return -ENODEV; - } - - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX detected but unusable.\n"); + if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c index 236c80974..be00aa48b 100644 --- a/arch/x86/crypto/cast5_avx_glue.c +++ b/arch/x86/crypto/cast5_avx_glue.c @@ -31,8 +31,7 @@ #include <crypto/cast5.h> #include <crypto/cryptd.h> #include <crypto/ctr.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <asm/crypto/glue_helper.h> #define CAST5_PARALLEL_BLOCKS 16 @@ -468,16 +467,10 @@ static struct crypto_alg cast5_algs[6] = { { static int __init cast5_init(void) { - u64 xcr0; + const char *feature_name; - if (!cpu_has_avx || !cpu_has_osxsave) { - pr_info("AVX instructions are not detected.\n"); - return -ENODEV; - } - - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX detected but unusable.\n"); + if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c index f448810ca..5dbba7224 100644 --- a/arch/x86/crypto/cast6_avx_glue.c +++ b/arch/x86/crypto/cast6_avx_glue.c @@ -36,8 +36,7 @@ #include <crypto/ctr.h> #include <crypto/lrw.h> #include <crypto/xts.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <asm/crypto/glue_helper.h> #define CAST6_PARALLEL_BLOCKS 8 @@ -590,16 +589,10 @@ static struct crypto_alg cast6_algs[10] = { { static int __init cast6_init(void) { - u64 xcr0; + const char *feature_name; - if (!cpu_has_avx || !cpu_has_osxsave) { - pr_info("AVX instructions are not detected.\n"); - return -ENODEV; - } - - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX detected but unusable.\n"); + if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c index 1937fc1d8..07d2c6c86 100644 --- a/arch/x86/crypto/crc32-pclmul_glue.c +++ b/arch/x86/crypto/crc32-pclmul_glue.c @@ -35,7 +35,7 @@ #include <asm/cpufeature.h> #include <asm/cpu_device_id.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #define CHKSUM_BLOCK_SIZE 1 #define CHKSUM_DIGEST_SIZE 4 diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c index 28640c3d6..81a595d75 100644 --- a/arch/x86/crypto/crc32c-intel_glue.c +++ b/arch/x86/crypto/crc32c-intel_glue.c @@ -32,8 +32,7 @@ #include <asm/cpufeature.h> #include <asm/cpu_device_id.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #define CHKSUM_BLOCK_SIZE 1 #define CHKSUM_DIGEST_SIZE 4 diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c index b6c67bf30..a3fcfc97a 100644 --- a/arch/x86/crypto/crct10dif-pclmul_glue.c +++ b/arch/x86/crypto/crct10dif-pclmul_glue.c @@ -29,7 +29,7 @@ #include <linux/init.h> #include <linux/string.h> #include <linux/kernel.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #include <asm/cpufeature.h> #include <asm/cpu_device_id.h> diff --git a/arch/x86/crypto/fpu.c b/arch/x86/crypto/fpu.c index f368ba261..e7d679e2a 100644 --- a/arch/x86/crypto/fpu.c +++ b/arch/x86/crypto/fpu.c @@ -18,7 +18,7 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/crypto.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> struct crypto_fpu_ctx { struct crypto_blkcipher *child; @@ -156,7 +156,7 @@ int __init crypto_fpu_init(void) return crypto_register_template(&crypto_fpu_tmpl); } -void __exit crypto_fpu_exit(void) +void crypto_fpu_exit(void) { crypto_unregister_template(&crypto_fpu_tmpl); } diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index 2079baf06..64d7cf1b5 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -19,7 +19,7 @@ #include <crypto/cryptd.h> #include <crypto/gf128mul.h> #include <crypto/internal/hash.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #include <asm/cpu_device_id.h> #define GHASH_BLOCK_SIZE 16 diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c index 2f63dc89e..7d838dc4d 100644 --- a/arch/x86/crypto/serpent_avx2_glue.c +++ b/arch/x86/crypto/serpent_avx2_glue.c @@ -20,8 +20,7 @@ #include <crypto/lrw.h> #include <crypto/xts.h> #include <crypto/serpent.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <asm/crypto/serpent-avx.h> #include <asm/crypto/glue_helper.h> @@ -537,16 +536,14 @@ static struct crypto_alg srp_algs[10] = { { static int __init init(void) { - u64 xcr0; + const char *feature_name; if (!cpu_has_avx2 || !cpu_has_osxsave) { pr_info("AVX2 instructions are not detected.\n"); return -ENODEV; } - - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX detected but unusable.\n"); + if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c index c8d478af8..da7dafc9b 100644 --- a/arch/x86/crypto/serpent_avx_glue.c +++ b/arch/x86/crypto/serpent_avx_glue.c @@ -36,8 +36,7 @@ #include <crypto/ctr.h> #include <crypto/lrw.h> #include <crypto/xts.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <asm/crypto/serpent-avx.h> #include <asm/crypto/glue_helper.h> @@ -596,16 +595,10 @@ static struct crypto_alg serpent_algs[10] = { { static int __init serpent_init(void) { - u64 xcr0; + const char *feature_name; - if (!cpu_has_avx || !cpu_has_osxsave) { - printk(KERN_INFO "AVX instructions are not detected.\n"); - return -ENODEV; - } - - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - printk(KERN_INFO "AVX detected but unusable.\n"); + if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } diff --git a/arch/x86/crypto/sha-mb/sha1_mb.c b/arch/x86/crypto/sha-mb/sha1_mb.c index e510b1c5d..a841e9765 100644 --- a/arch/x86/crypto/sha-mb/sha1_mb.c +++ b/arch/x86/crypto/sha-mb/sha1_mb.c @@ -65,11 +65,8 @@ #include <crypto/mcryptd.h> #include <crypto/crypto_wq.h> #include <asm/byteorder.h> -#include <asm/i387.h> -#include <asm/xcr.h> -#include <asm/xsave.h> #include <linux/hardirq.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/api.h> #include "sha_mb_ctx.h" #define FLUSH_INTERVAL 1000 /* in usec */ @@ -885,7 +882,8 @@ static int __init sha1_mb_mod_init(void) INIT_DELAYED_WORK(&cpu_state->flush, mcryptd_flusher); cpu_state->cpu = cpu; cpu_state->alg_state = &sha1_mb_alg_state; - cpu_state->mgr = (struct sha1_ctx_mgr *) kzalloc(sizeof(struct sha1_ctx_mgr), GFP_KERNEL); + cpu_state->mgr = kzalloc(sizeof(struct sha1_ctx_mgr), + GFP_KERNEL); if (!cpu_state->mgr) goto err2; sha1_ctx_mgr_init(cpu_state->mgr); diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c index 33d1b9dc1..7c48e8b20 100644 --- a/arch/x86/crypto/sha1_ssse3_glue.c +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -29,9 +29,7 @@ #include <linux/types.h> #include <crypto/sha.h> #include <crypto/sha1_base.h> -#include <asm/i387.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> asmlinkage void sha1_transform_ssse3(u32 *digest, const char *data, @@ -123,15 +121,9 @@ static struct shash_alg alg = { #ifdef CONFIG_AS_AVX static bool __init avx_usable(void) { - u64 xcr0; - - if (!cpu_has_avx || !cpu_has_osxsave) - return false; - - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX detected but unusable.\n"); - + if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) { + if (cpu_has_avx) + pr_info("AVX detected but unusable.\n"); return false; } diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c index ccc338881..f8097fc0d 100644 --- a/arch/x86/crypto/sha256_ssse3_glue.c +++ b/arch/x86/crypto/sha256_ssse3_glue.c @@ -37,9 +37,7 @@ #include <linux/types.h> #include <crypto/sha.h> #include <crypto/sha256_base.h> -#include <asm/i387.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <linux/string.h> asmlinkage void sha256_transform_ssse3(u32 *digest, const char *data, @@ -132,15 +130,9 @@ static struct shash_alg algs[] = { { #ifdef CONFIG_AS_AVX static bool __init avx_usable(void) { - u64 xcr0; - - if (!cpu_has_avx || !cpu_has_osxsave) - return false; - - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX detected but unusable.\n"); - + if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) { + if (cpu_has_avx) + pr_info("AVX detected but unusable.\n"); return false; } diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c index d9fa4c1e0..2edad7b81 100644 --- a/arch/x86/crypto/sha512_ssse3_glue.c +++ b/arch/x86/crypto/sha512_ssse3_glue.c @@ -35,9 +35,7 @@ #include <linux/types.h> #include <crypto/sha.h> #include <crypto/sha512_base.h> -#include <asm/i387.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <linux/string.h> @@ -131,15 +129,9 @@ static struct shash_alg algs[] = { { #ifdef CONFIG_AS_AVX static bool __init avx_usable(void) { - u64 xcr0; - - if (!cpu_has_avx || !cpu_has_osxsave) - return false; - - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX detected but unusable.\n"); - + if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) { + if (cpu_has_avx) + pr_info("AVX detected but unusable.\n"); return false; } diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c index b5e2d5651..c2bd0ce71 100644 --- a/arch/x86/crypto/twofish_avx_glue.c +++ b/arch/x86/crypto/twofish_avx_glue.c @@ -36,9 +36,7 @@ #include <crypto/ctr.h> #include <crypto/lrw.h> #include <crypto/xts.h> -#include <asm/i387.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <asm/crypto/twofish.h> #include <asm/crypto/glue_helper.h> #include <crypto/scatterwalk.h> @@ -558,16 +556,10 @@ static struct crypto_alg twofish_algs[10] = { { static int __init twofish_init(void) { - u64 xcr0; + const char *feature_name; - if (!cpu_has_avx || !cpu_has_osxsave) { - printk(KERN_INFO "AVX instructions are not detected.\n"); - return -ENODEV; - } - - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - printk(KERN_INFO "AVX detected but unusable.\n"); + if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile new file mode 100644 index 000000000..7a144971d --- /dev/null +++ b/arch/x86/entry/Makefile @@ -0,0 +1,10 @@ +# +# Makefile for the x86 low level entry code +# +obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o + +obj-y += vdso/ +obj-y += vsyscall/ + +obj-$(CONFIG_IA32_EMULATION) += entry_64_compat.o syscall_32.o + diff --git a/arch/x86/include/asm/calling.h b/arch/x86/entry/calling.h index 1c8b50edb..f4e6308c4 100644 --- a/arch/x86/include/asm/calling.h +++ b/arch/x86/entry/calling.h @@ -46,8 +46,6 @@ For 32-bit we have the following conventions - kernel is built with */ -#include <asm/dwarf2.h> - #ifdef CONFIG_X86_64 /* @@ -91,28 +89,27 @@ For 32-bit we have the following conventions - kernel is built with #define SIZEOF_PTREGS 21*8 .macro ALLOC_PT_GPREGS_ON_STACK addskip=0 - subq $15*8+\addskip, %rsp - CFI_ADJUST_CFA_OFFSET 15*8+\addskip + addq $-(15*8+\addskip), %rsp .endm .macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8910=1 r11=1 .if \r11 - movq_cfi r11, 6*8+\offset + movq %r11, 6*8+\offset(%rsp) .endif .if \r8910 - movq_cfi r10, 7*8+\offset - movq_cfi r9, 8*8+\offset - movq_cfi r8, 9*8+\offset + movq %r10, 7*8+\offset(%rsp) + movq %r9, 8*8+\offset(%rsp) + movq %r8, 9*8+\offset(%rsp) .endif .if \rax - movq_cfi rax, 10*8+\offset + movq %rax, 10*8+\offset(%rsp) .endif .if \rcx - movq_cfi rcx, 11*8+\offset + movq %rcx, 11*8+\offset(%rsp) .endif - movq_cfi rdx, 12*8+\offset - movq_cfi rsi, 13*8+\offset - movq_cfi rdi, 14*8+\offset + movq %rdx, 12*8+\offset(%rsp) + movq %rsi, 13*8+\offset(%rsp) + movq %rdi, 14*8+\offset(%rsp) .endm .macro SAVE_C_REGS offset=0 SAVE_C_REGS_HELPER \offset, 1, 1, 1, 1 @@ -131,24 +128,24 @@ For 32-bit we have the following conventions - kernel is built with .endm .macro SAVE_EXTRA_REGS offset=0 - movq_cfi r15, 0*8+\offset - movq_cfi r14, 1*8+\offset - movq_cfi r13, 2*8+\offset - movq_cfi r12, 3*8+\offset - movq_cfi rbp, 4*8+\offset - movq_cfi rbx, 5*8+\offset + movq %r15, 0*8+\offset(%rsp) + movq %r14, 1*8+\offset(%rsp) + movq %r13, 2*8+\offset(%rsp) + movq %r12, 3*8+\offset(%rsp) + movq %rbp, 4*8+\offset(%rsp) + movq %rbx, 5*8+\offset(%rsp) .endm .macro SAVE_EXTRA_REGS_RBP offset=0 - movq_cfi rbp, 4*8+\offset + movq %rbp, 4*8+\offset(%rsp) .endm .macro RESTORE_EXTRA_REGS offset=0 - movq_cfi_restore 0*8+\offset, r15 - movq_cfi_restore 1*8+\offset, r14 - movq_cfi_restore 2*8+\offset, r13 - movq_cfi_restore 3*8+\offset, r12 - movq_cfi_restore 4*8+\offset, rbp - movq_cfi_restore 5*8+\offset, rbx + movq 0*8+\offset(%rsp), %r15 + movq 1*8+\offset(%rsp), %r14 + movq 2*8+\offset(%rsp), %r13 + movq 3*8+\offset(%rsp), %r12 + movq 4*8+\offset(%rsp), %rbp + movq 5*8+\offset(%rsp), %rbx .endm .macro ZERO_EXTRA_REGS @@ -162,24 +159,24 @@ For 32-bit we have the following conventions - kernel is built with .macro RESTORE_C_REGS_HELPER rstor_rax=1, rstor_rcx=1, rstor_r11=1, rstor_r8910=1, rstor_rdx=1 .if \rstor_r11 - movq_cfi_restore 6*8, r11 + movq 6*8(%rsp), %r11 .endif .if \rstor_r8910 - movq_cfi_restore 7*8, r10 - movq_cfi_restore 8*8, r9 - movq_cfi_restore 9*8, r8 + movq 7*8(%rsp), %r10 + movq 8*8(%rsp), %r9 + movq 9*8(%rsp), %r8 .endif .if \rstor_rax - movq_cfi_restore 10*8, rax + movq 10*8(%rsp), %rax .endif .if \rstor_rcx - movq_cfi_restore 11*8, rcx + movq 11*8(%rsp), %rcx .endif .if \rstor_rdx - movq_cfi_restore 12*8, rdx + movq 12*8(%rsp), %rdx .endif - movq_cfi_restore 13*8, rsi - movq_cfi_restore 14*8, rdi + movq 13*8(%rsp), %rsi + movq 14*8(%rsp), %rdi .endm .macro RESTORE_C_REGS RESTORE_C_REGS_HELPER 1,1,1,1,1 @@ -204,8 +201,7 @@ For 32-bit we have the following conventions - kernel is built with .endm .macro REMOVE_PT_GPREGS_FROM_STACK addskip=0 - addq $15*8+\addskip, %rsp - CFI_ADJUST_CFA_OFFSET -(15*8+\addskip) + subq $-(15*8+\addskip), %rsp .endm .macro icebp @@ -224,23 +220,23 @@ For 32-bit we have the following conventions - kernel is built with */ .macro SAVE_ALL - pushl_cfi_reg eax - pushl_cfi_reg ebp - pushl_cfi_reg edi - pushl_cfi_reg esi - pushl_cfi_reg edx - pushl_cfi_reg ecx - pushl_cfi_reg ebx + pushl %eax + pushl %ebp + pushl %edi + pushl %esi + pushl %edx + pushl %ecx + pushl %ebx .endm .macro RESTORE_ALL - popl_cfi_reg ebx - popl_cfi_reg ecx - popl_cfi_reg edx - popl_cfi_reg esi - popl_cfi_reg edi - popl_cfi_reg ebp - popl_cfi_reg eax + popl %ebx + popl %ecx + popl %edx + popl %esi + popl %edi + popl %ebp + popl %eax .endm #endif /* CONFIG_X86_64 */ diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S new file mode 100644 index 000000000..21dc60a60 --- /dev/null +++ b/arch/x86/entry/entry_32.S @@ -0,0 +1,1248 @@ +/* + * Copyright (C) 1991,1992 Linus Torvalds + * + * entry_32.S contains the system-call and low-level fault and trap handling routines. + * + * Stack layout in 'syscall_exit': + * ptrace needs to have all registers on the stack. + * If the order here is changed, it needs to be + * updated in fork.c:copy_process(), signal.c:do_signal(), + * ptrace.c and ptrace.h + * + * 0(%esp) - %ebx + * 4(%esp) - %ecx + * 8(%esp) - %edx + * C(%esp) - %esi + * 10(%esp) - %edi + * 14(%esp) - %ebp + * 18(%esp) - %eax + * 1C(%esp) - %ds + * 20(%esp) - %es + * 24(%esp) - %fs + * 28(%esp) - %gs saved iff !CONFIG_X86_32_LAZY_GS + * 2C(%esp) - orig_eax + * 30(%esp) - %eip + * 34(%esp) - %cs + * 38(%esp) - %eflags + * 3C(%esp) - %oldesp + * 40(%esp) - %oldss + */ + +#include <linux/linkage.h> +#include <linux/err.h> +#include <asm/thread_info.h> +#include <asm/irqflags.h> +#include <asm/errno.h> +#include <asm/segment.h> +#include <asm/smp.h> +#include <asm/page_types.h> +#include <asm/percpu.h> +#include <asm/processor-flags.h> +#include <asm/ftrace.h> +#include <asm/irq_vectors.h> +#include <asm/cpufeature.h> +#include <asm/alternative-asm.h> +#include <asm/asm.h> +#include <asm/smap.h> + +/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ +#include <linux/elf-em.h> +#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE) +#define __AUDIT_ARCH_LE 0x40000000 + +#ifndef CONFIG_AUDITSYSCALL +# define sysenter_audit syscall_trace_entry +# define sysexit_audit syscall_exit_work +#endif + + .section .entry.text, "ax" + +/* + * We use macros for low-level operations which need to be overridden + * for paravirtualization. The following will never clobber any registers: + * INTERRUPT_RETURN (aka. "iret") + * GET_CR0_INTO_EAX (aka. "movl %cr0, %eax") + * ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit"). + * + * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must + * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY). + * Allowing a register to be clobbered can shrink the paravirt replacement + * enough to patch inline, increasing performance. + */ + +#ifdef CONFIG_PREEMPT +# define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF +#else +# define preempt_stop(clobbers) +# define resume_kernel restore_all +#endif + +.macro TRACE_IRQS_IRET +#ifdef CONFIG_TRACE_IRQFLAGS + testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off? + jz 1f + TRACE_IRQS_ON +1: +#endif +.endm + +/* + * User gs save/restore + * + * %gs is used for userland TLS and kernel only uses it for stack + * canary which is required to be at %gs:20 by gcc. Read the comment + * at the top of stackprotector.h for more info. + * + * Local labels 98 and 99 are used. + */ +#ifdef CONFIG_X86_32_LAZY_GS + + /* unfortunately push/pop can't be no-op */ +.macro PUSH_GS + pushl $0 +.endm +.macro POP_GS pop=0 + addl $(4 + \pop), %esp +.endm +.macro POP_GS_EX +.endm + + /* all the rest are no-op */ +.macro PTGS_TO_GS +.endm +.macro PTGS_TO_GS_EX +.endm +.macro GS_TO_REG reg +.endm +.macro REG_TO_PTGS reg +.endm +.macro SET_KERNEL_GS reg +.endm + +#else /* CONFIG_X86_32_LAZY_GS */ + +.macro PUSH_GS + pushl %gs +.endm + +.macro POP_GS pop=0 +98: popl %gs + .if \pop <> 0 + add $\pop, %esp + .endif +.endm +.macro POP_GS_EX +.pushsection .fixup, "ax" +99: movl $0, (%esp) + jmp 98b +.popsection + _ASM_EXTABLE(98b, 99b) +.endm + +.macro PTGS_TO_GS +98: mov PT_GS(%esp), %gs +.endm +.macro PTGS_TO_GS_EX +.pushsection .fixup, "ax" +99: movl $0, PT_GS(%esp) + jmp 98b +.popsection + _ASM_EXTABLE(98b, 99b) +.endm + +.macro GS_TO_REG reg + movl %gs, \reg +.endm +.macro REG_TO_PTGS reg + movl \reg, PT_GS(%esp) +.endm +.macro SET_KERNEL_GS reg + movl $(__KERNEL_STACK_CANARY), \reg + movl \reg, %gs +.endm + +#endif /* CONFIG_X86_32_LAZY_GS */ + +.macro SAVE_ALL + cld + PUSH_GS + pushl %fs + pushl %es + pushl %ds + pushl %eax + pushl %ebp + pushl %edi + pushl %esi + pushl %edx + pushl %ecx + pushl %ebx + movl $(__USER_DS), %edx + movl %edx, %ds + movl %edx, %es + movl $(__KERNEL_PERCPU), %edx + movl %edx, %fs + SET_KERNEL_GS %edx +.endm + +.macro RESTORE_INT_REGS + popl %ebx + popl %ecx + popl %edx + popl %esi + popl %edi + popl %ebp + popl %eax +.endm + +.macro RESTORE_REGS pop=0 + RESTORE_INT_REGS +1: popl %ds +2: popl %es +3: popl %fs + POP_GS \pop +.pushsection .fixup, "ax" +4: movl $0, (%esp) + jmp 1b +5: movl $0, (%esp) + jmp 2b +6: movl $0, (%esp) + jmp 3b +.popsection + _ASM_EXTABLE(1b, 4b) + _ASM_EXTABLE(2b, 5b) + _ASM_EXTABLE(3b, 6b) + POP_GS_EX +.endm + +ENTRY(ret_from_fork) + pushl %eax + call schedule_tail + GET_THREAD_INFO(%ebp) + popl %eax + pushl $0x0202 # Reset kernel eflags + popfl + jmp syscall_exit +END(ret_from_fork) + +ENTRY(ret_from_kernel_thread) + pushl %eax + call schedule_tail + GET_THREAD_INFO(%ebp) + popl %eax + pushl $0x0202 # Reset kernel eflags + popfl + movl PT_EBP(%esp), %eax + call *PT_EBX(%esp) + movl $0, PT_EAX(%esp) + jmp syscall_exit +ENDPROC(ret_from_kernel_thread) + +/* + * Return to user mode is not as complex as all this looks, + * but we want the default path for a system call return to + * go as quickly as possible which is why some of this is + * less clear than it otherwise should be. + */ + + # userspace resumption stub bypassing syscall exit tracing + ALIGN +ret_from_exception: + preempt_stop(CLBR_ANY) +ret_from_intr: + GET_THREAD_INFO(%ebp) +#ifdef CONFIG_VM86 + movl PT_EFLAGS(%esp), %eax # mix EFLAGS and CS + movb PT_CS(%esp), %al + andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax +#else + /* + * We can be coming here from child spawned by kernel_thread(). + */ + movl PT_CS(%esp), %eax + andl $SEGMENT_RPL_MASK, %eax +#endif + cmpl $USER_RPL, %eax + jb resume_kernel # not returning to v8086 or userspace + +ENTRY(resume_userspace) + LOCKDEP_SYS_EXIT + DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt + # setting need_resched or sigpending + # between sampling and the iret + TRACE_IRQS_OFF + movl TI_flags(%ebp), %ecx + andl $_TIF_WORK_MASK, %ecx # is there any work to be done on + # int/exception return? + jne work_pending + jmp restore_all +END(ret_from_exception) + +#ifdef CONFIG_PREEMPT +ENTRY(resume_kernel) + DISABLE_INTERRUPTS(CLBR_ANY) +need_resched: + cmpl $0, PER_CPU_VAR(__preempt_count) + jnz restore_all + testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off (exception path) ? + jz restore_all + call preempt_schedule_irq + jmp need_resched +END(resume_kernel) +#endif + +/* + * SYSENTER_RETURN points to after the SYSENTER instruction + * in the vsyscall page. See vsyscall-sysentry.S, which defines + * the symbol. + */ + + # SYSENTER call handler stub +ENTRY(entry_SYSENTER_32) + movl TSS_sysenter_sp0(%esp), %esp +sysenter_past_esp: + /* + * Interrupts are disabled here, but we can't trace it until + * enough kernel state to call TRACE_IRQS_OFF can be called - but + * we immediately enable interrupts at that point anyway. + */ + pushl $__USER_DS + pushl %ebp + pushfl + orl $X86_EFLAGS_IF, (%esp) + pushl $__USER_CS + /* + * Push current_thread_info()->sysenter_return to the stack. + * A tiny bit of offset fixup is necessary: TI_sysenter_return + * is relative to thread_info, which is at the bottom of the + * kernel stack page. 4*4 means the 4 words pushed above; + * TOP_OF_KERNEL_STACK_PADDING takes us to the top of the stack; + * and THREAD_SIZE takes us to the bottom. + */ + pushl ((TI_sysenter_return) - THREAD_SIZE + TOP_OF_KERNEL_STACK_PADDING + 4*4)(%esp) + + pushl %eax + SAVE_ALL + ENABLE_INTERRUPTS(CLBR_NONE) + +/* + * Load the potential sixth argument from user stack. + * Careful about security. + */ + cmpl $__PAGE_OFFSET-3, %ebp + jae syscall_fault + ASM_STAC +1: movl (%ebp), %ebp + ASM_CLAC + movl %ebp, PT_EBP(%esp) + _ASM_EXTABLE(1b, syscall_fault) + + GET_THREAD_INFO(%ebp) + + testl $_TIF_WORK_SYSCALL_ENTRY, TI_flags(%ebp) + jnz sysenter_audit +sysenter_do_call: + cmpl $(NR_syscalls), %eax + jae sysenter_badsys + call *sys_call_table(, %eax, 4) +sysenter_after_call: + movl %eax, PT_EAX(%esp) + LOCKDEP_SYS_EXIT + DISABLE_INTERRUPTS(CLBR_ANY) + TRACE_IRQS_OFF + movl TI_flags(%ebp), %ecx + testl $_TIF_ALLWORK_MASK, %ecx + jnz sysexit_audit +sysenter_exit: +/* if something modifies registers it must also disable sysexit */ + movl PT_EIP(%esp), %edx + movl PT_OLDESP(%esp), %ecx + xorl %ebp, %ebp + TRACE_IRQS_ON +1: mov PT_FS(%esp), %fs + PTGS_TO_GS + ENABLE_INTERRUPTS_SYSEXIT + +#ifdef CONFIG_AUDITSYSCALL +sysenter_audit: + testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), TI_flags(%ebp) + jnz syscall_trace_entry + /* movl PT_EAX(%esp), %eax already set, syscall number: 1st arg to audit */ + movl PT_EBX(%esp), %edx /* ebx/a0: 2nd arg to audit */ + /* movl PT_ECX(%esp), %ecx already set, a1: 3nd arg to audit */ + pushl PT_ESI(%esp) /* a3: 5th arg */ + pushl PT_EDX+4(%esp) /* a2: 4th arg */ + call __audit_syscall_entry + popl %ecx /* get that remapped edx off the stack */ + popl %ecx /* get that remapped esi off the stack */ + movl PT_EAX(%esp), %eax /* reload syscall number */ + jmp sysenter_do_call + +sysexit_audit: + testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx + jnz syscall_exit_work + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_ANY) + movl %eax, %edx /* second arg, syscall return value */ + cmpl $-MAX_ERRNO, %eax /* is it an error ? */ + setbe %al /* 1 if so, 0 if not */ + movzbl %al, %eax /* zero-extend that */ + call __audit_syscall_exit + DISABLE_INTERRUPTS(CLBR_ANY) + TRACE_IRQS_OFF + movl TI_flags(%ebp), %ecx + testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx + jnz syscall_exit_work + movl PT_EAX(%esp), %eax /* reload syscall return value */ + jmp sysenter_exit +#endif + +.pushsection .fixup, "ax" +2: movl $0, PT_FS(%esp) + jmp 1b +.popsection + _ASM_EXTABLE(1b, 2b) + PTGS_TO_GS_EX +ENDPROC(entry_SYSENTER_32) + + # system call handler stub +ENTRY(entry_INT80_32) + ASM_CLAC + pushl %eax # save orig_eax + SAVE_ALL + GET_THREAD_INFO(%ebp) + # system call tracing in operation / emulation + testl $_TIF_WORK_SYSCALL_ENTRY, TI_flags(%ebp) + jnz syscall_trace_entry + cmpl $(NR_syscalls), %eax + jae syscall_badsys +syscall_call: + call *sys_call_table(, %eax, 4) +syscall_after_call: + movl %eax, PT_EAX(%esp) # store the return value +syscall_exit: + LOCKDEP_SYS_EXIT + DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt + # setting need_resched or sigpending + # between sampling and the iret + TRACE_IRQS_OFF + movl TI_flags(%ebp), %ecx + testl $_TIF_ALLWORK_MASK, %ecx # current->work + jnz syscall_exit_work + +restore_all: + TRACE_IRQS_IRET +restore_all_notrace: +#ifdef CONFIG_X86_ESPFIX32 + movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS + /* + * Warning: PT_OLDSS(%esp) contains the wrong/random values if we + * are returning to the kernel. + * See comments in process.c:copy_thread() for details. + */ + movb PT_OLDSS(%esp), %ah + movb PT_CS(%esp), %al + andl $(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax + cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax + je ldt_ss # returning to user-space with LDT SS +#endif +restore_nocheck: + RESTORE_REGS 4 # skip orig_eax/error_code +irq_return: + INTERRUPT_RETURN +.section .fixup, "ax" +ENTRY(iret_exc ) + pushl $0 # no error code + pushl $do_iret_error + jmp error_code +.previous + _ASM_EXTABLE(irq_return, iret_exc) + +#ifdef CONFIG_X86_ESPFIX32 +ldt_ss: +#ifdef CONFIG_PARAVIRT + /* + * The kernel can't run on a non-flat stack if paravirt mode + * is active. Rather than try to fixup the high bits of + * ESP, bypass this code entirely. This may break DOSemu + * and/or Wine support in a paravirt VM, although the option + * is still available to implement the setting of the high + * 16-bits in the INTERRUPT_RETURN paravirt-op. + */ + cmpl $0, pv_info+PARAVIRT_enabled + jne restore_nocheck +#endif + +/* + * Setup and switch to ESPFIX stack + * + * We're returning to userspace with a 16 bit stack. The CPU will not + * restore the high word of ESP for us on executing iret... This is an + * "official" bug of all the x86-compatible CPUs, which we can work + * around to make dosemu and wine happy. We do this by preloading the + * high word of ESP with the high word of the userspace ESP while + * compensating for the offset by changing to the ESPFIX segment with + * a base address that matches for the difference. + */ +#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8) + mov %esp, %edx /* load kernel esp */ + mov PT_OLDESP(%esp), %eax /* load userspace esp */ + mov %dx, %ax /* eax: new kernel esp */ + sub %eax, %edx /* offset (low word is 0) */ + shr $16, %edx + mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */ + mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */ + pushl $__ESPFIX_SS + pushl %eax /* new kernel esp */ + /* + * Disable interrupts, but do not irqtrace this section: we + * will soon execute iret and the tracer was already set to + * the irqstate after the IRET: + */ + DISABLE_INTERRUPTS(CLBR_EAX) + lss (%esp), %esp /* switch to espfix segment */ + jmp restore_nocheck +#endif +ENDPROC(entry_INT80_32) + + # perform work that needs to be done immediately before resumption + ALIGN +work_pending: + testb $_TIF_NEED_RESCHED, %cl + jz work_notifysig +work_resched: + call schedule + LOCKDEP_SYS_EXIT + DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt + # setting need_resched or sigpending + # between sampling and the iret + TRACE_IRQS_OFF + movl TI_flags(%ebp), %ecx + andl $_TIF_WORK_MASK, %ecx # is there any work to be done other + # than syscall tracing? + jz restore_all + testb $_TIF_NEED_RESCHED, %cl + jnz work_resched + +work_notifysig: # deal with pending signals and + # notify-resume requests +#ifdef CONFIG_VM86 + testl $X86_EFLAGS_VM, PT_EFLAGS(%esp) + movl %esp, %eax + jnz work_notifysig_v86 # returning to kernel-space or + # vm86-space +1: +#else + movl %esp, %eax +#endif + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_NONE) + movb PT_CS(%esp), %bl + andb $SEGMENT_RPL_MASK, %bl + cmpb $USER_RPL, %bl + jb resume_kernel + xorl %edx, %edx + call do_notify_resume + jmp resume_userspace + +#ifdef CONFIG_VM86 + ALIGN +work_notifysig_v86: + pushl %ecx # save ti_flags for do_notify_resume + call save_v86_state # %eax contains pt_regs pointer + popl %ecx + movl %eax, %esp + jmp 1b +#endif +END(work_pending) + + # perform syscall exit tracing + ALIGN +syscall_trace_entry: + movl $-ENOSYS, PT_EAX(%esp) + movl %esp, %eax + call syscall_trace_enter + /* What it returned is what we'll actually use. */ + cmpl $(NR_syscalls), %eax + jnae syscall_call + jmp syscall_exit +END(syscall_trace_entry) + + # perform syscall exit tracing + ALIGN +syscall_exit_work: + testl $_TIF_WORK_SYSCALL_EXIT, %ecx + jz work_pending + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_ANY) # could let syscall_trace_leave() call + # schedule() instead + movl %esp, %eax + call syscall_trace_leave + jmp resume_userspace +END(syscall_exit_work) + +syscall_fault: + ASM_CLAC + GET_THREAD_INFO(%ebp) + movl $-EFAULT, PT_EAX(%esp) + jmp resume_userspace +END(syscall_fault) + +syscall_badsys: + movl $-ENOSYS, %eax + jmp syscall_after_call +END(syscall_badsys) + +sysenter_badsys: + movl $-ENOSYS, %eax + jmp sysenter_after_call +END(sysenter_badsys) + +.macro FIXUP_ESPFIX_STACK +/* + * Switch back for ESPFIX stack to the normal zerobased stack + * + * We can't call C functions using the ESPFIX stack. This code reads + * the high word of the segment base from the GDT and swiches to the + * normal stack and adjusts ESP with the matching offset. + */ +#ifdef CONFIG_X86_ESPFIX32 + /* fixup the stack */ + mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */ + mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */ + shl $16, %eax + addl %esp, %eax /* the adjusted stack pointer */ + pushl $__KERNEL_DS + pushl %eax + lss (%esp), %esp /* switch to the normal stack segment */ +#endif +.endm +.macro UNWIND_ESPFIX_STACK +#ifdef CONFIG_X86_ESPFIX32 + movl %ss, %eax + /* see if on espfix stack */ + cmpw $__ESPFIX_SS, %ax + jne 27f + movl $__KERNEL_DS, %eax + movl %eax, %ds + movl %eax, %es + /* switch to normal stack */ + FIXUP_ESPFIX_STACK +27: +#endif +.endm + +/* + * Build the entry stubs with some assembler magic. + * We pack 1 stub into every 8-byte block. + */ + .align 8 +ENTRY(irq_entries_start) + vector=FIRST_EXTERNAL_VECTOR + .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR) + pushl $(~vector+0x80) /* Note: always in signed byte range */ + vector=vector+1 + jmp common_interrupt + .align 8 + .endr +END(irq_entries_start) + +/* + * the CPU automatically disables interrupts when executing an IRQ vector, + * so IRQ-flags tracing has to follow that: + */ + .p2align CONFIG_X86_L1_CACHE_SHIFT +common_interrupt: + ASM_CLAC + addl $-0x80, (%esp) /* Adjust vector into the [-256, -1] range */ + SAVE_ALL + TRACE_IRQS_OFF + movl %esp, %eax + call do_IRQ + jmp ret_from_intr +ENDPROC(common_interrupt) + +#define BUILD_INTERRUPT3(name, nr, fn) \ +ENTRY(name) \ + ASM_CLAC; \ + pushl $~(nr); \ + SAVE_ALL; \ + TRACE_IRQS_OFF \ + movl %esp, %eax; \ + call fn; \ + jmp ret_from_intr; \ +ENDPROC(name) + + +#ifdef CONFIG_TRACING +# define TRACE_BUILD_INTERRUPT(name, nr) BUILD_INTERRUPT3(trace_##name, nr, smp_trace_##name) +#else +# define TRACE_BUILD_INTERRUPT(name, nr) +#endif + +#define BUILD_INTERRUPT(name, nr) \ + BUILD_INTERRUPT3(name, nr, smp_##name); \ + TRACE_BUILD_INTERRUPT(name, nr) + +/* The include is where all of the SMP etc. interrupts come from */ +#include <asm/entry_arch.h> + +ENTRY(coprocessor_error) + ASM_CLAC + pushl $0 + pushl $do_coprocessor_error + jmp error_code +END(coprocessor_error) + +ENTRY(simd_coprocessor_error) + ASM_CLAC + pushl $0 +#ifdef CONFIG_X86_INVD_BUG + /* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */ + ALTERNATIVE "pushl $do_general_protection", \ + "pushl $do_simd_coprocessor_error", \ + X86_FEATURE_XMM +#else + pushl $do_simd_coprocessor_error +#endif + jmp error_code +END(simd_coprocessor_error) + +ENTRY(device_not_available) + ASM_CLAC + pushl $-1 # mark this as an int + pushl $do_device_not_available + jmp error_code +END(device_not_available) + +#ifdef CONFIG_PARAVIRT +ENTRY(native_iret) + iret + _ASM_EXTABLE(native_iret, iret_exc) +END(native_iret) + +ENTRY(native_irq_enable_sysexit) + sti + sysexit +END(native_irq_enable_sysexit) +#endif + +ENTRY(overflow) + ASM_CLAC + pushl $0 + pushl $do_overflow + jmp error_code +END(overflow) + +ENTRY(bounds) + ASM_CLAC + pushl $0 + pushl $do_bounds + jmp error_code +END(bounds) + +ENTRY(invalid_op) + ASM_CLAC + pushl $0 + pushl $do_invalid_op + jmp error_code +END(invalid_op) + +ENTRY(coprocessor_segment_overrun) + ASM_CLAC + pushl $0 + pushl $do_coprocessor_segment_overrun + jmp error_code +END(coprocessor_segment_overrun) + +ENTRY(invalid_TSS) + ASM_CLAC + pushl $do_invalid_TSS + jmp error_code +END(invalid_TSS) + +ENTRY(segment_not_present) + ASM_CLAC + pushl $do_segment_not_present + jmp error_code +END(segment_not_present) + +ENTRY(stack_segment) + ASM_CLAC + pushl $do_stack_segment + jmp error_code +END(stack_segment) + +ENTRY(alignment_check) + ASM_CLAC + pushl $do_alignment_check + jmp error_code +END(alignment_check) + +ENTRY(divide_error) + ASM_CLAC + pushl $0 # no error code + pushl $do_divide_error + jmp error_code +END(divide_error) + +#ifdef CONFIG_X86_MCE +ENTRY(machine_check) + ASM_CLAC + pushl $0 + pushl machine_check_vector + jmp error_code +END(machine_check) +#endif + +ENTRY(spurious_interrupt_bug) + ASM_CLAC + pushl $0 + pushl $do_spurious_interrupt_bug + jmp error_code +END(spurious_interrupt_bug) + +#ifdef CONFIG_XEN +/* + * Xen doesn't set %esp to be precisely what the normal SYSENTER + * entry point expects, so fix it up before using the normal path. + */ +ENTRY(xen_sysenter_target) + addl $5*4, %esp /* remove xen-provided frame */ + jmp sysenter_past_esp + +ENTRY(xen_hypervisor_callback) + pushl $-1 /* orig_ax = -1 => not a system call */ + SAVE_ALL + TRACE_IRQS_OFF + + /* + * Check to see if we got the event in the critical + * region in xen_iret_direct, after we've reenabled + * events and checked for pending events. This simulates + * iret instruction's behaviour where it delivers a + * pending interrupt when enabling interrupts: + */ + movl PT_EIP(%esp), %eax + cmpl $xen_iret_start_crit, %eax + jb 1f + cmpl $xen_iret_end_crit, %eax + jae 1f + + jmp xen_iret_crit_fixup + +ENTRY(xen_do_upcall) +1: mov %esp, %eax + call xen_evtchn_do_upcall +#ifndef CONFIG_PREEMPT + call xen_maybe_preempt_hcall +#endif + jmp ret_from_intr +ENDPROC(xen_hypervisor_callback) + +/* + * Hypervisor uses this for application faults while it executes. + * We get here for two reasons: + * 1. Fault while reloading DS, ES, FS or GS + * 2. Fault while executing IRET + * Category 1 we fix up by reattempting the load, and zeroing the segment + * register if the load fails. + * Category 2 we fix up by jumping to do_iret_error. We cannot use the + * normal Linux return path in this case because if we use the IRET hypercall + * to pop the stack frame we end up in an infinite loop of failsafe callbacks. + * We distinguish between categories by maintaining a status value in EAX. + */ +ENTRY(xen_failsafe_callback) + pushl %eax + movl $1, %eax +1: mov 4(%esp), %ds +2: mov 8(%esp), %es +3: mov 12(%esp), %fs +4: mov 16(%esp), %gs + /* EAX == 0 => Category 1 (Bad segment) + EAX != 0 => Category 2 (Bad IRET) */ + testl %eax, %eax + popl %eax + lea 16(%esp), %esp + jz 5f + jmp iret_exc +5: pushl $-1 /* orig_ax = -1 => not a system call */ + SAVE_ALL + jmp ret_from_exception + +.section .fixup, "ax" +6: xorl %eax, %eax + movl %eax, 4(%esp) + jmp 1b +7: xorl %eax, %eax + movl %eax, 8(%esp) + jmp 2b +8: xorl %eax, %eax + movl %eax, 12(%esp) + jmp 3b +9: xorl %eax, %eax + movl %eax, 16(%esp) + jmp 4b +.previous + _ASM_EXTABLE(1b, 6b) + _ASM_EXTABLE(2b, 7b) + _ASM_EXTABLE(3b, 8b) + _ASM_EXTABLE(4b, 9b) +ENDPROC(xen_failsafe_callback) + +BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR, + xen_evtchn_do_upcall) + +#endif /* CONFIG_XEN */ + +#if IS_ENABLED(CONFIG_HYPERV) + +BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR, + hyperv_vector_handler) + +#endif /* CONFIG_HYPERV */ + +#ifdef CONFIG_FUNCTION_TRACER +#ifdef CONFIG_DYNAMIC_FTRACE + +ENTRY(mcount) + ret +END(mcount) + +ENTRY(ftrace_caller) + pushl %eax + pushl %ecx + pushl %edx + pushl $0 /* Pass NULL as regs pointer */ + movl 4*4(%esp), %eax + movl 0x4(%ebp), %edx + movl function_trace_op, %ecx + subl $MCOUNT_INSN_SIZE, %eax + +.globl ftrace_call +ftrace_call: + call ftrace_stub + + addl $4, %esp /* skip NULL pointer */ + popl %edx + popl %ecx + popl %eax +ftrace_ret: +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +.globl ftrace_graph_call +ftrace_graph_call: + jmp ftrace_stub +#endif + +.globl ftrace_stub +ftrace_stub: + ret +END(ftrace_caller) + +ENTRY(ftrace_regs_caller) + pushf /* push flags before compare (in cs location) */ + + /* + * i386 does not save SS and ESP when coming from kernel. + * Instead, to get sp, ®s->sp is used (see ptrace.h). + * Unfortunately, that means eflags must be at the same location + * as the current return ip is. We move the return ip into the + * ip location, and move flags into the return ip location. + */ + pushl 4(%esp) /* save return ip into ip slot */ + + pushl $0 /* Load 0 into orig_ax */ + pushl %gs + pushl %fs + pushl %es + pushl %ds + pushl %eax + pushl %ebp + pushl %edi + pushl %esi + pushl %edx + pushl %ecx + pushl %ebx + + movl 13*4(%esp), %eax /* Get the saved flags */ + movl %eax, 14*4(%esp) /* Move saved flags into regs->flags location */ + /* clobbering return ip */ + movl $__KERNEL_CS, 13*4(%esp) + + movl 12*4(%esp), %eax /* Load ip (1st parameter) */ + subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */ + movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */ + movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */ + pushl %esp /* Save pt_regs as 4th parameter */ + +GLOBAL(ftrace_regs_call) + call ftrace_stub + + addl $4, %esp /* Skip pt_regs */ + movl 14*4(%esp), %eax /* Move flags back into cs */ + movl %eax, 13*4(%esp) /* Needed to keep addl from modifying flags */ + movl 12*4(%esp), %eax /* Get return ip from regs->ip */ + movl %eax, 14*4(%esp) /* Put return ip back for ret */ + + popl %ebx + popl %ecx + popl %edx + popl %esi + popl %edi + popl %ebp + popl %eax + popl %ds + popl %es + popl %fs + popl %gs + addl $8, %esp /* Skip orig_ax and ip */ + popf /* Pop flags at end (no addl to corrupt flags) */ + jmp ftrace_ret + + popf + jmp ftrace_stub +#else /* ! CONFIG_DYNAMIC_FTRACE */ + +ENTRY(mcount) + cmpl $__PAGE_OFFSET, %esp + jb ftrace_stub /* Paging not enabled yet? */ + + cmpl $ftrace_stub, ftrace_trace_function + jnz trace +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + cmpl $ftrace_stub, ftrace_graph_return + jnz ftrace_graph_caller + + cmpl $ftrace_graph_entry_stub, ftrace_graph_entry + jnz ftrace_graph_caller +#endif +.globl ftrace_stub +ftrace_stub: + ret + + /* taken from glibc */ +trace: + pushl %eax + pushl %ecx + pushl %edx + movl 0xc(%esp), %eax + movl 0x4(%ebp), %edx + subl $MCOUNT_INSN_SIZE, %eax + + call *ftrace_trace_function + + popl %edx + popl %ecx + popl %eax + jmp ftrace_stub +END(mcount) +#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_FUNCTION_TRACER */ + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +ENTRY(ftrace_graph_caller) + pushl %eax + pushl %ecx + pushl %edx + movl 0xc(%esp), %eax + lea 0x4(%ebp), %edx + movl (%ebp), %ecx + subl $MCOUNT_INSN_SIZE, %eax + call prepare_ftrace_return + popl %edx + popl %ecx + popl %eax + ret +END(ftrace_graph_caller) + +.globl return_to_handler +return_to_handler: + pushl %eax + pushl %edx + movl %ebp, %eax + call ftrace_return_to_handler + movl %eax, %ecx + popl %edx + popl %eax + jmp *%ecx +#endif + +#ifdef CONFIG_TRACING +ENTRY(trace_page_fault) + ASM_CLAC + pushl $trace_do_page_fault + jmp error_code +END(trace_page_fault) +#endif + +ENTRY(page_fault) + ASM_CLAC + pushl $do_page_fault + ALIGN +error_code: + /* the function address is in %gs's slot on the stack */ + pushl %fs + pushl %es + pushl %ds + pushl %eax + pushl %ebp + pushl %edi + pushl %esi + pushl %edx + pushl %ecx + pushl %ebx + cld + movl $(__KERNEL_PERCPU), %ecx + movl %ecx, %fs + UNWIND_ESPFIX_STACK + GS_TO_REG %ecx + movl PT_GS(%esp), %edi # get the function address + movl PT_ORIG_EAX(%esp), %edx # get the error code + movl $-1, PT_ORIG_EAX(%esp) # no syscall to restart + REG_TO_PTGS %ecx + SET_KERNEL_GS %ecx + movl $(__USER_DS), %ecx + movl %ecx, %ds + movl %ecx, %es + TRACE_IRQS_OFF + movl %esp, %eax # pt_regs pointer + call *%edi + jmp ret_from_exception +END(page_fault) + +/* + * Debug traps and NMI can happen at the one SYSENTER instruction + * that sets up the real kernel stack. Check here, since we can't + * allow the wrong stack to be used. + * + * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have + * already pushed 3 words if it hits on the sysenter instruction: + * eflags, cs and eip. + * + * We just load the right stack, and push the three (known) values + * by hand onto the new stack - while updating the return eip past + * the instruction that would have done it for sysenter. + */ +.macro FIX_STACK offset ok label + cmpw $__KERNEL_CS, 4(%esp) + jne \ok +\label: + movl TSS_sysenter_sp0 + \offset(%esp), %esp + pushfl + pushl $__KERNEL_CS + pushl $sysenter_past_esp +.endm + +ENTRY(debug) + ASM_CLAC + cmpl $entry_SYSENTER_32, (%esp) + jne debug_stack_correct + FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn +debug_stack_correct: + pushl $-1 # mark this as an int + SAVE_ALL + TRACE_IRQS_OFF + xorl %edx, %edx # error code 0 + movl %esp, %eax # pt_regs pointer + call do_debug + jmp ret_from_exception +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 + * clear up the stack. So we first check whether we got an + * NMI on the sysenter entry path, but after that we need to + * check whether we got an NMI on the debug path where the debug + * fault happened on the sysenter path. + */ +ENTRY(nmi) + ASM_CLAC +#ifdef CONFIG_X86_ESPFIX32 + pushl %eax + movl %ss, %eax + cmpw $__ESPFIX_SS, %ax + popl %eax + je nmi_espfix_stack +#endif + cmpl $entry_SYSENTER_32, (%esp) + je nmi_stack_fixup + pushl %eax + movl %esp, %eax + /* + * Do not access memory above the end of our stack page, + * it might not exist. + */ + andl $(THREAD_SIZE-1), %eax + cmpl $(THREAD_SIZE-20), %eax + popl %eax + jae nmi_stack_correct + cmpl $entry_SYSENTER_32, 12(%esp) + je nmi_debug_stack_check +nmi_stack_correct: + pushl %eax + SAVE_ALL + xorl %edx, %edx # zero error code + movl %esp, %eax # pt_regs pointer + call do_nmi + jmp restore_all_notrace + +nmi_stack_fixup: + FIX_STACK 12, nmi_stack_correct, 1 + jmp nmi_stack_correct + +nmi_debug_stack_check: + cmpw $__KERNEL_CS, 16(%esp) + jne nmi_stack_correct + cmpl $debug, (%esp) + jb nmi_stack_correct + cmpl $debug_esp_fix_insn, (%esp) + ja nmi_stack_correct + FIX_STACK 24, nmi_stack_correct, 1 + jmp nmi_stack_correct + +#ifdef CONFIG_X86_ESPFIX32 +nmi_espfix_stack: + /* + * create the pointer to lss back + */ + pushl %ss + pushl %esp + addl $4, (%esp) + /* copy the iret frame of 12 bytes */ + .rept 3 + pushl 16(%esp) + .endr + pushl %eax + SAVE_ALL + FIXUP_ESPFIX_STACK # %eax == %esp + xorl %edx, %edx # zero error code + call do_nmi + RESTORE_REGS + lss 12+4(%esp), %esp # back to espfix stack + jmp irq_return +#endif +END(nmi) + +ENTRY(int3) + ASM_CLAC + pushl $-1 # mark this as an int + SAVE_ALL + TRACE_IRQS_OFF + xorl %edx, %edx # zero error code + movl %esp, %eax # pt_regs pointer + call do_int3 + jmp ret_from_exception +END(int3) + +ENTRY(general_protection) + pushl $do_general_protection + jmp error_code +END(general_protection) + +#ifdef CONFIG_KVM_GUEST +ENTRY(async_page_fault) + ASM_CLAC + pushl $do_async_page_fault + jmp error_code +END(async_page_fault) +#endif diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/entry/entry_64.S index 4bd6c1975..8cb3e438f 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -4,34 +4,25 @@ * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs * Copyright (C) 2000 Pavel Machek <pavel@suse.cz> - */ - -/* + * * entry.S contains the system-call and fault low-level handling routines. * * Some of this is documented in Documentation/x86/entry_64.txt * - * NOTE: This code handles signal-recognition, which happens every time - * after an interrupt and after each system call. - * * A note on terminology: - * - iret frame: Architecture defined interrupt frame from SS to RIP - * at the top of the kernel process stack. + * - iret frame: Architecture defined interrupt frame from SS to RIP + * at the top of the kernel process stack. * * Some macro usage: - * - CFI macros are used to generate dwarf2 unwind information for better - * backtraces. They don't change any code. - * - ENTRY/END Define functions in the symbol table. - * - TRACE_IRQ_* - Trace hard interrupt state for lock debugging. - * - idtentry - Define exception entry points. + * - ENTRY/END: Define functions in the symbol table. + * - TRACE_IRQ_*: Trace hardirq state for lock debugging. + * - idtentry: Define exception entry points. */ - #include <linux/linkage.h> #include <asm/segment.h> #include <asm/cache.h> #include <asm/errno.h> -#include <asm/dwarf2.h> -#include <asm/calling.h> +#include "calling.h" #include <asm/asm-offsets.h> #include <asm/msr.h> #include <asm/unistd.h> @@ -49,13 +40,12 @@ /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ #include <linux/elf-em.h> -#define AUDIT_ARCH_X86_64 (EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE) -#define __AUDIT_ARCH_64BIT 0x80000000 -#define __AUDIT_ARCH_LE 0x40000000 - - .code64 - .section .entry.text, "ax" +#define AUDIT_ARCH_X86_64 (EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE) +#define __AUDIT_ARCH_64BIT 0x80000000 +#define __AUDIT_ARCH_LE 0x40000000 +.code64 +.section .entry.text, "ax" #ifdef CONFIG_PARAVIRT ENTRY(native_usergs_sysret64) @@ -64,11 +54,10 @@ ENTRY(native_usergs_sysret64) ENDPROC(native_usergs_sysret64) #endif /* CONFIG_PARAVIRT */ - .macro TRACE_IRQS_IRETQ #ifdef CONFIG_TRACE_IRQFLAGS - bt $9,EFLAGS(%rsp) /* interrupts off? */ - jnc 1f + bt $9, EFLAGS(%rsp) /* interrupts off? */ + jnc 1f TRACE_IRQS_ON 1: #endif @@ -88,89 +77,34 @@ ENDPROC(native_usergs_sysret64) #if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_TRACE_IRQFLAGS) .macro TRACE_IRQS_OFF_DEBUG - call debug_stack_set_zero + call debug_stack_set_zero TRACE_IRQS_OFF - call debug_stack_reset + call debug_stack_reset .endm .macro TRACE_IRQS_ON_DEBUG - call debug_stack_set_zero + call debug_stack_set_zero TRACE_IRQS_ON - call debug_stack_reset + call debug_stack_reset .endm .macro TRACE_IRQS_IRETQ_DEBUG - bt $9,EFLAGS(%rsp) /* interrupts off? */ - jnc 1f + bt $9, EFLAGS(%rsp) /* interrupts off? */ + jnc 1f TRACE_IRQS_ON_DEBUG 1: .endm #else -# define TRACE_IRQS_OFF_DEBUG TRACE_IRQS_OFF -# define TRACE_IRQS_ON_DEBUG TRACE_IRQS_ON -# define TRACE_IRQS_IRETQ_DEBUG TRACE_IRQS_IRETQ +# define TRACE_IRQS_OFF_DEBUG TRACE_IRQS_OFF +# define TRACE_IRQS_ON_DEBUG TRACE_IRQS_ON +# define TRACE_IRQS_IRETQ_DEBUG TRACE_IRQS_IRETQ #endif /* - * empty frame - */ - .macro EMPTY_FRAME start=1 offset=0 - .if \start - CFI_STARTPROC simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA rsp,8+\offset - .else - CFI_DEF_CFA_OFFSET 8+\offset - .endif - .endm - -/* - * initial frame state for interrupts (and exceptions without error code) - */ - .macro INTR_FRAME start=1 offset=0 - EMPTY_FRAME \start, 5*8+\offset - /*CFI_REL_OFFSET ss, 4*8+\offset*/ - CFI_REL_OFFSET rsp, 3*8+\offset - /*CFI_REL_OFFSET rflags, 2*8+\offset*/ - /*CFI_REL_OFFSET cs, 1*8+\offset*/ - CFI_REL_OFFSET rip, 0*8+\offset - .endm - -/* - * initial frame state for exceptions with error code (and interrupts - * with vector already pushed) - */ - .macro XCPT_FRAME start=1 offset=0 - INTR_FRAME \start, 1*8+\offset - .endm - -/* - * frame that enables passing a complete pt_regs to a C function. - */ - .macro DEFAULT_FRAME start=1 offset=0 - XCPT_FRAME \start, ORIG_RAX+\offset - CFI_REL_OFFSET rdi, RDI+\offset - CFI_REL_OFFSET rsi, RSI+\offset - CFI_REL_OFFSET rdx, RDX+\offset - CFI_REL_OFFSET rcx, RCX+\offset - CFI_REL_OFFSET rax, RAX+\offset - CFI_REL_OFFSET r8, R8+\offset - CFI_REL_OFFSET r9, R9+\offset - CFI_REL_OFFSET r10, R10+\offset - CFI_REL_OFFSET r11, R11+\offset - CFI_REL_OFFSET rbx, RBX+\offset - CFI_REL_OFFSET rbp, RBP+\offset - CFI_REL_OFFSET r12, R12+\offset - CFI_REL_OFFSET r13, R13+\offset - CFI_REL_OFFSET r14, R14+\offset - CFI_REL_OFFSET r15, R15+\offset - .endm - -/* - * 64bit SYSCALL instruction entry. Up to 6 arguments in registers. + * 64-bit SYSCALL instruction entry. Up to 6 arguments in registers. * - * 64bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11, + * 64-bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11, * then loads new ss, cs, and rip from previously programmed MSRs. * rflags gets masked by a value from another MSR (so CLD and CLAC * are not needed). SYSCALL does not save anything on the stack @@ -186,7 +120,7 @@ ENDPROC(native_usergs_sysret64) * r10 arg3 (needs to be moved to rcx to conform to C ABI) * r8 arg4 * r9 arg5 - * (note: r12-r15,rbp,rbx are callee-preserved in C ABI) + * (note: r12-r15, rbp, rbx are callee-preserved in C ABI) * * Only called from user space. * @@ -195,13 +129,7 @@ ENDPROC(native_usergs_sysret64) * with them due to bugs in both AMD and Intel CPUs. */ -ENTRY(system_call) - CFI_STARTPROC simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA rsp,0 - CFI_REGISTER rip,rcx - /*CFI_REGISTER rflags,r11*/ - +ENTRY(entry_SYSCALL_64) /* * Interrupts are off on entry. * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON, @@ -213,14 +141,14 @@ ENTRY(system_call) * after the swapgs, so that it can do the swapgs * for the guest and jump here on syscall. */ -GLOBAL(system_call_after_swapgs) +GLOBAL(entry_SYSCALL_64_after_swapgs) - movq %rsp,PER_CPU_VAR(rsp_scratch) - movq PER_CPU_VAR(kernel_stack),%rsp + movq %rsp, PER_CPU_VAR(rsp_scratch) + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp /* Construct struct pt_regs on stack */ - pushq_cfi $__USER_DS /* pt_regs->ss */ - pushq_cfi PER_CPU_VAR(rsp_scratch) /* pt_regs->sp */ + pushq $__USER_DS /* pt_regs->ss */ + pushq PER_CPU_VAR(rsp_scratch) /* pt_regs->sp */ /* * Re-enable interrupts. * We use 'rsp_scratch' as a scratch space, hence irq-off block above @@ -229,36 +157,34 @@ GLOBAL(system_call_after_swapgs) * with using rsp_scratch: */ ENABLE_INTERRUPTS(CLBR_NONE) - pushq_cfi %r11 /* pt_regs->flags */ - pushq_cfi $__USER_CS /* pt_regs->cs */ - pushq_cfi %rcx /* pt_regs->ip */ - CFI_REL_OFFSET rip,0 - pushq_cfi_reg rax /* pt_regs->orig_ax */ - pushq_cfi_reg rdi /* pt_regs->di */ - pushq_cfi_reg rsi /* pt_regs->si */ - pushq_cfi_reg rdx /* pt_regs->dx */ - pushq_cfi_reg rcx /* pt_regs->cx */ - pushq_cfi $-ENOSYS /* pt_regs->ax */ - pushq_cfi_reg r8 /* pt_regs->r8 */ - pushq_cfi_reg r9 /* pt_regs->r9 */ - pushq_cfi_reg r10 /* pt_regs->r10 */ - pushq_cfi_reg r11 /* pt_regs->r11 */ - sub $(6*8),%rsp /* pt_regs->bp,bx,r12-15 not saved */ - CFI_ADJUST_CFA_OFFSET 6*8 - - testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - jnz tracesys -system_call_fastpath: + pushq %r11 /* pt_regs->flags */ + pushq $__USER_CS /* pt_regs->cs */ + pushq %rcx /* pt_regs->ip */ + pushq %rax /* pt_regs->orig_ax */ + pushq %rdi /* pt_regs->di */ + pushq %rsi /* pt_regs->si */ + pushq %rdx /* pt_regs->dx */ + pushq %rcx /* pt_regs->cx */ + pushq $-ENOSYS /* pt_regs->ax */ + pushq %r8 /* pt_regs->r8 */ + pushq %r9 /* pt_regs->r9 */ + pushq %r10 /* pt_regs->r10 */ + pushq %r11 /* pt_regs->r11 */ + sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */ + + testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) + jnz tracesys +entry_SYSCALL_64_fastpath: #if __SYSCALL_MASK == ~0 - cmpq $__NR_syscall_max,%rax + cmpq $__NR_syscall_max, %rax #else - andl $__SYSCALL_MASK,%eax - cmpl $__NR_syscall_max,%eax + andl $__SYSCALL_MASK, %eax + cmpl $__NR_syscall_max, %eax #endif - ja 1f /* return -ENOSYS (already in pt_regs->ax) */ - movq %r10,%rcx - call *sys_call_table(,%rax,8) - movq %rax,RAX(%rsp) + ja 1f /* return -ENOSYS (already in pt_regs->ax) */ + movq %r10, %rcx + call *sys_call_table(, %rax, 8) + movq %rax, RAX(%rsp) 1: /* * Syscall return path ending with SYSRET (fast path). @@ -279,19 +205,15 @@ system_call_fastpath: * flags (TIF_NOTIFY_RESUME, TIF_USER_RETURN_NOTIFY, etc) set is * very bad. */ - testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - jnz int_ret_from_sys_call_irqs_off /* Go to the slow path */ - - CFI_REMEMBER_STATE + testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) + jnz int_ret_from_sys_call_irqs_off /* Go to the slow path */ RESTORE_C_REGS_EXCEPT_RCX_R11 - movq RIP(%rsp),%rcx - CFI_REGISTER rip,rcx - movq EFLAGS(%rsp),%r11 - /*CFI_REGISTER rflags,r11*/ - movq RSP(%rsp),%rsp + movq RIP(%rsp), %rcx + movq EFLAGS(%rsp), %r11 + movq RSP(%rsp), %rsp /* - * 64bit SYSRET restores rip from rcx, + * 64-bit SYSRET restores rip from rcx, * rflags from r11 (but RF and VM bits are forced to 0), * cs and ss are loaded from MSRs. * Restoration of rflags re-enables interrupts. @@ -307,25 +229,23 @@ system_call_fastpath: */ USERGS_SYSRET64 - CFI_RESTORE_STATE - /* Do syscall entry tracing */ tracesys: - movq %rsp, %rdi - movl $AUDIT_ARCH_X86_64, %esi - call syscall_trace_enter_phase1 - test %rax, %rax - jnz tracesys_phase2 /* if needed, run the slow path */ - RESTORE_C_REGS_EXCEPT_RAX /* else restore clobbered regs */ - movq ORIG_RAX(%rsp), %rax - jmp system_call_fastpath /* and return to the fast path */ + movq %rsp, %rdi + movl $AUDIT_ARCH_X86_64, %esi + call syscall_trace_enter_phase1 + test %rax, %rax + jnz tracesys_phase2 /* if needed, run the slow path */ + RESTORE_C_REGS_EXCEPT_RAX /* else restore clobbered regs */ + movq ORIG_RAX(%rsp), %rax + jmp entry_SYSCALL_64_fastpath /* and return to the fast path */ tracesys_phase2: SAVE_EXTRA_REGS - movq %rsp, %rdi - movl $AUDIT_ARCH_X86_64, %esi - movq %rax,%rdx - call syscall_trace_enter_phase2 + movq %rsp, %rdi + movl $AUDIT_ARCH_X86_64, %esi + movq %rax, %rdx + call syscall_trace_enter_phase2 /* * Reload registers from stack in case ptrace changed them. @@ -335,15 +255,15 @@ tracesys_phase2: RESTORE_C_REGS_EXCEPT_RAX RESTORE_EXTRA_REGS #if __SYSCALL_MASK == ~0 - cmpq $__NR_syscall_max,%rax + cmpq $__NR_syscall_max, %rax #else - andl $__SYSCALL_MASK,%eax - cmpl $__NR_syscall_max,%eax + andl $__SYSCALL_MASK, %eax + cmpl $__NR_syscall_max, %eax #endif - ja 1f /* return -ENOSYS (already in pt_regs->ax) */ - movq %r10,%rcx /* fixup for C */ - call *sys_call_table(,%rax,8) - movq %rax,RAX(%rsp) + ja 1f /* return -ENOSYS (already in pt_regs->ax) */ + movq %r10, %rcx /* fixup for C */ + call *sys_call_table(, %rax, 8) + movq %rax, RAX(%rsp) 1: /* Use IRET because user could have changed pt_regs->foo */ @@ -355,31 +275,33 @@ GLOBAL(int_ret_from_sys_call) DISABLE_INTERRUPTS(CLBR_NONE) int_ret_from_sys_call_irqs_off: /* jumps come here from the irqs-off SYSRET path */ TRACE_IRQS_OFF - movl $_TIF_ALLWORK_MASK,%edi + movl $_TIF_ALLWORK_MASK, %edi /* edi: mask to check */ GLOBAL(int_with_check) LOCKDEP_SYS_EXIT_IRQ GET_THREAD_INFO(%rcx) - movl TI_flags(%rcx),%edx - andl %edi,%edx - jnz int_careful - andl $~TS_COMPAT,TI_status(%rcx) + movl TI_flags(%rcx), %edx + andl %edi, %edx + jnz int_careful + andl $~TS_COMPAT, TI_status(%rcx) jmp syscall_return - /* Either reschedule or signal or syscall exit tracking needed. */ - /* First do a reschedule test. */ - /* edx: work, edi: workmask */ + /* + * Either reschedule or signal or syscall exit tracking needed. + * First do a reschedule test. + * edx: work, edi: workmask + */ int_careful: - bt $TIF_NEED_RESCHED,%edx - jnc int_very_careful + bt $TIF_NEED_RESCHED, %edx + jnc int_very_careful TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) - pushq_cfi %rdi + pushq %rdi SCHEDULE_USER - popq_cfi %rdi + popq %rdi DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - jmp int_with_check + jmp int_with_check /* handle signals and tracing -- both require a full pt_regs */ int_very_careful: @@ -387,27 +309,27 @@ int_very_careful: ENABLE_INTERRUPTS(CLBR_NONE) SAVE_EXTRA_REGS /* Check for syscall exit trace */ - testl $_TIF_WORK_SYSCALL_EXIT,%edx - jz int_signal - pushq_cfi %rdi - leaq 8(%rsp),%rdi # &ptregs -> arg1 - call syscall_trace_leave - popq_cfi %rdi - andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU),%edi - jmp int_restore_rest + testl $_TIF_WORK_SYSCALL_EXIT, %edx + jz int_signal + pushq %rdi + leaq 8(%rsp), %rdi /* &ptregs -> arg1 */ + call syscall_trace_leave + popq %rdi + andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU), %edi + jmp int_restore_rest int_signal: - testl $_TIF_DO_NOTIFY_MASK,%edx - jz 1f - movq %rsp,%rdi # &ptregs -> arg1 - xorl %esi,%esi # oldset -> arg2 - call do_notify_resume -1: movl $_TIF_WORK_MASK,%edi + testl $_TIF_DO_NOTIFY_MASK, %edx + jz 1f + movq %rsp, %rdi /* &ptregs -> arg1 */ + xorl %esi, %esi /* oldset -> arg2 */ + call do_notify_resume +1: movl $_TIF_WORK_MASK, %edi int_restore_rest: RESTORE_EXTRA_REGS DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - jmp int_with_check + jmp int_with_check syscall_return: /* The IRETQ could re-enable interrupts: */ @@ -418,34 +340,37 @@ syscall_return: * Try to use SYSRET instead of IRET if we're returning to * a completely clean 64-bit userspace context. */ - movq RCX(%rsp),%rcx - cmpq %rcx,RIP(%rsp) /* RCX == RIP */ - jne opportunistic_sysret_failed + movq RCX(%rsp), %rcx + movq RIP(%rsp), %r11 + cmpq %rcx, %r11 /* RCX == RIP */ + jne opportunistic_sysret_failed /* * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP * in kernel space. This essentially lets the user take over - * the kernel, since userspace controls RSP. It's not worth - * testing for canonicalness exactly -- this check detects any - * of the 17 high bits set, which is true for non-canonical - * or kernel addresses. (This will pessimize vsyscall=native. - * Big deal.) + * the kernel, since userspace controls RSP. * - * If virtual addresses ever become wider, this will need + * If width of "canonical tail" ever becomes variable, this will need * to be updated to remain correct on both old and new CPUs. */ .ifne __VIRTUAL_MASK_SHIFT - 47 .error "virtual address width changed -- SYSRET checks need update" .endif - shr $__VIRTUAL_MASK_SHIFT, %rcx - jnz opportunistic_sysret_failed - cmpq $__USER_CS,CS(%rsp) /* CS must match SYSRET */ - jne opportunistic_sysret_failed + /* Change top 16 bits to be the sign-extension of 47th bit */ + shl $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx + sar $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx + + /* If this changed %rcx, it was not canonical */ + cmpq %rcx, %r11 + jne opportunistic_sysret_failed - movq R11(%rsp),%r11 - cmpq %r11,EFLAGS(%rsp) /* R11 == RFLAGS */ - jne opportunistic_sysret_failed + cmpq $__USER_CS, CS(%rsp) /* CS must match SYSRET */ + jne opportunistic_sysret_failed + + movq R11(%rsp), %r11 + cmpq %r11, EFLAGS(%rsp) /* R11 == RFLAGS */ + jne opportunistic_sysret_failed /* * SYSRET can't restore RF. SYSRET can restore TF, but unlike IRET, @@ -454,47 +379,41 @@ syscall_return: * with register state that satisfies the opportunistic SYSRET * conditions. For example, single-stepping this user code: * - * movq $stuck_here,%rcx + * movq $stuck_here, %rcx * pushfq * popq %r11 * stuck_here: * * would never get past 'stuck_here'. */ - testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11 - jnz opportunistic_sysret_failed + testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11 + jnz opportunistic_sysret_failed /* nothing to check for RSP */ - cmpq $__USER_DS,SS(%rsp) /* SS must match SYSRET */ - jne opportunistic_sysret_failed + cmpq $__USER_DS, SS(%rsp) /* SS must match SYSRET */ + jne opportunistic_sysret_failed /* - * We win! This label is here just for ease of understanding - * perf profiles. Nothing jumps here. + * We win! This label is here just for ease of understanding + * perf profiles. Nothing jumps here. */ syscall_return_via_sysret: - CFI_REMEMBER_STATE - /* r11 is already restored (see code above) */ - RESTORE_C_REGS_EXCEPT_R11 - movq RSP(%rsp),%rsp + /* rcx and r11 are already restored (see code above) */ + RESTORE_C_REGS_EXCEPT_RCX_R11 + movq RSP(%rsp), %rsp USERGS_SYSRET64 - CFI_RESTORE_STATE opportunistic_sysret_failed: SWAPGS jmp restore_c_regs_and_iret - CFI_ENDPROC -END(system_call) +END(entry_SYSCALL_64) .macro FORK_LIKE func ENTRY(stub_\func) - CFI_STARTPROC - DEFAULT_FRAME 0, 8 /* offset 8: return address */ SAVE_EXTRA_REGS 8 - jmp sys_\func - CFI_ENDPROC + jmp sys_\func END(stub_\func) .endm @@ -503,8 +422,6 @@ END(stub_\func) FORK_LIKE vfork ENTRY(stub_execve) - CFI_STARTPROC - DEFAULT_FRAME 0, 8 call sys_execve return_from_execve: testl %eax, %eax @@ -514,11 +431,9 @@ return_from_execve: 1: /* must use IRET code path (pt_regs->cs may have changed) */ addq $8, %rsp - CFI_ADJUST_CFA_OFFSET -8 ZERO_EXTRA_REGS - movq %rax,RAX(%rsp) + movq %rax, RAX(%rsp) jmp int_ret_from_sys_call - CFI_ENDPROC END(stub_execve) /* * Remaining execve stubs are only 7 bytes long. @@ -526,47 +441,25 @@ END(stub_execve) */ .align 8 GLOBAL(stub_execveat) - CFI_STARTPROC - DEFAULT_FRAME 0, 8 call sys_execveat jmp return_from_execve - CFI_ENDPROC END(stub_execveat) -#ifdef CONFIG_X86_X32_ABI +#if defined(CONFIG_X86_X32_ABI) || defined(CONFIG_IA32_EMULATION) .align 8 GLOBAL(stub_x32_execve) - CFI_STARTPROC - DEFAULT_FRAME 0, 8 - call compat_sys_execve - jmp return_from_execve - CFI_ENDPROC -END(stub_x32_execve) - .align 8 -GLOBAL(stub_x32_execveat) - CFI_STARTPROC - DEFAULT_FRAME 0, 8 - call compat_sys_execveat - jmp return_from_execve - CFI_ENDPROC -END(stub_x32_execveat) -#endif - -#ifdef CONFIG_IA32_EMULATION - .align 8 GLOBAL(stub32_execve) - CFI_STARTPROC call compat_sys_execve jmp return_from_execve - CFI_ENDPROC END(stub32_execve) +END(stub_x32_execve) .align 8 +GLOBAL(stub_x32_execveat) GLOBAL(stub32_execveat) - CFI_STARTPROC call compat_sys_execveat jmp return_from_execve - CFI_ENDPROC END(stub32_execveat) +END(stub_x32_execveat) #endif /* @@ -574,8 +467,6 @@ END(stub32_execveat) * This cannot be done with SYSRET, so use the IRET return path instead. */ ENTRY(stub_rt_sigreturn) - CFI_STARTPROC - DEFAULT_FRAME 0, 8 /* * SAVE_EXTRA_REGS result is not normally needed: * sigreturn overwrites all pt_regs->GPREGS. @@ -584,24 +475,19 @@ ENTRY(stub_rt_sigreturn) * we SAVE_EXTRA_REGS here. */ SAVE_EXTRA_REGS 8 - call sys_rt_sigreturn + call sys_rt_sigreturn return_from_stub: addq $8, %rsp - CFI_ADJUST_CFA_OFFSET -8 RESTORE_EXTRA_REGS - movq %rax,RAX(%rsp) - jmp int_ret_from_sys_call - CFI_ENDPROC + movq %rax, RAX(%rsp) + jmp int_ret_from_sys_call END(stub_rt_sigreturn) #ifdef CONFIG_X86_X32_ABI ENTRY(stub_x32_rt_sigreturn) - CFI_STARTPROC - DEFAULT_FRAME 0, 8 SAVE_EXTRA_REGS 8 - call sys32_x32_rt_sigreturn - jmp return_from_stub - CFI_ENDPROC + call sys32_x32_rt_sigreturn + jmp return_from_stub END(stub_x32_rt_sigreturn) #endif @@ -611,36 +497,36 @@ END(stub_x32_rt_sigreturn) * rdi: prev task we switched from */ ENTRY(ret_from_fork) - DEFAULT_FRAME - LOCK ; btr $TIF_FORK,TI_flags(%r8) + LOCK ; btr $TIF_FORK, TI_flags(%r8) - pushq_cfi $0x0002 - popfq_cfi # reset kernel eflags + pushq $0x0002 + popfq /* reset kernel eflags */ - call schedule_tail # rdi: 'prev' task parameter + call schedule_tail /* rdi: 'prev' task parameter */ RESTORE_EXTRA_REGS - testl $3,CS(%rsp) # from kernel_thread? + testb $3, CS(%rsp) /* from kernel_thread? */ /* * By the time we get here, we have no idea whether our pt_regs, * ti flags, and ti status came from the 64-bit SYSCALL fast path, - * the slow path, or one of the ia32entry paths. + * the slow path, or one of the 32-bit compat paths. * Use IRET code path to return, since it can safely handle * all of the above. */ jnz int_ret_from_sys_call - /* We came from kernel_thread */ - /* nb: we depend on RESTORE_EXTRA_REGS above */ - movq %rbp, %rdi - call *%rbx - movl $0, RAX(%rsp) + /* + * We came from kernel_thread + * nb: we depend on RESTORE_EXTRA_REGS above + */ + movq %rbp, %rdi + call *%rbx + movl $0, RAX(%rsp) RESTORE_EXTRA_REGS - jmp int_ret_from_sys_call - CFI_ENDPROC + jmp int_ret_from_sys_call END(ret_from_fork) /* @@ -649,16 +535,13 @@ END(ret_from_fork) */ .align 8 ENTRY(irq_entries_start) - INTR_FRAME vector=FIRST_EXTERNAL_VECTOR .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR) - pushq_cfi $(~vector+0x80) /* Note: always in signed byte range */ + pushq $(~vector+0x80) /* Note: always in signed byte range */ vector=vector+1 jmp common_interrupt - CFI_ADJUST_CFA_OFFSET -8 .align 8 .endr - CFI_ENDPROC END(irq_entries_start) /* @@ -684,10 +567,10 @@ END(irq_entries_start) /* this goes to 0(%rsp) for unwinder, not for saving the value: */ SAVE_EXTRA_REGS_RBP -RBP - leaq -RBP(%rsp),%rdi /* arg1 for \func (pointer to pt_regs) */ + leaq -RBP(%rsp), %rdi /* arg1 for \func (pointer to pt_regs) */ - testl $3, CS-RBP(%rsp) - je 1f + testb $3, CS-RBP(%rsp) + jz 1f SWAPGS 1: /* @@ -697,24 +580,14 @@ END(irq_entries_start) * a little cheaper to use a separate counter in the PDA (short of * moving irq_enter into assembly, which would be too much work) */ - movq %rsp, %rsi - incl PER_CPU_VAR(irq_count) - cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp - CFI_DEF_CFA_REGISTER rsi - pushq %rsi - /* - * For debugger: - * "CFA (Current Frame Address) is the value on stack + offset" - */ - CFI_ESCAPE 0x0f /* DW_CFA_def_cfa_expression */, 6, \ - 0x77 /* DW_OP_breg7 (rsp) */, 0, \ - 0x06 /* DW_OP_deref */, \ - 0x08 /* DW_OP_const1u */, SIZEOF_PTREGS-RBP, \ - 0x22 /* DW_OP_plus */ + movq %rsp, %rsi + incl PER_CPU_VAR(irq_count) + cmovzq PER_CPU_VAR(irq_stack_ptr), %rsp + pushq %rsi /* We entered an interrupt context - irqs are off: */ TRACE_IRQS_OFF - call \func + call \func .endm /* @@ -723,42 +596,36 @@ END(irq_entries_start) */ .p2align CONFIG_X86_L1_CACHE_SHIFT common_interrupt: - XCPT_FRAME ASM_CLAC - addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */ + addq $-0x80, (%rsp) /* Adjust vector to [-256, -1] range */ interrupt do_IRQ /* 0(%rsp): old RSP */ ret_from_intr: DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - decl PER_CPU_VAR(irq_count) + decl PER_CPU_VAR(irq_count) /* Restore saved previous stack */ - popq %rsi - CFI_DEF_CFA rsi,SIZEOF_PTREGS-RBP /* reg/off reset after def_cfa_expr */ + popq %rsi /* return code expects complete pt_regs - adjust rsp accordingly: */ - leaq -RBP(%rsi),%rsp - CFI_DEF_CFA_REGISTER rsp - CFI_ADJUST_CFA_OFFSET RBP + leaq -RBP(%rsi), %rsp - testl $3,CS(%rsp) - je retint_kernel + testb $3, CS(%rsp) + jz retint_kernel /* Interrupt came from user space */ - +retint_user: GET_THREAD_INFO(%rcx) - /* - * %rcx: thread info. Interrupts off. - */ + + /* %rcx: thread info. Interrupts are off. */ retint_with_reschedule: - movl $_TIF_WORK_MASK,%edi + movl $_TIF_WORK_MASK, %edi retint_check: LOCKDEP_SYS_EXIT_IRQ - movl TI_flags(%rcx),%edx - andl %edi,%edx - CFI_REMEMBER_STATE - jnz retint_careful + movl TI_flags(%rcx), %edx + andl %edi, %edx + jnz retint_careful -retint_swapgs: /* return to user-space */ +retint_swapgs: /* return to user-space */ /* * The iretq could re-enable interrupts: */ @@ -773,9 +640,9 @@ retint_kernel: #ifdef CONFIG_PREEMPT /* Interrupts are off */ /* Check if we need preemption */ - bt $9,EFLAGS(%rsp) /* interrupts were off? */ + bt $9, EFLAGS(%rsp) /* were interrupts off? */ jnc 1f -0: cmpl $0,PER_CPU_VAR(__preempt_count) +0: cmpl $0, PER_CPU_VAR(__preempt_count) jnz 1f call preempt_schedule_irq jmp 0b @@ -801,8 +668,8 @@ ENTRY(native_iret) * 64-bit mode SS:RSP on the exception stack is always valid. */ #ifdef CONFIG_X86_ESPFIX64 - testb $4,(SS-RIP)(%rsp) - jnz native_irq_return_ldt + testb $4, (SS-RIP)(%rsp) + jnz native_irq_return_ldt #endif .global native_irq_return_iret @@ -817,62 +684,60 @@ native_irq_return_iret: #ifdef CONFIG_X86_ESPFIX64 native_irq_return_ldt: - pushq_cfi %rax - pushq_cfi %rdi + pushq %rax + pushq %rdi SWAPGS - movq PER_CPU_VAR(espfix_waddr),%rdi - movq %rax,(0*8)(%rdi) /* RAX */ - movq (2*8)(%rsp),%rax /* RIP */ - movq %rax,(1*8)(%rdi) - movq (3*8)(%rsp),%rax /* CS */ - movq %rax,(2*8)(%rdi) - movq (4*8)(%rsp),%rax /* RFLAGS */ - movq %rax,(3*8)(%rdi) - movq (6*8)(%rsp),%rax /* SS */ - movq %rax,(5*8)(%rdi) - movq (5*8)(%rsp),%rax /* RSP */ - movq %rax,(4*8)(%rdi) - andl $0xffff0000,%eax - popq_cfi %rdi - orq PER_CPU_VAR(espfix_stack),%rax + movq PER_CPU_VAR(espfix_waddr), %rdi + movq %rax, (0*8)(%rdi) /* RAX */ + movq (2*8)(%rsp), %rax /* RIP */ + movq %rax, (1*8)(%rdi) + movq (3*8)(%rsp), %rax /* CS */ + movq %rax, (2*8)(%rdi) + movq (4*8)(%rsp), %rax /* RFLAGS */ + movq %rax, (3*8)(%rdi) + movq (6*8)(%rsp), %rax /* SS */ + movq %rax, (5*8)(%rdi) + movq (5*8)(%rsp), %rax /* RSP */ + movq %rax, (4*8)(%rdi) + andl $0xffff0000, %eax + popq %rdi + orq PER_CPU_VAR(espfix_stack), %rax SWAPGS - movq %rax,%rsp - popq_cfi %rax - jmp native_irq_return_iret + movq %rax, %rsp + popq %rax + jmp native_irq_return_iret #endif /* edi: workmask, edx: work */ retint_careful: - CFI_RESTORE_STATE - bt $TIF_NEED_RESCHED,%edx - jnc retint_signal + bt $TIF_NEED_RESCHED, %edx + jnc retint_signal TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) - pushq_cfi %rdi + pushq %rdi SCHEDULE_USER - popq_cfi %rdi + popq %rdi GET_THREAD_INFO(%rcx) DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - jmp retint_check + jmp retint_check retint_signal: - testl $_TIF_DO_NOTIFY_MASK,%edx - jz retint_swapgs + testl $_TIF_DO_NOTIFY_MASK, %edx + jz retint_swapgs TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) SAVE_EXTRA_REGS - movq $-1,ORIG_RAX(%rsp) - xorl %esi,%esi # oldset - movq %rsp,%rdi # &pt_regs - call do_notify_resume + movq $-1, ORIG_RAX(%rsp) + xorl %esi, %esi /* oldset */ + movq %rsp, %rdi /* &pt_regs */ + call do_notify_resume RESTORE_EXTRA_REGS DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF GET_THREAD_INFO(%rcx) - jmp retint_with_reschedule + jmp retint_with_reschedule - CFI_ENDPROC END(common_interrupt) /* @@ -880,13 +745,11 @@ END(common_interrupt) */ .macro apicinterrupt3 num sym do_sym ENTRY(\sym) - INTR_FRAME ASM_CLAC - pushq_cfi $~(\num) + pushq $~(\num) .Lcommon_\sym: interrupt \do_sym - jmp ret_from_intr - CFI_ENDPROC + jmp ret_from_intr END(\sym) .endm @@ -908,53 +771,45 @@ trace_apicinterrupt \num \sym .endm #ifdef CONFIG_SMP -apicinterrupt3 IRQ_MOVE_CLEANUP_VECTOR \ - irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt -apicinterrupt3 REBOOT_VECTOR \ - reboot_interrupt smp_reboot_interrupt +apicinterrupt3 IRQ_MOVE_CLEANUP_VECTOR irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt +apicinterrupt3 REBOOT_VECTOR reboot_interrupt smp_reboot_interrupt #endif #ifdef CONFIG_X86_UV -apicinterrupt3 UV_BAU_MESSAGE \ - uv_bau_message_intr1 uv_bau_message_interrupt +apicinterrupt3 UV_BAU_MESSAGE uv_bau_message_intr1 uv_bau_message_interrupt #endif -apicinterrupt LOCAL_TIMER_VECTOR \ - apic_timer_interrupt smp_apic_timer_interrupt -apicinterrupt X86_PLATFORM_IPI_VECTOR \ - x86_platform_ipi smp_x86_platform_ipi + +apicinterrupt LOCAL_TIMER_VECTOR apic_timer_interrupt smp_apic_timer_interrupt +apicinterrupt X86_PLATFORM_IPI_VECTOR x86_platform_ipi smp_x86_platform_ipi #ifdef CONFIG_HAVE_KVM -apicinterrupt3 POSTED_INTR_VECTOR \ - kvm_posted_intr_ipi smp_kvm_posted_intr_ipi +apicinterrupt3 POSTED_INTR_VECTOR kvm_posted_intr_ipi smp_kvm_posted_intr_ipi +apicinterrupt3 POSTED_INTR_WAKEUP_VECTOR kvm_posted_intr_wakeup_ipi smp_kvm_posted_intr_wakeup_ipi #endif #ifdef CONFIG_X86_MCE_THRESHOLD -apicinterrupt THRESHOLD_APIC_VECTOR \ - threshold_interrupt smp_threshold_interrupt +apicinterrupt THRESHOLD_APIC_VECTOR threshold_interrupt smp_threshold_interrupt +#endif + +#ifdef CONFIG_X86_MCE_AMD +apicinterrupt DEFERRED_ERROR_VECTOR deferred_error_interrupt smp_deferred_error_interrupt #endif #ifdef CONFIG_X86_THERMAL_VECTOR -apicinterrupt THERMAL_APIC_VECTOR \ - thermal_interrupt smp_thermal_interrupt +apicinterrupt THERMAL_APIC_VECTOR thermal_interrupt smp_thermal_interrupt #endif #ifdef CONFIG_SMP -apicinterrupt CALL_FUNCTION_SINGLE_VECTOR \ - call_function_single_interrupt smp_call_function_single_interrupt -apicinterrupt CALL_FUNCTION_VECTOR \ - call_function_interrupt smp_call_function_interrupt -apicinterrupt RESCHEDULE_VECTOR \ - reschedule_interrupt smp_reschedule_interrupt +apicinterrupt CALL_FUNCTION_SINGLE_VECTOR call_function_single_interrupt smp_call_function_single_interrupt +apicinterrupt CALL_FUNCTION_VECTOR call_function_interrupt smp_call_function_interrupt +apicinterrupt RESCHEDULE_VECTOR reschedule_interrupt smp_reschedule_interrupt #endif -apicinterrupt ERROR_APIC_VECTOR \ - error_interrupt smp_error_interrupt -apicinterrupt SPURIOUS_APIC_VECTOR \ - spurious_interrupt smp_spurious_interrupt +apicinterrupt ERROR_APIC_VECTOR error_interrupt smp_error_interrupt +apicinterrupt SPURIOUS_APIC_VECTOR spurious_interrupt smp_spurious_interrupt #ifdef CONFIG_IRQ_WORK -apicinterrupt IRQ_WORK_VECTOR \ - irq_work_interrupt smp_irq_work_interrupt +apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt #endif /* @@ -969,100 +824,87 @@ ENTRY(\sym) .error "using shift_ist requires paranoid=1" .endif - .if \has_error_code - XCPT_FRAME - .else - INTR_FRAME - .endif - ASM_CLAC PARAVIRT_ADJUST_EXCEPTION_FRAME .ifeq \has_error_code - pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ + pushq $-1 /* ORIG_RAX: no syscall to restart */ .endif ALLOC_PT_GPREGS_ON_STACK .if \paranoid .if \paranoid == 1 - CFI_REMEMBER_STATE - testl $3, CS(%rsp) /* If coming from userspace, switch */ - jnz 1f /* stacks. */ + testb $3, CS(%rsp) /* If coming from userspace, switch stacks */ + jnz 1f .endif - call paranoid_entry + call paranoid_entry .else - call error_entry + call error_entry .endif /* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */ - DEFAULT_FRAME 0 - .if \paranoid .if \shift_ist != -1 - TRACE_IRQS_OFF_DEBUG /* reload IDT in case of recursion */ + TRACE_IRQS_OFF_DEBUG /* reload IDT in case of recursion */ .else TRACE_IRQS_OFF .endif .endif - movq %rsp,%rdi /* pt_regs pointer */ + movq %rsp, %rdi /* pt_regs pointer */ .if \has_error_code - movq ORIG_RAX(%rsp),%rsi /* get error code */ - movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */ + movq ORIG_RAX(%rsp), %rsi /* get error code */ + movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */ .else - xorl %esi,%esi /* no error code */ + xorl %esi, %esi /* no error code */ .endif .if \shift_ist != -1 - subq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist) + subq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist) .endif - call \do_sym + call \do_sym .if \shift_ist != -1 - addq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist) + addq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist) .endif /* these procedures expect "no swapgs" flag in ebx */ .if \paranoid - jmp paranoid_exit + jmp paranoid_exit .else - jmp error_exit + jmp error_exit .endif .if \paranoid == 1 - CFI_RESTORE_STATE /* * Paranoid entry from userspace. Switch stacks and treat it * as a normal entry. This means that paranoid handlers * run in real process context if user_mode(regs). */ 1: - call error_entry + call error_entry - DEFAULT_FRAME 0 - movq %rsp,%rdi /* pt_regs pointer */ - call sync_regs - movq %rax,%rsp /* switch stack */ + movq %rsp, %rdi /* pt_regs pointer */ + call sync_regs + movq %rax, %rsp /* switch stack */ - movq %rsp,%rdi /* pt_regs pointer */ + movq %rsp, %rdi /* pt_regs pointer */ .if \has_error_code - movq ORIG_RAX(%rsp),%rsi /* get error code */ - movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */ + movq ORIG_RAX(%rsp), %rsi /* get error code */ + movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */ .else - xorl %esi,%esi /* no error code */ + xorl %esi, %esi /* no error code */ .endif - call \do_sym + call \do_sym - jmp error_exit /* %ebx: no swapgs flag */ + jmp error_exit /* %ebx: no swapgs flag */ .endif - - CFI_ENDPROC END(\sym) .endm @@ -1077,65 +919,58 @@ idtentry \sym \do_sym has_error_code=\has_error_code .endm #endif -idtentry divide_error do_divide_error has_error_code=0 -idtentry overflow do_overflow has_error_code=0 -idtentry bounds do_bounds has_error_code=0 -idtentry invalid_op do_invalid_op has_error_code=0 -idtentry device_not_available do_device_not_available has_error_code=0 -idtentry double_fault do_double_fault has_error_code=1 paranoid=2 -idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0 -idtentry invalid_TSS do_invalid_TSS has_error_code=1 -idtentry segment_not_present do_segment_not_present has_error_code=1 -idtentry spurious_interrupt_bug do_spurious_interrupt_bug has_error_code=0 -idtentry coprocessor_error do_coprocessor_error has_error_code=0 -idtentry alignment_check do_alignment_check has_error_code=1 -idtentry simd_coprocessor_error do_simd_coprocessor_error has_error_code=0 - - - /* Reload gs selector with exception handling */ - /* edi: new selector */ +idtentry divide_error do_divide_error has_error_code=0 +idtentry overflow do_overflow has_error_code=0 +idtentry bounds do_bounds has_error_code=0 +idtentry invalid_op do_invalid_op has_error_code=0 +idtentry device_not_available do_device_not_available has_error_code=0 +idtentry double_fault do_double_fault has_error_code=1 paranoid=2 +idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0 +idtentry invalid_TSS do_invalid_TSS has_error_code=1 +idtentry segment_not_present do_segment_not_present has_error_code=1 +idtentry spurious_interrupt_bug do_spurious_interrupt_bug has_error_code=0 +idtentry coprocessor_error do_coprocessor_error has_error_code=0 +idtentry alignment_check do_alignment_check has_error_code=1 +idtentry simd_coprocessor_error do_simd_coprocessor_error has_error_code=0 + + + /* + * Reload gs selector with exception handling + * edi: new selector + */ ENTRY(native_load_gs_index) - CFI_STARTPROC - pushfq_cfi + pushfq DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI) SWAPGS gs_change: - movl %edi,%gs -2: mfence /* workaround */ + movl %edi, %gs +2: mfence /* workaround */ SWAPGS - popfq_cfi + popfq ret - CFI_ENDPROC END(native_load_gs_index) - _ASM_EXTABLE(gs_change,bad_gs) - .section .fixup,"ax" + _ASM_EXTABLE(gs_change, bad_gs) + .section .fixup, "ax" /* running with kernelgs */ bad_gs: - SWAPGS /* switch back to user gs */ - xorl %eax,%eax - movl %eax,%gs - jmp 2b + SWAPGS /* switch back to user gs */ + xorl %eax, %eax + movl %eax, %gs + jmp 2b .previous /* Call softirq on interrupt stack. Interrupts are off. */ ENTRY(do_softirq_own_stack) - CFI_STARTPROC - pushq_cfi %rbp - CFI_REL_OFFSET rbp,0 - mov %rsp,%rbp - CFI_DEF_CFA_REGISTER rbp - incl PER_CPU_VAR(irq_count) - cmove PER_CPU_VAR(irq_stack_ptr),%rsp - push %rbp # backlink for old unwinder - call __do_softirq + pushq %rbp + mov %rsp, %rbp + incl PER_CPU_VAR(irq_count) + cmove PER_CPU_VAR(irq_stack_ptr), %rsp + push %rbp /* frame pointer backlink */ + call __do_softirq leaveq - CFI_RESTORE rbp - CFI_DEF_CFA_REGISTER rsp - CFI_ADJUST_CFA_OFFSET -8 - decl PER_CPU_VAR(irq_count) + decl PER_CPU_VAR(irq_count) ret - CFI_ENDPROC END(do_softirq_own_stack) #ifdef CONFIG_XEN @@ -1154,29 +989,24 @@ idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0 * existing activation in its critical region -- if so, we pop the current * activation and restart the handler using the previous one. */ -ENTRY(xen_do_hypervisor_callback) # do_hypervisor_callback(struct *pt_regs) - CFI_STARTPROC +ENTRY(xen_do_hypervisor_callback) /* do_hypervisor_callback(struct *pt_regs) */ + /* * Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will * see the correct pointer to the pt_regs */ - movq %rdi, %rsp # we don't return, adjust the stack frame - CFI_ENDPROC - DEFAULT_FRAME -11: incl PER_CPU_VAR(irq_count) - movq %rsp,%rbp - CFI_DEF_CFA_REGISTER rbp - cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp - pushq %rbp # backlink for old unwinder - call xen_evtchn_do_upcall - popq %rsp - CFI_DEF_CFA_REGISTER rsp - decl PER_CPU_VAR(irq_count) + movq %rdi, %rsp /* we don't return, adjust the stack frame */ +11: incl PER_CPU_VAR(irq_count) + movq %rsp, %rbp + cmovzq PER_CPU_VAR(irq_stack_ptr), %rsp + pushq %rbp /* frame pointer backlink */ + call xen_evtchn_do_upcall + popq %rsp + decl PER_CPU_VAR(irq_count) #ifndef CONFIG_PREEMPT - call xen_maybe_preempt_hcall + call xen_maybe_preempt_hcall #endif - jmp error_exit - CFI_ENDPROC + jmp error_exit END(xen_do_hypervisor_callback) /* @@ -1193,51 +1023,35 @@ END(xen_do_hypervisor_callback) * with its current contents: any discrepancy means we in category 1. */ ENTRY(xen_failsafe_callback) - INTR_FRAME 1 (6*8) - /*CFI_REL_OFFSET gs,GS*/ - /*CFI_REL_OFFSET fs,FS*/ - /*CFI_REL_OFFSET es,ES*/ - /*CFI_REL_OFFSET ds,DS*/ - CFI_REL_OFFSET r11,8 - CFI_REL_OFFSET rcx,0 - movw %ds,%cx - cmpw %cx,0x10(%rsp) - CFI_REMEMBER_STATE - jne 1f - movw %es,%cx - cmpw %cx,0x18(%rsp) - jne 1f - movw %fs,%cx - cmpw %cx,0x20(%rsp) - jne 1f - movw %gs,%cx - cmpw %cx,0x28(%rsp) - jne 1f + movl %ds, %ecx + cmpw %cx, 0x10(%rsp) + jne 1f + movl %es, %ecx + cmpw %cx, 0x18(%rsp) + jne 1f + movl %fs, %ecx + cmpw %cx, 0x20(%rsp) + jne 1f + movl %gs, %ecx + cmpw %cx, 0x28(%rsp) + jne 1f /* All segments match their saved values => Category 2 (Bad IRET). */ - movq (%rsp),%rcx - CFI_RESTORE rcx - movq 8(%rsp),%r11 - CFI_RESTORE r11 - addq $0x30,%rsp - CFI_ADJUST_CFA_OFFSET -0x30 - pushq_cfi $0 /* RIP */ - pushq_cfi %r11 - pushq_cfi %rcx - jmp general_protection - CFI_RESTORE_STATE + movq (%rsp), %rcx + movq 8(%rsp), %r11 + addq $0x30, %rsp + pushq $0 /* RIP */ + pushq %r11 + pushq %rcx + jmp general_protection 1: /* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */ - movq (%rsp),%rcx - CFI_RESTORE rcx - movq 8(%rsp),%r11 - CFI_RESTORE r11 - addq $0x30,%rsp - CFI_ADJUST_CFA_OFFSET -0x30 - pushq_cfi $-1 /* orig_ax = -1 => not a system call */ + movq (%rsp), %rcx + movq 8(%rsp), %r11 + addq $0x30, %rsp + pushq $-1 /* orig_ax = -1 => not a system call */ ALLOC_PT_GPREGS_ON_STACK SAVE_C_REGS SAVE_EXTRA_REGS - jmp error_exit - CFI_ENDPROC + jmp error_exit END(xen_failsafe_callback) apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ @@ -1250,21 +1064,25 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ hyperv_callback_vector hyperv_vector_handler #endif /* CONFIG_HYPERV */ -idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK -idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK -idtentry stack_segment do_stack_segment has_error_code=1 +idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK +idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK +idtentry stack_segment do_stack_segment has_error_code=1 + #ifdef CONFIG_XEN -idtentry xen_debug do_debug has_error_code=0 -idtentry xen_int3 do_int3 has_error_code=0 -idtentry xen_stack_segment do_stack_segment has_error_code=1 +idtentry xen_debug do_debug has_error_code=0 +idtentry xen_int3 do_int3 has_error_code=0 +idtentry xen_stack_segment do_stack_segment has_error_code=1 #endif -idtentry general_protection do_general_protection has_error_code=1 -trace_idtentry page_fault do_page_fault has_error_code=1 + +idtentry general_protection do_general_protection has_error_code=1 +trace_idtentry page_fault do_page_fault has_error_code=1 + #ifdef CONFIG_KVM_GUEST -idtentry async_page_fault do_async_page_fault has_error_code=1 +idtentry async_page_fault do_async_page_fault has_error_code=1 #endif + #ifdef CONFIG_X86_MCE -idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip) +idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip) #endif /* @@ -1273,19 +1091,17 @@ idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector( * Return: ebx=0: need swapgs on exit, ebx=1: otherwise */ ENTRY(paranoid_entry) - XCPT_FRAME 1 15*8 cld SAVE_C_REGS 8 SAVE_EXTRA_REGS 8 - movl $1,%ebx - movl $MSR_GS_BASE,%ecx + movl $1, %ebx + movl $MSR_GS_BASE, %ecx rdmsr - testl %edx,%edx - js 1f /* negative -> in kernel */ + testl %edx, %edx + js 1f /* negative -> in kernel */ SWAPGS - xorl %ebx,%ebx + xorl %ebx, %ebx 1: ret - CFI_ENDPROC END(paranoid_entry) /* @@ -1297,17 +1113,17 @@ END(paranoid_entry) * in syscall entry), so checking for preemption here would * be complicated. Fortunately, we there's no good reason * to try to handle preemption here. + * + * On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */ -/* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */ ENTRY(paranoid_exit) - DEFAULT_FRAME DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF_DEBUG - testl %ebx,%ebx /* swapgs needed? */ - jnz paranoid_exit_no_swapgs + testl %ebx, %ebx /* swapgs needed? */ + jnz paranoid_exit_no_swapgs TRACE_IRQS_IRETQ SWAPGS_UNSAFE_STACK - jmp paranoid_exit_restore + jmp paranoid_exit_restore paranoid_exit_no_swapgs: TRACE_IRQS_IRETQ_DEBUG paranoid_exit_restore: @@ -1315,24 +1131,24 @@ paranoid_exit_restore: RESTORE_C_REGS REMOVE_PT_GPREGS_FROM_STACK 8 INTERRUPT_RETURN - CFI_ENDPROC END(paranoid_exit) /* * Save all registers in pt_regs, and switch gs if needed. - * Return: ebx=0: need swapgs on exit, ebx=1: otherwise + * Return: EBX=0: came from user mode; EBX=1: otherwise */ ENTRY(error_entry) - XCPT_FRAME 1 15*8 cld SAVE_C_REGS 8 SAVE_EXTRA_REGS 8 - xorl %ebx,%ebx - testl $3,CS+8(%rsp) - je error_kernelspace -error_swapgs: + xorl %ebx, %ebx + testb $3, CS+8(%rsp) + jz error_kernelspace + + /* We entered from user mode */ SWAPGS -error_sti: + +error_entry_done: TRACE_IRQS_OFF ret @@ -1343,56 +1159,66 @@ error_sti: * for these here too. */ error_kernelspace: - CFI_REL_OFFSET rcx, RCX+8 - incl %ebx - leaq native_irq_return_iret(%rip),%rcx - cmpq %rcx,RIP+8(%rsp) - je error_bad_iret - movl %ecx,%eax /* zero extend */ - cmpq %rax,RIP+8(%rsp) - je bstep_iret - cmpq $gs_change,RIP+8(%rsp) - je error_swapgs - jmp error_sti + incl %ebx + leaq native_irq_return_iret(%rip), %rcx + cmpq %rcx, RIP+8(%rsp) + je error_bad_iret + movl %ecx, %eax /* zero extend */ + cmpq %rax, RIP+8(%rsp) + je bstep_iret + cmpq $gs_change, RIP+8(%rsp) + jne error_entry_done + + /* + * hack: gs_change can fail with user gsbase. If this happens, fix up + * gsbase and proceed. We'll fix up the exception and land in + * gs_change's error handler with kernel gsbase. + */ + SWAPGS + jmp error_entry_done bstep_iret: /* Fix truncated RIP */ - movq %rcx,RIP+8(%rsp) + movq %rcx, RIP+8(%rsp) /* fall through */ error_bad_iret: + /* + * We came from an IRET to user mode, so we have user gsbase. + * Switch to kernel gsbase: + */ SWAPGS - mov %rsp,%rdi - call fixup_bad_iret - mov %rax,%rsp - decl %ebx /* Return to usergs */ - jmp error_sti - CFI_ENDPROC + + /* + * Pretend that the exception came from user mode: set up pt_regs + * as if we faulted immediately after IRET and clear EBX so that + * error_exit knows that we will be returning to user mode. + */ + mov %rsp, %rdi + call fixup_bad_iret + mov %rax, %rsp + decl %ebx + jmp error_entry_done END(error_entry) -/* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */ +/* + * On entry, EBS is a "return to kernel mode" flag: + * 1: already in kernel mode, don't need SWAPGS + * 0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode + */ ENTRY(error_exit) - DEFAULT_FRAME - movl %ebx,%eax + movl %ebx, %eax RESTORE_EXTRA_REGS DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - GET_THREAD_INFO(%rcx) - testl %eax,%eax - jne retint_kernel - LOCKDEP_SYS_EXIT_IRQ - movl TI_flags(%rcx),%edx - movl $_TIF_WORK_MASK,%edi - andl %edi,%edx - jnz retint_careful - jmp retint_swapgs - CFI_ENDPROC + testl %eax, %eax + jnz retint_kernel + jmp retint_user END(error_exit) /* Runs on exception stack */ ENTRY(nmi) - INTR_FRAME PARAVIRT_ADJUST_EXCEPTION_FRAME /* * We allow breakpoints in NMIs. If a breakpoint occurs, then @@ -1433,8 +1259,7 @@ ENTRY(nmi) */ /* Use %rdx as our temp variable throughout */ - pushq_cfi %rdx - CFI_REL_OFFSET rdx, 0 + pushq %rdx testb $3, CS-RIP+8(%rsp) jz .Lnmi_from_kernel @@ -1450,7 +1275,7 @@ ENTRY(nmi) SWAPGS cld movq %rsp, %rdx - movq PER_CPU_VAR(kernel_stack), %rsp + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp pushq 5*8(%rdx) /* pt_regs->ss */ pushq 4*8(%rdx) /* pt_regs->rsp */ pushq 3*8(%rdx) /* pt_regs->flags */ @@ -1478,6 +1303,7 @@ ENTRY(nmi) * due to nesting -- we're on the normal thread stack and we're * done with the NMI stack. */ + movq %rsp, %rdi movq $-1, %rsi call do_nmi @@ -1556,8 +1382,8 @@ ENTRY(nmi) * This will not detect if we interrupted an outer NMI just * before IRET. */ - cmpl $1, -8(%rsp) - je nested_nmi + cmpl $1, -8(%rsp) + je nested_nmi /* * Now test if the previous stack was an NMI stack. This covers @@ -1576,6 +1402,7 @@ ENTRY(nmi) cmpq %rdx, 4*8(%rsp) /* If the stack pointer is above the NMI stack, this is a normal NMI */ ja first_nmi + subq $EXCEPTION_STKSZ, %rdx cmpq %rdx, 4*8(%rsp) /* If it is below the NMI stack, it is a normal NMI */ @@ -1588,55 +1415,60 @@ ENTRY(nmi) /* This is a nested NMI. */ - CFI_REMEMBER_STATE - nested_nmi: /* * Modify the "iret" frame to point to repeat_nmi, forcing another * iteration of NMI handling. */ - leaq -1*8(%rsp), %rdx - movq %rdx, %rsp - CFI_ADJUST_CFA_OFFSET 1*8 - leaq -10*8(%rsp), %rdx - pushq_cfi $__KERNEL_DS - pushq_cfi %rdx - pushfq_cfi - pushq_cfi $__KERNEL_CS - pushq_cfi $repeat_nmi + subq $8, %rsp + leaq -10*8(%rsp), %rdx + pushq $__KERNEL_DS + pushq %rdx + pushfq + pushq $__KERNEL_CS + pushq $repeat_nmi /* Put stack back */ - addq $(6*8), %rsp - CFI_ADJUST_CFA_OFFSET -6*8 + addq $(6*8), %rsp nested_nmi_out: - popq_cfi %rdx - CFI_RESTORE rdx + popq %rdx /* We are returning to kernel mode, so this cannot result in a fault. */ INTERRUPT_RETURN - CFI_RESTORE_STATE first_nmi: /* Restore rdx. */ - movq (%rsp), %rdx - CFI_RESTORE rdx + movq (%rsp), %rdx - /* Set "NMI executing" on the stack. */ - pushq_cfi $1 + /* Make room for "NMI executing". */ + pushq $0 /* Leave room for the "iret" frame */ - subq $(5*8), %rsp - CFI_ADJUST_CFA_OFFSET 5*8 + subq $(5*8), %rsp /* Copy the "original" frame to the "outermost" frame */ .rept 5 - pushq_cfi 11*8(%rsp) + pushq 11*8(%rsp) .endr - CFI_DEF_CFA_OFFSET 5*8 /* Everything up to here is safe from nested NMIs */ +#ifdef CONFIG_DEBUG_ENTRY + /* + * For ease of testing, unmask NMIs right away. Disabled by + * default because IRET is very expensive. + */ + pushq $0 /* SS */ + pushq %rsp /* RSP (minus 8 because of the previous push) */ + addq $8, (%rsp) /* Fix up RSP */ + pushfq /* RFLAGS */ + pushq $__KERNEL_CS /* CS */ + pushq $1f /* RIP */ + INTERRUPT_RETURN /* continues at repeat_nmi below */ +1: +#endif + repeat_nmi: /* * If there was a nested NMI, the first NMI's iret will return @@ -1650,24 +1482,21 @@ repeat_nmi: * RSP is pointing to "outermost RIP". gsbase is unknown, but, if * we're repeating an NMI, gsbase has the same value that it had on * the first iteration. paranoid_entry will load the kernel - * gsbase if needed before we call do_nmi. - * - * Set "NMI executing" in case we came back here via IRET. + * gsbase if needed before we call do_nmi. "NMI executing" + * is zero. */ - movq $1, 10*8(%rsp) + movq $1, 10*8(%rsp) /* Set "NMI executing". */ /* * Copy the "outermost" frame to the "iret" frame. NMIs that nest * here must not modify the "iret" frame while we're writing to * it or it will end up containing garbage. */ - addq $(10*8), %rsp - CFI_ADJUST_CFA_OFFSET -10*8 + addq $(10*8), %rsp .rept 5 - pushq_cfi -6*8(%rsp) + pushq -6*8(%rsp) .endr - subq $(5*8), %rsp - CFI_DEF_CFA_OFFSET 5*8 + subq $(5*8), %rsp end_repeat_nmi: /* @@ -1675,7 +1504,7 @@ end_repeat_nmi: * If this happens, then the inner NMI will change the "iret" * frame to point back to repeat_nmi. */ - pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ + pushq $-1 /* ORIG_RAX: no syscall to restart */ ALLOC_PT_GPREGS_ON_STACK /* @@ -1685,16 +1514,15 @@ end_repeat_nmi: * setting NEED_RESCHED or anything that normal interrupts and * exceptions might do. */ - call paranoid_entry - DEFAULT_FRAME 0 + call paranoid_entry /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */ - movq %rsp,%rdi - movq $-1,%rsi - call do_nmi + movq %rsp, %rdi + movq $-1, %rsi + call do_nmi - testl %ebx,%ebx /* swapgs needed? */ - jnz nmi_restore + testl %ebx, %ebx /* swapgs needed? */ + jnz nmi_restore nmi_swapgs: SWAPGS_UNSAFE_STACK nmi_restore: @@ -1721,13 +1549,9 @@ nmi_restore: * mode, so this cannot result in a fault. */ INTERRUPT_RETURN - CFI_ENDPROC END(nmi) ENTRY(ignore_sysret) - CFI_STARTPROC - mov $-ENOSYS,%eax + mov $-ENOSYS, %eax sysret - CFI_ENDPROC END(ignore_sysret) - diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S new file mode 100644 index 000000000..a7e257d9c --- /dev/null +++ b/arch/x86/entry/entry_64_compat.S @@ -0,0 +1,561 @@ +/* + * Compatibility mode system call entry point for x86-64. + * + * Copyright 2000-2002 Andi Kleen, SuSE Labs. + */ +#include "calling.h" +#include <asm/asm-offsets.h> +#include <asm/current.h> +#include <asm/errno.h> +#include <asm/ia32_unistd.h> +#include <asm/thread_info.h> +#include <asm/segment.h> +#include <asm/irqflags.h> +#include <asm/asm.h> +#include <asm/smap.h> +#include <linux/linkage.h> +#include <linux/err.h> + +/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ +#include <linux/elf-em.h> +#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE) +#define __AUDIT_ARCH_LE 0x40000000 + +#ifndef CONFIG_AUDITSYSCALL +# define sysexit_audit ia32_ret_from_sys_call +# define sysretl_audit ia32_ret_from_sys_call +#endif + + .section .entry.text, "ax" + +#ifdef CONFIG_PARAVIRT +ENTRY(native_usergs_sysret32) + swapgs + sysretl +ENDPROC(native_usergs_sysret32) +#endif + +/* + * 32-bit SYSENTER instruction entry. + * + * SYSENTER loads ss, rsp, cs, and rip from previously programmed MSRs. + * IF and VM in rflags are cleared (IOW: interrupts are off). + * SYSENTER does not save anything on the stack, + * and does not save old rip (!!!) and rflags. + * + * Arguments: + * eax system call number + * ebx arg1 + * ecx arg2 + * edx arg3 + * esi arg4 + * edi arg5 + * ebp user stack + * 0(%ebp) arg6 + * + * This is purely a fast path. For anything complicated we use the int 0x80 + * path below. We set up a complete hardware stack frame to share code + * with the int 0x80 path. + */ +ENTRY(entry_SYSENTER_compat) + /* + * Interrupts are off on entry. + * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON, + * it is too small to ever cause noticeable irq latency. + */ + SWAPGS_UNSAFE_STACK + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + ENABLE_INTERRUPTS(CLBR_NONE) + + /* Zero-extending 32-bit regs, do not remove */ + movl %ebp, %ebp + movl %eax, %eax + + movl ASM_THREAD_INFO(TI_sysenter_return, %rsp, 0), %r10d + + /* Construct struct pt_regs on stack */ + pushq $__USER32_DS /* pt_regs->ss */ + pushq %rbp /* pt_regs->sp */ + pushfq /* pt_regs->flags */ + pushq $__USER32_CS /* pt_regs->cs */ + pushq %r10 /* pt_regs->ip = thread_info->sysenter_return */ + pushq %rax /* pt_regs->orig_ax */ + pushq %rdi /* pt_regs->di */ + pushq %rsi /* pt_regs->si */ + pushq %rdx /* pt_regs->dx */ + pushq %rcx /* pt_regs->cx */ + pushq $-ENOSYS /* pt_regs->ax */ + cld + sub $(10*8), %rsp /* pt_regs->r8-11, bp, bx, r12-15 not saved */ + + /* + * no need to do an access_ok check here because rbp has been + * 32-bit zero extended + */ + ASM_STAC +1: movl (%rbp), %ebp + _ASM_EXTABLE(1b, ia32_badarg) + ASM_CLAC + + /* + * Sysenter doesn't filter flags, so we need to clear NT + * ourselves. To save a few cycles, we can check whether + * NT was set instead of doing an unconditional popfq. + */ + testl $X86_EFLAGS_NT, EFLAGS(%rsp) + jnz sysenter_fix_flags +sysenter_flags_fixed: + + orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) + testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) + jnz sysenter_tracesys + +sysenter_do_call: + /* 32-bit syscall -> 64-bit C ABI argument conversion */ + movl %edi, %r8d /* arg5 */ + movl %ebp, %r9d /* arg6 */ + xchg %ecx, %esi /* rsi:arg2, rcx:arg4 */ + movl %ebx, %edi /* arg1 */ + movl %edx, %edx /* arg3 (zero extension) */ +sysenter_dispatch: + cmpq $(IA32_NR_syscalls-1), %rax + ja 1f + call *ia32_sys_call_table(, %rax, 8) + movq %rax, RAX(%rsp) +1: + DISABLE_INTERRUPTS(CLBR_NONE) + TRACE_IRQS_OFF + testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) + jnz sysexit_audit +sysexit_from_sys_call: + /* + * NB: SYSEXIT is not obviously safe for 64-bit kernels -- an + * NMI between STI and SYSEXIT has poorly specified behavior, + * and and NMI followed by an IRQ with usergs is fatal. So + * we just pretend we're using SYSEXIT but we really use + * SYSRETL instead. + * + * This code path is still called 'sysexit' because it pairs + * with 'sysenter' and it uses the SYSENTER calling convention. + */ + andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) + movl RIP(%rsp), %ecx /* User %eip */ + movq RAX(%rsp), %rax + RESTORE_RSI_RDI + xorl %edx, %edx /* Do not leak kernel information */ + xorq %r8, %r8 + xorq %r9, %r9 + xorq %r10, %r10 + movl EFLAGS(%rsp), %r11d /* User eflags */ + TRACE_IRQS_ON + + /* + * SYSRETL works even on Intel CPUs. Use it in preference to SYSEXIT, + * since it avoids a dicey window with interrupts enabled. + */ + movl RSP(%rsp), %esp + + /* + * USERGS_SYSRET32 does: + * gsbase = user's gs base + * eip = ecx + * rflags = r11 + * cs = __USER32_CS + * ss = __USER_DS + * + * The prologue set RIP(%rsp) to VDSO32_SYSENTER_RETURN, which does: + * + * pop %ebp + * pop %edx + * pop %ecx + * + * Therefore, we invoke SYSRETL with EDX and R8-R10 zeroed to + * avoid info leaks. R11 ends up with VDSO32_SYSENTER_RETURN's + * address (already known to user code), and R12-R15 are + * callee-saved and therefore don't contain any interesting + * kernel data. + */ + USERGS_SYSRET32 + +#ifdef CONFIG_AUDITSYSCALL + .macro auditsys_entry_common + /* + * At this point, registers hold syscall args in the 32-bit syscall ABI: + * EAX is syscall number, the 6 args are in EBX,ECX,EDX,ESI,EDI,EBP. + * + * We want to pass them to __audit_syscall_entry(), which is a 64-bit + * C function with 5 parameters, so shuffle them to match what + * the function expects: RDI,RSI,RDX,RCX,R8. + */ + movl %esi, %r8d /* arg5 (R8 ) <= 4th syscall arg (ESI) */ + xchg %ecx, %edx /* arg4 (RCX) <= 3rd syscall arg (EDX) */ + /* arg3 (RDX) <= 2nd syscall arg (ECX) */ + movl %ebx, %esi /* arg2 (RSI) <= 1st syscall arg (EBX) */ + movl %eax, %edi /* arg1 (RDI) <= syscall number (EAX) */ + call __audit_syscall_entry + + /* + * We are going to jump back to the syscall dispatch code. + * Prepare syscall args as required by the 64-bit C ABI. + * Registers clobbered by __audit_syscall_entry() are + * loaded from pt_regs on stack: + */ + movl ORIG_RAX(%rsp), %eax /* syscall number */ + movl %ebx, %edi /* arg1 */ + movl RCX(%rsp), %esi /* arg2 */ + movl RDX(%rsp), %edx /* arg3 */ + movl RSI(%rsp), %ecx /* arg4 */ + movl RDI(%rsp), %r8d /* arg5 */ + .endm + + .macro auditsys_exit exit + testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) + jnz ia32_ret_from_sys_call + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_NONE) + movl %eax, %esi /* second arg, syscall return value */ + cmpl $-MAX_ERRNO, %eax /* is it an error ? */ + jbe 1f + movslq %eax, %rsi /* if error sign extend to 64 bits */ +1: setbe %al /* 1 if error, 0 if not */ + movzbl %al, %edi /* zero-extend that into %edi */ + call __audit_syscall_exit + movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %edi + DISABLE_INTERRUPTS(CLBR_NONE) + TRACE_IRQS_OFF + testl %edi, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) + jz \exit + xorl %eax, %eax /* Do not leak kernel information */ + movq %rax, R11(%rsp) + movq %rax, R10(%rsp) + movq %rax, R9(%rsp) + movq %rax, R8(%rsp) + jmp int_with_check + .endm + +sysenter_auditsys: + auditsys_entry_common + movl %ebp, %r9d /* reload 6th syscall arg */ + jmp sysenter_dispatch + +sysexit_audit: + auditsys_exit sysexit_from_sys_call +#endif + +sysenter_fix_flags: + pushq $(X86_EFLAGS_IF|X86_EFLAGS_FIXED) + popfq + jmp sysenter_flags_fixed + +sysenter_tracesys: +#ifdef CONFIG_AUDITSYSCALL + testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) + jz sysenter_auditsys +#endif + SAVE_EXTRA_REGS + xorl %eax, %eax /* Do not leak kernel information */ + movq %rax, R11(%rsp) + movq %rax, R10(%rsp) + movq %rax, R9(%rsp) + movq %rax, R8(%rsp) + movq %rsp, %rdi /* &pt_regs -> arg1 */ + call syscall_trace_enter + + /* Reload arg registers from stack. (see sysenter_tracesys) */ + movl RCX(%rsp), %ecx + movl RDX(%rsp), %edx + movl RSI(%rsp), %esi + movl RDI(%rsp), %edi + movl %eax, %eax /* zero extension */ + + RESTORE_EXTRA_REGS + jmp sysenter_do_call +ENDPROC(entry_SYSENTER_compat) + +/* + * 32-bit SYSCALL instruction entry. + * + * 32-bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11, + * then loads new ss, cs, and rip from previously programmed MSRs. + * rflags gets masked by a value from another MSR (so CLD and CLAC + * are not needed). SYSCALL does not save anything on the stack + * and does not change rsp. + * + * Note: rflags saving+masking-with-MSR happens only in Long mode + * (in legacy 32-bit mode, IF, RF and VM bits are cleared and that's it). + * Don't get confused: rflags saving+masking depends on Long Mode Active bit + * (EFER.LMA=1), NOT on bitness of userspace where SYSCALL executes + * or target CS descriptor's L bit (SYSCALL does not read segment descriptors). + * + * Arguments: + * eax system call number + * ecx return address + * ebx arg1 + * ebp arg2 (note: not saved in the stack frame, should not be touched) + * edx arg3 + * esi arg4 + * edi arg5 + * esp user stack + * 0(%esp) arg6 + * + * This is purely a fast path. For anything complicated we use the int 0x80 + * path below. We set up a complete hardware stack frame to share code + * with the int 0x80 path. + */ +ENTRY(entry_SYSCALL_compat) + /* + * Interrupts are off on entry. + * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON, + * it is too small to ever cause noticeable irq latency. + */ + SWAPGS_UNSAFE_STACK + movl %esp, %r8d + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + ENABLE_INTERRUPTS(CLBR_NONE) + + /* Zero-extending 32-bit regs, do not remove */ + movl %eax, %eax + + /* Construct struct pt_regs on stack */ + pushq $__USER32_DS /* pt_regs->ss */ + pushq %r8 /* pt_regs->sp */ + pushq %r11 /* pt_regs->flags */ + pushq $__USER32_CS /* pt_regs->cs */ + pushq %rcx /* pt_regs->ip */ + pushq %rax /* pt_regs->orig_ax */ + pushq %rdi /* pt_regs->di */ + pushq %rsi /* pt_regs->si */ + pushq %rdx /* pt_regs->dx */ + pushq %rbp /* pt_regs->cx */ + movl %ebp, %ecx + pushq $-ENOSYS /* pt_regs->ax */ + sub $(10*8), %rsp /* pt_regs->r8-11, bp, bx, r12-15 not saved */ + + /* + * No need to do an access_ok check here because r8 has been + * 32-bit zero extended: + */ + ASM_STAC +1: movl (%r8), %r9d + _ASM_EXTABLE(1b, ia32_badarg) + ASM_CLAC + orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) + testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) + jnz cstar_tracesys + +cstar_do_call: + /* 32-bit syscall -> 64-bit C ABI argument conversion */ + movl %edi, %r8d /* arg5 */ + /* r9 already loaded */ /* arg6 */ + xchg %ecx, %esi /* rsi:arg2, rcx:arg4 */ + movl %ebx, %edi /* arg1 */ + movl %edx, %edx /* arg3 (zero extension) */ + +cstar_dispatch: + cmpq $(IA32_NR_syscalls-1), %rax + ja 1f + + call *ia32_sys_call_table(, %rax, 8) + movq %rax, RAX(%rsp) +1: + DISABLE_INTERRUPTS(CLBR_NONE) + TRACE_IRQS_OFF + testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) + jnz sysretl_audit + +sysretl_from_sys_call: + andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) + RESTORE_RSI_RDI_RDX + movl RIP(%rsp), %ecx + movl EFLAGS(%rsp), %r11d + movq RAX(%rsp), %rax + xorq %r10, %r10 + xorq %r9, %r9 + xorq %r8, %r8 + TRACE_IRQS_ON + movl RSP(%rsp), %esp + /* + * 64-bit->32-bit SYSRET restores eip from ecx, + * eflags from r11 (but RF and VM bits are forced to 0), + * cs and ss are loaded from MSRs. + * (Note: 32-bit->32-bit SYSRET is different: since r11 + * does not exist, it merely sets eflags.IF=1). + * + * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss + * descriptor is not reinitialized. This means that we must + * avoid SYSRET with SS == NULL, which could happen if we schedule, + * exit the kernel, and re-enter using an interrupt vector. (All + * interrupt entries on x86_64 set SS to NULL.) We prevent that + * from happening by reloading SS in __switch_to. + */ + USERGS_SYSRET32 + +#ifdef CONFIG_AUDITSYSCALL +cstar_auditsys: + movl %r9d, R9(%rsp) /* register to be clobbered by call */ + auditsys_entry_common + movl R9(%rsp), %r9d /* reload 6th syscall arg */ + jmp cstar_dispatch + +sysretl_audit: + auditsys_exit sysretl_from_sys_call +#endif + +cstar_tracesys: +#ifdef CONFIG_AUDITSYSCALL + testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) + jz cstar_auditsys +#endif + xchgl %r9d, %ebp + SAVE_EXTRA_REGS + xorl %eax, %eax /* Do not leak kernel information */ + movq %rax, R11(%rsp) + movq %rax, R10(%rsp) + movq %r9, R9(%rsp) + movq %rax, R8(%rsp) + movq %rsp, %rdi /* &pt_regs -> arg1 */ + call syscall_trace_enter + movl R9(%rsp), %r9d + + /* Reload arg registers from stack. (see sysenter_tracesys) */ + movl RCX(%rsp), %ecx + movl RDX(%rsp), %edx + movl RSI(%rsp), %esi + movl RDI(%rsp), %edi + movl %eax, %eax /* zero extension */ + + RESTORE_EXTRA_REGS + xchgl %ebp, %r9d + jmp cstar_do_call +END(entry_SYSCALL_compat) + +ia32_badarg: + ASM_CLAC + movq $-EFAULT, RAX(%rsp) +ia32_ret_from_sys_call: + xorl %eax, %eax /* Do not leak kernel information */ + movq %rax, R11(%rsp) + movq %rax, R10(%rsp) + movq %rax, R9(%rsp) + movq %rax, R8(%rsp) + jmp int_ret_from_sys_call + +/* + * Emulated IA32 system calls via int 0x80. + * + * Arguments: + * eax system call number + * ebx arg1 + * ecx arg2 + * edx arg3 + * esi arg4 + * edi arg5 + * ebp arg6 (note: not saved in the stack frame, should not be touched) + * + * Notes: + * Uses the same stack frame as the x86-64 version. + * All registers except eax must be saved (but ptrace may violate that). + * Arguments are zero extended. For system calls that want sign extension and + * take long arguments a wrapper is needed. Most calls can just be called + * directly. + * Assumes it is only called from user space and entered with interrupts off. + */ + +ENTRY(entry_INT80_compat) + /* + * Interrupts are off on entry. + * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON, + * it is too small to ever cause noticeable irq latency. + */ + PARAVIRT_ADJUST_EXCEPTION_FRAME + SWAPGS + ENABLE_INTERRUPTS(CLBR_NONE) + + /* Zero-extending 32-bit regs, do not remove */ + movl %eax, %eax + + /* Construct struct pt_regs on stack (iret frame is already on stack) */ + pushq %rax /* pt_regs->orig_ax */ + pushq %rdi /* pt_regs->di */ + pushq %rsi /* pt_regs->si */ + pushq %rdx /* pt_regs->dx */ + pushq %rcx /* pt_regs->cx */ + pushq $-ENOSYS /* pt_regs->ax */ + pushq $0 /* pt_regs->r8 */ + pushq $0 /* pt_regs->r9 */ + pushq $0 /* pt_regs->r10 */ + pushq $0 /* pt_regs->r11 */ + cld + sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */ + + orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) + testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) + jnz ia32_tracesys + +ia32_do_call: + /* 32-bit syscall -> 64-bit C ABI argument conversion */ + movl %edi, %r8d /* arg5 */ + movl %ebp, %r9d /* arg6 */ + xchg %ecx, %esi /* rsi:arg2, rcx:arg4 */ + movl %ebx, %edi /* arg1 */ + movl %edx, %edx /* arg3 (zero extension) */ + cmpq $(IA32_NR_syscalls-1), %rax + ja 1f + + call *ia32_sys_call_table(, %rax, 8) + movq %rax, RAX(%rsp) +1: + jmp int_ret_from_sys_call + +ia32_tracesys: + SAVE_EXTRA_REGS + movq %rsp, %rdi /* &pt_regs -> arg1 */ + call syscall_trace_enter + /* + * Reload arg registers from stack in case ptrace changed them. + * Don't reload %eax because syscall_trace_enter() returned + * the %rax value we should see. But do truncate it to 32 bits. + * If it's -1 to make us punt the syscall, then (u32)-1 is still + * an appropriately invalid value. + */ + movl RCX(%rsp), %ecx + movl RDX(%rsp), %edx + movl RSI(%rsp), %esi + movl RDI(%rsp), %edi + movl %eax, %eax /* zero extension */ + RESTORE_EXTRA_REGS + jmp ia32_do_call +END(entry_INT80_compat) + + .macro PTREGSCALL label, func + ALIGN +GLOBAL(\label) + leaq \func(%rip), %rax + jmp ia32_ptregs_common + .endm + + PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn + PTREGSCALL stub32_sigreturn, sys32_sigreturn + PTREGSCALL stub32_fork, sys_fork + PTREGSCALL stub32_vfork, sys_vfork + + ALIGN +GLOBAL(stub32_clone) + leaq sys_clone(%rip), %rax + /* + * The 32-bit clone ABI is: clone(..., int tls_val, int *child_tidptr). + * The 64-bit clone ABI is: clone(..., int *child_tidptr, int tls_val). + * + * The native 64-bit kernel's sys_clone() implements the latter, + * so we need to swap arguments here before calling it: + */ + xchg %r8, %rcx + jmp ia32_ptregs_common + + ALIGN +ia32_ptregs_common: + SAVE_EXTRA_REGS 8 + call *%rax + RESTORE_EXTRA_REGS 8 + ret +END(ia32_ptregs_common) diff --git a/arch/x86/kernel/syscall_32.c b/arch/x86/entry/syscall_32.c index 3777189c4..8ea34f94e 100644 --- a/arch/x86/kernel/syscall_32.c +++ b/arch/x86/entry/syscall_32.c @@ -10,7 +10,7 @@ #else #define SYM(sym, compat) sym #define ia32_sys_call_table sys_call_table -#define __NR_ia32_syscall_max __NR_syscall_max +#define __NR_syscall_compat_max __NR_syscall_max #endif #define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void SYM(sym, compat)(void) ; @@ -23,11 +23,11 @@ typedef asmlinkage void (*sys_call_ptr_t)(void); extern asmlinkage void sys_ni_syscall(void); -__visible const sys_call_ptr_t ia32_sys_call_table[__NR_ia32_syscall_max+1] = { +__visible const sys_call_ptr_t ia32_sys_call_table[__NR_syscall_compat_max+1] = { /* * Smells like a compiler bug -- it doesn't work * when the & below is removed. */ - [0 ... __NR_ia32_syscall_max] = &sys_ni_syscall, + [0 ... __NR_syscall_compat_max] = &sys_ni_syscall, #include <asm/syscalls_32.h> }; diff --git a/arch/x86/kernel/syscall_64.c b/arch/x86/entry/syscall_64.c index 4ac730b37..4ac730b37 100644 --- a/arch/x86/kernel/syscall_64.c +++ b/arch/x86/entry/syscall_64.c diff --git a/arch/x86/syscalls/Makefile b/arch/x86/entry/syscalls/Makefile index a55abb9f6..57aa59fd1 100644 --- a/arch/x86/syscalls/Makefile +++ b/arch/x86/entry/syscalls/Makefile @@ -1,5 +1,5 @@ -out := $(obj)/../include/generated/asm -uapi := $(obj)/../include/generated/uapi/asm +out := $(obj)/../../include/generated/asm +uapi := $(obj)/../../include/generated/uapi/asm # Create output directory if not already present _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') \ diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index ef8187f9d..ef8187f9d 100644 --- a/arch/x86/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 9ef32d5f1..9ef32d5f1 100644 --- a/arch/x86/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl diff --git a/arch/x86/syscalls/syscallhdr.sh b/arch/x86/entry/syscalls/syscallhdr.sh index 31fd5f1f3..31fd5f1f3 100644 --- a/arch/x86/syscalls/syscallhdr.sh +++ b/arch/x86/entry/syscalls/syscallhdr.sh diff --git a/arch/x86/syscalls/syscalltbl.sh b/arch/x86/entry/syscalls/syscalltbl.sh index 0e7f8ec07..0e7f8ec07 100644 --- a/arch/x86/syscalls/syscalltbl.sh +++ b/arch/x86/entry/syscalls/syscalltbl.sh diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/entry/thunk_32.S index 5eb715087..e5a17114a 100644 --- a/arch/x86/lib/thunk_32.S +++ b/arch/x86/entry/thunk_32.S @@ -6,16 +6,14 @@ */ #include <linux/linkage.h> #include <asm/asm.h> - #include <asm/dwarf2.h> /* put return address in eax (arg1) */ .macro THUNK name, func, put_ret_addr_in_eax=0 .globl \name \name: - CFI_STARTPROC - pushl_cfi_reg eax - pushl_cfi_reg ecx - pushl_cfi_reg edx + pushl %eax + pushl %ecx + pushl %edx .if \put_ret_addr_in_eax /* Place EIP in the arg1 */ @@ -23,11 +21,10 @@ .endif call \func - popl_cfi_reg edx - popl_cfi_reg ecx - popl_cfi_reg eax + popl %edx + popl %ecx + popl %eax ret - CFI_ENDPROC _ASM_NOKPROBE(\name) .endm @@ -38,8 +35,6 @@ #ifdef CONFIG_PREEMPT THUNK ___preempt_schedule, preempt_schedule -#ifdef CONFIG_CONTEXT_TRACKING - THUNK ___preempt_schedule_context, preempt_schedule_context -#endif + THUNK ___preempt_schedule_notrace, preempt_schedule_notrace #endif diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/entry/thunk_64.S index f89ba4e93..efb2b932b 100644 --- a/arch/x86/lib/thunk_64.S +++ b/arch/x86/entry/thunk_64.S @@ -6,35 +6,32 @@ * Subject to the GNU public license, v.2. No warranty of any kind. */ #include <linux/linkage.h> -#include <asm/dwarf2.h> -#include <asm/calling.h> +#include "calling.h" #include <asm/asm.h> /* rdi: arg1 ... normal C conventions. rax is saved/restored. */ .macro THUNK name, func, put_ret_addr_in_rdi=0 .globl \name \name: - CFI_STARTPROC /* this one pushes 9 elems, the next one would be %rIP */ - pushq_cfi_reg rdi - pushq_cfi_reg rsi - pushq_cfi_reg rdx - pushq_cfi_reg rcx - pushq_cfi_reg rax - pushq_cfi_reg r8 - pushq_cfi_reg r9 - pushq_cfi_reg r10 - pushq_cfi_reg r11 + pushq %rdi + pushq %rsi + pushq %rdx + pushq %rcx + pushq %rax + pushq %r8 + pushq %r9 + pushq %r10 + pushq %r11 .if \put_ret_addr_in_rdi /* 9*8(%rsp) is return addr on stack */ - movq_cfi_restore 9*8, rdi + movq 9*8(%rsp), %rdi .endif call \func jmp restore - CFI_ENDPROC _ASM_NOKPROBE(\name) .endm @@ -49,27 +46,22 @@ #ifdef CONFIG_PREEMPT THUNK ___preempt_schedule, preempt_schedule -#ifdef CONFIG_CONTEXT_TRACKING - THUNK ___preempt_schedule_context, preempt_schedule_context -#endif + THUNK ___preempt_schedule_notrace, preempt_schedule_notrace #endif #if defined(CONFIG_TRACE_IRQFLAGS) \ || defined(CONFIG_DEBUG_LOCK_ALLOC) \ || defined(CONFIG_PREEMPT) - CFI_STARTPROC - CFI_ADJUST_CFA_OFFSET 9*8 restore: - popq_cfi_reg r11 - popq_cfi_reg r10 - popq_cfi_reg r9 - popq_cfi_reg r8 - popq_cfi_reg rax - popq_cfi_reg rcx - popq_cfi_reg rdx - popq_cfi_reg rsi - popq_cfi_reg rdi + popq %r11 + popq %r10 + popq %r9 + popq %r8 + popq %rax + popq %rcx + popq %rdx + popq %rsi + popq %rdi ret - CFI_ENDPROC _ASM_NOKPROBE(restore) #endif diff --git a/arch/x86/vdso/.gitignore b/arch/x86/entry/vdso/.gitignore index aae8ffdd5..aae8ffdd5 100644 --- a/arch/x86/vdso/.gitignore +++ b/arch/x86/entry/vdso/.gitignore diff --git a/arch/x86/vdso/Makefile b/arch/x86/entry/vdso/Makefile index e97032069..e97032069 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile diff --git a/arch/x86/vdso/checkundef.sh b/arch/x86/entry/vdso/checkundef.sh index 7ee90a9b5..7ee90a9b5 100644..100755 --- a/arch/x86/vdso/checkundef.sh +++ b/arch/x86/entry/vdso/checkundef.sh diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index 979332275..979332275 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c diff --git a/arch/x86/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S index de2c92102..de2c92102 100644 --- a/arch/x86/vdso/vdso-layout.lds.S +++ b/arch/x86/entry/vdso/vdso-layout.lds.S diff --git a/arch/x86/vdso/vdso-note.S b/arch/x86/entry/vdso/vdso-note.S index 79a071e43..79a071e43 100644 --- a/arch/x86/vdso/vdso-note.S +++ b/arch/x86/entry/vdso/vdso-note.S diff --git a/arch/x86/vdso/vdso.lds.S b/arch/x86/entry/vdso/vdso.lds.S index 680793264..680793264 100644 --- a/arch/x86/vdso/vdso.lds.S +++ b/arch/x86/entry/vdso/vdso.lds.S diff --git a/arch/x86/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c index 8627db24a..8627db24a 100644 --- a/arch/x86/vdso/vdso2c.c +++ b/arch/x86/entry/vdso/vdso2c.c diff --git a/arch/x86/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h index 022498755..022498755 100644 --- a/arch/x86/vdso/vdso2c.h +++ b/arch/x86/entry/vdso/vdso2c.h diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c index e904c2705..e904c2705 100644 --- a/arch/x86/vdso/vdso32-setup.c +++ b/arch/x86/entry/vdso/vdso32-setup.c diff --git a/arch/x86/vdso/vdso32/.gitignore b/arch/x86/entry/vdso/vdso32/.gitignore index e45fba9d0..e45fba9d0 100644 --- a/arch/x86/vdso/vdso32/.gitignore +++ b/arch/x86/entry/vdso/vdso32/.gitignore diff --git a/arch/x86/vdso/vdso32/int80.S b/arch/x86/entry/vdso/vdso32/int80.S index b15b7c01a..b15b7c01a 100644 --- a/arch/x86/vdso/vdso32/int80.S +++ b/arch/x86/entry/vdso/vdso32/int80.S diff --git a/arch/x86/vdso/vdso32/note.S b/arch/x86/entry/vdso/vdso32/note.S index c83f25734..c83f25734 100644 --- a/arch/x86/vdso/vdso32/note.S +++ b/arch/x86/entry/vdso/vdso32/note.S diff --git a/arch/x86/vdso/vdso32/sigreturn.S b/arch/x86/entry/vdso/vdso32/sigreturn.S index d7ec4e251..d7ec4e251 100644 --- a/arch/x86/vdso/vdso32/sigreturn.S +++ b/arch/x86/entry/vdso/vdso32/sigreturn.S diff --git a/arch/x86/vdso/vdso32/syscall.S b/arch/x86/entry/vdso/vdso32/syscall.S index 6b286bb52..6b286bb52 100644 --- a/arch/x86/vdso/vdso32/syscall.S +++ b/arch/x86/entry/vdso/vdso32/syscall.S diff --git a/arch/x86/vdso/vdso32/sysenter.S b/arch/x86/entry/vdso/vdso32/sysenter.S index e354bceee..e354bceee 100644 --- a/arch/x86/vdso/vdso32/sysenter.S +++ b/arch/x86/entry/vdso/vdso32/sysenter.S diff --git a/arch/x86/vdso/vdso32/vclock_gettime.c b/arch/x86/entry/vdso/vdso32/vclock_gettime.c index 175cc72c0..175cc72c0 100644 --- a/arch/x86/vdso/vdso32/vclock_gettime.c +++ b/arch/x86/entry/vdso/vdso32/vclock_gettime.c diff --git a/arch/x86/vdso/vdso32/vdso-fakesections.c b/arch/x86/entry/vdso/vdso32/vdso-fakesections.c index 541468e25..541468e25 100644 --- a/arch/x86/vdso/vdso32/vdso-fakesections.c +++ b/arch/x86/entry/vdso/vdso32/vdso-fakesections.c diff --git a/arch/x86/vdso/vdso32/vdso32.lds.S b/arch/x86/entry/vdso/vdso32/vdso32.lds.S index 31056cf29..31056cf29 100644 --- a/arch/x86/vdso/vdso32/vdso32.lds.S +++ b/arch/x86/entry/vdso/vdso32/vdso32.lds.S diff --git a/arch/x86/vdso/vdsox32.lds.S b/arch/x86/entry/vdso/vdsox32.lds.S index 697c11ece..697c11ece 100644 --- a/arch/x86/vdso/vdsox32.lds.S +++ b/arch/x86/entry/vdso/vdsox32.lds.S diff --git a/arch/x86/vdso/vgetcpu.c b/arch/x86/entry/vdso/vgetcpu.c index 8ec3d1f4c..8ec3d1f4c 100644 --- a/arch/x86/vdso/vgetcpu.c +++ b/arch/x86/entry/vdso/vgetcpu.c diff --git a/arch/x86/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 1c9f750c3..1c9f750c3 100644 --- a/arch/x86/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c diff --git a/arch/x86/entry/vsyscall/Makefile b/arch/x86/entry/vsyscall/Makefile new file mode 100644 index 000000000..a9f4856f6 --- /dev/null +++ b/arch/x86/entry/vsyscall/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for the x86 low level vsyscall code +# +obj-y := vsyscall_gtod.o + +obj-$(CONFIG_X86_VSYSCALL_EMULATION) += vsyscall_64.o vsyscall_emu_64.o + diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index 2dcc6ff6f..2dcc6ff6f 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c diff --git a/arch/x86/kernel/vsyscall_emu_64.S b/arch/x86/entry/vsyscall/vsyscall_emu_64.S index c9596a9af..c9596a9af 100644 --- a/arch/x86/kernel/vsyscall_emu_64.S +++ b/arch/x86/entry/vsyscall/vsyscall_emu_64.S diff --git a/arch/x86/kernel/vsyscall_gtod.c b/arch/x86/entry/vsyscall/vsyscall_gtod.c index 51e330416..51e330416 100644 --- a/arch/x86/kernel/vsyscall_gtod.c +++ b/arch/x86/entry/vsyscall/vsyscall_gtod.c diff --git a/arch/x86/kernel/vsyscall_trace.h b/arch/x86/entry/vsyscall/vsyscall_trace.h index a8b2edec5..9dd7359a3 100644 --- a/arch/x86/kernel/vsyscall_trace.h +++ b/arch/x86/entry/vsyscall/vsyscall_trace.h @@ -24,6 +24,6 @@ TRACE_EVENT(emulate_vsyscall, #endif #undef TRACE_INCLUDE_PATH -#define TRACE_INCLUDE_PATH ../../arch/x86/kernel +#define TRACE_INCLUDE_PATH ../../arch/x86/entry/vsyscall/ #define TRACE_INCLUDE_FILE vsyscall_trace #include <trace/define_trace.h> diff --git a/arch/x86/ia32/Makefile b/arch/x86/ia32/Makefile index bb635c641..cd4339bae 100644 --- a/arch/x86/ia32/Makefile +++ b/arch/x86/ia32/Makefile @@ -2,7 +2,7 @@ # Makefile for the ia32 kernel emulation subsystem. # -obj-$(CONFIG_IA32_EMULATION) := ia32entry.o sys_ia32.o ia32_signal.o +obj-$(CONFIG_IA32_EMULATION) := sys_ia32.o ia32_signal.o obj-$(CONFIG_IA32_AOUT) += ia32_aout.o diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index c81d35e6c..ae3a29ae8 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -21,8 +21,8 @@ #include <linux/binfmts.h> #include <asm/ucontext.h> #include <asm/uaccess.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> +#include <asm/fpu/signal.h> #include <asm/ptrace.h> #include <asm/ia32_unistd.h> #include <asm/user32.h> @@ -198,7 +198,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs, buf = compat_ptr(tmp); } get_user_catch(err); - err |= restore_xstate_sig(buf, 1); + err |= fpu__restore_sig(buf, 1); force_iret(); @@ -308,6 +308,7 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size, void __user **fpstate) { + struct fpu *fpu = ¤t->thread.fpu; unsigned long sp; /* Default to using normal stack */ @@ -322,12 +323,12 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, ksig->ka.sa.sa_restorer) sp = (unsigned long) ksig->ka.sa.sa_restorer; - if (used_math()) { + if (fpu->fpstate_active) { unsigned long fx_aligned, math_size; - sp = alloc_mathframe(sp, 1, &fx_aligned, &math_size); + sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size); *fpstate = (struct _fpstate_ia32 __user *) sp; - if (save_xstate_sig(*fpstate, (void __user *)fx_aligned, + if (copy_fpstate_to_sigframe(*fpstate, (void __user *)fx_aligned, math_size) < 0) return (void __user *) -1L; } diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S deleted file mode 100644 index 72bf2680f..000000000 --- a/arch/x86/ia32/ia32entry.S +++ /dev/null @@ -1,611 +0,0 @@ -/* - * Compatibility mode system call entry point for x86-64. - * - * Copyright 2000-2002 Andi Kleen, SuSE Labs. - */ - -#include <asm/dwarf2.h> -#include <asm/calling.h> -#include <asm/asm-offsets.h> -#include <asm/current.h> -#include <asm/errno.h> -#include <asm/ia32_unistd.h> -#include <asm/thread_info.h> -#include <asm/segment.h> -#include <asm/irqflags.h> -#include <asm/asm.h> -#include <asm/smap.h> -#include <linux/linkage.h> -#include <linux/err.h> - -/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ -#include <linux/elf-em.h> -#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE) -#define __AUDIT_ARCH_LE 0x40000000 - -#ifndef CONFIG_AUDITSYSCALL -#define sysexit_audit ia32_ret_from_sys_call -#define sysretl_audit ia32_ret_from_sys_call -#endif - - .section .entry.text, "ax" - - /* clobbers %rax */ - .macro CLEAR_RREGS _r9=rax - xorl %eax,%eax - movq %rax,R11(%rsp) - movq %rax,R10(%rsp) - movq %\_r9,R9(%rsp) - movq %rax,R8(%rsp) - .endm - - /* - * Reload arg registers from stack in case ptrace changed them. - * We don't reload %eax because syscall_trace_enter() returned - * the %rax value we should see. Instead, we just truncate that - * value to 32 bits again as we did on entry from user mode. - * If it's a new value set by user_regset during entry tracing, - * this matches the normal truncation of the user-mode value. - * If it's -1 to make us punt the syscall, then (u32)-1 is still - * an appropriately invalid value. - */ - .macro LOAD_ARGS32 _r9=0 - .if \_r9 - movl R9(%rsp),%r9d - .endif - movl RCX(%rsp),%ecx - movl RDX(%rsp),%edx - movl RSI(%rsp),%esi - movl RDI(%rsp),%edi - movl %eax,%eax /* zero extension */ - .endm - - .macro CFI_STARTPROC32 simple - CFI_STARTPROC \simple - CFI_UNDEFINED r8 - CFI_UNDEFINED r9 - CFI_UNDEFINED r10 - CFI_UNDEFINED r11 - CFI_UNDEFINED r12 - CFI_UNDEFINED r13 - CFI_UNDEFINED r14 - CFI_UNDEFINED r15 - .endm - -#ifdef CONFIG_PARAVIRT -ENTRY(native_usergs_sysret32) - swapgs - sysretl -ENDPROC(native_usergs_sysret32) - -ENTRY(native_irq_enable_sysexit) - swapgs - sti - sysexit -ENDPROC(native_irq_enable_sysexit) -#endif - -/* - * 32bit SYSENTER instruction entry. - * - * SYSENTER loads ss, rsp, cs, and rip from previously programmed MSRs. - * IF and VM in rflags are cleared (IOW: interrupts are off). - * SYSENTER does not save anything on the stack, - * and does not save old rip (!!!) and rflags. - * - * Arguments: - * eax system call number - * ebx arg1 - * ecx arg2 - * edx arg3 - * esi arg4 - * edi arg5 - * ebp user stack - * 0(%ebp) arg6 - * - * This is purely a fast path. For anything complicated we use the int 0x80 - * path below. We set up a complete hardware stack frame to share code - * with the int 0x80 path. - */ -ENTRY(ia32_sysenter_target) - CFI_STARTPROC32 simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA rsp,0 - CFI_REGISTER rsp,rbp - - /* - * Interrupts are off on entry. - * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON, - * it is too small to ever cause noticeable irq latency. - */ - SWAPGS_UNSAFE_STACK - movq PER_CPU_VAR(cpu_tss + TSS_sp0), %rsp - ENABLE_INTERRUPTS(CLBR_NONE) - - /* Zero-extending 32-bit regs, do not remove */ - movl %ebp, %ebp - movl %eax, %eax - - movl ASM_THREAD_INFO(TI_sysenter_return, %rsp, 0), %r10d - CFI_REGISTER rip,r10 - - /* Construct struct pt_regs on stack */ - pushq_cfi $__USER32_DS /* pt_regs->ss */ - pushq_cfi %rbp /* pt_regs->sp */ - CFI_REL_OFFSET rsp,0 - pushfq_cfi /* pt_regs->flags */ - pushq_cfi $__USER32_CS /* pt_regs->cs */ - pushq_cfi %r10 /* pt_regs->ip = thread_info->sysenter_return */ - CFI_REL_OFFSET rip,0 - pushq_cfi_reg rax /* pt_regs->orig_ax */ - pushq_cfi_reg rdi /* pt_regs->di */ - pushq_cfi_reg rsi /* pt_regs->si */ - pushq_cfi_reg rdx /* pt_regs->dx */ - pushq_cfi_reg rcx /* pt_regs->cx */ - pushq_cfi_reg rax /* pt_regs->ax */ - cld - sub $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */ - CFI_ADJUST_CFA_OFFSET 10*8 - - /* - * no need to do an access_ok check here because rbp has been - * 32bit zero extended - */ - ASM_STAC -1: movl (%rbp),%ebp - _ASM_EXTABLE(1b,ia32_badarg) - ASM_CLAC - - /* - * Sysenter doesn't filter flags, so we need to clear NT - * ourselves. To save a few cycles, we can check whether - * NT was set instead of doing an unconditional popfq. - */ - testl $X86_EFLAGS_NT,EFLAGS(%rsp) - jnz sysenter_fix_flags -sysenter_flags_fixed: - - orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) - testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - CFI_REMEMBER_STATE - jnz sysenter_tracesys - cmpq $(IA32_NR_syscalls-1),%rax - ja ia32_badsys -sysenter_do_call: - /* 32bit syscall -> 64bit C ABI argument conversion */ - movl %edi,%r8d /* arg5 */ - movl %ebp,%r9d /* arg6 */ - xchg %ecx,%esi /* rsi:arg2, rcx:arg4 */ - movl %ebx,%edi /* arg1 */ - movl %edx,%edx /* arg3 (zero extension) */ -sysenter_dispatch: - call *ia32_sys_call_table(,%rax,8) - movq %rax,RAX(%rsp) - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - jnz sysexit_audit -sysexit_from_sys_call: - /* - * NB: SYSEXIT is not obviously safe for 64-bit kernels -- an - * NMI between STI and SYSEXIT has poorly specified behavior, - * and and NMI followed by an IRQ with usergs is fatal. So - * we just pretend we're using SYSEXIT but we really use - * SYSRETL instead. - * - * This code path is still called 'sysexit' because it pairs - * with 'sysenter' and it uses the SYSENTER calling convention. - */ - andl $~TS_COMPAT,ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) - movl RIP(%rsp),%ecx /* User %eip */ - CFI_REGISTER rip,rcx - RESTORE_RSI_RDI - xorl %edx,%edx /* avoid info leaks */ - xorq %r8,%r8 - xorq %r9,%r9 - xorq %r10,%r10 - movl EFLAGS(%rsp),%r11d /* User eflags */ - /*CFI_RESTORE rflags*/ - TRACE_IRQS_ON - - /* - * SYSRETL works even on Intel CPUs. Use it in preference to SYSEXIT, - * since it avoids a dicey window with interrupts enabled. - */ - movl RSP(%rsp),%esp - - /* - * USERGS_SYSRET32 does: - * gsbase = user's gs base - * eip = ecx - * rflags = r11 - * cs = __USER32_CS - * ss = __USER_DS - * - * The prologue set RIP(%rsp) to VDSO32_SYSENTER_RETURN, which does: - * - * pop %ebp - * pop %edx - * pop %ecx - * - * Therefore, we invoke SYSRETL with EDX and R8-R10 zeroed to - * avoid info leaks. R11 ends up with VDSO32_SYSENTER_RETURN's - * address (already known to user code), and R12-R15 are - * callee-saved and therefore don't contain any interesting - * kernel data. - */ - USERGS_SYSRET32 - - CFI_RESTORE_STATE - -#ifdef CONFIG_AUDITSYSCALL - .macro auditsys_entry_common - movl %esi,%r8d /* 5th arg: 4th syscall arg */ - movl %ecx,%r9d /*swap with edx*/ - movl %edx,%ecx /* 4th arg: 3rd syscall arg */ - movl %r9d,%edx /* 3rd arg: 2nd syscall arg */ - movl %ebx,%esi /* 2nd arg: 1st syscall arg */ - movl %eax,%edi /* 1st arg: syscall number */ - call __audit_syscall_entry - movl RAX(%rsp),%eax /* reload syscall number */ - cmpq $(IA32_NR_syscalls-1),%rax - ja ia32_badsys - movl %ebx,%edi /* reload 1st syscall arg */ - movl RCX(%rsp),%esi /* reload 2nd syscall arg */ - movl RDX(%rsp),%edx /* reload 3rd syscall arg */ - movl RSI(%rsp),%ecx /* reload 4th syscall arg */ - movl RDI(%rsp),%r8d /* reload 5th syscall arg */ - .endm - - .macro auditsys_exit exit - testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - jnz ia32_ret_from_sys_call - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) - movl %eax,%esi /* second arg, syscall return value */ - cmpl $-MAX_ERRNO,%eax /* is it an error ? */ - jbe 1f - movslq %eax, %rsi /* if error sign extend to 64 bits */ -1: setbe %al /* 1 if error, 0 if not */ - movzbl %al,%edi /* zero-extend that into %edi */ - call __audit_syscall_exit - movq RAX(%rsp),%rax /* reload syscall return value */ - movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - testl %edi, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - jz \exit - CLEAR_RREGS - jmp int_with_check - .endm - -sysenter_auditsys: - auditsys_entry_common - movl %ebp,%r9d /* reload 6th syscall arg */ - jmp sysenter_dispatch - -sysexit_audit: - auditsys_exit sysexit_from_sys_call -#endif - -sysenter_fix_flags: - pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED) - popfq_cfi - jmp sysenter_flags_fixed - -sysenter_tracesys: -#ifdef CONFIG_AUDITSYSCALL - testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - jz sysenter_auditsys -#endif - SAVE_EXTRA_REGS - CLEAR_RREGS - movq $-ENOSYS,RAX(%rsp)/* ptrace can change this for a bad syscall */ - movq %rsp,%rdi /* &pt_regs -> arg1 */ - call syscall_trace_enter - LOAD_ARGS32 /* reload args from stack in case ptrace changed it */ - RESTORE_EXTRA_REGS - cmpq $(IA32_NR_syscalls-1),%rax - ja int_ret_from_sys_call /* sysenter_tracesys has set RAX(%rsp) */ - jmp sysenter_do_call - CFI_ENDPROC -ENDPROC(ia32_sysenter_target) - -/* - * 32bit SYSCALL instruction entry. - * - * 32bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11, - * then loads new ss, cs, and rip from previously programmed MSRs. - * rflags gets masked by a value from another MSR (so CLD and CLAC - * are not needed). SYSCALL does not save anything on the stack - * and does not change rsp. - * - * Note: rflags saving+masking-with-MSR happens only in Long mode - * (in legacy 32bit mode, IF, RF and VM bits are cleared and that's it). - * Don't get confused: rflags saving+masking depends on Long Mode Active bit - * (EFER.LMA=1), NOT on bitness of userspace where SYSCALL executes - * or target CS descriptor's L bit (SYSCALL does not read segment descriptors). - * - * Arguments: - * eax system call number - * ecx return address - * ebx arg1 - * ebp arg2 (note: not saved in the stack frame, should not be touched) - * edx arg3 - * esi arg4 - * edi arg5 - * esp user stack - * 0(%esp) arg6 - * - * This is purely a fast path. For anything complicated we use the int 0x80 - * path below. We set up a complete hardware stack frame to share code - * with the int 0x80 path. - */ -ENTRY(ia32_cstar_target) - CFI_STARTPROC32 simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA rsp,0 - CFI_REGISTER rip,rcx - /*CFI_REGISTER rflags,r11*/ - - /* - * Interrupts are off on entry. - * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON, - * it is too small to ever cause noticeable irq latency. - */ - SWAPGS_UNSAFE_STACK - movl %esp,%r8d - CFI_REGISTER rsp,r8 - movq PER_CPU_VAR(kernel_stack),%rsp - ENABLE_INTERRUPTS(CLBR_NONE) - - /* Zero-extending 32-bit regs, do not remove */ - movl %eax,%eax - - /* Construct struct pt_regs on stack */ - pushq_cfi $__USER32_DS /* pt_regs->ss */ - pushq_cfi %r8 /* pt_regs->sp */ - CFI_REL_OFFSET rsp,0 - pushq_cfi %r11 /* pt_regs->flags */ - pushq_cfi $__USER32_CS /* pt_regs->cs */ - pushq_cfi %rcx /* pt_regs->ip */ - CFI_REL_OFFSET rip,0 - pushq_cfi_reg rax /* pt_regs->orig_ax */ - pushq_cfi_reg rdi /* pt_regs->di */ - pushq_cfi_reg rsi /* pt_regs->si */ - pushq_cfi_reg rdx /* pt_regs->dx */ - pushq_cfi_reg rbp /* pt_regs->cx */ - movl %ebp,%ecx - pushq_cfi_reg rax /* pt_regs->ax */ - sub $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */ - CFI_ADJUST_CFA_OFFSET 10*8 - - /* - * no need to do an access_ok check here because r8 has been - * 32bit zero extended - */ - ASM_STAC -1: movl (%r8),%r9d - _ASM_EXTABLE(1b,ia32_badarg) - ASM_CLAC - orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) - testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - CFI_REMEMBER_STATE - jnz cstar_tracesys - cmpq $IA32_NR_syscalls-1,%rax - ja ia32_badsys -cstar_do_call: - /* 32bit syscall -> 64bit C ABI argument conversion */ - movl %edi,%r8d /* arg5 */ - /* r9 already loaded */ /* arg6 */ - xchg %ecx,%esi /* rsi:arg2, rcx:arg4 */ - movl %ebx,%edi /* arg1 */ - movl %edx,%edx /* arg3 (zero extension) */ -cstar_dispatch: - call *ia32_sys_call_table(,%rax,8) - movq %rax,RAX(%rsp) - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - jnz sysretl_audit -sysretl_from_sys_call: - andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) - RESTORE_RSI_RDI_RDX - movl RIP(%rsp),%ecx - CFI_REGISTER rip,rcx - movl EFLAGS(%rsp),%r11d - /*CFI_REGISTER rflags,r11*/ - xorq %r10,%r10 - xorq %r9,%r9 - xorq %r8,%r8 - TRACE_IRQS_ON - movl RSP(%rsp),%esp - CFI_RESTORE rsp - /* - * 64bit->32bit SYSRET restores eip from ecx, - * eflags from r11 (but RF and VM bits are forced to 0), - * cs and ss are loaded from MSRs. - * (Note: 32bit->32bit SYSRET is different: since r11 - * does not exist, it merely sets eflags.IF=1). - * - * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss - * descriptor is not reinitialized. This means that we must - * avoid SYSRET with SS == NULL, which could happen if we schedule, - * exit the kernel, and re-enter using an interrupt vector. (All - * interrupt entries on x86_64 set SS to NULL.) We prevent that - * from happening by reloading SS in __switch_to. - */ - USERGS_SYSRET32 - -#ifdef CONFIG_AUDITSYSCALL -cstar_auditsys: - CFI_RESTORE_STATE - movl %r9d,R9(%rsp) /* register to be clobbered by call */ - auditsys_entry_common - movl R9(%rsp),%r9d /* reload 6th syscall arg */ - jmp cstar_dispatch - -sysretl_audit: - auditsys_exit sysretl_from_sys_call -#endif - -cstar_tracesys: -#ifdef CONFIG_AUDITSYSCALL - testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - jz cstar_auditsys -#endif - xchgl %r9d,%ebp - SAVE_EXTRA_REGS - CLEAR_RREGS r9 - movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */ - movq %rsp,%rdi /* &pt_regs -> arg1 */ - call syscall_trace_enter - LOAD_ARGS32 1 /* reload args from stack in case ptrace changed it */ - RESTORE_EXTRA_REGS - xchgl %ebp,%r9d - cmpq $(IA32_NR_syscalls-1),%rax - ja int_ret_from_sys_call /* cstar_tracesys has set RAX(%rsp) */ - jmp cstar_do_call -END(ia32_cstar_target) - -ia32_badarg: - ASM_CLAC - movq $-EFAULT,%rax - jmp ia32_sysret - CFI_ENDPROC - -/* - * Emulated IA32 system calls via int 0x80. - * - * Arguments: - * eax system call number - * ebx arg1 - * ecx arg2 - * edx arg3 - * esi arg4 - * edi arg5 - * ebp arg6 (note: not saved in the stack frame, should not be touched) - * - * Notes: - * Uses the same stack frame as the x86-64 version. - * All registers except eax must be saved (but ptrace may violate that). - * Arguments are zero extended. For system calls that want sign extension and - * take long arguments a wrapper is needed. Most calls can just be called - * directly. - * Assumes it is only called from user space and entered with interrupts off. - */ - -ENTRY(ia32_syscall) - CFI_STARTPROC32 simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA rsp,5*8 - /*CFI_REL_OFFSET ss,4*8 */ - CFI_REL_OFFSET rsp,3*8 - /*CFI_REL_OFFSET rflags,2*8 */ - /*CFI_REL_OFFSET cs,1*8 */ - CFI_REL_OFFSET rip,0*8 - - /* - * Interrupts are off on entry. - * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON, - * it is too small to ever cause noticeable irq latency. - */ - PARAVIRT_ADJUST_EXCEPTION_FRAME - SWAPGS - ENABLE_INTERRUPTS(CLBR_NONE) - - /* Zero-extending 32-bit regs, do not remove */ - movl %eax,%eax - - /* Construct struct pt_regs on stack (iret frame is already on stack) */ - pushq_cfi_reg rax /* pt_regs->orig_ax */ - pushq_cfi_reg rdi /* pt_regs->di */ - pushq_cfi_reg rsi /* pt_regs->si */ - pushq_cfi_reg rdx /* pt_regs->dx */ - pushq_cfi_reg rcx /* pt_regs->cx */ - pushq_cfi_reg rax /* pt_regs->ax */ - cld - sub $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */ - CFI_ADJUST_CFA_OFFSET 10*8 - - orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) - testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - jnz ia32_tracesys - cmpq $(IA32_NR_syscalls-1),%rax - ja ia32_badsys -ia32_do_call: - /* 32bit syscall -> 64bit C ABI argument conversion */ - movl %edi,%r8d /* arg5 */ - movl %ebp,%r9d /* arg6 */ - xchg %ecx,%esi /* rsi:arg2, rcx:arg4 */ - movl %ebx,%edi /* arg1 */ - movl %edx,%edx /* arg3 (zero extension) */ - call *ia32_sys_call_table(,%rax,8) # xxx: rip relative -ia32_sysret: - movq %rax,RAX(%rsp) -ia32_ret_from_sys_call: - CLEAR_RREGS - jmp int_ret_from_sys_call - -ia32_tracesys: - SAVE_EXTRA_REGS - CLEAR_RREGS - movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */ - movq %rsp,%rdi /* &pt_regs -> arg1 */ - call syscall_trace_enter - LOAD_ARGS32 /* reload args from stack in case ptrace changed it */ - RESTORE_EXTRA_REGS - cmpq $(IA32_NR_syscalls-1),%rax - ja int_ret_from_sys_call /* ia32_tracesys has set RAX(%rsp) */ - jmp ia32_do_call -END(ia32_syscall) - -ia32_badsys: - movq $0,ORIG_RAX(%rsp) - movq $-ENOSYS,%rax - jmp ia32_sysret - - CFI_ENDPROC - - .macro PTREGSCALL label, func - ALIGN -GLOBAL(\label) - leaq \func(%rip),%rax - jmp ia32_ptregs_common - .endm - - CFI_STARTPROC32 - - PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn - PTREGSCALL stub32_sigreturn, sys32_sigreturn - PTREGSCALL stub32_fork, sys_fork - PTREGSCALL stub32_vfork, sys_vfork - - ALIGN -GLOBAL(stub32_clone) - leaq sys_clone(%rip),%rax - mov %r8, %rcx - jmp ia32_ptregs_common - - ALIGN -ia32_ptregs_common: - CFI_ENDPROC - CFI_STARTPROC32 simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA rsp,SIZEOF_PTREGS - CFI_REL_OFFSET rax,RAX - CFI_REL_OFFSET rcx,RCX - CFI_REL_OFFSET rdx,RDX - CFI_REL_OFFSET rsi,RSI - CFI_REL_OFFSET rdi,RDI - CFI_REL_OFFSET rip,RIP -/* CFI_REL_OFFSET cs,CS*/ -/* CFI_REL_OFFSET rflags,EFLAGS*/ - CFI_REL_OFFSET rsp,RSP -/* CFI_REL_OFFSET ss,SS*/ - SAVE_EXTRA_REGS 8 - call *%rax - RESTORE_EXTRA_REGS 8 - ret - CFI_ENDPROC -END(ia32_ptregs_common) diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index d55a210a4..aeac434c9 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -9,4 +9,4 @@ generic-y += cputime.h generic-y += dma-contiguous.h generic-y += early_ioremap.h generic-y += mcs_spinlock.h -generic-y += scatterlist.h +generic-y += mm-arch-hooks.h diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h index bdf02eeee..e7636bac7 100644 --- a/arch/x86/include/asm/alternative-asm.h +++ b/arch/x86/include/asm/alternative-asm.h @@ -18,6 +18,12 @@ .endm #endif +/* + * Issue one struct alt_instr descriptor entry (need to put it into + * the section .altinstructions, see below). This entry contains + * enough information for the alternatives patching code to patch an + * instruction. See apply_alternatives(). + */ .macro altinstruction_entry orig alt feature orig_len alt_len pad_len .long \orig - . .long \alt - . @@ -27,6 +33,12 @@ .byte \pad_len .endm +/* + * Define an alternative between two instructions. If @feature is + * present, early code in apply_alternatives() replaces @oldinstr with + * @newinstr. ".skip" directive takes care of proper instruction padding + * in case @newinstr is longer than @oldinstr. + */ .macro ALTERNATIVE oldinstr, newinstr, feature 140: \oldinstr @@ -55,6 +67,12 @@ */ #define alt_max_short(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b))))) + +/* + * Same as ALTERNATIVE macro above but for two alternatives. If CPU + * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has + * @feature2, it replaces @oldinstr with @feature2. + */ .macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2 140: \oldinstr diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index ba32af062..7bfc85bbb 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -52,6 +52,12 @@ struct alt_instr { u8 padlen; /* length of build-time padding */ } __packed; +/* + * Debug flag that can be tested to see whether alternative + * instructions were patched in already: + */ +extern int alternatives_patched; + extern void alternative_instructions(void); extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end); diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index aaac3b2fb..1a5da2e63 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -98,11 +98,22 @@ static inline u16 amd_get_node_id(struct pci_dev *pdev) return 0; } +static inline bool amd_gart_present(void) +{ + /* GART present only on Fam15h, upto model 0fh */ + if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 || + (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10)) + return true; + + return false; +} + #else #define amd_nb_num(x) 0 #define amd_nb_has_feature(x) false #define node_to_amd_nb(x) NULL +#define amd_gart_present(x) false #endif diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 976b86a32..c8393634c 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -644,6 +644,12 @@ static inline void entering_ack_irq(void) entering_irq(); } +static inline void ipi_entering_ack_irq(void) +{ + ack_APIC_irq(); + irq_enter(); +} + static inline void exiting_irq(void) { irq_exit(); diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 7730c1c5c..189679aba 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -63,6 +63,31 @@ _ASM_ALIGN ; \ _ASM_PTR (entry); \ .popsection + +.macro ALIGN_DESTINATION + /* check for bad alignment of destination */ + movl %edi,%ecx + andl $7,%ecx + jz 102f /* already aligned */ + subl $8,%ecx + negl %ecx + subl %ecx,%edx +100: movb (%rsi),%al +101: movb %al,(%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz 100b +102: + .section .fixup,"ax" +103: addl %ecx,%edx /* ecx is zerorest also */ + jmp copy_user_handle_tail + .previous + + _ASM_EXTABLE(100b,103b) + _ASM_EXTABLE(101b,103b) + .endm + #else # define _ASM_EXTABLE(from,to) \ " .pushsection \"__ex_table\",\"a\"\n" \ diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 5e5cd123f..e9168955c 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -22,7 +22,7 @@ * * Atomically reads the value of @v. */ -static inline int atomic_read(const atomic_t *v) +static __always_inline int atomic_read(const atomic_t *v) { return ACCESS_ONCE((v)->counter); } @@ -34,7 +34,7 @@ static inline int atomic_read(const atomic_t *v) * * Atomically sets the value of @v to @i. */ -static inline void atomic_set(atomic_t *v, int i) +static __always_inline void atomic_set(atomic_t *v, int i) { v->counter = i; } @@ -46,7 +46,7 @@ static inline void atomic_set(atomic_t *v, int i) * * Atomically adds @i to @v. */ -static inline void atomic_add(int i, atomic_t *v) +static __always_inline void atomic_add(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "addl %1,%0" : "+m" (v->counter) @@ -60,7 +60,7 @@ static inline void atomic_add(int i, atomic_t *v) * * Atomically subtracts @i from @v. */ -static inline void atomic_sub(int i, atomic_t *v) +static __always_inline void atomic_sub(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "subl %1,%0" : "+m" (v->counter) @@ -76,7 +76,7 @@ static inline void atomic_sub(int i, atomic_t *v) * true if the result is zero, or false for all * other cases. */ -static inline int atomic_sub_and_test(int i, atomic_t *v) +static __always_inline int atomic_sub_and_test(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", "e"); } @@ -87,7 +87,7 @@ static inline int atomic_sub_and_test(int i, atomic_t *v) * * Atomically increments @v by 1. */ -static inline void atomic_inc(atomic_t *v) +static __always_inline void atomic_inc(atomic_t *v) { asm volatile(LOCK_PREFIX "incl %0" : "+m" (v->counter)); @@ -99,7 +99,7 @@ static inline void atomic_inc(atomic_t *v) * * Atomically decrements @v by 1. */ -static inline void atomic_dec(atomic_t *v) +static __always_inline void atomic_dec(atomic_t *v) { asm volatile(LOCK_PREFIX "decl %0" : "+m" (v->counter)); @@ -113,7 +113,7 @@ static inline void atomic_dec(atomic_t *v) * returns true if the result is 0, or false for all other * cases. */ -static inline int atomic_dec_and_test(atomic_t *v) +static __always_inline int atomic_dec_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e"); } @@ -126,7 +126,7 @@ static inline int atomic_dec_and_test(atomic_t *v) * and returns true if the result is zero, or false for all * other cases. */ -static inline int atomic_inc_and_test(atomic_t *v) +static __always_inline int atomic_inc_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", "e"); } @@ -140,7 +140,7 @@ static inline int atomic_inc_and_test(atomic_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -static inline int atomic_add_negative(int i, atomic_t *v) +static __always_inline int atomic_add_negative(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", "s"); } @@ -152,7 +152,7 @@ static inline int atomic_add_negative(int i, atomic_t *v) * * Atomically adds @i to @v and returns @i + @v */ -static inline int atomic_add_return(int i, atomic_t *v) +static __always_inline int atomic_add_return(int i, atomic_t *v) { return i + xadd(&v->counter, i); } @@ -164,7 +164,7 @@ static inline int atomic_add_return(int i, atomic_t *v) * * Atomically subtracts @i from @v and returns @v - @i */ -static inline int atomic_sub_return(int i, atomic_t *v) +static __always_inline int atomic_sub_return(int i, atomic_t *v) { return atomic_add_return(-i, v); } @@ -172,7 +172,7 @@ static inline int atomic_sub_return(int i, atomic_t *v) #define atomic_inc_return(v) (atomic_add_return(1, v)) #define atomic_dec_return(v) (atomic_sub_return(1, v)) -static inline int atomic_cmpxchg(atomic_t *v, int old, int new) +static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new) { return cmpxchg(&v->counter, old, new); } @@ -191,7 +191,7 @@ static inline int atomic_xchg(atomic_t *v, int new) * Atomically adds @a to @v, so long as @v was not already @u. * Returns the old value of @v. */ -static inline int __atomic_add_unless(atomic_t *v, int a, int u) +static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u) { int c, old; c = atomic_read(v); @@ -213,7 +213,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) * Atomically adds 1 to @v * Returns the new value of @u */ -static inline short int atomic_inc_short(short int *v) +static __always_inline short int atomic_inc_short(short int *v) { asm(LOCK_PREFIX "addw $1, %0" : "+m" (*v)); return *v; diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index f8d273e18..b965f9e03 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -40,7 +40,7 @@ static inline void atomic64_set(atomic64_t *v, long i) * * Atomically adds @i to @v. */ -static inline void atomic64_add(long i, atomic64_t *v) +static __always_inline void atomic64_add(long i, atomic64_t *v) { asm volatile(LOCK_PREFIX "addq %1,%0" : "=m" (v->counter) @@ -81,7 +81,7 @@ static inline int atomic64_sub_and_test(long i, atomic64_t *v) * * Atomically increments @v by 1. */ -static inline void atomic64_inc(atomic64_t *v) +static __always_inline void atomic64_inc(atomic64_t *v) { asm volatile(LOCK_PREFIX "incq %0" : "=m" (v->counter) @@ -94,7 +94,7 @@ static inline void atomic64_inc(atomic64_t *v) * * Atomically decrements @v by 1. */ -static inline void atomic64_dec(atomic64_t *v) +static __always_inline void atomic64_dec(atomic64_t *v) { asm volatile(LOCK_PREFIX "decq %0" : "=m" (v->counter) @@ -148,7 +148,7 @@ static inline int atomic64_add_negative(long i, atomic64_t *v) * * Atomically adds @i to @v and returns @i + @v */ -static inline long atomic64_add_return(long i, atomic64_t *v) +static __always_inline long atomic64_add_return(long i, atomic64_t *v) { return i + xadd(&v->counter, i); } diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 959e45b81..e51a8f803 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -35,12 +35,12 @@ #define smp_mb() mb() #define smp_rmb() dma_rmb() #define smp_wmb() barrier() -#define set_mb(var, value) do { (void)xchg(&var, value); } while (0) +#define smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0) #else /* !SMP */ #define smp_mb() barrier() #define smp_rmb() barrier() #define smp_wmb() barrier() -#define set_mb(var, value) do { var = value; barrier(); } while (0) +#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); barrier(); } while (0) #endif /* SMP */ #define read_barrier_depends() do { } while (0) diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h index 47c8e32f6..9bf3ea14b 100644 --- a/arch/x86/include/asm/cacheflush.h +++ b/arch/x86/include/asm/cacheflush.h @@ -4,11 +4,12 @@ /* Caches aren't brain-dead on the intel. */ #include <asm-generic/cacheflush.h> #include <asm/special_insns.h> +#include <asm/uaccess.h> /* * The set_memory_* API can be used to change various attributes of a virtual * address range. The attributes include: - * Cachability : UnCached, WriteCombining, WriteBack + * Cachability : UnCached, WriteCombining, WriteThrough, WriteBack * Executability : eXeutable, NoteXecutable * Read/Write : ReadOnly, ReadWrite * Presence : NotPresent @@ -35,9 +36,11 @@ int _set_memory_uc(unsigned long addr, int numpages); int _set_memory_wc(unsigned long addr, int numpages); +int _set_memory_wt(unsigned long addr, int numpages); int _set_memory_wb(unsigned long addr, int numpages); int set_memory_uc(unsigned long addr, int numpages); int set_memory_wc(unsigned long addr, int numpages); +int set_memory_wt(unsigned long addr, int numpages); int set_memory_wb(unsigned long addr, int numpages); int set_memory_x(unsigned long addr, int numpages); int set_memory_nx(unsigned long addr, int numpages); @@ -48,10 +51,12 @@ int set_memory_4k(unsigned long addr, int numpages); int set_memory_array_uc(unsigned long *addr, int addrinarray); int set_memory_array_wc(unsigned long *addr, int addrinarray); +int set_memory_array_wt(unsigned long *addr, int addrinarray); int set_memory_array_wb(unsigned long *addr, int addrinarray); int set_pages_array_uc(struct page **pages, int addrinarray); int set_pages_array_wc(struct page **pages, int addrinarray); +int set_pages_array_wt(struct page **pages, int addrinarray); int set_pages_array_wb(struct page **pages, int addrinarray); /* @@ -104,4 +109,75 @@ static inline int rodata_test(void) } #endif +#ifdef ARCH_HAS_NOCACHE_UACCESS + +/** + * arch_memcpy_to_pmem - copy data to persistent memory + * @dst: destination buffer for the copy + * @src: source buffer for the copy + * @n: length of the copy in bytes + * + * Copy data to persistent memory media via non-temporal stores so that + * a subsequent arch_wmb_pmem() can flush cpu and memory controller + * write buffers to guarantee durability. + */ +static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src, + size_t n) +{ + int unwritten; + + /* + * We are copying between two kernel buffers, if + * __copy_from_user_inatomic_nocache() returns an error (page + * fault) we would have already reported a general protection fault + * before the WARN+BUG. + */ + unwritten = __copy_from_user_inatomic_nocache((void __force *) dst, + (void __user *) src, n); + if (WARN(unwritten, "%s: fault copying %p <- %p unwritten: %d\n", + __func__, dst, src, unwritten)) + BUG(); +} + +/** + * arch_wmb_pmem - synchronize writes to persistent memory + * + * After a series of arch_memcpy_to_pmem() operations this drains data + * from cpu write buffers and any platform (memory controller) buffers + * to ensure that written data is durable on persistent memory media. + */ +static inline void arch_wmb_pmem(void) +{ + /* + * wmb() to 'sfence' all previous writes such that they are + * architecturally visible to 'pcommit'. Note, that we've + * already arranged for pmem writes to avoid the cache via + * arch_memcpy_to_pmem(). + */ + wmb(); + pcommit_sfence(); +} + +static inline bool __arch_has_wmb_pmem(void) +{ +#ifdef CONFIG_X86_64 + /* + * We require that wmb() be an 'sfence', that is only guaranteed on + * 64-bit builds + */ + return static_cpu_has(X86_FEATURE_PCOMMIT); +#else + return false; +#endif +} +#else /* ARCH_HAS_NOCACHE_UACCESS i.e. ARCH=um */ +extern void arch_memcpy_to_pmem(void __pmem *dst, const void *src, size_t n); +extern void arch_wmb_pmem(void); + +static inline bool __arch_has_wmb_pmem(void) +{ + return false; +} +#endif + #endif /* _ASM_X86_CACHEFLUSH_H */ diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index 99c105d78..ad19841ed 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -4,8 +4,6 @@ #include <linux/compiler.h> #include <asm/alternative.h> /* Provides LOCK_PREFIX */ -#define __HAVE_ARCH_CMPXCHG 1 - /* * Non-existant functions to indicate usage errors at link time * (or compile-time if the compiler implements __compiletime_error(). diff --git a/arch/x86/include/asm/crypto/glue_helper.h b/arch/x86/include/asm/crypto/glue_helper.h index 1eef55596..03bb1065c 100644 --- a/arch/x86/include/asm/crypto/glue_helper.h +++ b/arch/x86/include/asm/crypto/glue_helper.h @@ -7,7 +7,7 @@ #include <linux/kernel.h> #include <linux/crypto.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #include <crypto/b128ops.h> typedef void (*common_glue_func_t)(void *ctx, u8 *dst, const u8 *src); diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index a0bf89fd2..4e10d73cf 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -280,21 +280,6 @@ static inline void clear_LDT(void) set_ldt(NULL, 0); } -/* - * load one particular LDT into the current CPU - */ -static inline void load_LDT_nolock(mm_context_t *pc) -{ - set_ldt(pc->ldt, pc->size); -} - -static inline void load_LDT(mm_context_t *pc) -{ - preempt_disable(); - load_LDT_nolock(pc); - preempt_enable(); -} - static inline unsigned long get_desc_base(const struct desc_struct *desc) { return (unsigned)(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24)); diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 808dae63e..1f5b7287d 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -127,50 +127,14 @@ static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp) #define dma_alloc_coherent(d,s,h,f) dma_alloc_attrs(d,s,h,f,NULL) -static inline void * +void * dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t gfp, struct dma_attrs *attrs) -{ - struct dma_map_ops *ops = get_dma_ops(dev); - void *memory; - - gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); - - if (dma_alloc_from_coherent(dev, size, dma_handle, &memory)) - return memory; - - if (!dev) - dev = &x86_dma_fallback_dev; - - if (!is_device_dma_capable(dev)) - return NULL; - - if (!ops->alloc) - return NULL; - - memory = ops->alloc(dev, size, dma_handle, - dma_alloc_coherent_gfp_flags(dev, gfp), attrs); - debug_dma_alloc_coherent(dev, size, *dma_handle, memory); - - return memory; -} + gfp_t gfp, struct dma_attrs *attrs); #define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL) -static inline void dma_free_attrs(struct device *dev, size_t size, - void *vaddr, dma_addr_t bus, - struct dma_attrs *attrs) -{ - struct dma_map_ops *ops = get_dma_ops(dev); - - WARN_ON(irqs_disabled()); /* for portability */ - - if (dma_release_from_coherent(dev, get_order(size), vaddr)) - return; - - debug_dma_free_coherent(dev, size, vaddr, bus); - if (ops->free) - ops->free(dev, size, vaddr, bus, attrs); -} +void dma_free_attrs(struct device *dev, size_t size, + void *vaddr, dma_addr_t bus, + struct dma_attrs *attrs); #endif diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h deleted file mode 100644 index de1cdaf4d..000000000 --- a/arch/x86/include/asm/dwarf2.h +++ /dev/null @@ -1,170 +0,0 @@ -#ifndef _ASM_X86_DWARF2_H -#define _ASM_X86_DWARF2_H - -#ifndef __ASSEMBLY__ -#warning "asm/dwarf2.h should be only included in pure assembly files" -#endif - -/* - * Macros for dwarf2 CFI unwind table entries. - * See "as.info" for details on these pseudo ops. Unfortunately - * they are only supported in very new binutils, so define them - * away for older version. - */ - -#ifdef CONFIG_AS_CFI - -#define CFI_STARTPROC .cfi_startproc -#define CFI_ENDPROC .cfi_endproc -#define CFI_DEF_CFA .cfi_def_cfa -#define CFI_DEF_CFA_REGISTER .cfi_def_cfa_register -#define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset -#define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset -#define CFI_OFFSET .cfi_offset -#define CFI_REL_OFFSET .cfi_rel_offset -#define CFI_REGISTER .cfi_register -#define CFI_RESTORE .cfi_restore -#define CFI_REMEMBER_STATE .cfi_remember_state -#define CFI_RESTORE_STATE .cfi_restore_state -#define CFI_UNDEFINED .cfi_undefined -#define CFI_ESCAPE .cfi_escape - -#ifdef CONFIG_AS_CFI_SIGNAL_FRAME -#define CFI_SIGNAL_FRAME .cfi_signal_frame -#else -#define CFI_SIGNAL_FRAME -#endif - -#if defined(CONFIG_AS_CFI_SECTIONS) && defined(__ASSEMBLY__) - /* - * Emit CFI data in .debug_frame sections, not .eh_frame sections. - * The latter we currently just discard since we don't do DWARF - * unwinding at runtime. So only the offline DWARF information is - * useful to anyone. Note we should not use this directive if this - * file is used in the vDSO assembly, or if vmlinux.lds.S gets - * changed so it doesn't discard .eh_frame. - */ - .cfi_sections .debug_frame -#endif - -#else - -/* - * Due to the structure of pre-exisiting code, don't use assembler line - * comment character # to ignore the arguments. Instead, use a dummy macro. - */ -.macro cfi_ignore a=0, b=0, c=0, d=0 -.endm - -#define CFI_STARTPROC cfi_ignore -#define CFI_ENDPROC cfi_ignore -#define CFI_DEF_CFA cfi_ignore -#define CFI_DEF_CFA_REGISTER cfi_ignore -#define CFI_DEF_CFA_OFFSET cfi_ignore -#define CFI_ADJUST_CFA_OFFSET cfi_ignore -#define CFI_OFFSET cfi_ignore -#define CFI_REL_OFFSET cfi_ignore -#define CFI_REGISTER cfi_ignore -#define CFI_RESTORE cfi_ignore -#define CFI_REMEMBER_STATE cfi_ignore -#define CFI_RESTORE_STATE cfi_ignore -#define CFI_UNDEFINED cfi_ignore -#define CFI_ESCAPE cfi_ignore -#define CFI_SIGNAL_FRAME cfi_ignore - -#endif - -/* - * An attempt to make CFI annotations more or less - * correct and shorter. It is implied that you know - * what you're doing if you use them. - */ -#ifdef __ASSEMBLY__ -#ifdef CONFIG_X86_64 - .macro pushq_cfi reg - pushq \reg - CFI_ADJUST_CFA_OFFSET 8 - .endm - - .macro pushq_cfi_reg reg - pushq %\reg - CFI_ADJUST_CFA_OFFSET 8 - CFI_REL_OFFSET \reg, 0 - .endm - - .macro popq_cfi reg - popq \reg - CFI_ADJUST_CFA_OFFSET -8 - .endm - - .macro popq_cfi_reg reg - popq %\reg - CFI_ADJUST_CFA_OFFSET -8 - CFI_RESTORE \reg - .endm - - .macro pushfq_cfi - pushfq - CFI_ADJUST_CFA_OFFSET 8 - .endm - - .macro popfq_cfi - popfq - CFI_ADJUST_CFA_OFFSET -8 - .endm - - .macro movq_cfi reg offset=0 - movq %\reg, \offset(%rsp) - CFI_REL_OFFSET \reg, \offset - .endm - - .macro movq_cfi_restore offset reg - movq \offset(%rsp), %\reg - CFI_RESTORE \reg - .endm -#else /*!CONFIG_X86_64*/ - .macro pushl_cfi reg - pushl \reg - CFI_ADJUST_CFA_OFFSET 4 - .endm - - .macro pushl_cfi_reg reg - pushl %\reg - CFI_ADJUST_CFA_OFFSET 4 - CFI_REL_OFFSET \reg, 0 - .endm - - .macro popl_cfi reg - popl \reg - CFI_ADJUST_CFA_OFFSET -4 - .endm - - .macro popl_cfi_reg reg - popl %\reg - CFI_ADJUST_CFA_OFFSET -4 - CFI_RESTORE \reg - .endm - - .macro pushfl_cfi - pushfl - CFI_ADJUST_CFA_OFFSET 4 - .endm - - .macro popfl_cfi - popfl - CFI_ADJUST_CFA_OFFSET -4 - .endm - - .macro movl_cfi reg offset=0 - movl %\reg, \offset(%esp) - CFI_REL_OFFSET \reg, \offset - .endm - - .macro movl_cfi_restore offset reg - movl \offset(%esp), %\reg - CFI_RESTORE \reg - .endm -#endif /*!CONFIG_X86_64*/ -#endif /*__ASSEMBLY__*/ - -#endif /* _ASM_X86_DWARF2_H */ diff --git a/arch/x86/include/asm/edac.h b/arch/x86/include/asm/edac.h index e9b57ecc7..cf8fdf83b 100644 --- a/arch/x86/include/asm/edac.h +++ b/arch/x86/include/asm/edac.h @@ -3,7 +3,7 @@ /* ECC atomic, DMA, SMP and interrupt safe scrub function */ -static inline void atomic_scrub(void *va, u32 size) +static inline void edac_atomic_scrub(void *va, u32 size) { u32 i, *virt_addr = va; diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 3738b138b..155162ea0 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -1,7 +1,7 @@ #ifndef _ASM_X86_EFI_H #define _ASM_X86_EFI_H -#include <asm/i387.h> +#include <asm/fpu/api.h> #include <asm/pgtable.h> /* diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h index dc5fa6614..df002992d 100644 --- a/arch/x86/include/asm/entry_arch.h +++ b/arch/x86/include/asm/entry_arch.h @@ -23,6 +23,8 @@ BUILD_INTERRUPT(x86_platform_ipi, X86_PLATFORM_IPI_VECTOR) #ifdef CONFIG_HAVE_KVM BUILD_INTERRUPT3(kvm_posted_intr_ipi, POSTED_INTR_VECTOR, smp_kvm_posted_intr_ipi) +BUILD_INTERRUPT3(kvm_posted_intr_wakeup_ipi, POSTED_INTR_WAKEUP_VECTOR, + smp_kvm_posted_intr_wakeup_ipi) #endif /* @@ -50,4 +52,7 @@ BUILD_INTERRUPT(thermal_interrupt,THERMAL_APIC_VECTOR) BUILD_INTERRUPT(threshold_interrupt,THRESHOLD_APIC_VECTOR) #endif +#ifdef CONFIG_X86_MCE_AMD +BUILD_INTERRUPT(deferred_error_interrupt, DEFERRED_ERROR_VECTOR) +#endif #endif diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h index 99efebb2f..ca3ce9ab9 100644 --- a/arch/x86/include/asm/espfix.h +++ b/arch/x86/include/asm/espfix.h @@ -9,7 +9,7 @@ DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr); extern void init_espfix_bsp(void); -extern void init_espfix_ap(void); +extern void init_espfix_ap(int cpu); #endif /* CONFIG_X86_64 */ diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h deleted file mode 100644 index da5e96756..000000000 --- a/arch/x86/include/asm/fpu-internal.h +++ /dev/null @@ -1,626 +0,0 @@ -/* - * Copyright (C) 1994 Linus Torvalds - * - * Pentium III FXSR, SSE support - * General FPU state handling cleanups - * Gareth Hughes <gareth@valinux.com>, May 2000 - * x86-64 work by Andi Kleen 2002 - */ - -#ifndef _FPU_INTERNAL_H -#define _FPU_INTERNAL_H - -#include <linux/kernel_stat.h> -#include <linux/regset.h> -#include <linux/compat.h> -#include <linux/slab.h> -#include <asm/asm.h> -#include <asm/cpufeature.h> -#include <asm/processor.h> -#include <asm/sigcontext.h> -#include <asm/user.h> -#include <asm/uaccess.h> -#include <asm/xsave.h> -#include <asm/smap.h> - -#ifdef CONFIG_X86_64 -# include <asm/sigcontext32.h> -# include <asm/user32.h> -struct ksignal; -int ia32_setup_rt_frame(int sig, struct ksignal *ksig, - compat_sigset_t *set, struct pt_regs *regs); -int ia32_setup_frame(int sig, struct ksignal *ksig, - compat_sigset_t *set, struct pt_regs *regs); -#else -# define user_i387_ia32_struct user_i387_struct -# define user32_fxsr_struct user_fxsr_struct -# define ia32_setup_frame __setup_frame -# define ia32_setup_rt_frame __setup_rt_frame -#endif - -extern unsigned int mxcsr_feature_mask; -extern void fpu_init(void); -extern void eager_fpu_init(void); - -DECLARE_PER_CPU(struct task_struct *, fpu_owner_task); - -extern void convert_from_fxsr(struct user_i387_ia32_struct *env, - struct task_struct *tsk); -extern void convert_to_fxsr(struct task_struct *tsk, - const struct user_i387_ia32_struct *env); - -extern user_regset_active_fn fpregs_active, xfpregs_active; -extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get, - xstateregs_get; -extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set, - xstateregs_set; - -/* - * xstateregs_active == fpregs_active. Please refer to the comment - * at the definition of fpregs_active. - */ -#define xstateregs_active fpregs_active - -#ifdef CONFIG_MATH_EMULATION -extern void finit_soft_fpu(struct i387_soft_struct *soft); -#else -static inline void finit_soft_fpu(struct i387_soft_struct *soft) {} -#endif - -/* - * Must be run with preemption disabled: this clears the fpu_owner_task, - * on this CPU. - * - * This will disable any lazy FPU state restore of the current FPU state, - * but if the current thread owns the FPU, it will still be saved by. - */ -static inline void __cpu_disable_lazy_restore(unsigned int cpu) -{ - per_cpu(fpu_owner_task, cpu) = NULL; -} - -/* - * Used to indicate that the FPU state in memory is newer than the FPU - * state in registers, and the FPU state should be reloaded next time the - * task is run. Only safe on the current task, or non-running tasks. - */ -static inline void task_disable_lazy_fpu_restore(struct task_struct *tsk) -{ - tsk->thread.fpu.last_cpu = ~0; -} - -static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu) -{ - return new == this_cpu_read_stable(fpu_owner_task) && - cpu == new->thread.fpu.last_cpu; -} - -static inline int is_ia32_compat_frame(void) -{ - return config_enabled(CONFIG_IA32_EMULATION) && - test_thread_flag(TIF_IA32); -} - -static inline int is_ia32_frame(void) -{ - return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame(); -} - -static inline int is_x32_frame(void) -{ - return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32); -} - -#define X87_FSW_ES (1 << 7) /* Exception Summary */ - -static __always_inline __pure bool use_eager_fpu(void) -{ - return static_cpu_has_safe(X86_FEATURE_EAGER_FPU); -} - -static __always_inline __pure bool use_xsaveopt(void) -{ - return static_cpu_has_safe(X86_FEATURE_XSAVEOPT); -} - -static __always_inline __pure bool use_xsave(void) -{ - return static_cpu_has_safe(X86_FEATURE_XSAVE); -} - -static __always_inline __pure bool use_fxsr(void) -{ - return static_cpu_has_safe(X86_FEATURE_FXSR); -} - -static inline void fx_finit(struct i387_fxsave_struct *fx) -{ - fx->cwd = 0x37f; - fx->mxcsr = MXCSR_DEFAULT; -} - -extern void __sanitize_i387_state(struct task_struct *); - -static inline void sanitize_i387_state(struct task_struct *tsk) -{ - if (!use_xsaveopt()) - return; - __sanitize_i387_state(tsk); -} - -#define user_insn(insn, output, input...) \ -({ \ - int err; \ - asm volatile(ASM_STAC "\n" \ - "1:" #insn "\n\t" \ - "2: " ASM_CLAC "\n" \ - ".section .fixup,\"ax\"\n" \ - "3: movl $-1,%[err]\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ - : [err] "=r" (err), output \ - : "0"(0), input); \ - err; \ -}) - -#define check_insn(insn, output, input...) \ -({ \ - int err; \ - asm volatile("1:" #insn "\n\t" \ - "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: movl $-1,%[err]\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ - : [err] "=r" (err), output \ - : "0"(0), input); \ - err; \ -}) - -static inline int fsave_user(struct i387_fsave_struct __user *fx) -{ - return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx)); -} - -static inline int fxsave_user(struct i387_fxsave_struct __user *fx) -{ - if (config_enabled(CONFIG_X86_32)) - return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx)); - else if (config_enabled(CONFIG_AS_FXSAVEQ)) - return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx)); - - /* See comment in fpu_fxsave() below. */ - return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx)); -} - -static inline int fxrstor_checking(struct i387_fxsave_struct *fx) -{ - if (config_enabled(CONFIG_X86_32)) - return check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); - else if (config_enabled(CONFIG_AS_FXSAVEQ)) - return check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); - - /* See comment in fpu_fxsave() below. */ - return check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), - "m" (*fx)); -} - -static inline int fxrstor_user(struct i387_fxsave_struct __user *fx) -{ - if (config_enabled(CONFIG_X86_32)) - return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); - else if (config_enabled(CONFIG_AS_FXSAVEQ)) - return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); - - /* See comment in fpu_fxsave() below. */ - return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), - "m" (*fx)); -} - -static inline int frstor_checking(struct i387_fsave_struct *fx) -{ - return check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); -} - -static inline int frstor_user(struct i387_fsave_struct __user *fx) -{ - return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); -} - -static inline void fpu_fxsave(struct fpu *fpu) -{ - if (config_enabled(CONFIG_X86_32)) - asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state->fxsave)); - else if (config_enabled(CONFIG_AS_FXSAVEQ)) - asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state->fxsave)); - else { - /* Using "rex64; fxsave %0" is broken because, if the memory - * operand uses any extended registers for addressing, a second - * REX prefix will be generated (to the assembler, rex64 - * followed by semicolon is a separate instruction), and hence - * the 64-bitness is lost. - * - * Using "fxsaveq %0" would be the ideal choice, but is only - * supported starting with gas 2.16. - * - * Using, as a workaround, the properly prefixed form below - * isn't accepted by any binutils version so far released, - * complaining that the same type of prefix is used twice if - * an extended register is needed for addressing (fix submitted - * to mainline 2005-11-21). - * - * asm volatile("rex64/fxsave %0" : "=m" (fpu->state->fxsave)); - * - * This, however, we can work around by forcing the compiler to - * select an addressing mode that doesn't require extended - * registers. - */ - asm volatile( "rex64/fxsave (%[fx])" - : "=m" (fpu->state->fxsave) - : [fx] "R" (&fpu->state->fxsave)); - } -} - -/* - * These must be called with preempt disabled. Returns - * 'true' if the FPU state is still intact. - */ -static inline int fpu_save_init(struct fpu *fpu) -{ - if (use_xsave()) { - fpu_xsave(fpu); - - /* - * xsave header may indicate the init state of the FP. - */ - if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP)) - return 1; - } else if (use_fxsr()) { - fpu_fxsave(fpu); - } else { - asm volatile("fnsave %[fx]; fwait" - : [fx] "=m" (fpu->state->fsave)); - return 0; - } - - /* - * If exceptions are pending, we need to clear them so - * that we don't randomly get exceptions later. - * - * FIXME! Is this perhaps only true for the old-style - * irq13 case? Maybe we could leave the x87 state - * intact otherwise? - */ - if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) { - asm volatile("fnclex"); - return 0; - } - return 1; -} - -static inline int __save_init_fpu(struct task_struct *tsk) -{ - return fpu_save_init(&tsk->thread.fpu); -} - -static inline int fpu_restore_checking(struct fpu *fpu) -{ - if (use_xsave()) - return fpu_xrstor_checking(&fpu->state->xsave); - else if (use_fxsr()) - return fxrstor_checking(&fpu->state->fxsave); - else - return frstor_checking(&fpu->state->fsave); -} - -static inline int restore_fpu_checking(struct task_struct *tsk) -{ - /* - * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is - * pending. Clear the x87 state here by setting it to fixed values. - * "m" is a random variable that should be in L1. - */ - if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) { - asm volatile( - "fnclex\n\t" - "emms\n\t" - "fildl %P[addr]" /* set F?P to defined value */ - : : [addr] "m" (tsk->thread.fpu.has_fpu)); - } - - return fpu_restore_checking(&tsk->thread.fpu); -} - -/* - * Software FPU state helpers. Careful: these need to - * be preemption protection *and* they need to be - * properly paired with the CR0.TS changes! - */ -static inline int __thread_has_fpu(struct task_struct *tsk) -{ - return tsk->thread.fpu.has_fpu; -} - -/* Must be paired with an 'stts' after! */ -static inline void __thread_clear_has_fpu(struct task_struct *tsk) -{ - tsk->thread.fpu.has_fpu = 0; - this_cpu_write(fpu_owner_task, NULL); -} - -/* Must be paired with a 'clts' before! */ -static inline void __thread_set_has_fpu(struct task_struct *tsk) -{ - tsk->thread.fpu.has_fpu = 1; - this_cpu_write(fpu_owner_task, tsk); -} - -/* - * Encapsulate the CR0.TS handling together with the - * software flag. - * - * These generally need preemption protection to work, - * do try to avoid using these on their own. - */ -static inline void __thread_fpu_end(struct task_struct *tsk) -{ - __thread_clear_has_fpu(tsk); - if (!use_eager_fpu()) - stts(); -} - -static inline void __thread_fpu_begin(struct task_struct *tsk) -{ - if (!use_eager_fpu()) - clts(); - __thread_set_has_fpu(tsk); -} - -static inline void drop_fpu(struct task_struct *tsk) -{ - /* - * Forget coprocessor state.. - */ - preempt_disable(); - tsk->thread.fpu_counter = 0; - - if (__thread_has_fpu(tsk)) { - /* Ignore delayed exceptions from user space */ - asm volatile("1: fwait\n" - "2:\n" - _ASM_EXTABLE(1b, 2b)); - __thread_fpu_end(tsk); - } - - clear_stopped_child_used_math(tsk); - preempt_enable(); -} - -static inline void restore_init_xstate(void) -{ - if (use_xsave()) - xrstor_state(init_xstate_buf, -1); - else - fxrstor_checking(&init_xstate_buf->i387); -} - -/* - * Reset the FPU state in the eager case and drop it in the lazy case (later use - * will reinit it). - */ -static inline void fpu_reset_state(struct task_struct *tsk) -{ - if (!use_eager_fpu()) - drop_fpu(tsk); - else - restore_init_xstate(); -} - -/* - * FPU state switching for scheduling. - * - * This is a two-stage process: - * - * - switch_fpu_prepare() saves the old state and - * sets the new state of the CR0.TS bit. This is - * done within the context of the old process. - * - * - switch_fpu_finish() restores the new state as - * necessary. - */ -typedef struct { int preload; } fpu_switch_t; - -static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu) -{ - fpu_switch_t fpu; - - /* - * If the task has used the math, pre-load the FPU on xsave processors - * or if the past 5 consecutive context-switches used math. - */ - fpu.preload = tsk_used_math(new) && - (use_eager_fpu() || new->thread.fpu_counter > 5); - - if (__thread_has_fpu(old)) { - if (!__save_init_fpu(old)) - task_disable_lazy_fpu_restore(old); - else - old->thread.fpu.last_cpu = cpu; - - /* But leave fpu_owner_task! */ - old->thread.fpu.has_fpu = 0; - - /* Don't change CR0.TS if we just switch! */ - if (fpu.preload) { - new->thread.fpu_counter++; - __thread_set_has_fpu(new); - prefetch(new->thread.fpu.state); - } else if (!use_eager_fpu()) - stts(); - } else { - old->thread.fpu_counter = 0; - task_disable_lazy_fpu_restore(old); - if (fpu.preload) { - new->thread.fpu_counter++; - if (fpu_lazy_restore(new, cpu)) - fpu.preload = 0; - else - prefetch(new->thread.fpu.state); - __thread_fpu_begin(new); - } - } - return fpu; -} - -/* - * By the time this gets called, we've already cleared CR0.TS and - * given the process the FPU if we are going to preload the FPU - * state - all we need to do is to conditionally restore the register - * state itself. - */ -static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu) -{ - if (fpu.preload) { - if (unlikely(restore_fpu_checking(new))) - fpu_reset_state(new); - } -} - -/* - * Signal frame handlers... - */ -extern int save_xstate_sig(void __user *buf, void __user *fx, int size); -extern int __restore_xstate_sig(void __user *buf, void __user *fx, int size); - -static inline int xstate_sigframe_size(void) -{ - return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size; -} - -static inline int restore_xstate_sig(void __user *buf, int ia32_frame) -{ - void __user *buf_fx = buf; - int size = xstate_sigframe_size(); - - if (ia32_frame && use_fxsr()) { - buf_fx = buf + sizeof(struct i387_fsave_struct); - size += sizeof(struct i387_fsave_struct); - } - - return __restore_xstate_sig(buf, buf_fx, size); -} - -/* - * Needs to be preemption-safe. - * - * NOTE! user_fpu_begin() must be used only immediately before restoring - * the save state. It does not do any saving/restoring on its own. In - * lazy FPU mode, it is just an optimization to avoid a #NM exception, - * the task can lose the FPU right after preempt_enable(). - */ -static inline void user_fpu_begin(void) -{ - preempt_disable(); - if (!user_has_fpu()) - __thread_fpu_begin(current); - preempt_enable(); -} - -static inline void __save_fpu(struct task_struct *tsk) -{ - if (use_xsave()) { - if (unlikely(system_state == SYSTEM_BOOTING)) - xsave_state_booting(&tsk->thread.fpu.state->xsave, -1); - else - xsave_state(&tsk->thread.fpu.state->xsave, -1); - } else - fpu_fxsave(&tsk->thread.fpu); -} - -/* - * i387 state interaction - */ -static inline unsigned short get_fpu_cwd(struct task_struct *tsk) -{ - if (cpu_has_fxsr) { - return tsk->thread.fpu.state->fxsave.cwd; - } else { - return (unsigned short)tsk->thread.fpu.state->fsave.cwd; - } -} - -static inline unsigned short get_fpu_swd(struct task_struct *tsk) -{ - if (cpu_has_fxsr) { - return tsk->thread.fpu.state->fxsave.swd; - } else { - return (unsigned short)tsk->thread.fpu.state->fsave.swd; - } -} - -static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk) -{ - if (cpu_has_xmm) { - return tsk->thread.fpu.state->fxsave.mxcsr; - } else { - return MXCSR_DEFAULT; - } -} - -static bool fpu_allocated(struct fpu *fpu) -{ - return fpu->state != NULL; -} - -static inline int fpu_alloc(struct fpu *fpu) -{ - if (fpu_allocated(fpu)) - return 0; - fpu->state = kmem_cache_alloc(task_xstate_cachep, GFP_KERNEL); - if (!fpu->state) - return -ENOMEM; - WARN_ON((unsigned long)fpu->state & 15); - return 0; -} - -static inline void fpu_free(struct fpu *fpu) -{ - if (fpu->state) { - kmem_cache_free(task_xstate_cachep, fpu->state); - fpu->state = NULL; - } -} - -static inline void fpu_copy(struct task_struct *dst, struct task_struct *src) -{ - if (use_eager_fpu()) { - memset(&dst->thread.fpu.state->xsave, 0, xstate_size); - __save_fpu(dst); - } else { - struct fpu *dfpu = &dst->thread.fpu; - struct fpu *sfpu = &src->thread.fpu; - - unlazy_fpu(src); - memcpy(dfpu->state, sfpu->state, xstate_size); - } -} - -static inline unsigned long -alloc_mathframe(unsigned long sp, int ia32_frame, unsigned long *buf_fx, - unsigned long *size) -{ - unsigned long frame_size = xstate_sigframe_size(); - - *buf_fx = sp = round_down(sp - frame_size, 64); - if (ia32_frame && use_fxsr()) { - frame_size += sizeof(struct i387_fsave_struct); - sp -= sizeof(struct i387_fsave_struct); - } - - *size = frame_size; - return sp; -} - -#endif diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h new file mode 100644 index 000000000..1429a7c73 --- /dev/null +++ b/arch/x86/include/asm/fpu/api.h @@ -0,0 +1,48 @@ +/* + * Copyright (C) 1994 Linus Torvalds + * + * Pentium III FXSR, SSE support + * General FPU state handling cleanups + * Gareth Hughes <gareth@valinux.com>, May 2000 + * x86-64 work by Andi Kleen 2002 + */ + +#ifndef _ASM_X86_FPU_API_H +#define _ASM_X86_FPU_API_H + +/* + * Careful: __kernel_fpu_begin/end() must be called with preempt disabled + * and they don't touch the preempt state on their own. + * If you enable preemption after __kernel_fpu_begin(), preempt notifier + * should call the __kernel_fpu_end() to prevent the kernel/user FPU + * state from getting corrupted. KVM for example uses this model. + * + * All other cases use kernel_fpu_begin/end() which disable preemption + * during kernel FPU usage. + */ +extern void __kernel_fpu_begin(void); +extern void __kernel_fpu_end(void); +extern void kernel_fpu_begin(void); +extern void kernel_fpu_end(void); +extern bool irq_fpu_usable(void); + +/* + * Some instructions like VIA's padlock instructions generate a spurious + * DNA fault but don't modify SSE registers. And these instructions + * get used from interrupt context as well. To prevent these kernel instructions + * in interrupt context interacting wrongly with other user/kernel fpu usage, we + * should use them only in the context of irq_ts_save/restore() + */ +extern int irq_ts_save(void); +extern void irq_ts_restore(int TS_state); + +/* + * Query the presence of one or more xfeatures. Works on any legacy CPU as well. + * + * If 'feature_name' is set then put a human-readable description of + * the feature there as well - this can be used to print error (or success) + * messages. + */ +extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name); + +#endif /* _ASM_X86_FPU_API_H */ diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h new file mode 100644 index 000000000..3c3550c3a --- /dev/null +++ b/arch/x86/include/asm/fpu/internal.h @@ -0,0 +1,694 @@ +/* + * Copyright (C) 1994 Linus Torvalds + * + * Pentium III FXSR, SSE support + * General FPU state handling cleanups + * Gareth Hughes <gareth@valinux.com>, May 2000 + * x86-64 work by Andi Kleen 2002 + */ + +#ifndef _ASM_X86_FPU_INTERNAL_H +#define _ASM_X86_FPU_INTERNAL_H + +#include <linux/compat.h> +#include <linux/sched.h> +#include <linux/slab.h> + +#include <asm/user.h> +#include <asm/fpu/api.h> +#include <asm/fpu/xstate.h> + +/* + * High level FPU state handling functions: + */ +extern void fpu__activate_curr(struct fpu *fpu); +extern void fpu__activate_fpstate_read(struct fpu *fpu); +extern void fpu__activate_fpstate_write(struct fpu *fpu); +extern void fpu__save(struct fpu *fpu); +extern void fpu__restore(struct fpu *fpu); +extern int fpu__restore_sig(void __user *buf, int ia32_frame); +extern void fpu__drop(struct fpu *fpu); +extern int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu); +extern void fpu__clear(struct fpu *fpu); +extern int fpu__exception_code(struct fpu *fpu, int trap_nr); +extern int dump_fpu(struct pt_regs *ptregs, struct user_i387_struct *fpstate); + +/* + * Boot time FPU initialization functions: + */ +extern void fpu__init_cpu(void); +extern void fpu__init_system_xstate(void); +extern void fpu__init_cpu_xstate(void); +extern void fpu__init_system(struct cpuinfo_x86 *c); +extern void fpu__init_check_bugs(void); +extern void fpu__resume_cpu(void); + +/* + * Debugging facility: + */ +#ifdef CONFIG_X86_DEBUG_FPU +# define WARN_ON_FPU(x) WARN_ON_ONCE(x) +#else +# define WARN_ON_FPU(x) ({ (void)(x); 0; }) +#endif + +/* + * FPU related CPU feature flag helper routines: + */ +static __always_inline __pure bool use_eager_fpu(void) +{ + return static_cpu_has_safe(X86_FEATURE_EAGER_FPU); +} + +static __always_inline __pure bool use_xsaveopt(void) +{ + return static_cpu_has_safe(X86_FEATURE_XSAVEOPT); +} + +static __always_inline __pure bool use_xsave(void) +{ + return static_cpu_has_safe(X86_FEATURE_XSAVE); +} + +static __always_inline __pure bool use_fxsr(void) +{ + return static_cpu_has_safe(X86_FEATURE_FXSR); +} + +/* + * fpstate handling functions: + */ + +extern union fpregs_state init_fpstate; + +extern void fpstate_init(union fpregs_state *state); +#ifdef CONFIG_MATH_EMULATION +extern void fpstate_init_soft(struct swregs_state *soft); +#else +static inline void fpstate_init_soft(struct swregs_state *soft) {} +#endif +static inline void fpstate_init_fxstate(struct fxregs_state *fx) +{ + fx->cwd = 0x37f; + fx->mxcsr = MXCSR_DEFAULT; +} +extern void fpstate_sanitize_xstate(struct fpu *fpu); + +#define user_insn(insn, output, input...) \ +({ \ + int err; \ + asm volatile(ASM_STAC "\n" \ + "1:" #insn "\n\t" \ + "2: " ASM_CLAC "\n" \ + ".section .fixup,\"ax\"\n" \ + "3: movl $-1,%[err]\n" \ + " jmp 2b\n" \ + ".previous\n" \ + _ASM_EXTABLE(1b, 3b) \ + : [err] "=r" (err), output \ + : "0"(0), input); \ + err; \ +}) + +#define check_insn(insn, output, input...) \ +({ \ + int err; \ + asm volatile("1:" #insn "\n\t" \ + "2:\n" \ + ".section .fixup,\"ax\"\n" \ + "3: movl $-1,%[err]\n" \ + " jmp 2b\n" \ + ".previous\n" \ + _ASM_EXTABLE(1b, 3b) \ + : [err] "=r" (err), output \ + : "0"(0), input); \ + err; \ +}) + +static inline int copy_fregs_to_user(struct fregs_state __user *fx) +{ + return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx)); +} + +static inline int copy_fxregs_to_user(struct fxregs_state __user *fx) +{ + if (config_enabled(CONFIG_X86_32)) + return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx)); + else if (config_enabled(CONFIG_AS_FXSAVEQ)) + return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx)); + + /* See comment in copy_fxregs_to_kernel() below. */ + return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx)); +} + +static inline void copy_kernel_to_fxregs(struct fxregs_state *fx) +{ + int err; + + if (config_enabled(CONFIG_X86_32)) { + err = check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); + } else { + if (config_enabled(CONFIG_AS_FXSAVEQ)) { + err = check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); + } else { + /* See comment in copy_fxregs_to_kernel() below. */ + err = check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx)); + } + } + /* Copying from a kernel buffer to FPU registers should never fail: */ + WARN_ON_FPU(err); +} + +static inline int copy_user_to_fxregs(struct fxregs_state __user *fx) +{ + if (config_enabled(CONFIG_X86_32)) + return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); + else if (config_enabled(CONFIG_AS_FXSAVEQ)) + return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); + + /* See comment in copy_fxregs_to_kernel() below. */ + return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), + "m" (*fx)); +} + +static inline void copy_kernel_to_fregs(struct fregs_state *fx) +{ + int err = check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); + + WARN_ON_FPU(err); +} + +static inline int copy_user_to_fregs(struct fregs_state __user *fx) +{ + return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); +} + +static inline void copy_fxregs_to_kernel(struct fpu *fpu) +{ + if (config_enabled(CONFIG_X86_32)) + asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state.fxsave)); + else if (config_enabled(CONFIG_AS_FXSAVEQ)) + asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state.fxsave)); + else { + /* Using "rex64; fxsave %0" is broken because, if the memory + * operand uses any extended registers for addressing, a second + * REX prefix will be generated (to the assembler, rex64 + * followed by semicolon is a separate instruction), and hence + * the 64-bitness is lost. + * + * Using "fxsaveq %0" would be the ideal choice, but is only + * supported starting with gas 2.16. + * + * Using, as a workaround, the properly prefixed form below + * isn't accepted by any binutils version so far released, + * complaining that the same type of prefix is used twice if + * an extended register is needed for addressing (fix submitted + * to mainline 2005-11-21). + * + * asm volatile("rex64/fxsave %0" : "=m" (fpu->state.fxsave)); + * + * This, however, we can work around by forcing the compiler to + * select an addressing mode that doesn't require extended + * registers. + */ + asm volatile( "rex64/fxsave (%[fx])" + : "=m" (fpu->state.fxsave) + : [fx] "R" (&fpu->state.fxsave)); + } +} + +/* These macros all use (%edi)/(%rdi) as the single memory argument. */ +#define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27" +#define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37" +#define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f" +#define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f" +#define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f" + +/* xstate instruction fault handler: */ +#define xstate_fault(__err) \ + \ + ".section .fixup,\"ax\"\n" \ + \ + "3: movl $-2,%[_err]\n" \ + " jmp 2b\n" \ + \ + ".previous\n" \ + \ + _ASM_EXTABLE(1b, 3b) \ + : [_err] "=r" (__err) + +/* + * This function is called only during boot time when x86 caps are not set + * up and alternative can not be used yet. + */ +static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate) +{ + u64 mask = -1; + u32 lmask = mask; + u32 hmask = mask >> 32; + int err = 0; + + WARN_ON(system_state != SYSTEM_BOOTING); + + if (boot_cpu_has(X86_FEATURE_XSAVES)) + asm volatile("1:"XSAVES"\n\t" + "2:\n\t" + xstate_fault(err) + : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) + : "memory"); + else + asm volatile("1:"XSAVE"\n\t" + "2:\n\t" + xstate_fault(err) + : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) + : "memory"); + + /* We should never fault when copying to a kernel buffer: */ + WARN_ON_FPU(err); +} + +/* + * This function is called only during boot time when x86 caps are not set + * up and alternative can not be used yet. + */ +static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate) +{ + u64 mask = -1; + u32 lmask = mask; + u32 hmask = mask >> 32; + int err = 0; + + WARN_ON(system_state != SYSTEM_BOOTING); + + if (boot_cpu_has(X86_FEATURE_XSAVES)) + asm volatile("1:"XRSTORS"\n\t" + "2:\n\t" + xstate_fault(err) + : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) + : "memory"); + else + asm volatile("1:"XRSTOR"\n\t" + "2:\n\t" + xstate_fault(err) + : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) + : "memory"); + + /* We should never fault when copying from a kernel buffer: */ + WARN_ON_FPU(err); +} + +/* + * Save processor xstate to xsave area. + */ +static inline void copy_xregs_to_kernel(struct xregs_state *xstate) +{ + u64 mask = -1; + u32 lmask = mask; + u32 hmask = mask >> 32; + int err = 0; + + WARN_ON(!alternatives_patched); + + /* + * If xsaves is enabled, xsaves replaces xsaveopt because + * it supports compact format and supervisor states in addition to + * modified optimization in xsaveopt. + * + * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave + * because xsaveopt supports modified optimization which is not + * supported by xsave. + * + * If none of xsaves and xsaveopt is enabled, use xsave. + */ + alternative_input_2( + "1:"XSAVE, + XSAVEOPT, + X86_FEATURE_XSAVEOPT, + XSAVES, + X86_FEATURE_XSAVES, + [xstate] "D" (xstate), "a" (lmask), "d" (hmask) : + "memory"); + asm volatile("2:\n\t" + xstate_fault(err) + : "0" (err) + : "memory"); + + /* We should never fault when copying to a kernel buffer: */ + WARN_ON_FPU(err); +} + +/* + * Restore processor xstate from xsave area. + */ +static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask) +{ + u32 lmask = mask; + u32 hmask = mask >> 32; + int err = 0; + + /* + * Use xrstors to restore context if it is enabled. xrstors supports + * compacted format of xsave area which is not supported by xrstor. + */ + alternative_input( + "1: " XRSTOR, + XRSTORS, + X86_FEATURE_XSAVES, + "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask) + : "memory"); + + asm volatile("2:\n" + xstate_fault(err) + : "0" (err) + : "memory"); + + /* We should never fault when copying from a kernel buffer: */ + WARN_ON_FPU(err); +} + +/* + * Save xstate to user space xsave area. + * + * We don't use modified optimization because xrstor/xrstors might track + * a different application. + * + * We don't use compacted format xsave area for + * backward compatibility for old applications which don't understand + * compacted format of xsave area. + */ +static inline int copy_xregs_to_user(struct xregs_state __user *buf) +{ + int err; + + /* + * Clear the xsave header first, so that reserved fields are + * initialized to zero. + */ + err = __clear_user(&buf->header, sizeof(buf->header)); + if (unlikely(err)) + return -EFAULT; + + __asm__ __volatile__(ASM_STAC "\n" + "1:"XSAVE"\n" + "2: " ASM_CLAC "\n" + xstate_fault(err) + : "D" (buf), "a" (-1), "d" (-1), "0" (err) + : "memory"); + return err; +} + +/* + * Restore xstate from user space xsave area. + */ +static inline int copy_user_to_xregs(struct xregs_state __user *buf, u64 mask) +{ + struct xregs_state *xstate = ((__force struct xregs_state *)buf); + u32 lmask = mask; + u32 hmask = mask >> 32; + int err = 0; + + __asm__ __volatile__(ASM_STAC "\n" + "1:"XRSTOR"\n" + "2: " ASM_CLAC "\n" + xstate_fault(err) + : "D" (xstate), "a" (lmask), "d" (hmask), "0" (err) + : "memory"); /* memory required? */ + return err; +} + +/* + * These must be called with preempt disabled. Returns + * 'true' if the FPU state is still intact and we can + * keep registers active. + * + * The legacy FNSAVE instruction cleared all FPU state + * unconditionally, so registers are essentially destroyed. + * Modern FPU state can be kept in registers, if there are + * no pending FP exceptions. + */ +static inline int copy_fpregs_to_fpstate(struct fpu *fpu) +{ + if (likely(use_xsave())) { + copy_xregs_to_kernel(&fpu->state.xsave); + return 1; + } + + if (likely(use_fxsr())) { + copy_fxregs_to_kernel(fpu); + return 1; + } + + /* + * Legacy FPU register saving, FNSAVE always clears FPU registers, + * so we have to mark them inactive: + */ + asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave)); + + return 0; +} + +static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate) +{ + if (use_xsave()) { + copy_kernel_to_xregs(&fpstate->xsave, -1); + } else { + if (use_fxsr()) + copy_kernel_to_fxregs(&fpstate->fxsave); + else + copy_kernel_to_fregs(&fpstate->fsave); + } +} + +static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate) +{ + /* + * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is + * pending. Clear the x87 state here by setting it to fixed values. + * "m" is a random variable that should be in L1. + */ + if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) { + asm volatile( + "fnclex\n\t" + "emms\n\t" + "fildl %P[addr]" /* set F?P to defined value */ + : : [addr] "m" (fpstate)); + } + + __copy_kernel_to_fpregs(fpstate); +} + +extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size); + +/* + * FPU context switch related helper methods: + */ + +DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); + +/* + * Must be run with preemption disabled: this clears the fpu_fpregs_owner_ctx, + * on this CPU. + * + * This will disable any lazy FPU state restore of the current FPU state, + * but if the current thread owns the FPU, it will still be saved by. + */ +static inline void __cpu_disable_lazy_restore(unsigned int cpu) +{ + per_cpu(fpu_fpregs_owner_ctx, cpu) = NULL; +} + +static inline int fpu_want_lazy_restore(struct fpu *fpu, unsigned int cpu) +{ + return fpu == this_cpu_read_stable(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu; +} + + +/* + * Wrap lazy FPU TS handling in a 'hw fpregs activation/deactivation' + * idiom, which is then paired with the sw-flag (fpregs_active) later on: + */ + +static inline void __fpregs_activate_hw(void) +{ + if (!use_eager_fpu()) + clts(); +} + +static inline void __fpregs_deactivate_hw(void) +{ + if (!use_eager_fpu()) + stts(); +} + +/* Must be paired with an 'stts' (fpregs_deactivate_hw()) after! */ +static inline void __fpregs_deactivate(struct fpu *fpu) +{ + WARN_ON_FPU(!fpu->fpregs_active); + + fpu->fpregs_active = 0; + this_cpu_write(fpu_fpregs_owner_ctx, NULL); +} + +/* Must be paired with a 'clts' (fpregs_activate_hw()) before! */ +static inline void __fpregs_activate(struct fpu *fpu) +{ + WARN_ON_FPU(fpu->fpregs_active); + + fpu->fpregs_active = 1; + this_cpu_write(fpu_fpregs_owner_ctx, fpu); +} + +/* + * The question "does this thread have fpu access?" + * is slightly racy, since preemption could come in + * and revoke it immediately after the test. + * + * However, even in that very unlikely scenario, + * we can just assume we have FPU access - typically + * to save the FP state - we'll just take a #NM + * fault and get the FPU access back. + */ +static inline int fpregs_active(void) +{ + return current->thread.fpu.fpregs_active; +} + +/* + * Encapsulate the CR0.TS handling together with the + * software flag. + * + * These generally need preemption protection to work, + * do try to avoid using these on their own. + */ +static inline void fpregs_activate(struct fpu *fpu) +{ + __fpregs_activate_hw(); + __fpregs_activate(fpu); +} + +static inline void fpregs_deactivate(struct fpu *fpu) +{ + __fpregs_deactivate(fpu); + __fpregs_deactivate_hw(); +} + +/* + * FPU state switching for scheduling. + * + * This is a two-stage process: + * + * - switch_fpu_prepare() saves the old state and + * sets the new state of the CR0.TS bit. This is + * done within the context of the old process. + * + * - switch_fpu_finish() restores the new state as + * necessary. + */ +typedef struct { int preload; } fpu_switch_t; + +static inline fpu_switch_t +switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu) +{ + fpu_switch_t fpu; + + /* + * If the task has used the math, pre-load the FPU on xsave processors + * or if the past 5 consecutive context-switches used math. + */ + fpu.preload = new_fpu->fpstate_active && + (use_eager_fpu() || new_fpu->counter > 5); + + if (old_fpu->fpregs_active) { + if (!copy_fpregs_to_fpstate(old_fpu)) + old_fpu->last_cpu = -1; + else + old_fpu->last_cpu = cpu; + + /* But leave fpu_fpregs_owner_ctx! */ + old_fpu->fpregs_active = 0; + + /* Don't change CR0.TS if we just switch! */ + if (fpu.preload) { + new_fpu->counter++; + __fpregs_activate(new_fpu); + prefetch(&new_fpu->state); + } else { + __fpregs_deactivate_hw(); + } + } else { + old_fpu->counter = 0; + old_fpu->last_cpu = -1; + if (fpu.preload) { + new_fpu->counter++; + if (fpu_want_lazy_restore(new_fpu, cpu)) + fpu.preload = 0; + else + prefetch(&new_fpu->state); + fpregs_activate(new_fpu); + } + } + return fpu; +} + +/* + * Misc helper functions: + */ + +/* + * By the time this gets called, we've already cleared CR0.TS and + * given the process the FPU if we are going to preload the FPU + * state - all we need to do is to conditionally restore the register + * state itself. + */ +static inline void switch_fpu_finish(struct fpu *new_fpu, fpu_switch_t fpu_switch) +{ + if (fpu_switch.preload) + copy_kernel_to_fpregs(&new_fpu->state); +} + +/* + * Needs to be preemption-safe. + * + * NOTE! user_fpu_begin() must be used only immediately before restoring + * the save state. It does not do any saving/restoring on its own. In + * lazy FPU mode, it is just an optimization to avoid a #NM exception, + * the task can lose the FPU right after preempt_enable(). + */ +static inline void user_fpu_begin(void) +{ + struct fpu *fpu = ¤t->thread.fpu; + + preempt_disable(); + if (!fpregs_active()) + fpregs_activate(fpu); + preempt_enable(); +} + +/* + * MXCSR and XCR definitions: + */ + +extern unsigned int mxcsr_feature_mask; + +#define XCR_XFEATURE_ENABLED_MASK 0x00000000 + +static inline u64 xgetbv(u32 index) +{ + u32 eax, edx; + + asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */ + : "=a" (eax), "=d" (edx) + : "c" (index)); + return eax + ((u64)edx << 32); +} + +static inline void xsetbv(u32 index, u64 value) +{ + u32 eax = value; + u32 edx = value >> 32; + + asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */ + : : "a" (eax), "d" (edx), "c" (index)); +} + +#endif /* _ASM_X86_FPU_INTERNAL_H */ diff --git a/arch/x86/include/asm/fpu/regset.h b/arch/x86/include/asm/fpu/regset.h new file mode 100644 index 000000000..39d3107ac --- /dev/null +++ b/arch/x86/include/asm/fpu/regset.h @@ -0,0 +1,21 @@ +/* + * FPU regset handling methods: + */ +#ifndef _ASM_X86_FPU_REGSET_H +#define _ASM_X86_FPU_REGSET_H + +#include <linux/regset.h> + +extern user_regset_active_fn regset_fpregs_active, regset_xregset_fpregs_active; +extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get, + xstateregs_get; +extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set, + xstateregs_set; + +/* + * xstateregs_active == regset_fpregs_active. Please refer to the comment + * at the definition of regset_fpregs_active. + */ +#define xstateregs_active regset_fpregs_active + +#endif /* _ASM_X86_FPU_REGSET_H */ diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h new file mode 100644 index 000000000..7358e9d61 --- /dev/null +++ b/arch/x86/include/asm/fpu/signal.h @@ -0,0 +1,33 @@ +/* + * x86 FPU signal frame handling methods: + */ +#ifndef _ASM_X86_FPU_SIGNAL_H +#define _ASM_X86_FPU_SIGNAL_H + +#ifdef CONFIG_X86_64 +# include <asm/sigcontext32.h> +# include <asm/user32.h> +struct ksignal; +int ia32_setup_rt_frame(int sig, struct ksignal *ksig, + compat_sigset_t *set, struct pt_regs *regs); +int ia32_setup_frame(int sig, struct ksignal *ksig, + compat_sigset_t *set, struct pt_regs *regs); +#else +# define user_i387_ia32_struct user_i387_struct +# define user32_fxsr_struct user_fxsr_struct +# define ia32_setup_frame __setup_frame +# define ia32_setup_rt_frame __setup_rt_frame +#endif + +extern void convert_from_fxsr(struct user_i387_ia32_struct *env, + struct task_struct *tsk); +extern void convert_to_fxsr(struct task_struct *tsk, + const struct user_i387_ia32_struct *env); + +unsigned long +fpu__alloc_mathframe(unsigned long sp, int ia32_frame, + unsigned long *buf_fx, unsigned long *size); + +extern void fpu__init_prepare_fx_sw_frame(void); + +#endif /* _ASM_X86_FPU_SIGNAL_H */ diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h new file mode 100644 index 000000000..c49c51731 --- /dev/null +++ b/arch/x86/include/asm/fpu/types.h @@ -0,0 +1,297 @@ +/* + * FPU data structures: + */ +#ifndef _ASM_X86_FPU_H +#define _ASM_X86_FPU_H + +/* + * The legacy x87 FPU state format, as saved by FSAVE and + * restored by the FRSTOR instructions: + */ +struct fregs_state { + u32 cwd; /* FPU Control Word */ + u32 swd; /* FPU Status Word */ + u32 twd; /* FPU Tag Word */ + u32 fip; /* FPU IP Offset */ + u32 fcs; /* FPU IP Selector */ + u32 foo; /* FPU Operand Pointer Offset */ + u32 fos; /* FPU Operand Pointer Selector */ + + /* 8*10 bytes for each FP-reg = 80 bytes: */ + u32 st_space[20]; + + /* Software status information [not touched by FSAVE]: */ + u32 status; +}; + +/* + * The legacy fx SSE/MMX FPU state format, as saved by FXSAVE and + * restored by the FXRSTOR instructions. It's similar to the FSAVE + * format, but differs in some areas, plus has extensions at + * the end for the XMM registers. + */ +struct fxregs_state { + u16 cwd; /* Control Word */ + u16 swd; /* Status Word */ + u16 twd; /* Tag Word */ + u16 fop; /* Last Instruction Opcode */ + union { + struct { + u64 rip; /* Instruction Pointer */ + u64 rdp; /* Data Pointer */ + }; + struct { + u32 fip; /* FPU IP Offset */ + u32 fcs; /* FPU IP Selector */ + u32 foo; /* FPU Operand Offset */ + u32 fos; /* FPU Operand Selector */ + }; + }; + u32 mxcsr; /* MXCSR Register State */ + u32 mxcsr_mask; /* MXCSR Mask */ + + /* 8*16 bytes for each FP-reg = 128 bytes: */ + u32 st_space[32]; + + /* 16*16 bytes for each XMM-reg = 256 bytes: */ + u32 xmm_space[64]; + + u32 padding[12]; + + union { + u32 padding1[12]; + u32 sw_reserved[12]; + }; + +} __attribute__((aligned(16))); + +/* Default value for fxregs_state.mxcsr: */ +#define MXCSR_DEFAULT 0x1f80 + +/* + * Software based FPU emulation state. This is arbitrary really, + * it matches the x87 format to make it easier to understand: + */ +struct swregs_state { + u32 cwd; + u32 swd; + u32 twd; + u32 fip; + u32 fcs; + u32 foo; + u32 fos; + /* 8*10 bytes for each FP-reg = 80 bytes: */ + u32 st_space[20]; + u8 ftop; + u8 changed; + u8 lookahead; + u8 no_update; + u8 rm; + u8 alimit; + struct math_emu_info *info; + u32 entry_eip; +}; + +/* + * List of XSAVE features Linux knows about: + */ +enum xfeature_bit { + XSTATE_BIT_FP, + XSTATE_BIT_SSE, + XSTATE_BIT_YMM, + XSTATE_BIT_BNDREGS, + XSTATE_BIT_BNDCSR, + XSTATE_BIT_OPMASK, + XSTATE_BIT_ZMM_Hi256, + XSTATE_BIT_Hi16_ZMM, + + XFEATURES_NR_MAX, +}; + +#define XSTATE_FP (1 << XSTATE_BIT_FP) +#define XSTATE_SSE (1 << XSTATE_BIT_SSE) +#define XSTATE_YMM (1 << XSTATE_BIT_YMM) +#define XSTATE_BNDREGS (1 << XSTATE_BIT_BNDREGS) +#define XSTATE_BNDCSR (1 << XSTATE_BIT_BNDCSR) +#define XSTATE_OPMASK (1 << XSTATE_BIT_OPMASK) +#define XSTATE_ZMM_Hi256 (1 << XSTATE_BIT_ZMM_Hi256) +#define XSTATE_Hi16_ZMM (1 << XSTATE_BIT_Hi16_ZMM) + +#define XSTATE_FPSSE (XSTATE_FP | XSTATE_SSE) +#define XSTATE_AVX512 (XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM) + +/* + * There are 16x 256-bit AVX registers named YMM0-YMM15. + * The low 128 bits are aliased to the 16 SSE registers (XMM0-XMM15) + * and are stored in 'struct fxregs_state::xmm_space[]'. + * + * The high 128 bits are stored here: + * 16x 128 bits == 256 bytes. + */ +struct ymmh_struct { + u8 ymmh_space[256]; +}; + +/* We don't support LWP yet: */ +struct lwp_struct { + u8 reserved[128]; +}; + +/* Intel MPX support: */ +struct bndreg { + u64 lower_bound; + u64 upper_bound; +} __packed; + +struct bndcsr { + u64 bndcfgu; + u64 bndstatus; +} __packed; + +struct mpx_struct { + struct bndreg bndreg[4]; + struct bndcsr bndcsr; +}; + +struct xstate_header { + u64 xfeatures; + u64 xcomp_bv; + u64 reserved[6]; +} __attribute__((packed)); + +/* New processor state extensions should be added here: */ +#define XSTATE_RESERVE (sizeof(struct ymmh_struct) + \ + sizeof(struct lwp_struct) + \ + sizeof(struct mpx_struct) ) +/* + * This is our most modern FPU state format, as saved by the XSAVE + * and restored by the XRSTOR instructions. + * + * It consists of a legacy fxregs portion, an xstate header and + * subsequent fixed size areas as defined by the xstate header. + * Not all CPUs support all the extensions. + */ +struct xregs_state { + struct fxregs_state i387; + struct xstate_header header; + u8 __reserved[XSTATE_RESERVE]; +} __attribute__ ((packed, aligned (64))); + +/* + * This is a union of all the possible FPU state formats + * put together, so that we can pick the right one runtime. + * + * The size of the structure is determined by the largest + * member - which is the xsave area: + */ +union fpregs_state { + struct fregs_state fsave; + struct fxregs_state fxsave; + struct swregs_state soft; + struct xregs_state xsave; + u8 __padding[PAGE_SIZE]; +}; + +/* + * Highest level per task FPU state data structure that + * contains the FPU register state plus various FPU + * state fields: + */ +struct fpu { + /* + * @last_cpu: + * + * Records the last CPU on which this context was loaded into + * FPU registers. (In the lazy-restore case we might be + * able to reuse FPU registers across multiple context switches + * this way, if no intermediate task used the FPU.) + * + * A value of -1 is used to indicate that the FPU state in context + * memory is newer than the FPU state in registers, and that the + * FPU state should be reloaded next time the task is run. + */ + unsigned int last_cpu; + + /* + * @fpstate_active: + * + * This flag indicates whether this context is active: if the task + * is not running then we can restore from this context, if the task + * is running then we should save into this context. + */ + unsigned char fpstate_active; + + /* + * @fpregs_active: + * + * This flag determines whether a given context is actively + * loaded into the FPU's registers and that those registers + * represent the task's current FPU state. + * + * Note the interaction with fpstate_active: + * + * # task does not use the FPU: + * fpstate_active == 0 + * + * # task uses the FPU and regs are active: + * fpstate_active == 1 && fpregs_active == 1 + * + * # the regs are inactive but still match fpstate: + * fpstate_active == 1 && fpregs_active == 0 && fpregs_owner == fpu + * + * The third state is what we use for the lazy restore optimization + * on lazy-switching CPUs. + */ + unsigned char fpregs_active; + + /* + * @counter: + * + * This counter contains the number of consecutive context switches + * during which the FPU stays used. If this is over a threshold, the + * lazy FPU restore logic becomes eager, to save the trap overhead. + * This is an unsigned char so that after 256 iterations the counter + * wraps and the context switch behavior turns lazy again; this is to + * deal with bursty apps that only use the FPU for a short time: + */ + unsigned char counter; + /* + * @state: + * + * In-memory copy of all FPU registers that we save/restore + * over context switches. If the task is using the FPU then + * the registers in the FPU are more recent than this state + * copy. If the task context-switches away then they get + * saved here and represent the FPU state. + * + * After context switches there may be a (short) time period + * during which the in-FPU hardware registers are unchanged + * and still perfectly match this state, if the tasks + * scheduled afterwards are not using the FPU. + * + * This is the 'lazy restore' window of optimization, which + * we track though 'fpu_fpregs_owner_ctx' and 'fpu->last_cpu'. + * + * We detect whether a subsequent task uses the FPU via setting + * CR0::TS to 1, which causes any FPU use to raise a #NM fault. + * + * During this window, if the task gets scheduled again, we + * might be able to skip having to do a restore from this + * memory buffer to the hardware registers - at the cost of + * incurring the overhead of #NM fault traps. + * + * Note that on modern CPUs that support the XSAVEOPT (or other + * optimized XSAVE instructions), we don't use #NM traps anymore, + * as the hardware can track whether FPU registers need saving + * or not. On such CPUs we activate the non-lazy ('eagerfpu') + * logic, which unconditionally saves/restores all FPU state + * across context switches. (if FPU state exists.) + */ + union fpregs_state state; + /* + * WARNING: 'state' is dynamically-sized. Do not put + * anything after it here. + */ +}; + +#endif /* _ASM_X86_FPU_H */ diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h new file mode 100644 index 000000000..4656b25bb --- /dev/null +++ b/arch/x86/include/asm/fpu/xstate.h @@ -0,0 +1,46 @@ +#ifndef __ASM_X86_XSAVE_H +#define __ASM_X86_XSAVE_H + +#include <linux/types.h> +#include <asm/processor.h> +#include <linux/uaccess.h> + +/* Bit 63 of XCR0 is reserved for future expansion */ +#define XSTATE_EXTEND_MASK (~(XSTATE_FPSSE | (1ULL << 63))) + +#define XSTATE_CPUID 0x0000000d + +#define FXSAVE_SIZE 512 + +#define XSAVE_HDR_SIZE 64 +#define XSAVE_HDR_OFFSET FXSAVE_SIZE + +#define XSAVE_YMM_SIZE 256 +#define XSAVE_YMM_OFFSET (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET) + +/* Supported features which support lazy state saving */ +#define XSTATE_LAZY (XSTATE_FP | XSTATE_SSE | XSTATE_YMM \ + | XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM) + +/* Supported features which require eager state saving */ +#define XSTATE_EAGER (XSTATE_BNDREGS | XSTATE_BNDCSR) + +/* All currently supported features */ +#define XCNTXT_MASK (XSTATE_LAZY | XSTATE_EAGER) + +#ifdef CONFIG_X86_64 +#define REX_PREFIX "0x48, " +#else +#define REX_PREFIX +#endif + +extern unsigned int xstate_size; +extern u64 xfeatures_mask; +extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; + +extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask); + +void *get_xsave_addr(struct xregs_state *xsave, int xstate); +const void *get_xsave_field_ptr(int xstate_field); + +#endif diff --git a/arch/x86/include/asm/frame.h b/arch/x86/include/asm/frame.h index 3b629f47e..793179cf8 100644 --- a/arch/x86/include/asm/frame.h +++ b/arch/x86/include/asm/frame.h @@ -1,20 +1,17 @@ #ifdef __ASSEMBLY__ #include <asm/asm.h> -#include <asm/dwarf2.h> /* The annotation hides the frame from the unwinder and makes it look like a ordinary ebp save/restore. This avoids some special cases for frame pointer later */ #ifdef CONFIG_FRAME_POINTER .macro FRAME - __ASM_SIZE(push,_cfi) %__ASM_REG(bp) - CFI_REL_OFFSET __ASM_REG(bp), 0 + __ASM_SIZE(push,) %__ASM_REG(bp) __ASM_SIZE(mov) %__ASM_REG(sp), %__ASM_REG(bp) .endm .macro ENDFRAME - __ASM_SIZE(pop,_cfi) %__ASM_REG(bp) - CFI_RESTORE __ASM_REG(bp) + __ASM_SIZE(pop,) %__ASM_REG(bp) .endm #else .macro FRAME diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 0f5fb6b65..7178043b0 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -14,6 +14,7 @@ typedef struct { #endif #ifdef CONFIG_HAVE_KVM unsigned int kvm_posted_intr_ipis; + unsigned int kvm_posted_intr_wakeup_ipis; #endif unsigned int x86_platform_ipis; /* arch dependent */ unsigned int apic_perf_irqs; @@ -33,6 +34,9 @@ typedef struct { #ifdef CONFIG_X86_MCE_THRESHOLD unsigned int irq_threshold_count; #endif +#ifdef CONFIG_X86_MCE_AMD + unsigned int irq_deferred_error_count; +#endif #if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN) unsigned int irq_hv_callback_count; #endif diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h index 36f712594..5fa9fb0f8 100644 --- a/arch/x86/include/asm/hpet.h +++ b/arch/x86/include/asm/hpet.h @@ -74,20 +74,16 @@ extern unsigned int hpet_readl(unsigned int a); extern void force_hpet_resume(void); struct irq_data; +struct hpet_dev; +struct irq_domain; + extern void hpet_msi_unmask(struct irq_data *data); extern void hpet_msi_mask(struct irq_data *data); -struct hpet_dev; extern void hpet_msi_write(struct hpet_dev *hdev, struct msi_msg *msg); extern void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg); - -#ifdef CONFIG_PCI_MSI -extern int default_setup_hpet_msi(unsigned int irq, unsigned int id); -#else -static inline int default_setup_hpet_msi(unsigned int irq, unsigned int id) -{ - return -EINVAL; -} -#endif +extern struct irq_domain *hpet_create_irq_domain(int hpet_id); +extern int hpet_assign_irq(struct irq_domain *domain, + struct hpet_dev *dev, int dev_num); #ifdef CONFIG_HPET_EMULATE_RTC diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h index 68c05398b..f8a29d2c9 100644 --- a/arch/x86/include/asm/hugetlb.h +++ b/arch/x86/include/asm/hugetlb.h @@ -26,9 +26,6 @@ static inline int prepare_hugepage_range(struct file *file, return 0; } -static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm) { -} - static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, @@ -83,15 +80,6 @@ static inline pte_t huge_ptep_get(pte_t *ptep) return *ptep; } -static inline int arch_prepare_hugepage(struct page *page) -{ - return 0; -} - -static inline void arch_release_hugepage(struct page *page) -{ -} - static inline void arch_clear_hugepage_flags(struct page *page) { } diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index e9571ddab..6615032e1 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -29,6 +29,7 @@ extern asmlinkage void apic_timer_interrupt(void); extern asmlinkage void x86_platform_ipi(void); extern asmlinkage void kvm_posted_intr_ipi(void); +extern asmlinkage void kvm_posted_intr_wakeup_ipi(void); extern asmlinkage void error_interrupt(void); extern asmlinkage void irq_work_interrupt(void); @@ -36,43 +37,10 @@ extern asmlinkage void spurious_interrupt(void); extern asmlinkage void thermal_interrupt(void); extern asmlinkage void reschedule_interrupt(void); -extern asmlinkage void invalidate_interrupt(void); -extern asmlinkage void invalidate_interrupt0(void); -extern asmlinkage void invalidate_interrupt1(void); -extern asmlinkage void invalidate_interrupt2(void); -extern asmlinkage void invalidate_interrupt3(void); -extern asmlinkage void invalidate_interrupt4(void); -extern asmlinkage void invalidate_interrupt5(void); -extern asmlinkage void invalidate_interrupt6(void); -extern asmlinkage void invalidate_interrupt7(void); -extern asmlinkage void invalidate_interrupt8(void); -extern asmlinkage void invalidate_interrupt9(void); -extern asmlinkage void invalidate_interrupt10(void); -extern asmlinkage void invalidate_interrupt11(void); -extern asmlinkage void invalidate_interrupt12(void); -extern asmlinkage void invalidate_interrupt13(void); -extern asmlinkage void invalidate_interrupt14(void); -extern asmlinkage void invalidate_interrupt15(void); -extern asmlinkage void invalidate_interrupt16(void); -extern asmlinkage void invalidate_interrupt17(void); -extern asmlinkage void invalidate_interrupt18(void); -extern asmlinkage void invalidate_interrupt19(void); -extern asmlinkage void invalidate_interrupt20(void); -extern asmlinkage void invalidate_interrupt21(void); -extern asmlinkage void invalidate_interrupt22(void); -extern asmlinkage void invalidate_interrupt23(void); -extern asmlinkage void invalidate_interrupt24(void); -extern asmlinkage void invalidate_interrupt25(void); -extern asmlinkage void invalidate_interrupt26(void); -extern asmlinkage void invalidate_interrupt27(void); -extern asmlinkage void invalidate_interrupt28(void); -extern asmlinkage void invalidate_interrupt29(void); -extern asmlinkage void invalidate_interrupt30(void); -extern asmlinkage void invalidate_interrupt31(void); - extern asmlinkage void irq_move_cleanup_interrupt(void); extern asmlinkage void reboot_interrupt(void); extern asmlinkage void threshold_interrupt(void); +extern asmlinkage void deferred_error_interrupt(void); extern asmlinkage void call_function_interrupt(void); extern asmlinkage void call_function_single_interrupt(void); @@ -87,60 +55,93 @@ extern void trace_spurious_interrupt(void); extern void trace_thermal_interrupt(void); extern void trace_reschedule_interrupt(void); extern void trace_threshold_interrupt(void); +extern void trace_deferred_error_interrupt(void); extern void trace_call_function_interrupt(void); extern void trace_call_function_single_interrupt(void); #define trace_irq_move_cleanup_interrupt irq_move_cleanup_interrupt #define trace_reboot_interrupt reboot_interrupt #define trace_kvm_posted_intr_ipi kvm_posted_intr_ipi +#define trace_kvm_posted_intr_wakeup_ipi kvm_posted_intr_wakeup_ipi #endif /* CONFIG_TRACING */ -#ifdef CONFIG_IRQ_REMAP -/* Intel specific interrupt remapping information */ -struct irq_2_iommu { - struct intel_iommu *iommu; - u16 irte_index; - u16 sub_handle; - u8 irte_mask; -}; - -/* AMD specific interrupt remapping information */ -struct irq_2_irte { - u16 devid; /* Device ID for IRTE table */ - u16 index; /* Index into IRTE table*/ -}; -#endif /* CONFIG_IRQ_REMAP */ - #ifdef CONFIG_X86_LOCAL_APIC struct irq_data; +struct pci_dev; +struct msi_desc; + +enum irq_alloc_type { + X86_IRQ_ALLOC_TYPE_IOAPIC = 1, + X86_IRQ_ALLOC_TYPE_HPET, + X86_IRQ_ALLOC_TYPE_MSI, + X86_IRQ_ALLOC_TYPE_MSIX, + X86_IRQ_ALLOC_TYPE_DMAR, + X86_IRQ_ALLOC_TYPE_UV, +}; -struct irq_cfg { - cpumask_var_t domain; - cpumask_var_t old_domain; - u8 vector; - u8 move_in_progress : 1; -#ifdef CONFIG_IRQ_REMAP - u8 remapped : 1; +struct irq_alloc_info { + enum irq_alloc_type type; + u32 flags; + const struct cpumask *mask; /* CPU mask for vector allocation */ union { - struct irq_2_iommu irq_2_iommu; - struct irq_2_irte irq_2_irte; - }; + int unused; +#ifdef CONFIG_HPET_TIMER + struct { + int hpet_id; + int hpet_index; + void *hpet_data; + }; #endif - union { -#ifdef CONFIG_X86_IO_APIC +#ifdef CONFIG_PCI_MSI struct { - struct list_head irq_2_pin; + struct pci_dev *msi_dev; + irq_hw_number_t msi_hwirq; + }; +#endif +#ifdef CONFIG_X86_IO_APIC + struct { + int ioapic_id; + int ioapic_pin; + int ioapic_node; + u32 ioapic_trigger : 1; + u32 ioapic_polarity : 1; + u32 ioapic_valid : 1; + struct IO_APIC_route_entry *ioapic_entry; + }; +#endif +#ifdef CONFIG_DMAR_TABLE + struct { + int dmar_id; + void *dmar_data; + }; +#endif +#ifdef CONFIG_HT_IRQ + struct { + int ht_pos; + int ht_idx; + struct pci_dev *ht_dev; + void *ht_update; + }; +#endif +#ifdef CONFIG_X86_UV + struct { + int uv_limit; + int uv_blade; + unsigned long uv_offset; + char *uv_name; }; #endif }; }; +struct irq_cfg { + unsigned int dest_apicid; + u8 vector; +}; + extern struct irq_cfg *irq_cfg(unsigned int irq); extern struct irq_cfg *irqd_cfg(struct irq_data *irq_data); -extern struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node); extern void lock_vector_lock(void); extern void unlock_vector_lock(void); -extern int assign_irq_vector(int, struct irq_cfg *, const struct cpumask *); -extern void clear_irq_vector(int irq, struct irq_cfg *cfg); extern void setup_vector_irq(int cpu); #ifdef CONFIG_SMP extern void send_cleanup_vector(struct irq_cfg *); @@ -150,10 +151,7 @@ static inline void send_cleanup_vector(struct irq_cfg *c) { } static inline void irq_complete_move(struct irq_cfg *c) { } #endif -extern int apic_retrigger_irq(struct irq_data *data); extern void apic_ack_edge(struct irq_data *data); -extern int apic_set_affinity(struct irq_data *data, const struct cpumask *mask, - unsigned int *dest_id); #else /* CONFIG_X86_LOCAL_APIC */ static inline void lock_vector_lock(void) {} static inline void unlock_vector_lock(void) {} @@ -163,8 +161,7 @@ static inline void unlock_vector_lock(void) {} extern atomic_t irq_err_count; extern atomic_t irq_mis_count; -/* EISA */ -extern void eisa_set_level_irq(unsigned int irq); +extern void elcr_set_level_irq(unsigned int irq); /* SMP */ extern __visible void smp_apic_timer_interrupt(struct pt_regs *); @@ -178,7 +175,6 @@ extern asmlinkage void smp_irq_move_cleanup_interrupt(void); extern __visible void smp_reschedule_interrupt(struct pt_regs *); extern __visible void smp_call_function_interrupt(struct pt_regs *); extern __visible void smp_call_function_single_interrupt(struct pt_regs *); -extern __visible void smp_invalidate_interrupt(struct pt_regs *); #endif extern char irq_entries_start[]; diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h deleted file mode 100644 index 6eb6fcb83..000000000 --- a/arch/x86/include/asm/i387.h +++ /dev/null @@ -1,108 +0,0 @@ -/* - * Copyright (C) 1994 Linus Torvalds - * - * Pentium III FXSR, SSE support - * General FPU state handling cleanups - * Gareth Hughes <gareth@valinux.com>, May 2000 - * x86-64 work by Andi Kleen 2002 - */ - -#ifndef _ASM_X86_I387_H -#define _ASM_X86_I387_H - -#ifndef __ASSEMBLY__ - -#include <linux/sched.h> -#include <linux/hardirq.h> - -struct pt_regs; -struct user_i387_struct; - -extern int init_fpu(struct task_struct *child); -extern void fpu_finit(struct fpu *fpu); -extern int dump_fpu(struct pt_regs *, struct user_i387_struct *); -extern void math_state_restore(void); - -extern bool irq_fpu_usable(void); - -/* - * Careful: __kernel_fpu_begin/end() must be called with preempt disabled - * and they don't touch the preempt state on their own. - * If you enable preemption after __kernel_fpu_begin(), preempt notifier - * should call the __kernel_fpu_end() to prevent the kernel/user FPU - * state from getting corrupted. KVM for example uses this model. - * - * All other cases use kernel_fpu_begin/end() which disable preemption - * during kernel FPU usage. - */ -extern void __kernel_fpu_begin(void); -extern void __kernel_fpu_end(void); - -static inline void kernel_fpu_begin(void) -{ - preempt_disable(); - WARN_ON_ONCE(!irq_fpu_usable()); - __kernel_fpu_begin(); -} - -static inline void kernel_fpu_end(void) -{ - __kernel_fpu_end(); - preempt_enable(); -} - -/* Must be called with preempt disabled */ -extern void kernel_fpu_disable(void); -extern void kernel_fpu_enable(void); - -/* - * Some instructions like VIA's padlock instructions generate a spurious - * DNA fault but don't modify SSE registers. And these instructions - * get used from interrupt context as well. To prevent these kernel instructions - * in interrupt context interacting wrongly with other user/kernel fpu usage, we - * should use them only in the context of irq_ts_save/restore() - */ -static inline int irq_ts_save(void) -{ - /* - * If in process context and not atomic, we can take a spurious DNA fault. - * Otherwise, doing clts() in process context requires disabling preemption - * or some heavy lifting like kernel_fpu_begin() - */ - if (!in_atomic()) - return 0; - - if (read_cr0() & X86_CR0_TS) { - clts(); - return 1; - } - - return 0; -} - -static inline void irq_ts_restore(int TS_state) -{ - if (TS_state) - stts(); -} - -/* - * The question "does this thread have fpu access?" - * is slightly racy, since preemption could come in - * and revoke it immediately after the test. - * - * However, even in that very unlikely scenario, - * we can just assume we have FPU access - typically - * to save the FP state - we'll just take a #NM - * fault and get the FPU access back. - */ -static inline int user_has_fpu(void) -{ - return current->thread.fpu.has_fpu; -} - -extern void unlazy_fpu(struct task_struct *tsk); - -#endif /* __ASSEMBLY__ */ - -#endif /* _ASM_X86_I387_H */ diff --git a/arch/x86/include/asm/intel_pmc_ipc.h b/arch/x86/include/asm/intel_pmc_ipc.h new file mode 100644 index 000000000..cd0310e18 --- /dev/null +++ b/arch/x86/include/asm/intel_pmc_ipc.h @@ -0,0 +1,55 @@ +#ifndef _ASM_X86_INTEL_PMC_IPC_H_ +#define _ASM_X86_INTEL_PMC_IPC_H_ + +/* Commands */ +#define PMC_IPC_PMIC_ACCESS 0xFF +#define PMC_IPC_PMIC_ACCESS_READ 0x0 +#define PMC_IPC_PMIC_ACCESS_WRITE 0x1 +#define PMC_IPC_USB_PWR_CTRL 0xF0 +#define PMC_IPC_PMIC_BLACKLIST_SEL 0xEF +#define PMC_IPC_PHY_CONFIG 0xEE +#define PMC_IPC_NORTHPEAK_CTRL 0xED +#define PMC_IPC_PM_DEBUG 0xEC +#define PMC_IPC_PMC_TELEMTRY 0xEB +#define PMC_IPC_PMC_FW_MSG_CTRL 0xEA + +/* IPC return code */ +#define IPC_ERR_NONE 0 +#define IPC_ERR_CMD_NOT_SUPPORTED 1 +#define IPC_ERR_CMD_NOT_SERVICED 2 +#define IPC_ERR_UNABLE_TO_SERVICE 3 +#define IPC_ERR_CMD_INVALID 4 +#define IPC_ERR_CMD_FAILED 5 +#define IPC_ERR_EMSECURITY 6 +#define IPC_ERR_UNSIGNEDKERNEL 7 + +#if IS_ENABLED(CONFIG_INTEL_PMC_IPC) + +int intel_pmc_ipc_simple_command(int cmd, int sub); +int intel_pmc_ipc_raw_cmd(u32 cmd, u32 sub, u8 *in, u32 inlen, + u32 *out, u32 outlen, u32 dptr, u32 sptr); +int intel_pmc_ipc_command(u32 cmd, u32 sub, u8 *in, u32 inlen, + u32 *out, u32 outlen); + +#else + +static inline int intel_pmc_ipc_simple_command(int cmd, int sub) +{ + return -EINVAL; +} + +static inline int intel_pmc_ipc_raw_cmd(u32 cmd, u32 sub, u8 *in, u32 inlen, + u32 *out, u32 outlen, u32 dptr, u32 sptr) +{ + return -EINVAL; +} + +static inline int intel_pmc_ipc_command(u32 cmd, u32 sub, u8 *in, u32 inlen, + u32 *out, u32 outlen) +{ + return -EINVAL; +} + +#endif /*CONFIG_INTEL_PMC_IPC*/ + +#endif diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 34a5b9370..cc9c61bc1 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -35,11 +35,13 @@ */ #define ARCH_HAS_IOREMAP_WC +#define ARCH_HAS_IOREMAP_WT #include <linux/string.h> #include <linux/compiler.h> #include <asm/page.h> #include <asm/early_ioremap.h> +#include <asm/pgtable_types.h> #define build_mmio_read(name, size, type, reg, barrier) \ static inline type name(const volatile void __iomem *addr) \ @@ -177,6 +179,7 @@ static inline unsigned int isa_virt_to_bus(volatile void *address) * look at pci_iomap(). */ extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size); +extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size); extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size); extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, unsigned long prot_val); @@ -197,8 +200,6 @@ extern void set_iounmap_nonlazy(void); #include <asm-generic/iomap.h> -#include <linux/vmalloc.h> - /* * Convert a virtual cached pointer to an uncached pointer */ @@ -247,6 +248,12 @@ static inline void flush_write_buffers(void) #endif } +static inline void __pmem *arch_memremap_pmem(resource_size_t offset, + unsigned long size) +{ + return (void __force __pmem *) ioremap_cache(offset, size); +} + #endif /* __KERNEL__ */ extern void native_io_delay(void); @@ -320,6 +327,7 @@ extern void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr); extern int ioremap_change_attr(unsigned long vaddr, unsigned long size, enum page_cache_mode pcm); extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size); +extern void __iomem *ioremap_wt(resource_size_t offset, unsigned long size); extern bool is_early_ioremap_ptep(pte_t *ptep); @@ -338,6 +346,9 @@ extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1, #define IO_SPACE_LIMIT 0xffff #ifdef CONFIG_MTRR +extern int __must_check arch_phys_wc_index(int handle); +#define arch_phys_wc_index arch_phys_wc_index + extern int __must_check arch_phys_wc_add(unsigned long base, unsigned long size); extern void arch_phys_wc_del(int handle); diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 2f91685fe..6cbf2cfb3 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -95,9 +95,22 @@ struct IR_IO_APIC_route_entry { index : 15; } __attribute__ ((packed)); -#define IOAPIC_AUTO -1 -#define IOAPIC_EDGE 0 -#define IOAPIC_LEVEL 1 +struct irq_alloc_info; +struct ioapic_domain_cfg; + +#define IOAPIC_AUTO -1 +#define IOAPIC_EDGE 0 +#define IOAPIC_LEVEL 1 + +#define IOAPIC_MASKED 1 +#define IOAPIC_UNMASKED 0 + +#define IOAPIC_POL_HIGH 0 +#define IOAPIC_POL_LOW 1 + +#define IOAPIC_DEST_MODE_PHYSICAL 0 +#define IOAPIC_DEST_MODE_LOGICAL 1 + #define IOAPIC_MAP_ALLOC 0x1 #define IOAPIC_MAP_CHECK 0x2 @@ -110,9 +123,6 @@ extern int nr_ioapics; extern int mpc_ioapic_id(int ioapic); extern unsigned int mpc_ioapic_addr(int ioapic); -extern struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic); - -#define MP_MAX_IOAPIC_PIN 127 /* # of MP IRQ source entries */ extern int mp_irq_entries; @@ -120,9 +130,6 @@ extern int mp_irq_entries; /* MP IRQ source entries */ extern struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES]; -/* Older SiS APIC requires we rewrite the index register */ -extern int sis_apic_bug; - /* 1 if "noapic" boot option passed */ extern int skip_ioapic_setup; @@ -132,6 +139,8 @@ extern int noioapicquirk; /* -1 if "noapic" boot option passed */ extern int noioapicreroute; +extern u32 gsi_top; + extern unsigned long io_apic_irqs; #define IO_APIC_IRQ(x) (((x) >= NR_IRQS_LEGACY) || ((1 << (x)) & io_apic_irqs)) @@ -147,13 +156,6 @@ struct irq_cfg; extern void ioapic_insert_resources(void); extern int arch_early_ioapic_init(void); -extern int native_setup_ioapic_entry(int, struct IO_APIC_route_entry *, - unsigned int, int, - struct io_apic_irq_attr *); -extern void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg); - -extern void native_eoi_ioapic_pin(int apic, int pin, int vector); - extern int save_ioapic_entries(void); extern void mask_ioapic_entries(void); extern int restore_ioapic_entries(void); @@ -161,82 +163,32 @@ extern int restore_ioapic_entries(void); extern void setup_ioapic_ids_from_mpc(void); extern void setup_ioapic_ids_from_mpc_nocheck(void); -struct io_apic_irq_attr { - int ioapic; - int ioapic_pin; - int trigger; - int polarity; -}; - -enum ioapic_domain_type { - IOAPIC_DOMAIN_INVALID, - IOAPIC_DOMAIN_LEGACY, - IOAPIC_DOMAIN_STRICT, - IOAPIC_DOMAIN_DYNAMIC, -}; - -struct device_node; -struct irq_domain; -struct irq_domain_ops; - -struct ioapic_domain_cfg { - enum ioapic_domain_type type; - const struct irq_domain_ops *ops; - struct device_node *dev; -}; - -struct mp_ioapic_gsi{ - u32 gsi_base; - u32 gsi_end; -}; -extern u32 gsi_top; - extern int mp_find_ioapic(u32 gsi); extern int mp_find_ioapic_pin(int ioapic, u32 gsi); -extern u32 mp_pin_to_gsi(int ioapic, int pin); -extern int mp_map_gsi_to_irq(u32 gsi, unsigned int flags); +extern int mp_map_gsi_to_irq(u32 gsi, unsigned int flags, + struct irq_alloc_info *info); extern void mp_unmap_irq(int irq); extern int mp_register_ioapic(int id, u32 address, u32 gsi_base, struct ioapic_domain_cfg *cfg); extern int mp_unregister_ioapic(u32 gsi_base); extern int mp_ioapic_registered(u32 gsi_base); -extern int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq); -extern void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq); -extern int mp_set_gsi_attr(u32 gsi, int trigger, int polarity, int node); -extern void __init pre_init_apic_IRQ0(void); + +extern void ioapic_set_alloc_attr(struct irq_alloc_info *info, + int node, int trigger, int polarity); extern void mp_save_irq(struct mpc_intsrc *m); extern void disable_ioapic_support(void); -extern void __init native_io_apic_init_mappings(void); +extern void __init io_apic_init_mappings(void); extern unsigned int native_io_apic_read(unsigned int apic, unsigned int reg); -extern void native_io_apic_write(unsigned int apic, unsigned int reg, unsigned int val); -extern void native_io_apic_modify(unsigned int apic, unsigned int reg, unsigned int val); extern void native_disable_io_apic(void); -extern void native_io_apic_print_entries(unsigned int apic, unsigned int nr_entries); -extern void intel_ir_io_apic_print_entries(unsigned int apic, unsigned int nr_entries); -extern int native_ioapic_set_affinity(struct irq_data *, - const struct cpumask *, - bool); static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg) { return x86_io_apic_ops.read(apic, reg); } -static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value) -{ - x86_io_apic_ops.write(apic, reg, value); -} -static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value) -{ - x86_io_apic_ops.modify(apic, reg, value); -} - -extern void io_apic_eoi(unsigned int apic, unsigned int vector); - extern void setup_IO_APIC(void); extern void enable_IO_APIC(void); extern void disable_IO_APIC(void); @@ -253,8 +205,12 @@ static inline int arch_early_ioapic_init(void) { return 0; } static inline void print_IO_APICs(void) {} #define gsi_top (NR_IRQS_LEGACY) static inline int mp_find_ioapic(u32 gsi) { return 0; } -static inline u32 mp_pin_to_gsi(int ioapic, int pin) { return UINT_MAX; } -static inline int mp_map_gsi_to_irq(u32 gsi, unsigned int flags) { return gsi; } +static inline int mp_map_gsi_to_irq(u32 gsi, unsigned int flags, + struct irq_alloc_info *info) +{ + return gsi; +} + static inline void mp_unmap_irq(int irq) { } static inline int save_ioapic_entries(void) @@ -268,17 +224,11 @@ static inline int restore_ioapic_entries(void) return -ENOMEM; } -static inline void mp_save_irq(struct mpc_intsrc *m) { }; +static inline void mp_save_irq(struct mpc_intsrc *m) { } static inline void disable_ioapic_support(void) { } -#define native_io_apic_init_mappings NULL +static inline void io_apic_init_mappings(void) { } #define native_io_apic_read NULL -#define native_io_apic_write NULL -#define native_io_apic_modify NULL #define native_disable_io_apic NULL -#define native_io_apic_print_entries NULL -#define native_ioapic_set_affinity NULL -#define native_setup_ioapic_entry NULL -#define native_eoi_ioapic_pin NULL static inline void setup_IO_APIC(void) { } static inline void enable_IO_APIC(void) { } diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index a80cbb88e..8008d0658 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -30,6 +30,10 @@ extern void fixup_irqs(void); extern void irq_force_complete_move(int); #endif +#ifdef CONFIG_HAVE_KVM +extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void)); +#endif + extern void (*x86_platform_ipi_callback)(void); extern void native_init_IRQ(void); extern bool handle_irq(unsigned irq, struct pt_regs *regs); diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h index 6224d316c..046c7fb1c 100644 --- a/arch/x86/include/asm/irq_remapping.h +++ b/arch/x86/include/asm/irq_remapping.h @@ -22,84 +22,72 @@ #ifndef __X86_IRQ_REMAPPING_H #define __X86_IRQ_REMAPPING_H +#include <asm/irqdomain.h> +#include <asm/hw_irq.h> #include <asm/io_apic.h> -struct IO_APIC_route_entry; -struct io_apic_irq_attr; -struct irq_chip; struct msi_msg; -struct pci_dev; -struct irq_cfg; +struct irq_alloc_info; + +enum irq_remap_cap { + IRQ_POSTING_CAP = 0, +}; #ifdef CONFIG_IRQ_REMAP +extern bool irq_remapping_cap(enum irq_remap_cap cap); extern void set_irq_remapping_broken(void); extern int irq_remapping_prepare(void); extern int irq_remapping_enable(void); extern void irq_remapping_disable(void); extern int irq_remapping_reenable(int); extern int irq_remap_enable_fault_handling(void); -extern int setup_ioapic_remapped_entry(int irq, - struct IO_APIC_route_entry *entry, - unsigned int destination, - int vector, - struct io_apic_irq_attr *attr); -extern void free_remapped_irq(int irq); -extern void compose_remapped_msi_msg(struct pci_dev *pdev, - unsigned int irq, unsigned int dest, - struct msi_msg *msg, u8 hpet_id); -extern int setup_hpet_msi_remapped(unsigned int irq, unsigned int id); extern void panic_if_irq_remap(const char *msg); -extern bool setup_remapped_irq(int irq, - struct irq_cfg *cfg, - struct irq_chip *chip); -void irq_remap_modify_chip_defaults(struct irq_chip *chip); +extern struct irq_domain * +irq_remapping_get_ir_irq_domain(struct irq_alloc_info *info); +extern struct irq_domain * +irq_remapping_get_irq_domain(struct irq_alloc_info *info); + +/* Create PCI MSI/MSIx irqdomain, use @parent as the parent irqdomain. */ +extern struct irq_domain *arch_create_msi_irq_domain(struct irq_domain *parent); + +/* Get parent irqdomain for interrupt remapping irqdomain */ +static inline struct irq_domain *arch_get_ir_parent_domain(void) +{ + return x86_vector_domain; +} + +struct vcpu_data { + u64 pi_desc_addr; /* Physical address of PI Descriptor */ + u32 vector; /* Guest vector of the interrupt */ +}; #else /* CONFIG_IRQ_REMAP */ +static inline bool irq_remapping_cap(enum irq_remap_cap cap) { return 0; } static inline void set_irq_remapping_broken(void) { } static inline int irq_remapping_prepare(void) { return -ENODEV; } static inline int irq_remapping_enable(void) { return -ENODEV; } static inline void irq_remapping_disable(void) { } static inline int irq_remapping_reenable(int eim) { return -ENODEV; } static inline int irq_remap_enable_fault_handling(void) { return -ENODEV; } -static inline int setup_ioapic_remapped_entry(int irq, - struct IO_APIC_route_entry *entry, - unsigned int destination, - int vector, - struct io_apic_irq_attr *attr) -{ - return -ENODEV; -} -static inline void free_remapped_irq(int irq) { } -static inline void compose_remapped_msi_msg(struct pci_dev *pdev, - unsigned int irq, unsigned int dest, - struct msi_msg *msg, u8 hpet_id) -{ -} -static inline int setup_hpet_msi_remapped(unsigned int irq, unsigned int id) -{ - return -ENODEV; -} static inline void panic_if_irq_remap(const char *msg) { } -static inline void irq_remap_modify_chip_defaults(struct irq_chip *chip) +static inline struct irq_domain * +irq_remapping_get_ir_irq_domain(struct irq_alloc_info *info) { + return NULL; } -static inline bool setup_remapped_irq(int irq, - struct irq_cfg *cfg, - struct irq_chip *chip) +static inline struct irq_domain * +irq_remapping_get_irq_domain(struct irq_alloc_info *info) { - return false; + return NULL; } -#endif /* CONFIG_IRQ_REMAP */ - -#define dmar_alloc_hwirq() irq_alloc_hwirq(-1) -#define dmar_free_hwirq irq_free_hwirq +#endif /* CONFIG_IRQ_REMAP */ #endif /* __X86_IRQ_REMAPPING_H */ diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 666c89ec4..4c2d2eb20 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -47,31 +47,12 @@ #define IRQ_MOVE_CLEANUP_VECTOR FIRST_EXTERNAL_VECTOR #define IA32_SYSCALL_VECTOR 0x80 -#ifdef CONFIG_X86_32 -# define SYSCALL_VECTOR 0x80 -#endif /* * Vectors 0x30-0x3f are used for ISA interrupts. * round up to the next 16-vector boundary */ -#define IRQ0_VECTOR ((FIRST_EXTERNAL_VECTOR + 16) & ~15) - -#define IRQ1_VECTOR (IRQ0_VECTOR + 1) -#define IRQ2_VECTOR (IRQ0_VECTOR + 2) -#define IRQ3_VECTOR (IRQ0_VECTOR + 3) -#define IRQ4_VECTOR (IRQ0_VECTOR + 4) -#define IRQ5_VECTOR (IRQ0_VECTOR + 5) -#define IRQ6_VECTOR (IRQ0_VECTOR + 6) -#define IRQ7_VECTOR (IRQ0_VECTOR + 7) -#define IRQ8_VECTOR (IRQ0_VECTOR + 8) -#define IRQ9_VECTOR (IRQ0_VECTOR + 9) -#define IRQ10_VECTOR (IRQ0_VECTOR + 10) -#define IRQ11_VECTOR (IRQ0_VECTOR + 11) -#define IRQ12_VECTOR (IRQ0_VECTOR + 12) -#define IRQ13_VECTOR (IRQ0_VECTOR + 13) -#define IRQ14_VECTOR (IRQ0_VECTOR + 14) -#define IRQ15_VECTOR (IRQ0_VECTOR + 15) +#define ISA_IRQ_VECTOR(irq) (((FIRST_EXTERNAL_VECTOR + 16) & ~15) + irq) /* * Special IRQ vectors used by the SMP architecture, 0xf0-0xff @@ -102,21 +83,23 @@ */ #define X86_PLATFORM_IPI_VECTOR 0xf7 -/* Vector for KVM to deliver posted interrupt IPI */ -#ifdef CONFIG_HAVE_KVM -#define POSTED_INTR_VECTOR 0xf2 -#endif - +#define POSTED_INTR_WAKEUP_VECTOR 0xf1 /* * IRQ work vector: */ #define IRQ_WORK_VECTOR 0xf6 #define UV_BAU_MESSAGE 0xf5 +#define DEFERRED_ERROR_VECTOR 0xf4 /* Vector on which hypervisor callbacks will be delivered */ #define HYPERVISOR_CALLBACK_VECTOR 0xf3 +/* Vector for KVM to deliver posted interrupt IPI */ +#ifdef CONFIG_HAVE_KVM +#define POSTED_INTR_VECTOR 0xf2 +#endif + /* * Local APIC timer IRQ vector is on a different priority level, * to work around the 'lost local interrupt if more than 2 IRQ @@ -155,18 +138,22 @@ static inline int invalid_vm86_irq(int irq) * static arrays. */ -#define NR_IRQS_LEGACY 16 +#define NR_IRQS_LEGACY 16 -#define IO_APIC_VECTOR_LIMIT ( 32 * MAX_IO_APICS ) +#define CPU_VECTOR_LIMIT (64 * NR_CPUS) +#define IO_APIC_VECTOR_LIMIT (32 * MAX_IO_APICS) -#ifdef CONFIG_X86_IO_APIC -# define CPU_VECTOR_LIMIT (64 * NR_CPUS) -# define NR_IRQS \ +#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_PCI_MSI) +#define NR_IRQS \ (CPU_VECTOR_LIMIT > IO_APIC_VECTOR_LIMIT ? \ (NR_VECTORS + CPU_VECTOR_LIMIT) : \ (NR_VECTORS + IO_APIC_VECTOR_LIMIT)) -#else /* !CONFIG_X86_IO_APIC: */ -# define NR_IRQS NR_IRQS_LEGACY +#elif defined(CONFIG_X86_IO_APIC) +#define NR_IRQS (NR_VECTORS + IO_APIC_VECTOR_LIMIT) +#elif defined(CONFIG_PCI_MSI) +#define NR_IRQS (NR_VECTORS + CPU_VECTOR_LIMIT) +#else +#define NR_IRQS NR_IRQS_LEGACY #endif #endif /* _ASM_X86_IRQ_VECTORS_H */ diff --git a/arch/x86/include/asm/irqdomain.h b/arch/x86/include/asm/irqdomain.h new file mode 100644 index 000000000..d26075b52 --- /dev/null +++ b/arch/x86/include/asm/irqdomain.h @@ -0,0 +1,63 @@ +#ifndef _ASM_IRQDOMAIN_H +#define _ASM_IRQDOMAIN_H + +#include <linux/irqdomain.h> +#include <asm/hw_irq.h> + +#ifdef CONFIG_X86_LOCAL_APIC +enum { + /* Allocate contiguous CPU vectors */ + X86_IRQ_ALLOC_CONTIGUOUS_VECTORS = 0x1, +}; + +extern struct irq_domain *x86_vector_domain; + +extern void init_irq_alloc_info(struct irq_alloc_info *info, + const struct cpumask *mask); +extern void copy_irq_alloc_info(struct irq_alloc_info *dst, + struct irq_alloc_info *src); +#endif /* CONFIG_X86_LOCAL_APIC */ + +#ifdef CONFIG_X86_IO_APIC +struct device_node; +struct irq_data; + +enum ioapic_domain_type { + IOAPIC_DOMAIN_INVALID, + IOAPIC_DOMAIN_LEGACY, + IOAPIC_DOMAIN_STRICT, + IOAPIC_DOMAIN_DYNAMIC, +}; + +struct ioapic_domain_cfg { + enum ioapic_domain_type type; + const struct irq_domain_ops *ops; + struct device_node *dev; +}; + +extern const struct irq_domain_ops mp_ioapic_irqdomain_ops; + +extern int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg); +extern void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs); +extern void mp_irqdomain_activate(struct irq_domain *domain, + struct irq_data *irq_data); +extern void mp_irqdomain_deactivate(struct irq_domain *domain, + struct irq_data *irq_data); +extern int mp_irqdomain_ioapic_idx(struct irq_domain *domain); +#endif /* CONFIG_X86_IO_APIC */ + +#ifdef CONFIG_PCI_MSI +extern void arch_init_msi_domain(struct irq_domain *domain); +#else +static inline void arch_init_msi_domain(struct irq_domain *domain) { } +#endif + +#ifdef CONFIG_HT_IRQ +extern void arch_init_htirq_domain(struct irq_domain *domain); +#else +static inline void arch_init_htirq_domain(struct irq_domain *domain) { } +#endif + +#endif diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 57a9d94fe..e16466ec4 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -193,6 +193,8 @@ struct x86_emulate_ops { int (*cpl)(struct x86_emulate_ctxt *ctxt); int (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest); int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value); + u64 (*get_smbase)(struct x86_emulate_ctxt *ctxt); + void (*set_smbase)(struct x86_emulate_ctxt *ctxt, u64 smbase); int (*set_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data); int (*get_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata); int (*check_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc); @@ -262,6 +264,11 @@ enum x86emul_mode { X86EMUL_MODE_PROT64, /* 64-bit (long) mode. */ }; +/* These match some of the HF_* flags defined in kvm_host.h */ +#define X86EMUL_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */ +#define X86EMUL_SMM_MASK (1 << 6) +#define X86EMUL_SMM_INSIDE_NMI_MASK (1 << 7) + struct x86_emulate_ctxt { const struct x86_emulate_ops *ops; @@ -273,8 +280,8 @@ struct x86_emulate_ctxt { /* interruptibility state, as a result of execution of STI or MOV SS */ int interruptibility; + int emul_flags; - bool guest_mode; /* guest running a nested guest */ bool perm_ok; /* do not check permissions if true */ bool ud; /* inject an #UD if host doesn't support insn */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 41b06fca3..49ec9038e 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -184,23 +184,12 @@ struct kvm_mmu_memory_cache { void *objects[KVM_NR_MEM_OBJS]; }; -/* - * kvm_mmu_page_role, below, is defined as: - * - * bits 0:3 - total guest paging levels (2-4, or zero for real mode) - * bits 4:7 - page table level for this shadow (1-4) - * bits 8:9 - page table quadrant for 2-level guests - * bit 16 - direct mapping of virtual to physical mapping at gfn - * used for real mode and two-dimensional paging - * bits 17:19 - common access permissions for all ptes in this shadow page - */ union kvm_mmu_page_role { unsigned word; struct { unsigned level:4; unsigned cr4_pae:1; unsigned quadrant:2; - unsigned pad_for_nice_hex_output:6; unsigned direct:1; unsigned access:3; unsigned invalid:1; @@ -208,6 +197,15 @@ union kvm_mmu_page_role { unsigned cr0_wp:1; unsigned smep_andnot_wp:1; unsigned smap_andnot_wp:1; + unsigned :8; + + /* + * This is left at the top of the word so that + * kvm_memslots_for_spte_role can extract it with a + * simple shift. While there is room, give it a whole + * byte so it is also faster to load it from memory. + */ + unsigned smm:8; }; }; @@ -338,12 +336,28 @@ struct kvm_pmu { u64 reprogram_pmi; }; +struct kvm_pmu_ops; + enum { KVM_DEBUGREG_BP_ENABLED = 1, KVM_DEBUGREG_WONT_EXIT = 2, KVM_DEBUGREG_RELOAD = 4, }; +struct kvm_mtrr_range { + u64 base; + u64 mask; + struct list_head node; +}; + +struct kvm_mtrr { + struct kvm_mtrr_range var_ranges[KVM_NR_VAR_MTRR]; + mtrr_type fixed_ranges[KVM_NR_FIXED_MTRR_REGION]; + u64 deftype; + + struct list_head head; +}; + struct kvm_vcpu_arch { /* * rip and regs accesses must go through @@ -368,6 +382,7 @@ struct kvm_vcpu_arch { int32_t apic_arb_prio; int mp_state; u64 ia32_misc_enable_msr; + u64 smbase; bool tpr_access_reporting; u64 ia32_xss; @@ -471,8 +486,9 @@ struct kvm_vcpu_arch { atomic_t nmi_queued; /* unprocessed asynchronous NMIs */ unsigned nmi_pending; /* NMI queued after currently running handler */ bool nmi_injected; /* Trying to inject an NMI this entry */ + bool smi_pending; /* SMI queued after currently running handler */ - struct mtrr_state_type mtrr_state; + struct kvm_mtrr mtrr_state; u64 pat; unsigned switch_db_regs; @@ -588,6 +604,8 @@ struct kvm_arch { bool iommu_noncoherent; #define __KVM_HAVE_ARCH_NONCOHERENT_DMA atomic_t noncoherent_dma_count; +#define __KVM_HAVE_ARCH_ASSIGNED_DEVICE + atomic_t assigned_device_count; struct kvm_pic *vpic; struct kvm_ioapic *vioapic; struct kvm_pit *vpit; @@ -637,6 +655,8 @@ struct kvm_arch { #endif bool boot_vcpu_runs_old_kvmclock; + + u64 disabled_quirks; }; struct kvm_vm_stat { @@ -689,12 +709,13 @@ struct msr_data { struct kvm_lapic_irq { u32 vector; - u32 delivery_mode; - u32 dest_mode; - u32 level; - u32 trig_mode; + u16 delivery_mode; + u16 dest_mode; + bool level; + u16 trig_mode; u32 shorthand; u32 dest_id; + bool msi_redir_hint; }; struct kvm_x86_ops { @@ -706,19 +727,20 @@ struct kvm_x86_ops { int (*hardware_setup)(void); /* __init */ void (*hardware_unsetup)(void); /* __exit */ bool (*cpu_has_accelerated_tpr)(void); + bool (*cpu_has_high_real_mode_segbase)(void); void (*cpuid_update)(struct kvm_vcpu *vcpu); /* Create, but do not attach this VCPU */ struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id); void (*vcpu_free)(struct kvm_vcpu *vcpu); - void (*vcpu_reset)(struct kvm_vcpu *vcpu); + void (*vcpu_reset)(struct kvm_vcpu *vcpu, bool init_event); void (*prepare_guest_switch)(struct kvm_vcpu *vcpu); void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu); void (*vcpu_put)(struct kvm_vcpu *vcpu); void (*update_db_bp_intercept)(struct kvm_vcpu *vcpu); - int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); + int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr); int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr); u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg); void (*get_segment)(struct kvm_vcpu *vcpu, @@ -836,6 +858,8 @@ struct kvm_x86_ops { void (*enable_log_dirty_pt_masked)(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t offset, unsigned long mask); + /* pmu operations of sub-arch */ + const struct kvm_pmu_ops *pmu_ops; }; struct kvm_arch_async_pf { @@ -871,7 +895,7 @@ void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, struct kvm_memory_slot *memslot); void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, - struct kvm_memory_slot *memslot); + const struct kvm_memory_slot *memslot); void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot); void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm, @@ -882,7 +906,7 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask); void kvm_mmu_zap_all(struct kvm *kvm); -void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm); +void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, struct kvm_memslots *slots); unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm); void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages); @@ -890,7 +914,6 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3); int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, const void *val, int bytes); -u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn); struct kvm_irq_mask_notifier { void (*func)(struct kvm_irq_mask_notifier *kimn, bool masked); @@ -938,7 +961,7 @@ static inline int emulate_instruction(struct kvm_vcpu *vcpu, void kvm_enable_efer_bits(u64); bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer); -int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data); +int kvm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr); int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr); struct x86_emulate_ctxt; @@ -967,7 +990,7 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw); void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l); int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr); -int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); +int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr); int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr); unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu); @@ -1002,8 +1025,6 @@ void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id); void kvm_inject_nmi(struct kvm_vcpu *vcpu); -int fx_init(struct kvm_vcpu *vcpu); - void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, int bytes); int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn); @@ -1112,6 +1133,14 @@ enum { #define HF_NMI_MASK (1 << 3) #define HF_IRET_MASK (1 << 4) #define HF_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */ +#define HF_SMM_MASK (1 << 6) +#define HF_SMM_INSIDE_NMI_MASK (1 << 7) + +#define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE +#define KVM_ADDRESS_SPACE_NUM 2 + +#define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0) +#define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm) /* * Hardware virtualization extension instructions may fault if a @@ -1146,7 +1175,7 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); -void kvm_vcpu_reset(struct kvm_vcpu *vcpu); +void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu); void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, unsigned long address); @@ -1170,16 +1199,9 @@ void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err); int kvm_is_in_guest(void); -void kvm_pmu_init(struct kvm_vcpu *vcpu); -void kvm_pmu_destroy(struct kvm_vcpu *vcpu); -void kvm_pmu_reset(struct kvm_vcpu *vcpu); -void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu); -bool kvm_pmu_msr(struct kvm_vcpu *vcpu, u32 msr); -int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data); -int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); -int kvm_pmu_check_pmc(struct kvm_vcpu *vcpu, unsigned pmc); -int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data); -void kvm_handle_pmu_event(struct kvm_vcpu *vcpu); -void kvm_deliver_pmi(struct kvm_vcpu *vcpu); +int __x86_set_memory_region(struct kvm *kvm, + const struct kvm_userspace_memory_region *mem); +int x86_set_memory_region(struct kvm *kvm, + const struct kvm_userspace_memory_region *mem); #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/livepatch.h b/arch/x86/include/asm/livepatch.h index 2d29197bd..19c099afa 100644 --- a/arch/x86/include/asm/livepatch.h +++ b/arch/x86/include/asm/livepatch.h @@ -21,6 +21,7 @@ #ifndef _ASM_X86_LIVEPATCH_H #define _ASM_X86_LIVEPATCH_H +#include <asm/setup.h> #include <linux/module.h> #include <linux/ftrace.h> diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 1f5a86d51..982dfc367 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -17,11 +17,16 @@ #define MCG_EXT_CNT(c) (((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT) #define MCG_SER_P (1ULL<<24) /* MCA recovery/new status bits */ #define MCG_ELOG_P (1ULL<<26) /* Extended error log supported */ +#define MCG_LMCE_P (1ULL<<27) /* Local machine check supported */ /* MCG_STATUS register defines */ #define MCG_STATUS_RIPV (1ULL<<0) /* restart ip valid */ #define MCG_STATUS_EIPV (1ULL<<1) /* ip points to correct instruction */ #define MCG_STATUS_MCIP (1ULL<<2) /* machine check in progress */ +#define MCG_STATUS_LMCES (1ULL<<3) /* LMCE signaled */ + +/* MCG_EXT_CTL register defines */ +#define MCG_EXT_CTL_LMCE_EN (1ULL<<0) /* Enable LMCE */ /* MCi_STATUS register defines */ #define MCI_STATUS_VAL (1ULL<<63) /* valid error */ @@ -104,6 +109,7 @@ struct mce_log { struct mca_config { bool dont_log_ce; bool cmci_disabled; + bool lmce_disabled; bool ignore_ce; bool disabled; bool ser; @@ -117,8 +123,19 @@ struct mca_config { }; struct mce_vendor_flags { - __u64 overflow_recov : 1, /* cpuid_ebx(80000007) */ - __reserved_0 : 63; + /* + * overflow recovery cpuid bit indicates that overflow + * conditions are not fatal + */ + __u64 overflow_recov : 1, + + /* + * SUCCOR stands for S/W UnCorrectable error COntainment + * and Recovery. It indicates support for data poisoning + * in HW and deferred error interrupts. + */ + succor : 1, + __reserved_0 : 62; }; extern struct mce_vendor_flags mce_flags; @@ -168,12 +185,16 @@ void cmci_clear(void); void cmci_reenable(void); void cmci_rediscover(void); void cmci_recheck(void); +void lmce_clear(void); +void lmce_enable(void); #else static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { } static inline void cmci_clear(void) {} static inline void cmci_reenable(void) {} static inline void cmci_rediscover(void) {} static inline void cmci_recheck(void) {} +static inline void lmce_clear(void) {} +static inline void lmce_enable(void) {} #endif #ifdef CONFIG_X86_MCE_AMD @@ -223,6 +244,9 @@ void do_machine_check(struct pt_regs *, long); extern void (*mce_threshold_vector)(void); extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu); +/* Deferred error interrupt handler */ +extern void (*deferred_error_int_vector)(void); + /* * Thermal handler */ diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 2fb20d6f7..9e6278c71 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -1,6 +1,8 @@ #ifndef _ASM_X86_MICROCODE_H #define _ASM_X86_MICROCODE_H +#include <linux/earlycpio.h> + #define native_rdmsr(msr, val1, val2) \ do { \ u64 __val = native_read_msr((msr)); \ @@ -152,6 +154,7 @@ extern void __init load_ucode_bsp(void); extern void load_ucode_ap(void); extern int __init save_microcode_in_initrd(void); void reload_early_microcode(void); +extern bool get_builtin_firmware(struct cpio_data *cd, const char *name); #else static inline void __init load_ucode_bsp(void) {} static inline void load_ucode_ap(void) {} @@ -160,6 +163,9 @@ static inline int __init save_microcode_in_initrd(void) return 0; } static inline void reload_early_microcode(void) {} +static inline bool get_builtin_firmware(struct cpio_data *cd, const char *name) +{ + return false; +} #endif - #endif /* _ASM_X86_MICROCODE_H */ diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h index af935397e..ac6d32897 100644 --- a/arch/x86/include/asm/microcode_amd.h +++ b/arch/x86/include/asm/microcode_amd.h @@ -65,12 +65,12 @@ extern enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, s extern u8 amd_ucode_patch[PATCH_MAX_SIZE]; #ifdef CONFIG_MICROCODE_AMD_EARLY -extern void __init load_ucode_amd_bsp(void); +extern void __init load_ucode_amd_bsp(unsigned int family); extern void load_ucode_amd_ap(void); extern int __init save_microcode_in_initrd_amd(void); void reload_ucode_amd(void); #else -static inline void __init load_ucode_amd_bsp(void) {} +static inline void __init load_ucode_amd_bsp(unsigned int family) {} static inline void load_ucode_amd_ap(void) {} static inline int __init save_microcode_in_initrd_amd(void) { return -EINVAL; } void reload_ucode_amd(void) {} diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h index 2b9209c46..7991c6061 100644 --- a/arch/x86/include/asm/microcode_intel.h +++ b/arch/x86/include/asm/microcode_intel.h @@ -51,20 +51,11 @@ struct extended_sigtable { (((struct microcode_intel *)mc)->hdr.datasize ? \ ((struct microcode_intel *)mc)->hdr.datasize : DEFAULT_UCODE_DATASIZE) -#define sigmatch(s1, s2, p1, p2) \ - (((s1) == (s2)) && (((p1) & (p2)) || (((p1) == 0) && ((p2) == 0)))) - #define exttable_size(et) ((et)->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE) -extern int get_matching_microcode(unsigned int csig, int cpf, int rev, void *mc); +extern int has_newer_microcode(void *mc, unsigned int csig, int cpf, int rev); extern int microcode_sanity_check(void *mc, int print_err); -extern int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc); - -static inline int -revision_is_newer(struct microcode_header_intel *mc_header, int rev) -{ - return (mc_header->rev <= rev) ? 0 : 1; -} +extern int find_matching_signature(void *mc, unsigned int csig, int cpf); #ifdef CONFIG_MICROCODE_INTEL_EARLY extern void __init load_ucode_intel_bsp(void); diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 09b9620a7..364d27481 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -9,8 +9,7 @@ * we put the segment information here. */ typedef struct { - void *ldt; - int size; + struct ldt_struct *ldt; #ifdef CONFIG_X86_64 /* True if mm supports a task running in 32 bit compatibility mode. */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index e997f70f8..984abfe47 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -34,6 +34,50 @@ static inline void load_mm_cr4(struct mm_struct *mm) {} #endif /* + * ldt_structs can be allocated, used, and freed, but they are never + * modified while live. + */ +struct ldt_struct { + /* + * Xen requires page-aligned LDTs with special permissions. This is + * needed to prevent us from installing evil descriptors such as + * call gates. On native, we could merge the ldt_struct and LDT + * allocations, but it's not worth trying to optimize. + */ + struct desc_struct *entries; + int size; +}; + +static inline void load_mm_ldt(struct mm_struct *mm) +{ + struct ldt_struct *ldt; + + /* lockless_dereference synchronizes with smp_store_release */ + ldt = lockless_dereference(mm->context.ldt); + + /* + * Any change to mm->context.ldt is followed by an IPI to all + * CPUs with the mm active. The LDT will not be freed until + * after the IPI is handled by all such CPUs. This means that, + * if the ldt_struct changes before we return, the values we see + * will be safe, and the new values will be loaded before we run + * any user code. + * + * NB: don't try to convert this to use RCU without extreme care. + * We would still need IRQs off, because we don't want to change + * the local LDT after an IPI loaded a newer value than the one + * that we can see. + */ + + if (unlikely(ldt)) + set_ldt(ldt->entries, ldt->size); + else + clear_LDT(); + + DEBUG_LOCKS_WARN_ON(preemptible()); +} + +/* * Used for LDT copy/destruction. */ int init_new_context(struct task_struct *tsk, struct mm_struct *mm); @@ -78,12 +122,12 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, * was called and then modify_ldt changed * prev->context.ldt but suppressed an IPI to this CPU. * In this case, prev->context.ldt != NULL, because we - * never free an LDT while the mm still exists. That - * means that next->context.ldt != prev->context.ldt, - * because mms never share an LDT. + * never set context.ldt to NULL while the mm still + * exists. That means that next->context.ldt != + * prev->context.ldt, because mms never share an LDT. */ if (unlikely(prev->context.ldt != next->context.ldt)) - load_LDT_nolock(&next->context); + load_mm_ldt(next); } #ifdef CONFIG_SMP else { @@ -106,7 +150,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, load_cr3(next->pgd); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); load_mm_cr4(next); - load_LDT_nolock(&next->context); + load_mm_ldt(next); } } #endif @@ -142,6 +186,19 @@ static inline void arch_exit_mmap(struct mm_struct *mm) paravirt_arch_exit_mmap(mm); } +#ifdef CONFIG_X86_64 +static inline bool is_64bit_mm(struct mm_struct *mm) +{ + return !config_enabled(CONFIG_IA32_EMULATION) || + !(mm->context.ia32_compat == TIF_IA32); +} +#else +static inline bool is_64bit_mm(struct mm_struct *mm) +{ + return false; +} +#endif + static inline void arch_bprm_mm_init(struct mm_struct *mm, struct vm_area_struct *vma) { diff --git a/arch/x86/include/asm/mpx.h b/arch/x86/include/asm/mpx.h index a952a13d5..7a3549527 100644 --- a/arch/x86/include/asm/mpx.h +++ b/arch/x86/include/asm/mpx.h @@ -13,55 +13,50 @@ #define MPX_BNDCFG_ENABLE_FLAG 0x1 #define MPX_BD_ENTRY_VALID_FLAG 0x1 -#ifdef CONFIG_X86_64 - -/* upper 28 bits [47:20] of the virtual address in 64-bit used to - * index into bounds directory (BD). - */ -#define MPX_BD_ENTRY_OFFSET 28 -#define MPX_BD_ENTRY_SHIFT 3 -/* bits [19:3] of the virtual address in 64-bit used to index into - * bounds table (BT). +/* + * The upper 28 bits [47:20] of the virtual address in 64-bit + * are used to index into bounds directory (BD). + * + * The directory is 2G (2^31) in size, and with 8-byte entries + * it has 2^28 entries. */ -#define MPX_BT_ENTRY_OFFSET 17 -#define MPX_BT_ENTRY_SHIFT 5 -#define MPX_IGN_BITS 3 -#define MPX_BD_ENTRY_TAIL 3 +#define MPX_BD_SIZE_BYTES_64 (1UL<<31) +#define MPX_BD_ENTRY_BYTES_64 8 +#define MPX_BD_NR_ENTRIES_64 (MPX_BD_SIZE_BYTES_64/MPX_BD_ENTRY_BYTES_64) -#else - -#define MPX_BD_ENTRY_OFFSET 20 -#define MPX_BD_ENTRY_SHIFT 2 -#define MPX_BT_ENTRY_OFFSET 10 -#define MPX_BT_ENTRY_SHIFT 4 -#define MPX_IGN_BITS 2 -#define MPX_BD_ENTRY_TAIL 2 +/* + * The 32-bit directory is 4MB (2^22) in size, and with 4-byte + * entries it has 2^20 entries. + */ +#define MPX_BD_SIZE_BYTES_32 (1UL<<22) +#define MPX_BD_ENTRY_BYTES_32 4 +#define MPX_BD_NR_ENTRIES_32 (MPX_BD_SIZE_BYTES_32/MPX_BD_ENTRY_BYTES_32) -#endif +/* + * A 64-bit table is 4MB total in size, and an entry is + * 4 64-bit pointers in size. + */ +#define MPX_BT_SIZE_BYTES_64 (1UL<<22) +#define MPX_BT_ENTRY_BYTES_64 32 +#define MPX_BT_NR_ENTRIES_64 (MPX_BT_SIZE_BYTES_64/MPX_BT_ENTRY_BYTES_64) -#define MPX_BD_SIZE_BYTES (1UL<<(MPX_BD_ENTRY_OFFSET+MPX_BD_ENTRY_SHIFT)) -#define MPX_BT_SIZE_BYTES (1UL<<(MPX_BT_ENTRY_OFFSET+MPX_BT_ENTRY_SHIFT)) +/* + * A 32-bit table is 16kB total in size, and an entry is + * 4 32-bit pointers in size. + */ +#define MPX_BT_SIZE_BYTES_32 (1UL<<14) +#define MPX_BT_ENTRY_BYTES_32 16 +#define MPX_BT_NR_ENTRIES_32 (MPX_BT_SIZE_BYTES_32/MPX_BT_ENTRY_BYTES_32) #define MPX_BNDSTA_TAIL 2 #define MPX_BNDCFG_TAIL 12 #define MPX_BNDSTA_ADDR_MASK (~((1UL<<MPX_BNDSTA_TAIL)-1)) #define MPX_BNDCFG_ADDR_MASK (~((1UL<<MPX_BNDCFG_TAIL)-1)) -#define MPX_BT_ADDR_MASK (~((1UL<<MPX_BD_ENTRY_TAIL)-1)) - -#define MPX_BNDCFG_ADDR_MASK (~((1UL<<MPX_BNDCFG_TAIL)-1)) #define MPX_BNDSTA_ERROR_CODE 0x3 -#define MPX_BD_ENTRY_MASK ((1<<MPX_BD_ENTRY_OFFSET)-1) -#define MPX_BT_ENTRY_MASK ((1<<MPX_BT_ENTRY_OFFSET)-1) -#define MPX_GET_BD_ENTRY_OFFSET(addr) ((((addr)>>(MPX_BT_ENTRY_OFFSET+ \ - MPX_IGN_BITS)) & MPX_BD_ENTRY_MASK) << MPX_BD_ENTRY_SHIFT) -#define MPX_GET_BT_ENTRY_OFFSET(addr) ((((addr)>>MPX_IGN_BITS) & \ - MPX_BT_ENTRY_MASK) << MPX_BT_ENTRY_SHIFT) - #ifdef CONFIG_X86_INTEL_MPX -siginfo_t *mpx_generate_siginfo(struct pt_regs *regs, - struct xsave_struct *xsave_buf); -int mpx_handle_bd_fault(struct xsave_struct *xsave_buf); +siginfo_t *mpx_generate_siginfo(struct pt_regs *regs); +int mpx_handle_bd_fault(void); static inline int kernel_managing_mpx_tables(struct mm_struct *mm) { return (mm->bd_addr != MPX_INVALID_BOUNDS_DIR); @@ -77,12 +72,11 @@ static inline void mpx_mm_init(struct mm_struct *mm) void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long start, unsigned long end); #else -static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs, - struct xsave_struct *xsave_buf) +static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs) { return NULL; } -static inline int mpx_handle_bd_fault(struct xsave_struct *xsave_buf) +static inline int mpx_handle_bd_fault(void) { return -EINVAL; } diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h new file mode 100644 index 000000000..93724cc62 --- /dev/null +++ b/arch/x86/include/asm/msi.h @@ -0,0 +1,7 @@ +#ifndef _ASM_X86_MSI_H +#define _ASM_X86_MSI_H +#include <asm/hw_irq.h> + +typedef struct irq_alloc_info msi_alloc_info_t; + +#endif /* _ASM_X86_MSI_H */ diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 3c6bb342a..9ebc3d009 100644 --- a/arch/x86/include/uapi/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -56,6 +56,7 @@ #define MSR_IA32_MCG_CAP 0x00000179 #define MSR_IA32_MCG_STATUS 0x0000017a #define MSR_IA32_MCG_CTL 0x0000017b +#define MSR_IA32_MCG_EXT_CTL 0x000004d0 #define MSR_OFFCORE_RSP_0 0x000001a6 #define MSR_OFFCORE_RSP_1 0x000001a7 @@ -380,6 +381,7 @@ #define FEATURE_CONTROL_LOCKED (1<<0) #define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX (1<<1) #define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX (1<<2) +#define FEATURE_CONTROL_LMCE (1<<20) #define MSR_IA32_APICBASE 0x0000001b #define MSR_IA32_APICBASE_BSP (1<<8) diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index de36f22eb..e6a707eb5 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -1,13 +1,14 @@ #ifndef _ASM_X86_MSR_H #define _ASM_X86_MSR_H -#include <uapi/asm/msr.h> +#include "msr-index.h" #ifndef __ASSEMBLY__ #include <asm/asm.h> #include <asm/errno.h> #include <asm/cpumask.h> +#include <uapi/asm/msr.h> struct msr { union { @@ -205,8 +206,13 @@ do { \ #endif /* !CONFIG_PARAVIRT */ -#define wrmsrl_safe(msr, val) wrmsr_safe((msr), (u32)(val), \ - (u32)((val) >> 32)) +/* + * 64-bit version of wrmsr_safe(): + */ +static inline int wrmsrl_safe(u32 msr, u64 val) +{ + return wrmsr_safe(msr, (u32)val, (u32)(val >> 32)); +} #define write_tsc(low, high) wrmsr(MSR_IA32_TSC, (low), (high)) diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h index f768f6298..b94f6f64e 100644 --- a/arch/x86/include/asm/mtrr.h +++ b/arch/x86/include/asm/mtrr.h @@ -31,7 +31,7 @@ * arch_phys_wc_add and arch_phys_wc_del. */ # ifdef CONFIG_MTRR -extern u8 mtrr_type_lookup(u64 addr, u64 end); +extern u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform); extern void mtrr_save_fixed_ranges(void *); extern void mtrr_save_state(void); extern int mtrr_add(unsigned long base, unsigned long size, @@ -48,14 +48,13 @@ extern void mtrr_aps_init(void); extern void mtrr_bp_restore(void); extern int mtrr_trim_uncached_memory(unsigned long end_pfn); extern int amd_special_default_mtrr(void); -extern int phys_wc_to_mtrr_index(int handle); # else -static inline u8 mtrr_type_lookup(u64 addr, u64 end) +static inline u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform) { /* * Return no-MTRRs: */ - return 0xff; + return MTRR_TYPE_INVALID; } #define mtrr_save_fixed_ranges(arg) do {} while (0) #define mtrr_save_state() do {} while (0) @@ -84,10 +83,6 @@ static inline int mtrr_trim_uncached_memory(unsigned long end_pfn) static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi) { } -static inline int phys_wc_to_mtrr_index(int handle) -{ - return -1; -} #define mtrr_ap_init() do {} while (0) #define mtrr_bp_init() do {} while (0) @@ -127,4 +122,8 @@ struct mtrr_gentry32 { _IOW(MTRR_IOCTL_BASE, 9, struct mtrr_sentry32) #endif /* CONFIG_COMPAT */ +/* Bit fields for enabled in struct mtrr_state_type */ +#define MTRR_STATE_MTRR_FIXED_ENABLED 0x01 +#define MTRR_STATE_MTRR_ENABLED 0x02 + #endif /* _ASM_X86_MTRR_H */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 8957810ad..d143bfad4 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -712,6 +712,31 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx, #if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS) +#ifdef CONFIG_QUEUED_SPINLOCKS + +static __always_inline void pv_queued_spin_lock_slowpath(struct qspinlock *lock, + u32 val) +{ + PVOP_VCALL2(pv_lock_ops.queued_spin_lock_slowpath, lock, val); +} + +static __always_inline void pv_queued_spin_unlock(struct qspinlock *lock) +{ + PVOP_VCALLEE1(pv_lock_ops.queued_spin_unlock, lock); +} + +static __always_inline void pv_wait(u8 *ptr, u8 val) +{ + PVOP_VCALL2(pv_lock_ops.wait, ptr, val); +} + +static __always_inline void pv_kick(int cpu) +{ + PVOP_VCALL1(pv_lock_ops.kick, cpu); +} + +#else /* !CONFIG_QUEUED_SPINLOCKS */ + static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock, __ticket_t ticket) { @@ -724,7 +749,9 @@ static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock, PVOP_VCALL2(pv_lock_ops.unlock_kick, lock, ticket); } -#endif +#endif /* CONFIG_QUEUED_SPINLOCKS */ + +#endif /* SMP && PARAVIRT_SPINLOCKS */ #ifdef CONFIG_X86_32 #define PV_SAVE_REGS "pushl %ecx; pushl %edx;" diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index f7b0b5c11..a6b8f9fad 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -160,13 +160,14 @@ struct pv_cpu_ops { u64 (*read_pmc)(int counter); unsigned long long (*read_tscp)(unsigned int *aux); +#ifdef CONFIG_X86_32 /* * Atomically enable interrupts and return to userspace. This - * is only ever used to return to 32-bit processes; in a - * 64-bit kernel, it's used for 32-on-64 compat processes, but - * never native 64-bit processes. (Jump, not call.) + * is only used in 32-bit kernels. 64-bit kernels use + * usergs_sysret32 instead. */ void (*irq_enable_sysexit)(void); +#endif /* * Switch to usermode gs and return to 64-bit usermode using @@ -333,9 +334,19 @@ struct arch_spinlock; typedef u16 __ticket_t; #endif +struct qspinlock; + struct pv_lock_ops { +#ifdef CONFIG_QUEUED_SPINLOCKS + void (*queued_spin_lock_slowpath)(struct qspinlock *lock, u32 val); + struct paravirt_callee_save queued_spin_unlock; + + void (*wait)(u8 *ptr, u8 val); + void (*kick)(int cpu); +#else /* !CONFIG_QUEUED_SPINLOCKS */ struct paravirt_callee_save lock_spinning; void (*unlock_kick)(struct arch_spinlock *lock, __ticket_t ticket); +#endif /* !CONFIG_QUEUED_SPINLOCKS */ }; /* This contains all the paravirt structures: we get a convenient diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h index 91bc4ba95..ca6c228d5 100644 --- a/arch/x86/include/asm/pat.h +++ b/arch/x86/include/asm/pat.h @@ -4,14 +4,9 @@ #include <linux/types.h> #include <asm/pgtable_types.h> -#ifdef CONFIG_X86_PAT -extern int pat_enabled; -#else -static const int pat_enabled; -#endif - +bool pat_enabled(void); extern void pat_init(void); -void pat_init_cache_modes(void); +void pat_init_cache_modes(u64); extern int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm); diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 4e370a5d8..462594320 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -5,7 +5,7 @@ #include <linux/types.h> #include <linux/slab.h> #include <linux/string.h> -#include <asm/scatterlist.h> +#include <linux/scatterlist.h> #include <asm/io.h> #include <asm/x86_init.h> @@ -80,13 +80,6 @@ extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, #ifdef CONFIG_PCI extern void early_quirks(void); -static inline void pci_dma_burst_advice(struct pci_dev *pdev, - enum pci_dma_burst_strategy *strat, - unsigned long *strategy_parameter) -{ - *strat = PCI_DMA_BURST_INFINITY; - *strategy_parameter = ~0UL; -} #else static inline void early_quirks(void) { } #endif @@ -96,15 +89,10 @@ extern void pci_iommu_alloc(void); #ifdef CONFIG_PCI_MSI /* implemented in arch/x86/kernel/apic/io_apic. */ struct msi_desc; -void native_compose_msi_msg(struct pci_dev *pdev, unsigned int irq, - unsigned int dest, struct msi_msg *msg, u8 hpet_id); int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); void native_teardown_msi_irq(unsigned int irq); void native_restore_msi_irqs(struct pci_dev *dev); -int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, - unsigned int irq_base, unsigned int irq_offset); #else -#define native_compose_msi_msg NULL #define native_setup_msi_irqs NULL #define native_teardown_msi_irq NULL #endif diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index fe57e7a98..867da5bbb 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -398,11 +398,17 @@ static inline int is_new_memtype_allowed(u64 paddr, unsigned long size, * requested memtype: * - request is uncached, return cannot be write-back * - request is write-combine, return cannot be write-back + * - request is write-through, return cannot be write-back + * - request is write-through, return cannot be write-combine */ if ((pcm == _PAGE_CACHE_MODE_UC_MINUS && new_pcm == _PAGE_CACHE_MODE_WB) || (pcm == _PAGE_CACHE_MODE_WC && - new_pcm == _PAGE_CACHE_MODE_WB)) { + new_pcm == _PAGE_CACHE_MODE_WB) || + (pcm == _PAGE_CACHE_MODE_WT && + new_pcm == _PAGE_CACHE_MODE_WB) || + (pcm == _PAGE_CACHE_MODE_WT && + new_pcm == _PAGE_CACHE_MODE_WC)) { return 0; } @@ -799,8 +805,8 @@ static inline int pmd_write(pmd_t pmd) return pmd_flags(pmd) & _PAGE_RW; } -#define __HAVE_ARCH_PMDP_GET_AND_CLEAR -static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm, unsigned long addr, +#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR +static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { pmd_t pmd = native_pmdp_get_and_clear(pmdp); diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 78f0c8cbe..13f310bfc 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -367,6 +367,9 @@ extern int nx_enabled; #define pgprot_writecombine pgprot_writecombine extern pgprot_t pgprot_writecombine(pgprot_t prot); +#define pgprot_writethrough pgprot_writethrough +extern pgprot_t pgprot_writethrough(pgprot_t prot); + /* Indicate that x86 has its own track and untrack pfn vma functions */ #define __HAVE_PFNMAP_TRACKING diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index 8f3271842..dca71714f 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -99,11 +99,9 @@ static __always_inline bool should_resched(void) extern asmlinkage void ___preempt_schedule(void); # define __preempt_schedule() asm ("call ___preempt_schedule") extern asmlinkage void preempt_schedule(void); -# ifdef CONFIG_CONTEXT_TRACKING - extern asmlinkage void ___preempt_schedule_context(void); -# define __preempt_schedule_context() asm ("call ___preempt_schedule_context") - extern asmlinkage void preempt_schedule_context(void); -# endif + extern asmlinkage void ___preempt_schedule_notrace(void); +# define __preempt_schedule_notrace() asm ("call ___preempt_schedule_notrace") + extern asmlinkage void preempt_schedule_notrace(void); #endif #endif /* __ASM_PREEMPT_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 23ba6765b..944f1785e 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -21,6 +21,7 @@ struct mm_struct; #include <asm/desc_defs.h> #include <asm/nops.h> #include <asm/special_insns.h> +#include <asm/fpu/types.h> #include <linux/personality.h> #include <linux/cpumask.h> @@ -52,11 +53,16 @@ static inline void *current_text_addr(void) return pc; } +/* + * These alignment constraints are for performance in the vSMP case, + * but in the task_struct case we must also meet hardware imposed + * alignment requirements of the FPU state: + */ #ifdef CONFIG_X86_VSMP # define ARCH_MIN_TASKALIGN (1 << INTERNODE_CACHE_SHIFT) # define ARCH_MIN_MMSTRUCT_ALIGN (1 << INTERNODE_CACHE_SHIFT) #else -# define ARCH_MIN_TASKALIGN 16 +# define ARCH_MIN_TASKALIGN __alignof__(union fpregs_state) # define ARCH_MIN_MMSTRUCT_ALIGN 0 #endif @@ -166,7 +172,6 @@ extern const struct seq_operations cpuinfo_op; #define cache_line_size() (boot_cpu_data.x86_cache_alignment) extern void cpu_detect(struct cpuinfo_x86 *c); -extern void fpu_detect(struct cpuinfo_x86 *c); extern void early_cpu_init(void); extern void identify_boot_cpu(void); @@ -313,128 +318,6 @@ struct orig_ist { unsigned long ist[7]; }; -#define MXCSR_DEFAULT 0x1f80 - -struct i387_fsave_struct { - u32 cwd; /* FPU Control Word */ - u32 swd; /* FPU Status Word */ - u32 twd; /* FPU Tag Word */ - u32 fip; /* FPU IP Offset */ - u32 fcs; /* FPU IP Selector */ - u32 foo; /* FPU Operand Pointer Offset */ - u32 fos; /* FPU Operand Pointer Selector */ - - /* 8*10 bytes for each FP-reg = 80 bytes: */ - u32 st_space[20]; - - /* Software status information [not touched by FSAVE ]: */ - u32 status; -}; - -struct i387_fxsave_struct { - u16 cwd; /* Control Word */ - u16 swd; /* Status Word */ - u16 twd; /* Tag Word */ - u16 fop; /* Last Instruction Opcode */ - union { - struct { - u64 rip; /* Instruction Pointer */ - u64 rdp; /* Data Pointer */ - }; - struct { - u32 fip; /* FPU IP Offset */ - u32 fcs; /* FPU IP Selector */ - u32 foo; /* FPU Operand Offset */ - u32 fos; /* FPU Operand Selector */ - }; - }; - u32 mxcsr; /* MXCSR Register State */ - u32 mxcsr_mask; /* MXCSR Mask */ - - /* 8*16 bytes for each FP-reg = 128 bytes: */ - u32 st_space[32]; - - /* 16*16 bytes for each XMM-reg = 256 bytes: */ - u32 xmm_space[64]; - - u32 padding[12]; - - union { - u32 padding1[12]; - u32 sw_reserved[12]; - }; - -} __attribute__((aligned(16))); - -struct i387_soft_struct { - u32 cwd; - u32 swd; - u32 twd; - u32 fip; - u32 fcs; - u32 foo; - u32 fos; - /* 8*10 bytes for each FP-reg = 80 bytes: */ - u32 st_space[20]; - u8 ftop; - u8 changed; - u8 lookahead; - u8 no_update; - u8 rm; - u8 alimit; - struct math_emu_info *info; - u32 entry_eip; -}; - -struct ymmh_struct { - /* 16 * 16 bytes for each YMMH-reg = 256 bytes */ - u32 ymmh_space[64]; -}; - -/* We don't support LWP yet: */ -struct lwp_struct { - u8 reserved[128]; -}; - -struct bndreg { - u64 lower_bound; - u64 upper_bound; -} __packed; - -struct bndcsr { - u64 bndcfgu; - u64 bndstatus; -} __packed; - -struct xsave_hdr_struct { - u64 xstate_bv; - u64 xcomp_bv; - u64 reserved[6]; -} __attribute__((packed)); - -struct xsave_struct { - struct i387_fxsave_struct i387; - struct xsave_hdr_struct xsave_hdr; - struct ymmh_struct ymmh; - struct lwp_struct lwp; - struct bndreg bndreg[4]; - struct bndcsr bndcsr; - /* new processor state extensions will go here */ -} __attribute__ ((packed, aligned (64))); - -union thread_xstate { - struct i387_fsave_struct fsave; - struct i387_fxsave_struct fxsave; - struct i387_soft_struct soft; - struct xsave_struct xsave; -}; - -struct fpu { - unsigned int last_cpu; - unsigned int has_fpu; - union thread_xstate *state; -}; - #ifdef CONFIG_X86_64 DECLARE_PER_CPU(struct orig_ist, orig_ist); @@ -483,8 +366,6 @@ DECLARE_PER_CPU(struct irq_stack *, softirq_stack); #endif /* X86_64 */ extern unsigned int xstate_size; -extern void free_thread_xstate(struct task_struct *); -extern struct kmem_cache *task_xstate_cachep; struct perf_event; @@ -508,6 +389,7 @@ struct thread_struct { unsigned long fs; #endif unsigned long gs; + /* Save middle states of ptrace breakpoints */ struct perf_event *ptrace_bps[HBP_NUM]; /* Debug status used for traps, single steps, etc... */ @@ -518,8 +400,6 @@ struct thread_struct { unsigned long cr2; unsigned long trap_nr; unsigned long error_code; - /* floating point and extended processor state */ - struct fpu fpu; #ifdef CONFIG_X86_32 /* Virtual 86 mode info */ struct vm86_struct __user *vm86_info; @@ -535,15 +415,13 @@ struct thread_struct { unsigned long iopl; /* Max allowed port in the bitmap, in bytes: */ unsigned io_bitmap_max; + + /* Floating point and extended processor state */ + struct fpu fpu; /* - * fpu_counter contains the number of consecutive context switches - * that the FPU is used. If this is over a threshold, the lazy fpu - * saving becomes unlazy to save the trap. This is an unsigned char - * so that after 256 times the counter wraps and the behavior turns - * lazy again; this to deal with bursty apps that only use FPU for - * a short time + * WARNING: 'fpu' is dynamically-sized. It *MUST* be at + * the end. */ - unsigned char fpu_counter; }; /* @@ -928,24 +806,25 @@ extern int get_tsc_mode(unsigned long adr); extern int set_tsc_mode(unsigned int val); /* Register/unregister a process' MPX related resource */ -#define MPX_ENABLE_MANAGEMENT(tsk) mpx_enable_management((tsk)) -#define MPX_DISABLE_MANAGEMENT(tsk) mpx_disable_management((tsk)) +#define MPX_ENABLE_MANAGEMENT() mpx_enable_management() +#define MPX_DISABLE_MANAGEMENT() mpx_disable_management() #ifdef CONFIG_X86_INTEL_MPX -extern int mpx_enable_management(struct task_struct *tsk); -extern int mpx_disable_management(struct task_struct *tsk); +extern int mpx_enable_management(void); +extern int mpx_disable_management(void); #else -static inline int mpx_enable_management(struct task_struct *tsk) +static inline int mpx_enable_management(void) { return -EINVAL; } -static inline int mpx_disable_management(struct task_struct *tsk) +static inline int mpx_disable_management(void) { return -EINVAL; } #endif /* CONFIG_X86_INTEL_MPX */ extern u16 amd_get_nb_id(int cpu); +extern u32 amd_get_nodes_per_socket(void); static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) { diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index a90f8972d..a4a77286c 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -5,12 +5,14 @@ /* misc architecture specific prototypes */ -void system_call(void); void syscall_init(void); -void ia32_syscall(void); -void ia32_cstar_target(void); -void ia32_sysenter_target(void); +void entry_SYSCALL_64(void); +void entry_SYSCALL_compat(void); +void entry_INT80_32(void); +void entry_INT80_compat(void); +void entry_SYSENTER_32(void); +void entry_SYSENTER_compat(void); void x86_configure_nx(void); void x86_report_nx(void); diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h index 6167fd798..655e07a48 100644 --- a/arch/x86/include/asm/pvclock-abi.h +++ b/arch/x86/include/asm/pvclock-abi.h @@ -41,5 +41,6 @@ struct pvclock_wall_clock { #define PVCLOCK_TSC_STABLE_BIT (1 << 0) #define PVCLOCK_GUEST_STOPPED (1 << 1) +#define PVCLOCK_COUNTS_FROM_ZERO (1 << 2) #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_PVCLOCK_ABI_H */ diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index d6b078e9f..628954cee 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -86,7 +86,6 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, offset = pvclock_get_nsec_offset(src); ret = src->system_time + offset; ret_flags = src->flags; - rdtsc_barrier(); *cycles = ret; *flags = ret_flags; diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h new file mode 100644 index 000000000..9d51fae1c --- /dev/null +++ b/arch/x86/include/asm/qspinlock.h @@ -0,0 +1,57 @@ +#ifndef _ASM_X86_QSPINLOCK_H +#define _ASM_X86_QSPINLOCK_H + +#include <asm/cpufeature.h> +#include <asm-generic/qspinlock_types.h> +#include <asm/paravirt.h> + +#define queued_spin_unlock queued_spin_unlock +/** + * queued_spin_unlock - release a queued spinlock + * @lock : Pointer to queued spinlock structure + * + * A smp_store_release() on the least-significant byte. + */ +static inline void native_queued_spin_unlock(struct qspinlock *lock) +{ + smp_store_release((u8 *)lock, 0); +} + +#ifdef CONFIG_PARAVIRT_SPINLOCKS +extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); +extern void __pv_init_lock_hash(void); +extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); +extern void __raw_callee_save___pv_queued_spin_unlock(struct qspinlock *lock); + +static inline void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) +{ + pv_queued_spin_lock_slowpath(lock, val); +} + +static inline void queued_spin_unlock(struct qspinlock *lock) +{ + pv_queued_spin_unlock(lock); +} +#else +static inline void queued_spin_unlock(struct qspinlock *lock) +{ + native_queued_spin_unlock(lock); +} +#endif + +#define virt_queued_spin_lock virt_queued_spin_lock + +static inline bool virt_queued_spin_lock(struct qspinlock *lock) +{ + if (!static_cpu_has(X86_FEATURE_HYPERVISOR)) + return false; + + while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0) + cpu_relax(); + + return true; +} + +#include <asm-generic/qspinlock.h> + +#endif /* _ASM_X86_QSPINLOCK_H */ diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h new file mode 100644 index 000000000..b002e711b --- /dev/null +++ b/arch/x86/include/asm/qspinlock_paravirt.h @@ -0,0 +1,6 @@ +#ifndef __ASM_QSPINLOCK_PARAVIRT_H +#define __ASM_QSPINLOCK_PARAVIRT_H + +PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock); + +#endif diff --git a/arch/x86/include/asm/serial.h b/arch/x86/include/asm/serial.h index 8378b8c91..bb658211e 100644 --- a/arch/x86/include/asm/serial.h +++ b/arch/x86/include/asm/serial.h @@ -11,7 +11,7 @@ #define BASE_BAUD (1843200/16) /* Standard COM flags (except for COM4, because of the 8514 problem) */ -#ifdef CONFIG_SERIAL_DETECT_IRQ +#ifdef CONFIG_SERIAL_8250_DETECT_IRQ # define STD_COMX_FLAGS (UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | UPF_AUTO_IRQ) # define STD_COM4_FLAGS (UPF_BOOT_AUTOCONF | 0 | UPF_AUTO_IRQ) #else diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index f69e06b28..11af24e09 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -60,17 +60,24 @@ static inline void x86_ce4100_early_setup(void) { } #ifndef _SETUP #include <asm/espfix.h> +#include <linux/kernel.h> /* * This is set up by the setup-routine at boot-time */ extern struct boot_params boot_params; +extern char _text[]; static inline bool kaslr_enabled(void) { return !!(boot_params.hdr.loadflags & KASLR_FLAG); } +static inline unsigned long kaslr_offset(void) +{ + return (unsigned long)&_text - __START_KERNEL; +} + /* * Do NOT EVER look at the BIOS memory size location. * It does not work on many machines. diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h index 6fe6b182c..9dfce4e04 100644 --- a/arch/x86/include/asm/sigcontext.h +++ b/arch/x86/include/asm/sigcontext.h @@ -57,9 +57,9 @@ struct sigcontext { unsigned long ip; unsigned long flags; unsigned short cs; - unsigned short __pad2; /* Was called gs, but was always zero. */ - unsigned short __pad1; /* Was called fs, but was always zero. */ - unsigned short ss; + unsigned short gs; + unsigned short fs; + unsigned short __pad0; unsigned long err; unsigned long trapno; unsigned long oldmask; diff --git a/arch/x86/include/asm/simd.h b/arch/x86/include/asm/simd.h index ee80b92f0..6c8a7ed13 100644 --- a/arch/x86/include/asm/simd.h +++ b/arch/x86/include/asm/simd.h @@ -1,5 +1,5 @@ -#include <asm/i387.h> +#include <asm/fpu/api.h> /* * may_use_simd - whether it is allowable at this time to issue SIMD diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 17a8dced1..222a6a3ca 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -37,16 +37,6 @@ DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id); DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number); -static inline struct cpumask *cpu_sibling_mask(int cpu) -{ - return per_cpu(cpu_sibling_map, cpu); -} - -static inline struct cpumask *cpu_core_mask(int cpu) -{ - return per_cpu(cpu_core_map, cpu); -} - static inline struct cpumask *cpu_llc_shared_mask(int cpu) { return per_cpu(cpu_llc_shared_map, cpu); diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index aeb4666e0..2270e41b3 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -215,6 +215,44 @@ static inline void clwb(volatile void *__p) : [pax] "a" (p)); } +/** + * pcommit_sfence() - persistent commit and fence + * + * The PCOMMIT instruction ensures that data that has been flushed from the + * processor's cache hierarchy with CLWB, CLFLUSHOPT or CLFLUSH is accepted to + * memory and is durable on the DIMM. The primary use case for this is + * persistent memory. + * + * This function shows how to properly use CLWB/CLFLUSHOPT/CLFLUSH and PCOMMIT + * with appropriate fencing. + * + * Example: + * void flush_and_commit_buffer(void *vaddr, unsigned int size) + * { + * unsigned long clflush_mask = boot_cpu_data.x86_clflush_size - 1; + * void *vend = vaddr + size; + * void *p; + * + * for (p = (void *)((unsigned long)vaddr & ~clflush_mask); + * p < vend; p += boot_cpu_data.x86_clflush_size) + * clwb(p); + * + * // SFENCE to order CLWB/CLFLUSHOPT/CLFLUSH cache flushes + * // MFENCE via mb() also works + * wmb(); + * + * // PCOMMIT and the required SFENCE for ordering + * pcommit_sfence(); + * } + * + * After this function completes the data pointed to by 'vaddr' has been + * accepted to memory and will be durable if the 'vaddr' points to persistent + * memory. + * + * PCOMMIT must always be ordered by an MFENCE or SFENCE, so to help simplify + * things we include both the PCOMMIT and the required SFENCE in the + * alternatives generated by pcommit_sfence(). + */ static inline void pcommit_sfence(void) { alternative(ASM_NOP7, diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 64b611782..be0a05913 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -42,6 +42,10 @@ extern struct static_key paravirt_ticketlocks_enabled; static __always_inline bool static_key_false(struct static_key *key); +#ifdef CONFIG_QUEUED_SPINLOCKS +#include <asm/qspinlock.h> +#else + #ifdef CONFIG_PARAVIRT_SPINLOCKS static inline void __ticket_enter_slowpath(arch_spinlock_t *lock) @@ -196,6 +200,7 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) cpu_relax(); } } +#endif /* CONFIG_QUEUED_SPINLOCKS */ /* * Read-write spinlocks, allowing multiple readers diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h index 5f9d7572d..65c3e37f8 100644 --- a/arch/x86/include/asm/spinlock_types.h +++ b/arch/x86/include/asm/spinlock_types.h @@ -23,6 +23,9 @@ typedef u32 __ticketpair_t; #define TICKET_SHIFT (sizeof(__ticket_t) * 8) +#ifdef CONFIG_QUEUED_SPINLOCKS +#include <asm-generic/qspinlock_types.h> +#else typedef struct arch_spinlock { union { __ticketpair_t head_tail; @@ -33,6 +36,7 @@ typedef struct arch_spinlock { } arch_spinlock_t; #define __ARCH_SPIN_LOCK_UNLOCKED { { 0 } } +#endif /* CONFIG_QUEUED_SPINLOCKS */ #include <asm-generic/qrwlock_types.h> diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index 6a998598f..c2e00bb2a 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -39,7 +39,9 @@ #include <asm/processor.h> #include <asm/percpu.h> #include <asm/desc.h> + #include <linux/random.h> +#include <linux/sched.h> /* * 24 byte read-only segment initializer for stack canary. Linker diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index 552d6c90a..d1793f068 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -7,7 +7,7 @@ #define _ASM_X86_SUSPEND_32_H #include <asm/desc.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> /* image of the saved processor state */ struct saved_context { diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h index bc6232834..7ebf0ebe4 100644 --- a/arch/x86/include/asm/suspend_64.h +++ b/arch/x86/include/asm/suspend_64.h @@ -7,7 +7,7 @@ #define _ASM_X86_SUSPEND_64_H #include <asm/desc.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> /* * Image of the saved processor state, used by the low level ACPI suspend to diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 751bf4b7b..d7f3b3b78 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -79,12 +79,12 @@ do { \ #else /* CONFIG_X86_32 */ /* frame pointer must be last for get_wchan */ -#define SAVE_CONTEXT "pushq %%rbp ; movq %%rsi,%%rbp\n\t" -#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp\t" +#define SAVE_CONTEXT "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t" +#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t" #define __EXTRA_CLOBBER \ , "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \ - "r12", "r13", "r14", "r15", "flags" + "r12", "r13", "r14", "r15" #ifdef CONFIG_CC_STACKPROTECTOR #define __switch_canary \ @@ -100,11 +100,7 @@ do { \ #define __switch_canary_iparam #endif /* CC_STACKPROTECTOR */ -/* - * There is no need to save or restore flags, because flags are always - * clean in kernel mode, with the possible exception of IOPL. Kernel IOPL - * has no effect. - */ +/* Save restore flags to clear handle leaking NT */ #define switch_to(prev, next, last) \ asm volatile(SAVE_CONTEXT \ "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index b4bdec3e9..225ee545e 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -177,8 +177,6 @@ struct thread_info { */ #ifndef __ASSEMBLY__ -DECLARE_PER_CPU(unsigned long, kernel_stack); - static inline struct thread_info *current_thread_info(void) { return (struct thread_info *)(current_top_of_stack() - THREAD_SIZE); @@ -197,9 +195,13 @@ static inline unsigned long current_stack_pointer(void) #else /* !__ASSEMBLY__ */ +#ifdef CONFIG_X86_64 +# define cpu_current_top_of_stack (cpu_tss + TSS_sp0) +#endif + /* Load thread_info address into "reg" */ #define GET_THREAD_INFO(reg) \ - _ASM_MOV PER_CPU_VAR(kernel_stack),reg ; \ + _ASM_MOV PER_CPU_VAR(cpu_current_top_of_stack),reg ; \ _ASM_SUB $(THREAD_SIZE),reg ; /* diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 0e8f04f2c..0fb46482d 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -26,7 +26,7 @@ #define _ASM_X86_TOPOLOGY_H #ifdef CONFIG_X86_32 -# ifdef CONFIG_X86_HT +# ifdef CONFIG_SMP # define ENABLE_TOPO_DEFINES # endif #else @@ -124,7 +124,7 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu); #ifdef ENABLE_TOPO_DEFINES #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) -#define topology_thread_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) +#define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) #endif static inline void arch_fix_phys_package_id(int num, u32 slot) diff --git a/arch/x86/include/asm/trace/irq_vectors.h b/arch/x86/include/asm/trace/irq_vectors.h index 4cab89000..38a09a13a 100644 --- a/arch/x86/include/asm/trace/irq_vectors.h +++ b/arch/x86/include/asm/trace/irq_vectors.h @@ -101,6 +101,12 @@ DEFINE_IRQ_VECTOR_EVENT(call_function_single); DEFINE_IRQ_VECTOR_EVENT(threshold_apic); /* + * deferred_error_apic - called when entering/exiting a deferred apic interrupt + * vector handler + */ +DEFINE_IRQ_VECTOR_EVENT(deferred_error_apic); + +/* * thermal_apic - called when entering/exiting a thermal apic interrupt * vector handler */ diff --git a/arch/x86/include/asm/trace/mpx.h b/arch/x86/include/asm/trace/mpx.h new file mode 100644 index 000000000..173dd3ba1 --- /dev/null +++ b/arch/x86/include/asm/trace/mpx.h @@ -0,0 +1,132 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mpx + +#if !defined(_TRACE_MPX_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_MPX_H + +#include <linux/tracepoint.h> + +#ifdef CONFIG_X86_INTEL_MPX + +TRACE_EVENT(mpx_bounds_register_exception, + + TP_PROTO(void *addr_referenced, + const struct bndreg *bndreg), + TP_ARGS(addr_referenced, bndreg), + + TP_STRUCT__entry( + __field(void *, addr_referenced) + __field(u64, lower_bound) + __field(u64, upper_bound) + ), + + TP_fast_assign( + __entry->addr_referenced = addr_referenced; + __entry->lower_bound = bndreg->lower_bound; + __entry->upper_bound = bndreg->upper_bound; + ), + /* + * Note that we are printing out the '~' of the upper + * bounds register here. It is actually stored in its + * one's complement form so that its 'init' state + * corresponds to all 0's. But, that looks like + * gibberish when printed out, so print out the 1's + * complement instead of the actual value here. Note + * though that you still need to specify filters for the + * actual value, not the displayed one. + */ + TP_printk("address referenced: 0x%p bounds: lower: 0x%llx ~upper: 0x%llx", + __entry->addr_referenced, + __entry->lower_bound, + ~__entry->upper_bound + ) +); + +TRACE_EVENT(bounds_exception_mpx, + + TP_PROTO(const struct bndcsr *bndcsr), + TP_ARGS(bndcsr), + + TP_STRUCT__entry( + __field(u64, bndcfgu) + __field(u64, bndstatus) + ), + + TP_fast_assign( + /* need to get rid of the 'const' on bndcsr */ + __entry->bndcfgu = (u64)bndcsr->bndcfgu; + __entry->bndstatus = (u64)bndcsr->bndstatus; + ), + + TP_printk("bndcfgu:0x%llx bndstatus:0x%llx", + __entry->bndcfgu, + __entry->bndstatus) +); + +DECLARE_EVENT_CLASS(mpx_range_trace, + + TP_PROTO(unsigned long start, + unsigned long end), + TP_ARGS(start, end), + + TP_STRUCT__entry( + __field(unsigned long, start) + __field(unsigned long, end) + ), + + TP_fast_assign( + __entry->start = start; + __entry->end = end; + ), + + TP_printk("[0x%p:0x%p]", + (void *)__entry->start, + (void *)__entry->end + ) +); + +DEFINE_EVENT(mpx_range_trace, mpx_unmap_zap, + TP_PROTO(unsigned long start, unsigned long end), + TP_ARGS(start, end) +); + +DEFINE_EVENT(mpx_range_trace, mpx_unmap_search, + TP_PROTO(unsigned long start, unsigned long end), + TP_ARGS(start, end) +); + +TRACE_EVENT(mpx_new_bounds_table, + + TP_PROTO(unsigned long table_vaddr), + TP_ARGS(table_vaddr), + + TP_STRUCT__entry( + __field(unsigned long, table_vaddr) + ), + + TP_fast_assign( + __entry->table_vaddr = table_vaddr; + ), + + TP_printk("table vaddr:%p", (void *)__entry->table_vaddr) +); + +#else + +/* + * This gets used outside of MPX-specific code, so we need a stub. + */ +static inline void trace_bounds_exception_mpx(const struct bndcsr *bndcsr) +{ +} + +#endif /* CONFIG_X86_INTEL_MPX */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH asm/trace/ +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE mpx +#endif /* _TRACE_MPX_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 4e49d7dff..c5380bea2 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -108,7 +108,8 @@ extern int panic_on_unrecovered_nmi; void math_emulate(struct math_emu_info *); #ifndef CONFIG_X86_32 asmlinkage void smp_thermal_interrupt(void); -asmlinkage void mce_threshold_interrupt(void); +asmlinkage void smp_threshold_interrupt(void); +asmlinkage void smp_deferred_error_interrupt(void); #endif extern enum ctx_state ist_enter(struct pt_regs *regs); diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index ace9dec05..a8df874f3 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -74,7 +74,8 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un * @addr: User space pointer to start of block to check * @size: Size of block to check * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Checks if a pointer to a block of memory in user space is valid. * @@ -145,7 +146,8 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) * @x: Variable to store result. * @ptr: Source address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger @@ -240,7 +242,8 @@ extern void __put_user_8(void); * @x: Value to copy to user space. * @ptr: Destination address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger @@ -455,7 +458,8 @@ struct __large_struct { unsigned long buf[100]; }; * @x: Variable to store result. * @ptr: Source address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger @@ -479,7 +483,8 @@ struct __large_struct { unsigned long buf[100]; }; * @x: Value to copy to user space. * @ptr: Destination address, in user space. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index 3c03a5de6..f5dcb5204 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -59,6 +59,10 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) __put_user_size(*(u32 *)from, (u32 __user *)to, 4, ret, 4); return ret; + case 8: + __put_user_size(*(u64 *)from, (u64 __user *)to, + 8, ret, 8); + return ret; } } return __copy_to_user_ll(to, from, n); @@ -70,7 +74,8 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) * @from: Source address, in kernel space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from kernel space to user space. Caller must check * the specified block with access_ok() before calling this function. @@ -117,7 +122,8 @@ __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) * @from: Source address, in user space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from user space to kernel space. Caller must check * the specified block with access_ok() before calling this function. diff --git a/arch/x86/include/asm/user.h b/arch/x86/include/asm/user.h index ccab4af16..59a54e869 100644 --- a/arch/x86/include/asm/user.h +++ b/arch/x86/include/asm/user.h @@ -14,8 +14,8 @@ struct user_ymmh_regs { __u32 ymmh_space[64]; }; -struct user_xsave_hdr { - __u64 xstate_bv; +struct user_xstate_header { + __u64 xfeatures; __u64 reserved1[2]; __u64 reserved2[5]; }; @@ -41,11 +41,11 @@ struct user_xsave_hdr { * particular process/thread. * * Also when the user modifies certain state FP/SSE/etc through the - * ptrace interface, they must ensure that the xsave_hdr.xstate_bv + * ptrace interface, they must ensure that the header.xfeatures * bytes[512..519] of the memory layout are updated correspondingly. * i.e., for example when FP state is modified to a non-init state, - * xsave_hdr.xstate_bv's bit 0 must be set to '1', when SSE is modified to - * non-init state, xsave_hdr.xstate_bv's bit 1 must to be set to '1', etc. + * header.xfeatures's bit 0 must be set to '1', when SSE is modified to + * non-init state, header.xfeatures's bit 1 must to be set to '1', etc. */ #define USER_XSTATE_FX_SW_WORDS 6 #define USER_XSTATE_XCR0_WORD 0 @@ -55,7 +55,7 @@ struct user_xstateregs { __u64 fpx_space[58]; __u64 xstate_fx_sw[USER_XSTATE_FX_SW_WORDS]; } i387; - struct user_xsave_hdr xsave_hdr; + struct user_xstate_header header; struct user_ymmh_regs ymmh; /* further processor state extensions go here */ }; diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index f58a9c7a3..48d34d28f 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -171,38 +171,17 @@ struct x86_platform_ops { }; struct pci_dev; -struct msi_msg; struct x86_msi_ops { int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type); - void (*compose_msi_msg)(struct pci_dev *dev, unsigned int irq, - unsigned int dest, struct msi_msg *msg, - u8 hpet_id); void (*teardown_msi_irq)(unsigned int irq); void (*teardown_msi_irqs)(struct pci_dev *dev); void (*restore_msi_irqs)(struct pci_dev *dev); - int (*setup_hpet_msi)(unsigned int irq, unsigned int id); }; -struct IO_APIC_route_entry; -struct io_apic_irq_attr; -struct irq_data; -struct cpumask; - struct x86_io_apic_ops { - void (*init) (void); unsigned int (*read) (unsigned int apic, unsigned int reg); - void (*write) (unsigned int apic, unsigned int reg, unsigned int value); - void (*modify) (unsigned int apic, unsigned int reg, unsigned int value); void (*disable)(void); - void (*print_entries)(unsigned int apic, unsigned int nr_entries); - int (*set_affinity)(struct irq_data *data, - const struct cpumask *mask, - bool force); - int (*setup_entry)(int irq, struct IO_APIC_route_entry *entry, - unsigned int destination, int vector, - struct io_apic_irq_attr *attr); - void (*eoi_ioapic_pin)(int apic, int pin, int vector); }; extern struct x86_init_ops x86_init; diff --git a/arch/x86/include/asm/xcr.h b/arch/x86/include/asm/xcr.h deleted file mode 100644 index f2cba4e79..000000000 --- a/arch/x86/include/asm/xcr.h +++ /dev/null @@ -1,49 +0,0 @@ -/* -*- linux-c -*- ------------------------------------------------------- * - * - * Copyright 2008 rPath, Inc. - All Rights Reserved - * - * This file is part of the Linux kernel, and is made available under - * the terms of the GNU General Public License version 2 or (at your - * option) any later version; incorporated herein by reference. - * - * ----------------------------------------------------------------------- */ - -/* - * asm-x86/xcr.h - * - * Definitions for the eXtended Control Register instructions - */ - -#ifndef _ASM_X86_XCR_H -#define _ASM_X86_XCR_H - -#define XCR_XFEATURE_ENABLED_MASK 0x00000000 - -#ifdef __KERNEL__ -# ifndef __ASSEMBLY__ - -#include <linux/types.h> - -static inline u64 xgetbv(u32 index) -{ - u32 eax, edx; - - asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */ - : "=a" (eax), "=d" (edx) - : "c" (index)); - return eax + ((u64)edx << 32); -} - -static inline void xsetbv(u32 index, u64 value) -{ - u32 eax = value; - u32 edx = value >> 32; - - asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */ - : : "a" (eax), "d" (edx), "c" (index)); -} - -# endif /* __ASSEMBLY__ */ -#endif /* __KERNEL__ */ - -#endif /* _ASM_X86_XCR_H */ diff --git a/arch/x86/include/asm/xor.h b/arch/x86/include/asm/xor.h index d8829751b..1f5c5161e 100644 --- a/arch/x86/include/asm/xor.h +++ b/arch/x86/include/asm/xor.h @@ -36,7 +36,7 @@ * no advantages to be gotten from x86-64 here anyways. */ -#include <asm/i387.h> +#include <asm/fpu/api.h> #ifdef CONFIG_X86_32 /* reduce register pressure */ diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h index ce05722e3..5a08bc8bf 100644 --- a/arch/x86/include/asm/xor_32.h +++ b/arch/x86/include/asm/xor_32.h @@ -26,7 +26,7 @@ #define XO3(x, y) " pxor 8*("#x")(%4), %%mm"#y" ;\n" #define XO4(x, y) " pxor 8*("#x")(%5), %%mm"#y" ;\n" -#include <asm/i387.h> +#include <asm/fpu/api.h> static void xor_pII_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h index 492b29802..7c0a517ec 100644 --- a/arch/x86/include/asm/xor_avx.h +++ b/arch/x86/include/asm/xor_avx.h @@ -18,7 +18,7 @@ #ifdef CONFIG_AS_AVX #include <linux/compiler.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #define BLOCK4(i) \ BLOCK(32 * i, 0) \ diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h deleted file mode 100644 index c9a6d68b8..000000000 --- a/arch/x86/include/asm/xsave.h +++ /dev/null @@ -1,257 +0,0 @@ -#ifndef __ASM_X86_XSAVE_H -#define __ASM_X86_XSAVE_H - -#include <linux/types.h> -#include <asm/processor.h> - -#define XSTATE_CPUID 0x0000000d - -#define XSTATE_FP 0x1 -#define XSTATE_SSE 0x2 -#define XSTATE_YMM 0x4 -#define XSTATE_BNDREGS 0x8 -#define XSTATE_BNDCSR 0x10 -#define XSTATE_OPMASK 0x20 -#define XSTATE_ZMM_Hi256 0x40 -#define XSTATE_Hi16_ZMM 0x80 - -#define XSTATE_FPSSE (XSTATE_FP | XSTATE_SSE) -#define XSTATE_AVX512 (XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM) -/* Bit 63 of XCR0 is reserved for future expansion */ -#define XSTATE_EXTEND_MASK (~(XSTATE_FPSSE | (1ULL << 63))) - -#define FXSAVE_SIZE 512 - -#define XSAVE_HDR_SIZE 64 -#define XSAVE_HDR_OFFSET FXSAVE_SIZE - -#define XSAVE_YMM_SIZE 256 -#define XSAVE_YMM_OFFSET (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET) - -/* Supported features which support lazy state saving */ -#define XSTATE_LAZY (XSTATE_FP | XSTATE_SSE | XSTATE_YMM \ - | XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM) - -/* Supported features which require eager state saving */ -#define XSTATE_EAGER (XSTATE_BNDREGS | XSTATE_BNDCSR) - -/* All currently supported features */ -#define XCNTXT_MASK (XSTATE_LAZY | XSTATE_EAGER) - -#ifdef CONFIG_X86_64 -#define REX_PREFIX "0x48, " -#else -#define REX_PREFIX -#endif - -extern unsigned int xstate_size; -extern u64 pcntxt_mask; -extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; -extern struct xsave_struct *init_xstate_buf; - -extern void xsave_init(void); -extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask); -extern int init_fpu(struct task_struct *child); - -/* These macros all use (%edi)/(%rdi) as the single memory argument. */ -#define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27" -#define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37" -#define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f" -#define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f" -#define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f" - -#define xstate_fault ".section .fixup,\"ax\"\n" \ - "3: movl $-1,%[err]\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ - : [err] "=r" (err) - -/* - * This function is called only during boot time when x86 caps are not set - * up and alternative can not be used yet. - */ -static inline int xsave_state_booting(struct xsave_struct *fx, u64 mask) -{ - u32 lmask = mask; - u32 hmask = mask >> 32; - int err = 0; - - WARN_ON(system_state != SYSTEM_BOOTING); - - if (boot_cpu_has(X86_FEATURE_XSAVES)) - asm volatile("1:"XSAVES"\n\t" - "2:\n\t" - xstate_fault - : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) - : "memory"); - else - asm volatile("1:"XSAVE"\n\t" - "2:\n\t" - xstate_fault - : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) - : "memory"); - return err; -} - -/* - * This function is called only during boot time when x86 caps are not set - * up and alternative can not be used yet. - */ -static inline int xrstor_state_booting(struct xsave_struct *fx, u64 mask) -{ - u32 lmask = mask; - u32 hmask = mask >> 32; - int err = 0; - - WARN_ON(system_state != SYSTEM_BOOTING); - - if (boot_cpu_has(X86_FEATURE_XSAVES)) - asm volatile("1:"XRSTORS"\n\t" - "2:\n\t" - xstate_fault - : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) - : "memory"); - else - asm volatile("1:"XRSTOR"\n\t" - "2:\n\t" - xstate_fault - : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) - : "memory"); - return err; -} - -/* - * Save processor xstate to xsave area. - */ -static inline int xsave_state(struct xsave_struct *fx, u64 mask) -{ - u32 lmask = mask; - u32 hmask = mask >> 32; - int err = 0; - - /* - * If xsaves is enabled, xsaves replaces xsaveopt because - * it supports compact format and supervisor states in addition to - * modified optimization in xsaveopt. - * - * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave - * because xsaveopt supports modified optimization which is not - * supported by xsave. - * - * If none of xsaves and xsaveopt is enabled, use xsave. - */ - alternative_input_2( - "1:"XSAVE, - XSAVEOPT, - X86_FEATURE_XSAVEOPT, - XSAVES, - X86_FEATURE_XSAVES, - [fx] "D" (fx), "a" (lmask), "d" (hmask) : - "memory"); - asm volatile("2:\n\t" - xstate_fault - : "0" (0) - : "memory"); - - return err; -} - -/* - * Restore processor xstate from xsave area. - */ -static inline int xrstor_state(struct xsave_struct *fx, u64 mask) -{ - int err = 0; - u32 lmask = mask; - u32 hmask = mask >> 32; - - /* - * Use xrstors to restore context if it is enabled. xrstors supports - * compacted format of xsave area which is not supported by xrstor. - */ - alternative_input( - "1: " XRSTOR, - XRSTORS, - X86_FEATURE_XSAVES, - "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) - : "memory"); - - asm volatile("2:\n" - xstate_fault - : "0" (0) - : "memory"); - - return err; -} - -/* - * Save xstate context for old process during context switch. - */ -static inline void fpu_xsave(struct fpu *fpu) -{ - xsave_state(&fpu->state->xsave, -1); -} - -/* - * Restore xstate context for new process during context switch. - */ -static inline int fpu_xrstor_checking(struct xsave_struct *fx) -{ - return xrstor_state(fx, -1); -} - -/* - * Save xstate to user space xsave area. - * - * We don't use modified optimization because xrstor/xrstors might track - * a different application. - * - * We don't use compacted format xsave area for - * backward compatibility for old applications which don't understand - * compacted format of xsave area. - */ -static inline int xsave_user(struct xsave_struct __user *buf) -{ - int err; - - /* - * Clear the xsave header first, so that reserved fields are - * initialized to zero. - */ - err = __clear_user(&buf->xsave_hdr, sizeof(buf->xsave_hdr)); - if (unlikely(err)) - return -EFAULT; - - __asm__ __volatile__(ASM_STAC "\n" - "1:"XSAVE"\n" - "2: " ASM_CLAC "\n" - xstate_fault - : "D" (buf), "a" (-1), "d" (-1), "0" (0) - : "memory"); - return err; -} - -/* - * Restore xstate from user space xsave area. - */ -static inline int xrestore_user(struct xsave_struct __user *buf, u64 mask) -{ - int err = 0; - struct xsave_struct *xstate = ((__force struct xsave_struct *)buf); - u32 lmask = mask; - u32 hmask = mask >> 32; - - __asm__ __volatile__(ASM_STAC "\n" - "1:"XRSTOR"\n" - "2: " ASM_CLAC "\n" - xstate_fault - : "D" (xstate), "a" (lmask), "d" (hmask), "0" (0) - : "memory"); /* memory required? */ - return err; -} - -void *get_xsave_addr(struct xsave_struct *xsave, int xstate); -void setup_xstate_comp(void); - -#endif diff --git a/arch/x86/include/uapi/asm/e820.h b/arch/x86/include/uapi/asm/e820.h index 960a8a9dc..0f457e6ea 100644 --- a/arch/x86/include/uapi/asm/e820.h +++ b/arch/x86/include/uapi/asm/e820.h @@ -32,6 +32,7 @@ #define E820_ACPI 3 #define E820_NVS 4 #define E820_UNUSABLE 5 +#define E820_PMEM 7 /* * This is a non-standardized way to represent ADR or NVDIMM regions that diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h index ce6068dbc..f36d56bd7 100644 --- a/arch/x86/include/uapi/asm/hyperv.h +++ b/arch/x86/include/uapi/asm/hyperv.h @@ -108,6 +108,8 @@ #define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE (1 << 4) /* Support for a virtual guest idle state is available */ #define HV_X64_GUEST_IDLE_STATE_AVAILABLE (1 << 5) +/* Guest crash data handler available */ +#define HV_X64_GUEST_CRASH_MSR_AVAILABLE (1 << 10) /* * Implementation recommendations. Indicates which behaviors the hypervisor @@ -199,6 +201,17 @@ #define HV_X64_MSR_STIMER3_CONFIG 0x400000B6 #define HV_X64_MSR_STIMER3_COUNT 0x400000B7 +/* Hyper-V guest crash notification MSR's */ +#define HV_X64_MSR_CRASH_P0 0x40000100 +#define HV_X64_MSR_CRASH_P1 0x40000101 +#define HV_X64_MSR_CRASH_P2 0x40000102 +#define HV_X64_MSR_CRASH_P3 0x40000103 +#define HV_X64_MSR_CRASH_P4 0x40000104 +#define HV_X64_MSR_CRASH_CTL 0x40000105 +#define HV_X64_MSR_CRASH_CTL_NOTIFY (1ULL << 63) +#define HV_X64_MSR_CRASH_PARAMS \ + (1 + (HV_X64_MSR_CRASH_P4 - HV_X64_MSR_CRASH_P0)) + #define HV_X64_MSR_HYPERCALL_ENABLE 0x00000001 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT 12 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK \ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index d7dcef58a..cd54147cb 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -106,6 +106,8 @@ struct kvm_ioapic_state { #define KVM_IRQCHIP_IOAPIC 2 #define KVM_NR_IRQCHIPS 3 +#define KVM_RUN_X86_SMM (1 << 0) + /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */ @@ -281,6 +283,7 @@ struct kvm_reinject_control { #define KVM_VCPUEVENT_VALID_NMI_PENDING 0x00000001 #define KVM_VCPUEVENT_VALID_SIPI_VECTOR 0x00000002 #define KVM_VCPUEVENT_VALID_SHADOW 0x00000004 +#define KVM_VCPUEVENT_VALID_SMM 0x00000008 /* Interrupt shadow states */ #define KVM_X86_SHADOW_INT_MOV_SS 0x01 @@ -309,7 +312,13 @@ struct kvm_vcpu_events { } nmi; __u32 sipi_vector; __u32 flags; - __u32 reserved[10]; + struct { + __u8 smm; + __u8 pending; + __u8 smm_inside_nmi; + __u8 latched_init; + } smi; + __u32 reserved[9]; }; /* for KVM_GET/SET_DEBUGREGS */ @@ -345,4 +354,7 @@ struct kvm_xcrs { struct kvm_sync_regs { }; +#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) +#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) + #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/include/uapi/asm/msr.h b/arch/x86/include/uapi/asm/msr.h index 155e51048..c41f4fe25 100644 --- a/arch/x86/include/uapi/asm/msr.h +++ b/arch/x86/include/uapi/asm/msr.h @@ -1,8 +1,6 @@ #ifndef _UAPI_ASM_X86_MSR_H #define _UAPI_ASM_X86_MSR_H -#include <asm/msr-index.h> - #ifndef __ASSEMBLY__ #include <linux/types.h> diff --git a/arch/x86/include/uapi/asm/mtrr.h b/arch/x86/include/uapi/asm/mtrr.h index d0acb658c..7528dcf59 100644 --- a/arch/x86/include/uapi/asm/mtrr.h +++ b/arch/x86/include/uapi/asm/mtrr.h @@ -103,7 +103,7 @@ struct mtrr_state_type { #define MTRRIOC_GET_PAGE_ENTRY _IOWR(MTRR_IOCTL_BASE, 8, struct mtrr_gentry) #define MTRRIOC_KILL_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE, 9, struct mtrr_sentry) -/* These are the region types */ +/* MTRR memory types, which are defined in SDM */ #define MTRR_TYPE_UNCACHABLE 0 #define MTRR_TYPE_WRCOMB 1 /*#define MTRR_TYPE_ 2*/ @@ -113,5 +113,11 @@ struct mtrr_state_type { #define MTRR_TYPE_WRBACK 6 #define MTRR_NUM_TYPES 7 +/* + * Invalid MTRR memory type. mtrr_type_lookup() returns this value when + * MTRRs are disabled. Note, this value is allocated from the reserved + * values (0x7-0xff) of the MTRR memory types. + */ +#define MTRR_TYPE_INVALID 0xff #endif /* _UAPI_ASM_X86_MTRR_H */ diff --git a/arch/x86/include/uapi/asm/sigcontext.h b/arch/x86/include/uapi/asm/sigcontext.h index 16dc4e8a2..40836a9a7 100644 --- a/arch/x86/include/uapi/asm/sigcontext.h +++ b/arch/x86/include/uapi/asm/sigcontext.h @@ -25,7 +25,7 @@ struct _fpx_sw_bytes { __u32 extended_size; /* total size of the layout referred by * fpstate pointer in the sigcontext. */ - __u64 xstate_bv; + __u64 xfeatures; /* feature bit mask (including fp/sse/extended * state) that is present in the memory * layout. @@ -177,24 +177,9 @@ struct sigcontext { __u64 rip; __u64 eflags; /* RFLAGS */ __u16 cs; - - /* - * Prior to 2.5.64 ("[PATCH] x86-64 updates for 2.5.64-bk3"), - * Linux saved and restored fs and gs in these slots. This - * was counterproductive, as fsbase and gsbase were never - * saved, so arch_prctl was presumably unreliable. - * - * If these slots are ever needed for any other purpose, there - * is some risk that very old 64-bit binaries could get - * confused. I doubt that many such binaries still work, - * though, since the same patch in 2.5.64 also removed the - * 64-bit set_thread_area syscall, so it appears that there is - * no TLS API that works in both pre- and post-2.5.64 kernels. - */ - __u16 __pad2; /* Was gs. */ - __u16 __pad1; /* Was fs. */ - - __u16 ss; + __u16 gs; + __u16 fs; + __u16 __pad0; __u64 err; __u64 trapno; __u64 oldmask; @@ -209,8 +194,8 @@ struct sigcontext { #endif /* !__i386__ */ -struct _xsave_hdr { - __u64 xstate_bv; +struct _header { + __u64 xfeatures; __u64 reserved1[2]; __u64 reserved2[5]; }; @@ -228,7 +213,7 @@ struct _ymmh_state { */ struct _xstate { struct _fpstate fpstate; - struct _xsave_hdr xstate_hdr; + struct _header xstate_hdr; struct _ymmh_state ymmh; /* new processor state extensions go here */ }; diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 9bcd0b56c..0f15af41b 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -22,7 +22,7 @@ KASAN_SANITIZE_dumpstack_$(BITS).o := n CFLAGS_irq.o := -I$(src)/../include/asm/trace -obj-y := process_$(BITS).o signal.o entry_$(BITS).o +obj-y := process_$(BITS).o signal.o obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o obj-y += time.o ioport.o ldt.o dumpstack.o nmi.o obj-y += setup.o x86_init.o i8259.o irqinit.o jump_label.o @@ -31,9 +31,6 @@ obj-y += probe_roms.o obj-$(CONFIG_X86_32) += i386_ksyms_32.o obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o obj-$(CONFIG_X86_64) += mcount_64.o -obj-y += syscall_$(BITS).o vsyscall_gtod.o -obj-$(CONFIG_IA32_EMULATION) += syscall_32.o -obj-$(CONFIG_X86_VSYSCALL_EMULATION) += vsyscall_64.o vsyscall_emu_64.o obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o obj-$(CONFIG_SYSFS) += ksysfs.o obj-y += bootflag.o e820.o @@ -44,7 +41,7 @@ obj-y += pci-iommu_table.o obj-y += resource.o obj-y += process.o -obj-y += i387.o xsave.o +obj-y += fpu/ obj-y += ptrace.o obj-$(CONFIG_X86_32) += tls.o obj-$(CONFIG_IA32_EMULATION) += tls.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index bde7a2dc5..e49ee24da 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -31,12 +31,12 @@ #include <linux/module.h> #include <linux/dmi.h> #include <linux/irq.h> -#include <linux/irqdomain.h> #include <linux/slab.h> #include <linux/bootmem.h> #include <linux/ioport.h> #include <linux/pci.h> +#include <asm/irqdomain.h> #include <asm/pci_x86.h> #include <asm/pgtable.h> #include <asm/io_apic.h> @@ -400,57 +400,13 @@ static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger, return 0; } -static int mp_register_gsi(struct device *dev, u32 gsi, int trigger, - int polarity) -{ - int irq, node; - - if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC) - return gsi; - - trigger = trigger == ACPI_EDGE_SENSITIVE ? 0 : 1; - polarity = polarity == ACPI_ACTIVE_HIGH ? 0 : 1; - node = dev ? dev_to_node(dev) : NUMA_NO_NODE; - if (mp_set_gsi_attr(gsi, trigger, polarity, node)) { - pr_warn("Failed to set pin attr for GSI%d\n", gsi); - return -1; - } - - irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC); - if (irq < 0) - return irq; - - /* Don't set up the ACPI SCI because it's already set up */ - if (enable_update_mptable && acpi_gbl_FADT.sci_interrupt != gsi) - mp_config_acpi_gsi(dev, gsi, trigger, polarity); - - return irq; -} - -static void mp_unregister_gsi(u32 gsi) -{ - int irq; - - if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC) - return; - - irq = mp_map_gsi_to_irq(gsi, 0); - if (irq > 0) - mp_unmap_irq(irq); -} - -static struct irq_domain_ops acpi_irqdomain_ops = { - .map = mp_irqdomain_map, - .unmap = mp_irqdomain_unmap, -}; - static int __init acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end) { struct acpi_madt_io_apic *ioapic = NULL; struct ioapic_domain_cfg cfg = { .type = IOAPIC_DOMAIN_DYNAMIC, - .ops = &acpi_irqdomain_ops, + .ops = &mp_ioapic_irqdomain_ops, }; ioapic = (struct acpi_madt_io_apic *)header; @@ -652,7 +608,7 @@ static int acpi_register_gsi_pic(struct device *dev, u32 gsi, * Make sure all (legacy) PCI IRQs are set as level-triggered. */ if (trigger == ACPI_LEVEL_SENSITIVE) - eisa_set_level_irq(gsi); + elcr_set_level_irq(gsi); #endif return gsi; @@ -663,10 +619,21 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi, int trigger, int polarity) { int irq = gsi; - #ifdef CONFIG_X86_IO_APIC + int node; + struct irq_alloc_info info; + + node = dev ? dev_to_node(dev) : NUMA_NO_NODE; + trigger = trigger == ACPI_EDGE_SENSITIVE ? 0 : 1; + polarity = polarity == ACPI_ACTIVE_HIGH ? 0 : 1; + ioapic_set_alloc_attr(&info, node, trigger, polarity); + mutex_lock(&acpi_ioapic_lock); - irq = mp_register_gsi(dev, gsi, trigger, polarity); + irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info); + /* Don't set up the ACPI SCI because it's already set up */ + if (irq >= 0 && enable_update_mptable && + acpi_gbl_FADT.sci_interrupt != gsi) + mp_config_acpi_gsi(dev, gsi, trigger, polarity); mutex_unlock(&acpi_ioapic_lock); #endif @@ -676,8 +643,12 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi, static void acpi_unregister_gsi_ioapic(u32 gsi) { #ifdef CONFIG_X86_IO_APIC + int irq; + mutex_lock(&acpi_ioapic_lock); - mp_unregister_gsi(gsi); + irq = mp_map_gsi_to_irq(gsi, 0, NULL); + if (irq > 0) + mp_unmap_irq(irq); mutex_unlock(&acpi_ioapic_lock); #endif } @@ -786,7 +757,7 @@ int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base) u64 addr; struct ioapic_domain_cfg cfg = { .type = IOAPIC_DOMAIN_DYNAMIC, - .ops = &acpi_irqdomain_ops, + .ops = &mp_ioapic_irqdomain_ops, }; ioapic_id = acpi_get_ioapic_id(handle, gsi_base, &addr); @@ -1432,42 +1403,6 @@ static struct dmi_system_id __initdata acpi_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 360"), }, }, - /* ThinkPad Edge 11 (AMD) */ - { - .callback = dmi_ignore_irq0_timer_override, - .ident = "ThinkPad Edge", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "254523U"), - }, - }, - /* ThinkPad Edge 13 (AMD) */ - { - .callback = dmi_ignore_irq0_timer_override, - .ident = "ThinkPad Edge", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "022120U"), - }, - }, - /* ThinkPad Edge 14 (AMD) */ - { - .callback = dmi_ignore_irq0_timer_override, - .ident = "ThinkPad Edge", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "019923U"), - }, - }, - /* ThinkPad Edge 15 (AMD) */ - { - .callback = dmi_ignore_irq0_timer_override, - .ident = "ThinkPad Edge", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "030222U"), - }, - }, {} }; diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S index 665c6b7d2..0c26b1b44 100644 --- a/arch/x86/kernel/acpi/wakeup_32.S +++ b/arch/x86/kernel/acpi/wakeup_32.S @@ -12,11 +12,13 @@ ENTRY(wakeup_pmode_return) wakeup_pmode_return: movw $__KERNEL_DS, %ax movw %ax, %ss - movw %ax, %ds - movw %ax, %es movw %ax, %fs movw %ax, %gs + movw $__USER_DS, %ax + movw %ax, %ds + movw %ax, %es + # reload the gdt, as we need the full 32 bit address lidt saved_idt lldt saved_ldt diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index ae693b51e..8c35df468 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -62,7 +62,7 @@ ENTRY(do_suspend_lowlevel) pushfq popq pt_regs_flags(%rax) - movq $resume_point, saved_rip(%rip) + movq $.Lresume_point, saved_rip(%rip) movq %rsp, saved_rsp movq %rbp, saved_rbp @@ -75,10 +75,10 @@ ENTRY(do_suspend_lowlevel) xorl %eax, %eax call x86_acpi_enter_sleep_state /* in case something went wrong, restore the machine status and go on */ - jmp resume_point + jmp .Lresume_point .align 4 -resume_point: +.Lresume_point: /* We don't restore %rax, it must be 0 anyway */ movq $saved_context, %rax movq saved_context_cr4(%rax), %rbx diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index aef653193..c42827eb8 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -21,6 +21,10 @@ #include <asm/io.h> #include <asm/fixmap.h> +int __read_mostly alternatives_patched; + +EXPORT_SYMBOL_GPL(alternatives_patched); + #define MAX_PATCH_LEN (255-1) static int __initdata_or_module debug_alternative; @@ -227,6 +231,15 @@ void __init arch_init_ideal_nops(void) #endif } break; + + case X86_VENDOR_AMD: + if (boot_cpu_data.x86 > 0xf) { + ideal_nops = p6_nops; + return; + } + + /* fall through */ + default: #ifdef CONFIG_X86_64 ideal_nops = k8_nops; @@ -627,6 +640,7 @@ void __init alternative_instructions(void) apply_paravirt(__parainstructions, __parainstructions_end); restart_nmi(); + alternatives_patched = 1; } /** diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 5caed1dd7..29fa475ec 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -89,9 +89,7 @@ int amd_cache_northbridges(void) next_northbridge(link, amd_nb_link_ids); } - /* GART present only on Fam15h upto model 0fh */ - if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 || - (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10)) + if (amd_gart_present()) amd_northbridges.flags |= AMD_NB_GART; /* diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index 6a7c23ff2..ede92c336 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -171,10 +171,6 @@ static int __init apbt_clockevent_register(void) static void apbt_setup_irq(struct apbt_dev *adev) { - /* timer0 irq has been setup early */ - if (adev->irq == 0) - return; - irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT); irq_set_affinity(adev->irq, cpumask_of(adev->cpu)); } diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 76164e173..6e85f7136 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -262,6 +262,9 @@ void __init early_gart_iommu_check(void) u64 aper_base = 0, last_aper_base = 0; int aper_enabled = 0, last_aper_enabled = 0, last_valid = 0; + if (!amd_gart_present()) + return; + if (!early_pci_allowed()) return; @@ -355,6 +358,9 @@ int __init gart_iommu_hole_init(void) int fix, slot, valid_agp = 0; int i, node; + if (!amd_gart_present()) + return -ENODEV; + if (gart_iommu_aperture_disabled || !fix_aperture || !early_pci_allowed()) return -ENODEV; @@ -452,7 +458,7 @@ out: force_iommu || valid_agp || fallback_aper_force) { - pr_info("Your BIOS doesn't leave a aperture memory hole\n"); + pr_info("Your BIOS doesn't leave an aperture memory hole\n"); pr_info("Please enable the IOMMU option in the BIOS setup\n"); pr_info("This costs you %dMB of RAM\n", 32 << fallback_aper_order); diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index dcb52850a..cde732c1b 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1424,7 +1424,7 @@ static inline void __x2apic_disable(void) { u64 msr; - if (cpu_has_apic) + if (!cpu_has_apic) return; rdmsrl(MSR_IA32_APICBASE, msr); @@ -1483,10 +1483,13 @@ void x2apic_setup(void) static __init void x2apic_disable(void) { - u32 x2apic_id; + u32 x2apic_id, state = x2apic_state; - if (x2apic_state != X2APIC_ON) - goto out; + x2apic_mode = 0; + x2apic_state = X2APIC_DISABLED; + + if (state != X2APIC_ON) + return; x2apic_id = read_apic_id(); if (x2apic_id >= 255) @@ -1494,9 +1497,6 @@ static __init void x2apic_disable(void) __x2apic_disable(); register_lapic_address(mp_lapic_addr); -out: - x2apic_state = X2APIC_DISABLED; - x2apic_mode = 0; } static __init void x2apic_enable(void) diff --git a/arch/x86/kernel/apic/htirq.c b/arch/x86/kernel/apic/htirq.c index 816f36e97..ae50d3454 100644 --- a/arch/x86/kernel/apic/htirq.c +++ b/arch/x86/kernel/apic/htirq.c @@ -3,6 +3,8 @@ * * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo * Moved from arch/x86/kernel/apic/io_apic.c. + * Jiang Liu <jiang.liu@linux.intel.com> + * Add support of hierarchical irqdomain * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -14,78 +16,112 @@ #include <linux/device.h> #include <linux/pci.h> #include <linux/htirq.h> +#include <asm/irqdomain.h> #include <asm/hw_irq.h> #include <asm/apic.h> #include <asm/hypertransport.h> +static struct irq_domain *htirq_domain; + /* * Hypertransport interrupt support */ -static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector) -{ - struct ht_irq_msg msg; - - fetch_ht_irq_msg(irq, &msg); - - msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK | HT_IRQ_LOW_DEST_ID_MASK); - msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK); - - msg.address_lo |= HT_IRQ_LOW_VECTOR(vector) | HT_IRQ_LOW_DEST_ID(dest); - msg.address_hi |= HT_IRQ_HIGH_DEST_ID(dest); - - write_ht_irq_msg(irq, &msg); -} - static int ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { - struct irq_cfg *cfg = irqd_cfg(data); - unsigned int dest; + struct irq_data *parent = data->parent_data; int ret; - ret = apic_set_affinity(data, mask, &dest); - if (ret) - return ret; - - target_ht_irq(data->irq, dest, cfg->vector); - return IRQ_SET_MASK_OK_NOCOPY; + ret = parent->chip->irq_set_affinity(parent, mask, force); + if (ret >= 0) { + struct ht_irq_msg msg; + struct irq_cfg *cfg = irqd_cfg(data); + + fetch_ht_irq_msg(data->irq, &msg); + msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK | + HT_IRQ_LOW_DEST_ID_MASK); + msg.address_lo |= HT_IRQ_LOW_VECTOR(cfg->vector) | + HT_IRQ_LOW_DEST_ID(cfg->dest_apicid); + msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK); + msg.address_hi |= HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid); + write_ht_irq_msg(data->irq, &msg); + } + + return ret; } static struct irq_chip ht_irq_chip = { .name = "PCI-HT", .irq_mask = mask_ht_irq, .irq_unmask = unmask_ht_irq, - .irq_ack = apic_ack_edge, + .irq_ack = irq_chip_ack_parent, .irq_set_affinity = ht_set_affinity, - .irq_retrigger = apic_retrigger_irq, + .irq_retrigger = irq_chip_retrigger_hierarchy, .flags = IRQCHIP_SKIP_SET_WAKE, }; -int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) +static int htirq_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) { - struct irq_cfg *cfg; - struct ht_irq_msg msg; - unsigned dest; - int err; + struct ht_irq_cfg *ht_cfg; + struct irq_alloc_info *info = arg; + struct pci_dev *dev; + irq_hw_number_t hwirq; + int ret; - if (disable_apic) - return -ENXIO; + if (nr_irqs > 1 || !info) + return -EINVAL; - cfg = irq_cfg(irq); - err = assign_irq_vector(irq, cfg, apic->target_cpus()); - if (err) - return err; + dev = info->ht_dev; + hwirq = (info->ht_idx & 0xFF) | + PCI_DEVID(dev->bus->number, dev->devfn) << 8 | + (pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 24; + if (irq_find_mapping(domain, hwirq) > 0) + return -EEXIST; - err = apic->cpu_mask_to_apicid_and(cfg->domain, - apic->target_cpus(), &dest); - if (err) - return err; + ht_cfg = kmalloc(sizeof(*ht_cfg), GFP_KERNEL); + if (!ht_cfg) + return -ENOMEM; - msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest); + ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info); + if (ret < 0) { + kfree(ht_cfg); + return ret; + } + + /* Initialize msg to a value that will never match the first write. */ + ht_cfg->msg.address_lo = 0xffffffff; + ht_cfg->msg.address_hi = 0xffffffff; + ht_cfg->dev = info->ht_dev; + ht_cfg->update = info->ht_update; + ht_cfg->pos = info->ht_pos; + ht_cfg->idx = 0x10 + (info->ht_idx * 2); + irq_domain_set_info(domain, virq, hwirq, &ht_irq_chip, ht_cfg, + handle_edge_irq, ht_cfg, "edge"); + + return 0; +} + +static void htirq_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq); + + BUG_ON(nr_irqs != 1); + kfree(irq_data->chip_data); + irq_domain_free_irqs_top(domain, virq, nr_irqs); +} +static void htirq_domain_activate(struct irq_domain *domain, + struct irq_data *irq_data) +{ + struct ht_irq_msg msg; + struct irq_cfg *cfg = irqd_cfg(irq_data); + + msg.address_hi = HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid); msg.address_lo = HT_IRQ_LOW_BASE | - HT_IRQ_LOW_DEST_ID(dest) | + HT_IRQ_LOW_DEST_ID(cfg->dest_apicid) | HT_IRQ_LOW_VECTOR(cfg->vector) | ((apic->irq_dest_mode == 0) ? HT_IRQ_LOW_DM_PHYSICAL : @@ -95,13 +131,56 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) HT_IRQ_LOW_MT_FIXED : HT_IRQ_LOW_MT_ARBITRATED) | HT_IRQ_LOW_IRQ_MASKED; + write_ht_irq_msg(irq_data->irq, &msg); +} - write_ht_irq_msg(irq, &msg); +static void htirq_domain_deactivate(struct irq_domain *domain, + struct irq_data *irq_data) +{ + struct ht_irq_msg msg; - irq_set_chip_and_handler_name(irq, &ht_irq_chip, - handle_edge_irq, "edge"); + memset(&msg, 0, sizeof(msg)); + write_ht_irq_msg(irq_data->irq, &msg); +} - dev_dbg(&dev->dev, "irq %d for HT\n", irq); +static const struct irq_domain_ops htirq_domain_ops = { + .alloc = htirq_domain_alloc, + .free = htirq_domain_free, + .activate = htirq_domain_activate, + .deactivate = htirq_domain_deactivate, +}; - return 0; +void arch_init_htirq_domain(struct irq_domain *parent) +{ + if (disable_apic) + return; + + htirq_domain = irq_domain_add_tree(NULL, &htirq_domain_ops, NULL); + if (!htirq_domain) + pr_warn("failed to initialize irqdomain for HTIRQ.\n"); + else + htirq_domain->parent = parent; +} + +int arch_setup_ht_irq(int idx, int pos, struct pci_dev *dev, + ht_irq_update_t *update) +{ + struct irq_alloc_info info; + + if (!htirq_domain) + return -ENOSYS; + + init_irq_alloc_info(&info, NULL); + info.ht_idx = idx; + info.ht_pos = pos; + info.ht_dev = dev; + info.ht_update = update; + + return irq_domain_alloc_irqs(htirq_domain, 1, dev_to_node(&dev->dev), + &info); +} + +void arch_teardown_ht_irq(unsigned int irq) +{ + irq_domain_free_irqs(irq, 1); } diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index a72075cf2..206052e55 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -18,6 +18,16 @@ * and Rolf G. Tews * for testing these extensively * Paul Diefenbaugh : Added full ACPI support + * + * Historical information which is worth to be preserved: + * + * - SiS APIC rmw bug: + * + * We used to have a workaround for a bug in SiS chips which + * required to rewrite the index register for a read-modify-write + * operation as the chip lost the index information which was + * setup for the read already. We cache the data now, so that + * workaround has been removed. */ #include <linux/mm.h> @@ -31,13 +41,13 @@ #include <linux/acpi.h> #include <linux/module.h> #include <linux/syscore_ops.h> -#include <linux/irqdomain.h> #include <linux/freezer.h> #include <linux/kthread.h> #include <linux/jiffies.h> /* time_after() */ #include <linux/slab.h> #include <linux/bootmem.h> +#include <asm/irqdomain.h> #include <asm/idle.h> #include <asm/io.h> #include <asm/smp.h> @@ -63,27 +73,31 @@ #define for_each_ioapic_pin(idx, pin) \ for_each_ioapic((idx)) \ for_each_pin((idx), (pin)) - #define for_each_irq_pin(entry, head) \ list_for_each_entry(entry, &head, list) -/* - * Is the SiS APIC rmw bug present ? - * -1 = don't know, 0 = no, 1 = yes - */ -int sis_apic_bug = -1; - static DEFINE_RAW_SPINLOCK(ioapic_lock); static DEFINE_MUTEX(ioapic_mutex); static unsigned int ioapic_dynirq_base; static int ioapic_initialized; -struct mp_pin_info { +struct irq_pin_list { + struct list_head list; + int apic, pin; +}; + +struct mp_chip_data { + struct list_head irq_2_pin; + struct IO_APIC_route_entry entry; int trigger; int polarity; - int node; - int set; u32 count; + bool isa_irq; +}; + +struct mp_ioapic_gsi { + u32 gsi_base; + u32 gsi_end; }; static struct ioapic { @@ -101,7 +115,6 @@ static struct ioapic { struct mp_ioapic_gsi gsi_config; struct ioapic_domain_cfg irqdomain_cfg; struct irq_domain *irqdomain; - struct mp_pin_info *pin_info; struct resource *iomem_res; } ioapics[MAX_IO_APICS]; @@ -117,7 +130,7 @@ unsigned int mpc_ioapic_addr(int ioapic_idx) return ioapics[ioapic_idx].mp_config.apicaddr; } -struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic_idx) +static inline struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic_idx) { return &ioapics[ioapic_idx].gsi_config; } @@ -129,11 +142,16 @@ static inline int mp_ioapic_pin_count(int ioapic) return gsi_cfg->gsi_end - gsi_cfg->gsi_base + 1; } -u32 mp_pin_to_gsi(int ioapic, int pin) +static inline u32 mp_pin_to_gsi(int ioapic, int pin) { return mp_ioapic_gsi_routing(ioapic)->gsi_base + pin; } +static inline bool mp_is_legacy_irq(int irq) +{ + return irq >= 0 && irq < nr_legacy_irqs(); +} + /* * Initialize all legacy IRQs and all pins on the first IOAPIC * if we have legacy interrupt controller. Kernel boot option "pirq=" @@ -144,12 +162,7 @@ static inline int mp_init_irq_at_boot(int ioapic, int irq) if (!nr_legacy_irqs()) return 0; - return ioapic == 0 || (irq >= 0 && irq < nr_legacy_irqs()); -} - -static inline struct mp_pin_info *mp_pin_info(int ioapic_idx, int pin) -{ - return ioapics[ioapic_idx].pin_info + pin; + return ioapic == 0 || mp_is_legacy_irq(irq); } static inline struct irq_domain *mp_ioapic_irqdomain(int ioapic) @@ -216,16 +229,6 @@ void mp_save_irq(struct mpc_intsrc *m) panic("Max # of irq sources exceeded!!\n"); } -struct irq_pin_list { - struct list_head list; - int apic, pin; -}; - -static struct irq_pin_list *alloc_irq_pin_list(int node) -{ - return kzalloc_node(sizeof(struct irq_pin_list), GFP_KERNEL, node); -} - static void alloc_ioapic_saved_registers(int idx) { size_t size; @@ -247,8 +250,7 @@ static void free_ioapic_saved_registers(int idx) int __init arch_early_ioapic_init(void) { - struct irq_cfg *cfg; - int i, node = cpu_to_node(0); + int i; if (!nr_legacy_irqs()) io_apic_irqs = ~0UL; @@ -256,16 +258,6 @@ int __init arch_early_ioapic_init(void) for_each_ioapic(i) alloc_ioapic_saved_registers(i); - /* - * For legacy IRQ's, start with assigning irq0 to irq15 to - * IRQ0_VECTOR to IRQ15_VECTOR for all cpu's. - */ - for (i = 0; i < nr_legacy_irqs(); i++) { - cfg = alloc_irq_and_cfg_at(i, node); - cfg->vector = IRQ0_VECTOR + i; - cpumask_setall(cfg->domain); - } - return 0; } @@ -283,7 +275,7 @@ static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx) + (mpc_ioapic_addr(idx) & ~PAGE_MASK); } -void io_apic_eoi(unsigned int apic, unsigned int vector) +static inline void io_apic_eoi(unsigned int apic, unsigned int vector) { struct io_apic __iomem *io_apic = io_apic_base(apic); writel(vector, &io_apic->eoi); @@ -296,7 +288,8 @@ unsigned int native_io_apic_read(unsigned int apic, unsigned int reg) return readl(&io_apic->data); } -void native_io_apic_write(unsigned int apic, unsigned int reg, unsigned int value) +static void io_apic_write(unsigned int apic, unsigned int reg, + unsigned int value) { struct io_apic __iomem *io_apic = io_apic_base(apic); @@ -304,21 +297,6 @@ void native_io_apic_write(unsigned int apic, unsigned int reg, unsigned int valu writel(value, &io_apic->data); } -/* - * Re-write a value: to be used for read-modify-write - * cycles where the read already set up the index register. - * - * Older SiS APIC requires we rewrite the index register - */ -void native_io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value) -{ - struct io_apic __iomem *io_apic = io_apic_base(apic); - - if (sis_apic_bug) - writel(reg, &io_apic->index); - writel(value, &io_apic->data); -} - union entry_union { struct { u32 w1, w2; }; struct IO_APIC_route_entry entry; @@ -378,7 +356,7 @@ static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e) static void ioapic_mask_entry(int apic, int pin) { unsigned long flags; - union entry_union eu = { .entry.mask = 1 }; + union entry_union eu = { .entry.mask = IOAPIC_MASKED }; raw_spin_lock_irqsave(&ioapic_lock, flags); io_apic_write(apic, 0x10 + 2*pin, eu.w1); @@ -391,16 +369,17 @@ static void ioapic_mask_entry(int apic, int pin) * shared ISA-space IRQs, so we have to support them. We are super * fast in the common case, and fast for shared ISA-space IRQs. */ -static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin) +static int __add_pin_to_irq_node(struct mp_chip_data *data, + int node, int apic, int pin) { struct irq_pin_list *entry; /* don't allow duplicates */ - for_each_irq_pin(entry, cfg->irq_2_pin) + for_each_irq_pin(entry, data->irq_2_pin) if (entry->apic == apic && entry->pin == pin) return 0; - entry = alloc_irq_pin_list(node); + entry = kzalloc_node(sizeof(struct irq_pin_list), GFP_ATOMIC, node); if (!entry) { pr_err("can not alloc irq_pin_list (%d,%d,%d)\n", node, apic, pin); @@ -408,16 +387,16 @@ static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pi } entry->apic = apic; entry->pin = pin; + list_add_tail(&entry->list, &data->irq_2_pin); - list_add_tail(&entry->list, &cfg->irq_2_pin); return 0; } -static void __remove_pin_from_irq(struct irq_cfg *cfg, int apic, int pin) +static void __remove_pin_from_irq(struct mp_chip_data *data, int apic, int pin) { struct irq_pin_list *tmp, *entry; - list_for_each_entry_safe(entry, tmp, &cfg->irq_2_pin, list) + list_for_each_entry_safe(entry, tmp, &data->irq_2_pin, list) if (entry->apic == apic && entry->pin == pin) { list_del(&entry->list); kfree(entry); @@ -425,22 +404,23 @@ static void __remove_pin_from_irq(struct irq_cfg *cfg, int apic, int pin) } } -static void add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin) +static void add_pin_to_irq_node(struct mp_chip_data *data, + int node, int apic, int pin) { - if (__add_pin_to_irq_node(cfg, node, apic, pin)) + if (__add_pin_to_irq_node(data, node, apic, pin)) panic("IO-APIC: failed to add irq-pin. Can not proceed\n"); } /* * Reroute an IRQ to a different pin. */ -static void __init replace_pin_at_irq_node(struct irq_cfg *cfg, int node, +static void __init replace_pin_at_irq_node(struct mp_chip_data *data, int node, int oldapic, int oldpin, int newapic, int newpin) { struct irq_pin_list *entry; - for_each_irq_pin(entry, cfg->irq_2_pin) { + for_each_irq_pin(entry, data->irq_2_pin) { if (entry->apic == oldapic && entry->pin == oldpin) { entry->apic = newapic; entry->pin = newpin; @@ -450,32 +430,26 @@ static void __init replace_pin_at_irq_node(struct irq_cfg *cfg, int node, } /* old apic/pin didn't exist, so just add new ones */ - add_pin_to_irq_node(cfg, node, newapic, newpin); + add_pin_to_irq_node(data, node, newapic, newpin); } -static void __io_apic_modify_irq(struct irq_pin_list *entry, - int mask_and, int mask_or, - void (*final)(struct irq_pin_list *entry)) -{ - unsigned int reg, pin; - - pin = entry->pin; - reg = io_apic_read(entry->apic, 0x10 + pin * 2); - reg &= mask_and; - reg |= mask_or; - io_apic_modify(entry->apic, 0x10 + pin * 2, reg); - if (final) - final(entry); -} - -static void io_apic_modify_irq(struct irq_cfg *cfg, +static void io_apic_modify_irq(struct mp_chip_data *data, int mask_and, int mask_or, void (*final)(struct irq_pin_list *entry)) { + union entry_union eu; struct irq_pin_list *entry; - for_each_irq_pin(entry, cfg->irq_2_pin) - __io_apic_modify_irq(entry, mask_and, mask_or, final); + eu.entry = data->entry; + eu.w1 &= mask_and; + eu.w1 |= mask_or; + data->entry = eu.entry; + + for_each_irq_pin(entry, data->irq_2_pin) { + io_apic_write(entry->apic, 0x10 + 2 * entry->pin, eu.w1); + if (final) + final(entry); + } } static void io_apic_sync(struct irq_pin_list *entry) @@ -490,39 +464,31 @@ static void io_apic_sync(struct irq_pin_list *entry) readl(&io_apic->data); } -static void mask_ioapic(struct irq_cfg *cfg) +static void mask_ioapic_irq(struct irq_data *irq_data) { + struct mp_chip_data *data = irq_data->chip_data; unsigned long flags; raw_spin_lock_irqsave(&ioapic_lock, flags); - io_apic_modify_irq(cfg, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync); + io_apic_modify_irq(data, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync); raw_spin_unlock_irqrestore(&ioapic_lock, flags); } -static void mask_ioapic_irq(struct irq_data *data) -{ - mask_ioapic(irqd_cfg(data)); -} - -static void __unmask_ioapic(struct irq_cfg *cfg) +static void __unmask_ioapic(struct mp_chip_data *data) { - io_apic_modify_irq(cfg, ~IO_APIC_REDIR_MASKED, 0, NULL); + io_apic_modify_irq(data, ~IO_APIC_REDIR_MASKED, 0, NULL); } -static void unmask_ioapic(struct irq_cfg *cfg) +static void unmask_ioapic_irq(struct irq_data *irq_data) { + struct mp_chip_data *data = irq_data->chip_data; unsigned long flags; raw_spin_lock_irqsave(&ioapic_lock, flags); - __unmask_ioapic(cfg); + __unmask_ioapic(data); raw_spin_unlock_irqrestore(&ioapic_lock, flags); } -static void unmask_ioapic_irq(struct irq_data *data) -{ - unmask_ioapic(irqd_cfg(data)); -} - /* * IO-APIC versions below 0x20 don't support EOI register. * For the record, here is the information about various versions: @@ -539,7 +505,7 @@ static void unmask_ioapic_irq(struct irq_data *data) * Otherwise, we simulate the EOI message manually by changing the trigger * mode to edge and then back to level, with RTE being masked during this. */ -void native_eoi_ioapic_pin(int apic, int pin, int vector) +static void __eoi_ioapic_pin(int apic, int pin, int vector) { if (mpc_ioapic_ver(apic) >= 0x20) { io_apic_eoi(apic, vector); @@ -551,7 +517,7 @@ void native_eoi_ioapic_pin(int apic, int pin, int vector) /* * Mask the entry and change the trigger mode to edge. */ - entry1.mask = 1; + entry1.mask = IOAPIC_MASKED; entry1.trigger = IOAPIC_EDGE; __ioapic_write_entry(apic, pin, entry1); @@ -563,15 +529,14 @@ void native_eoi_ioapic_pin(int apic, int pin, int vector) } } -void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg) +void eoi_ioapic_pin(int vector, struct mp_chip_data *data) { - struct irq_pin_list *entry; unsigned long flags; + struct irq_pin_list *entry; raw_spin_lock_irqsave(&ioapic_lock, flags); - for_each_irq_pin(entry, cfg->irq_2_pin) - x86_io_apic_ops.eoi_ioapic_pin(entry->apic, entry->pin, - cfg->vector); + for_each_irq_pin(entry, data->irq_2_pin) + __eoi_ioapic_pin(entry->apic, entry->pin, vector); raw_spin_unlock_irqrestore(&ioapic_lock, flags); } @@ -588,8 +553,8 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) * Make sure the entry is masked and re-read the contents to check * if it is a level triggered pin and if the remote-IRR is set. */ - if (!entry.mask) { - entry.mask = 1; + if (entry.mask == IOAPIC_UNMASKED) { + entry.mask = IOAPIC_MASKED; ioapic_write_entry(apic, pin, entry); entry = ioapic_read_entry(apic, pin); } @@ -602,13 +567,12 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) * doesn't clear the remote-IRR if the trigger mode is not * set to level. */ - if (!entry.trigger) { + if (entry.trigger == IOAPIC_EDGE) { entry.trigger = IOAPIC_LEVEL; ioapic_write_entry(apic, pin, entry); } - raw_spin_lock_irqsave(&ioapic_lock, flags); - x86_io_apic_ops.eoi_ioapic_pin(apic, pin, entry.vector); + __eoi_ioapic_pin(apic, pin, entry.vector); raw_spin_unlock_irqrestore(&ioapic_lock, flags); } @@ -706,8 +670,8 @@ void mask_ioapic_entries(void) struct IO_APIC_route_entry entry; entry = ioapics[apic].saved_registers[pin]; - if (!entry.mask) { - entry.mask = 1; + if (entry.mask == IOAPIC_UNMASKED) { + entry.mask = IOAPIC_MASKED; ioapic_write_entry(apic, pin, entry); } } @@ -809,11 +773,11 @@ static int EISA_ELCR(unsigned int irq) #endif -/* ISA interrupts are always polarity zero edge triggered, +/* ISA interrupts are always active high edge triggered, * when listed as conforming in the MP table. */ -#define default_ISA_trigger(idx) (0) -#define default_ISA_polarity(idx) (0) +#define default_ISA_trigger(idx) (IOAPIC_EDGE) +#define default_ISA_polarity(idx) (IOAPIC_POL_HIGH) /* EISA interrupts are always polarity zero and can be edge or level * trigger depending on the ELCR value. If an interrupt is listed as @@ -823,53 +787,55 @@ static int EISA_ELCR(unsigned int irq) #define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].srcbusirq)) #define default_EISA_polarity(idx) default_ISA_polarity(idx) -/* PCI interrupts are always polarity one level triggered, +/* PCI interrupts are always active low level triggered, * when listed as conforming in the MP table. */ -#define default_PCI_trigger(idx) (1) -#define default_PCI_polarity(idx) (1) +#define default_PCI_trigger(idx) (IOAPIC_LEVEL) +#define default_PCI_polarity(idx) (IOAPIC_POL_LOW) static int irq_polarity(int idx) { int bus = mp_irqs[idx].srcbus; - int polarity; /* * Determine IRQ line polarity (high active or low active): */ - switch (mp_irqs[idx].irqflag & 3) - { - case 0: /* conforms, ie. bus-type dependent polarity */ - 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; - break; - } - case 2: /* reserved */ - { - pr_warn("broken BIOS!!\n"); - polarity = 1; - break; - } - case 3: /* low active */ - { - polarity = 1; - break; - } - default: /* invalid */ - { - pr_warn("broken BIOS!!\n"); - polarity = 1; - break; - } + switch (mp_irqs[idx].irqflag & 0x03) { + case 0: + /* conforms to spec, ie. bus-type dependent polarity */ + if (test_bit(bus, mp_bus_not_pci)) + return default_ISA_polarity(idx); + else + return default_PCI_polarity(idx); + case 1: + return IOAPIC_POL_HIGH; + case 2: + pr_warn("IOAPIC: Invalid polarity: 2, defaulting to low\n"); + case 3: + default: /* Pointless default required due to do gcc stupidity */ + return IOAPIC_POL_LOW; + } +} + +#ifdef CONFIG_EISA +static int eisa_irq_trigger(int idx, int bus, int trigger) +{ + switch (mp_bus_id_to_type[bus]) { + case MP_BUS_PCI: + case MP_BUS_ISA: + return trigger; + case MP_BUS_EISA: + return default_EISA_trigger(idx); } - return polarity; + pr_warn("IOAPIC: Invalid srcbus: %d defaulting to level\n", bus); + return IOAPIC_LEVEL; +} +#else +static inline int eisa_irq_trigger(int idx, int bus, int trigger) +{ + return trigger; } +#endif static int irq_trigger(int idx) { @@ -879,153 +845,227 @@ static int irq_trigger(int idx) /* * Determine IRQ trigger mode (edge or level sensitive): */ - switch ((mp_irqs[idx].irqflag>>2) & 3) - { - case 0: /* conforms, ie. bus-type dependent */ - if (test_bit(bus, mp_bus_not_pci)) - trigger = default_ISA_trigger(idx); - else - trigger = default_PCI_trigger(idx); -#ifdef CONFIG_EISA - switch (mp_bus_id_to_type[bus]) { - case MP_BUS_ISA: /* ISA pin */ - { - /* set before the switch */ - break; - } - case MP_BUS_EISA: /* EISA pin */ - { - trigger = default_EISA_trigger(idx); - break; - } - case MP_BUS_PCI: /* PCI pin */ - { - /* set before the switch */ - break; - } - default: - { - pr_warn("broken BIOS!!\n"); - trigger = 1; - break; - } - } + switch ((mp_irqs[idx].irqflag >> 2) & 0x03) { + case 0: + /* conforms to spec, ie. bus-type dependent trigger mode */ + if (test_bit(bus, mp_bus_not_pci)) + trigger = default_ISA_trigger(idx); + else + trigger = default_PCI_trigger(idx); + /* Take EISA into account */ + return eisa_irq_trigger(idx, bus, trigger); + case 1: + return IOAPIC_EDGE; + case 2: + pr_warn("IOAPIC: Invalid trigger mode 2 defaulting to level\n"); + case 3: + default: /* Pointless default required due to do gcc stupidity */ + return IOAPIC_LEVEL; + } +} + +void ioapic_set_alloc_attr(struct irq_alloc_info *info, int node, + int trigger, int polarity) +{ + init_irq_alloc_info(info, NULL); + info->type = X86_IRQ_ALLOC_TYPE_IOAPIC; + info->ioapic_node = node; + info->ioapic_trigger = trigger; + info->ioapic_polarity = polarity; + info->ioapic_valid = 1; +} + +#ifndef CONFIG_ACPI +int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity); #endif - break; - case 1: /* edge */ - { - trigger = 0; - break; - } - case 2: /* reserved */ - { - pr_warn("broken BIOS!!\n"); - trigger = 1; - break; - } - case 3: /* level */ - { - trigger = 1; - break; - } - default: /* invalid */ - { - pr_warn("broken BIOS!!\n"); - trigger = 0; - break; + +static void ioapic_copy_alloc_attr(struct irq_alloc_info *dst, + struct irq_alloc_info *src, + u32 gsi, int ioapic_idx, int pin) +{ + int trigger, polarity; + + copy_irq_alloc_info(dst, src); + dst->type = X86_IRQ_ALLOC_TYPE_IOAPIC; + dst->ioapic_id = mpc_ioapic_id(ioapic_idx); + dst->ioapic_pin = pin; + dst->ioapic_valid = 1; + if (src && src->ioapic_valid) { + dst->ioapic_node = src->ioapic_node; + dst->ioapic_trigger = src->ioapic_trigger; + dst->ioapic_polarity = src->ioapic_polarity; + } else { + dst->ioapic_node = NUMA_NO_NODE; + if (acpi_get_override_irq(gsi, &trigger, &polarity) >= 0) { + dst->ioapic_trigger = trigger; + dst->ioapic_polarity = polarity; + } else { + /* + * PCI interrupts are always active low level + * triggered. + */ + dst->ioapic_trigger = IOAPIC_LEVEL; + dst->ioapic_polarity = IOAPIC_POL_LOW; } } - return trigger; } -static int alloc_irq_from_domain(struct irq_domain *domain, u32 gsi, int pin) +static int ioapic_alloc_attr_node(struct irq_alloc_info *info) { + return (info && info->ioapic_valid) ? info->ioapic_node : NUMA_NO_NODE; +} + +static void mp_register_handler(unsigned int irq, unsigned long trigger) +{ + irq_flow_handler_t hdl; + bool fasteoi; + + if (trigger) { + irq_set_status_flags(irq, IRQ_LEVEL); + fasteoi = true; + } else { + irq_clear_status_flags(irq, IRQ_LEVEL); + fasteoi = false; + } + + hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq; + __irq_set_handler(irq, hdl, 0, fasteoi ? "fasteoi" : "edge"); +} + +static bool mp_check_pin_attr(int irq, struct irq_alloc_info *info) +{ + struct mp_chip_data *data = irq_get_chip_data(irq); + + /* + * setup_IO_APIC_irqs() programs all legacy IRQs with default trigger + * and polarity attirbutes. So allow the first user to reprogram the + * pin with real trigger and polarity attributes. + */ + if (irq < nr_legacy_irqs() && data->count == 1) { + if (info->ioapic_trigger != data->trigger) + mp_register_handler(irq, info->ioapic_trigger); + data->entry.trigger = data->trigger = info->ioapic_trigger; + data->entry.polarity = data->polarity = info->ioapic_polarity; + } + + return data->trigger == info->ioapic_trigger && + data->polarity == info->ioapic_polarity; +} + +static int alloc_irq_from_domain(struct irq_domain *domain, int ioapic, u32 gsi, + struct irq_alloc_info *info) +{ + bool legacy = false; int irq = -1; - int ioapic = (int)(long)domain->host_data; int type = ioapics[ioapic].irqdomain_cfg.type; switch (type) { case IOAPIC_DOMAIN_LEGACY: /* - * Dynamically allocate IRQ number for non-ISA IRQs in the first 16 - * GSIs on some weird platforms. + * Dynamically allocate IRQ number for non-ISA IRQs in the first + * 16 GSIs on some weird platforms. */ - if (gsi < nr_legacy_irqs()) - irq = irq_create_mapping(domain, pin); - else if (irq_create_strict_mappings(domain, gsi, pin, 1) == 0) + if (!ioapic_initialized || gsi >= nr_legacy_irqs()) irq = gsi; + legacy = mp_is_legacy_irq(irq); break; case IOAPIC_DOMAIN_STRICT: - if (irq_create_strict_mappings(domain, gsi, pin, 1) == 0) - irq = gsi; + irq = gsi; break; case IOAPIC_DOMAIN_DYNAMIC: - irq = irq_create_mapping(domain, pin); break; default: WARN(1, "ioapic: unknown irqdomain type %d\n", type); - break; + return -1; } - return irq > 0 ? irq : -1; + return __irq_domain_alloc_irqs(domain, irq, 1, + ioapic_alloc_attr_node(info), + info, legacy); +} + +/* + * Need special handling for ISA IRQs because there may be multiple IOAPIC pins + * sharing the same ISA IRQ number and irqdomain only supports 1:1 mapping + * between IOAPIC pin and IRQ number. A typical IOAPIC has 24 pins, pin 0-15 are + * used for legacy IRQs and pin 16-23 are used for PCI IRQs (PIRQ A-H). + * When ACPI is disabled, only legacy IRQ numbers (IRQ0-15) are available, and + * some BIOSes may use MP Interrupt Source records to override IRQ numbers for + * PIRQs instead of reprogramming the interrupt routing logic. Thus there may be + * multiple pins sharing the same legacy IRQ number when ACPI is disabled. + */ +static int alloc_isa_irq_from_domain(struct irq_domain *domain, + int irq, int ioapic, int pin, + struct irq_alloc_info *info) +{ + struct mp_chip_data *data; + struct irq_data *irq_data = irq_get_irq_data(irq); + int node = ioapic_alloc_attr_node(info); + + /* + * Legacy ISA IRQ has already been allocated, just add pin to + * the pin list assoicated with this IRQ and program the IOAPIC + * entry. The IOAPIC entry + */ + if (irq_data && irq_data->parent_data) { + if (!mp_check_pin_attr(irq, info)) + return -EBUSY; + if (__add_pin_to_irq_node(irq_data->chip_data, node, ioapic, + info->ioapic_pin)) + return -ENOMEM; + } else { + irq = __irq_domain_alloc_irqs(domain, irq, 1, node, info, true); + if (irq >= 0) { + irq_data = irq_domain_get_irq_data(domain, irq); + data = irq_data->chip_data; + data->isa_irq = true; + } + } + + return irq; } static int mp_map_pin_to_irq(u32 gsi, int idx, int ioapic, int pin, - unsigned int flags) + unsigned int flags, struct irq_alloc_info *info) { int irq; + bool legacy = false; + struct irq_alloc_info tmp; + struct mp_chip_data *data; struct irq_domain *domain = mp_ioapic_irqdomain(ioapic); - struct mp_pin_info *info = mp_pin_info(ioapic, pin); if (!domain) - return -1; - - mutex_lock(&ioapic_mutex); + return -ENOSYS; - /* - * Don't use irqdomain to manage ISA IRQs because there may be - * multiple IOAPIC pins sharing the same ISA IRQ number and - * irqdomain only supports 1:1 mapping between IOAPIC pin and - * IRQ number. A typical IOAPIC has 24 pins, pin 0-15 are used - * for legacy IRQs and pin 16-23 are used for PCI IRQs (PIRQ A-H). - * When ACPI is disabled, only legacy IRQ numbers (IRQ0-15) are - * available, and some BIOSes may use MP Interrupt Source records - * to override IRQ numbers for PIRQs instead of reprogramming - * the interrupt routing logic. Thus there may be multiple pins - * sharing the same legacy IRQ number when ACPI is disabled. - */ if (idx >= 0 && test_bit(mp_irqs[idx].srcbus, mp_bus_not_pci)) { irq = mp_irqs[idx].srcbusirq; - if (flags & IOAPIC_MAP_ALLOC) { - if (info->count == 0 && - mp_irqdomain_map(domain, irq, pin) != 0) - irq = -1; + legacy = mp_is_legacy_irq(irq); + } - /* special handling for timer IRQ0 */ + mutex_lock(&ioapic_mutex); + if (!(flags & IOAPIC_MAP_ALLOC)) { + if (!legacy) { + irq = irq_find_mapping(domain, pin); if (irq == 0) - info->count++; + irq = -ENOENT; } } else { - irq = irq_find_mapping(domain, pin); - if (irq <= 0 && (flags & IOAPIC_MAP_ALLOC)) - irq = alloc_irq_from_domain(domain, gsi, pin); - } - - if (flags & IOAPIC_MAP_ALLOC) { - /* special handling for legacy IRQs */ - if (irq < nr_legacy_irqs() && info->count == 1 && - mp_irqdomain_map(domain, irq, pin) != 0) - irq = -1; - - if (irq > 0) - info->count++; - else if (info->count == 0) - info->set = 0; + ioapic_copy_alloc_attr(&tmp, info, gsi, ioapic, pin); + if (legacy) + irq = alloc_isa_irq_from_domain(domain, irq, + ioapic, pin, &tmp); + else if ((irq = irq_find_mapping(domain, pin)) == 0) + irq = alloc_irq_from_domain(domain, ioapic, gsi, &tmp); + else if (!mp_check_pin_attr(irq, &tmp)) + irq = -EBUSY; + if (irq >= 0) { + data = irq_get_chip_data(irq); + data->count++; + } } - mutex_unlock(&ioapic_mutex); - return irq > 0 ? irq : -1; + return irq; } static int pin_2_irq(int idx, int ioapic, int pin, unsigned int flags) @@ -1058,10 +1098,10 @@ static int pin_2_irq(int idx, int ioapic, int pin, unsigned int flags) } #endif - return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags); + return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags, NULL); } -int mp_map_gsi_to_irq(u32 gsi, unsigned int flags) +int mp_map_gsi_to_irq(u32 gsi, unsigned int flags, struct irq_alloc_info *info) { int ioapic, pin, idx; @@ -1074,31 +1114,24 @@ int mp_map_gsi_to_irq(u32 gsi, unsigned int flags) if ((flags & IOAPIC_MAP_CHECK) && idx < 0) return -1; - return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags); + return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags, info); } void mp_unmap_irq(int irq) { - struct irq_data *data = irq_get_irq_data(irq); - struct mp_pin_info *info; - int ioapic, pin; + struct irq_data *irq_data = irq_get_irq_data(irq); + struct mp_chip_data *data; - if (!data || !data->domain) + if (!irq_data || !irq_data->domain) return; - ioapic = (int)(long)data->domain->host_data; - pin = (int)data->hwirq; - info = mp_pin_info(ioapic, pin); + data = irq_data->chip_data; + if (!data || data->isa_irq) + return; mutex_lock(&ioapic_mutex); - if (--info->count == 0) { - info->set = 0; - if (irq < nr_legacy_irqs() && - ioapics[ioapic].irqdomain_cfg.type == IOAPIC_DOMAIN_LEGACY) - mp_irqdomain_unmap(data->domain, irq); - else - irq_dispose_mapping(irq); - } + if (--data->count == 0) + irq_domain_free_irqs(irq, 1); mutex_unlock(&ioapic_mutex); } @@ -1165,7 +1198,7 @@ out: } EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector); -static struct irq_chip ioapic_chip; +static struct irq_chip ioapic_chip, ioapic_ir_chip; #ifdef CONFIG_X86_32 static inline int IO_APIC_irq_trigger(int irq) @@ -1189,96 +1222,6 @@ static inline int IO_APIC_irq_trigger(int irq) } #endif -static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg, - unsigned long trigger) -{ - struct irq_chip *chip = &ioapic_chip; - irq_flow_handler_t hdl; - bool fasteoi; - - if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) || - trigger == IOAPIC_LEVEL) { - irq_set_status_flags(irq, IRQ_LEVEL); - fasteoi = true; - } else { - irq_clear_status_flags(irq, IRQ_LEVEL); - fasteoi = false; - } - - if (setup_remapped_irq(irq, cfg, chip)) - fasteoi = trigger != 0; - - hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq; - irq_set_chip_and_handler_name(irq, chip, hdl, - fasteoi ? "fasteoi" : "edge"); -} - -int native_setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry, - unsigned int destination, int vector, - struct io_apic_irq_attr *attr) -{ - memset(entry, 0, sizeof(*entry)); - - entry->delivery_mode = apic->irq_delivery_mode; - entry->dest_mode = apic->irq_dest_mode; - entry->dest = destination; - entry->vector = vector; - entry->mask = 0; /* enable IRQ */ - entry->trigger = attr->trigger; - entry->polarity = attr->polarity; - - /* - * Mask level triggered irqs. - * Use IRQ_DELAYED_DISABLE for edge triggered irqs. - */ - if (attr->trigger) - entry->mask = 1; - - return 0; -} - -static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg, - struct io_apic_irq_attr *attr) -{ - struct IO_APIC_route_entry entry; - unsigned int dest; - - if (!IO_APIC_IRQ(irq)) - return; - - if (assign_irq_vector(irq, cfg, apic->target_cpus())) - return; - - if (apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus(), - &dest)) { - pr_warn("Failed to obtain apicid for ioapic %d, pin %d\n", - mpc_ioapic_id(attr->ioapic), attr->ioapic_pin); - clear_irq_vector(irq, cfg); - - return; - } - - apic_printk(APIC_VERBOSE,KERN_DEBUG - "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> " - "IRQ %d Mode:%i Active:%i Dest:%d)\n", - attr->ioapic, mpc_ioapic_id(attr->ioapic), attr->ioapic_pin, - cfg->vector, irq, attr->trigger, attr->polarity, dest); - - if (x86_io_apic_ops.setup_entry(irq, &entry, dest, cfg->vector, attr)) { - pr_warn("Failed to setup ioapic entry for ioapic %d, pin %d\n", - mpc_ioapic_id(attr->ioapic), attr->ioapic_pin); - clear_irq_vector(irq, cfg); - - return; - } - - ioapic_register_intr(irq, cfg, attr->trigger); - if (irq < nr_legacy_irqs()) - legacy_pic->mask(irq); - - ioapic_write_entry(attr->ioapic, attr->ioapic_pin, entry); -} - static void __init setup_IO_APIC_irqs(void) { unsigned int ioapic, pin; @@ -1298,106 +1241,41 @@ static void __init setup_IO_APIC_irqs(void) } } -/* - * Set up the timer pin, possibly with the 8259A-master behind. - */ -static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx, - unsigned int pin, int vector) -{ - struct IO_APIC_route_entry entry; - unsigned int dest; - - memset(&entry, 0, sizeof(entry)); - - /* - * We use logical delivery to get the timer IRQ - * to the first CPU. - */ - if (unlikely(apic->cpu_mask_to_apicid_and(apic->target_cpus(), - apic->target_cpus(), &dest))) - dest = BAD_APICID; - - entry.dest_mode = apic->irq_dest_mode; - entry.mask = 0; /* don't mask IRQ for edge */ - entry.dest = dest; - entry.delivery_mode = apic->irq_delivery_mode; - entry.polarity = 0; - entry.trigger = 0; - entry.vector = vector; - - /* - * The timer IRQ doesn't have to know that behind the - * scene we may have a 8259A-master in AEOI mode ... - */ - irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, - "edge"); - - /* - * Add it to the IO-APIC irq-routing table: - */ - ioapic_write_entry(ioapic_idx, pin, entry); -} - -void native_io_apic_print_entries(unsigned int apic, unsigned int nr_entries) +void ioapic_zap_locks(void) { - int i; - - pr_debug(" NR Dst Mask Trig IRR Pol Stat Dmod Deli Vect:\n"); - - for (i = 0; i <= nr_entries; i++) { - struct IO_APIC_route_entry entry; - - entry = ioapic_read_entry(apic, i); - - pr_debug(" %02x %02X ", i, entry.dest); - pr_cont("%1d %1d %1d %1d %1d " - "%1d %1d %02X\n", - entry.mask, - entry.trigger, - entry.irr, - entry.polarity, - entry.delivery_status, - entry.dest_mode, - entry.delivery_mode, - entry.vector); - } + raw_spin_lock_init(&ioapic_lock); } -void intel_ir_io_apic_print_entries(unsigned int apic, - unsigned int nr_entries) +static void io_apic_print_entries(unsigned int apic, unsigned int nr_entries) { int i; + char buf[256]; + struct IO_APIC_route_entry entry; + struct IR_IO_APIC_route_entry *ir_entry = (void *)&entry; - pr_debug(" NR Indx Fmt Mask Trig IRR Pol Stat Indx2 Zero Vect:\n"); - + printk(KERN_DEBUG "IOAPIC %d:\n", apic); for (i = 0; i <= nr_entries; i++) { - struct IR_IO_APIC_route_entry *ir_entry; - struct IO_APIC_route_entry entry; - entry = ioapic_read_entry(apic, i); - - ir_entry = (struct IR_IO_APIC_route_entry *)&entry; - - pr_debug(" %02x %04X ", i, ir_entry->index); - pr_cont("%1d %1d %1d %1d %1d " - "%1d %1d %X %02X\n", - ir_entry->format, - ir_entry->mask, - ir_entry->trigger, - ir_entry->irr, - ir_entry->polarity, - ir_entry->delivery_status, - ir_entry->index2, - ir_entry->zero, - ir_entry->vector); + snprintf(buf, sizeof(buf), + " pin%02x, %s, %s, %s, V(%02X), IRR(%1d), S(%1d)", + i, + entry.mask == IOAPIC_MASKED ? "disabled" : "enabled ", + entry.trigger == IOAPIC_LEVEL ? "level" : "edge ", + entry.polarity == IOAPIC_POL_LOW ? "low " : "high", + entry.vector, entry.irr, entry.delivery_status); + if (ir_entry->format) + printk(KERN_DEBUG "%s, remapped, I(%04X), Z(%X)\n", + buf, (ir_entry->index << 15) | ir_entry->index, + ir_entry->zero); + else + printk(KERN_DEBUG "%s, %s, D(%02X), M(%1d)\n", + buf, + entry.dest_mode == IOAPIC_DEST_MODE_LOGICAL ? + "logical " : "physical", + entry.dest, entry.delivery_mode); } } -void ioapic_zap_locks(void) -{ - raw_spin_lock_init(&ioapic_lock); -} - static void __init print_IO_APIC(int ioapic_idx) { union IO_APIC_reg_00 reg_00; @@ -1451,16 +1329,13 @@ static void __init print_IO_APIC(int ioapic_idx) } printk(KERN_DEBUG ".... IRQ redirection table:\n"); - - x86_io_apic_ops.print_entries(ioapic_idx, reg_01.bits.entries); + io_apic_print_entries(ioapic_idx, reg_01.bits.entries); } void __init print_IO_APICs(void) { int ioapic_idx; - struct irq_cfg *cfg; unsigned int irq; - struct irq_chip *chip; printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries); for_each_ioapic(ioapic_idx) @@ -1480,18 +1355,20 @@ void __init print_IO_APICs(void) printk(KERN_DEBUG "IRQ to pin mappings:\n"); for_each_active_irq(irq) { struct irq_pin_list *entry; + struct irq_chip *chip; + struct mp_chip_data *data; chip = irq_get_chip(irq); - if (chip != &ioapic_chip) + if (chip != &ioapic_chip && chip != &ioapic_ir_chip) continue; - - cfg = irq_cfg(irq); - if (!cfg) + data = irq_get_chip_data(irq); + if (!data) continue; - if (list_empty(&cfg->irq_2_pin)) + if (list_empty(&data->irq_2_pin)) continue; + printk(KERN_DEBUG "IRQ%d ", irq); - for_each_irq_pin(entry, cfg->irq_2_pin) + for_each_irq_pin(entry, data->irq_2_pin) pr_cont("-> %d:%d", entry->apic, entry->pin); pr_cont("\n"); } @@ -1564,15 +1441,12 @@ void native_disable_io_apic(void) struct IO_APIC_route_entry entry; memset(&entry, 0, sizeof(entry)); - entry.mask = 0; /* Enabled */ - entry.trigger = 0; /* Edge */ - entry.irr = 0; - entry.polarity = 0; /* High */ - entry.delivery_status = 0; - entry.dest_mode = 0; /* Physical */ - entry.delivery_mode = dest_ExtINT; /* ExtInt */ - entry.vector = 0; - entry.dest = read_apic_id(); + entry.mask = IOAPIC_UNMASKED; + entry.trigger = IOAPIC_EDGE; + entry.polarity = IOAPIC_POL_HIGH; + entry.dest_mode = IOAPIC_DEST_MODE_PHYSICAL; + entry.delivery_mode = dest_ExtINT; + entry.dest = read_apic_id(); /* * Add it to the IO-APIC irq-routing table: @@ -1582,7 +1456,6 @@ void native_disable_io_apic(void) if (cpu_has_apic || apic_from_smp_config()) disconnect_bsp_APIC(ioapic_i8259.pin != -1); - } /* @@ -1792,7 +1665,6 @@ static int __init timer_irq_works(void) * This is not complete - we should be able to fake * an edge even if it isn't on the 8259A... */ - static unsigned int startup_ioapic_irq(struct irq_data *data) { int was_pending = 0, irq = data->irq; @@ -1804,74 +1676,22 @@ static unsigned int startup_ioapic_irq(struct irq_data *data) if (legacy_pic->irq_pending(irq)) was_pending = 1; } - __unmask_ioapic(irqd_cfg(data)); + __unmask_ioapic(data->chip_data); raw_spin_unlock_irqrestore(&ioapic_lock, flags); return was_pending; } -/* - * Level and edge triggered IO-APIC interrupts need different handling, - * so we use two separate IRQ descriptors. Edge triggered IRQs can be - * handled with the level-triggered descriptor, but that one has slightly - * more overhead. Level-triggered interrupts cannot be handled with the - * edge-triggered handler, without risking IRQ storms and other ugly - * races. - */ - -static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg) -{ - int apic, pin; - struct irq_pin_list *entry; - u8 vector = cfg->vector; - - for_each_irq_pin(entry, cfg->irq_2_pin) { - unsigned int reg; - - apic = entry->apic; - pin = entry->pin; - - io_apic_write(apic, 0x11 + pin*2, dest); - reg = io_apic_read(apic, 0x10 + pin*2); - reg &= ~IO_APIC_REDIR_VECTOR_MASK; - reg |= vector; - io_apic_modify(apic, 0x10 + pin*2, reg); - } -} - -int native_ioapic_set_affinity(struct irq_data *data, - const struct cpumask *mask, - bool force) -{ - unsigned int dest, irq = data->irq; - unsigned long flags; - int ret; - - if (!config_enabled(CONFIG_SMP)) - return -EPERM; - - raw_spin_lock_irqsave(&ioapic_lock, flags); - ret = apic_set_affinity(data, mask, &dest); - if (!ret) { - /* Only the high 8 bits are valid. */ - dest = SET_APIC_LOGICAL_ID(dest); - __target_IO_APIC_irq(irq, dest, irqd_cfg(data)); - ret = IRQ_SET_MASK_OK_NOCOPY; - } - raw_spin_unlock_irqrestore(&ioapic_lock, flags); - return ret; -} - atomic_t irq_mis_count; #ifdef CONFIG_GENERIC_PENDING_IRQ -static bool io_apic_level_ack_pending(struct irq_cfg *cfg) +static bool io_apic_level_ack_pending(struct mp_chip_data *data) { struct irq_pin_list *entry; unsigned long flags; raw_spin_lock_irqsave(&ioapic_lock, flags); - for_each_irq_pin(entry, cfg->irq_2_pin) { + for_each_irq_pin(entry, data->irq_2_pin) { unsigned int reg; int pin; @@ -1888,18 +1708,17 @@ static bool io_apic_level_ack_pending(struct irq_cfg *cfg) return false; } -static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg) +static inline bool ioapic_irqd_mask(struct irq_data *data) { /* If we are moving the irq we need to mask it */ if (unlikely(irqd_is_setaffinity_pending(data))) { - mask_ioapic(cfg); + mask_ioapic_irq(data); return true; } return false; } -static inline void ioapic_irqd_unmask(struct irq_data *data, - struct irq_cfg *cfg, bool masked) +static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked) { if (unlikely(masked)) { /* Only migrate the irq if the ack has been received. @@ -1928,31 +1747,30 @@ static inline void ioapic_irqd_unmask(struct irq_data *data, * accurate and is causing problems then it is a hardware bug * and you can go talk to the chipset vendor about it. */ - if (!io_apic_level_ack_pending(cfg)) + if (!io_apic_level_ack_pending(data->chip_data)) irq_move_masked_irq(data); - unmask_ioapic(cfg); + unmask_ioapic_irq(data); } } #else -static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg) +static inline bool ioapic_irqd_mask(struct irq_data *data) { return false; } -static inline void ioapic_irqd_unmask(struct irq_data *data, - struct irq_cfg *cfg, bool masked) +static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked) { } #endif -static void ack_ioapic_level(struct irq_data *data) +static void ioapic_ack_level(struct irq_data *irq_data) { - struct irq_cfg *cfg = irqd_cfg(data); - int i, irq = data->irq; + struct irq_cfg *cfg = irqd_cfg(irq_data); unsigned long v; bool masked; + int i; irq_complete_move(cfg); - masked = ioapic_irqd_mask(data, cfg); + masked = ioapic_irqd_mask(irq_data); /* * It appears there is an erratum which affects at least version 0x11 @@ -2004,11 +1822,49 @@ static void ack_ioapic_level(struct irq_data *data) */ if (!(v & (1 << (i & 0x1f)))) { atomic_inc(&irq_mis_count); + eoi_ioapic_pin(cfg->vector, irq_data->chip_data); + } + + ioapic_irqd_unmask(irq_data, masked); +} + +static void ioapic_ir_ack_level(struct irq_data *irq_data) +{ + struct mp_chip_data *data = irq_data->chip_data; - eoi_ioapic_irq(irq, cfg); + /* + * Intr-remapping uses pin number as the virtual vector + * in the RTE. Actual vector is programmed in + * intr-remapping table entry. Hence for the io-apic + * EOI we use the pin number. + */ + ack_APIC_irq(); + eoi_ioapic_pin(data->entry.vector, data); +} + +static int ioapic_set_affinity(struct irq_data *irq_data, + const struct cpumask *mask, bool force) +{ + struct irq_data *parent = irq_data->parent_data; + struct mp_chip_data *data = irq_data->chip_data; + struct irq_pin_list *entry; + struct irq_cfg *cfg; + unsigned long flags; + int ret; + + ret = parent->chip->irq_set_affinity(parent, mask, force); + raw_spin_lock_irqsave(&ioapic_lock, flags); + if (ret >= 0 && ret != IRQ_SET_MASK_OK_DONE) { + cfg = irqd_cfg(irq_data); + data->entry.dest = cfg->dest_apicid; + data->entry.vector = cfg->vector; + for_each_irq_pin(entry, data->irq_2_pin) + __ioapic_write_entry(entry->apic, entry->pin, + data->entry); } + raw_spin_unlock_irqrestore(&ioapic_lock, flags); - ioapic_irqd_unmask(data, cfg, masked); + return ret; } static struct irq_chip ioapic_chip __read_mostly = { @@ -2016,10 +1872,20 @@ static struct irq_chip ioapic_chip __read_mostly = { .irq_startup = startup_ioapic_irq, .irq_mask = mask_ioapic_irq, .irq_unmask = unmask_ioapic_irq, - .irq_ack = apic_ack_edge, - .irq_eoi = ack_ioapic_level, - .irq_set_affinity = native_ioapic_set_affinity, - .irq_retrigger = apic_retrigger_irq, + .irq_ack = irq_chip_ack_parent, + .irq_eoi = ioapic_ack_level, + .irq_set_affinity = ioapic_set_affinity, + .flags = IRQCHIP_SKIP_SET_WAKE, +}; + +static struct irq_chip ioapic_ir_chip __read_mostly = { + .name = "IR-IO-APIC", + .irq_startup = startup_ioapic_irq, + .irq_mask = mask_ioapic_irq, + .irq_unmask = unmask_ioapic_irq, + .irq_ack = irq_chip_ack_parent, + .irq_eoi = ioapic_ir_ack_level, + .irq_set_affinity = ioapic_set_affinity, .flags = IRQCHIP_SKIP_SET_WAKE, }; @@ -2113,12 +1979,12 @@ static inline void __init unlock_ExtINT_logic(void) memset(&entry1, 0, sizeof(entry1)); - entry1.dest_mode = 0; /* physical delivery */ - entry1.mask = 0; /* unmask IRQ now */ + entry1.dest_mode = IOAPIC_DEST_MODE_PHYSICAL; + entry1.mask = IOAPIC_UNMASKED; entry1.dest = hard_smp_processor_id(); entry1.delivery_mode = dest_ExtINT; entry1.polarity = entry0.polarity; - entry1.trigger = 0; + entry1.trigger = IOAPIC_EDGE; entry1.vector = 0; ioapic_write_entry(apic, pin, entry1); @@ -2152,6 +2018,25 @@ static int __init disable_timer_pin_setup(char *arg) } early_param("disable_timer_pin_1", disable_timer_pin_setup); +static int mp_alloc_timer_irq(int ioapic, int pin) +{ + int irq = -1; + struct irq_domain *domain = mp_ioapic_irqdomain(ioapic); + + if (domain) { + struct irq_alloc_info info; + + ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 0, 0); + info.ioapic_id = mpc_ioapic_id(ioapic); + info.ioapic_pin = pin; + mutex_lock(&ioapic_mutex); + irq = alloc_isa_irq_from_domain(domain, 0, ioapic, pin, &info); + mutex_unlock(&ioapic_mutex); + } + + return irq; +} + /* * This code may look a bit paranoid, but it's supposed to cooperate with * a wide range of boards and BIOS bugs. Fortunately only the timer IRQ @@ -2162,7 +2047,9 @@ early_param("disable_timer_pin_1", disable_timer_pin_setup); */ static inline void __init check_timer(void) { - struct irq_cfg *cfg = irq_cfg(0); + struct irq_data *irq_data = irq_get_irq_data(0); + struct mp_chip_data *data = irq_data->chip_data; + struct irq_cfg *cfg = irqd_cfg(irq_data); int node = cpu_to_node(0); int apic1, pin1, apic2, pin2; unsigned long flags; @@ -2174,7 +2061,6 @@ static inline void __init check_timer(void) * get/set the timer IRQ vector: */ legacy_pic->mask(0); - assign_irq_vector(0, cfg, apic->target_cpus()); /* * As IRQ0 is to be enabled in the 8259A, the virtual @@ -2215,23 +2101,21 @@ static inline void __init check_timer(void) } if (pin1 != -1) { - /* - * Ok, does IRQ0 through the IOAPIC work? - */ + /* Ok, does IRQ0 through the IOAPIC work? */ if (no_pin1) { - add_pin_to_irq_node(cfg, node, apic1, pin1); - setup_timer_IRQ0_pin(apic1, pin1, cfg->vector); + mp_alloc_timer_irq(apic1, pin1); } else { - /* for edge trigger, setup_ioapic_irq already - * leave it unmasked. + /* + * for edge trigger, it's already unmasked, * so only need to unmask if it is level-trigger * do we really have level trigger timer? */ int idx; idx = find_irq_entry(apic1, pin1, mp_INT); if (idx != -1 && irq_trigger(idx)) - unmask_ioapic(cfg); + unmask_ioapic_irq(irq_get_chip_data(0)); } + irq_domain_activate_irq(irq_data); if (timer_irq_works()) { if (disable_timer_pin_1 > 0) clear_IO_APIC_pin(0, pin1); @@ -2251,8 +2135,8 @@ static inline void __init check_timer(void) /* * legacy devices should be connected to IO APIC #0 */ - replace_pin_at_irq_node(cfg, node, apic1, pin1, apic2, pin2); - setup_timer_IRQ0_pin(apic2, pin2, cfg->vector); + replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2); + irq_domain_activate_irq(irq_data); legacy_pic->unmask(0); if (timer_irq_works()) { apic_printk(APIC_QUIET, KERN_INFO "....... works.\n"); @@ -2329,36 +2213,35 @@ out: static int mp_irqdomain_create(int ioapic) { - size_t size; + struct irq_alloc_info info; + struct irq_domain *parent; int hwirqs = mp_ioapic_pin_count(ioapic); struct ioapic *ip = &ioapics[ioapic]; struct ioapic_domain_cfg *cfg = &ip->irqdomain_cfg; struct mp_ioapic_gsi *gsi_cfg = mp_ioapic_gsi_routing(ioapic); - size = sizeof(struct mp_pin_info) * mp_ioapic_pin_count(ioapic); - ip->pin_info = kzalloc(size, GFP_KERNEL); - if (!ip->pin_info) - return -ENOMEM; - if (cfg->type == IOAPIC_DOMAIN_INVALID) return 0; + init_irq_alloc_info(&info, NULL); + info.type = X86_IRQ_ALLOC_TYPE_IOAPIC; + info.ioapic_id = mpc_ioapic_id(ioapic); + parent = irq_remapping_get_ir_irq_domain(&info); + if (!parent) + parent = x86_vector_domain; + ip->irqdomain = irq_domain_add_linear(cfg->dev, hwirqs, cfg->ops, (void *)(long)ioapic); - if(!ip->irqdomain) { - kfree(ip->pin_info); - ip->pin_info = NULL; + if (!ip->irqdomain) return -ENOMEM; - } + + ip->irqdomain->parent = parent; if (cfg->type == IOAPIC_DOMAIN_LEGACY || cfg->type == IOAPIC_DOMAIN_STRICT) ioapic_dynirq_base = max(ioapic_dynirq_base, gsi_cfg->gsi_end + 1); - if (gsi_cfg->gsi_base == 0) - irq_set_default_host(ip->irqdomain); - return 0; } @@ -2368,8 +2251,6 @@ static void ioapic_destroy_irqdomain(int idx) irq_domain_remove(ioapics[idx].irqdomain); ioapics[idx].irqdomain = NULL; } - kfree(ioapics[idx].pin_info); - ioapics[idx].pin_info = NULL; } void __init setup_IO_APIC(void) @@ -2399,20 +2280,6 @@ void __init setup_IO_APIC(void) ioapic_initialized = 1; } -/* - * Called after all the initialization is done. If we didn't find any - * APIC bugs then we can allow the modify fast path - */ - -static int __init io_apic_bug_finalize(void) -{ - if (sis_apic_bug == -1) - sis_apic_bug = 0; - return 0; -} - -late_initcall(io_apic_bug_finalize); - static void resume_ioapic_id(int ioapic_idx) { unsigned long flags; @@ -2451,20 +2318,6 @@ static int __init ioapic_init_ops(void) device_initcall(ioapic_init_ops); -static int -io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr) -{ - struct irq_cfg *cfg = alloc_irq_and_cfg_at(irq, node); - int ret; - - if (!cfg) - return -EINVAL; - ret = __add_pin_to_irq_node(cfg, node, attr->ioapic, attr->ioapic_pin); - if (!ret) - setup_ioapic_irq(irq, cfg, attr); - return ret; -} - static int io_apic_get_redir_entries(int ioapic) { union IO_APIC_reg_01 reg_01; @@ -2638,11 +2491,6 @@ int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity) { int ioapic, pin, idx; -#ifdef CONFIG_ACPI - if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC) - return -1; -#endif - if (skip_ioapic_setup) return -1; @@ -2697,7 +2545,7 @@ void __init setup_ioapic_dest(void) else mask = apic->target_cpus(); - x86_io_apic_ops.set_affinity(idata, mask, false); + irq_set_affinity(irq, mask); } } @@ -2742,7 +2590,7 @@ static struct resource * __init ioapic_setup_resources(void) return res; } -void __init native_io_apic_init_mappings(void) +void __init io_apic_init_mappings(void) { unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0; struct resource *ioapic_res; @@ -2967,7 +2815,6 @@ int mp_unregister_ioapic(u32 gsi_base) { int ioapic, pin; int found = 0; - struct mp_pin_info *pin_info; for_each_ioapic(ioapic) if (ioapics[ioapic].gsi_config.gsi_base == gsi_base) { @@ -2980,11 +2827,17 @@ int mp_unregister_ioapic(u32 gsi_base) } for_each_pin(ioapic, pin) { - pin_info = mp_pin_info(ioapic, pin); - if (pin_info->count) { - pr_warn("pin%d on IOAPIC%d is still in use.\n", - pin, ioapic); - return -EBUSY; + u32 gsi = mp_pin_to_gsi(ioapic, pin); + int irq = mp_map_gsi_to_irq(gsi, 0, NULL); + struct mp_chip_data *data; + + if (irq >= 0) { + data = irq_get_chip_data(irq); + if (data && data->count) { + pr_warn("pin%d on IOAPIC%d is still in use.\n", + pin, ioapic); + return -EBUSY; + } } } @@ -3011,108 +2864,141 @@ int mp_ioapic_registered(u32 gsi_base) return 0; } -static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr, - int ioapic, int ioapic_pin, - int trigger, int polarity) +static void mp_irqdomain_get_attr(u32 gsi, struct mp_chip_data *data, + struct irq_alloc_info *info) { - irq_attr->ioapic = ioapic; - irq_attr->ioapic_pin = ioapic_pin; - irq_attr->trigger = trigger; - irq_attr->polarity = polarity; + if (info && info->ioapic_valid) { + data->trigger = info->ioapic_trigger; + data->polarity = info->ioapic_polarity; + } else if (acpi_get_override_irq(gsi, &data->trigger, + &data->polarity) < 0) { + /* PCI interrupts are always active low level triggered. */ + data->trigger = IOAPIC_LEVEL; + data->polarity = IOAPIC_POL_LOW; + } } -int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq) +static void mp_setup_entry(struct irq_cfg *cfg, struct mp_chip_data *data, + struct IO_APIC_route_entry *entry) { - int ioapic = (int)(long)domain->host_data; - struct mp_pin_info *info = mp_pin_info(ioapic, hwirq); - struct io_apic_irq_attr attr; + memset(entry, 0, sizeof(*entry)); + entry->delivery_mode = apic->irq_delivery_mode; + entry->dest_mode = apic->irq_dest_mode; + entry->dest = cfg->dest_apicid; + entry->vector = cfg->vector; + entry->trigger = data->trigger; + entry->polarity = data->polarity; + /* + * Mask level triggered irqs. Edge triggered irqs are masked + * by the irq core code in case they fire. + */ + if (data->trigger == IOAPIC_LEVEL) + entry->mask = IOAPIC_MASKED; + else + entry->mask = IOAPIC_UNMASKED; +} - /* Get default attribute if not set by caller yet */ - if (!info->set) { - u32 gsi = mp_pin_to_gsi(ioapic, hwirq); +int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) +{ + int ret, ioapic, pin; + struct irq_cfg *cfg; + struct irq_data *irq_data; + struct mp_chip_data *data; + struct irq_alloc_info *info = arg; - if (acpi_get_override_irq(gsi, &info->trigger, - &info->polarity) < 0) { - /* - * PCI interrupts are always polarity one level - * triggered. - */ - info->trigger = 1; - info->polarity = 1; - } - info->node = NUMA_NO_NODE; + if (!info || nr_irqs > 1) + return -EINVAL; + irq_data = irq_domain_get_irq_data(domain, virq); + if (!irq_data) + return -EINVAL; - /* - * setup_IO_APIC_irqs() programs all legacy IRQs with default - * trigger and polarity attributes. Don't set the flag for that - * case so the first legacy IRQ user could reprogram the pin - * with real trigger and polarity attributes. - */ - if (virq >= nr_legacy_irqs() || info->count) - info->set = 1; - } - set_io_apic_irq_attr(&attr, ioapic, hwirq, info->trigger, - info->polarity); + ioapic = mp_irqdomain_ioapic_idx(domain); + pin = info->ioapic_pin; + if (irq_find_mapping(domain, (irq_hw_number_t)pin) > 0) + return -EEXIST; - return io_apic_setup_irq_pin(virq, info->node, &attr); -} + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; -void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq) -{ - struct irq_data *data = irq_get_irq_data(virq); - struct irq_cfg *cfg = irq_cfg(virq); - int ioapic = (int)(long)domain->host_data; - int pin = (int)data->hwirq; + info->ioapic_entry = &data->entry; + ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info); + if (ret < 0) { + kfree(data); + return ret; + } + + INIT_LIST_HEAD(&data->irq_2_pin); + irq_data->hwirq = info->ioapic_pin; + irq_data->chip = (domain->parent == x86_vector_domain) ? + &ioapic_chip : &ioapic_ir_chip; + irq_data->chip_data = data; + mp_irqdomain_get_attr(mp_pin_to_gsi(ioapic, pin), data, info); + + cfg = irqd_cfg(irq_data); + add_pin_to_irq_node(data, ioapic_alloc_attr_node(info), ioapic, pin); + if (info->ioapic_entry) + mp_setup_entry(cfg, data, info->ioapic_entry); + mp_register_handler(virq, data->trigger); + if (virq < nr_legacy_irqs()) + legacy_pic->mask(virq); + + apic_printk(APIC_VERBOSE, KERN_DEBUG + "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> IRQ %d Mode:%i Active:%i Dest:%d)\n", + ioapic, mpc_ioapic_id(ioapic), pin, cfg->vector, + virq, data->trigger, data->polarity, cfg->dest_apicid); - ioapic_mask_entry(ioapic, pin); - __remove_pin_from_irq(cfg, ioapic, pin); - WARN_ON(!list_empty(&cfg->irq_2_pin)); - arch_teardown_hwirq(virq); + return 0; } -int mp_set_gsi_attr(u32 gsi, int trigger, int polarity, int node) +void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) { - int ret = 0; - int ioapic, pin; - struct mp_pin_info *info; + struct irq_data *irq_data; + struct mp_chip_data *data; - ioapic = mp_find_ioapic(gsi); - if (ioapic < 0) - return -ENODEV; - - pin = mp_find_ioapic_pin(ioapic, gsi); - info = mp_pin_info(ioapic, pin); - trigger = trigger ? 1 : 0; - polarity = polarity ? 1 : 0; - - mutex_lock(&ioapic_mutex); - if (!info->set) { - info->trigger = trigger; - info->polarity = polarity; - info->node = node; - info->set = 1; - } else if (info->trigger != trigger || info->polarity != polarity) { - ret = -EBUSY; + BUG_ON(nr_irqs != 1); + irq_data = irq_domain_get_irq_data(domain, virq); + if (irq_data && irq_data->chip_data) { + data = irq_data->chip_data; + __remove_pin_from_irq(data, mp_irqdomain_ioapic_idx(domain), + (int)irq_data->hwirq); + WARN_ON(!list_empty(&data->irq_2_pin)); + kfree(irq_data->chip_data); } - mutex_unlock(&ioapic_mutex); - - return ret; + irq_domain_free_irqs_top(domain, virq, nr_irqs); } -/* Enable IOAPIC early just for system timer */ -void __init pre_init_apic_IRQ0(void) +void mp_irqdomain_activate(struct irq_domain *domain, + struct irq_data *irq_data) { - struct io_apic_irq_attr attr = { 0, 0, 0, 0 }; + unsigned long flags; + struct irq_pin_list *entry; + struct mp_chip_data *data = irq_data->chip_data; - printk(KERN_INFO "Early APIC setup for system timer0\n"); -#ifndef CONFIG_SMP - physid_set_mask_of_physid(boot_cpu_physical_apicid, - &phys_cpu_present_map); -#endif - setup_local_APIC(); + raw_spin_lock_irqsave(&ioapic_lock, flags); + for_each_irq_pin(entry, data->irq_2_pin) + __ioapic_write_entry(entry->apic, entry->pin, data->entry); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); +} - io_apic_setup_irq_pin(0, 0, &attr); - irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, - "edge"); +void mp_irqdomain_deactivate(struct irq_domain *domain, + struct irq_data *irq_data) +{ + /* It won't be called for IRQ with multiple IOAPIC pins associated */ + ioapic_mask_entry(mp_irqdomain_ioapic_idx(domain), + (int)irq_data->hwirq); +} + +int mp_irqdomain_ioapic_idx(struct irq_domain *domain) +{ + return (int)(long)domain->host_data; } + +const struct irq_domain_ops mp_ioapic_irqdomain_ops = { + .alloc = mp_irqdomain_alloc, + .free = mp_irqdomain_free, + .activate = mp_irqdomain_activate, + .deactivate = mp_irqdomain_deactivate, +}; diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index d6ba2d660..1a9d735e0 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -3,6 +3,8 @@ * * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo * Moved from arch/x86/kernel/apic/io_apic.c. + * Jiang Liu <jiang.liu@linux.intel.com> + * Convert to hierarchical irqdomain * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -14,22 +16,23 @@ #include <linux/dmar.h> #include <linux/hpet.h> #include <linux/msi.h> +#include <asm/irqdomain.h> #include <asm/msidef.h> #include <asm/hpet.h> #include <asm/hw_irq.h> #include <asm/apic.h> #include <asm/irq_remapping.h> -void native_compose_msi_msg(struct pci_dev *pdev, - unsigned int irq, unsigned int dest, - struct msi_msg *msg, u8 hpet_id) +static struct irq_domain *msi_default_domain; + +static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) { - struct irq_cfg *cfg = irq_cfg(irq); + struct irq_cfg *cfg = irqd_cfg(data); msg->address_hi = MSI_ADDR_BASE_HI; if (x2apic_enabled()) - msg->address_hi |= MSI_ADDR_EXT_DEST_ID(dest); + msg->address_hi |= MSI_ADDR_EXT_DEST_ID(cfg->dest_apicid); msg->address_lo = MSI_ADDR_BASE_LO | @@ -39,7 +42,7 @@ void native_compose_msi_msg(struct pci_dev *pdev, ((apic->irq_delivery_mode != dest_LowestPrio) ? MSI_ADDR_REDIRECTION_CPU : MSI_ADDR_REDIRECTION_LOWPRI) | - MSI_ADDR_DEST_ID(dest); + MSI_ADDR_DEST_ID(cfg->dest_apicid); msg->data = MSI_DATA_TRIGGER_EDGE | @@ -50,180 +53,201 @@ void native_compose_msi_msg(struct pci_dev *pdev, MSI_DATA_VECTOR(cfg->vector); } -static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, - struct msi_msg *msg, u8 hpet_id) +/* + * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices, + * which implement the MSI or MSI-X Capability Structure. + */ +static struct irq_chip pci_msi_controller = { + .name = "PCI-MSI", + .irq_unmask = pci_msi_unmask_irq, + .irq_mask = pci_msi_mask_irq, + .irq_ack = irq_chip_ack_parent, + .irq_retrigger = irq_chip_retrigger_hierarchy, + .irq_compose_msi_msg = irq_msi_compose_msg, + .flags = IRQCHIP_SKIP_SET_WAKE, +}; + +int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) { - struct irq_cfg *cfg; - int err; - unsigned dest; + struct irq_domain *domain; + struct irq_alloc_info info; - if (disable_apic) - return -ENXIO; + init_irq_alloc_info(&info, NULL); + info.type = X86_IRQ_ALLOC_TYPE_MSI; + info.msi_dev = dev; - cfg = irq_cfg(irq); - err = assign_irq_vector(irq, cfg, apic->target_cpus()); - if (err) - return err; + domain = irq_remapping_get_irq_domain(&info); + if (domain == NULL) + domain = msi_default_domain; + if (domain == NULL) + return -ENOSYS; - err = apic->cpu_mask_to_apicid_and(cfg->domain, - apic->target_cpus(), &dest); - if (err) - return err; + return pci_msi_domain_alloc_irqs(domain, dev, nvec, type); +} - x86_msi.compose_msi_msg(pdev, irq, dest, msg, hpet_id); +void native_teardown_msi_irq(unsigned int irq) +{ + irq_domain_free_irqs(irq, 1); +} - return 0; +static irq_hw_number_t pci_msi_get_hwirq(struct msi_domain_info *info, + msi_alloc_info_t *arg) +{ + return arg->msi_hwirq; } -static int -msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) +static int pci_msi_prepare(struct irq_domain *domain, struct device *dev, + int nvec, msi_alloc_info_t *arg) { - struct irq_cfg *cfg = irqd_cfg(data); - struct msi_msg msg; - unsigned int dest; - int ret; + struct pci_dev *pdev = to_pci_dev(dev); + struct msi_desc *desc = first_pci_msi_entry(pdev); + + init_irq_alloc_info(arg, NULL); + arg->msi_dev = pdev; + if (desc->msi_attrib.is_msix) { + arg->type = X86_IRQ_ALLOC_TYPE_MSIX; + } else { + arg->type = X86_IRQ_ALLOC_TYPE_MSI; + arg->flags |= X86_IRQ_ALLOC_CONTIGUOUS_VECTORS; + } - ret = apic_set_affinity(data, mask, &dest); - if (ret) - return ret; + return 0; +} - __get_cached_msi_msg(data->msi_desc, &msg); +static void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) +{ + arg->msi_hwirq = pci_msi_domain_calc_hwirq(arg->msi_dev, desc); +} + +static struct msi_domain_ops pci_msi_domain_ops = { + .get_hwirq = pci_msi_get_hwirq, + .msi_prepare = pci_msi_prepare, + .set_desc = pci_msi_set_desc, +}; - msg.data &= ~MSI_DATA_VECTOR_MASK; - msg.data |= MSI_DATA_VECTOR(cfg->vector); - msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK; - msg.address_lo |= MSI_ADDR_DEST_ID(dest); +static struct msi_domain_info pci_msi_domain_info = { + .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_PCI_MSIX, + .ops = &pci_msi_domain_ops, + .chip = &pci_msi_controller, + .handler = handle_edge_irq, + .handler_name = "edge", +}; - __pci_write_msi_msg(data->msi_desc, &msg); +void arch_init_msi_domain(struct irq_domain *parent) +{ + if (disable_apic) + return; - return IRQ_SET_MASK_OK_NOCOPY; + msi_default_domain = pci_msi_create_irq_domain(NULL, + &pci_msi_domain_info, parent); + if (!msi_default_domain) + pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n"); } -/* - * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices, - * which implement the MSI or MSI-X Capability Structure. - */ -static struct irq_chip msi_chip = { - .name = "PCI-MSI", +#ifdef CONFIG_IRQ_REMAP +static struct irq_chip pci_msi_ir_controller = { + .name = "IR-PCI-MSI", .irq_unmask = pci_msi_unmask_irq, .irq_mask = pci_msi_mask_irq, - .irq_ack = apic_ack_edge, - .irq_set_affinity = msi_set_affinity, - .irq_retrigger = apic_retrigger_irq, + .irq_ack = irq_chip_ack_parent, + .irq_retrigger = irq_chip_retrigger_hierarchy, + .irq_set_vcpu_affinity = irq_chip_set_vcpu_affinity_parent, .flags = IRQCHIP_SKIP_SET_WAKE, }; -int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, - unsigned int irq_base, unsigned int irq_offset) -{ - struct irq_chip *chip = &msi_chip; - struct msi_msg msg; - unsigned int irq = irq_base + irq_offset; - int ret; - - ret = msi_compose_msg(dev, irq, &msg, -1); - if (ret < 0) - return ret; - - irq_set_msi_desc_off(irq_base, irq_offset, msidesc); - - /* - * MSI-X message is written per-IRQ, the offset is always 0. - * MSI message denotes a contiguous group of IRQs, written for 0th IRQ. - */ - if (!irq_offset) - pci_write_msi_msg(irq, &msg); +static struct msi_domain_info pci_msi_ir_domain_info = { + .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX, + .ops = &pci_msi_domain_ops, + .chip = &pci_msi_ir_controller, + .handler = handle_edge_irq, + .handler_name = "edge", +}; - setup_remapped_irq(irq, irq_cfg(irq), chip); +struct irq_domain *arch_create_msi_irq_domain(struct irq_domain *parent) +{ + return pci_msi_create_irq_domain(NULL, &pci_msi_ir_domain_info, parent); +} +#endif - irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge"); +#ifdef CONFIG_DMAR_TABLE +static void dmar_msi_write_msg(struct irq_data *data, struct msi_msg *msg) +{ + dmar_msi_write(data->irq, msg); +} - dev_dbg(&dev->dev, "irq %d for MSI/MSI-X\n", irq); +static struct irq_chip dmar_msi_controller = { + .name = "DMAR-MSI", + .irq_unmask = dmar_msi_unmask, + .irq_mask = dmar_msi_mask, + .irq_ack = irq_chip_ack_parent, + .irq_set_affinity = msi_domain_set_affinity, + .irq_retrigger = irq_chip_retrigger_hierarchy, + .irq_compose_msi_msg = irq_msi_compose_msg, + .irq_write_msi_msg = dmar_msi_write_msg, + .flags = IRQCHIP_SKIP_SET_WAKE, +}; - return 0; +static irq_hw_number_t dmar_msi_get_hwirq(struct msi_domain_info *info, + msi_alloc_info_t *arg) +{ + return arg->dmar_id; } -int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) +static int dmar_msi_init(struct irq_domain *domain, + struct msi_domain_info *info, unsigned int virq, + irq_hw_number_t hwirq, msi_alloc_info_t *arg) { - struct msi_desc *msidesc; - unsigned int irq; - int node, ret; + irq_domain_set_info(domain, virq, arg->dmar_id, info->chip, NULL, + handle_edge_irq, arg->dmar_data, "edge"); - /* Multiple MSI vectors only supported with interrupt remapping */ - if (type == PCI_CAP_ID_MSI && nvec > 1) - return 1; + return 0; +} - node = dev_to_node(&dev->dev); +static struct msi_domain_ops dmar_msi_domain_ops = { + .get_hwirq = dmar_msi_get_hwirq, + .msi_init = dmar_msi_init, +}; - list_for_each_entry(msidesc, &dev->msi_list, list) { - irq = irq_alloc_hwirq(node); - if (!irq) - return -ENOSPC; +static struct msi_domain_info dmar_msi_domain_info = { + .ops = &dmar_msi_domain_ops, + .chip = &dmar_msi_controller, +}; - ret = setup_msi_irq(dev, msidesc, irq, 0); - if (ret < 0) { - irq_free_hwirq(irq); - return ret; - } +static struct irq_domain *dmar_get_irq_domain(void) +{ + static struct irq_domain *dmar_domain; + static DEFINE_MUTEX(dmar_lock); - } - return 0; -} + mutex_lock(&dmar_lock); + if (dmar_domain == NULL) + dmar_domain = msi_create_irq_domain(NULL, &dmar_msi_domain_info, + x86_vector_domain); + mutex_unlock(&dmar_lock); -void native_teardown_msi_irq(unsigned int irq) -{ - irq_free_hwirq(irq); + return dmar_domain; } -#ifdef CONFIG_DMAR_TABLE -static int -dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, - bool force) +int dmar_alloc_hwirq(int id, int node, void *arg) { - struct irq_cfg *cfg = irqd_cfg(data); - unsigned int dest, irq = data->irq; - struct msi_msg msg; - int ret; - - ret = apic_set_affinity(data, mask, &dest); - if (ret) - return ret; + struct irq_domain *domain = dmar_get_irq_domain(); + struct irq_alloc_info info; - dmar_msi_read(irq, &msg); + if (!domain) + return -1; - msg.data &= ~MSI_DATA_VECTOR_MASK; - msg.data |= MSI_DATA_VECTOR(cfg->vector); - msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK; - msg.address_lo |= MSI_ADDR_DEST_ID(dest); - msg.address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(dest); + init_irq_alloc_info(&info, NULL); + info.type = X86_IRQ_ALLOC_TYPE_DMAR; + info.dmar_id = id; + info.dmar_data = arg; - dmar_msi_write(irq, &msg); - - return IRQ_SET_MASK_OK_NOCOPY; + return irq_domain_alloc_irqs(domain, 1, node, &info); } -static struct irq_chip dmar_msi_type = { - .name = "DMAR_MSI", - .irq_unmask = dmar_msi_unmask, - .irq_mask = dmar_msi_mask, - .irq_ack = apic_ack_edge, - .irq_set_affinity = dmar_msi_set_affinity, - .irq_retrigger = apic_retrigger_irq, - .flags = IRQCHIP_SKIP_SET_WAKE, -}; - -int arch_setup_dmar_msi(unsigned int irq) +void dmar_free_hwirq(int irq) { - int ret; - struct msi_msg msg; - - ret = msi_compose_msg(NULL, irq, &msg, -1); - if (ret < 0) - return ret; - dmar_msi_write(irq, &msg); - irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq, - "edge"); - return 0; + irq_domain_free_irqs(irq, 1); } #endif @@ -231,56 +255,103 @@ int arch_setup_dmar_msi(unsigned int irq) * MSI message composition */ #ifdef CONFIG_HPET_TIMER +static inline int hpet_dev_id(struct irq_domain *domain) +{ + struct msi_domain_info *info = msi_get_domain_info(domain); + + return (int)(long)info->data; +} -static int hpet_msi_set_affinity(struct irq_data *data, - const struct cpumask *mask, bool force) +static void hpet_msi_write_msg(struct irq_data *data, struct msi_msg *msg) { - struct irq_cfg *cfg = irqd_cfg(data); - struct msi_msg msg; - unsigned int dest; - int ret; + hpet_msi_write(data->handler_data, msg); +} - ret = apic_set_affinity(data, mask, &dest); - if (ret) - return ret; +static struct irq_chip hpet_msi_controller = { + .name = "HPET-MSI", + .irq_unmask = hpet_msi_unmask, + .irq_mask = hpet_msi_mask, + .irq_ack = irq_chip_ack_parent, + .irq_set_affinity = msi_domain_set_affinity, + .irq_retrigger = irq_chip_retrigger_hierarchy, + .irq_compose_msi_msg = irq_msi_compose_msg, + .irq_write_msi_msg = hpet_msi_write_msg, + .flags = IRQCHIP_SKIP_SET_WAKE, +}; - hpet_msi_read(data->handler_data, &msg); +static irq_hw_number_t hpet_msi_get_hwirq(struct msi_domain_info *info, + msi_alloc_info_t *arg) +{ + return arg->hpet_index; +} - msg.data &= ~MSI_DATA_VECTOR_MASK; - msg.data |= MSI_DATA_VECTOR(cfg->vector); - msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK; - msg.address_lo |= MSI_ADDR_DEST_ID(dest); +static int hpet_msi_init(struct irq_domain *domain, + struct msi_domain_info *info, unsigned int virq, + irq_hw_number_t hwirq, msi_alloc_info_t *arg) +{ + irq_set_status_flags(virq, IRQ_MOVE_PCNTXT); + irq_domain_set_info(domain, virq, arg->hpet_index, info->chip, NULL, + handle_edge_irq, arg->hpet_data, "edge"); - hpet_msi_write(data->handler_data, &msg); + return 0; +} - return IRQ_SET_MASK_OK_NOCOPY; +static void hpet_msi_free(struct irq_domain *domain, + struct msi_domain_info *info, unsigned int virq) +{ + irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT); } -static struct irq_chip hpet_msi_type = { - .name = "HPET_MSI", - .irq_unmask = hpet_msi_unmask, - .irq_mask = hpet_msi_mask, - .irq_ack = apic_ack_edge, - .irq_set_affinity = hpet_msi_set_affinity, - .irq_retrigger = apic_retrigger_irq, - .flags = IRQCHIP_SKIP_SET_WAKE, +static struct msi_domain_ops hpet_msi_domain_ops = { + .get_hwirq = hpet_msi_get_hwirq, + .msi_init = hpet_msi_init, + .msi_free = hpet_msi_free, +}; + +static struct msi_domain_info hpet_msi_domain_info = { + .ops = &hpet_msi_domain_ops, + .chip = &hpet_msi_controller, }; -int default_setup_hpet_msi(unsigned int irq, unsigned int id) +struct irq_domain *hpet_create_irq_domain(int hpet_id) { - struct irq_chip *chip = &hpet_msi_type; - struct msi_msg msg; - int ret; + struct irq_domain *parent; + struct irq_alloc_info info; + struct msi_domain_info *domain_info; + + if (x86_vector_domain == NULL) + return NULL; + + domain_info = kzalloc(sizeof(*domain_info), GFP_KERNEL); + if (!domain_info) + return NULL; + + *domain_info = hpet_msi_domain_info; + domain_info->data = (void *)(long)hpet_id; + + init_irq_alloc_info(&info, NULL); + info.type = X86_IRQ_ALLOC_TYPE_HPET; + info.hpet_id = hpet_id; + parent = irq_remapping_get_ir_irq_domain(&info); + if (parent == NULL) + parent = x86_vector_domain; + else + hpet_msi_controller.name = "IR-HPET-MSI"; + + return msi_create_irq_domain(NULL, domain_info, parent); +} - ret = msi_compose_msg(NULL, irq, &msg, id); - if (ret < 0) - return ret; +int hpet_assign_irq(struct irq_domain *domain, struct hpet_dev *dev, + int dev_num) +{ + struct irq_alloc_info info; - hpet_msi_write(irq_get_handler_data(irq), &msg); - irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - setup_remapped_irq(irq, irq_cfg(irq), chip); + init_irq_alloc_info(&info, NULL); + info.type = X86_IRQ_ALLOC_TYPE_HPET; + info.hpet_data = dev; + info.hpet_id = hpet_dev_id(domain); + info.hpet_index = dev_num; - irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge"); - return 0; + return irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, &info); } #endif diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 6cedd7914..2683f36e4 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -3,6 +3,8 @@ * * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo * Moved from arch/x86/kernel/apic/io_apic.c. + * Jiang Liu <jiang.liu@linux.intel.com> + * Enable support of hierarchical irqdomains * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -11,15 +13,28 @@ #include <linux/interrupt.h> #include <linux/init.h> #include <linux/compiler.h> -#include <linux/irqdomain.h> #include <linux/slab.h> +#include <asm/irqdomain.h> #include <asm/hw_irq.h> #include <asm/apic.h> #include <asm/i8259.h> #include <asm/desc.h> #include <asm/irq_remapping.h> +struct apic_chip_data { + struct irq_cfg cfg; + cpumask_var_t domain; + cpumask_var_t old_domain; + u8 move_in_progress : 1; +}; + +struct irq_domain *x86_vector_domain; static DEFINE_RAW_SPINLOCK(vector_lock); +static cpumask_var_t vector_cpumask; +static struct irq_chip lapic_controller; +#ifdef CONFIG_X86_IO_APIC +static struct apic_chip_data *legacy_irq_data[NR_IRQS_LEGACY]; +#endif void lock_vector_lock(void) { @@ -34,71 +49,59 @@ void unlock_vector_lock(void) raw_spin_unlock(&vector_lock); } -struct irq_cfg *irq_cfg(unsigned int irq) +static struct apic_chip_data *apic_chip_data(struct irq_data *irq_data) { - return irq_get_chip_data(irq); + if (!irq_data) + return NULL; + + while (irq_data->parent_data) + irq_data = irq_data->parent_data; + + return irq_data->chip_data; } struct irq_cfg *irqd_cfg(struct irq_data *irq_data) { - return irq_data->chip_data; + struct apic_chip_data *data = apic_chip_data(irq_data); + + return data ? &data->cfg : NULL; } -static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node) +struct irq_cfg *irq_cfg(unsigned int irq) { - struct irq_cfg *cfg; + return irqd_cfg(irq_get_irq_data(irq)); +} - cfg = kzalloc_node(sizeof(*cfg), GFP_KERNEL, node); - if (!cfg) +static struct apic_chip_data *alloc_apic_chip_data(int node) +{ + struct apic_chip_data *data; + + data = kzalloc_node(sizeof(*data), GFP_KERNEL, node); + if (!data) return NULL; - if (!zalloc_cpumask_var_node(&cfg->domain, GFP_KERNEL, node)) - goto out_cfg; - if (!zalloc_cpumask_var_node(&cfg->old_domain, GFP_KERNEL, node)) + if (!zalloc_cpumask_var_node(&data->domain, GFP_KERNEL, node)) + goto out_data; + if (!zalloc_cpumask_var_node(&data->old_domain, GFP_KERNEL, node)) goto out_domain; -#ifdef CONFIG_X86_IO_APIC - INIT_LIST_HEAD(&cfg->irq_2_pin); -#endif - return cfg; + return data; out_domain: - free_cpumask_var(cfg->domain); -out_cfg: - kfree(cfg); + free_cpumask_var(data->domain); +out_data: + kfree(data); return NULL; } -struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node) +static void free_apic_chip_data(struct apic_chip_data *data) { - int res = irq_alloc_desc_at(at, node); - struct irq_cfg *cfg; - - if (res < 0) { - if (res != -EEXIST) - return NULL; - cfg = irq_cfg(at); - if (cfg) - return cfg; + if (data) { + free_cpumask_var(data->domain); + free_cpumask_var(data->old_domain); + kfree(data); } - - cfg = alloc_irq_cfg(at, node); - if (cfg) - irq_set_chip_data(at, cfg); - else - irq_free_desc(at); - return cfg; } -static void free_irq_cfg(unsigned int at, struct irq_cfg *cfg) -{ - if (!cfg) - return; - irq_set_chip_data(at, NULL); - free_cpumask_var(cfg->domain); - free_cpumask_var(cfg->old_domain); - kfree(cfg); -} - -static int -__assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) +static int __assign_irq_vector(int irq, struct apic_chip_data *d, + const struct cpumask *mask) { /* * NOTE! The local APIC isn't very good at handling @@ -114,36 +117,33 @@ __assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START; static int current_offset = VECTOR_OFFSET_START % 16; int cpu, err; - cpumask_var_t tmp_mask; - if (cfg->move_in_progress) + if (d->move_in_progress) return -EBUSY; - if (!alloc_cpumask_var(&tmp_mask, GFP_ATOMIC)) - return -ENOMEM; - /* Only try and allocate irqs on cpus that are present */ err = -ENOSPC; - cpumask_clear(cfg->old_domain); + cpumask_clear(d->old_domain); cpu = cpumask_first_and(mask, cpu_online_mask); while (cpu < nr_cpu_ids) { int new_cpu, vector, offset; - apic->vector_allocation_domain(cpu, tmp_mask, mask); + apic->vector_allocation_domain(cpu, vector_cpumask, mask); - if (cpumask_subset(tmp_mask, cfg->domain)) { + if (cpumask_subset(vector_cpumask, d->domain)) { err = 0; - if (cpumask_equal(tmp_mask, cfg->domain)) + if (cpumask_equal(vector_cpumask, d->domain)) break; /* * New cpumask using the vector is a proper subset of * the current in use mask. So cleanup the vector * allocation for the members that are not used anymore. */ - cpumask_andnot(cfg->old_domain, cfg->domain, tmp_mask); - cfg->move_in_progress = - cpumask_intersects(cfg->old_domain, cpu_online_mask); - cpumask_and(cfg->domain, cfg->domain, tmp_mask); + cpumask_andnot(d->old_domain, d->domain, + vector_cpumask); + d->move_in_progress = + cpumask_intersects(d->old_domain, cpu_online_mask); + cpumask_and(d->domain, d->domain, vector_cpumask); break; } @@ -157,16 +157,18 @@ next: } if (unlikely(current_vector == vector)) { - cpumask_or(cfg->old_domain, cfg->old_domain, tmp_mask); - cpumask_andnot(tmp_mask, mask, cfg->old_domain); - cpu = cpumask_first_and(tmp_mask, cpu_online_mask); + cpumask_or(d->old_domain, d->old_domain, + vector_cpumask); + cpumask_andnot(vector_cpumask, mask, d->old_domain); + cpu = cpumask_first_and(vector_cpumask, + cpu_online_mask); continue; } if (test_bit(vector, used_vectors)) goto next; - for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) { + for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) { if (per_cpu(vector_irq, new_cpu)[vector] > VECTOR_UNDEFINED) goto next; @@ -174,55 +176,73 @@ next: /* Found one! */ current_vector = vector; current_offset = offset; - if (cfg->vector) { - cpumask_copy(cfg->old_domain, cfg->domain); - cfg->move_in_progress = - cpumask_intersects(cfg->old_domain, cpu_online_mask); + if (d->cfg.vector) { + cpumask_copy(d->old_domain, d->domain); + d->move_in_progress = + cpumask_intersects(d->old_domain, cpu_online_mask); } - for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) + for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) per_cpu(vector_irq, new_cpu)[vector] = irq; - cfg->vector = vector; - cpumask_copy(cfg->domain, tmp_mask); + d->cfg.vector = vector; + cpumask_copy(d->domain, vector_cpumask); err = 0; break; } - free_cpumask_var(tmp_mask); + + if (!err) { + /* cache destination APIC IDs into cfg->dest_apicid */ + err = apic->cpu_mask_to_apicid_and(mask, d->domain, + &d->cfg.dest_apicid); + } return err; } -int assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) +static int assign_irq_vector(int irq, struct apic_chip_data *data, + const struct cpumask *mask) { int err; unsigned long flags; raw_spin_lock_irqsave(&vector_lock, flags); - err = __assign_irq_vector(irq, cfg, mask); + err = __assign_irq_vector(irq, data, mask); raw_spin_unlock_irqrestore(&vector_lock, flags); return err; } -void clear_irq_vector(int irq, struct irq_cfg *cfg) +static int assign_irq_vector_policy(int irq, int node, + struct apic_chip_data *data, + struct irq_alloc_info *info) +{ + if (info && info->mask) + return assign_irq_vector(irq, data, info->mask); + if (node != NUMA_NO_NODE && + assign_irq_vector(irq, data, cpumask_of_node(node)) == 0) + return 0; + return assign_irq_vector(irq, data, apic->target_cpus()); +} + +static void clear_irq_vector(int irq, struct apic_chip_data *data) { int cpu, vector; unsigned long flags; raw_spin_lock_irqsave(&vector_lock, flags); - BUG_ON(!cfg->vector); + BUG_ON(!data->cfg.vector); - vector = cfg->vector; - for_each_cpu_and(cpu, cfg->domain, cpu_online_mask) + vector = data->cfg.vector; + for_each_cpu_and(cpu, data->domain, cpu_online_mask) per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; - cfg->vector = 0; - cpumask_clear(cfg->domain); + data->cfg.vector = 0; + cpumask_clear(data->domain); - if (likely(!cfg->move_in_progress)) { + if (likely(!data->move_in_progress)) { raw_spin_unlock_irqrestore(&vector_lock, flags); return; } - for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) { + for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) { for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { if (per_cpu(vector_irq, cpu)[vector] != irq) @@ -231,10 +251,95 @@ void clear_irq_vector(int irq, struct irq_cfg *cfg) break; } } - cfg->move_in_progress = 0; + data->move_in_progress = 0; raw_spin_unlock_irqrestore(&vector_lock, flags); } +void init_irq_alloc_info(struct irq_alloc_info *info, + const struct cpumask *mask) +{ + memset(info, 0, sizeof(*info)); + info->mask = mask; +} + +void copy_irq_alloc_info(struct irq_alloc_info *dst, struct irq_alloc_info *src) +{ + if (src) + *dst = *src; + else + memset(dst, 0, sizeof(*dst)); +} + +static void x86_vector_free_irqs(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + struct irq_data *irq_data; + int i; + + for (i = 0; i < nr_irqs; i++) { + irq_data = irq_domain_get_irq_data(x86_vector_domain, virq + i); + if (irq_data && irq_data->chip_data) { + clear_irq_vector(virq + i, irq_data->chip_data); + free_apic_chip_data(irq_data->chip_data); +#ifdef CONFIG_X86_IO_APIC + if (virq + i < nr_legacy_irqs()) + legacy_irq_data[virq + i] = NULL; +#endif + irq_domain_reset_irq_data(irq_data); + } + } +} + +static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) +{ + struct irq_alloc_info *info = arg; + struct apic_chip_data *data; + struct irq_data *irq_data; + int i, err; + + if (disable_apic) + return -ENXIO; + + /* Currently vector allocator can't guarantee contiguous allocations */ + if ((info->flags & X86_IRQ_ALLOC_CONTIGUOUS_VECTORS) && nr_irqs > 1) + return -ENOSYS; + + for (i = 0; i < nr_irqs; i++) { + irq_data = irq_domain_get_irq_data(domain, virq + i); + BUG_ON(!irq_data); +#ifdef CONFIG_X86_IO_APIC + if (virq + i < nr_legacy_irqs() && legacy_irq_data[virq + i]) + data = legacy_irq_data[virq + i]; + else +#endif + data = alloc_apic_chip_data(irq_data->node); + if (!data) { + err = -ENOMEM; + goto error; + } + + irq_data->chip = &lapic_controller; + irq_data->chip_data = data; + irq_data->hwirq = virq + i; + err = assign_irq_vector_policy(virq + i, irq_data->node, data, + info); + if (err) + goto error; + } + + return 0; + +error: + x86_vector_free_irqs(domain, virq, i + 1); + return err; +} + +static const struct irq_domain_ops x86_vector_domain_ops = { + .alloc = x86_vector_alloc_irqs, + .free = x86_vector_free_irqs, +}; + int __init arch_probe_nr_irqs(void) { int nr; @@ -258,8 +363,43 @@ int __init arch_probe_nr_irqs(void) return nr_legacy_irqs(); } +#ifdef CONFIG_X86_IO_APIC +static void init_legacy_irqs(void) +{ + int i, node = cpu_to_node(0); + struct apic_chip_data *data; + + /* + * For legacy IRQ's, start with assigning irq0 to irq15 to + * ISA_IRQ_VECTOR(i) for all cpu's. + */ + for (i = 0; i < nr_legacy_irqs(); i++) { + data = legacy_irq_data[i] = alloc_apic_chip_data(node); + BUG_ON(!data); + + data->cfg.vector = ISA_IRQ_VECTOR(i); + cpumask_setall(data->domain); + irq_set_chip_data(i, data); + } +} +#else +static void init_legacy_irqs(void) { } +#endif + int __init arch_early_irq_init(void) { + init_legacy_irqs(); + + x86_vector_domain = irq_domain_add_tree(NULL, &x86_vector_domain_ops, + NULL); + BUG_ON(x86_vector_domain == NULL); + irq_set_default_host(x86_vector_domain); + + arch_init_msi_domain(x86_vector_domain); + arch_init_htirq_domain(x86_vector_domain); + + BUG_ON(!alloc_cpumask_var(&vector_cpumask, GFP_KERNEL)); + return arch_early_ioapic_init(); } @@ -267,23 +407,17 @@ static void __setup_vector_irq(int cpu) { /* Initialize vector_irq on a new cpu */ int irq, vector; - struct irq_cfg *cfg; + struct apic_chip_data *data; - /* - * vector_lock will make sure that we don't run into irq vector - * assignments that might be happening on another cpu in parallel, - * while we setup our initial vector to irq mappings. - */ - raw_spin_lock(&vector_lock); /* Mark the inuse vectors */ for_each_active_irq(irq) { - cfg = irq_cfg(irq); - if (!cfg) + data = apic_chip_data(irq_get_irq_data(irq)); + if (!data) continue; - if (!cpumask_test_cpu(cpu, cfg->domain)) + if (!cpumask_test_cpu(cpu, data->domain)) continue; - vector = cfg->vector; + vector = data->cfg.vector; per_cpu(vector_irq, cpu)[vector] = irq; } /* Mark the free vectors */ @@ -292,20 +426,20 @@ static void __setup_vector_irq(int cpu) if (irq <= VECTOR_UNDEFINED) continue; - cfg = irq_cfg(irq); - if (!cpumask_test_cpu(cpu, cfg->domain)) + data = apic_chip_data(irq_get_irq_data(irq)); + if (!cpumask_test_cpu(cpu, data->domain)) per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; } - raw_spin_unlock(&vector_lock); } /* - * Setup the vector to irq mappings. + * Setup the vector to irq mappings. Must be called with vector_lock held. */ void setup_vector_irq(int cpu) { int irq; + lockdep_assert_held(&vector_lock); /* * On most of the platforms, legacy PIC delivers the interrupts on the * boot cpu. But there are certain platforms where PIC interrupts are @@ -314,20 +448,20 @@ void setup_vector_irq(int cpu) * legacy vector to irq mapping: */ for (irq = 0; irq < nr_legacy_irqs(); irq++) - per_cpu(vector_irq, cpu)[IRQ0_VECTOR + irq] = irq; + per_cpu(vector_irq, cpu)[ISA_IRQ_VECTOR(irq)] = irq; __setup_vector_irq(cpu); } -int apic_retrigger_irq(struct irq_data *data) +static int apic_retrigger_irq(struct irq_data *irq_data) { - struct irq_cfg *cfg = irqd_cfg(data); + struct apic_chip_data *data = apic_chip_data(irq_data); unsigned long flags; int cpu; raw_spin_lock_irqsave(&vector_lock, flags); - cpu = cpumask_first_and(cfg->domain, cpu_online_mask); - apic->send_IPI_mask(cpumask_of(cpu), cfg->vector); + cpu = cpumask_first_and(data->domain, cpu_online_mask); + apic->send_IPI_mask(cpumask_of(cpu), data->cfg.vector); raw_spin_unlock_irqrestore(&vector_lock, flags); return 1; @@ -340,73 +474,76 @@ void apic_ack_edge(struct irq_data *data) ack_APIC_irq(); } -/* - * Either sets data->affinity to a valid value, and returns - * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and - * leaves data->affinity untouched. - */ -int apic_set_affinity(struct irq_data *data, const struct cpumask *mask, - unsigned int *dest_id) +static int apic_set_affinity(struct irq_data *irq_data, + const struct cpumask *dest, bool force) { - struct irq_cfg *cfg = irqd_cfg(data); - unsigned int irq = data->irq; - int err; + struct apic_chip_data *data = irq_data->chip_data; + int err, irq = irq_data->irq; if (!config_enabled(CONFIG_SMP)) return -EPERM; - if (!cpumask_intersects(mask, cpu_online_mask)) + if (!cpumask_intersects(dest, cpu_online_mask)) return -EINVAL; - err = assign_irq_vector(irq, cfg, mask); - if (err) - return err; - - err = apic->cpu_mask_to_apicid_and(mask, cfg->domain, dest_id); + err = assign_irq_vector(irq, data, dest); if (err) { - if (assign_irq_vector(irq, cfg, data->affinity)) + struct irq_data *top = irq_get_irq_data(irq); + + if (assign_irq_vector(irq, data, top->affinity)) pr_err("Failed to recover vector for irq %d\n", irq); return err; } - cpumask_copy(data->affinity, mask); - - return 0; + return IRQ_SET_MASK_OK; } +static struct irq_chip lapic_controller = { + .irq_ack = apic_ack_edge, + .irq_set_affinity = apic_set_affinity, + .irq_retrigger = apic_retrigger_irq, +}; + #ifdef CONFIG_SMP -void send_cleanup_vector(struct irq_cfg *cfg) +static void __send_cleanup_vector(struct apic_chip_data *data) { cpumask_var_t cleanup_mask; if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) { unsigned int i; - for_each_cpu_and(i, cfg->old_domain, cpu_online_mask) + for_each_cpu_and(i, data->old_domain, cpu_online_mask) apic->send_IPI_mask(cpumask_of(i), IRQ_MOVE_CLEANUP_VECTOR); } else { - cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask); + cpumask_and(cleanup_mask, data->old_domain, cpu_online_mask); apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR); free_cpumask_var(cleanup_mask); } - cfg->move_in_progress = 0; + data->move_in_progress = 0; +} + +void send_cleanup_vector(struct irq_cfg *cfg) +{ + struct apic_chip_data *data; + + data = container_of(cfg, struct apic_chip_data, cfg); + if (data->move_in_progress) + __send_cleanup_vector(data); } asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) { unsigned vector, me; - ack_APIC_irq(); - irq_enter(); - exit_idle(); + entering_ack_irq(); me = smp_processor_id(); for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { int irq; unsigned int irr; struct irq_desc *desc; - struct irq_cfg *cfg; + struct apic_chip_data *data; irq = __this_cpu_read(vector_irq[vector]); @@ -417,8 +554,8 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) if (!desc) continue; - cfg = irq_cfg(irq); - if (!cfg) + data = apic_chip_data(&desc->irq_data); + if (!data) continue; raw_spin_lock(&desc->lock); @@ -427,10 +564,11 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) * Check if the irq migration is in progress. If so, we * haven't received the cleanup request yet for this irq. */ - if (cfg->move_in_progress) + if (data->move_in_progress) goto unlock; - if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) + if (vector == data->cfg.vector && + cpumask_test_cpu(me, data->domain)) goto unlock; irr = apic_read(APIC_IRR + (vector / 32 * 0x10)); @@ -450,20 +588,21 @@ unlock: raw_spin_unlock(&desc->lock); } - irq_exit(); + exiting_irq(); } static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector) { unsigned me; + struct apic_chip_data *data; - if (likely(!cfg->move_in_progress)) + data = container_of(cfg, struct apic_chip_data, cfg); + if (likely(!data->move_in_progress)) return; me = smp_processor_id(); - - if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) - send_cleanup_vector(cfg); + if (vector == data->cfg.vector && cpumask_test_cpu(me, data->domain)) + __send_cleanup_vector(data); } void irq_complete_move(struct irq_cfg *cfg) @@ -475,46 +614,11 @@ void irq_force_complete_move(int irq) { struct irq_cfg *cfg = irq_cfg(irq); - if (!cfg) - return; - - __irq_complete_move(cfg, cfg->vector); + if (cfg) + __irq_complete_move(cfg, cfg->vector); } #endif -/* - * Dynamic irq allocate and deallocation. Should be replaced by irq domains! - */ -int arch_setup_hwirq(unsigned int irq, int node) -{ - struct irq_cfg *cfg; - unsigned long flags; - int ret; - - cfg = alloc_irq_cfg(irq, node); - if (!cfg) - return -ENOMEM; - - raw_spin_lock_irqsave(&vector_lock, flags); - ret = __assign_irq_vector(irq, cfg, apic->target_cpus()); - raw_spin_unlock_irqrestore(&vector_lock, flags); - - if (!ret) - irq_set_chip_data(irq, cfg); - else - free_irq_cfg(irq, cfg); - return ret; -} - -void arch_teardown_hwirq(unsigned int irq) -{ - struct irq_cfg *cfg = irq_cfg(irq); - - free_remapped_irq(irq); - clear_irq_vector(irq, cfg); - free_irq_cfg(irq, cfg); -} - static void __init print_APIC_field(int base) { int i; diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 6fae733e9..3ffd92565 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -21,11 +21,13 @@ early_param("x2apic_phys", set_x2apic_phys_mode); static bool x2apic_fadt_phys(void) { +#ifdef CONFIG_ACPI if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) && (acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) { printk(KERN_DEBUG "System requires x2apic physical mode\n"); return true; } +#endif return false; } diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 9f6b93419..8e3d22a1a 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -41,6 +41,25 @@ void common(void) { OFFSET(pbe_orig_address, pbe, orig_address); OFFSET(pbe_next, pbe, next); +#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) + BLANK(); + OFFSET(IA32_SIGCONTEXT_ax, sigcontext_ia32, ax); + OFFSET(IA32_SIGCONTEXT_bx, sigcontext_ia32, bx); + OFFSET(IA32_SIGCONTEXT_cx, sigcontext_ia32, cx); + OFFSET(IA32_SIGCONTEXT_dx, sigcontext_ia32, dx); + OFFSET(IA32_SIGCONTEXT_si, sigcontext_ia32, si); + OFFSET(IA32_SIGCONTEXT_di, sigcontext_ia32, di); + OFFSET(IA32_SIGCONTEXT_bp, sigcontext_ia32, bp); + OFFSET(IA32_SIGCONTEXT_sp, sigcontext_ia32, sp); + OFFSET(IA32_SIGCONTEXT_ip, sigcontext_ia32, ip); + + BLANK(); + OFFSET(TI_sysenter_return, thread_info, sysenter_return); + + BLANK(); + OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext); +#endif + #ifdef CONFIG_PARAVIRT BLANK(); OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled); @@ -49,7 +68,9 @@ void common(void) { OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable); OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable); OFFSET(PV_CPU_iret, pv_cpu_ops, iret); +#ifdef CONFIG_X86_32 OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit); +#endif OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0); OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2); #endif diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index 47703aed7..6ce39025f 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -17,17 +17,6 @@ void foo(void); void foo(void) { - OFFSET(IA32_SIGCONTEXT_ax, sigcontext, ax); - OFFSET(IA32_SIGCONTEXT_bx, sigcontext, bx); - OFFSET(IA32_SIGCONTEXT_cx, sigcontext, cx); - OFFSET(IA32_SIGCONTEXT_dx, sigcontext, dx); - OFFSET(IA32_SIGCONTEXT_si, sigcontext, si); - OFFSET(IA32_SIGCONTEXT_di, sigcontext, di); - OFFSET(IA32_SIGCONTEXT_bp, sigcontext, bp); - OFFSET(IA32_SIGCONTEXT_sp, sigcontext, sp); - OFFSET(IA32_SIGCONTEXT_ip, sigcontext, ip); - BLANK(); - OFFSET(CPUINFO_x86, cpuinfo_x86, x86); OFFSET(CPUINFO_x86_vendor, cpuinfo_x86, x86_vendor); OFFSET(CPUINFO_x86_model, cpuinfo_x86, x86_model); @@ -37,10 +26,6 @@ void foo(void) OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id); BLANK(); - OFFSET(TI_sysenter_return, thread_info, sysenter_return); - OFFSET(TI_cpu, thread_info, cpu); - BLANK(); - OFFSET(PT_EBX, pt_regs, bx); OFFSET(PT_ECX, pt_regs, cx); OFFSET(PT_EDX, pt_regs, dx); @@ -60,9 +45,6 @@ void foo(void) OFFSET(PT_OLDSS, pt_regs, ss); BLANK(); - OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe, uc.uc_mcontext); - BLANK(); - OFFSET(saved_context_gdt_desc, saved_context, gdt_desc); BLANK(); diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 5ce6f2da8..d8f42f902 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -29,27 +29,6 @@ int main(void) BLANK(); #endif -#ifdef CONFIG_IA32_EMULATION - OFFSET(TI_sysenter_return, thread_info, sysenter_return); - BLANK(); - -#define ENTRY(entry) OFFSET(IA32_SIGCONTEXT_ ## entry, sigcontext_ia32, entry) - ENTRY(ax); - ENTRY(bx); - ENTRY(cx); - ENTRY(dx); - ENTRY(si); - ENTRY(di); - ENTRY(bp); - ENTRY(sp); - ENTRY(ip); - BLANK(); -#undef ENTRY - - OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext); - BLANK(); -#endif - #define ENTRY(entry) OFFSET(pt_regs_ ## entry, pt_regs, entry) ENTRY(bx); ENTRY(cx); @@ -87,7 +66,7 @@ int main(void) DEFINE(__NR_syscall_max, sizeof(syscalls_64) - 1); DEFINE(NR_syscalls, sizeof(syscalls_64)); - DEFINE(__NR_ia32_syscall_max, sizeof(syscalls_ia32) - 1); + DEFINE(__NR_syscall_compat_max, sizeof(syscalls_ia32) - 1); DEFINE(IA32_NR_syscalls, sizeof(syscalls_ia32)); return 0; diff --git a/arch/x86/kernel/bootflag.c b/arch/x86/kernel/bootflag.c index 5de7f4c56..52c8e3c77 100644 --- a/arch/x86/kernel/bootflag.c +++ b/arch/x86/kernel/bootflag.c @@ -98,4 +98,4 @@ static int __init sbf_init(void) return 0; } -module_init(sbf_init); +arch_initcall(sbf_init); diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c index 83a799562..58118e207 100644 --- a/arch/x86/kernel/check.c +++ b/arch/x86/kernel/check.c @@ -91,7 +91,8 @@ void __init setup_bios_corruption_check(void) corruption_check_size = round_up(corruption_check_size, PAGE_SIZE); - for_each_free_mem_range(i, NUMA_NO_NODE, &start, &end, NULL) { + for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, + NULL) { start = clamp_t(phys_addr_t, round_up(start, PAGE_SIZE), PAGE_SIZE, corruption_check_size); end = clamp_t(phys_addr_t, round_down(end, PAGE_SIZE), diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index e4cf63301..dd3a4baff 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -19,6 +19,13 @@ #include "cpu.h" +/* + * nodes_per_socket: Stores the number of nodes per socket. + * Refer to Fam15h Models 00-0fh BKDG - CPUID Fn8000_001E_ECX + * Node Identifiers[10:8] + */ +static u32 nodes_per_socket = 1; + static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p) { u32 gprs[8] = { 0 }; @@ -288,10 +295,10 @@ static int nearby_node(int apicid) * Assumption: Number of cores in each internal node is the same. * (2) AMD processors supporting compute units */ -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP static void amd_get_topology(struct cpuinfo_x86 *c) { - u32 nodes, cores_per_cu = 1; + u32 cores_per_cu = 1; u8 node_id; int cpu = smp_processor_id(); @@ -300,7 +307,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c) u32 eax, ebx, ecx, edx; cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); - nodes = ((ecx >> 8) & 7) + 1; + nodes_per_socket = ((ecx >> 8) & 7) + 1; node_id = ecx & 7; /* get compute unit information */ @@ -311,18 +318,18 @@ static void amd_get_topology(struct cpuinfo_x86 *c) u64 value; rdmsrl(MSR_FAM10H_NODE_ID, value); - nodes = ((value >> 3) & 7) + 1; + nodes_per_socket = ((value >> 3) & 7) + 1; node_id = value & 7; } else return; /* fixup multi-node processor information */ - if (nodes > 1) { + if (nodes_per_socket > 1) { u32 cores_per_node; u32 cus_per_node; set_cpu_cap(c, X86_FEATURE_AMD_DCM); - cores_per_node = c->x86_max_cores / nodes; + cores_per_node = c->x86_max_cores / nodes_per_socket; cus_per_node = cores_per_node / cores_per_cu; /* store NodeID, use llc_shared_map to store sibling info */ @@ -341,7 +348,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c) */ static void amd_detect_cmp(struct cpuinfo_x86 *c) { -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP unsigned bits; int cpu = smp_processor_id(); @@ -366,6 +373,12 @@ u16 amd_get_nb_id(int cpu) } EXPORT_SYMBOL_GPL(amd_get_nb_id); +u32 amd_get_nodes_per_socket(void) +{ + return nodes_per_socket; +} +EXPORT_SYMBOL_GPL(amd_get_nodes_per_socket); + static void srat_detect_node(struct cpuinfo_x86 *c) { #ifdef CONFIG_NUMA @@ -420,7 +433,7 @@ static void srat_detect_node(struct cpuinfo_x86 *c) static void early_init_amd_mc(struct cpuinfo_x86 *c) { -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP unsigned bits, ecx; /* Multi core CPU? */ @@ -520,8 +533,16 @@ static void early_init_amd(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_K6_MTRR); #endif #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI) - /* check CPU config space for extended APIC ID */ - if (cpu_has_apic && c->x86 >= 0xf) { + /* + * ApicID can always be treated as an 8-bit value for AMD APIC versions + * >= 0x10, but even old K8s came out of reset with version 0x10. So, we + * can safely set X86_FEATURE_EXTD_APICID unconditionally for families + * after 16h. + */ + if (cpu_has_apic && c->x86 > 0x16) { + set_cpu_cap(c, X86_FEATURE_EXTD_APICID); + } else if (cpu_has_apic && c->x86 >= 0xf) { + /* check CPU config space for extended APIC ID */ unsigned int val; val = read_pci_config(0, 24, 0, 0x68); if ((val & ((1 << 17) | (1 << 18))) == ((1 << 17) | (1 << 18))) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 03445346e..bd17db15a 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -12,57 +12,11 @@ #include <asm/bugs.h> #include <asm/processor.h> #include <asm/processor-flags.h> -#include <asm/i387.h> +#include <asm/fpu/internal.h> #include <asm/msr.h> #include <asm/paravirt.h> #include <asm/alternative.h> -static double __initdata x = 4195835.0; -static double __initdata y = 3145727.0; - -/* - * This used to check for exceptions.. - * However, it turns out that to support that, - * the XMM trap handlers basically had to - * be buggy. So let's have a correct XMM trap - * handler, and forget about printing out - * some status at boot. - * - * We should really only care about bugs here - * anyway. Not features. - */ -static void __init check_fpu(void) -{ - s32 fdiv_bug; - - kernel_fpu_begin(); - - /* - * trap_init() enabled FXSR and company _before_ testing for FP - * problems here. - * - * Test for the divl bug: http://en.wikipedia.org/wiki/Fdiv_bug - */ - __asm__("fninit\n\t" - "fldl %1\n\t" - "fdivl %2\n\t" - "fmull %2\n\t" - "fldl %1\n\t" - "fsubp %%st,%%st(1)\n\t" - "fistpl %0\n\t" - "fwait\n\t" - "fninit" - : "=m" (*&fdiv_bug) - : "m" (*&x), "m" (*&y)); - - kernel_fpu_end(); - - if (fdiv_bug) { - set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV); - pr_warn("Hmm, FPU with FDIV bug\n"); - } -} - void __init check_bugs(void) { identify_boot_cpu(); @@ -85,10 +39,5 @@ void __init check_bugs(void) '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); alternative_instructions(); - /* - * kernel_fpu_begin/end() in check_fpu() relies on the patched - * alternative instructions. - */ - if (cpu_has_fpu) - check_fpu(); + fpu__init_check_bugs(); } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index a62cf04da..cb9e5df42 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -5,6 +5,7 @@ #include <linux/module.h> #include <linux/percpu.h> #include <linux/string.h> +#include <linux/ctype.h> #include <linux/delay.h> #include <linux/sched.h> #include <linux/init.h> @@ -31,8 +32,7 @@ #include <asm/setup.h> #include <asm/apic.h> #include <asm/desc.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/mtrr.h> #include <linux/numa.h> #include <asm/asm.h> @@ -145,32 +145,21 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { } }; EXPORT_PER_CPU_SYMBOL_GPL(gdt_page); -static int __init x86_xsave_setup(char *s) +static int __init x86_mpx_setup(char *s) { + /* require an exact match without trailing characters */ if (strlen(s)) return 0; - setup_clear_cpu_cap(X86_FEATURE_XSAVE); - setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); - setup_clear_cpu_cap(X86_FEATURE_XSAVES); - setup_clear_cpu_cap(X86_FEATURE_AVX); - setup_clear_cpu_cap(X86_FEATURE_AVX2); - return 1; -} -__setup("noxsave", x86_xsave_setup); -static int __init x86_xsaveopt_setup(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); - return 1; -} -__setup("noxsaveopt", x86_xsaveopt_setup); + /* do not emit a message if the feature is not present */ + if (!boot_cpu_has(X86_FEATURE_MPX)) + return 1; -static int __init x86_xsaves_setup(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_XSAVES); + setup_clear_cpu_cap(X86_FEATURE_MPX); + pr_info("nompx: Intel Memory Protection Extensions (MPX) disabled\n"); return 1; } -__setup("noxsaves", x86_xsaves_setup); +__setup("nompx", x86_mpx_setup); #ifdef CONFIG_X86_32 static int cachesize_override = -1; @@ -183,14 +172,6 @@ static int __init cachesize_setup(char *str) } __setup("cachesize=", cachesize_setup); -static int __init x86_fxsr_setup(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_FXSR); - setup_clear_cpu_cap(X86_FEATURE_XMM); - return 1; -} -__setup("nofxsr", x86_fxsr_setup); - static int __init x86_sep_setup(char *s) { setup_clear_cpu_cap(X86_FEATURE_SEP); @@ -419,7 +400,7 @@ static const struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {}; static void get_model_name(struct cpuinfo_x86 *c) { unsigned int *v; - char *p, *q; + char *p, *q, *s; if (c->extended_cpuid_level < 0x80000004) return; @@ -430,19 +411,21 @@ static void get_model_name(struct cpuinfo_x86 *c) cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]); c->x86_model_id[48] = 0; - /* - * Intel chips right-justify this string for some dumb reason; - * undo that brain damage: - */ - p = q = &c->x86_model_id[0]; + /* Trim whitespace */ + p = q = s = &c->x86_model_id[0]; + while (*p == ' ') p++; - if (p != q) { - while (*p) - *q++ = *p++; - while (q <= &c->x86_model_id[48]) - *q++ = '\0'; /* Zero-pad the rest */ + + while (*p) { + /* Note the last non-whitespace index */ + if (!isspace(*p)) + s = q; + + *q++ = *p++; } + + *(s + 1) = '\0'; } void cpu_detect_cache_sizes(struct cpuinfo_x86 *c) @@ -508,7 +491,7 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c) void detect_ht(struct cpuinfo_x86 *c) { -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP u32 eax, ebx, ecx, edx; int index_msb, core_bits; static bool printed; @@ -759,7 +742,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) cpu_detect(c); get_cpu_vendor(c); get_cpu_cap(c); - fpu_detect(c); if (this_cpu->c_early_init) this_cpu->c_early_init(c); @@ -771,6 +753,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) this_cpu->c_bsp_init(c); setup_force_cpu_cap(X86_FEATURE_ALWAYS); + fpu__init_system(c); } void __init early_cpu_init(void) @@ -844,7 +827,7 @@ static void generic_identify(struct cpuinfo_x86 *c) if (c->cpuid_level >= 0x00000001) { c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF; #ifdef CONFIG_X86_32 -# ifdef CONFIG_X86_HT +# ifdef CONFIG_SMP c->apicid = apic->phys_pkg_id(c->initial_apicid, 0); # else c->apicid = c->initial_apicid; @@ -1026,7 +1009,7 @@ void enable_sep_cpu(void) (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack), 0); - wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)ia32_sysenter_target, 0); + wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0); out: put_cpu(); @@ -1122,7 +1105,7 @@ void print_cpu_info(struct cpuinfo_x86 *c) printk(KERN_CONT "%s ", vendor); if (c->x86_model_id[0]) - printk(KERN_CONT "%s", strim(c->x86_model_id)); + printk(KERN_CONT "%s", c->x86_model_id); else printk(KERN_CONT "%d86", c->x86); @@ -1155,10 +1138,6 @@ static __init int setup_disablecpuid(char *arg) } __setup("clearcpuid=", setup_disablecpuid); -DEFINE_PER_CPU(unsigned long, kernel_stack) = - (unsigned long)&init_thread_union + THREAD_SIZE; -EXPORT_PER_CPU_SYMBOL(kernel_stack); - #ifdef CONFIG_X86_64 struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table }; struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1, @@ -1183,8 +1162,6 @@ DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1; DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT; EXPORT_PER_CPU_SYMBOL(__preempt_count); -DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); - /* * Special IST stacks which the CPU switches to when it calls * an IST-marked descriptor entry. Up to 7 stacks (hardware @@ -1208,10 +1185,10 @@ void syscall_init(void) * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip. */ wrmsrl(MSR_STAR, ((u64)__USER32_CS)<<48 | ((u64)__KERNEL_CS)<<32); - wrmsrl(MSR_LSTAR, system_call); + wrmsrl(MSR_LSTAR, entry_SYSCALL_64); #ifdef CONFIG_IA32_EMULATION - wrmsrl(MSR_CSTAR, ia32_cstar_target); + wrmsrl(MSR_CSTAR, entry_SYSCALL_compat); /* * This only works on Intel CPUs. * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP. @@ -1220,7 +1197,7 @@ void syscall_init(void) */ wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); - wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target); + wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat); #else wrmsrl(MSR_CSTAR, ignore_sysret); wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG); @@ -1275,7 +1252,6 @@ DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task; EXPORT_PER_CPU_SYMBOL(current_task); DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT; EXPORT_PER_CPU_SYMBOL(__preempt_count); -DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); /* * On x86_32, vm86 modifies tss.sp0, so sp0 isn't a reliable way to find @@ -1434,12 +1410,12 @@ void cpu_init(void) load_sp0(t, ¤t->thread); set_tss_desc(cpu, t); load_TR_desc(); - load_LDT(&init_mm.context); + load_mm_ldt(&init_mm); clear_all_debug_regs(); dbg_restore_debug_regs(); - fpu_init(); + fpu__init_cpu(); if (is_uv_system()) uv_cpu_init(); @@ -1483,7 +1459,7 @@ void cpu_init(void) load_sp0(t, thread); set_tss_desc(cpu, t); load_TR_desc(); - load_LDT(&init_mm.context); + load_mm_ldt(&init_mm); t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap); @@ -1495,7 +1471,7 @@ void cpu_init(void) clear_all_debug_regs(); dbg_restore_debug_regs(); - fpu_init(); + fpu__init_cpu(); } #endif diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index ba2546f0d..50163fa90 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -27,7 +27,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) { - bool allow_fast_string = true; + u64 misc_enable; /* Unmask CPUID levels if masked: */ if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) { @@ -126,28 +126,17 @@ static void early_init_intel(struct cpuinfo_x86 *c) * Ingo Molnar reported a Pentium D (model 6) and a Xeon * (model 2) with the same problem. */ - if (c->x86 == 15) { - allow_fast_string = false; - + if (c->x86 == 15) if (msr_clear_bit(MSR_IA32_MISC_ENABLE, MSR_IA32_MISC_ENABLE_FAST_STRING_BIT) > 0) pr_info("kmemcheck: Disabling fast string operations\n"); - } #endif /* - * If BIOS didn't enable fast string operation, try to enable - * it ourselves. If that fails, then clear the fast string - * and enhanced fast string CPU capabilities. + * If fast string is not enabled in IA32_MISC_ENABLE for any reason, + * clear the fast string and enhanced fast string CPU capabilities. */ if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) { - u64 misc_enable; - - if (allow_fast_string && - msr_set_bit(MSR_IA32_MISC_ENABLE, - MSR_IA32_MISC_ENABLE_FAST_STRING_BIT) > 0) - pr_info(FW_WARN "IA32_MISC_ENABLE.FAST_STRING_ENABLE was not set\n"); - rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable); if (!(misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING)) { printk(KERN_INFO "Disabled fast string operations\n"); @@ -504,24 +493,6 @@ static void init_intel(struct cpuinfo_x86 *c) wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb); } } - - /* Enable monitor/mwait if BIOS didn't do it for us. */ - if (!cpu_has(c, X86_FEATURE_MWAIT) && cpu_has(c, X86_FEATURE_XMM3) - && c->x86 >= 6 && !(c->x86 == 6 && c->x86_model < 0x1c) - && !(c->x86 == 0xf && c->x86_model < 3)) { - /* - * Some non-SSE3 cpus will #GP. We check for that, - * but it can't hurt to be safe. - */ - msr_set_bit(MSR_IA32_MISC_ENABLE, MSR_IA32_MISC_ENABLE_MWAIT_BIT); - - /* Re-read monitor capability. */ - if (cpuid_ecx(1) & 0x8) { - set_cpu_cap(c, X86_FEATURE_MWAIT); - - printk(KERN_WARNING FW_WARN "IA32_MISC_ENABLE.ENABLE_MONITOR_FSM was not set\n"); - } - } } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index edcb0e28c..be4febc58 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -654,7 +654,7 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c) unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */ unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */ unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb; -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP unsigned int cpu = c->cpu_index; #endif @@ -773,19 +773,19 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c) if (new_l2) { l2 = new_l2; -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP per_cpu(cpu_llc_id, cpu) = l2_id; #endif } if (new_l3) { l3 = new_l3; -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP per_cpu(cpu_llc_id, cpu) = l3_id; #endif } -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP /* * If cpu_llc_id is not yet set, this means cpuid_level < 4 which in * turns means that the only possibility is SMT (as indicated in diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 20190bdac..df919ff10 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -53,9 +53,12 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex); #define rcu_dereference_check_mce(p) \ - rcu_dereference_index_check((p), \ - rcu_read_lock_sched_held() || \ - lockdep_is_held(&mce_chrdev_read_mutex)) +({ \ + rcu_lockdep_assert(rcu_read_lock_sched_held() || \ + lockdep_is_held(&mce_chrdev_read_mutex), \ + "suspicious rcu_dereference_check_mce() usage"); \ + smp_load_acquire(&(p)); \ +}) #define CREATE_TRACE_POINTS #include <trace/events/mce.h> @@ -1050,6 +1053,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) char *msg = "Unknown"; u64 recover_paddr = ~0ull; int flags = MF_ACTION_REQUIRED; + int lmce = 0; prev_state = ist_enter(regs); @@ -1077,11 +1081,20 @@ void do_machine_check(struct pt_regs *regs, long error_code) kill_it = 1; /* - * Go through all the banks in exclusion of the other CPUs. - * This way we don't report duplicated events on shared banks - * because the first one to see it will clear it. + * Check if this MCE is signaled to only this logical processor */ - order = mce_start(&no_way_out); + if (m.mcgstatus & MCG_STATUS_LMCES) + lmce = 1; + else { + /* + * Go through all the banks in exclusion of the other CPUs. + * This way we don't report duplicated events on shared banks + * because the first one to see it will clear it. + * If this is a Local MCE, then no need to perform rendezvous. + */ + order = mce_start(&no_way_out); + } + for (i = 0; i < cfg->banks; i++) { __clear_bit(i, toclear); if (!test_bit(i, valid_banks)) @@ -1158,8 +1171,18 @@ void do_machine_check(struct pt_regs *regs, long error_code) * Do most of the synchronization with other CPUs. * When there's any problem use only local no_way_out state. */ - if (mce_end(order) < 0) - no_way_out = worst >= MCE_PANIC_SEVERITY; + if (!lmce) { + if (mce_end(order) < 0) + no_way_out = worst >= MCE_PANIC_SEVERITY; + } else { + /* + * Local MCE skipped calling mce_reign() + * If we found a fatal error, we need to panic here. + */ + if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) + mce_panic("Machine check from unknown source", + NULL, NULL); + } /* * At insane "tolerant" levels we take no action. Otherwise @@ -1640,10 +1663,16 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) mce_intel_feature_init(c); mce_adjust_timer = cmci_intel_adjust_timer; break; - case X86_VENDOR_AMD: + + case X86_VENDOR_AMD: { + u32 ebx = cpuid_ebx(0x80000007); + mce_amd_feature_init(c); - mce_flags.overflow_recov = cpuid_ebx(0x80000007) & 0x1; + mce_flags.overflow_recov = !!(ebx & BIT(0)); + mce_flags.succor = !!(ebx & BIT(1)); break; + } + default: break; } @@ -1887,7 +1916,7 @@ out: static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait) { poll_wait(file, &mce_chrdev_wait, wait); - if (rcu_access_index(mcelog.next)) + if (READ_ONCE(mcelog.next)) return POLLIN | POLLRDNORM; if (!mce_apei_read_done && apei_check_mce()) return POLLIN | POLLRDNORM; @@ -1932,8 +1961,8 @@ void register_mce_write_callback(ssize_t (*fn)(struct file *filp, } EXPORT_SYMBOL_GPL(register_mce_write_callback); -ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf, - size_t usize, loff_t *off) +static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf, + size_t usize, loff_t *off) { if (mce_write) return mce_write(filp, ubuf, usize, off); @@ -1979,6 +2008,7 @@ void mce_disable_bank(int bank) /* * mce=off Disables machine check * mce=no_cmci Disables CMCI + * mce=no_lmce Disables LMCE * mce=dont_log_ce Clears corrected events silently, no log created for CEs. * mce=ignore_ce Disables polling and CMCI, corrected events are not cleared. * mce=TOLERANCELEVEL[,monarchtimeout] (number, see above) @@ -2002,6 +2032,8 @@ static int __init mcheck_enable(char *str) cfg->disabled = true; else if (!strcmp(str, "no_cmci")) cfg->cmci_disabled = true; + else if (!strcmp(str, "no_lmce")) + cfg->lmce_disabled = true; else if (!strcmp(str, "dont_log_ce")) cfg->dont_log_ce = true; else if (!strcmp(str, "ignore_ce")) @@ -2011,11 +2043,8 @@ static int __init mcheck_enable(char *str) else if (!strcmp(str, "bios_cmci_threshold")) cfg->bios_cmci_threshold = true; else if (isdigit(str[0])) { - get_option(&str, &(cfg->tolerant)); - if (*str == ',') { - ++str; + if (get_option(&str, &cfg->tolerant) == 2) get_option(&str, &(cfg->monarch_timeout)); - } } else { pr_info("mce argument %s ignored. Please use /sys\n", str); return 0; diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 55ad9b37c..e99b15077 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -1,19 +1,13 @@ /* - * (c) 2005-2012 Advanced Micro Devices, Inc. + * (c) 2005-2015 Advanced Micro Devices, Inc. * Your use of this code is subject to the terms and conditions of the * GNU general public license version 2. See "COPYING" or * http://www.gnu.org/licenses/gpl.html * * Written by Jacob Shin - AMD, Inc. - * * Maintained by: Borislav Petkov <bp@alien8.de> * - * April 2006 - * - added support for AMD Family 0x10 processors - * May 2012 - * - major scrubbing - * - * All MC4_MISCi registers are shared between multi-cores + * All MC4_MISCi registers are shared between cores on a node. */ #include <linux/interrupt.h> #include <linux/notifier.h> @@ -32,6 +26,7 @@ #include <asm/idle.h> #include <asm/mce.h> #include <asm/msr.h> +#include <asm/trace/irq_vectors.h> #define NR_BLOCKS 9 #define THRESHOLD_MAX 0xFFF @@ -47,6 +42,13 @@ #define MASK_BLKPTR_LO 0xFF000000 #define MCG_XBLK_ADDR 0xC0000400 +/* Deferred error settings */ +#define MSR_CU_DEF_ERR 0xC0000410 +#define MASK_DEF_LVTOFF 0x000000F0 +#define MASK_DEF_INT_TYPE 0x00000006 +#define DEF_LVT_OFF 0x2 +#define DEF_INT_TYPE_APIC 0x2 + static const char * const th_names[] = { "load_store", "insn_fetch", @@ -60,6 +62,13 @@ static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks); static DEFINE_PER_CPU(unsigned char, bank_map); /* see which banks are on */ static void amd_threshold_interrupt(void); +static void amd_deferred_error_interrupt(void); + +static void default_deferred_error_interrupt(void) +{ + pr_err("Unexpected deferred interrupt at vector %x\n", DEFERRED_ERROR_VECTOR); +} +void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt; /* * CPU Initialization @@ -196,7 +205,7 @@ static void mce_threshold_block_init(struct threshold_block *b, int offset) threshold_restart_bank(&tr); }; -static int setup_APIC_mce(int reserved, int new) +static int setup_APIC_mce_threshold(int reserved, int new) { if (reserved < 0 && !setup_APIC_eilvt(new, THRESHOLD_APIC_VECTOR, APIC_EILVT_MSG_FIX, 0)) @@ -205,6 +214,39 @@ static int setup_APIC_mce(int reserved, int new) return reserved; } +static int setup_APIC_deferred_error(int reserved, int new) +{ + if (reserved < 0 && !setup_APIC_eilvt(new, DEFERRED_ERROR_VECTOR, + APIC_EILVT_MSG_FIX, 0)) + return new; + + return reserved; +} + +static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c) +{ + u32 low = 0, high = 0; + int def_offset = -1, def_new; + + if (rdmsr_safe(MSR_CU_DEF_ERR, &low, &high)) + return; + + def_new = (low & MASK_DEF_LVTOFF) >> 4; + if (!(low & MASK_DEF_LVTOFF)) { + pr_err(FW_BUG "Your BIOS is not setting up LVT offset 0x2 for deferred error IRQs correctly.\n"); + def_new = DEF_LVT_OFF; + low = (low & ~MASK_DEF_LVTOFF) | (DEF_LVT_OFF << 4); + } + + def_offset = setup_APIC_deferred_error(def_offset, def_new); + if ((def_offset == def_new) && + (deferred_error_int_vector != amd_deferred_error_interrupt)) + deferred_error_int_vector = amd_deferred_error_interrupt; + + low = (low & ~MASK_DEF_INT_TYPE) | DEF_INT_TYPE_APIC; + wrmsr(MSR_CU_DEF_ERR, low, high); +} + /* cpu init entry point, called from mce.c with preempt off */ void mce_amd_feature_init(struct cpuinfo_x86 *c) { @@ -252,7 +294,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) b.interrupt_enable = 1; new = (high & MASK_LVTOFF_HI) >> 20; - offset = setup_APIC_mce(offset, new); + offset = setup_APIC_mce_threshold(offset, new); if ((offset == new) && (mce_threshold_vector != amd_threshold_interrupt)) @@ -262,6 +304,73 @@ init: mce_threshold_block_init(&b, offset); } } + + if (mce_flags.succor) + deferred_error_interrupt_enable(c); +} + +static void __log_error(unsigned int bank, bool threshold_err, u64 misc) +{ + struct mce m; + u64 status; + + rdmsrl(MSR_IA32_MCx_STATUS(bank), status); + if (!(status & MCI_STATUS_VAL)) + return; + + mce_setup(&m); + + m.status = status; + m.bank = bank; + + if (threshold_err) + m.misc = misc; + + if (m.status & MCI_STATUS_ADDRV) + rdmsrl(MSR_IA32_MCx_ADDR(bank), m.addr); + + mce_log(&m); + wrmsrl(MSR_IA32_MCx_STATUS(bank), 0); +} + +static inline void __smp_deferred_error_interrupt(void) +{ + inc_irq_stat(irq_deferred_error_count); + deferred_error_int_vector(); +} + +asmlinkage __visible void smp_deferred_error_interrupt(void) +{ + entering_irq(); + __smp_deferred_error_interrupt(); + exiting_ack_irq(); +} + +asmlinkage __visible void smp_trace_deferred_error_interrupt(void) +{ + entering_irq(); + trace_deferred_error_apic_entry(DEFERRED_ERROR_VECTOR); + __smp_deferred_error_interrupt(); + trace_deferred_error_apic_exit(DEFERRED_ERROR_VECTOR); + exiting_ack_irq(); +} + +/* APIC interrupt handler for deferred errors */ +static void amd_deferred_error_interrupt(void) +{ + u64 status; + unsigned int bank; + + for (bank = 0; bank < mca_cfg.banks; ++bank) { + rdmsrl(MSR_IA32_MCx_STATUS(bank), status); + + if (!(status & MCI_STATUS_VAL) || + !(status & MCI_STATUS_DEFERRED)) + continue; + + __log_error(bank, false, 0); + break; + } } /* @@ -273,12 +382,12 @@ init: * the interrupt goes off when error_count reaches threshold_limit. * the handler will simply log mcelog w/ software defined bank number. */ + static void amd_threshold_interrupt(void) { u32 low = 0, high = 0, address = 0; int cpu = smp_processor_id(); unsigned int bank, block; - struct mce m; /* assume first bank caused it */ for (bank = 0; bank < mca_cfg.banks; ++bank) { @@ -321,15 +430,7 @@ static void amd_threshold_interrupt(void) return; log: - mce_setup(&m); - rdmsrl(MSR_IA32_MCx_STATUS(bank), m.status); - if (!(m.status & MCI_STATUS_VAL)) - return; - m.misc = ((u64)high << 32) | low; - m.bank = bank; - mce_log(&m); - - wrmsrl(MSR_IA32_MCx_STATUS(bank), 0); + __log_error(bank, true, ((u64)high << 32) | low); } /* diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index b4a41cf03..844f56c56 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -91,6 +91,36 @@ static int cmci_supported(int *banks) return !!(cap & MCG_CMCI_P); } +static bool lmce_supported(void) +{ + u64 tmp; + + if (mca_cfg.lmce_disabled) + return false; + + rdmsrl(MSR_IA32_MCG_CAP, tmp); + + /* + * LMCE depends on recovery support in the processor. Hence both + * MCG_SER_P and MCG_LMCE_P should be present in MCG_CAP. + */ + if ((tmp & (MCG_SER_P | MCG_LMCE_P)) != + (MCG_SER_P | MCG_LMCE_P)) + return false; + + /* + * BIOS should indicate support for LMCE by setting bit 20 in + * IA32_FEATURE_CONTROL without which touching MCG_EXT_CTL will + * generate a #GP fault. + */ + rdmsrl(MSR_IA32_FEATURE_CONTROL, tmp); + if ((tmp & (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE)) == + (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE)) + return true; + + return false; +} + bool mce_intel_cmci_poll(void) { if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE) @@ -405,8 +435,22 @@ static void intel_init_cmci(void) cmci_recheck(); } +void intel_init_lmce(void) +{ + u64 val; + + if (!lmce_supported()) + return; + + rdmsrl(MSR_IA32_MCG_EXT_CTL, val); + + if (!(val & MCG_EXT_CTL_LMCE_EN)) + wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN); +} + void mce_intel_feature_init(struct cpuinfo_x86 *c) { intel_init_thermal(c); intel_init_cmci(); + intel_init_lmce(); } diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c index 816a25c90..5d1fb6061 100644 --- a/arch/x86/kernel/cpu/microcode/amd_early.c +++ b/arch/x86/kernel/cpu/microcode/amd_early.c @@ -228,7 +228,23 @@ static void apply_ucode_in_initrd(void *ucode, size_t size, bool save_patch) } } -void __init load_ucode_amd_bsp(void) +static bool __init load_builtin_amd_microcode(struct cpio_data *cp, + unsigned int family) +{ +#ifdef CONFIG_X86_64 + char fw_name[36] = "/*(DEBLOBBED)*/"; + + if (family >= 0x15) + snprintf(fw_name, sizeof(fw_name), + "/*(DEBLOBBED)*/", family); + + return get_builtin_firmware(cp, fw_name); +#else + return false; +#endif +} + +void __init load_ucode_amd_bsp(unsigned int family) { struct cpio_data cp; void **data; @@ -243,8 +259,10 @@ void __init load_ucode_amd_bsp(void) #endif cp = find_ucode_in_initrd(); - if (!cp.data) - return; + if (!cp.data) { + if (!load_builtin_amd_microcode(&cp, family)) + return; + } *data = cp.data; *size = cp.size; diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 36a83617e..6236a54a6 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -1,74 +1,16 @@ /* - * Intel CPU Microcode Update Driver for Linux + * CPU Microcode Update Driver for Linux * - * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk> - * 2006 Shaohua Li <shaohua.li@intel.com> + * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk> + * 2006 Shaohua Li <shaohua.li@intel.com> + * 2013-2015 Borislav Petkov <bp@alien8.de> * - * This driver allows to upgrade microcode on Intel processors - * belonging to IA-32 family - PentiumPro, Pentium II, - * Pentium III, Xeon, Pentium 4, etc. + * This driver allows to upgrade microcode on x86 processors. * - * Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture - * Software Developer's Manual - * Order Number 253668 or free download from: - * - * http://developer.intel.com/Assets/PDF/manual/253668.pdf - * - * For more information, go to http://www.urbanmyth.org/microcode - * - * 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. - * - * 1.0 16 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Initial release. - * 1.01 18 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Added read() support + cleanups. - * 1.02 21 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Added 'device trimming' support. open(O_WRONLY) zeroes - * and frees the saved copy of applied microcode. - * 1.03 29 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Made to use devfs (/dev/cpu/microcode) + cleanups. - * 1.04 06 Jun 2000, Simon Trimmer <simon@veritas.com> - * Added misc device support (now uses both devfs and misc). - * Added MICROCODE_IOCFREE ioctl to clear memory. - * 1.05 09 Jun 2000, Simon Trimmer <simon@veritas.com> - * Messages for error cases (non Intel & no suitable microcode). - * 1.06 03 Aug 2000, Tigran Aivazian <tigran@veritas.com> - * Removed ->release(). Removed exclusive open and status bitmap. - * Added microcode_rwsem to serialize read()/write()/ioctl(). - * Removed global kernel lock usage. - * 1.07 07 Sep 2000, Tigran Aivazian <tigran@veritas.com> - * Write 0 to 0x8B msr and then cpuid before reading revision, - * so that it works even if there were no update done by the - * BIOS. Otherwise, reading from 0x8B gives junk (which happened - * to be 0 on my machine which is why it worked even when I - * disabled update by the BIOS) - * Thanks to Eric W. Biederman <ebiederman@lnxi.com> for the fix. - * 1.08 11 Dec 2000, Richard Schaal <richard.schaal@intel.com> and - * Tigran Aivazian <tigran@veritas.com> - * Intel Pentium 4 processor support and bugfixes. - * 1.09 30 Oct 2001, Tigran Aivazian <tigran@veritas.com> - * Bugfix for HT (Hyper-Threading) enabled processors - * whereby processor resources are shared by all logical processors - * in a single CPU package. - * 1.10 28 Feb 2002 Asit K Mallick <asit.k.mallick@intel.com> and - * Tigran Aivazian <tigran@veritas.com>, - * Serialize updates as required on HT processors due to - * speculative nature of implementation. - * 1.11 22 Mar 2002 Tigran Aivazian <tigran@veritas.com> - * Fix the panic when writing zero-length microcode chunk. - * 1.12 29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>, - * Jun Nakajima <jun.nakajima@intel.com> - * Support for the microcode updates in the new format. - * 1.13 10 Oct 2003 Tigran Aivazian <tigran@veritas.com> - * Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl - * because we no longer hold a copy of applied microcode - * in kernel memory. - * 1.14 25 Jun 2004 Tigran Aivazian <tigran@veritas.com> - * Fix sigmatch() macro to handle old CPUs with pf == 0. - * Thanks to Stuart Swales for pointing out this bug. + * 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. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/arch/x86/kernel/cpu/microcode/core_early.c b/arch/x86/kernel/cpu/microcode/core_early.c index a413a69cb..8ebc421d6 100644 --- a/arch/x86/kernel/cpu/microcode/core_early.c +++ b/arch/x86/kernel/cpu/microcode/core_early.c @@ -3,6 +3,7 @@ * * Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com> * H Peter Anvin" <hpa@zytor.com> + * (C) 2015 Borislav Petkov <bp@alien8.de> * * This driver allows to early upgrade microcode on Intel processors * belonging to IA-32 family - PentiumPro, Pentium II, @@ -17,6 +18,7 @@ * 2 of the License, or (at your option) any later version. */ #include <linux/module.h> +#include <linux/firmware.h> #include <asm/microcode.h> #include <asm/microcode_intel.h> #include <asm/microcode_amd.h> @@ -43,9 +45,29 @@ static bool __init check_loader_disabled_bsp(void) return *res; } +extern struct builtin_fw __start_builtin_fw[]; +extern struct builtin_fw __end_builtin_fw[]; + +bool get_builtin_firmware(struct cpio_data *cd, const char *name) +{ +#ifdef CONFIG_FW_LOADER + struct builtin_fw *b_fw; + + for (b_fw = __start_builtin_fw; b_fw != __end_builtin_fw; b_fw++) { + if (!strcmp(name, b_fw->name)) { + cd->size = b_fw->size; + cd->data = b_fw->data; + return true; + } + } +#endif + return false; +} + void __init load_ucode_bsp(void) { - int vendor, family; + int vendor; + unsigned int family; if (check_loader_disabled_bsp()) return; @@ -63,7 +85,7 @@ void __init load_ucode_bsp(void) break; case X86_VENDOR_AMD: if (family >= 0x10) - load_ucode_amd_bsp(); + load_ucode_amd_bsp(family); break; default: break; diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index a493d9d5a..2869d81ff 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -1,74 +1,13 @@ /* - * Intel CPU Microcode Update Driver for Linux + * Intel CPU Microcode Update Driver for Linux * - * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk> - * 2006 Shaohua Li <shaohua.li@intel.com> + * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk> + * 2006 Shaohua Li <shaohua.li@intel.com> * - * This driver allows to upgrade microcode on Intel processors - * belonging to IA-32 family - PentiumPro, Pentium II, - * Pentium III, Xeon, Pentium 4, etc. - * - * Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture - * Software Developer's Manual - * Order Number 253668 or free download from: - * - * http://developer.intel.com/Assets/PDF/manual/253668.pdf - * - * For more information, go to http://www.urbanmyth.org/microcode - * - * 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. - * - * 1.0 16 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Initial release. - * 1.01 18 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Added read() support + cleanups. - * 1.02 21 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Added 'device trimming' support. open(O_WRONLY) zeroes - * and frees the saved copy of applied microcode. - * 1.03 29 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Made to use devfs (/dev/cpu/microcode) + cleanups. - * 1.04 06 Jun 2000, Simon Trimmer <simon@veritas.com> - * Added misc device support (now uses both devfs and misc). - * Added MICROCODE_IOCFREE ioctl to clear memory. - * 1.05 09 Jun 2000, Simon Trimmer <simon@veritas.com> - * Messages for error cases (non Intel & no suitable microcode). - * 1.06 03 Aug 2000, Tigran Aivazian <tigran@veritas.com> - * Removed ->release(). Removed exclusive open and status bitmap. - * Added microcode_rwsem to serialize read()/write()/ioctl(). - * Removed global kernel lock usage. - * 1.07 07 Sep 2000, Tigran Aivazian <tigran@veritas.com> - * Write 0 to 0x8B msr and then cpuid before reading revision, - * so that it works even if there were no update done by the - * BIOS. Otherwise, reading from 0x8B gives junk (which happened - * to be 0 on my machine which is why it worked even when I - * disabled update by the BIOS) - * Thanks to Eric W. Biederman <ebiederman@lnxi.com> for the fix. - * 1.08 11 Dec 2000, Richard Schaal <richard.schaal@intel.com> and - * Tigran Aivazian <tigran@veritas.com> - * Intel Pentium 4 processor support and bugfixes. - * 1.09 30 Oct 2001, Tigran Aivazian <tigran@veritas.com> - * Bugfix for HT (Hyper-Threading) enabled processors - * whereby processor resources are shared by all logical processors - * in a single CPU package. - * 1.10 28 Feb 2002 Asit K Mallick <asit.k.mallick@intel.com> and - * Tigran Aivazian <tigran@veritas.com>, - * Serialize updates as required on HT processors due to - * speculative nature of implementation. - * 1.11 22 Mar 2002 Tigran Aivazian <tigran@veritas.com> - * Fix the panic when writing zero-length microcode chunk. - * 1.12 29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>, - * Jun Nakajima <jun.nakajima@intel.com> - * Support for the microcode updates in the new format. - * 1.13 10 Oct 2003 Tigran Aivazian <tigran@veritas.com> - * Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl - * because we no longer hold a copy of applied microcode - * in kernel memory. - * 1.14 25 Jun 2004 Tigran Aivazian <tigran@veritas.com> - * Fix sigmatch() macro to handle old CPUs with pf == 0. - * Thanks to Stuart Swales for pointing out this bug. + * 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. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -124,7 +63,7 @@ static int get_matching_mc(struct microcode_intel *mc_intel, int cpu) cpf = cpu_sig.pf; crev = cpu_sig.rev; - return get_matching_microcode(csig, cpf, crev, mc_intel); + return has_newer_microcode(mc_intel, csig, cpf, crev); } static int apply_microcode_intel(int cpu) @@ -226,7 +165,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, csig = uci->cpu_sig.sig; cpf = uci->cpu_sig.pf; - if (get_matching_microcode(csig, cpf, new_rev, mc)) { + if (has_newer_microcode(mc, csig, cpf, new_rev)) { vfree(new_mc); new_rev = mc_header.rev; new_mc = mc; diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c index 4d843f80e..6b5021fc3 100644 --- a/arch/x86/kernel/cpu/microcode/intel_early.c +++ b/arch/x86/kernel/cpu/microcode/intel_early.c @@ -59,10 +59,10 @@ load_microcode_early(struct microcode_intel **saved, ucode_ptr = saved[i]; mc_hdr = (struct microcode_header_intel *)ucode_ptr; - ret = get_matching_microcode(uci->cpu_sig.sig, - uci->cpu_sig.pf, - new_rev, - ucode_ptr); + ret = has_newer_microcode(ucode_ptr, + uci->cpu_sig.sig, + uci->cpu_sig.pf, + new_rev); if (!ret) continue; @@ -246,7 +246,7 @@ static unsigned int _save_mc(struct microcode_intel **mc_saved, u8 *ucode_ptr, unsigned int num_saved) { struct microcode_header_intel *mc_hdr, *mc_saved_hdr; - unsigned int sig, pf, new_rev; + unsigned int sig, pf; int found = 0, i; mc_hdr = (struct microcode_header_intel *)ucode_ptr; @@ -255,14 +255,13 @@ static unsigned int _save_mc(struct microcode_intel **mc_saved, mc_saved_hdr = (struct microcode_header_intel *)mc_saved[i]; sig = mc_saved_hdr->sig; pf = mc_saved_hdr->pf; - new_rev = mc_hdr->rev; - if (!get_matching_sig(sig, pf, new_rev, ucode_ptr)) + if (!find_matching_signature(ucode_ptr, sig, pf)) continue; found = 1; - if (!revision_is_newer(mc_hdr, new_rev)) + if (mc_hdr->rev <= mc_saved_hdr->rev) continue; /* @@ -522,6 +521,27 @@ out: EXPORT_SYMBOL_GPL(save_mc_for_early); #endif +static bool __init load_builtin_intel_microcode(struct cpio_data *cp) +{ +#ifdef CONFIG_X86_64 + unsigned int eax = 0x00000001, ebx, ecx = 0, edx; + unsigned int family, model, stepping; + char name[30]; + + native_cpuid(&eax, &ebx, &ecx, &edx); + + family = __x86_family(eax); + model = x86_model(eax); + stepping = eax & 0xf; + + sprintf(name, "/*(DEBLOBBED)*/", family, model, stepping); + + return get_builtin_firmware(cp, name); +#else + return false; +#endif +} + static __initdata char ucode_name[] = "/*(DEBLOBBED)*/"; static __init enum ucode_state scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd, @@ -540,8 +560,10 @@ scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd, cd.size = 0; cd = find_cpio_data(p, (void *)start, size, &offset); - if (!cd.data) - return UCODE_ERROR; + if (!cd.data) { + if (!load_builtin_intel_microcode(&cd)) + return UCODE_ERROR; + } return get_matching_model_microcode(0, start, cd.data, cd.size, mc_saved_data, initrd, uci); diff --git a/arch/x86/kernel/cpu/microcode/intel_lib.c b/arch/x86/kernel/cpu/microcode/intel_lib.c index cd47a510a..1883d252f 100644 --- a/arch/x86/kernel/cpu/microcode/intel_lib.c +++ b/arch/x86/kernel/cpu/microcode/intel_lib.c @@ -31,11 +31,18 @@ #include <asm/processor.h> #include <asm/msr.h> -static inline int -update_match_cpu(unsigned int csig, unsigned int cpf, - unsigned int sig, unsigned int pf) +static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1, + unsigned int s2, unsigned int p2) { - return (!sigmatch(sig, csig, pf, cpf)) ? 0 : 1; + if (s1 != s2) + return false; + + /* Processor flags are either both 0 ... */ + if (!p1 && !p2) + return true; + + /* ... or they intersect. */ + return p1 & p2; } int microcode_sanity_check(void *mc, int print_err) @@ -124,27 +131,25 @@ EXPORT_SYMBOL_GPL(microcode_sanity_check); /* * Returns 1 if update has been found, 0 otherwise. */ -int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc) +int find_matching_signature(void *mc, unsigned int csig, int cpf) { - struct microcode_header_intel *mc_header = mc; - struct extended_sigtable *ext_header; - unsigned long total_size = get_totalsize(mc_header); - int ext_sigcount, i; + struct microcode_header_intel *mc_hdr = mc; + struct extended_sigtable *ext_hdr; struct extended_signature *ext_sig; + int i; - if (update_match_cpu(csig, cpf, mc_header->sig, mc_header->pf)) + if (cpu_signatures_match(csig, cpf, mc_hdr->sig, mc_hdr->pf)) return 1; /* Look for ext. headers: */ - if (total_size <= get_datasize(mc_header) + MC_HEADER_SIZE) + if (get_totalsize(mc_hdr) <= get_datasize(mc_hdr) + MC_HEADER_SIZE) return 0; - ext_header = mc + get_datasize(mc_header) + MC_HEADER_SIZE; - ext_sigcount = ext_header->count; - ext_sig = (void *)ext_header + EXT_HEADER_SIZE; + ext_hdr = mc + get_datasize(mc_hdr) + MC_HEADER_SIZE; + ext_sig = (void *)ext_hdr + EXT_HEADER_SIZE; - for (i = 0; i < ext_sigcount; i++) { - if (update_match_cpu(csig, cpf, ext_sig->sig, ext_sig->pf)) + for (i = 0; i < ext_hdr->count; i++) { + if (cpu_signatures_match(csig, cpf, ext_sig->sig, ext_sig->pf)) return 1; ext_sig++; } @@ -154,13 +159,13 @@ int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc) /* * Returns 1 if update has been found, 0 otherwise. */ -int get_matching_microcode(unsigned int csig, int cpf, int rev, void *mc) +int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev) { struct microcode_header_intel *mc_hdr = mc; - if (!revision_is_newer(mc_hdr, rev)) + if (mc_hdr->rev <= new_rev) return 0; - return get_matching_sig(csig, cpf, rev, mc); + return find_matching_signature(mc, csig, cpf); } -EXPORT_SYMBOL_GPL(get_matching_microcode); +EXPORT_SYMBOL_GPL(has_newer_microcode); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 939155ffd..aad4bd84b 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -39,14 +39,12 @@ void hyperv_vector_handler(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); - irq_enter(); - exit_idle(); - + entering_irq(); inc_irq_stat(irq_hv_callback_count); if (vmbus_handler) vmbus_handler(); - irq_exit(); + exiting_irq(); set_irq_regs(old_regs); } diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 5f90b85ff..70d7c93f4 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -98,7 +98,8 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range, continue; base = range_state[i].base_pfn; if (base < (1<<(20-PAGE_SHIFT)) && mtrr_state.have_fixed && - (mtrr_state.enabled & 1)) { + (mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) && + (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) { /* Var MTRR contains UC entry below 1M? Skip it: */ printk(BIOS_BUG_MSG, i); if (base + size <= (1<<(20-PAGE_SHIFT))) diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 7d74f7b3c..3b533cf37 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -102,59 +102,76 @@ static int check_type_overlap(u8 *prev, u8 *curr) return 0; } -/* - * Error/Semi-error returns: - * 0xFF - when MTRR is not enabled - * *repeat == 1 implies [start:end] spanned across MTRR range and type returned - * corresponds only to [start:*partial_end]. - * Caller has to lookup again for [*partial_end:end]. +/** + * mtrr_type_lookup_fixed - look up memory type in MTRR fixed entries + * + * Return the MTRR fixed memory type of 'start'. + * + * MTRR fixed entries are divided into the following ways: + * 0x00000 - 0x7FFFF : This range is divided into eight 64KB sub-ranges + * 0x80000 - 0xBFFFF : This range is divided into sixteen 16KB sub-ranges + * 0xC0000 - 0xFFFFF : This range is divided into sixty-four 4KB sub-ranges + * + * Return Values: + * MTRR_TYPE_(type) - Matched memory type + * MTRR_TYPE_INVALID - Unmatched + */ +static u8 mtrr_type_lookup_fixed(u64 start, u64 end) +{ + int idx; + + if (start >= 0x100000) + return MTRR_TYPE_INVALID; + + /* 0x0 - 0x7FFFF */ + if (start < 0x80000) { + idx = 0; + idx += (start >> 16); + return mtrr_state.fixed_ranges[idx]; + /* 0x80000 - 0xBFFFF */ + } else if (start < 0xC0000) { + idx = 1 * 8; + idx += ((start - 0x80000) >> 14); + return mtrr_state.fixed_ranges[idx]; + } + + /* 0xC0000 - 0xFFFFF */ + idx = 3 * 8; + idx += ((start - 0xC0000) >> 12); + return mtrr_state.fixed_ranges[idx]; +} + +/** + * mtrr_type_lookup_variable - look up memory type in MTRR variable entries + * + * Return Value: + * MTRR_TYPE_(type) - Matched memory type or default memory type (unmatched) + * + * Output Arguments: + * repeat - Set to 1 when [start:end] spanned across MTRR range and type + * returned corresponds only to [start:*partial_end]. Caller has + * to lookup again for [*partial_end:end]. + * + * uniform - Set to 1 when an MTRR covers the region uniformly, i.e. the + * region is fully covered by a single MTRR entry or the default + * type. */ -static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat) +static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end, + int *repeat, u8 *uniform) { int i; u64 base, mask; u8 prev_match, curr_match; *repeat = 0; - if (!mtrr_state_set) - return 0xFF; - - if (!mtrr_state.enabled) - return 0xFF; + *uniform = 1; - /* Make end inclusive end, instead of exclusive */ + /* Make end inclusive instead of exclusive */ end--; - /* Look in fixed ranges. Just return the type as per start */ - if (mtrr_state.have_fixed && (start < 0x100000)) { - int idx; - - if (start < 0x80000) { - idx = 0; - idx += (start >> 16); - return mtrr_state.fixed_ranges[idx]; - } else if (start < 0xC0000) { - idx = 1 * 8; - idx += ((start - 0x80000) >> 14); - return mtrr_state.fixed_ranges[idx]; - } else if (start < 0x1000000) { - idx = 3 * 8; - idx += ((start - 0xC0000) >> 12); - return mtrr_state.fixed_ranges[idx]; - } - } - - /* - * Look in variable ranges - * Look of multiple ranges matching this address and pick type - * as per MTRR precedence - */ - if (!(mtrr_state.enabled & 2)) - return mtrr_state.def_type; - - prev_match = 0xFF; + prev_match = MTRR_TYPE_INVALID; for (i = 0; i < num_var_ranges; ++i) { - unsigned short start_state, end_state; + unsigned short start_state, end_state, inclusive; if (!(mtrr_state.var_ranges[i].mask_lo & (1 << 11))) continue; @@ -166,20 +183,29 @@ static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat) start_state = ((start & mask) == (base & mask)); end_state = ((end & mask) == (base & mask)); + inclusive = ((start < base) && (end > base)); - if (start_state != end_state) { + if ((start_state != end_state) || inclusive) { /* * We have start:end spanning across an MTRR. - * We split the region into - * either - * (start:mtrr_end) (mtrr_end:end) - * or - * (start:mtrr_start) (mtrr_start:end) + * We split the region into either + * + * - start_state:1 + * (start:mtrr_end)(mtrr_end:end) + * - end_state:1 + * (start:mtrr_start)(mtrr_start:end) + * - inclusive:1 + * (start:mtrr_start)(mtrr_start:mtrr_end)(mtrr_end:end) + * * depending on kind of overlap. - * Return the type for first region and a pointer to - * the start of second region so that caller will - * lookup again on the second region. - * Note: This way we handle multiple overlaps as well. + * + * Return the type of the first region and a pointer + * to the start of next region so that caller will be + * advised to lookup again after having adjusted start + * and end. + * + * Note: This way we handle overlaps with multiple + * entries and the default type properly. */ if (start_state) *partial_end = base + get_mtrr_size(mask); @@ -193,59 +219,94 @@ static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat) end = *partial_end - 1; /* end is inclusive */ *repeat = 1; + *uniform = 0; } if ((start & mask) != (base & mask)) continue; curr_match = mtrr_state.var_ranges[i].base_lo & 0xff; - if (prev_match == 0xFF) { + if (prev_match == MTRR_TYPE_INVALID) { prev_match = curr_match; continue; } + *uniform = 0; if (check_type_overlap(&prev_match, &curr_match)) return curr_match; } - if (mtrr_tom2) { - if (start >= (1ULL<<32) && (end < mtrr_tom2)) - return MTRR_TYPE_WRBACK; - } - - if (prev_match != 0xFF) + if (prev_match != MTRR_TYPE_INVALID) return prev_match; return mtrr_state.def_type; } -/* - * Returns the effective MTRR type for the region - * Error return: - * 0xFF - when MTRR is not enabled +/** + * mtrr_type_lookup - look up memory type in MTRR + * + * Return Values: + * MTRR_TYPE_(type) - The effective MTRR type for the region + * MTRR_TYPE_INVALID - MTRR is disabled + * + * Output Argument: + * uniform - Set to 1 when an MTRR covers the region uniformly, i.e. the + * region is fully covered by a single MTRR entry or the default + * type. */ -u8 mtrr_type_lookup(u64 start, u64 end) +u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform) { - u8 type, prev_type; + u8 type, prev_type, is_uniform = 1, dummy; int repeat; u64 partial_end; - type = __mtrr_type_lookup(start, end, &partial_end, &repeat); + if (!mtrr_state_set) + return MTRR_TYPE_INVALID; + + if (!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED)) + return MTRR_TYPE_INVALID; + + /* + * Look up the fixed ranges first, which take priority over + * the variable ranges. + */ + if ((start < 0x100000) && + (mtrr_state.have_fixed) && + (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) { + is_uniform = 0; + type = mtrr_type_lookup_fixed(start, end); + goto out; + } + + /* + * Look up the variable ranges. Look of multiple ranges matching + * this address and pick type as per MTRR precedence. + */ + type = mtrr_type_lookup_variable(start, end, &partial_end, + &repeat, &is_uniform); /* * Common path is with repeat = 0. * However, we can have cases where [start:end] spans across some - * MTRR range. Do repeated lookups for that case here. + * MTRR ranges and/or the default type. Do repeated lookups for + * that case here. */ while (repeat) { prev_type = type; start = partial_end; - type = __mtrr_type_lookup(start, end, &partial_end, &repeat); + is_uniform = 0; + type = mtrr_type_lookup_variable(start, end, &partial_end, + &repeat, &dummy); if (check_type_overlap(&prev_type, &type)) - return type; + goto out; } + if (mtrr_tom2 && (start >= (1ULL<<32)) && (end < mtrr_tom2)) + type = MTRR_TYPE_WRBACK; + +out: + *uniform = is_uniform; return type; } @@ -347,7 +408,9 @@ static void __init print_mtrr_state(void) mtrr_attrib_to_str(mtrr_state.def_type)); if (mtrr_state.have_fixed) { pr_debug("MTRR fixed ranges %sabled:\n", - mtrr_state.enabled & 1 ? "en" : "dis"); + ((mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) && + (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) ? + "en" : "dis"); print_fixed(0x00000, 0x10000, mtrr_state.fixed_ranges + 0); for (i = 0; i < 2; ++i) print_fixed(0x80000 + i * 0x20000, 0x04000, @@ -360,7 +423,7 @@ static void __init print_mtrr_state(void) print_fixed_last(); } pr_debug("MTRR variable ranges %sabled:\n", - mtrr_state.enabled & 2 ? "en" : "dis"); + mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED ? "en" : "dis"); high_width = (__ffs64(size_or_mask) - (32 - PAGE_SHIFT) + 3) / 4; for (i = 0; i < num_var_ranges; ++i) { @@ -382,7 +445,7 @@ static void __init print_mtrr_state(void) } /* Grab all of the MTRR state for this CPU into *state */ -void __init get_mtrr_state(void) +bool __init get_mtrr_state(void) { struct mtrr_var_range *vrs; unsigned long flags; @@ -426,6 +489,8 @@ void __init get_mtrr_state(void) post_set(); local_irq_restore(flags); + + return !!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED); } /* Some BIOS's are messed up and don't set all MTRRs the same! */ diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index ea5f363a1..e7ed0d8eb 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -59,6 +59,12 @@ #define MTRR_TO_PHYS_WC_OFFSET 1000 u32 num_var_ranges; +static bool __mtrr_enabled; + +static bool mtrr_enabled(void) +{ + return __mtrr_enabled; +} unsigned int mtrr_usage_table[MTRR_MAX_VAR_RANGES]; static DEFINE_MUTEX(mtrr_mutex); @@ -286,7 +292,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, int i, replace, error; mtrr_type ltype; - if (!mtrr_if) + if (!mtrr_enabled()) return -ENXIO; error = mtrr_if->validate_add_page(base, size, type); @@ -435,6 +441,8 @@ static int mtrr_check(unsigned long base, unsigned long size) int mtrr_add(unsigned long base, unsigned long size, unsigned int type, bool increment) { + if (!mtrr_enabled()) + return -ENODEV; if (mtrr_check(base, size)) return -EINVAL; return mtrr_add_page(base >> PAGE_SHIFT, size >> PAGE_SHIFT, type, @@ -463,8 +471,8 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) unsigned long lbase, lsize; int error = -EINVAL; - if (!mtrr_if) - return -ENXIO; + if (!mtrr_enabled()) + return -ENODEV; max = num_var_ranges; /* No CPU hotplug when we change MTRR entries */ @@ -523,6 +531,8 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) */ int mtrr_del(int reg, unsigned long base, unsigned long size) { + if (!mtrr_enabled()) + return -ENODEV; if (mtrr_check(base, size)) return -EINVAL; return mtrr_del_page(reg, base >> PAGE_SHIFT, size >> PAGE_SHIFT); @@ -538,6 +548,9 @@ EXPORT_SYMBOL(mtrr_del); * attempts to add a WC MTRR covering size bytes starting at base and * logs an error if this fails. * + * The called should provide a power of two size on an equivalent + * power of two boundary. + * * Drivers must store the return value to pass to mtrr_del_wc_if_needed, * but drivers should not try to interpret that return value. */ @@ -545,7 +558,7 @@ int arch_phys_wc_add(unsigned long base, unsigned long size) { int ret; - if (pat_enabled) + if (pat_enabled() || !mtrr_enabled()) return 0; /* Success! (We don't need to do anything.) */ ret = mtrr_add(base, size, MTRR_TYPE_WRCOMB, true); @@ -577,7 +590,7 @@ void arch_phys_wc_del(int handle) EXPORT_SYMBOL(arch_phys_wc_del); /* - * phys_wc_to_mtrr_index - translates arch_phys_wc_add's return value + * arch_phys_wc_index - translates arch_phys_wc_add's return value * @handle: Return value from arch_phys_wc_add * * This will turn the return value from arch_phys_wc_add into an mtrr @@ -587,14 +600,14 @@ EXPORT_SYMBOL(arch_phys_wc_del); * in printk line. Alas there is an illegitimate use in some ancient * drm ioctls. */ -int phys_wc_to_mtrr_index(int handle) +int arch_phys_wc_index(int handle) { if (handle < MTRR_TO_PHYS_WC_OFFSET) return -1; else return handle - MTRR_TO_PHYS_WC_OFFSET; } -EXPORT_SYMBOL_GPL(phys_wc_to_mtrr_index); +EXPORT_SYMBOL_GPL(arch_phys_wc_index); /* * HACK ALERT! @@ -734,10 +747,12 @@ void __init mtrr_bp_init(void) } if (mtrr_if) { + __mtrr_enabled = true; set_num_var_ranges(); init_table(); if (use_intel()) { - get_mtrr_state(); + /* BIOS may override */ + __mtrr_enabled = get_mtrr_state(); if (mtrr_cleanup(phys_addr)) { changed_by_mtrr_cleanup = 1; @@ -745,10 +760,16 @@ void __init mtrr_bp_init(void) } } } + + if (!mtrr_enabled()) + pr_info("MTRR: Disabled\n"); } void mtrr_ap_init(void) { + if (!mtrr_enabled()) + return; + if (!use_intel() || mtrr_aps_delayed_init) return; /* @@ -774,6 +795,9 @@ void mtrr_save_state(void) { int first_cpu; + if (!mtrr_enabled()) + return; + get_online_cpus(); first_cpu = cpumask_first(cpu_online_mask); smp_call_function_single(first_cpu, mtrr_save_fixed_ranges, NULL, 1); @@ -782,6 +806,8 @@ void mtrr_save_state(void) void set_mtrr_aps_delayed_init(void) { + if (!mtrr_enabled()) + return; if (!use_intel()) return; @@ -793,7 +819,7 @@ void set_mtrr_aps_delayed_init(void) */ void mtrr_aps_init(void) { - if (!use_intel()) + if (!use_intel() || !mtrr_enabled()) return; /* @@ -810,7 +836,7 @@ void mtrr_aps_init(void) void mtrr_bp_restore(void) { - if (!use_intel()) + if (!use_intel() || !mtrr_enabled()) return; mtrr_if->set_all(); @@ -818,7 +844,7 @@ void mtrr_bp_restore(void) static int __init mtrr_init_finialize(void) { - if (!mtrr_if) + if (!mtrr_enabled()) return 0; if (use_intel()) { diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index df5e41f31..951884dcc 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -51,7 +51,7 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt); void fill_mtrr_var_range(unsigned int index, u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi); -void get_mtrr_state(void); +bool get_mtrr_state(void); extern void set_mtrr_ops(const struct mtrr_ops *ops); diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index aa4e3a74e..9469dfa55 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -135,6 +135,7 @@ static int x86_pmu_extra_regs(u64 config, struct perf_event *event) } static atomic_t active_events; +static atomic_t pmc_refcount; static DEFINE_MUTEX(pmc_reserve_mutex); #ifdef CONFIG_X86_LOCAL_APIC @@ -271,6 +272,7 @@ msr_fail: static void hw_perf_event_destroy(struct perf_event *event) { x86_release_hardware(); + atomic_dec(&active_events); } void hw_perf_lbr_event_destroy(struct perf_event *event) @@ -324,16 +326,16 @@ int x86_reserve_hardware(void) { int err = 0; - if (!atomic_inc_not_zero(&active_events)) { + if (!atomic_inc_not_zero(&pmc_refcount)) { mutex_lock(&pmc_reserve_mutex); - if (atomic_read(&active_events) == 0) { + if (atomic_read(&pmc_refcount) == 0) { if (!reserve_pmc_hardware()) err = -EBUSY; else reserve_ds_buffers(); } if (!err) - atomic_inc(&active_events); + atomic_inc(&pmc_refcount); mutex_unlock(&pmc_reserve_mutex); } @@ -342,7 +344,7 @@ int x86_reserve_hardware(void) void x86_release_hardware(void) { - if (atomic_dec_and_mutex_lock(&active_events, &pmc_reserve_mutex)) { + if (atomic_dec_and_mutex_lock(&pmc_refcount, &pmc_reserve_mutex)) { release_pmc_hardware(); release_ds_buffers(); mutex_unlock(&pmc_reserve_mutex); @@ -355,28 +357,30 @@ void x86_release_hardware(void) */ int x86_add_exclusive(unsigned int what) { - int ret = -EBUSY, i; - - if (atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) - return 0; + int i; - mutex_lock(&pmc_reserve_mutex); - for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) { - if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i])) - goto out; + if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) { + mutex_lock(&pmc_reserve_mutex); + for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) { + if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i])) + goto fail_unlock; + } + atomic_inc(&x86_pmu.lbr_exclusive[what]); + mutex_unlock(&pmc_reserve_mutex); } - atomic_inc(&x86_pmu.lbr_exclusive[what]); - ret = 0; + atomic_inc(&active_events); + return 0; -out: +fail_unlock: mutex_unlock(&pmc_reserve_mutex); - return ret; + return -EBUSY; } void x86_del_exclusive(unsigned int what) { atomic_dec(&x86_pmu.lbr_exclusive[what]); + atomic_dec(&active_events); } int x86_setup_perfctr(struct perf_event *event) @@ -557,6 +561,7 @@ static int __x86_pmu_event_init(struct perf_event *event) if (err) return err; + atomic_inc(&active_events); event->destroy = hw_perf_event_destroy; event->hw.idx = -1; @@ -895,10 +900,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) if (x86_pmu.commit_scheduling) x86_pmu.commit_scheduling(cpuc, i, assign[i]); } - } - - if (!assign || unsched) { - + } else { for (i = 0; i < n; i++) { e = cpuc->event_list[i]; /* @@ -1111,13 +1113,16 @@ int x86_perf_event_set_period(struct perf_event *event) per_cpu(pmc_prev_left[idx], smp_processor_id()) = left; - /* - * The hw event starts counting from this event offset, - * mark it to be able to extra future deltas: - */ - local64_set(&hwc->prev_count, (u64)-left); + if (!(hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) || + local64_read(&hwc->prev_count) != (u64)-left) { + /* + * The hw event starts counting from this event offset, + * mark it to be able to extra future deltas: + */ + local64_set(&hwc->prev_count, (u64)-left); - wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); + wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); + } /* * Due to erratum on certan cpu we need @@ -1429,6 +1434,10 @@ perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs) u64 finish_clock; int ret; + /* + * All PMUs/events that share this PMI handler should make sure to + * increment active_events for their events. + */ if (!atomic_read(&active_events)) return NMI_DONE; @@ -2170,21 +2179,25 @@ static unsigned long get_segment_base(unsigned int segment) int idx = segment >> 3; if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) { + struct ldt_struct *ldt; + if (idx > LDT_ENTRIES) return 0; - if (idx > current->active_mm->context.size) + /* IRQs are off, so this synchronizes with smp_store_release */ + ldt = lockless_dereference(current->active_mm->context.ldt); + if (!ldt || idx > ldt->size) return 0; - desc = current->active_mm->context.ldt; + desc = &ldt->entries[idx]; } else { if (idx > GDT_ENTRIES) return 0; - desc = raw_cpu_ptr(gdt_page.gdt); + desc = raw_cpu_ptr(gdt_page.gdt) + idx; } - return get_desc_base(desc + idx); + return get_desc_base(desc); } #ifdef CONFIG_COMPAT diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index f068695ea..3e7fd27df 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -75,6 +75,8 @@ struct event_constraint { #define PERF_X86_EVENT_DYNAMIC 0x0080 /* dynamic alloc'd constraint */ #define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */ #define PERF_X86_EVENT_EXCL_ACCT 0x0200 /* accounted EXCL event */ +#define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */ +#define PERF_X86_EVENT_FREERUNNING 0x0800 /* use freerunning PEBS */ struct amd_nb { @@ -88,6 +90,18 @@ struct amd_nb { #define MAX_PEBS_EVENTS 8 /* + * Flags PEBS can handle without an PMI. + * + * TID can only be handled by flushing at context switch. + * + */ +#define PEBS_FREERUNNING_FLAGS \ + (PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \ + PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \ + PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \ + PERF_SAMPLE_TRANSACTION) + +/* * A debug store configuration. * * We only support architectures that use 64bit fields. @@ -133,7 +147,6 @@ enum intel_excl_state_type { }; struct intel_excl_states { - enum intel_excl_state_type init_state[X86_PMC_IDX_MAX]; enum intel_excl_state_type state[X86_PMC_IDX_MAX]; bool sched_started; /* true if scheduling has started */ }; @@ -527,10 +540,10 @@ struct x86_pmu { void (*put_event_constraints)(struct cpu_hw_events *cpuc, struct perf_event *event); - void (*commit_scheduling)(struct cpu_hw_events *cpuc, int idx, int cntr); - void (*start_scheduling)(struct cpu_hw_events *cpuc); + void (*commit_scheduling)(struct cpu_hw_events *cpuc, int idx, int cntr); + void (*stop_scheduling)(struct cpu_hw_events *cpuc); struct event_constraint *event_constraints; @@ -870,6 +883,8 @@ void intel_pmu_pebs_enable_all(void); void intel_pmu_pebs_disable_all(void); +void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in); + void intel_ds_init(void); void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 2813ea0f1..6326ae24e 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1903,9 +1903,8 @@ static void intel_start_scheduling(struct cpu_hw_events *cpuc) { struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct intel_excl_states *xl, *xlo; + struct intel_excl_states *xl; int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; /* sibling thread */ /* * nothing needed if in group validation mode @@ -1916,10 +1915,9 @@ intel_start_scheduling(struct cpu_hw_events *cpuc) /* * no exclusion needed */ - if (!excl_cntrs) + if (WARN_ON_ONCE(!excl_cntrs)) return; - xlo = &excl_cntrs->states[o_tid]; xl = &excl_cntrs->states[tid]; xl->sched_started = true; @@ -1928,22 +1926,41 @@ intel_start_scheduling(struct cpu_hw_events *cpuc) * in stop_event_scheduling() * makes scheduling appear as a transaction */ - WARN_ON_ONCE(!irqs_disabled()); raw_spin_lock(&excl_cntrs->lock); +} - /* - * save initial state of sibling thread - */ - memcpy(xlo->init_state, xlo->state, sizeof(xlo->init_state)); +static void intel_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int cntr) +{ + struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; + struct event_constraint *c = cpuc->event_constraint[idx]; + struct intel_excl_states *xl; + int tid = cpuc->excl_thread_id; + + if (cpuc->is_fake || !is_ht_workaround_enabled()) + return; + + if (WARN_ON_ONCE(!excl_cntrs)) + return; + + if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) + return; + + xl = &excl_cntrs->states[tid]; + + lockdep_assert_held(&excl_cntrs->lock); + + if (c->flags & PERF_X86_EVENT_EXCL) + xl->state[cntr] = INTEL_EXCL_EXCLUSIVE; + else + xl->state[cntr] = INTEL_EXCL_SHARED; } static void intel_stop_scheduling(struct cpu_hw_events *cpuc) { struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct intel_excl_states *xl, *xlo; + struct intel_excl_states *xl; int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; /* sibling thread */ /* * nothing needed if in group validation mode @@ -1953,17 +1970,11 @@ intel_stop_scheduling(struct cpu_hw_events *cpuc) /* * no exclusion needed */ - if (!excl_cntrs) + if (WARN_ON_ONCE(!excl_cntrs)) return; - xlo = &excl_cntrs->states[o_tid]; xl = &excl_cntrs->states[tid]; - /* - * make new sibling thread state visible - */ - memcpy(xlo->state, xlo->init_state, sizeof(xlo->state)); - xl->sched_started = false; /* * release shared state lock (acquired in intel_start_scheduling()) @@ -1975,12 +1986,10 @@ static struct event_constraint * intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, int idx, struct event_constraint *c) { - struct event_constraint *cx; struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct intel_excl_states *xl, *xlo; - int is_excl, i; + struct intel_excl_states *xlo; int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; /* alternate */ + int is_excl, i; /* * validating a group does not require @@ -1992,27 +2001,8 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, /* * no exclusion needed */ - if (!excl_cntrs) + if (WARN_ON_ONCE(!excl_cntrs)) return c; - /* - * event requires exclusive counter access - * across HT threads - */ - is_excl = c->flags & PERF_X86_EVENT_EXCL; - if (is_excl && !(event->hw.flags & PERF_X86_EVENT_EXCL_ACCT)) { - event->hw.flags |= PERF_X86_EVENT_EXCL_ACCT; - if (!cpuc->n_excl++) - WRITE_ONCE(excl_cntrs->has_exclusive[tid], 1); - } - - /* - * xl = state of current HT - * xlo = state of sibling HT - */ - xl = &excl_cntrs->states[tid]; - xlo = &excl_cntrs->states[o_tid]; - - cx = c; /* * because we modify the constraint, we need @@ -2023,10 +2013,7 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, * been cloned (marked dynamic) */ if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) { - - /* sanity check */ - if (idx < 0) - return &emptyconstraint; + struct event_constraint *cx; /* * grab pre-allocated constraint entry @@ -2037,13 +2024,14 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, * initialize dynamic constraint * with static constraint */ - memcpy(cx, c, sizeof(*cx)); + *cx = *c; /* * mark constraint as dynamic, so we * can free it later on */ cx->flags |= PERF_X86_EVENT_DYNAMIC; + c = cx; } /* @@ -2054,6 +2042,22 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, */ /* + * state of sibling HT + */ + xlo = &excl_cntrs->states[tid ^ 1]; + + /* + * event requires exclusive counter access + * across HT threads + */ + is_excl = c->flags & PERF_X86_EVENT_EXCL; + if (is_excl && !(event->hw.flags & PERF_X86_EVENT_EXCL_ACCT)) { + event->hw.flags |= PERF_X86_EVENT_EXCL_ACCT; + if (!cpuc->n_excl++) + WRITE_ONCE(excl_cntrs->has_exclusive[tid], 1); + } + + /* * Modify static constraint with current dynamic * state of thread * @@ -2061,37 +2065,37 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, * SHARED : sibling counter measuring non-exclusive event * UNUSED : sibling counter unused */ - for_each_set_bit(i, cx->idxmsk, X86_PMC_IDX_MAX) { + for_each_set_bit(i, c->idxmsk, X86_PMC_IDX_MAX) { /* * exclusive event in sibling counter * our corresponding counter cannot be used * regardless of our event */ - if (xl->state[i] == INTEL_EXCL_EXCLUSIVE) - __clear_bit(i, cx->idxmsk); + if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE) + __clear_bit(i, c->idxmsk); /* * if measuring an exclusive event, sibling * measuring non-exclusive, then counter cannot * be used */ - if (is_excl && xl->state[i] == INTEL_EXCL_SHARED) - __clear_bit(i, cx->idxmsk); + if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED) + __clear_bit(i, c->idxmsk); } /* * recompute actual bit weight for scheduling algorithm */ - cx->weight = hweight64(cx->idxmsk64); + c->weight = hweight64(c->idxmsk64); /* * if we return an empty mask, then switch * back to static empty constraint to avoid * the cost of freeing later on */ - if (cx->weight == 0) - cx = &emptyconstraint; + if (c->weight == 0) + c = &emptyconstraint; - return cx; + return c; } static struct event_constraint * @@ -2124,10 +2128,8 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc, { struct hw_perf_event *hwc = &event->hw; struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct intel_excl_states *xlo, *xl; - unsigned long flags = 0; /* keep compiler happy */ int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; + struct intel_excl_states *xl; /* * nothing needed if in group validation mode @@ -2135,13 +2137,9 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc, if (cpuc->is_fake) return; - WARN_ON_ONCE(!excl_cntrs); - - if (!excl_cntrs) + if (WARN_ON_ONCE(!excl_cntrs)) return; - xl = &excl_cntrs->states[tid]; - xlo = &excl_cntrs->states[o_tid]; if (hwc->flags & PERF_X86_EVENT_EXCL_ACCT) { hwc->flags &= ~PERF_X86_EVENT_EXCL_ACCT; if (!--cpuc->n_excl) @@ -2149,22 +2147,25 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc, } /* - * put_constraint may be called from x86_schedule_events() - * which already has the lock held so here make locking - * conditional + * If event was actually assigned, then mark the counter state as + * unused now. */ - if (!xl->sched_started) - raw_spin_lock_irqsave(&excl_cntrs->lock, flags); + if (hwc->idx >= 0) { + xl = &excl_cntrs->states[tid]; - /* - * if event was actually assigned, then mark the - * counter state as unused now - */ - if (hwc->idx >= 0) - xlo->state[hwc->idx] = INTEL_EXCL_UNUSED; + /* + * put_constraint may be called from x86_schedule_events() + * which already has the lock held so here make locking + * conditional. + */ + if (!xl->sched_started) + raw_spin_lock(&excl_cntrs->lock); - if (!xl->sched_started) - raw_spin_unlock_irqrestore(&excl_cntrs->lock, flags); + xl->state[hwc->idx] = INTEL_EXCL_UNUSED; + + if (!xl->sched_started) + raw_spin_unlock(&excl_cntrs->lock); + } } static void @@ -2196,41 +2197,6 @@ static void intel_put_event_constraints(struct cpu_hw_events *cpuc, intel_put_excl_constraints(cpuc, event); } -static void intel_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int cntr) -{ - struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct event_constraint *c = cpuc->event_constraint[idx]; - struct intel_excl_states *xlo, *xl; - int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; - int is_excl; - - if (cpuc->is_fake || !c) - return; - - is_excl = c->flags & PERF_X86_EVENT_EXCL; - - if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) - return; - - WARN_ON_ONCE(!excl_cntrs); - - if (!excl_cntrs) - return; - - xl = &excl_cntrs->states[tid]; - xlo = &excl_cntrs->states[o_tid]; - - WARN_ON_ONCE(!raw_spin_is_locked(&excl_cntrs->lock)); - - if (cntr >= 0) { - if (is_excl) - xlo->init_state[cntr] = INTEL_EXCL_EXCLUSIVE; - else - xlo->init_state[cntr] = INTEL_EXCL_SHARED; - } -} - static void intel_pebs_aliases_core2(struct perf_event *event) { if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) { @@ -2294,8 +2260,15 @@ static int intel_pmu_hw_config(struct perf_event *event) if (ret) return ret; - if (event->attr.precise_ip && x86_pmu.pebs_aliases) - x86_pmu.pebs_aliases(event); + if (event->attr.precise_ip) { + if (!event->attr.freq) { + event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD; + if (!(event->attr.sample_type & ~PEBS_FREERUNNING_FLAGS)) + event->hw.flags |= PERF_X86_EVENT_FREERUNNING; + } + if (x86_pmu.pebs_aliases) + x86_pmu.pebs_aliases(event); + } if (needs_branch_stack(event)) { ret = intel_pmu_setup_lbr_filter(event); @@ -2544,19 +2517,11 @@ struct intel_shared_regs *allocate_shared_regs(int cpu) static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu) { struct intel_excl_cntrs *c; - int i; c = kzalloc_node(sizeof(struct intel_excl_cntrs), GFP_KERNEL, cpu_to_node(cpu)); if (c) { raw_spin_lock_init(&c->lock); - for (i = 0; i < X86_PMC_IDX_MAX; i++) { - c->states[0].state[i] = INTEL_EXCL_UNUSED; - c->states[0].init_state[i] = INTEL_EXCL_UNUSED; - - c->states[1].state[i] = INTEL_EXCL_UNUSED; - c->states[1].init_state[i] = INTEL_EXCL_UNUSED; - } c->core_id = -1; } return c; @@ -2569,7 +2534,7 @@ static int intel_pmu_cpu_prepare(int cpu) if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) { cpuc->shared_regs = allocate_shared_regs(cpu); if (!cpuc->shared_regs) - return NOTIFY_BAD; + goto err; } if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) { @@ -2577,18 +2542,27 @@ static int intel_pmu_cpu_prepare(int cpu) cpuc->constraint_list = kzalloc(sz, GFP_KERNEL); if (!cpuc->constraint_list) - return NOTIFY_BAD; + goto err_shared_regs; cpuc->excl_cntrs = allocate_excl_cntrs(cpu); - if (!cpuc->excl_cntrs) { - kfree(cpuc->constraint_list); - kfree(cpuc->shared_regs); - return NOTIFY_BAD; - } + if (!cpuc->excl_cntrs) + goto err_constraint_list; + cpuc->excl_thread_id = 0; } return NOTIFY_OK; + +err_constraint_list: + kfree(cpuc->constraint_list); + cpuc->constraint_list = NULL; + +err_shared_regs: + kfree(cpuc->shared_regs); + cpuc->shared_regs = NULL; + +err: + return NOTIFY_BAD; } static void intel_pmu_cpu_starting(int cpu) @@ -2611,7 +2585,7 @@ static void intel_pmu_cpu_starting(int cpu) if (!(x86_pmu.flags & PMU_FL_NO_HT_SHARING)) { void **onln = &cpuc->kfree_on_online[X86_PERF_KFREE_SHARED]; - for_each_cpu(i, topology_thread_cpumask(cpu)) { + for_each_cpu(i, topology_sibling_cpumask(cpu)) { struct intel_shared_regs *pc; pc = per_cpu(cpu_hw_events, i).shared_regs; @@ -2629,7 +2603,7 @@ static void intel_pmu_cpu_starting(int cpu) cpuc->lbr_sel = &cpuc->shared_regs->regs[EXTRA_REG_LBR]; if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) { - for_each_cpu(i, topology_thread_cpumask(cpu)) { + for_each_cpu(i, topology_sibling_cpumask(cpu)) { struct intel_excl_cntrs *c; c = per_cpu(cpu_hw_events, i).excl_cntrs; @@ -2677,6 +2651,15 @@ static void intel_pmu_cpu_dying(int cpu) fini_debug_store_on_cpu(cpu); } +static void intel_pmu_sched_task(struct perf_event_context *ctx, + bool sched_in) +{ + if (x86_pmu.pebs_active) + intel_pmu_pebs_sched_task(ctx, sched_in); + if (x86_pmu.lbr_nr) + intel_pmu_lbr_sched_task(ctx, sched_in); +} + PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63"); PMU_FORMAT_ATTR(ldlat, "config1:0-15"); @@ -2766,7 +2749,7 @@ static __initconst const struct x86_pmu intel_pmu = { .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, .guest_get_msrs = intel_guest_get_msrs, - .sched_task = intel_pmu_lbr_sched_task, + .sched_task = intel_pmu_sched_task, }; static __init void intel_clovertown_quirk(void) @@ -2939,8 +2922,8 @@ static __init void intel_ht_bug(void) { x86_pmu.flags |= PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED; - x86_pmu.commit_scheduling = intel_commit_scheduling; x86_pmu.start_scheduling = intel_start_scheduling; + x86_pmu.commit_scheduling = intel_commit_scheduling; x86_pmu.stop_scheduling = intel_stop_scheduling; } @@ -3388,7 +3371,7 @@ static __init int fixup_ht_bug(void) if (!(x86_pmu.flags & PMU_FL_EXCL_ENABLED)) return 0; - w = cpumask_weight(topology_thread_cpumask(cpu)); + w = cpumask_weight(topology_sibling_cpumask(cpu)); if (w > 1) { pr_info("PMU erratum BJ122, BV98, HSD29 worked around, HT is on\n"); return 0; @@ -3398,8 +3381,8 @@ static __init int fixup_ht_bug(void) x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED); - x86_pmu.commit_scheduling = NULL; x86_pmu.start_scheduling = NULL; + x86_pmu.commit_scheduling = NULL; x86_pmu.stop_scheduling = NULL; watchdog_nmi_enable_all(); diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/kernel/cpu/perf_event_intel_bts.c index 7795f3f8b..43dd672d7 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_bts.c +++ b/arch/x86/kernel/cpu/perf_event_intel_bts.c @@ -530,5 +530,4 @@ static __init int bts_init(void) return perf_pmu_register(&bts_pmu, "intel_bts", -1); } - -module_init(bts_init); +arch_initcall(bts_init); diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c index cb77b11bc..377e8f8ed 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c +++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c @@ -13,16 +13,35 @@ #define MSR_IA32_QM_CTR 0x0c8e #define MSR_IA32_QM_EVTSEL 0x0c8d -static unsigned int cqm_max_rmid = -1; +static u32 cqm_max_rmid = -1; static unsigned int cqm_l3_scale; /* supposedly cacheline size */ -struct intel_cqm_state { - raw_spinlock_t lock; - int rmid; - int cnt; +/** + * struct intel_pqr_state - State cache for the PQR MSR + * @rmid: The cached Resource Monitoring ID + * @closid: The cached Class Of Service ID + * @rmid_usecnt: The usage counter for rmid + * + * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the + * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always + * contains both parts, so we need to cache them. + * + * The cache also helps to avoid pointless updates if the value does + * not change. + */ +struct intel_pqr_state { + u32 rmid; + u32 closid; + int rmid_usecnt; }; -static DEFINE_PER_CPU(struct intel_cqm_state, cqm_state); +/* + * The cached intel_pqr_state is strictly per CPU and can never be + * updated from a remote CPU. Both functions which modify the state + * (intel_cqm_event_start and intel_cqm_event_stop) are called with + * interrupts disabled, which is sufficient for the protection. + */ +static DEFINE_PER_CPU(struct intel_pqr_state, pqr_state); /* * Protects cache_cgroups and cqm_rmid_free_lru and cqm_rmid_limbo_lru. @@ -57,7 +76,7 @@ static cpumask_t cqm_cpumask; * near-zero occupancy value, i.e. no cachelines are tagged with this * RMID, once __intel_cqm_rmid_rotate() returns. */ -static unsigned int intel_cqm_rotation_rmid; +static u32 intel_cqm_rotation_rmid; #define INVALID_RMID (-1) @@ -69,7 +88,7 @@ static unsigned int intel_cqm_rotation_rmid; * Likewise, an rmid value of -1 is used to indicate "no rmid currently * assigned" and is used as part of the rotation code. */ -static inline bool __rmid_valid(unsigned int rmid) +static inline bool __rmid_valid(u32 rmid) { if (!rmid || rmid == INVALID_RMID) return false; @@ -77,7 +96,7 @@ static inline bool __rmid_valid(unsigned int rmid) return true; } -static u64 __rmid_read(unsigned int rmid) +static u64 __rmid_read(u32 rmid) { u64 val; @@ -102,7 +121,7 @@ enum rmid_recycle_state { }; struct cqm_rmid_entry { - unsigned int rmid; + u32 rmid; enum rmid_recycle_state state; struct list_head list; unsigned long queue_time; @@ -147,7 +166,7 @@ static LIST_HEAD(cqm_rmid_limbo_lru); */ static struct cqm_rmid_entry **cqm_rmid_ptrs; -static inline struct cqm_rmid_entry *__rmid_entry(int rmid) +static inline struct cqm_rmid_entry *__rmid_entry(u32 rmid) { struct cqm_rmid_entry *entry; @@ -162,7 +181,7 @@ static inline struct cqm_rmid_entry *__rmid_entry(int rmid) * * We expect to be called with cache_mutex held. */ -static int __get_rmid(void) +static u32 __get_rmid(void) { struct cqm_rmid_entry *entry; @@ -177,7 +196,7 @@ static int __get_rmid(void) return entry->rmid; } -static void __put_rmid(unsigned int rmid) +static void __put_rmid(u32 rmid) { struct cqm_rmid_entry *entry; @@ -372,7 +391,7 @@ static bool __conflict_event(struct perf_event *a, struct perf_event *b) } struct rmid_read { - unsigned int rmid; + u32 rmid; atomic64_t value; }; @@ -381,12 +400,11 @@ static void __intel_cqm_event_count(void *info); /* * Exchange the RMID of a group of events. */ -static unsigned int -intel_cqm_xchg_rmid(struct perf_event *group, unsigned int rmid) +static u32 intel_cqm_xchg_rmid(struct perf_event *group, u32 rmid) { struct perf_event *event; - unsigned int old_rmid = group->hw.cqm_rmid; struct list_head *head = &group->hw.cqm_group_entry; + u32 old_rmid = group->hw.cqm_rmid; lockdep_assert_held(&cache_mutex); @@ -451,7 +469,7 @@ static void intel_cqm_stable(void *arg) * If we have group events waiting for an RMID that don't conflict with * events already running, assign @rmid. */ -static bool intel_cqm_sched_in_event(unsigned int rmid) +static bool intel_cqm_sched_in_event(u32 rmid) { struct perf_event *leader, *event; @@ -598,7 +616,7 @@ static bool intel_cqm_rmid_stabilize(unsigned int *available) static void __intel_cqm_pick_and_rotate(struct perf_event *next) { struct perf_event *rotor; - unsigned int rmid; + u32 rmid; lockdep_assert_held(&cache_mutex); @@ -626,7 +644,7 @@ static void __intel_cqm_pick_and_rotate(struct perf_event *next) static void intel_cqm_sched_out_conflicting_events(struct perf_event *event) { struct perf_event *group, *g; - unsigned int rmid; + u32 rmid; lockdep_assert_held(&cache_mutex); @@ -828,8 +846,8 @@ static void intel_cqm_setup_event(struct perf_event *event, struct perf_event **group) { struct perf_event *iter; - unsigned int rmid; bool conflict = false; + u32 rmid; list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) { rmid = iter->hw.cqm_rmid; @@ -860,7 +878,7 @@ static void intel_cqm_setup_event(struct perf_event *event, static void intel_cqm_event_read(struct perf_event *event) { unsigned long flags; - unsigned int rmid; + u32 rmid; u64 val; /* @@ -969,55 +987,48 @@ out: static void intel_cqm_event_start(struct perf_event *event, int mode) { - struct intel_cqm_state *state = this_cpu_ptr(&cqm_state); - unsigned int rmid = event->hw.cqm_rmid; - unsigned long flags; + struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); + u32 rmid = event->hw.cqm_rmid; if (!(event->hw.cqm_state & PERF_HES_STOPPED)) return; event->hw.cqm_state &= ~PERF_HES_STOPPED; - raw_spin_lock_irqsave(&state->lock, flags); - - if (state->cnt++) - WARN_ON_ONCE(state->rmid != rmid); - else + if (state->rmid_usecnt++) { + if (!WARN_ON_ONCE(state->rmid != rmid)) + return; + } else { WARN_ON_ONCE(state->rmid); + } state->rmid = rmid; - wrmsrl(MSR_IA32_PQR_ASSOC, state->rmid); - - raw_spin_unlock_irqrestore(&state->lock, flags); + wrmsr(MSR_IA32_PQR_ASSOC, rmid, state->closid); } static void intel_cqm_event_stop(struct perf_event *event, int mode) { - struct intel_cqm_state *state = this_cpu_ptr(&cqm_state); - unsigned long flags; + struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); if (event->hw.cqm_state & PERF_HES_STOPPED) return; event->hw.cqm_state |= PERF_HES_STOPPED; - raw_spin_lock_irqsave(&state->lock, flags); intel_cqm_event_read(event); - if (!--state->cnt) { + if (!--state->rmid_usecnt) { state->rmid = 0; - wrmsrl(MSR_IA32_PQR_ASSOC, 0); + wrmsr(MSR_IA32_PQR_ASSOC, 0, state->closid); } else { WARN_ON_ONCE(!state->rmid); } - - raw_spin_unlock_irqrestore(&state->lock, flags); } static int intel_cqm_event_add(struct perf_event *event, int mode) { unsigned long flags; - unsigned int rmid; + u32 rmid; raw_spin_lock_irqsave(&cache_lock, flags); @@ -1032,11 +1043,6 @@ static int intel_cqm_event_add(struct perf_event *event, int mode) return 0; } -static void intel_cqm_event_del(struct perf_event *event, int mode) -{ - intel_cqm_event_stop(event, mode); -} - static void intel_cqm_event_destroy(struct perf_event *event) { struct perf_event *group_other = NULL; @@ -1065,7 +1071,7 @@ static void intel_cqm_event_destroy(struct perf_event *event) list_replace(&event->hw.cqm_groups_entry, &group_other->hw.cqm_groups_entry); } else { - unsigned int rmid = event->hw.cqm_rmid; + u32 rmid = event->hw.cqm_rmid; if (__rmid_valid(rmid)) __put_rmid(rmid); @@ -1229,7 +1235,7 @@ static struct pmu intel_cqm_pmu = { .task_ctx_nr = perf_sw_context, .event_init = intel_cqm_event_init, .add = intel_cqm_event_add, - .del = intel_cqm_event_del, + .del = intel_cqm_event_stop, .start = intel_cqm_event_start, .stop = intel_cqm_event_stop, .read = intel_cqm_event_read, @@ -1249,14 +1255,14 @@ static inline void cqm_pick_event_reader(int cpu) cpumask_set_cpu(cpu, &cqm_cpumask); } -static void intel_cqm_cpu_prepare(unsigned int cpu) +static void intel_cqm_cpu_starting(unsigned int cpu) { - struct intel_cqm_state *state = &per_cpu(cqm_state, cpu); + struct intel_pqr_state *state = &per_cpu(pqr_state, cpu); struct cpuinfo_x86 *c = &cpu_data(cpu); - raw_spin_lock_init(&state->lock); state->rmid = 0; - state->cnt = 0; + state->closid = 0; + state->rmid_usecnt = 0; WARN_ON(c->x86_cache_max_rmid != cqm_max_rmid); WARN_ON(c->x86_cache_occ_scale != cqm_l3_scale); @@ -1290,13 +1296,11 @@ static int intel_cqm_cpu_notifier(struct notifier_block *nb, unsigned int cpu = (unsigned long)hcpu; switch (action & ~CPU_TASKS_FROZEN) { - case CPU_UP_PREPARE: - intel_cqm_cpu_prepare(cpu); - break; case CPU_DOWN_PREPARE: intel_cqm_cpu_exit(cpu); break; case CPU_STARTING: + intel_cqm_cpu_starting(cpu); cqm_pick_event_reader(cpu); break; } @@ -1367,7 +1371,7 @@ static int __init intel_cqm_init(void) goto out; for_each_online_cpu(i) { - intel_cqm_cpu_prepare(i); + intel_cqm_cpu_starting(i); cqm_pick_event_reader(i); } diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 7f73b3553..71fc40238 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -11,7 +11,7 @@ #define BTS_RECORD_SIZE 24 #define BTS_BUFFER_SIZE (PAGE_SIZE << 4) -#define PEBS_BUFFER_SIZE PAGE_SIZE +#define PEBS_BUFFER_SIZE (PAGE_SIZE << 4) #define PEBS_FIXUP_SIZE PAGE_SIZE /* @@ -250,7 +250,7 @@ static int alloc_pebs_buffer(int cpu) { struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; int node = cpu_to_node(cpu); - int max, thresh = 1; /* always use a single PEBS record */ + int max; void *buffer, *ibuffer; if (!x86_pmu.pebs) @@ -280,9 +280,6 @@ static int alloc_pebs_buffer(int cpu) ds->pebs_absolute_maximum = ds->pebs_buffer_base + max * x86_pmu.pebs_record_size; - ds->pebs_interrupt_threshold = ds->pebs_buffer_base + - thresh * x86_pmu.pebs_record_size; - return 0; } @@ -549,6 +546,19 @@ int intel_pmu_drain_bts_buffer(void) return 1; } +static inline void intel_pmu_drain_pebs_buffer(void) +{ + struct pt_regs regs; + + x86_pmu.drain_pebs(®s); +} + +void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in) +{ + if (!sched_in) + intel_pmu_drain_pebs_buffer(); +} + /* * PEBS */ @@ -684,25 +694,66 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event) return &emptyconstraint; } +static inline bool pebs_is_enabled(struct cpu_hw_events *cpuc) +{ + return (cpuc->pebs_enabled & ((1ULL << MAX_PEBS_EVENTS) - 1)); +} + void intel_pmu_pebs_enable(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; + struct debug_store *ds = cpuc->ds; + bool first_pebs; + u64 threshold; hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT; + first_pebs = !pebs_is_enabled(cpuc); cpuc->pebs_enabled |= 1ULL << hwc->idx; if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32); else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST) cpuc->pebs_enabled |= 1ULL << 63; + + /* + * When the event is constrained enough we can use a larger + * threshold and run the event with less frequent PMI. + */ + if (hwc->flags & PERF_X86_EVENT_FREERUNNING) { + threshold = ds->pebs_absolute_maximum - + x86_pmu.max_pebs_events * x86_pmu.pebs_record_size; + + if (first_pebs) + perf_sched_cb_inc(event->ctx->pmu); + } else { + threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size; + + /* + * If not all events can use larger buffer, + * roll back to threshold = 1 + */ + if (!first_pebs && + (ds->pebs_interrupt_threshold > threshold)) + perf_sched_cb_dec(event->ctx->pmu); + } + + /* Use auto-reload if possible to save a MSR write in the PMI */ + if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { + ds->pebs_event_reset[hwc->idx] = + (u64)(-hwc->sample_period) & x86_pmu.cntval_mask; + } + + if (first_pebs || ds->pebs_interrupt_threshold > threshold) + ds->pebs_interrupt_threshold = threshold; } void intel_pmu_pebs_disable(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; + struct debug_store *ds = cpuc->ds; cpuc->pebs_enabled &= ~(1ULL << hwc->idx); @@ -711,6 +762,13 @@ void intel_pmu_pebs_disable(struct perf_event *event) else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST) cpuc->pebs_enabled &= ~(1ULL << 63); + if (ds->pebs_interrupt_threshold > + ds->pebs_buffer_base + x86_pmu.pebs_record_size) { + intel_pmu_drain_pebs_buffer(); + if (!pebs_is_enabled(cpuc)) + perf_sched_cb_dec(event->ctx->pmu); + } + if (cpuc->enabled) wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); @@ -846,8 +904,10 @@ static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs) return txn; } -static void __intel_pmu_pebs_event(struct perf_event *event, - struct pt_regs *iregs, void *__pebs) +static void setup_pebs_sample_data(struct perf_event *event, + struct pt_regs *iregs, void *__pebs, + struct perf_sample_data *data, + struct pt_regs *regs) { #define PERF_X86_EVENT_PEBS_HSW_PREC \ (PERF_X86_EVENT_PEBS_ST_HSW | \ @@ -859,13 +919,11 @@ static void __intel_pmu_pebs_event(struct perf_event *event, */ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct pebs_record_hsw *pebs = __pebs; - struct perf_sample_data data; - struct pt_regs regs; u64 sample_type; int fll, fst, dsrc; int fl = event->hw.flags; - if (!intel_pmu_save_and_restart(event)) + if (pebs == NULL) return; sample_type = event->attr.sample_type; @@ -874,15 +932,15 @@ static void __intel_pmu_pebs_event(struct perf_event *event, fll = fl & PERF_X86_EVENT_PEBS_LDLAT; fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC); - perf_sample_data_init(&data, 0, event->hw.last_period); + perf_sample_data_init(data, 0, event->hw.last_period); - data.period = event->hw.last_period; + data->period = event->hw.last_period; /* * Use latency for weight (only avail with PEBS-LL) */ if (fll && (sample_type & PERF_SAMPLE_WEIGHT)) - data.weight = pebs->lat; + data->weight = pebs->lat; /* * data.data_src encodes the data source @@ -895,7 +953,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event, val = precise_datala_hsw(event, pebs->dse); else if (fst) val = precise_store_data(pebs->dse); - data.data_src.val = val; + data->data_src.val = val; } /* @@ -908,61 +966,123 @@ static void __intel_pmu_pebs_event(struct perf_event *event, * PERF_SAMPLE_IP and PERF_SAMPLE_CALLCHAIN to function properly. * A possible PERF_SAMPLE_REGS will have to transfer all regs. */ - regs = *iregs; - regs.flags = pebs->flags; - set_linear_ip(®s, pebs->ip); - regs.bp = pebs->bp; - regs.sp = pebs->sp; + *regs = *iregs; + regs->flags = pebs->flags; + set_linear_ip(regs, pebs->ip); + regs->bp = pebs->bp; + regs->sp = pebs->sp; if (sample_type & PERF_SAMPLE_REGS_INTR) { - regs.ax = pebs->ax; - regs.bx = pebs->bx; - regs.cx = pebs->cx; - regs.dx = pebs->dx; - regs.si = pebs->si; - regs.di = pebs->di; - regs.bp = pebs->bp; - regs.sp = pebs->sp; - - regs.flags = pebs->flags; + regs->ax = pebs->ax; + regs->bx = pebs->bx; + regs->cx = pebs->cx; + regs->dx = pebs->dx; + regs->si = pebs->si; + regs->di = pebs->di; + regs->bp = pebs->bp; + regs->sp = pebs->sp; + + regs->flags = pebs->flags; #ifndef CONFIG_X86_32 - regs.r8 = pebs->r8; - regs.r9 = pebs->r9; - regs.r10 = pebs->r10; - regs.r11 = pebs->r11; - regs.r12 = pebs->r12; - regs.r13 = pebs->r13; - regs.r14 = pebs->r14; - regs.r15 = pebs->r15; + regs->r8 = pebs->r8; + regs->r9 = pebs->r9; + regs->r10 = pebs->r10; + regs->r11 = pebs->r11; + regs->r12 = pebs->r12; + regs->r13 = pebs->r13; + regs->r14 = pebs->r14; + regs->r15 = pebs->r15; #endif } if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) { - regs.ip = pebs->real_ip; - regs.flags |= PERF_EFLAGS_EXACT; - } else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(®s)) - regs.flags |= PERF_EFLAGS_EXACT; + regs->ip = pebs->real_ip; + regs->flags |= PERF_EFLAGS_EXACT; + } else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(regs)) + regs->flags |= PERF_EFLAGS_EXACT; else - regs.flags &= ~PERF_EFLAGS_EXACT; + regs->flags &= ~PERF_EFLAGS_EXACT; if ((sample_type & PERF_SAMPLE_ADDR) && x86_pmu.intel_cap.pebs_format >= 1) - data.addr = pebs->dla; + data->addr = pebs->dla; if (x86_pmu.intel_cap.pebs_format >= 2) { /* Only set the TSX weight when no memory weight. */ if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll) - data.weight = intel_hsw_weight(pebs); + data->weight = intel_hsw_weight(pebs); if (sample_type & PERF_SAMPLE_TRANSACTION) - data.txn = intel_hsw_transaction(pebs); + data->txn = intel_hsw_transaction(pebs); } if (has_branch_stack(event)) - data.br_stack = &cpuc->lbr_stack; + data->br_stack = &cpuc->lbr_stack; +} + +static inline void * +get_next_pebs_record_by_bit(void *base, void *top, int bit) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + void *at; + u64 pebs_status; + + if (base == NULL) + return NULL; + + for (at = base; at < top; at += x86_pmu.pebs_record_size) { + struct pebs_record_nhm *p = at; + + if (test_bit(bit, (unsigned long *)&p->status)) { + /* PEBS v3 has accurate status bits */ + if (x86_pmu.intel_cap.pebs_format >= 3) + return at; - if (perf_event_overflow(event, &data, ®s)) + if (p->status == (1 << bit)) + return at; + + /* clear non-PEBS bit and re-check */ + pebs_status = p->status & cpuc->pebs_enabled; + pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1; + if (pebs_status == (1 << bit)) + return at; + } + } + return NULL; +} + +static void __intel_pmu_pebs_event(struct perf_event *event, + struct pt_regs *iregs, + void *base, void *top, + int bit, int count) +{ + struct perf_sample_data data; + struct pt_regs regs; + void *at = get_next_pebs_record_by_bit(base, top, bit); + + if (!intel_pmu_save_and_restart(event) && + !(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)) + return; + + while (count > 1) { + setup_pebs_sample_data(event, iregs, at, &data, ®s); + perf_event_output(event, &data, ®s); + at += x86_pmu.pebs_record_size; + at = get_next_pebs_record_by_bit(at, top, bit); + count--; + } + + setup_pebs_sample_data(event, iregs, at, &data, ®s); + + /* + * All but the last records are processed. + * The last one is left to be able to call the overflow handler. + */ + if (perf_event_overflow(event, &data, ®s)) { x86_pmu_stop(event, 0); + return; + } + } static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) @@ -992,72 +1112,99 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) if (!event->attr.precise_ip) return; - n = top - at; + n = (top - at) / x86_pmu.pebs_record_size; if (n <= 0) return; - /* - * Should not happen, we program the threshold at 1 and do not - * set a reset value. - */ - WARN_ONCE(n > 1, "bad leftover pebs %d\n", n); - at += n - 1; - - __intel_pmu_pebs_event(event, iregs, at); + __intel_pmu_pebs_event(event, iregs, at, top, 0, n); } static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct debug_store *ds = cpuc->ds; - struct perf_event *event = NULL; - void *at, *top; - u64 status = 0; - int bit; + struct perf_event *event; + void *base, *at, *top; + short counts[MAX_PEBS_EVENTS] = {}; + short error[MAX_PEBS_EVENTS] = {}; + int bit, i; if (!x86_pmu.pebs_active) return; - at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base; + base = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base; top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index; ds->pebs_index = ds->pebs_buffer_base; - if (unlikely(at > top)) + if (unlikely(base >= top)) return; - /* - * Should not happen, we program the threshold at 1 and do not - * set a reset value. - */ - WARN_ONCE(top - at > x86_pmu.max_pebs_events * x86_pmu.pebs_record_size, - "Unexpected number of pebs records %ld\n", - (long)(top - at) / x86_pmu.pebs_record_size); - - for (; at < top; at += x86_pmu.pebs_record_size) { + for (at = base; at < top; at += x86_pmu.pebs_record_size) { struct pebs_record_nhm *p = at; - for_each_set_bit(bit, (unsigned long *)&p->status, - x86_pmu.max_pebs_events) { - event = cpuc->events[bit]; - if (!test_bit(bit, cpuc->active_mask)) - continue; - - WARN_ON_ONCE(!event); + /* PEBS v3 has accurate status bits */ + if (x86_pmu.intel_cap.pebs_format >= 3) { + for_each_set_bit(bit, (unsigned long *)&p->status, + MAX_PEBS_EVENTS) + counts[bit]++; - if (!event->attr.precise_ip) - continue; + continue; + } - if (__test_and_set_bit(bit, (unsigned long *)&status)) + bit = find_first_bit((unsigned long *)&p->status, + x86_pmu.max_pebs_events); + if (bit >= x86_pmu.max_pebs_events) + continue; + if (!test_bit(bit, cpuc->active_mask)) + continue; + /* + * The PEBS hardware does not deal well with the situation + * when events happen near to each other and multiple bits + * are set. But it should happen rarely. + * + * If these events include one PEBS and multiple non-PEBS + * events, it doesn't impact PEBS record. The record will + * be handled normally. (slow path) + * + * If these events include two or more PEBS events, the + * records for the events can be collapsed into a single + * one, and it's not possible to reconstruct all events + * that caused the PEBS record. It's called collision. + * If collision happened, the record will be dropped. + * + */ + if (p->status != (1 << bit)) { + u64 pebs_status; + + /* slow path */ + pebs_status = p->status & cpuc->pebs_enabled; + pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1; + if (pebs_status != (1 << bit)) { + for_each_set_bit(i, (unsigned long *)&pebs_status, + MAX_PEBS_EVENTS) + error[i]++; continue; - - break; + } } + counts[bit]++; + } - if (!event || bit >= x86_pmu.max_pebs_events) + for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) { + if ((counts[bit] == 0) && (error[bit] == 0)) continue; + event = cpuc->events[bit]; + WARN_ON_ONCE(!event); + WARN_ON_ONCE(!event->attr.precise_ip); - __intel_pmu_pebs_event(event, iregs, at); + /* log dropped samples number */ + if (error[bit]) + perf_log_lost_samples(event, error[bit]); + + if (counts[bit]) { + __intel_pmu_pebs_event(event, iregs, base, + top, bit, counts[bit]); + } } } diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index 94e5b506c..452a7bd2d 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -96,6 +96,7 @@ enum { X86_BR_NO_TX = 1 << 14,/* not in transaction */ X86_BR_ZERO_CALL = 1 << 15,/* zero length call */ X86_BR_CALL_STACK = 1 << 16,/* call stack */ + X86_BR_IND_JMP = 1 << 17,/* indirect jump */ }; #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL) @@ -113,6 +114,7 @@ enum { X86_BR_IRQ |\ X86_BR_ABORT |\ X86_BR_IND_CALL |\ + X86_BR_IND_JMP |\ X86_BR_ZERO_CALL) #define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY) @@ -262,9 +264,6 @@ void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in) struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct x86_perf_task_context *task_ctx; - if (!x86_pmu.lbr_nr) - return; - /* * If LBR callstack feature is enabled and the stack was saved when * the task was scheduled out, restore the stack. Otherwise flush @@ -523,6 +522,9 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event) X86_BR_CALL_STACK; } + if (br_type & PERF_SAMPLE_BRANCH_IND_JUMP) + mask |= X86_BR_IND_JMP; + /* * stash actual user request into reg, it may * be used by fixup code for some CPU @@ -736,7 +738,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort) break; case 4: case 5: - ret = X86_BR_JMP; + ret = X86_BR_IND_JMP; break; } break; @@ -844,6 +846,7 @@ static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { */ [PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL | LBR_IND_JMP, [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, + [PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP, }; static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { @@ -856,6 +859,7 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { | LBR_FAR, [PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL, [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, + [PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP, }; static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { @@ -870,6 +874,7 @@ static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, [PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT] = LBR_REL_CALL | LBR_IND_CALL | LBR_RETURN | LBR_CALL_STACK, + [PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP, }; /* core */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c index 123ff1bb2..183de7196 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_pt.c +++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c @@ -187,15 +187,6 @@ static bool pt_event_valid(struct perf_event *event) * These all are cpu affine and operate on a local PT */ -static bool pt_is_running(void) -{ - u64 ctl; - - rdmsrl(MSR_IA32_RTIT_CTL, ctl); - - return !!(ctl & RTIT_CTL_TRACEEN); -} - static void pt_config(struct perf_event *event) { u64 reg; @@ -609,7 +600,12 @@ static unsigned int pt_topa_next_entry(struct pt_buffer *buf, unsigned int pg) * @handle: Current output handle. * * Place INT and STOP marks to prevent overwriting old data that the consumer - * hasn't yet collected. + * hasn't yet collected and waking up the consumer after a certain fraction of + * the buffer has filled up. Only needed and sensible for non-snapshot counters. + * + * This obviously relies on buf::head to figure out buffer markers, so it has + * to be called after pt_buffer_reset_offsets() and before the hardware tracing + * is enabled. */ static int pt_buffer_reset_markers(struct pt_buffer *buf, struct perf_output_handle *handle) @@ -618,9 +614,6 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf, unsigned long head = local64_read(&buf->head); unsigned long idx, npages, wakeup; - if (buf->snapshot) - return 0; - /* can't stop in the middle of an output region */ if (buf->output_off + handle->size + 1 < sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size)) @@ -674,7 +667,7 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf) struct topa *cur = buf->first, *prev = buf->last; struct topa_entry *te_cur = TOPA_ENTRY(cur, 0), *te_prev = TOPA_ENTRY(prev, prev->last - 1); - int pg = 0, idx = 0, ntopa = 0; + int pg = 0, idx = 0; while (pg < buf->nr_pages) { int tidx; @@ -689,9 +682,9 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf) /* advance to next topa table */ idx = 0; cur = list_entry(cur->list.next, struct topa, list); - ntopa++; - } else + } else { idx++; + } te_cur = TOPA_ENTRY(cur, idx); } @@ -703,7 +696,14 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf) * @head: Write pointer (aux_head) from AUX buffer. * * Find the ToPA table and entry corresponding to given @head and set buffer's - * "current" pointers accordingly. + * "current" pointers accordingly. This is done after we have obtained the + * current aux_head position from a successful call to perf_aux_output_begin() + * to make sure the hardware is writing to the right place. + * + * This function modifies buf::{cur,cur_idx,output_off} that will be programmed + * into PT msrs when the tracing is enabled and buf::head and buf::data_size, + * which are used to determine INT and STOP markers' locations by a subsequent + * call to pt_buffer_reset_markers(). */ static void pt_buffer_reset_offsets(struct pt_buffer *buf, unsigned long head) { @@ -901,6 +901,7 @@ void intel_pt_interrupt(void) } pt_buffer_reset_offsets(buf, pt->handle.head); + /* snapshot counters don't use PMI, so it's safe */ ret = pt_buffer_reset_markers(buf, &pt->handle); if (ret) { perf_aux_output_end(&pt->handle, 0, true); @@ -923,7 +924,7 @@ static void pt_event_start(struct perf_event *event, int mode) struct pt *pt = this_cpu_ptr(&pt_ctx); struct pt_buffer *buf = perf_get_aux(&pt->handle); - if (pt_is_running() || !buf || pt_buffer_is_full(buf, pt)) { + if (!buf || pt_buffer_is_full(buf, pt)) { event->hw.state = PERF_HES_STOPPED; return; } @@ -954,7 +955,6 @@ static void pt_event_stop(struct perf_event *event, int mode) event->hw.state = PERF_HES_STOPPED; if (mode & PERF_EF_UPDATE) { - struct pt *pt = this_cpu_ptr(&pt_ctx); struct pt_buffer *buf = perf_get_aux(&pt->handle); if (!buf) @@ -1106,5 +1106,4 @@ static __init int pt_init(void) return ret; } - -module_init(pt_init); +arch_initcall(pt_init); diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c index 358c54ad2..5cbd4e64f 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -204,9 +204,8 @@ again: static void rapl_start_hrtimer(struct rapl_pmu *pmu) { - __hrtimer_start_range_ns(&pmu->hrtimer, - pmu->timer_interval, 0, - HRTIMER_MODE_REL_PINNED, 0); + hrtimer_start(&pmu->hrtimer, pmu->timer_interval, + HRTIMER_MODE_REL_PINNED); } static void rapl_stop_hrtimer(struct rapl_pmu *pmu) diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 90b7c501c..21b5e38c9 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -233,9 +233,8 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer) void uncore_pmu_start_hrtimer(struct intel_uncore_box *box) { - __hrtimer_start_range_ns(&box->hrtimer, - ns_to_ktime(box->hrtimer_duration), 0, - HRTIMER_MODE_REL_PINNED, 0); + hrtimer_start(&box->hrtimer, ns_to_ktime(box->hrtimer_duration), + HRTIMER_MODE_REL_PINNED); } void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box) @@ -922,6 +921,9 @@ static int __init uncore_pci_init(void) case 69: /* Haswell Celeron */ ret = hsw_uncore_pci_init(); break; + case 61: /* Broadwell */ + ret = bdw_uncore_pci_init(); + break; default: return 0; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index ceac8f5dc..0f77f0a19 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -325,6 +325,7 @@ extern struct event_constraint uncore_constraint_empty; int snb_uncore_pci_init(void); int ivb_uncore_pci_init(void); int hsw_uncore_pci_init(void); +int bdw_uncore_pci_init(void); void snb_uncore_cpu_init(void); void nhm_uncore_cpu_init(void); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c index 4562e9e22..b005a78c7 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c @@ -7,6 +7,7 @@ #define PCI_DEVICE_ID_INTEL_IVB_E3_IMC 0x0150 #define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00 #define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04 +#define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604 /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -486,6 +487,14 @@ static const struct pci_device_id hsw_uncore_pci_ids[] = { { /* end: all zeroes */ }, }; +static const struct pci_device_id bdw_uncore_pci_ids[] = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ }, +}; + static struct pci_driver snb_uncore_pci_driver = { .name = "snb_uncore", .id_table = snb_uncore_pci_ids, @@ -501,6 +510,11 @@ static struct pci_driver hsw_uncore_pci_driver = { .id_table = hsw_uncore_pci_ids, }; +static struct pci_driver bdw_uncore_pci_driver = { + .name = "bdw_uncore", + .id_table = bdw_uncore_pci_ids, +}; + struct imc_uncore_pci_dev { __u32 pci_id; struct pci_driver *driver; @@ -514,6 +528,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = { IMC_DEV(IVB_E3_IMC, &ivb_uncore_pci_driver), /* Xeon E3-1200 v2/3rd Gen Core processor */ IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core Processor */ IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core ULT Mobile Processor */ + IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver), /* 5th Gen Core U */ { /* end marker */ } }; @@ -561,6 +576,11 @@ int hsw_uncore_pci_init(void) return imc_uncore_pci_init(); } +int bdw_uncore_pci_init(void) +{ + return imc_uncore_pci_init(); +} + /* end of Sandy Bridge uncore support */ /* Nehalem uncore support */ diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index e7d8c7608..18ca99f27 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -12,7 +12,8 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c, { #ifdef CONFIG_SMP seq_printf(m, "physical id\t: %d\n", c->phys_proc_id); - seq_printf(m, "siblings\t: %d\n", cpumask_weight(cpu_core_mask(cpu))); + seq_printf(m, "siblings\t: %d\n", + cpumask_weight(topology_core_cpumask(cpu))); seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id); seq_printf(m, "cpu cores\t: %d\n", c->booted_cores); seq_printf(m, "apicid\t\t: %d\n", c->apicid); diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index c76d3e37c..e068d6683 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -22,6 +22,7 @@ #include <linux/elfcore.h> #include <linux/module.h> #include <linux/slab.h> +#include <linux/vmalloc.h> #include <asm/processor.h> #include <asm/hardirq.h> diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 6367a780c..1f4acd68b 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -4,7 +4,6 @@ #include <linux/bootmem.h> #include <linux/export.h> #include <linux/io.h> -#include <linux/irqdomain.h> #include <linux/interrupt.h> #include <linux/list.h> #include <linux/of.h> @@ -17,6 +16,7 @@ #include <linux/of_pci.h> #include <linux/initrd.h> +#include <asm/irqdomain.h> #include <asm/hpet.h> #include <asm/apic.h> #include <asm/pci_x86.h> @@ -65,7 +65,7 @@ static int __init add_bus_probe(void) return of_platform_bus_probe(NULL, ce4100_ids, NULL); } -module_init(add_bus_probe); +device_initcall(add_bus_probe); #ifdef CONFIG_PCI struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus) @@ -196,38 +196,31 @@ static struct of_ioapic_type of_ioapic_type[] = }, }; -static int ioapic_xlate(struct irq_domain *domain, - struct device_node *controller, - const u32 *intspec, u32 intsize, - irq_hw_number_t *out_hwirq, u32 *out_type) +static int dt_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) { + struct of_phandle_args *irq_data = (void *)arg; struct of_ioapic_type *it; - u32 line, idx, gsi; + struct irq_alloc_info tmp; - if (WARN_ON(intsize < 2)) + if (WARN_ON(irq_data->args_count < 2)) return -EINVAL; - - line = intspec[0]; - - if (intspec[1] >= ARRAY_SIZE(of_ioapic_type)) + if (irq_data->args[1] >= ARRAY_SIZE(of_ioapic_type)) return -EINVAL; - it = &of_ioapic_type[intspec[1]]; + it = &of_ioapic_type[irq_data->args[1]]; + ioapic_set_alloc_attr(&tmp, NUMA_NO_NODE, it->trigger, it->polarity); + tmp.ioapic_id = mpc_ioapic_id(mp_irqdomain_ioapic_idx(domain)); + tmp.ioapic_pin = irq_data->args[0]; - idx = (u32)(long)domain->host_data; - gsi = mp_pin_to_gsi(idx, line); - if (mp_set_gsi_attr(gsi, it->trigger, it->polarity, cpu_to_node(0))) - return -EBUSY; - - *out_hwirq = line; - *out_type = it->out_type; - return 0; + return mp_irqdomain_alloc(domain, virq, nr_irqs, &tmp); } -const struct irq_domain_ops ioapic_irq_domain_ops = { - .map = mp_irqdomain_map, - .unmap = mp_irqdomain_unmap, - .xlate = ioapic_xlate, +static const struct irq_domain_ops ioapic_irq_domain_ops = { + .alloc = dt_irqdomain_alloc, + .free = mp_irqdomain_free, + .activate = mp_irqdomain_activate, + .deactivate = mp_irqdomain_deactivate, }; static void __init dtb_add_ioapic(struct device_node *dn) diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index e2ce85db2..a102564d0 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -149,6 +149,7 @@ static void __init e820_print_type(u32 type) case E820_UNUSABLE: printk(KERN_CONT "unusable"); break; + case E820_PMEM: case E820_PRAM: printk(KERN_CONT "persistent (type %u)", type); break; @@ -918,11 +919,32 @@ static inline const char *e820_type_to_string(int e820_type) case E820_ACPI: return "ACPI Tables"; case E820_NVS: return "ACPI Non-volatile Storage"; case E820_UNUSABLE: return "Unusable memory"; - case E820_PRAM: return "Persistent RAM"; + case E820_PRAM: return "Persistent Memory (legacy)"; + case E820_PMEM: return "Persistent Memory"; default: return "reserved"; } } +static bool do_mark_busy(u32 type, struct resource *res) +{ + /* this is the legacy bios/dos rom-shadow + mmio region */ + if (res->start < (1ULL<<20)) + return true; + + /* + * Treat persistent memory like device memory, i.e. reserve it + * for exclusive use of a driver + */ + switch (type) { + case E820_RESERVED: + case E820_PRAM: + case E820_PMEM: + return false; + default: + return true; + } +} + /* * Mark e820 reserved areas as busy for the resource manager. */ @@ -952,9 +974,7 @@ void __init e820_reserve_resources(void) * pci device BAR resource and insert them later in * pcibios_resource_survey() */ - if (((e820.map[i].type != E820_RESERVED) && - (e820.map[i].type != E820_PRAM)) || - res->start < (1ULL<<20)) { + if (do_mark_busy(e820.map[i].type, res)) { res->flags |= IORESOURCE_BUSY; insert_resource(&iomem_resource, res); } @@ -1123,7 +1143,8 @@ void __init memblock_find_dma_reserve(void) nr_pages += end_pfn - start_pfn; } - for_each_free_mem_range(u, NUMA_NO_NODE, &start, &end, NULL) { + for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, + NULL) { start_pfn = min_t(unsigned long, PFN_UP(start), MAX_DMA_PFN); end_pfn = min_t(unsigned long, PFN_DOWN(end), MAX_DMA_PFN); if (start_pfn < end_pfn) diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index fe9f0b79a..9f9cc682e 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -546,6 +546,7 @@ static const struct pci_device_id intel_stolen_ids[] __initconst = { INTEL_BDW_D_IDS(&gen8_stolen_funcs), INTEL_CHV_IDS(&chv_stolen_funcs), INTEL_SKL_IDS(&gen9_stolen_funcs), + INTEL_BXT_IDS(&gen9_stolen_funcs), }; static void __init intel_graphics_stolen(int num, int slot, int func) @@ -627,8 +628,12 @@ static struct chipset early_qrk[] __initdata = { { PCI_VENDOR_ID_INTEL, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA, PCI_ANY_ID, QFLAG_APPLY_ONCE, intel_graphics_stolen }, /* - * HPET on current version of Baytrail platform has accuracy - * problems, disable it for now: + * HPET on the current version of the Baytrail platform has accuracy + * problems: it will halt in deep idle state - so we disable it. + * + * More details can be found in section 18.10.1.3 of the datasheet: + * + * http://www.intel.com/content/dam/www/public/us/en/documents/datasheets/atom-z8000-datasheet-vol-1.pdf */ { PCI_VENDOR_ID_INTEL, 0x0f00, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index 62b9e04d4..6c413d0c0 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -177,7 +177,9 @@ static __init void early_serial_init(char *s) } if (*s) { - if (kstrtoul(s, 0, &baud) < 0 || baud == 0) + baud = simple_strtoull(s, &e, 0); + + if (baud == 0 || s == e) baud = DEFAULT_BAUD; } diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S deleted file mode 100644 index 1c309763e..000000000 --- a/arch/x86/kernel/entry_32.S +++ /dev/null @@ -1,1401 +0,0 @@ -/* - * - * Copyright (C) 1991, 1992 Linus Torvalds - */ - -/* - * entry.S contains the system-call and fault low-level handling routines. - * This also contains the timer-interrupt handler, as well as all interrupts - * and faults that can result in a task-switch. - * - * NOTE: This code handles signal-recognition, which happens every time - * after a timer-interrupt and after each system call. - * - * I changed all the .align's to 4 (16 byte alignment), as that's faster - * on a 486. - * - * Stack layout in 'syscall_exit': - * ptrace needs to have all regs on the stack. - * if the order here is changed, it needs to be - * updated in fork.c:copy_process, signal.c:do_signal, - * ptrace.c and ptrace.h - * - * 0(%esp) - %ebx - * 4(%esp) - %ecx - * 8(%esp) - %edx - * C(%esp) - %esi - * 10(%esp) - %edi - * 14(%esp) - %ebp - * 18(%esp) - %eax - * 1C(%esp) - %ds - * 20(%esp) - %es - * 24(%esp) - %fs - * 28(%esp) - %gs saved iff !CONFIG_X86_32_LAZY_GS - * 2C(%esp) - orig_eax - * 30(%esp) - %eip - * 34(%esp) - %cs - * 38(%esp) - %eflags - * 3C(%esp) - %oldesp - * 40(%esp) - %oldss - * - * "current" is in register %ebx during any slow entries. - */ - -#include <linux/linkage.h> -#include <linux/err.h> -#include <asm/thread_info.h> -#include <asm/irqflags.h> -#include <asm/errno.h> -#include <asm/segment.h> -#include <asm/smp.h> -#include <asm/page_types.h> -#include <asm/percpu.h> -#include <asm/dwarf2.h> -#include <asm/processor-flags.h> -#include <asm/ftrace.h> -#include <asm/irq_vectors.h> -#include <asm/cpufeature.h> -#include <asm/alternative-asm.h> -#include <asm/asm.h> -#include <asm/smap.h> - -/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ -#include <linux/elf-em.h> -#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE) -#define __AUDIT_ARCH_LE 0x40000000 - -#ifndef CONFIG_AUDITSYSCALL -#define sysenter_audit syscall_trace_entry -#define sysexit_audit syscall_exit_work -#endif - - .section .entry.text, "ax" - -/* - * We use macros for low-level operations which need to be overridden - * for paravirtualization. The following will never clobber any registers: - * INTERRUPT_RETURN (aka. "iret") - * GET_CR0_INTO_EAX (aka. "movl %cr0, %eax") - * ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit"). - * - * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must - * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY). - * Allowing a register to be clobbered can shrink the paravirt replacement - * enough to patch inline, increasing performance. - */ - -#ifdef CONFIG_PREEMPT -#define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF -#else -#define preempt_stop(clobbers) -#define resume_kernel restore_all -#endif - -.macro TRACE_IRQS_IRET -#ifdef CONFIG_TRACE_IRQFLAGS - testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off? - jz 1f - TRACE_IRQS_ON -1: -#endif -.endm - -/* - * User gs save/restore - * - * %gs is used for userland TLS and kernel only uses it for stack - * canary which is required to be at %gs:20 by gcc. Read the comment - * at the top of stackprotector.h for more info. - * - * Local labels 98 and 99 are used. - */ -#ifdef CONFIG_X86_32_LAZY_GS - - /* unfortunately push/pop can't be no-op */ -.macro PUSH_GS - pushl_cfi $0 -.endm -.macro POP_GS pop=0 - addl $(4 + \pop), %esp - CFI_ADJUST_CFA_OFFSET -(4 + \pop) -.endm -.macro POP_GS_EX -.endm - - /* all the rest are no-op */ -.macro PTGS_TO_GS -.endm -.macro PTGS_TO_GS_EX -.endm -.macro GS_TO_REG reg -.endm -.macro REG_TO_PTGS reg -.endm -.macro SET_KERNEL_GS reg -.endm - -#else /* CONFIG_X86_32_LAZY_GS */ - -.macro PUSH_GS - pushl_cfi %gs - /*CFI_REL_OFFSET gs, 0*/ -.endm - -.macro POP_GS pop=0 -98: popl_cfi %gs - /*CFI_RESTORE gs*/ - .if \pop <> 0 - add $\pop, %esp - CFI_ADJUST_CFA_OFFSET -\pop - .endif -.endm -.macro POP_GS_EX -.pushsection .fixup, "ax" -99: movl $0, (%esp) - jmp 98b -.popsection - _ASM_EXTABLE(98b,99b) -.endm - -.macro PTGS_TO_GS -98: mov PT_GS(%esp), %gs -.endm -.macro PTGS_TO_GS_EX -.pushsection .fixup, "ax" -99: movl $0, PT_GS(%esp) - jmp 98b -.popsection - _ASM_EXTABLE(98b,99b) -.endm - -.macro GS_TO_REG reg - movl %gs, \reg - /*CFI_REGISTER gs, \reg*/ -.endm -.macro REG_TO_PTGS reg - movl \reg, PT_GS(%esp) - /*CFI_REL_OFFSET gs, PT_GS*/ -.endm -.macro SET_KERNEL_GS reg - movl $(__KERNEL_STACK_CANARY), \reg - movl \reg, %gs -.endm - -#endif /* CONFIG_X86_32_LAZY_GS */ - -.macro SAVE_ALL - cld - PUSH_GS - pushl_cfi %fs - /*CFI_REL_OFFSET fs, 0;*/ - pushl_cfi %es - /*CFI_REL_OFFSET es, 0;*/ - pushl_cfi %ds - /*CFI_REL_OFFSET ds, 0;*/ - pushl_cfi %eax - CFI_REL_OFFSET eax, 0 - pushl_cfi %ebp - CFI_REL_OFFSET ebp, 0 - pushl_cfi %edi - CFI_REL_OFFSET edi, 0 - pushl_cfi %esi - CFI_REL_OFFSET esi, 0 - pushl_cfi %edx - CFI_REL_OFFSET edx, 0 - pushl_cfi %ecx - CFI_REL_OFFSET ecx, 0 - pushl_cfi %ebx - CFI_REL_OFFSET ebx, 0 - movl $(__USER_DS), %edx - movl %edx, %ds - movl %edx, %es - movl $(__KERNEL_PERCPU), %edx - movl %edx, %fs - SET_KERNEL_GS %edx -.endm - -.macro RESTORE_INT_REGS - popl_cfi %ebx - CFI_RESTORE ebx - popl_cfi %ecx - CFI_RESTORE ecx - popl_cfi %edx - CFI_RESTORE edx - popl_cfi %esi - CFI_RESTORE esi - popl_cfi %edi - CFI_RESTORE edi - popl_cfi %ebp - CFI_RESTORE ebp - popl_cfi %eax - CFI_RESTORE eax -.endm - -.macro RESTORE_REGS pop=0 - RESTORE_INT_REGS -1: popl_cfi %ds - /*CFI_RESTORE ds;*/ -2: popl_cfi %es - /*CFI_RESTORE es;*/ -3: popl_cfi %fs - /*CFI_RESTORE fs;*/ - POP_GS \pop -.pushsection .fixup, "ax" -4: movl $0, (%esp) - jmp 1b -5: movl $0, (%esp) - jmp 2b -6: movl $0, (%esp) - jmp 3b -.popsection - _ASM_EXTABLE(1b,4b) - _ASM_EXTABLE(2b,5b) - _ASM_EXTABLE(3b,6b) - POP_GS_EX -.endm - -.macro 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 -.endm - -.macro 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 -.endm - -.macro RING0_PTREGS_FRAME - CFI_STARTPROC simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA esp, PT_OLDESP-PT_EBX - /*CFI_OFFSET cs, PT_CS-PT_OLDESP;*/ - CFI_OFFSET eip, PT_EIP-PT_OLDESP - /*CFI_OFFSET es, PT_ES-PT_OLDESP;*/ - /*CFI_OFFSET ds, PT_DS-PT_OLDESP;*/ - CFI_OFFSET eax, PT_EAX-PT_OLDESP - CFI_OFFSET ebp, PT_EBP-PT_OLDESP - CFI_OFFSET edi, PT_EDI-PT_OLDESP - CFI_OFFSET esi, PT_ESI-PT_OLDESP - CFI_OFFSET edx, PT_EDX-PT_OLDESP - CFI_OFFSET ecx, PT_ECX-PT_OLDESP - CFI_OFFSET ebx, PT_EBX-PT_OLDESP -.endm - -ENTRY(ret_from_fork) - CFI_STARTPROC - pushl_cfi %eax - call schedule_tail - GET_THREAD_INFO(%ebp) - popl_cfi %eax - pushl_cfi $0x0202 # Reset kernel eflags - popfl_cfi - jmp syscall_exit - CFI_ENDPROC -END(ret_from_fork) - -ENTRY(ret_from_kernel_thread) - CFI_STARTPROC - pushl_cfi %eax - call schedule_tail - GET_THREAD_INFO(%ebp) - popl_cfi %eax - pushl_cfi $0x0202 # Reset kernel eflags - popfl_cfi - movl PT_EBP(%esp),%eax - call *PT_EBX(%esp) - movl $0,PT_EAX(%esp) - jmp syscall_exit - CFI_ENDPROC -ENDPROC(ret_from_kernel_thread) - -/* - * Return to user mode is not as complex as all this looks, - * but we want the default path for a system call return to - * go as quickly as possible which is why some of this is - * less clear than it otherwise should be. - */ - - # userspace resumption stub bypassing syscall exit tracing - ALIGN - RING0_PTREGS_FRAME -ret_from_exception: - preempt_stop(CLBR_ANY) -ret_from_intr: - GET_THREAD_INFO(%ebp) -#ifdef CONFIG_VM86 - movl PT_EFLAGS(%esp), %eax # mix EFLAGS and CS - movb PT_CS(%esp), %al - andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax -#else - /* - * We can be coming here from child spawned by kernel_thread(). - */ - movl PT_CS(%esp), %eax - andl $SEGMENT_RPL_MASK, %eax -#endif - cmpl $USER_RPL, %eax - jb resume_kernel # not returning to v8086 or userspace - -ENTRY(resume_userspace) - LOCKDEP_SYS_EXIT - DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt - # setting need_resched or sigpending - # between sampling and the iret - TRACE_IRQS_OFF - movl TI_flags(%ebp), %ecx - andl $_TIF_WORK_MASK, %ecx # is there any work to be done on - # int/exception return? - jne work_pending - jmp restore_all -END(ret_from_exception) - -#ifdef CONFIG_PREEMPT -ENTRY(resume_kernel) - DISABLE_INTERRUPTS(CLBR_ANY) -need_resched: - cmpl $0,PER_CPU_VAR(__preempt_count) - jnz restore_all - testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off (exception path) ? - jz restore_all - call preempt_schedule_irq - jmp need_resched -END(resume_kernel) -#endif - CFI_ENDPROC - -/* SYSENTER_RETURN points to after the "sysenter" instruction in - the vsyscall page. See vsyscall-sysentry.S, which defines the symbol. */ - - # sysenter call handler stub -ENTRY(ia32_sysenter_target) - CFI_STARTPROC simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA esp, 0 - CFI_REGISTER esp, ebp - movl TSS_sysenter_sp0(%esp),%esp -sysenter_past_esp: - /* - * Interrupts are disabled here, but we can't trace it until - * enough kernel state to call TRACE_IRQS_OFF can be called - but - * we immediately enable interrupts at that point anyway. - */ - pushl_cfi $__USER_DS - /*CFI_REL_OFFSET ss, 0*/ - pushl_cfi %ebp - CFI_REL_OFFSET esp, 0 - pushfl_cfi - orl $X86_EFLAGS_IF, (%esp) - pushl_cfi $__USER_CS - /*CFI_REL_OFFSET cs, 0*/ - /* - * Push current_thread_info()->sysenter_return to the stack. - * A tiny bit of offset fixup is necessary: TI_sysenter_return - * is relative to thread_info, which is at the bottom of the - * kernel stack page. 4*4 means the 4 words pushed above; - * TOP_OF_KERNEL_STACK_PADDING takes us to the top of the stack; - * and THREAD_SIZE takes us to the bottom. - */ - pushl_cfi ((TI_sysenter_return) - THREAD_SIZE + TOP_OF_KERNEL_STACK_PADDING + 4*4)(%esp) - CFI_REL_OFFSET eip, 0 - - pushl_cfi %eax - SAVE_ALL - ENABLE_INTERRUPTS(CLBR_NONE) - -/* - * Load the potential sixth argument from user stack. - * Careful about security. - */ - cmpl $__PAGE_OFFSET-3,%ebp - jae syscall_fault - ASM_STAC -1: movl (%ebp),%ebp - ASM_CLAC - movl %ebp,PT_EBP(%esp) - _ASM_EXTABLE(1b,syscall_fault) - - GET_THREAD_INFO(%ebp) - - testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp) - jnz sysenter_audit -sysenter_do_call: - cmpl $(NR_syscalls), %eax - jae sysenter_badsys - call *sys_call_table(,%eax,4) -sysenter_after_call: - movl %eax,PT_EAX(%esp) - LOCKDEP_SYS_EXIT - DISABLE_INTERRUPTS(CLBR_ANY) - TRACE_IRQS_OFF - movl TI_flags(%ebp), %ecx - testl $_TIF_ALLWORK_MASK, %ecx - jnz sysexit_audit -sysenter_exit: -/* if something modifies registers it must also disable sysexit */ - movl PT_EIP(%esp), %edx - movl PT_OLDESP(%esp), %ecx - xorl %ebp,%ebp - TRACE_IRQS_ON -1: mov PT_FS(%esp), %fs - PTGS_TO_GS - ENABLE_INTERRUPTS_SYSEXIT - -#ifdef CONFIG_AUDITSYSCALL -sysenter_audit: - testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%ebp) - jnz syscall_trace_entry - /* movl PT_EAX(%esp), %eax already set, syscall number: 1st arg to audit */ - movl PT_EBX(%esp), %edx /* ebx/a0: 2nd arg to audit */ - /* movl PT_ECX(%esp), %ecx already set, a1: 3nd arg to audit */ - pushl_cfi PT_ESI(%esp) /* a3: 5th arg */ - pushl_cfi PT_EDX+4(%esp) /* a2: 4th arg */ - call __audit_syscall_entry - popl_cfi %ecx /* get that remapped edx off the stack */ - popl_cfi %ecx /* get that remapped esi off the stack */ - movl PT_EAX(%esp),%eax /* reload syscall number */ - jmp sysenter_do_call - -sysexit_audit: - testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx - jnz syscall_exit_work - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_ANY) - movl %eax,%edx /* second arg, syscall return value */ - cmpl $-MAX_ERRNO,%eax /* is it an error ? */ - setbe %al /* 1 if so, 0 if not */ - movzbl %al,%eax /* zero-extend that */ - call __audit_syscall_exit - DISABLE_INTERRUPTS(CLBR_ANY) - TRACE_IRQS_OFF - movl TI_flags(%ebp), %ecx - testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx - jnz syscall_exit_work - movl PT_EAX(%esp),%eax /* reload syscall return value */ - jmp sysenter_exit -#endif - - CFI_ENDPROC -.pushsection .fixup,"ax" -2: movl $0,PT_FS(%esp) - jmp 1b -.popsection - _ASM_EXTABLE(1b,2b) - PTGS_TO_GS_EX -ENDPROC(ia32_sysenter_target) - - # system call handler stub -ENTRY(system_call) - RING0_INT_FRAME # can't unwind into user space anyway - ASM_CLAC - pushl_cfi %eax # save orig_eax - SAVE_ALL - GET_THREAD_INFO(%ebp) - # system call tracing in operation / emulation - testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp) - jnz syscall_trace_entry - cmpl $(NR_syscalls), %eax - jae syscall_badsys -syscall_call: - call *sys_call_table(,%eax,4) -syscall_after_call: - movl %eax,PT_EAX(%esp) # store the return value -syscall_exit: - LOCKDEP_SYS_EXIT - DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt - # setting need_resched or sigpending - # between sampling and the iret - TRACE_IRQS_OFF - movl TI_flags(%ebp), %ecx - testl $_TIF_ALLWORK_MASK, %ecx # current->work - jnz syscall_exit_work - -restore_all: - TRACE_IRQS_IRET -restore_all_notrace: -#ifdef CONFIG_X86_ESPFIX32 - movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS - # Warning: PT_OLDSS(%esp) contains the wrong/random values if we - # are returning to the kernel. - # See comments in process.c:copy_thread() for details. - movb PT_OLDSS(%esp), %ah - movb PT_CS(%esp), %al - andl $(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax - cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax - CFI_REMEMBER_STATE - je ldt_ss # returning to user-space with LDT SS -#endif -restore_nocheck: - RESTORE_REGS 4 # skip orig_eax/error_code -irq_return: - INTERRUPT_RETURN -.section .fixup,"ax" -ENTRY(iret_exc) - pushl $0 # no error code - pushl $do_iret_error - jmp error_code -.previous - _ASM_EXTABLE(irq_return,iret_exc) - -#ifdef CONFIG_X86_ESPFIX32 - CFI_RESTORE_STATE -ldt_ss: -#ifdef CONFIG_PARAVIRT - /* - * The kernel can't run on a non-flat stack if paravirt mode - * is active. Rather than try to fixup the high bits of - * ESP, bypass this code entirely. This may break DOSemu - * and/or Wine support in a paravirt VM, although the option - * is still available to implement the setting of the high - * 16-bits in the INTERRUPT_RETURN paravirt-op. - */ - cmpl $0, pv_info+PARAVIRT_enabled - jne restore_nocheck -#endif - -/* - * Setup and switch to ESPFIX stack - * - * We're returning to userspace with a 16 bit stack. The CPU will not - * restore the high word of ESP for us on executing iret... This is an - * "official" bug of all the x86-compatible CPUs, which we can work - * around to make dosemu and wine happy. We do this by preloading the - * high word of ESP with the high word of the userspace ESP while - * compensating for the offset by changing to the ESPFIX segment with - * a base address that matches for the difference. - */ -#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8) - mov %esp, %edx /* load kernel esp */ - mov PT_OLDESP(%esp), %eax /* load userspace esp */ - mov %dx, %ax /* eax: new kernel esp */ - sub %eax, %edx /* offset (low word is 0) */ - shr $16, %edx - mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */ - mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */ - pushl_cfi $__ESPFIX_SS - pushl_cfi %eax /* new kernel esp */ - /* Disable interrupts, but do not irqtrace this section: we - * will soon execute iret and the tracer was already set to - * the irqstate after the iret */ - DISABLE_INTERRUPTS(CLBR_EAX) - lss (%esp), %esp /* switch to espfix segment */ - CFI_ADJUST_CFA_OFFSET -8 - jmp restore_nocheck -#endif - CFI_ENDPROC -ENDPROC(system_call) - - # perform work that needs to be done immediately before resumption - ALIGN - RING0_PTREGS_FRAME # can't unwind into user space anyway -work_pending: - testb $_TIF_NEED_RESCHED, %cl - jz work_notifysig -work_resched: - call schedule - LOCKDEP_SYS_EXIT - DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt - # setting need_resched or sigpending - # between sampling and the iret - TRACE_IRQS_OFF - movl TI_flags(%ebp), %ecx - andl $_TIF_WORK_MASK, %ecx # is there any work to be done other - # than syscall tracing? - jz restore_all - testb $_TIF_NEED_RESCHED, %cl - jnz work_resched - -work_notifysig: # deal with pending signals and - # notify-resume requests -#ifdef CONFIG_VM86 - testl $X86_EFLAGS_VM, PT_EFLAGS(%esp) - movl %esp, %eax - jnz work_notifysig_v86 # returning to kernel-space or - # vm86-space -1: -#else - movl %esp, %eax -#endif - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) - movb PT_CS(%esp), %bl - andb $SEGMENT_RPL_MASK, %bl - cmpb $USER_RPL, %bl - jb resume_kernel - xorl %edx, %edx - call do_notify_resume - jmp resume_userspace - -#ifdef CONFIG_VM86 - ALIGN -work_notifysig_v86: - pushl_cfi %ecx # save ti_flags for do_notify_resume - call save_v86_state # %eax contains pt_regs pointer - popl_cfi %ecx - movl %eax, %esp - jmp 1b -#endif -END(work_pending) - - # perform syscall exit tracing - ALIGN -syscall_trace_entry: - movl $-ENOSYS,PT_EAX(%esp) - movl %esp, %eax - call syscall_trace_enter - /* What it returned is what we'll actually use. */ - cmpl $(NR_syscalls), %eax - jnae syscall_call - jmp syscall_exit -END(syscall_trace_entry) - - # perform syscall exit tracing - ALIGN -syscall_exit_work: - testl $_TIF_WORK_SYSCALL_EXIT, %ecx - jz work_pending - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_ANY) # could let syscall_trace_leave() call - # schedule() instead - movl %esp, %eax - call syscall_trace_leave - jmp resume_userspace -END(syscall_exit_work) - CFI_ENDPROC - - RING0_INT_FRAME # can't unwind into user space anyway -syscall_fault: - ASM_CLAC - GET_THREAD_INFO(%ebp) - movl $-EFAULT,PT_EAX(%esp) - jmp resume_userspace -END(syscall_fault) - -syscall_badsys: - movl $-ENOSYS,%eax - jmp syscall_after_call -END(syscall_badsys) - -sysenter_badsys: - movl $-ENOSYS,%eax - jmp sysenter_after_call -END(sysenter_badsys) - CFI_ENDPROC - -.macro FIXUP_ESPFIX_STACK -/* - * Switch back for ESPFIX stack to the normal zerobased stack - * - * We can't call C functions using the ESPFIX stack. This code reads - * the high word of the segment base from the GDT and swiches to the - * normal stack and adjusts ESP with the matching offset. - */ -#ifdef CONFIG_X86_ESPFIX32 - /* fixup the stack */ - mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */ - mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */ - shl $16, %eax - addl %esp, %eax /* the adjusted stack pointer */ - pushl_cfi $__KERNEL_DS - pushl_cfi %eax - lss (%esp), %esp /* switch to the normal stack segment */ - CFI_ADJUST_CFA_OFFSET -8 -#endif -.endm -.macro UNWIND_ESPFIX_STACK -#ifdef CONFIG_X86_ESPFIX32 - movl %ss, %eax - /* see if on espfix stack */ - cmpw $__ESPFIX_SS, %ax - jne 27f - movl $__KERNEL_DS, %eax - movl %eax, %ds - movl %eax, %es - /* switch to normal stack */ - FIXUP_ESPFIX_STACK -27: -#endif -.endm - -/* - * Build the entry stubs with some assembler magic. - * We pack 1 stub into every 8-byte block. - */ - .align 8 -ENTRY(irq_entries_start) - RING0_INT_FRAME - vector=FIRST_EXTERNAL_VECTOR - .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR) - pushl_cfi $(~vector+0x80) /* Note: always in signed byte range */ - vector=vector+1 - jmp common_interrupt - CFI_ADJUST_CFA_OFFSET -4 - .align 8 - .endr -END(irq_entries_start) - -/* - * the CPU automatically disables interrupts when executing an IRQ vector, - * so IRQ-flags tracing has to follow that: - */ - .p2align CONFIG_X86_L1_CACHE_SHIFT -common_interrupt: - ASM_CLAC - addl $-0x80,(%esp) /* Adjust vector into the [-256,-1] range */ - SAVE_ALL - TRACE_IRQS_OFF - movl %esp,%eax - call do_IRQ - jmp ret_from_intr -ENDPROC(common_interrupt) - CFI_ENDPROC - -#define BUILD_INTERRUPT3(name, nr, fn) \ -ENTRY(name) \ - RING0_INT_FRAME; \ - ASM_CLAC; \ - pushl_cfi $~(nr); \ - SAVE_ALL; \ - TRACE_IRQS_OFF \ - movl %esp,%eax; \ - call fn; \ - jmp ret_from_intr; \ - CFI_ENDPROC; \ -ENDPROC(name) - - -#ifdef CONFIG_TRACING -#define TRACE_BUILD_INTERRUPT(name, nr) \ - BUILD_INTERRUPT3(trace_##name, nr, smp_trace_##name) -#else -#define TRACE_BUILD_INTERRUPT(name, nr) -#endif - -#define BUILD_INTERRUPT(name, nr) \ - BUILD_INTERRUPT3(name, nr, smp_##name); \ - TRACE_BUILD_INTERRUPT(name, nr) - -/* The include is where all of the SMP etc. interrupts come from */ -#include <asm/entry_arch.h> - -ENTRY(coprocessor_error) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 - pushl_cfi $do_coprocessor_error - jmp error_code - CFI_ENDPROC -END(coprocessor_error) - -ENTRY(simd_coprocessor_error) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 -#ifdef CONFIG_X86_INVD_BUG - /* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */ - ALTERNATIVE "pushl_cfi $do_general_protection", \ - "pushl $do_simd_coprocessor_error", \ - X86_FEATURE_XMM -#else - pushl_cfi $do_simd_coprocessor_error -#endif - jmp error_code - CFI_ENDPROC -END(simd_coprocessor_error) - -ENTRY(device_not_available) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $-1 # mark this as an int - pushl_cfi $do_device_not_available - jmp error_code - CFI_ENDPROC -END(device_not_available) - -#ifdef CONFIG_PARAVIRT -ENTRY(native_iret) - iret - _ASM_EXTABLE(native_iret, iret_exc) -END(native_iret) - -ENTRY(native_irq_enable_sysexit) - sti - sysexit -END(native_irq_enable_sysexit) -#endif - -ENTRY(overflow) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 - pushl_cfi $do_overflow - jmp error_code - CFI_ENDPROC -END(overflow) - -ENTRY(bounds) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 - pushl_cfi $do_bounds - jmp error_code - CFI_ENDPROC -END(bounds) - -ENTRY(invalid_op) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 - pushl_cfi $do_invalid_op - jmp error_code - CFI_ENDPROC -END(invalid_op) - -ENTRY(coprocessor_segment_overrun) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 - pushl_cfi $do_coprocessor_segment_overrun - jmp error_code - CFI_ENDPROC -END(coprocessor_segment_overrun) - -ENTRY(invalid_TSS) - RING0_EC_FRAME - ASM_CLAC - pushl_cfi $do_invalid_TSS - jmp error_code - CFI_ENDPROC -END(invalid_TSS) - -ENTRY(segment_not_present) - RING0_EC_FRAME - ASM_CLAC - pushl_cfi $do_segment_not_present - jmp error_code - CFI_ENDPROC -END(segment_not_present) - -ENTRY(stack_segment) - RING0_EC_FRAME - ASM_CLAC - pushl_cfi $do_stack_segment - jmp error_code - CFI_ENDPROC -END(stack_segment) - -ENTRY(alignment_check) - RING0_EC_FRAME - ASM_CLAC - pushl_cfi $do_alignment_check - jmp error_code - CFI_ENDPROC -END(alignment_check) - -ENTRY(divide_error) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 # no error code - pushl_cfi $do_divide_error - jmp error_code - CFI_ENDPROC -END(divide_error) - -#ifdef CONFIG_X86_MCE -ENTRY(machine_check) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 - pushl_cfi machine_check_vector - jmp error_code - CFI_ENDPROC -END(machine_check) -#endif - -ENTRY(spurious_interrupt_bug) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 - pushl_cfi $do_spurious_interrupt_bug - jmp error_code - CFI_ENDPROC -END(spurious_interrupt_bug) - -#ifdef CONFIG_XEN -/* Xen doesn't set %esp to be precisely what the normal sysenter - entrypoint expects, so fix it up before using the normal path. */ -ENTRY(xen_sysenter_target) - RING0_INT_FRAME - addl $5*4, %esp /* remove xen-provided frame */ - CFI_ADJUST_CFA_OFFSET -5*4 - jmp sysenter_past_esp - CFI_ENDPROC - -ENTRY(xen_hypervisor_callback) - CFI_STARTPROC - pushl_cfi $-1 /* orig_ax = -1 => not a system call */ - SAVE_ALL - TRACE_IRQS_OFF - - /* Check to see if we got the event in the critical - region in xen_iret_direct, after we've reenabled - events and checked for pending events. This simulates - iret instruction's behaviour where it delivers a - pending interrupt when enabling interrupts. */ - movl PT_EIP(%esp),%eax - cmpl $xen_iret_start_crit,%eax - jb 1f - cmpl $xen_iret_end_crit,%eax - jae 1f - - jmp xen_iret_crit_fixup - -ENTRY(xen_do_upcall) -1: mov %esp, %eax - call xen_evtchn_do_upcall -#ifndef CONFIG_PREEMPT - call xen_maybe_preempt_hcall -#endif - jmp ret_from_intr - CFI_ENDPROC -ENDPROC(xen_hypervisor_callback) - -# Hypervisor uses this for application faults while it executes. -# We get here for two reasons: -# 1. Fault while reloading DS, ES, FS or GS -# 2. Fault while executing IRET -# Category 1 we fix up by reattempting the load, and zeroing the segment -# register if the load fails. -# Category 2 we fix up by jumping to do_iret_error. We cannot use the -# normal Linux return path in this case because if we use the IRET hypercall -# to pop the stack frame we end up in an infinite loop of failsafe callbacks. -# We distinguish between categories by maintaining a status value in EAX. -ENTRY(xen_failsafe_callback) - CFI_STARTPROC - pushl_cfi %eax - movl $1,%eax -1: mov 4(%esp),%ds -2: mov 8(%esp),%es -3: mov 12(%esp),%fs -4: mov 16(%esp),%gs - /* EAX == 0 => Category 1 (Bad segment) - EAX != 0 => Category 2 (Bad IRET) */ - testl %eax,%eax - popl_cfi %eax - lea 16(%esp),%esp - CFI_ADJUST_CFA_OFFSET -16 - jz 5f - jmp iret_exc -5: pushl_cfi $-1 /* orig_ax = -1 => not a system call */ - SAVE_ALL - jmp ret_from_exception - CFI_ENDPROC - -.section .fixup,"ax" -6: xorl %eax,%eax - movl %eax,4(%esp) - jmp 1b -7: xorl %eax,%eax - movl %eax,8(%esp) - jmp 2b -8: xorl %eax,%eax - movl %eax,12(%esp) - jmp 3b -9: xorl %eax,%eax - movl %eax,16(%esp) - jmp 4b -.previous - _ASM_EXTABLE(1b,6b) - _ASM_EXTABLE(2b,7b) - _ASM_EXTABLE(3b,8b) - _ASM_EXTABLE(4b,9b) -ENDPROC(xen_failsafe_callback) - -BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR, - xen_evtchn_do_upcall) - -#endif /* CONFIG_XEN */ - -#if IS_ENABLED(CONFIG_HYPERV) - -BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR, - hyperv_vector_handler) - -#endif /* CONFIG_HYPERV */ - -#ifdef CONFIG_FUNCTION_TRACER -#ifdef CONFIG_DYNAMIC_FTRACE - -ENTRY(mcount) - ret -END(mcount) - -ENTRY(ftrace_caller) - pushl %eax - pushl %ecx - pushl %edx - pushl $0 /* Pass NULL as regs pointer */ - movl 4*4(%esp), %eax - movl 0x4(%ebp), %edx - movl function_trace_op, %ecx - subl $MCOUNT_INSN_SIZE, %eax - -.globl ftrace_call -ftrace_call: - call ftrace_stub - - addl $4,%esp /* skip NULL pointer */ - popl %edx - popl %ecx - popl %eax -ftrace_ret: -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -.globl ftrace_graph_call -ftrace_graph_call: - jmp ftrace_stub -#endif - -.globl ftrace_stub -ftrace_stub: - ret -END(ftrace_caller) - -ENTRY(ftrace_regs_caller) - pushf /* push flags before compare (in cs location) */ - - /* - * i386 does not save SS and ESP when coming from kernel. - * Instead, to get sp, ®s->sp is used (see ptrace.h). - * Unfortunately, that means eflags must be at the same location - * as the current return ip is. We move the return ip into the - * ip location, and move flags into the return ip location. - */ - pushl 4(%esp) /* save return ip into ip slot */ - - pushl $0 /* Load 0 into orig_ax */ - pushl %gs - pushl %fs - pushl %es - pushl %ds - pushl %eax - pushl %ebp - pushl %edi - pushl %esi - pushl %edx - pushl %ecx - pushl %ebx - - movl 13*4(%esp), %eax /* Get the saved flags */ - movl %eax, 14*4(%esp) /* Move saved flags into regs->flags location */ - /* clobbering return ip */ - movl $__KERNEL_CS,13*4(%esp) - - movl 12*4(%esp), %eax /* Load ip (1st parameter) */ - subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */ - movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */ - movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */ - pushl %esp /* Save pt_regs as 4th parameter */ - -GLOBAL(ftrace_regs_call) - call ftrace_stub - - addl $4, %esp /* Skip pt_regs */ - movl 14*4(%esp), %eax /* Move flags back into cs */ - movl %eax, 13*4(%esp) /* Needed to keep addl from modifying flags */ - movl 12*4(%esp), %eax /* Get return ip from regs->ip */ - movl %eax, 14*4(%esp) /* Put return ip back for ret */ - - popl %ebx - popl %ecx - popl %edx - popl %esi - popl %edi - popl %ebp - popl %eax - popl %ds - popl %es - popl %fs - popl %gs - addl $8, %esp /* Skip orig_ax and ip */ - popf /* Pop flags at end (no addl to corrupt flags) */ - jmp ftrace_ret - - popf - jmp ftrace_stub -#else /* ! CONFIG_DYNAMIC_FTRACE */ - -ENTRY(mcount) - cmpl $__PAGE_OFFSET, %esp - jb ftrace_stub /* Paging not enabled yet? */ - - cmpl $ftrace_stub, ftrace_trace_function - jnz trace -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - cmpl $ftrace_stub, ftrace_graph_return - jnz ftrace_graph_caller - - cmpl $ftrace_graph_entry_stub, ftrace_graph_entry - jnz ftrace_graph_caller -#endif -.globl ftrace_stub -ftrace_stub: - ret - - /* taken from glibc */ -trace: - pushl %eax - pushl %ecx - pushl %edx - movl 0xc(%esp), %eax - movl 0x4(%ebp), %edx - subl $MCOUNT_INSN_SIZE, %eax - - call *ftrace_trace_function - - popl %edx - popl %ecx - popl %eax - jmp ftrace_stub -END(mcount) -#endif /* CONFIG_DYNAMIC_FTRACE */ -#endif /* CONFIG_FUNCTION_TRACER */ - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -ENTRY(ftrace_graph_caller) - pushl %eax - pushl %ecx - pushl %edx - movl 0xc(%esp), %eax - lea 0x4(%ebp), %edx - movl (%ebp), %ecx - subl $MCOUNT_INSN_SIZE, %eax - call prepare_ftrace_return - popl %edx - popl %ecx - popl %eax - ret -END(ftrace_graph_caller) - -.globl return_to_handler -return_to_handler: - pushl %eax - pushl %edx - movl %ebp, %eax - call ftrace_return_to_handler - movl %eax, %ecx - popl %edx - popl %eax - jmp *%ecx -#endif - -#ifdef CONFIG_TRACING -ENTRY(trace_page_fault) - RING0_EC_FRAME - ASM_CLAC - pushl_cfi $trace_do_page_fault - jmp error_code - CFI_ENDPROC -END(trace_page_fault) -#endif - -ENTRY(page_fault) - RING0_EC_FRAME - ASM_CLAC - pushl_cfi $do_page_fault - ALIGN -error_code: - /* the function address is in %gs's slot on the stack */ - pushl_cfi %fs - /*CFI_REL_OFFSET fs, 0*/ - pushl_cfi %es - /*CFI_REL_OFFSET es, 0*/ - pushl_cfi %ds - /*CFI_REL_OFFSET ds, 0*/ - pushl_cfi_reg eax - pushl_cfi_reg ebp - pushl_cfi_reg edi - pushl_cfi_reg esi - pushl_cfi_reg edx - pushl_cfi_reg ecx - pushl_cfi_reg ebx - cld - movl $(__KERNEL_PERCPU), %ecx - movl %ecx, %fs - UNWIND_ESPFIX_STACK - GS_TO_REG %ecx - movl PT_GS(%esp), %edi # get the function address - movl PT_ORIG_EAX(%esp), %edx # get the error code - movl $-1, PT_ORIG_EAX(%esp) # no syscall to restart - REG_TO_PTGS %ecx - SET_KERNEL_GS %ecx - movl $(__USER_DS), %ecx - movl %ecx, %ds - movl %ecx, %es - TRACE_IRQS_OFF - movl %esp,%eax # pt_regs pointer - call *%edi - jmp ret_from_exception - CFI_ENDPROC -END(page_fault) - -/* - * Debug traps and NMI can happen at the one SYSENTER instruction - * that sets up the real kernel stack. Check here, since we can't - * allow the wrong stack to be used. - * - * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have - * already pushed 3 words if it hits on the sysenter instruction: - * eflags, cs and eip. - * - * We just load the right stack, and push the three (known) values - * by hand onto the new stack - while updating the return eip past - * the instruction that would have done it for sysenter. - */ -.macro FIX_STACK offset ok label - cmpw $__KERNEL_CS, 4(%esp) - jne \ok -\label: - movl TSS_sysenter_sp0 + \offset(%esp), %esp - CFI_DEF_CFA esp, 0 - CFI_UNDEFINED eip - pushfl_cfi - pushl_cfi $__KERNEL_CS - pushl_cfi $sysenter_past_esp - CFI_REL_OFFSET eip, 0 -.endm - -ENTRY(debug) - RING0_INT_FRAME - ASM_CLAC - cmpl $ia32_sysenter_target,(%esp) - jne debug_stack_correct - FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn -debug_stack_correct: - pushl_cfi $-1 # mark this as an int - SAVE_ALL - TRACE_IRQS_OFF - xorl %edx,%edx # error code 0 - movl %esp,%eax # pt_regs pointer - call do_debug - jmp ret_from_exception - CFI_ENDPROC -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 - * clear up the stack. So we first check whether we got an - * NMI on the sysenter entry path, but after that we need to - * check whether we got an NMI on the debug path where the debug - * fault happened on the sysenter path. - */ -ENTRY(nmi) - RING0_INT_FRAME - ASM_CLAC -#ifdef CONFIG_X86_ESPFIX32 - pushl_cfi %eax - movl %ss, %eax - cmpw $__ESPFIX_SS, %ax - popl_cfi %eax - je nmi_espfix_stack -#endif - cmpl $ia32_sysenter_target,(%esp) - je nmi_stack_fixup - pushl_cfi %eax - movl %esp,%eax - /* Do not access memory above the end of our stack page, - * it might not exist. - */ - andl $(THREAD_SIZE-1),%eax - cmpl $(THREAD_SIZE-20),%eax - popl_cfi %eax - jae nmi_stack_correct - cmpl $ia32_sysenter_target,12(%esp) - je nmi_debug_stack_check -nmi_stack_correct: - /* We have a RING0_INT_FRAME here */ - pushl_cfi %eax - SAVE_ALL - xorl %edx,%edx # zero error code - movl %esp,%eax # pt_regs pointer - call do_nmi - jmp restore_all_notrace - 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) - jb nmi_stack_correct - cmpl $debug_esp_fix_insn,(%esp) - ja nmi_stack_correct - FIX_STACK 24, nmi_stack_correct, 1 - jmp nmi_stack_correct - -#ifdef CONFIG_X86_ESPFIX32 -nmi_espfix_stack: - /* We have a RING0_INT_FRAME here. - * - * create the pointer to lss back - */ - pushl_cfi %ss - pushl_cfi %esp - addl $4, (%esp) - /* copy the iret frame of 12 bytes */ - .rept 3 - pushl_cfi 16(%esp) - .endr - pushl_cfi %eax - SAVE_ALL - FIXUP_ESPFIX_STACK # %eax == %esp - xorl %edx,%edx # zero error code - call do_nmi - RESTORE_REGS - lss 12+4(%esp), %esp # back to espfix stack - CFI_ADJUST_CFA_OFFSET -24 - jmp irq_return -#endif - CFI_ENDPROC -END(nmi) - -ENTRY(int3) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $-1 # mark this as an int - SAVE_ALL - TRACE_IRQS_OFF - xorl %edx,%edx # zero error code - movl %esp,%eax # pt_regs pointer - call do_int3 - jmp ret_from_exception - CFI_ENDPROC -END(int3) - -ENTRY(general_protection) - RING0_EC_FRAME - pushl_cfi $do_general_protection - jmp error_code - CFI_ENDPROC -END(general_protection) - -#ifdef CONFIG_KVM_GUEST -ENTRY(async_page_fault) - RING0_EC_FRAME - ASM_CLAC - pushl_cfi $do_async_page_fault - jmp error_code - CFI_ENDPROC -END(async_page_fault) -#endif - diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 7cce04c98..ce95676ab 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -131,25 +131,24 @@ void __init init_espfix_bsp(void) init_espfix_random(); /* The rest is the same as for any other processor */ - init_espfix_ap(); + init_espfix_ap(0); } -void init_espfix_ap(void) +void init_espfix_ap(int cpu) { - unsigned int cpu, page; + unsigned int page; unsigned long addr; pud_t pud, *pud_p; pmd_t pmd, *pmd_p; pte_t pte, *pte_p; - int n; + int n, node; void *stack_page; pteval_t ptemask; /* We only have to do this once... */ - if (likely(this_cpu_read(espfix_stack))) + if (likely(per_cpu(espfix_stack, cpu))) return; /* Already initialized */ - cpu = smp_processor_id(); addr = espfix_base_addr(cpu); page = cpu/ESPFIX_STACKS_PER_PAGE; @@ -165,13 +164,15 @@ void init_espfix_ap(void) if (stack_page) goto unlock_done; + node = cpu_to_node(cpu); ptemask = __supported_pte_mask; pud_p = &espfix_pud_page[pud_index(addr)]; pud = *pud_p; if (!pud_present(pud)) { - pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP); - SetPageTOI_Untracked(virt_to_page(pmd_p)); + struct page *page = alloc_pages_node(node, PGALLOC_GFP, 0); + + pmd_p = (pmd_t *)page_address(page); pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask)); paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT); for (n = 0; n < ESPFIX_PUD_CLONES; n++) @@ -181,8 +182,9 @@ void init_espfix_ap(void) pmd_p = pmd_offset(&pud, addr); pmd = *pmd_p; if (!pmd_present(pmd)) { - pte_p = (pte_t *)__get_free_page(PGALLOC_GFP); - SetPageTOI_Untracked(virt_to_page(pte_p)); + struct page *page = alloc_pages_node(node, PGALLOC_GFP, 0); + + pte_p = (pte_t *)page_address(page); pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask)); paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT); for (n = 0; n < ESPFIX_PMD_CLONES; n++) @@ -190,8 +192,7 @@ void init_espfix_ap(void) } pte_p = pte_offset_kernel(&pmd, addr); - stack_page = (void *)__get_free_page(GFP_KERNEL); - SetPageTOI_Untracked(virt_to_page(stack_page)); + stack_page = page_address(alloc_pages_node(node, GFP_KERNEL, 0)); pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask)); for (n = 0; n < ESPFIX_PTE_CLONES; n++) set_pte(&pte_p[n*PTE_STRIDE], pte); @@ -202,7 +203,7 @@ void init_espfix_ap(void) unlock_done: mutex_unlock(&espfix_init_mutex); done: - this_cpu_write(espfix_stack, addr); - this_cpu_write(espfix_waddr, (unsigned long)stack_page - + (addr & ~PAGE_MASK)); + per_cpu(espfix_stack, cpu) = addr; + per_cpu(espfix_waddr, cpu) = (unsigned long)stack_page + + (addr & ~PAGE_MASK); } diff --git a/arch/x86/kernel/fpu/Makefile b/arch/x86/kernel/fpu/Makefile new file mode 100644 index 000000000..68279efb8 --- /dev/null +++ b/arch/x86/kernel/fpu/Makefile @@ -0,0 +1,5 @@ +# +# Build rules for the FPU support code: +# + +obj-y += init.o bugs.o core.o regset.o signal.o xstate.o diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c new file mode 100644 index 000000000..dd9ca9b60 --- /dev/null +++ b/arch/x86/kernel/fpu/bugs.c @@ -0,0 +1,71 @@ +/* + * x86 FPU bug checks: + */ +#include <asm/fpu/internal.h> + +/* + * Boot time CPU/FPU FDIV bug detection code: + */ + +static double __initdata x = 4195835.0; +static double __initdata y = 3145727.0; + +/* + * This used to check for exceptions.. + * However, it turns out that to support that, + * the XMM trap handlers basically had to + * be buggy. So let's have a correct XMM trap + * handler, and forget about printing out + * some status at boot. + * + * We should really only care about bugs here + * anyway. Not features. + */ +static void __init check_fpu(void) +{ + u32 cr0_saved; + s32 fdiv_bug; + + /* We might have CR0::TS set already, clear it: */ + cr0_saved = read_cr0(); + write_cr0(cr0_saved & ~X86_CR0_TS); + + kernel_fpu_begin(); + + /* + * trap_init() enabled FXSR and company _before_ testing for FP + * problems here. + * + * Test for the divl bug: http://en.wikipedia.org/wiki/Fdiv_bug + */ + __asm__("fninit\n\t" + "fldl %1\n\t" + "fdivl %2\n\t" + "fmull %2\n\t" + "fldl %1\n\t" + "fsubp %%st,%%st(1)\n\t" + "fistpl %0\n\t" + "fwait\n\t" + "fninit" + : "=m" (*&fdiv_bug) + : "m" (*&x), "m" (*&y)); + + kernel_fpu_end(); + + write_cr0(cr0_saved); + + if (fdiv_bug) { + set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV); + pr_warn("Hmm, FPU with FDIV bug\n"); + } +} + +void __init fpu__init_check_bugs(void) +{ + /* + * kernel_fpu_begin/end() in check_fpu() relies on the patched + * alternative instructions. + */ + if (cpu_has_fpu) + check_fpu(); +} diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c new file mode 100644 index 000000000..d25097c3f --- /dev/null +++ b/arch/x86/kernel/fpu/core.c @@ -0,0 +1,523 @@ +/* + * Copyright (C) 1994 Linus Torvalds + * + * Pentium III FXSR, SSE support + * General FPU state handling cleanups + * Gareth Hughes <gareth@valinux.com>, May 2000 + */ +#include <asm/fpu/internal.h> +#include <asm/fpu/regset.h> +#include <asm/fpu/signal.h> +#include <asm/traps.h> + +#include <linux/hardirq.h> + +/* + * Represents the initial FPU state. It's mostly (but not completely) zeroes, + * depending on the FPU hardware format: + */ +union fpregs_state init_fpstate __read_mostly; + +/* + * Track whether the kernel is using the FPU state + * currently. + * + * This flag is used: + * + * - by IRQ context code to potentially use the FPU + * if it's unused. + * + * - to debug kernel_fpu_begin()/end() correctness + */ +static DEFINE_PER_CPU(bool, in_kernel_fpu); + +/* + * Track which context is using the FPU on the CPU: + */ +DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); + +static void kernel_fpu_disable(void) +{ + WARN_ON_FPU(this_cpu_read(in_kernel_fpu)); + this_cpu_write(in_kernel_fpu, true); +} + +static void kernel_fpu_enable(void) +{ + WARN_ON_FPU(!this_cpu_read(in_kernel_fpu)); + this_cpu_write(in_kernel_fpu, false); +} + +static bool kernel_fpu_disabled(void) +{ + return this_cpu_read(in_kernel_fpu); +} + +/* + * Were we in an interrupt that interrupted kernel mode? + * + * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that + * pair does nothing at all: the thread must not have fpu (so + * that we don't try to save the FPU state), and TS must + * be set (so that the clts/stts pair does nothing that is + * visible in the interrupted kernel thread). + * + * Except for the eagerfpu case when we return true; in the likely case + * the thread has FPU but we are not going to set/clear TS. + */ +static bool interrupted_kernel_fpu_idle(void) +{ + if (kernel_fpu_disabled()) + return false; + + if (use_eager_fpu()) + return true; + + return !current->thread.fpu.fpregs_active && (read_cr0() & X86_CR0_TS); +} + +/* + * Were we in user mode (or vm86 mode) when we were + * interrupted? + * + * Doing kernel_fpu_begin/end() is ok if we are running + * in an interrupt context from user mode - we'll just + * save the FPU state as required. + */ +static bool interrupted_user_mode(void) +{ + struct pt_regs *regs = get_irq_regs(); + return regs && user_mode(regs); +} + +/* + * Can we use the FPU in kernel mode with the + * whole "kernel_fpu_begin/end()" sequence? + * + * It's always ok in process context (ie "not interrupt") + * but it is sometimes ok even from an irq. + */ +bool irq_fpu_usable(void) +{ + return !in_interrupt() || + interrupted_user_mode() || + interrupted_kernel_fpu_idle(); +} +EXPORT_SYMBOL(irq_fpu_usable); + +void __kernel_fpu_begin(void) +{ + struct fpu *fpu = ¤t->thread.fpu; + + WARN_ON_FPU(!irq_fpu_usable()); + + kernel_fpu_disable(); + + if (fpu->fpregs_active) { + copy_fpregs_to_fpstate(fpu); + } else { + this_cpu_write(fpu_fpregs_owner_ctx, NULL); + __fpregs_activate_hw(); + } +} +EXPORT_SYMBOL(__kernel_fpu_begin); + +void __kernel_fpu_end(void) +{ + struct fpu *fpu = ¤t->thread.fpu; + + if (fpu->fpregs_active) + copy_kernel_to_fpregs(&fpu->state); + else + __fpregs_deactivate_hw(); + + kernel_fpu_enable(); +} +EXPORT_SYMBOL(__kernel_fpu_end); + +void kernel_fpu_begin(void) +{ + preempt_disable(); + __kernel_fpu_begin(); +} +EXPORT_SYMBOL_GPL(kernel_fpu_begin); + +void kernel_fpu_end(void) +{ + __kernel_fpu_end(); + preempt_enable(); +} +EXPORT_SYMBOL_GPL(kernel_fpu_end); + +/* + * CR0::TS save/restore functions: + */ +int irq_ts_save(void) +{ + /* + * If in process context and not atomic, we can take a spurious DNA fault. + * Otherwise, doing clts() in process context requires disabling preemption + * or some heavy lifting like kernel_fpu_begin() + */ + if (!in_atomic()) + return 0; + + if (read_cr0() & X86_CR0_TS) { + clts(); + return 1; + } + + return 0; +} +EXPORT_SYMBOL_GPL(irq_ts_save); + +void irq_ts_restore(int TS_state) +{ + if (TS_state) + stts(); +} +EXPORT_SYMBOL_GPL(irq_ts_restore); + +/* + * Save the FPU state (mark it for reload if necessary): + * + * This only ever gets called for the current task. + */ +void fpu__save(struct fpu *fpu) +{ + WARN_ON_FPU(fpu != ¤t->thread.fpu); + + preempt_disable(); + if (fpu->fpregs_active) { + if (!copy_fpregs_to_fpstate(fpu)) + fpregs_deactivate(fpu); + } + preempt_enable(); +} +EXPORT_SYMBOL_GPL(fpu__save); + +/* + * Legacy x87 fpstate state init: + */ +static inline void fpstate_init_fstate(struct fregs_state *fp) +{ + fp->cwd = 0xffff037fu; + fp->swd = 0xffff0000u; + fp->twd = 0xffffffffu; + fp->fos = 0xffff0000u; +} + +void fpstate_init(union fpregs_state *state) +{ + if (!cpu_has_fpu) { + fpstate_init_soft(&state->soft); + return; + } + + memset(state, 0, xstate_size); + + if (cpu_has_fxsr) + fpstate_init_fxstate(&state->fxsave); + else + fpstate_init_fstate(&state->fsave); +} +EXPORT_SYMBOL_GPL(fpstate_init); + +/* + * Copy the current task's FPU state to a new task's FPU context. + * + * In both the 'eager' and the 'lazy' case we save hardware registers + * directly to the destination buffer. + */ +static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu) +{ + WARN_ON_FPU(src_fpu != ¤t->thread.fpu); + + /* + * Don't let 'init optimized' areas of the XSAVE area + * leak into the child task: + */ + if (use_eager_fpu()) + memset(&dst_fpu->state.xsave, 0, xstate_size); + + /* + * Save current FPU registers directly into the child + * FPU context, without any memory-to-memory copying. + * + * If the FPU context got destroyed in the process (FNSAVE + * done on old CPUs) then copy it back into the source + * context and mark the current task for lazy restore. + * + * We have to do all this with preemption disabled, + * mostly because of the FNSAVE case, because in that + * case we must not allow preemption in the window + * between the FNSAVE and us marking the context lazy. + * + * It shouldn't be an issue as even FNSAVE is plenty + * fast in terms of critical section length. + */ + preempt_disable(); + if (!copy_fpregs_to_fpstate(dst_fpu)) { + memcpy(&src_fpu->state, &dst_fpu->state, xstate_size); + fpregs_deactivate(src_fpu); + } + preempt_enable(); +} + +int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) +{ + dst_fpu->counter = 0; + dst_fpu->fpregs_active = 0; + dst_fpu->last_cpu = -1; + + if (src_fpu->fpstate_active && cpu_has_fpu) + fpu_copy(dst_fpu, src_fpu); + + return 0; +} + +/* + * Activate the current task's in-memory FPU context, + * if it has not been used before: + */ +void fpu__activate_curr(struct fpu *fpu) +{ + WARN_ON_FPU(fpu != ¤t->thread.fpu); + + if (!fpu->fpstate_active) { + fpstate_init(&fpu->state); + + /* Safe to do for the current task: */ + fpu->fpstate_active = 1; + } +} +EXPORT_SYMBOL_GPL(fpu__activate_curr); + +/* + * This function must be called before we read a task's fpstate. + * + * If the task has not used the FPU before then initialize its + * fpstate. + * + * If the task has used the FPU before then save it. + */ +void fpu__activate_fpstate_read(struct fpu *fpu) +{ + /* + * If fpregs are active (in the current CPU), then + * copy them to the fpstate: + */ + if (fpu->fpregs_active) { + fpu__save(fpu); + } else { + if (!fpu->fpstate_active) { + fpstate_init(&fpu->state); + + /* Safe to do for current and for stopped child tasks: */ + fpu->fpstate_active = 1; + } + } +} + +/* + * This function must be called before we write a task's fpstate. + * + * If the task has used the FPU before then unlazy it. + * If the task has not used the FPU before then initialize its fpstate. + * + * After this function call, after registers in the fpstate are + * modified and the child task has woken up, the child task will + * restore the modified FPU state from the modified context. If we + * didn't clear its lazy status here then the lazy in-registers + * state pending on its former CPU could be restored, corrupting + * the modifications. + */ +void fpu__activate_fpstate_write(struct fpu *fpu) +{ + /* + * Only stopped child tasks can be used to modify the FPU + * state in the fpstate buffer: + */ + WARN_ON_FPU(fpu == ¤t->thread.fpu); + + if (fpu->fpstate_active) { + /* Invalidate any lazy state: */ + fpu->last_cpu = -1; + } else { + fpstate_init(&fpu->state); + + /* Safe to do for stopped child tasks: */ + fpu->fpstate_active = 1; + } +} + +/* + * 'fpu__restore()' is called to copy FPU registers from + * the FPU fpstate to the live hw registers and to activate + * access to the hardware registers, so that FPU instructions + * can be used afterwards. + * + * Must be called with kernel preemption disabled (for example + * with local interrupts disabled, as it is in the case of + * do_device_not_available()). + */ +void fpu__restore(struct fpu *fpu) +{ + fpu__activate_curr(fpu); + + /* Avoid __kernel_fpu_begin() right after fpregs_activate() */ + kernel_fpu_disable(); + fpregs_activate(fpu); + copy_kernel_to_fpregs(&fpu->state); + fpu->counter++; + kernel_fpu_enable(); +} +EXPORT_SYMBOL_GPL(fpu__restore); + +/* + * Drops current FPU state: deactivates the fpregs and + * the fpstate. NOTE: it still leaves previous contents + * in the fpregs in the eager-FPU case. + * + * This function can be used in cases where we know that + * a state-restore is coming: either an explicit one, + * or a reschedule. + */ +void fpu__drop(struct fpu *fpu) +{ + preempt_disable(); + fpu->counter = 0; + + if (fpu->fpregs_active) { + /* Ignore delayed exceptions from user space */ + asm volatile("1: fwait\n" + "2:\n" + _ASM_EXTABLE(1b, 2b)); + fpregs_deactivate(fpu); + } + + fpu->fpstate_active = 0; + + preempt_enable(); +} + +/* + * Clear FPU registers by setting them up from + * the init fpstate: + */ +static inline void copy_init_fpstate_to_fpregs(void) +{ + if (use_xsave()) + copy_kernel_to_xregs(&init_fpstate.xsave, -1); + else + copy_kernel_to_fxregs(&init_fpstate.fxsave); +} + +/* + * Clear the FPU state back to init state. + * + * Called by sys_execve(), by the signal handler code and by various + * error paths. + */ +void fpu__clear(struct fpu *fpu) +{ + WARN_ON_FPU(fpu != ¤t->thread.fpu); /* Almost certainly an anomaly */ + + if (!use_eager_fpu()) { + /* FPU state will be reallocated lazily at the first use. */ + fpu__drop(fpu); + } else { + if (!fpu->fpstate_active) { + fpu__activate_curr(fpu); + user_fpu_begin(); + } + copy_init_fpstate_to_fpregs(); + } +} + +/* + * x87 math exception handling: + */ + +static inline unsigned short get_fpu_cwd(struct fpu *fpu) +{ + if (cpu_has_fxsr) { + return fpu->state.fxsave.cwd; + } else { + return (unsigned short)fpu->state.fsave.cwd; + } +} + +static inline unsigned short get_fpu_swd(struct fpu *fpu) +{ + if (cpu_has_fxsr) { + return fpu->state.fxsave.swd; + } else { + return (unsigned short)fpu->state.fsave.swd; + } +} + +static inline unsigned short get_fpu_mxcsr(struct fpu *fpu) +{ + if (cpu_has_xmm) { + return fpu->state.fxsave.mxcsr; + } else { + return MXCSR_DEFAULT; + } +} + +int fpu__exception_code(struct fpu *fpu, int trap_nr) +{ + int err; + + if (trap_nr == X86_TRAP_MF) { + unsigned short cwd, swd; + /* + * (~cwd & swd) will mask out exceptions that are not set to unmasked + * status. 0x3f is the exception bits in these regs, 0x200 is the + * C1 reg you need in case of a stack fault, 0x040 is the stack + * fault bit. We should only be taking one exception at a time, + * so if this combination doesn't produce any single exception, + * then we have a bad program that isn't synchronizing its FPU usage + * and it will suffer the consequences since we won't be able to + * fully reproduce the context of the exception + */ + cwd = get_fpu_cwd(fpu); + swd = get_fpu_swd(fpu); + + err = swd & ~cwd; + } else { + /* + * The SIMD FPU exceptions are handled a little differently, as there + * is only a single status/control register. Thus, to determine which + * unmasked exception was caught we must mask the exception mask bits + * at 0x1f80, and then use these to mask the exception bits at 0x3f. + */ + unsigned short mxcsr = get_fpu_mxcsr(fpu); + err = ~(mxcsr >> 7) & mxcsr; + } + + if (err & 0x001) { /* Invalid op */ + /* + * swd & 0x240 == 0x040: Stack Underflow + * swd & 0x240 == 0x240: Stack Overflow + * User must clear the SF bit (0x40) if set + */ + return FPE_FLTINV; + } else if (err & 0x004) { /* Divide by Zero */ + return FPE_FLTDIV; + } else if (err & 0x008) { /* Overflow */ + return FPE_FLTOVF; + } else if (err & 0x012) { /* Denormal, Underflow */ + return FPE_FLTUND; + } else if (err & 0x020) { /* Precision */ + return FPE_FLTRES; + } + + /* + * If we're using IRQ 13, or supposedly even some trap + * X86_TRAP_MF implementations, it's possible + * we get a spurious trap, which is not an error. + */ + return 0; +} diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c new file mode 100644 index 000000000..d14e9ac32 --- /dev/null +++ b/arch/x86/kernel/fpu/init.c @@ -0,0 +1,406 @@ +/* + * x86 FPU boot time init code: + */ +#include <asm/fpu/internal.h> +#include <asm/tlbflush.h> + +#include <linux/sched.h> + +/* + * Initialize the TS bit in CR0 according to the style of context-switches + * we are using: + */ +static void fpu__init_cpu_ctx_switch(void) +{ + if (!cpu_has_eager_fpu) + stts(); + else + clts(); +} + +/* + * Initialize the registers found in all CPUs, CR0 and CR4: + */ +static void fpu__init_cpu_generic(void) +{ + unsigned long cr0; + unsigned long cr4_mask = 0; + + if (cpu_has_fxsr) + cr4_mask |= X86_CR4_OSFXSR; + if (cpu_has_xmm) + cr4_mask |= X86_CR4_OSXMMEXCPT; + if (cr4_mask) + cr4_set_bits(cr4_mask); + + cr0 = read_cr0(); + cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */ + if (!cpu_has_fpu) + cr0 |= X86_CR0_EM; + write_cr0(cr0); + + /* Flush out any pending x87 state: */ +#ifdef CONFIG_MATH_EMULATION + if (!cpu_has_fpu) + fpstate_init_soft(¤t->thread.fpu.state.soft); + else +#endif + asm volatile ("fninit"); +} + +/* + * Enable all supported FPU features. Called when a CPU is brought online: + */ +void fpu__init_cpu(void) +{ + fpu__init_cpu_generic(); + fpu__init_cpu_xstate(); + fpu__init_cpu_ctx_switch(); +} + +/* + * The earliest FPU detection code. + * + * Set the X86_FEATURE_FPU CPU-capability bit based on + * trying to execute an actual sequence of FPU instructions: + */ +static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) +{ + unsigned long cr0; + u16 fsw, fcw; + + fsw = fcw = 0xffff; + + cr0 = read_cr0(); + cr0 &= ~(X86_CR0_TS | X86_CR0_EM); + write_cr0(cr0); + + asm volatile("fninit ; fnstsw %0 ; fnstcw %1" + : "+m" (fsw), "+m" (fcw)); + + if (fsw == 0 && (fcw & 0x103f) == 0x003f) + set_cpu_cap(c, X86_FEATURE_FPU); + else + clear_cpu_cap(c, X86_FEATURE_FPU); + +#ifndef CONFIG_MATH_EMULATION + if (!cpu_has_fpu) { + pr_emerg("x86/fpu: Giving up, no FPU found and no math emulation present\n"); + for (;;) + asm volatile("hlt"); + } +#endif +} + +/* + * Boot time FPU feature detection code: + */ +unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; + +static void __init fpu__init_system_mxcsr(void) +{ + unsigned int mask = 0; + + if (cpu_has_fxsr) { + /* Static because GCC does not get 16-byte stack alignment right: */ + static struct fxregs_state fxregs __initdata; + + asm volatile("fxsave %0" : "+m" (fxregs)); + + mask = fxregs.mxcsr_mask; + + /* + * If zero then use the default features mask, + * which has all features set, except the + * denormals-are-zero feature bit: + */ + if (mask == 0) + mask = 0x0000ffbf; + } + mxcsr_feature_mask &= mask; +} + +/* + * Once per bootup FPU initialization sequences that will run on most x86 CPUs: + */ +static void __init fpu__init_system_generic(void) +{ + /* + * Set up the legacy init FPU context. (xstate init might overwrite this + * with a more modern format, if the CPU supports it.) + */ + fpstate_init_fxstate(&init_fpstate.fxsave); + + fpu__init_system_mxcsr(); +} + +/* + * Size of the FPU context state. All tasks in the system use the + * same context size, regardless of what portion they use. + * This is inherent to the XSAVE architecture which puts all state + * components into a single, continuous memory block: + */ +unsigned int xstate_size; +EXPORT_SYMBOL_GPL(xstate_size); + +/* Enforce that 'MEMBER' is the last field of 'TYPE': */ +#define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER) \ + BUILD_BUG_ON(sizeof(TYPE) != offsetofend(TYPE, MEMBER)) + +/* + * We append the 'struct fpu' to the task_struct: + */ +static void __init fpu__init_task_struct_size(void) +{ + int task_size = sizeof(struct task_struct); + + /* + * Subtract off the static size of the register state. + * It potentially has a bunch of padding. + */ + task_size -= sizeof(((struct task_struct *)0)->thread.fpu.state); + + /* + * Add back the dynamically-calculated register state + * size. + */ + task_size += xstate_size; + + /* + * We dynamically size 'struct fpu', so we require that + * it be at the end of 'thread_struct' and that + * 'thread_struct' be at the end of 'task_struct'. If + * you hit a compile error here, check the structure to + * see if something got added to the end. + */ + CHECK_MEMBER_AT_END_OF(struct fpu, state); + CHECK_MEMBER_AT_END_OF(struct thread_struct, fpu); + CHECK_MEMBER_AT_END_OF(struct task_struct, thread); + + arch_task_struct_size = task_size; +} + +/* + * Set up the xstate_size based on the legacy FPU context size. + * + * We set this up first, and later it will be overwritten by + * fpu__init_system_xstate() if the CPU knows about xstates. + */ +static void __init fpu__init_system_xstate_size_legacy(void) +{ + static int on_boot_cpu = 1; + + WARN_ON_FPU(!on_boot_cpu); + on_boot_cpu = 0; + + /* + * Note that xstate_size might be overwriten later during + * fpu__init_system_xstate(). + */ + + if (!cpu_has_fpu) { + /* + * Disable xsave as we do not support it if i387 + * emulation is enabled. + */ + setup_clear_cpu_cap(X86_FEATURE_XSAVE); + setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); + xstate_size = sizeof(struct swregs_state); + } else { + if (cpu_has_fxsr) + xstate_size = sizeof(struct fxregs_state); + else + xstate_size = sizeof(struct fregs_state); + } + /* + * Quirk: we don't yet handle the XSAVES* instructions + * correctly, as we don't correctly convert between + * standard and compacted format when interfacing + * with user-space - so disable it for now. + * + * The difference is small: with recent CPUs the + * compacted format is only marginally smaller than + * the standard FPU state format. + * + * ( This is easy to backport while we are fixing + * XSAVES* support. ) + */ + setup_clear_cpu_cap(X86_FEATURE_XSAVES); +} + +/* + * FPU context switching strategies: + * + * Against popular belief, we don't do lazy FPU saves, due to the + * task migration complications it brings on SMP - we only do + * lazy FPU restores. + * + * 'lazy' is the traditional strategy, which is based on setting + * CR0::TS to 1 during context-switch (instead of doing a full + * restore of the FPU state), which causes the first FPU instruction + * after the context switch (whenever it is executed) to fault - at + * which point we lazily restore the FPU state into FPU registers. + * + * Tasks are of course under no obligation to execute FPU instructions, + * so it can easily happen that another context-switch occurs without + * a single FPU instruction being executed. If we eventually switch + * back to the original task (that still owns the FPU) then we have + * not only saved the restores along the way, but we also have the + * FPU ready to be used for the original task. + * + * 'eager' switching is used on modern CPUs, there we switch the FPU + * state during every context switch, regardless of whether the task + * has used FPU instructions in that time slice or not. This is done + * because modern FPU context saving instructions are able to optimize + * state saving and restoration in hardware: they can detect both + * unused and untouched FPU state and optimize accordingly. + * + * [ Note that even in 'lazy' mode we might optimize context switches + * to use 'eager' restores, if we detect that a task is using the FPU + * frequently. See the fpu->counter logic in fpu/internal.h for that. ] + */ +static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO; + +static int __init eager_fpu_setup(char *s) +{ + if (!strcmp(s, "on")) + eagerfpu = ENABLE; + else if (!strcmp(s, "off")) + eagerfpu = DISABLE; + else if (!strcmp(s, "auto")) + eagerfpu = AUTO; + return 1; +} +__setup("eagerfpu=", eager_fpu_setup); + +/* + * Pick the FPU context switching strategy: + */ +static void __init fpu__init_system_ctx_switch(void) +{ + static bool on_boot_cpu = 1; + + WARN_ON_FPU(!on_boot_cpu); + on_boot_cpu = 0; + + WARN_ON_FPU(current->thread.fpu.fpstate_active); + current_thread_info()->status = 0; + + /* Auto enable eagerfpu for xsaveopt */ + if (cpu_has_xsaveopt && eagerfpu != DISABLE) + eagerfpu = ENABLE; + + if (xfeatures_mask & XSTATE_EAGER) { + if (eagerfpu == DISABLE) { + pr_err("x86/fpu: eagerfpu switching disabled, disabling the following xstate features: 0x%llx.\n", + xfeatures_mask & XSTATE_EAGER); + xfeatures_mask &= ~XSTATE_EAGER; + } else { + eagerfpu = ENABLE; + } + } + + if (eagerfpu == ENABLE) + setup_force_cpu_cap(X86_FEATURE_EAGER_FPU); + + printk(KERN_INFO "x86/fpu: Using '%s' FPU context switches.\n", eagerfpu == ENABLE ? "eager" : "lazy"); +} + +/* + * Called on the boot CPU once per system bootup, to set up the initial + * FPU state that is later cloned into all processes: + */ +void __init fpu__init_system(struct cpuinfo_x86 *c) +{ + fpu__init_system_early_generic(c); + + /* + * The FPU has to be operational for some of the + * later FPU init activities: + */ + fpu__init_cpu(); + + /* + * But don't leave CR0::TS set yet, as some of the FPU setup + * methods depend on being able to execute FPU instructions + * that will fault on a set TS, such as the FXSAVE in + * fpu__init_system_mxcsr(). + */ + clts(); + + fpu__init_system_generic(); + fpu__init_system_xstate_size_legacy(); + fpu__init_system_xstate(); + fpu__init_task_struct_size(); + + fpu__init_system_ctx_switch(); +} + +/* + * Boot parameter to turn off FPU support and fall back to math-emu: + */ +static int __init no_387(char *s) +{ + setup_clear_cpu_cap(X86_FEATURE_FPU); + return 1; +} +__setup("no387", no_387); + +/* + * Disable all xstate CPU features: + */ +static int __init x86_noxsave_setup(char *s) +{ + if (strlen(s)) + return 0; + + setup_clear_cpu_cap(X86_FEATURE_XSAVE); + setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); + setup_clear_cpu_cap(X86_FEATURE_XSAVEC); + setup_clear_cpu_cap(X86_FEATURE_XSAVES); + setup_clear_cpu_cap(X86_FEATURE_AVX); + setup_clear_cpu_cap(X86_FEATURE_AVX2); + setup_clear_cpu_cap(X86_FEATURE_AVX512F); + setup_clear_cpu_cap(X86_FEATURE_AVX512PF); + setup_clear_cpu_cap(X86_FEATURE_AVX512ER); + setup_clear_cpu_cap(X86_FEATURE_AVX512CD); + setup_clear_cpu_cap(X86_FEATURE_MPX); + + return 1; +} +__setup("noxsave", x86_noxsave_setup); + +/* + * Disable the XSAVEOPT instruction specifically: + */ +static int __init x86_noxsaveopt_setup(char *s) +{ + setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); + + return 1; +} +__setup("noxsaveopt", x86_noxsaveopt_setup); + +/* + * Disable the XSAVES instruction: + */ +static int __init x86_noxsaves_setup(char *s) +{ + setup_clear_cpu_cap(X86_FEATURE_XSAVES); + + return 1; +} +__setup("noxsaves", x86_noxsaves_setup); + +/* + * Disable FX save/restore and SSE support: + */ +static int __init x86_nofxsr_setup(char *s) +{ + setup_clear_cpu_cap(X86_FEATURE_FXSR); + setup_clear_cpu_cap(X86_FEATURE_FXSR_OPT); + setup_clear_cpu_cap(X86_FEATURE_XMM); + + return 1; +} +__setup("nofxsr", x86_nofxsr_setup); diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c new file mode 100644 index 000000000..dc60810c1 --- /dev/null +++ b/arch/x86/kernel/fpu/regset.c @@ -0,0 +1,356 @@ +/* + * FPU register's regset abstraction, for ptrace, core dumps, etc. + */ +#include <asm/fpu/internal.h> +#include <asm/fpu/signal.h> +#include <asm/fpu/regset.h> + +/* + * The xstateregs_active() routine is the same as the regset_fpregs_active() routine, + * as the "regset->n" for the xstate regset will be updated based on the feature + * capabilites supported by the xsave. + */ +int regset_fpregs_active(struct task_struct *target, const struct user_regset *regset) +{ + struct fpu *target_fpu = &target->thread.fpu; + + return target_fpu->fpstate_active ? regset->n : 0; +} + +int regset_xregset_fpregs_active(struct task_struct *target, const struct user_regset *regset) +{ + struct fpu *target_fpu = &target->thread.fpu; + + return (cpu_has_fxsr && target_fpu->fpstate_active) ? regset->n : 0; +} + +int xfpregs_get(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + + if (!cpu_has_fxsr) + return -ENODEV; + + fpu__activate_fpstate_read(fpu); + fpstate_sanitize_xstate(fpu); + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &fpu->state.fxsave, 0, -1); +} + +int xfpregs_set(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + int ret; + + if (!cpu_has_fxsr) + return -ENODEV; + + fpu__activate_fpstate_write(fpu); + fpstate_sanitize_xstate(fpu); + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &fpu->state.fxsave, 0, -1); + + /* + * mxcsr reserved bits must be masked to zero for security reasons. + */ + fpu->state.fxsave.mxcsr &= mxcsr_feature_mask; + + /* + * update the header bits in the xsave header, indicating the + * presence of FP and SSE state. + */ + if (cpu_has_xsave) + fpu->state.xsave.header.xfeatures |= XSTATE_FPSSE; + + return ret; +} + +int xstateregs_get(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + struct xregs_state *xsave; + int ret; + + if (!cpu_has_xsave) + return -ENODEV; + + fpu__activate_fpstate_read(fpu); + + xsave = &fpu->state.xsave; + + /* + * Copy the 48bytes defined by the software first into the xstate + * memory layout in the thread struct, so that we can copy the entire + * xstateregs to the user using one user_regset_copyout(). + */ + memcpy(&xsave->i387.sw_reserved, + xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes)); + /* + * Copy the xstate memory layout. + */ + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); + return ret; +} + +int xstateregs_set(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + struct xregs_state *xsave; + int ret; + + if (!cpu_has_xsave) + return -ENODEV; + + fpu__activate_fpstate_write(fpu); + + xsave = &fpu->state.xsave; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); + /* + * mxcsr reserved bits must be masked to zero for security reasons. + */ + xsave->i387.mxcsr &= mxcsr_feature_mask; + xsave->header.xfeatures &= xfeatures_mask; + /* + * These bits must be zero. + */ + memset(&xsave->header.reserved, 0, 48); + + return ret; +} + +#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION + +/* + * FPU tag word conversions. + */ + +static inline unsigned short twd_i387_to_fxsr(unsigned short twd) +{ + unsigned int tmp; /* to avoid 16 bit prefixes in the code */ + + /* Transform each pair of bits into 01 (valid) or 00 (empty) */ + tmp = ~twd; + tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */ + /* and move the valid bits to the lower byte. */ + tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */ + tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */ + tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */ + + return tmp; +} + +#define FPREG_ADDR(f, n) ((void *)&(f)->st_space + (n) * 16) +#define FP_EXP_TAG_VALID 0 +#define FP_EXP_TAG_ZERO 1 +#define FP_EXP_TAG_SPECIAL 2 +#define FP_EXP_TAG_EMPTY 3 + +static inline u32 twd_fxsr_to_i387(struct fxregs_state *fxsave) +{ + struct _fpxreg *st; + u32 tos = (fxsave->swd >> 11) & 7; + u32 twd = (unsigned long) fxsave->twd; + u32 tag; + u32 ret = 0xffff0000u; + int i; + + for (i = 0; i < 8; i++, twd >>= 1) { + if (twd & 0x1) { + st = FPREG_ADDR(fxsave, (i - tos) & 7); + + switch (st->exponent & 0x7fff) { + case 0x7fff: + tag = FP_EXP_TAG_SPECIAL; + break; + case 0x0000: + if (!st->significand[0] && + !st->significand[1] && + !st->significand[2] && + !st->significand[3]) + tag = FP_EXP_TAG_ZERO; + else + tag = FP_EXP_TAG_SPECIAL; + break; + default: + if (st->significand[3] & 0x8000) + tag = FP_EXP_TAG_VALID; + else + tag = FP_EXP_TAG_SPECIAL; + break; + } + } else { + tag = FP_EXP_TAG_EMPTY; + } + ret |= tag << (2 * i); + } + return ret; +} + +/* + * FXSR floating point environment conversions. + */ + +void +convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk) +{ + struct fxregs_state *fxsave = &tsk->thread.fpu.state.fxsave; + struct _fpreg *to = (struct _fpreg *) &env->st_space[0]; + struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0]; + int i; + + env->cwd = fxsave->cwd | 0xffff0000u; + env->swd = fxsave->swd | 0xffff0000u; + env->twd = twd_fxsr_to_i387(fxsave); + +#ifdef CONFIG_X86_64 + env->fip = fxsave->rip; + env->foo = fxsave->rdp; + /* + * should be actually ds/cs at fpu exception time, but + * that information is not available in 64bit mode. + */ + env->fcs = task_pt_regs(tsk)->cs; + if (tsk == current) { + savesegment(ds, env->fos); + } else { + env->fos = tsk->thread.ds; + } + env->fos |= 0xffff0000; +#else + env->fip = fxsave->fip; + env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16); + env->foo = fxsave->foo; + env->fos = fxsave->fos; +#endif + + for (i = 0; i < 8; ++i) + memcpy(&to[i], &from[i], sizeof(to[0])); +} + +void convert_to_fxsr(struct task_struct *tsk, + const struct user_i387_ia32_struct *env) + +{ + struct fxregs_state *fxsave = &tsk->thread.fpu.state.fxsave; + struct _fpreg *from = (struct _fpreg *) &env->st_space[0]; + struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0]; + int i; + + fxsave->cwd = env->cwd; + fxsave->swd = env->swd; + fxsave->twd = twd_i387_to_fxsr(env->twd); + fxsave->fop = (u16) ((u32) env->fcs >> 16); +#ifdef CONFIG_X86_64 + fxsave->rip = env->fip; + fxsave->rdp = env->foo; + /* cs and ds ignored */ +#else + fxsave->fip = env->fip; + fxsave->fcs = (env->fcs & 0xffff); + fxsave->foo = env->foo; + fxsave->fos = env->fos; +#endif + + for (i = 0; i < 8; ++i) + memcpy(&to[i], &from[i], sizeof(from[0])); +} + +int fpregs_get(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + struct user_i387_ia32_struct env; + + fpu__activate_fpstate_read(fpu); + + if (!static_cpu_has(X86_FEATURE_FPU)) + return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); + + if (!cpu_has_fxsr) + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &fpu->state.fsave, 0, + -1); + + fpstate_sanitize_xstate(fpu); + + if (kbuf && pos == 0 && count == sizeof(env)) { + convert_from_fxsr(kbuf, target); + return 0; + } + + convert_from_fxsr(&env, target); + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &env, 0, -1); +} + +int fpregs_set(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + struct user_i387_ia32_struct env; + int ret; + + fpu__activate_fpstate_write(fpu); + fpstate_sanitize_xstate(fpu); + + if (!static_cpu_has(X86_FEATURE_FPU)) + return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); + + if (!cpu_has_fxsr) + return user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &fpu->state.fsave, 0, + -1); + + if (pos > 0 || count < sizeof(env)) + convert_from_fxsr(&env, target); + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1); + if (!ret) + convert_to_fxsr(target, &env); + + /* + * update the header bit in the xsave header, indicating the + * presence of FP. + */ + if (cpu_has_xsave) + fpu->state.xsave.header.xfeatures |= XSTATE_FP; + return ret; +} + +/* + * FPU state for core dumps. + * This is only used for a.out dumps now. + * It is declared generically using elf_fpregset_t (which is + * struct user_i387_struct) but is in fact only used for 32-bit + * dumps, so on 64-bit it is really struct user_i387_ia32_struct. + */ +int dump_fpu(struct pt_regs *regs, struct user_i387_struct *ufpu) +{ + struct task_struct *tsk = current; + struct fpu *fpu = &tsk->thread.fpu; + int fpvalid; + + fpvalid = fpu->fpstate_active; + if (fpvalid) + fpvalid = !fpregs_get(tsk, NULL, + 0, sizeof(struct user_i387_ia32_struct), + ufpu, NULL); + + return fpvalid; +} +EXPORT_SYMBOL(dump_fpu); + +#endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */ diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c new file mode 100644 index 000000000..50ec9af1b --- /dev/null +++ b/arch/x86/kernel/fpu/signal.c @@ -0,0 +1,404 @@ +/* + * FPU signal frame handling routines. + */ + +#include <linux/compat.h> +#include <linux/cpu.h> + +#include <asm/fpu/internal.h> +#include <asm/fpu/signal.h> +#include <asm/fpu/regset.h> + +#include <asm/sigframe.h> + +static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32; + +/* + * Check for the presence of extended state information in the + * user fpstate pointer in the sigcontext. + */ +static inline int check_for_xstate(struct fxregs_state __user *buf, + void __user *fpstate, + struct _fpx_sw_bytes *fx_sw) +{ + int min_xstate_size = sizeof(struct fxregs_state) + + sizeof(struct xstate_header); + unsigned int magic2; + + if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw))) + return -1; + + /* Check for the first magic field and other error scenarios. */ + if (fx_sw->magic1 != FP_XSTATE_MAGIC1 || + fx_sw->xstate_size < min_xstate_size || + fx_sw->xstate_size > xstate_size || + fx_sw->xstate_size > fx_sw->extended_size) + return -1; + + /* + * Check for the presence of second magic word at the end of memory + * layout. This detects the case where the user just copied the legacy + * fpstate layout with out copying the extended state information + * in the memory layout. + */ + if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size)) + || magic2 != FP_XSTATE_MAGIC2) + return -1; + + return 0; +} + +/* + * Signal frame handlers. + */ +static inline int save_fsave_header(struct task_struct *tsk, void __user *buf) +{ + if (use_fxsr()) { + struct xregs_state *xsave = &tsk->thread.fpu.state.xsave; + struct user_i387_ia32_struct env; + struct _fpstate_ia32 __user *fp = buf; + + convert_from_fxsr(&env, tsk); + + if (__copy_to_user(buf, &env, sizeof(env)) || + __put_user(xsave->i387.swd, &fp->status) || + __put_user(X86_FXSR_MAGIC, &fp->magic)) + return -1; + } else { + struct fregs_state __user *fp = buf; + u32 swd; + if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status)) + return -1; + } + + return 0; +} + +static inline int save_xstate_epilog(void __user *buf, int ia32_frame) +{ + struct xregs_state __user *x = buf; + struct _fpx_sw_bytes *sw_bytes; + u32 xfeatures; + int err; + + /* Setup the bytes not touched by the [f]xsave and reserved for SW. */ + sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved; + err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes)); + + if (!use_xsave()) + return err; + + err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size)); + + /* + * Read the xfeatures which we copied (directly from the cpu or + * from the state in task struct) to the user buffers. + */ + err |= __get_user(xfeatures, (__u32 *)&x->header.xfeatures); + + /* + * For legacy compatible, we always set FP/SSE bits in the bit + * vector while saving the state to the user context. This will + * enable us capturing any changes(during sigreturn) to + * the FP/SSE bits by the legacy applications which don't touch + * xfeatures in the xsave header. + * + * xsave aware apps can change the xfeatures in the xsave + * header as well as change any contents in the memory layout. + * xrestore as part of sigreturn will capture all the changes. + */ + xfeatures |= XSTATE_FPSSE; + + err |= __put_user(xfeatures, (__u32 *)&x->header.xfeatures); + + return err; +} + +static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf) +{ + int err; + + if (use_xsave()) + err = copy_xregs_to_user(buf); + else if (use_fxsr()) + err = copy_fxregs_to_user((struct fxregs_state __user *) buf); + else + err = copy_fregs_to_user((struct fregs_state __user *) buf); + + if (unlikely(err) && __clear_user(buf, xstate_size)) + err = -EFAULT; + return err; +} + +/* + * Save the fpu, extended register state to the user signal frame. + * + * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save + * state is copied. + * 'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'. + * + * buf == buf_fx for 64-bit frames and 32-bit fsave frame. + * buf != buf_fx for 32-bit frames with fxstate. + * + * If the fpu, extended register state is live, save the state directly + * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise, + * copy the thread's fpu state to the user frame starting at 'buf_fx'. + * + * If this is a 32-bit frame with fxstate, put a fsave header before + * the aligned state at 'buf_fx'. + * + * For [f]xsave state, update the SW reserved fields in the [f]xsave frame + * indicating the absence/presence of the extended state to the user. + */ +int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) +{ + struct xregs_state *xsave = ¤t->thread.fpu.state.xsave; + struct task_struct *tsk = current; + int ia32_fxstate = (buf != buf_fx); + + ia32_fxstate &= (config_enabled(CONFIG_X86_32) || + config_enabled(CONFIG_IA32_EMULATION)); + + if (!access_ok(VERIFY_WRITE, buf, size)) + return -EACCES; + + if (!static_cpu_has(X86_FEATURE_FPU)) + return fpregs_soft_get(current, NULL, 0, + sizeof(struct user_i387_ia32_struct), NULL, + (struct _fpstate_ia32 __user *) buf) ? -1 : 1; + + if (fpregs_active()) { + /* Save the live register state to the user directly. */ + if (copy_fpregs_to_sigframe(buf_fx)) + return -1; + /* Update the thread's fxstate to save the fsave header. */ + if (ia32_fxstate) + copy_fxregs_to_kernel(&tsk->thread.fpu); + } else { + fpstate_sanitize_xstate(&tsk->thread.fpu); + if (__copy_to_user(buf_fx, xsave, xstate_size)) + return -1; + } + + /* Save the fsave header for the 32-bit frames. */ + if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf)) + return -1; + + if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate)) + return -1; + + return 0; +} + +static inline void +sanitize_restored_xstate(struct task_struct *tsk, + struct user_i387_ia32_struct *ia32_env, + u64 xfeatures, int fx_only) +{ + struct xregs_state *xsave = &tsk->thread.fpu.state.xsave; + struct xstate_header *header = &xsave->header; + + if (use_xsave()) { + /* These bits must be zero. */ + memset(header->reserved, 0, 48); + + /* + * Init the state that is not present in the memory + * layout and not enabled by the OS. + */ + if (fx_only) + header->xfeatures = XSTATE_FPSSE; + else + header->xfeatures &= (xfeatures_mask & xfeatures); + } + + if (use_fxsr()) { + /* + * mscsr reserved bits must be masked to zero for security + * reasons. + */ + xsave->i387.mxcsr &= mxcsr_feature_mask; + + convert_to_fxsr(tsk, ia32_env); + } +} + +/* + * Restore the extended state if present. Otherwise, restore the FP/SSE state. + */ +static inline int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only) +{ + if (use_xsave()) { + if ((unsigned long)buf % 64 || fx_only) { + u64 init_bv = xfeatures_mask & ~XSTATE_FPSSE; + copy_kernel_to_xregs(&init_fpstate.xsave, init_bv); + return copy_user_to_fxregs(buf); + } else { + u64 init_bv = xfeatures_mask & ~xbv; + if (unlikely(init_bv)) + copy_kernel_to_xregs(&init_fpstate.xsave, init_bv); + return copy_user_to_xregs(buf, xbv); + } + } else if (use_fxsr()) { + return copy_user_to_fxregs(buf); + } else + return copy_user_to_fregs(buf); +} + +static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) +{ + int ia32_fxstate = (buf != buf_fx); + struct task_struct *tsk = current; + struct fpu *fpu = &tsk->thread.fpu; + int state_size = xstate_size; + u64 xfeatures = 0; + int fx_only = 0; + + ia32_fxstate &= (config_enabled(CONFIG_X86_32) || + config_enabled(CONFIG_IA32_EMULATION)); + + if (!buf) { + fpu__clear(fpu); + return 0; + } + + if (!access_ok(VERIFY_READ, buf, size)) + return -EACCES; + + fpu__activate_curr(fpu); + + if (!static_cpu_has(X86_FEATURE_FPU)) + return fpregs_soft_set(current, NULL, + 0, sizeof(struct user_i387_ia32_struct), + NULL, buf) != 0; + + if (use_xsave()) { + struct _fpx_sw_bytes fx_sw_user; + if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) { + /* + * Couldn't find the extended state information in the + * memory layout. Restore just the FP/SSE and init all + * the other extended state. + */ + state_size = sizeof(struct fxregs_state); + fx_only = 1; + } else { + state_size = fx_sw_user.xstate_size; + xfeatures = fx_sw_user.xfeatures; + } + } + + if (ia32_fxstate) { + /* + * For 32-bit frames with fxstate, copy the user state to the + * thread's fpu state, reconstruct fxstate from the fsave + * header. Sanitize the copied state etc. + */ + struct fpu *fpu = &tsk->thread.fpu; + struct user_i387_ia32_struct env; + int err = 0; + + /* + * Drop the current fpu which clears fpu->fpstate_active. This ensures + * that any context-switch during the copy of the new state, + * avoids the intermediate state from getting restored/saved. + * Thus avoiding the new restored state from getting corrupted. + * We will be ready to restore/save the state only after + * fpu->fpstate_active is again set. + */ + fpu__drop(fpu); + + if (__copy_from_user(&fpu->state.xsave, buf_fx, state_size) || + __copy_from_user(&env, buf, sizeof(env))) { + fpstate_init(&fpu->state); + err = -1; + } else { + sanitize_restored_xstate(tsk, &env, xfeatures, fx_only); + } + + fpu->fpstate_active = 1; + if (use_eager_fpu()) { + preempt_disable(); + fpu__restore(fpu); + preempt_enable(); + } + + return err; + } else { + /* + * For 64-bit frames and 32-bit fsave frames, restore the user + * state to the registers directly (with exceptions handled). + */ + user_fpu_begin(); + if (copy_user_to_fpregs_zeroing(buf_fx, xfeatures, fx_only)) { + fpu__clear(fpu); + return -1; + } + } + + return 0; +} + +static inline int xstate_sigframe_size(void) +{ + return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size; +} + +/* + * Restore FPU state from a sigframe: + */ +int fpu__restore_sig(void __user *buf, int ia32_frame) +{ + void __user *buf_fx = buf; + int size = xstate_sigframe_size(); + + if (ia32_frame && use_fxsr()) { + buf_fx = buf + sizeof(struct fregs_state); + size += sizeof(struct fregs_state); + } + + return __fpu__restore_sig(buf, buf_fx, size); +} + +unsigned long +fpu__alloc_mathframe(unsigned long sp, int ia32_frame, + unsigned long *buf_fx, unsigned long *size) +{ + unsigned long frame_size = xstate_sigframe_size(); + + *buf_fx = sp = round_down(sp - frame_size, 64); + if (ia32_frame && use_fxsr()) { + frame_size += sizeof(struct fregs_state); + sp -= sizeof(struct fregs_state); + } + + *size = frame_size; + + return sp; +} +/* + * Prepare the SW reserved portion of the fxsave memory layout, indicating + * the presence of the extended state information in the memory layout + * pointed by the fpstate pointer in the sigcontext. + * This will be saved when ever the FP and extended state context is + * saved on the user stack during the signal handler delivery to the user. + */ +void fpu__init_prepare_fx_sw_frame(void) +{ + int fsave_header_size = sizeof(struct fregs_state); + int size = xstate_size + FP_XSTATE_MAGIC2_SIZE; + + if (config_enabled(CONFIG_X86_32)) + size += fsave_header_size; + + fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1; + fx_sw_reserved.extended_size = size; + fx_sw_reserved.xfeatures = xfeatures_mask; + fx_sw_reserved.xstate_size = xstate_size; + + if (config_enabled(CONFIG_IA32_EMULATION)) { + fx_sw_reserved_ia32 = fx_sw_reserved; + fx_sw_reserved_ia32.extended_size += fsave_header_size; + } +} + diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c new file mode 100644 index 000000000..62fc001c7 --- /dev/null +++ b/arch/x86/kernel/fpu/xstate.c @@ -0,0 +1,461 @@ +/* + * xsave/xrstor support. + * + * Author: Suresh Siddha <suresh.b.siddha@intel.com> + */ +#include <linux/compat.h> +#include <linux/cpu.h> + +#include <asm/fpu/api.h> +#include <asm/fpu/internal.h> +#include <asm/fpu/signal.h> +#include <asm/fpu/regset.h> + +#include <asm/tlbflush.h> + +static const char *xfeature_names[] = +{ + "x87 floating point registers" , + "SSE registers" , + "AVX registers" , + "MPX bounds registers" , + "MPX CSR" , + "AVX-512 opmask" , + "AVX-512 Hi256" , + "AVX-512 ZMM_Hi256" , + "unknown xstate feature" , +}; + +/* + * Mask of xstate features supported by the CPU and the kernel: + */ +u64 xfeatures_mask __read_mostly; + +static unsigned int xstate_offsets[XFEATURES_NR_MAX] = { [ 0 ... XFEATURES_NR_MAX - 1] = -1}; +static unsigned int xstate_sizes[XFEATURES_NR_MAX] = { [ 0 ... XFEATURES_NR_MAX - 1] = -1}; +static unsigned int xstate_comp_offsets[sizeof(xfeatures_mask)*8]; + +/* The number of supported xfeatures in xfeatures_mask: */ +static unsigned int xfeatures_nr; + +/* + * Return whether the system supports a given xfeature. + * + * Also return the name of the (most advanced) feature that the caller requested: + */ +int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name) +{ + u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask; + + if (unlikely(feature_name)) { + long xfeature_idx, max_idx; + u64 xfeatures_print; + /* + * So we use FLS here to be able to print the most advanced + * feature that was requested but is missing. So if a driver + * asks about "XSTATE_SSE | XSTATE_YMM" we'll print the + * missing AVX feature - this is the most informative message + * to users: + */ + if (xfeatures_missing) + xfeatures_print = xfeatures_missing; + else + xfeatures_print = xfeatures_needed; + + xfeature_idx = fls64(xfeatures_print)-1; + max_idx = ARRAY_SIZE(xfeature_names)-1; + xfeature_idx = min(xfeature_idx, max_idx); + + *feature_name = xfeature_names[xfeature_idx]; + } + + if (xfeatures_missing) + return 0; + + return 1; +} +EXPORT_SYMBOL_GPL(cpu_has_xfeatures); + +/* + * When executing XSAVEOPT (or other optimized XSAVE instructions), if + * a processor implementation detects that an FPU state component is still + * (or is again) in its initialized state, it may clear the corresponding + * bit in the header.xfeatures field, and can skip the writeout of registers + * to the corresponding memory layout. + * + * This means that when the bit is zero, the state component might still contain + * some previous - non-initialized register state. + * + * Before writing xstate information to user-space we sanitize those components, + * to always ensure that the memory layout of a feature will be in the init state + * if the corresponding header bit is zero. This is to ensure that user-space doesn't + * see some stale state in the memory layout during signal handling, debugging etc. + */ +void fpstate_sanitize_xstate(struct fpu *fpu) +{ + struct fxregs_state *fx = &fpu->state.fxsave; + int feature_bit; + u64 xfeatures; + + if (!use_xsaveopt()) + return; + + xfeatures = fpu->state.xsave.header.xfeatures; + + /* + * None of the feature bits are in init state. So nothing else + * to do for us, as the memory layout is up to date. + */ + if ((xfeatures & xfeatures_mask) == xfeatures_mask) + return; + + /* + * FP is in init state + */ + if (!(xfeatures & XSTATE_FP)) { + fx->cwd = 0x37f; + fx->swd = 0; + fx->twd = 0; + fx->fop = 0; + fx->rip = 0; + fx->rdp = 0; + memset(&fx->st_space[0], 0, 128); + } + + /* + * SSE is in init state + */ + if (!(xfeatures & XSTATE_SSE)) + memset(&fx->xmm_space[0], 0, 256); + + /* + * First two features are FPU and SSE, which above we handled + * in a special way already: + */ + feature_bit = 0x2; + xfeatures = (xfeatures_mask & ~xfeatures) >> 2; + + /* + * Update all the remaining memory layouts according to their + * standard xstate layout, if their header bit is in the init + * state: + */ + while (xfeatures) { + if (xfeatures & 0x1) { + int offset = xstate_offsets[feature_bit]; + int size = xstate_sizes[feature_bit]; + + memcpy((void *)fx + offset, + (void *)&init_fpstate.xsave + offset, + size); + } + + xfeatures >>= 1; + feature_bit++; + } +} + +/* + * Enable the extended processor state save/restore feature. + * Called once per CPU onlining. + */ +void fpu__init_cpu_xstate(void) +{ + if (!cpu_has_xsave || !xfeatures_mask) + return; + + cr4_set_bits(X86_CR4_OSXSAVE); + xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask); +} + +/* + * Record the offsets and sizes of various xstates contained + * in the XSAVE state memory layout. + * + * ( Note that certain features might be non-present, for them + * we'll have 0 offset and 0 size. ) + */ +static void __init setup_xstate_features(void) +{ + u32 eax, ebx, ecx, edx, leaf; + + xfeatures_nr = fls64(xfeatures_mask); + + for (leaf = 2; leaf < xfeatures_nr; leaf++) { + cpuid_count(XSTATE_CPUID, leaf, &eax, &ebx, &ecx, &edx); + + xstate_offsets[leaf] = ebx; + xstate_sizes[leaf] = eax; + + printk(KERN_INFO "x86/fpu: xstate_offset[%d]: %04x, xstate_sizes[%d]: %04x\n", leaf, ebx, leaf, eax); + } +} + +static void __init print_xstate_feature(u64 xstate_mask) +{ + const char *feature_name; + + if (cpu_has_xfeatures(xstate_mask, &feature_name)) + pr_info("x86/fpu: Supporting XSAVE feature 0x%02Lx: '%s'\n", xstate_mask, feature_name); +} + +/* + * Print out all the supported xstate features: + */ +static void __init print_xstate_features(void) +{ + print_xstate_feature(XSTATE_FP); + print_xstate_feature(XSTATE_SSE); + print_xstate_feature(XSTATE_YMM); + print_xstate_feature(XSTATE_BNDREGS); + print_xstate_feature(XSTATE_BNDCSR); + print_xstate_feature(XSTATE_OPMASK); + print_xstate_feature(XSTATE_ZMM_Hi256); + print_xstate_feature(XSTATE_Hi16_ZMM); +} + +/* + * This function sets up offsets and sizes of all extended states in + * xsave area. This supports both standard format and compacted format + * of the xsave aread. + */ +static void __init setup_xstate_comp(void) +{ + unsigned int xstate_comp_sizes[sizeof(xfeatures_mask)*8]; + int i; + + /* + * The FP xstates and SSE xstates are legacy states. They are always + * in the fixed offsets in the xsave area in either compacted form + * or standard form. + */ + xstate_comp_offsets[0] = 0; + xstate_comp_offsets[1] = offsetof(struct fxregs_state, xmm_space); + + if (!cpu_has_xsaves) { + for (i = 2; i < xfeatures_nr; i++) { + if (test_bit(i, (unsigned long *)&xfeatures_mask)) { + xstate_comp_offsets[i] = xstate_offsets[i]; + xstate_comp_sizes[i] = xstate_sizes[i]; + } + } + return; + } + + xstate_comp_offsets[2] = FXSAVE_SIZE + XSAVE_HDR_SIZE; + + for (i = 2; i < xfeatures_nr; i++) { + if (test_bit(i, (unsigned long *)&xfeatures_mask)) + xstate_comp_sizes[i] = xstate_sizes[i]; + else + xstate_comp_sizes[i] = 0; + + if (i > 2) + xstate_comp_offsets[i] = xstate_comp_offsets[i-1] + + xstate_comp_sizes[i-1]; + + } +} + +/* + * setup the xstate image representing the init state + */ +static void __init setup_init_fpu_buf(void) +{ + static int on_boot_cpu = 1; + + WARN_ON_FPU(!on_boot_cpu); + on_boot_cpu = 0; + + if (!cpu_has_xsave) + return; + + setup_xstate_features(); + print_xstate_features(); + + if (cpu_has_xsaves) { + init_fpstate.xsave.header.xcomp_bv = (u64)1 << 63 | xfeatures_mask; + init_fpstate.xsave.header.xfeatures = xfeatures_mask; + } + + /* + * Init all the features state with header_bv being 0x0 + */ + copy_kernel_to_xregs_booting(&init_fpstate.xsave); + + /* + * Dump the init state again. This is to identify the init state + * of any feature which is not represented by all zero's. + */ + copy_xregs_to_kernel_booting(&init_fpstate.xsave); +} + +/* + * Calculate total size of enabled xstates in XCR0/xfeatures_mask. + */ +static void __init init_xstate_size(void) +{ + unsigned int eax, ebx, ecx, edx; + int i; + + if (!cpu_has_xsaves) { + cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); + xstate_size = ebx; + return; + } + + xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE; + for (i = 2; i < 64; i++) { + if (test_bit(i, (unsigned long *)&xfeatures_mask)) { + cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); + xstate_size += eax; + } + } +} + +/* + * Enable and initialize the xsave feature. + * Called once per system bootup. + */ +void __init fpu__init_system_xstate(void) +{ + unsigned int eax, ebx, ecx, edx; + static int on_boot_cpu = 1; + + WARN_ON_FPU(!on_boot_cpu); + on_boot_cpu = 0; + + if (!cpu_has_xsave) { + pr_info("x86/fpu: Legacy x87 FPU detected.\n"); + return; + } + + if (boot_cpu_data.cpuid_level < XSTATE_CPUID) { + WARN_ON_FPU(1); + return; + } + + cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); + xfeatures_mask = eax + ((u64)edx << 32); + + if ((xfeatures_mask & XSTATE_FPSSE) != XSTATE_FPSSE) { + pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n", xfeatures_mask); + BUG(); + } + + /* Support only the state known to the OS: */ + xfeatures_mask = xfeatures_mask & XCNTXT_MASK; + + /* Enable xstate instructions to be able to continue with initialization: */ + fpu__init_cpu_xstate(); + + /* Recompute the context size for enabled features: */ + init_xstate_size(); + + update_regset_xstate_info(xstate_size, xfeatures_mask); + fpu__init_prepare_fx_sw_frame(); + setup_init_fpu_buf(); + setup_xstate_comp(); + + pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is 0x%x bytes, using '%s' format.\n", + xfeatures_mask, + xstate_size, + cpu_has_xsaves ? "compacted" : "standard"); +} + +/* + * Restore minimal FPU state after suspend: + */ +void fpu__resume_cpu(void) +{ + /* + * Restore XCR0 on xsave capable CPUs: + */ + if (cpu_has_xsave) + xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask); +} + +/* + * Given the xsave area and a state inside, this function returns the + * address of the state. + * + * This is the API that is called to get xstate address in either + * standard format or compacted format of xsave area. + * + * Note that if there is no data for the field in the xsave buffer + * this will return NULL. + * + * Inputs: + * xstate: the thread's storage area for all FPU data + * xstate_feature: state which is defined in xsave.h (e.g. + * XSTATE_FP, XSTATE_SSE, etc...) + * Output: + * address of the state in the xsave area, or NULL if the + * field is not present in the xsave buffer. + */ +void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature) +{ + int feature_nr = fls64(xstate_feature) - 1; + /* + * Do we even *have* xsave state? + */ + if (!boot_cpu_has(X86_FEATURE_XSAVE)) + return NULL; + + xsave = ¤t->thread.fpu.state.xsave; + /* + * We should not ever be requesting features that we + * have not enabled. Remember that pcntxt_mask is + * what we write to the XCR0 register. + */ + WARN_ONCE(!(xfeatures_mask & xstate_feature), + "get of unsupported state"); + /* + * This assumes the last 'xsave*' instruction to + * have requested that 'xstate_feature' be saved. + * If it did not, we might be seeing and old value + * of the field in the buffer. + * + * This can happen because the last 'xsave' did not + * request that this feature be saved (unlikely) + * or because the "init optimization" caused it + * to not be saved. + */ + if (!(xsave->header.xfeatures & xstate_feature)) + return NULL; + + return (void *)xsave + xstate_comp_offsets[feature_nr]; +} +EXPORT_SYMBOL_GPL(get_xsave_addr); + +/* + * This wraps up the common operations that need to occur when retrieving + * data from xsave state. It first ensures that the current task was + * using the FPU and retrieves the data in to a buffer. It then calculates + * the offset of the requested field in the buffer. + * + * This function is safe to call whether the FPU is in use or not. + * + * Note that this only works on the current task. + * + * Inputs: + * @xsave_state: state which is defined in xsave.h (e.g. XSTATE_FP, + * XSTATE_SSE, etc...) + * Output: + * address of the state in the xsave area or NULL if the state + * is not present or is in its 'init state'. + */ +const void *get_xsave_field_ptr(int xsave_state) +{ + struct fpu *fpu = ¤t->thread.fpu; + + if (!fpu->fpstate_active) + return NULL; + /* + * fpu__save() takes the CPU's xstate registers + * and saves them off to the 'fpu memory buffer. + */ + fpu__save(fpu); + + return get_xsave_addr(&fpu->state.xsave, xsave_state); +} diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 7e429c99c..0e2d96ffd 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -557,7 +557,7 @@ early_idt_handler_common: cld cmpl $2,(%esp) # X86_TRAP_NMI - je is_nmi # Ignore NMI + je .Lis_nmi # Ignore NMI cmpl $2,%ss:early_recursion_flag je hlt_loop @@ -610,7 +610,7 @@ ex_entry: pop %ecx pop %eax decl %ss:early_recursion_flag -is_nmi: +.Lis_nmi: addl $8,%esp /* drop vector number and error code */ iret ENDPROC(early_idt_handler_common) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 7e5da2cbe..1d40ca8a7 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -346,7 +346,7 @@ early_idt_handler_common: cld cmpl $2,(%rsp) # X86_TRAP_NMI - je is_nmi # Ignore NMI + je .Lis_nmi # Ignore NMI cmpl $2,early_recursion_flag(%rip) jz 1f @@ -411,7 +411,7 @@ early_idt_handler_common: popq %rcx popq %rax decl early_recursion_flag(%rip) -is_nmi: +.Lis_nmi: addq $16,%rsp # drop vector number and error code INTERRUPT_RETURN ENDPROC(early_idt_handler_common) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 3acbff471..10757d0a3 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -12,6 +12,7 @@ #include <linux/pm.h> #include <linux/io.h> +#include <asm/irqdomain.h> #include <asm/fixmap.h> #include <asm/hpet.h> #include <asm/time.h> @@ -305,8 +306,6 @@ static void hpet_legacy_clockevent_register(void) printk(KERN_DEBUG "hpet clockevent registered\n"); } -static int hpet_setup_msi_irq(unsigned int irq); - static void hpet_set_mode(enum clock_event_mode mode, struct clock_event_device *evt, int timer) { @@ -357,7 +356,7 @@ static void hpet_set_mode(enum clock_event_mode mode, hpet_enable_legacy_int(); } else { struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); - hpet_setup_msi_irq(hdev->irq); + irq_domain_activate_irq(irq_get_irq_data(hdev->irq)); disable_irq(hdev->irq); irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu)); enable_irq(hdev->irq); @@ -423,6 +422,7 @@ static int hpet_legacy_next_event(unsigned long delta, static DEFINE_PER_CPU(struct hpet_dev *, cpu_hpet_dev); static struct hpet_dev *hpet_devs; +static struct irq_domain *hpet_domain; void hpet_msi_unmask(struct irq_data *data) { @@ -473,31 +473,6 @@ static int hpet_msi_next_event(unsigned long delta, return hpet_next_event(delta, evt, hdev->num); } -static int hpet_setup_msi_irq(unsigned int irq) -{ - if (x86_msi.setup_hpet_msi(irq, hpet_blockid)) { - irq_free_hwirq(irq); - return -EINVAL; - } - return 0; -} - -static int hpet_assign_irq(struct hpet_dev *dev) -{ - unsigned int irq = irq_alloc_hwirq(-1); - - if (!irq) - return -EINVAL; - - irq_set_handler_data(irq, dev); - - if (hpet_setup_msi_irq(irq)) - return -EINVAL; - - dev->irq = irq; - return 0; -} - static irqreturn_t hpet_interrupt_handler(int irq, void *data) { struct hpet_dev *dev = (struct hpet_dev *)data; @@ -540,9 +515,6 @@ static void init_one_hpet_msi_clockevent(struct hpet_dev *hdev, int cpu) if (!(hdev->flags & HPET_DEV_VALID)) return; - if (hpet_setup_msi_irq(hdev->irq)) - return; - hdev->cpu = cpu; per_cpu(cpu_hpet_dev, cpu) = hdev; evt->name = hdev->name; @@ -574,7 +546,7 @@ static void hpet_msi_capability_lookup(unsigned int start_timer) unsigned int id; unsigned int num_timers; unsigned int num_timers_used = 0; - int i; + int i, irq; if (hpet_msi_disable) return; @@ -587,6 +559,10 @@ static void hpet_msi_capability_lookup(unsigned int start_timer) num_timers++; /* Value read out starts from 0 */ hpet_print_config(); + hpet_domain = hpet_create_irq_domain(hpet_blockid); + if (!hpet_domain) + return; + hpet_devs = kzalloc(sizeof(struct hpet_dev) * num_timers, GFP_KERNEL); if (!hpet_devs) return; @@ -604,12 +580,14 @@ static void hpet_msi_capability_lookup(unsigned int start_timer) hdev->flags = 0; if (cfg & HPET_TN_PERIODIC_CAP) hdev->flags |= HPET_DEV_PERI_CAP; + sprintf(hdev->name, "hpet%d", i); hdev->num = i; - sprintf(hdev->name, "hpet%d", i); - if (hpet_assign_irq(hdev)) + irq = hpet_assign_irq(hpet_domain, hdev, hdev->num); + if (irq <= 0) continue; + hdev->irq = irq; hdev->flags |= HPET_DEV_FSB_CAP; hdev->flags |= HPET_DEV_VALID; num_timers_used++; @@ -709,10 +687,6 @@ static int hpet_cpuhp_notify(struct notifier_block *n, } #else -static int hpet_setup_msi_irq(unsigned int irq) -{ - return 0; -} static void hpet_msi_capability_lookup(unsigned int start_timer) { return; diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c index 05fd74f53..64341aa48 100644 --- a/arch/x86/kernel/i386_ksyms_32.c +++ b/arch/x86/kernel/i386_ksyms_32.c @@ -40,7 +40,5 @@ EXPORT_SYMBOL(empty_zero_page); #ifdef CONFIG_PREEMPT EXPORT_SYMBOL(___preempt_schedule); -#ifdef CONFIG_CONTEXT_TRACKING -EXPORT_SYMBOL(___preempt_schedule_context); -#endif +EXPORT_SYMBOL(___preempt_schedule_notrace); #endif diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c deleted file mode 100644 index 6185d3141..000000000 --- a/arch/x86/kernel/i387.c +++ /dev/null @@ -1,671 +0,0 @@ -/* - * Copyright (C) 1994 Linus Torvalds - * - * Pentium III FXSR, SSE support - * General FPU state handling cleanups - * Gareth Hughes <gareth@valinux.com>, May 2000 - */ -#include <linux/module.h> -#include <linux/regset.h> -#include <linux/sched.h> -#include <linux/slab.h> - -#include <asm/sigcontext.h> -#include <asm/processor.h> -#include <asm/math_emu.h> -#include <asm/tlbflush.h> -#include <asm/uaccess.h> -#include <asm/ptrace.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> -#include <asm/user.h> - -static DEFINE_PER_CPU(bool, in_kernel_fpu); - -void kernel_fpu_disable(void) -{ - WARN_ON(this_cpu_read(in_kernel_fpu)); - this_cpu_write(in_kernel_fpu, true); -} - -void kernel_fpu_enable(void) -{ - this_cpu_write(in_kernel_fpu, false); -} - -/* - * Were we in an interrupt that interrupted kernel mode? - * - * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that - * pair does nothing at all: the thread must not have fpu (so - * that we don't try to save the FPU state), and TS must - * be set (so that the clts/stts pair does nothing that is - * visible in the interrupted kernel thread). - * - * Except for the eagerfpu case when we return true; in the likely case - * the thread has FPU but we are not going to set/clear TS. - */ -static inline bool interrupted_kernel_fpu_idle(void) -{ - if (this_cpu_read(in_kernel_fpu)) - return false; - - if (use_eager_fpu()) - return true; - - return !__thread_has_fpu(current) && - (read_cr0() & X86_CR0_TS); -} - -/* - * Were we in user mode (or vm86 mode) when we were - * interrupted? - * - * Doing kernel_fpu_begin/end() is ok if we are running - * in an interrupt context from user mode - we'll just - * save the FPU state as required. - */ -static inline bool interrupted_user_mode(void) -{ - struct pt_regs *regs = get_irq_regs(); - return regs && user_mode(regs); -} - -/* - * Can we use the FPU in kernel mode with the - * whole "kernel_fpu_begin/end()" sequence? - * - * It's always ok in process context (ie "not interrupt") - * but it is sometimes ok even from an irq. - */ -bool irq_fpu_usable(void) -{ - return !in_interrupt() || - interrupted_user_mode() || - interrupted_kernel_fpu_idle(); -} -EXPORT_SYMBOL(irq_fpu_usable); - -void __kernel_fpu_begin(void) -{ - struct task_struct *me = current; - - this_cpu_write(in_kernel_fpu, true); - - if (__thread_has_fpu(me)) { - __save_init_fpu(me); - } else { - this_cpu_write(fpu_owner_task, NULL); - if (!use_eager_fpu()) - clts(); - } -} -EXPORT_SYMBOL(__kernel_fpu_begin); - -void __kernel_fpu_end(void) -{ - struct task_struct *me = current; - - if (__thread_has_fpu(me)) { - if (WARN_ON(restore_fpu_checking(me))) - fpu_reset_state(me); - } else if (!use_eager_fpu()) { - stts(); - } - - this_cpu_write(in_kernel_fpu, false); -} -EXPORT_SYMBOL(__kernel_fpu_end); - -void unlazy_fpu(struct task_struct *tsk) -{ - preempt_disable(); - if (__thread_has_fpu(tsk)) { - if (use_eager_fpu()) { - __save_fpu(tsk); - } else { - __save_init_fpu(tsk); - __thread_fpu_end(tsk); - } - } - preempt_enable(); -} -EXPORT_SYMBOL(unlazy_fpu); - -unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; -unsigned int xstate_size; -EXPORT_SYMBOL_GPL(xstate_size); -static struct i387_fxsave_struct fx_scratch; - -static void mxcsr_feature_mask_init(void) -{ - unsigned long mask = 0; - - if (cpu_has_fxsr) { - memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct)); - asm volatile("fxsave %0" : "+m" (fx_scratch)); - mask = fx_scratch.mxcsr_mask; - if (mask == 0) - mask = 0x0000ffbf; - } - mxcsr_feature_mask &= mask; -} - -static void init_thread_xstate(void) -{ - /* - * Note that xstate_size might be overwriten later during - * xsave_init(). - */ - - if (!cpu_has_fpu) { - /* - * Disable xsave as we do not support it if i387 - * emulation is enabled. - */ - setup_clear_cpu_cap(X86_FEATURE_XSAVE); - setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); - xstate_size = sizeof(struct i387_soft_struct); - return; - } - - if (cpu_has_fxsr) - xstate_size = sizeof(struct i387_fxsave_struct); - else - xstate_size = sizeof(struct i387_fsave_struct); - - /* - * Quirk: we don't yet handle the XSAVES* instructions - * correctly, as we don't correctly convert between - * standard and compacted format when interfacing - * with user-space - so disable it for now. - * - * The difference is small: with recent CPUs the - * compacted format is only marginally smaller than - * the standard FPU state format. - * - * ( This is easy to backport while we are fixing - * XSAVES* support. ) - */ - setup_clear_cpu_cap(X86_FEATURE_XSAVES); -} - -/* - * Called at bootup to set up the initial FPU state that is later cloned - * into all processes. - */ - -void fpu_init(void) -{ - unsigned long cr0; - unsigned long cr4_mask = 0; - -#ifndef CONFIG_MATH_EMULATION - if (!cpu_has_fpu) { - pr_emerg("No FPU found and no math emulation present\n"); - pr_emerg("Giving up\n"); - for (;;) - asm volatile("hlt"); - } -#endif - if (cpu_has_fxsr) - cr4_mask |= X86_CR4_OSFXSR; - if (cpu_has_xmm) - cr4_mask |= X86_CR4_OSXMMEXCPT; - if (cr4_mask) - cr4_set_bits(cr4_mask); - - cr0 = read_cr0(); - cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */ - if (!cpu_has_fpu) - cr0 |= X86_CR0_EM; - write_cr0(cr0); - - /* - * init_thread_xstate is only called once to avoid overriding - * xstate_size during boot time or during CPU hotplug. - */ - if (xstate_size == 0) - init_thread_xstate(); - - mxcsr_feature_mask_init(); - xsave_init(); - eager_fpu_init(); -} - -void fpu_finit(struct fpu *fpu) -{ - if (!cpu_has_fpu) { - finit_soft_fpu(&fpu->state->soft); - return; - } - - memset(fpu->state, 0, xstate_size); - - if (cpu_has_fxsr) { - fx_finit(&fpu->state->fxsave); - } else { - struct i387_fsave_struct *fp = &fpu->state->fsave; - fp->cwd = 0xffff037fu; - fp->swd = 0xffff0000u; - fp->twd = 0xffffffffu; - fp->fos = 0xffff0000u; - } -} -EXPORT_SYMBOL_GPL(fpu_finit); - -/* - * The _current_ task is using the FPU for the first time - * so initialize it and set the mxcsr to its default - * value at reset if we support XMM instructions and then - * remember the current task has used the FPU. - */ -int init_fpu(struct task_struct *tsk) -{ - int ret; - - if (tsk_used_math(tsk)) { - if (cpu_has_fpu && tsk == current) - unlazy_fpu(tsk); - task_disable_lazy_fpu_restore(tsk); - return 0; - } - - /* - * Memory allocation at the first usage of the FPU and other state. - */ - ret = fpu_alloc(&tsk->thread.fpu); - if (ret) - return ret; - - fpu_finit(&tsk->thread.fpu); - - set_stopped_child_used_math(tsk); - return 0; -} -EXPORT_SYMBOL_GPL(init_fpu); - -/* - * The xstateregs_active() routine is the same as the fpregs_active() routine, - * as the "regset->n" for the xstate regset will be updated based on the feature - * capabilites supported by the xsave. - */ -int fpregs_active(struct task_struct *target, const struct user_regset *regset) -{ - return tsk_used_math(target) ? regset->n : 0; -} - -int xfpregs_active(struct task_struct *target, const struct user_regset *regset) -{ - return (cpu_has_fxsr && tsk_used_math(target)) ? regset->n : 0; -} - -int xfpregs_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) -{ - int ret; - - if (!cpu_has_fxsr) - return -ENODEV; - - ret = init_fpu(target); - if (ret) - return ret; - - sanitize_i387_state(target); - - return user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu.state->fxsave, 0, -1); -} - -int xfpregs_set(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) -{ - int ret; - - if (!cpu_has_fxsr) - return -ENODEV; - - ret = init_fpu(target); - if (ret) - return ret; - - sanitize_i387_state(target); - - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu.state->fxsave, 0, -1); - - /* - * mxcsr reserved bits must be masked to zero for security reasons. - */ - target->thread.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask; - - /* - * update the header bits in the xsave header, indicating the - * presence of FP and SSE state. - */ - if (cpu_has_xsave) - target->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE; - - return ret; -} - -int xstateregs_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) -{ - struct xsave_struct *xsave; - int ret; - - if (!cpu_has_xsave) - return -ENODEV; - - ret = init_fpu(target); - if (ret) - return ret; - - xsave = &target->thread.fpu.state->xsave; - - /* - * Copy the 48bytes defined by the software first into the xstate - * memory layout in the thread struct, so that we can copy the entire - * xstateregs to the user using one user_regset_copyout(). - */ - memcpy(&xsave->i387.sw_reserved, - xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes)); - /* - * Copy the xstate memory layout. - */ - ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); - return ret; -} - -int xstateregs_set(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) -{ - struct xsave_struct *xsave; - int ret; - - if (!cpu_has_xsave) - return -ENODEV; - - ret = init_fpu(target); - if (ret) - return ret; - - xsave = &target->thread.fpu.state->xsave; - - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); - /* - * mxcsr reserved bits must be masked to zero for security reasons. - */ - xsave->i387.mxcsr &= mxcsr_feature_mask; - xsave->xsave_hdr.xstate_bv &= pcntxt_mask; - /* - * These bits must be zero. - */ - memset(&xsave->xsave_hdr.reserved, 0, 48); - return ret; -} - -#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION - -/* - * FPU tag word conversions. - */ - -static inline unsigned short twd_i387_to_fxsr(unsigned short twd) -{ - unsigned int tmp; /* to avoid 16 bit prefixes in the code */ - - /* Transform each pair of bits into 01 (valid) or 00 (empty) */ - tmp = ~twd; - tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */ - /* and move the valid bits to the lower byte. */ - tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */ - tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */ - tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */ - - return tmp; -} - -#define FPREG_ADDR(f, n) ((void *)&(f)->st_space + (n) * 16) -#define FP_EXP_TAG_VALID 0 -#define FP_EXP_TAG_ZERO 1 -#define FP_EXP_TAG_SPECIAL 2 -#define FP_EXP_TAG_EMPTY 3 - -static inline u32 twd_fxsr_to_i387(struct i387_fxsave_struct *fxsave) -{ - struct _fpxreg *st; - u32 tos = (fxsave->swd >> 11) & 7; - u32 twd = (unsigned long) fxsave->twd; - u32 tag; - u32 ret = 0xffff0000u; - int i; - - for (i = 0; i < 8; i++, twd >>= 1) { - if (twd & 0x1) { - st = FPREG_ADDR(fxsave, (i - tos) & 7); - - switch (st->exponent & 0x7fff) { - case 0x7fff: - tag = FP_EXP_TAG_SPECIAL; - break; - case 0x0000: - if (!st->significand[0] && - !st->significand[1] && - !st->significand[2] && - !st->significand[3]) - tag = FP_EXP_TAG_ZERO; - else - tag = FP_EXP_TAG_SPECIAL; - break; - default: - if (st->significand[3] & 0x8000) - tag = FP_EXP_TAG_VALID; - else - tag = FP_EXP_TAG_SPECIAL; - break; - } - } else { - tag = FP_EXP_TAG_EMPTY; - } - ret |= tag << (2 * i); - } - return ret; -} - -/* - * FXSR floating point environment conversions. - */ - -void -convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk) -{ - struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave; - struct _fpreg *to = (struct _fpreg *) &env->st_space[0]; - struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0]; - int i; - - env->cwd = fxsave->cwd | 0xffff0000u; - env->swd = fxsave->swd | 0xffff0000u; - env->twd = twd_fxsr_to_i387(fxsave); - -#ifdef CONFIG_X86_64 - env->fip = fxsave->rip; - env->foo = fxsave->rdp; - /* - * should be actually ds/cs at fpu exception time, but - * that information is not available in 64bit mode. - */ - env->fcs = task_pt_regs(tsk)->cs; - if (tsk == current) { - savesegment(ds, env->fos); - } else { - env->fos = tsk->thread.ds; - } - env->fos |= 0xffff0000; -#else - env->fip = fxsave->fip; - env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16); - env->foo = fxsave->foo; - env->fos = fxsave->fos; -#endif - - for (i = 0; i < 8; ++i) - memcpy(&to[i], &from[i], sizeof(to[0])); -} - -void convert_to_fxsr(struct task_struct *tsk, - const struct user_i387_ia32_struct *env) - -{ - struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave; - struct _fpreg *from = (struct _fpreg *) &env->st_space[0]; - struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0]; - int i; - - fxsave->cwd = env->cwd; - fxsave->swd = env->swd; - fxsave->twd = twd_i387_to_fxsr(env->twd); - fxsave->fop = (u16) ((u32) env->fcs >> 16); -#ifdef CONFIG_X86_64 - fxsave->rip = env->fip; - fxsave->rdp = env->foo; - /* cs and ds ignored */ -#else - fxsave->fip = env->fip; - fxsave->fcs = (env->fcs & 0xffff); - fxsave->foo = env->foo; - fxsave->fos = env->fos; -#endif - - for (i = 0; i < 8; ++i) - memcpy(&to[i], &from[i], sizeof(from[0])); -} - -int fpregs_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) -{ - struct user_i387_ia32_struct env; - int ret; - - ret = init_fpu(target); - if (ret) - return ret; - - if (!static_cpu_has(X86_FEATURE_FPU)) - return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); - - if (!cpu_has_fxsr) - return user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu.state->fsave, 0, - -1); - - sanitize_i387_state(target); - - if (kbuf && pos == 0 && count == sizeof(env)) { - convert_from_fxsr(kbuf, target); - return 0; - } - - convert_from_fxsr(&env, target); - - return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &env, 0, -1); -} - -int fpregs_set(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) -{ - struct user_i387_ia32_struct env; - int ret; - - ret = init_fpu(target); - if (ret) - return ret; - - sanitize_i387_state(target); - - if (!static_cpu_has(X86_FEATURE_FPU)) - return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); - - if (!cpu_has_fxsr) - return user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu.state->fsave, 0, - -1); - - if (pos > 0 || count < sizeof(env)) - convert_from_fxsr(&env, target); - - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1); - if (!ret) - convert_to_fxsr(target, &env); - - /* - * update the header bit in the xsave header, indicating the - * presence of FP. - */ - if (cpu_has_xsave) - target->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FP; - return ret; -} - -/* - * FPU state for core dumps. - * This is only used for a.out dumps now. - * It is declared generically using elf_fpregset_t (which is - * struct user_i387_struct) but is in fact only used for 32-bit - * dumps, so on 64-bit it is really struct user_i387_ia32_struct. - */ -int dump_fpu(struct pt_regs *regs, struct user_i387_struct *fpu) -{ - struct task_struct *tsk = current; - int fpvalid; - - fpvalid = !!used_math(); - if (fpvalid) - fpvalid = !fpregs_get(tsk, NULL, - 0, sizeof(struct user_i387_ia32_struct), - fpu, NULL); - - return fpvalid; -} -EXPORT_SYMBOL(dump_fpu); - -#endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */ - -static int __init no_387(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_FPU); - return 1; -} - -__setup("no387", no_387); - -void fpu_detect(struct cpuinfo_x86 *c) -{ - unsigned long cr0; - u16 fsw, fcw; - - fsw = fcw = 0xffff; - - cr0 = read_cr0(); - cr0 &= ~(X86_CR0_TS | X86_CR0_EM); - write_cr0(cr0); - - asm volatile("fninit ; fnstsw %0 ; fnstcw %1" - : "+m" (fsw), "+m" (fcw)); - - if (fsw == 0 && (fcw & 0x103f) == 0x003f) - set_cpu_cap(c, X86_FEATURE_FPU); - else - clear_cpu_cap(c, X86_FEATURE_FPU); - - /* The final cr0 value is set in fpu_init() */ -} diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index e7cc5370c..16cb827a5 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -329,8 +329,8 @@ static void init_8259A(int auto_eoi) */ outb_pic(0x11, PIC_MASTER_CMD); /* ICW1: select 8259A-1 init */ - /* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 */ - outb_pic(IRQ0_VECTOR, PIC_MASTER_IMR); + /* ICW2: 8259A-1 IR0-7 mapped to ISA_IRQ_VECTOR(0) */ + outb_pic(ISA_IRQ_VECTOR(0), PIC_MASTER_IMR); /* 8259A-1 (the master) has a slave on IR2 */ outb_pic(1U << PIC_CASCADE_IR, PIC_MASTER_IMR); @@ -342,8 +342,8 @@ static void init_8259A(int auto_eoi) outb_pic(0x11, PIC_SLAVE_CMD); /* ICW1: select 8259A-2 init */ - /* ICW2: 8259A-2 IR0-7 mapped to IRQ8_VECTOR */ - outb_pic(IRQ8_VECTOR, PIC_SLAVE_IMR); + /* ICW2: 8259A-2 IR0-7 mapped to ISA_IRQ_VECTOR(8) */ + outb_pic(ISA_IRQ_VECTOR(8), PIC_SLAVE_IMR); /* 8259A-2 is a slave on master's IR2 */ outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR); /* (slave's support for AEOI in flat mode is to be investigated) */ diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 816f81544..37dae792d 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -28,18 +28,8 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) if ((from + num <= from) || (from + num > IO_BITMAP_BITS)) return -EINVAL; -#ifdef CONFIG_SCHED_BFS_AUTOISO - if (turn_on) { - struct sched_param param = { .sched_priority = 0 }; - if (!capable(CAP_SYS_RAWIO)) - return -EPERM; - /* Start X as SCHED_ISO */ - sched_setscheduler_nocheck(current, SCHED_ISO, ¶m); - } -#else if (turn_on && !capable(CAP_SYS_RAWIO)) return -EPERM; -#endif /* * If it's the first ioperm() call in this thread's lifetime, set the @@ -113,15 +103,8 @@ SYSCALL_DEFINE1(iopl, unsigned int, level) return -EINVAL; /* Trying to gain more privileges? */ if (level > old) { -#ifdef CONFIG_SCHED_BFS_AUTOISO - struct sched_param param = { .sched_priority = 0 }; -#endif if (!capable(CAP_SYS_RAWIO)) return -EPERM; -#ifdef CONFIG_SCHED_BFS_AUTOISO - /* Start X as SCHED_ISO */ - sched_setscheduler_nocheck(current, SCHED_ISO, ¶m); -#endif } regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) | (level << 12); t->iopl = level << 12; diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index e5952c225..c7dfe1be7 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -22,6 +22,12 @@ #define CREATE_TRACE_POINTS #include <asm/trace/irq_vectors.h> +DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); +EXPORT_PER_CPU_SYMBOL(irq_stat); + +DEFINE_PER_CPU(struct pt_regs *, irq_regs); +EXPORT_PER_CPU_SYMBOL(irq_regs); + atomic_t irq_err_count; /* Function pointer for generic interrupt vector handling */ @@ -116,6 +122,12 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_printf(p, "%10u ", irq_stats(j)->irq_threshold_count); seq_puts(p, " Threshold APIC interrupts\n"); #endif +#ifdef CONFIG_X86_MCE_AMD + seq_printf(p, "%*s: ", prec, "DFR"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", irq_stats(j)->irq_deferred_error_count); + seq_puts(p, " Deferred Error APIC interrupts\n"); +#endif #ifdef CONFIG_X86_MCE seq_printf(p, "%*s: ", prec, "MCE"); for_each_online_cpu(j) @@ -136,6 +148,18 @@ int arch_show_interrupts(struct seq_file *p, int prec) #if defined(CONFIG_X86_IO_APIC) seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count)); #endif +#ifdef CONFIG_HAVE_KVM + seq_printf(p, "%*s: ", prec, "PIN"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", irq_stats(j)->kvm_posted_intr_ipis); + seq_puts(p, " Posted-interrupt notification event\n"); + + seq_printf(p, "%*s: ", prec, "PIW"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", + irq_stats(j)->kvm_posted_intr_wakeup_ipis); + seq_puts(p, " Posted-interrupt wakeup event\n"); +#endif return 0; } @@ -192,8 +216,7 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs) unsigned vector = ~regs->orig_ax; unsigned irq; - irq_enter(); - exit_idle(); + entering_irq(); irq = __this_cpu_read(vector_irq[vector]); @@ -209,7 +232,7 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs) } } - irq_exit(); + exiting_irq(); set_irq_regs(old_regs); return 1; @@ -237,6 +260,18 @@ __visible void smp_x86_platform_ipi(struct pt_regs *regs) } #ifdef CONFIG_HAVE_KVM +static void dummy_handler(void) {} +static void (*kvm_posted_intr_wakeup_handler)(void) = dummy_handler; + +void kvm_set_posted_intr_wakeup_handler(void (*handler)(void)) +{ + if (handler) + kvm_posted_intr_wakeup_handler = handler; + else + kvm_posted_intr_wakeup_handler = dummy_handler; +} +EXPORT_SYMBOL_GPL(kvm_set_posted_intr_wakeup_handler); + /* * Handler for POSTED_INTERRUPT_VECTOR. */ @@ -244,16 +279,23 @@ __visible void smp_kvm_posted_intr_ipi(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); - ack_APIC_irq(); - - irq_enter(); - - exit_idle(); - + entering_ack_irq(); inc_irq_stat(kvm_posted_intr_ipis); + exiting_irq(); + set_irq_regs(old_regs); +} - irq_exit(); +/* + * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR. + */ +__visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + entering_ack_irq(); + inc_irq_stat(kvm_posted_intr_wakeup_ipis); + kvm_posted_intr_wakeup_handler(); + exiting_irq(); set_irq_regs(old_regs); } #endif @@ -305,14 +347,22 @@ int check_irq_vectors_for_cpu_disable(void) if (!desc) continue; + /* + * Protect against concurrent action removal, + * affinity changes etc. + */ + raw_spin_lock(&desc->lock); data = irq_desc_get_irq_data(desc); cpumask_copy(&affinity_new, data->affinity); cpumask_clear_cpu(this_cpu, &affinity_new); /* Do not count inactive or per-cpu irqs. */ - if (!irq_has_action(irq) || irqd_is_per_cpu(data)) + if (!irq_has_action(irq) || irqd_is_per_cpu(data)) { + raw_spin_unlock(&desc->lock); continue; + } + raw_spin_unlock(&desc->lock); /* * A single irq may be mapped to multiple * cpu's vector_irq[] (for example IOAPIC cluster @@ -343,6 +393,9 @@ int check_irq_vectors_for_cpu_disable(void) * vector. If the vector is marked in the used vectors * bitmap or an irq is assigned to it, we don't count * it as available. + * + * As this is an inaccurate snapshot anyway, we can do + * this w/o holding vector_lock. */ for (vector = FIRST_EXTERNAL_VECTOR; vector < first_system_vector; vector++) { @@ -444,6 +497,11 @@ void fixup_irqs(void) */ mdelay(1); + /* + * We can walk the vector array of this cpu without holding + * vector_lock because the cpu is already marked !online, so + * nothing else will touch it. + */ for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { unsigned int irr; @@ -455,9 +513,9 @@ void fixup_irqs(void) irq = __this_cpu_read(vector_irq[vector]); desc = irq_to_desc(irq); + raw_spin_lock(&desc->lock); data = irq_desc_get_irq_data(desc); chip = irq_data_get_irq_chip(data); - raw_spin_lock(&desc->lock); if (chip->irq_retrigger) { chip->irq_retrigger(data); __this_cpu_write(vector_irq[vector], VECTOR_RETRIGGERED); diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index f9fd86a7f..cd74f5978 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -21,12 +21,6 @@ #include <asm/apic.h> -DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); -EXPORT_PER_CPU_SYMBOL(irq_stat); - -DEFINE_PER_CPU(struct pt_regs *, irq_regs); -EXPORT_PER_CPU_SYMBOL(irq_regs); - #ifdef CONFIG_DEBUG_STACKOVERFLOW int sysctl_panic_on_stackoverflow __read_mostly; diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 394e643d7..bc4604e50 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -20,12 +20,6 @@ #include <asm/idle.h> #include <asm/apic.h> -DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); -EXPORT_PER_CPU_SYMBOL(irq_stat); - -DEFINE_PER_CPU(struct pt_regs *, irq_regs); -EXPORT_PER_CPU_SYMBOL(irq_regs); - int sysctl_panic_on_stackoverflow; /* diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c index 15d741ddf..dc5fa6a1e 100644 --- a/arch/x86/kernel/irq_work.c +++ b/arch/x86/kernel/irq_work.c @@ -10,12 +10,6 @@ #include <asm/apic.h> #include <asm/trace/irq_vectors.h> -static inline void irq_work_entering_irq(void) -{ - irq_enter(); - ack_APIC_irq(); -} - static inline void __smp_irq_work_interrupt(void) { inc_irq_stat(apic_irq_work_irqs); @@ -24,14 +18,14 @@ static inline void __smp_irq_work_interrupt(void) __visible void smp_irq_work_interrupt(struct pt_regs *regs) { - irq_work_entering_irq(); + ipi_entering_ack_irq(); __smp_irq_work_interrupt(); exiting_irq(); } __visible void smp_trace_irq_work_interrupt(struct pt_regs *regs) { - irq_work_entering_irq(); + ipi_entering_ack_irq(); trace_irq_work_entry(IRQ_WORK_VECTOR); __smp_irq_work_interrupt(); trace_irq_work_exit(IRQ_WORK_VECTOR); diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index cd10a6437..a3a5e158e 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -86,7 +86,7 @@ void __init init_IRQ(void) int i; /* - * On cpu 0, Assign IRQ0_VECTOR..IRQ15_VECTOR's to IRQ 0..15. + * On cpu 0, Assign ISA_IRQ_VECTOR(irq) to IRQ 0..15. * If these IRQ's are handled by legacy interrupt-controllers like PIC, * then this configuration will likely be static after the boot. If * these IRQ's are handled by more mordern controllers like IO-APIC, @@ -94,7 +94,7 @@ void __init init_IRQ(void) * irq's migrate etc. */ for (i = 0; i < nr_legacy_irqs(); i++) - per_cpu(vector_irq, 0)[IRQ0_VECTOR + i] = i; + per_cpu(vector_irq, 0)[ISA_IRQ_VECTOR(i)] = i; x86_init.irqs.intr_init(); } @@ -135,6 +135,10 @@ static void __init apic_intr_init(void) alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt); #endif +#ifdef CONFIG_X86_MCE_AMD + alloc_intr_gate(DEFERRED_ERROR_VECTOR, deferred_error_interrupt); +#endif + #ifdef CONFIG_X86_LOCAL_APIC /* self generated IPI for local APIC timer */ alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt); @@ -144,6 +148,8 @@ static void __init apic_intr_init(void) #ifdef CONFIG_HAVE_KVM /* IPI for KVM to deliver posted interrupt */ alloc_intr_gate(POSTED_INTR_VECTOR, kvm_posted_intr_ipi); + /* IPI for KVM to deliver interrupt to wake up tasks */ + alloc_intr_gate(POSTED_INTR_WAKEUP_VECTOR, kvm_posted_intr_wakeup_ipi); #endif /* IPI vectors for APIC spurious and error interrupts */ diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index ca05f8648..ca83f7ac3 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -72,15 +72,16 @@ static int setup_cmdline(struct kimage *image, struct boot_params *params, unsigned long cmdline_len) { char *cmdline_ptr = ((char *)params) + cmdline_offset; - unsigned long cmdline_ptr_phys, len; + unsigned long cmdline_ptr_phys, len = 0; uint32_t cmdline_low_32, cmdline_ext_32; - memcpy(cmdline_ptr, cmdline, cmdline_len); if (image->type == KEXEC_TYPE_CRASH) { - len = sprintf(cmdline_ptr + cmdline_len - 1, - " elfcorehdr=0x%lx", image->arch.elf_load_addr); - cmdline_len += len; + len = sprintf(cmdline_ptr, + "elfcorehdr=0x%lx ", image->arch.elf_load_addr); } + memcpy(cmdline_ptr + len, cmdline, cmdline_len); + cmdline_len += len; + cmdline_ptr[cmdline_len - 1] = '\0'; pr_debug("Final command line is: %s\n", cmdline_ptr); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 943562006..47190bd39 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -331,7 +331,7 @@ static void kvm_guest_apic_eoi_write(u32 reg, u32 val) apic_write(APIC_EOI, APIC_EOI_ACK); } -void kvm_guest_cpu_init(void) +static void kvm_guest_cpu_init(void) { if (!kvm_para_available()) return; @@ -584,6 +584,39 @@ static void kvm_kick_cpu(int cpu) kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid); } + +#ifdef CONFIG_QUEUED_SPINLOCKS + +#include <asm/qspinlock.h> + +static void kvm_wait(u8 *ptr, u8 val) +{ + unsigned long flags; + + if (in_nmi()) + return; + + local_irq_save(flags); + + if (READ_ONCE(*ptr) != val) + goto out; + + /* + * halt until it's our turn and kicked. Note that we do safe halt + * for irq enabled case to avoid hang when lock info is overwritten + * in irq spinlock slowpath and no spurious interrupt occur to save us. + */ + if (arch_irqs_disabled_flags(flags)) + halt(); + else + safe_halt(); + +out: + local_irq_restore(flags); +} + +#else /* !CONFIG_QUEUED_SPINLOCKS */ + enum kvm_contention_stat { TAKEN_SLOW, TAKEN_SLOW_PICKUP, @@ -655,7 +688,7 @@ static inline void spin_time_accum_blocked(u64 start) static struct dentry *d_spin_debug; static struct dentry *d_kvm_debug; -struct dentry *kvm_init_debugfs(void) +static struct dentry *kvm_init_debugfs(void) { d_kvm_debug = debugfs_create_dir("kvm-guest", NULL); if (!d_kvm_debug) @@ -817,6 +850,8 @@ static void kvm_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket) } } +#endif /* !CONFIG_QUEUED_SPINLOCKS */ + /* * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present. */ @@ -828,8 +863,16 @@ void __init kvm_spinlock_init(void) if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) return; +#ifdef CONFIG_QUEUED_SPINLOCKS + __pv_init_lock_hash(); + pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath; + pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock); + pv_lock_ops.wait = kvm_wait; + pv_lock_ops.kick = kvm_kick_cpu; +#else /* !CONFIG_QUEUED_SPINLOCKS */ pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning); pv_lock_ops.unlock_kick = kvm_unlock_kick; +#endif } static __init int kvm_spinlock_init_jump(void) diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 42caaef89..49487b488 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -24,6 +24,7 @@ #include <linux/percpu.h> #include <linux/hardirq.h> #include <linux/memblock.h> +#include <linux/sched.h> #include <asm/x86_init.h> #include <asm/reboot.h> @@ -217,8 +218,10 @@ static void kvm_shutdown(void) void __init kvmclock_init(void) { + struct pvclock_vcpu_time_info *vcpu_time; unsigned long mem; - int size; + int size, cpu; + u8 flags; size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS); @@ -264,7 +267,14 @@ void __init kvmclock_init(void) pv_info.name = "KVM"; if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) - pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT); + pvclock_set_flags(~0); + + cpu = get_cpu(); + vcpu_time = &hv_clock[cpu].pvti; + flags = pvclock_read_flags(vcpu_time); + if (flags & PVCLOCK_COUNTS_FROM_ZERO) + set_sched_clock_stable(); + put_cpu(); } int __init kvm_setup_vsyscall_timeinfo(void) diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index c37886d75..2bcc0525f 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -12,6 +12,7 @@ #include <linux/string.h> #include <linux/mm.h> #include <linux/smp.h> +#include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> @@ -20,82 +21,82 @@ #include <asm/mmu_context.h> #include <asm/syscalls.h> -#ifdef CONFIG_SMP +/* context.lock is held for us, so we don't need any locking. */ static void flush_ldt(void *current_mm) { - if (current->active_mm == current_mm) - load_LDT(¤t->active_mm->context); + mm_context_t *pc; + + if (current->active_mm != current_mm) + return; + + pc = ¤t->active_mm->context; + set_ldt(pc->ldt->entries, pc->ldt->size); } -#endif -static int alloc_ldt(mm_context_t *pc, int mincount, int reload) +/* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */ +static struct ldt_struct *alloc_ldt_struct(int size) { - void *oldldt, *newldt; - int oldsize; - - if (mincount <= pc->size) - return 0; - oldsize = pc->size; - mincount = (mincount + (PAGE_SIZE / LDT_ENTRY_SIZE - 1)) & - (~(PAGE_SIZE / LDT_ENTRY_SIZE - 1)); - if (mincount * LDT_ENTRY_SIZE > PAGE_SIZE) - newldt = vmalloc(mincount * LDT_ENTRY_SIZE); + struct ldt_struct *new_ldt; + int alloc_size; + + if (size > LDT_ENTRIES) + return NULL; + + new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL); + if (!new_ldt) + return NULL; + + BUILD_BUG_ON(LDT_ENTRY_SIZE != sizeof(struct desc_struct)); + alloc_size = size * LDT_ENTRY_SIZE; + + /* + * Xen is very picky: it requires a page-aligned LDT that has no + * trailing nonzero bytes in any page that contains LDT descriptors. + * Keep it simple: zero the whole allocation and never allocate less + * than PAGE_SIZE. + */ + if (alloc_size > PAGE_SIZE) + new_ldt->entries = vzalloc(alloc_size); else - newldt = (void *)__get_free_page(GFP_KERNEL); - - if (!newldt) - return -ENOMEM; + new_ldt->entries = kzalloc(PAGE_SIZE, GFP_KERNEL); - if (oldsize) - memcpy(newldt, pc->ldt, oldsize * LDT_ENTRY_SIZE); - oldldt = pc->ldt; - memset(newldt + oldsize * LDT_ENTRY_SIZE, 0, - (mincount - oldsize) * LDT_ENTRY_SIZE); + if (!new_ldt->entries) { + kfree(new_ldt); + return NULL; + } - paravirt_alloc_ldt(newldt, mincount); + new_ldt->size = size; + return new_ldt; +} -#ifdef CONFIG_X86_64 - /* CHECKME: Do we really need this ? */ - wmb(); -#endif - pc->ldt = newldt; - wmb(); - pc->size = mincount; - wmb(); - - if (reload) { -#ifdef CONFIG_SMP - preempt_disable(); - load_LDT(pc); - if (!cpumask_equal(mm_cpumask(current->mm), - cpumask_of(smp_processor_id()))) - smp_call_function(flush_ldt, current->mm, 1); - preempt_enable(); -#else - load_LDT(pc); -#endif - } - if (oldsize) { - paravirt_free_ldt(oldldt, oldsize); - if (oldsize * LDT_ENTRY_SIZE > PAGE_SIZE) - vfree(oldldt); - else - put_page(virt_to_page(oldldt)); - } - return 0; +/* After calling this, the LDT is immutable. */ +static void finalize_ldt_struct(struct ldt_struct *ldt) +{ + paravirt_alloc_ldt(ldt->entries, ldt->size); } -static inline int copy_ldt(mm_context_t *new, mm_context_t *old) +/* context.lock is held */ +static void install_ldt(struct mm_struct *current_mm, + struct ldt_struct *ldt) { - int err = alloc_ldt(new, old->size, 0); - int i; + /* Synchronizes with lockless_dereference in load_mm_ldt. */ + smp_store_release(¤t_mm->context.ldt, ldt); + + /* Activate the LDT for all CPUs using current_mm. */ + on_each_cpu_mask(mm_cpumask(current_mm), flush_ldt, current_mm, true); +} - if (err < 0) - return err; +static void free_ldt_struct(struct ldt_struct *ldt) +{ + if (likely(!ldt)) + return; - for (i = 0; i < old->size; i++) - write_ldt_entry(new->ldt, i, old->ldt + i * LDT_ENTRY_SIZE); - return 0; + paravirt_free_ldt(ldt->entries, ldt->size); + if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE) + vfree(ldt->entries); + else + kfree(ldt->entries); + kfree(ldt); } /* @@ -104,17 +105,37 @@ static inline int copy_ldt(mm_context_t *new, mm_context_t *old) */ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { + struct ldt_struct *new_ldt; struct mm_struct *old_mm; int retval = 0; mutex_init(&mm->context.lock); - mm->context.size = 0; old_mm = current->mm; - if (old_mm && old_mm->context.size > 0) { - mutex_lock(&old_mm->context.lock); - retval = copy_ldt(&mm->context, &old_mm->context); - mutex_unlock(&old_mm->context.lock); + if (!old_mm) { + mm->context.ldt = NULL; + return 0; } + + mutex_lock(&old_mm->context.lock); + if (!old_mm->context.ldt) { + mm->context.ldt = NULL; + goto out_unlock; + } + + new_ldt = alloc_ldt_struct(old_mm->context.ldt->size); + if (!new_ldt) { + retval = -ENOMEM; + goto out_unlock; + } + + memcpy(new_ldt->entries, old_mm->context.ldt->entries, + new_ldt->size * LDT_ENTRY_SIZE); + finalize_ldt_struct(new_ldt); + + mm->context.ldt = new_ldt; + +out_unlock: + mutex_unlock(&old_mm->context.lock); return retval; } @@ -125,53 +146,47 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) */ void destroy_context(struct mm_struct *mm) { - if (mm->context.size) { -#ifdef CONFIG_X86_32 - /* CHECKME: Can this ever happen ? */ - if (mm == current->active_mm) - clear_LDT(); -#endif - paravirt_free_ldt(mm->context.ldt, mm->context.size); - if (mm->context.size * LDT_ENTRY_SIZE > PAGE_SIZE) - vfree(mm->context.ldt); - else - put_page(virt_to_page(mm->context.ldt)); - mm->context.size = 0; - } + free_ldt_struct(mm->context.ldt); + mm->context.ldt = NULL; } static int read_ldt(void __user *ptr, unsigned long bytecount) { - int err; + int retval; unsigned long size; struct mm_struct *mm = current->mm; - if (!mm->context.size) - return 0; + mutex_lock(&mm->context.lock); + + if (!mm->context.ldt) { + retval = 0; + goto out_unlock; + } + if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES) bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES; - mutex_lock(&mm->context.lock); - size = mm->context.size * LDT_ENTRY_SIZE; + size = mm->context.ldt->size * LDT_ENTRY_SIZE; if (size > bytecount) size = bytecount; - err = 0; - if (copy_to_user(ptr, mm->context.ldt, size)) - err = -EFAULT; - mutex_unlock(&mm->context.lock); - if (err < 0) - goto error_return; + if (copy_to_user(ptr, mm->context.ldt->entries, size)) { + retval = -EFAULT; + goto out_unlock; + } + if (size != bytecount) { - /* zero-fill the rest */ - if (clear_user(ptr + size, bytecount - size) != 0) { - err = -EFAULT; - goto error_return; + /* Zero-fill the rest and pretend we read bytecount bytes. */ + if (clear_user(ptr + size, bytecount - size)) { + retval = -EFAULT; + goto out_unlock; } } - return bytecount; -error_return: - return err; + retval = bytecount; + +out_unlock: + mutex_unlock(&mm->context.lock); + return retval; } static int read_default_ldt(void __user *ptr, unsigned long bytecount) @@ -195,6 +210,8 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) struct desc_struct ldt; int error; struct user_desc ldt_info; + int oldsize, newsize; + struct ldt_struct *new_ldt, *old_ldt; error = -EINVAL; if (bytecount != sizeof(ldt_info)) @@ -213,34 +230,39 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) goto out; } - mutex_lock(&mm->context.lock); - if (ldt_info.entry_number >= mm->context.size) { - error = alloc_ldt(¤t->mm->context, - ldt_info.entry_number + 1, 1); - if (error < 0) - goto out_unlock; - } - - /* Allow LDTs to be cleared by the user. */ - if (ldt_info.base_addr == 0 && ldt_info.limit == 0) { - if (oldmode || LDT_empty(&ldt_info)) { - memset(&ldt, 0, sizeof(ldt)); - goto install; + if ((oldmode && !ldt_info.base_addr && !ldt_info.limit) || + LDT_empty(&ldt_info)) { + /* The user wants to clear the entry. */ + memset(&ldt, 0, sizeof(ldt)); + } else { + if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { + error = -EINVAL; + goto out; } + + fill_ldt(&ldt, &ldt_info); + if (oldmode) + ldt.avl = 0; } - if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { - error = -EINVAL; + mutex_lock(&mm->context.lock); + + old_ldt = mm->context.ldt; + oldsize = old_ldt ? old_ldt->size : 0; + newsize = max((int)(ldt_info.entry_number + 1), oldsize); + + error = -ENOMEM; + new_ldt = alloc_ldt_struct(newsize); + if (!new_ldt) goto out_unlock; - } - fill_ldt(&ldt, &ldt_info); - if (oldmode) - ldt.avl = 0; + if (old_ldt) + memcpy(new_ldt->entries, old_ldt->entries, oldsize * LDT_ENTRY_SIZE); + new_ldt->entries[ldt_info.entry_number] = ldt; + finalize_ldt_struct(new_ldt); - /* Install the new entry ... */ -install: - write_ldt_entry(mm->context.ldt, ldt_info.entry_number, &ldt); + install_ldt(mm, new_ldt); + free_ldt_struct(old_ldt); error = 0; out_unlock: diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 415480d3e..819ab3f9c 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -17,6 +17,7 @@ #include <linux/ftrace.h> #include <linux/io.h> #include <linux/suspend.h> +#include <linux/vmalloc.h> #include <asm/init.h> #include <asm/pgtable.h> @@ -25,6 +26,7 @@ #include <asm/io_apic.h> #include <asm/debugreg.h> #include <asm/kexec-bzimage64.h> +#include <asm/setup.h> #ifdef CONFIG_KEXEC_FILE static struct kexec_file_ops *kexec_file_loaders[] = { @@ -334,7 +336,7 @@ void arch_crash_save_vmcoreinfo(void) VMCOREINFO_LENGTH(node_data, MAX_NUMNODES); #endif vmcoreinfo_append_str("KERNELOFFSET=%lx\n", - (unsigned long)&_text - __START_KERNEL); + kaslr_offset()); } /* arch-dependent functionality related to kexec file-based syscall */ diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 2d2a237f2..30ca7607c 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -19,8 +19,8 @@ #include <linux/module.h> #include <linux/smp.h> #include <linux/pci.h> -#include <linux/irqdomain.h> +#include <asm/irqdomain.h> #include <asm/mtrr.h> #include <asm/mpspec.h> #include <asm/pgalloc.h> @@ -113,11 +113,6 @@ static void __init MP_bus_info(struct mpc_bus *m) pr_warn("Unknown bustype %s - ignoring\n", str); } -static struct irq_domain_ops mp_ioapic_irqdomain_ops = { - .map = mp_irqdomain_map, - .unmap = mp_irqdomain_unmap, -}; - static void __init MP_ioapic_info(struct mpc_ioapic *m) { struct ioapic_domain_cfg cfg = { diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c index bbb6c7316..33ee3e0ef 100644 --- a/arch/x86/kernel/paravirt-spinlocks.c +++ b/arch/x86/kernel/paravirt-spinlocks.c @@ -8,11 +8,33 @@ #include <asm/paravirt.h> +#ifdef CONFIG_QUEUED_SPINLOCKS +__visible void __native_queued_spin_unlock(struct qspinlock *lock) +{ + native_queued_spin_unlock(lock); +} + +PV_CALLEE_SAVE_REGS_THUNK(__native_queued_spin_unlock); + +bool pv_is_native_spin_unlock(void) +{ + return pv_lock_ops.queued_spin_unlock.func == + __raw_callee_save___native_queued_spin_unlock; +} +#endif + struct pv_lock_ops pv_lock_ops = { #ifdef CONFIG_SMP +#ifdef CONFIG_QUEUED_SPINLOCKS + .queued_spin_lock_slowpath = native_queued_spin_lock_slowpath, + .queued_spin_unlock = PV_CALLEE_SAVE(__native_queued_spin_unlock), + .wait = paravirt_nop, + .kick = paravirt_nop, +#else /* !CONFIG_QUEUED_SPINLOCKS */ .lock_spinning = __PV_IS_CALLEE_SAVE(paravirt_nop), .unlock_kick = paravirt_nop, -#endif +#endif /* !CONFIG_QUEUED_SPINLOCKS */ +#endif /* SMP */ }; EXPORT_SYMBOL(pv_lock_ops); diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index c614dd492..58bcfb67c 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -154,7 +154,9 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf, ret = paravirt_patch_ident_64(insnbuf, len); else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) || +#ifdef CONFIG_X86_32 type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit) || +#endif type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret32) || type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret64)) /* If operation requires a jmp, then jmp */ @@ -371,7 +373,7 @@ __visible struct pv_cpu_ops pv_cpu_ops = { .load_sp0 = native_load_sp0, -#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) +#if defined(CONFIG_X86_32) .irq_enable_sysexit = native_irq_enable_sysexit, #endif #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c index d9f32e6d6..e1b013696 100644 --- a/arch/x86/kernel/paravirt_patch_32.c +++ b/arch/x86/kernel/paravirt_patch_32.c @@ -12,6 +12,10 @@ DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax"); DEF_NATIVE(pv_cpu_ops, clts, "clts"); DEF_NATIVE(pv_cpu_ops, read_tsc, "rdtsc"); +#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) +DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%eax)"); +#endif + unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len) { /* arg in %eax, return in %eax */ @@ -24,6 +28,8 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len) return 0; } +extern bool pv_is_native_spin_unlock(void); + unsigned native_patch(u8 type, u16 clobbers, void *ibuf, unsigned long addr, unsigned len) { @@ -47,14 +53,22 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_mmu_ops, write_cr3); PATCH_SITE(pv_cpu_ops, clts); PATCH_SITE(pv_cpu_ops, read_tsc); - - patch_site: - ret = paravirt_patch_insns(ibuf, len, start, end); - break; +#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) + case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock): + if (pv_is_native_spin_unlock()) { + start = start_pv_lock_ops_queued_spin_unlock; + end = end_pv_lock_ops_queued_spin_unlock; + goto patch_site; + } +#endif default: ret = paravirt_patch_default(type, clobbers, ibuf, addr, len); break; + +patch_site: + ret = paravirt_patch_insns(ibuf, len, start, end); + break; } #undef PATCH_SITE return ret; diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index a1da6737b..8aa05583b 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -21,6 +21,10 @@ DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs"); DEF_NATIVE(, mov32, "mov %edi, %eax"); DEF_NATIVE(, mov64, "mov %rdi, %rax"); +#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) +DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)"); +#endif + unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len) { return paravirt_patch_insns(insnbuf, len, @@ -33,6 +37,8 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len) start__mov64, end__mov64); } +extern bool pv_is_native_spin_unlock(void); + unsigned native_patch(u8 type, u16 clobbers, void *ibuf, unsigned long addr, unsigned len) { @@ -49,7 +55,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_irq_ops, save_fl); PATCH_SITE(pv_irq_ops, irq_enable); PATCH_SITE(pv_irq_ops, irq_disable); - PATCH_SITE(pv_cpu_ops, irq_enable_sysexit); PATCH_SITE(pv_cpu_ops, usergs_sysret32); PATCH_SITE(pv_cpu_ops, usergs_sysret64); PATCH_SITE(pv_cpu_ops, swapgs); @@ -59,14 +64,22 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_cpu_ops, clts); PATCH_SITE(pv_mmu_ops, flush_tlb_single); PATCH_SITE(pv_cpu_ops, wbinvd); - - patch_site: - ret = paravirt_patch_insns(ibuf, len, start, end); - break; +#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) + case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock): + if (pv_is_native_spin_unlock()) { + start = start_pv_lock_ops_queued_spin_unlock; + end = end_pv_lock_ops_queued_spin_unlock; + goto patch_site; + } +#endif default: ret = paravirt_patch_default(type, clobbers, ibuf, addr, len); break; + +patch_site: + ret = paravirt_patch_insns(ibuf, len, start, end); + break; } #undef PATCH_SITE return ret; diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index a25e202bb..353972c19 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -140,6 +140,51 @@ void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr, free_pages((unsigned long)vaddr, get_order(size)); } +void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t gfp, struct dma_attrs *attrs) +{ + struct dma_map_ops *ops = get_dma_ops(dev); + void *memory; + + gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); + + if (dma_alloc_from_coherent(dev, size, dma_handle, &memory)) + return memory; + + if (!dev) + dev = &x86_dma_fallback_dev; + + if (!is_device_dma_capable(dev)) + return NULL; + + if (!ops->alloc) + return NULL; + + memory = ops->alloc(dev, size, dma_handle, + dma_alloc_coherent_gfp_flags(dev, gfp), attrs); + debug_dma_alloc_coherent(dev, size, *dma_handle, memory); + + return memory; +} +EXPORT_SYMBOL(dma_alloc_attrs); + +void dma_free_attrs(struct device *dev, size_t size, + void *vaddr, dma_addr_t bus, + struct dma_attrs *attrs) +{ + struct dma_map_ops *ops = get_dma_ops(dev); + + WARN_ON(irqs_disabled()); /* for portability */ + + if (dma_release_from_coherent(dev, get_order(size), vaddr)) + return; + + debug_dma_free_coherent(dev, size, vaddr, bus); + if (ops->free) + ops->free(dev, size, vaddr, bus, attrs); +} +EXPORT_SYMBOL(dma_free_attrs); + /* * See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel * parameter documentation. diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 77dd0ad58..adf0392d5 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -20,6 +20,13 @@ void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, { void *vaddr; + /* + * Don't print a warning when the first allocation attempt fails. + * swiotlb_alloc_coherent() will print a warning when the DMA + * memory allocation ultimately failed. + */ + flags |= __GFP_NOWARN; + vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags, attrs); if (vaddr) diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c index 3420c874d..64f90f53b 100644 --- a/arch/x86/kernel/pmem.c +++ b/arch/x86/kernel/pmem.c @@ -1,53 +1,82 @@ /* * Copyright (c) 2015, Christoph Hellwig. + * Copyright (c) 2015, Intel Corporation. */ -#include <linux/memblock.h> #include <linux/platform_device.h> -#include <linux/slab.h> +#include <linux/libnvdimm.h> +#include <linux/module.h> #include <asm/e820.h> -#include <asm/page_types.h> -#include <asm/setup.h> -static __init void register_pmem_device(struct resource *res) +static void e820_pmem_release(struct device *dev) { - struct platform_device *pdev; - int error; + struct nvdimm_bus *nvdimm_bus = dev->platform_data; - pdev = platform_device_alloc("pmem", PLATFORM_DEVID_AUTO); - if (!pdev) - return; + if (nvdimm_bus) + nvdimm_bus_unregister(nvdimm_bus); +} - error = platform_device_add_resources(pdev, res, 1); - if (error) - goto out_put_pdev; +static struct platform_device e820_pmem = { + .name = "e820_pmem", + .id = -1, + .dev = { + .release = e820_pmem_release, + }, +}; - error = platform_device_add(pdev); - if (error) - goto out_put_pdev; - return; +static const struct attribute_group *e820_pmem_attribute_groups[] = { + &nvdimm_bus_attribute_group, + NULL, +}; -out_put_pdev: - dev_warn(&pdev->dev, "failed to add 'pmem' (persistent memory) device!\n"); - platform_device_put(pdev); -} +static const struct attribute_group *e820_pmem_region_attribute_groups[] = { + &nd_region_attribute_group, + &nd_device_attribute_group, + NULL, +}; -static __init int register_pmem_devices(void) +static __init int register_e820_pmem(void) { - int i; + static struct nvdimm_bus_descriptor nd_desc; + struct device *dev = &e820_pmem.dev; + struct nvdimm_bus *nvdimm_bus; + int rc, i; + + rc = platform_device_register(&e820_pmem); + if (rc) + return rc; + + nd_desc.attr_groups = e820_pmem_attribute_groups; + nd_desc.provider_name = "e820"; + nvdimm_bus = nvdimm_bus_register(dev, &nd_desc); + if (!nvdimm_bus) + goto err; + dev->platform_data = nvdimm_bus; for (i = 0; i < e820.nr_map; i++) { struct e820entry *ei = &e820.map[i]; + struct resource res = { + .flags = IORESOURCE_MEM, + .start = ei->addr, + .end = ei->addr + ei->size - 1, + }; + struct nd_region_desc ndr_desc; + + if (ei->type != E820_PRAM) + continue; - if (ei->type == E820_PRAM) { - struct resource res = { - .flags = IORESOURCE_MEM, - .start = ei->addr, - .end = ei->addr + ei->size - 1, - }; - register_pmem_device(&res); - } + memset(&ndr_desc, 0, sizeof(ndr_desc)); + ndr_desc.res = &res; + ndr_desc.attr_groups = e820_pmem_region_attribute_groups; + ndr_desc.numa_node = NUMA_NO_NODE; + if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc)) + goto err; } return 0; + + err: + dev_err(dev, "failed to register legacy persistent memory ranges\n"); + platform_device_unregister(&e820_pmem); + return -ENXIO; } -device_initcall(register_pmem_devices); +device_initcall(register_e820_pmem); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 6e338e3b1..c27cad726 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -25,8 +25,7 @@ #include <asm/idle.h> #include <asm/uaccess.h> #include <asm/mwait.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/debugreg.h> #include <asm/nmi.h> #include <asm/tlbflush.h> @@ -76,47 +75,15 @@ void idle_notifier_unregister(struct notifier_block *n) EXPORT_SYMBOL_GPL(idle_notifier_unregister); #endif -struct kmem_cache *task_xstate_cachep; -EXPORT_SYMBOL_GPL(task_xstate_cachep); - /* * this gets called so that we can store lazy state into memory and copy the * current task into the new thread. */ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { - *dst = *src; - - dst->thread.fpu_counter = 0; - dst->thread.fpu.has_fpu = 0; - dst->thread.fpu.state = NULL; - task_disable_lazy_fpu_restore(dst); - if (tsk_used_math(src)) { - int err = fpu_alloc(&dst->thread.fpu); - if (err) - return err; - fpu_copy(dst, src); - } - return 0; -} - -void free_thread_xstate(struct task_struct *tsk) -{ - fpu_free(&tsk->thread.fpu); -} + memcpy(dst, src, arch_task_struct_size); -void arch_release_task_struct(struct task_struct *tsk) -{ - free_thread_xstate(tsk); -} - -void arch_task_cache_init(void) -{ - task_xstate_cachep = - kmem_cache_create("task_xstate", xstate_size, - __alignof__(union thread_xstate), - SLAB_PANIC | SLAB_NOTRACK, NULL); - setup_xstate_comp(); + return fpu__copy(&dst->thread.fpu, &src->thread.fpu); } /* @@ -127,6 +94,7 @@ void exit_thread(void) struct task_struct *me = current; struct thread_struct *t = &me->thread; unsigned long *bp = t->io_bitmap_ptr; + struct fpu *fpu = &t->fpu; if (bp) { struct tss_struct *tss = &per_cpu(cpu_tss, get_cpu()); @@ -142,7 +110,7 @@ void exit_thread(void) kfree(bp); } - drop_fpu(me); + fpu__drop(fpu); } void flush_thread(void) @@ -152,19 +120,7 @@ void flush_thread(void) flush_ptrace_hw_breakpoint(tsk); memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); - if (!use_eager_fpu()) { - /* FPU state will be reallocated lazily at the first use. */ - drop_fpu(tsk); - free_thread_xstate(tsk); - } else { - if (!tsk_used_math(tsk)) { - /* kthread execs. TODO: cleanup this horror. */ - if (WARN_ON(init_fpu(tsk))) - force_sig(SIGKILL, tsk); - user_fpu_begin(); - } - restore_init_xstate(); - } + fpu__clear(&tsk->thread.fpu); } static void hard_disable_TSC(void) @@ -445,14 +401,14 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) } /* - * MONITOR/MWAIT with no hints, used for default default C1 state. - * This invokes MWAIT with interrutps enabled and no flags, - * which is backwards compatible with the original MWAIT implementation. + * MONITOR/MWAIT with no hints, used for default C1 state. This invokes MWAIT + * with interrupts enabled and no flags, which is backwards compatible with the + * original MWAIT implementation. */ - static void mwait_idle(void) { if (!current_set_polling_and_test()) { + trace_cpu_idle_rcuidle(1, smp_processor_id()); if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) { smp_mb(); /* quirk */ clflush((void *)¤t_thread_info()->flags); @@ -464,6 +420,7 @@ static void mwait_idle(void) __sti_mwait(0, 0); else local_irq_enable(); + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } else { local_irq_enable(); } diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 8ed2106b0..f73c962fe 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -39,8 +39,7 @@ #include <asm/pgtable.h> #include <asm/ldt.h> #include <asm/processor.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/desc.h> #ifdef CONFIG_MATH_EMULATION #include <asm/math_emu.h> @@ -129,8 +128,8 @@ void release_thread(struct task_struct *dead_task) release_vm86_irqs(dead_task); } -int copy_thread(unsigned long clone_flags, unsigned long sp, - unsigned long arg, struct task_struct *p) +int copy_thread_tls(unsigned long clone_flags, unsigned long sp, + unsigned long arg, struct task_struct *p, unsigned long tls) { struct pt_regs *childregs = task_pt_regs(p); struct task_struct *tsk; @@ -185,7 +184,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, */ if (clone_flags & CLONE_SETTLS) err = do_set_thread_area(p, -1, - (struct user_desc __user *)childregs->si, 0); + (struct user_desc __user *)tls, 0); if (err && p->thread.io_bitmap_ptr) { kfree(p->thread.io_bitmap_ptr); @@ -242,14 +241,16 @@ __visible __notrace_funcgraph struct task_struct * __switch_to(struct task_struct *prev_p, struct task_struct *next_p) { struct thread_struct *prev = &prev_p->thread, - *next = &next_p->thread; + *next = &next_p->thread; + struct fpu *prev_fpu = &prev->fpu; + struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(cpu_tss, cpu); - fpu_switch_t fpu; + fpu_switch_t fpu_switch; /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ - fpu = switch_fpu_prepare(prev_p, next_p, cpu); + fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu); /* * Save away %gs. No need to save %fs, as it was saved on the @@ -296,19 +297,16 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * Leave lazy mode, flushing any hypercalls made here. * This must be done before restoring TLS segments so * the GDT and LDT are properly updated, and must be - * done before math_state_restore, so the TS bit is up + * done before fpu__restore(), so the TS bit is up * to date. */ arch_end_context_switch(next_p); /* - * Reload esp0, kernel_stack, and current_top_of_stack. This changes + * Reload esp0 and cpu_current_top_of_stack. This changes * current_thread_info(). */ load_sp0(tss, next); - this_cpu_write(kernel_stack, - (unsigned long)task_stack_page(next_p) + - THREAD_SIZE); this_cpu_write(cpu_current_top_of_stack, (unsigned long)task_stack_page(next_p) + THREAD_SIZE); @@ -319,7 +317,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) if (prev->gs | next->gs) lazy_load_gs(next->gs); - switch_fpu_finish(next_p, fpu); + switch_fpu_finish(next_fpu, fpu_switch); this_cpu_write(current_task, next_p); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index ddfdbf74f..f6b916387 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -38,8 +38,7 @@ #include <asm/pgtable.h> #include <asm/processor.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/mmu_context.h> #include <asm/prctl.h> #include <asm/desc.h> @@ -122,11 +121,11 @@ void __show_regs(struct pt_regs *regs, int all) void release_thread(struct task_struct *dead_task) { if (dead_task->mm) { - if (dead_task->mm->context.size) { + if (dead_task->mm->context.ldt) { pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n", dead_task->comm, dead_task->mm->context.ldt, - dead_task->mm->context.size); + dead_task->mm->context.ldt->size); BUG(); } } @@ -151,8 +150,8 @@ static inline u32 read_32bit_tls(struct task_struct *t, int tls) return get_desc_base(&t->thread.tls_array[tls]); } -int copy_thread(unsigned long clone_flags, unsigned long sp, - unsigned long arg, struct task_struct *p) +int copy_thread_tls(unsigned long clone_flags, unsigned long sp, + unsigned long arg, struct task_struct *p, unsigned long tls) { int err; struct pt_regs *childregs; @@ -208,10 +207,10 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, #ifdef CONFIG_IA32_EMULATION if (is_ia32_task()) err = do_set_thread_area(p, -1, - (struct user_desc __user *)childregs->si, 0); + (struct user_desc __user *)tls, 0); else #endif - err = do_arch_prctl(p, ARCH_SET_FS, childregs->r8); + err = do_arch_prctl(p, ARCH_SET_FS, tls); if (err) goto out; } @@ -274,12 +273,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) { struct thread_struct *prev = &prev_p->thread; struct thread_struct *next = &next_p->thread; + struct fpu *prev_fpu = &prev->fpu; + struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(cpu_tss, cpu); unsigned fsindex, gsindex; - fpu_switch_t fpu; + fpu_switch_t fpu_switch; - fpu = switch_fpu_prepare(prev_p, next_p, cpu); + fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu); /* We must save %fs and %gs before load_TLS() because * %fs and %gs may be cleared by load_TLS(). @@ -299,7 +300,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * Leave lazy mode, flushing any hypercalls made here. This * must be done after loading TLS entries in the GDT but before * loading segments that might reference them, and and it must - * be done before math_state_restore, so the TS bit is up to + * be done before fpu__restore(), so the TS bit is up to * date. */ arch_end_context_switch(next_p); @@ -391,7 +392,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) wrmsrl(MSR_KERNEL_GS_BASE, next->gs); prev->gsindex = gsindex; - switch_fpu_finish(next_p, fpu); + switch_fpu_finish(next_fpu, fpu_switch); /* * Switch the PDA and FPU contexts. @@ -409,9 +410,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) /* Reload esp0 and ss1. This changes current_thread_info(). */ load_sp0(tss, next); - this_cpu_write(kernel_stack, - (unsigned long)task_stack_page(next_p) + THREAD_SIZE); - /* * Now maybe reload the debug registers and handle I/O bitmaps */ diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index a7bc79480..9be72bc36 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -11,7 +11,6 @@ #include <linux/errno.h> #include <linux/slab.h> #include <linux/ptrace.h> -#include <linux/regset.h> #include <linux/tracehook.h> #include <linux/user.h> #include <linux/elf.h> @@ -28,8 +27,9 @@ #include <asm/uaccess.h> #include <asm/pgtable.h> #include <asm/processor.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> +#include <asm/fpu/signal.h> +#include <asm/fpu/regset.h> #include <asm/debugreg.h> #include <asm/ldt.h> #include <asm/desc.h> @@ -1297,7 +1297,7 @@ static struct user_regset x86_64_regsets[] __read_mostly = { .core_note_type = NT_PRFPREG, .n = sizeof(struct user_i387_struct) / sizeof(long), .size = sizeof(long), .align = sizeof(long), - .active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set + .active = regset_xregset_fpregs_active, .get = xfpregs_get, .set = xfpregs_set }, [REGSET_XSTATE] = { .core_note_type = NT_X86_XSTATE, @@ -1338,13 +1338,13 @@ static struct user_regset x86_32_regsets[] __read_mostly = { .core_note_type = NT_PRFPREG, .n = sizeof(struct user_i387_ia32_struct) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), - .active = fpregs_active, .get = fpregs_get, .set = fpregs_set + .active = regset_fpregs_active, .get = fpregs_get, .set = fpregs_set }, [REGSET_XFP] = { .core_note_type = NT_PRXFPREG, .n = sizeof(struct user32_fxsr_struct) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), - .active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set + .active = regset_xregset_fpregs_active, .get = xfpregs_get, .set = xfpregs_set }, [REGSET_XSTATE] = { .core_note_type = NT_X86_XSTATE, diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index d74ac3329..80f874bf9 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -461,19 +461,18 @@ static void __init e820_reserve_setup_data(void) { struct setup_data *data; u64 pa_data; - int found = 0; pa_data = boot_params.hdr.setup_data; + if (!pa_data) + return; + while (pa_data) { data = early_memremap(pa_data, sizeof(*data)); e820_update_range(pa_data, sizeof(*data)+data->len, E820_RAM, E820_RESERVED_KERN); - found = 1; pa_data = data->next; early_memunmap(data, sizeof(*data)); } - if (!found) - return; sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); memcpy(&e820_saved, &e820, sizeof(struct e820map)); @@ -531,12 +530,14 @@ static void __init reserve_crashkernel_low(void) if (ret != 0) { /* * two parts from lib/swiotlb.c: - * swiotlb size: user specified with swiotlb= or default. - * swiotlb overflow buffer: now is hardcoded to 32k. - * We round it to 8M for other buffers that - * may need to stay low too. + * -swiotlb size: user-specified with swiotlb= or default. + * + * -swiotlb overflow buffer: now hardcoded to 32k. We round it + * to 8M for other buffers that may need to stay low too. Also + * make sure we allocate enough extra low memory so that we + * don't run out of DMA buffers for 32-bit devices. */ - low_size = swiotlb_size_or_default() + (8UL<<20); + low_size = max(swiotlb_size_or_default() + (8UL<<20), 256UL<<20); auto_set = true; } else { /* passed with crashkernel=0,low ? */ @@ -834,7 +835,7 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) { if (kaslr_enabled()) { pr_emerg("Kernel Offset: 0x%lx from 0x%lx (relocation range: 0x%lx-0x%lx)\n", - (unsigned long)&_text - __START_KERNEL, + kaslr_offset(), __START_KERNEL, __START_KERNEL_map, MODULES_VADDR-1); @@ -1103,6 +1104,9 @@ void __init setup_arch(char **cmdline_p) memblock_set_current_limit(ISA_END_ADDRESS); memblock_x86_fill(); + if (efi_enabled(EFI_BOOT)) + efi_find_mirror(); + /* * The EFI specification says that boot service code won't be called * after ExitBootServices(). This is, in fact, a lie. @@ -1222,8 +1226,7 @@ void __init setup_arch(char **cmdline_p) init_cpu_to_node(); init_apic_mappings(); - if (x86_io_apic_ops.init) - x86_io_apic_ops.init(); + io_apic_init_mappings(); kvm_guest_init(); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 1ea14fd53..71820c42b 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -26,8 +26,8 @@ #include <asm/processor.h> #include <asm/ucontext.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> +#include <asm/fpu/signal.h> #include <asm/vdso.h> #include <asm/mce.h> #include <asm/sighandling.h> @@ -93,8 +93,15 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc) COPY(r15); #endif /* CONFIG_X86_64 */ +#ifdef CONFIG_X86_32 COPY_SEG_CPL3(cs); COPY_SEG_CPL3(ss); +#else /* !CONFIG_X86_32 */ + /* Kernel saves and restores only the CS segment register on signals, + * which is the bare minimum needed to allow mixed 32/64-bit code. + * App's signal handler can save/restore other segments if needed. */ + COPY_SEG_CPL3(cs); +#endif /* CONFIG_X86_32 */ get_user_ex(tmpflags, &sc->flags); regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); @@ -103,7 +110,7 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc) get_user_ex(buf, &sc->fpstate); } get_user_catch(err); - err |= restore_xstate_sig(buf, config_enabled(CONFIG_X86_32)); + err |= fpu__restore_sig(buf, config_enabled(CONFIG_X86_32)); force_iret(); @@ -154,9 +161,8 @@ int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, #else /* !CONFIG_X86_32 */ put_user_ex(regs->flags, &sc->flags); put_user_ex(regs->cs, &sc->cs); - put_user_ex(0, &sc->__pad2); - put_user_ex(0, &sc->__pad1); - put_user_ex(regs->ss, &sc->ss); + put_user_ex(0, &sc->gs); + put_user_ex(0, &sc->fs); #endif /* CONFIG_X86_32 */ put_user_ex(fpstate, &sc->fpstate); @@ -199,6 +205,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, unsigned long sp = regs->sp; unsigned long buf_fx = 0; int onsigstack = on_sig_stack(sp); + struct fpu *fpu = ¤t->thread.fpu; /* redzone */ if (config_enabled(CONFIG_X86_64)) @@ -218,9 +225,9 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, } } - if (used_math()) { - sp = alloc_mathframe(sp, config_enabled(CONFIG_X86_32), - &buf_fx, &math_size); + if (fpu->fpstate_active) { + sp = fpu__alloc_mathframe(sp, config_enabled(CONFIG_X86_32), + &buf_fx, &math_size); *fpstate = (void __user *)sp; } @@ -234,8 +241,8 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, return (void __user *)-1L; /* save i387 and extended state */ - if (used_math() && - save_xstate_sig(*fpstate, (void __user *)buf_fx, math_size) < 0) + if (fpu->fpstate_active && + copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size) < 0) return (void __user *)-1L; return (void __user *)sp; @@ -450,19 +457,9 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, regs->sp = (unsigned long)frame; - /* - * Set up the CS and SS registers to run signal handlers in - * 64-bit mode, even if the handler happens to be interrupting - * 32-bit or 16-bit code. - * - * SS is subtle. In 64-bit mode, we don't need any particular - * SS descriptor, but we do need SS to be valid. It's possible - * that the old SS is entirely bogus -- this can happen if the - * signal we're trying to deliver is #GP or #SS caused by a bad - * SS value. - */ + /* Set up the CS register to run signal handlers in 64-bit mode, + even if the handler happens to be interrupting 32-bit code. */ regs->cs = __USER_CS; - regs->ss = __USER_DS; return 0; } @@ -593,6 +590,22 @@ badframe: return 0; } +static inline int is_ia32_compat_frame(void) +{ + return config_enabled(CONFIG_IA32_EMULATION) && + test_thread_flag(TIF_IA32); +} + +static inline int is_ia32_frame(void) +{ + return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame(); +} + +static inline int is_x32_frame(void) +{ + return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32); +} + static int setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) { @@ -617,6 +630,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) { bool stepping, failed; + struct fpu *fpu = ¤t->thread.fpu; /* Are we from a system call? */ if (syscall_get_nr(current, regs) >= 0) { @@ -665,8 +679,8 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) /* * Ensure the signal handler starts with the new fpu state. */ - if (used_math()) - fpu_reset_state(current); + if (fpu->fpstate_active) + fpu__clear(fpu); } signal_setup_done(failed, ksig, stepping); } diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index be8e1bde0..15aaa69bb 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -170,8 +170,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs) asmlinkage __visible void smp_reboot_interrupt(void) { - ack_APIC_irq(); - irq_enter(); + ipi_entering_ack_irq(); stop_this_cpu(NULL); irq_exit(); } @@ -265,12 +264,6 @@ __visible void smp_reschedule_interrupt(struct pt_regs *regs) */ } -static inline void smp_entering_irq(void) -{ - ack_APIC_irq(); - irq_enter(); -} - __visible void smp_trace_reschedule_interrupt(struct pt_regs *regs) { /* @@ -279,7 +272,7 @@ __visible void smp_trace_reschedule_interrupt(struct pt_regs *regs) * scheduler_ipi(). This is OK, since those functions are allowed * to nest. */ - smp_entering_irq(); + ipi_entering_ack_irq(); trace_reschedule_entry(RESCHEDULE_VECTOR); __smp_reschedule_interrupt(); trace_reschedule_exit(RESCHEDULE_VECTOR); @@ -297,14 +290,14 @@ static inline void __smp_call_function_interrupt(void) __visible void smp_call_function_interrupt(struct pt_regs *regs) { - smp_entering_irq(); + ipi_entering_ack_irq(); __smp_call_function_interrupt(); exiting_irq(); } __visible void smp_trace_call_function_interrupt(struct pt_regs *regs) { - smp_entering_irq(); + ipi_entering_ack_irq(); trace_call_function_entry(CALL_FUNCTION_VECTOR); __smp_call_function_interrupt(); trace_call_function_exit(CALL_FUNCTION_VECTOR); @@ -319,14 +312,14 @@ static inline void __smp_call_function_single_interrupt(void) __visible void smp_call_function_single_interrupt(struct pt_regs *regs) { - smp_entering_irq(); + ipi_entering_ack_irq(); __smp_call_function_single_interrupt(); exiting_irq(); } __visible void smp_trace_call_function_single_interrupt(struct pt_regs *regs) { - smp_entering_irq(); + ipi_entering_ack_irq(); trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR); __smp_call_function_single_interrupt(); trace_call_function_single_exit(CALL_FUNCTION_SINGLE_VECTOR); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 50e547eac..b1f3ed9c7 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -68,8 +68,7 @@ #include <asm/mwait.h> #include <asm/apic.h> #include <asm/io_apic.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/setup.h> #include <asm/uv/uv.h> #include <linux/mc146818rtc.h> @@ -172,11 +171,6 @@ static void smp_callin(void) apic_ap_setup(); /* - * Need to setup vector mappings before we enable interrupts. - */ - setup_vector_irq(smp_processor_id()); - - /* * Save our processor parameters. Note: this information * is needed for clock calibration. */ @@ -240,18 +234,13 @@ static void notrace start_secondary(void *unused) check_tsc_sync_target(); /* - * Enable the espfix hack for this CPU - */ -#ifdef CONFIG_X86_ESPFIX64 - init_espfix_ap(); -#endif - - /* - * We need to hold vector_lock so there the set of online cpus - * does not change while we are assigning vectors to cpus. Holding - * this lock ensures we don't half assign or remove an irq from a cpu. + * Lock vector_lock and initialize the vectors on this cpu + * before setting the cpu online. We must set it online with + * vector_lock held to prevent a concurrent setup/teardown + * from seeing a half valid vector space. */ lock_vector_lock(); + setup_vector_irq(smp_processor_id()); set_cpu_online(smp_processor_id(), true); unlock_vector_lock(); cpu_set_state_online(smp_processor_id()); @@ -314,10 +303,10 @@ topology_sane(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o, const char *name) cpu1, name, cpu2, cpu_to_node(cpu1), cpu_to_node(cpu2)); } -#define link_mask(_m, c1, c2) \ +#define link_mask(mfunc, c1, c2) \ do { \ - cpumask_set_cpu((c1), cpu_##_m##_mask(c2)); \ - cpumask_set_cpu((c2), cpu_##_m##_mask(c1)); \ + cpumask_set_cpu((c1), mfunc(c2)); \ + cpumask_set_cpu((c2), mfunc(c1)); \ } while (0) static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) @@ -398,9 +387,9 @@ void set_cpu_sibling_map(int cpu) cpumask_set_cpu(cpu, cpu_sibling_setup_mask); if (!has_mp) { - cpumask_set_cpu(cpu, cpu_sibling_mask(cpu)); + cpumask_set_cpu(cpu, topology_sibling_cpumask(cpu)); cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu)); - cpumask_set_cpu(cpu, cpu_core_mask(cpu)); + cpumask_set_cpu(cpu, topology_core_cpumask(cpu)); c->booted_cores = 1; return; } @@ -409,32 +398,34 @@ void set_cpu_sibling_map(int cpu) o = &cpu_data(i); if ((i == cpu) || (has_smt && match_smt(c, o))) - link_mask(sibling, cpu, i); + link_mask(topology_sibling_cpumask, cpu, i); if ((i == cpu) || (has_mp && match_llc(c, o))) - link_mask(llc_shared, cpu, i); + link_mask(cpu_llc_shared_mask, cpu, i); } /* * This needs a separate iteration over the cpus because we rely on all - * cpu_sibling_mask links to be set-up. + * topology_sibling_cpumask links to be set-up. */ for_each_cpu(i, cpu_sibling_setup_mask) { o = &cpu_data(i); if ((i == cpu) || (has_mp && match_die(c, o))) { - link_mask(core, cpu, i); + link_mask(topology_core_cpumask, cpu, i); /* * Does this new cpu bringup a new core? */ - if (cpumask_weight(cpu_sibling_mask(cpu)) == 1) { + if (cpumask_weight( + topology_sibling_cpumask(cpu)) == 1) { /* * for each core in package, increment * the booted_cores for this new cpu */ - if (cpumask_first(cpu_sibling_mask(i)) == i) + if (cpumask_first( + topology_sibling_cpumask(i)) == i) c->booted_cores++; /* * increment the core count for all @@ -514,6 +505,40 @@ void __inquire_remote_apic(int apicid) } /* + * The Multiprocessor Specification 1.4 (1997) example code suggests + * that there should be a 10ms delay between the BSP asserting INIT + * and de-asserting INIT, when starting a remote processor. + * But that slows boot and resume on modern processors, which include + * many cores and don't require that delay. + * + * Cmdline "init_cpu_udelay=" is available to over-ride this delay. + * Modern processor families are quirked to remove the delay entirely. + */ +#define UDELAY_10MS_DEFAULT 10000 + +static unsigned int init_udelay = UDELAY_10MS_DEFAULT; + +static int __init cpu_init_udelay(char *str) +{ + get_option(&str, &init_udelay); + + return 0; +} +early_param("cpu_init_udelay", cpu_init_udelay); + +static void __init smp_quirk_init_udelay(void) +{ + /* if cmdline changed it from default, leave it alone */ + if (init_udelay != UDELAY_10MS_DEFAULT) + return; + + /* if modern processor, use no delay */ + if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) || + ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF))) + init_udelay = 0; +} + +/* * Poke the other CPU in the eye via NMI to wake it up. Remember that the normal * INIT, INIT, STARTUP sequence will reset the chip hard for us, and this * won't ... remember to clear down the APIC, etc later. @@ -555,7 +580,7 @@ wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip) static int wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) { - unsigned long send_status, accept_status = 0; + unsigned long send_status = 0, accept_status = 0; int maxlvt, num_starts, j; maxlvt = lapic_get_maxlvt(); @@ -583,7 +608,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) pr_debug("Waiting for send to finish...\n"); send_status = safe_apic_wait_icr_idle(); - mdelay(10); + udelay(init_udelay); pr_debug("Deasserting INIT\n"); @@ -651,6 +676,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) * Give the other CPU some time to accept the IPI. */ udelay(200); + if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */ apic_write(APIC_ESR, 0); accept_status = (apic_read(APIC_ESR) & 0xEF); @@ -792,8 +818,6 @@ void common_cpu_up(unsigned int cpu, struct task_struct *idle) clear_tsk_thread_flag(idle, TIF_FORK); initial_gs = per_cpu_offset(cpu); #endif - per_cpu(kernel_stack, cpu) = - (unsigned long)task_stack_page(idle) + THREAD_SIZE; } /* @@ -820,6 +844,13 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) initial_code = (unsigned long)start_secondary; stack_start = idle->thread.sp; + /* + * Enable the espfix hack for this CPU + */ +#ifdef CONFIG_X86_ESPFIX64 + init_espfix_ap(cpu); +#endif + /* So we see what's up */ announce_cpu(cpu, apicid); @@ -961,8 +992,17 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) common_cpu_up(cpu, tidle); + /* + * We have to walk the irq descriptors to setup the vector + * space for the cpu which comes online. Prevent irq + * alloc/free across the bringup. + */ + irq_lock_sparse(); + err = do_boot_cpu(apicid, cpu, tidle); + if (err) { + irq_unlock_sparse(); pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu); return -EIO; } @@ -980,6 +1020,8 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) touch_nmi_watchdog(); } + irq_unlock_sparse(); + return 0; } @@ -1009,8 +1051,8 @@ static __init void disable_smp(void) physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map); else physid_set_mask_of_physid(0, &phys_cpu_present_map); - cpumask_set_cpu(0, cpu_sibling_mask(0)); - cpumask_set_cpu(0, cpu_core_mask(0)); + cpumask_set_cpu(0, topology_sibling_cpumask(0)); + cpumask_set_cpu(0, topology_core_cpumask(0)); } enum { @@ -1176,6 +1218,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) uv_system_init(); set_mtrr_aps_delayed_init(); + + smp_quirk_init_udelay(); } void arch_enable_nonboot_cpus_begin(void) @@ -1293,22 +1337,22 @@ static void remove_siblinginfo(int cpu) int sibling; struct cpuinfo_x86 *c = &cpu_data(cpu); - for_each_cpu(sibling, cpu_core_mask(cpu)) { - cpumask_clear_cpu(cpu, cpu_core_mask(sibling)); + for_each_cpu(sibling, topology_core_cpumask(cpu)) { + cpumask_clear_cpu(cpu, topology_core_cpumask(sibling)); /*/ * last thread sibling in this cpu core going down */ - if (cpumask_weight(cpu_sibling_mask(cpu)) == 1) + if (cpumask_weight(topology_sibling_cpumask(cpu)) == 1) cpu_data(sibling).booted_cores--; } - for_each_cpu(sibling, cpu_sibling_mask(cpu)) - cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling)); + for_each_cpu(sibling, topology_sibling_cpumask(cpu)) + cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling)); for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling)); cpumask_clear(cpu_llc_shared_mask(cpu)); - cpumask_clear(cpu_sibling_mask(cpu)); - cpumask_clear(cpu_core_mask(cpu)); + cpumask_clear(topology_sibling_cpumask(cpu)); + cpumask_clear(topology_core_cpumask(cpu)); c->phys_proc_id = 0; c->cpu_core_id = 0; cpumask_clear_cpu(cpu, cpu_sibling_setup_mask); diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 9b4d51d0c..0ccb53a9f 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -5,6 +5,7 @@ #include <linux/mm.h> #include <linux/ptrace.h> #include <asm/desc.h> +#include <asm/mmu_context.h> unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs) { @@ -27,13 +28,14 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re struct desc_struct *desc; unsigned long base; - seg &= ~7UL; + seg >>= 3; mutex_lock(&child->mm->context.lock); - if (unlikely((seg >> 3) >= child->mm->context.size)) + if (unlikely(!child->mm->context.ldt || + seg >= child->mm->context.ldt->size)) addr = -1L; /* bogus selector, access would fault */ else { - desc = child->mm->context.ldt + seg; + desc = &child->mm->context.ldt->entries[seg]; base = get_desc_base(desc); /* 16-bit code segment? */ diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 324ab5247..f5791927a 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -54,12 +54,13 @@ #include <asm/ftrace.h> #include <asm/traps.h> #include <asm/desc.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/mce.h> #include <asm/fixmap.h> #include <asm/mach_traps.h> #include <asm/alternative.h> +#include <asm/fpu/xstate.h> +#include <asm/trace/mpx.h> #include <asm/mpx.h> #ifdef CONFIG_X86_64 @@ -72,8 +73,7 @@ gate_desc debug_idt_table[NR_VECTORS] __page_aligned_bss; #else #include <asm/processor-flags.h> #include <asm/setup.h> - -asmlinkage int system_call(void); +#include <asm/proto.h> #endif /* Must be page-aligned because the real IDT is used in a fixmap. */ @@ -371,10 +371,8 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) { - struct task_struct *tsk = current; - struct xsave_struct *xsave_buf; enum ctx_state prev_state; - struct bndcsr *bndcsr; + const struct bndcsr *bndcsr; siginfo_t *info; prev_state = exception_enter(); @@ -393,15 +391,15 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) /* * We need to look at BNDSTATUS to resolve this exception. - * It is not directly accessible, though, so we need to - * do an xsave and then pull it out of the xsave buffer. + * A NULL here might mean that it is in its 'init state', + * which is all zeros which indicates MPX was not + * responsible for the exception. */ - fpu_save_init(&tsk->thread.fpu); - xsave_buf = &(tsk->thread.fpu.state->xsave); - bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR); + bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR); if (!bndcsr) goto exit_trap; + trace_bounds_exception_mpx(bndcsr); /* * The error code field of the BNDSTATUS register communicates status * information of a bound range exception #BR or operation involving @@ -409,11 +407,11 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) */ switch (bndcsr->bndstatus & MPX_BNDSTA_ERROR_CODE) { case 2: /* Bound directory has invalid entry. */ - if (mpx_handle_bd_fault(xsave_buf)) + if (mpx_handle_bd_fault()) goto exit_trap; break; /* Success, it was handled */ case 1: /* Bound violation. */ - info = mpx_generate_siginfo(regs, xsave_buf); + info = mpx_generate_siginfo(regs); if (IS_ERR(info)) { /* * We failed to decode the MPX instruction. Act as if @@ -709,8 +707,8 @@ NOKPROBE_SYMBOL(do_debug); static void math_error(struct pt_regs *regs, int error_code, int trapnr) { struct task_struct *task = current; + struct fpu *fpu = &task->thread.fpu; siginfo_t info; - unsigned short err; char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" : "simd exception"; @@ -718,8 +716,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr) return; conditional_sti(regs); - if (!user_mode(regs)) - { + if (!user_mode(regs)) { if (!fixup_exception(regs)) { task->thread.error_code = error_code; task->thread.trap_nr = trapnr; @@ -731,62 +728,20 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr) /* * Save the info for the exception handler and clear the error. */ - unlazy_fpu(task); - task->thread.trap_nr = trapnr; + fpu__save(fpu); + + task->thread.trap_nr = trapnr; task->thread.error_code = error_code; - info.si_signo = SIGFPE; - info.si_errno = 0; - info.si_addr = (void __user *)uprobe_get_trap_addr(regs); - if (trapnr == X86_TRAP_MF) { - unsigned short cwd, swd; - /* - * (~cwd & swd) will mask out exceptions that are not set to unmasked - * status. 0x3f is the exception bits in these regs, 0x200 is the - * C1 reg you need in case of a stack fault, 0x040 is the stack - * fault bit. We should only be taking one exception at a time, - * so if this combination doesn't produce any single exception, - * then we have a bad program that isn't synchronizing its FPU usage - * and it will suffer the consequences since we won't be able to - * fully reproduce the context of the exception - */ - cwd = get_fpu_cwd(task); - swd = get_fpu_swd(task); + info.si_signo = SIGFPE; + info.si_errno = 0; + info.si_addr = (void __user *)uprobe_get_trap_addr(regs); - err = swd & ~cwd; - } else { - /* - * The SIMD FPU exceptions are handled a little differently, as there - * is only a single status/control register. Thus, to determine which - * unmasked exception was caught we must mask the exception mask bits - * at 0x1f80, and then use these to mask the exception bits at 0x3f. - */ - unsigned short mxcsr = get_fpu_mxcsr(task); - err = ~(mxcsr >> 7) & mxcsr; - } + info.si_code = fpu__exception_code(fpu, trapnr); - if (err & 0x001) { /* Invalid op */ - /* - * swd & 0x240 == 0x040: Stack Underflow - * swd & 0x240 == 0x240: Stack Overflow - * User must clear the SF bit (0x40) if set - */ - info.si_code = FPE_FLTINV; - } else if (err & 0x004) { /* Divide by Zero */ - info.si_code = FPE_FLTDIV; - } else if (err & 0x008) { /* Overflow */ - info.si_code = FPE_FLTOVF; - } else if (err & 0x012) { /* Denormal, Underflow */ - info.si_code = FPE_FLTUND; - } else if (err & 0x020) { /* Precision */ - info.si_code = FPE_FLTRES; - } else { - /* - * If we're using IRQ 13, or supposedly even some trap - * X86_TRAP_MF implementations, it's possible - * we get a spurious trap, which is not an error. - */ + /* Retry when we get spurious exceptions: */ + if (!info.si_code) return; - } + force_sig_info(SIGFPE, &info, task); } @@ -813,62 +768,8 @@ dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *regs, long error_code) { conditional_sti(regs); -#if 0 - /* No need to warn about this any longer. */ - pr_info("Ignoring P6 Local APIC Spurious Interrupt Bug...\n"); -#endif -} - -asmlinkage __visible void __attribute__((weak)) smp_thermal_interrupt(void) -{ } -asmlinkage __visible void __attribute__((weak)) smp_threshold_interrupt(void) -{ -} - -/* - * 'math_state_restore()' saves the current math information in the - * old math state array, and gets the new ones from the current task - * - * Careful.. There are problems with IBM-designed IRQ13 behaviour. - * Don't touch unless you *really* know how it works. - * - * Must be called with kernel preemption disabled (eg with local - * local interrupts as in the case of do_device_not_available). - */ -void math_state_restore(void) -{ - struct task_struct *tsk = current; - - if (!tsk_used_math(tsk)) { - local_irq_enable(); - /* - * does a slab alloc which can sleep - */ - if (init_fpu(tsk)) { - /* - * ran out of memory! - */ - do_group_exit(SIGKILL); - return; - } - local_irq_disable(); - } - - /* Avoid __kernel_fpu_begin() right after __thread_fpu_begin() */ - kernel_fpu_disable(); - __thread_fpu_begin(tsk); - if (unlikely(restore_fpu_checking(tsk))) { - fpu_reset_state(tsk); - force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk); - } else { - tsk->thread.fpu_counter++; - } - kernel_fpu_enable(); -} -EXPORT_SYMBOL_GPL(math_state_restore); - dotraplinkage void do_device_not_available(struct pt_regs *regs, long error_code) { @@ -889,7 +790,7 @@ do_device_not_available(struct pt_regs *regs, long error_code) return; } #endif - math_state_restore(); /* interrupts still off */ + fpu__restore(¤t->thread.fpu); /* interrupts still off */ #ifdef CONFIG_X86_32 conditional_sti(regs); #endif @@ -992,13 +893,13 @@ void __init trap_init(void) set_bit(i, used_vectors); #ifdef CONFIG_IA32_EMULATION - set_system_intr_gate(IA32_SYSCALL_VECTOR, ia32_syscall); + set_system_intr_gate(IA32_SYSCALL_VECTOR, entry_INT80_compat); set_bit(IA32_SYSCALL_VECTOR, used_vectors); #endif #ifdef CONFIG_X86_32 - set_system_trap_gate(SYSCALL_VECTOR, &system_call); - set_bit(SYSCALL_VECTOR, used_vectors); + set_system_trap_gate(IA32_SYSCALL_VECTOR, entry_INT80_32); + set_bit(IA32_SYSCALL_VECTOR, used_vectors); #endif /* diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index f95603842..7437b41f6 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -12,7 +12,6 @@ #include <linux/percpu.h> #include <linux/timex.h> #include <linux/static_key.h> -#include <linux/mm.h> #include <asm/hpet.h> #include <asm/timer.h> @@ -196,10 +195,6 @@ static void cyc2ns_init(int cpu) c2n->head = c2n->data; c2n->tail = c2n->data; - - // Don't let TuxOnIce make data RO - a secondary CPU will cause a triple fault - // if it loads microcode, which then does a printk, which may end up invoking cycles_2_ns - SetPageTOI_Untracked(virt_to_page(c2n)); } static inline unsigned long long cycles_2_ns(unsigned long long cyc) @@ -603,10 +598,19 @@ static unsigned long quick_pit_calibrate(void) if (!pit_expect_msb(0xff-i, &delta, &d2)) break; + delta -= tsc; + + /* + * Extrapolate the error and fail fast if the error will + * never be below 500 ppm. + */ + if (i == 1 && + d1 + d2 >= (delta * MAX_QUICK_PIT_ITERATIONS) >> 11) + return 0; + /* * Iterate until the error is less than 500 ppm */ - delta -= tsc; if (d1+d2 >= delta >> 11) continue; diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 26488487b..dd8d0791d 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -113,7 +113,7 @@ static void check_tsc_warp(unsigned int timeout) */ static inline unsigned int loop_timeout(int cpu) { - return (cpumask_weight(cpu_core_mask(cpu)) > 1) ? 2 : 20; + return (cpumask_weight(topology_core_cpumask(cpu)) > 1) ? 2 : 20; } /* diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 0b81ad67d..664762447 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -29,6 +29,7 @@ #include <linux/kdebug.h> #include <asm/processor.h> #include <asm/insn.h> +#include <asm/mmu_context.h> /* Post-execution fixups. */ @@ -312,11 +313,6 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool } #ifdef CONFIG_X86_64 -static inline bool is_64bit_mm(struct mm_struct *mm) -{ - return !config_enabled(CONFIG_IA32_EMULATION) || - !(mm->context.ia32_compat == TIF_IA32); -} /* * If arch_uprobe->insn doesn't use rip-relative addressing, return * immediately. Otherwise, rewrite the instruction so that it accesses @@ -497,10 +493,6 @@ static void riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) } } #else /* 32-bit: */ -static inline bool is_64bit_mm(struct mm_struct *mm) -{ - return false; -} /* * No RIP-relative addressing on 32-bit */ diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index ee22c1d93..b034b1b14 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -72,7 +72,7 @@ asmlinkage __visible void vsmp_irq_enable(void) } PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_enable); -static unsigned __init_or_module vsmp_patch(u8 type, u16 clobbers, void *ibuf, +static unsigned __init vsmp_patch(u8 type, u16 clobbers, void *ibuf, unsigned long addr, unsigned len) { switch (type) { diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index 37d8fa443..a0695be19 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -75,7 +75,5 @@ EXPORT_SYMBOL(native_load_gs_index); #ifdef CONFIG_PREEMPT EXPORT_SYMBOL(___preempt_schedule); -#ifdef CONFIG_CONTEXT_TRACKING -EXPORT_SYMBOL(___preempt_schedule_context); -#endif +EXPORT_SYMBOL(___preempt_schedule_notrace); #endif diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 234b0722d..3839628d9 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -11,7 +11,6 @@ #include <asm/bios_ebda.h> #include <asm/paravirt.h> #include <asm/pci_x86.h> -#include <asm/pci.h> #include <asm/mpspec.h> #include <asm/setup.h> #include <asm/apic.h> @@ -111,11 +110,9 @@ EXPORT_SYMBOL_GPL(x86_platform); #if defined(CONFIG_PCI_MSI) struct x86_msi_ops x86_msi = { .setup_msi_irqs = native_setup_msi_irqs, - .compose_msi_msg = native_compose_msi_msg, .teardown_msi_irq = native_teardown_msi_irq, .teardown_msi_irqs = default_teardown_msi_irqs, .restore_msi_irqs = default_restore_msi_irqs, - .setup_hpet_msi = default_setup_hpet_msi, }; /* MSI arch specific hooks */ @@ -141,13 +138,6 @@ void arch_restore_msi_irqs(struct pci_dev *dev) #endif struct x86_io_apic_ops x86_io_apic_ops = { - .init = native_io_apic_init_mappings, .read = native_io_apic_read, - .write = native_io_apic_write, - .modify = native_io_apic_modify, .disable = native_disable_io_apic, - .print_entries = native_io_apic_print_entries, - .set_affinity = native_ioapic_set_affinity, - .setup_entry = native_setup_ioapic_entry, - .eoi_ioapic_pin = native_eoi_ioapic_pin, }; diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c deleted file mode 100644 index 87a815b85..000000000 --- a/arch/x86/kernel/xsave.c +++ /dev/null @@ -1,724 +0,0 @@ -/* - * xsave/xrstor support. - * - * Author: Suresh Siddha <suresh.b.siddha@intel.com> - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/bootmem.h> -#include <linux/compat.h> -#include <linux/cpu.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> -#include <asm/sigframe.h> -#include <asm/tlbflush.h> -#include <asm/xcr.h> - -/* - * Supported feature mask by the CPU and the kernel. - */ -u64 pcntxt_mask; - -/* - * Represents init state for the supported extended state. - */ -struct xsave_struct *init_xstate_buf; - -static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32; -static unsigned int *xstate_offsets, *xstate_sizes; -static unsigned int xstate_comp_offsets[sizeof(pcntxt_mask)*8]; -static unsigned int xstate_features; - -/* - * If a processor implementation discern that a processor state component is - * in its initialized state it may modify the corresponding bit in the - * xsave_hdr.xstate_bv as '0', with out modifying the corresponding memory - * layout in the case of xsaveopt. While presenting the xstate information to - * the user, we always ensure that the memory layout of a feature will be in - * the init state if the corresponding header bit is zero. This is to ensure - * that the user doesn't see some stale state in the memory layout during - * signal handling, debugging etc. - */ -void __sanitize_i387_state(struct task_struct *tsk) -{ - struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave; - int feature_bit = 0x2; - u64 xstate_bv; - - if (!fx) - return; - - xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv; - - /* - * None of the feature bits are in init state. So nothing else - * to do for us, as the memory layout is up to date. - */ - if ((xstate_bv & pcntxt_mask) == pcntxt_mask) - return; - - /* - * FP is in init state - */ - if (!(xstate_bv & XSTATE_FP)) { - fx->cwd = 0x37f; - fx->swd = 0; - fx->twd = 0; - fx->fop = 0; - fx->rip = 0; - fx->rdp = 0; - memset(&fx->st_space[0], 0, 128); - } - - /* - * SSE is in init state - */ - if (!(xstate_bv & XSTATE_SSE)) - memset(&fx->xmm_space[0], 0, 256); - - xstate_bv = (pcntxt_mask & ~xstate_bv) >> 2; - - /* - * Update all the other memory layouts for which the corresponding - * header bit is in the init state. - */ - while (xstate_bv) { - if (xstate_bv & 0x1) { - int offset = xstate_offsets[feature_bit]; - int size = xstate_sizes[feature_bit]; - - memcpy(((void *) fx) + offset, - ((void *) init_xstate_buf) + offset, - size); - } - - xstate_bv >>= 1; - feature_bit++; - } -} - -/* - * Check for the presence of extended state information in the - * user fpstate pointer in the sigcontext. - */ -static inline int check_for_xstate(struct i387_fxsave_struct __user *buf, - void __user *fpstate, - struct _fpx_sw_bytes *fx_sw) -{ - int min_xstate_size = sizeof(struct i387_fxsave_struct) + - sizeof(struct xsave_hdr_struct); - unsigned int magic2; - - if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw))) - return -1; - - /* Check for the first magic field and other error scenarios. */ - if (fx_sw->magic1 != FP_XSTATE_MAGIC1 || - fx_sw->xstate_size < min_xstate_size || - fx_sw->xstate_size > xstate_size || - fx_sw->xstate_size > fx_sw->extended_size) - return -1; - - /* - * Check for the presence of second magic word at the end of memory - * layout. This detects the case where the user just copied the legacy - * fpstate layout with out copying the extended state information - * in the memory layout. - */ - if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size)) - || magic2 != FP_XSTATE_MAGIC2) - return -1; - - return 0; -} - -/* - * Signal frame handlers. - */ -static inline int save_fsave_header(struct task_struct *tsk, void __user *buf) -{ - if (use_fxsr()) { - struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave; - struct user_i387_ia32_struct env; - struct _fpstate_ia32 __user *fp = buf; - - convert_from_fxsr(&env, tsk); - - if (__copy_to_user(buf, &env, sizeof(env)) || - __put_user(xsave->i387.swd, &fp->status) || - __put_user(X86_FXSR_MAGIC, &fp->magic)) - return -1; - } else { - struct i387_fsave_struct __user *fp = buf; - u32 swd; - if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status)) - return -1; - } - - return 0; -} - -static inline int save_xstate_epilog(void __user *buf, int ia32_frame) -{ - struct xsave_struct __user *x = buf; - struct _fpx_sw_bytes *sw_bytes; - u32 xstate_bv; - int err; - - /* Setup the bytes not touched by the [f]xsave and reserved for SW. */ - sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved; - err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes)); - - if (!use_xsave()) - return err; - - err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size)); - - /* - * Read the xstate_bv which we copied (directly from the cpu or - * from the state in task struct) to the user buffers. - */ - err |= __get_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv); - - /* - * For legacy compatible, we always set FP/SSE bits in the bit - * vector while saving the state to the user context. This will - * enable us capturing any changes(during sigreturn) to - * the FP/SSE bits by the legacy applications which don't touch - * xstate_bv in the xsave header. - * - * xsave aware apps can change the xstate_bv in the xsave - * header as well as change any contents in the memory layout. - * xrestore as part of sigreturn will capture all the changes. - */ - xstate_bv |= XSTATE_FPSSE; - - err |= __put_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv); - - return err; -} - -static inline int save_user_xstate(struct xsave_struct __user *buf) -{ - int err; - - if (use_xsave()) - err = xsave_user(buf); - else if (use_fxsr()) - err = fxsave_user((struct i387_fxsave_struct __user *) buf); - else - err = fsave_user((struct i387_fsave_struct __user *) buf); - - if (unlikely(err) && __clear_user(buf, xstate_size)) - err = -EFAULT; - return err; -} - -/* - * Save the fpu, extended register state to the user signal frame. - * - * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save - * state is copied. - * 'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'. - * - * buf == buf_fx for 64-bit frames and 32-bit fsave frame. - * buf != buf_fx for 32-bit frames with fxstate. - * - * If the fpu, extended register state is live, save the state directly - * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise, - * copy the thread's fpu state to the user frame starting at 'buf_fx'. - * - * If this is a 32-bit frame with fxstate, put a fsave header before - * the aligned state at 'buf_fx'. - * - * For [f]xsave state, update the SW reserved fields in the [f]xsave frame - * indicating the absence/presence of the extended state to the user. - */ -int save_xstate_sig(void __user *buf, void __user *buf_fx, int size) -{ - struct xsave_struct *xsave = ¤t->thread.fpu.state->xsave; - struct task_struct *tsk = current; - int ia32_fxstate = (buf != buf_fx); - - ia32_fxstate &= (config_enabled(CONFIG_X86_32) || - config_enabled(CONFIG_IA32_EMULATION)); - - if (!access_ok(VERIFY_WRITE, buf, size)) - return -EACCES; - - if (!static_cpu_has(X86_FEATURE_FPU)) - return fpregs_soft_get(current, NULL, 0, - sizeof(struct user_i387_ia32_struct), NULL, - (struct _fpstate_ia32 __user *) buf) ? -1 : 1; - - if (user_has_fpu()) { - /* Save the live register state to the user directly. */ - if (save_user_xstate(buf_fx)) - return -1; - /* Update the thread's fxstate to save the fsave header. */ - if (ia32_fxstate) - fpu_fxsave(&tsk->thread.fpu); - } else { - sanitize_i387_state(tsk); - if (__copy_to_user(buf_fx, xsave, xstate_size)) - return -1; - } - - /* Save the fsave header for the 32-bit frames. */ - if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf)) - return -1; - - if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate)) - return -1; - - return 0; -} - -static inline void -sanitize_restored_xstate(struct task_struct *tsk, - struct user_i387_ia32_struct *ia32_env, - u64 xstate_bv, int fx_only) -{ - struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave; - struct xsave_hdr_struct *xsave_hdr = &xsave->xsave_hdr; - - if (use_xsave()) { - /* These bits must be zero. */ - memset(xsave_hdr->reserved, 0, 48); - - /* - * Init the state that is not present in the memory - * layout and not enabled by the OS. - */ - if (fx_only) - xsave_hdr->xstate_bv = XSTATE_FPSSE; - else - xsave_hdr->xstate_bv &= (pcntxt_mask & xstate_bv); - } - - if (use_fxsr()) { - /* - * mscsr reserved bits must be masked to zero for security - * reasons. - */ - xsave->i387.mxcsr &= mxcsr_feature_mask; - - convert_to_fxsr(tsk, ia32_env); - } -} - -/* - * Restore the extended state if present. Otherwise, restore the FP/SSE state. - */ -static inline int restore_user_xstate(void __user *buf, u64 xbv, int fx_only) -{ - if (use_xsave()) { - if ((unsigned long)buf % 64 || fx_only) { - u64 init_bv = pcntxt_mask & ~XSTATE_FPSSE; - xrstor_state(init_xstate_buf, init_bv); - return fxrstor_user(buf); - } else { - u64 init_bv = pcntxt_mask & ~xbv; - if (unlikely(init_bv)) - xrstor_state(init_xstate_buf, init_bv); - return xrestore_user(buf, xbv); - } - } else if (use_fxsr()) { - return fxrstor_user(buf); - } else - return frstor_user(buf); -} - -int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) -{ - int ia32_fxstate = (buf != buf_fx); - struct task_struct *tsk = current; - int state_size = xstate_size; - u64 xstate_bv = 0; - int fx_only = 0; - - ia32_fxstate &= (config_enabled(CONFIG_X86_32) || - config_enabled(CONFIG_IA32_EMULATION)); - - if (!buf) { - fpu_reset_state(tsk); - return 0; - } - - if (!access_ok(VERIFY_READ, buf, size)) - return -EACCES; - - if (!used_math() && init_fpu(tsk)) - return -1; - - if (!static_cpu_has(X86_FEATURE_FPU)) - return fpregs_soft_set(current, NULL, - 0, sizeof(struct user_i387_ia32_struct), - NULL, buf) != 0; - - if (use_xsave()) { - struct _fpx_sw_bytes fx_sw_user; - if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) { - /* - * Couldn't find the extended state information in the - * memory layout. Restore just the FP/SSE and init all - * the other extended state. - */ - state_size = sizeof(struct i387_fxsave_struct); - fx_only = 1; - } else { - state_size = fx_sw_user.xstate_size; - xstate_bv = fx_sw_user.xstate_bv; - } - } - - if (ia32_fxstate) { - /* - * For 32-bit frames with fxstate, copy the user state to the - * thread's fpu state, reconstruct fxstate from the fsave - * header. Sanitize the copied state etc. - */ - struct fpu *fpu = &tsk->thread.fpu; - struct user_i387_ia32_struct env; - int err = 0; - - /* - * Drop the current fpu which clears used_math(). This ensures - * that any context-switch during the copy of the new state, - * avoids the intermediate state from getting restored/saved. - * Thus avoiding the new restored state from getting corrupted. - * We will be ready to restore/save the state only after - * set_used_math() is again set. - */ - drop_fpu(tsk); - - if (__copy_from_user(&fpu->state->xsave, buf_fx, state_size) || - __copy_from_user(&env, buf, sizeof(env))) { - fpu_finit(fpu); - err = -1; - } else { - sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only); - } - - set_used_math(); - if (use_eager_fpu()) { - preempt_disable(); - math_state_restore(); - preempt_enable(); - } - - return err; - } else { - /* - * For 64-bit frames and 32-bit fsave frames, restore the user - * state to the registers directly (with exceptions handled). - */ - user_fpu_begin(); - if (restore_user_xstate(buf_fx, xstate_bv, fx_only)) { - fpu_reset_state(tsk); - return -1; - } - } - - return 0; -} - -/* - * Prepare the SW reserved portion of the fxsave memory layout, indicating - * the presence of the extended state information in the memory layout - * pointed by the fpstate pointer in the sigcontext. - * This will be saved when ever the FP and extended state context is - * saved on the user stack during the signal handler delivery to the user. - */ -static void prepare_fx_sw_frame(void) -{ - int fsave_header_size = sizeof(struct i387_fsave_struct); - int size = xstate_size + FP_XSTATE_MAGIC2_SIZE; - - if (config_enabled(CONFIG_X86_32)) - size += fsave_header_size; - - fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1; - fx_sw_reserved.extended_size = size; - fx_sw_reserved.xstate_bv = pcntxt_mask; - fx_sw_reserved.xstate_size = xstate_size; - - if (config_enabled(CONFIG_IA32_EMULATION)) { - fx_sw_reserved_ia32 = fx_sw_reserved; - fx_sw_reserved_ia32.extended_size += fsave_header_size; - } -} - -/* - * Enable the extended processor state save/restore feature - */ -static inline void xstate_enable(void) -{ - cr4_set_bits(X86_CR4_OSXSAVE); - xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask); -} - -/* - * Record the offsets and sizes of different state managed by the xsave - * memory layout. - */ -static void __init setup_xstate_features(void) -{ - int eax, ebx, ecx, edx, leaf = 0x2; - - xstate_features = fls64(pcntxt_mask); - xstate_offsets = alloc_bootmem(xstate_features * sizeof(int)); - xstate_sizes = alloc_bootmem(xstate_features * sizeof(int)); - - do { - cpuid_count(XSTATE_CPUID, leaf, &eax, &ebx, &ecx, &edx); - - if (eax == 0) - break; - - xstate_offsets[leaf] = ebx; - xstate_sizes[leaf] = eax; - - leaf++; - } while (1); -} - -/* - * This function sets up offsets and sizes of all extended states in - * xsave area. This supports both standard format and compacted format - * of the xsave aread. - * - * Input: void - * Output: void - */ -void setup_xstate_comp(void) -{ - unsigned int xstate_comp_sizes[sizeof(pcntxt_mask)*8]; - int i; - - /* - * The FP xstates and SSE xstates are legacy states. They are always - * in the fixed offsets in the xsave area in either compacted form - * or standard form. - */ - xstate_comp_offsets[0] = 0; - xstate_comp_offsets[1] = offsetof(struct i387_fxsave_struct, xmm_space); - - if (!cpu_has_xsaves) { - for (i = 2; i < xstate_features; i++) { - if (test_bit(i, (unsigned long *)&pcntxt_mask)) { - xstate_comp_offsets[i] = xstate_offsets[i]; - xstate_comp_sizes[i] = xstate_sizes[i]; - } - } - return; - } - - xstate_comp_offsets[2] = FXSAVE_SIZE + XSAVE_HDR_SIZE; - - for (i = 2; i < xstate_features; i++) { - if (test_bit(i, (unsigned long *)&pcntxt_mask)) - xstate_comp_sizes[i] = xstate_sizes[i]; - else - xstate_comp_sizes[i] = 0; - - if (i > 2) - xstate_comp_offsets[i] = xstate_comp_offsets[i-1] - + xstate_comp_sizes[i-1]; - - } -} - -/* - * setup the xstate image representing the init state - */ -static void __init setup_init_fpu_buf(void) -{ - /* - * Setup init_xstate_buf to represent the init state of - * all the features managed by the xsave - */ - init_xstate_buf = alloc_bootmem_align(xstate_size, - __alignof__(struct xsave_struct)); - fx_finit(&init_xstate_buf->i387); - - if (!cpu_has_xsave) - return; - - setup_xstate_features(); - - if (cpu_has_xsaves) { - init_xstate_buf->xsave_hdr.xcomp_bv = - (u64)1 << 63 | pcntxt_mask; - init_xstate_buf->xsave_hdr.xstate_bv = pcntxt_mask; - } - - /* - * Init all the features state with header_bv being 0x0 - */ - xrstor_state_booting(init_xstate_buf, -1); - /* - * Dump the init state again. This is to identify the init state - * of any feature which is not represented by all zero's. - */ - xsave_state_booting(init_xstate_buf, -1); -} - -static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO; -static int __init eager_fpu_setup(char *s) -{ - if (!strcmp(s, "on")) - eagerfpu = ENABLE; - else if (!strcmp(s, "off")) - eagerfpu = DISABLE; - else if (!strcmp(s, "auto")) - eagerfpu = AUTO; - return 1; -} -__setup("eagerfpu=", eager_fpu_setup); - - -/* - * Calculate total size of enabled xstates in XCR0/pcntxt_mask. - */ -static void __init init_xstate_size(void) -{ - unsigned int eax, ebx, ecx, edx; - int i; - - if (!cpu_has_xsaves) { - cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); - xstate_size = ebx; - return; - } - - xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE; - for (i = 2; i < 64; i++) { - if (test_bit(i, (unsigned long *)&pcntxt_mask)) { - cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); - xstate_size += eax; - } - } -} - -/* - * Enable and initialize the xsave feature. - */ -static void __init xstate_enable_boot_cpu(void) -{ - unsigned int eax, ebx, ecx, edx; - - if (boot_cpu_data.cpuid_level < XSTATE_CPUID) { - WARN(1, KERN_ERR "XSTATE_CPUID missing\n"); - return; - } - - cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); - pcntxt_mask = eax + ((u64)edx << 32); - - if ((pcntxt_mask & XSTATE_FPSSE) != XSTATE_FPSSE) { - pr_err("FP/SSE not shown under xsave features 0x%llx\n", - pcntxt_mask); - BUG(); - } - - /* - * Support only the state known to OS. - */ - pcntxt_mask = pcntxt_mask & XCNTXT_MASK; - - xstate_enable(); - - /* - * Recompute the context size for enabled features - */ - init_xstate_size(); - - update_regset_xstate_info(xstate_size, pcntxt_mask); - prepare_fx_sw_frame(); - setup_init_fpu_buf(); - - /* Auto enable eagerfpu for xsaveopt */ - if (cpu_has_xsaveopt && eagerfpu != DISABLE) - eagerfpu = ENABLE; - - if (pcntxt_mask & XSTATE_EAGER) { - if (eagerfpu == DISABLE) { - pr_err("eagerfpu not present, disabling some xstate features: 0x%llx\n", - pcntxt_mask & XSTATE_EAGER); - pcntxt_mask &= ~XSTATE_EAGER; - } else { - eagerfpu = ENABLE; - } - } - - pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x using %s\n", - pcntxt_mask, xstate_size, - cpu_has_xsaves ? "compacted form" : "standard form"); -} - -/* - * For the very first instance, this calls xstate_enable_boot_cpu(); - * for all subsequent instances, this calls xstate_enable(). - * - * This is somewhat obfuscated due to the lack of powerful enough - * overrides for the section checks. - */ -void xsave_init(void) -{ - static __refdata void (*next_func)(void) = xstate_enable_boot_cpu; - void (*this_func)(void); - - if (!cpu_has_xsave) - return; - - this_func = next_func; - next_func = xstate_enable; - this_func(); -} - -/* - * setup_init_fpu_buf() is __init and it is OK to call it here because - * init_xstate_buf will be unset only once during boot. - */ -void __init_refok eager_fpu_init(void) -{ - WARN_ON(used_math()); - current_thread_info()->status = 0; - - if (eagerfpu == ENABLE) - setup_force_cpu_cap(X86_FEATURE_EAGER_FPU); - - if (!cpu_has_eager_fpu) { - stts(); - return; - } - - if (!init_xstate_buf) - setup_init_fpu_buf(); -} - -/* - * Given the xsave area and a state inside, this function returns the - * address of the state. - * - * This is the API that is called to get xstate address in either - * standard format or compacted format of xsave area. - * - * Inputs: - * xsave: base address of the xsave area; - * xstate: state which is defined in xsave.h (e.g. XSTATE_FP, XSTATE_SSE, - * etc.) - * Output: - * address of the state in the xsave area. - */ -void *get_xsave_addr(struct xsave_struct *xsave, int xstate) -{ - int feature = fls64(xstate) - 1; - if (!test_bit(feature, (unsigned long *)&pcntxt_mask)) - return NULL; - - return (void *)xsave + xstate_comp_offsets[feature]; -} -EXPORT_SYMBOL_GPL(get_xsave_addr); diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 413a7bf9e..d8a1d5627 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -86,15 +86,16 @@ config KVM_MMU_AUDIT auditing of KVM MMU events at runtime. config KVM_DEVICE_ASSIGNMENT - bool "KVM legacy PCI device assignment support" + bool "KVM legacy PCI device assignment support (DEPRECATED)" depends on KVM && PCI && IOMMU_API - default y + default n ---help--- Provide support for legacy PCI device assignment through KVM. The kernel now also supports a full featured userspace device driver - framework through VFIO, which supersedes much of this support. + framework through VFIO, which supersedes this support and provides + better security. - If unsure, say Y. + If unsure, say N. # OK, it's a little counter-intuitive to do this, but it puts it neatly under # the virtualization menu. diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 16e8f962e..67d215cb8 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -12,10 +12,10 @@ kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \ kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ - i8254.o ioapic.o irq_comm.o cpuid.o pmu.o + i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += assigned-dev.o iommu.o -kvm-intel-y += vmx.o -kvm-amd-y += svm.o +kvm-intel-y += vmx.o pmu_intel.o +kvm-amd-y += svm.o pmu_amd.o obj-$(CONFIG_KVM) += kvm.o obj-$(CONFIG_KVM_INTEL) += kvm-intel.o diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 1d08ad358..2fbea2544 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -16,14 +16,14 @@ #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> -#include <asm/i387.h> /* For use_eager_fpu. Ugh! */ -#include <asm/fpu-internal.h> /* For use_eager_fpu. Ugh! */ +#include <asm/fpu/internal.h> /* For use_eager_fpu. Ugh! */ #include <asm/user.h> -#include <asm/xsave.h> +#include <asm/fpu/xstate.h> #include "cpuid.h" #include "lapic.h" #include "mmu.h" #include "trace.h" +#include "pmu.h" static u32 xstate_required_size(u64 xstate_bv, bool compacted) { @@ -97,7 +97,9 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) if (best && (best->eax & (F(XSAVES) | F(XSAVEC)))) best->ebx = xstate_required_size(vcpu->arch.xcr0, true); - vcpu->arch.eager_fpu = guest_cpuid_has_mpx(vcpu); + vcpu->arch.eager_fpu = use_eager_fpu() || guest_cpuid_has_mpx(vcpu); + if (vcpu->arch.eager_fpu) + kvm_x86_ops->fpu_activate(vcpu); /* * The existing code assumes virtual address is 48-bit in the canonical @@ -111,7 +113,7 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) /* Update physical-address width */ vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); - kvm_pmu_cpuid_update(vcpu); + kvm_pmu_refresh(vcpu); return 0; } @@ -415,6 +417,12 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, } break; } + case 6: /* Thermal management */ + entry->eax = 0x4; /* allow ARAT */ + entry->ebx = 0; + entry->ecx = 0; + entry->edx = 0; + break; case 7: { entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; /* Mask ebx against host capability word 9 */ @@ -591,7 +599,6 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, break; case 3: /* Processor serial number */ case 5: /* MONITOR/MWAIT */ - case 6: /* Thermal management */ case 0xC0000002: case 0xC0000003: case 0xC0000004: diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 496b3695d..dd05b9cef 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -70,6 +70,14 @@ static inline bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu) return best && (best->ebx & bit(X86_FEATURE_FSGSBASE)); } +static inline bool guest_cpuid_has_longmode(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); + return best && (best->edx & bit(X86_FEATURE_LM)); +} + static inline bool guest_cpuid_has_osvw(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 630bcb0d7..e7a4fde5d 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -25,6 +25,7 @@ #include <linux/module.h> #include <asm/kvm_emulate.h> #include <linux/stringify.h> +#include <asm/debugreg.h> #include "x86.h" #include "tss.h" @@ -523,13 +524,9 @@ static void masked_increment(ulong *reg, ulong mask, int inc) static inline void register_address_increment(struct x86_emulate_ctxt *ctxt, int reg, int inc) { - ulong mask; + ulong *preg = reg_rmw(ctxt, reg); - if (ctxt->ad_bytes == sizeof(unsigned long)) - mask = ~0UL; - else - mask = ad_mask(ctxt); - masked_increment(reg_rmw(ctxt, reg), mask, inc); + assign_register(preg, *preg + inc, ctxt->ad_bytes); } static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc) @@ -2262,6 +2259,260 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt) return rc; } +static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt) +{ + u32 eax, ebx, ecx, edx; + + eax = 0x80000001; + ecx = 0; + ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx); + return edx & bit(X86_FEATURE_LM); +} + +#define GET_SMSTATE(type, smbase, offset) \ + ({ \ + type __val; \ + int r = ctxt->ops->read_std(ctxt, smbase + offset, &__val, \ + sizeof(__val), NULL); \ + if (r != X86EMUL_CONTINUE) \ + return X86EMUL_UNHANDLEABLE; \ + __val; \ + }) + +static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags) +{ + desc->g = (flags >> 23) & 1; + desc->d = (flags >> 22) & 1; + desc->l = (flags >> 21) & 1; + desc->avl = (flags >> 20) & 1; + desc->p = (flags >> 15) & 1; + desc->dpl = (flags >> 13) & 3; + desc->s = (flags >> 12) & 1; + desc->type = (flags >> 8) & 15; +} + +static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, u64 smbase, int n) +{ + struct desc_struct desc; + int offset; + u16 selector; + + selector = GET_SMSTATE(u32, smbase, 0x7fa8 + n * 4); + + if (n < 3) + offset = 0x7f84 + n * 12; + else + offset = 0x7f2c + (n - 3) * 12; + + set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8)); + set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4)); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, offset)); + ctxt->ops->set_segment(ctxt, selector, &desc, 0, n); + return X86EMUL_CONTINUE; +} + +static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n) +{ + struct desc_struct desc; + int offset; + u16 selector; + u32 base3; + + offset = 0x7e00 + n * 16; + + selector = GET_SMSTATE(u16, smbase, offset); + rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smbase, offset + 2) << 8); + set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4)); + set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8)); + base3 = GET_SMSTATE(u32, smbase, offset + 12); + + ctxt->ops->set_segment(ctxt, selector, &desc, base3, n); + return X86EMUL_CONTINUE; +} + +static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt, + u64 cr0, u64 cr4) +{ + int bad; + + /* + * First enable PAE, long mode needs it before CR0.PG = 1 is set. + * Then enable protected mode. However, PCID cannot be enabled + * if EFER.LMA=0, so set it separately. + */ + bad = ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE); + if (bad) + return X86EMUL_UNHANDLEABLE; + + bad = ctxt->ops->set_cr(ctxt, 0, cr0); + if (bad) + return X86EMUL_UNHANDLEABLE; + + if (cr4 & X86_CR4_PCIDE) { + bad = ctxt->ops->set_cr(ctxt, 4, cr4); + if (bad) + return X86EMUL_UNHANDLEABLE; + } + + return X86EMUL_CONTINUE; +} + +static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase) +{ + struct desc_struct desc; + struct desc_ptr dt; + u16 selector; + u32 val, cr0, cr4; + int i; + + cr0 = GET_SMSTATE(u32, smbase, 0x7ffc); + ctxt->ops->set_cr(ctxt, 3, GET_SMSTATE(u32, smbase, 0x7ff8)); + ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED; + ctxt->_eip = GET_SMSTATE(u32, smbase, 0x7ff0); + + for (i = 0; i < 8; i++) + *reg_write(ctxt, i) = GET_SMSTATE(u32, smbase, 0x7fd0 + i * 4); + + val = GET_SMSTATE(u32, smbase, 0x7fcc); + ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1); + val = GET_SMSTATE(u32, smbase, 0x7fc8); + ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1); + + selector = GET_SMSTATE(u32, smbase, 0x7fc4); + set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f64)); + set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f60)); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f5c)); + ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR); + + selector = GET_SMSTATE(u32, smbase, 0x7fc0); + set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f80)); + set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f7c)); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f78)); + ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR); + + dt.address = GET_SMSTATE(u32, smbase, 0x7f74); + dt.size = GET_SMSTATE(u32, smbase, 0x7f70); + ctxt->ops->set_gdt(ctxt, &dt); + + dt.address = GET_SMSTATE(u32, smbase, 0x7f58); + dt.size = GET_SMSTATE(u32, smbase, 0x7f54); + ctxt->ops->set_idt(ctxt, &dt); + + for (i = 0; i < 6; i++) { + int r = rsm_load_seg_32(ctxt, smbase, i); + if (r != X86EMUL_CONTINUE) + return r; + } + + cr4 = GET_SMSTATE(u32, smbase, 0x7f14); + + ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8)); + + return rsm_enter_protected_mode(ctxt, cr0, cr4); +} + +static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase) +{ + struct desc_struct desc; + struct desc_ptr dt; + u64 val, cr0, cr4; + u32 base3; + u16 selector; + int i; + + for (i = 0; i < 16; i++) + *reg_write(ctxt, i) = GET_SMSTATE(u64, smbase, 0x7ff8 - i * 8); + + ctxt->_eip = GET_SMSTATE(u64, smbase, 0x7f78); + ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7f70) | X86_EFLAGS_FIXED; + + val = GET_SMSTATE(u32, smbase, 0x7f68); + ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1); + val = GET_SMSTATE(u32, smbase, 0x7f60); + ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1); + + cr0 = GET_SMSTATE(u64, smbase, 0x7f58); + ctxt->ops->set_cr(ctxt, 3, GET_SMSTATE(u64, smbase, 0x7f50)); + cr4 = GET_SMSTATE(u64, smbase, 0x7f48); + ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00)); + val = GET_SMSTATE(u64, smbase, 0x7ed0); + ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA); + + selector = GET_SMSTATE(u32, smbase, 0x7e90); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e92) << 8); + set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e94)); + set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e98)); + base3 = GET_SMSTATE(u32, smbase, 0x7e9c); + ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR); + + dt.size = GET_SMSTATE(u32, smbase, 0x7e84); + dt.address = GET_SMSTATE(u64, smbase, 0x7e88); + ctxt->ops->set_idt(ctxt, &dt); + + selector = GET_SMSTATE(u32, smbase, 0x7e70); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e72) << 8); + set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e74)); + set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e78)); + base3 = GET_SMSTATE(u32, smbase, 0x7e7c); + ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR); + + dt.size = GET_SMSTATE(u32, smbase, 0x7e64); + dt.address = GET_SMSTATE(u64, smbase, 0x7e68); + ctxt->ops->set_gdt(ctxt, &dt); + + for (i = 0; i < 6; i++) { + int r = rsm_load_seg_64(ctxt, smbase, i); + if (r != X86EMUL_CONTINUE) + return r; + } + + return rsm_enter_protected_mode(ctxt, cr0, cr4); +} + +static int em_rsm(struct x86_emulate_ctxt *ctxt) +{ + unsigned long cr0, cr4, efer; + u64 smbase; + int ret; + + if ((ctxt->emul_flags & X86EMUL_SMM_MASK) == 0) + return emulate_ud(ctxt); + + /* + * Get back to real mode, to prepare a safe state in which to load + * CR0/CR3/CR4/EFER. Also this will ensure that addresses passed + * to read_std/write_std are not virtual. + * + * CR4.PCIDE must be zero, because it is a 64-bit mode only feature. + */ + cr0 = ctxt->ops->get_cr(ctxt, 0); + if (cr0 & X86_CR0_PE) + ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE)); + cr4 = ctxt->ops->get_cr(ctxt, 4); + if (cr4 & X86_CR4_PAE) + ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE); + efer = 0; + ctxt->ops->set_msr(ctxt, MSR_EFER, efer); + + smbase = ctxt->ops->get_smbase(ctxt); + if (emulator_has_longmode(ctxt)) + ret = rsm_load_state_64(ctxt, smbase + 0x8000); + else + ret = rsm_load_state_32(ctxt, smbase + 0x8000); + + if (ret != X86EMUL_CONTINUE) { + /* FIXME: should triple fault */ + return X86EMUL_UNHANDLEABLE; + } + + if ((ctxt->emul_flags & X86EMUL_SMM_INSIDE_NMI_MASK) == 0) + ctxt->ops->set_nmi_mask(ctxt, false); + + ctxt->emul_flags &= ~X86EMUL_SMM_INSIDE_NMI_MASK; + ctxt->emul_flags &= ~X86EMUL_SMM_MASK; + return X86EMUL_CONTINUE; +} + static void setup_syscalls_segments(struct x86_emulate_ctxt *ctxt, struct desc_struct *cs, struct desc_struct *ss) @@ -2573,6 +2824,30 @@ static bool emulator_io_permited(struct x86_emulate_ctxt *ctxt, return true; } +static void string_registers_quirk(struct x86_emulate_ctxt *ctxt) +{ + /* + * Intel CPUs mask the counter and pointers in quite strange + * manner when ECX is zero due to REP-string optimizations. + */ +#ifdef CONFIG_X86_64 + if (ctxt->ad_bytes != 4 || !vendor_intel(ctxt)) + return; + + *reg_write(ctxt, VCPU_REGS_RCX) = 0; + + switch (ctxt->b) { + case 0xa4: /* movsb */ + case 0xa5: /* movsd/w */ + *reg_rmw(ctxt, VCPU_REGS_RSI) &= (u32)-1; + /* fall through */ + case 0xaa: /* stosb */ + case 0xab: /* stosd/w */ + *reg_rmw(ctxt, VCPU_REGS_RDI) &= (u32)-1; + } +#endif +} + static void save_state_to_tss16(struct x86_emulate_ctxt *ctxt, struct tss_segment_16 *tss) { @@ -2849,7 +3124,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, ulong old_tss_base = ops->get_cached_segment_base(ctxt, VCPU_SREG_TR); u32 desc_limit; - ulong desc_addr; + ulong desc_addr, dr7; /* FIXME: old_tss_base == ~0 ? */ @@ -2934,6 +3209,9 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, ret = em_push(ctxt); } + ops->get_dr(ctxt, 7, &dr7); + ops->set_dr(ctxt, 7, dr7 & ~(DR_LOCAL_ENABLE_MASK | DR_LOCAL_SLOWDOWN)); + return ret; } @@ -3840,7 +4118,7 @@ static const struct opcode group5[] = { F(DstMem | SrcNone | Lock, em_inc), F(DstMem | SrcNone | Lock, em_dec), I(SrcMem | NearBranch, em_call_near_abs), - I(SrcMemFAddr | ImplicitOps | Stack, em_call_far), + I(SrcMemFAddr | ImplicitOps, em_call_far), I(SrcMem | NearBranch, em_jmp_abs), I(SrcMemFAddr | ImplicitOps, em_jmp_far), I(SrcMem | Stack, em_push), D(Undefined), @@ -4173,7 +4451,7 @@ static const struct opcode twobyte_table[256] = { F(DstMem | SrcReg | Src2CL | ModRM, em_shld), N, N, /* 0xA8 - 0xAF */ I(Stack | Src2GS, em_push_sreg), I(Stack | Src2GS, em_pop_sreg), - DI(ImplicitOps, rsm), + II(No64 | EmulateOnUD | ImplicitOps, em_rsm, rsm), F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_bts), F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shrd), F(DstMem | SrcReg | Src2CL | ModRM, em_shrd), @@ -4871,7 +5149,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) fetch_possible_mmx_operand(ctxt, &ctxt->dst); } - if (unlikely(ctxt->guest_mode) && (ctxt->d & Intercept)) { + if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_PRE_EXCEPT); if (rc != X86EMUL_CONTINUE) @@ -4900,7 +5178,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) goto done; } - if (unlikely(ctxt->guest_mode) && (ctxt->d & Intercept)) { + if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_POST_EXCEPT); if (rc != X86EMUL_CONTINUE) @@ -4910,6 +5188,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) if (ctxt->rep_prefix && (ctxt->d & String)) { /* All REP prefixes have the same first termination condition */ if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0) { + string_registers_quirk(ctxt); ctxt->eip = ctxt->_eip; ctxt->eflags &= ~X86_EFLAGS_RF; goto done; @@ -4953,7 +5232,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) special_insn: - if (unlikely(ctxt->guest_mode) && (ctxt->d & Intercept)) { + if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_POST_MEMACCESS); if (rc != X86EMUL_CONTINUE) diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 28146f03c..856f79105 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -349,6 +349,7 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status) irqe.delivery_mode = entry->fields.delivery_mode << 8; irqe.level = 1; irqe.shorthand = 0; + irqe.msi_redir_hint = false; if (irqe.trig_mode == IOAPIC_EDGE_TRIG) ioapic->irr_delivered |= 1 << irq; @@ -637,11 +638,9 @@ void kvm_ioapic_destroy(struct kvm *kvm) struct kvm_ioapic *ioapic = kvm->arch.vioapic; cancel_delayed_work_sync(&ioapic->eoi_inject); - if (ioapic) { - kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev); - kvm->arch.vioapic = NULL; - kfree(ioapic); - } + kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev); + kvm->arch.vioapic = NULL; + kfree(ioapic); } int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) diff --git a/arch/x86/kvm/iommu.c b/arch/x86/kvm/iommu.c index 7dbced309..5c520ebf6 100644 --- a/arch/x86/kvm/iommu.c +++ b/arch/x86/kvm/iommu.c @@ -200,6 +200,7 @@ int kvm_assign_device(struct kvm *kvm, struct pci_dev *pdev) goto out_unmap; } + kvm_arch_start_assignment(kvm); pci_set_dev_assigned(pdev); dev_info(&pdev->dev, "kvm assign device\n"); @@ -224,6 +225,7 @@ int kvm_deassign_device(struct kvm *kvm, struct pci_dev *pdev) iommu_detach_device(domain, &pdev->dev); pci_clear_dev_assigned(pdev); + kvm_arch_end_assignment(kvm); dev_info(&pdev->dev, "kvm deassign device\n"); diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 72298b3ac..9efff9e5b 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -31,6 +31,8 @@ #include "ioapic.h" +#include "lapic.h" + static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) @@ -48,11 +50,6 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, line_status); } -inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq) -{ - return irq->delivery_mode == APIC_DM_LOWEST; -} - int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, unsigned long *dest_map) { @@ -60,7 +57,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_vcpu *vcpu, *lowest = NULL; if (irq->dest_mode == 0 && irq->dest_id == 0xff && - kvm_is_dm_lowest_prio(irq)) { + kvm_lowest_prio_delivery(irq)) { printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n"); irq->delivery_mode = APIC_DM_FIXED; } @@ -76,7 +73,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, irq->dest_id, irq->dest_mode)) continue; - if (!kvm_is_dm_lowest_prio(irq)) { + if (!kvm_lowest_prio_delivery(irq)) { if (r < 0) r = 0; r += kvm_apic_set_irq(vcpu, irq, dest_map); @@ -106,9 +103,10 @@ static inline void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e, irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo; irq->trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data; irq->delivery_mode = e->msi.data & 0x700; + irq->msi_redir_hint = ((e->msi.address_lo + & MSI_ADDR_REDIRECTION_LOWPRI) > 0); irq->level = 1; irq->shorthand = 0; - /* TODO Deal with RH bit of MSI message address */ } int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 544076c4f..e1e89ee4a 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -99,4 +99,9 @@ static inline bool is_guest_mode(struct kvm_vcpu *vcpu) return vcpu->arch.hflags & HF_GUEST_MASK; } +static inline bool is_smm(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.hflags & HF_SMM_MASK; +} + #endif diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 67d07e051..2a5ca97c2 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -240,6 +240,15 @@ static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id) recalculate_apic_map(apic->vcpu->kvm); } +static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u8 id) +{ + u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf)); + + apic_set_reg(apic, APIC_ID, id << 24); + apic_set_reg(apic, APIC_LDR, ldr); + recalculate_apic_map(apic->vcpu->kvm); +} + static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type) { return !(kvm_apic_get_reg(apic, lvt_type) & APIC_LVT_MASKED); @@ -728,7 +737,7 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, dst = map->logical_map[cid]; - if (irq->delivery_mode == APIC_DM_LOWEST) { + if (kvm_lowest_prio_delivery(irq)) { int l = -1; for_each_set_bit(i, &bitmap, 16) { if (!dst[i]) @@ -799,7 +808,9 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, break; case APIC_DM_SMI: - apic_debug("Ignoring guest SMI\n"); + result = 1; + kvm_make_request(KVM_REQ_SMI, vcpu); + kvm_vcpu_kick(vcpu); break; case APIC_DM_NMI: @@ -914,9 +925,10 @@ static void apic_send_ipi(struct kvm_lapic *apic) irq.vector = icr_low & APIC_VECTOR_MASK; irq.delivery_mode = icr_low & APIC_MODE_MASK; irq.dest_mode = icr_low & APIC_DEST_MASK; - irq.level = icr_low & APIC_INT_ASSERT; + irq.level = (icr_low & APIC_INT_ASSERT) != 0; irq.trig_mode = icr_low & APIC_INT_LEVELTRIG; irq.shorthand = icr_low & APIC_SHORT_MASK; + irq.msi_redir_hint = false; if (apic_x2apic_mode(apic)) irq.dest_id = icr_high; else @@ -926,10 +938,11 @@ static void apic_send_ipi(struct kvm_lapic *apic) apic_debug("icr_high 0x%x, icr_low 0x%x, " "short_hand 0x%x, dest 0x%x, trig_mode 0x%x, level 0x%x, " - "dest_mode 0x%x, delivery_mode 0x%x, vector 0x%x\n", + "dest_mode 0x%x, delivery_mode 0x%x, vector 0x%x, " + "msi_redir_hint 0x%x\n", icr_high, icr_low, irq.shorthand, irq.dest_id, irq.trig_mode, irq.level, irq.dest_mode, irq.delivery_mode, - irq.vector); + irq.vector, irq.msi_redir_hint); kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq, NULL); } @@ -1244,16 +1257,17 @@ static void start_apic_timer(struct kvm_lapic *apic) static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val) { - int nmi_wd_enabled = apic_lvt_nmi_mode(kvm_apic_get_reg(apic, APIC_LVT0)); + bool lvt0_in_nmi_mode = apic_lvt_nmi_mode(lvt0_val); - if (apic_lvt_nmi_mode(lvt0_val)) { - if (!nmi_wd_enabled) { + if (apic->lvt0_in_nmi_mode != lvt0_in_nmi_mode) { + apic->lvt0_in_nmi_mode = lvt0_in_nmi_mode; + if (lvt0_in_nmi_mode) { apic_debug("Receive NMI setting on APIC_LVT0 " "for cpu %d\n", apic->vcpu->vcpu_id); atomic_inc(&apic->vcpu->kvm->arch.vapics_in_nmi_mode); - } - } else if (nmi_wd_enabled) - atomic_dec(&apic->vcpu->kvm->arch.vapics_in_nmi_mode); + } else + atomic_dec(&apic->vcpu->kvm->arch.vapics_in_nmi_mode); + } } static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) @@ -1541,9 +1555,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) if ((old_value ^ value) & X2APIC_ENABLE) { if (value & X2APIC_ENABLE) { - u32 id = kvm_apic_id(apic); - u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf)); - kvm_apic_set_ldr(apic, ldr); + kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id); kvm_x86_ops->set_virtual_x2apic_mode(vcpu, true); } else kvm_x86_ops->set_virtual_x2apic_mode(vcpu, false); @@ -1562,7 +1574,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) } -void kvm_lapic_reset(struct kvm_vcpu *vcpu) +void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) { struct kvm_lapic *apic; int i; @@ -1576,19 +1588,23 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu) /* Stop the timer in case it's a reset to an active apic */ hrtimer_cancel(&apic->lapic_timer.timer); - kvm_apic_set_id(apic, vcpu->vcpu_id); + if (!init_event) + kvm_apic_set_id(apic, vcpu->vcpu_id); kvm_apic_set_version(apic->vcpu); for (i = 0; i < APIC_LVT_NUM; i++) apic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED); apic_update_lvtt(apic); - apic_set_reg(apic, APIC_LVT0, - SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT)); + if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED)) + apic_set_reg(apic, APIC_LVT0, + SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT)); + apic_manage_nmi_watchdog(apic, kvm_apic_get_reg(apic, APIC_LVT0)); apic_set_reg(apic, APIC_DFR, 0xffffffffU); apic_set_spiv(apic, 0xff); apic_set_reg(apic, APIC_TASKPRI, 0); - kvm_apic_set_ldr(apic, 0); + if (!apic_x2apic_mode(apic)) + kvm_apic_set_ldr(apic, 0); apic_set_reg(apic, APIC_ESR, 0); apic_set_reg(apic, APIC_ICR, 0); apic_set_reg(apic, APIC_ICR2, 0); @@ -1717,7 +1733,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu) APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE); static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */ - kvm_lapic_reset(vcpu); + kvm_lapic_reset(vcpu, false); kvm_iodevice_init(&apic->dev, &apic_mmio_ops); return 0; @@ -2050,11 +2066,22 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) if (!kvm_vcpu_has_lapic(vcpu) || !apic->pending_events) return; - pe = xchg(&apic->pending_events, 0); + /* + * INITs are latched while in SMM. Because an SMM CPU cannot + * be in KVM_MP_STATE_INIT_RECEIVED state, just eat SIPIs + * and delay processing of INIT until the next RSM. + */ + if (is_smm(vcpu)) { + WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED); + if (test_bit(KVM_APIC_SIPI, &apic->pending_events)) + clear_bit(KVM_APIC_SIPI, &apic->pending_events); + return; + } + pe = xchg(&apic->pending_events, 0); if (test_bit(KVM_APIC_INIT, &pe)) { - kvm_lapic_reset(vcpu); - kvm_vcpu_reset(vcpu); + kvm_lapic_reset(vcpu, true); + kvm_vcpu_reset(vcpu, true); if (kvm_vcpu_is_bsp(apic->vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index c4ea87eed..719527482 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -26,6 +26,7 @@ struct kvm_lapic { struct kvm_vcpu *vcpu; bool sw_enabled; bool irr_pending; + bool lvt0_in_nmi_mode; /* Number of bits set in ISR. */ s16 isr_count; /* The highest vector set in ISR; if -1 - invalid, must scan ISR. */ @@ -48,7 +49,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu); int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu); int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu); void kvm_apic_accept_events(struct kvm_vcpu *vcpu); -void kvm_lapic_reset(struct kvm_vcpu *vcpu); +void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event); u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu); void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8); void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu); @@ -153,6 +154,17 @@ static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu) return kvm_vcpu_has_lapic(vcpu) && vcpu->arch.apic->pending_events; } +static inline bool kvm_lowest_prio_delivery(struct kvm_lapic_irq *irq) +{ + return (irq->delivery_mode == APIC_DM_LOWEST || + irq->msi_redir_hint); +} + +static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_has_lapic(vcpu) && test_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); +} + bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector); void wait_lapic_expire(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index b73337634..44171462b 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -223,15 +223,15 @@ static unsigned int get_mmio_spte_generation(u64 spte) return gen; } -static unsigned int kvm_current_mmio_generation(struct kvm *kvm) +static unsigned int kvm_current_mmio_generation(struct kvm_vcpu *vcpu) { - return kvm_memslots(kvm)->generation & MMIO_GEN_MASK; + return kvm_vcpu_memslots(vcpu)->generation & MMIO_GEN_MASK; } -static void mark_mmio_spte(struct kvm *kvm, u64 *sptep, u64 gfn, +static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, unsigned access) { - unsigned int gen = kvm_current_mmio_generation(kvm); + unsigned int gen = kvm_current_mmio_generation(vcpu); u64 mask = generation_mmio_spte_mask(gen); access &= ACC_WRITE_MASK | ACC_USER_MASK; @@ -258,22 +258,22 @@ static unsigned get_mmio_spte_access(u64 spte) return (spte & ~mask) & ~PAGE_MASK; } -static bool set_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn, +static bool set_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, pfn_t pfn, unsigned access) { if (unlikely(is_noslot_pfn(pfn))) { - mark_mmio_spte(kvm, sptep, gfn, access); + mark_mmio_spte(vcpu, sptep, gfn, access); return true; } return false; } -static bool check_mmio_spte(struct kvm *kvm, u64 spte) +static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte) { unsigned int kvm_gen, spte_gen; - kvm_gen = kvm_current_mmio_generation(kvm); + kvm_gen = kvm_current_mmio_generation(vcpu); spte_gen = get_mmio_spte_generation(spte); trace_check_mmio_spte(spte, kvm_gen, spte_gen); @@ -804,30 +804,36 @@ static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn, return &slot->arch.lpage_info[level - 2][idx]; } -static void account_shadowed(struct kvm *kvm, gfn_t gfn) +static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) { + struct kvm_memslots *slots; struct kvm_memory_slot *slot; struct kvm_lpage_info *linfo; + gfn_t gfn; int i; - slot = gfn_to_memslot(kvm, gfn); - for (i = PT_DIRECTORY_LEVEL; - i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { + gfn = sp->gfn; + slots = kvm_memslots_for_spte_role(kvm, sp->role); + slot = __gfn_to_memslot(slots, gfn); + for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { linfo = lpage_info_slot(gfn, slot, i); linfo->write_count += 1; } kvm->arch.indirect_shadow_pages++; } -static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn) +static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) { + struct kvm_memslots *slots; struct kvm_memory_slot *slot; struct kvm_lpage_info *linfo; + gfn_t gfn; int i; - slot = gfn_to_memslot(kvm, gfn); - for (i = PT_DIRECTORY_LEVEL; - i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { + gfn = sp->gfn; + slots = kvm_memslots_for_spte_role(kvm, sp->role); + slot = __gfn_to_memslot(slots, gfn); + for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { linfo = lpage_info_slot(gfn, slot, i); linfo->write_count -= 1; WARN_ON(linfo->write_count < 0); @@ -835,14 +841,14 @@ static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn) kvm->arch.indirect_shadow_pages--; } -static int has_wrprotected_page(struct kvm *kvm, +static int has_wrprotected_page(struct kvm_vcpu *vcpu, gfn_t gfn, int level) { struct kvm_memory_slot *slot; struct kvm_lpage_info *linfo; - slot = gfn_to_memslot(kvm, gfn); + slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); if (slot) { linfo = lpage_info_slot(gfn, slot, level); return linfo->write_count; @@ -858,8 +864,7 @@ static int host_mapping_level(struct kvm *kvm, gfn_t gfn) page_size = kvm_host_page_size(kvm, gfn); - for (i = PT_PAGE_TABLE_LEVEL; - i < (PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES); ++i) { + for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { if (page_size >= KVM_HPAGE_SIZE(i)) ret = i; else @@ -875,7 +880,7 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn, { struct kvm_memory_slot *slot; - slot = gfn_to_memslot(vcpu->kvm, gfn); + slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); if (!slot || slot->flags & KVM_MEMSLOT_INVALID || (no_dirty_log && slot->dirty_bitmap)) slot = NULL; @@ -900,7 +905,7 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn) max_level = min(kvm_x86_ops->get_lpage_level(), host_level); for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level) - if (has_wrprotected_page(vcpu->kvm, large_gfn, level)) + if (has_wrprotected_page(vcpu, large_gfn, level)) break; return level - 1; @@ -1042,12 +1047,14 @@ static unsigned long *__gfn_to_rmap(gfn_t gfn, int level, /* * Take gfn and return the reverse mapping to it. */ -static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level) +static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, struct kvm_mmu_page *sp) { + struct kvm_memslots *slots; struct kvm_memory_slot *slot; - slot = gfn_to_memslot(kvm, gfn); - return __gfn_to_rmap(gfn, level, slot); + slots = kvm_memslots_for_spte_role(kvm, sp->role); + slot = __gfn_to_memslot(slots, gfn); + return __gfn_to_rmap(gfn, sp->role.level, slot); } static bool rmap_can_add(struct kvm_vcpu *vcpu) @@ -1065,7 +1072,7 @@ static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) sp = page_header(__pa(spte)); kvm_mmu_page_set_gfn(sp, spte - sp->spt, gfn); - rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level); + rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp); return pte_list_add(vcpu, spte, rmapp); } @@ -1077,7 +1084,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) sp = page_header(__pa(spte)); gfn = kvm_mmu_page_get_gfn(sp, spte - sp->spt); - rmapp = gfn_to_rmap(kvm, gfn, sp->role.level); + rmapp = gfn_to_rmap(kvm, gfn, sp); pte_list_remove(spte, rmapp); } @@ -1142,6 +1149,11 @@ static u64 *rmap_get_next(struct rmap_iterator *iter) return NULL; } +#define for_each_rmap_spte(_rmap_, _iter_, _spte_) \ + for (_spte_ = rmap_get_first(*_rmap_, _iter_); \ + _spte_ && ({BUG_ON(!is_shadow_present_pte(*_spte_)); 1;}); \ + _spte_ = rmap_get_next(_iter_)) + static void drop_spte(struct kvm *kvm, u64 *sptep) { if (mmu_spte_clear_track_bits(sptep)) @@ -1205,12 +1217,8 @@ static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp, struct rmap_iterator iter; bool flush = false; - for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { - BUG_ON(!(*sptep & PT_PRESENT_MASK)); - + for_each_rmap_spte(rmapp, &iter, sptep) flush |= spte_write_protect(kvm, sptep, pt_protect); - sptep = rmap_get_next(&iter); - } return flush; } @@ -1232,12 +1240,8 @@ static bool __rmap_clear_dirty(struct kvm *kvm, unsigned long *rmapp) struct rmap_iterator iter; bool flush = false; - for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { - BUG_ON(!(*sptep & PT_PRESENT_MASK)); - + for_each_rmap_spte(rmapp, &iter, sptep) flush |= spte_clear_dirty(kvm, sptep); - sptep = rmap_get_next(&iter); - } return flush; } @@ -1259,12 +1263,8 @@ static bool __rmap_set_dirty(struct kvm *kvm, unsigned long *rmapp) struct rmap_iterator iter; bool flush = false; - for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { - BUG_ON(!(*sptep & PT_PRESENT_MASK)); - + for_each_rmap_spte(rmapp, &iter, sptep) flush |= spte_set_dirty(kvm, sptep); - sptep = rmap_get_next(&iter); - } return flush; } @@ -1342,42 +1342,45 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask); } -static bool rmap_write_protect(struct kvm *kvm, u64 gfn) +static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn) { struct kvm_memory_slot *slot; unsigned long *rmapp; int i; bool write_protected = false; - slot = gfn_to_memslot(kvm, gfn); + slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); - for (i = PT_PAGE_TABLE_LEVEL; - i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { + for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { rmapp = __gfn_to_rmap(gfn, i, slot); - write_protected |= __rmap_write_protect(kvm, rmapp, true); + write_protected |= __rmap_write_protect(vcpu->kvm, rmapp, true); } return write_protected; } -static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, - struct kvm_memory_slot *slot, gfn_t gfn, int level, - unsigned long data) +static bool kvm_zap_rmapp(struct kvm *kvm, unsigned long *rmapp) { u64 *sptep; struct rmap_iterator iter; - int need_tlb_flush = 0; + bool flush = false; while ((sptep = rmap_get_first(*rmapp, &iter))) { BUG_ON(!(*sptep & PT_PRESENT_MASK)); - rmap_printk("kvm_rmap_unmap_hva: spte %p %llx gfn %llx (%d)\n", - sptep, *sptep, gfn, level); + rmap_printk("%s: spte %p %llx.\n", __func__, sptep, *sptep); drop_spte(kvm, sptep); - need_tlb_flush = 1; + flush = true; } - return need_tlb_flush; + return flush; +} + +static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, + struct kvm_memory_slot *slot, gfn_t gfn, int level, + unsigned long data) +{ + return kvm_zap_rmapp(kvm, rmapp); } static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, @@ -1394,8 +1397,8 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, WARN_ON(pte_huge(*ptep)); new_pfn = pte_pfn(*ptep); - for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { - BUG_ON(!is_shadow_present_pte(*sptep)); +restart: + for_each_rmap_spte(rmapp, &iter, sptep) { rmap_printk("kvm_set_pte_rmapp: spte %p %llx gfn %llx (%d)\n", sptep, *sptep, gfn, level); @@ -1403,7 +1406,7 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, if (pte_write(*ptep)) { drop_spte(kvm, sptep); - sptep = rmap_get_first(*rmapp, &iter); + goto restart; } else { new_spte = *sptep & ~PT64_BASE_ADDR_MASK; new_spte |= (u64)new_pfn << PAGE_SHIFT; @@ -1414,7 +1417,6 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, mmu_spte_clear_track_bits(sptep); mmu_spte_set(sptep, new_spte); - sptep = rmap_get_next(&iter); } } @@ -1424,6 +1426,74 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, return 0; } +struct slot_rmap_walk_iterator { + /* input fields. */ + struct kvm_memory_slot *slot; + gfn_t start_gfn; + gfn_t end_gfn; + int start_level; + int end_level; + + /* output fields. */ + gfn_t gfn; + unsigned long *rmap; + int level; + + /* private field. */ + unsigned long *end_rmap; +}; + +static void +rmap_walk_init_level(struct slot_rmap_walk_iterator *iterator, int level) +{ + iterator->level = level; + iterator->gfn = iterator->start_gfn; + iterator->rmap = __gfn_to_rmap(iterator->gfn, level, iterator->slot); + iterator->end_rmap = __gfn_to_rmap(iterator->end_gfn, level, + iterator->slot); +} + +static void +slot_rmap_walk_init(struct slot_rmap_walk_iterator *iterator, + struct kvm_memory_slot *slot, int start_level, + int end_level, gfn_t start_gfn, gfn_t end_gfn) +{ + iterator->slot = slot; + iterator->start_level = start_level; + iterator->end_level = end_level; + iterator->start_gfn = start_gfn; + iterator->end_gfn = end_gfn; + + rmap_walk_init_level(iterator, iterator->start_level); +} + +static bool slot_rmap_walk_okay(struct slot_rmap_walk_iterator *iterator) +{ + return !!iterator->rmap; +} + +static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator) +{ + if (++iterator->rmap <= iterator->end_rmap) { + iterator->gfn += (1UL << KVM_HPAGE_GFN_SHIFT(iterator->level)); + return; + } + + if (++iterator->level > iterator->end_level) { + iterator->rmap = NULL; + return; + } + + rmap_walk_init_level(iterator, iterator->level); +} + +#define for_each_slot_rmap_range(_slot_, _start_level_, _end_level_, \ + _start_gfn, _end_gfn, _iter_) \ + for (slot_rmap_walk_init(_iter_, _slot_, _start_level_, \ + _end_level_, _start_gfn, _end_gfn); \ + slot_rmap_walk_okay(_iter_); \ + slot_rmap_walk_next(_iter_)) + static int kvm_handle_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, @@ -1435,48 +1505,36 @@ static int kvm_handle_hva_range(struct kvm *kvm, int level, unsigned long data)) { - int j; - int ret = 0; struct kvm_memslots *slots; struct kvm_memory_slot *memslot; + struct slot_rmap_walk_iterator iterator; + int ret = 0; + int i; - slots = kvm_memslots(kvm); - - kvm_for_each_memslot(memslot, slots) { - unsigned long hva_start, hva_end; - gfn_t gfn_start, gfn_end; - - hva_start = max(start, memslot->userspace_addr); - hva_end = min(end, memslot->userspace_addr + - (memslot->npages << PAGE_SHIFT)); - if (hva_start >= hva_end) - continue; - /* - * {gfn(page) | page intersects with [hva_start, hva_end)} = - * {gfn_start, gfn_start+1, ..., gfn_end-1}. - */ - gfn_start = hva_to_gfn_memslot(hva_start, memslot); - gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot); - - for (j = PT_PAGE_TABLE_LEVEL; - j < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++j) { - unsigned long idx, idx_end; - unsigned long *rmapp; - gfn_t gfn = gfn_start; + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + slots = __kvm_memslots(kvm, i); + kvm_for_each_memslot(memslot, slots) { + unsigned long hva_start, hva_end; + gfn_t gfn_start, gfn_end; + hva_start = max(start, memslot->userspace_addr); + hva_end = min(end, memslot->userspace_addr + + (memslot->npages << PAGE_SHIFT)); + if (hva_start >= hva_end) + continue; /* - * {idx(page_j) | page_j intersects with - * [hva_start, hva_end)} = {idx, idx+1, ..., idx_end}. + * {gfn(page) | page intersects with [hva_start, hva_end)} = + * {gfn_start, gfn_start+1, ..., gfn_end-1}. */ - idx = gfn_to_index(gfn_start, memslot->base_gfn, j); - idx_end = gfn_to_index(gfn_end - 1, memslot->base_gfn, j); - - rmapp = __gfn_to_rmap(gfn_start, j, memslot); - - for (; idx <= idx_end; - ++idx, gfn += (1UL << KVM_HPAGE_GFN_SHIFT(j))) - ret |= handler(kvm, rmapp++, memslot, - gfn, j, data); + gfn_start = hva_to_gfn_memslot(hva_start, memslot); + gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot); + + for_each_slot_rmap_range(memslot, PT_PAGE_TABLE_LEVEL, + PT_MAX_HUGEPAGE_LEVEL, + gfn_start, gfn_end - 1, + &iterator) + ret |= handler(kvm, iterator.rmap, memslot, + iterator.gfn, iterator.level, data); } } @@ -1518,16 +1576,13 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, BUG_ON(!shadow_accessed_mask); - for (sptep = rmap_get_first(*rmapp, &iter); sptep; - sptep = rmap_get_next(&iter)) { - BUG_ON(!is_shadow_present_pte(*sptep)); - + for_each_rmap_spte(rmapp, &iter, sptep) if (*sptep & shadow_accessed_mask) { young = 1; clear_bit((ffs(shadow_accessed_mask) - 1), (unsigned long *)sptep); } - } + trace_kvm_age_page(gfn, level, slot, young); return young; } @@ -1548,15 +1603,11 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp, if (!shadow_accessed_mask) goto out; - for (sptep = rmap_get_first(*rmapp, &iter); sptep; - sptep = rmap_get_next(&iter)) { - BUG_ON(!is_shadow_present_pte(*sptep)); - + for_each_rmap_spte(rmapp, &iter, sptep) if (*sptep & shadow_accessed_mask) { young = 1; break; } - } out: return young; } @@ -1570,7 +1621,7 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) sp = page_header(__pa(spte)); - rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level); + rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp); kvm_unmap_rmapp(vcpu->kvm, rmapp, NULL, gfn, sp->role.level, 0); kvm_flush_remote_tlbs(vcpu->kvm); @@ -1990,7 +2041,7 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu, bool protected = false; for_each_sp(pages, sp, parents, i) - protected |= rmap_write_protect(vcpu->kvm, sp->gfn); + protected |= rmap_write_protect(vcpu, sp->gfn); if (protected) kvm_flush_remote_tlbs(vcpu->kvm); @@ -2088,12 +2139,12 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, hlist_add_head(&sp->hash_link, &vcpu->kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)]); if (!direct) { - if (rmap_write_protect(vcpu->kvm, gfn)) + if (rmap_write_protect(vcpu, gfn)) kvm_flush_remote_tlbs(vcpu->kvm); if (level > PT_PAGE_TABLE_LEVEL && need_sync) kvm_sync_pages(vcpu, gfn); - account_shadowed(vcpu->kvm, gfn); + account_shadowed(vcpu->kvm, sp); } sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen; init_shadow_page_table(sp); @@ -2274,7 +2325,7 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, kvm_mmu_unlink_parents(kvm, sp); if (!sp->role.invalid && !sp->role.direct) - unaccount_shadowed(kvm, sp->gfn); + unaccount_shadowed(kvm, sp); if (sp->unsync) kvm_unlink_unsync_page(kvm, sp); @@ -2386,111 +2437,6 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page); -/* - * The function is based on mtrr_type_lookup() in - * arch/x86/kernel/cpu/mtrr/generic.c - */ -static int get_mtrr_type(struct mtrr_state_type *mtrr_state, - u64 start, u64 end) -{ - int i; - u64 base, mask; - u8 prev_match, curr_match; - int num_var_ranges = KVM_NR_VAR_MTRR; - - if (!mtrr_state->enabled) - return 0xFF; - - /* Make end inclusive end, instead of exclusive */ - end--; - - /* Look in fixed ranges. Just return the type as per start */ - if (mtrr_state->have_fixed && (start < 0x100000)) { - int idx; - - if (start < 0x80000) { - idx = 0; - idx += (start >> 16); - return mtrr_state->fixed_ranges[idx]; - } else if (start < 0xC0000) { - idx = 1 * 8; - idx += ((start - 0x80000) >> 14); - return mtrr_state->fixed_ranges[idx]; - } else if (start < 0x1000000) { - idx = 3 * 8; - idx += ((start - 0xC0000) >> 12); - return mtrr_state->fixed_ranges[idx]; - } - } - - /* - * Look in variable ranges - * Look of multiple ranges matching this address and pick type - * as per MTRR precedence - */ - if (!(mtrr_state->enabled & 2)) - return mtrr_state->def_type; - - prev_match = 0xFF; - for (i = 0; i < num_var_ranges; ++i) { - unsigned short start_state, end_state; - - if (!(mtrr_state->var_ranges[i].mask_lo & (1 << 11))) - continue; - - base = (((u64)mtrr_state->var_ranges[i].base_hi) << 32) + - (mtrr_state->var_ranges[i].base_lo & PAGE_MASK); - mask = (((u64)mtrr_state->var_ranges[i].mask_hi) << 32) + - (mtrr_state->var_ranges[i].mask_lo & PAGE_MASK); - - start_state = ((start & mask) == (base & mask)); - end_state = ((end & mask) == (base & mask)); - if (start_state != end_state) - return 0xFE; - - if ((start & mask) != (base & mask)) - continue; - - curr_match = mtrr_state->var_ranges[i].base_lo & 0xff; - if (prev_match == 0xFF) { - prev_match = curr_match; - continue; - } - - if (prev_match == MTRR_TYPE_UNCACHABLE || - curr_match == MTRR_TYPE_UNCACHABLE) - return MTRR_TYPE_UNCACHABLE; - - if ((prev_match == MTRR_TYPE_WRBACK && - curr_match == MTRR_TYPE_WRTHROUGH) || - (prev_match == MTRR_TYPE_WRTHROUGH && - curr_match == MTRR_TYPE_WRBACK)) { - prev_match = MTRR_TYPE_WRTHROUGH; - curr_match = MTRR_TYPE_WRTHROUGH; - } - - if (prev_match != curr_match) - return MTRR_TYPE_UNCACHABLE; - } - - if (prev_match != 0xFF) - return prev_match; - - return mtrr_state->def_type; -} - -u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) -{ - u8 mtrr; - - mtrr = get_mtrr_type(&vcpu->arch.mtrr_state, gfn << PAGE_SHIFT, - (gfn << PAGE_SHIFT) + PAGE_SIZE); - if (mtrr == 0xfe || mtrr == 0xff) - mtrr = MTRR_TYPE_WRBACK; - return mtrr; -} -EXPORT_SYMBOL_GPL(kvm_get_guest_memory_type); - static void __kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { trace_kvm_mmu_unsync_page(sp); @@ -2533,6 +2479,14 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, return 0; } +static bool kvm_is_mmio_pfn(pfn_t pfn) +{ + if (pfn_valid(pfn)) + return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn)); + + return true; +} + static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, int level, gfn_t gfn, pfn_t pfn, bool speculative, @@ -2541,7 +2495,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 spte; int ret = 0; - if (set_mmio_spte(vcpu->kvm, sptep, gfn, pfn, pte_access)) + if (set_mmio_spte(vcpu, sptep, gfn, pfn, pte_access)) return 0; spte = PT_PRESENT_MASK; @@ -2560,7 +2514,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, spte |= PT_PAGE_SIZE_MASK; if (tdp_enabled) spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn, - kvm_is_reserved_pfn(pfn)); + kvm_is_mmio_pfn(pfn)); if (host_writable) spte |= SPTE_HOST_WRITEABLE; @@ -2578,7 +2532,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, * be fixed if guest refault. */ if (level > PT_PAGE_TABLE_LEVEL && - has_wrprotected_page(vcpu->kvm, gfn, level)) + has_wrprotected_page(vcpu, gfn, level)) goto done; spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE; @@ -2602,7 +2556,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, } if (pte_access & ACC_WRITE_MASK) { - mark_page_dirty(vcpu->kvm, gfn); + kvm_vcpu_mark_page_dirty(vcpu, gfn); spte |= shadow_dirty_mask; } @@ -2692,15 +2646,17 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, u64 *start, u64 *end) { struct page *pages[PTE_PREFETCH_NUM]; + struct kvm_memory_slot *slot; unsigned access = sp->role.access; int i, ret; gfn_t gfn; gfn = kvm_mmu_page_get_gfn(sp, start - sp->spt); - if (!gfn_to_memslot_dirty_bitmap(vcpu, gfn, access & ACC_WRITE_MASK)) + slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, access & ACC_WRITE_MASK); + if (!slot) return -1; - ret = gfn_to_page_many_atomic(vcpu->kvm, gfn, pages, end - start); + ret = gfn_to_page_many_atomic(slot, gfn, pages, end - start); if (ret <= 0) return -1; @@ -2818,7 +2774,7 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, pfn_t pfn) return 1; if (pfn == KVM_PFN_ERR_HWPOISON) { - kvm_send_hwpoison_signal(gfn_to_hva(vcpu->kvm, gfn), current); + kvm_send_hwpoison_signal(kvm_vcpu_gfn_to_hva(vcpu, gfn), current); return 0; } @@ -2841,7 +2797,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL && PageTransCompound(pfn_to_page(pfn)) && - !has_wrprotected_page(vcpu->kvm, gfn, PT_DIRECTORY_LEVEL)) { + !has_wrprotected_page(vcpu, gfn, PT_DIRECTORY_LEVEL)) { unsigned long mask; /* * mmu_notifier_retry was successful and we hold the @@ -2933,7 +2889,7 @@ fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, * Compare with set_spte where instead shadow_dirty_mask is set. */ if (cmpxchg64(sptep, spte, spte | PT_WRITABLE_MASK) == spte) - mark_page_dirty(vcpu->kvm, gfn); + kvm_vcpu_mark_page_dirty(vcpu, gfn); return true; } @@ -3388,7 +3344,7 @@ int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct) gfn_t gfn = get_mmio_spte_gfn(spte); unsigned access = get_mmio_spte_access(spte); - if (!check_mmio_spte(vcpu->kvm, spte)) + if (!check_mmio_spte(vcpu, spte)) return RET_MMIO_PF_INVALID; if (direct) @@ -3460,7 +3416,7 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) arch.direct_map = vcpu->arch.mmu.direct_map; arch.cr3 = vcpu->arch.mmu.get_cr3(vcpu); - return kvm_setup_async_pf(vcpu, gva, gfn_to_hva(vcpu->kvm, gfn), &arch); + return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); } static bool can_do_async_pf(struct kvm_vcpu *vcpu) @@ -3475,10 +3431,12 @@ static bool can_do_async_pf(struct kvm_vcpu *vcpu) static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, gva_t gva, pfn_t *pfn, bool write, bool *writable) { + struct kvm_memory_slot *slot; bool async; - *pfn = gfn_to_pfn_async(vcpu->kvm, gfn, &async, write, writable); - + slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + async = false; + *pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async, write, writable); if (!async) return false; /* *pfn has correct page already */ @@ -3492,11 +3450,20 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, return true; } - *pfn = gfn_to_pfn_prot(vcpu->kvm, gfn, write, writable); - + *pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL, write, writable); return false; } +static bool +check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level) +{ + int page_num = KVM_PAGES_PER_HPAGE(level); + + gfn &= ~(page_num - 1); + + return kvm_mtrr_check_gfn_range_consistency(vcpu, gfn, page_num); +} + static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, bool prefault) { @@ -3522,9 +3489,17 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, if (r) return r; - force_pt_level = mapping_level_dirty_bitmap(vcpu, gfn); + if (mapping_level_dirty_bitmap(vcpu, gfn) || + !check_hugepage_cache_consistency(vcpu, gfn, PT_DIRECTORY_LEVEL)) + force_pt_level = 1; + else + force_pt_level = 0; + if (likely(!force_pt_level)) { level = mapping_level(vcpu, gfn); + if (level > PT_DIRECTORY_LEVEL && + !check_hugepage_cache_consistency(vcpu, gfn, level)) + level = PT_DIRECTORY_LEVEL; gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); } else level = PT_PAGE_TABLE_LEVEL; @@ -3590,7 +3565,7 @@ static void inject_page_fault(struct kvm_vcpu *vcpu, vcpu->arch.mmu.inject_page_fault(vcpu, fault); } -static bool sync_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn, +static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, unsigned access, int *nr_present) { if (unlikely(is_mmio_spte(*sptep))) { @@ -3600,7 +3575,7 @@ static bool sync_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn, } (*nr_present)++; - mark_mmio_spte(kvm, sptep, gfn, access); + mark_mmio_spte(vcpu, sptep, gfn, access); return true; } @@ -3878,6 +3853,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) struct kvm_mmu *context = &vcpu->arch.mmu; context->base_role.word = 0; + context->base_role.smm = is_smm(vcpu); context->page_fault = tdp_page_fault; context->sync_page = nonpaging_sync_page; context->invlpg = nonpaging_invlpg; @@ -3939,6 +3915,7 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu) = smep && !is_write_protection(vcpu); context->base_role.smap_andnot_wp = smap && !is_write_protection(vcpu); + context->base_role.smm = is_smm(vcpu); } EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu); @@ -4110,7 +4087,7 @@ static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, /* Handle a 32-bit guest writing two halves of a 64-bit gpte */ *gpa &= ~(gpa_t)7; *bytes = 8; - r = kvm_read_guest(vcpu->kvm, *gpa, &gentry, 8); + r = kvm_vcpu_read_guest(vcpu, *gpa, &gentry, 8); if (r) gentry = 0; new = (const u8 *)&gentry; @@ -4222,6 +4199,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, mask.nxe = 1; mask.smep_andnot_wp = 1; mask.smap_andnot_wp = 1; + mask.smm = 1; /* * If we don't have indirect shadow pages, it means no page is @@ -4420,36 +4398,115 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu) init_kvm_mmu(vcpu); } -void kvm_mmu_slot_remove_write_access(struct kvm *kvm, - struct kvm_memory_slot *memslot) +/* The return value indicates if tlb flush on all vcpus is needed. */ +typedef bool (*slot_level_handler) (struct kvm *kvm, unsigned long *rmap); + +/* The caller should hold mmu-lock before calling this function. */ +static bool +slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, int start_level, int end_level, + gfn_t start_gfn, gfn_t end_gfn, bool lock_flush_tlb) { - gfn_t last_gfn; - int i; + struct slot_rmap_walk_iterator iterator; bool flush = false; - last_gfn = memslot->base_gfn + memslot->npages - 1; + for_each_slot_rmap_range(memslot, start_level, end_level, start_gfn, + end_gfn, &iterator) { + if (iterator.rmap) + flush |= fn(kvm, iterator.rmap); - spin_lock(&kvm->mmu_lock); + if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { + if (flush && lock_flush_tlb) { + kvm_flush_remote_tlbs(kvm); + flush = false; + } + cond_resched_lock(&kvm->mmu_lock); + } + } + + if (flush && lock_flush_tlb) { + kvm_flush_remote_tlbs(kvm); + flush = false; + } + + return flush; +} + +static bool +slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, int start_level, int end_level, + bool lock_flush_tlb) +{ + return slot_handle_level_range(kvm, memslot, fn, start_level, + end_level, memslot->base_gfn, + memslot->base_gfn + memslot->npages - 1, + lock_flush_tlb); +} + +static bool +slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, bool lock_flush_tlb) +{ + return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL, + PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); +} + +static bool +slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, bool lock_flush_tlb) +{ + return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL + 1, + PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); +} - for (i = PT_PAGE_TABLE_LEVEL; - i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { - unsigned long *rmapp; - unsigned long last_index, index; +static bool +slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, bool lock_flush_tlb) +{ + return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL, + PT_PAGE_TABLE_LEVEL, lock_flush_tlb); +} - rmapp = memslot->arch.rmap[i - PT_PAGE_TABLE_LEVEL]; - last_index = gfn_to_index(last_gfn, memslot->base_gfn, i); +void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + int i; - for (index = 0; index <= last_index; ++index, ++rmapp) { - if (*rmapp) - flush |= __rmap_write_protect(kvm, rmapp, - false); + spin_lock(&kvm->mmu_lock); + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + slots = __kvm_memslots(kvm, i); + kvm_for_each_memslot(memslot, slots) { + gfn_t start, end; + + start = max(gfn_start, memslot->base_gfn); + end = min(gfn_end, memslot->base_gfn + memslot->npages); + if (start >= end) + continue; - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) - cond_resched_lock(&kvm->mmu_lock); + slot_handle_level_range(kvm, memslot, kvm_zap_rmapp, + PT_PAGE_TABLE_LEVEL, PT_MAX_HUGEPAGE_LEVEL, + start, end - 1, true); } } spin_unlock(&kvm->mmu_lock); +} + +static bool slot_rmap_write_protect(struct kvm *kvm, unsigned long *rmapp) +{ + return __rmap_write_protect(kvm, rmapp, false); +} + +void kvm_mmu_slot_remove_write_access(struct kvm *kvm, + struct kvm_memory_slot *memslot) +{ + bool flush; + + spin_lock(&kvm->mmu_lock); + flush = slot_handle_all_level(kvm, memslot, slot_rmap_write_protect, + false); + spin_unlock(&kvm->mmu_lock); /* * kvm_mmu_slot_remove_write_access() and kvm_vm_ioctl_get_dirty_log() @@ -4482,9 +4539,8 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, pfn_t pfn; struct kvm_mmu_page *sp; - for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { - BUG_ON(!(*sptep & PT_PRESENT_MASK)); - +restart: + for_each_rmap_spte(rmapp, &iter, sptep) { sp = page_header(__pa(sptep)); pfn = spte_to_pfn(*sptep); @@ -4499,71 +4555,31 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, !kvm_is_reserved_pfn(pfn) && PageTransCompound(pfn_to_page(pfn))) { drop_spte(kvm, sptep); - sptep = rmap_get_first(*rmapp, &iter); need_tlb_flush = 1; - } else - sptep = rmap_get_next(&iter); + goto restart; + } } return need_tlb_flush; } void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, - struct kvm_memory_slot *memslot) + const struct kvm_memory_slot *memslot) { - bool flush = false; - unsigned long *rmapp; - unsigned long last_index, index; - + /* FIXME: const-ify all uses of struct kvm_memory_slot. */ spin_lock(&kvm->mmu_lock); - - rmapp = memslot->arch.rmap[0]; - last_index = gfn_to_index(memslot->base_gfn + memslot->npages - 1, - memslot->base_gfn, PT_PAGE_TABLE_LEVEL); - - for (index = 0; index <= last_index; ++index, ++rmapp) { - if (*rmapp) - flush |= kvm_mmu_zap_collapsible_spte(kvm, rmapp); - - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { - if (flush) { - kvm_flush_remote_tlbs(kvm); - flush = false; - } - cond_resched_lock(&kvm->mmu_lock); - } - } - - if (flush) - kvm_flush_remote_tlbs(kvm); - + slot_handle_leaf(kvm, (struct kvm_memory_slot *)memslot, + kvm_mmu_zap_collapsible_spte, true); spin_unlock(&kvm->mmu_lock); } void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot) { - gfn_t last_gfn; - unsigned long *rmapp; - unsigned long last_index, index; - bool flush = false; - - last_gfn = memslot->base_gfn + memslot->npages - 1; + bool flush; spin_lock(&kvm->mmu_lock); - - rmapp = memslot->arch.rmap[PT_PAGE_TABLE_LEVEL - 1]; - last_index = gfn_to_index(last_gfn, memslot->base_gfn, - PT_PAGE_TABLE_LEVEL); - - for (index = 0; index <= last_index; ++index, ++rmapp) { - if (*rmapp) - flush |= __rmap_clear_dirty(kvm, rmapp); - - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) - cond_resched_lock(&kvm->mmu_lock); - } - + flush = slot_handle_leaf(kvm, memslot, __rmap_clear_dirty, false); spin_unlock(&kvm->mmu_lock); lockdep_assert_held(&kvm->slots_lock); @@ -4582,31 +4598,11 @@ EXPORT_SYMBOL_GPL(kvm_mmu_slot_leaf_clear_dirty); void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm, struct kvm_memory_slot *memslot) { - gfn_t last_gfn; - int i; - bool flush = false; - - last_gfn = memslot->base_gfn + memslot->npages - 1; + bool flush; spin_lock(&kvm->mmu_lock); - - for (i = PT_PAGE_TABLE_LEVEL + 1; /* skip rmap for 4K page */ - i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { - unsigned long *rmapp; - unsigned long last_index, index; - - rmapp = memslot->arch.rmap[i - PT_PAGE_TABLE_LEVEL]; - last_index = gfn_to_index(last_gfn, memslot->base_gfn, i); - - for (index = 0; index <= last_index; ++index, ++rmapp) { - if (*rmapp) - flush |= __rmap_write_protect(kvm, rmapp, - false); - - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) - cond_resched_lock(&kvm->mmu_lock); - } - } + flush = slot_handle_large_level(kvm, memslot, slot_rmap_write_protect, + false); spin_unlock(&kvm->mmu_lock); /* see kvm_mmu_slot_remove_write_access */ @@ -4620,31 +4616,10 @@ EXPORT_SYMBOL_GPL(kvm_mmu_slot_largepage_remove_write_access); void kvm_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot) { - gfn_t last_gfn; - int i; - bool flush = false; - - last_gfn = memslot->base_gfn + memslot->npages - 1; + bool flush; spin_lock(&kvm->mmu_lock); - - for (i = PT_PAGE_TABLE_LEVEL; - i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { - unsigned long *rmapp; - unsigned long last_index, index; - - rmapp = memslot->arch.rmap[i - PT_PAGE_TABLE_LEVEL]; - last_index = gfn_to_index(last_gfn, memslot->base_gfn, i); - - for (index = 0; index <= last_index; ++index, ++rmapp) { - if (*rmapp) - flush |= __rmap_set_dirty(kvm, rmapp); - - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) - cond_resched_lock(&kvm->mmu_lock); - } - } - + flush = slot_handle_all_level(kvm, memslot, __rmap_set_dirty, false); spin_unlock(&kvm->mmu_lock); lockdep_assert_held(&kvm->slots_lock); @@ -4741,13 +4716,13 @@ static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm) return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages)); } -void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm) +void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, struct kvm_memslots *slots) { /* * The very rare case: if the generation-number is round, * zap all shadow pages. */ - if (unlikely(kvm_current_mmio_generation(kvm) == 0)) { + if (unlikely((slots->generation & MMIO_GEN_MASK) == 0)) { printk_ratelimited(KERN_DEBUG "kvm: zapping shadow pages for mmio generation wraparound\n"); kvm_mmu_invalidate_zap_all_pages(kvm); } @@ -4869,15 +4844,18 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm) unsigned int nr_pages = 0; struct kvm_memslots *slots; struct kvm_memory_slot *memslot; + int i; - slots = kvm_memslots(kvm); + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + slots = __kvm_memslots(kvm, i); - kvm_for_each_memslot(memslot, slots) - nr_pages += memslot->npages; + kvm_for_each_memslot(memslot, slots) + nr_pages += memslot->npages; + } nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000; nr_mmu_pages = max(nr_mmu_pages, - (unsigned int) KVM_MIN_ALLOC_MMU_PAGES); + (unsigned int) KVM_MIN_ALLOC_MMU_PAGES); return nr_mmu_pages; } diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 0ada65ecd..398d21c0f 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -43,6 +43,7 @@ #define PT_PDPE_LEVEL 3 #define PT_DIRECTORY_LEVEL 2 #define PT_PAGE_TABLE_LEVEL 1 +#define PT_MAX_HUGEPAGE_LEVEL (PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES - 1) static inline u64 rsvd_bits(int s, int e) { @@ -170,4 +171,5 @@ static inline bool permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, } void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm); +void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end); #endif diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c index 9ade5cfb5..03d518e49 100644 --- a/arch/x86/kvm/mmu_audit.c +++ b/arch/x86/kvm/mmu_audit.c @@ -114,7 +114,7 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level) return; gfn = kvm_mmu_page_get_gfn(sp, sptep - sp->spt); - pfn = gfn_to_pfn_atomic(vcpu->kvm, gfn); + pfn = kvm_vcpu_gfn_to_pfn_atomic(vcpu, gfn); if (is_error_pfn(pfn)) return; @@ -131,12 +131,16 @@ static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10); unsigned long *rmapp; struct kvm_mmu_page *rev_sp; + struct kvm_memslots *slots; + struct kvm_memory_slot *slot; gfn_t gfn; rev_sp = page_header(__pa(sptep)); gfn = kvm_mmu_page_get_gfn(rev_sp, sptep - rev_sp->spt); - if (!gfn_to_memslot(kvm, gfn)) { + slots = kvm_memslots_for_spte_role(kvm, rev_sp->role); + slot = __gfn_to_memslot(slots, gfn); + if (!slot) { if (!__ratelimit(&ratelimit_state)) return; audit_printk(kvm, "no memslot for gfn %llx\n", gfn); @@ -146,7 +150,7 @@ static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) return; } - rmapp = gfn_to_rmap(kvm, gfn, rev_sp->role.level); + rmapp = __gfn_to_rmap(gfn, rev_sp->role.level, slot); if (!*rmapp) { if (!__ratelimit(&ratelimit_state)) return; @@ -191,19 +195,21 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp) unsigned long *rmapp; u64 *sptep; struct rmap_iterator iter; + struct kvm_memslots *slots; + struct kvm_memory_slot *slot; if (sp->role.direct || sp->unsync || sp->role.invalid) return; - rmapp = gfn_to_rmap(kvm, sp->gfn, PT_PAGE_TABLE_LEVEL); + slots = kvm_memslots_for_spte_role(kvm, sp->role); + slot = __gfn_to_memslot(slots, sp->gfn); + rmapp = __gfn_to_rmap(sp->gfn, PT_PAGE_TABLE_LEVEL, slot); - for (sptep = rmap_get_first(*rmapp, &iter); sptep; - sptep = rmap_get_next(&iter)) { + for_each_rmap_spte(rmapp, &iter, sptep) if (is_writable_pte(*sptep)) audit_printk(kvm, "shadow page has writable " "mappings: gfn %llx role %x\n", sp->gfn, sp->role.word); - } } static void audit_sp(struct kvm *kvm, struct kvm_mmu_page *sp) @@ -291,7 +297,7 @@ static int mmu_audit_set(const char *val, const struct kernel_param *kp) return 0; } -static struct kernel_param_ops audit_param_ops = { +static const struct kernel_param_ops audit_param_ops = { .set = mmu_audit_set, .get = param_get_bool, }; diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index ce463a9cc..5a24b846a 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -2,7 +2,7 @@ #define _TRACE_KVMMMU_H #include <linux/tracepoint.h> -#include <linux/ftrace_event.h> +#include <linux/trace_events.h> #undef TRACE_SYSTEM #define TRACE_SYSTEM kvmmmu diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c new file mode 100644 index 000000000..9e8bf1357 --- /dev/null +++ b/arch/x86/kvm/mtrr.c @@ -0,0 +1,719 @@ +/* + * vMTRR implementation + * + * Copyright (C) 2006 Qumranet, Inc. + * Copyright 2010 Red Hat, Inc. and/or its affiliates. + * Copyright(C) 2015 Intel Corporation. + * + * Authors: + * Yaniv Kamay <yaniv@qumranet.com> + * Avi Kivity <avi@qumranet.com> + * Marcelo Tosatti <mtosatti@redhat.com> + * Paolo Bonzini <pbonzini@redhat.com> + * Xiao Guangrong <guangrong.xiao@linux.intel.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include <linux/kvm_host.h> +#include <asm/mtrr.h> + +#include "cpuid.h" +#include "mmu.h" + +#define IA32_MTRR_DEF_TYPE_E (1ULL << 11) +#define IA32_MTRR_DEF_TYPE_FE (1ULL << 10) +#define IA32_MTRR_DEF_TYPE_TYPE_MASK (0xff) + +static bool msr_mtrr_valid(unsigned msr) +{ + switch (msr) { + case 0x200 ... 0x200 + 2 * KVM_NR_VAR_MTRR - 1: + case MSR_MTRRfix64K_00000: + case MSR_MTRRfix16K_80000: + case MSR_MTRRfix16K_A0000: + case MSR_MTRRfix4K_C0000: + case MSR_MTRRfix4K_C8000: + case MSR_MTRRfix4K_D0000: + case MSR_MTRRfix4K_D8000: + case MSR_MTRRfix4K_E0000: + case MSR_MTRRfix4K_E8000: + case MSR_MTRRfix4K_F0000: + case MSR_MTRRfix4K_F8000: + case MSR_MTRRdefType: + case MSR_IA32_CR_PAT: + return true; + case 0x2f8: + return true; + } + return false; +} + +static bool valid_pat_type(unsigned t) +{ + return t < 8 && (1 << t) & 0xf3; /* 0, 1, 4, 5, 6, 7 */ +} + +static bool valid_mtrr_type(unsigned t) +{ + return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */ +} + +bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + int i; + u64 mask; + + if (!msr_mtrr_valid(msr)) + return false; + + if (msr == MSR_IA32_CR_PAT) { + for (i = 0; i < 8; i++) + if (!valid_pat_type((data >> (i * 8)) & 0xff)) + return false; + return true; + } else if (msr == MSR_MTRRdefType) { + if (data & ~0xcff) + return false; + return valid_mtrr_type(data & 0xff); + } else if (msr >= MSR_MTRRfix64K_00000 && msr <= MSR_MTRRfix4K_F8000) { + for (i = 0; i < 8 ; i++) + if (!valid_mtrr_type((data >> (i * 8)) & 0xff)) + return false; + return true; + } + + /* variable MTRRs */ + WARN_ON(!(msr >= 0x200 && msr < 0x200 + 2 * KVM_NR_VAR_MTRR)); + + mask = (~0ULL) << cpuid_maxphyaddr(vcpu); + if ((msr & 1) == 0) { + /* MTRR base */ + if (!valid_mtrr_type(data & 0xff)) + return false; + mask |= 0xf00; + } else + /* MTRR mask */ + mask |= 0x7ff; + if (data & mask) { + kvm_inject_gp(vcpu, 0); + return false; + } + + return true; +} +EXPORT_SYMBOL_GPL(kvm_mtrr_valid); + +static bool mtrr_is_enabled(struct kvm_mtrr *mtrr_state) +{ + return !!(mtrr_state->deftype & IA32_MTRR_DEF_TYPE_E); +} + +static bool fixed_mtrr_is_enabled(struct kvm_mtrr *mtrr_state) +{ + return !!(mtrr_state->deftype & IA32_MTRR_DEF_TYPE_FE); +} + +static u8 mtrr_default_type(struct kvm_mtrr *mtrr_state) +{ + return mtrr_state->deftype & IA32_MTRR_DEF_TYPE_TYPE_MASK; +} + +static u8 mtrr_disabled_type(void) +{ + /* + * Intel SDM 11.11.2.2: all MTRRs are disabled when + * IA32_MTRR_DEF_TYPE.E bit is cleared, and the UC + * memory type is applied to all of physical memory. + */ + return MTRR_TYPE_UNCACHABLE; +} + +/* +* Three terms are used in the following code: +* - segment, it indicates the address segments covered by fixed MTRRs. +* - unit, it corresponds to the MSR entry in the segment. +* - range, a range is covered in one memory cache type. +*/ +struct fixed_mtrr_segment { + u64 start; + u64 end; + + int range_shift; + + /* the start position in kvm_mtrr.fixed_ranges[]. */ + int range_start; +}; + +static struct fixed_mtrr_segment fixed_seg_table[] = { + /* MSR_MTRRfix64K_00000, 1 unit. 64K fixed mtrr. */ + { + .start = 0x0, + .end = 0x80000, + .range_shift = 16, /* 64K */ + .range_start = 0, + }, + + /* + * MSR_MTRRfix16K_80000 ... MSR_MTRRfix16K_A0000, 2 units, + * 16K fixed mtrr. + */ + { + .start = 0x80000, + .end = 0xc0000, + .range_shift = 14, /* 16K */ + .range_start = 8, + }, + + /* + * MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000, 8 units, + * 4K fixed mtrr. + */ + { + .start = 0xc0000, + .end = 0x100000, + .range_shift = 12, /* 12K */ + .range_start = 24, + } +}; + +/* + * The size of unit is covered in one MSR, one MSR entry contains + * 8 ranges so that unit size is always 8 * 2^range_shift. + */ +static u64 fixed_mtrr_seg_unit_size(int seg) +{ + return 8 << fixed_seg_table[seg].range_shift; +} + +static bool fixed_msr_to_seg_unit(u32 msr, int *seg, int *unit) +{ + switch (msr) { + case MSR_MTRRfix64K_00000: + *seg = 0; + *unit = 0; + break; + case MSR_MTRRfix16K_80000 ... MSR_MTRRfix16K_A0000: + *seg = 1; + *unit = msr - MSR_MTRRfix16K_80000; + break; + case MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000: + *seg = 2; + *unit = msr - MSR_MTRRfix4K_C0000; + break; + default: + return false; + } + + return true; +} + +static void fixed_mtrr_seg_unit_range(int seg, int unit, u64 *start, u64 *end) +{ + struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg]; + u64 unit_size = fixed_mtrr_seg_unit_size(seg); + + *start = mtrr_seg->start + unit * unit_size; + *end = *start + unit_size; + WARN_ON(*end > mtrr_seg->end); +} + +static int fixed_mtrr_seg_unit_range_index(int seg, int unit) +{ + struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg]; + + WARN_ON(mtrr_seg->start + unit * fixed_mtrr_seg_unit_size(seg) + > mtrr_seg->end); + + /* each unit has 8 ranges. */ + return mtrr_seg->range_start + 8 * unit; +} + +static int fixed_mtrr_seg_end_range_index(int seg) +{ + struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg]; + int n; + + n = (mtrr_seg->end - mtrr_seg->start) >> mtrr_seg->range_shift; + return mtrr_seg->range_start + n - 1; +} + +static bool fixed_msr_to_range(u32 msr, u64 *start, u64 *end) +{ + int seg, unit; + + if (!fixed_msr_to_seg_unit(msr, &seg, &unit)) + return false; + + fixed_mtrr_seg_unit_range(seg, unit, start, end); + return true; +} + +static int fixed_msr_to_range_index(u32 msr) +{ + int seg, unit; + + if (!fixed_msr_to_seg_unit(msr, &seg, &unit)) + return -1; + + return fixed_mtrr_seg_unit_range_index(seg, unit); +} + +static int fixed_mtrr_addr_to_seg(u64 addr) +{ + struct fixed_mtrr_segment *mtrr_seg; + int seg, seg_num = ARRAY_SIZE(fixed_seg_table); + + for (seg = 0; seg < seg_num; seg++) { + mtrr_seg = &fixed_seg_table[seg]; + if (mtrr_seg->start >= addr && addr < mtrr_seg->end) + return seg; + } + + return -1; +} + +static int fixed_mtrr_addr_seg_to_range_index(u64 addr, int seg) +{ + struct fixed_mtrr_segment *mtrr_seg; + int index; + + mtrr_seg = &fixed_seg_table[seg]; + index = mtrr_seg->range_start; + index += (addr - mtrr_seg->start) >> mtrr_seg->range_shift; + return index; +} + +static u64 fixed_mtrr_range_end_addr(int seg, int index) +{ + struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg]; + int pos = index - mtrr_seg->range_start; + + return mtrr_seg->start + ((pos + 1) << mtrr_seg->range_shift); +} + +static void var_mtrr_range(struct kvm_mtrr_range *range, u64 *start, u64 *end) +{ + u64 mask; + + *start = range->base & PAGE_MASK; + + mask = range->mask & PAGE_MASK; + mask |= ~0ULL << boot_cpu_data.x86_phys_bits; + + /* This cannot overflow because writing to the reserved bits of + * variable MTRRs causes a #GP. + */ + *end = (*start | ~mask) + 1; +} + +static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr) +{ + struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; + gfn_t start, end; + int index; + + if (msr == MSR_IA32_CR_PAT || !tdp_enabled || + !kvm_arch_has_noncoherent_dma(vcpu->kvm)) + return; + + if (!mtrr_is_enabled(mtrr_state) && msr != MSR_MTRRdefType) + return; + + /* fixed MTRRs. */ + if (fixed_msr_to_range(msr, &start, &end)) { + if (!fixed_mtrr_is_enabled(mtrr_state)) + return; + } else if (msr == MSR_MTRRdefType) { + start = 0x0; + end = ~0ULL; + } else { + /* variable range MTRRs. */ + index = (msr - 0x200) / 2; + var_mtrr_range(&mtrr_state->var_ranges[index], &start, &end); + } + + kvm_zap_gfn_range(vcpu->kvm, gpa_to_gfn(start), gpa_to_gfn(end)); +} + +static bool var_mtrr_range_is_valid(struct kvm_mtrr_range *range) +{ + return (range->mask & (1 << 11)) != 0; +} + +static void set_var_mtrr_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; + struct kvm_mtrr_range *tmp, *cur; + int index, is_mtrr_mask; + + index = (msr - 0x200) / 2; + is_mtrr_mask = msr - 0x200 - 2 * index; + cur = &mtrr_state->var_ranges[index]; + + /* remove the entry if it's in the list. */ + if (var_mtrr_range_is_valid(cur)) + list_del(&mtrr_state->var_ranges[index].node); + + if (!is_mtrr_mask) + cur->base = data; + else + cur->mask = data; + + /* add it to the list if it's enabled. */ + if (var_mtrr_range_is_valid(cur)) { + list_for_each_entry(tmp, &mtrr_state->head, node) + if (cur->base >= tmp->base) + break; + list_add_tail(&cur->node, &tmp->node); + } +} + +int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + int index; + + if (!kvm_mtrr_valid(vcpu, msr, data)) + return 1; + + index = fixed_msr_to_range_index(msr); + if (index >= 0) + *(u64 *)&vcpu->arch.mtrr_state.fixed_ranges[index] = data; + else if (msr == MSR_MTRRdefType) + vcpu->arch.mtrr_state.deftype = data; + else if (msr == MSR_IA32_CR_PAT) + vcpu->arch.pat = data; + else + set_var_mtrr_msr(vcpu, msr, data); + + update_mtrr(vcpu, msr); + return 0; +} + +int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + int index; + + /* MSR_MTRRcap is a readonly MSR. */ + if (msr == MSR_MTRRcap) { + /* + * SMRR = 0 + * WC = 1 + * FIX = 1 + * VCNT = KVM_NR_VAR_MTRR + */ + *pdata = 0x500 | KVM_NR_VAR_MTRR; + return 0; + } + + if (!msr_mtrr_valid(msr)) + return 1; + + index = fixed_msr_to_range_index(msr); + if (index >= 0) + *pdata = *(u64 *)&vcpu->arch.mtrr_state.fixed_ranges[index]; + else if (msr == MSR_MTRRdefType) + *pdata = vcpu->arch.mtrr_state.deftype; + else if (msr == MSR_IA32_CR_PAT) + *pdata = vcpu->arch.pat; + else { /* Variable MTRRs */ + int is_mtrr_mask; + + index = (msr - 0x200) / 2; + is_mtrr_mask = msr - 0x200 - 2 * index; + if (!is_mtrr_mask) + *pdata = vcpu->arch.mtrr_state.var_ranges[index].base; + else + *pdata = vcpu->arch.mtrr_state.var_ranges[index].mask; + } + + return 0; +} + +void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu) +{ + INIT_LIST_HEAD(&vcpu->arch.mtrr_state.head); +} + +struct mtrr_iter { + /* input fields. */ + struct kvm_mtrr *mtrr_state; + u64 start; + u64 end; + + /* output fields. */ + int mem_type; + /* mtrr is completely disabled? */ + bool mtrr_disabled; + /* [start, end) is not fully covered in MTRRs? */ + bool partial_map; + + /* private fields. */ + union { + /* used for fixed MTRRs. */ + struct { + int index; + int seg; + }; + + /* used for var MTRRs. */ + struct { + struct kvm_mtrr_range *range; + /* max address has been covered in var MTRRs. */ + u64 start_max; + }; + }; + + bool fixed; +}; + +static bool mtrr_lookup_fixed_start(struct mtrr_iter *iter) +{ + int seg, index; + + if (!fixed_mtrr_is_enabled(iter->mtrr_state)) + return false; + + seg = fixed_mtrr_addr_to_seg(iter->start); + if (seg < 0) + return false; + + iter->fixed = true; + index = fixed_mtrr_addr_seg_to_range_index(iter->start, seg); + iter->index = index; + iter->seg = seg; + return true; +} + +static bool match_var_range(struct mtrr_iter *iter, + struct kvm_mtrr_range *range) +{ + u64 start, end; + + var_mtrr_range(range, &start, &end); + if (!(start >= iter->end || end <= iter->start)) { + iter->range = range; + + /* + * the function is called when we do kvm_mtrr.head walking. + * Range has the minimum base address which interleaves + * [looker->start_max, looker->end). + */ + iter->partial_map |= iter->start_max < start; + + /* update the max address has been covered. */ + iter->start_max = max(iter->start_max, end); + return true; + } + + return false; +} + +static void __mtrr_lookup_var_next(struct mtrr_iter *iter) +{ + struct kvm_mtrr *mtrr_state = iter->mtrr_state; + + list_for_each_entry_continue(iter->range, &mtrr_state->head, node) + if (match_var_range(iter, iter->range)) + return; + + iter->range = NULL; + iter->partial_map |= iter->start_max < iter->end; +} + +static void mtrr_lookup_var_start(struct mtrr_iter *iter) +{ + struct kvm_mtrr *mtrr_state = iter->mtrr_state; + + iter->fixed = false; + iter->start_max = iter->start; + iter->range = list_prepare_entry(iter->range, &mtrr_state->head, node); + + __mtrr_lookup_var_next(iter); +} + +static void mtrr_lookup_fixed_next(struct mtrr_iter *iter) +{ + /* terminate the lookup. */ + if (fixed_mtrr_range_end_addr(iter->seg, iter->index) >= iter->end) { + iter->fixed = false; + iter->range = NULL; + return; + } + + iter->index++; + + /* have looked up for all fixed MTRRs. */ + if (iter->index >= ARRAY_SIZE(iter->mtrr_state->fixed_ranges)) + return mtrr_lookup_var_start(iter); + + /* switch to next segment. */ + if (iter->index > fixed_mtrr_seg_end_range_index(iter->seg)) + iter->seg++; +} + +static void mtrr_lookup_var_next(struct mtrr_iter *iter) +{ + __mtrr_lookup_var_next(iter); +} + +static void mtrr_lookup_start(struct mtrr_iter *iter) +{ + if (!mtrr_is_enabled(iter->mtrr_state)) { + iter->mtrr_disabled = true; + return; + } + + if (!mtrr_lookup_fixed_start(iter)) + mtrr_lookup_var_start(iter); +} + +static void mtrr_lookup_init(struct mtrr_iter *iter, + struct kvm_mtrr *mtrr_state, u64 start, u64 end) +{ + iter->mtrr_state = mtrr_state; + iter->start = start; + iter->end = end; + iter->mtrr_disabled = false; + iter->partial_map = false; + iter->fixed = false; + iter->range = NULL; + + mtrr_lookup_start(iter); +} + +static bool mtrr_lookup_okay(struct mtrr_iter *iter) +{ + if (iter->fixed) { + iter->mem_type = iter->mtrr_state->fixed_ranges[iter->index]; + return true; + } + + if (iter->range) { + iter->mem_type = iter->range->base & 0xff; + return true; + } + + return false; +} + +static void mtrr_lookup_next(struct mtrr_iter *iter) +{ + if (iter->fixed) + mtrr_lookup_fixed_next(iter); + else + mtrr_lookup_var_next(iter); +} + +#define mtrr_for_each_mem_type(_iter_, _mtrr_, _gpa_start_, _gpa_end_) \ + for (mtrr_lookup_init(_iter_, _mtrr_, _gpa_start_, _gpa_end_); \ + mtrr_lookup_okay(_iter_); mtrr_lookup_next(_iter_)) + +u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; + struct mtrr_iter iter; + u64 start, end; + int type = -1; + const int wt_wb_mask = (1 << MTRR_TYPE_WRBACK) + | (1 << MTRR_TYPE_WRTHROUGH); + + start = gfn_to_gpa(gfn); + end = start + PAGE_SIZE; + + mtrr_for_each_mem_type(&iter, mtrr_state, start, end) { + int curr_type = iter.mem_type; + + /* + * Please refer to Intel SDM Volume 3: 11.11.4.1 MTRR + * Precedences. + */ + + if (type == -1) { + type = curr_type; + continue; + } + + /* + * If two or more variable memory ranges match and the + * memory types are identical, then that memory type is + * used. + */ + if (type == curr_type) + continue; + + /* + * If two or more variable memory ranges match and one of + * the memory types is UC, the UC memory type used. + */ + if (curr_type == MTRR_TYPE_UNCACHABLE) + return MTRR_TYPE_UNCACHABLE; + + /* + * If two or more variable memory ranges match and the + * memory types are WT and WB, the WT memory type is used. + */ + if (((1 << type) & wt_wb_mask) && + ((1 << curr_type) & wt_wb_mask)) { + type = MTRR_TYPE_WRTHROUGH; + continue; + } + + /* + * For overlaps not defined by the above rules, processor + * behavior is undefined. + */ + + /* We use WB for this undefined behavior. :( */ + return MTRR_TYPE_WRBACK; + } + + if (iter.mtrr_disabled) + return mtrr_disabled_type(); + + /* not contained in any MTRRs. */ + if (type == -1) + return mtrr_default_type(mtrr_state); + + /* + * We just check one page, partially covered by MTRRs is + * impossible. + */ + WARN_ON(iter.partial_map); + + return type; +} +EXPORT_SYMBOL_GPL(kvm_mtrr_get_guest_memory_type); + +bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, + int page_num) +{ + struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; + struct mtrr_iter iter; + u64 start, end; + int type = -1; + + start = gfn_to_gpa(gfn); + end = gfn_to_gpa(gfn + page_num); + mtrr_for_each_mem_type(&iter, mtrr_state, start, end) { + if (type == -1) { + type = iter.mem_type; + continue; + } + + if (type != iter.mem_type) + return false; + } + + if (iter.mtrr_disabled) + return true; + + if (!iter.partial_map) + return true; + + if (type == -1) + return true; + + return type == mtrr_default_type(mtrr_state); +} diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 6e6d115fe..0f67d7e24 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -256,7 +256,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, if (ret) return ret; - mark_page_dirty(vcpu->kvm, table_gfn); + kvm_vcpu_mark_page_dirty(vcpu, table_gfn); walker->ptes[level] = pte; } return 0; @@ -338,7 +338,7 @@ retry_walk: real_gfn = gpa_to_gfn(real_gfn); - host_addr = gfn_to_hva_prot(vcpu->kvm, real_gfn, + host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, real_gfn, &walker->pte_writable[walker->level - 1]); if (unlikely(kvm_is_error_hva(host_addr))) goto error; @@ -511,11 +511,11 @@ static bool FNAME(gpte_changed)(struct kvm_vcpu *vcpu, base_gpa = pte_gpa & ~mask; index = (pte_gpa - base_gpa) / sizeof(pt_element_t); - r = kvm_read_guest_atomic(vcpu->kvm, base_gpa, + r = kvm_vcpu_read_guest_atomic(vcpu, base_gpa, gw->prefetch_ptes, sizeof(gw->prefetch_ptes)); curr_pte = gw->prefetch_ptes[index]; } else - r = kvm_read_guest_atomic(vcpu->kvm, pte_gpa, + r = kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &curr_pte, sizeof(curr_pte)); return r || curr_pte != gw->ptes[level - 1]; @@ -869,8 +869,8 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) if (!rmap_can_add(vcpu)) break; - if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte, - sizeof(pt_element_t))) + if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte, + sizeof(pt_element_t))) break; FNAME(update_pte)(vcpu, sp, sptep, &gpte); @@ -956,8 +956,8 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) pte_gpa = first_pte_gpa + i * sizeof(pt_element_t); - if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte, - sizeof(pt_element_t))) + if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte, + sizeof(pt_element_t))) return -EINVAL; if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) { @@ -970,7 +970,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) pte_access &= FNAME(gpte_access)(vcpu, gpte); FNAME(protect_clean_gpte)(&pte_access, gpte); - if (sync_mmio_spte(vcpu->kvm, &sp->spt[i], gfn, pte_access, + if (sync_mmio_spte(vcpu, &sp->spt[i], gfn, pte_access, &nr_present)) continue; diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 29fbf9dfd..31aa2c85d 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -1,11 +1,12 @@ /* * Kernel-based Virtual Machine -- Performance Monitoring Unit support * - * Copyright 2011 Red Hat, Inc. and/or its affiliates. + * Copyright 2015 Red Hat, Inc. and/or its affiliates. * * Authors: * Avi Kivity <avi@redhat.com> * Gleb Natapov <gleb@redhat.com> + * Wei Huang <wei@redhat.com> * * This work is licensed under the terms of the GNU GPL, version 2. See * the COPYING file in the top-level directory. @@ -19,88 +20,39 @@ #include "x86.h" #include "cpuid.h" #include "lapic.h" +#include "pmu.h" + +/* NOTE: + * - Each perf counter is defined as "struct kvm_pmc"; + * - There are two types of perf counters: general purpose (gp) and fixed. + * gp counters are stored in gp_counters[] and fixed counters are stored + * in fixed_counters[] respectively. Both of them are part of "struct + * kvm_pmu"; + * - pmu.c understands the difference between gp counters and fixed counters. + * However AMD doesn't support fixed-counters; + * - There are three types of index to access perf counters (PMC): + * 1. MSR (named msr): For example Intel has MSR_IA32_PERFCTRn and AMD + * has MSR_K7_PERFCTRn. + * 2. MSR Index (named idx): This normally is used by RDPMC instruction. + * For instance AMD RDPMC instruction uses 0000_0003h in ECX to access + * C001_0007h (MSR_K7_PERCTR3). Intel has a similar mechanism, except + * that it also supports fixed counters. idx can be used to as index to + * gp and fixed counters. + * 3. Global PMC Index (named pmc): pmc is an index specific to PMU + * code. Each pmc, stored in kvm_pmc.idx field, is unique across + * all perf counters (both gp and fixed). The mapping relationship + * between pmc and perf counters is as the following: + * * Intel: [0 .. INTEL_PMC_MAX_GENERIC-1] <=> gp counters + * [INTEL_PMC_IDX_FIXED .. INTEL_PMC_IDX_FIXED + 2] <=> fixed + * * AMD: [0 .. AMD64_NUM_COUNTERS-1] <=> gp counters + */ -static struct kvm_arch_event_perf_mapping { - u8 eventsel; - u8 unit_mask; - unsigned event_type; - bool inexact; -} arch_events[] = { - /* Index must match CPUID 0x0A.EBX bit vector */ - [0] = { 0x3c, 0x00, PERF_COUNT_HW_CPU_CYCLES }, - [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS }, - [2] = { 0x3c, 0x01, PERF_COUNT_HW_BUS_CYCLES }, - [3] = { 0x2e, 0x4f, PERF_COUNT_HW_CACHE_REFERENCES }, - [4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES }, - [5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, - [6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, - [7] = { 0x00, 0x30, PERF_COUNT_HW_REF_CPU_CYCLES }, -}; - -/* mapping between fixed pmc index and arch_events array */ -static int fixed_pmc_events[] = {1, 0, 7}; - -static bool pmc_is_gp(struct kvm_pmc *pmc) -{ - return pmc->type == KVM_PMC_GP; -} - -static inline u64 pmc_bitmask(struct kvm_pmc *pmc) -{ - struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; - - return pmu->counter_bitmask[pmc->type]; -} - -static inline bool pmc_enabled(struct kvm_pmc *pmc) -{ - struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; - return test_bit(pmc->idx, (unsigned long *)&pmu->global_ctrl); -} - -static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr, - u32 base) -{ - if (msr >= base && msr < base + pmu->nr_arch_gp_counters) - return &pmu->gp_counters[msr - base]; - return NULL; -} - -static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr) -{ - int base = MSR_CORE_PERF_FIXED_CTR0; - if (msr >= base && msr < base + pmu->nr_arch_fixed_counters) - return &pmu->fixed_counters[msr - base]; - return NULL; -} - -static inline struct kvm_pmc *get_fixed_pmc_idx(struct kvm_pmu *pmu, int idx) -{ - return get_fixed_pmc(pmu, MSR_CORE_PERF_FIXED_CTR0 + idx); -} - -static struct kvm_pmc *global_idx_to_pmc(struct kvm_pmu *pmu, int idx) -{ - if (idx < INTEL_PMC_IDX_FIXED) - return get_gp_pmc(pmu, MSR_P6_EVNTSEL0 + idx, MSR_P6_EVNTSEL0); - else - return get_fixed_pmc_idx(pmu, idx - INTEL_PMC_IDX_FIXED); -} - -void kvm_deliver_pmi(struct kvm_vcpu *vcpu) -{ - if (vcpu->arch.apic) - kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTPC); -} - -static void trigger_pmi(struct irq_work *irq_work) +static void kvm_pmi_trigger_fn(struct irq_work *irq_work) { - struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, - irq_work); - struct kvm_vcpu *vcpu = container_of(pmu, struct kvm_vcpu, - arch.pmu); + struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, irq_work); + struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); - kvm_deliver_pmi(vcpu); + kvm_pmu_deliver_pmi(vcpu); } static void kvm_perf_overflow(struct perf_event *perf_event, @@ -108,63 +60,46 @@ static void kvm_perf_overflow(struct perf_event *perf_event, struct pt_regs *regs) { struct kvm_pmc *pmc = perf_event->overflow_handler_context; - struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; - if (!test_and_set_bit(pmc->idx, (unsigned long *)&pmu->reprogram_pmi)) { + struct kvm_pmu *pmu = pmc_to_pmu(pmc); + + if (!test_and_set_bit(pmc->idx, + (unsigned long *)&pmu->reprogram_pmi)) { __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); kvm_make_request(KVM_REQ_PMU, pmc->vcpu); } } static void kvm_perf_overflow_intr(struct perf_event *perf_event, - struct perf_sample_data *data, struct pt_regs *regs) + struct perf_sample_data *data, + struct pt_regs *regs) { struct kvm_pmc *pmc = perf_event->overflow_handler_context; - struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; - if (!test_and_set_bit(pmc->idx, (unsigned long *)&pmu->reprogram_pmi)) { + struct kvm_pmu *pmu = pmc_to_pmu(pmc); + + if (!test_and_set_bit(pmc->idx, + (unsigned long *)&pmu->reprogram_pmi)) { __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); kvm_make_request(KVM_REQ_PMU, pmc->vcpu); + /* * Inject PMI. If vcpu was in a guest mode during NMI PMI * can be ejected on a guest mode re-entry. Otherwise we can't * be sure that vcpu wasn't executing hlt instruction at the - * time of vmexit and is not going to re-enter guest mode until, + * time of vmexit and is not going to re-enter guest mode until * woken up. So we should wake it, but this is impossible from * NMI context. Do it from irq work instead. */ if (!kvm_is_in_guest()) - irq_work_queue(&pmc->vcpu->arch.pmu.irq_work); + irq_work_queue(&pmc_to_pmu(pmc)->irq_work); else kvm_make_request(KVM_REQ_PMI, pmc->vcpu); } } -static u64 read_pmc(struct kvm_pmc *pmc) -{ - u64 counter, enabled, running; - - counter = pmc->counter; - - if (pmc->perf_event) - counter += perf_event_read_value(pmc->perf_event, - &enabled, &running); - - /* FIXME: Scaling needed? */ - - return counter & pmc_bitmask(pmc); -} - -static void stop_counter(struct kvm_pmc *pmc) -{ - if (pmc->perf_event) { - pmc->counter = read_pmc(pmc); - perf_event_release_kernel(pmc->perf_event); - pmc->perf_event = NULL; - } -} - -static void reprogram_counter(struct kvm_pmc *pmc, u32 type, - unsigned config, bool exclude_user, bool exclude_kernel, - bool intr, bool in_tx, bool in_tx_cp) +static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, + unsigned config, bool exclude_user, + bool exclude_kernel, bool intr, + bool in_tx, bool in_tx_cp) { struct perf_event *event; struct perf_event_attr attr = { @@ -177,6 +112,7 @@ static void reprogram_counter(struct kvm_pmc *pmc, u32 type, .exclude_kernel = exclude_kernel, .config = config, }; + if (in_tx) attr.config |= HSW_IN_TX; if (in_tx_cp) @@ -188,33 +124,16 @@ static void reprogram_counter(struct kvm_pmc *pmc, u32 type, intr ? kvm_perf_overflow_intr : kvm_perf_overflow, pmc); if (IS_ERR(event)) { - printk_once("kvm: pmu event creation failed %ld\n", - PTR_ERR(event)); + printk_once("kvm_pmu: event creation failed %ld\n", + PTR_ERR(event)); return; } pmc->perf_event = event; - clear_bit(pmc->idx, (unsigned long*)&pmc->vcpu->arch.pmu.reprogram_pmi); -} - -static unsigned find_arch_event(struct kvm_pmu *pmu, u8 event_select, - u8 unit_mask) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(arch_events); i++) - if (arch_events[i].eventsel == event_select - && arch_events[i].unit_mask == unit_mask - && (pmu->available_event_types & (1 << i))) - break; - - if (i == ARRAY_SIZE(arch_events)) - return PERF_COUNT_HW_MAX; - - return arch_events[i].event_type; + clear_bit(pmc->idx, (unsigned long*)&pmc_to_pmu(pmc)->reprogram_pmi); } -static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) +void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) { unsigned config, type = PERF_TYPE_RAW; u8 event_select, unit_mask; @@ -224,21 +143,22 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) pmc->eventsel = eventsel; - stop_counter(pmc); + pmc_stop_counter(pmc); - if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_enabled(pmc)) + if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_is_enabled(pmc)) return; event_select = eventsel & ARCH_PERFMON_EVENTSEL_EVENT; unit_mask = (eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE | - ARCH_PERFMON_EVENTSEL_INV | - ARCH_PERFMON_EVENTSEL_CMASK | - HSW_IN_TX | - HSW_IN_TX_CHECKPOINTED))) { - config = find_arch_event(&pmc->vcpu->arch.pmu, event_select, - unit_mask); + ARCH_PERFMON_EVENTSEL_INV | + ARCH_PERFMON_EVENTSEL_CMASK | + HSW_IN_TX | + HSW_IN_TX_CHECKPOINTED))) { + config = kvm_x86_ops->pmu_ops->find_arch_event(pmc_to_pmu(pmc), + event_select, + unit_mask); if (config != PERF_COUNT_HW_MAX) type = PERF_TYPE_HARDWARE; } @@ -246,56 +166,36 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) if (type == PERF_TYPE_RAW) config = eventsel & X86_RAW_EVENT_MASK; - reprogram_counter(pmc, type, config, - !(eventsel & ARCH_PERFMON_EVENTSEL_USR), - !(eventsel & ARCH_PERFMON_EVENTSEL_OS), - eventsel & ARCH_PERFMON_EVENTSEL_INT, - (eventsel & HSW_IN_TX), - (eventsel & HSW_IN_TX_CHECKPOINTED)); + pmc_reprogram_counter(pmc, type, config, + !(eventsel & ARCH_PERFMON_EVENTSEL_USR), + !(eventsel & ARCH_PERFMON_EVENTSEL_OS), + eventsel & ARCH_PERFMON_EVENTSEL_INT, + (eventsel & HSW_IN_TX), + (eventsel & HSW_IN_TX_CHECKPOINTED)); } +EXPORT_SYMBOL_GPL(reprogram_gp_counter); -static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx) +void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx) { - unsigned en = en_pmi & 0x3; - bool pmi = en_pmi & 0x8; + unsigned en_field = ctrl & 0x3; + bool pmi = ctrl & 0x8; - stop_counter(pmc); + pmc_stop_counter(pmc); - if (!en || !pmc_enabled(pmc)) + if (!en_field || !pmc_is_enabled(pmc)) return; - reprogram_counter(pmc, PERF_TYPE_HARDWARE, - arch_events[fixed_pmc_events[idx]].event_type, - !(en & 0x2), /* exclude user */ - !(en & 0x1), /* exclude kernel */ - pmi, false, false); + pmc_reprogram_counter(pmc, PERF_TYPE_HARDWARE, + kvm_x86_ops->pmu_ops->find_fixed_event(idx), + !(en_field & 0x2), /* exclude user */ + !(en_field & 0x1), /* exclude kernel */ + pmi, false, false); } +EXPORT_SYMBOL_GPL(reprogram_fixed_counter); -static inline u8 fixed_en_pmi(u64 ctrl, int idx) +void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx) { - return (ctrl >> (idx * 4)) & 0xf; -} - -static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) -{ - int i; - - for (i = 0; i < pmu->nr_arch_fixed_counters; i++) { - u8 en_pmi = fixed_en_pmi(data, i); - struct kvm_pmc *pmc = get_fixed_pmc_idx(pmu, i); - - if (fixed_en_pmi(pmu->fixed_ctr_ctrl, i) == en_pmi) - continue; - - reprogram_fixed_counter(pmc, en_pmi, i); - } - - pmu->fixed_ctr_ctrl = data; -} - -static void reprogram_idx(struct kvm_pmu *pmu, int idx) -{ - struct kvm_pmc *pmc = global_idx_to_pmc(pmu, idx); + struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, pmc_idx); if (!pmc) return; @@ -303,274 +203,107 @@ static void reprogram_idx(struct kvm_pmu *pmu, int idx) if (pmc_is_gp(pmc)) reprogram_gp_counter(pmc, pmc->eventsel); else { - int fidx = idx - INTEL_PMC_IDX_FIXED; - reprogram_fixed_counter(pmc, - fixed_en_pmi(pmu->fixed_ctr_ctrl, fidx), fidx); + int idx = pmc_idx - INTEL_PMC_IDX_FIXED; + u8 ctrl = fixed_ctrl_field(pmu->fixed_ctr_ctrl, idx); + + reprogram_fixed_counter(pmc, ctrl, idx); } } +EXPORT_SYMBOL_GPL(reprogram_counter); -static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data) +void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) { + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + u64 bitmask; int bit; - u64 diff = pmu->global_ctrl ^ data; - - pmu->global_ctrl = data; - - for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) - reprogram_idx(pmu, bit); -} -bool kvm_pmu_msr(struct kvm_vcpu *vcpu, u32 msr) -{ - struct kvm_pmu *pmu = &vcpu->arch.pmu; - int ret; - - switch (msr) { - case MSR_CORE_PERF_FIXED_CTR_CTRL: - case MSR_CORE_PERF_GLOBAL_STATUS: - case MSR_CORE_PERF_GLOBAL_CTRL: - case MSR_CORE_PERF_GLOBAL_OVF_CTRL: - ret = pmu->version > 1; - break; - default: - ret = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0) - || get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0) - || get_fixed_pmc(pmu, msr); - break; - } - return ret; -} + bitmask = pmu->reprogram_pmi; -int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data) -{ - struct kvm_pmu *pmu = &vcpu->arch.pmu; - struct kvm_pmc *pmc; + for_each_set_bit(bit, (unsigned long *)&bitmask, X86_PMC_IDX_MAX) { + struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, bit); - switch (index) { - case MSR_CORE_PERF_FIXED_CTR_CTRL: - *data = pmu->fixed_ctr_ctrl; - return 0; - case MSR_CORE_PERF_GLOBAL_STATUS: - *data = pmu->global_status; - return 0; - case MSR_CORE_PERF_GLOBAL_CTRL: - *data = pmu->global_ctrl; - return 0; - case MSR_CORE_PERF_GLOBAL_OVF_CTRL: - *data = pmu->global_ovf_ctrl; - return 0; - default: - if ((pmc = get_gp_pmc(pmu, index, MSR_IA32_PERFCTR0)) || - (pmc = get_fixed_pmc(pmu, index))) { - *data = read_pmc(pmc); - return 0; - } else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) { - *data = pmc->eventsel; - return 0; + if (unlikely(!pmc || !pmc->perf_event)) { + clear_bit(bit, (unsigned long *)&pmu->reprogram_pmi); + continue; } - } - return 1; -} -int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) -{ - struct kvm_pmu *pmu = &vcpu->arch.pmu; - struct kvm_pmc *pmc; - u32 index = msr_info->index; - u64 data = msr_info->data; - - switch (index) { - case MSR_CORE_PERF_FIXED_CTR_CTRL: - if (pmu->fixed_ctr_ctrl == data) - return 0; - if (!(data & 0xfffffffffffff444ull)) { - reprogram_fixed_counters(pmu, data); - return 0; - } - break; - case MSR_CORE_PERF_GLOBAL_STATUS: - if (msr_info->host_initiated) { - pmu->global_status = data; - return 0; - } - break; /* RO MSR */ - case MSR_CORE_PERF_GLOBAL_CTRL: - if (pmu->global_ctrl == data) - return 0; - if (!(data & pmu->global_ctrl_mask)) { - global_ctrl_changed(pmu, data); - return 0; - } - break; - case MSR_CORE_PERF_GLOBAL_OVF_CTRL: - if (!(data & (pmu->global_ctrl_mask & ~(3ull<<62)))) { - if (!msr_info->host_initiated) - pmu->global_status &= ~data; - pmu->global_ovf_ctrl = data; - return 0; - } - break; - default: - if ((pmc = get_gp_pmc(pmu, index, MSR_IA32_PERFCTR0)) || - (pmc = get_fixed_pmc(pmu, index))) { - if (!msr_info->host_initiated) - data = (s64)(s32)data; - pmc->counter += data - read_pmc(pmc); - return 0; - } else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) { - if (data == pmc->eventsel) - return 0; - if (!(data & pmu->reserved_bits)) { - reprogram_gp_counter(pmc, data); - return 0; - } - } + reprogram_counter(pmu, bit); } - return 1; } -int kvm_pmu_check_pmc(struct kvm_vcpu *vcpu, unsigned pmc) +/* check if idx is a valid index to access PMU */ +int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) { - struct kvm_pmu *pmu = &vcpu->arch.pmu; - bool fixed = pmc & (1u << 30); - pmc &= ~(3u << 30); - return (!fixed && pmc >= pmu->nr_arch_gp_counters) || - (fixed && pmc >= pmu->nr_arch_fixed_counters); + return kvm_x86_ops->pmu_ops->is_valid_msr_idx(vcpu, idx); } -int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data) +int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) { - struct kvm_pmu *pmu = &vcpu->arch.pmu; - bool fast_mode = pmc & (1u << 31); - bool fixed = pmc & (1u << 30); - struct kvm_pmc *counters; - u64 ctr; - - pmc &= ~(3u << 30); - if (!fixed && pmc >= pmu->nr_arch_gp_counters) - return 1; - if (fixed && pmc >= pmu->nr_arch_fixed_counters) + bool fast_mode = idx & (1u << 31); + struct kvm_pmc *pmc; + u64 ctr_val; + + pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, idx); + if (!pmc) return 1; - counters = fixed ? pmu->fixed_counters : pmu->gp_counters; - ctr = read_pmc(&counters[pmc]); + + ctr_val = pmc_read_counter(pmc); if (fast_mode) - ctr = (u32)ctr; - *data = ctr; + ctr_val = (u32)ctr_val; + *data = ctr_val; return 0; } -void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu) +void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu) { - struct kvm_pmu *pmu = &vcpu->arch.pmu; - struct kvm_cpuid_entry2 *entry; - union cpuid10_eax eax; - union cpuid10_edx edx; - - pmu->nr_arch_gp_counters = 0; - pmu->nr_arch_fixed_counters = 0; - pmu->counter_bitmask[KVM_PMC_GP] = 0; - pmu->counter_bitmask[KVM_PMC_FIXED] = 0; - pmu->version = 0; - pmu->reserved_bits = 0xffffffff00200000ull; - - entry = kvm_find_cpuid_entry(vcpu, 0xa, 0); - if (!entry) - return; - eax.full = entry->eax; - edx.full = entry->edx; - - pmu->version = eax.split.version_id; - if (!pmu->version) - return; - - pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters, - INTEL_PMC_MAX_GENERIC); - pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1; - pmu->available_event_types = ~entry->ebx & - ((1ull << eax.split.mask_length) - 1); - - if (pmu->version == 1) { - pmu->nr_arch_fixed_counters = 0; - } else { - pmu->nr_arch_fixed_counters = - min_t(int, edx.split.num_counters_fixed, - INTEL_PMC_MAX_FIXED); - pmu->counter_bitmask[KVM_PMC_FIXED] = - ((u64)1 << edx.split.bit_width_fixed) - 1; - } + if (vcpu->arch.apic) + kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTPC); +} - pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) | - (((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED); - pmu->global_ctrl_mask = ~pmu->global_ctrl; +bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) +{ + return kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, msr); +} - entry = kvm_find_cpuid_entry(vcpu, 7, 0); - if (entry && - (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) && - (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM))) - pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED; +int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) +{ + return kvm_x86_ops->pmu_ops->get_msr(vcpu, msr, data); } -void kvm_pmu_init(struct kvm_vcpu *vcpu) +int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { - int i; - struct kvm_pmu *pmu = &vcpu->arch.pmu; + return kvm_x86_ops->pmu_ops->set_msr(vcpu, msr_info); +} - memset(pmu, 0, sizeof(*pmu)); - for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { - pmu->gp_counters[i].type = KVM_PMC_GP; - pmu->gp_counters[i].vcpu = vcpu; - pmu->gp_counters[i].idx = i; - } - for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) { - pmu->fixed_counters[i].type = KVM_PMC_FIXED; - pmu->fixed_counters[i].vcpu = vcpu; - pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED; - } - init_irq_work(&pmu->irq_work, trigger_pmi); - kvm_pmu_cpuid_update(vcpu); +/* refresh PMU settings. This function generally is called when underlying + * settings are changed (such as changes of PMU CPUID by guest VMs), which + * should rarely happen. + */ +void kvm_pmu_refresh(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops->pmu_ops->refresh(vcpu); } void kvm_pmu_reset(struct kvm_vcpu *vcpu) { - struct kvm_pmu *pmu = &vcpu->arch.pmu; - int i; + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); irq_work_sync(&pmu->irq_work); - for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { - struct kvm_pmc *pmc = &pmu->gp_counters[i]; - stop_counter(pmc); - pmc->counter = pmc->eventsel = 0; - } + kvm_x86_ops->pmu_ops->reset(vcpu); +} - for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) - stop_counter(&pmu->fixed_counters[i]); +void kvm_pmu_init(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = - pmu->global_ovf_ctrl = 0; + memset(pmu, 0, sizeof(*pmu)); + kvm_x86_ops->pmu_ops->init(vcpu); + init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn); + kvm_pmu_refresh(vcpu); } void kvm_pmu_destroy(struct kvm_vcpu *vcpu) { kvm_pmu_reset(vcpu); } - -void kvm_handle_pmu_event(struct kvm_vcpu *vcpu) -{ - struct kvm_pmu *pmu = &vcpu->arch.pmu; - u64 bitmask; - int bit; - - bitmask = pmu->reprogram_pmi; - - for_each_set_bit(bit, (unsigned long *)&bitmask, X86_PMC_IDX_MAX) { - struct kvm_pmc *pmc = global_idx_to_pmc(pmu, bit); - - if (unlikely(!pmc || !pmc->perf_event)) { - clear_bit(bit, (unsigned long *)&pmu->reprogram_pmi); - continue; - } - - reprogram_idx(pmu, bit); - } -} diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h new file mode 100644 index 000000000..f96e1f962 --- /dev/null +++ b/arch/x86/kvm/pmu.h @@ -0,0 +1,118 @@ +#ifndef __KVM_X86_PMU_H +#define __KVM_X86_PMU_H + +#define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu) +#define pmu_to_vcpu(pmu) (container_of((pmu), struct kvm_vcpu, arch.pmu)) +#define pmc_to_pmu(pmc) (&(pmc)->vcpu->arch.pmu) + +/* retrieve the 4 bits for EN and PMI out of IA32_FIXED_CTR_CTRL */ +#define fixed_ctrl_field(ctrl_reg, idx) (((ctrl_reg) >> ((idx)*4)) & 0xf) + +struct kvm_event_hw_type_mapping { + u8 eventsel; + u8 unit_mask; + unsigned event_type; +}; + +struct kvm_pmu_ops { + unsigned (*find_arch_event)(struct kvm_pmu *pmu, u8 event_select, + u8 unit_mask); + unsigned (*find_fixed_event)(int idx); + bool (*pmc_is_enabled)(struct kvm_pmc *pmc); + struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu, int pmc_idx); + struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, unsigned idx); + int (*is_valid_msr_idx)(struct kvm_vcpu *vcpu, unsigned idx); + bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr); + int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr, u64 *data); + int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info); + void (*refresh)(struct kvm_vcpu *vcpu); + void (*init)(struct kvm_vcpu *vcpu); + void (*reset)(struct kvm_vcpu *vcpu); +}; + +static inline u64 pmc_bitmask(struct kvm_pmc *pmc) +{ + struct kvm_pmu *pmu = pmc_to_pmu(pmc); + + return pmu->counter_bitmask[pmc->type]; +} + +static inline u64 pmc_read_counter(struct kvm_pmc *pmc) +{ + u64 counter, enabled, running; + + counter = pmc->counter; + if (pmc->perf_event) + counter += perf_event_read_value(pmc->perf_event, + &enabled, &running); + /* FIXME: Scaling needed? */ + return counter & pmc_bitmask(pmc); +} + +static inline void pmc_stop_counter(struct kvm_pmc *pmc) +{ + if (pmc->perf_event) { + pmc->counter = pmc_read_counter(pmc); + perf_event_release_kernel(pmc->perf_event); + pmc->perf_event = NULL; + } +} + +static inline bool pmc_is_gp(struct kvm_pmc *pmc) +{ + return pmc->type == KVM_PMC_GP; +} + +static inline bool pmc_is_fixed(struct kvm_pmc *pmc) +{ + return pmc->type == KVM_PMC_FIXED; +} + +static inline bool pmc_is_enabled(struct kvm_pmc *pmc) +{ + return kvm_x86_ops->pmu_ops->pmc_is_enabled(pmc); +} + +/* returns general purpose PMC with the specified MSR. Note that it can be + * used for both PERFCTRn and EVNTSELn; that is why it accepts base as a + * paramenter to tell them apart. + */ +static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr, + u32 base) +{ + if (msr >= base && msr < base + pmu->nr_arch_gp_counters) + return &pmu->gp_counters[msr - base]; + + return NULL; +} + +/* returns fixed PMC with the specified MSR */ +static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr) +{ + int base = MSR_CORE_PERF_FIXED_CTR0; + + if (msr >= base && msr < base + pmu->nr_arch_fixed_counters) + return &pmu->fixed_counters[msr - base]; + + return NULL; +} + +void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel); +void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int fixed_idx); +void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx); + +void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu); +void kvm_pmu_handle_event(struct kvm_vcpu *vcpu); +int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data); +int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx); +bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr); +int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data); +int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); +void kvm_pmu_refresh(struct kvm_vcpu *vcpu); +void kvm_pmu_reset(struct kvm_vcpu *vcpu); +void kvm_pmu_init(struct kvm_vcpu *vcpu); +void kvm_pmu_destroy(struct kvm_vcpu *vcpu); + +extern struct kvm_pmu_ops intel_pmu_ops; +extern struct kvm_pmu_ops amd_pmu_ops; +#endif /* __KVM_X86_PMU_H */ diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c new file mode 100644 index 000000000..886aa25a7 --- /dev/null +++ b/arch/x86/kvm/pmu_amd.c @@ -0,0 +1,207 @@ +/* + * KVM PMU support for AMD + * + * Copyright 2015, Red Hat, Inc. and/or its affiliates. + * + * Author: + * Wei Huang <wei@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Implementation is based on pmu_intel.c file + */ +#include <linux/types.h> +#include <linux/kvm_host.h> +#include <linux/perf_event.h> +#include "x86.h" +#include "cpuid.h" +#include "lapic.h" +#include "pmu.h" + +/* duplicated from amd_perfmon_event_map, K7 and above should work. */ +static struct kvm_event_hw_type_mapping amd_event_mapping[] = { + [0] = { 0x76, 0x00, PERF_COUNT_HW_CPU_CYCLES }, + [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS }, + [2] = { 0x80, 0x00, PERF_COUNT_HW_CACHE_REFERENCES }, + [3] = { 0x81, 0x00, PERF_COUNT_HW_CACHE_MISSES }, + [4] = { 0xc2, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, + [5] = { 0xc3, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, + [6] = { 0xd0, 0x00, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND }, + [7] = { 0xd1, 0x00, PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, +}; + +static unsigned amd_find_arch_event(struct kvm_pmu *pmu, + u8 event_select, + u8 unit_mask) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(amd_event_mapping); i++) + if (amd_event_mapping[i].eventsel == event_select + && amd_event_mapping[i].unit_mask == unit_mask) + break; + + if (i == ARRAY_SIZE(amd_event_mapping)) + return PERF_COUNT_HW_MAX; + + return amd_event_mapping[i].event_type; +} + +/* return PERF_COUNT_HW_MAX as AMD doesn't have fixed events */ +static unsigned amd_find_fixed_event(int idx) +{ + return PERF_COUNT_HW_MAX; +} + +/* check if a PMC is enabled by comparing it against global_ctrl bits. Because + * AMD CPU doesn't have global_ctrl MSR, all PMCs are enabled (return TRUE). + */ +static bool amd_pmc_is_enabled(struct kvm_pmc *pmc) +{ + return true; +} + +static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) +{ + return get_gp_pmc(pmu, MSR_K7_EVNTSEL0 + pmc_idx, MSR_K7_EVNTSEL0); +} + +/* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */ +static int amd_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + + idx &= ~(3u << 30); + + return (idx >= pmu->nr_arch_gp_counters); +} + +/* idx is the ECX register of RDPMC instruction */ +static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *counters; + + idx &= ~(3u << 30); + if (idx >= pmu->nr_arch_gp_counters) + return NULL; + counters = pmu->gp_counters; + + return &counters[idx]; +} + +static bool amd_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + int ret = false; + + ret = get_gp_pmc(pmu, msr, MSR_K7_PERFCTR0) || + get_gp_pmc(pmu, msr, MSR_K7_EVNTSEL0); + + return ret; +} + +static int amd_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + + /* MSR_K7_PERFCTRn */ + pmc = get_gp_pmc(pmu, msr, MSR_K7_PERFCTR0); + if (pmc) { + *data = pmc_read_counter(pmc); + return 0; + } + /* MSR_K7_EVNTSELn */ + pmc = get_gp_pmc(pmu, msr, MSR_K7_EVNTSEL0); + if (pmc) { + *data = pmc->eventsel; + return 0; + } + + return 1; +} + +static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + u32 msr = msr_info->index; + u64 data = msr_info->data; + + /* MSR_K7_PERFCTRn */ + pmc = get_gp_pmc(pmu, msr, MSR_K7_PERFCTR0); + if (pmc) { + if (!msr_info->host_initiated) + data = (s64)data; + pmc->counter += data - pmc_read_counter(pmc); + return 0; + } + /* MSR_K7_EVNTSELn */ + pmc = get_gp_pmc(pmu, msr, MSR_K7_EVNTSEL0); + if (pmc) { + if (data == pmc->eventsel) + return 0; + if (!(data & pmu->reserved_bits)) { + reprogram_gp_counter(pmc, data); + return 0; + } + } + + return 1; +} + +static void amd_pmu_refresh(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + + pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS; + pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1; + pmu->reserved_bits = 0xffffffff00200000ull; + /* not applicable to AMD; but clean them to prevent any fall out */ + pmu->counter_bitmask[KVM_PMC_FIXED] = 0; + pmu->nr_arch_fixed_counters = 0; + pmu->version = 0; + pmu->global_status = 0; +} + +static void amd_pmu_init(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + int i; + + for (i = 0; i < AMD64_NUM_COUNTERS ; i++) { + pmu->gp_counters[i].type = KVM_PMC_GP; + pmu->gp_counters[i].vcpu = vcpu; + pmu->gp_counters[i].idx = i; + } +} + +static void amd_pmu_reset(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + int i; + + for (i = 0; i < AMD64_NUM_COUNTERS; i++) { + struct kvm_pmc *pmc = &pmu->gp_counters[i]; + + pmc_stop_counter(pmc); + pmc->counter = pmc->eventsel = 0; + } +} + +struct kvm_pmu_ops amd_pmu_ops = { + .find_arch_event = amd_find_arch_event, + .find_fixed_event = amd_find_fixed_event, + .pmc_is_enabled = amd_pmc_is_enabled, + .pmc_idx_to_pmc = amd_pmc_idx_to_pmc, + .msr_idx_to_pmc = amd_msr_idx_to_pmc, + .is_valid_msr_idx = amd_is_valid_msr_idx, + .is_valid_msr = amd_is_valid_msr, + .get_msr = amd_pmu_get_msr, + .set_msr = amd_pmu_set_msr, + .refresh = amd_pmu_refresh, + .init = amd_pmu_init, + .reset = amd_pmu_reset, +}; diff --git a/arch/x86/kvm/pmu_intel.c b/arch/x86/kvm/pmu_intel.c new file mode 100644 index 000000000..ab38af4f4 --- /dev/null +++ b/arch/x86/kvm/pmu_intel.c @@ -0,0 +1,358 @@ +/* + * KVM PMU support for Intel CPUs + * + * Copyright 2011 Red Hat, Inc. and/or its affiliates. + * + * Authors: + * Avi Kivity <avi@redhat.com> + * Gleb Natapov <gleb@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ +#include <linux/types.h> +#include <linux/kvm_host.h> +#include <linux/perf_event.h> +#include <asm/perf_event.h> +#include "x86.h" +#include "cpuid.h" +#include "lapic.h" +#include "pmu.h" + +static struct kvm_event_hw_type_mapping intel_arch_events[] = { + /* Index must match CPUID 0x0A.EBX bit vector */ + [0] = { 0x3c, 0x00, PERF_COUNT_HW_CPU_CYCLES }, + [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS }, + [2] = { 0x3c, 0x01, PERF_COUNT_HW_BUS_CYCLES }, + [3] = { 0x2e, 0x4f, PERF_COUNT_HW_CACHE_REFERENCES }, + [4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES }, + [5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, + [6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, + [7] = { 0x00, 0x30, PERF_COUNT_HW_REF_CPU_CYCLES }, +}; + +/* mapping between fixed pmc index and intel_arch_events array */ +static int fixed_pmc_events[] = {1, 0, 7}; + +static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) +{ + int i; + + for (i = 0; i < pmu->nr_arch_fixed_counters; i++) { + u8 new_ctrl = fixed_ctrl_field(data, i); + u8 old_ctrl = fixed_ctrl_field(pmu->fixed_ctr_ctrl, i); + struct kvm_pmc *pmc; + + pmc = get_fixed_pmc(pmu, MSR_CORE_PERF_FIXED_CTR0 + i); + + if (old_ctrl == new_ctrl) + continue; + + reprogram_fixed_counter(pmc, new_ctrl, i); + } + + pmu->fixed_ctr_ctrl = data; +} + +/* function is called when global control register has been updated. */ +static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data) +{ + int bit; + u64 diff = pmu->global_ctrl ^ data; + + pmu->global_ctrl = data; + + for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) + reprogram_counter(pmu, bit); +} + +static unsigned intel_find_arch_event(struct kvm_pmu *pmu, + u8 event_select, + u8 unit_mask) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(intel_arch_events); i++) + if (intel_arch_events[i].eventsel == event_select + && intel_arch_events[i].unit_mask == unit_mask + && (pmu->available_event_types & (1 << i))) + break; + + if (i == ARRAY_SIZE(intel_arch_events)) + return PERF_COUNT_HW_MAX; + + return intel_arch_events[i].event_type; +} + +static unsigned intel_find_fixed_event(int idx) +{ + if (idx >= ARRAY_SIZE(fixed_pmc_events)) + return PERF_COUNT_HW_MAX; + + return intel_arch_events[fixed_pmc_events[idx]].event_type; +} + +/* check if a PMC is enabled by comparising it with globl_ctrl bits. */ +static bool intel_pmc_is_enabled(struct kvm_pmc *pmc) +{ + struct kvm_pmu *pmu = pmc_to_pmu(pmc); + + return test_bit(pmc->idx, (unsigned long *)&pmu->global_ctrl); +} + +static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) +{ + if (pmc_idx < INTEL_PMC_IDX_FIXED) + return get_gp_pmc(pmu, MSR_P6_EVNTSEL0 + pmc_idx, + MSR_P6_EVNTSEL0); + else { + u32 idx = pmc_idx - INTEL_PMC_IDX_FIXED; + + return get_fixed_pmc(pmu, idx + MSR_CORE_PERF_FIXED_CTR0); + } +} + +/* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */ +static int intel_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + bool fixed = idx & (1u << 30); + + idx &= ~(3u << 30); + + return (!fixed && idx >= pmu->nr_arch_gp_counters) || + (fixed && idx >= pmu->nr_arch_fixed_counters); +} + +static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu, + unsigned idx) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + bool fixed = idx & (1u << 30); + struct kvm_pmc *counters; + + idx &= ~(3u << 30); + if (!fixed && idx >= pmu->nr_arch_gp_counters) + return NULL; + if (fixed && idx >= pmu->nr_arch_fixed_counters) + return NULL; + counters = fixed ? pmu->fixed_counters : pmu->gp_counters; + + return &counters[idx]; +} + +static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + int ret; + + switch (msr) { + case MSR_CORE_PERF_FIXED_CTR_CTRL: + case MSR_CORE_PERF_GLOBAL_STATUS: + case MSR_CORE_PERF_GLOBAL_CTRL: + case MSR_CORE_PERF_GLOBAL_OVF_CTRL: + ret = pmu->version > 1; + break; + default: + ret = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0) || + get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0) || + get_fixed_pmc(pmu, msr); + break; + } + + return ret; +} + +static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + + switch (msr) { + case MSR_CORE_PERF_FIXED_CTR_CTRL: + *data = pmu->fixed_ctr_ctrl; + return 0; + case MSR_CORE_PERF_GLOBAL_STATUS: + *data = pmu->global_status; + return 0; + case MSR_CORE_PERF_GLOBAL_CTRL: + *data = pmu->global_ctrl; + return 0; + case MSR_CORE_PERF_GLOBAL_OVF_CTRL: + *data = pmu->global_ovf_ctrl; + return 0; + default: + if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) || + (pmc = get_fixed_pmc(pmu, msr))) { + *data = pmc_read_counter(pmc); + return 0; + } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { + *data = pmc->eventsel; + return 0; + } + } + + return 1; +} + +static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + u32 msr = msr_info->index; + u64 data = msr_info->data; + + switch (msr) { + case MSR_CORE_PERF_FIXED_CTR_CTRL: + if (pmu->fixed_ctr_ctrl == data) + return 0; + if (!(data & 0xfffffffffffff444ull)) { + reprogram_fixed_counters(pmu, data); + return 0; + } + break; + case MSR_CORE_PERF_GLOBAL_STATUS: + if (msr_info->host_initiated) { + pmu->global_status = data; + return 0; + } + break; /* RO MSR */ + case MSR_CORE_PERF_GLOBAL_CTRL: + if (pmu->global_ctrl == data) + return 0; + if (!(data & pmu->global_ctrl_mask)) { + global_ctrl_changed(pmu, data); + return 0; + } + break; + case MSR_CORE_PERF_GLOBAL_OVF_CTRL: + if (!(data & (pmu->global_ctrl_mask & ~(3ull<<62)))) { + if (!msr_info->host_initiated) + pmu->global_status &= ~data; + pmu->global_ovf_ctrl = data; + return 0; + } + break; + default: + if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) || + (pmc = get_fixed_pmc(pmu, msr))) { + if (!msr_info->host_initiated) + data = (s64)(s32)data; + pmc->counter += data - pmc_read_counter(pmc); + return 0; + } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { + if (data == pmc->eventsel) + return 0; + if (!(data & pmu->reserved_bits)) { + reprogram_gp_counter(pmc, data); + return 0; + } + } + } + + return 1; +} + +static void intel_pmu_refresh(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_cpuid_entry2 *entry; + union cpuid10_eax eax; + union cpuid10_edx edx; + + pmu->nr_arch_gp_counters = 0; + pmu->nr_arch_fixed_counters = 0; + pmu->counter_bitmask[KVM_PMC_GP] = 0; + pmu->counter_bitmask[KVM_PMC_FIXED] = 0; + pmu->version = 0; + pmu->reserved_bits = 0xffffffff00200000ull; + + entry = kvm_find_cpuid_entry(vcpu, 0xa, 0); + if (!entry) + return; + eax.full = entry->eax; + edx.full = entry->edx; + + pmu->version = eax.split.version_id; + if (!pmu->version) + return; + + pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters, + INTEL_PMC_MAX_GENERIC); + pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1; + pmu->available_event_types = ~entry->ebx & + ((1ull << eax.split.mask_length) - 1); + + if (pmu->version == 1) { + pmu->nr_arch_fixed_counters = 0; + } else { + pmu->nr_arch_fixed_counters = + min_t(int, edx.split.num_counters_fixed, + INTEL_PMC_MAX_FIXED); + pmu->counter_bitmask[KVM_PMC_FIXED] = + ((u64)1 << edx.split.bit_width_fixed) - 1; + } + + pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) | + (((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED); + pmu->global_ctrl_mask = ~pmu->global_ctrl; + + entry = kvm_find_cpuid_entry(vcpu, 7, 0); + if (entry && + (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) && + (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM))) + pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED; +} + +static void intel_pmu_init(struct kvm_vcpu *vcpu) +{ + int i; + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + + for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { + pmu->gp_counters[i].type = KVM_PMC_GP; + pmu->gp_counters[i].vcpu = vcpu; + pmu->gp_counters[i].idx = i; + } + + for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) { + pmu->fixed_counters[i].type = KVM_PMC_FIXED; + pmu->fixed_counters[i].vcpu = vcpu; + pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED; + } +} + +static void intel_pmu_reset(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + int i; + + for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { + struct kvm_pmc *pmc = &pmu->gp_counters[i]; + + pmc_stop_counter(pmc); + pmc->counter = pmc->eventsel = 0; + } + + for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) + pmc_stop_counter(&pmu->fixed_counters[i]); + + pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = + pmu->global_ovf_ctrl = 0; +} + +struct kvm_pmu_ops intel_pmu_ops = { + .find_arch_event = intel_find_arch_event, + .find_fixed_event = intel_find_fixed_event, + .pmc_is_enabled = intel_pmc_is_enabled, + .pmc_idx_to_pmc = intel_pmc_idx_to_pmc, + .msr_idx_to_pmc = intel_msr_idx_to_pmc, + .is_valid_msr_idx = intel_is_valid_msr_idx, + .is_valid_msr = intel_is_valid_msr, + .get_msr = intel_pmu_get_msr, + .set_msr = intel_pmu_set_msr, + .refresh = intel_pmu_refresh, + .init = intel_pmu_init, + .reset = intel_pmu_reset, +}; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 4911bf191..8e0c0844c 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -21,6 +21,7 @@ #include "kvm_cache_regs.h" #include "x86.h" #include "cpuid.h" +#include "pmu.h" #include <linux/module.h> #include <linux/mod_devicetable.h> @@ -28,7 +29,7 @@ #include <linux/vmalloc.h> #include <linux/highmem.h> #include <linux/sched.h> -#include <linux/ftrace_event.h> +#include <linux/trace_events.h> #include <linux/slab.h> #include <asm/perf_event.h> @@ -864,6 +865,64 @@ static void svm_disable_lbrv(struct vcpu_svm *svm) set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0); } +#define MTRR_TYPE_UC_MINUS 7 +#define MTRR2PROTVAL_INVALID 0xff + +static u8 mtrr2protval[8]; + +static u8 fallback_mtrr_type(int mtrr) +{ + /* + * WT and WP aren't always available in the host PAT. Treat + * them as UC and UC- respectively. Everything else should be + * there. + */ + switch (mtrr) + { + case MTRR_TYPE_WRTHROUGH: + return MTRR_TYPE_UNCACHABLE; + case MTRR_TYPE_WRPROT: + return MTRR_TYPE_UC_MINUS; + default: + BUG(); + } +} + +static void build_mtrr2protval(void) +{ + int i; + u64 pat; + + for (i = 0; i < 8; i++) + mtrr2protval[i] = MTRR2PROTVAL_INVALID; + + /* Ignore the invalid MTRR types. */ + mtrr2protval[2] = 0; + mtrr2protval[3] = 0; + + /* + * Use host PAT value to figure out the mapping from guest MTRR + * values to nested page table PAT/PCD/PWT values. We do not + * want to change the host PAT value every time we enter the + * guest. + */ + rdmsrl(MSR_IA32_CR_PAT, pat); + for (i = 0; i < 8; i++) { + u8 mtrr = pat >> (8 * i); + + if (mtrr2protval[mtrr] == MTRR2PROTVAL_INVALID) + mtrr2protval[mtrr] = __cm_idx2pte(i); + } + + for (i = 0; i < 8; i++) { + if (mtrr2protval[i] == MTRR2PROTVAL_INVALID) { + u8 fallback = fallback_mtrr_type(i); + mtrr2protval[i] = mtrr2protval[fallback]; + BUG_ON(mtrr2protval[i] == MTRR2PROTVAL_INVALID); + } + } +} + static __init int svm_hardware_setup(void) { int cpu; @@ -930,6 +989,7 @@ static __init int svm_hardware_setup(void) } else kvm_disable_tdp(); + build_mtrr2protval(); return 0; err: @@ -1084,7 +1144,40 @@ static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) return target_tsc - tsc; } -static void init_vmcb(struct vcpu_svm *svm) +static void svm_set_guest_pat(struct vcpu_svm *svm, u64 *g_pat) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + + /* Unlike Intel, AMD takes the guest's CR0.CD into account. + * + * AMD does not have IPAT. To emulate it for the case of guests + * with no assigned devices, just set everything to WB. If guests + * have assigned devices, however, we cannot force WB for RAM + * pages only, so use the guest PAT directly. + */ + if (!kvm_arch_has_assigned_device(vcpu->kvm)) + *g_pat = 0x0606060606060606; + else + *g_pat = vcpu->arch.pat; +} + +static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) +{ + u8 mtrr; + + /* + * 1. MMIO: trust guest MTRR, so same as item 3. + * 2. No passthrough: always map as WB, and force guest PAT to WB as well + * 3. Passthrough: can't guarantee the result, try to trust guest. + */ + if (!is_mmio && !kvm_arch_has_assigned_device(vcpu->kvm)) + return 0; + + mtrr = kvm_mtrr_get_guest_memory_type(vcpu, gfn); + return mtrr2protval[mtrr]; +} + +static void init_vmcb(struct vcpu_svm *svm, bool init_event) { struct vmcb_control_area *control = &svm->vmcb->control; struct vmcb_save_area *save = &svm->vmcb->save; @@ -1155,17 +1248,17 @@ static void init_vmcb(struct vcpu_svm *svm) init_sys_seg(&save->ldtr, SEG_TYPE_LDT); init_sys_seg(&save->tr, SEG_TYPE_BUSY_TSS16); - svm_set_efer(&svm->vcpu, 0); + if (!init_event) + svm_set_efer(&svm->vcpu, 0); save->dr6 = 0xffff0ff0; kvm_set_rflags(&svm->vcpu, 2); save->rip = 0x0000fff0; svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip; /* - * This is the guest-visible cr0 value. * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0. + * It also updates the guest-visible cr0 value. */ - svm->vcpu.arch.cr0 = 0; (void)kvm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET); save->cr4 = X86_CR4_PAE; @@ -1178,7 +1271,8 @@ static void init_vmcb(struct vcpu_svm *svm) clr_exception_intercept(svm, PF_VECTOR); clr_cr_intercept(svm, INTERCEPT_CR3_READ); clr_cr_intercept(svm, INTERCEPT_CR3_WRITE); - save->g_pat = 0x0007040600070406ULL; + save->g_pat = svm->vcpu.arch.pat; + svm_set_guest_pat(svm, &save->g_pat); save->cr3 = 0; save->cr4 = 0; } @@ -1197,13 +1291,19 @@ static void init_vmcb(struct vcpu_svm *svm) enable_gif(svm); } -static void svm_vcpu_reset(struct kvm_vcpu *vcpu) +static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { struct vcpu_svm *svm = to_svm(vcpu); u32 dummy; u32 eax = 1; - init_vmcb(svm); + if (!init_event) { + svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE | + MSR_IA32_APICBASE_ENABLE; + if (kvm_vcpu_is_reset_bsp(&svm->vcpu)) + svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP; + } + init_vmcb(svm, init_event); kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy); kvm_register_write(vcpu, VCPU_REGS_RDX, eax); @@ -1259,12 +1359,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) clear_page(svm->vmcb); svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT; svm->asid_generation = 0; - init_vmcb(svm); - - svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE | - MSR_IA32_APICBASE_ENABLE; - if (kvm_vcpu_is_reset_bsp(&svm->vcpu)) - svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP; + init_vmcb(svm, false); svm_init_osvw(&svm->vcpu); @@ -1577,7 +1672,8 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) * does not do it - this results in some delay at * reboot */ - cr0 &= ~(X86_CR0_CD | X86_CR0_NW); + if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) + cr0 &= ~(X86_CR0_CD | X86_CR0_NW); svm->vmcb->save.cr0 = cr0; mark_dirty(svm->vmcb, VMCB_CR); update_cr0_intercept(svm); @@ -1885,7 +1981,7 @@ static int shutdown_interception(struct vcpu_svm *svm) * so reinitialize it. */ clear_page(svm->vmcb); - init_vmcb(svm); + init_vmcb(svm, false); kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; return 0; @@ -1955,8 +2051,8 @@ static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) u64 pdpte; int ret; - ret = kvm_read_guest_page(vcpu->kvm, gpa_to_gfn(cr3), &pdpte, - offset_in_page(cr3) + index * 8, 8); + ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(cr3), &pdpte, + offset_in_page(cr3) + index * 8, 8); if (ret) return 0; return pdpte; @@ -2114,7 +2210,7 @@ static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, struct page **_page) might_sleep(); - page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT); + page = kvm_vcpu_gfn_to_page(&svm->vcpu, gpa >> PAGE_SHIFT); if (is_error_page(page)) goto error; @@ -2153,7 +2249,7 @@ static int nested_svm_intercept_ioio(struct vcpu_svm *svm) mask = (0xf >> (4 - size)) << start_bit; val = 0; - if (kvm_read_guest(svm->vcpu.kvm, gpa, &val, iopm_len)) + if (kvm_vcpu_read_guest(&svm->vcpu, gpa, &val, iopm_len)) return NESTED_EXIT_DONE; return (val & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST; @@ -2178,7 +2274,7 @@ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm) /* Offset is in 32 bit units but need in 8 bit units */ offset *= 4; - if (kvm_read_guest(svm->vcpu.kvm, svm->nested.vmcb_msrpm + offset, &value, 4)) + if (kvm_vcpu_read_guest(&svm->vcpu, svm->nested.vmcb_msrpm + offset, &value, 4)) return NESTED_EXIT_DONE; return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST; @@ -2449,7 +2545,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) p = msrpm_offsets[i]; offset = svm->nested.vmcb_msrpm + (p * 4); - if (kvm_read_guest(svm->vcpu.kvm, offset, &value, 4)) + if (kvm_vcpu_read_guest(&svm->vcpu, offset, &value, 4)) return false; svm->nested.msrpm[p] = svm->msrpm[p] | value; @@ -3069,42 +3165,42 @@ static u64 svm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) svm_scale_tsc(vcpu, host_tsc); } -static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) +static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct vcpu_svm *svm = to_svm(vcpu); - switch (ecx) { + switch (msr_info->index) { case MSR_IA32_TSC: { - *data = svm->vmcb->control.tsc_offset + + msr_info->data = svm->vmcb->control.tsc_offset + svm_scale_tsc(vcpu, native_read_tsc()); break; } case MSR_STAR: - *data = svm->vmcb->save.star; + msr_info->data = svm->vmcb->save.star; break; #ifdef CONFIG_X86_64 case MSR_LSTAR: - *data = svm->vmcb->save.lstar; + msr_info->data = svm->vmcb->save.lstar; break; case MSR_CSTAR: - *data = svm->vmcb->save.cstar; + msr_info->data = svm->vmcb->save.cstar; break; case MSR_KERNEL_GS_BASE: - *data = svm->vmcb->save.kernel_gs_base; + msr_info->data = svm->vmcb->save.kernel_gs_base; break; case MSR_SYSCALL_MASK: - *data = svm->vmcb->save.sfmask; + msr_info->data = svm->vmcb->save.sfmask; break; #endif case MSR_IA32_SYSENTER_CS: - *data = svm->vmcb->save.sysenter_cs; + msr_info->data = svm->vmcb->save.sysenter_cs; break; case MSR_IA32_SYSENTER_EIP: - *data = svm->sysenter_eip; + msr_info->data = svm->sysenter_eip; break; case MSR_IA32_SYSENTER_ESP: - *data = svm->sysenter_esp; + msr_info->data = svm->sysenter_esp; break; /* * Nobody will change the following 5 values in the VMCB so we can @@ -3112,31 +3208,31 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) * implemented. */ case MSR_IA32_DEBUGCTLMSR: - *data = svm->vmcb->save.dbgctl; + msr_info->data = svm->vmcb->save.dbgctl; break; case MSR_IA32_LASTBRANCHFROMIP: - *data = svm->vmcb->save.br_from; + msr_info->data = svm->vmcb->save.br_from; break; case MSR_IA32_LASTBRANCHTOIP: - *data = svm->vmcb->save.br_to; + msr_info->data = svm->vmcb->save.br_to; break; case MSR_IA32_LASTINTFROMIP: - *data = svm->vmcb->save.last_excp_from; + msr_info->data = svm->vmcb->save.last_excp_from; break; case MSR_IA32_LASTINTTOIP: - *data = svm->vmcb->save.last_excp_to; + msr_info->data = svm->vmcb->save.last_excp_to; break; case MSR_VM_HSAVE_PA: - *data = svm->nested.hsave_msr; + msr_info->data = svm->nested.hsave_msr; break; case MSR_VM_CR: - *data = svm->nested.vm_cr_msr; + msr_info->data = svm->nested.vm_cr_msr; break; case MSR_IA32_UCODE_REV: - *data = 0x01000065; + msr_info->data = 0x01000065; break; default: - return kvm_get_msr_common(vcpu, ecx, data); + return kvm_get_msr_common(vcpu, msr_info); } return 0; } @@ -3144,16 +3240,20 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) static int rdmsr_interception(struct vcpu_svm *svm) { u32 ecx = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX); - u64 data; + struct msr_data msr_info; - if (svm_get_msr(&svm->vcpu, ecx, &data)) { + msr_info.index = ecx; + msr_info.host_initiated = false; + if (svm_get_msr(&svm->vcpu, &msr_info)) { trace_kvm_msr_read_ex(ecx); kvm_inject_gp(&svm->vcpu, 0); } else { - trace_kvm_msr_read(ecx, data); + trace_kvm_msr_read(ecx, msr_info.data); - kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, data & 0xffffffff); - kvm_register_write(&svm->vcpu, VCPU_REGS_RDX, data >> 32); + kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, + msr_info.data & 0xffffffff); + kvm_register_write(&svm->vcpu, VCPU_REGS_RDX, + msr_info.data >> 32); svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; skip_emulated_instruction(&svm->vcpu); } @@ -3247,6 +3347,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_VM_IGNNE: vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); break; + case MSR_IA32_CR_PAT: + if (npt_enabled) { + if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data)) + return 1; + vcpu->arch.pat = data; + svm_set_guest_pat(svm, &svm->vmcb->save.g_pat); + mark_dirty(svm->vmcb, VMCB_NPT); + break; + } + /* fall through */ default: return kvm_set_msr_common(vcpu, msr); } @@ -3390,6 +3500,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_MWAIT] = mwait_interception, [SVM_EXIT_XSETBV] = xsetbv_interception, [SVM_EXIT_NPF] = pf_interception, + [SVM_EXIT_RSM] = emulate_on_interception, }; static void dump_vmcb(struct kvm_vcpu *vcpu) @@ -4075,9 +4186,9 @@ static bool svm_cpu_has_accelerated_tpr(void) return false; } -static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) +static bool svm_has_high_real_mode_segbase(void) { - return 0; + return true; } static void svm_cpuid_update(struct kvm_vcpu *vcpu) @@ -4350,6 +4461,7 @@ static struct kvm_x86_ops svm_x86_ops = { .hardware_enable = svm_hardware_enable, .hardware_disable = svm_hardware_disable, .cpu_has_accelerated_tpr = svm_cpu_has_accelerated_tpr, + .cpu_has_high_real_mode_segbase = svm_has_high_real_mode_segbase, .vcpu_create = svm_create_vcpu, .vcpu_free = svm_free_vcpu, @@ -4444,6 +4556,8 @@ static struct kvm_x86_ops svm_x86_ops = { .handle_external_intr = svm_handle_external_intr, .sched_in = svm_sched_in, + + .pmu_ops = &amd_pmu_ops, }; static int __init svm_init(void) diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 7c7bc8bef..4eae7c35d 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -952,6 +952,28 @@ TRACE_EVENT(kvm_wait_lapic_expire, __entry->delta < 0 ? "early" : "late") ); +TRACE_EVENT(kvm_enter_smm, + TP_PROTO(unsigned int vcpu_id, u64 smbase, bool entering), + TP_ARGS(vcpu_id, smbase, entering), + + TP_STRUCT__entry( + __field( unsigned int, vcpu_id ) + __field( u64, smbase ) + __field( bool, entering ) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->smbase = smbase; + __entry->entering = entering; + ), + + TP_printk("vcpu %u: %s SMM, smbase 0x%llx", + __entry->vcpu_id, + __entry->entering ? "entering" : "leaving", + __entry->smbase) +); + #endif /* _TRACE_KVM_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 2d73807f0..83b7b5cd7 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -28,7 +28,7 @@ #include <linux/sched.h> #include <linux/moduleparam.h> #include <linux/mod_devicetable.h> -#include <linux/ftrace_event.h> +#include <linux/trace_events.h> #include <linux/slab.h> #include <linux/tboot.h> #include <linux/hrtimer.h> @@ -40,14 +40,14 @@ #include <asm/vmx.h> #include <asm/virtext.h> #include <asm/mce.h> -#include <asm/i387.h> -#include <asm/xcr.h> +#include <asm/fpu/internal.h> #include <asm/perf_event.h> #include <asm/debugreg.h> #include <asm/kexec.h> #include <asm/apic.h> #include "trace.h" +#include "pmu.h" #define __ex(x) __kvm_handle_fault_on_reboot(x) #define __ex_clear(x, reg) \ @@ -786,7 +786,7 @@ static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) static struct page *nested_get_page(struct kvm_vcpu *vcpu, gpa_t addr) { - struct page *page = gfn_to_page(vcpu->kvm, addr >> PAGE_SHIFT); + struct page *page = kvm_vcpu_gfn_to_page(vcpu, addr >> PAGE_SHIFT); if (is_error_page(page)) return NULL; @@ -1883,7 +1883,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) * If the FPU is not active (through the host task or * the guest vcpu), then restore the cr0.TS bit. */ - if (!user_has_fpu() && !vmx->vcpu.guest_fpu_loaded) + if (!fpregs_active() && !vmx->vcpu.guest_fpu_loaded) stts(); load_gdt(this_cpu_ptr(&host_gdt)); } @@ -2170,8 +2170,7 @@ static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu) if (is_guest_mode(vcpu)) msr_bitmap = vmx_msr_bitmap_nested; - else if (irqchip_in_kernel(vcpu->kvm) && - apic_x2apic_mode(vcpu->arch.apic)) { + else if (vcpu->arch.apic_base & X2APIC_ENABLE) { if (is_long_mode(vcpu)) msr_bitmap = vmx_msr_bitmap_longmode_x2apic; else @@ -2623,76 +2622,69 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ -static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) +static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { - u64 data; struct shared_msr_entry *msr; - if (!pdata) { - printk(KERN_ERR "BUG: get_msr called with NULL pdata\n"); - return -EINVAL; - } - - switch (msr_index) { + switch (msr_info->index) { #ifdef CONFIG_X86_64 case MSR_FS_BASE: - data = vmcs_readl(GUEST_FS_BASE); + msr_info->data = vmcs_readl(GUEST_FS_BASE); break; case MSR_GS_BASE: - data = vmcs_readl(GUEST_GS_BASE); + msr_info->data = vmcs_readl(GUEST_GS_BASE); break; case MSR_KERNEL_GS_BASE: vmx_load_host_state(to_vmx(vcpu)); - data = to_vmx(vcpu)->msr_guest_kernel_gs_base; + msr_info->data = to_vmx(vcpu)->msr_guest_kernel_gs_base; break; #endif case MSR_EFER: - return kvm_get_msr_common(vcpu, msr_index, pdata); + return kvm_get_msr_common(vcpu, msr_info); case MSR_IA32_TSC: - data = guest_read_tsc(); + msr_info->data = guest_read_tsc(); break; case MSR_IA32_SYSENTER_CS: - data = vmcs_read32(GUEST_SYSENTER_CS); + msr_info->data = vmcs_read32(GUEST_SYSENTER_CS); break; case MSR_IA32_SYSENTER_EIP: - data = vmcs_readl(GUEST_SYSENTER_EIP); + msr_info->data = vmcs_readl(GUEST_SYSENTER_EIP); break; case MSR_IA32_SYSENTER_ESP: - data = vmcs_readl(GUEST_SYSENTER_ESP); + msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP); break; case MSR_IA32_BNDCFGS: if (!vmx_mpx_supported()) return 1; - data = vmcs_read64(GUEST_BNDCFGS); + msr_info->data = vmcs_read64(GUEST_BNDCFGS); break; case MSR_IA32_FEATURE_CONTROL: if (!nested_vmx_allowed(vcpu)) return 1; - data = to_vmx(vcpu)->nested.msr_ia32_feature_control; + msr_info->data = to_vmx(vcpu)->nested.msr_ia32_feature_control; break; case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: if (!nested_vmx_allowed(vcpu)) return 1; - return vmx_get_vmx_msr(vcpu, msr_index, pdata); + return vmx_get_vmx_msr(vcpu, msr_info->index, &msr_info->data); case MSR_IA32_XSS: if (!vmx_xsaves_supported()) return 1; - data = vcpu->arch.ia32_xss; + msr_info->data = vcpu->arch.ia32_xss; break; case MSR_TSC_AUX: if (!to_vmx(vcpu)->rdtscp_enabled) return 1; /* Otherwise falls through */ default: - msr = find_msr_entry(to_vmx(vcpu), msr_index); + msr = find_msr_entry(to_vmx(vcpu), msr_info->index); if (msr) { - data = msr->data; + msr_info->data = msr->data; break; } - return kvm_get_msr_common(vcpu, msr_index, pdata); + return kvm_get_msr_common(vcpu, msr_info); } - *pdata = data; return 0; } @@ -4123,7 +4115,7 @@ static int alloc_apic_access_page(struct kvm *kvm) kvm_userspace_mem.flags = 0; kvm_userspace_mem.guest_phys_addr = APIC_DEFAULT_PHYS_BASE; kvm_userspace_mem.memory_size = PAGE_SIZE; - r = __kvm_set_memory_region(kvm, &kvm_userspace_mem); + r = __x86_set_memory_region(kvm, &kvm_userspace_mem); if (r) goto out; @@ -4158,7 +4150,7 @@ static int alloc_identity_pagetable(struct kvm *kvm) kvm_userspace_mem.guest_phys_addr = kvm->arch.ept_identity_map_addr; kvm_userspace_mem.memory_size = PAGE_SIZE; - r = __kvm_set_memory_region(kvm, &kvm_userspace_mem); + r = __x86_set_memory_region(kvm, &kvm_userspace_mem); return r; } @@ -4667,16 +4659,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0); vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest)); - if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { - u32 msr_low, msr_high; - u64 host_pat; - rdmsr(MSR_IA32_CR_PAT, msr_low, msr_high); - host_pat = msr_low | ((u64) msr_high << 32); - /* Write the default value follow host pat */ - vmcs_write64(GUEST_IA32_PAT, host_pat); - /* Keep arch.pat sync with GUEST_IA32_PAT */ - vmx->vcpu.arch.pat = host_pat; - } + if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) + vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) { u32 index = vmx_msr_index[i]; @@ -4708,22 +4692,27 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) return 0; } -static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) +static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct msr_data apic_base_msr; + u64 cr0; vmx->rmode.vm86_active = 0; vmx->soft_vnmi_blocked = 0; vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); - kvm_set_cr8(&vmx->vcpu, 0); - apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; - if (kvm_vcpu_is_reset_bsp(&vmx->vcpu)) - apic_base_msr.data |= MSR_IA32_APICBASE_BSP; - apic_base_msr.host_initiated = true; - kvm_set_apic_base(&vmx->vcpu, &apic_base_msr); + kvm_set_cr8(vcpu, 0); + + if (!init_event) { + apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | + MSR_IA32_APICBASE_ENABLE; + if (kvm_vcpu_is_reset_bsp(vcpu)) + apic_base_msr.data |= MSR_IA32_APICBASE_BSP; + apic_base_msr.host_initiated = true; + kvm_set_apic_base(vcpu, &apic_base_msr); + } vmx_segment_cache_clear(vmx); @@ -4747,9 +4736,12 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_LDTR_LIMIT, 0xffff); vmcs_write32(GUEST_LDTR_AR_BYTES, 0x00082); - vmcs_write32(GUEST_SYSENTER_CS, 0); - vmcs_writel(GUEST_SYSENTER_ESP, 0); - vmcs_writel(GUEST_SYSENTER_EIP, 0); + if (!init_event) { + vmcs_write32(GUEST_SYSENTER_CS, 0); + vmcs_writel(GUEST_SYSENTER_ESP, 0); + vmcs_writel(GUEST_SYSENTER_EIP, 0); + vmcs_write64(GUEST_IA32_DEBUGCTL, 0); + } vmcs_writel(GUEST_RFLAGS, 0x02); kvm_rip_write(vcpu, 0xfff0); @@ -4764,18 +4756,15 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0); - /* Special registers */ - vmcs_write64(GUEST_IA32_DEBUGCTL, 0); - setup_msrs(vmx); vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); /* 22.2.1 */ - if (cpu_has_vmx_tpr_shadow()) { + if (cpu_has_vmx_tpr_shadow() && !init_event) { vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0); - if (vm_need_tpr_shadow(vmx->vcpu.kvm)) + if (vm_need_tpr_shadow(vcpu->kvm)) vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, - __pa(vmx->vcpu.arch.apic->regs)); + __pa(vcpu->arch.apic->regs)); vmcs_write32(TPR_THRESHOLD, 0); } @@ -4787,12 +4776,14 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) if (vmx->vpid != 0) vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); - vmx->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; - vmx_set_cr0(&vmx->vcpu, kvm_read_cr0(vcpu)); /* enter rmode */ - vmx_set_cr4(&vmx->vcpu, 0); - vmx_set_efer(&vmx->vcpu, 0); - vmx_fpu_activate(&vmx->vcpu); - update_exception_bitmap(&vmx->vcpu); + cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; + vmx_set_cr0(vcpu, cr0); /* enter rmode */ + vmx->vcpu.arch.cr0 = cr0; + vmx_set_cr4(vcpu, 0); + if (!init_event) + vmx_set_efer(vcpu, 0); + vmx_fpu_activate(vcpu); + update_exception_bitmap(vcpu); vpid_sync_context(vmx); } @@ -4965,7 +4956,7 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) .flags = 0, }; - ret = kvm_set_memory_region(kvm, &tss_mem); + ret = x86_set_memory_region(kvm, &tss_mem); if (ret) return ret; kvm->arch.tss_addr = addr; @@ -5475,19 +5466,21 @@ static int handle_cpuid(struct kvm_vcpu *vcpu) static int handle_rdmsr(struct kvm_vcpu *vcpu) { u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX]; - u64 data; + struct msr_data msr_info; - if (vmx_get_msr(vcpu, ecx, &data)) { + msr_info.index = ecx; + msr_info.host_initiated = false; + if (vmx_get_msr(vcpu, &msr_info)) { trace_kvm_msr_read_ex(ecx); kvm_inject_gp(vcpu, 0); return 1; } - trace_kvm_msr_read(ecx, data); + trace_kvm_msr_read(ecx, msr_info.data); /* FIXME: handling of bits 32:63 of rax, rdx */ - vcpu->arch.regs[VCPU_REGS_RAX] = data & -1u; - vcpu->arch.regs[VCPU_REGS_RDX] = (data >> 32) & -1u; + vcpu->arch.regs[VCPU_REGS_RAX] = msr_info.data & -1u; + vcpu->arch.regs[VCPU_REGS_RDX] = (msr_info.data >> 32) & -1u; skip_emulated_instruction(vcpu); return 1; } @@ -5710,9 +5703,6 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) return 0; } - /* clear all local breakpoint enable flags */ - vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~0x155); - /* * TODO: What about debug traps on tss switch? * Are we supposed to inject them and update dr6? @@ -7333,7 +7323,7 @@ static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, bitmap += (port & 0x7fff) / 8; if (last_bitmap != bitmap) - if (kvm_read_guest(vcpu->kvm, bitmap, &b, 1)) + if (kvm_vcpu_read_guest(vcpu, bitmap, &b, 1)) return true; if (b & (1 << (port & 7))) return true; @@ -7377,7 +7367,7 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu, /* Then read the msr_index'th bit from this bitmap: */ if (msr_index < 1024*8) { unsigned char b; - if (kvm_read_guest(vcpu->kvm, bitmap + msr_index/8, &b, 1)) + if (kvm_vcpu_read_guest(vcpu, bitmap + msr_index/8, &b, 1)) return true; return 1 & (b >> (msr_index & 7)); } else @@ -7642,9 +7632,9 @@ static void vmx_disable_pml(struct vcpu_vmx *vmx) vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); } -static void vmx_flush_pml_buffer(struct vcpu_vmx *vmx) +static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu) { - struct kvm *kvm = vmx->vcpu.kvm; + struct vcpu_vmx *vmx = to_vmx(vcpu); u64 *pml_buf; u16 pml_idx; @@ -7666,7 +7656,7 @@ static void vmx_flush_pml_buffer(struct vcpu_vmx *vmx) gpa = pml_buf[pml_idx]; WARN_ON(gpa & (PAGE_SIZE - 1)); - mark_page_dirty(kvm, gpa >> PAGE_SHIFT); + kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT); } /* reset PML index */ @@ -7691,6 +7681,158 @@ static void kvm_flush_pml_buffers(struct kvm *kvm) kvm_vcpu_kick(vcpu); } +static void vmx_dump_sel(char *name, uint32_t sel) +{ + pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n", + name, vmcs_read32(sel), + vmcs_read32(sel + GUEST_ES_AR_BYTES - GUEST_ES_SELECTOR), + vmcs_read32(sel + GUEST_ES_LIMIT - GUEST_ES_SELECTOR), + vmcs_readl(sel + GUEST_ES_BASE - GUEST_ES_SELECTOR)); +} + +static void vmx_dump_dtsel(char *name, uint32_t limit) +{ + pr_err("%s limit=0x%08x, base=0x%016lx\n", + name, vmcs_read32(limit), + vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT)); +} + +static void dump_vmcs(void) +{ + u32 vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS); + u32 vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS); + u32 cpu_based_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); + u32 pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL); + u32 secondary_exec_control = 0; + unsigned long cr4 = vmcs_readl(GUEST_CR4); + u64 efer = vmcs_readl(GUEST_IA32_EFER); + int i, n; + + if (cpu_has_secondary_exec_ctrls()) + secondary_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); + + pr_err("*** Guest State ***\n"); + pr_err("CR0: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n", + vmcs_readl(GUEST_CR0), vmcs_readl(CR0_READ_SHADOW), + vmcs_readl(CR0_GUEST_HOST_MASK)); + pr_err("CR4: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n", + cr4, vmcs_readl(CR4_READ_SHADOW), vmcs_readl(CR4_GUEST_HOST_MASK)); + pr_err("CR3 = 0x%016lx\n", vmcs_readl(GUEST_CR3)); + if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT) && + (cr4 & X86_CR4_PAE) && !(efer & EFER_LMA)) + { + pr_err("PDPTR0 = 0x%016lx PDPTR1 = 0x%016lx\n", + vmcs_readl(GUEST_PDPTR0), vmcs_readl(GUEST_PDPTR1)); + pr_err("PDPTR2 = 0x%016lx PDPTR3 = 0x%016lx\n", + vmcs_readl(GUEST_PDPTR2), vmcs_readl(GUEST_PDPTR3)); + } + pr_err("RSP = 0x%016lx RIP = 0x%016lx\n", + vmcs_readl(GUEST_RSP), vmcs_readl(GUEST_RIP)); + pr_err("RFLAGS=0x%08lx DR7 = 0x%016lx\n", + vmcs_readl(GUEST_RFLAGS), vmcs_readl(GUEST_DR7)); + pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n", + vmcs_readl(GUEST_SYSENTER_ESP), + vmcs_read32(GUEST_SYSENTER_CS), vmcs_readl(GUEST_SYSENTER_EIP)); + vmx_dump_sel("CS: ", GUEST_CS_SELECTOR); + vmx_dump_sel("DS: ", GUEST_DS_SELECTOR); + vmx_dump_sel("SS: ", GUEST_SS_SELECTOR); + vmx_dump_sel("ES: ", GUEST_ES_SELECTOR); + vmx_dump_sel("FS: ", GUEST_FS_SELECTOR); + vmx_dump_sel("GS: ", GUEST_GS_SELECTOR); + vmx_dump_dtsel("GDTR:", GUEST_GDTR_LIMIT); + vmx_dump_sel("LDTR:", GUEST_LDTR_SELECTOR); + vmx_dump_dtsel("IDTR:", GUEST_IDTR_LIMIT); + vmx_dump_sel("TR: ", GUEST_TR_SELECTOR); + if ((vmexit_ctl & (VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER)) || + (vmentry_ctl & (VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_IA32_EFER))) + pr_err("EFER = 0x%016llx PAT = 0x%016lx\n", + efer, vmcs_readl(GUEST_IA32_PAT)); + pr_err("DebugCtl = 0x%016lx DebugExceptions = 0x%016lx\n", + vmcs_readl(GUEST_IA32_DEBUGCTL), + vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS)); + if (vmentry_ctl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) + pr_err("PerfGlobCtl = 0x%016lx\n", + vmcs_readl(GUEST_IA32_PERF_GLOBAL_CTRL)); + if (vmentry_ctl & VM_ENTRY_LOAD_BNDCFGS) + pr_err("BndCfgS = 0x%016lx\n", vmcs_readl(GUEST_BNDCFGS)); + pr_err("Interruptibility = %08x ActivityState = %08x\n", + vmcs_read32(GUEST_INTERRUPTIBILITY_INFO), + vmcs_read32(GUEST_ACTIVITY_STATE)); + if (secondary_exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) + pr_err("InterruptStatus = %04x\n", + vmcs_read16(GUEST_INTR_STATUS)); + + pr_err("*** Host State ***\n"); + pr_err("RIP = 0x%016lx RSP = 0x%016lx\n", + vmcs_readl(HOST_RIP), vmcs_readl(HOST_RSP)); + pr_err("CS=%04x SS=%04x DS=%04x ES=%04x FS=%04x GS=%04x TR=%04x\n", + vmcs_read16(HOST_CS_SELECTOR), vmcs_read16(HOST_SS_SELECTOR), + vmcs_read16(HOST_DS_SELECTOR), vmcs_read16(HOST_ES_SELECTOR), + vmcs_read16(HOST_FS_SELECTOR), vmcs_read16(HOST_GS_SELECTOR), + vmcs_read16(HOST_TR_SELECTOR)); + pr_err("FSBase=%016lx GSBase=%016lx TRBase=%016lx\n", + vmcs_readl(HOST_FS_BASE), vmcs_readl(HOST_GS_BASE), + vmcs_readl(HOST_TR_BASE)); + pr_err("GDTBase=%016lx IDTBase=%016lx\n", + vmcs_readl(HOST_GDTR_BASE), vmcs_readl(HOST_IDTR_BASE)); + pr_err("CR0=%016lx CR3=%016lx CR4=%016lx\n", + vmcs_readl(HOST_CR0), vmcs_readl(HOST_CR3), + vmcs_readl(HOST_CR4)); + pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n", + vmcs_readl(HOST_IA32_SYSENTER_ESP), + vmcs_read32(HOST_IA32_SYSENTER_CS), + vmcs_readl(HOST_IA32_SYSENTER_EIP)); + if (vmexit_ctl & (VM_EXIT_LOAD_IA32_PAT | VM_EXIT_LOAD_IA32_EFER)) + pr_err("EFER = 0x%016lx PAT = 0x%016lx\n", + vmcs_readl(HOST_IA32_EFER), vmcs_readl(HOST_IA32_PAT)); + if (vmexit_ctl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) + pr_err("PerfGlobCtl = 0x%016lx\n", + vmcs_readl(HOST_IA32_PERF_GLOBAL_CTRL)); + + pr_err("*** Control State ***\n"); + pr_err("PinBased=%08x CPUBased=%08x SecondaryExec=%08x\n", + pin_based_exec_ctrl, cpu_based_exec_ctrl, secondary_exec_control); + pr_err("EntryControls=%08x ExitControls=%08x\n", vmentry_ctl, vmexit_ctl); + pr_err("ExceptionBitmap=%08x PFECmask=%08x PFECmatch=%08x\n", + vmcs_read32(EXCEPTION_BITMAP), + vmcs_read32(PAGE_FAULT_ERROR_CODE_MASK), + vmcs_read32(PAGE_FAULT_ERROR_CODE_MATCH)); + pr_err("VMEntry: intr_info=%08x errcode=%08x ilen=%08x\n", + vmcs_read32(VM_ENTRY_INTR_INFO_FIELD), + vmcs_read32(VM_ENTRY_EXCEPTION_ERROR_CODE), + vmcs_read32(VM_ENTRY_INSTRUCTION_LEN)); + pr_err("VMExit: intr_info=%08x errcode=%08x ilen=%08x\n", + vmcs_read32(VM_EXIT_INTR_INFO), + vmcs_read32(VM_EXIT_INTR_ERROR_CODE), + vmcs_read32(VM_EXIT_INSTRUCTION_LEN)); + pr_err(" reason=%08x qualification=%016lx\n", + vmcs_read32(VM_EXIT_REASON), vmcs_readl(EXIT_QUALIFICATION)); + pr_err("IDTVectoring: info=%08x errcode=%08x\n", + vmcs_read32(IDT_VECTORING_INFO_FIELD), + vmcs_read32(IDT_VECTORING_ERROR_CODE)); + pr_err("TSC Offset = 0x%016lx\n", vmcs_readl(TSC_OFFSET)); + if (cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW) + pr_err("TPR Threshold = 0x%02x\n", vmcs_read32(TPR_THRESHOLD)); + if (pin_based_exec_ctrl & PIN_BASED_POSTED_INTR) + pr_err("PostedIntrVec = 0x%02x\n", vmcs_read16(POSTED_INTR_NV)); + if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT)) + pr_err("EPT pointer = 0x%016lx\n", vmcs_readl(EPT_POINTER)); + n = vmcs_read32(CR3_TARGET_COUNT); + for (i = 0; i + 1 < n; i += 4) + pr_err("CR3 target%u=%016lx target%u=%016lx\n", + i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2), + i + 1, vmcs_readl(CR3_TARGET_VALUE0 + i * 2 + 2)); + if (i < n) + pr_err("CR3 target%u=%016lx\n", + i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2)); + if (secondary_exec_control & SECONDARY_EXEC_PAUSE_LOOP_EXITING) + pr_err("PLE Gap=%08x Window=%08x\n", + vmcs_read32(PLE_GAP), vmcs_read32(PLE_WINDOW)); + if (secondary_exec_control & SECONDARY_EXEC_ENABLE_VPID) + pr_err("Virtual processor ID = 0x%04x\n", + vmcs_read16(VIRTUAL_PROCESSOR_ID)); +} + /* * The guest has exited. See if we can fix it or if we need userspace * assistance. @@ -7709,7 +7851,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) * flushed already. */ if (enable_pml) - vmx_flush_pml_buffer(vmx); + vmx_flush_pml_buffer(vcpu); /* If guest state is invalid, start emulating */ if (vmx->emulation_required) @@ -7723,6 +7865,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) } if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) { + dump_vmcs(); vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; vcpu->run->fail_entry.hardware_entry_failure_reason = exit_reason; @@ -7996,6 +8139,11 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) local_irq_enable(); } +static bool vmx_has_high_real_mode_segbase(void) +{ + return enable_unrestricted_guest || emulate_invalid_guest_state; +} + static bool vmx_mpx_supported(void) { return (vmcs_config.vmexit_ctrl & VM_EXIT_CLEAR_BNDCFGS) && @@ -8480,29 +8628,39 @@ static int get_ept_level(void) static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { - u64 ret; + u8 cache; + u64 ipat = 0; /* For VT-d and EPT combination - * 1. MMIO: always map as UC + * 1. MMIO: guest may want to apply WC, trust it. * 2. EPT with VT-d: * a. VT-d without snooping control feature: can't guarantee the - * result, try to trust guest. + * result, try to trust guest. So the same as item 1. * b. VT-d with snooping control feature: snooping control feature of * VT-d engine can guarantee the cache correctness. Just set it * to WB to keep consistent with host. So the same as item 3. * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep * consistent with host MTRR */ - if (is_mmio) - ret = MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT; - else if (kvm_arch_has_noncoherent_dma(vcpu->kvm)) - ret = kvm_get_guest_memory_type(vcpu, gfn) << - VMX_EPT_MT_EPTE_SHIFT; - else - ret = (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT) - | VMX_EPT_IPAT_BIT; + if (!is_mmio && !kvm_arch_has_noncoherent_dma(vcpu->kvm)) { + ipat = VMX_EPT_IPAT_BIT; + cache = MTRR_TYPE_WRBACK; + goto exit; + } - return ret; + if (kvm_read_cr0(vcpu) & X86_CR0_CD) { + ipat = VMX_EPT_IPAT_BIT; + if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) + cache = MTRR_TYPE_WRBACK; + else + cache = MTRR_TYPE_UNCACHABLE; + goto exit; + } + + cache = kvm_mtrr_get_guest_memory_type(vcpu, gfn); + +exit: + return (cache << VMX_EPT_MT_EPTE_SHIFT) | ipat; } static int vmx_get_lpage_level(void) @@ -8924,7 +9082,7 @@ static int nested_vmx_msr_check_common(struct kvm_vcpu *vcpu, struct vmx_msr_entry *e) { /* x2APIC MSR accesses are not allowed */ - if (apic_x2apic_mode(vcpu->arch.apic) && e->index >> 8 == 0x8) + if (vcpu->arch.apic_base & X2APIC_ENABLE && e->index >> 8 == 0x8) return -EINVAL; if (e->index == MSR_IA32_UCODE_WRITE || /* SDM Table 35-2 */ e->index == MSR_IA32_UCODE_REV) @@ -8966,8 +9124,8 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) msr.host_initiated = false; for (i = 0; i < count; i++) { - if (kvm_read_guest(vcpu->kvm, gpa + i * sizeof(e), - &e, sizeof(e))) { + if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e), + &e, sizeof(e))) { pr_warn_ratelimited( "%s cannot read MSR entry (%u, 0x%08llx)\n", __func__, i, gpa + i * sizeof(e)); @@ -8999,9 +9157,10 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) struct vmx_msr_entry e; for (i = 0; i < count; i++) { - if (kvm_read_guest(vcpu->kvm, - gpa + i * sizeof(e), - &e, 2 * sizeof(u32))) { + struct msr_data msr_info; + if (kvm_vcpu_read_guest(vcpu, + gpa + i * sizeof(e), + &e, 2 * sizeof(u32))) { pr_warn_ratelimited( "%s cannot read MSR entry (%u, 0x%08llx)\n", __func__, i, gpa + i * sizeof(e)); @@ -9013,19 +9172,21 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) __func__, i, e.index, e.reserved); return -EINVAL; } - if (kvm_get_msr(vcpu, e.index, &e.value)) { + msr_info.host_initiated = false; + msr_info.index = e.index; + if (kvm_get_msr(vcpu, &msr_info)) { pr_warn_ratelimited( "%s cannot read MSR (%u, 0x%x)\n", __func__, i, e.index); return -EINVAL; } - if (kvm_write_guest(vcpu->kvm, - gpa + i * sizeof(e) + - offsetof(struct vmx_msr_entry, value), - &e.value, sizeof(e.value))) { + if (kvm_vcpu_write_guest(vcpu, + gpa + i * sizeof(e) + + offsetof(struct vmx_msr_entry, value), + &msr_info.data, sizeof(msr_info.data))) { pr_warn_ratelimited( "%s cannot write MSR (%u, 0x%x, 0x%llx)\n", - __func__, i, e.index, e.value); + __func__, i, e.index, msr_info.data); return -EINVAL; } } @@ -10150,6 +10311,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .hardware_enable = hardware_enable, .hardware_disable = hardware_disable, .cpu_has_accelerated_tpr = report_flexpriority, + .cpu_has_high_real_mode_segbase = vmx_has_high_real_mode_segbase, .vcpu_create = vmx_create_vcpu, .vcpu_free = vmx_free_vcpu, @@ -10255,6 +10417,8 @@ static struct kvm_x86_ops vmx_x86_ops = { .slot_disable_log_dirty = vmx_slot_disable_log_dirty, .flush_log_dirty = vmx_flush_log_dirty, .enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked, + + .pmu_ops = &intel_pmu_ops, }; static int __init vmx_init(void) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ea306adbb..8f0f6eca6 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -28,6 +28,7 @@ #include "x86.h" #include "cpuid.h" #include "assigned-dev.h" +#include "pmu.h" #include <linux/clocksource.h> #include <linux/interrupt.h> @@ -57,11 +58,9 @@ #include <asm/debugreg.h> #include <asm/msr.h> #include <asm/desc.h> -#include <asm/mtrr.h> #include <asm/mce.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> /* Ugh! */ -#include <asm/xcr.h> +#include <linux/kernel_stat.h> +#include <asm/fpu/internal.h> /* Ugh! */ #include <asm/pvclock.h> #include <asm/div64.h> @@ -99,6 +98,9 @@ module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR); unsigned int min_timer_period_us = 500; module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR); +static bool __read_mostly kvmclock_periodic_sync = true; +module_param(kvmclock_periodic_sync, bool, S_IRUGO); + bool kvm_has_tsc_control; EXPORT_SYMBOL_GPL(kvm_has_tsc_control); u32 kvm_max_guest_tsc_khz; @@ -475,7 +477,7 @@ EXPORT_SYMBOL_GPL(kvm_require_dr); /* * This function will be used to read from the physical memory of the currently - * running guest. The difference to kvm_read_guest_page is that this function + * running guest. The difference to kvm_vcpu_read_guest_page is that this function * can read from guest physical or from the guest's guest physical memory. */ int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, @@ -493,7 +495,7 @@ int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, real_gfn = gpa_to_gfn(real_gfn); - return kvm_read_guest_page(vcpu->kvm, real_gfn, data, offset, len); + return kvm_vcpu_read_guest_page(vcpu, real_gfn, data, offset, len); } EXPORT_SYMBOL_GPL(kvm_read_guest_page_mmu); @@ -572,8 +574,7 @@ out: int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { unsigned long old_cr0 = kvm_read_cr0(vcpu); - unsigned long update_bits = X86_CR0_PG | X86_CR0_WP | - X86_CR0_CD | X86_CR0_NW; + unsigned long update_bits = X86_CR0_PG | X86_CR0_WP; cr0 |= X86_CR0_ET; @@ -619,6 +620,10 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if ((cr0 ^ old_cr0) & update_bits) kvm_mmu_reset_context(vcpu); + + if ((cr0 ^ old_cr0) & X86_CR0_CD) + kvm_zap_gfn_range(vcpu->kvm, 0, ~0ULL); + return 0; } EXPORT_SYMBOL_GPL(kvm_set_cr0); @@ -908,7 +913,7 @@ bool kvm_rdpmc(struct kvm_vcpu *vcpu) u64 data; int err; - err = kvm_pmu_read_pmc(vcpu, ecx, &data); + err = kvm_pmu_rdpmc(vcpu, ecx, &data); if (err) return err; kvm_register_write(vcpu, VCPU_REGS_RAX, (u32)data); @@ -923,17 +928,11 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc); * * This list is modified at module load time to reflect the * capabilities of the host cpu. This capabilities test skips MSRs that are - * kvm-specific. Those are put in the beginning of the list. + * kvm-specific. Those are put in emulated_msrs; filtering of emulated_msrs + * may depend on host virtualization features rather than host cpu features. */ -#define KVM_SAVE_MSRS_BEGIN 12 static u32 msrs_to_save[] = { - MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, - MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, - HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, - HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC, - HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, - MSR_KVM_PV_EOI_EN, MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_STAR, #ifdef CONFIG_X86_64 @@ -945,14 +944,24 @@ static u32 msrs_to_save[] = { static unsigned num_msrs_to_save; -static const u32 emulated_msrs[] = { +static u32 emulated_msrs[] = { + MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, + MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, + HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, + HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC, + HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, + MSR_KVM_PV_EOI_EN, + MSR_IA32_TSC_ADJUST, MSR_IA32_TSCDEADLINE, MSR_IA32_MISC_ENABLE, MSR_IA32_MCG_STATUS, MSR_IA32_MCG_CTL, + MSR_IA32_SMBASE, }; +static unsigned num_emulated_msrs; + bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) { if (efer & efer_reserved_bits) @@ -1046,6 +1055,21 @@ EXPORT_SYMBOL_GPL(kvm_set_msr); /* * Adapt set_msr() to msr_io()'s calling convention */ +static int do_get_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) +{ + struct msr_data msr; + int r; + + msr.index = index; + msr.host_initiated = true; + r = kvm_get_msr(vcpu, &msr); + if (r) + return r; + + *data = msr.data; + return 0; +} + static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) { struct msr_data msr; @@ -1698,6 +1722,8 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) vcpu->pvclock_set_guest_stopped_request = false; } + pvclock_flags |= PVCLOCK_COUNTS_FROM_ZERO; + /* If the host uses TSC clocksource, then it is stable */ if (use_master_clock) pvclock_flags |= PVCLOCK_TSC_STABLE_BIT; @@ -1768,127 +1794,14 @@ static void kvmclock_sync_fn(struct work_struct *work) kvmclock_sync_work); struct kvm *kvm = container_of(ka, struct kvm, arch); + if (!kvmclock_periodic_sync) + return; + schedule_delayed_work(&kvm->arch.kvmclock_update_work, 0); schedule_delayed_work(&kvm->arch.kvmclock_sync_work, KVMCLOCK_SYNC_PERIOD); } -static bool msr_mtrr_valid(unsigned msr) -{ - switch (msr) { - case 0x200 ... 0x200 + 2 * KVM_NR_VAR_MTRR - 1: - case MSR_MTRRfix64K_00000: - case MSR_MTRRfix16K_80000: - case MSR_MTRRfix16K_A0000: - case MSR_MTRRfix4K_C0000: - case MSR_MTRRfix4K_C8000: - case MSR_MTRRfix4K_D0000: - case MSR_MTRRfix4K_D8000: - case MSR_MTRRfix4K_E0000: - case MSR_MTRRfix4K_E8000: - case MSR_MTRRfix4K_F0000: - case MSR_MTRRfix4K_F8000: - case MSR_MTRRdefType: - case MSR_IA32_CR_PAT: - return true; - case 0x2f8: - return true; - } - return false; -} - -static bool valid_pat_type(unsigned t) -{ - return t < 8 && (1 << t) & 0xf3; /* 0, 1, 4, 5, 6, 7 */ -} - -static bool valid_mtrr_type(unsigned t) -{ - return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */ -} - -bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data) -{ - int i; - u64 mask; - - if (!msr_mtrr_valid(msr)) - return false; - - if (msr == MSR_IA32_CR_PAT) { - for (i = 0; i < 8; i++) - if (!valid_pat_type((data >> (i * 8)) & 0xff)) - return false; - return true; - } else if (msr == MSR_MTRRdefType) { - if (data & ~0xcff) - return false; - return valid_mtrr_type(data & 0xff); - } else if (msr >= MSR_MTRRfix64K_00000 && msr <= MSR_MTRRfix4K_F8000) { - for (i = 0; i < 8 ; i++) - if (!valid_mtrr_type((data >> (i * 8)) & 0xff)) - return false; - return true; - } - - /* variable MTRRs */ - WARN_ON(!(msr >= 0x200 && msr < 0x200 + 2 * KVM_NR_VAR_MTRR)); - - mask = (~0ULL) << cpuid_maxphyaddr(vcpu); - if ((msr & 1) == 0) { - /* MTRR base */ - if (!valid_mtrr_type(data & 0xff)) - return false; - mask |= 0xf00; - } else - /* MTRR mask */ - mask |= 0x7ff; - if (data & mask) { - kvm_inject_gp(vcpu, 0); - return false; - } - - return true; -} -EXPORT_SYMBOL_GPL(kvm_mtrr_valid); - -static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data) -{ - u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges; - - if (!kvm_mtrr_valid(vcpu, msr, data)) - return 1; - - if (msr == MSR_MTRRdefType) { - vcpu->arch.mtrr_state.def_type = data; - vcpu->arch.mtrr_state.enabled = (data & 0xc00) >> 10; - } else if (msr == MSR_MTRRfix64K_00000) - p[0] = data; - else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000) - p[1 + msr - MSR_MTRRfix16K_80000] = data; - else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000) - p[3 + msr - MSR_MTRRfix4K_C0000] = data; - else if (msr == MSR_IA32_CR_PAT) - vcpu->arch.pat = data; - else { /* Variable MTRRs */ - int idx, is_mtrr_mask; - u64 *pt; - - idx = (msr - 0x200) / 2; - is_mtrr_mask = msr - 0x200 - 2 * idx; - if (!is_mtrr_mask) - pt = - (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo; - else - pt = - (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo; - *pt = data; - } - - kvm_mmu_reset_context(vcpu); - return 0; -} - static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data) { u64 mcg_cap = vcpu->arch.mcg_cap; @@ -1947,7 +1860,7 @@ static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data) r = PTR_ERR(page); goto out; } - if (kvm_write_guest(kvm, page_addr, page, PAGE_SIZE)) + if (kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE)) goto out_free; r = 0; out_free: @@ -2047,13 +1960,13 @@ static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data) break; } gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT; - addr = gfn_to_hva(vcpu->kvm, gfn); + addr = kvm_vcpu_gfn_to_hva(vcpu, gfn); if (kvm_is_error_hva(addr)) return 1; if (__clear_user((void __user *)addr, PAGE_SIZE)) return 1; vcpu->arch.hv_vapic = data; - mark_page_dirty(vcpu->kvm, gfn); + kvm_vcpu_mark_page_dirty(vcpu, gfn); if (kvm_lapic_enable_pv_eoi(vcpu, gfn_to_gpa(gfn) | KVM_MSR_ENABLED)) return 1; break; @@ -2180,7 +2093,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) __func__, data); break; case 0x200 ... 0x2ff: - return set_msr_mtrr(vcpu, msr, data); + return kvm_mtrr_set_msr(vcpu, msr, data); case MSR_IA32_APICBASE: return kvm_set_apic_base(vcpu, msr_info); case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: @@ -2192,7 +2105,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (guest_cpuid_has_tsc_adjust(vcpu)) { if (!msr_info->host_initiated) { s64 adj = data - vcpu->arch.ia32_tsc_adjust_msr; - kvm_x86_ops->adjust_tsc_offset(vcpu, adj, true); + adjust_tsc_offset_guest(vcpu, adj); } vcpu->arch.ia32_tsc_adjust_msr = data; } @@ -2200,6 +2113,11 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_MISC_ENABLE: vcpu->arch.ia32_misc_enable_msr = data; break; + case MSR_IA32_SMBASE: + if (!msr_info->host_initiated) + return 1; + vcpu->arch.smbase = data; + break; case MSR_KVM_WALL_CLOCK_NEW: case MSR_KVM_WALL_CLOCK: vcpu->kvm->arch.wall_clock = data; @@ -2220,6 +2138,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) &vcpu->requests); ka->boot_vcpu_runs_old_kvmclock = tmp; + + ka->kvmclock_offset = -get_kernel_ns(); } vcpu->arch.time = data; @@ -2281,37 +2201,12 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: return set_msr_mce(vcpu, msr, data); - /* Performance counters are not protected by a CPUID bit, - * so we should check all of them in the generic path for the sake of - * cross vendor migration. - * Writing a zero into the event select MSRs disables them, - * which we perfectly emulate ;-). Any other value should be at least - * reported, some guests depend on them. - */ - case MSR_K7_EVNTSEL0: - case MSR_K7_EVNTSEL1: - case MSR_K7_EVNTSEL2: - case MSR_K7_EVNTSEL3: - if (data != 0) - vcpu_unimpl(vcpu, "unimplemented perfctr wrmsr: " - "0x%x data 0x%llx\n", msr, data); - break; - /* at least RHEL 4 unconditionally writes to the perfctr registers, - * so we ignore writes to make it happy. - */ - case MSR_K7_PERFCTR0: - case MSR_K7_PERFCTR1: - case MSR_K7_PERFCTR2: - case MSR_K7_PERFCTR3: - vcpu_unimpl(vcpu, "unimplemented perfctr wrmsr: " - "0x%x data 0x%llx\n", msr, data); - break; - case MSR_P6_PERFCTR0: - case MSR_P6_PERFCTR1: - pr = true; - case MSR_P6_EVNTSEL0: - case MSR_P6_EVNTSEL1: - if (kvm_pmu_msr(vcpu, msr)) + case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: + case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: + pr = true; /* fall through */ + case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: + case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1: + if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); if (pr || data != 0) @@ -2357,7 +2252,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) default: if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr)) return xen_hvm_config(vcpu, data); - if (kvm_pmu_msr(vcpu, msr)) + if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); if (!ignore_msrs) { vcpu_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", @@ -2379,48 +2274,12 @@ EXPORT_SYMBOL_GPL(kvm_set_msr_common); * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ -int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) +int kvm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { - return kvm_x86_ops->get_msr(vcpu, msr_index, pdata); + return kvm_x86_ops->get_msr(vcpu, msr); } EXPORT_SYMBOL_GPL(kvm_get_msr); -static int get_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) -{ - u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges; - - if (!msr_mtrr_valid(msr)) - return 1; - - if (msr == MSR_MTRRdefType) - *pdata = vcpu->arch.mtrr_state.def_type + - (vcpu->arch.mtrr_state.enabled << 10); - else if (msr == MSR_MTRRfix64K_00000) - *pdata = p[0]; - else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000) - *pdata = p[1 + msr - MSR_MTRRfix16K_80000]; - else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000) - *pdata = p[3 + msr - MSR_MTRRfix4K_C0000]; - else if (msr == MSR_IA32_CR_PAT) - *pdata = vcpu->arch.pat; - else { /* Variable MTRRs */ - int idx, is_mtrr_mask; - u64 *pt; - - idx = (msr - 0x200) / 2; - is_mtrr_mask = msr - 0x200 - 2 * idx; - if (!is_mtrr_mask) - pt = - (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo; - else - pt = - (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo; - *pdata = *pt; - } - - return 0; -} - static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) { u64 data; @@ -2518,11 +2377,9 @@ static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) return 0; } -int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { - u64 data; - - switch (msr) { + switch (msr_info->index) { case MSR_IA32_PLATFORM_ID: case MSR_IA32_EBL_CR_POWERON: case MSR_IA32_DEBUGCTLMSR: @@ -2533,38 +2390,28 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_K8_SYSCFG: case MSR_K7_HWCR: case MSR_VM_HSAVE_PA: - case MSR_K7_EVNTSEL0: - case MSR_K7_EVNTSEL1: - case MSR_K7_EVNTSEL2: - case MSR_K7_EVNTSEL3: - case MSR_K7_PERFCTR0: - case MSR_K7_PERFCTR1: - case MSR_K7_PERFCTR2: - case MSR_K7_PERFCTR3: case MSR_K8_INT_PENDING_MSG: case MSR_AMD64_NB_CFG: case MSR_FAM10H_MMIO_CONF_BASE: case MSR_AMD64_BU_CFG2: - data = 0; + msr_info->data = 0; break; - case MSR_P6_PERFCTR0: - case MSR_P6_PERFCTR1: - case MSR_P6_EVNTSEL0: - case MSR_P6_EVNTSEL1: - if (kvm_pmu_msr(vcpu, msr)) - return kvm_pmu_get_msr(vcpu, msr, pdata); - data = 0; + case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: + case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: + case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: + case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1: + if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) + return kvm_pmu_get_msr(vcpu, msr_info->index, &msr_info->data); + msr_info->data = 0; break; case MSR_IA32_UCODE_REV: - data = 0x100000000ULL; + msr_info->data = 0x100000000ULL; break; case MSR_MTRRcap: - data = 0x500 | KVM_NR_VAR_MTRR; - break; case 0x200 ... 0x2ff: - return get_msr_mtrr(vcpu, msr, pdata); + return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data); case 0xcd: /* fsb frequency */ - data = 3; + msr_info->data = 3; break; /* * MSR_EBC_FREQUENCY_ID @@ -2578,48 +2425,53 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) * multiplying by zero otherwise. */ case MSR_EBC_FREQUENCY_ID: - data = 1 << 24; + msr_info->data = 1 << 24; break; case MSR_IA32_APICBASE: - data = kvm_get_apic_base(vcpu); + msr_info->data = kvm_get_apic_base(vcpu); break; case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: - return kvm_x2apic_msr_read(vcpu, msr, pdata); + return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data); break; case MSR_IA32_TSCDEADLINE: - data = kvm_get_lapic_tscdeadline_msr(vcpu); + msr_info->data = kvm_get_lapic_tscdeadline_msr(vcpu); break; case MSR_IA32_TSC_ADJUST: - data = (u64)vcpu->arch.ia32_tsc_adjust_msr; + msr_info->data = (u64)vcpu->arch.ia32_tsc_adjust_msr; break; case MSR_IA32_MISC_ENABLE: - data = vcpu->arch.ia32_misc_enable_msr; + msr_info->data = vcpu->arch.ia32_misc_enable_msr; + break; + case MSR_IA32_SMBASE: + if (!msr_info->host_initiated) + return 1; + msr_info->data = vcpu->arch.smbase; break; case MSR_IA32_PERF_STATUS: /* TSC increment by tick */ - data = 1000ULL; + msr_info->data = 1000ULL; /* CPU multiplier */ - data |= (((uint64_t)4ULL) << 40); + msr_info->data |= (((uint64_t)4ULL) << 40); break; case MSR_EFER: - data = vcpu->arch.efer; + msr_info->data = vcpu->arch.efer; break; case MSR_KVM_WALL_CLOCK: case MSR_KVM_WALL_CLOCK_NEW: - data = vcpu->kvm->arch.wall_clock; + msr_info->data = vcpu->kvm->arch.wall_clock; break; case MSR_KVM_SYSTEM_TIME: case MSR_KVM_SYSTEM_TIME_NEW: - data = vcpu->arch.time; + msr_info->data = vcpu->arch.time; break; case MSR_KVM_ASYNC_PF_EN: - data = vcpu->arch.apf.msr_val; + msr_info->data = vcpu->arch.apf.msr_val; break; case MSR_KVM_STEAL_TIME: - data = vcpu->arch.st.msr_val; + msr_info->data = vcpu->arch.st.msr_val; break; case MSR_KVM_PV_EOI_EN: - data = vcpu->arch.pv_eoi.msr_val; + msr_info->data = vcpu->arch.pv_eoi.msr_val; break; case MSR_IA32_P5_MC_ADDR: case MSR_IA32_P5_MC_TYPE: @@ -2627,7 +2479,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_IA32_MCG_CTL: case MSR_IA32_MCG_STATUS: case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: - return get_msr_mce(vcpu, msr, pdata); + return get_msr_mce(vcpu, msr_info->index, &msr_info->data); case MSR_K7_CLK_CTL: /* * Provide expected ramp-up count for K7. All other @@ -2638,17 +2490,17 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) * type 6, model 8 and higher from exploding due to * the rdmsr failing. */ - data = 0x20000000; + msr_info->data = 0x20000000; break; case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: - if (kvm_hv_msr_partition_wide(msr)) { + if (kvm_hv_msr_partition_wide(msr_info->index)) { int r; mutex_lock(&vcpu->kvm->lock); - r = get_msr_hyperv_pw(vcpu, msr, pdata); + r = get_msr_hyperv_pw(vcpu, msr_info->index, &msr_info->data); mutex_unlock(&vcpu->kvm->lock); return r; } else - return get_msr_hyperv(vcpu, msr, pdata); + return get_msr_hyperv(vcpu, msr_info->index, &msr_info->data); break; case MSR_IA32_BBL_CR_CTL3: /* This legacy MSR exists but isn't fully documented in current @@ -2661,31 +2513,30 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) * L2 cache control register 3: 64GB range, 256KB size, * enabled, latency 0x1, configured */ - data = 0xbe702111; + msr_info->data = 0xbe702111; break; case MSR_AMD64_OSVW_ID_LENGTH: if (!guest_cpuid_has_osvw(vcpu)) return 1; - data = vcpu->arch.osvw.length; + msr_info->data = vcpu->arch.osvw.length; break; case MSR_AMD64_OSVW_STATUS: if (!guest_cpuid_has_osvw(vcpu)) return 1; - data = vcpu->arch.osvw.status; + msr_info->data = vcpu->arch.osvw.status; break; default: - if (kvm_pmu_msr(vcpu, msr)) - return kvm_pmu_get_msr(vcpu, msr, pdata); + if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) + return kvm_pmu_get_msr(vcpu, msr_info->index, &msr_info->data); if (!ignore_msrs) { - vcpu_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr); + vcpu_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr_info->index); return 1; } else { - vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr); - data = 0; + vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr_info->index); + msr_info->data = 0; } break; } - *pdata = data; return 0; } EXPORT_SYMBOL_GPL(kvm_get_msr_common); @@ -2798,12 +2649,25 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV_TIME: case KVM_CAP_IOAPIC_POLARITY_IGNORED: case KVM_CAP_TSC_DEADLINE_TIMER: + case KVM_CAP_ENABLE_CAP_VM: + case KVM_CAP_DISABLE_QUIRKS: #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT case KVM_CAP_ASSIGN_DEV_IRQ: case KVM_CAP_PCI_2_3: #endif r = 1; break; + case KVM_CAP_X86_SMM: + /* SMBASE is usually relocated above 1M on modern chipsets, + * and SMM handlers might indeed rely on 4G segment limits, + * so do not report SMM to be available if real mode is + * emulated via vm86 mode. Still, do not go to great lengths + * to avoid userspace's usage of the feature, because it is a + * fringe case that is not enabled except via specific settings + * of the module parameters. + */ + r = kvm_x86_ops->cpu_has_high_real_mode_segbase(); + break; case KVM_CAP_COALESCED_MMIO: r = KVM_COALESCED_MMIO_PAGE_OFFSET; break; @@ -2860,7 +2724,7 @@ long kvm_arch_dev_ioctl(struct file *filp, if (copy_from_user(&msr_list, user_msr_list, sizeof msr_list)) goto out; n = msr_list.nmsrs; - msr_list.nmsrs = num_msrs_to_save + ARRAY_SIZE(emulated_msrs); + msr_list.nmsrs = num_msrs_to_save + num_emulated_msrs; if (copy_to_user(user_msr_list, &msr_list, sizeof msr_list)) goto out; r = -E2BIG; @@ -2872,7 +2736,7 @@ long kvm_arch_dev_ioctl(struct file *filp, goto out; if (copy_to_user(user_msr_list->indices + num_msrs_to_save, &emulated_msrs, - ARRAY_SIZE(emulated_msrs) * sizeof(u32))) + num_emulated_msrs * sizeof(u32))) goto out; r = 0; break; @@ -3016,6 +2880,13 @@ static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu) return 0; } +static int kvm_vcpu_ioctl_smi(struct kvm_vcpu *vcpu) +{ + kvm_make_request(KVM_REQ_SMI, vcpu); + + return 0; +} + static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu, struct kvm_tpr_access_ctl *tac) { @@ -3121,8 +2992,15 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, events->sipi_vector = 0; /* never valid when reporting to user space */ + events->smi.smm = is_smm(vcpu); + events->smi.pending = vcpu->arch.smi_pending; + events->smi.smm_inside_nmi = + !!(vcpu->arch.hflags & HF_SMM_INSIDE_NMI_MASK); + events->smi.latched_init = kvm_lapic_latched_init(vcpu); + events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING - | KVM_VCPUEVENT_VALID_SHADOW); + | KVM_VCPUEVENT_VALID_SHADOW + | KVM_VCPUEVENT_VALID_SMM); memset(&events->reserved, 0, sizeof(events->reserved)); } @@ -3131,7 +3009,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, { if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING | KVM_VCPUEVENT_VALID_SIPI_VECTOR - | KVM_VCPUEVENT_VALID_SHADOW)) + | KVM_VCPUEVENT_VALID_SHADOW + | KVM_VCPUEVENT_VALID_SMM)) return -EINVAL; process_nmi(vcpu); @@ -3156,6 +3035,24 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, kvm_vcpu_has_lapic(vcpu)) vcpu->arch.apic->sipi_vector = events->sipi_vector; + if (events->flags & KVM_VCPUEVENT_VALID_SMM) { + if (events->smi.smm) + vcpu->arch.hflags |= HF_SMM_MASK; + else + vcpu->arch.hflags &= ~HF_SMM_MASK; + vcpu->arch.smi_pending = events->smi.pending; + if (events->smi.smm_inside_nmi) + vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; + else + vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK; + if (kvm_vcpu_has_lapic(vcpu)) { + if (events->smi.latched_init) + set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + else + clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + } + } + kvm_make_request(KVM_REQ_EVENT, vcpu); return 0; @@ -3194,8 +3091,8 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu) { - struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave; - u64 xstate_bv = xsave->xsave_hdr.xstate_bv; + struct xregs_state *xsave = &vcpu->arch.guest_fpu.state.xsave; + u64 xstate_bv = xsave->header.xfeatures; u64 valid; /* @@ -3230,7 +3127,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu) static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) { - struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave; + struct xregs_state *xsave = &vcpu->arch.guest_fpu.state.xsave; u64 xstate_bv = *(u64 *)(src + XSAVE_HDR_OFFSET); u64 valid; @@ -3241,9 +3138,9 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) memcpy(xsave, src, XSAVE_HDR_OFFSET); /* Set XSTATE_BV and possibly XCOMP_BV. */ - xsave->xsave_hdr.xstate_bv = xstate_bv; + xsave->header.xfeatures = xstate_bv; if (cpu_has_xsaves) - xsave->xsave_hdr.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED; + xsave->header.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED; /* * Copy each region from the non-compacted offset to the @@ -3260,8 +3157,7 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) cpuid_count(XSTATE_CPUID, index, &size, &offset, &ecx, &edx); memcpy(dest, src + offset, size); - } else - WARN_ON_ONCE(1); + } valid -= feature; } @@ -3275,8 +3171,8 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, fill_xsave((u8 *) guest_xsave->region, vcpu); } else { memcpy(guest_xsave->region, - &vcpu->arch.guest_fpu.state->fxsave, - sizeof(struct i387_fxsave_struct)); + &vcpu->arch.guest_fpu.state.fxsave, + sizeof(struct fxregs_state)); *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] = XSTATE_FPSSE; } @@ -3300,8 +3196,8 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, } else { if (xstate_bv & ~XSTATE_FPSSE) return -EINVAL; - memcpy(&vcpu->arch.guest_fpu.state->fxsave, - guest_xsave->region, sizeof(struct i387_fxsave_struct)); + memcpy(&vcpu->arch.guest_fpu.state.fxsave, + guest_xsave->region, sizeof(struct fxregs_state)); } return 0; } @@ -3415,6 +3311,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_vcpu_ioctl_nmi(vcpu); break; } + case KVM_SMI: { + r = kvm_vcpu_ioctl_smi(vcpu); + break; + } case KVM_SET_CPUID: { struct kvm_cpuid __user *cpuid_arg = argp; struct kvm_cpuid cpuid; @@ -3454,7 +3354,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_GET_MSRS: - r = msr_io(vcpu, argp, kvm_get_msr, 1); + r = msr_io(vcpu, argp, do_get_msr, 1); break; case KVM_SET_MSRS: r = msr_io(vcpu, argp, do_set_msr, 0); @@ -3845,6 +3745,26 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event, return 0; } +static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, + struct kvm_enable_cap *cap) +{ + int r; + + if (cap->flags) + return -EINVAL; + + switch (cap->cap) { + case KVM_CAP_DISABLE_QUIRKS: + kvm->arch.disabled_quirks = cap->args[0]; + r = 0; + break; + default: + r = -EINVAL; + break; + } + return r; +} + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -4097,7 +4017,15 @@ long kvm_arch_vm_ioctl(struct file *filp, r = 0; break; } + case KVM_ENABLE_CAP: { + struct kvm_enable_cap cap; + r = -EFAULT; + if (copy_from_user(&cap, argp, sizeof(cap))) + goto out; + r = kvm_vm_ioctl_enable_cap(kvm, &cap); + break; + } default: r = kvm_vm_ioctl_assigned_device(kvm, ioctl, arg); } @@ -4110,8 +4038,7 @@ static void kvm_init_msr_list(void) u32 dummy[2]; unsigned i, j; - /* skip the first msrs in the list. KVM-specific */ - for (i = j = KVM_SAVE_MSRS_BEGIN; i < ARRAY_SIZE(msrs_to_save); i++) { + for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) { if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0) continue; @@ -4136,6 +4063,22 @@ static void kvm_init_msr_list(void) j++; } num_msrs_to_save = j; + + for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) { + switch (emulated_msrs[i]) { + case MSR_IA32_SMBASE: + if (!kvm_x86_ops->cpu_has_high_real_mode_segbase()) + continue; + break; + default: + break; + } + + if (j < i) + emulated_msrs[j] = emulated_msrs[i]; + j++; + } + num_emulated_msrs = j; } static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, @@ -4253,8 +4196,8 @@ static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes, if (gpa == UNMAPPED_GVA) return X86EMUL_PROPAGATE_FAULT; - ret = kvm_read_guest_page(vcpu->kvm, gpa >> PAGE_SHIFT, data, - offset, toread); + ret = kvm_vcpu_read_guest_page(vcpu, gpa >> PAGE_SHIFT, data, + offset, toread); if (ret < 0) { r = X86EMUL_IO_NEEDED; goto out; @@ -4287,8 +4230,8 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt, offset = addr & (PAGE_SIZE-1); if (WARN_ON(offset + bytes > PAGE_SIZE)) bytes = (unsigned)PAGE_SIZE - offset; - ret = kvm_read_guest_page(vcpu->kvm, gpa >> PAGE_SHIFT, val, - offset, bytes); + ret = kvm_vcpu_read_guest_page(vcpu, gpa >> PAGE_SHIFT, val, + offset, bytes); if (unlikely(ret < 0)) return X86EMUL_IO_NEEDED; @@ -4334,7 +4277,7 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt, if (gpa == UNMAPPED_GVA) return X86EMUL_PROPAGATE_FAULT; - ret = kvm_write_guest(vcpu->kvm, gpa, data, towrite); + ret = kvm_vcpu_write_guest(vcpu, gpa, data, towrite); if (ret < 0) { r = X86EMUL_IO_NEEDED; goto out; @@ -4387,7 +4330,7 @@ int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, { int ret; - ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes); + ret = kvm_vcpu_write_guest(vcpu, gpa, val, bytes); if (ret < 0) return 0; kvm_mmu_pte_write(vcpu, gpa, val, bytes); @@ -4421,7 +4364,7 @@ static int read_prepare(struct kvm_vcpu *vcpu, void *val, int bytes) static int read_emulate(struct kvm_vcpu *vcpu, gpa_t gpa, void *val, int bytes) { - return !kvm_read_guest(vcpu->kvm, gpa, val, bytes); + return !kvm_vcpu_read_guest(vcpu, gpa, val, bytes); } static int write_emulate(struct kvm_vcpu *vcpu, gpa_t gpa, @@ -4619,7 +4562,7 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK)) goto emul_write; - page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); + page = kvm_vcpu_gfn_to_page(vcpu, gpa >> PAGE_SHIFT); if (is_error_page(page)) goto emul_write; @@ -4647,7 +4590,7 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, if (!exchanged) return X86EMUL_CMPXCHG_FAILED; - mark_page_dirty(vcpu->kvm, gpa >> PAGE_SHIFT); + kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT); kvm_mmu_pte_write(vcpu, gpa, new, bytes); return X86EMUL_CONTINUE; @@ -4946,7 +4889,17 @@ static void emulator_set_segment(struct x86_emulate_ctxt *ctxt, u16 selector, static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata) { - return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata); + struct msr_data msr; + int r; + + msr.index = msr_index; + msr.host_initiated = false; + r = kvm_get_msr(emul_to_vcpu(ctxt), &msr); + if (r) + return r; + + *pdata = msr.data; + return 0; } static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, @@ -4960,16 +4913,30 @@ static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, return kvm_set_msr(emul_to_vcpu(ctxt), &msr); } +static u64 emulator_get_smbase(struct x86_emulate_ctxt *ctxt) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + + return vcpu->arch.smbase; +} + +static void emulator_set_smbase(struct x86_emulate_ctxt *ctxt, u64 smbase) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + + vcpu->arch.smbase = smbase; +} + static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt, u32 pmc) { - return kvm_pmu_check_pmc(emul_to_vcpu(ctxt), pmc); + return kvm_pmu_is_valid_msr_idx(emul_to_vcpu(ctxt), pmc); } static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt, u32 pmc, u64 *pdata) { - return kvm_pmu_read_pmc(emul_to_vcpu(ctxt), pmc, pdata); + return kvm_pmu_rdpmc(emul_to_vcpu(ctxt), pmc, pdata); } static void emulator_halt(struct x86_emulate_ctxt *ctxt) @@ -5045,6 +5012,8 @@ static const struct x86_emulate_ops emulate_ops = { .cpl = emulator_get_cpl, .get_dr = emulator_get_dr, .set_dr = emulator_set_dr, + .get_smbase = emulator_get_smbase, + .set_smbase = emulator_set_smbase, .set_msr = emulator_set_msr, .get_msr = emulator_get_msr, .check_pmc = emulator_check_pmc, @@ -5106,7 +5075,10 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) (cs_l && is_long_mode(vcpu)) ? X86EMUL_MODE_PROT64 : cs_db ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; - ctxt->guest_mode = is_guest_mode(vcpu); + BUILD_BUG_ON(HF_GUEST_MASK != X86EMUL_GUEST_MASK); + BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK); + BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK); + ctxt->emul_flags = vcpu->arch.hflags; init_decode_cache(ctxt); vcpu->arch.emulate_regs_need_sync_from_vcpu = false; @@ -5275,6 +5247,34 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, static int complete_emulated_mmio(struct kvm_vcpu *vcpu); static int complete_emulated_pio(struct kvm_vcpu *vcpu); +static void kvm_smm_changed(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.hflags & HF_SMM_MASK)) { + /* This is a good place to trace that we are exiting SMM. */ + trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, false); + + if (unlikely(vcpu->arch.smi_pending)) { + kvm_make_request(KVM_REQ_SMI, vcpu); + vcpu->arch.smi_pending = 0; + } else { + /* Process a latched INIT, if any. */ + kvm_make_request(KVM_REQ_EVENT, vcpu); + } + } + + kvm_mmu_reset_context(vcpu); +} + +static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags) +{ + unsigned changed = vcpu->arch.hflags ^ emul_flags; + + vcpu->arch.hflags = emul_flags; + + if (changed & HF_SMM_MASK) + kvm_smm_changed(vcpu); +} + static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7, unsigned long *db) { @@ -5474,6 +5474,8 @@ restart: unsigned long rflags = kvm_x86_ops->get_rflags(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; + if (vcpu->arch.hflags != ctxt->emul_flags) + kvm_set_hflags(vcpu, ctxt->emul_flags); kvm_rip_write(vcpu, ctxt->eip); if (r == EMULATE_DONE) kvm_vcpu_check_singlestep(vcpu, rflags, &r); @@ -5952,6 +5954,7 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) lapic_irq.shorthand = 0; lapic_irq.dest_mode = 0; lapic_irq.dest_id = apicid; + lapic_irq.msi_redir_hint = false; lapic_irq.delivery_mode = APIC_DM_REMRD; kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL); @@ -6039,6 +6042,7 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) struct kvm_run *kvm_run = vcpu->run; kvm_run->if_flag = (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0; + kvm_run->flags = is_smm(vcpu) ? KVM_RUN_X86_SMM : 0; kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); if (irqchip_in_kernel(vcpu->kvm)) @@ -6162,6 +6166,238 @@ static void process_nmi(struct kvm_vcpu *vcpu) kvm_make_request(KVM_REQ_EVENT, vcpu); } +#define put_smstate(type, buf, offset, val) \ + *(type *)((buf) + (offset) - 0x7e00) = val + +static u32 process_smi_get_segment_flags(struct kvm_segment *seg) +{ + u32 flags = 0; + flags |= seg->g << 23; + flags |= seg->db << 22; + flags |= seg->l << 21; + flags |= seg->avl << 20; + flags |= seg->present << 15; + flags |= seg->dpl << 13; + flags |= seg->s << 12; + flags |= seg->type << 8; + return flags; +} + +static void process_smi_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n) +{ + struct kvm_segment seg; + int offset; + + kvm_get_segment(vcpu, &seg, n); + put_smstate(u32, buf, 0x7fa8 + n * 4, seg.selector); + + if (n < 3) + offset = 0x7f84 + n * 12; + else + offset = 0x7f2c + (n - 3) * 12; + + put_smstate(u32, buf, offset + 8, seg.base); + put_smstate(u32, buf, offset + 4, seg.limit); + put_smstate(u32, buf, offset, process_smi_get_segment_flags(&seg)); +} + +static void process_smi_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n) +{ + struct kvm_segment seg; + int offset; + u16 flags; + + kvm_get_segment(vcpu, &seg, n); + offset = 0x7e00 + n * 16; + + flags = process_smi_get_segment_flags(&seg) >> 8; + put_smstate(u16, buf, offset, seg.selector); + put_smstate(u16, buf, offset + 2, flags); + put_smstate(u32, buf, offset + 4, seg.limit); + put_smstate(u64, buf, offset + 8, seg.base); +} + +static void process_smi_save_state_32(struct kvm_vcpu *vcpu, char *buf) +{ + struct desc_ptr dt; + struct kvm_segment seg; + unsigned long val; + int i; + + put_smstate(u32, buf, 0x7ffc, kvm_read_cr0(vcpu)); + put_smstate(u32, buf, 0x7ff8, kvm_read_cr3(vcpu)); + put_smstate(u32, buf, 0x7ff4, kvm_get_rflags(vcpu)); + put_smstate(u32, buf, 0x7ff0, kvm_rip_read(vcpu)); + + for (i = 0; i < 8; i++) + put_smstate(u32, buf, 0x7fd0 + i * 4, kvm_register_read(vcpu, i)); + + kvm_get_dr(vcpu, 6, &val); + put_smstate(u32, buf, 0x7fcc, (u32)val); + kvm_get_dr(vcpu, 7, &val); + put_smstate(u32, buf, 0x7fc8, (u32)val); + + kvm_get_segment(vcpu, &seg, VCPU_SREG_TR); + put_smstate(u32, buf, 0x7fc4, seg.selector); + put_smstate(u32, buf, 0x7f64, seg.base); + put_smstate(u32, buf, 0x7f60, seg.limit); + put_smstate(u32, buf, 0x7f5c, process_smi_get_segment_flags(&seg)); + + kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR); + put_smstate(u32, buf, 0x7fc0, seg.selector); + put_smstate(u32, buf, 0x7f80, seg.base); + put_smstate(u32, buf, 0x7f7c, seg.limit); + put_smstate(u32, buf, 0x7f78, process_smi_get_segment_flags(&seg)); + + kvm_x86_ops->get_gdt(vcpu, &dt); + put_smstate(u32, buf, 0x7f74, dt.address); + put_smstate(u32, buf, 0x7f70, dt.size); + + kvm_x86_ops->get_idt(vcpu, &dt); + put_smstate(u32, buf, 0x7f58, dt.address); + put_smstate(u32, buf, 0x7f54, dt.size); + + for (i = 0; i < 6; i++) + process_smi_save_seg_32(vcpu, buf, i); + + put_smstate(u32, buf, 0x7f14, kvm_read_cr4(vcpu)); + + /* revision id */ + put_smstate(u32, buf, 0x7efc, 0x00020000); + put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase); +} + +static void process_smi_save_state_64(struct kvm_vcpu *vcpu, char *buf) +{ +#ifdef CONFIG_X86_64 + struct desc_ptr dt; + struct kvm_segment seg; + unsigned long val; + int i; + + for (i = 0; i < 16; i++) + put_smstate(u64, buf, 0x7ff8 - i * 8, kvm_register_read(vcpu, i)); + + put_smstate(u64, buf, 0x7f78, kvm_rip_read(vcpu)); + put_smstate(u32, buf, 0x7f70, kvm_get_rflags(vcpu)); + + kvm_get_dr(vcpu, 6, &val); + put_smstate(u64, buf, 0x7f68, val); + kvm_get_dr(vcpu, 7, &val); + put_smstate(u64, buf, 0x7f60, val); + + put_smstate(u64, buf, 0x7f58, kvm_read_cr0(vcpu)); + put_smstate(u64, buf, 0x7f50, kvm_read_cr3(vcpu)); + put_smstate(u64, buf, 0x7f48, kvm_read_cr4(vcpu)); + + put_smstate(u32, buf, 0x7f00, vcpu->arch.smbase); + + /* revision id */ + put_smstate(u32, buf, 0x7efc, 0x00020064); + + put_smstate(u64, buf, 0x7ed0, vcpu->arch.efer); + + kvm_get_segment(vcpu, &seg, VCPU_SREG_TR); + put_smstate(u16, buf, 0x7e90, seg.selector); + put_smstate(u16, buf, 0x7e92, process_smi_get_segment_flags(&seg) >> 8); + put_smstate(u32, buf, 0x7e94, seg.limit); + put_smstate(u64, buf, 0x7e98, seg.base); + + kvm_x86_ops->get_idt(vcpu, &dt); + put_smstate(u32, buf, 0x7e84, dt.size); + put_smstate(u64, buf, 0x7e88, dt.address); + + kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR); + put_smstate(u16, buf, 0x7e70, seg.selector); + put_smstate(u16, buf, 0x7e72, process_smi_get_segment_flags(&seg) >> 8); + put_smstate(u32, buf, 0x7e74, seg.limit); + put_smstate(u64, buf, 0x7e78, seg.base); + + kvm_x86_ops->get_gdt(vcpu, &dt); + put_smstate(u32, buf, 0x7e64, dt.size); + put_smstate(u64, buf, 0x7e68, dt.address); + + for (i = 0; i < 6; i++) + process_smi_save_seg_64(vcpu, buf, i); +#else + WARN_ON_ONCE(1); +#endif +} + +static void process_smi(struct kvm_vcpu *vcpu) +{ + struct kvm_segment cs, ds; + struct desc_ptr dt; + char buf[512]; + u32 cr0; + + if (is_smm(vcpu)) { + vcpu->arch.smi_pending = true; + return; + } + + trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true); + vcpu->arch.hflags |= HF_SMM_MASK; + memset(buf, 0, 512); + if (guest_cpuid_has_longmode(vcpu)) + process_smi_save_state_64(vcpu, buf); + else + process_smi_save_state_32(vcpu, buf); + + kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf)); + + if (kvm_x86_ops->get_nmi_mask(vcpu)) + vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; + else + kvm_x86_ops->set_nmi_mask(vcpu, true); + + kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); + kvm_rip_write(vcpu, 0x8000); + + cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG); + kvm_x86_ops->set_cr0(vcpu, cr0); + vcpu->arch.cr0 = cr0; + + kvm_x86_ops->set_cr4(vcpu, 0); + + /* Undocumented: IDT limit is set to zero on entry to SMM. */ + dt.address = dt.size = 0; + kvm_x86_ops->set_idt(vcpu, &dt); + + __kvm_set_dr(vcpu, 7, DR7_FIXED_1); + + cs.selector = (vcpu->arch.smbase >> 4) & 0xffff; + cs.base = vcpu->arch.smbase; + + ds.selector = 0; + ds.base = 0; + + cs.limit = ds.limit = 0xffffffff; + cs.type = ds.type = 0x3; + cs.dpl = ds.dpl = 0; + cs.db = ds.db = 0; + cs.s = ds.s = 1; + cs.l = ds.l = 0; + cs.g = ds.g = 1; + cs.avl = ds.avl = 0; + cs.present = ds.present = 1; + cs.unusable = ds.unusable = 0; + cs.padding = ds.padding = 0; + + kvm_set_segment(vcpu, &cs, VCPU_SREG_CS); + kvm_set_segment(vcpu, &ds, VCPU_SREG_DS); + kvm_set_segment(vcpu, &ds, VCPU_SREG_ES); + kvm_set_segment(vcpu, &ds, VCPU_SREG_FS); + kvm_set_segment(vcpu, &ds, VCPU_SREG_GS); + kvm_set_segment(vcpu, &ds, VCPU_SREG_SS); + + if (guest_cpuid_has_longmode(vcpu)) + kvm_x86_ops->set_efer(vcpu, 0); + + kvm_update_cpuid(vcpu); + kvm_mmu_reset_context(vcpu); +} + static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) { u64 eoi_exit_bitmap[4]; @@ -6270,12 +6506,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu)) record_steal_time(vcpu); + if (kvm_check_request(KVM_REQ_SMI, vcpu)) + process_smi(vcpu); if (kvm_check_request(KVM_REQ_NMI, vcpu)) process_nmi(vcpu); if (kvm_check_request(KVM_REQ_PMU, vcpu)) - kvm_handle_pmu_event(vcpu); + kvm_pmu_handle_event(vcpu); if (kvm_check_request(KVM_REQ_PMI, vcpu)) - kvm_deliver_pmi(vcpu); + kvm_pmu_deliver_pmi(vcpu); if (kvm_check_request(KVM_REQ_SCAN_IOAPIC, vcpu)) vcpu_scan_ioapic(vcpu); if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu)) @@ -6347,7 +6585,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (req_immediate_exit) smp_send_reschedule(vcpu->cpu); - kvm_guest_enter(); + __kvm_guest_enter(); if (unlikely(vcpu->arch.switch_db_regs)) { set_debugreg(0, 7); @@ -6597,11 +6835,11 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { + struct fpu *fpu = ¤t->thread.fpu; int r; sigset_t sigsaved; - if (!tsk_used_math(current) && init_fpu(current)) - return -ENOMEM; + fpu__activate_curr(fpu); if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); @@ -6971,8 +7209,8 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { - struct i387_fxsave_struct *fxsave = - &vcpu->arch.guest_fpu.state->fxsave; + struct fxregs_state *fxsave = + &vcpu->arch.guest_fpu.state.fxsave; memcpy(fpu->fpr, fxsave->st_space, 128); fpu->fcw = fxsave->cwd; @@ -6988,8 +7226,8 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { - struct i387_fxsave_struct *fxsave = - &vcpu->arch.guest_fpu.state->fxsave; + struct fxregs_state *fxsave = + &vcpu->arch.guest_fpu.state.fxsave; memcpy(fxsave->st_space, fpu->fpr, 128); fxsave->cwd = fpu->fcw; @@ -7003,17 +7241,11 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) return 0; } -int fx_init(struct kvm_vcpu *vcpu) +static void fx_init(struct kvm_vcpu *vcpu) { - int err; - - err = fpu_alloc(&vcpu->arch.guest_fpu); - if (err) - return err; - - fpu_finit(&vcpu->arch.guest_fpu); + fpstate_init(&vcpu->arch.guest_fpu.state); if (cpu_has_xsaves) - vcpu->arch.guest_fpu.state->xsave.xsave_hdr.xcomp_bv = + vcpu->arch.guest_fpu.state.xsave.header.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED; /* @@ -7022,14 +7254,6 @@ int fx_init(struct kvm_vcpu *vcpu) vcpu->arch.xcr0 = XSTATE_FP; vcpu->arch.cr0 |= X86_CR0_ET; - - return 0; -} -EXPORT_SYMBOL_GPL(fx_init); - -static void fx_free(struct kvm_vcpu *vcpu) -{ - fpu_free(&vcpu->arch.guest_fpu); } void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) @@ -7045,7 +7269,7 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) kvm_put_guest_xcr0(vcpu); vcpu->guest_fpu_loaded = 1; __kernel_fpu_begin(); - fpu_restore_checking(&vcpu->arch.guest_fpu); + __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state); trace_kvm_fpu(1); } @@ -7053,16 +7277,25 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { kvm_put_guest_xcr0(vcpu); - if (!vcpu->guest_fpu_loaded) + if (!vcpu->guest_fpu_loaded) { + vcpu->fpu_counter = 0; return; + } vcpu->guest_fpu_loaded = 0; - fpu_save_init(&vcpu->arch.guest_fpu); + copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu); __kernel_fpu_end(); ++vcpu->stat.fpu_reload; - if (!vcpu->arch.eager_fpu) - kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); - + /* + * If using eager FPU mode, or if the guest is a frequent user + * of the FPU, just leave the FPU active for next time. + * Every 255 times fpu_counter rolls over to 0; a guest that uses + * the FPU in bursts will revert to loading it on demand. + */ + if (!vcpu->arch.eager_fpu) { + if (++vcpu->fpu_counter < 5) + kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); + } trace_kvm_fpu(0); } @@ -7071,7 +7304,6 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) kvmclock_reset(vcpu); free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); - fx_free(vcpu); kvm_x86_ops->vcpu_free(vcpu); } @@ -7087,11 +7319,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu = kvm_x86_ops->vcpu_create(kvm, id); - /* - * Activate fpu unconditionally in case the guest needs eager FPU. It will be - * deactivated soon if it doesn't. - */ - kvm_x86_ops->fpu_activate(vcpu); return vcpu; } @@ -7099,14 +7326,13 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { int r; - vcpu->arch.mtrr_state.have_fixed = 1; + kvm_vcpu_mtrr_init(vcpu); r = vcpu_load(vcpu); if (r) return r; - kvm_vcpu_reset(vcpu); + kvm_vcpu_reset(vcpu, false); kvm_mmu_setup(vcpu); vcpu_put(vcpu); - return r; } @@ -7123,6 +7349,9 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) kvm_write_tsc(vcpu, &msr); vcpu_put(vcpu); + if (!kvmclock_periodic_sync) + return; + schedule_delayed_work(&kvm->arch.kvmclock_sync_work, KVMCLOCK_SYNC_PERIOD); } @@ -7137,12 +7366,13 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kvm_mmu_unload(vcpu); vcpu_put(vcpu); - fx_free(vcpu); kvm_x86_ops->vcpu_free(vcpu); } -void kvm_vcpu_reset(struct kvm_vcpu *vcpu) +void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { + vcpu->arch.hflags = 0; + atomic_set(&vcpu->arch.nmi_queued, 0); vcpu->arch.nmi_pending = 0; vcpu->arch.nmi_injected = false; @@ -7168,13 +7398,16 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu) kvm_async_pf_hash_reset(vcpu); vcpu->arch.apf.halted = false; - kvm_pmu_reset(vcpu); + if (!init_event) { + kvm_pmu_reset(vcpu); + vcpu->arch.smbase = 0x30000; + } memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs)); vcpu->arch.regs_avail = ~0; vcpu->arch.regs_dirty = ~0; - kvm_x86_ops->vcpu_reset(vcpu); + kvm_x86_ops->vcpu_reset(vcpu, init_event); } void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) @@ -7363,9 +7596,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) goto fail_free_mce_banks; } - r = fx_init(vcpu); - if (r) - goto fail_free_wbinvd_dirty_mask; + fx_init(vcpu); vcpu->arch.ia32_tsc_adjust_msr = 0x0; vcpu->arch.pv_time_enabled = false; @@ -7375,12 +7606,13 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); + vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; + kvm_async_pf_hash_reset(vcpu); kvm_pmu_init(vcpu); return 0; -fail_free_wbinvd_dirty_mask: - free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); + fail_free_mce_banks: kfree(vcpu->arch.mce_banks); fail_free_lapic: @@ -7482,6 +7714,40 @@ void kvm_arch_sync_events(struct kvm *kvm) kvm_free_pit(kvm); } +int __x86_set_memory_region(struct kvm *kvm, + const struct kvm_userspace_memory_region *mem) +{ + int i, r; + + /* Called with kvm->slots_lock held. */ + BUG_ON(mem->slot >= KVM_MEM_SLOTS_NUM); + + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + struct kvm_userspace_memory_region m = *mem; + + m.slot |= i << 16; + r = __kvm_set_memory_region(kvm, &m); + if (r < 0) + return r; + } + + return 0; +} +EXPORT_SYMBOL_GPL(__x86_set_memory_region); + +int x86_set_memory_region(struct kvm *kvm, + const struct kvm_userspace_memory_region *mem) +{ + int r; + + mutex_lock(&kvm->slots_lock); + r = __x86_set_memory_region(kvm, mem); + mutex_unlock(&kvm->slots_lock); + + return r; +} +EXPORT_SYMBOL_GPL(x86_set_memory_region); + void kvm_arch_destroy_vm(struct kvm *kvm) { if (current->mm == kvm->mm) { @@ -7493,13 +7759,13 @@ void kvm_arch_destroy_vm(struct kvm *kvm) struct kvm_userspace_memory_region mem; memset(&mem, 0, sizeof(mem)); mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT; - kvm_set_memory_region(kvm, &mem); + x86_set_memory_region(kvm, &mem); mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT; - kvm_set_memory_region(kvm, &mem); + x86_set_memory_region(kvm, &mem); mem.slot = TSS_PRIVATE_MEMSLOT; - kvm_set_memory_region(kvm, &mem); + x86_set_memory_region(kvm, &mem); } kvm_iommu_unmap_guest(kvm); kfree(kvm->arch.vpic); @@ -7588,18 +7854,18 @@ out_free: return -ENOMEM; } -void kvm_arch_memslots_updated(struct kvm *kvm) +void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) { /* * memslots->generation has been incremented. * mmio generation may have reached its maximum value. */ - kvm_mmu_invalidate_mmio_sptes(kvm); + kvm_mmu_invalidate_mmio_sptes(kvm, slots); } int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, enum kvm_mr_change change) { /* @@ -7677,14 +7943,14 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, } void kvm_arch_commit_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, + const struct kvm_memory_slot *new, enum kvm_mr_change change) { - struct kvm_memory_slot *new; int nr_mmu_pages = 0; - if ((mem->slot >= KVM_USER_MEM_SLOTS) && (change == KVM_MR_DELETE)) { + if (change == KVM_MR_DELETE && old->id >= KVM_USER_MEM_SLOTS) { int ret; ret = vm_munmap(old->userspace_addr, @@ -7701,9 +7967,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, if (nr_mmu_pages) kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); - /* It's OK to get 'new' slot here as it has already been installed */ - new = id_to_memslot(kvm->memslots, mem->slot); - /* * Dirty logging tracks sptes in 4k granularity, meaning that large * sptes have to be split. If live migration is successful, the guest @@ -7728,9 +7991,11 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, * been zapped so no dirty logging staff is needed for old slot. For * KVM_MR_FLAGS_ONLY, the old slot is essentially the same one as the * new and it's also covered when dealing with the new slot. + * + * FIXME: const-ify all uses of struct kvm_memory_slot. */ if (change != KVM_MR_DELETE) - kvm_mmu_slot_apply_flags(kvm, new); + kvm_mmu_slot_apply_flags(kvm, (struct kvm_memory_slot *) new); } void kvm_arch_flush_shadow_all(struct kvm *kvm) @@ -7952,6 +8217,24 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu) kvm_x86_ops->interrupt_allowed(vcpu); } +void kvm_arch_start_assignment(struct kvm *kvm) +{ + atomic_inc(&kvm->arch.assigned_device_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_start_assignment); + +void kvm_arch_end_assignment(struct kvm *kvm) +{ + atomic_dec(&kvm->arch.assigned_device_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_end_assignment); + +bool kvm_arch_has_assigned_device(struct kvm *kvm) +{ + return atomic_read(&kvm->arch.assigned_device_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device); + void kvm_arch_register_noncoherent_dma(struct kvm *kvm) { atomic_inc(&kvm->arch.noncoherent_dma_count); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index f5fef1868..0ca2f3e48 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -4,6 +4,8 @@ #include <linux/kvm_host.h> #include "kvm_cache_regs.h" +#define MSR_IA32_CR_PAT_DEFAULT 0x0007040600070406ULL + static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu) { vcpu->arch.exception.pending = false; @@ -145,6 +147,11 @@ static inline void kvm_register_writel(struct kvm_vcpu *vcpu, return kvm_register_write(vcpu, reg, val); } +static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk) +{ + return !(kvm->arch.disabled_quirks & quirk); +} + void kvm_before_handle_nmi(struct kvm_vcpu *vcpu); void kvm_after_handle_nmi(struct kvm_vcpu *vcpu); void kvm_set_pending_timer(struct kvm_vcpu *vcpu); @@ -160,7 +167,13 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception); +void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu); +u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn); bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data); +int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data); +int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); +bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, + int page_num); #define KVM_SUPPORTED_XCR0 (XSTATE_FP | XSTATE_SSE | XSTATE_YMM \ | XSTATE_BNDREGS | XSTATE_BNDCSR \ diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 8f9a133cc..f2dc08c00 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -70,7 +70,7 @@ #include <asm/e820.h> #include <asm/mce.h> #include <asm/io.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #include <asm/stackprotector.h> #include <asm/reboot.h> /* for struct machine_ops */ #include <asm/kvm_para.h> @@ -90,7 +90,7 @@ struct lguest_data lguest_data = { .noirq_iret = (u32)lguest_noirq_iret, .kernel_address = PAGE_OFFSET, .blocked_interrupts = { 1 }, /* Block timer interrupts */ - .syscall_vec = SYSCALL_VECTOR, + .syscall_vec = IA32_SYSCALL_VECTOR, }; /*G:037 @@ -866,7 +866,7 @@ static void __init lguest_init_IRQ(void) for (i = FIRST_EXTERNAL_VECTOR; i < FIRST_SYSTEM_VECTOR; i++) { /* Some systems map "vectors" to interrupts weirdly. Not us! */ __this_cpu_write(vector_irq[i], i - FIRST_EXTERNAL_VECTOR); - if (i != SYSCALL_VECTOR) + if (i != IA32_SYSCALL_VECTOR) set_intr_gate(i, irq_entries_start + 8 * (i - FIRST_EXTERNAL_VECTOR)); } diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 1530afb07..f2587888d 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -17,7 +17,6 @@ clean-files := inat-tables.c obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o lib-y := delay.o misc.o cmdline.o -lib-y += thunk_$(BITS).o lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o lib-y += memcpy_$(BITS).o lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o @@ -40,6 +39,6 @@ else lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o lib-y += clear_page_64.o copy_page_64.o lib-y += memmove_64.o memset_64.o - lib-y += copy_user_64.o copy_user_nocache_64.o + lib-y += copy_user_64.o lib-y += cmpxchg16b_emu.o endif diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S index 00933d5e9..9b0ca8fe8 100644 --- a/arch/x86/lib/atomic64_386_32.S +++ b/arch/x86/lib/atomic64_386_32.S @@ -11,26 +11,23 @@ #include <linux/linkage.h> #include <asm/alternative-asm.h> -#include <asm/dwarf2.h> /* if you want SMP support, implement these with real spinlocks */ .macro LOCK reg - pushfl_cfi + pushfl cli .endm .macro UNLOCK reg - popfl_cfi + popfl .endm #define BEGIN(op) \ .macro endp; \ - CFI_ENDPROC; \ ENDPROC(atomic64_##op##_386); \ .purgem endp; \ .endm; \ ENTRY(atomic64_##op##_386); \ - CFI_STARTPROC; \ LOCK v; #define ENDP endp diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S index 082a85167..db3ae8544 100644 --- a/arch/x86/lib/atomic64_cx8_32.S +++ b/arch/x86/lib/atomic64_cx8_32.S @@ -11,7 +11,6 @@ #include <linux/linkage.h> #include <asm/alternative-asm.h> -#include <asm/dwarf2.h> .macro read64 reg movl %ebx, %eax @@ -22,16 +21,11 @@ .endm ENTRY(atomic64_read_cx8) - CFI_STARTPROC - read64 %ecx ret - CFI_ENDPROC ENDPROC(atomic64_read_cx8) ENTRY(atomic64_set_cx8) - CFI_STARTPROC - 1: /* we don't need LOCK_PREFIX since aligned 64-bit writes * are atomic on 586 and newer */ @@ -39,28 +33,23 @@ ENTRY(atomic64_set_cx8) jne 1b ret - CFI_ENDPROC ENDPROC(atomic64_set_cx8) ENTRY(atomic64_xchg_cx8) - CFI_STARTPROC - 1: LOCK_PREFIX cmpxchg8b (%esi) jne 1b ret - CFI_ENDPROC ENDPROC(atomic64_xchg_cx8) .macro addsub_return func ins insc ENTRY(atomic64_\func\()_return_cx8) - CFI_STARTPROC - pushl_cfi_reg ebp - pushl_cfi_reg ebx - pushl_cfi_reg esi - pushl_cfi_reg edi + pushl %ebp + pushl %ebx + pushl %esi + pushl %edi movl %eax, %esi movl %edx, %edi @@ -79,12 +68,11 @@ ENTRY(atomic64_\func\()_return_cx8) 10: movl %ebx, %eax movl %ecx, %edx - popl_cfi_reg edi - popl_cfi_reg esi - popl_cfi_reg ebx - popl_cfi_reg ebp + popl %edi + popl %esi + popl %ebx + popl %ebp ret - CFI_ENDPROC ENDPROC(atomic64_\func\()_return_cx8) .endm @@ -93,8 +81,7 @@ addsub_return sub sub sbb .macro incdec_return func ins insc ENTRY(atomic64_\func\()_return_cx8) - CFI_STARTPROC - pushl_cfi_reg ebx + pushl %ebx read64 %esi 1: @@ -109,9 +96,8 @@ ENTRY(atomic64_\func\()_return_cx8) 10: movl %ebx, %eax movl %ecx, %edx - popl_cfi_reg ebx + popl %ebx ret - CFI_ENDPROC ENDPROC(atomic64_\func\()_return_cx8) .endm @@ -119,8 +105,7 @@ incdec_return inc add adc incdec_return dec sub sbb ENTRY(atomic64_dec_if_positive_cx8) - CFI_STARTPROC - pushl_cfi_reg ebx + pushl %ebx read64 %esi 1: @@ -136,18 +121,16 @@ ENTRY(atomic64_dec_if_positive_cx8) 2: movl %ebx, %eax movl %ecx, %edx - popl_cfi_reg ebx + popl %ebx ret - CFI_ENDPROC ENDPROC(atomic64_dec_if_positive_cx8) ENTRY(atomic64_add_unless_cx8) - CFI_STARTPROC - pushl_cfi_reg ebp - pushl_cfi_reg ebx + pushl %ebp + pushl %ebx /* these just push these two parameters on the stack */ - pushl_cfi_reg edi - pushl_cfi_reg ecx + pushl %edi + pushl %ecx movl %eax, %ebp movl %edx, %edi @@ -168,21 +151,18 @@ ENTRY(atomic64_add_unless_cx8) movl $1, %eax 3: addl $8, %esp - CFI_ADJUST_CFA_OFFSET -8 - popl_cfi_reg ebx - popl_cfi_reg ebp + popl %ebx + popl %ebp ret 4: cmpl %edx, 4(%esp) jne 2b xorl %eax, %eax jmp 3b - CFI_ENDPROC ENDPROC(atomic64_add_unless_cx8) ENTRY(atomic64_inc_not_zero_cx8) - CFI_STARTPROC - pushl_cfi_reg ebx + pushl %ebx read64 %esi 1: @@ -199,7 +179,6 @@ ENTRY(atomic64_inc_not_zero_cx8) movl $1, %eax 3: - popl_cfi_reg ebx + popl %ebx ret - CFI_ENDPROC ENDPROC(atomic64_inc_not_zero_cx8) diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S index 9bc944a91..c1e623209 100644 --- a/arch/x86/lib/checksum_32.S +++ b/arch/x86/lib/checksum_32.S @@ -26,7 +26,6 @@ */ #include <linux/linkage.h> -#include <asm/dwarf2.h> #include <asm/errno.h> #include <asm/asm.h> @@ -50,9 +49,8 @@ unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum) * alignment for the unrolled loop. */ ENTRY(csum_partial) - CFI_STARTPROC - pushl_cfi_reg esi - pushl_cfi_reg ebx + pushl %esi + pushl %ebx movl 20(%esp),%eax # Function arg: unsigned int sum movl 16(%esp),%ecx # Function arg: int len movl 12(%esp),%esi # Function arg: unsigned char *buff @@ -129,10 +127,9 @@ ENTRY(csum_partial) jz 8f roll $8, %eax 8: - popl_cfi_reg ebx - popl_cfi_reg esi + popl %ebx + popl %esi ret - CFI_ENDPROC ENDPROC(csum_partial) #else @@ -140,9 +137,8 @@ ENDPROC(csum_partial) /* Version for PentiumII/PPro */ ENTRY(csum_partial) - CFI_STARTPROC - pushl_cfi_reg esi - pushl_cfi_reg ebx + pushl %esi + pushl %ebx movl 20(%esp),%eax # Function arg: unsigned int sum movl 16(%esp),%ecx # Function arg: int len movl 12(%esp),%esi # Function arg: const unsigned char *buf @@ -249,10 +245,9 @@ ENTRY(csum_partial) jz 90f roll $8, %eax 90: - popl_cfi_reg ebx - popl_cfi_reg esi + popl %ebx + popl %esi ret - CFI_ENDPROC ENDPROC(csum_partial) #endif @@ -287,12 +282,10 @@ unsigned int csum_partial_copy_generic (const char *src, char *dst, #define FP 12 ENTRY(csum_partial_copy_generic) - CFI_STARTPROC subl $4,%esp - CFI_ADJUST_CFA_OFFSET 4 - pushl_cfi_reg edi - pushl_cfi_reg esi - pushl_cfi_reg ebx + pushl %edi + pushl %esi + pushl %ebx movl ARGBASE+16(%esp),%eax # sum movl ARGBASE+12(%esp),%ecx # len movl ARGBASE+4(%esp),%esi # src @@ -401,12 +394,11 @@ DST( movb %cl, (%edi) ) .previous - popl_cfi_reg ebx - popl_cfi_reg esi - popl_cfi_reg edi - popl_cfi %ecx # equivalent to addl $4,%esp + popl %ebx + popl %esi + popl %edi + popl %ecx # equivalent to addl $4,%esp ret - CFI_ENDPROC ENDPROC(csum_partial_copy_generic) #else @@ -426,10 +418,9 @@ ENDPROC(csum_partial_copy_generic) #define ARGBASE 12 ENTRY(csum_partial_copy_generic) - CFI_STARTPROC - pushl_cfi_reg ebx - pushl_cfi_reg edi - pushl_cfi_reg esi + pushl %ebx + pushl %edi + pushl %esi movl ARGBASE+4(%esp),%esi #src movl ARGBASE+8(%esp),%edi #dst movl ARGBASE+12(%esp),%ecx #len @@ -489,11 +480,10 @@ DST( movb %dl, (%edi) ) jmp 7b .previous - popl_cfi_reg esi - popl_cfi_reg edi - popl_cfi_reg ebx + popl %esi + popl %edi + popl %ebx ret - CFI_ENDPROC ENDPROC(csum_partial_copy_generic) #undef ROUND diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S index e67e579c9..a2fe51b00 100644 --- a/arch/x86/lib/clear_page_64.S +++ b/arch/x86/lib/clear_page_64.S @@ -1,5 +1,4 @@ #include <linux/linkage.h> -#include <asm/dwarf2.h> #include <asm/cpufeature.h> #include <asm/alternative-asm.h> @@ -15,7 +14,6 @@ * %rdi - page */ ENTRY(clear_page) - CFI_STARTPROC ALTERNATIVE_2 "jmp clear_page_orig", "", X86_FEATURE_REP_GOOD, \ "jmp clear_page_c_e", X86_FEATURE_ERMS @@ -24,11 +22,9 @@ ENTRY(clear_page) xorl %eax,%eax rep stosq ret - CFI_ENDPROC ENDPROC(clear_page) ENTRY(clear_page_orig) - CFI_STARTPROC xorl %eax,%eax movl $4096/64,%ecx @@ -48,14 +44,11 @@ ENTRY(clear_page_orig) jnz .Lloop nop ret - CFI_ENDPROC ENDPROC(clear_page_orig) ENTRY(clear_page_c_e) - CFI_STARTPROC movl $4096,%ecx xorl %eax,%eax rep stosb ret - CFI_ENDPROC ENDPROC(clear_page_c_e) diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S index 40a172541..9b330242e 100644 --- a/arch/x86/lib/cmpxchg16b_emu.S +++ b/arch/x86/lib/cmpxchg16b_emu.S @@ -6,7 +6,6 @@ * */ #include <linux/linkage.h> -#include <asm/dwarf2.h> #include <asm/percpu.h> .text @@ -21,7 +20,6 @@ * %al : Operation successful */ ENTRY(this_cpu_cmpxchg16b_emu) -CFI_STARTPROC # # Emulate 'cmpxchg16b %gs:(%rsi)' except we return the result in %al not @@ -32,7 +30,7 @@ CFI_STARTPROC # *atomic* on a single cpu (as provided by the this_cpu_xx class of # macros). # - pushfq_cfi + pushfq cli cmpq PER_CPU_VAR((%rsi)), %rax @@ -43,17 +41,13 @@ CFI_STARTPROC movq %rbx, PER_CPU_VAR((%rsi)) movq %rcx, PER_CPU_VAR(8(%rsi)) - CFI_REMEMBER_STATE - popfq_cfi + popfq mov $1, %al ret - CFI_RESTORE_STATE .Lnot_same: - popfq_cfi + popfq xor %al,%al ret -CFI_ENDPROC - ENDPROC(this_cpu_cmpxchg16b_emu) diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S index b4807fce5..ad5349778 100644 --- a/arch/x86/lib/cmpxchg8b_emu.S +++ b/arch/x86/lib/cmpxchg8b_emu.S @@ -7,7 +7,6 @@ */ #include <linux/linkage.h> -#include <asm/dwarf2.h> .text @@ -20,14 +19,13 @@ * %ecx : high 32 bits of new value */ ENTRY(cmpxchg8b_emu) -CFI_STARTPROC # # Emulate 'cmpxchg8b (%esi)' on UP except we don't # set the whole ZF thing (caller will just compare # eax:edx with the expected value) # - pushfl_cfi + pushfl cli cmpl (%esi), %eax @@ -38,18 +36,15 @@ CFI_STARTPROC movl %ebx, (%esi) movl %ecx, 4(%esi) - CFI_REMEMBER_STATE - popfl_cfi + popfl ret - CFI_RESTORE_STATE .Lnot_same: movl (%esi), %eax .Lhalf_same: movl 4(%esi), %edx - popfl_cfi + popfl ret -CFI_ENDPROC ENDPROC(cmpxchg8b_emu) diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S index 8239dbcbf..009f98216 100644 --- a/arch/x86/lib/copy_page_64.S +++ b/arch/x86/lib/copy_page_64.S @@ -1,7 +1,6 @@ /* Written 2003 by Andi Kleen, based on a kernel by Evandro Menezes */ #include <linux/linkage.h> -#include <asm/dwarf2.h> #include <asm/cpufeature.h> #include <asm/alternative-asm.h> @@ -13,22 +12,16 @@ */ ALIGN ENTRY(copy_page) - CFI_STARTPROC ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD movl $4096/8, %ecx rep movsq ret - CFI_ENDPROC ENDPROC(copy_page) ENTRY(copy_page_regs) - CFI_STARTPROC subq $2*8, %rsp - CFI_ADJUST_CFA_OFFSET 2*8 movq %rbx, (%rsp) - CFI_REL_OFFSET rbx, 0 movq %r12, 1*8(%rsp) - CFI_REL_OFFSET r12, 1*8 movl $(4096/64)-5, %ecx .p2align 4 @@ -87,11 +80,7 @@ ENTRY(copy_page_regs) jnz .Loop2 movq (%rsp), %rbx - CFI_RESTORE rbx movq 1*8(%rsp), %r12 - CFI_RESTORE r12 addq $2*8, %rsp - CFI_ADJUST_CFA_OFFSET -2*8 ret - CFI_ENDPROC ENDPROC(copy_page_regs) diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index fa997dfae..982ce34f4 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -7,7 +7,6 @@ */ #include <linux/linkage.h> -#include <asm/dwarf2.h> #include <asm/current.h> #include <asm/asm-offsets.h> #include <asm/thread_info.h> @@ -16,33 +15,8 @@ #include <asm/asm.h> #include <asm/smap.h> - .macro ALIGN_DESTINATION - /* check for bad alignment of destination */ - movl %edi,%ecx - andl $7,%ecx - jz 102f /* already aligned */ - subl $8,%ecx - negl %ecx - subl %ecx,%edx -100: movb (%rsi),%al -101: movb %al,(%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz 100b -102: - .section .fixup,"ax" -103: addl %ecx,%edx /* ecx is zerorest also */ - jmp copy_user_handle_tail - .previous - - _ASM_EXTABLE(100b,103b) - _ASM_EXTABLE(101b,103b) - .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 @@ -54,12 +28,10 @@ ENTRY(_copy_to_user) X86_FEATURE_REP_GOOD, \ "jmp copy_user_enhanced_fast_string", \ X86_FEATURE_ERMS - CFI_ENDPROC ENDPROC(_copy_to_user) /* Standard copy_from_user with segment limit checking */ ENTRY(_copy_from_user) - CFI_STARTPROC GET_THREAD_INFO(%rax) movq %rsi,%rcx addq %rdx,%rcx @@ -71,14 +43,12 @@ ENTRY(_copy_from_user) X86_FEATURE_REP_GOOD, \ "jmp copy_user_enhanced_fast_string", \ X86_FEATURE_ERMS - CFI_ENDPROC ENDPROC(_copy_from_user) .section .fixup,"ax" /* must zero dest */ ENTRY(bad_from_user) bad_from_user: - CFI_STARTPROC movl %edx,%ecx xorl %eax,%eax rep @@ -86,7 +56,6 @@ bad_from_user: bad_to_user: movl %edx,%eax ret - CFI_ENDPROC ENDPROC(bad_from_user) .previous @@ -104,7 +73,6 @@ ENDPROC(bad_from_user) * eax uncopied bytes or 0 if successful. */ ENTRY(copy_user_generic_unrolled) - CFI_STARTPROC ASM_STAC cmpl $8,%edx jb 20f /* less then 8 bytes, go to byte copy loop */ @@ -186,7 +154,6 @@ ENTRY(copy_user_generic_unrolled) _ASM_EXTABLE(19b,40b) _ASM_EXTABLE(21b,50b) _ASM_EXTABLE(22b,50b) - CFI_ENDPROC ENDPROC(copy_user_generic_unrolled) /* Some CPUs run faster using the string copy instructions. @@ -208,7 +175,6 @@ ENDPROC(copy_user_generic_unrolled) * eax uncopied bytes or 0 if successful. */ ENTRY(copy_user_generic_string) - CFI_STARTPROC ASM_STAC cmpl $8,%edx jb 2f /* less than 8 bytes, go to byte copy loop */ @@ -233,7 +199,6 @@ ENTRY(copy_user_generic_string) _ASM_EXTABLE(1b,11b) _ASM_EXTABLE(3b,12b) - CFI_ENDPROC ENDPROC(copy_user_generic_string) /* @@ -249,7 +214,6 @@ ENDPROC(copy_user_generic_string) * eax uncopied bytes or 0 if successful. */ ENTRY(copy_user_enhanced_fast_string) - CFI_STARTPROC ASM_STAC movl %edx,%ecx 1: rep @@ -264,5 +228,94 @@ ENTRY(copy_user_enhanced_fast_string) .previous _ASM_EXTABLE(1b,12b) - CFI_ENDPROC ENDPROC(copy_user_enhanced_fast_string) + +/* + * copy_user_nocache - Uncached memory copy with exception handling + * This will force destination/source out of cache for more performance. + */ +ENTRY(__copy_user_nocache) + ASM_STAC + cmpl $8,%edx + jb 20f /* less then 8 bytes, go to byte copy loop */ + ALIGN_DESTINATION + movl %edx,%ecx + andl $63,%edx + shrl $6,%ecx + jz 17f +1: movq (%rsi),%r8 +2: movq 1*8(%rsi),%r9 +3: movq 2*8(%rsi),%r10 +4: movq 3*8(%rsi),%r11 +5: movnti %r8,(%rdi) +6: movnti %r9,1*8(%rdi) +7: movnti %r10,2*8(%rdi) +8: movnti %r11,3*8(%rdi) +9: movq 4*8(%rsi),%r8 +10: movq 5*8(%rsi),%r9 +11: movq 6*8(%rsi),%r10 +12: movq 7*8(%rsi),%r11 +13: movnti %r8,4*8(%rdi) +14: movnti %r9,5*8(%rdi) +15: movnti %r10,6*8(%rdi) +16: movnti %r11,7*8(%rdi) + leaq 64(%rsi),%rsi + leaq 64(%rdi),%rdi + decl %ecx + jnz 1b +17: movl %edx,%ecx + andl $7,%edx + shrl $3,%ecx + jz 20f +18: movq (%rsi),%r8 +19: movnti %r8,(%rdi) + leaq 8(%rsi),%rsi + leaq 8(%rdi),%rdi + decl %ecx + jnz 18b +20: andl %edx,%edx + jz 23f + movl %edx,%ecx +21: movb (%rsi),%al +22: movb %al,(%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz 21b +23: xorl %eax,%eax + ASM_CLAC + sfence + ret + + .section .fixup,"ax" +30: shll $6,%ecx + addl %ecx,%edx + jmp 60f +40: lea (%rdx,%rcx,8),%rdx + jmp 60f +50: movl %ecx,%edx +60: sfence + jmp copy_user_handle_tail + .previous + + _ASM_EXTABLE(1b,30b) + _ASM_EXTABLE(2b,30b) + _ASM_EXTABLE(3b,30b) + _ASM_EXTABLE(4b,30b) + _ASM_EXTABLE(5b,30b) + _ASM_EXTABLE(6b,30b) + _ASM_EXTABLE(7b,30b) + _ASM_EXTABLE(8b,30b) + _ASM_EXTABLE(9b,30b) + _ASM_EXTABLE(10b,30b) + _ASM_EXTABLE(11b,30b) + _ASM_EXTABLE(12b,30b) + _ASM_EXTABLE(13b,30b) + _ASM_EXTABLE(14b,30b) + _ASM_EXTABLE(15b,30b) + _ASM_EXTABLE(16b,30b) + _ASM_EXTABLE(18b,40b) + _ASM_EXTABLE(19b,40b) + _ASM_EXTABLE(21b,50b) + _ASM_EXTABLE(22b,50b) +ENDPROC(__copy_user_nocache) diff --git a/arch/x86/lib/copy_user_nocache_64.S b/arch/x86/lib/copy_user_nocache_64.S deleted file mode 100644 index 6a4f43c2d..000000000 --- a/arch/x86/lib/copy_user_nocache_64.S +++ /dev/null @@ -1,136 +0,0 @@ -/* - * Copyright 2008 Vitaly Mayatskikh <vmayatsk@redhat.com> - * Copyright 2002 Andi Kleen, SuSE Labs. - * Subject to the GNU Public License v2. - * - * Functions to copy from and to user space. - */ - -#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/asm.h> -#include <asm/smap.h> - - .macro ALIGN_DESTINATION -#ifdef FIX_ALIGNMENT - /* check for bad alignment of destination */ - movl %edi,%ecx - andl $7,%ecx - jz 102f /* already aligned */ - subl $8,%ecx - negl %ecx - subl %ecx,%edx -100: movb (%rsi),%al -101: movb %al,(%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz 100b -102: - .section .fixup,"ax" -103: addl %ecx,%edx /* ecx is zerorest also */ - jmp copy_user_handle_tail - .previous - - _ASM_EXTABLE(100b,103b) - _ASM_EXTABLE(101b,103b) -#endif - .endm - -/* - * copy_user_nocache - Uncached memory copy with exception handling - * This will force destination/source out of cache for more performance. - */ -ENTRY(__copy_user_nocache) - CFI_STARTPROC - ASM_STAC - cmpl $8,%edx - jb 20f /* less then 8 bytes, go to byte copy loop */ - ALIGN_DESTINATION - movl %edx,%ecx - andl $63,%edx - shrl $6,%ecx - jz 17f -1: movq (%rsi),%r8 -2: movq 1*8(%rsi),%r9 -3: movq 2*8(%rsi),%r10 -4: movq 3*8(%rsi),%r11 -5: movnti %r8,(%rdi) -6: movnti %r9,1*8(%rdi) -7: movnti %r10,2*8(%rdi) -8: movnti %r11,3*8(%rdi) -9: movq 4*8(%rsi),%r8 -10: movq 5*8(%rsi),%r9 -11: movq 6*8(%rsi),%r10 -12: movq 7*8(%rsi),%r11 -13: movnti %r8,4*8(%rdi) -14: movnti %r9,5*8(%rdi) -15: movnti %r10,6*8(%rdi) -16: movnti %r11,7*8(%rdi) - leaq 64(%rsi),%rsi - leaq 64(%rdi),%rdi - decl %ecx - jnz 1b -17: movl %edx,%ecx - andl $7,%edx - shrl $3,%ecx - jz 20f -18: movq (%rsi),%r8 -19: movnti %r8,(%rdi) - leaq 8(%rsi),%rsi - leaq 8(%rdi),%rdi - decl %ecx - jnz 18b -20: andl %edx,%edx - jz 23f - movl %edx,%ecx -21: movb (%rsi),%al -22: movb %al,(%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz 21b -23: xorl %eax,%eax - ASM_CLAC - sfence - ret - - .section .fixup,"ax" -30: shll $6,%ecx - addl %ecx,%edx - jmp 60f -40: lea (%rdx,%rcx,8),%rdx - jmp 60f -50: movl %ecx,%edx -60: sfence - jmp copy_user_handle_tail - .previous - - _ASM_EXTABLE(1b,30b) - _ASM_EXTABLE(2b,30b) - _ASM_EXTABLE(3b,30b) - _ASM_EXTABLE(4b,30b) - _ASM_EXTABLE(5b,30b) - _ASM_EXTABLE(6b,30b) - _ASM_EXTABLE(7b,30b) - _ASM_EXTABLE(8b,30b) - _ASM_EXTABLE(9b,30b) - _ASM_EXTABLE(10b,30b) - _ASM_EXTABLE(11b,30b) - _ASM_EXTABLE(12b,30b) - _ASM_EXTABLE(13b,30b) - _ASM_EXTABLE(14b,30b) - _ASM_EXTABLE(15b,30b) - _ASM_EXTABLE(16b,30b) - _ASM_EXTABLE(18b,40b) - _ASM_EXTABLE(19b,40b) - _ASM_EXTABLE(21b,50b) - _ASM_EXTABLE(22b,50b) - CFI_ENDPROC -ENDPROC(__copy_user_nocache) diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S index 973418296..7e48807b2 100644 --- a/arch/x86/lib/csum-copy_64.S +++ b/arch/x86/lib/csum-copy_64.S @@ -6,7 +6,6 @@ * for more details. No warranty for anything given at all. */ #include <linux/linkage.h> -#include <asm/dwarf2.h> #include <asm/errno.h> #include <asm/asm.h> @@ -47,23 +46,16 @@ 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) @@ -206,22 +198,14 @@ ENTRY(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: @@ -237,5 +221,4 @@ ENTRY(csum_partial_copy_generic) jz .Lende movl $-EFAULT, (%rax) jmp .Lende - CFI_ENDPROC ENDPROC(csum_partial_copy_generic) diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index a45123596..46668cda4 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -26,7 +26,6 @@ */ #include <linux/linkage.h> -#include <asm/dwarf2.h> #include <asm/page_types.h> #include <asm/errno.h> #include <asm/asm-offsets.h> @@ -36,7 +35,6 @@ .text ENTRY(__get_user_1) - CFI_STARTPROC GET_THREAD_INFO(%_ASM_DX) cmp TI_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user @@ -45,11 +43,9 @@ ENTRY(__get_user_1) xor %eax,%eax ASM_CLAC ret - CFI_ENDPROC ENDPROC(__get_user_1) ENTRY(__get_user_2) - CFI_STARTPROC add $1,%_ASM_AX jc bad_get_user GET_THREAD_INFO(%_ASM_DX) @@ -60,11 +56,9 @@ ENTRY(__get_user_2) xor %eax,%eax ASM_CLAC ret - CFI_ENDPROC ENDPROC(__get_user_2) ENTRY(__get_user_4) - CFI_STARTPROC add $3,%_ASM_AX jc bad_get_user GET_THREAD_INFO(%_ASM_DX) @@ -75,11 +69,9 @@ ENTRY(__get_user_4) xor %eax,%eax ASM_CLAC ret - CFI_ENDPROC ENDPROC(__get_user_4) ENTRY(__get_user_8) - CFI_STARTPROC #ifdef CONFIG_X86_64 add $7,%_ASM_AX jc bad_get_user @@ -104,28 +96,23 @@ ENTRY(__get_user_8) ASM_CLAC ret #endif - CFI_ENDPROC ENDPROC(__get_user_8) bad_get_user: - CFI_STARTPROC xor %edx,%edx mov $(-EFAULT),%_ASM_AX ASM_CLAC ret - CFI_ENDPROC END(bad_get_user) #ifdef CONFIG_X86_32 bad_get_user_8: - CFI_STARTPROC xor %edx,%edx xor %ecx,%ecx mov $(-EFAULT),%_ASM_AX ASM_CLAC ret - CFI_ENDPROC END(bad_get_user_8) #endif diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S index 05a95e713..33147fef3 100644 --- a/arch/x86/lib/iomap_copy_64.S +++ b/arch/x86/lib/iomap_copy_64.S @@ -16,15 +16,12 @@ */ #include <linux/linkage.h> -#include <asm/dwarf2.h> /* * override generic version in lib/iomap_copy.c */ ENTRY(__iowrite32_copy) - CFI_STARTPROC movl %edx,%ecx rep movsd ret - CFI_ENDPROC ENDPROC(__iowrite32_copy) diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index b046664f5..16698bba8 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -2,7 +2,6 @@ #include <linux/linkage.h> #include <asm/cpufeature.h> -#include <asm/dwarf2.h> #include <asm/alternative-asm.h> /* @@ -53,7 +52,6 @@ ENTRY(memcpy_erms) ENDPROC(memcpy_erms) ENTRY(memcpy_orig) - CFI_STARTPROC movq %rdi, %rax cmpq $0x20, %rdx @@ -178,5 +176,4 @@ ENTRY(memcpy_orig) .Lend: retq - CFI_ENDPROC ENDPROC(memcpy_orig) diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index 0f8a0d033..ca2afdd6d 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -6,7 +6,6 @@ * - Copyright 2011 Fenghua Yu <fenghua.yu@intel.com> */ #include <linux/linkage.h> -#include <asm/dwarf2.h> #include <asm/cpufeature.h> #include <asm/alternative-asm.h> @@ -27,7 +26,6 @@ ENTRY(memmove) ENTRY(__memmove) - CFI_STARTPROC /* Handle more 32 bytes in loop */ mov %rdi, %rax @@ -207,6 +205,5 @@ ENTRY(__memmove) movb %r11b, (%rdi) 13: retq - CFI_ENDPROC ENDPROC(__memmove) ENDPROC(memmove) diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S index 93118fb23..2661fad05 100644 --- a/arch/x86/lib/memset_64.S +++ b/arch/x86/lib/memset_64.S @@ -1,7 +1,6 @@ /* Copyright 2002 Andi Kleen, SuSE Labs */ #include <linux/linkage.h> -#include <asm/dwarf2.h> #include <asm/cpufeature.h> #include <asm/alternative-asm.h> @@ -66,7 +65,6 @@ ENTRY(memset_erms) ENDPROC(memset_erms) ENTRY(memset_orig) - CFI_STARTPROC movq %rdi,%r10 /* expand byte value */ @@ -78,7 +76,6 @@ ENTRY(memset_orig) movl %edi,%r9d andl $7,%r9d jnz .Lbad_alignment - CFI_REMEMBER_STATE .Lafter_bad_alignment: movq %rdx,%rcx @@ -128,7 +125,6 @@ ENTRY(memset_orig) movq %r10,%rax ret - CFI_RESTORE_STATE .Lbad_alignment: cmpq $7,%rdx jbe .Lhandle_7 @@ -139,5 +135,4 @@ ENTRY(memset_orig) subq %r8,%rdx jmp .Lafter_bad_alignment .Lfinal: - CFI_ENDPROC ENDPROC(memset_orig) diff --git a/arch/x86/lib/mmx_32.c b/arch/x86/lib/mmx_32.c index c9f2d9ba8..e5e3ed8dc 100644 --- a/arch/x86/lib/mmx_32.c +++ b/arch/x86/lib/mmx_32.c @@ -22,7 +22,7 @@ #include <linux/sched.h> #include <linux/types.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #include <asm/asm.h> void *_mmx_memcpy(void *to, const void *from, size_t len) diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S index 3ca5218fb..c81556409 100644 --- a/arch/x86/lib/msr-reg.S +++ b/arch/x86/lib/msr-reg.S @@ -1,6 +1,5 @@ #include <linux/linkage.h> #include <linux/errno.h> -#include <asm/dwarf2.h> #include <asm/asm.h> #include <asm/msr.h> @@ -13,9 +12,8 @@ */ .macro op_safe_regs op ENTRY(\op\()_safe_regs) - CFI_STARTPROC - pushq_cfi_reg rbx - pushq_cfi_reg rbp + pushq %rbx + pushq %rbp movq %rdi, %r10 /* Save pointer */ xorl %r11d, %r11d /* Return value */ movl (%rdi), %eax @@ -25,7 +23,6 @@ ENTRY(\op\()_safe_regs) movl 20(%rdi), %ebp movl 24(%rdi), %esi movl 28(%rdi), %edi - CFI_REMEMBER_STATE 1: \op 2: movl %eax, (%r10) movl %r11d, %eax /* Return value */ @@ -35,16 +32,14 @@ ENTRY(\op\()_safe_regs) movl %ebp, 20(%r10) movl %esi, 24(%r10) movl %edi, 28(%r10) - popq_cfi_reg rbp - popq_cfi_reg rbx + popq %rbp + popq %rbx ret 3: - CFI_RESTORE_STATE movl $-EIO, %r11d jmp 2b _ASM_EXTABLE(1b, 3b) - CFI_ENDPROC ENDPROC(\op\()_safe_regs) .endm @@ -52,13 +47,12 @@ ENDPROC(\op\()_safe_regs) .macro op_safe_regs op ENTRY(\op\()_safe_regs) - CFI_STARTPROC - pushl_cfi_reg ebx - pushl_cfi_reg ebp - pushl_cfi_reg esi - pushl_cfi_reg edi - pushl_cfi $0 /* Return value */ - pushl_cfi %eax + pushl %ebx + pushl %ebp + pushl %esi + pushl %edi + pushl $0 /* Return value */ + pushl %eax movl 4(%eax), %ecx movl 8(%eax), %edx movl 12(%eax), %ebx @@ -66,32 +60,28 @@ ENTRY(\op\()_safe_regs) movl 24(%eax), %esi movl 28(%eax), %edi movl (%eax), %eax - CFI_REMEMBER_STATE 1: \op -2: pushl_cfi %eax +2: pushl %eax movl 4(%esp), %eax - popl_cfi (%eax) + popl (%eax) addl $4, %esp - CFI_ADJUST_CFA_OFFSET -4 movl %ecx, 4(%eax) movl %edx, 8(%eax) movl %ebx, 12(%eax) movl %ebp, 20(%eax) movl %esi, 24(%eax) movl %edi, 28(%eax) - popl_cfi %eax - popl_cfi_reg edi - popl_cfi_reg esi - popl_cfi_reg ebp - popl_cfi_reg ebx + popl %eax + popl %edi + popl %esi + popl %ebp + popl %ebx ret 3: - CFI_RESTORE_STATE movl $-EIO, 4(%esp) jmp 2b _ASM_EXTABLE(1b, 3b) - CFI_ENDPROC ENDPROC(\op\()_safe_regs) .endm diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S index fc6ba17a7..e0817a12d 100644 --- a/arch/x86/lib/putuser.S +++ b/arch/x86/lib/putuser.S @@ -11,7 +11,6 @@ * return value. */ #include <linux/linkage.h> -#include <asm/dwarf2.h> #include <asm/thread_info.h> #include <asm/errno.h> #include <asm/asm.h> @@ -30,11 +29,9 @@ * as they get called from within inline assembly. */ -#define ENTER CFI_STARTPROC ; \ - GET_THREAD_INFO(%_ASM_BX) +#define ENTER GET_THREAD_INFO(%_ASM_BX) #define EXIT ASM_CLAC ; \ - ret ; \ - CFI_ENDPROC + ret .text ENTRY(__put_user_1) @@ -87,7 +84,6 @@ ENTRY(__put_user_8) ENDPROC(__put_user_8) bad_put_user: - CFI_STARTPROC movl $-EFAULT,%eax EXIT END(bad_put_user) diff --git a/arch/x86/lib/rwsem.S b/arch/x86/lib/rwsem.S index 2322abe4d..40027db99 100644 --- a/arch/x86/lib/rwsem.S +++ b/arch/x86/lib/rwsem.S @@ -15,7 +15,6 @@ #include <linux/linkage.h> #include <asm/alternative-asm.h> -#include <asm/dwarf2.h> #define __ASM_HALF_REG(reg) __ASM_SEL(reg, e##reg) #define __ASM_HALF_SIZE(inst) __ASM_SEL(inst##w, inst##l) @@ -34,10 +33,10 @@ */ #define save_common_regs \ - pushl_cfi_reg ecx + pushl %ecx #define restore_common_regs \ - popl_cfi_reg ecx + popl %ecx /* Avoid uglifying the argument copying x86-64 needs to do. */ .macro movq src, dst @@ -64,50 +63,45 @@ */ #define save_common_regs \ - pushq_cfi_reg rdi; \ - pushq_cfi_reg rsi; \ - pushq_cfi_reg rcx; \ - pushq_cfi_reg r8; \ - pushq_cfi_reg r9; \ - pushq_cfi_reg r10; \ - pushq_cfi_reg r11 + pushq %rdi; \ + pushq %rsi; \ + pushq %rcx; \ + pushq %r8; \ + pushq %r9; \ + pushq %r10; \ + pushq %r11 #define restore_common_regs \ - popq_cfi_reg r11; \ - popq_cfi_reg r10; \ - popq_cfi_reg r9; \ - popq_cfi_reg r8; \ - popq_cfi_reg rcx; \ - popq_cfi_reg rsi; \ - popq_cfi_reg rdi + popq %r11; \ + popq %r10; \ + popq %r9; \ + popq %r8; \ + popq %rcx; \ + popq %rsi; \ + popq %rdi #endif /* Fix up special calling conventions */ ENTRY(call_rwsem_down_read_failed) - CFI_STARTPROC save_common_regs - __ASM_SIZE(push,_cfi_reg) __ASM_REG(dx) + __ASM_SIZE(push,) %__ASM_REG(dx) movq %rax,%rdi call rwsem_down_read_failed - __ASM_SIZE(pop,_cfi_reg) __ASM_REG(dx) + __ASM_SIZE(pop,) %__ASM_REG(dx) restore_common_regs ret - CFI_ENDPROC ENDPROC(call_rwsem_down_read_failed) ENTRY(call_rwsem_down_write_failed) - CFI_STARTPROC save_common_regs movq %rax,%rdi call rwsem_down_write_failed restore_common_regs ret - CFI_ENDPROC ENDPROC(call_rwsem_down_write_failed) ENTRY(call_rwsem_wake) - CFI_STARTPROC /* do nothing if still outstanding active readers */ __ASM_HALF_SIZE(dec) %__ASM_HALF_REG(dx) jnz 1f @@ -116,17 +110,14 @@ ENTRY(call_rwsem_wake) call rwsem_wake restore_common_regs 1: ret - CFI_ENDPROC ENDPROC(call_rwsem_wake) ENTRY(call_rwsem_downgrade_wake) - CFI_STARTPROC save_common_regs - __ASM_SIZE(push,_cfi_reg) __ASM_REG(dx) + __ASM_SIZE(push,) %__ASM_REG(dx) movq %rax,%rdi call rwsem_downgrade_wake - __ASM_SIZE(pop,_cfi_reg) __ASM_REG(dx) + __ASM_SIZE(pop,) %__ASM_REG(dx) restore_common_regs ret - CFI_ENDPROC ENDPROC(call_rwsem_downgrade_wake) diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c index ddf9ecb53..e342586db 100644 --- a/arch/x86/lib/usercopy.c +++ b/arch/x86/lib/usercopy.c @@ -20,7 +20,7 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n) unsigned long ret; if (__range_not_ok(from, n, TASK_SIZE)) - return 0; + return n; /* * Even though this function is typically called from NMI/IRQ context diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index e2f5e21c0..91d93b95b 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -647,7 +647,8 @@ EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero); * @from: Source address, in kernel space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from kernel space to user space. * @@ -668,7 +669,8 @@ EXPORT_SYMBOL(_copy_to_user); * @from: Source address, in user space. * @n: Number of bytes to copy. * - * Context: User context only. This function may sleep. + * Context: User context only. This function may sleep if pagefaults are + * enabled. * * Copy data from user space to kernel space. * diff --git a/arch/x86/math-emu/fpu_aux.c b/arch/x86/math-emu/fpu_aux.c index dc8adad10..dd76a0572 100644 --- a/arch/x86/math-emu/fpu_aux.c +++ b/arch/x86/math-emu/fpu_aux.c @@ -30,7 +30,7 @@ static void fclex(void) } /* Needs to be externally visible */ -void finit_soft_fpu(struct i387_soft_struct *soft) +void fpstate_init_soft(struct swregs_state *soft) { struct address *oaddr, *iaddr; memset(soft, 0, sizeof(*soft)); @@ -52,7 +52,7 @@ void finit_soft_fpu(struct i387_soft_struct *soft) void finit(void) { - finit_soft_fpu(¤t->thread.fpu.state->soft); + fpstate_init_soft(¤t->thread.fpu.state.soft); } /* diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c index 9b8681241..3d8f2e421 100644 --- a/arch/x86/math-emu/fpu_entry.c +++ b/arch/x86/math-emu/fpu_entry.c @@ -29,9 +29,8 @@ #include <asm/uaccess.h> #include <asm/traps.h> -#include <asm/desc.h> #include <asm/user.h> -#include <asm/i387.h> +#include <asm/fpu/internal.h> #include "fpu_system.h" #include "fpu_emu.h" @@ -147,13 +146,9 @@ void math_emulate(struct math_emu_info *info) unsigned long code_base = 0; unsigned long code_limit = 0; /* Initialized to stop compiler warnings */ struct desc_struct code_descriptor; + struct fpu *fpu = ¤t->thread.fpu; - if (!used_math()) { - if (init_fpu(current)) { - do_group_exit(SIGKILL); - return; - } - } + fpu__activate_curr(fpu); #ifdef RE_ENTRANT_CHECKING if (emulating) { @@ -185,7 +180,7 @@ void math_emulate(struct math_emu_info *info) math_abort(FPU_info, SIGILL); } - code_descriptor = LDT_DESCRIPTOR(FPU_CS); + code_descriptor = FPU_get_ldt_descriptor(FPU_CS); if (SEG_D_SIZE(code_descriptor)) { /* The above test may be wrong, the book is not clear */ /* Segmented 32 bit protected mode */ @@ -673,7 +668,7 @@ void math_abort(struct math_emu_info *info, unsigned int signal) #endif /* PARANOID */ } -#define S387 ((struct i387_soft_struct *)s387) +#define S387 ((struct swregs_state *)s387) #define sstatus_word() \ ((S387->swd & ~SW_Top & 0xffff) | ((S387->ftop << SW_Top_Shift) & SW_Top)) @@ -682,14 +677,14 @@ int fpregs_soft_set(struct task_struct *target, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - struct i387_soft_struct *s387 = &target->thread.fpu.state->soft; + struct swregs_state *s387 = &target->thread.fpu.state.soft; void *space = s387->st_space; int ret; int offset, other, i, tags, regnr, tag, newtop; RE_ENTRANT_CHECK_OFF; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, s387, 0, - offsetof(struct i387_soft_struct, st_space)); + offsetof(struct swregs_state, st_space)); RE_ENTRANT_CHECK_ON; if (ret) @@ -734,7 +729,7 @@ int fpregs_soft_get(struct task_struct *target, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - struct i387_soft_struct *s387 = &target->thread.fpu.state->soft; + struct swregs_state *s387 = &target->thread.fpu.state.soft; const void *space = s387->st_space; int ret; int offset = (S387->ftop & 7) * 10, other = 80 - offset; @@ -752,7 +747,7 @@ int fpregs_soft_get(struct task_struct *target, #endif /* PECULIAR_486 */ ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, s387, 0, - offsetof(struct i387_soft_struct, st_space)); + offsetof(struct swregs_state, st_space)); /* Copy all registers in stack order. */ if (!ret) diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h index 2c614410a..5e044d506 100644 --- a/arch/x86/math-emu/fpu_system.h +++ b/arch/x86/math-emu/fpu_system.h @@ -16,9 +16,24 @@ #include <linux/kernel.h> #include <linux/mm.h> -/* s is always from a cpu register, and the cpu does bounds checking - * during register load --> no further bounds checks needed */ -#define LDT_DESCRIPTOR(s) (((struct desc_struct *)current->mm->context.ldt)[(s) >> 3]) +#include <asm/desc.h> +#include <asm/mmu_context.h> + +static inline struct desc_struct FPU_get_ldt_descriptor(unsigned seg) +{ + static struct desc_struct zero_desc; + struct desc_struct ret = zero_desc; + +#ifdef CONFIG_MODIFY_LDT_SYSCALL + seg >>= 3; + mutex_lock(¤t->mm->context.lock); + if (current->mm->context.ldt && seg < current->mm->context.ldt->size) + ret = current->mm->context.ldt->entries[seg]; + mutex_unlock(¤t->mm->context.lock); +#endif + return ret; +} + #define SEG_D_SIZE(x) ((x).b & (3 << 21)) #define SEG_G_BIT(x) ((x).b & (1 << 23)) #define SEG_GRANULARITY(x) (((x).b & (1 << 23)) ? 4096 : 1) @@ -31,7 +46,7 @@ #define SEG_EXPAND_DOWN(s) (((s).b & ((1 << 11) | (1 << 10))) \ == (1 << 10)) -#define I387 (current->thread.fpu.state) +#define I387 (¤t->thread.fpu.state) #define FPU_info (I387->soft.info) #define FPU_CS (*(unsigned short *) &(FPU_info->regs->cs)) diff --git a/arch/x86/math-emu/get_address.c b/arch/x86/math-emu/get_address.c index 6ef5e9938..8300db71c 100644 --- a/arch/x86/math-emu/get_address.c +++ b/arch/x86/math-emu/get_address.c @@ -20,7 +20,6 @@ #include <linux/stddef.h> #include <asm/uaccess.h> -#include <asm/desc.h> #include "fpu_system.h" #include "exception.h" @@ -158,7 +157,7 @@ static long pm_address(u_char FPU_modrm, u_char segment, addr->selector = PM_REG_(segment); } - descriptor = LDT_DESCRIPTOR(PM_REG_(segment)); + descriptor = FPU_get_ldt_descriptor(addr->selector); base_address = SEG_BASE_ADDR(descriptor); address = base_address + offset; limit = base_address diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 626899af4..9dc909841 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -13,7 +13,7 @@ #include <linux/hugetlb.h> /* hstate_index_to_shift */ #include <linux/prefetch.h> /* prefetchw */ #include <linux/context_tracking.h> /* exception_enter(), ... */ -#include <linux/tuxonice.h> /* incremental image support */ +#include <linux/uaccess.h> /* faulthandler_disabled() */ #include <asm/traps.h> /* dotraplinkage, ... */ #include <asm/pgalloc.h> /* pgd_*(), ... */ @@ -652,10 +652,6 @@ no_context(struct pt_regs *regs, unsigned long error_code, unsigned long flags; int sig; - if (toi_make_writable(init_mm.pgd, address)) { - return; - } - /* Are we prepared to handle this kernel fault? */ if (fixup_exception(regs)) { /* @@ -910,101 +906,10 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, } } -#ifdef CONFIG_TOI_INCREMENTAL -/** - * _toi_do_cbw - Do a copy-before-write before letting the faulting process continue - */ -static void toi_do_cbw(struct page *page) -{ - struct toi_cbw_state *state = this_cpu_ptr(&toi_cbw_states); - - state->active = 1; - wmb(); - - if (state->enabled && state->next && PageTOI_CBW(page)) { - struct toi_cbw *this = state->next; - memcpy(this->virt, page_address(page), PAGE_SIZE); - this->pfn = page_to_pfn(page); - state->next = this->next; - } - - state->active = 0; -} - -/** - * _toi_make_writable - Defuse TOI's write protection - */ -int _toi_make_writable(pte_t *pte) -{ - struct page *page = pte_page(*pte); - if (PageTOI_RO(page)) { - pgd_t *pgd = __va(read_cr3()); - /* - * If this is a TuxOnIce caused fault, we may not have permission to - * write to a page needed to reset the permissions of the original - * page. Use swapper_pg_dir to get around this. - */ - load_cr3(swapper_pg_dir); - - set_pte_atomic(pte, pte_mkwrite(*pte)); - SetPageTOI_Dirty(page); - ClearPageTOI_RO(page); - - toi_do_cbw(page); - - load_cr3(pgd); - return 1; - } - return 0; -} - -/** - * toi_make_writable - Handle a (potential) fault caused by TOI's write protection - * - * Make a page writable that was protected. Might be because of a fault, or - * because we're allocating it and want it to be untracked. - * - * Note that in the fault handling case, we don't care about the error code. If - * called from the double fault handler, we won't have one. We just check to - * see if the page was made RO by TOI, and mark it dirty/release the protection - * if it was. - */ -int toi_make_writable(pgd_t *pgd, unsigned long address) -{ - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - - pgd = pgd + pgd_index(address); - if (!pgd_present(*pgd)) - return 0; - - pud = pud_offset(pgd, address); - if (!pud_present(*pud)) - return 0; - - if (pud_large(*pud)) - return _toi_make_writable((pte_t *) pud); - - pmd = pmd_offset(pud, address); - if (!pmd_present(*pmd)) - return 0; - - if (pmd_large(*pmd)) - return _toi_make_writable((pte_t *) pmd); - - pte = pte_offset_kernel(pmd, address); - if (!pte_present(*pte)) - return 0; - - return _toi_make_writable(pte); -} -#endif - static int spurious_fault_check(unsigned long error_code, pte_t *pte) { if ((error_code & PF_WRITE) && !pte_write(*pte)) - return 0; + return 0; if ((error_code & PF_INSTR) && !pte_exec(*pte)) return 0; @@ -1167,15 +1072,6 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, kmemcheck_hide(regs); prefetchw(&mm->mmap_sem); - /* - * Detect and handle page faults due to TuxOnIce making pages read-only - * so that it can create incremental images. - * - * Do it early to avoid double faults. - */ - if (unlikely(toi_make_writable(init_mm.pgd, address))) - return; - if (unlikely(kmmio_fault(regs, address))) return; @@ -1231,9 +1127,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, /* * If we're in an interrupt, have no user context or are running - * in an atomic region then we must not take the fault: + * in a region with pagefaults disabled then we must not take the fault */ - if (unlikely(in_atomic() || !mm)) { + if (unlikely(faulthandler_disabled() || !mm)) { bad_area_nosemaphore(regs, error_code, address); return; } diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index 4500142bc..eecb207a2 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -35,7 +35,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot) unsigned long vaddr; int idx, type; - /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ + preempt_disable(); pagefault_disable(); if (!PageHighMem(page)) @@ -100,6 +100,7 @@ void __kunmap_atomic(void *kvaddr) #endif pagefault_enable(); + preempt_enable(); } EXPORT_SYMBOL(__kunmap_atomic); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index f971ac820..8533b46e6 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -40,7 +40,7 @@ */ uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM] = { [_PAGE_CACHE_MODE_WB ] = 0 | 0 , - [_PAGE_CACHE_MODE_WC ] = _PAGE_PWT | 0 , + [_PAGE_CACHE_MODE_WC ] = 0 | _PAGE_PCD, [_PAGE_CACHE_MODE_UC_MINUS] = 0 | _PAGE_PCD, [_PAGE_CACHE_MODE_UC ] = _PAGE_PWT | _PAGE_PCD, [_PAGE_CACHE_MODE_WT ] = 0 | _PAGE_PCD, @@ -50,11 +50,11 @@ EXPORT_SYMBOL(__cachemode2pte_tbl); uint8_t __pte2cachemode_tbl[8] = { [__pte2cm_idx( 0 | 0 | 0 )] = _PAGE_CACHE_MODE_WB, - [__pte2cm_idx(_PAGE_PWT | 0 | 0 )] = _PAGE_CACHE_MODE_WC, + [__pte2cm_idx(_PAGE_PWT | 0 | 0 )] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx( 0 | _PAGE_PCD | 0 )] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | 0 )] = _PAGE_CACHE_MODE_UC, [__pte2cm_idx( 0 | 0 | _PAGE_PAT)] = _PAGE_CACHE_MODE_WB, - [__pte2cm_idx(_PAGE_PWT | 0 | _PAGE_PAT)] = _PAGE_CACHE_MODE_WC, + [__pte2cm_idx(_PAGE_PWT | 0 | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx(0 | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC, }; @@ -147,10 +147,9 @@ static int page_size_mask; static void __init probe_page_size_mask(void) { -#if !defined(CONFIG_DEBUG_PAGEALLOC) && !defined(CONFIG_KMEMCHECK) && !defined(CONFIG_TOI_INCREMENTAL) +#if !defined(CONFIG_DEBUG_PAGEALLOC) && !defined(CONFIG_KMEMCHECK) /* - * For CONFIG_DEBUG_PAGEALLOC or TuxOnIce's incremental image support, - * identity mapping will use small pages. + * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages. * This will simplify cpa(), which otherwise needs to support splitting * large pages into small in interrupt context, etc. */ diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index c8140e128..8340e45c8 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -433,7 +433,7 @@ void __init add_highpages_with_active_regions(int nid, phys_addr_t start, end; u64 i; - for_each_free_mem_range(i, nid, &start, &end, NULL) { + for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &start, &end, NULL) { unsigned long pfn = clamp_t(unsigned long, PFN_UP(start), start_pfn, end_pfn); unsigned long e_pfn = clamp_t(unsigned long, PFN_DOWN(end), diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c index 9ca35fc60..9c0ff045f 100644 --- a/arch/x86/mm/iomap_32.c +++ b/arch/x86/mm/iomap_32.c @@ -59,6 +59,7 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot) unsigned long vaddr; int idx, type; + preempt_disable(); pagefault_disable(); type = kmap_atomic_idx_push(); @@ -77,13 +78,13 @@ void __iomem * iomap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot) { /* - * For non-PAT systems, promote PAGE_KERNEL_WC to PAGE_KERNEL_UC_MINUS. - * PAGE_KERNEL_WC maps to PWT, which translates to uncached if the - * MTRR is UC or WC. UC_MINUS gets the real intention, of the - * user, which is "WC if the MTRR is WC, UC if you can't do that." + * For non-PAT systems, translate non-WB request to UC- just in + * case the caller set the PWT bit to prot directly without using + * pgprot_writecombine(). UC- translates to uncached if the MTRR + * is UC or WC. UC- gets the real intention, of the user, which is + * "WC if the MTRR is WC, UC if you can't do that." */ - if (!pat_enabled && pgprot_val(prot) == - (__PAGE_KERNEL | cachemode2protval(_PAGE_CACHE_MODE_WC))) + if (!pat_enabled() && pgprot2cachemode(prot) != _PAGE_CACHE_MODE_WB) prot = __pgprot(__PAGE_KERNEL | cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS)); @@ -117,5 +118,6 @@ iounmap_atomic(void __iomem *kvaddr) } pagefault_enable(); + preempt_enable(); } EXPORT_SYMBOL_GPL(iounmap_atomic); diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 70e7444c6..b9c78f3bc 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -42,6 +42,9 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size, case _PAGE_CACHE_MODE_WC: err = _set_memory_wc(vaddr, nrpages); break; + case _PAGE_CACHE_MODE_WT: + err = _set_memory_wt(vaddr, nrpages); + break; case _PAGE_CACHE_MODE_WB: err = _set_memory_wb(vaddr, nrpages); break; @@ -60,8 +63,6 @@ static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages, !PageReserved(pfn_to_page(start_pfn + i))) return 1; - WARN_ONCE(1, "ioremap on RAM pfn 0x%lx\n", start_pfn); - return 0; } @@ -91,7 +92,6 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, pgprot_t prot; int retval; void __iomem *ret_addr; - int ram_region; /* Don't allow wraparound or zero size */ last_addr = phys_addr + size - 1; @@ -114,23 +114,15 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, /* * Don't allow anybody to remap normal RAM that we're using.. */ - /* First check if whole region can be identified as RAM or not */ - ram_region = region_is_ram(phys_addr, size); - if (ram_region > 0) { - WARN_ONCE(1, "ioremap on RAM at 0x%lx - 0x%lx\n", - (unsigned long int)phys_addr, - (unsigned long int)last_addr); + pfn = phys_addr >> PAGE_SHIFT; + last_pfn = last_addr >> PAGE_SHIFT; + if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL, + __ioremap_check_ram) == 1) { + WARN_ONCE(1, "ioremap on RAM at %pa - %pa\n", + &phys_addr, &last_addr); return NULL; } - /* If could not be identified(-1), check page by page */ - if (ram_region < 0) { - pfn = phys_addr >> PAGE_SHIFT; - last_pfn = last_addr >> PAGE_SHIFT; - if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL, - __ioremap_check_ram) == 1) - return NULL; - } /* * Mappings have to be page-aligned */ @@ -172,6 +164,10 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, prot = __pgprot(pgprot_val(prot) | cachemode2protval(_PAGE_CACHE_MODE_WC)); break; + case _PAGE_CACHE_MODE_WT: + prot = __pgprot(pgprot_val(prot) | + cachemode2protval(_PAGE_CACHE_MODE_WT)); + break; case _PAGE_CACHE_MODE_WB: break; } @@ -234,10 +230,11 @@ void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size) { /* * Ideally, this should be: - * pat_enabled ? _PAGE_CACHE_MODE_UC : _PAGE_CACHE_MODE_UC_MINUS; + * pat_enabled() ? _PAGE_CACHE_MODE_UC : _PAGE_CACHE_MODE_UC_MINUS; * * Till we fix all X drivers to use ioremap_wc(), we will use - * UC MINUS. + * UC MINUS. Drivers that are certain they need or can already + * be converted over to strong UC can use ioremap_uc(). */ enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC_MINUS; @@ -247,6 +244,39 @@ void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size) EXPORT_SYMBOL(ioremap_nocache); /** + * ioremap_uc - map bus memory into CPU space as strongly uncachable + * @phys_addr: bus address of the memory + * @size: size of the resource to map + * + * ioremap_uc performs a platform specific sequence of operations to + * make bus memory CPU accessible via the readb/readw/readl/writeb/ + * writew/writel functions and the other mmio helpers. The returned + * address is not guaranteed to be usable directly as a virtual + * address. + * + * This version of ioremap ensures that the memory is marked with a strong + * preference as completely uncachable on the CPU when possible. For non-PAT + * systems this ends up setting page-attribute flags PCD=1, PWT=1. For PAT + * systems this will set the PAT entry for the pages as strong UC. This call + * will honor existing caching rules from things like the PCI bus. Note that + * there are other caches and buffers on many busses. In particular driver + * authors should read up on PCI writes. + * + * It's useful if some control registers are in such an area and + * write combining or read caching is not desirable: + * + * Must be freed with iounmap. + */ +void __iomem *ioremap_uc(resource_size_t phys_addr, unsigned long size) +{ + enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC; + + return __ioremap_caller(phys_addr, size, pcm, + __builtin_return_address(0)); +} +EXPORT_SYMBOL_GPL(ioremap_uc); + +/** * ioremap_wc - map memory into CPU space write combined * @phys_addr: bus address of the memory * @size: size of the resource to map @@ -258,14 +288,28 @@ EXPORT_SYMBOL(ioremap_nocache); */ void __iomem *ioremap_wc(resource_size_t phys_addr, unsigned long size) { - if (pat_enabled) - return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WC, + return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WC, __builtin_return_address(0)); - else - return ioremap_nocache(phys_addr, size); } EXPORT_SYMBOL(ioremap_wc); +/** + * ioremap_wt - map memory into CPU space write through + * @phys_addr: bus address of the memory + * @size: size of the resource to map + * + * This version of ioremap ensures that the memory is marked write through. + * Write through stores data into memory while keeping the cache up-to-date. + * + * Must be freed with iounmap. + */ +void __iomem *ioremap_wt(resource_size_t phys_addr, unsigned long size) +{ + return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WT, + __builtin_return_address(0)); +} +EXPORT_SYMBOL(ioremap_wt); + void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size) { return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WB, @@ -331,7 +375,7 @@ void iounmap(volatile void __iomem *addr) } EXPORT_SYMBOL(iounmap); -int arch_ioremap_pud_supported(void) +int __init arch_ioremap_pud_supported(void) { #ifdef CONFIG_X86_64 return cpu_has_gbpages; @@ -340,7 +384,7 @@ int arch_ioremap_pud_supported(void) #endif } -int arch_ioremap_pmd_supported(void) +int __init arch_ioremap_pmd_supported(void) { return cpu_has_pse; } @@ -353,18 +397,18 @@ void *xlate_dev_mem_ptr(phys_addr_t phys) { unsigned long start = phys & PAGE_MASK; unsigned long offset = phys & ~PAGE_MASK; - unsigned long vaddr; + void *vaddr; /* If page is RAM, we can use __va. Otherwise ioremap and unmap. */ if (page_is_ram(start >> PAGE_SHIFT)) return __va(phys); - vaddr = (unsigned long)ioremap_cache(start, PAGE_SIZE); + vaddr = ioremap_cache(start, PAGE_SIZE); /* Only add the offset on success and return NULL if the ioremap() failed: */ if (vaddr) vaddr += offset; - return (void *)vaddr; + return vaddr; } void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr) @@ -373,7 +417,6 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr) return; iounmap((void __iomem *)((unsigned long)addr & PAGE_MASK)); - return; } static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] __page_aligned_bss; diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 9a54dbe98..e1840f3db 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -1,3 +1,4 @@ +#define pr_fmt(fmt) "kasan: " fmt #include <linux/bootmem.h> #include <linux/kasan.h> #include <linux/kdebug.h> @@ -237,4 +238,6 @@ void __init kasan_init(void) load_cr3(init_level4_pgt); __flush_tlb_all(); init_task.kasan_depth = 0; + + pr_info("Kernel address sanitizer initialized\n"); } diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index 4d1c11c07..db1b0bc50 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -10,13 +10,31 @@ #include <linux/syscalls.h> #include <linux/sched/sysctl.h> -#include <asm/i387.h> #include <asm/insn.h> #include <asm/mman.h> #include <asm/mmu_context.h> #include <asm/mpx.h> #include <asm/processor.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> + +#define CREATE_TRACE_POINTS +#include <asm/trace/mpx.h> + +static inline unsigned long mpx_bd_size_bytes(struct mm_struct *mm) +{ + if (is_64bit_mm(mm)) + return MPX_BD_SIZE_BYTES_64; + else + return MPX_BD_SIZE_BYTES_32; +} + +static inline unsigned long mpx_bt_size_bytes(struct mm_struct *mm) +{ + if (is_64bit_mm(mm)) + return MPX_BT_SIZE_BYTES_64; + else + return MPX_BT_SIZE_BYTES_32; +} /* * This is really a simplified "vm_mmap". it only handles MPX @@ -30,8 +48,8 @@ static unsigned long mpx_mmap(unsigned long len) vm_flags_t vm_flags; struct vm_area_struct *vma; - /* Only bounds table and bounds directory can be allocated here */ - if (len != MPX_BD_SIZE_BYTES && len != MPX_BT_SIZE_BYTES) + /* Only bounds table can be allocated here */ + if (len != mpx_bt_size_bytes(mm)) return -EINVAL; down_write(&mm->mmap_sem); @@ -254,10 +272,9 @@ bad_opcode: * * The caller is expected to kfree() the returned siginfo_t. */ -siginfo_t *mpx_generate_siginfo(struct pt_regs *regs, - struct xsave_struct *xsave_buf) +siginfo_t *mpx_generate_siginfo(struct pt_regs *regs) { - struct bndreg *bndregs, *bndreg; + const struct bndreg *bndregs, *bndreg; siginfo_t *info = NULL; struct insn insn; uint8_t bndregno; @@ -277,8 +294,8 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs, err = -EINVAL; goto err_out; } - /* get the bndregs _area_ of the xsave structure */ - bndregs = get_xsave_addr(xsave_buf, XSTATE_BNDREGS); + /* get bndregs field from current task's xsave area */ + bndregs = get_xsave_field_ptr(XSTATE_BNDREGS); if (!bndregs) { err = -EINVAL; goto err_out; @@ -316,6 +333,7 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs, err = -EINVAL; goto err_out; } + trace_mpx_bounds_register_exception(info->si_addr, bndreg); return info; err_out: /* info might be NULL, but kfree() handles that */ @@ -323,25 +341,18 @@ err_out: return ERR_PTR(err); } -static __user void *task_get_bounds_dir(struct task_struct *tsk) +static __user void *mpx_get_bounds_dir(void) { - struct bndcsr *bndcsr; + const struct bndcsr *bndcsr; if (!cpu_feature_enabled(X86_FEATURE_MPX)) return MPX_INVALID_BOUNDS_DIR; /* - * 32-bit binaries on 64-bit kernels are currently - * unsupported. - */ - if (IS_ENABLED(CONFIG_X86_64) && test_thread_flag(TIF_IA32)) - return MPX_INVALID_BOUNDS_DIR; - /* * The bounds directory pointer is stored in a register * only accessible if we first do an xsave. */ - fpu_save_init(&tsk->thread.fpu); - bndcsr = get_xsave_addr(&tsk->thread.fpu.state->xsave, XSTATE_BNDCSR); + bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR); if (!bndcsr) return MPX_INVALID_BOUNDS_DIR; @@ -360,10 +371,10 @@ static __user void *task_get_bounds_dir(struct task_struct *tsk) (bndcsr->bndcfgu & MPX_BNDCFG_ADDR_MASK); } -int mpx_enable_management(struct task_struct *tsk) +int mpx_enable_management(void) { void __user *bd_base = MPX_INVALID_BOUNDS_DIR; - struct mm_struct *mm = tsk->mm; + struct mm_struct *mm = current->mm; int ret = 0; /* @@ -372,11 +383,12 @@ int mpx_enable_management(struct task_struct *tsk) * directory into XSAVE/XRSTOR Save Area and enable MPX through * XRSTOR instruction. * - * fpu_xsave() is expected to be very expensive. Storing the bounds - * directory here means that we do not have to do xsave in the unmap - * path; we can just use mm->bd_addr instead. + * The copy_xregs_to_kernel() beneath get_xsave_field_ptr() is + * expected to be relatively expensive. Storing the bounds + * directory here means that we do not have to do xsave in the + * unmap path; we can just use mm->bd_addr instead. */ - bd_base = task_get_bounds_dir(tsk); + bd_base = mpx_get_bounds_dir(); down_write(&mm->mmap_sem); mm->bd_addr = bd_base; if (mm->bd_addr == MPX_INVALID_BOUNDS_DIR) @@ -386,7 +398,7 @@ int mpx_enable_management(struct task_struct *tsk) return ret; } -int mpx_disable_management(struct task_struct *tsk) +int mpx_disable_management(void) { struct mm_struct *mm = current->mm; @@ -399,29 +411,59 @@ int mpx_disable_management(struct task_struct *tsk) return 0; } +static int mpx_cmpxchg_bd_entry(struct mm_struct *mm, + unsigned long *curval, + unsigned long __user *addr, + unsigned long old_val, unsigned long new_val) +{ + int ret; + /* + * user_atomic_cmpxchg_inatomic() actually uses sizeof() + * the pointer that we pass to it to figure out how much + * data to cmpxchg. We have to be careful here not to + * pass a pointer to a 64-bit data type when we only want + * a 32-bit copy. + */ + if (is_64bit_mm(mm)) { + ret = user_atomic_cmpxchg_inatomic(curval, + addr, old_val, new_val); + } else { + u32 uninitialized_var(curval_32); + u32 old_val_32 = old_val; + u32 new_val_32 = new_val; + u32 __user *addr_32 = (u32 __user *)addr; + + ret = user_atomic_cmpxchg_inatomic(&curval_32, + addr_32, old_val_32, new_val_32); + *curval = curval_32; + } + return ret; +} + /* - * With 32-bit mode, MPX_BT_SIZE_BYTES is 4MB, and the size of each - * bounds table is 16KB. With 64-bit mode, MPX_BT_SIZE_BYTES is 2GB, + * With 32-bit mode, a bounds directory is 4MB, and the size of each + * bounds table is 16KB. With 64-bit mode, a bounds directory is 2GB, * and the size of each bounds table is 4MB. */ -static int allocate_bt(long __user *bd_entry) +static int allocate_bt(struct mm_struct *mm, long __user *bd_entry) { unsigned long expected_old_val = 0; unsigned long actual_old_val = 0; unsigned long bt_addr; + unsigned long bd_new_entry; int ret = 0; /* * Carve the virtual space out of userspace for the new * bounds table: */ - bt_addr = mpx_mmap(MPX_BT_SIZE_BYTES); + bt_addr = mpx_mmap(mpx_bt_size_bytes(mm)); if (IS_ERR((void *)bt_addr)) return PTR_ERR((void *)bt_addr); /* * Set the valid flag (kinda like _PAGE_PRESENT in a pte) */ - bt_addr = bt_addr | MPX_BD_ENTRY_VALID_FLAG; + bd_new_entry = bt_addr | MPX_BD_ENTRY_VALID_FLAG; /* * Go poke the address of the new bounds table in to the @@ -434,8 +476,8 @@ static int allocate_bt(long __user *bd_entry) * mmap_sem at this point, unlike some of the other part * of the MPX code that have to pagefault_disable(). */ - ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry, - expected_old_val, bt_addr); + ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val, bd_entry, + expected_old_val, bd_new_entry); if (ret) goto out_unmap; @@ -463,9 +505,10 @@ static int allocate_bt(long __user *bd_entry) ret = -EINVAL; goto out_unmap; } + trace_mpx_new_bounds_table(bt_addr); return 0; out_unmap: - vm_munmap(bt_addr & MPX_BT_ADDR_MASK, MPX_BT_SIZE_BYTES); + vm_munmap(bt_addr, mpx_bt_size_bytes(mm)); return ret; } @@ -480,12 +523,13 @@ out_unmap: * bound table is 16KB. With 64-bit mode, the size of BD is 2GB, * and the size of each bound table is 4MB. */ -static int do_mpx_bt_fault(struct xsave_struct *xsave_buf) +static int do_mpx_bt_fault(void) { unsigned long bd_entry, bd_base; - struct bndcsr *bndcsr; + const struct bndcsr *bndcsr; + struct mm_struct *mm = current->mm; - bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR); + bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR); if (!bndcsr) return -EINVAL; /* @@ -502,13 +546,13 @@ static int do_mpx_bt_fault(struct xsave_struct *xsave_buf) * the directory is. */ if ((bd_entry < bd_base) || - (bd_entry >= bd_base + MPX_BD_SIZE_BYTES)) + (bd_entry >= bd_base + mpx_bd_size_bytes(mm))) return -EINVAL; - return allocate_bt((long __user *)bd_entry); + return allocate_bt(mm, (long __user *)bd_entry); } -int mpx_handle_bd_fault(struct xsave_struct *xsave_buf) +int mpx_handle_bd_fault(void) { /* * Userspace never asked us to manage the bounds tables, @@ -517,7 +561,7 @@ int mpx_handle_bd_fault(struct xsave_struct *xsave_buf) if (!kernel_managing_mpx_tables(current->mm)) return -EINVAL; - if (do_mpx_bt_fault(xsave_buf)) { + if (do_mpx_bt_fault()) { force_sig(SIGSEGV, current); /* * The force_sig() is essentially "handling" this @@ -554,29 +598,55 @@ static int mpx_resolve_fault(long __user *addr, int write) return 0; } +static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm, + unsigned long bd_entry) +{ + unsigned long bt_addr = bd_entry; + int align_to_bytes; + /* + * Bit 0 in a bt_entry is always the valid bit. + */ + bt_addr &= ~MPX_BD_ENTRY_VALID_FLAG; + /* + * Tables are naturally aligned at 8-byte boundaries + * on 64-bit and 4-byte boundaries on 32-bit. The + * documentation makes it appear that the low bits + * are ignored by the hardware, so we do the same. + */ + if (is_64bit_mm(mm)) + align_to_bytes = 8; + else + align_to_bytes = 4; + bt_addr &= ~(align_to_bytes-1); + return bt_addr; +} + /* * Get the base of bounds tables pointed by specific bounds * directory entry. */ static int get_bt_addr(struct mm_struct *mm, - long __user *bd_entry, unsigned long *bt_addr) + long __user *bd_entry_ptr, + unsigned long *bt_addr_result) { int ret; int valid_bit; + unsigned long bd_entry; + unsigned long bt_addr; - if (!access_ok(VERIFY_READ, (bd_entry), sizeof(*bd_entry))) + if (!access_ok(VERIFY_READ, (bd_entry_ptr), sizeof(*bd_entry_ptr))) return -EFAULT; while (1) { int need_write = 0; pagefault_disable(); - ret = get_user(*bt_addr, bd_entry); + ret = get_user(bd_entry, bd_entry_ptr); pagefault_enable(); if (!ret) break; if (ret == -EFAULT) - ret = mpx_resolve_fault(bd_entry, need_write); + ret = mpx_resolve_fault(bd_entry_ptr, need_write); /* * If we could not resolve the fault, consider it * userspace's fault and error out. @@ -585,8 +655,8 @@ static int get_bt_addr(struct mm_struct *mm, return ret; } - valid_bit = *bt_addr & MPX_BD_ENTRY_VALID_FLAG; - *bt_addr &= MPX_BT_ADDR_MASK; + valid_bit = bd_entry & MPX_BD_ENTRY_VALID_FLAG; + bt_addr = mpx_bd_entry_to_bt_addr(mm, bd_entry); /* * When the kernel is managing bounds tables, a bounds directory @@ -595,7 +665,7 @@ static int get_bt_addr(struct mm_struct *mm, * data in the address field, we know something is wrong. This * -EINVAL return will cause a SIGSEGV. */ - if (!valid_bit && *bt_addr) + if (!valid_bit && bt_addr) return -EINVAL; /* * Do we have an completely zeroed bt entry? That is OK. It @@ -606,19 +676,100 @@ static int get_bt_addr(struct mm_struct *mm, if (!valid_bit) return -ENOENT; + *bt_addr_result = bt_addr; return 0; } +static inline int bt_entry_size_bytes(struct mm_struct *mm) +{ + if (is_64bit_mm(mm)) + return MPX_BT_ENTRY_BYTES_64; + else + return MPX_BT_ENTRY_BYTES_32; +} + +/* + * Take a virtual address and turns it in to the offset in bytes + * inside of the bounds table where the bounds table entry + * controlling 'addr' can be found. + */ +static unsigned long mpx_get_bt_entry_offset_bytes(struct mm_struct *mm, + unsigned long addr) +{ + unsigned long bt_table_nr_entries; + unsigned long offset = addr; + + if (is_64bit_mm(mm)) { + /* Bottom 3 bits are ignored on 64-bit */ + offset >>= 3; + bt_table_nr_entries = MPX_BT_NR_ENTRIES_64; + } else { + /* Bottom 2 bits are ignored on 32-bit */ + offset >>= 2; + bt_table_nr_entries = MPX_BT_NR_ENTRIES_32; + } + /* + * We know the size of the table in to which we are + * indexing, and we have eliminated all the low bits + * which are ignored for indexing. + * + * Mask out all the high bits which we do not need + * to index in to the table. Note that the tables + * are always powers of two so this gives us a proper + * mask. + */ + offset &= (bt_table_nr_entries-1); + /* + * We now have an entry offset in terms of *entries* in + * the table. We need to scale it back up to bytes. + */ + offset *= bt_entry_size_bytes(mm); + return offset; +} + +/* + * How much virtual address space does a single bounds + * directory entry cover? + * + * Note, we need a long long because 4GB doesn't fit in + * to a long on 32-bit. + */ +static inline unsigned long bd_entry_virt_space(struct mm_struct *mm) +{ + unsigned long long virt_space = (1ULL << boot_cpu_data.x86_virt_bits); + if (is_64bit_mm(mm)) + return virt_space / MPX_BD_NR_ENTRIES_64; + else + return virt_space / MPX_BD_NR_ENTRIES_32; +} + /* * Free the backing physical pages of bounds table 'bt_addr'. * Assume start...end is within that bounds table. */ -static int zap_bt_entries(struct mm_struct *mm, +static noinline int zap_bt_entries_mapping(struct mm_struct *mm, unsigned long bt_addr, - unsigned long start, unsigned long end) + unsigned long start_mapping, unsigned long end_mapping) { struct vm_area_struct *vma; unsigned long addr, len; + unsigned long start; + unsigned long end; + + /* + * if we 'end' on a boundary, the offset will be 0 which + * is not what we want. Back it up a byte to get the + * last bt entry. Then once we have the entry itself, + * move 'end' back up by the table entry size. + */ + start = bt_addr + mpx_get_bt_entry_offset_bytes(mm, start_mapping); + end = bt_addr + mpx_get_bt_entry_offset_bytes(mm, end_mapping - 1); + /* + * Move end back up by one entry. Among other things + * this ensures that it remains page-aligned and does + * not screw up zap_page_range() + */ + end += bt_entry_size_bytes(mm); /* * Find the first overlapping vma. If vma->vm_start > start, there @@ -630,7 +781,7 @@ static int zap_bt_entries(struct mm_struct *mm, return -EINVAL; /* - * A NUMA policy on a VM_MPX VMA could cause this bouds table to + * A NUMA policy on a VM_MPX VMA could cause this bounds table to * be split. So we need to look across the entire 'start -> end' * range of this bounds table, find all of the VM_MPX VMAs, and * zap only those. @@ -648,27 +799,65 @@ static int zap_bt_entries(struct mm_struct *mm, len = min(vma->vm_end, end) - addr; zap_page_range(vma, addr, len, NULL); + trace_mpx_unmap_zap(addr, addr+len); vma = vma->vm_next; addr = vma->vm_start; } - return 0; } -static int unmap_single_bt(struct mm_struct *mm, +static unsigned long mpx_get_bd_entry_offset(struct mm_struct *mm, + unsigned long addr) +{ + /* + * There are several ways to derive the bd offsets. We + * use the following approach here: + * 1. We know the size of the virtual address space + * 2. We know the number of entries in a bounds table + * 3. We know that each entry covers a fixed amount of + * virtual address space. + * So, we can just divide the virtual address by the + * virtual space used by one entry to determine which + * entry "controls" the given virtual address. + */ + if (is_64bit_mm(mm)) { + int bd_entry_size = 8; /* 64-bit pointer */ + /* + * Take the 64-bit addressing hole in to account. + */ + addr &= ((1UL << boot_cpu_data.x86_virt_bits) - 1); + return (addr / bd_entry_virt_space(mm)) * bd_entry_size; + } else { + int bd_entry_size = 4; /* 32-bit pointer */ + /* + * 32-bit has no hole so this case needs no mask + */ + return (addr / bd_entry_virt_space(mm)) * bd_entry_size; + } + /* + * The two return calls above are exact copies. If we + * pull out a single copy and put it in here, gcc won't + * realize that we're doing a power-of-2 divide and use + * shifts. It uses a real divide. If we put them up + * there, it manages to figure it out (gcc 4.8.3). + */ +} + +static int unmap_entire_bt(struct mm_struct *mm, long __user *bd_entry, unsigned long bt_addr) { unsigned long expected_old_val = bt_addr | MPX_BD_ENTRY_VALID_FLAG; - unsigned long actual_old_val = 0; + unsigned long uninitialized_var(actual_old_val); int ret; while (1) { int need_write = 1; + unsigned long cleared_bd_entry = 0; pagefault_disable(); - ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry, - expected_old_val, 0); + ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val, + bd_entry, expected_old_val, cleared_bd_entry); pagefault_enable(); if (!ret) break; @@ -687,9 +876,8 @@ static int unmap_single_bt(struct mm_struct *mm, if (actual_old_val != expected_old_val) { /* * Someone else raced with us to unmap the table. - * There was no bounds table pointed to by the - * directory, so declare success. Somebody freed - * it. + * That is OK, since we were both trying to do + * the same thing. Declare success. */ if (!actual_old_val) return 0; @@ -702,176 +890,113 @@ static int unmap_single_bt(struct mm_struct *mm, */ return -EINVAL; } - /* * Note, we are likely being called under do_munmap() already. To * avoid recursion, do_munmap() will check whether it comes * from one bounds table through VM_MPX flag. */ - return do_munmap(mm, bt_addr, MPX_BT_SIZE_BYTES); + return do_munmap(mm, bt_addr, mpx_bt_size_bytes(mm)); } -/* - * If the bounds table pointed by bounds directory 'bd_entry' is - * not shared, unmap this whole bounds table. Otherwise, only free - * those backing physical pages of bounds table entries covered - * in this virtual address region start...end. - */ -static int unmap_shared_bt(struct mm_struct *mm, - long __user *bd_entry, unsigned long start, - unsigned long end, bool prev_shared, bool next_shared) +static int try_unmap_single_bt(struct mm_struct *mm, + unsigned long start, unsigned long end) { - unsigned long bt_addr; - int ret; - - ret = get_bt_addr(mm, bd_entry, &bt_addr); + struct vm_area_struct *next; + struct vm_area_struct *prev; /* - * We could see an "error" ret for not-present bounds - * tables (not really an error), or actual errors, but - * stop unmapping either way. + * "bta" == Bounds Table Area: the area controlled by the + * bounds table that we are unmapping. */ - if (ret) - return ret; - - if (prev_shared && next_shared) - ret = zap_bt_entries(mm, bt_addr, - bt_addr+MPX_GET_BT_ENTRY_OFFSET(start), - bt_addr+MPX_GET_BT_ENTRY_OFFSET(end)); - else if (prev_shared) - ret = zap_bt_entries(mm, bt_addr, - bt_addr+MPX_GET_BT_ENTRY_OFFSET(start), - bt_addr+MPX_BT_SIZE_BYTES); - else if (next_shared) - ret = zap_bt_entries(mm, bt_addr, bt_addr, - bt_addr+MPX_GET_BT_ENTRY_OFFSET(end)); - else - ret = unmap_single_bt(mm, bd_entry, bt_addr); - - return ret; -} - -/* - * A virtual address region being munmap()ed might share bounds table - * with adjacent VMAs. We only need to free the backing physical - * memory of these shared bounds tables entries covered in this virtual - * address region. - */ -static int unmap_edge_bts(struct mm_struct *mm, - unsigned long start, unsigned long end) -{ + unsigned long bta_start_vaddr = start & ~(bd_entry_virt_space(mm)-1); + unsigned long bta_end_vaddr = bta_start_vaddr + bd_entry_virt_space(mm); + unsigned long uninitialized_var(bt_addr); + void __user *bde_vaddr; int ret; - long __user *bde_start, *bde_end; - struct vm_area_struct *prev, *next; - bool prev_shared = false, next_shared = false; - - bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start); - bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1); - /* - * Check whether bde_start and bde_end are shared with adjacent - * VMAs. - * - * We already unliked the VMAs from the mm's rbtree so 'start' + * We already unlinked the VMAs from the mm's rbtree so 'start' * is guaranteed to be in a hole. This gets us the first VMA * before the hole in to 'prev' and the next VMA after the hole * in to 'next'. */ next = find_vma_prev(mm, start, &prev); - if (prev && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(prev->vm_end-1)) - == bde_start) - prev_shared = true; - if (next && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(next->vm_start)) - == bde_end) - next_shared = true; - /* - * This virtual address region being munmap()ed is only - * covered by one bounds table. - * - * In this case, if this table is also shared with adjacent - * VMAs, only part of the backing physical memory of the bounds - * table need be freeed. Otherwise the whole bounds table need - * be unmapped. - */ - if (bde_start == bde_end) { - return unmap_shared_bt(mm, bde_start, start, end, - prev_shared, next_shared); + * Do not count other MPX bounds table VMAs as neighbors. + * Although theoretically possible, we do not allow bounds + * tables for bounds tables so our heads do not explode. + * If we count them as neighbors here, we may end up with + * lots of tables even though we have no actual table + * entries in use. + */ + while (next && (next->vm_flags & VM_MPX)) + next = next->vm_next; + while (prev && (prev->vm_flags & VM_MPX)) + prev = prev->vm_prev; + /* + * We know 'start' and 'end' lie within an area controlled + * by a single bounds table. See if there are any other + * VMAs controlled by that bounds table. If there are not + * then we can "expand" the are we are unmapping to possibly + * cover the entire table. + */ + next = find_vma_prev(mm, start, &prev); + if ((!prev || prev->vm_end <= bta_start_vaddr) && + (!next || next->vm_start >= bta_end_vaddr)) { + /* + * No neighbor VMAs controlled by same bounds + * table. Try to unmap the whole thing + */ + start = bta_start_vaddr; + end = bta_end_vaddr; } + bde_vaddr = mm->bd_addr + mpx_get_bd_entry_offset(mm, start); + ret = get_bt_addr(mm, bde_vaddr, &bt_addr); /* - * If more than one bounds tables are covered in this virtual - * address region being munmap()ed, we need to separately check - * whether bde_start and bde_end are shared with adjacent VMAs. + * No bounds table there, so nothing to unmap. */ - ret = unmap_shared_bt(mm, bde_start, start, end, prev_shared, false); - if (ret) - return ret; - ret = unmap_shared_bt(mm, bde_end, start, end, false, next_shared); + if (ret == -ENOENT) { + ret = 0; + return 0; + } if (ret) return ret; - - return 0; + /* + * We are unmapping an entire table. Either because the + * unmap that started this whole process was large enough + * to cover an entire table, or that the unmap was small + * but was the area covered by a bounds table. + */ + if ((start == bta_start_vaddr) && + (end == bta_end_vaddr)) + return unmap_entire_bt(mm, bde_vaddr, bt_addr); + return zap_bt_entries_mapping(mm, bt_addr, start, end); } static int mpx_unmap_tables(struct mm_struct *mm, unsigned long start, unsigned long end) { - int ret; - long __user *bd_entry, *bde_start, *bde_end; - unsigned long bt_addr; - - /* - * "Edge" bounds tables are those which are being used by the region - * (start -> end), but that may be shared with adjacent areas. If they - * turn out to be completely unshared, they will be freed. If they are - * shared, we will free the backing store (like an MADV_DONTNEED) for - * areas used by this region. - */ - ret = unmap_edge_bts(mm, start, end); - switch (ret) { - /* non-present tables are OK */ - case 0: - case -ENOENT: - /* Success, or no tables to unmap */ - break; - case -EINVAL: - case -EFAULT: - default: - return ret; - } - - /* - * Only unmap the bounds table that are - * 1. fully covered - * 2. not at the edges of the mapping, even if full aligned - */ - bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start); - bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1); - for (bd_entry = bde_start + 1; bd_entry < bde_end; bd_entry++) { - ret = get_bt_addr(mm, bd_entry, &bt_addr); - switch (ret) { - case 0: - break; - case -ENOENT: - /* No table here, try the next one */ - continue; - case -EINVAL: - case -EFAULT: - default: - /* - * Note: we are being strict here. - * Any time we run in to an issue - * unmapping tables, we stop and - * SIGSEGV. - */ - return ret; - } - - ret = unmap_single_bt(mm, bd_entry, bt_addr); + unsigned long one_unmap_start; + trace_mpx_unmap_search(start, end); + + one_unmap_start = start; + while (one_unmap_start < end) { + int ret; + unsigned long next_unmap_start = ALIGN(one_unmap_start+1, + bd_entry_virt_space(mm)); + unsigned long one_unmap_end = end; + /* + * if the end is beyond the current bounds table, + * move it back so we only deal with a single one + * at a time + */ + if (one_unmap_end > next_unmap_start) + one_unmap_end = next_unmap_start; + ret = try_unmap_single_bt(mm, one_unmap_start, one_unmap_end); if (ret) return ret; - } + one_unmap_start = next_unmap_start; + } return 0; } diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c index 6629f397b..8ff686aa7 100644 --- a/arch/x86/mm/pageattr-test.c +++ b/arch/x86/mm/pageattr-test.c @@ -9,6 +9,7 @@ #include <linux/random.h> #include <linux/kernel.h> #include <linux/mm.h> +#include <linux/vmalloc.h> #include <asm/cacheflush.h> #include <asm/pgtable.h> diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 89af288ec..727158cb3 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -14,6 +14,7 @@ #include <linux/percpu.h> #include <linux/gfp.h> #include <linux/pci.h> +#include <linux/vmalloc.h> #include <asm/e820.h> #include <asm/processor.h> @@ -129,16 +130,15 @@ within(unsigned long addr, unsigned long start, unsigned long end) */ void clflush_cache_range(void *vaddr, unsigned int size) { - void *vend = vaddr + size - 1; + unsigned long clflush_mask = boot_cpu_data.x86_clflush_size - 1; + void *vend = vaddr + size; + void *p; mb(); - for (; vaddr < vend; vaddr += boot_cpu_data.x86_clflush_size) - clflushopt(vaddr); - /* - * Flush any possible final partial cacheline: - */ - clflushopt(vend); + for (p = (void *)((unsigned long)vaddr & ~clflush_mask); + p < vend; p += boot_cpu_data.x86_clflush_size) + clflushopt(p); mb(); } @@ -418,13 +418,11 @@ phys_addr_t slow_virt_to_phys(void *__virt_addr) phys_addr_t phys_addr; unsigned long offset; enum pg_level level; - unsigned long psize; unsigned long pmask; pte_t *pte; pte = lookup_address(virt_addr, &level); BUG_ON(!pte); - psize = page_level_size(level); pmask = page_level_mask(level); offset = virt_addr & ~pmask; phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; @@ -1468,6 +1466,9 @@ int _set_memory_uc(unsigned long addr, int numpages) { /* * for now UC MINUS. see comments in ioremap_nocache() + * If you really need strong UC use ioremap_uc(), but note + * that you cannot override IO areas with set_memory_*() as + * these helpers cannot work with IO memory. */ return change_page_attr_set(&addr, numpages, cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS), @@ -1502,12 +1503,10 @@ EXPORT_SYMBOL(set_memory_uc); static int _set_memory_array(unsigned long *addr, int addrinarray, enum page_cache_mode new_type) { + enum page_cache_mode set_type; int i, j; int ret; - /* - * for now UC MINUS. see comments in ioremap_nocache() - */ for (i = 0; i < addrinarray; i++) { ret = reserve_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE, new_type, NULL); @@ -1515,9 +1514,12 @@ static int _set_memory_array(unsigned long *addr, int addrinarray, goto out_free; } + /* If WC, set to UC- first and then WC */ + set_type = (new_type == _PAGE_CACHE_MODE_WC) ? + _PAGE_CACHE_MODE_UC_MINUS : new_type; + ret = change_page_attr_set(addr, addrinarray, - cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS), - 1); + cachemode2pgprot(set_type), 1); if (!ret && new_type == _PAGE_CACHE_MODE_WC) ret = change_page_attr_set_clr(addr, addrinarray, @@ -1549,6 +1551,12 @@ int set_memory_array_wc(unsigned long *addr, int addrinarray) } EXPORT_SYMBOL(set_memory_array_wc); +int set_memory_array_wt(unsigned long *addr, int addrinarray) +{ + return _set_memory_array(addr, addrinarray, _PAGE_CACHE_MODE_WT); +} +EXPORT_SYMBOL_GPL(set_memory_array_wt); + int _set_memory_wc(unsigned long addr, int numpages) { int ret; @@ -1571,27 +1579,42 @@ int set_memory_wc(unsigned long addr, int numpages) { int ret; - if (!pat_enabled) - return set_memory_uc(addr, numpages); - ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, _PAGE_CACHE_MODE_WC, NULL); if (ret) - goto out_err; + return ret; ret = _set_memory_wc(addr, numpages); if (ret) - goto out_free; - - return 0; + free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); -out_free: - free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); -out_err: return ret; } EXPORT_SYMBOL(set_memory_wc); +int _set_memory_wt(unsigned long addr, int numpages) +{ + return change_page_attr_set(&addr, numpages, + cachemode2pgprot(_PAGE_CACHE_MODE_WT), 0); +} + +int set_memory_wt(unsigned long addr, int numpages) +{ + int ret; + + ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, + _PAGE_CACHE_MODE_WT, NULL); + if (ret) + return ret; + + ret = _set_memory_wt(addr, numpages); + if (ret) + free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); + + return ret; +} +EXPORT_SYMBOL_GPL(set_memory_wt); + int _set_memory_wb(unsigned long addr, int numpages) { /* WB cache mode is hard wired to all cache attribute bits being 0 */ @@ -1682,6 +1705,7 @@ static int _set_pages_array(struct page **pages, int addrinarray, { unsigned long start; unsigned long end; + enum page_cache_mode set_type; int i; int free_idx; int ret; @@ -1695,8 +1719,12 @@ static int _set_pages_array(struct page **pages, int addrinarray, goto err_out; } + /* If WC, set to UC- first and then WC */ + set_type = (new_type == _PAGE_CACHE_MODE_WC) ? + _PAGE_CACHE_MODE_UC_MINUS : new_type; + ret = cpa_set_pages_array(pages, addrinarray, - cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS)); + cachemode2pgprot(set_type)); if (!ret && new_type == _PAGE_CACHE_MODE_WC) ret = change_page_attr_set_clr(NULL, addrinarray, cachemode2pgprot( @@ -1730,6 +1758,12 @@ int set_pages_array_wc(struct page **pages, int addrinarray) } EXPORT_SYMBOL(set_pages_array_wc); +int set_pages_array_wt(struct page **pages, int addrinarray) +{ + return _set_pages_array(pages, addrinarray, _PAGE_CACHE_MODE_WT); +} +EXPORT_SYMBOL_GPL(set_pages_array_wt); + int set_pages_wb(struct page *page, int numpages) { unsigned long addr = (unsigned long)page_address(page); diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 35af6771a..188e3e07e 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -33,13 +33,17 @@ #include "pat_internal.h" #include "mm_internal.h" -#ifdef CONFIG_X86_PAT -int __read_mostly pat_enabled = 1; +#undef pr_fmt +#define pr_fmt(fmt) "" fmt + +static bool boot_cpu_done; + +static int __read_mostly __pat_enabled = IS_ENABLED(CONFIG_X86_PAT); static inline void pat_disable(const char *reason) { - pat_enabled = 0; - printk(KERN_INFO "%s\n", reason); + __pat_enabled = 0; + pr_info("x86/PAT: %s\n", reason); } static int __init nopat(char *str) @@ -48,13 +52,12 @@ static int __init nopat(char *str) return 0; } early_param("nopat", nopat); -#else -static inline void pat_disable(const char *reason) + +bool pat_enabled(void) { - (void)reason; + return !!__pat_enabled; } -#endif - +EXPORT_SYMBOL_GPL(pat_enabled); int pat_debug_enable; @@ -65,22 +68,24 @@ static int __init pat_debug_setup(char *str) } __setup("debugpat", pat_debug_setup); -static u64 __read_mostly boot_pat_state; - #ifdef CONFIG_X86_PAT /* - * X86 PAT uses page flags WC and Uncached together to keep track of - * memory type of pages that have backing page struct. X86 PAT supports 3 - * different memory types, _PAGE_CACHE_MODE_WB, _PAGE_CACHE_MODE_WC and - * _PAGE_CACHE_MODE_UC_MINUS and fourth state where page's memory type has not - * been changed from its default (value of -1 used to denote this). - * Note we do not support _PAGE_CACHE_MODE_UC here. + * X86 PAT uses page flags arch_1 and uncached together to keep track of + * memory type of pages that have backing page struct. + * + * X86 PAT supports 4 different memory types: + * - _PAGE_CACHE_MODE_WB + * - _PAGE_CACHE_MODE_WC + * - _PAGE_CACHE_MODE_UC_MINUS + * - _PAGE_CACHE_MODE_WT + * + * _PAGE_CACHE_MODE_WB is the default type. */ -#define _PGMT_DEFAULT 0 +#define _PGMT_WB 0 #define _PGMT_WC (1UL << PG_arch_1) #define _PGMT_UC_MINUS (1UL << PG_uncached) -#define _PGMT_WB (1UL << PG_uncached | 1UL << PG_arch_1) +#define _PGMT_WT (1UL << PG_uncached | 1UL << PG_arch_1) #define _PGMT_MASK (1UL << PG_uncached | 1UL << PG_arch_1) #define _PGMT_CLEAR_MASK (~_PGMT_MASK) @@ -88,14 +93,14 @@ static inline enum page_cache_mode get_page_memtype(struct page *pg) { unsigned long pg_flags = pg->flags & _PGMT_MASK; - if (pg_flags == _PGMT_DEFAULT) - return -1; + if (pg_flags == _PGMT_WB) + return _PAGE_CACHE_MODE_WB; else if (pg_flags == _PGMT_WC) return _PAGE_CACHE_MODE_WC; else if (pg_flags == _PGMT_UC_MINUS) return _PAGE_CACHE_MODE_UC_MINUS; else - return _PAGE_CACHE_MODE_WB; + return _PAGE_CACHE_MODE_WT; } static inline void set_page_memtype(struct page *pg, @@ -112,11 +117,12 @@ static inline void set_page_memtype(struct page *pg, case _PAGE_CACHE_MODE_UC_MINUS: memtype_flags = _PGMT_UC_MINUS; break; - case _PAGE_CACHE_MODE_WB: - memtype_flags = _PGMT_WB; + case _PAGE_CACHE_MODE_WT: + memtype_flags = _PGMT_WT; break; + case _PAGE_CACHE_MODE_WB: default: - memtype_flags = _PGMT_DEFAULT; + memtype_flags = _PGMT_WB; break; } @@ -174,78 +180,154 @@ static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg) * configuration. * Using lower indices is preferred, so we start with highest index. */ -void pat_init_cache_modes(void) +void pat_init_cache_modes(u64 pat) { - int i; enum page_cache_mode cache; char pat_msg[33]; - u64 pat; + int i; - rdmsrl(MSR_IA32_CR_PAT, pat); pat_msg[32] = 0; for (i = 7; i >= 0; i--) { cache = pat_get_cache_mode((pat >> (i * 8)) & 7, pat_msg + 4 * i); update_cache_mode_entry(i, cache); } - pr_info("PAT configuration [0-7]: %s\n", pat_msg); + pr_info("x86/PAT: Configuration [0-7]: %s\n", pat_msg); } #define PAT(x, y) ((u64)PAT_ ## y << ((x)*8)) -void pat_init(void) +static void pat_bsp_init(u64 pat) { - u64 pat; - bool boot_cpu = !boot_pat_state; + u64 tmp_pat; - if (!pat_enabled) + if (!cpu_has_pat) { + pat_disable("PAT not supported by CPU."); return; + } - if (!cpu_has_pat) { - if (!boot_pat_state) { - pat_disable("PAT not supported by CPU."); - return; - } else { - /* - * If this happens we are on a secondary CPU, but - * switched to PAT on the boot CPU. We have no way to - * undo PAT. - */ - printk(KERN_ERR "PAT enabled, " - "but not supported by secondary CPU\n"); - BUG(); - } + if (!pat_enabled()) + goto done; + + rdmsrl(MSR_IA32_CR_PAT, tmp_pat); + if (!tmp_pat) { + pat_disable("PAT MSR is 0, disabled."); + return; } - /* Set PWT to Write-Combining. All other bits stay the same */ - /* - * PTE encoding used in Linux: - * PAT - * |PCD - * ||PWT - * ||| - * 000 WB _PAGE_CACHE_WB - * 001 WC _PAGE_CACHE_WC - * 010 UC- _PAGE_CACHE_UC_MINUS - * 011 UC _PAGE_CACHE_UC - * PAT bit unused - */ - pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) | - PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC); - - /* Boot CPU check */ - if (!boot_pat_state) { - rdmsrl(MSR_IA32_CR_PAT, boot_pat_state); - if (!boot_pat_state) { - pat_disable("PAT read returns always zero, disabled."); - return; - } + wrmsrl(MSR_IA32_CR_PAT, pat); + +done: + pat_init_cache_modes(pat); +} + +static void pat_ap_init(u64 pat) +{ + if (!pat_enabled()) + return; + + if (!cpu_has_pat) { + /* + * If this happens we are on a secondary CPU, but switched to + * PAT on the boot CPU. We have no way to undo PAT. + */ + panic("x86/PAT: PAT enabled, but not supported by secondary CPU\n"); } wrmsrl(MSR_IA32_CR_PAT, pat); +} + +void pat_init(void) +{ + u64 pat; + struct cpuinfo_x86 *c = &boot_cpu_data; + + if (!pat_enabled()) { + /* + * No PAT. Emulate the PAT table that corresponds to the two + * cache bits, PWT (Write Through) and PCD (Cache Disable). This + * setup is the same as the BIOS default setup when the system + * has PAT but the "nopat" boot option has been specified. This + * emulated PAT table is used when MSR_IA32_CR_PAT returns 0. + * + * PTE encoding: + * + * PCD + * |PWT PAT + * || slot + * 00 0 WB : _PAGE_CACHE_MODE_WB + * 01 1 WT : _PAGE_CACHE_MODE_WT + * 10 2 UC-: _PAGE_CACHE_MODE_UC_MINUS + * 11 3 UC : _PAGE_CACHE_MODE_UC + * + * NOTE: When WC or WP is used, it is redirected to UC- per + * the default setup in __cachemode2pte_tbl[]. + */ + pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) | + PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC); - if (boot_cpu) - pat_init_cache_modes(); + } else if ((c->x86_vendor == X86_VENDOR_INTEL) && + (((c->x86 == 0x6) && (c->x86_model <= 0xd)) || + ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) { + /* + * PAT support with the lower four entries. Intel Pentium 2, + * 3, M, and 4 are affected by PAT errata, which makes the + * upper four entries unusable. To be on the safe side, we don't + * use those. + * + * PTE encoding: + * PAT + * |PCD + * ||PWT PAT + * ||| slot + * 000 0 WB : _PAGE_CACHE_MODE_WB + * 001 1 WC : _PAGE_CACHE_MODE_WC + * 010 2 UC-: _PAGE_CACHE_MODE_UC_MINUS + * 011 3 UC : _PAGE_CACHE_MODE_UC + * PAT bit unused + * + * NOTE: When WT or WP is used, it is redirected to UC- per + * the default setup in __cachemode2pte_tbl[]. + */ + pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) | + PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC); + } else { + /* + * Full PAT support. We put WT in slot 7 to improve + * robustness in the presence of errata that might cause + * the high PAT bit to be ignored. This way, a buggy slot 7 + * access will hit slot 3, and slot 3 is UC, so at worst + * we lose performance without causing a correctness issue. + * Pentium 4 erratum N46 is an example for such an erratum, + * although we try not to use PAT at all on affected CPUs. + * + * PTE encoding: + * PAT + * |PCD + * ||PWT PAT + * ||| slot + * 000 0 WB : _PAGE_CACHE_MODE_WB + * 001 1 WC : _PAGE_CACHE_MODE_WC + * 010 2 UC-: _PAGE_CACHE_MODE_UC_MINUS + * 011 3 UC : _PAGE_CACHE_MODE_UC + * 100 4 WB : Reserved + * 101 5 WC : Reserved + * 110 6 UC-: Reserved + * 111 7 WT : _PAGE_CACHE_MODE_WT + * + * The reserved slots are unused, but mapped to their + * corresponding types in the presence of PAT errata. + */ + pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) | + PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, WT); + } + + if (!boot_cpu_done) { + pat_bsp_init(pat); + boot_cpu_done = true; + } else { + pat_ap_init(pat); + } } #undef PAT @@ -267,9 +349,9 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end, * request is for WB. */ if (req_type == _PAGE_CACHE_MODE_WB) { - u8 mtrr_type; + u8 mtrr_type, uniform; - mtrr_type = mtrr_type_lookup(start, end); + mtrr_type = mtrr_type_lookup(start, end, &uniform); if (mtrr_type != MTRR_TYPE_WRBACK) return _PAGE_CACHE_MODE_UC_MINUS; @@ -324,9 +406,14 @@ static int pat_pagerange_is_ram(resource_size_t start, resource_size_t end) /* * For RAM pages, we use page flags to mark the pages with appropriate type. - * Here we do two pass: - * - Find the memtype of all the pages in the range, look for any conflicts - * - In case of no conflicts, set the new memtype for pages in the range + * The page flags are limited to four types, WB (default), WC, WT and UC-. + * WP request fails with -EINVAL, and UC gets redirected to UC-. Setting + * a new memory type is only allowed for a page mapped with the default WB + * type. + * + * Here we do two passes: + * - Find the memtype of all the pages in the range, look for any conflicts. + * - In case of no conflicts, set the new memtype for pages in the range. */ static int reserve_ram_pages_type(u64 start, u64 end, enum page_cache_mode req_type, @@ -335,6 +422,12 @@ static int reserve_ram_pages_type(u64 start, u64 end, struct page *page; u64 pfn; + if (req_type == _PAGE_CACHE_MODE_WP) { + if (new_type) + *new_type = _PAGE_CACHE_MODE_UC_MINUS; + return -EINVAL; + } + if (req_type == _PAGE_CACHE_MODE_UC) { /* We do not support strong UC */ WARN_ON_ONCE(1); @@ -346,8 +439,8 @@ static int reserve_ram_pages_type(u64 start, u64 end, page = pfn_to_page(pfn); type = get_page_memtype(page); - if (type != -1) { - pr_info("reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%x, req 0x%x\n", + if (type != _PAGE_CACHE_MODE_WB) { + pr_info("x86/PAT: reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%x, req 0x%x\n", start, end - 1, type, req_type); if (new_type) *new_type = type; @@ -373,7 +466,7 @@ static int free_ram_pages_type(u64 start, u64 end) for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) { page = pfn_to_page(pfn); - set_page_memtype(page, -1); + set_page_memtype(page, _PAGE_CACHE_MODE_WB); } return 0; } @@ -384,6 +477,7 @@ static int free_ram_pages_type(u64 start, u64 end) * - _PAGE_CACHE_MODE_WC * - _PAGE_CACHE_MODE_UC_MINUS * - _PAGE_CACHE_MODE_UC + * - _PAGE_CACHE_MODE_WT * * If new_type is NULL, function will return an error if it cannot reserve the * region with req_type. If new_type is non-NULL, function will return @@ -400,14 +494,10 @@ int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type, BUG_ON(start >= end); /* end is exclusive */ - if (!pat_enabled) { + if (!pat_enabled()) { /* This is identical to page table setting without PAT */ - if (new_type) { - if (req_type == _PAGE_CACHE_MODE_WC) - *new_type = _PAGE_CACHE_MODE_UC_MINUS; - else - *new_type = req_type; - } + if (new_type) + *new_type = req_type; return 0; } @@ -451,9 +541,9 @@ int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type, err = rbt_memtype_check_insert(new, new_type); if (err) { - printk(KERN_INFO "reserve_memtype failed [mem %#010Lx-%#010Lx], track %s, req %s\n", - start, end - 1, - cattr_name(new->type), cattr_name(req_type)); + pr_info("x86/PAT: reserve_memtype failed [mem %#010Lx-%#010Lx], track %s, req %s\n", + start, end - 1, + cattr_name(new->type), cattr_name(req_type)); kfree(new); spin_unlock(&memtype_lock); @@ -475,7 +565,7 @@ int free_memtype(u64 start, u64 end) int is_range_ram; struct memtype *entry; - if (!pat_enabled) + if (!pat_enabled()) return 0; /* Low ISA region is always mapped WB. No need to track */ @@ -497,8 +587,8 @@ int free_memtype(u64 start, u64 end) spin_unlock(&memtype_lock); if (!entry) { - printk(KERN_INFO "%s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n", - current->comm, current->pid, start, end - 1); + pr_info("x86/PAT: %s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n", + current->comm, current->pid, start, end - 1); return -EINVAL; } @@ -517,7 +607,7 @@ int free_memtype(u64 start, u64 end) * Only to be called when PAT is enabled * * Returns _PAGE_CACHE_MODE_WB, _PAGE_CACHE_MODE_WC, _PAGE_CACHE_MODE_UC_MINUS - * or _PAGE_CACHE_MODE_UC + * or _PAGE_CACHE_MODE_WT. */ static enum page_cache_mode lookup_memtype(u64 paddr) { @@ -529,16 +619,9 @@ static enum page_cache_mode lookup_memtype(u64 paddr) if (pat_pagerange_is_ram(paddr, paddr + PAGE_SIZE)) { struct page *page; - page = pfn_to_page(paddr >> PAGE_SHIFT); - rettype = get_page_memtype(page); - /* - * -1 from get_page_memtype() implies RAM page is in its - * default state and not reserved, and hence of type WB - */ - if (rettype == -1) - rettype = _PAGE_CACHE_MODE_WB; - return rettype; + page = pfn_to_page(paddr >> PAGE_SHIFT); + return get_page_memtype(page); } spin_lock(&memtype_lock); @@ -623,13 +706,13 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size) u64 to = from + size; u64 cursor = from; - if (!pat_enabled) + if (!pat_enabled()) return 1; while (cursor < to) { if (!devmem_is_allowed(pfn)) { - printk(KERN_INFO "Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx], PAT prevents it\n", - current->comm, from, to - 1); + pr_info("x86/PAT: Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx], PAT prevents it\n", + current->comm, from, to - 1); return 0; } cursor += PAGE_SIZE; @@ -659,7 +742,7 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, * caching for the high addresses through the KEN pin, but * we maintain the tradition of paranoia in this code. */ - if (!pat_enabled && + if (!pat_enabled() && !(boot_cpu_has(X86_FEATURE_MTRR) || boot_cpu_has(X86_FEATURE_K6_MTRR) || boot_cpu_has(X86_FEATURE_CYRIX_ARR) || @@ -698,8 +781,7 @@ int kernel_map_sync_memtype(u64 base, unsigned long size, size; if (ioremap_change_attr((unsigned long)__va(base), id_sz, pcm) < 0) { - printk(KERN_INFO "%s:%d ioremap_change_attr failed %s " - "for [mem %#010Lx-%#010Lx]\n", + pr_info("x86/PAT: %s:%d ioremap_change_attr failed %s for [mem %#010Lx-%#010Lx]\n", current->comm, current->pid, cattr_name(pcm), base, (unsigned long long)(base + size-1)); @@ -729,12 +811,12 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, * the type requested matches the type of first page in the range. */ if (is_ram) { - if (!pat_enabled) + if (!pat_enabled()) return 0; pcm = lookup_memtype(paddr); if (want_pcm != pcm) { - printk(KERN_WARNING "%s:%d map pfn RAM range req %s for [mem %#010Lx-%#010Lx], got %s\n", + pr_warn("x86/PAT: %s:%d map pfn RAM range req %s for [mem %#010Lx-%#010Lx], got %s\n", current->comm, current->pid, cattr_name(want_pcm), (unsigned long long)paddr, @@ -755,13 +837,12 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, if (strict_prot || !is_new_memtype_allowed(paddr, size, want_pcm, pcm)) { free_memtype(paddr, paddr + size); - printk(KERN_ERR "%s:%d map pfn expected mapping type %s" - " for [mem %#010Lx-%#010Lx], got %s\n", - current->comm, current->pid, - cattr_name(want_pcm), - (unsigned long long)paddr, - (unsigned long long)(paddr + size - 1), - cattr_name(pcm)); + pr_err("x86/PAT: %s:%d map pfn expected mapping type %s for [mem %#010Lx-%#010Lx], got %s\n", + current->comm, current->pid, + cattr_name(want_pcm), + (unsigned long long)paddr, + (unsigned long long)(paddr + size - 1), + cattr_name(pcm)); return -EINVAL; } /* @@ -844,7 +925,7 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, return ret; } - if (!pat_enabled) + if (!pat_enabled()) return 0; /* @@ -872,7 +953,7 @@ int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, { enum page_cache_mode pcm; - if (!pat_enabled) + if (!pat_enabled()) return 0; /* Set prot based on lookup */ @@ -913,14 +994,18 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, pgprot_t pgprot_writecombine(pgprot_t prot) { - if (pat_enabled) - return __pgprot(pgprot_val(prot) | + return __pgprot(pgprot_val(prot) | cachemode2protval(_PAGE_CACHE_MODE_WC)); - else - return pgprot_noncached(prot); } EXPORT_SYMBOL_GPL(pgprot_writecombine); +pgprot_t pgprot_writethrough(pgprot_t prot) +{ + return __pgprot(pgprot_val(prot) | + cachemode2protval(_PAGE_CACHE_MODE_WT)); +} +EXPORT_SYMBOL_GPL(pgprot_writethrough); + #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT) static struct memtype *memtype_get_idx(loff_t pos) @@ -996,7 +1081,7 @@ static const struct file_operations memtype_fops = { static int __init pat_memtype_list_init(void) { - if (pat_enabled) { + if (pat_enabled()) { debugfs_create_file("pat_memtype_list", S_IRUSR, arch_debugfs_dir, NULL, &memtype_fops); } diff --git a/arch/x86/mm/pat_internal.h b/arch/x86/mm/pat_internal.h index f64116203..a739bfc40 100644 --- a/arch/x86/mm/pat_internal.h +++ b/arch/x86/mm/pat_internal.h @@ -4,7 +4,7 @@ extern int pat_debug_enable; #define dprintk(fmt, arg...) \ - do { if (pat_debug_enable) printk(KERN_INFO fmt, ##arg); } while (0) + do { if (pat_debug_enable) pr_info("x86/PAT: " fmt, ##arg); } while (0) struct memtype { u64 start; diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c index 6582adcc8..639310803 100644 --- a/arch/x86/mm/pat_rbtree.c +++ b/arch/x86/mm/pat_rbtree.c @@ -160,9 +160,9 @@ success: return 0; failure: - printk(KERN_INFO "%s:%d conflicting memory types " - "%Lx-%Lx %s<->%s\n", current->comm, current->pid, start, - end, cattr_name(found_type), cattr_name(match->type)); + pr_info("x86/PAT: %s:%d conflicting memory types %Lx-%Lx %s<->%s\n", + current->comm, current->pid, start, end, + cattr_name(found_type), cattr_name(match->type)); return -EBUSY; } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 0b97d2c75..fb0a9dd1d 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -563,16 +563,31 @@ void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys, } #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP +/** + * pud_set_huge - setup kernel PUD mapping + * + * MTRRs can override PAT memory types with 4KiB granularity. Therefore, this + * function sets up a huge page only if any of the following conditions are met: + * + * - MTRRs are disabled, or + * + * - MTRRs are enabled and the range is completely covered by a single MTRR, or + * + * - MTRRs are enabled and the corresponding MTRR memory type is WB, which + * has no effect on the requested PAT memory type. + * + * Callers should try to decrease page size (1GB -> 2MB -> 4K) if the bigger + * page mapping attempt fails. + * + * Returns 1 on success and 0 on failure. + */ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) { - u8 mtrr; + u8 mtrr, uniform; - /* - * Do not use a huge page when the range is covered by non-WB type - * of MTRRs. - */ - mtrr = mtrr_type_lookup(addr, addr + PUD_SIZE); - if ((mtrr != MTRR_TYPE_WRBACK) && (mtrr != 0xFF)) + mtrr = mtrr_type_lookup(addr, addr + PUD_SIZE, &uniform); + if ((mtrr != MTRR_TYPE_INVALID) && (!uniform) && + (mtrr != MTRR_TYPE_WRBACK)) return 0; prot = pgprot_4k_2_large(prot); @@ -584,17 +599,24 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) return 1; } +/** + * pmd_set_huge - setup kernel PMD mapping + * + * See text over pud_set_huge() above. + * + * Returns 1 on success and 0 on failure. + */ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) { - u8 mtrr; + u8 mtrr, uniform; - /* - * Do not use a huge page when the range is covered by non-WB type - * of MTRRs. - */ - mtrr = mtrr_type_lookup(addr, addr + PMD_SIZE); - if ((mtrr != MTRR_TYPE_WRBACK) && (mtrr != 0xFF)) + mtrr = mtrr_type_lookup(addr, addr + PMD_SIZE, &uniform); + if ((mtrr != MTRR_TYPE_INVALID) && (!uniform) && + (mtrr != MTRR_TYPE_WRBACK)) { + pr_warn_once("%s: Cannot satisfy [mem %#010llx-%#010llx] with a huge-page mapping due to MTRR override.\n", + __func__, addr, addr + PMD_SIZE); return 0; + } prot = pgprot_4k_2_large(prot); @@ -605,6 +627,11 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) return 1; } +/** + * pud_clear_huge - clear kernel PUD mapping when it is set + * + * Returns 1 on success and 0 on failure (no PUD map is found). + */ int pud_clear_huge(pud_t *pud) { if (pud_large(*pud)) { @@ -615,6 +642,11 @@ int pud_clear_huge(pud_t *pud) return 0; } +/** + * pmd_clear_huge - clear kernel PMD mapping when it is set + * + * Returns 1 on success and 0 on failure (no PMD map is found). + */ int pmd_clear_huge(pmd_t *pmd) { if (pmd_large(*pmd)) { diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S index 6440221ce..4093216b3 100644 --- a/arch/x86/net/bpf_jit.S +++ b/arch/x86/net/bpf_jit.S @@ -8,7 +8,6 @@ * of the License. */ #include <linux/linkage.h> -#include <asm/dwarf2.h> /* * Calling convention : diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index ddeff4844..be2e7a2b1 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -12,6 +12,7 @@ #include <linux/filter.h> #include <linux/if_vlan.h> #include <asm/cacheflush.h> +#include <linux/bpf.h> int bpf_jit_enable __read_mostly; @@ -37,7 +38,8 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) return ptr + len; } -#define EMIT(bytes, len) do { prog = emit_code(prog, bytes, len); } while (0) +#define EMIT(bytes, len) \ + do { prog = emit_code(prog, bytes, len); cnt += len; } while (0) #define EMIT1(b1) EMIT(b1, 1) #define EMIT2(b1, b2) EMIT((b1) + ((b2) << 8), 2) @@ -186,31 +188,31 @@ struct jit_context { #define BPF_MAX_INSN_SIZE 128 #define BPF_INSN_SAFETY 64 -static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, - int oldproglen, struct jit_context *ctx) +#define STACKSIZE \ + (MAX_BPF_STACK + \ + 32 /* space for rbx, r13, r14, r15 */ + \ + 8 /* space for skb_copy_bits() buffer */) + +#define PROLOGUE_SIZE 51 + +/* emit x64 prologue code for BPF program and check it's size. + * bpf_tail_call helper will skip it while jumping into another program + */ +static void emit_prologue(u8 **pprog) { - struct bpf_insn *insn = bpf_prog->insnsi; - int insn_cnt = bpf_prog->len; - bool seen_ld_abs = ctx->seen_ld_abs | (oldproglen == 0); - bool seen_exit = false; - u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY]; - int i; - int proglen = 0; - u8 *prog = temp; - int stacksize = MAX_BPF_STACK + - 32 /* space for rbx, r13, r14, r15 */ + - 8 /* space for skb_copy_bits() buffer */; + u8 *prog = *pprog; + int cnt = 0; EMIT1(0x55); /* push rbp */ EMIT3(0x48, 0x89, 0xE5); /* mov rbp,rsp */ - /* sub rsp, stacksize */ - EMIT3_off32(0x48, 0x81, 0xEC, stacksize); + /* sub rsp, STACKSIZE */ + EMIT3_off32(0x48, 0x81, 0xEC, STACKSIZE); /* all classic BPF filters use R6(rbx) save it */ /* mov qword ptr [rbp-X],rbx */ - EMIT3_off32(0x48, 0x89, 0x9D, -stacksize); + EMIT3_off32(0x48, 0x89, 0x9D, -STACKSIZE); /* bpf_convert_filter() maps classic BPF register X to R7 and uses R8 * as temporary, so all tcpdump filters need to spill/fill R7(r13) and @@ -221,16 +223,112 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, */ /* mov qword ptr [rbp-X],r13 */ - EMIT3_off32(0x4C, 0x89, 0xAD, -stacksize + 8); + EMIT3_off32(0x4C, 0x89, 0xAD, -STACKSIZE + 8); /* mov qword ptr [rbp-X],r14 */ - EMIT3_off32(0x4C, 0x89, 0xB5, -stacksize + 16); + EMIT3_off32(0x4C, 0x89, 0xB5, -STACKSIZE + 16); /* mov qword ptr [rbp-X],r15 */ - EMIT3_off32(0x4C, 0x89, 0xBD, -stacksize + 24); + EMIT3_off32(0x4C, 0x89, 0xBD, -STACKSIZE + 24); /* clear A and X registers */ EMIT2(0x31, 0xc0); /* xor eax, eax */ EMIT3(0x4D, 0x31, 0xED); /* xor r13, r13 */ + /* clear tail_cnt: mov qword ptr [rbp-X], rax */ + EMIT3_off32(0x48, 0x89, 0x85, -STACKSIZE + 32); + + BUILD_BUG_ON(cnt != PROLOGUE_SIZE); + *pprog = prog; +} + +/* generate the following code: + * ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ... + * if (index >= array->map.max_entries) + * goto out; + * if (++tail_call_cnt > MAX_TAIL_CALL_CNT) + * goto out; + * prog = array->prog[index]; + * if (prog == NULL) + * goto out; + * goto *(prog->bpf_func + prologue_size); + * out: + */ +static void emit_bpf_tail_call(u8 **pprog) +{ + u8 *prog = *pprog; + int label1, label2, label3; + int cnt = 0; + + /* rdi - pointer to ctx + * rsi - pointer to bpf_array + * rdx - index in bpf_array + */ + + /* if (index >= array->map.max_entries) + * goto out; + */ + EMIT4(0x48, 0x8B, 0x46, /* mov rax, qword ptr [rsi + 16] */ + offsetof(struct bpf_array, map.max_entries)); + EMIT3(0x48, 0x39, 0xD0); /* cmp rax, rdx */ +#define OFFSET1 47 /* number of bytes to jump */ + EMIT2(X86_JBE, OFFSET1); /* jbe out */ + label1 = cnt; + + /* if (tail_call_cnt > MAX_TAIL_CALL_CNT) + * goto out; + */ + EMIT2_off32(0x8B, 0x85, -STACKSIZE + 36); /* mov eax, dword ptr [rbp - 516] */ + EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ +#define OFFSET2 36 + EMIT2(X86_JA, OFFSET2); /* ja out */ + label2 = cnt; + EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ + EMIT2_off32(0x89, 0x85, -STACKSIZE + 36); /* mov dword ptr [rbp - 516], eax */ + + /* prog = array->prog[index]; */ + EMIT4_off32(0x48, 0x8D, 0x84, 0xD6, /* lea rax, [rsi + rdx * 8 + offsetof(...)] */ + offsetof(struct bpf_array, prog)); + EMIT3(0x48, 0x8B, 0x00); /* mov rax, qword ptr [rax] */ + + /* if (prog == NULL) + * goto out; + */ + EMIT4(0x48, 0x83, 0xF8, 0x00); /* cmp rax, 0 */ +#define OFFSET3 10 + EMIT2(X86_JE, OFFSET3); /* je out */ + label3 = cnt; + + /* goto *(prog->bpf_func + prologue_size); */ + EMIT4(0x48, 0x8B, 0x40, /* mov rax, qword ptr [rax + 32] */ + offsetof(struct bpf_prog, bpf_func)); + EMIT4(0x48, 0x83, 0xC0, PROLOGUE_SIZE); /* add rax, prologue_size */ + + /* now we're ready to jump into next BPF program + * rdi == ctx (1st arg) + * rax == prog->bpf_func + prologue_size + */ + EMIT2(0xFF, 0xE0); /* jmp rax */ + + /* out: */ + BUILD_BUG_ON(cnt - label1 != OFFSET1); + BUILD_BUG_ON(cnt - label2 != OFFSET2); + BUILD_BUG_ON(cnt - label3 != OFFSET3); + *pprog = prog; +} + +static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, + int oldproglen, struct jit_context *ctx) +{ + struct bpf_insn *insn = bpf_prog->insnsi; + int insn_cnt = bpf_prog->len; + bool seen_ld_abs = ctx->seen_ld_abs | (oldproglen == 0); + bool seen_exit = false; + u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY]; + int i, cnt = 0; + int proglen = 0; + u8 *prog = temp; + + emit_prologue(&prog); + if (seen_ld_abs) { /* r9d : skb->len - skb->data_len (headlen) * r10 : skb->data @@ -739,6 +837,10 @@ xadd: if (is_imm8(insn->off)) } break; + case BPF_JMP | BPF_CALL | BPF_X: + emit_bpf_tail_call(&prog); + break; + /* cond jump */ case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JNE | BPF_X: @@ -891,13 +993,13 @@ common_load: /* update cleanup_addr */ ctx->cleanup_addr = proglen; /* mov rbx, qword ptr [rbp-X] */ - EMIT3_off32(0x48, 0x8B, 0x9D, -stacksize); + EMIT3_off32(0x48, 0x8B, 0x9D, -STACKSIZE); /* mov r13, qword ptr [rbp-X] */ - EMIT3_off32(0x4C, 0x8B, 0xAD, -stacksize + 8); + EMIT3_off32(0x4C, 0x8B, 0xAD, -STACKSIZE + 8); /* mov r14, qword ptr [rbp-X] */ - EMIT3_off32(0x4C, 0x8B, 0xB5, -stacksize + 16); + EMIT3_off32(0x4C, 0x8B, 0xB5, -STACKSIZE + 16); /* mov r15, qword ptr [rbp-X] */ - EMIT3_off32(0x4C, 0x8B, 0xBD, -stacksize + 24); + EMIT3_off32(0x4C, 0x8B, 0xBD, -STACKSIZE + 24); EMIT1(0xC9); /* leave */ EMIT1(0xC3); /* ret */ diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 349c0d32c..0a9f2caf3 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -429,12 +429,12 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, * Caller can followup with UC MINUS request and add a WC mtrr if there * is a free mtrr slot. */ - if (!pat_enabled && write_combine) + if (!pat_enabled() && write_combine) return -EINVAL; - if (pat_enabled && write_combine) + if (pat_enabled() && write_combine) prot |= cachemode2protval(_PAGE_CACHE_MODE_WC); - else if (pat_enabled || boot_cpu_data.x86 > 3) + else if (pat_enabled() || boot_cpu_data.x86 > 3) /* * ioremap() and ioremap_nocache() defaults to UC MINUS for now. * To avoid attribute conflicts, request UC MINUS here diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 852aa4c92..27062303c 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -208,6 +208,7 @@ static int pci_write(struct pci_bus *bus, unsigned int devfn, int where, static int intel_mid_pci_irq_enable(struct pci_dev *dev) { + struct irq_alloc_info info; int polarity; if (dev->irq_managed && dev->irq > 0) @@ -217,14 +218,13 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) polarity = 0; /* active high */ else polarity = 1; /* active low */ + ioapic_set_alloc_attr(&info, dev_to_node(&dev->dev), 1, polarity); /* * MRST only have IOAPIC, the PCI irq lines are 1:1 mapped to * IOAPIC RTE entries, so we just enable RTE for the device. */ - if (mp_set_gsi_attr(dev->irq, 1, polarity, dev_to_node(&dev->dev))) - return -EBUSY; - if (mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC) < 0) + if (mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC, &info) < 0) return -EBUSY; dev->irq_managed = 1; diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 5dc6ca5e1..9bd115484 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -146,19 +146,20 @@ static void __init pirq_peer_trick(void) /* * Code for querying and setting of IRQ routes on various interrupt routers. + * PIC Edge/Level Control Registers (ELCR) 0x4d0 & 0x4d1. */ -void eisa_set_level_irq(unsigned int irq) +void elcr_set_level_irq(unsigned int irq) { unsigned char mask = 1 << (irq & 7); unsigned int port = 0x4d0 + (irq >> 3); unsigned char val; - static u16 eisa_irq_mask; + static u16 elcr_irq_mask; - if (irq >= 16 || (1 << irq) & eisa_irq_mask) + if (irq >= 16 || (1 << irq) & elcr_irq_mask) return; - eisa_irq_mask |= (1 << irq); + elcr_irq_mask |= (1 << irq); printk(KERN_DEBUG "PCI: setting IRQ %u as level-triggered\n", irq); val = inb(port); if (!(val & mask)) { @@ -965,11 +966,11 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) } else if (r->get && (irq = r->get(pirq_router_dev, dev, pirq)) && \ ((!(pci_probe & PCI_USE_PIRQ_MASK)) || ((1 << irq) & mask))) { msg = "found"; - eisa_set_level_irq(irq); + elcr_set_level_irq(irq); } else if (newirq && r->set && (dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) { if (r->set(pirq_router_dev, dev, pirq, newirq)) { - eisa_set_level_irq(newirq); + elcr_set_level_irq(newirq); msg = "assigned"; irq = newirq; } diff --git a/arch/x86/platform/Makefile b/arch/x86/platform/Makefile index a62e0be3a..f1a6c8e86 100644 --- a/arch/x86/platform/Makefile +++ b/arch/x86/platform/Makefile @@ -1,4 +1,5 @@ # Platform specific code goes here +obj-y += atom/ obj-y += ce4100/ obj-y += efi/ obj-y += geode/ diff --git a/arch/x86/platform/atom/Makefile b/arch/x86/platform/atom/Makefile new file mode 100644 index 000000000..0a3a40cbc --- /dev/null +++ b/arch/x86/platform/atom/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_PUNIT_ATOM_DEBUG) += punit_atom_debug.o diff --git a/arch/x86/platform/atom/punit_atom_debug.c b/arch/x86/platform/atom/punit_atom_debug.c new file mode 100644 index 000000000..5ca8ead91 --- /dev/null +++ b/arch/x86/platform/atom/punit_atom_debug.c @@ -0,0 +1,183 @@ +/* + * Intel SOC Punit device state debug driver + * Punit controls power management for North Complex devices (Graphics + * blocks, Image Signal Processing, video processing, display, DSP etc.) + * + * Copyright (c) 2015, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/device.h> +#include <linux/debugfs.h> +#include <linux/seq_file.h> +#include <linux/io.h> +#include <asm/cpu_device_id.h> +#include <asm/iosf_mbi.h> + +/* Side band Interface port */ +#define PUNIT_PORT 0x04 +/* Power gate status reg */ +#define PWRGT_STATUS 0x61 +/* Subsystem config/status Video processor */ +#define VED_SS_PM0 0x32 +/* Subsystem config/status ISP (Image Signal Processor) */ +#define ISP_SS_PM0 0x39 +/* Subsystem config/status Input/output controller */ +#define MIO_SS_PM 0x3B +/* Shift bits for getting status for video, isp and i/o */ +#define SSS_SHIFT 24 +/* Shift bits for getting status for graphics rendering */ +#define RENDER_POS 0 +/* Shift bits for getting status for media control */ +#define MEDIA_POS 2 +/* Shift bits for getting status for Valley View/Baytrail display */ +#define VLV_DISPLAY_POS 6 +/* Subsystem config/status display for Cherry Trail SOC */ +#define CHT_DSP_SSS 0x36 +/* Shift bits for getting status for display */ +#define CHT_DSP_SSS_POS 16 + +struct punit_device { + char *name; + int reg; + int sss_pos; +}; + +static const struct punit_device punit_device_byt[] = { + { "GFX RENDER", PWRGT_STATUS, RENDER_POS }, + { "GFX MEDIA", PWRGT_STATUS, MEDIA_POS }, + { "DISPLAY", PWRGT_STATUS, VLV_DISPLAY_POS }, + { "VED", VED_SS_PM0, SSS_SHIFT }, + { "ISP", ISP_SS_PM0, SSS_SHIFT }, + { "MIO", MIO_SS_PM, SSS_SHIFT }, + { NULL } +}; + +static const struct punit_device punit_device_cht[] = { + { "GFX RENDER", PWRGT_STATUS, RENDER_POS }, + { "GFX MEDIA", PWRGT_STATUS, MEDIA_POS }, + { "DISPLAY", CHT_DSP_SSS, CHT_DSP_SSS_POS }, + { "VED", VED_SS_PM0, SSS_SHIFT }, + { "ISP", ISP_SS_PM0, SSS_SHIFT }, + { "MIO", MIO_SS_PM, SSS_SHIFT }, + { NULL } +}; + +static const char * const dstates[] = {"D0", "D0i1", "D0i2", "D0i3"}; + +static int punit_dev_state_show(struct seq_file *seq_file, void *unused) +{ + u32 punit_pwr_status; + struct punit_device *punit_devp = seq_file->private; + int index; + int status; + + seq_puts(seq_file, "\n\nPUNIT NORTH COMPLEX DEVICES :\n"); + while (punit_devp->name) { + status = iosf_mbi_read(PUNIT_PORT, BT_MBI_PMC_READ, + punit_devp->reg, + &punit_pwr_status); + if (status) { + seq_printf(seq_file, "%9s : Read Failed\n", + punit_devp->name); + } else { + index = (punit_pwr_status >> punit_devp->sss_pos) & 3; + seq_printf(seq_file, "%9s : %s\n", punit_devp->name, + dstates[index]); + } + punit_devp++; + } + + return 0; +} + +static int punit_dev_state_open(struct inode *inode, struct file *file) +{ + return single_open(file, punit_dev_state_show, inode->i_private); +} + +static const struct file_operations punit_dev_state_ops = { + .open = punit_dev_state_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static struct dentry *punit_dbg_file; + +static int punit_dbgfs_register(struct punit_device *punit_device) +{ + static struct dentry *dev_state; + + punit_dbg_file = debugfs_create_dir("punit_atom", NULL); + if (!punit_dbg_file) + return -ENXIO; + + dev_state = debugfs_create_file("dev_power_state", S_IFREG | S_IRUGO, + punit_dbg_file, punit_device, + &punit_dev_state_ops); + if (!dev_state) { + pr_err("punit_dev_state register failed\n"); + debugfs_remove(punit_dbg_file); + return -ENXIO; + } + + return 0; +} + +static void punit_dbgfs_unregister(void) +{ + debugfs_remove_recursive(punit_dbg_file); +} + +#define ICPU(model, drv_data) \ + { X86_VENDOR_INTEL, 6, model, X86_FEATURE_MWAIT,\ + (kernel_ulong_t)&drv_data } + +static const struct x86_cpu_id intel_punit_cpu_ids[] = { + ICPU(55, punit_device_byt), /* Valleyview, Bay Trail */ + ICPU(76, punit_device_cht), /* Braswell, Cherry Trail */ + {} +}; + +MODULE_DEVICE_TABLE(x86cpu, intel_punit_cpu_ids); + +static int __init punit_atom_debug_init(void) +{ + const struct x86_cpu_id *id; + int ret; + + id = x86_match_cpu(intel_punit_cpu_ids); + if (!id) + return -ENODEV; + + ret = punit_dbgfs_register((struct punit_device *)id->driver_data); + if (ret < 0) + return ret; + + return 0; +} + +static void __exit punit_atom_debug_exit(void) +{ + punit_dbgfs_unregister(); +} + +module_init(punit_atom_debug_init); +module_exit(punit_atom_debug_exit); + +MODULE_AUTHOR("Kumar P, Mahesh <mahesh.kumar.p@intel.com>"); +MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>"); +MODULE_DESCRIPTION("Driver for Punit devices states debugging"); +MODULE_LICENSE("GPL v2"); diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 841ea05e1..e4308fe6a 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -117,6 +117,27 @@ void efi_get_time(struct timespec *now) now->tv_nsec = 0; } +void __init efi_find_mirror(void) +{ + void *p; + u64 mirror_size = 0, total_size = 0; + + for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { + efi_memory_desc_t *md = p; + unsigned long long start = md->phys_addr; + unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; + + total_size += size; + if (md->attribute & EFI_MEMORY_MORE_RELIABLE) { + memblock_mark_mirror(start, size); + mirror_size += size; + } + } + if (mirror_size) + pr_info("Memory: %lldM/%lldM mirrored memory\n", + mirror_size>>20, total_size>>20); +} + /* * Tell the kernel about the EFI memory map. This might include * more than the max 128 entries that can fit in the e820 legacy @@ -153,6 +174,9 @@ static void __init do_add_efi_memmap(void) case EFI_UNUSABLE_MEMORY: e820_type = E820_UNUSABLE; break; + case EFI_PERSISTENT_MEMORY: + e820_type = E820_PMEM; + break; default: /* * EFI_RESERVED_TYPE EFI_RUNTIME_SERVICES_CODE @@ -501,6 +525,8 @@ void __init efi_init(void) if (efi_enabled(EFI_DBG)) print_efi_memmap(); + + efi_esrt_init(); } void __init efi_late_init(void) diff --git a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c index 0b283d4d0..de734134b 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c @@ -27,6 +27,7 @@ static struct platform_device wdt_dev = { static int tangier_probe(struct platform_device *pdev) { int gsi; + struct irq_alloc_info info; struct intel_mid_wdt_pdata *pdata = pdev->dev.platform_data; if (!pdata) @@ -34,8 +35,8 @@ static int tangier_probe(struct platform_device *pdev) /* IOAPIC builds identity mapping between GSI and IRQ on MID */ gsi = pdata->irq; - if (mp_set_gsi_attr(gsi, 1, 0, cpu_to_node(0)) || - mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC) <= 0) { + ioapic_set_alloc_attr(&info, cpu_to_node(0), 1, 0); + if (mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info) <= 0) { dev_warn(&pdev->dev, "cannot find interrupt %d in ioapic\n", gsi); return -EINVAL; diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c index 3005f0c89..01d54ea76 100644 --- a/arch/x86/platform/intel-mid/intel-mid.c +++ b/arch/x86/platform/intel-mid/intel-mid.c @@ -81,26 +81,34 @@ static unsigned long __init intel_mid_calibrate_tsc(void) return 0; } +static void __init intel_mid_setup_bp_timer(void) +{ + apbt_time_init(); + setup_boot_APIC_clock(); +} + static void __init intel_mid_time_init(void) { sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr); + switch (intel_mid_timer_options) { case INTEL_MID_TIMER_APBT_ONLY: break; case INTEL_MID_TIMER_LAPIC_APBT: - x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock; + /* Use apbt and local apic */ + x86_init.timers.setup_percpu_clockev = intel_mid_setup_bp_timer; x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock; - break; + return; default: if (!boot_cpu_has(X86_FEATURE_ARAT)) break; + /* Lapic only, no apbt */ x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock; x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock; return; } - /* we need at least one APB timer */ - pre_init_apic_IRQ0(); - apbt_time_init(); + + x86_init.timers.setup_percpu_clockev = apbt_time_init; } static void intel_mid_arch_setup(void) diff --git a/arch/x86/platform/intel-mid/intel_mid_vrtc.c b/arch/x86/platform/intel-mid/intel_mid_vrtc.c index 32947ba0f..ee40fcb6e 100644 --- a/arch/x86/platform/intel-mid/intel_mid_vrtc.c +++ b/arch/x86/platform/intel-mid/intel_mid_vrtc.c @@ -173,5 +173,4 @@ static int __init intel_mid_device_create(void) return platform_device_register(&vrtc_device); } - -module_init(intel_mid_device_create); +device_initcall(intel_mid_device_create); diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c index c14ad3477..ce992e8cc 100644 --- a/arch/x86/platform/intel-mid/sfi.c +++ b/arch/x86/platform/intel-mid/sfi.c @@ -95,18 +95,16 @@ int __init sfi_parse_mtmr(struct sfi_table_header *table) pr_debug("timer[%d]: paddr = 0x%08x, freq = %dHz, irq = %d\n", totallen, (u32)pentry->phys_addr, pentry->freq_hz, pentry->irq); - if (!pentry->irq) - continue; - mp_irq.type = MP_INTSRC; - mp_irq.irqtype = mp_INT; -/* triggering mode edge bit 2-3, active high polarity bit 0-1 */ - mp_irq.irqflag = 5; - mp_irq.srcbus = MP_BUS_ISA; - mp_irq.srcbusirq = pentry->irq; /* IRQ */ - mp_irq.dstapic = MP_APIC_ALL; - mp_irq.dstirq = pentry->irq; - mp_save_irq(&mp_irq); - mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC); + mp_irq.type = MP_INTSRC; + mp_irq.irqtype = mp_INT; + /* triggering mode edge bit 2-3, active high polarity bit 0-1 */ + mp_irq.irqflag = 5; + mp_irq.srcbus = MP_BUS_ISA; + mp_irq.srcbusirq = pentry->irq; /* IRQ */ + mp_irq.dstapic = MP_APIC_ALL; + mp_irq.dstirq = pentry->irq; + mp_save_irq(&mp_irq); + mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC, NULL); } return 0; @@ -177,7 +175,7 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table) mp_irq.dstapic = MP_APIC_ALL; mp_irq.dstirq = pentry->irq; mp_save_irq(&mp_irq); - mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC); + mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC, NULL); } return 0; } @@ -436,6 +434,7 @@ static int __init sfi_parse_devs(struct sfi_table_header *table) struct devs_id *dev = NULL; int num, i, ret; int polarity; + struct irq_alloc_info info; sb = (struct sfi_table_simple *)table; num = SFI_GET_NUM_ENTRIES(sb, struct sfi_device_table_entry); @@ -469,9 +468,8 @@ static int __init sfi_parse_devs(struct sfi_table_header *table) polarity = 1; } - ret = mp_set_gsi_attr(irq, 1, polarity, NUMA_NO_NODE); - if (ret == 0) - ret = mp_map_gsi_to_irq(irq, IOAPIC_MAP_ALLOC); + ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 1, polarity); + ret = mp_map_gsi_to_irq(irq, IOAPIC_MAP_ALLOC, &info); WARN_ON(ret < 0); } diff --git a/arch/x86/platform/sfi/sfi.c b/arch/x86/platform/sfi/sfi.c index 2a8a74f3b..6c7111bbd 100644 --- a/arch/x86/platform/sfi/sfi.c +++ b/arch/x86/platform/sfi/sfi.c @@ -25,8 +25,8 @@ #include <linux/init.h> #include <linux/sfi.h> #include <linux/io.h> -#include <linux/irqdomain.h> +#include <asm/irqdomain.h> #include <asm/io_apic.h> #include <asm/mpspec.h> #include <asm/setup.h> @@ -71,9 +71,6 @@ static int __init sfi_parse_cpus(struct sfi_table_header *table) #endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_IO_APIC -static struct irq_domain_ops sfi_ioapic_irqdomain_ops = { - .map = mp_irqdomain_map, -}; static int __init sfi_parse_ioapic(struct sfi_table_header *table) { @@ -82,7 +79,7 @@ static int __init sfi_parse_ioapic(struct sfi_table_header *table) int i, num; struct ioapic_domain_cfg cfg = { .type = IOAPIC_DOMAIN_STRICT, - .ops = &sfi_ioapic_irqdomain_ops, + .ops = &mp_ioapic_irqdomain_ops, }; sb = (struct sfi_table_simple *)table; diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c index 0ce673645..8570abe68 100644 --- a/arch/x86/platform/uv/uv_irq.c +++ b/arch/x86/platform/uv/uv_irq.c @@ -13,22 +13,37 @@ #include <linux/slab.h> #include <linux/irq.h> +#include <asm/irqdomain.h> #include <asm/apic.h> #include <asm/uv/uv_irq.h> #include <asm/uv/uv_hub.h> /* MMR offset and pnode of hub sourcing interrupts for a given irq */ -struct uv_irq_2_mmr_pnode{ - struct rb_node list; +struct uv_irq_2_mmr_pnode { unsigned long offset; int pnode; - int irq; }; -static DEFINE_SPINLOCK(uv_irq_lock); -static struct rb_root uv_irq_root; +static void uv_program_mmr(struct irq_cfg *cfg, struct uv_irq_2_mmr_pnode *info) +{ + unsigned long mmr_value; + struct uv_IO_APIC_route_entry *entry; + + BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != + sizeof(unsigned long)); + + mmr_value = 0; + entry = (struct uv_IO_APIC_route_entry *)&mmr_value; + entry->vector = cfg->vector; + entry->delivery_mode = apic->irq_delivery_mode; + entry->dest_mode = apic->irq_dest_mode; + entry->polarity = 0; + entry->trigger = 0; + entry->mask = 0; + entry->dest = cfg->dest_apicid; -static int uv_set_irq_affinity(struct irq_data *, const struct cpumask *, bool); + uv_write_global_mmr64(info->pnode, info->offset, mmr_value); +} static void uv_noop(struct irq_data *data) { } @@ -37,6 +52,23 @@ static void uv_ack_apic(struct irq_data *data) ack_APIC_irq(); } +static int +uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask, + bool force) +{ + struct irq_data *parent = data->parent_data; + struct irq_cfg *cfg = irqd_cfg(data); + int ret; + + ret = parent->chip->irq_set_affinity(parent, mask, force); + if (ret >= 0) { + uv_program_mmr(cfg, data->chip_data); + send_cleanup_vector(cfg); + } + + return ret; +} + static struct irq_chip uv_irq_chip = { .name = "UV-CORE", .irq_mask = uv_noop, @@ -45,189 +77,99 @@ static struct irq_chip uv_irq_chip = { .irq_set_affinity = uv_set_irq_affinity, }; -/* - * Add offset and pnode information of the hub sourcing interrupts to the - * rb tree for a specific irq. - */ -static int uv_set_irq_2_mmr_info(int irq, unsigned long offset, unsigned blade) +static int uv_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) { - struct rb_node **link = &uv_irq_root.rb_node; - struct rb_node *parent = NULL; - struct uv_irq_2_mmr_pnode *n; - struct uv_irq_2_mmr_pnode *e; - unsigned long irqflags; - - n = kmalloc_node(sizeof(struct uv_irq_2_mmr_pnode), GFP_KERNEL, - uv_blade_to_memory_nid(blade)); - if (!n) + struct uv_irq_2_mmr_pnode *chip_data; + struct irq_alloc_info *info = arg; + struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq); + int ret; + + if (nr_irqs > 1 || !info || info->type != X86_IRQ_ALLOC_TYPE_UV) + return -EINVAL; + + chip_data = kmalloc_node(sizeof(*chip_data), GFP_KERNEL, + irq_data->node); + if (!chip_data) return -ENOMEM; - n->irq = irq; - n->offset = offset; - n->pnode = uv_blade_to_pnode(blade); - spin_lock_irqsave(&uv_irq_lock, irqflags); - /* Find the right place in the rbtree: */ - while (*link) { - parent = *link; - e = rb_entry(parent, struct uv_irq_2_mmr_pnode, list); - - if (unlikely(irq == e->irq)) { - /* irq entry exists */ - e->pnode = uv_blade_to_pnode(blade); - e->offset = offset; - spin_unlock_irqrestore(&uv_irq_lock, irqflags); - kfree(n); - return 0; - } - - if (irq < e->irq) - link = &(*link)->rb_left; + ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg); + if (ret >= 0) { + if (info->uv_limit == UV_AFFINITY_CPU) + irq_set_status_flags(virq, IRQ_NO_BALANCING); else - link = &(*link)->rb_right; + irq_set_status_flags(virq, IRQ_MOVE_PCNTXT); + + chip_data->pnode = uv_blade_to_pnode(info->uv_blade); + chip_data->offset = info->uv_offset; + irq_domain_set_info(domain, virq, virq, &uv_irq_chip, chip_data, + handle_percpu_irq, NULL, info->uv_name); + } else { + kfree(chip_data); } - /* Insert the node into the rbtree. */ - rb_link_node(&n->list, parent, link); - rb_insert_color(&n->list, &uv_irq_root); - - spin_unlock_irqrestore(&uv_irq_lock, irqflags); - return 0; + return ret; } -/* Retrieve offset and pnode information from the rb tree for a specific irq */ -int uv_irq_2_mmr_info(int irq, unsigned long *offset, int *pnode) +static void uv_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) { - struct uv_irq_2_mmr_pnode *e; - struct rb_node *n; - unsigned long irqflags; - - spin_lock_irqsave(&uv_irq_lock, irqflags); - n = uv_irq_root.rb_node; - while (n) { - e = rb_entry(n, struct uv_irq_2_mmr_pnode, list); - - if (e->irq == irq) { - *offset = e->offset; - *pnode = e->pnode; - spin_unlock_irqrestore(&uv_irq_lock, irqflags); - return 0; - } - - if (irq < e->irq) - n = n->rb_left; - else - n = n->rb_right; - } - spin_unlock_irqrestore(&uv_irq_lock, irqflags); - return -1; + struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq); + + BUG_ON(nr_irqs != 1); + kfree(irq_data->chip_data); + irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT); + irq_clear_status_flags(virq, IRQ_NO_BALANCING); + irq_domain_free_irqs_top(domain, virq, nr_irqs); } /* * Re-target the irq to the specified CPU and enable the specified MMR located * on the specified blade to allow the sending of MSIs to the specified CPU. */ -static int -arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade, - unsigned long mmr_offset, int limit) +static void uv_domain_activate(struct irq_domain *domain, + struct irq_data *irq_data) { - const struct cpumask *eligible_cpu = cpumask_of(cpu); - struct irq_cfg *cfg = irq_cfg(irq); - unsigned long mmr_value; - struct uv_IO_APIC_route_entry *entry; - int mmr_pnode, err; - unsigned int dest; - - BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != - sizeof(unsigned long)); - - err = assign_irq_vector(irq, cfg, eligible_cpu); - if (err != 0) - return err; - - err = apic->cpu_mask_to_apicid_and(eligible_cpu, eligible_cpu, &dest); - if (err != 0) - return err; - - if (limit == UV_AFFINITY_CPU) - irq_set_status_flags(irq, IRQ_NO_BALANCING); - else - irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - - irq_set_chip_and_handler_name(irq, &uv_irq_chip, handle_percpu_irq, - irq_name); - - mmr_value = 0; - entry = (struct uv_IO_APIC_route_entry *)&mmr_value; - entry->vector = cfg->vector; - entry->delivery_mode = apic->irq_delivery_mode; - entry->dest_mode = apic->irq_dest_mode; - entry->polarity = 0; - entry->trigger = 0; - entry->mask = 0; - entry->dest = dest; - - mmr_pnode = uv_blade_to_pnode(mmr_blade); - uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value); - - if (cfg->move_in_progress) - send_cleanup_vector(cfg); - - return irq; + uv_program_mmr(irqd_cfg(irq_data), irq_data->chip_data); } /* * Disable the specified MMR located on the specified blade so that MSIs are * longer allowed to be sent. */ -static void arch_disable_uv_irq(int mmr_pnode, unsigned long mmr_offset) +static void uv_domain_deactivate(struct irq_domain *domain, + struct irq_data *irq_data) { unsigned long mmr_value; struct uv_IO_APIC_route_entry *entry; - BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != - sizeof(unsigned long)); - mmr_value = 0; entry = (struct uv_IO_APIC_route_entry *)&mmr_value; entry->mask = 1; - - uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value); + uv_program_mmr(irqd_cfg(irq_data), irq_data->chip_data); } -static int -uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask, - bool force) -{ - struct irq_cfg *cfg = irqd_cfg(data); - unsigned int dest; - unsigned long mmr_value, mmr_offset; - struct uv_IO_APIC_route_entry *entry; - int mmr_pnode; - - if (apic_set_affinity(data, mask, &dest)) - return -1; - - mmr_value = 0; - entry = (struct uv_IO_APIC_route_entry *)&mmr_value; - - entry->vector = cfg->vector; - entry->delivery_mode = apic->irq_delivery_mode; - entry->dest_mode = apic->irq_dest_mode; - entry->polarity = 0; - entry->trigger = 0; - entry->mask = 0; - entry->dest = dest; - - /* Get previously stored MMR and pnode of hub sourcing interrupts */ - if (uv_irq_2_mmr_info(data->irq, &mmr_offset, &mmr_pnode)) - return -1; - - uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value); +static const struct irq_domain_ops uv_domain_ops = { + .alloc = uv_domain_alloc, + .free = uv_domain_free, + .activate = uv_domain_activate, + .deactivate = uv_domain_deactivate, +}; - if (cfg->move_in_progress) - send_cleanup_vector(cfg); +static struct irq_domain *uv_get_irq_domain(void) +{ + static struct irq_domain *uv_domain; + static DEFINE_MUTEX(uv_lock); + + mutex_lock(&uv_lock); + if (uv_domain == NULL) { + uv_domain = irq_domain_add_tree(NULL, &uv_domain_ops, NULL); + if (uv_domain) + uv_domain->parent = x86_vector_domain; + } + mutex_unlock(&uv_lock); - return IRQ_SET_MASK_OK_NOCOPY; + return uv_domain; } /* @@ -238,19 +180,21 @@ uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask, int uv_setup_irq(char *irq_name, int cpu, int mmr_blade, unsigned long mmr_offset, int limit) { - int ret, irq = irq_alloc_hwirq(uv_blade_to_memory_nid(mmr_blade)); + struct irq_alloc_info info; + struct irq_domain *domain = uv_get_irq_domain(); - if (!irq) - return -EBUSY; + if (!domain) + return -ENOMEM; - ret = arch_enable_uv_irq(irq_name, irq, cpu, mmr_blade, mmr_offset, - limit); - if (ret == irq) - uv_set_irq_2_mmr_info(irq, mmr_offset, mmr_blade); - else - irq_free_hwirq(irq); + init_irq_alloc_info(&info, cpumask_of(cpu)); + info.type = X86_IRQ_ALLOC_TYPE_UV; + info.uv_limit = limit; + info.uv_blade = mmr_blade; + info.uv_offset = mmr_offset; + info.uv_name = irq_name; - return ret; + return irq_domain_alloc_irqs(domain, 1, + uv_blade_to_memory_nid(mmr_blade), &info); } EXPORT_SYMBOL_GPL(uv_setup_irq); @@ -263,26 +207,6 @@ EXPORT_SYMBOL_GPL(uv_setup_irq); */ void uv_teardown_irq(unsigned int irq) { - struct uv_irq_2_mmr_pnode *e; - struct rb_node *n; - unsigned long irqflags; - - spin_lock_irqsave(&uv_irq_lock, irqflags); - n = uv_irq_root.rb_node; - while (n) { - e = rb_entry(n, struct uv_irq_2_mmr_pnode, list); - if (e->irq == irq) { - arch_disable_uv_irq(e->pnode, e->offset); - rb_erase(n, &uv_irq_root); - kfree(e); - break; - } - if (irq < e->irq) - n = n->rb_left; - else - n = n->rb_right; - } - spin_unlock_irqrestore(&uv_irq_lock, irqflags); - irq_free_hwirq(irq); + irq_domain_free_irqs(irq, 1); } EXPORT_SYMBOL_GPL(uv_teardown_irq); diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index 7488cafab..020c101c2 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -104,7 +104,7 @@ static int param_set_local64(const char *val, const struct kernel_param *kp) return 0; } -static struct kernel_param_ops param_ops_local64 = { +static const struct kernel_param_ops param_ops_local64 = { .get = param_get_local64, .set = param_set_local64, }; diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 757678fb2..9ab52791f 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -18,11 +18,11 @@ #include <asm/mtrr.h> #include <asm/page.h> #include <asm/mce.h> -#include <asm/xcr.h> #include <asm/suspend.h> +#include <asm/fpu/internal.h> #include <asm/debugreg.h> -#include <asm/fpu-internal.h> /* pcntxt_mask */ #include <asm/cpu.h> +#include <asm/mmu_context.h> #ifdef CONFIG_X86_32 __visible unsigned long saved_context_ebx; @@ -154,7 +154,9 @@ static void fix_processor_context(void) syscall_init(); /* This sets MSR_*STAR and related */ #endif load_TR_desc(); /* This does ltr */ - load_LDT(¤t->active_mm->context); /* This does lldt */ + load_mm_ldt(current->active_mm); /* This does lldt */ + + fpu__resume_cpu(); } /** @@ -221,12 +223,6 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) wrmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base); #endif - /* - * restore XCR0 for xsave capable cpu's. - */ - if (cpu_has_xsave) - xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask); - fix_processor_context(); do_fpu_end(); diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S index 3c4469a7a..e2386cb4e 100644 --- a/arch/x86/power/hibernate_asm_64.S +++ b/arch/x86/power/hibernate_asm_64.S @@ -78,9 +78,9 @@ ENTRY(restore_image) /* code below has been relocated to a safe page */ ENTRY(core_restore_code) -loop: +.Lloop: testq %rdx, %rdx - jz done + jz .Ldone /* get addresses from the pbe and copy the page */ movq pbe_address(%rdx), %rsi @@ -91,8 +91,8 @@ loop: /* progress to the next pbe */ movq pbe_next(%rdx), %rdx - jmp loop -done: + jmp .Lloop +.Ldone: /* jump to the restore_registers address from the image header */ jmpq *%rax /* diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile index acb384d24..a8fecc226 100644 --- a/arch/x86/um/Makefile +++ b/arch/x86/um/Makefile @@ -26,7 +26,7 @@ else obj-y += syscalls_64.o vdso/ -subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../lib/thunk_64.o \ +subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../entry/thunk_64.o \ ../lib/rwsem.o endif diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h index 7e8a1a650..b9531d343 100644 --- a/arch/x86/um/asm/barrier.h +++ b/arch/x86/um/asm/barrier.h @@ -39,7 +39,8 @@ #define smp_mb() barrier() #define smp_rmb() barrier() #define smp_wmb() barrier() -#define set_mb(var, value) do { var = value; barrier(); } while (0) + +#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); barrier(); } while (0) #define read_barrier_depends() do { } while (0) #define smp_read_barrier_depends() do { } while (0) diff --git a/arch/x86/um/asm/checksum.h b/arch/x86/um/asm/checksum.h index 4b181b744..ee940185e 100644 --- a/arch/x86/um/asm/checksum.h +++ b/arch/x86/um/asm/checksum.h @@ -3,6 +3,7 @@ #include <linux/string.h> #include <linux/in6.h> +#include <linux/uaccess.h> /* * computes the checksum of a memory block at buff, length len, diff --git a/arch/x86/um/asm/elf.h b/arch/x86/um/asm/elf.h index 0a656b727..548197212 100644 --- a/arch/x86/um/asm/elf.h +++ b/arch/x86/um/asm/elf.h @@ -200,8 +200,6 @@ typedef elf_greg_t elf_gregset_t[ELF_NGREG]; typedef struct user_i387_struct elf_fpregset_t; -#define task_pt_regs(t) (&(t)->thread.regs) - struct task_struct; extern int elf_core_copy_fpregs(struct task_struct *t, elf_fpregset_t *fpu); diff --git a/arch/x86/um/asm/processor.h b/arch/x86/um/asm/processor.h index 2a206d2b1..233ee09c1 100644 --- a/arch/x86/um/asm/processor.h +++ b/arch/x86/um/asm/processor.h @@ -28,6 +28,8 @@ static inline void rep_nop(void) #define cpu_relax() rep_nop() #define cpu_relax_lowlatency() cpu_relax() +#define task_pt_regs(t) (&(t)->thread.regs) + #include <asm/processor-generic.h> #endif diff --git a/arch/x86/um/asm/segment.h b/arch/x86/um/asm/segment.h index 45183fcd1..41dd5e1f3 100644 --- a/arch/x86/um/asm/segment.h +++ b/arch/x86/um/asm/segment.h @@ -7,4 +7,12 @@ extern int host_gdt_entry_tls_min; #define GDT_ENTRY_TLS_MIN host_gdt_entry_tls_min #define GDT_ENTRY_TLS_MAX (GDT_ENTRY_TLS_MIN + GDT_ENTRY_TLS_ENTRIES - 1) +typedef struct { + unsigned long seg; +} mm_segment_t; + +#define MAKE_MM_SEG(s) ((mm_segment_t) { (s) }) +#define KERNEL_DS MAKE_MM_SEG(~0UL) +#define USER_DS MAKE_MM_SEG(TASK_SIZE) + #endif diff --git a/arch/x86/um/ldt.c b/arch/x86/um/ldt.c index 5c0b711d2..9701a4fd7 100644 --- a/arch/x86/um/ldt.c +++ b/arch/x86/um/ldt.c @@ -6,6 +6,7 @@ #include <linux/mm.h> #include <linux/sched.h> #include <linux/slab.h> +#include <linux/uaccess.h> #include <asm/unistd.h> #include <os.h> #include <skas.h> diff --git a/arch/x86/um/mem_32.c b/arch/x86/um/mem_32.c index f40281e5d..744afdc18 100644 --- a/arch/x86/um/mem_32.c +++ b/arch/x86/um/mem_32.c @@ -7,8 +7,7 @@ */ #include <linux/mm.h> -#include <asm/page.h> -#include <asm/mman.h> +#include <asm/elf.h> static struct vm_area_struct gate_vma; diff --git a/arch/x86/um/mem_64.c b/arch/x86/um/mem_64.c index f8fecaddc..7642e2e2a 100644 --- a/arch/x86/um/mem_64.c +++ b/arch/x86/um/mem_64.c @@ -1,6 +1,5 @@ #include <linux/mm.h> -#include <asm/page.h> -#include <asm/mman.h> +#include <asm/elf.h> const char *arch_vma_name(struct vm_area_struct *vma) { diff --git a/arch/x86/um/ptrace_32.c b/arch/x86/um/ptrace_32.c index ce3dd4f36..a29756f2d 100644 --- a/arch/x86/um/ptrace_32.c +++ b/arch/x86/um/ptrace_32.c @@ -6,6 +6,7 @@ #include <linux/mm.h> #include <linux/sched.h> #include <asm/uaccess.h> +#include <asm/ptrace-abi.h> #include <skas.h> extern int arch_switch_tls(struct task_struct *to); diff --git a/arch/x86/um/ptrace_64.c b/arch/x86/um/ptrace_64.c index 3b52bf0b4..a629694ee 100644 --- a/arch/x86/um/ptrace_64.c +++ b/arch/x86/um/ptrace_64.c @@ -11,6 +11,7 @@ #define __FRAME_OFFSETS #include <asm/ptrace.h> #include <asm/uaccess.h> +#include <asm/ptrace-abi.h> /* * determines which flags the user has access to. diff --git a/arch/x86/um/shared/sysdep/tls.h b/arch/x86/um/shared/sysdep/tls.h index 27cce00c6..a682db13d 100644 --- a/arch/x86/um/shared/sysdep/tls.h +++ b/arch/x86/um/shared/sysdep/tls.h @@ -1,7 +1,7 @@ #ifndef _SYSDEP_TLS_H #define _SYSDEP_TLS_H -# ifndef __KERNEL__ +#ifdef __UM_HOST__ /* Change name to avoid conflicts with the original one from <asm/ldt.h>, which * may be named user_desc (but in 2.4 and in header matching its API was named @@ -22,11 +22,11 @@ typedef struct um_dup_user_desc { #endif } user_desc_t; -# else /* __KERNEL__ */ +#else /* __UM_HOST__ */ typedef struct user_desc user_desc_t; -# endif /* __KERNEL__ */ +#endif /* __UM_HOST__ */ extern int os_set_thread_area(user_desc_t *info, int pid); extern int os_get_thread_area(user_desc_t *info, int pid); diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c index 592491d1d..06934a8a4 100644 --- a/arch/x86/um/signal.c +++ b/arch/x86/um/signal.c @@ -541,7 +541,8 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, */ /* x86-64 should always use SA_RESTORER. */ if (ksig->ka.sa.sa_flags & SA_RESTORER) - err |= __put_user(ksig->ka.sa.sa_restorer, &frame->pretcode); + err |= __put_user((void *)ksig->ka.sa.sa_restorer, + &frame->pretcode); else /* could use a vstub here */ return err; diff --git a/arch/x86/um/syscalls_64.c b/arch/x86/um/syscalls_64.c index adb08eb5c..e65522753 100644 --- a/arch/x86/um/syscalls_64.c +++ b/arch/x86/um/syscalls_64.c @@ -6,6 +6,7 @@ */ #include <linux/sched.h> +#include <linux/uaccess.h> #include <asm/prctl.h> /* XXX This should get the constants from libc */ #include <os.h> diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c index 80ffa5b99..48e38584d 100644 --- a/arch/x86/um/tls_32.c +++ b/arch/x86/um/tls_32.c @@ -7,6 +7,7 @@ #include <linux/sched.h> #include <linux/syscalls.h> #include <asm/uaccess.h> +#include <asm/ptrace-abi.h> #include <os.h> #include <skas.h> #include <sysdep/tls.h> diff --git a/arch/x86/um/tls_64.c b/arch/x86/um/tls_64.c index d22363cb8..3ad714373 100644 --- a/arch/x86/um/tls_64.c +++ b/arch/x86/um/tls_64.c @@ -1,4 +1,5 @@ #include <linux/sched.h> +#include <asm/ptrace-abi.h> void clear_flushed_tls(struct task_struct *task) { diff --git a/arch/x86/um/vdso/vma.c b/arch/x86/um/vdso/vma.c index 916cda4cd..237c6831e 100644 --- a/arch/x86/um/vdso/vma.c +++ b/arch/x86/um/vdso/vma.c @@ -10,6 +10,7 @@ #include <linux/sched.h> #include <linux/mm.h> #include <asm/page.h> +#include <asm/elf.h> #include <linux/init.h> static unsigned int __read_mostly vdso_enabled = 1; diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index e88fda867..484145368 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -8,7 +8,7 @@ config XEN select PARAVIRT_CLOCK select XEN_HAVE_PVMMU depends on X86_64 || (X86_32 && X86_PAE) - depends on X86_TSC + depends on X86_LOCAL_APIC && X86_TSC help This is the Linux Xen port. Enabling this will allow the kernel to boot in a paravirtualized environment under the @@ -17,7 +17,7 @@ config XEN config XEN_DOM0 def_bool y depends on XEN && PCI_XEN && SWIOTLB_XEN - depends on X86_LOCAL_APIC && X86_IO_APIC && ACPI && PCI + depends on X86_IO_APIC && ACPI && PCI config XEN_PVHVM def_bool y diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 7322755f3..4b6e29ac0 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -13,13 +13,13 @@ CFLAGS_mmu.o := $(nostackp) obj-y := enlighten.o setup.o multicalls.o mmu.o irq.o \ time.o xen-asm.o xen-asm_$(BITS).o \ grant-table.o suspend.o platform-pci-unplug.o \ - p2m.o + p2m.o apic.o obj-$(CONFIG_EVENT_TRACING) += trace.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o -obj-$(CONFIG_XEN_DOM0) += apic.o vga.o +obj-$(CONFIG_XEN_DOM0) += vga.o obj-$(CONFIG_SWIOTLB_XEN) += pci-swiotlb-xen.o obj-$(CONFIG_XEN_EFI) += efi.o diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index a671e8372..11d6fb4e8 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1221,10 +1221,11 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .read_tscp = native_read_tscp, .iret = xen_iret, - .irq_enable_sysexit = xen_sysexit, #ifdef CONFIG_X86_64 .usergs_sysret32 = xen_sysret32, .usergs_sysret64 = xen_sysret64, +#else + .irq_enable_sysexit = xen_sysexit, #endif .load_tr_desc = paravirt_nop, @@ -1463,7 +1464,7 @@ static void xen_pvh_set_cr_flags(int cpu) return; /* * For BSP, PSE PGE are set in probe_page_size_mask(), for APs - * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu_init. + * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu__init_cpu(). */ if (cpu_has_pse) cr4_set_bits_and_update_boot(X86_CR4_PSE); @@ -1507,6 +1508,7 @@ asmlinkage __visible void __init xen_start_kernel(void) { struct physdev_set_iopl set_iopl; unsigned long initrd_start = 0; + u64 pat; int rc; if (!xen_start_info) @@ -1614,8 +1616,8 @@ asmlinkage __visible void __init xen_start_kernel(void) * Modify the cache mode translation tables to match Xen's PAT * configuration. */ - - pat_init_cache_modes(); + rdmsrl(MSR_IA32_CR_PAT, pat); + pat_init_cache_modes(pat); /* keep using Xen gdt for now; no urgent need to change it */ diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index b47124d4c..8b7f18e20 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -67,6 +67,7 @@ #include <linux/seq_file.h> #include <linux/bootmem.h> #include <linux/slab.h> +#include <linux/vmalloc.h> #include <asm/cache.h> #include <asm/setup.h> diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 956374c1e..9e2ba5c6e 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -17,6 +17,56 @@ #include "xen-ops.h" #include "debugfs.h" +static DEFINE_PER_CPU(int, lock_kicker_irq) = -1; +static DEFINE_PER_CPU(char *, irq_name); +static bool xen_pvspin = true; + +#ifdef CONFIG_QUEUED_SPINLOCKS + +#include <asm/qspinlock.h> + +static void xen_qlock_kick(int cpu) +{ + xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR); +} + +/* + * Halt the current CPU & release it back to the host + */ +static void xen_qlock_wait(u8 *byte, u8 val) +{ + int irq = __this_cpu_read(lock_kicker_irq); + + /* If kicker interrupts not initialized yet, just spin */ + if (irq == -1) + return; + + /* clear pending */ + xen_clear_irq_pending(irq); + barrier(); + + /* + * We check the byte value after clearing pending IRQ to make sure + * that we won't miss a wakeup event because of the clearing. + * + * The sync_clear_bit() call in xen_clear_irq_pending() is atomic. + * So it is effectively a memory barrier for x86. + */ + if (READ_ONCE(*byte) != val) + return; + + /* + * If an interrupt happens here, it will leave the wakeup irq + * pending, which will cause xen_poll_irq() to return + * immediately. + */ + + /* Block until irq becomes pending (or perhaps a spurious wakeup) */ + xen_poll_irq(irq); +} + +#else /* CONFIG_QUEUED_SPINLOCKS */ + enum xen_contention_stat { TAKEN_SLOW, TAKEN_SLOW_PICKUP, @@ -100,12 +150,9 @@ struct xen_lock_waiting { __ticket_t want; }; -static DEFINE_PER_CPU(int, lock_kicker_irq) = -1; -static DEFINE_PER_CPU(char *, irq_name); static DEFINE_PER_CPU(struct xen_lock_waiting, lock_waiting); static cpumask_t waiting_cpus; -static bool xen_pvspin = true; __visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want) { int irq = __this_cpu_read(lock_kicker_irq); @@ -217,6 +264,7 @@ static void xen_unlock_kick(struct arch_spinlock *lock, __ticket_t next) } } } +#endif /* CONFIG_QUEUED_SPINLOCKS */ static irqreturn_t dummy_handler(int irq, void *dev_id) { @@ -280,8 +328,16 @@ void __init xen_init_spinlocks(void) return; } printk(KERN_DEBUG "xen: PV spinlocks enabled\n"); +#ifdef CONFIG_QUEUED_SPINLOCKS + __pv_init_lock_hash(); + pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath; + pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock); + pv_lock_ops.wait = xen_qlock_wait; + pv_lock_ops.kick = xen_qlock_kick; +#else pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning); pv_lock_ops.unlock_kick = xen_unlock_kick; +#endif } /* @@ -310,7 +366,7 @@ static __init int xen_parse_nopvspin(char *arg) } early_param("xen_nopvspin", xen_parse_nopvspin); -#ifdef CONFIG_XEN_DEBUG_FS +#if defined(CONFIG_XEN_DEBUG_FS) && !defined(CONFIG_QUEUED_SPINLOCKS) static struct dentry *d_spin_debug; diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S index 985fc3ee0..f22667abf 100644 --- a/arch/x86/xen/xen-asm_64.S +++ b/arch/x86/xen/xen-asm_64.S @@ -15,6 +15,8 @@ #include <asm/percpu.h> #include <asm/processor-flags.h> #include <asm/segment.h> +#include <asm/asm-offsets.h> +#include <asm/thread_info.h> #include <xen/interface/xen.h> @@ -47,29 +49,13 @@ ENTRY(xen_iret) ENDPATCH(xen_iret) RELOC(xen_iret, 1b+1) -/* - * sysexit is not used for 64-bit processes, so it's only ever used to - * return to 32-bit compat userspace. - */ -ENTRY(xen_sysexit) - pushq $__USER32_DS - pushq %rcx - pushq $X86_EFLAGS_IF - pushq $__USER32_CS - pushq %rdx - - pushq $0 -1: jmp hypercall_iret -ENDPATCH(xen_sysexit) -RELOC(xen_sysexit, 1b+1) - ENTRY(xen_sysret64) /* * We're already on the usermode stack at this point, but * still with the kernel gs, so we can easily switch back */ movq %rsp, PER_CPU_VAR(rsp_scratch) - movq PER_CPU_VAR(kernel_stack), %rsp + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp pushq $__USER_DS pushq PER_CPU_VAR(rsp_scratch) @@ -88,7 +74,7 @@ ENTRY(xen_sysret32) * still with the kernel gs, so we can easily switch back */ movq %rsp, PER_CPU_VAR(rsp_scratch) - movq PER_CPU_VAR(kernel_stack), %rsp + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp pushq $__USER32_DS pushq PER_CPU_VAR(rsp_scratch) @@ -128,7 +114,7 @@ RELOC(xen_sysret32, 1b+1) /* Normal 64-bit system call target */ ENTRY(xen_syscall_target) undo_xen_syscall - jmp system_call_after_swapgs + jmp entry_SYSCALL_64_after_swapgs ENDPROC(xen_syscall_target) #ifdef CONFIG_IA32_EMULATION @@ -136,13 +122,13 @@ ENDPROC(xen_syscall_target) /* 32-bit compat syscall target */ ENTRY(xen_syscall32_target) undo_xen_syscall - jmp ia32_cstar_target + jmp entry_SYSCALL_compat ENDPROC(xen_syscall32_target) /* 32-bit compat sysenter target */ ENTRY(xen_sysenter_target) undo_xen_syscall - jmp ia32_sysenter_target + jmp entry_SYSENTER_compat ENDPROC(xen_sysenter_target) #else /* !CONFIG_IA32_EMULATION */ diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 9e195c683..2292721b1 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -101,17 +101,15 @@ struct dom0_vga_console_info; #ifdef CONFIG_XEN_DOM0 void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size); -void __init xen_init_apic(void); #else static inline void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size) { } -static inline void __init xen_init_apic(void) -{ -} #endif +void __init xen_init_apic(void); + #ifdef CONFIG_XEN_EFI extern void xen_efi_init(void); #else @@ -134,7 +132,9 @@ DECL_ASM(void, xen_restore_fl_direct, unsigned long); /* These are not functions, and cannot be called normally */ __visible void xen_iret(void); +#ifdef CONFIG_X86_32 __visible void xen_sysexit(void); +#endif __visible void xen_sysret32(void); __visible void xen_sysret64(void); __visible void xen_adjust_exception_frame(void); |