diff options
Diffstat (limited to 'arch/x86')
440 files changed, 23460 insertions, 10441 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index b3a1a5d77d92..9bd3cc03d51d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -24,10 +24,12 @@ config X86 select ARCH_DISCARD_MEMBLOCK select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS + select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FAST_MULTIPLIER select ARCH_HAS_GCOV_PROFILE_ALL - select ARCH_HAS_PMEM_API + select ARCH_HAS_PMEM_API if X86_64 + select ARCH_HAS_MMIO_FLUSH select ARCH_HAS_SG_CHAIN select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI @@ -41,6 +43,7 @@ config X86 select ARCH_USE_CMPXCHG_LOCKREF if X86_64 select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS + select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH if SMP select ARCH_WANTS_DYNAMIC_TASK_STRUCT select ARCH_WANT_FRAME_POINTERS select ARCH_WANT_IPC_PARSE_VERSION if X86_32 @@ -80,6 +83,8 @@ config X86 select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP select HAVE_ARCH_KGDB select HAVE_ARCH_KMEMCHECK + select HAVE_ARCH_MMAP_RND_BITS if MMU + select HAVE_ARCH_MMAP_RND_COMPAT_BITS if MMU && COMPAT select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_SOFT_DIRTY if X86_64 select HAVE_ARCH_TRACEHOOK @@ -133,7 +138,7 @@ config X86 select HAVE_PERF_USER_STACK_DUMP select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_SYSCALL_TRACEPOINTS - select HAVE_UID16 if X86_32 + select HAVE_UID16 if X86_32 || IA32_EMULATION select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_USER_RETURN_NOTIFIER select IRQ_FORCED_THREADING @@ -175,12 +180,23 @@ config LOCKDEP_SUPPORT config STACKTRACE_SUPPORT def_bool y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - config MMU def_bool y +config ARCH_MMAP_RND_BITS_MIN + default 28 if 64BIT + default 8 + +config ARCH_MMAP_RND_BITS_MAX + default 32 if 64BIT + default 16 + +config ARCH_MMAP_RND_COMPAT_BITS_MIN + default 8 + +config ARCH_MMAP_RND_COMPAT_BITS_MAX + default 16 + config SBUS bool @@ -347,6 +363,17 @@ config X86_FEATURE_NAMES If in doubt, say Y. +config X86_FAST_FEATURE_TESTS + bool "Fast CPU feature tests" if EMBEDDED + default y + ---help--- + Some fast-paths in the kernel depend on the capabilities of the CPU. + Say Y here for the kernel to patch in the appropriate code at runtime + based on the capabilities of the CPU. The infrastructure for patching + code at runtime takes up some additional space; space-constrained + embedded systems may wish to say N here to produce smaller, slightly + slower code. + config X86_X2APIC bool "Support x2apic" depends on X86_LOCAL_APIC && X86_64 && (IRQ_REMAP || HYPERVISOR_GUEST) @@ -521,9 +548,10 @@ config X86_INTEL_QUARK config X86_INTEL_LPSS bool "Intel Low Power Subsystem Support" - depends on ACPI + depends on X86 && ACPI select COMMON_CLK select PINCTRL + select IOSF_MBI ---help--- Select to build support for Intel Low Power Subsystem such as found on Intel Lynxpoint PCH. Selecting this option enables @@ -685,6 +713,14 @@ config PARAVIRT_SPINLOCKS If you are unsure how to answer this question, answer Y. +config QUEUED_LOCK_STAT + bool "Paravirt queued spinlock statistics" + depends on PARAVIRT_SPINLOCKS && DEBUG_FS && QUEUED_SPINLOCKS + ---help--- + Enable the collection of statistical data on the slowpath + behavior of paravirtualized queued spinlocks and report + them on debugfs. + source "arch/x86/xen/Kconfig" config KVM_GUEST @@ -955,6 +991,7 @@ config X86_REROUTE_FOR_BROKEN_BOOT_IRQS config X86_MCE bool "Machine Check / overheating reporting" + select GENERIC_ALLOCATOR default y ---help--- Machine Check support allows the processor to notify the @@ -1002,19 +1039,42 @@ config X86_THERMAL_VECTOR def_bool y depends on X86_MCE_INTEL -config VM86 - bool "Enable VM86 support" if EXPERT - default y +config X86_LEGACY_VM86 + bool "Legacy VM86 support" + default n depends on X86_32 ---help--- - This option is required by programs like DOSEMU to run - 16-bit real mode legacy code on x86 processors. It also may - be needed by software like XFree86 to initialize some video - cards via BIOS. Disabling this option saves about 6K. + This option allows user programs to put the CPU into V8086 + mode, which is an 80286-era approximation of 16-bit real mode. + + Some very old versions of X and/or vbetool require this option + for user mode setting. Similarly, DOSEMU will use it if + available to accelerate real mode DOS programs. However, any + recent version of DOSEMU, X, or vbetool should be fully + functional even without kernel VM86 support, as they will all + fall back to software emulation. Nevertheless, if you are using + a 16-bit DOS program where 16-bit performance matters, vm86 + mode might be faster than emulation and you might want to + enable this option. + + Note that any app that works on a 64-bit kernel is unlikely to + need this option, as 64-bit kernels don't, and can't, support + V8086 mode. This option is also unrelated to 16-bit protected + mode and is not needed to run most 16-bit programs under Wine. + + Enabling this option increases the complexity of the kernel + and slows down exception handling a tiny bit. + + If unsure, say N here. + +config VM86 + bool + default X86_LEGACY_VM86 config X86_16BIT bool "Enable support for 16-bit segments" if EXPERT default y + depends on MODIFY_LDT_SYSCALL ---help--- This option is required by programs like Wine to run 16-bit protected mode legacy code on x86 processors. Disabling @@ -1097,8 +1157,10 @@ config X86_REBOOTFIXUPS Say N otherwise. config MICROCODE - tristate "CPU microcode loading support" + bool "CPU microcode loading support" + default y depends on CPU_SUP_AMD || CPU_SUP_INTEL + depends on BLK_DEV_INITRD select FW_LOADER ---help--- @@ -1140,24 +1202,6 @@ config MICROCODE_OLD_INTERFACE def_bool y depends on MICROCODE -config MICROCODE_INTEL_EARLY - bool - -config MICROCODE_AMD_EARLY - bool - -config MICROCODE_EARLY - bool "Early load microcode" - depends on MICROCODE=y && BLK_DEV_INITRD - select MICROCODE_INTEL_EARLY if MICROCODE_INTEL - select MICROCODE_AMD_EARLY if MICROCODE_AMD - default y - help - This option provides functionality to read additional microcode data - at the beginning of initrd image. The data tells kernel to load - microcode to CPU's as early as possible. No functional change if no - microcode data is glued to the initrd, therefore it's safe to say Y. - config X86_MSR tristate "/dev/cpu/*/msr - Model-specific register support" ---help--- @@ -1282,6 +1326,7 @@ config HIGHMEM config X86_PAE bool "PAE (Physical Address Extension) Support" depends on X86_32 && !HIGHMEM4G + select SWIOTLB ---help--- PAE is required for NX support, and furthermore enables larger swapspace support for non-overcommit purposes. It @@ -1426,10 +1471,14 @@ config ILLEGAL_POINTER_VALUE source "mm/Kconfig" +config X86_PMEM_LEGACY_DEVICE + bool + config X86_PMEM_LEGACY - bool "Support non-standard NVDIMMs and ADR protected memory" + tristate "Support non-standard NVDIMMs and ADR protected memory" depends on PHYS_ADDR_T_64BIT depends on BLK_DEV + select X86_PMEM_LEGACY_DEVICE select LIBNVDIMM help Treat memory marked using the non-standard e820 type of 12 as used @@ -1509,6 +1558,7 @@ config X86_RESERVE_LOW config MATH_EMULATION bool + depends on MODIFY_LDT_SYSCALL prompt "Math emulation" if X86_32 ---help--- Linux can emulate a math coprocessor (used for floating point @@ -1724,6 +1774,7 @@ source kernel/Kconfig.hz config KEXEC bool "kexec system call" + select KEXEC_CORE ---help--- kexec is a system call that implements the ability to shutdown your current kernel, and to start another kernel. It is like a reboot @@ -1740,8 +1791,8 @@ config KEXEC config KEXEC_FILE bool "kexec file based system call" + select KEXEC_CORE select BUILD_BIN2C - depends on KEXEC depends on X86_64 depends on CRYPTO=y depends on CRYPTO_SHA256=y @@ -2010,6 +2061,55 @@ config COMPAT_VDSO If unsure, say N: if you are compiling your own kernel, you are unlikely to be using a buggy version of glibc. +choice + prompt "vsyscall table for legacy applications" + depends on X86_64 + default LEGACY_VSYSCALL_EMULATE + help + Legacy user code that does not know how to find the vDSO expects + to be able to issue three syscalls by calling fixed addresses in + kernel space. Since this location is not randomized with ASLR, + it can be used to assist security vulnerability exploitation. + + This setting can be changed at boot time via the kernel command + line parameter vsyscall=[native|emulate|none]. + + On a system with recent enough glibc (2.14 or newer) and no + static binaries, you can say None without a performance penalty + to improve security. + + If unsure, select "Emulate". + + config LEGACY_VSYSCALL_NATIVE + bool "Native" + help + Actual executable code is located in the fixed vsyscall + address mapping, implementing time() efficiently. Since + this makes the mapping executable, it can be used during + security vulnerability exploitation (traditionally as + ROP gadgets). This configuration is not recommended. + + config LEGACY_VSYSCALL_EMULATE + bool "Emulate" + help + The kernel traps and emulates calls into the fixed + vsyscall address mapping. This makes the mapping + non-executable, but it still contains known contents, + which could be used in certain rare security vulnerability + exploits. This configuration is recommended when userspace + still uses the vsyscall area. + + config LEGACY_VSYSCALL_NONE + bool "None" + help + There will be no vsyscall mapping at all. This will + eliminate any risk of ASLR bypass due to the vsyscall + fixed address mapping. Attempts to use the vsyscalls + will be reported to dmesg, so that either old or + malicious userspace programs can be identified. + +endchoice + config CMDLINE_BOOL bool "Built-in kernel command line" ---help--- @@ -2053,6 +2153,22 @@ config CMDLINE_OVERRIDE This is used to work around broken boot loaders. This should be set to 'N' under normal conditions. +config MODIFY_LDT_SYSCALL + bool "Enable the LDT (local descriptor table)" if EXPERT + default y + ---help--- + Linux can allow user programs to install a per-process x86 + Local Descriptor Table (LDT) using the modify_ldt(2) system + call. This is required to run 16-bit or segmented code such as + DOSEMU or some Wine programs. It is also used by some very old + threading libraries. + + Enabling this feature adds a small amount of overhead to + context switches and increases the low-level kernel attack + surface. Disabling it removes the modify_ldt(2) system call. + + Saying 'N' here may make sense for embedded or server kernels. + source "kernel/livepatch/Kconfig" endmenu @@ -2522,7 +2638,7 @@ config IA32_EMULATION depends on X86_64 select BINFMT_ELF select COMPAT_BINFMT_ELF - select HAVE_UID16 + select ARCH_WANT_OLD_COMPAT_IPC ---help--- Include code to run legacy 32-bit programs under a 64-bit kernel. You should likely turn this on, unless you're @@ -2536,7 +2652,7 @@ config IA32_AOUT config X86_X32 bool "x32 ABI for 64-bit mode" - depends on X86_64 && IA32_EMULATION + depends on X86_64 ---help--- Include code to run binaries for the x32 native 32-bit ABI for 64-bit processors. An x32 process gets access to the @@ -2550,7 +2666,6 @@ config X86_X32 config COMPAT def_bool y depends on IA32_EMULATION || X86_X32 - select ARCH_WANT_OLD_COMPAT_IPC if COMPAT config COMPAT_FOR_U64_ALIGNMENT @@ -2584,6 +2699,19 @@ config PMC_ATOM def_bool y depends on PCI +config VMD + depends on PCI_MSI + tristate "Volume Management Device Driver" + default N + ---help--- + Adds support for the Intel Volume Management Device (VMD). VMD is a + secondary PCI host bridge that allows PCI Express root ports, + and devices attached to them, to be removed from the default + PCI domain and placed within the VMD domain. This provides + more bus resources than are otherwise possible with a + single domain. If you know your system provides one of these and + has devices attached to it, say Y; if you are not sure, say N. + source "net/Kconfig" source "drivers/Kconfig" diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 6983314c8b37..3ba5ff2f2d08 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -3,10 +3,6 @@ choice prompt "Processor family" default M686 if X86_32 default GENERIC_CPU if X86_64 - -config M486 - bool "486" - depends on X86_32 ---help--- This is the processor type of your CPU. This information is used for optimizing purposes. In order to compile a kernel @@ -23,9 +19,9 @@ config M486 Here are the settings recommended for greatest speed: - "486" for the AMD/Cyrix/IBM/Intel 486DX/DX2/DX4 or - SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or U5S. + SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or U5S. - "586" for generic Pentium CPUs lacking the TSC - (time stamp counter) register. + (time stamp counter) register. - "Pentium-Classic" for the Intel Pentium. - "Pentium-MMX" for the Intel Pentium MMX. - "Pentium-Pro" for the Intel Pentium Pro. @@ -34,17 +30,31 @@ config M486 - "Pentium-4" for the Intel Pentium 4 or P4-based Celeron. - "K6" for the AMD K6, K6-II and K6-III (aka K6-3D). - "Athlon" for the AMD K7 family (Athlon/Duron/Thunderbird). + - "Opteron/Athlon64/Hammer/K8" for all K8 and newer AMD CPUs. - "Crusoe" for the Transmeta Crusoe series. - "Efficeon" for the Transmeta Efficeon series. - "Winchip-C6" for original IDT Winchip. - "Winchip-2" for IDT Winchips with 3dNow! capabilities. + - "AMD Elan" for the 32-bit AMD Elan embedded CPU. - "GeodeGX1" for Geode GX1 (Cyrix MediaGX). - "Geode GX/LX" For AMD Geode GX and LX processors. - "CyrixIII/VIA C3" for VIA Cyrix III or VIA C3. - "VIA C3-2" for VIA C3-2 "Nehemiah" (model 9 and above). - "VIA C7" for VIA C7. + - "Intel P4" for the Pentium 4/Netburst microarchitecture. + - "Core 2/newer Xeon" for all core2 and newer Intel CPUs. + - "Intel Atom" for the Atom-microarchitecture CPUs. + - "Generic-x86-64" for a kernel which runs on any x86-64 CPU. + + See each option's help text for additional details. If you don't know + what to do, choose "486". - If you don't know what to do, choose "486". +config M486 + bool "486" + depends on X86_32 + ---help--- + Select this for an 486-class CPU such as AMD/Cyrix/IBM/Intel + 486DX/DX2/DX4 or SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or U5S. config M586 bool "586/K5/5x86/6x86/6x86MX" diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index d8c0d3266173..9b18ed97a8a2 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -5,23 +5,6 @@ config TRACE_IRQFLAGS_SUPPORT source "lib/Kconfig.debug" -config STRICT_DEVMEM - bool "Filter access to /dev/mem" - ---help--- - If this option is disabled, you allow userspace (root) access to all - of memory, including kernel and userspace memory. Accidental - access to this is obviously disastrous, but specific access can - be used by people debugging the kernel. Note that with PAT support - enabled, even in this case there are restrictions on /dev/mem - use due to the cache aliasing requirements. - - If this option is switched on, the /dev/mem file only allows - userspace access to PCI space and the BIOS code and data regions. - This is sufficient for dosemu and X and all common users of - /dev/mem. - - If in doubt, say Y. - config X86_VERBOSE_BOOTUP bool "Enable verbose x86 bootup info messages" default y @@ -65,10 +48,14 @@ config EARLY_PRINTK_EFI This is useful for kernel debugging when your machine crashes very early before the console code is initialized. +config X86_PTDUMP_CORE + def_bool n + config X86_PTDUMP - bool "Export kernel pagetable layout to userspace via debugfs" + tristate "Export kernel pagetable layout to userspace via debugfs" depends on DEBUG_KERNEL select DEBUG_FS + select X86_PTDUMP_CORE ---help--- Say Y here if you want to show the kernel pagetable layout in a debugfs file. This information is only useful for kernel developers @@ -79,7 +66,8 @@ config X86_PTDUMP config EFI_PGT_DUMP bool "Dump the EFI pagetable" - depends on EFI && X86_PTDUMP + depends on EFI + select X86_PTDUMP_CORE ---help--- Enable this if you want to dump the EFI page table before enabling virtual mode. This can be used to debug miscellaneous @@ -105,6 +93,34 @@ config DEBUG_RODATA_TEST feature as well as for the change_page_attr() infrastructure. If in doubt, say "N" +config DEBUG_WX + bool "Warn on W+X mappings at boot" + depends on DEBUG_RODATA + select X86_PTDUMP_CORE + ---help--- + Generate a warning if any W+X mappings are found at boot. + + This is useful for discovering cases where the kernel is leaving + W+X mappings after applying NX, as such mappings are a security risk. + + Look for a message in dmesg output like this: + + x86/mm: Checked W+X mappings: passed, no W+X pages found. + + or like this, if the check failed: + + x86/mm: Checked W+X mappings: FAILED, <N> W+X pages found. + + Note that even if the check fails, your kernel is possibly + still fine, as W+X mappings are not a security hole in + themselves, what they do is that they make the exploitation + of other unfixed kernel bugs easier. + + There is no runtime or memory usage effect of this option + once the kernel has booted up - it's a one time check. + + If in doubt, say "Y". + config DEBUG_SET_MODULE_RONX bool "Set loadable kernel module data as NX and text as RO" depends on MODULES diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 118e6debc483..4086abca0b32 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -39,6 +39,16 @@ ifdef CONFIG_X86_NEED_RELOCS LDFLAGS_vmlinux := --emit-relocs endif +# +# Prevent GCC from generating any FP code by mistake. +# +# This must happen before we try the -mpreferred-stack-boundary, see: +# +# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383 +# +KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow +KBUILD_CFLAGS += $(call cc-option,-mno-avx,) + ifeq ($(CONFIG_X86_32),y) BITS := 32 UTS_MACHINE := i386 @@ -149,15 +159,23 @@ 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) 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$(comma)%ymm1,-DCONFIG_AS_AVX2=1) +sha1_ni_instr :=$(call as-instr,sha1msg1 %xmm0$(comma)%xmm1,-DCONFIG_AS_SHA1_NI=1) +sha256_ni_instr :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,-DCONFIG_AS_SHA256_NI=1) -KBUILD_AFLAGS += $(asinstr) $(avx_instr) $(avx2_instr) -KBUILD_CFLAGS += $(asinstr) $(avx_instr) $(avx2_instr) +KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(sha1_ni_instr) $(sha256_ni_instr) +KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(sha1_ni_instr) $(sha256_ni_instr) LDFLAGS := -m elf_$(UTS_MACHINE) @@ -167,9 +185,6 @@ KBUILD_CFLAGS += -pipe KBUILD_CFLAGS += -Wno-sign-compare # KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -# prevent gcc from generating any FP code by mistake -KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -KBUILD_CFLAGS += $(call cc-option,-mno-avx,) KBUILD_CFLAGS += $(mflags-y) KBUILD_AFLAGS += $(mflags-y) @@ -212,6 +227,8 @@ drivers-$(CONFIG_PM) += arch/x86/power/ drivers-$(CONFIG_FB) += arch/x86/video/ +drivers-$(CONFIG_RAS) += arch/x86/ras/ + #### # boot loader support. Several targets are kept for legacy purposes diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 57bbf2fb21f6..2ee62dba0373 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -9,13 +9,13 @@ # Changed by many, many contributors over the years. # +KASAN_SANITIZE := n + # If you want to preset the SVGA mode, uncomment the next line and # set SVGA_MODE to whatever number you want. # Set it to -DSVGA_MODE=NORMAL_VGA if you just want the EGA/VGA mode. # The number is the same as you would ordinarily press at bootup. -KASAN_SANITIZE := n - SVGA_MODE := -DSVGA_MODE=NORMAL_VGA targets := vmlinux.bin setup.bin setup.elf bzImage @@ -23,7 +23,7 @@ targets += fdimage fdimage144 fdimage288 image.iso mtools.conf subdir- := compressed setup-y += a20.o bioscall.o cmdline.o copy.o cpu.o cpuflags.o cpucheck.o -setup-y += early_serial_console.o edd.o header.o main.o mca.o memory.o +setup-y += early_serial_console.o edd.o header.o main.o memory.o setup-y += pm.o pmjump.o printf.o regs.o string.o tty.o video.o setup-y += video-mode.o version.o setup-$(CONFIG_X86_APM_BOOT) += apm.o diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index bd49ec61255c..9011a88353de 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -23,7 +23,6 @@ #include <stdarg.h> #include <linux/types.h> #include <linux/edd.h> -#include <asm/boot.h> #include <asm/setup.h> #include "bitops.h" #include "ctype.h" @@ -307,9 +306,6 @@ void query_edd(void); /* header.S */ void __attribute__((noreturn)) die(void); -/* mca.c */ -int query_mca(void); - /* memory.c */ int detect_memory(void); diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c index d7b1f655b3ef..6a9b96b4624d 100644 --- a/arch/x86/boot/compressed/aslr.c +++ b/arch/x86/boot/compressed/aslr.c @@ -82,7 +82,7 @@ static unsigned long get_random_long(void) if (has_cpuflag(X86_FEATURE_TSC)) { debug_putstr(" RDTSC"); - rdtscll(raw); + raw = rdtsc(); random ^= raw; use_i8254 = false; diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 7d69afd8b6fa..583d539a4197 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -624,7 +624,7 @@ setup_pixel_info(struct screen_info *si, u32 pixels_per_scan_line, static efi_status_t __gop_query32(struct efi_graphics_output_protocol_32 *gop32, struct efi_graphics_output_mode_info **info, - unsigned long *size, u32 *fb_base) + unsigned long *size, u64 *fb_base) { struct efi_graphics_output_protocol_mode_32 *mode; efi_status_t status; @@ -650,7 +650,8 @@ setup_gop32(struct screen_info *si, efi_guid_t *proto, unsigned long nr_gops; u16 width, height; u32 pixels_per_scan_line; - u32 fb_base; + u32 ext_lfb_base; + u64 fb_base; struct efi_pixel_bitmask pixel_info; int pixel_format; efi_status_t status; @@ -667,6 +668,7 @@ setup_gop32(struct screen_info *si, efi_guid_t *proto, bool conout_found = false; void *dummy = NULL; u32 h = handles[i]; + u64 current_fb_base; status = efi_call_early(handle_protocol, h, proto, (void **)&gop32); @@ -678,7 +680,7 @@ setup_gop32(struct screen_info *si, efi_guid_t *proto, if (status == EFI_SUCCESS) conout_found = true; - status = __gop_query32(gop32, &info, &size, &fb_base); + status = __gop_query32(gop32, &info, &size, ¤t_fb_base); if (status == EFI_SUCCESS && (!first_gop || conout_found)) { /* * Systems that use the UEFI Console Splitter may @@ -692,6 +694,7 @@ setup_gop32(struct screen_info *si, efi_guid_t *proto, pixel_format = info->pixel_format; pixel_info = info->pixel_information; pixels_per_scan_line = info->pixels_per_scan_line; + fb_base = current_fb_base; /* * Once we've found a GOP supporting ConOut, @@ -713,6 +716,13 @@ setup_gop32(struct screen_info *si, efi_guid_t *proto, si->lfb_width = width; si->lfb_height = height; si->lfb_base = fb_base; + + ext_lfb_base = (u64)(unsigned long)fb_base >> 32; + if (ext_lfb_base) { + si->capabilities |= VIDEO_CAPABILITY_64BIT_BASE; + si->ext_lfb_base = ext_lfb_base; + } + si->pages = 1; setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format); @@ -727,7 +737,7 @@ out: static efi_status_t __gop_query64(struct efi_graphics_output_protocol_64 *gop64, struct efi_graphics_output_mode_info **info, - unsigned long *size, u32 *fb_base) + unsigned long *size, u64 *fb_base) { struct efi_graphics_output_protocol_mode_64 *mode; efi_status_t status; @@ -753,7 +763,8 @@ setup_gop64(struct screen_info *si, efi_guid_t *proto, unsigned long nr_gops; u16 width, height; u32 pixels_per_scan_line; - u32 fb_base; + u32 ext_lfb_base; + u64 fb_base; struct efi_pixel_bitmask pixel_info; int pixel_format; efi_status_t status; @@ -770,6 +781,7 @@ setup_gop64(struct screen_info *si, efi_guid_t *proto, bool conout_found = false; void *dummy = NULL; u64 h = handles[i]; + u64 current_fb_base; status = efi_call_early(handle_protocol, h, proto, (void **)&gop64); @@ -781,7 +793,7 @@ setup_gop64(struct screen_info *si, efi_guid_t *proto, if (status == EFI_SUCCESS) conout_found = true; - status = __gop_query64(gop64, &info, &size, &fb_base); + status = __gop_query64(gop64, &info, &size, ¤t_fb_base); if (status == EFI_SUCCESS && (!first_gop || conout_found)) { /* * Systems that use the UEFI Console Splitter may @@ -795,6 +807,7 @@ setup_gop64(struct screen_info *si, efi_guid_t *proto, pixel_format = info->pixel_format; pixel_info = info->pixel_information; pixels_per_scan_line = info->pixels_per_scan_line; + fb_base = current_fb_base; /* * Once we've found a GOP supporting ConOut, @@ -816,6 +829,13 @@ setup_gop64(struct screen_info *si, efi_guid_t *proto, si->lfb_width = width; si->lfb_height = height; si->lfb_base = fb_base; + + ext_lfb_base = (u64)(unsigned long)fb_base >> 32; + if (ext_lfb_base) { + si->capabilities |= VIDEO_CAPABILITY_64BIT_BASE; + si->ext_lfb_base = ext_lfb_base; + } + si->pages = 1; setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format); @@ -1041,7 +1061,6 @@ void setup_graphics(struct boot_params *boot_params) struct boot_params *make_boot_params(struct efi_config *c) { struct boot_params *boot_params; - struct sys_desc_table *sdt; struct apm_bios_info *bi; struct setup_header *hdr; struct efi_info *efi; @@ -1089,7 +1108,6 @@ struct boot_params *make_boot_params(struct efi_config *c) hdr = &boot_params->hdr; efi = &boot_params->efi_info; bi = &boot_params->apm_bios_info; - sdt = &boot_params->sys_desc_table; /* Copy the second sector to boot_params */ memcpy(&hdr->jump, image->image_base + 512, 512); @@ -1118,8 +1136,6 @@ struct boot_params *make_boot_params(struct efi_config *c) /* Clear APM BIOS info */ memset(bi, 0, sizeof(*bi)); - memset(sdt, 0, sizeof(*sdt)); - status = efi_parse_options(cmdline_ptr); if (status != EFI_SUCCESS) goto fail2; diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index a107b935e22f..79dac1758e7c 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -220,6 +220,23 @@ void __putstr(const char *s) outb(0xff & (pos >> 1), vidport+1); } +void __puthex(unsigned long value) +{ + char alpha[2] = "0"; + int bits; + + for (bits = sizeof(value) * 8 - 4; bits >= 0; bits -= 4) { + unsigned long digit = (value >> bits) & 0xf; + + if (digit < 0xA) + alpha[0] = '0' + digit; + else + alpha[0] = 'a' + (digit - 0xA); + + __putstr(alpha); + } +} + static void error(char *x) { error_putstr("\n\n"); @@ -399,6 +416,13 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap, free_mem_ptr = heap; /* Heap */ free_mem_end_ptr = heap + BOOT_HEAP_SIZE; + /* Report initial kernel position details. */ + debug_putaddr(input_data); + debug_putaddr(input_len); + debug_putaddr(output); + debug_putaddr(output_len); + debug_putaddr(run_size); + /* * The memory hole needed for the kernel is the larger of either * the entire decompressed kernel plus relocation table, or the @@ -424,7 +448,8 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap, #endif debug_putstr("\nDecompressing Linux... "); - decompress(input_data, input_len, NULL, NULL, output, NULL, error); + __decompress(input_data, input_len, NULL, NULL, output, output_len, + NULL, error); parse_elf(output); /* * 32-bit always performs relocations. 64-bit relocations are only diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 805d25ca5f1d..3783dc3e10b3 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -34,16 +34,27 @@ extern memptr free_mem_ptr; extern memptr free_mem_end_ptr; extern struct boot_params *real_mode; /* Pointer to real-mode data */ void __putstr(const char *s); +void __puthex(unsigned long value); #define error_putstr(__x) __putstr(__x) +#define error_puthex(__x) __puthex(__x) #ifdef CONFIG_X86_VERBOSE_BOOTUP #define debug_putstr(__x) __putstr(__x) +#define debug_puthex(__x) __puthex(__x) +#define debug_putaddr(__x) { \ + debug_putstr(#__x ": 0x"); \ + debug_puthex((unsigned long)(__x)); \ + debug_putstr("\n"); \ + } #else static inline void debug_putstr(const char *s) { } +static inline void debug_puthex(const char *s) +{ } +#define debug_putaddr(x) /* */ #endif diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 16ef02596db2..6236b9ec4b76 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -154,7 +154,7 @@ extra_header_fields: #else .quad 0 # ImageBase #endif - .long CONFIG_PHYSICAL_ALIGN # SectionAlignment + .long 0x20 # SectionAlignment .long 0x20 # FileAlignment .word 0 # MajorOperatingSystemVersion .word 0 # MinorOperatingSystemVersion @@ -414,7 +414,7 @@ xloadflags: # define XLF23 0 #endif -#if defined(CONFIG_X86_64) && defined(CONFIG_EFI) && defined(CONFIG_KEXEC) +#if defined(CONFIG_X86_64) && defined(CONFIG_EFI) && defined(CONFIG_KEXEC_CORE) # define XLF4 XLF_EFI_KEXEC #else # define XLF4 0 diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c index fd6c9f236996..9bcea386db65 100644 --- a/arch/x86/boot/main.c +++ b/arch/x86/boot/main.c @@ -161,9 +161,6 @@ void main(void) /* Set keyboard repeat rate (why?) and query the lock flags */ keyboard_init(); - /* Query MCA information */ - query_mca(); - /* Query Intel SpeedStep (IST) information */ query_ist(); diff --git a/arch/x86/boot/mca.c b/arch/x86/boot/mca.c deleted file mode 100644 index a95a531148ef..000000000000 --- a/arch/x86/boot/mca.c +++ /dev/null @@ -1,38 +0,0 @@ -/* -*- linux-c -*- ------------------------------------------------------- * - * - * Copyright (C) 1991, 1992 Linus Torvalds - * Copyright 2007 rPath, Inc. - All Rights Reserved - * Copyright 2009 Intel Corporation; author H. Peter Anvin - * - * This file is part of the Linux kernel, and is made available under - * the terms of the GNU General Public License version 2. - * - * ----------------------------------------------------------------------- */ - -/* - * Get the MCA system description table - */ - -#include "boot.h" - -int query_mca(void) -{ - struct biosregs ireg, oreg; - u16 len; - - initregs(&ireg); - ireg.ah = 0xc0; - intcall(0x15, &ireg, &oreg); - - if (oreg.eflags & X86_EFLAGS_CF) - return -1; /* No MCA present */ - - set_fs(oreg.es); - len = rdfs16(oreg.bx); - - if (len > sizeof(boot_params.sys_desc_table)) - len = sizeof(boot_params.sys_desc_table); - - copy_from_fs(&boot_params.sys_desc_table, oreg.bx, len); - return 0; -} diff --git a/arch/x86/boot/video-mode.c b/arch/x86/boot/video-mode.c index aa8a96b052e3..95c7a818c0ed 100644 --- a/arch/x86/boot/video-mode.c +++ b/arch/x86/boot/video-mode.c @@ -19,6 +19,8 @@ #include "video.h" #include "vesa.h" +#include <uapi/asm/boot.h> + /* * Common variables */ diff --git a/arch/x86/boot/video.c b/arch/x86/boot/video.c index 05111bb8d018..77780e386e9b 100644 --- a/arch/x86/boot/video.c +++ b/arch/x86/boot/video.c @@ -13,6 +13,8 @@ * Select video mode */ +#include <uapi/asm/boot.h> + #include "boot.h" #include "video.h" #include "vesa.h" diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index aaa1118bf01e..028be48c8839 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -23,6 +23,7 @@ CONFIG_BLK_DEV_INITRD=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y CONFIG_KPROBES=y +CONFIG_JUMP_LABEL=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 315b86106572..cb5b3ab5beec 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -22,6 +22,7 @@ CONFIG_BLK_DEV_INITRD=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y CONFIG_KPROBES=y +CONFIG_JUMP_LABEL=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y @@ -207,7 +208,6 @@ CONFIG_AGP_AMD64=y CONFIG_AGP_INTEL=y CONFIG_DRM=y CONFIG_DRM_I915=y -CONFIG_DRM_I915_KMS=y CONFIG_FB_MODE_HELPERS=y CONFIG_FB_TILEBLITTING=y CONFIG_FB_EFI=y diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index 5a4a089e8b1f..b9b912a44d61 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -5,6 +5,8 @@ avx_supported := $(call as-instr,vpxor %xmm0$(comma)%xmm0$(comma)%xmm0,yes,no) avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\ $(comma)4)$(comma)%ymm2,yes,no) +sha1_ni_supported :=$(call as-instr,sha1msg1 %xmm0$(comma)%xmm1,yes,no) +sha256_ni_supported :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,yes,no) obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o @@ -20,6 +22,7 @@ obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o obj-$(CONFIG_CRYPTO_TWOFISH_X86_64_3WAY) += twofish-x86_64-3way.o obj-$(CONFIG_CRYPTO_SALSA20_X86_64) += salsa20-x86_64.o +obj-$(CONFIG_CRYPTO_CHACHA20_X86_64) += chacha20-x86_64.o obj-$(CONFIG_CRYPTO_SERPENT_SSE2_X86_64) += serpent-sse2-x86_64.o obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o @@ -30,6 +33,7 @@ obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o obj-$(CONFIG_CRYPTO_CRCT10DIF_PCLMUL) += crct10dif-pclmul.o +obj-$(CONFIG_CRYPTO_POLY1305_X86_64) += poly1305-x86_64.o # These modules require assembler to support AVX. ifeq ($(avx_supported),yes) @@ -60,6 +64,7 @@ blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o twofish-x86_64-3way-y := twofish-x86_64-asm_64-3way.o twofish_glue_3way.o salsa20-x86_64-y := salsa20-x86_64-asm_64.o salsa20_glue.o +chacha20-x86_64-y := chacha20-ssse3-x86_64.o chacha20_glue.o serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o ifeq ($(avx_supported),yes) @@ -75,6 +80,7 @@ endif ifeq ($(avx2_supported),yes) camellia-aesni-avx2-y := camellia-aesni-avx2-asm_64.o camellia_aesni_avx2_glue.o + chacha20-x86_64-y += chacha20-avx2-x86_64.o serpent-avx2-y := serpent-avx2-asm_64.o serpent_avx2_glue.o endif @@ -82,12 +88,20 @@ aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o fpu.o aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o aes_ctrby8_avx-x86_64.o ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o +poly1305-x86_64-y := poly1305-sse2-x86_64.o poly1305_glue.o ifeq ($(avx2_supported),yes) sha1-ssse3-y += sha1_avx2_x86_64_asm.o +poly1305-x86_64-y += poly1305-avx2-x86_64.o +endif +ifeq ($(sha1_ni_supported),yes) +sha1-ssse3-y += sha1_ni_asm.o endif crc32c-intel-y := crc32c-intel_glue.o crc32c-intel-$(CONFIG_64BIT) += crc32c-pcl-intel-asm_64.o crc32-pclmul-y := crc32-pclmul_asm.o crc32-pclmul_glue.o sha256-ssse3-y := sha256-ssse3-asm.o sha256-avx-asm.o sha256-avx2-asm.o sha256_ssse3_glue.o +ifeq ($(sha256_ni_supported),yes) +sha256-ssse3-y += sha256_ni_asm.o +endif sha512-ssse3-y := sha512-ssse3-asm.o sha512-avx-asm.o sha512-avx2-asm.o sha512_ssse3_glue.o crct10dif-pclmul-y := crct10dif-pcl-asm_64.o crct10dif-pclmul_glue.o diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index dccad38b59a8..3633ad6145c5 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -803,10 +803,7 @@ static int rfc4106_init(struct crypto_aead *aead) return PTR_ERR(cryptd_tfm); *ctx = cryptd_tfm; - crypto_aead_set_reqsize( - aead, - sizeof(struct aead_request) + - crypto_aead_reqsize(&cryptd_tfm->base)); + crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base)); return 0; } @@ -955,8 +952,8 @@ static int helper_rfc4106_encrypt(struct aead_request *req) /* Assuming we are supporting rfc4106 64-bit extended */ /* sequence numbers We need to have the AAD length equal */ - /* to 8 or 12 bytes */ - if (unlikely(req->assoclen != 8 && req->assoclen != 12)) + /* to 16 or 20 bytes */ + if (unlikely(req->assoclen != 16 && req->assoclen != 20)) return -EINVAL; /* IV below built */ @@ -992,9 +989,9 @@ static int helper_rfc4106_encrypt(struct aead_request *req) } 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); + aesni_gcm_enc_tfm(aes_ctx, dst, src, req->cryptlen, iv, + ctx->hash_subkey, assoc, req->assoclen - 8, + dst + req->cryptlen, auth_tag_len); kernel_fpu_end(); /* The authTag (aka the Integrity Check Value) needs to be written @@ -1033,12 +1030,12 @@ static int helper_rfc4106_decrypt(struct aead_request *req) struct scatter_walk dst_sg_walk; unsigned int i; - if (unlikely(req->assoclen != 8 && req->assoclen != 12)) + if (unlikely(req->assoclen != 16 && req->assoclen != 20)) return -EINVAL; /* Assuming we are supporting rfc4106 64-bit extended */ /* sequence numbers We need to have the AAD length */ - /* equal to 8 or 12 bytes */ + /* equal to 16 or 20 bytes */ tempCipherLen = (unsigned long)(req->cryptlen - auth_tag_len); /* IV below built */ @@ -1075,8 +1072,8 @@ static int helper_rfc4106_decrypt(struct aead_request *req) 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); + ctx->hash_subkey, assoc, req->assoclen - 8, + authTag, auth_tag_len); kernel_fpu_end(); /* Compare generated tag with passed in tag. */ @@ -1105,19 +1102,12 @@ static int rfc4106_encrypt(struct aead_request *req) struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct cryptd_aead **ctx = crypto_aead_ctx(tfm); struct cryptd_aead *cryptd_tfm = *ctx; - struct aead_request *subreq = aead_request_ctx(req); - aead_request_set_tfm(subreq, irq_fpu_usable() ? - cryptd_aead_child(cryptd_tfm) : - &cryptd_tfm->base); + aead_request_set_tfm(req, irq_fpu_usable() ? + cryptd_aead_child(cryptd_tfm) : + &cryptd_tfm->base); - 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); + return crypto_aead_encrypt(req); } static int rfc4106_decrypt(struct aead_request *req) @@ -1125,19 +1115,12 @@ static int rfc4106_decrypt(struct aead_request *req) struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct cryptd_aead **ctx = crypto_aead_ctx(tfm); struct cryptd_aead *cryptd_tfm = *ctx; - struct aead_request *subreq = aead_request_ctx(req); - - aead_request_set_tfm(subreq, irq_fpu_usable() ? - cryptd_aead_child(cryptd_tfm) : - &cryptd_tfm->base); - 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); + aead_request_set_tfm(req, irq_fpu_usable() ? + cryptd_aead_child(cryptd_tfm) : + &cryptd_tfm->base); - return crypto_aead_decrypt(subreq); + return crypto_aead_decrypt(req); } #endif diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c index 4c65c70e628b..d84456924563 100644 --- a/arch/x86/crypto/camellia_aesni_avx2_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c @@ -567,7 +567,8 @@ static int __init camellia_aesni_init(void) return -ENODEV; } - if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) { + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_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 80a0e4389c9a..93d8f295784e 100644 --- a/arch/x86/crypto/camellia_aesni_avx_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx_glue.c @@ -554,7 +554,13 @@ static int __init camellia_aesni_init(void) { const char *feature_name; - if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &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; + } + + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_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 be00aa48b2b5..8648158f3916 100644 --- a/arch/x86/crypto/cast5_avx_glue.c +++ b/arch/x86/crypto/cast5_avx_glue.c @@ -469,7 +469,8 @@ static int __init cast5_init(void) { const char *feature_name; - if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) { + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_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 5dbba7224221..fca459578c35 100644 --- a/arch/x86/crypto/cast6_avx_glue.c +++ b/arch/x86/crypto/cast6_avx_glue.c @@ -591,7 +591,8 @@ static int __init cast6_init(void) { const char *feature_name; - if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) { + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, + &feature_name)) { pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } diff --git a/arch/x86/crypto/chacha20-avx2-x86_64.S b/arch/x86/crypto/chacha20-avx2-x86_64.S new file mode 100644 index 000000000000..16694e625f77 --- /dev/null +++ b/arch/x86/crypto/chacha20-avx2-x86_64.S @@ -0,0 +1,443 @@ +/* + * ChaCha20 256-bit cipher algorithm, RFC7539, x64 AVX2 functions + * + * Copyright (C) 2015 Martin Willi + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/linkage.h> + +.data +.align 32 + +ROT8: .octa 0x0e0d0c0f0a09080b0605040702010003 + .octa 0x0e0d0c0f0a09080b0605040702010003 +ROT16: .octa 0x0d0c0f0e09080b0a0504070601000302 + .octa 0x0d0c0f0e09080b0a0504070601000302 +CTRINC: .octa 0x00000003000000020000000100000000 + .octa 0x00000007000000060000000500000004 + +.text + +ENTRY(chacha20_8block_xor_avx2) + # %rdi: Input state matrix, s + # %rsi: 8 data blocks output, o + # %rdx: 8 data blocks input, i + + # This function encrypts eight consecutive ChaCha20 blocks by loading + # the state matrix in AVX registers eight times. As we need some + # scratch registers, we save the first four registers on the stack. The + # algorithm performs each operation on the corresponding word of each + # state matrix, hence requires no word shuffling. For final XORing step + # we transpose the matrix by interleaving 32-, 64- and then 128-bit + # words, which allows us to do XOR in AVX registers. 8/16-bit word + # rotation is done with the slightly better performing byte shuffling, + # 7/12-bit word rotation uses traditional shift+OR. + + vzeroupper + # 4 * 32 byte stack, 32-byte aligned + mov %rsp, %r8 + and $~31, %rsp + sub $0x80, %rsp + + # x0..15[0-7] = s[0..15] + vpbroadcastd 0x00(%rdi),%ymm0 + vpbroadcastd 0x04(%rdi),%ymm1 + vpbroadcastd 0x08(%rdi),%ymm2 + vpbroadcastd 0x0c(%rdi),%ymm3 + vpbroadcastd 0x10(%rdi),%ymm4 + vpbroadcastd 0x14(%rdi),%ymm5 + vpbroadcastd 0x18(%rdi),%ymm6 + vpbroadcastd 0x1c(%rdi),%ymm7 + vpbroadcastd 0x20(%rdi),%ymm8 + vpbroadcastd 0x24(%rdi),%ymm9 + vpbroadcastd 0x28(%rdi),%ymm10 + vpbroadcastd 0x2c(%rdi),%ymm11 + vpbroadcastd 0x30(%rdi),%ymm12 + vpbroadcastd 0x34(%rdi),%ymm13 + vpbroadcastd 0x38(%rdi),%ymm14 + vpbroadcastd 0x3c(%rdi),%ymm15 + # x0..3 on stack + vmovdqa %ymm0,0x00(%rsp) + vmovdqa %ymm1,0x20(%rsp) + vmovdqa %ymm2,0x40(%rsp) + vmovdqa %ymm3,0x60(%rsp) + + vmovdqa CTRINC(%rip),%ymm1 + vmovdqa ROT8(%rip),%ymm2 + vmovdqa ROT16(%rip),%ymm3 + + # x12 += counter values 0-3 + vpaddd %ymm1,%ymm12,%ymm12 + + mov $10,%ecx + +.Ldoubleround8: + # x0 += x4, x12 = rotl32(x12 ^ x0, 16) + vpaddd 0x00(%rsp),%ymm4,%ymm0 + vmovdqa %ymm0,0x00(%rsp) + vpxor %ymm0,%ymm12,%ymm12 + vpshufb %ymm3,%ymm12,%ymm12 + # x1 += x5, x13 = rotl32(x13 ^ x1, 16) + vpaddd 0x20(%rsp),%ymm5,%ymm0 + vmovdqa %ymm0,0x20(%rsp) + vpxor %ymm0,%ymm13,%ymm13 + vpshufb %ymm3,%ymm13,%ymm13 + # x2 += x6, x14 = rotl32(x14 ^ x2, 16) + vpaddd 0x40(%rsp),%ymm6,%ymm0 + vmovdqa %ymm0,0x40(%rsp) + vpxor %ymm0,%ymm14,%ymm14 + vpshufb %ymm3,%ymm14,%ymm14 + # x3 += x7, x15 = rotl32(x15 ^ x3, 16) + vpaddd 0x60(%rsp),%ymm7,%ymm0 + vmovdqa %ymm0,0x60(%rsp) + vpxor %ymm0,%ymm15,%ymm15 + vpshufb %ymm3,%ymm15,%ymm15 + + # x8 += x12, x4 = rotl32(x4 ^ x8, 12) + vpaddd %ymm12,%ymm8,%ymm8 + vpxor %ymm8,%ymm4,%ymm4 + vpslld $12,%ymm4,%ymm0 + vpsrld $20,%ymm4,%ymm4 + vpor %ymm0,%ymm4,%ymm4 + # x9 += x13, x5 = rotl32(x5 ^ x9, 12) + vpaddd %ymm13,%ymm9,%ymm9 + vpxor %ymm9,%ymm5,%ymm5 + vpslld $12,%ymm5,%ymm0 + vpsrld $20,%ymm5,%ymm5 + vpor %ymm0,%ymm5,%ymm5 + # x10 += x14, x6 = rotl32(x6 ^ x10, 12) + vpaddd %ymm14,%ymm10,%ymm10 + vpxor %ymm10,%ymm6,%ymm6 + vpslld $12,%ymm6,%ymm0 + vpsrld $20,%ymm6,%ymm6 + vpor %ymm0,%ymm6,%ymm6 + # x11 += x15, x7 = rotl32(x7 ^ x11, 12) + vpaddd %ymm15,%ymm11,%ymm11 + vpxor %ymm11,%ymm7,%ymm7 + vpslld $12,%ymm7,%ymm0 + vpsrld $20,%ymm7,%ymm7 + vpor %ymm0,%ymm7,%ymm7 + + # x0 += x4, x12 = rotl32(x12 ^ x0, 8) + vpaddd 0x00(%rsp),%ymm4,%ymm0 + vmovdqa %ymm0,0x00(%rsp) + vpxor %ymm0,%ymm12,%ymm12 + vpshufb %ymm2,%ymm12,%ymm12 + # x1 += x5, x13 = rotl32(x13 ^ x1, 8) + vpaddd 0x20(%rsp),%ymm5,%ymm0 + vmovdqa %ymm0,0x20(%rsp) + vpxor %ymm0,%ymm13,%ymm13 + vpshufb %ymm2,%ymm13,%ymm13 + # x2 += x6, x14 = rotl32(x14 ^ x2, 8) + vpaddd 0x40(%rsp),%ymm6,%ymm0 + vmovdqa %ymm0,0x40(%rsp) + vpxor %ymm0,%ymm14,%ymm14 + vpshufb %ymm2,%ymm14,%ymm14 + # x3 += x7, x15 = rotl32(x15 ^ x3, 8) + vpaddd 0x60(%rsp),%ymm7,%ymm0 + vmovdqa %ymm0,0x60(%rsp) + vpxor %ymm0,%ymm15,%ymm15 + vpshufb %ymm2,%ymm15,%ymm15 + + # x8 += x12, x4 = rotl32(x4 ^ x8, 7) + vpaddd %ymm12,%ymm8,%ymm8 + vpxor %ymm8,%ymm4,%ymm4 + vpslld $7,%ymm4,%ymm0 + vpsrld $25,%ymm4,%ymm4 + vpor %ymm0,%ymm4,%ymm4 + # x9 += x13, x5 = rotl32(x5 ^ x9, 7) + vpaddd %ymm13,%ymm9,%ymm9 + vpxor %ymm9,%ymm5,%ymm5 + vpslld $7,%ymm5,%ymm0 + vpsrld $25,%ymm5,%ymm5 + vpor %ymm0,%ymm5,%ymm5 + # x10 += x14, x6 = rotl32(x6 ^ x10, 7) + vpaddd %ymm14,%ymm10,%ymm10 + vpxor %ymm10,%ymm6,%ymm6 + vpslld $7,%ymm6,%ymm0 + vpsrld $25,%ymm6,%ymm6 + vpor %ymm0,%ymm6,%ymm6 + # x11 += x15, x7 = rotl32(x7 ^ x11, 7) + vpaddd %ymm15,%ymm11,%ymm11 + vpxor %ymm11,%ymm7,%ymm7 + vpslld $7,%ymm7,%ymm0 + vpsrld $25,%ymm7,%ymm7 + vpor %ymm0,%ymm7,%ymm7 + + # x0 += x5, x15 = rotl32(x15 ^ x0, 16) + vpaddd 0x00(%rsp),%ymm5,%ymm0 + vmovdqa %ymm0,0x00(%rsp) + vpxor %ymm0,%ymm15,%ymm15 + vpshufb %ymm3,%ymm15,%ymm15 + # x1 += x6, x12 = rotl32(x12 ^ x1, 16)%ymm0 + vpaddd 0x20(%rsp),%ymm6,%ymm0 + vmovdqa %ymm0,0x20(%rsp) + vpxor %ymm0,%ymm12,%ymm12 + vpshufb %ymm3,%ymm12,%ymm12 + # x2 += x7, x13 = rotl32(x13 ^ x2, 16) + vpaddd 0x40(%rsp),%ymm7,%ymm0 + vmovdqa %ymm0,0x40(%rsp) + vpxor %ymm0,%ymm13,%ymm13 + vpshufb %ymm3,%ymm13,%ymm13 + # x3 += x4, x14 = rotl32(x14 ^ x3, 16) + vpaddd 0x60(%rsp),%ymm4,%ymm0 + vmovdqa %ymm0,0x60(%rsp) + vpxor %ymm0,%ymm14,%ymm14 + vpshufb %ymm3,%ymm14,%ymm14 + + # x10 += x15, x5 = rotl32(x5 ^ x10, 12) + vpaddd %ymm15,%ymm10,%ymm10 + vpxor %ymm10,%ymm5,%ymm5 + vpslld $12,%ymm5,%ymm0 + vpsrld $20,%ymm5,%ymm5 + vpor %ymm0,%ymm5,%ymm5 + # x11 += x12, x6 = rotl32(x6 ^ x11, 12) + vpaddd %ymm12,%ymm11,%ymm11 + vpxor %ymm11,%ymm6,%ymm6 + vpslld $12,%ymm6,%ymm0 + vpsrld $20,%ymm6,%ymm6 + vpor %ymm0,%ymm6,%ymm6 + # x8 += x13, x7 = rotl32(x7 ^ x8, 12) + vpaddd %ymm13,%ymm8,%ymm8 + vpxor %ymm8,%ymm7,%ymm7 + vpslld $12,%ymm7,%ymm0 + vpsrld $20,%ymm7,%ymm7 + vpor %ymm0,%ymm7,%ymm7 + # x9 += x14, x4 = rotl32(x4 ^ x9, 12) + vpaddd %ymm14,%ymm9,%ymm9 + vpxor %ymm9,%ymm4,%ymm4 + vpslld $12,%ymm4,%ymm0 + vpsrld $20,%ymm4,%ymm4 + vpor %ymm0,%ymm4,%ymm4 + + # x0 += x5, x15 = rotl32(x15 ^ x0, 8) + vpaddd 0x00(%rsp),%ymm5,%ymm0 + vmovdqa %ymm0,0x00(%rsp) + vpxor %ymm0,%ymm15,%ymm15 + vpshufb %ymm2,%ymm15,%ymm15 + # x1 += x6, x12 = rotl32(x12 ^ x1, 8) + vpaddd 0x20(%rsp),%ymm6,%ymm0 + vmovdqa %ymm0,0x20(%rsp) + vpxor %ymm0,%ymm12,%ymm12 + vpshufb %ymm2,%ymm12,%ymm12 + # x2 += x7, x13 = rotl32(x13 ^ x2, 8) + vpaddd 0x40(%rsp),%ymm7,%ymm0 + vmovdqa %ymm0,0x40(%rsp) + vpxor %ymm0,%ymm13,%ymm13 + vpshufb %ymm2,%ymm13,%ymm13 + # x3 += x4, x14 = rotl32(x14 ^ x3, 8) + vpaddd 0x60(%rsp),%ymm4,%ymm0 + vmovdqa %ymm0,0x60(%rsp) + vpxor %ymm0,%ymm14,%ymm14 + vpshufb %ymm2,%ymm14,%ymm14 + + # x10 += x15, x5 = rotl32(x5 ^ x10, 7) + vpaddd %ymm15,%ymm10,%ymm10 + vpxor %ymm10,%ymm5,%ymm5 + vpslld $7,%ymm5,%ymm0 + vpsrld $25,%ymm5,%ymm5 + vpor %ymm0,%ymm5,%ymm5 + # x11 += x12, x6 = rotl32(x6 ^ x11, 7) + vpaddd %ymm12,%ymm11,%ymm11 + vpxor %ymm11,%ymm6,%ymm6 + vpslld $7,%ymm6,%ymm0 + vpsrld $25,%ymm6,%ymm6 + vpor %ymm0,%ymm6,%ymm6 + # x8 += x13, x7 = rotl32(x7 ^ x8, 7) + vpaddd %ymm13,%ymm8,%ymm8 + vpxor %ymm8,%ymm7,%ymm7 + vpslld $7,%ymm7,%ymm0 + vpsrld $25,%ymm7,%ymm7 + vpor %ymm0,%ymm7,%ymm7 + # x9 += x14, x4 = rotl32(x4 ^ x9, 7) + vpaddd %ymm14,%ymm9,%ymm9 + vpxor %ymm9,%ymm4,%ymm4 + vpslld $7,%ymm4,%ymm0 + vpsrld $25,%ymm4,%ymm4 + vpor %ymm0,%ymm4,%ymm4 + + dec %ecx + jnz .Ldoubleround8 + + # x0..15[0-3] += s[0..15] + vpbroadcastd 0x00(%rdi),%ymm0 + vpaddd 0x00(%rsp),%ymm0,%ymm0 + vmovdqa %ymm0,0x00(%rsp) + vpbroadcastd 0x04(%rdi),%ymm0 + vpaddd 0x20(%rsp),%ymm0,%ymm0 + vmovdqa %ymm0,0x20(%rsp) + vpbroadcastd 0x08(%rdi),%ymm0 + vpaddd 0x40(%rsp),%ymm0,%ymm0 + vmovdqa %ymm0,0x40(%rsp) + vpbroadcastd 0x0c(%rdi),%ymm0 + vpaddd 0x60(%rsp),%ymm0,%ymm0 + vmovdqa %ymm0,0x60(%rsp) + vpbroadcastd 0x10(%rdi),%ymm0 + vpaddd %ymm0,%ymm4,%ymm4 + vpbroadcastd 0x14(%rdi),%ymm0 + vpaddd %ymm0,%ymm5,%ymm5 + vpbroadcastd 0x18(%rdi),%ymm0 + vpaddd %ymm0,%ymm6,%ymm6 + vpbroadcastd 0x1c(%rdi),%ymm0 + vpaddd %ymm0,%ymm7,%ymm7 + vpbroadcastd 0x20(%rdi),%ymm0 + vpaddd %ymm0,%ymm8,%ymm8 + vpbroadcastd 0x24(%rdi),%ymm0 + vpaddd %ymm0,%ymm9,%ymm9 + vpbroadcastd 0x28(%rdi),%ymm0 + vpaddd %ymm0,%ymm10,%ymm10 + vpbroadcastd 0x2c(%rdi),%ymm0 + vpaddd %ymm0,%ymm11,%ymm11 + vpbroadcastd 0x30(%rdi),%ymm0 + vpaddd %ymm0,%ymm12,%ymm12 + vpbroadcastd 0x34(%rdi),%ymm0 + vpaddd %ymm0,%ymm13,%ymm13 + vpbroadcastd 0x38(%rdi),%ymm0 + vpaddd %ymm0,%ymm14,%ymm14 + vpbroadcastd 0x3c(%rdi),%ymm0 + vpaddd %ymm0,%ymm15,%ymm15 + + # x12 += counter values 0-3 + vpaddd %ymm1,%ymm12,%ymm12 + + # interleave 32-bit words in state n, n+1 + vmovdqa 0x00(%rsp),%ymm0 + vmovdqa 0x20(%rsp),%ymm1 + vpunpckldq %ymm1,%ymm0,%ymm2 + vpunpckhdq %ymm1,%ymm0,%ymm1 + vmovdqa %ymm2,0x00(%rsp) + vmovdqa %ymm1,0x20(%rsp) + vmovdqa 0x40(%rsp),%ymm0 + vmovdqa 0x60(%rsp),%ymm1 + vpunpckldq %ymm1,%ymm0,%ymm2 + vpunpckhdq %ymm1,%ymm0,%ymm1 + vmovdqa %ymm2,0x40(%rsp) + vmovdqa %ymm1,0x60(%rsp) + vmovdqa %ymm4,%ymm0 + vpunpckldq %ymm5,%ymm0,%ymm4 + vpunpckhdq %ymm5,%ymm0,%ymm5 + vmovdqa %ymm6,%ymm0 + vpunpckldq %ymm7,%ymm0,%ymm6 + vpunpckhdq %ymm7,%ymm0,%ymm7 + vmovdqa %ymm8,%ymm0 + vpunpckldq %ymm9,%ymm0,%ymm8 + vpunpckhdq %ymm9,%ymm0,%ymm9 + vmovdqa %ymm10,%ymm0 + vpunpckldq %ymm11,%ymm0,%ymm10 + vpunpckhdq %ymm11,%ymm0,%ymm11 + vmovdqa %ymm12,%ymm0 + vpunpckldq %ymm13,%ymm0,%ymm12 + vpunpckhdq %ymm13,%ymm0,%ymm13 + vmovdqa %ymm14,%ymm0 + vpunpckldq %ymm15,%ymm0,%ymm14 + vpunpckhdq %ymm15,%ymm0,%ymm15 + + # interleave 64-bit words in state n, n+2 + vmovdqa 0x00(%rsp),%ymm0 + vmovdqa 0x40(%rsp),%ymm2 + vpunpcklqdq %ymm2,%ymm0,%ymm1 + vpunpckhqdq %ymm2,%ymm0,%ymm2 + vmovdqa %ymm1,0x00(%rsp) + vmovdqa %ymm2,0x40(%rsp) + vmovdqa 0x20(%rsp),%ymm0 + vmovdqa 0x60(%rsp),%ymm2 + vpunpcklqdq %ymm2,%ymm0,%ymm1 + vpunpckhqdq %ymm2,%ymm0,%ymm2 + vmovdqa %ymm1,0x20(%rsp) + vmovdqa %ymm2,0x60(%rsp) + vmovdqa %ymm4,%ymm0 + vpunpcklqdq %ymm6,%ymm0,%ymm4 + vpunpckhqdq %ymm6,%ymm0,%ymm6 + vmovdqa %ymm5,%ymm0 + vpunpcklqdq %ymm7,%ymm0,%ymm5 + vpunpckhqdq %ymm7,%ymm0,%ymm7 + vmovdqa %ymm8,%ymm0 + vpunpcklqdq %ymm10,%ymm0,%ymm8 + vpunpckhqdq %ymm10,%ymm0,%ymm10 + vmovdqa %ymm9,%ymm0 + vpunpcklqdq %ymm11,%ymm0,%ymm9 + vpunpckhqdq %ymm11,%ymm0,%ymm11 + vmovdqa %ymm12,%ymm0 + vpunpcklqdq %ymm14,%ymm0,%ymm12 + vpunpckhqdq %ymm14,%ymm0,%ymm14 + vmovdqa %ymm13,%ymm0 + vpunpcklqdq %ymm15,%ymm0,%ymm13 + vpunpckhqdq %ymm15,%ymm0,%ymm15 + + # interleave 128-bit words in state n, n+4 + vmovdqa 0x00(%rsp),%ymm0 + vperm2i128 $0x20,%ymm4,%ymm0,%ymm1 + vperm2i128 $0x31,%ymm4,%ymm0,%ymm4 + vmovdqa %ymm1,0x00(%rsp) + vmovdqa 0x20(%rsp),%ymm0 + vperm2i128 $0x20,%ymm5,%ymm0,%ymm1 + vperm2i128 $0x31,%ymm5,%ymm0,%ymm5 + vmovdqa %ymm1,0x20(%rsp) + vmovdqa 0x40(%rsp),%ymm0 + vperm2i128 $0x20,%ymm6,%ymm0,%ymm1 + vperm2i128 $0x31,%ymm6,%ymm0,%ymm6 + vmovdqa %ymm1,0x40(%rsp) + vmovdqa 0x60(%rsp),%ymm0 + vperm2i128 $0x20,%ymm7,%ymm0,%ymm1 + vperm2i128 $0x31,%ymm7,%ymm0,%ymm7 + vmovdqa %ymm1,0x60(%rsp) + vperm2i128 $0x20,%ymm12,%ymm8,%ymm0 + vperm2i128 $0x31,%ymm12,%ymm8,%ymm12 + vmovdqa %ymm0,%ymm8 + vperm2i128 $0x20,%ymm13,%ymm9,%ymm0 + vperm2i128 $0x31,%ymm13,%ymm9,%ymm13 + vmovdqa %ymm0,%ymm9 + vperm2i128 $0x20,%ymm14,%ymm10,%ymm0 + vperm2i128 $0x31,%ymm14,%ymm10,%ymm14 + vmovdqa %ymm0,%ymm10 + vperm2i128 $0x20,%ymm15,%ymm11,%ymm0 + vperm2i128 $0x31,%ymm15,%ymm11,%ymm15 + vmovdqa %ymm0,%ymm11 + + # xor with corresponding input, write to output + vmovdqa 0x00(%rsp),%ymm0 + vpxor 0x0000(%rdx),%ymm0,%ymm0 + vmovdqu %ymm0,0x0000(%rsi) + vmovdqa 0x20(%rsp),%ymm0 + vpxor 0x0080(%rdx),%ymm0,%ymm0 + vmovdqu %ymm0,0x0080(%rsi) + vmovdqa 0x40(%rsp),%ymm0 + vpxor 0x0040(%rdx),%ymm0,%ymm0 + vmovdqu %ymm0,0x0040(%rsi) + vmovdqa 0x60(%rsp),%ymm0 + vpxor 0x00c0(%rdx),%ymm0,%ymm0 + vmovdqu %ymm0,0x00c0(%rsi) + vpxor 0x0100(%rdx),%ymm4,%ymm4 + vmovdqu %ymm4,0x0100(%rsi) + vpxor 0x0180(%rdx),%ymm5,%ymm5 + vmovdqu %ymm5,0x00180(%rsi) + vpxor 0x0140(%rdx),%ymm6,%ymm6 + vmovdqu %ymm6,0x0140(%rsi) + vpxor 0x01c0(%rdx),%ymm7,%ymm7 + vmovdqu %ymm7,0x01c0(%rsi) + vpxor 0x0020(%rdx),%ymm8,%ymm8 + vmovdqu %ymm8,0x0020(%rsi) + vpxor 0x00a0(%rdx),%ymm9,%ymm9 + vmovdqu %ymm9,0x00a0(%rsi) + vpxor 0x0060(%rdx),%ymm10,%ymm10 + vmovdqu %ymm10,0x0060(%rsi) + vpxor 0x00e0(%rdx),%ymm11,%ymm11 + vmovdqu %ymm11,0x00e0(%rsi) + vpxor 0x0120(%rdx),%ymm12,%ymm12 + vmovdqu %ymm12,0x0120(%rsi) + vpxor 0x01a0(%rdx),%ymm13,%ymm13 + vmovdqu %ymm13,0x01a0(%rsi) + vpxor 0x0160(%rdx),%ymm14,%ymm14 + vmovdqu %ymm14,0x0160(%rsi) + vpxor 0x01e0(%rdx),%ymm15,%ymm15 + vmovdqu %ymm15,0x01e0(%rsi) + + vzeroupper + mov %r8,%rsp + ret +ENDPROC(chacha20_8block_xor_avx2) diff --git a/arch/x86/crypto/chacha20-ssse3-x86_64.S b/arch/x86/crypto/chacha20-ssse3-x86_64.S new file mode 100644 index 000000000000..712b13047b41 --- /dev/null +++ b/arch/x86/crypto/chacha20-ssse3-x86_64.S @@ -0,0 +1,625 @@ +/* + * ChaCha20 256-bit cipher algorithm, RFC7539, x64 SSSE3 functions + * + * Copyright (C) 2015 Martin Willi + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/linkage.h> + +.data +.align 16 + +ROT8: .octa 0x0e0d0c0f0a09080b0605040702010003 +ROT16: .octa 0x0d0c0f0e09080b0a0504070601000302 +CTRINC: .octa 0x00000003000000020000000100000000 + +.text + +ENTRY(chacha20_block_xor_ssse3) + # %rdi: Input state matrix, s + # %rsi: 1 data block output, o + # %rdx: 1 data block input, i + + # This function encrypts one ChaCha20 block by loading the state matrix + # in four SSE registers. It performs matrix operation on four words in + # parallel, but requireds shuffling to rearrange the words after each + # round. 8/16-bit word rotation is done with the slightly better + # performing SSSE3 byte shuffling, 7/12-bit word rotation uses + # traditional shift+OR. + + # x0..3 = s0..3 + movdqa 0x00(%rdi),%xmm0 + movdqa 0x10(%rdi),%xmm1 + movdqa 0x20(%rdi),%xmm2 + movdqa 0x30(%rdi),%xmm3 + movdqa %xmm0,%xmm8 + movdqa %xmm1,%xmm9 + movdqa %xmm2,%xmm10 + movdqa %xmm3,%xmm11 + + movdqa ROT8(%rip),%xmm4 + movdqa ROT16(%rip),%xmm5 + + mov $10,%ecx + +.Ldoubleround: + + # x0 += x1, x3 = rotl32(x3 ^ x0, 16) + paddd %xmm1,%xmm0 + pxor %xmm0,%xmm3 + pshufb %xmm5,%xmm3 + + # x2 += x3, x1 = rotl32(x1 ^ x2, 12) + paddd %xmm3,%xmm2 + pxor %xmm2,%xmm1 + movdqa %xmm1,%xmm6 + pslld $12,%xmm6 + psrld $20,%xmm1 + por %xmm6,%xmm1 + + # x0 += x1, x3 = rotl32(x3 ^ x0, 8) + paddd %xmm1,%xmm0 + pxor %xmm0,%xmm3 + pshufb %xmm4,%xmm3 + + # x2 += x3, x1 = rotl32(x1 ^ x2, 7) + paddd %xmm3,%xmm2 + pxor %xmm2,%xmm1 + movdqa %xmm1,%xmm7 + pslld $7,%xmm7 + psrld $25,%xmm1 + por %xmm7,%xmm1 + + # x1 = shuffle32(x1, MASK(0, 3, 2, 1)) + pshufd $0x39,%xmm1,%xmm1 + # x2 = shuffle32(x2, MASK(1, 0, 3, 2)) + pshufd $0x4e,%xmm2,%xmm2 + # x3 = shuffle32(x3, MASK(2, 1, 0, 3)) + pshufd $0x93,%xmm3,%xmm3 + + # x0 += x1, x3 = rotl32(x3 ^ x0, 16) + paddd %xmm1,%xmm0 + pxor %xmm0,%xmm3 + pshufb %xmm5,%xmm3 + + # x2 += x3, x1 = rotl32(x1 ^ x2, 12) + paddd %xmm3,%xmm2 + pxor %xmm2,%xmm1 + movdqa %xmm1,%xmm6 + pslld $12,%xmm6 + psrld $20,%xmm1 + por %xmm6,%xmm1 + + # x0 += x1, x3 = rotl32(x3 ^ x0, 8) + paddd %xmm1,%xmm0 + pxor %xmm0,%xmm3 + pshufb %xmm4,%xmm3 + + # x2 += x3, x1 = rotl32(x1 ^ x2, 7) + paddd %xmm3,%xmm2 + pxor %xmm2,%xmm1 + movdqa %xmm1,%xmm7 + pslld $7,%xmm7 + psrld $25,%xmm1 + por %xmm7,%xmm1 + + # x1 = shuffle32(x1, MASK(2, 1, 0, 3)) + pshufd $0x93,%xmm1,%xmm1 + # x2 = shuffle32(x2, MASK(1, 0, 3, 2)) + pshufd $0x4e,%xmm2,%xmm2 + # x3 = shuffle32(x3, MASK(0, 3, 2, 1)) + pshufd $0x39,%xmm3,%xmm3 + + dec %ecx + jnz .Ldoubleround + + # o0 = i0 ^ (x0 + s0) + movdqu 0x00(%rdx),%xmm4 + paddd %xmm8,%xmm0 + pxor %xmm4,%xmm0 + movdqu %xmm0,0x00(%rsi) + # o1 = i1 ^ (x1 + s1) + movdqu 0x10(%rdx),%xmm5 + paddd %xmm9,%xmm1 + pxor %xmm5,%xmm1 + movdqu %xmm1,0x10(%rsi) + # o2 = i2 ^ (x2 + s2) + movdqu 0x20(%rdx),%xmm6 + paddd %xmm10,%xmm2 + pxor %xmm6,%xmm2 + movdqu %xmm2,0x20(%rsi) + # o3 = i3 ^ (x3 + s3) + movdqu 0x30(%rdx),%xmm7 + paddd %xmm11,%xmm3 + pxor %xmm7,%xmm3 + movdqu %xmm3,0x30(%rsi) + + ret +ENDPROC(chacha20_block_xor_ssse3) + +ENTRY(chacha20_4block_xor_ssse3) + # %rdi: Input state matrix, s + # %rsi: 4 data blocks output, o + # %rdx: 4 data blocks input, i + + # This function encrypts four consecutive ChaCha20 blocks by loading the + # the state matrix in SSE registers four times. As we need some scratch + # registers, we save the first four registers on the stack. The + # algorithm performs each operation on the corresponding word of each + # state matrix, hence requires no word shuffling. For final XORing step + # we transpose the matrix by interleaving 32- and then 64-bit words, + # which allows us to do XOR in SSE registers. 8/16-bit word rotation is + # done with the slightly better performing SSSE3 byte shuffling, + # 7/12-bit word rotation uses traditional shift+OR. + + sub $0x40,%rsp + + # x0..15[0-3] = s0..3[0..3] + movq 0x00(%rdi),%xmm1 + pshufd $0x00,%xmm1,%xmm0 + pshufd $0x55,%xmm1,%xmm1 + movq 0x08(%rdi),%xmm3 + pshufd $0x00,%xmm3,%xmm2 + pshufd $0x55,%xmm3,%xmm3 + movq 0x10(%rdi),%xmm5 + pshufd $0x00,%xmm5,%xmm4 + pshufd $0x55,%xmm5,%xmm5 + movq 0x18(%rdi),%xmm7 + pshufd $0x00,%xmm7,%xmm6 + pshufd $0x55,%xmm7,%xmm7 + movq 0x20(%rdi),%xmm9 + pshufd $0x00,%xmm9,%xmm8 + pshufd $0x55,%xmm9,%xmm9 + movq 0x28(%rdi),%xmm11 + pshufd $0x00,%xmm11,%xmm10 + pshufd $0x55,%xmm11,%xmm11 + movq 0x30(%rdi),%xmm13 + pshufd $0x00,%xmm13,%xmm12 + pshufd $0x55,%xmm13,%xmm13 + movq 0x38(%rdi),%xmm15 + pshufd $0x00,%xmm15,%xmm14 + pshufd $0x55,%xmm15,%xmm15 + # x0..3 on stack + movdqa %xmm0,0x00(%rsp) + movdqa %xmm1,0x10(%rsp) + movdqa %xmm2,0x20(%rsp) + movdqa %xmm3,0x30(%rsp) + + movdqa CTRINC(%rip),%xmm1 + movdqa ROT8(%rip),%xmm2 + movdqa ROT16(%rip),%xmm3 + + # x12 += counter values 0-3 + paddd %xmm1,%xmm12 + + mov $10,%ecx + +.Ldoubleround4: + # x0 += x4, x12 = rotl32(x12 ^ x0, 16) + movdqa 0x00(%rsp),%xmm0 + paddd %xmm4,%xmm0 + movdqa %xmm0,0x00(%rsp) + pxor %xmm0,%xmm12 + pshufb %xmm3,%xmm12 + # x1 += x5, x13 = rotl32(x13 ^ x1, 16) + movdqa 0x10(%rsp),%xmm0 + paddd %xmm5,%xmm0 + movdqa %xmm0,0x10(%rsp) + pxor %xmm0,%xmm13 + pshufb %xmm3,%xmm13 + # x2 += x6, x14 = rotl32(x14 ^ x2, 16) + movdqa 0x20(%rsp),%xmm0 + paddd %xmm6,%xmm0 + movdqa %xmm0,0x20(%rsp) + pxor %xmm0,%xmm14 + pshufb %xmm3,%xmm14 + # x3 += x7, x15 = rotl32(x15 ^ x3, 16) + movdqa 0x30(%rsp),%xmm0 + paddd %xmm7,%xmm0 + movdqa %xmm0,0x30(%rsp) + pxor %xmm0,%xmm15 + pshufb %xmm3,%xmm15 + + # x8 += x12, x4 = rotl32(x4 ^ x8, 12) + paddd %xmm12,%xmm8 + pxor %xmm8,%xmm4 + movdqa %xmm4,%xmm0 + pslld $12,%xmm0 + psrld $20,%xmm4 + por %xmm0,%xmm4 + # x9 += x13, x5 = rotl32(x5 ^ x9, 12) + paddd %xmm13,%xmm9 + pxor %xmm9,%xmm5 + movdqa %xmm5,%xmm0 + pslld $12,%xmm0 + psrld $20,%xmm5 + por %xmm0,%xmm5 + # x10 += x14, x6 = rotl32(x6 ^ x10, 12) + paddd %xmm14,%xmm10 + pxor %xmm10,%xmm6 + movdqa %xmm6,%xmm0 + pslld $12,%xmm0 + psrld $20,%xmm6 + por %xmm0,%xmm6 + # x11 += x15, x7 = rotl32(x7 ^ x11, 12) + paddd %xmm15,%xmm11 + pxor %xmm11,%xmm7 + movdqa %xmm7,%xmm0 + pslld $12,%xmm0 + psrld $20,%xmm7 + por %xmm0,%xmm7 + + # x0 += x4, x12 = rotl32(x12 ^ x0, 8) + movdqa 0x00(%rsp),%xmm0 + paddd %xmm4,%xmm0 + movdqa %xmm0,0x00(%rsp) + pxor %xmm0,%xmm12 + pshufb %xmm2,%xmm12 + # x1 += x5, x13 = rotl32(x13 ^ x1, 8) + movdqa 0x10(%rsp),%xmm0 + paddd %xmm5,%xmm0 + movdqa %xmm0,0x10(%rsp) + pxor %xmm0,%xmm13 + pshufb %xmm2,%xmm13 + # x2 += x6, x14 = rotl32(x14 ^ x2, 8) + movdqa 0x20(%rsp),%xmm0 + paddd %xmm6,%xmm0 + movdqa %xmm0,0x20(%rsp) + pxor %xmm0,%xmm14 + pshufb %xmm2,%xmm14 + # x3 += x7, x15 = rotl32(x15 ^ x3, 8) + movdqa 0x30(%rsp),%xmm0 + paddd %xmm7,%xmm0 + movdqa %xmm0,0x30(%rsp) + pxor %xmm0,%xmm15 + pshufb %xmm2,%xmm15 + + # x8 += x12, x4 = rotl32(x4 ^ x8, 7) + paddd %xmm12,%xmm8 + pxor %xmm8,%xmm4 + movdqa %xmm4,%xmm0 + pslld $7,%xmm0 + psrld $25,%xmm4 + por %xmm0,%xmm4 + # x9 += x13, x5 = rotl32(x5 ^ x9, 7) + paddd %xmm13,%xmm9 + pxor %xmm9,%xmm5 + movdqa %xmm5,%xmm0 + pslld $7,%xmm0 + psrld $25,%xmm5 + por %xmm0,%xmm5 + # x10 += x14, x6 = rotl32(x6 ^ x10, 7) + paddd %xmm14,%xmm10 + pxor %xmm10,%xmm6 + movdqa %xmm6,%xmm0 + pslld $7,%xmm0 + psrld $25,%xmm6 + por %xmm0,%xmm6 + # x11 += x15, x7 = rotl32(x7 ^ x11, 7) + paddd %xmm15,%xmm11 + pxor %xmm11,%xmm7 + movdqa %xmm7,%xmm0 + pslld $7,%xmm0 + psrld $25,%xmm7 + por %xmm0,%xmm7 + + # x0 += x5, x15 = rotl32(x15 ^ x0, 16) + movdqa 0x00(%rsp),%xmm0 + paddd %xmm5,%xmm0 + movdqa %xmm0,0x00(%rsp) + pxor %xmm0,%xmm15 + pshufb %xmm3,%xmm15 + # x1 += x6, x12 = rotl32(x12 ^ x1, 16) + movdqa 0x10(%rsp),%xmm0 + paddd %xmm6,%xmm0 + movdqa %xmm0,0x10(%rsp) + pxor %xmm0,%xmm12 + pshufb %xmm3,%xmm12 + # x2 += x7, x13 = rotl32(x13 ^ x2, 16) + movdqa 0x20(%rsp),%xmm0 + paddd %xmm7,%xmm0 + movdqa %xmm0,0x20(%rsp) + pxor %xmm0,%xmm13 + pshufb %xmm3,%xmm13 + # x3 += x4, x14 = rotl32(x14 ^ x3, 16) + movdqa 0x30(%rsp),%xmm0 + paddd %xmm4,%xmm0 + movdqa %xmm0,0x30(%rsp) + pxor %xmm0,%xmm14 + pshufb %xmm3,%xmm14 + + # x10 += x15, x5 = rotl32(x5 ^ x10, 12) + paddd %xmm15,%xmm10 + pxor %xmm10,%xmm5 + movdqa %xmm5,%xmm0 + pslld $12,%xmm0 + psrld $20,%xmm5 + por %xmm0,%xmm5 + # x11 += x12, x6 = rotl32(x6 ^ x11, 12) + paddd %xmm12,%xmm11 + pxor %xmm11,%xmm6 + movdqa %xmm6,%xmm0 + pslld $12,%xmm0 + psrld $20,%xmm6 + por %xmm0,%xmm6 + # x8 += x13, x7 = rotl32(x7 ^ x8, 12) + paddd %xmm13,%xmm8 + pxor %xmm8,%xmm7 + movdqa %xmm7,%xmm0 + pslld $12,%xmm0 + psrld $20,%xmm7 + por %xmm0,%xmm7 + # x9 += x14, x4 = rotl32(x4 ^ x9, 12) + paddd %xmm14,%xmm9 + pxor %xmm9,%xmm4 + movdqa %xmm4,%xmm0 + pslld $12,%xmm0 + psrld $20,%xmm4 + por %xmm0,%xmm4 + + # x0 += x5, x15 = rotl32(x15 ^ x0, 8) + movdqa 0x00(%rsp),%xmm0 + paddd %xmm5,%xmm0 + movdqa %xmm0,0x00(%rsp) + pxor %xmm0,%xmm15 + pshufb %xmm2,%xmm15 + # x1 += x6, x12 = rotl32(x12 ^ x1, 8) + movdqa 0x10(%rsp),%xmm0 + paddd %xmm6,%xmm0 + movdqa %xmm0,0x10(%rsp) + pxor %xmm0,%xmm12 + pshufb %xmm2,%xmm12 + # x2 += x7, x13 = rotl32(x13 ^ x2, 8) + movdqa 0x20(%rsp),%xmm0 + paddd %xmm7,%xmm0 + movdqa %xmm0,0x20(%rsp) + pxor %xmm0,%xmm13 + pshufb %xmm2,%xmm13 + # x3 += x4, x14 = rotl32(x14 ^ x3, 8) + movdqa 0x30(%rsp),%xmm0 + paddd %xmm4,%xmm0 + movdqa %xmm0,0x30(%rsp) + pxor %xmm0,%xmm14 + pshufb %xmm2,%xmm14 + + # x10 += x15, x5 = rotl32(x5 ^ x10, 7) + paddd %xmm15,%xmm10 + pxor %xmm10,%xmm5 + movdqa %xmm5,%xmm0 + pslld $7,%xmm0 + psrld $25,%xmm5 + por %xmm0,%xmm5 + # x11 += x12, x6 = rotl32(x6 ^ x11, 7) + paddd %xmm12,%xmm11 + pxor %xmm11,%xmm6 + movdqa %xmm6,%xmm0 + pslld $7,%xmm0 + psrld $25,%xmm6 + por %xmm0,%xmm6 + # x8 += x13, x7 = rotl32(x7 ^ x8, 7) + paddd %xmm13,%xmm8 + pxor %xmm8,%xmm7 + movdqa %xmm7,%xmm0 + pslld $7,%xmm0 + psrld $25,%xmm7 + por %xmm0,%xmm7 + # x9 += x14, x4 = rotl32(x4 ^ x9, 7) + paddd %xmm14,%xmm9 + pxor %xmm9,%xmm4 + movdqa %xmm4,%xmm0 + pslld $7,%xmm0 + psrld $25,%xmm4 + por %xmm0,%xmm4 + + dec %ecx + jnz .Ldoubleround4 + + # x0[0-3] += s0[0] + # x1[0-3] += s0[1] + movq 0x00(%rdi),%xmm3 + pshufd $0x00,%xmm3,%xmm2 + pshufd $0x55,%xmm3,%xmm3 + paddd 0x00(%rsp),%xmm2 + movdqa %xmm2,0x00(%rsp) + paddd 0x10(%rsp),%xmm3 + movdqa %xmm3,0x10(%rsp) + # x2[0-3] += s0[2] + # x3[0-3] += s0[3] + movq 0x08(%rdi),%xmm3 + pshufd $0x00,%xmm3,%xmm2 + pshufd $0x55,%xmm3,%xmm3 + paddd 0x20(%rsp),%xmm2 + movdqa %xmm2,0x20(%rsp) + paddd 0x30(%rsp),%xmm3 + movdqa %xmm3,0x30(%rsp) + + # x4[0-3] += s1[0] + # x5[0-3] += s1[1] + movq 0x10(%rdi),%xmm3 + pshufd $0x00,%xmm3,%xmm2 + pshufd $0x55,%xmm3,%xmm3 + paddd %xmm2,%xmm4 + paddd %xmm3,%xmm5 + # x6[0-3] += s1[2] + # x7[0-3] += s1[3] + movq 0x18(%rdi),%xmm3 + pshufd $0x00,%xmm3,%xmm2 + pshufd $0x55,%xmm3,%xmm3 + paddd %xmm2,%xmm6 + paddd %xmm3,%xmm7 + + # x8[0-3] += s2[0] + # x9[0-3] += s2[1] + movq 0x20(%rdi),%xmm3 + pshufd $0x00,%xmm3,%xmm2 + pshufd $0x55,%xmm3,%xmm3 + paddd %xmm2,%xmm8 + paddd %xmm3,%xmm9 + # x10[0-3] += s2[2] + # x11[0-3] += s2[3] + movq 0x28(%rdi),%xmm3 + pshufd $0x00,%xmm3,%xmm2 + pshufd $0x55,%xmm3,%xmm3 + paddd %xmm2,%xmm10 + paddd %xmm3,%xmm11 + + # x12[0-3] += s3[0] + # x13[0-3] += s3[1] + movq 0x30(%rdi),%xmm3 + pshufd $0x00,%xmm3,%xmm2 + pshufd $0x55,%xmm3,%xmm3 + paddd %xmm2,%xmm12 + paddd %xmm3,%xmm13 + # x14[0-3] += s3[2] + # x15[0-3] += s3[3] + movq 0x38(%rdi),%xmm3 + pshufd $0x00,%xmm3,%xmm2 + pshufd $0x55,%xmm3,%xmm3 + paddd %xmm2,%xmm14 + paddd %xmm3,%xmm15 + + # x12 += counter values 0-3 + paddd %xmm1,%xmm12 + + # interleave 32-bit words in state n, n+1 + movdqa 0x00(%rsp),%xmm0 + movdqa 0x10(%rsp),%xmm1 + movdqa %xmm0,%xmm2 + punpckldq %xmm1,%xmm2 + punpckhdq %xmm1,%xmm0 + movdqa %xmm2,0x00(%rsp) + movdqa %xmm0,0x10(%rsp) + movdqa 0x20(%rsp),%xmm0 + movdqa 0x30(%rsp),%xmm1 + movdqa %xmm0,%xmm2 + punpckldq %xmm1,%xmm2 + punpckhdq %xmm1,%xmm0 + movdqa %xmm2,0x20(%rsp) + movdqa %xmm0,0x30(%rsp) + movdqa %xmm4,%xmm0 + punpckldq %xmm5,%xmm4 + punpckhdq %xmm5,%xmm0 + movdqa %xmm0,%xmm5 + movdqa %xmm6,%xmm0 + punpckldq %xmm7,%xmm6 + punpckhdq %xmm7,%xmm0 + movdqa %xmm0,%xmm7 + movdqa %xmm8,%xmm0 + punpckldq %xmm9,%xmm8 + punpckhdq %xmm9,%xmm0 + movdqa %xmm0,%xmm9 + movdqa %xmm10,%xmm0 + punpckldq %xmm11,%xmm10 + punpckhdq %xmm11,%xmm0 + movdqa %xmm0,%xmm11 + movdqa %xmm12,%xmm0 + punpckldq %xmm13,%xmm12 + punpckhdq %xmm13,%xmm0 + movdqa %xmm0,%xmm13 + movdqa %xmm14,%xmm0 + punpckldq %xmm15,%xmm14 + punpckhdq %xmm15,%xmm0 + movdqa %xmm0,%xmm15 + + # interleave 64-bit words in state n, n+2 + movdqa 0x00(%rsp),%xmm0 + movdqa 0x20(%rsp),%xmm1 + movdqa %xmm0,%xmm2 + punpcklqdq %xmm1,%xmm2 + punpckhqdq %xmm1,%xmm0 + movdqa %xmm2,0x00(%rsp) + movdqa %xmm0,0x20(%rsp) + movdqa 0x10(%rsp),%xmm0 + movdqa 0x30(%rsp),%xmm1 + movdqa %xmm0,%xmm2 + punpcklqdq %xmm1,%xmm2 + punpckhqdq %xmm1,%xmm0 + movdqa %xmm2,0x10(%rsp) + movdqa %xmm0,0x30(%rsp) + movdqa %xmm4,%xmm0 + punpcklqdq %xmm6,%xmm4 + punpckhqdq %xmm6,%xmm0 + movdqa %xmm0,%xmm6 + movdqa %xmm5,%xmm0 + punpcklqdq %xmm7,%xmm5 + punpckhqdq %xmm7,%xmm0 + movdqa %xmm0,%xmm7 + movdqa %xmm8,%xmm0 + punpcklqdq %xmm10,%xmm8 + punpckhqdq %xmm10,%xmm0 + movdqa %xmm0,%xmm10 + movdqa %xmm9,%xmm0 + punpcklqdq %xmm11,%xmm9 + punpckhqdq %xmm11,%xmm0 + movdqa %xmm0,%xmm11 + movdqa %xmm12,%xmm0 + punpcklqdq %xmm14,%xmm12 + punpckhqdq %xmm14,%xmm0 + movdqa %xmm0,%xmm14 + movdqa %xmm13,%xmm0 + punpcklqdq %xmm15,%xmm13 + punpckhqdq %xmm15,%xmm0 + movdqa %xmm0,%xmm15 + + # xor with corresponding input, write to output + movdqa 0x00(%rsp),%xmm0 + movdqu 0x00(%rdx),%xmm1 + pxor %xmm1,%xmm0 + movdqu %xmm0,0x00(%rsi) + movdqa 0x10(%rsp),%xmm0 + movdqu 0x80(%rdx),%xmm1 + pxor %xmm1,%xmm0 + movdqu %xmm0,0x80(%rsi) + movdqa 0x20(%rsp),%xmm0 + movdqu 0x40(%rdx),%xmm1 + pxor %xmm1,%xmm0 + movdqu %xmm0,0x40(%rsi) + movdqa 0x30(%rsp),%xmm0 + movdqu 0xc0(%rdx),%xmm1 + pxor %xmm1,%xmm0 + movdqu %xmm0,0xc0(%rsi) + movdqu 0x10(%rdx),%xmm1 + pxor %xmm1,%xmm4 + movdqu %xmm4,0x10(%rsi) + movdqu 0x90(%rdx),%xmm1 + pxor %xmm1,%xmm5 + movdqu %xmm5,0x90(%rsi) + movdqu 0x50(%rdx),%xmm1 + pxor %xmm1,%xmm6 + movdqu %xmm6,0x50(%rsi) + movdqu 0xd0(%rdx),%xmm1 + pxor %xmm1,%xmm7 + movdqu %xmm7,0xd0(%rsi) + movdqu 0x20(%rdx),%xmm1 + pxor %xmm1,%xmm8 + movdqu %xmm8,0x20(%rsi) + movdqu 0xa0(%rdx),%xmm1 + pxor %xmm1,%xmm9 + movdqu %xmm9,0xa0(%rsi) + movdqu 0x60(%rdx),%xmm1 + pxor %xmm1,%xmm10 + movdqu %xmm10,0x60(%rsi) + movdqu 0xe0(%rdx),%xmm1 + pxor %xmm1,%xmm11 + movdqu %xmm11,0xe0(%rsi) + movdqu 0x30(%rdx),%xmm1 + pxor %xmm1,%xmm12 + movdqu %xmm12,0x30(%rsi) + movdqu 0xb0(%rdx),%xmm1 + pxor %xmm1,%xmm13 + movdqu %xmm13,0xb0(%rsi) + movdqu 0x70(%rdx),%xmm1 + pxor %xmm1,%xmm14 + movdqu %xmm14,0x70(%rsi) + movdqu 0xf0(%rdx),%xmm1 + pxor %xmm1,%xmm15 + movdqu %xmm15,0xf0(%rsi) + + add $0x40,%rsp + ret +ENDPROC(chacha20_4block_xor_ssse3) diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c new file mode 100644 index 000000000000..8baaff5af0b5 --- /dev/null +++ b/arch/x86/crypto/chacha20_glue.c @@ -0,0 +1,150 @@ +/* + * ChaCha20 256-bit cipher algorithm, RFC7539, SIMD glue code + * + * Copyright (C) 2015 Martin Willi + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <crypto/algapi.h> +#include <crypto/chacha20.h> +#include <linux/crypto.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <asm/fpu/api.h> +#include <asm/simd.h> + +#define CHACHA20_STATE_ALIGN 16 + +asmlinkage void chacha20_block_xor_ssse3(u32 *state, u8 *dst, const u8 *src); +asmlinkage void chacha20_4block_xor_ssse3(u32 *state, u8 *dst, const u8 *src); +#ifdef CONFIG_AS_AVX2 +asmlinkage void chacha20_8block_xor_avx2(u32 *state, u8 *dst, const u8 *src); +static bool chacha20_use_avx2; +#endif + +static void chacha20_dosimd(u32 *state, u8 *dst, const u8 *src, + unsigned int bytes) +{ + u8 buf[CHACHA20_BLOCK_SIZE]; + +#ifdef CONFIG_AS_AVX2 + if (chacha20_use_avx2) { + while (bytes >= CHACHA20_BLOCK_SIZE * 8) { + chacha20_8block_xor_avx2(state, dst, src); + bytes -= CHACHA20_BLOCK_SIZE * 8; + src += CHACHA20_BLOCK_SIZE * 8; + dst += CHACHA20_BLOCK_SIZE * 8; + state[12] += 8; + } + } +#endif + while (bytes >= CHACHA20_BLOCK_SIZE * 4) { + chacha20_4block_xor_ssse3(state, dst, src); + bytes -= CHACHA20_BLOCK_SIZE * 4; + src += CHACHA20_BLOCK_SIZE * 4; + dst += CHACHA20_BLOCK_SIZE * 4; + state[12] += 4; + } + while (bytes >= CHACHA20_BLOCK_SIZE) { + chacha20_block_xor_ssse3(state, dst, src); + bytes -= CHACHA20_BLOCK_SIZE; + src += CHACHA20_BLOCK_SIZE; + dst += CHACHA20_BLOCK_SIZE; + state[12]++; + } + if (bytes) { + memcpy(buf, src, bytes); + chacha20_block_xor_ssse3(state, buf, buf); + memcpy(dst, buf, bytes); + } +} + +static int chacha20_simd(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + u32 *state, state_buf[16 + (CHACHA20_STATE_ALIGN / sizeof(u32)) - 1]; + struct blkcipher_walk walk; + int err; + + if (!may_use_simd()) + return crypto_chacha20_crypt(desc, dst, src, nbytes); + + state = (u32 *)roundup((uintptr_t)state_buf, CHACHA20_STATE_ALIGN); + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt_block(desc, &walk, CHACHA20_BLOCK_SIZE); + + crypto_chacha20_init(state, crypto_blkcipher_ctx(desc->tfm), walk.iv); + + kernel_fpu_begin(); + + while (walk.nbytes >= CHACHA20_BLOCK_SIZE) { + chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr, + rounddown(walk.nbytes, CHACHA20_BLOCK_SIZE)); + err = blkcipher_walk_done(desc, &walk, + walk.nbytes % CHACHA20_BLOCK_SIZE); + } + + if (walk.nbytes) { + chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr, + walk.nbytes); + err = blkcipher_walk_done(desc, &walk, 0); + } + + kernel_fpu_end(); + + return err; +} + +static struct crypto_alg alg = { + .cra_name = "chacha20", + .cra_driver_name = "chacha20-simd", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = 1, + .cra_type = &crypto_blkcipher_type, + .cra_ctxsize = sizeof(struct chacha20_ctx), + .cra_alignmask = sizeof(u32) - 1, + .cra_module = THIS_MODULE, + .cra_u = { + .blkcipher = { + .min_keysize = CHACHA20_KEY_SIZE, + .max_keysize = CHACHA20_KEY_SIZE, + .ivsize = CHACHA20_IV_SIZE, + .geniv = "seqiv", + .setkey = crypto_chacha20_setkey, + .encrypt = chacha20_simd, + .decrypt = chacha20_simd, + }, + }, +}; + +static int __init chacha20_simd_mod_init(void) +{ + if (!boot_cpu_has(X86_FEATURE_SSSE3)) + return -ENODEV; + +#ifdef CONFIG_AS_AVX2 + chacha20_use_avx2 = cpu_has_avx && cpu_has_avx2 && + cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL); +#endif + return crypto_register_alg(&alg); +} + +static void __exit chacha20_simd_mod_fini(void) +{ + crypto_unregister_alg(&alg); +} + +module_init(chacha20_simd_mod_init); +module_exit(chacha20_simd_mod_fini); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Martin Willi <martin@strongswan.org>"); +MODULE_DESCRIPTION("chacha20 cipher algorithm, SIMD accelerated"); +MODULE_ALIAS_CRYPTO("chacha20"); +MODULE_ALIAS_CRYPTO("chacha20-simd"); diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c index 81a595d75cf5..0e9871693f24 100644 --- a/arch/x86/crypto/crc32c-intel_glue.c +++ b/arch/x86/crypto/crc32c-intel_glue.c @@ -257,7 +257,7 @@ static int __init crc32c_intel_mod_init(void) if (!x86_match_cpu(crc32c_cpu_id)) return -ENODEV; #ifdef CONFIG_X86_64 - if (cpu_has_pclmulqdq) { + if (boot_cpu_has(X86_FEATURE_PCLMULQDQ)) { alg.update = crc32c_pcl_intel_update; alg.finup = crc32c_pcl_intel_finup; alg.digest = crc32c_pcl_intel_digest; diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S index 225be06edc80..4fe27e074194 100644 --- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S +++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S @@ -330,7 +330,7 @@ ENDPROC(crc_pcl) ## PCLMULQDQ tables ## Table is 128 entries x 2 words (8 bytes) each ################################################################ -.section .rotata, "a", %progbits +.section .rodata, "a", %progbits .align 8 K_table: .long 0x493c7d27, 0x00000001 diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index 64d7cf1b50e1..a69321a77783 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -219,6 +219,29 @@ static int ghash_async_final(struct ahash_request *req) } } +static int ghash_async_import(struct ahash_request *req, const void *in) +{ + struct ahash_request *cryptd_req = ahash_request_ctx(req); + struct shash_desc *desc = cryptd_shash_desc(cryptd_req); + struct ghash_desc_ctx *dctx = shash_desc_ctx(desc); + + ghash_async_init(req); + memcpy(dctx, in, sizeof(*dctx)); + return 0; + +} + +static int ghash_async_export(struct ahash_request *req, void *out) +{ + struct ahash_request *cryptd_req = ahash_request_ctx(req); + struct shash_desc *desc = cryptd_shash_desc(cryptd_req); + struct ghash_desc_ctx *dctx = shash_desc_ctx(desc); + + memcpy(out, dctx, sizeof(*dctx)); + return 0; + +} + static int ghash_async_digest(struct ahash_request *req) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); @@ -288,12 +311,16 @@ static struct ahash_alg ghash_async_alg = { .final = ghash_async_final, .setkey = ghash_async_setkey, .digest = ghash_async_digest, + .export = ghash_async_export, + .import = ghash_async_import, .halg = { .digestsize = GHASH_DIGEST_SIZE, + .statesize = sizeof(struct ghash_desc_ctx), .base = { .cra_name = "ghash", .cra_driver_name = "ghash-clmulni", .cra_priority = 400, + .cra_ctxsize = sizeof(struct ghash_async_ctx), .cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC, .cra_blocksize = GHASH_BLOCK_SIZE, .cra_type = &crypto_ahash_type, diff --git a/arch/x86/crypto/poly1305-avx2-x86_64.S b/arch/x86/crypto/poly1305-avx2-x86_64.S new file mode 100644 index 000000000000..eff2f414e22b --- /dev/null +++ b/arch/x86/crypto/poly1305-avx2-x86_64.S @@ -0,0 +1,386 @@ +/* + * Poly1305 authenticator algorithm, RFC7539, x64 AVX2 functions + * + * Copyright (C) 2015 Martin Willi + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/linkage.h> + +.data +.align 32 + +ANMASK: .octa 0x0000000003ffffff0000000003ffffff + .octa 0x0000000003ffffff0000000003ffffff +ORMASK: .octa 0x00000000010000000000000001000000 + .octa 0x00000000010000000000000001000000 + +.text + +#define h0 0x00(%rdi) +#define h1 0x04(%rdi) +#define h2 0x08(%rdi) +#define h3 0x0c(%rdi) +#define h4 0x10(%rdi) +#define r0 0x00(%rdx) +#define r1 0x04(%rdx) +#define r2 0x08(%rdx) +#define r3 0x0c(%rdx) +#define r4 0x10(%rdx) +#define u0 0x00(%r8) +#define u1 0x04(%r8) +#define u2 0x08(%r8) +#define u3 0x0c(%r8) +#define u4 0x10(%r8) +#define w0 0x14(%r8) +#define w1 0x18(%r8) +#define w2 0x1c(%r8) +#define w3 0x20(%r8) +#define w4 0x24(%r8) +#define y0 0x28(%r8) +#define y1 0x2c(%r8) +#define y2 0x30(%r8) +#define y3 0x34(%r8) +#define y4 0x38(%r8) +#define m %rsi +#define hc0 %ymm0 +#define hc1 %ymm1 +#define hc2 %ymm2 +#define hc3 %ymm3 +#define hc4 %ymm4 +#define hc0x %xmm0 +#define hc1x %xmm1 +#define hc2x %xmm2 +#define hc3x %xmm3 +#define hc4x %xmm4 +#define t1 %ymm5 +#define t2 %ymm6 +#define t1x %xmm5 +#define t2x %xmm6 +#define ruwy0 %ymm7 +#define ruwy1 %ymm8 +#define ruwy2 %ymm9 +#define ruwy3 %ymm10 +#define ruwy4 %ymm11 +#define ruwy0x %xmm7 +#define ruwy1x %xmm8 +#define ruwy2x %xmm9 +#define ruwy3x %xmm10 +#define ruwy4x %xmm11 +#define svxz1 %ymm12 +#define svxz2 %ymm13 +#define svxz3 %ymm14 +#define svxz4 %ymm15 +#define d0 %r9 +#define d1 %r10 +#define d2 %r11 +#define d3 %r12 +#define d4 %r13 + +ENTRY(poly1305_4block_avx2) + # %rdi: Accumulator h[5] + # %rsi: 64 byte input block m + # %rdx: Poly1305 key r[5] + # %rcx: Quadblock count + # %r8: Poly1305 derived key r^2 u[5], r^3 w[5], r^4 y[5], + + # This four-block variant uses loop unrolled block processing. It + # requires 4 Poly1305 keys: r, r^2, r^3 and r^4: + # h = (h + m) * r => h = (h + m1) * r^4 + m2 * r^3 + m3 * r^2 + m4 * r + + vzeroupper + push %rbx + push %r12 + push %r13 + + # combine r0,u0,w0,y0 + vmovd y0,ruwy0x + vmovd w0,t1x + vpunpcklqdq t1,ruwy0,ruwy0 + vmovd u0,t1x + vmovd r0,t2x + vpunpcklqdq t2,t1,t1 + vperm2i128 $0x20,t1,ruwy0,ruwy0 + + # combine r1,u1,w1,y1 and s1=r1*5,v1=u1*5,x1=w1*5,z1=y1*5 + vmovd y1,ruwy1x + vmovd w1,t1x + vpunpcklqdq t1,ruwy1,ruwy1 + vmovd u1,t1x + vmovd r1,t2x + vpunpcklqdq t2,t1,t1 + vperm2i128 $0x20,t1,ruwy1,ruwy1 + vpslld $2,ruwy1,svxz1 + vpaddd ruwy1,svxz1,svxz1 + + # combine r2,u2,w2,y2 and s2=r2*5,v2=u2*5,x2=w2*5,z2=y2*5 + vmovd y2,ruwy2x + vmovd w2,t1x + vpunpcklqdq t1,ruwy2,ruwy2 + vmovd u2,t1x + vmovd r2,t2x + vpunpcklqdq t2,t1,t1 + vperm2i128 $0x20,t1,ruwy2,ruwy2 + vpslld $2,ruwy2,svxz2 + vpaddd ruwy2,svxz2,svxz2 + + # combine r3,u3,w3,y3 and s3=r3*5,v3=u3*5,x3=w3*5,z3=y3*5 + vmovd y3,ruwy3x + vmovd w3,t1x + vpunpcklqdq t1,ruwy3,ruwy3 + vmovd u3,t1x + vmovd r3,t2x + vpunpcklqdq t2,t1,t1 + vperm2i128 $0x20,t1,ruwy3,ruwy3 + vpslld $2,ruwy3,svxz3 + vpaddd ruwy3,svxz3,svxz3 + + # combine r4,u4,w4,y4 and s4=r4*5,v4=u4*5,x4=w4*5,z4=y4*5 + vmovd y4,ruwy4x + vmovd w4,t1x + vpunpcklqdq t1,ruwy4,ruwy4 + vmovd u4,t1x + vmovd r4,t2x + vpunpcklqdq t2,t1,t1 + vperm2i128 $0x20,t1,ruwy4,ruwy4 + vpslld $2,ruwy4,svxz4 + vpaddd ruwy4,svxz4,svxz4 + +.Ldoblock4: + # hc0 = [m[48-51] & 0x3ffffff, m[32-35] & 0x3ffffff, + # m[16-19] & 0x3ffffff, m[ 0- 3] & 0x3ffffff + h0] + vmovd 0x00(m),hc0x + vmovd 0x10(m),t1x + vpunpcklqdq t1,hc0,hc0 + vmovd 0x20(m),t1x + vmovd 0x30(m),t2x + vpunpcklqdq t2,t1,t1 + vperm2i128 $0x20,t1,hc0,hc0 + vpand ANMASK(%rip),hc0,hc0 + vmovd h0,t1x + vpaddd t1,hc0,hc0 + # hc1 = [(m[51-54] >> 2) & 0x3ffffff, (m[35-38] >> 2) & 0x3ffffff, + # (m[19-22] >> 2) & 0x3ffffff, (m[ 3- 6] >> 2) & 0x3ffffff + h1] + vmovd 0x03(m),hc1x + vmovd 0x13(m),t1x + vpunpcklqdq t1,hc1,hc1 + vmovd 0x23(m),t1x + vmovd 0x33(m),t2x + vpunpcklqdq t2,t1,t1 + vperm2i128 $0x20,t1,hc1,hc1 + vpsrld $2,hc1,hc1 + vpand ANMASK(%rip),hc1,hc1 + vmovd h1,t1x + vpaddd t1,hc1,hc1 + # hc2 = [(m[54-57] >> 4) & 0x3ffffff, (m[38-41] >> 4) & 0x3ffffff, + # (m[22-25] >> 4) & 0x3ffffff, (m[ 6- 9] >> 4) & 0x3ffffff + h2] + vmovd 0x06(m),hc2x + vmovd 0x16(m),t1x + vpunpcklqdq t1,hc2,hc2 + vmovd 0x26(m),t1x + vmovd 0x36(m),t2x + vpunpcklqdq t2,t1,t1 + vperm2i128 $0x20,t1,hc2,hc2 + vpsrld $4,hc2,hc2 + vpand ANMASK(%rip),hc2,hc2 + vmovd h2,t1x + vpaddd t1,hc2,hc2 + # hc3 = [(m[57-60] >> 6) & 0x3ffffff, (m[41-44] >> 6) & 0x3ffffff, + # (m[25-28] >> 6) & 0x3ffffff, (m[ 9-12] >> 6) & 0x3ffffff + h3] + vmovd 0x09(m),hc3x + vmovd 0x19(m),t1x + vpunpcklqdq t1,hc3,hc3 + vmovd 0x29(m),t1x + vmovd 0x39(m),t2x + vpunpcklqdq t2,t1,t1 + vperm2i128 $0x20,t1,hc3,hc3 + vpsrld $6,hc3,hc3 + vpand ANMASK(%rip),hc3,hc3 + vmovd h3,t1x + vpaddd t1,hc3,hc3 + # hc4 = [(m[60-63] >> 8) | (1<<24), (m[44-47] >> 8) | (1<<24), + # (m[28-31] >> 8) | (1<<24), (m[12-15] >> 8) | (1<<24) + h4] + vmovd 0x0c(m),hc4x + vmovd 0x1c(m),t1x + vpunpcklqdq t1,hc4,hc4 + vmovd 0x2c(m),t1x + vmovd 0x3c(m),t2x + vpunpcklqdq t2,t1,t1 + vperm2i128 $0x20,t1,hc4,hc4 + vpsrld $8,hc4,hc4 + vpor ORMASK(%rip),hc4,hc4 + vmovd h4,t1x + vpaddd t1,hc4,hc4 + + # t1 = [ hc0[3] * r0, hc0[2] * u0, hc0[1] * w0, hc0[0] * y0 ] + vpmuludq hc0,ruwy0,t1 + # t1 += [ hc1[3] * s4, hc1[2] * v4, hc1[1] * x4, hc1[0] * z4 ] + vpmuludq hc1,svxz4,t2 + vpaddq t2,t1,t1 + # t1 += [ hc2[3] * s3, hc2[2] * v3, hc2[1] * x3, hc2[0] * z3 ] + vpmuludq hc2,svxz3,t2 + vpaddq t2,t1,t1 + # t1 += [ hc3[3] * s2, hc3[2] * v2, hc3[1] * x2, hc3[0] * z2 ] + vpmuludq hc3,svxz2,t2 + vpaddq t2,t1,t1 + # t1 += [ hc4[3] * s1, hc4[2] * v1, hc4[1] * x1, hc4[0] * z1 ] + vpmuludq hc4,svxz1,t2 + vpaddq t2,t1,t1 + # d0 = t1[0] + t1[1] + t[2] + t[3] + vpermq $0xee,t1,t2 + vpaddq t2,t1,t1 + vpsrldq $8,t1,t2 + vpaddq t2,t1,t1 + vmovq t1x,d0 + + # t1 = [ hc0[3] * r1, hc0[2] * u1,hc0[1] * w1, hc0[0] * y1 ] + vpmuludq hc0,ruwy1,t1 + # t1 += [ hc1[3] * r0, hc1[2] * u0, hc1[1] * w0, hc1[0] * y0 ] + vpmuludq hc1,ruwy0,t2 + vpaddq t2,t1,t1 + # t1 += [ hc2[3] * s4, hc2[2] * v4, hc2[1] * x4, hc2[0] * z4 ] + vpmuludq hc2,svxz4,t2 + vpaddq t2,t1,t1 + # t1 += [ hc3[3] * s3, hc3[2] * v3, hc3[1] * x3, hc3[0] * z3 ] + vpmuludq hc3,svxz3,t2 + vpaddq t2,t1,t1 + # t1 += [ hc4[3] * s2, hc4[2] * v2, hc4[1] * x2, hc4[0] * z2 ] + vpmuludq hc4,svxz2,t2 + vpaddq t2,t1,t1 + # d1 = t1[0] + t1[1] + t1[3] + t1[4] + vpermq $0xee,t1,t2 + vpaddq t2,t1,t1 + vpsrldq $8,t1,t2 + vpaddq t2,t1,t1 + vmovq t1x,d1 + + # t1 = [ hc0[3] * r2, hc0[2] * u2, hc0[1] * w2, hc0[0] * y2 ] + vpmuludq hc0,ruwy2,t1 + # t1 += [ hc1[3] * r1, hc1[2] * u1, hc1[1] * w1, hc1[0] * y1 ] + vpmuludq hc1,ruwy1,t2 + vpaddq t2,t1,t1 + # t1 += [ hc2[3] * r0, hc2[2] * u0, hc2[1] * w0, hc2[0] * y0 ] + vpmuludq hc2,ruwy0,t2 + vpaddq t2,t1,t1 + # t1 += [ hc3[3] * s4, hc3[2] * v4, hc3[1] * x4, hc3[0] * z4 ] + vpmuludq hc3,svxz4,t2 + vpaddq t2,t1,t1 + # t1 += [ hc4[3] * s3, hc4[2] * v3, hc4[1] * x3, hc4[0] * z3 ] + vpmuludq hc4,svxz3,t2 + vpaddq t2,t1,t1 + # d2 = t1[0] + t1[1] + t1[2] + t1[3] + vpermq $0xee,t1,t2 + vpaddq t2,t1,t1 + vpsrldq $8,t1,t2 + vpaddq t2,t1,t1 + vmovq t1x,d2 + + # t1 = [ hc0[3] * r3, hc0[2] * u3, hc0[1] * w3, hc0[0] * y3 ] + vpmuludq hc0,ruwy3,t1 + # t1 += [ hc1[3] * r2, hc1[2] * u2, hc1[1] * w2, hc1[0] * y2 ] + vpmuludq hc1,ruwy2,t2 + vpaddq t2,t1,t1 + # t1 += [ hc2[3] * r1, hc2[2] * u1, hc2[1] * w1, hc2[0] * y1 ] + vpmuludq hc2,ruwy1,t2 + vpaddq t2,t1,t1 + # t1 += [ hc3[3] * r0, hc3[2] * u0, hc3[1] * w0, hc3[0] * y0 ] + vpmuludq hc3,ruwy0,t2 + vpaddq t2,t1,t1 + # t1 += [ hc4[3] * s4, hc4[2] * v4, hc4[1] * x4, hc4[0] * z4 ] + vpmuludq hc4,svxz4,t2 + vpaddq t2,t1,t1 + # d3 = t1[0] + t1[1] + t1[2] + t1[3] + vpermq $0xee,t1,t2 + vpaddq t2,t1,t1 + vpsrldq $8,t1,t2 + vpaddq t2,t1,t1 + vmovq t1x,d3 + + # t1 = [ hc0[3] * r4, hc0[2] * u4, hc0[1] * w4, hc0[0] * y4 ] + vpmuludq hc0,ruwy4,t1 + # t1 += [ hc1[3] * r3, hc1[2] * u3, hc1[1] * w3, hc1[0] * y3 ] + vpmuludq hc1,ruwy3,t2 + vpaddq t2,t1,t1 + # t1 += [ hc2[3] * r2, hc2[2] * u2, hc2[1] * w2, hc2[0] * y2 ] + vpmuludq hc2,ruwy2,t2 + vpaddq t2,t1,t1 + # t1 += [ hc3[3] * r1, hc3[2] * u1, hc3[1] * w1, hc3[0] * y1 ] + vpmuludq hc3,ruwy1,t2 + vpaddq t2,t1,t1 + # t1 += [ hc4[3] * r0, hc4[2] * u0, hc4[1] * w0, hc4[0] * y0 ] + vpmuludq hc4,ruwy0,t2 + vpaddq t2,t1,t1 + # d4 = t1[0] + t1[1] + t1[2] + t1[3] + vpermq $0xee,t1,t2 + vpaddq t2,t1,t1 + vpsrldq $8,t1,t2 + vpaddq t2,t1,t1 + vmovq t1x,d4 + + # d1 += d0 >> 26 + mov d0,%rax + shr $26,%rax + add %rax,d1 + # h0 = d0 & 0x3ffffff + mov d0,%rbx + and $0x3ffffff,%ebx + + # d2 += d1 >> 26 + mov d1,%rax + shr $26,%rax + add %rax,d2 + # h1 = d1 & 0x3ffffff + mov d1,%rax + and $0x3ffffff,%eax + mov %eax,h1 + + # d3 += d2 >> 26 + mov d2,%rax + shr $26,%rax + add %rax,d3 + # h2 = d2 & 0x3ffffff + mov d2,%rax + and $0x3ffffff,%eax + mov %eax,h2 + + # d4 += d3 >> 26 + mov d3,%rax + shr $26,%rax + add %rax,d4 + # h3 = d3 & 0x3ffffff + mov d3,%rax + and $0x3ffffff,%eax + mov %eax,h3 + + # h0 += (d4 >> 26) * 5 + mov d4,%rax + shr $26,%rax + lea (%eax,%eax,4),%eax + add %eax,%ebx + # h4 = d4 & 0x3ffffff + mov d4,%rax + and $0x3ffffff,%eax + mov %eax,h4 + + # h1 += h0 >> 26 + mov %ebx,%eax + shr $26,%eax + add %eax,h1 + # h0 = h0 & 0x3ffffff + andl $0x3ffffff,%ebx + mov %ebx,h0 + + add $0x40,m + dec %rcx + jnz .Ldoblock4 + + vzeroupper + pop %r13 + pop %r12 + pop %rbx + ret +ENDPROC(poly1305_4block_avx2) diff --git a/arch/x86/crypto/poly1305-sse2-x86_64.S b/arch/x86/crypto/poly1305-sse2-x86_64.S new file mode 100644 index 000000000000..338c748054ed --- /dev/null +++ b/arch/x86/crypto/poly1305-sse2-x86_64.S @@ -0,0 +1,582 @@ +/* + * Poly1305 authenticator algorithm, RFC7539, x64 SSE2 functions + * + * Copyright (C) 2015 Martin Willi + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/linkage.h> + +.data +.align 16 + +ANMASK: .octa 0x0000000003ffffff0000000003ffffff +ORMASK: .octa 0x00000000010000000000000001000000 + +.text + +#define h0 0x00(%rdi) +#define h1 0x04(%rdi) +#define h2 0x08(%rdi) +#define h3 0x0c(%rdi) +#define h4 0x10(%rdi) +#define r0 0x00(%rdx) +#define r1 0x04(%rdx) +#define r2 0x08(%rdx) +#define r3 0x0c(%rdx) +#define r4 0x10(%rdx) +#define s1 0x00(%rsp) +#define s2 0x04(%rsp) +#define s3 0x08(%rsp) +#define s4 0x0c(%rsp) +#define m %rsi +#define h01 %xmm0 +#define h23 %xmm1 +#define h44 %xmm2 +#define t1 %xmm3 +#define t2 %xmm4 +#define t3 %xmm5 +#define t4 %xmm6 +#define mask %xmm7 +#define d0 %r8 +#define d1 %r9 +#define d2 %r10 +#define d3 %r11 +#define d4 %r12 + +ENTRY(poly1305_block_sse2) + # %rdi: Accumulator h[5] + # %rsi: 16 byte input block m + # %rdx: Poly1305 key r[5] + # %rcx: Block count + + # This single block variant tries to improve performance by doing two + # multiplications in parallel using SSE instructions. There is quite + # some quardword packing involved, hence the speedup is marginal. + + push %rbx + push %r12 + sub $0x10,%rsp + + # s1..s4 = r1..r4 * 5 + mov r1,%eax + lea (%eax,%eax,4),%eax + mov %eax,s1 + mov r2,%eax + lea (%eax,%eax,4),%eax + mov %eax,s2 + mov r3,%eax + lea (%eax,%eax,4),%eax + mov %eax,s3 + mov r4,%eax + lea (%eax,%eax,4),%eax + mov %eax,s4 + + movdqa ANMASK(%rip),mask + +.Ldoblock: + # h01 = [0, h1, 0, h0] + # h23 = [0, h3, 0, h2] + # h44 = [0, h4, 0, h4] + movd h0,h01 + movd h1,t1 + movd h2,h23 + movd h3,t2 + movd h4,h44 + punpcklqdq t1,h01 + punpcklqdq t2,h23 + punpcklqdq h44,h44 + + # h01 += [ (m[3-6] >> 2) & 0x3ffffff, m[0-3] & 0x3ffffff ] + movd 0x00(m),t1 + movd 0x03(m),t2 + psrld $2,t2 + punpcklqdq t2,t1 + pand mask,t1 + paddd t1,h01 + # h23 += [ (m[9-12] >> 6) & 0x3ffffff, (m[6-9] >> 4) & 0x3ffffff ] + movd 0x06(m),t1 + movd 0x09(m),t2 + psrld $4,t1 + psrld $6,t2 + punpcklqdq t2,t1 + pand mask,t1 + paddd t1,h23 + # h44 += [ (m[12-15] >> 8) | (1 << 24), (m[12-15] >> 8) | (1 << 24) ] + mov 0x0c(m),%eax + shr $8,%eax + or $0x01000000,%eax + movd %eax,t1 + pshufd $0xc4,t1,t1 + paddd t1,h44 + + # t1[0] = h0 * r0 + h2 * s3 + # t1[1] = h1 * s4 + h3 * s2 + movd r0,t1 + movd s4,t2 + punpcklqdq t2,t1 + pmuludq h01,t1 + movd s3,t2 + movd s2,t3 + punpcklqdq t3,t2 + pmuludq h23,t2 + paddq t2,t1 + # t2[0] = h0 * r1 + h2 * s4 + # t2[1] = h1 * r0 + h3 * s3 + movd r1,t2 + movd r0,t3 + punpcklqdq t3,t2 + pmuludq h01,t2 + movd s4,t3 + movd s3,t4 + punpcklqdq t4,t3 + pmuludq h23,t3 + paddq t3,t2 + # t3[0] = h4 * s1 + # t3[1] = h4 * s2 + movd s1,t3 + movd s2,t4 + punpcklqdq t4,t3 + pmuludq h44,t3 + # d0 = t1[0] + t1[1] + t3[0] + # d1 = t2[0] + t2[1] + t3[1] + movdqa t1,t4 + punpcklqdq t2,t4 + punpckhqdq t2,t1 + paddq t4,t1 + paddq t3,t1 + movq t1,d0 + psrldq $8,t1 + movq t1,d1 + + # t1[0] = h0 * r2 + h2 * r0 + # t1[1] = h1 * r1 + h3 * s4 + movd r2,t1 + movd r1,t2 + punpcklqdq t2,t1 + pmuludq h01,t1 + movd r0,t2 + movd s4,t3 + punpcklqdq t3,t2 + pmuludq h23,t2 + paddq t2,t1 + # t2[0] = h0 * r3 + h2 * r1 + # t2[1] = h1 * r2 + h3 * r0 + movd r3,t2 + movd r2,t3 + punpcklqdq t3,t2 + pmuludq h01,t2 + movd r1,t3 + movd r0,t4 + punpcklqdq t4,t3 + pmuludq h23,t3 + paddq t3,t2 + # t3[0] = h4 * s3 + # t3[1] = h4 * s4 + movd s3,t3 + movd s4,t4 + punpcklqdq t4,t3 + pmuludq h44,t3 + # d2 = t1[0] + t1[1] + t3[0] + # d3 = t2[0] + t2[1] + t3[1] + movdqa t1,t4 + punpcklqdq t2,t4 + punpckhqdq t2,t1 + paddq t4,t1 + paddq t3,t1 + movq t1,d2 + psrldq $8,t1 + movq t1,d3 + + # t1[0] = h0 * r4 + h2 * r2 + # t1[1] = h1 * r3 + h3 * r1 + movd r4,t1 + movd r3,t2 + punpcklqdq t2,t1 + pmuludq h01,t1 + movd r2,t2 + movd r1,t3 + punpcklqdq t3,t2 + pmuludq h23,t2 + paddq t2,t1 + # t3[0] = h4 * r0 + movd r0,t3 + pmuludq h44,t3 + # d4 = t1[0] + t1[1] + t3[0] + movdqa t1,t4 + psrldq $8,t4 + paddq t4,t1 + paddq t3,t1 + movq t1,d4 + + # d1 += d0 >> 26 + mov d0,%rax + shr $26,%rax + add %rax,d1 + # h0 = d0 & 0x3ffffff + mov d0,%rbx + and $0x3ffffff,%ebx + + # d2 += d1 >> 26 + mov d1,%rax + shr $26,%rax + add %rax,d2 + # h1 = d1 & 0x3ffffff + mov d1,%rax + and $0x3ffffff,%eax + mov %eax,h1 + + # d3 += d2 >> 26 + mov d2,%rax + shr $26,%rax + add %rax,d3 + # h2 = d2 & 0x3ffffff + mov d2,%rax + and $0x3ffffff,%eax + mov %eax,h2 + + # d4 += d3 >> 26 + mov d3,%rax + shr $26,%rax + add %rax,d4 + # h3 = d3 & 0x3ffffff + mov d3,%rax + and $0x3ffffff,%eax + mov %eax,h3 + + # h0 += (d4 >> 26) * 5 + mov d4,%rax + shr $26,%rax + lea (%eax,%eax,4),%eax + add %eax,%ebx + # h4 = d4 & 0x3ffffff + mov d4,%rax + and $0x3ffffff,%eax + mov %eax,h4 + + # h1 += h0 >> 26 + mov %ebx,%eax + shr $26,%eax + add %eax,h1 + # h0 = h0 & 0x3ffffff + andl $0x3ffffff,%ebx + mov %ebx,h0 + + add $0x10,m + dec %rcx + jnz .Ldoblock + + add $0x10,%rsp + pop %r12 + pop %rbx + ret +ENDPROC(poly1305_block_sse2) + + +#define u0 0x00(%r8) +#define u1 0x04(%r8) +#define u2 0x08(%r8) +#define u3 0x0c(%r8) +#define u4 0x10(%r8) +#define hc0 %xmm0 +#define hc1 %xmm1 +#define hc2 %xmm2 +#define hc3 %xmm5 +#define hc4 %xmm6 +#define ru0 %xmm7 +#define ru1 %xmm8 +#define ru2 %xmm9 +#define ru3 %xmm10 +#define ru4 %xmm11 +#define sv1 %xmm12 +#define sv2 %xmm13 +#define sv3 %xmm14 +#define sv4 %xmm15 +#undef d0 +#define d0 %r13 + +ENTRY(poly1305_2block_sse2) + # %rdi: Accumulator h[5] + # %rsi: 16 byte input block m + # %rdx: Poly1305 key r[5] + # %rcx: Doubleblock count + # %r8: Poly1305 derived key r^2 u[5] + + # This two-block variant further improves performance by using loop + # unrolled block processing. This is more straight forward and does + # less byte shuffling, but requires a second Poly1305 key r^2: + # h = (h + m) * r => h = (h + m1) * r^2 + m2 * r + + push %rbx + push %r12 + push %r13 + + # combine r0,u0 + movd u0,ru0 + movd r0,t1 + punpcklqdq t1,ru0 + + # combine r1,u1 and s1=r1*5,v1=u1*5 + movd u1,ru1 + movd r1,t1 + punpcklqdq t1,ru1 + movdqa ru1,sv1 + pslld $2,sv1 + paddd ru1,sv1 + + # combine r2,u2 and s2=r2*5,v2=u2*5 + movd u2,ru2 + movd r2,t1 + punpcklqdq t1,ru2 + movdqa ru2,sv2 + pslld $2,sv2 + paddd ru2,sv2 + + # combine r3,u3 and s3=r3*5,v3=u3*5 + movd u3,ru3 + movd r3,t1 + punpcklqdq t1,ru3 + movdqa ru3,sv3 + pslld $2,sv3 + paddd ru3,sv3 + + # combine r4,u4 and s4=r4*5,v4=u4*5 + movd u4,ru4 + movd r4,t1 + punpcklqdq t1,ru4 + movdqa ru4,sv4 + pslld $2,sv4 + paddd ru4,sv4 + +.Ldoblock2: + # hc0 = [ m[16-19] & 0x3ffffff, h0 + m[0-3] & 0x3ffffff ] + movd 0x00(m),hc0 + movd 0x10(m),t1 + punpcklqdq t1,hc0 + pand ANMASK(%rip),hc0 + movd h0,t1 + paddd t1,hc0 + # hc1 = [ (m[19-22] >> 2) & 0x3ffffff, h1 + (m[3-6] >> 2) & 0x3ffffff ] + movd 0x03(m),hc1 + movd 0x13(m),t1 + punpcklqdq t1,hc1 + psrld $2,hc1 + pand ANMASK(%rip),hc1 + movd h1,t1 + paddd t1,hc1 + # hc2 = [ (m[22-25] >> 4) & 0x3ffffff, h2 + (m[6-9] >> 4) & 0x3ffffff ] + movd 0x06(m),hc2 + movd 0x16(m),t1 + punpcklqdq t1,hc2 + psrld $4,hc2 + pand ANMASK(%rip),hc2 + movd h2,t1 + paddd t1,hc2 + # hc3 = [ (m[25-28] >> 6) & 0x3ffffff, h3 + (m[9-12] >> 6) & 0x3ffffff ] + movd 0x09(m),hc3 + movd 0x19(m),t1 + punpcklqdq t1,hc3 + psrld $6,hc3 + pand ANMASK(%rip),hc3 + movd h3,t1 + paddd t1,hc3 + # hc4 = [ (m[28-31] >> 8) | (1<<24), h4 + (m[12-15] >> 8) | (1<<24) ] + movd 0x0c(m),hc4 + movd 0x1c(m),t1 + punpcklqdq t1,hc4 + psrld $8,hc4 + por ORMASK(%rip),hc4 + movd h4,t1 + paddd t1,hc4 + + # t1 = [ hc0[1] * r0, hc0[0] * u0 ] + movdqa ru0,t1 + pmuludq hc0,t1 + # t1 += [ hc1[1] * s4, hc1[0] * v4 ] + movdqa sv4,t2 + pmuludq hc1,t2 + paddq t2,t1 + # t1 += [ hc2[1] * s3, hc2[0] * v3 ] + movdqa sv3,t2 + pmuludq hc2,t2 + paddq t2,t1 + # t1 += [ hc3[1] * s2, hc3[0] * v2 ] + movdqa sv2,t2 + pmuludq hc3,t2 + paddq t2,t1 + # t1 += [ hc4[1] * s1, hc4[0] * v1 ] + movdqa sv1,t2 + pmuludq hc4,t2 + paddq t2,t1 + # d0 = t1[0] + t1[1] + movdqa t1,t2 + psrldq $8,t2 + paddq t2,t1 + movq t1,d0 + + # t1 = [ hc0[1] * r1, hc0[0] * u1 ] + movdqa ru1,t1 + pmuludq hc0,t1 + # t1 += [ hc1[1] * r0, hc1[0] * u0 ] + movdqa ru0,t2 + pmuludq hc1,t2 + paddq t2,t1 + # t1 += [ hc2[1] * s4, hc2[0] * v4 ] + movdqa sv4,t2 + pmuludq hc2,t2 + paddq t2,t1 + # t1 += [ hc3[1] * s3, hc3[0] * v3 ] + movdqa sv3,t2 + pmuludq hc3,t2 + paddq t2,t1 + # t1 += [ hc4[1] * s2, hc4[0] * v2 ] + movdqa sv2,t2 + pmuludq hc4,t2 + paddq t2,t1 + # d1 = t1[0] + t1[1] + movdqa t1,t2 + psrldq $8,t2 + paddq t2,t1 + movq t1,d1 + + # t1 = [ hc0[1] * r2, hc0[0] * u2 ] + movdqa ru2,t1 + pmuludq hc0,t1 + # t1 += [ hc1[1] * r1, hc1[0] * u1 ] + movdqa ru1,t2 + pmuludq hc1,t2 + paddq t2,t1 + # t1 += [ hc2[1] * r0, hc2[0] * u0 ] + movdqa ru0,t2 + pmuludq hc2,t2 + paddq t2,t1 + # t1 += [ hc3[1] * s4, hc3[0] * v4 ] + movdqa sv4,t2 + pmuludq hc3,t2 + paddq t2,t1 + # t1 += [ hc4[1] * s3, hc4[0] * v3 ] + movdqa sv3,t2 + pmuludq hc4,t2 + paddq t2,t1 + # d2 = t1[0] + t1[1] + movdqa t1,t2 + psrldq $8,t2 + paddq t2,t1 + movq t1,d2 + + # t1 = [ hc0[1] * r3, hc0[0] * u3 ] + movdqa ru3,t1 + pmuludq hc0,t1 + # t1 += [ hc1[1] * r2, hc1[0] * u2 ] + movdqa ru2,t2 + pmuludq hc1,t2 + paddq t2,t1 + # t1 += [ hc2[1] * r1, hc2[0] * u1 ] + movdqa ru1,t2 + pmuludq hc2,t2 + paddq t2,t1 + # t1 += [ hc3[1] * r0, hc3[0] * u0 ] + movdqa ru0,t2 + pmuludq hc3,t2 + paddq t2,t1 + # t1 += [ hc4[1] * s4, hc4[0] * v4 ] + movdqa sv4,t2 + pmuludq hc4,t2 + paddq t2,t1 + # d3 = t1[0] + t1[1] + movdqa t1,t2 + psrldq $8,t2 + paddq t2,t1 + movq t1,d3 + + # t1 = [ hc0[1] * r4, hc0[0] * u4 ] + movdqa ru4,t1 + pmuludq hc0,t1 + # t1 += [ hc1[1] * r3, hc1[0] * u3 ] + movdqa ru3,t2 + pmuludq hc1,t2 + paddq t2,t1 + # t1 += [ hc2[1] * r2, hc2[0] * u2 ] + movdqa ru2,t2 + pmuludq hc2,t2 + paddq t2,t1 + # t1 += [ hc3[1] * r1, hc3[0] * u1 ] + movdqa ru1,t2 + pmuludq hc3,t2 + paddq t2,t1 + # t1 += [ hc4[1] * r0, hc4[0] * u0 ] + movdqa ru0,t2 + pmuludq hc4,t2 + paddq t2,t1 + # d4 = t1[0] + t1[1] + movdqa t1,t2 + psrldq $8,t2 + paddq t2,t1 + movq t1,d4 + + # d1 += d0 >> 26 + mov d0,%rax + shr $26,%rax + add %rax,d1 + # h0 = d0 & 0x3ffffff + mov d0,%rbx + and $0x3ffffff,%ebx + + # d2 += d1 >> 26 + mov d1,%rax + shr $26,%rax + add %rax,d2 + # h1 = d1 & 0x3ffffff + mov d1,%rax + and $0x3ffffff,%eax + mov %eax,h1 + + # d3 += d2 >> 26 + mov d2,%rax + shr $26,%rax + add %rax,d3 + # h2 = d2 & 0x3ffffff + mov d2,%rax + and $0x3ffffff,%eax + mov %eax,h2 + + # d4 += d3 >> 26 + mov d3,%rax + shr $26,%rax + add %rax,d4 + # h3 = d3 & 0x3ffffff + mov d3,%rax + and $0x3ffffff,%eax + mov %eax,h3 + + # h0 += (d4 >> 26) * 5 + mov d4,%rax + shr $26,%rax + lea (%eax,%eax,4),%eax + add %eax,%ebx + # h4 = d4 & 0x3ffffff + mov d4,%rax + and $0x3ffffff,%eax + mov %eax,h4 + + # h1 += h0 >> 26 + mov %ebx,%eax + shr $26,%eax + add %eax,h1 + # h0 = h0 & 0x3ffffff + andl $0x3ffffff,%ebx + mov %ebx,h0 + + add $0x20,m + dec %rcx + jnz .Ldoblock2 + + pop %r13 + pop %r12 + pop %rbx + ret +ENDPROC(poly1305_2block_sse2) diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c new file mode 100644 index 000000000000..4264a3d59589 --- /dev/null +++ b/arch/x86/crypto/poly1305_glue.c @@ -0,0 +1,207 @@ +/* + * Poly1305 authenticator algorithm, RFC7539, SIMD glue code + * + * Copyright (C) 2015 Martin Willi + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <crypto/algapi.h> +#include <crypto/internal/hash.h> +#include <crypto/poly1305.h> +#include <linux/crypto.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <asm/fpu/api.h> +#include <asm/simd.h> + +struct poly1305_simd_desc_ctx { + struct poly1305_desc_ctx base; + /* derived key u set? */ + bool uset; +#ifdef CONFIG_AS_AVX2 + /* derived keys r^3, r^4 set? */ + bool wset; +#endif + /* derived Poly1305 key r^2 */ + u32 u[5]; + /* ... silently appended r^3 and r^4 when using AVX2 */ +}; + +asmlinkage void poly1305_block_sse2(u32 *h, const u8 *src, + const u32 *r, unsigned int blocks); +asmlinkage void poly1305_2block_sse2(u32 *h, const u8 *src, const u32 *r, + unsigned int blocks, const u32 *u); +#ifdef CONFIG_AS_AVX2 +asmlinkage void poly1305_4block_avx2(u32 *h, const u8 *src, const u32 *r, + unsigned int blocks, const u32 *u); +static bool poly1305_use_avx2; +#endif + +static int poly1305_simd_init(struct shash_desc *desc) +{ + struct poly1305_simd_desc_ctx *sctx = shash_desc_ctx(desc); + + sctx->uset = false; +#ifdef CONFIG_AS_AVX2 + sctx->wset = false; +#endif + + return crypto_poly1305_init(desc); +} + +static void poly1305_simd_mult(u32 *a, const u32 *b) +{ + u8 m[POLY1305_BLOCK_SIZE]; + + memset(m, 0, sizeof(m)); + /* The poly1305 block function adds a hi-bit to the accumulator which + * we don't need for key multiplication; compensate for it. */ + a[4] -= 1 << 24; + poly1305_block_sse2(a, m, b, 1); +} + +static unsigned int poly1305_simd_blocks(struct poly1305_desc_ctx *dctx, + const u8 *src, unsigned int srclen) +{ + struct poly1305_simd_desc_ctx *sctx; + unsigned int blocks, datalen; + + BUILD_BUG_ON(offsetof(struct poly1305_simd_desc_ctx, base)); + sctx = container_of(dctx, struct poly1305_simd_desc_ctx, base); + + if (unlikely(!dctx->sset)) { + datalen = crypto_poly1305_setdesckey(dctx, src, srclen); + src += srclen - datalen; + srclen = datalen; + } + +#ifdef CONFIG_AS_AVX2 + if (poly1305_use_avx2 && srclen >= POLY1305_BLOCK_SIZE * 4) { + if (unlikely(!sctx->wset)) { + if (!sctx->uset) { + memcpy(sctx->u, dctx->r, sizeof(sctx->u)); + poly1305_simd_mult(sctx->u, dctx->r); + sctx->uset = true; + } + memcpy(sctx->u + 5, sctx->u, sizeof(sctx->u)); + poly1305_simd_mult(sctx->u + 5, dctx->r); + memcpy(sctx->u + 10, sctx->u + 5, sizeof(sctx->u)); + poly1305_simd_mult(sctx->u + 10, dctx->r); + sctx->wset = true; + } + blocks = srclen / (POLY1305_BLOCK_SIZE * 4); + poly1305_4block_avx2(dctx->h, src, dctx->r, blocks, sctx->u); + src += POLY1305_BLOCK_SIZE * 4 * blocks; + srclen -= POLY1305_BLOCK_SIZE * 4 * blocks; + } +#endif + if (likely(srclen >= POLY1305_BLOCK_SIZE * 2)) { + if (unlikely(!sctx->uset)) { + memcpy(sctx->u, dctx->r, sizeof(sctx->u)); + poly1305_simd_mult(sctx->u, dctx->r); + sctx->uset = true; + } + blocks = srclen / (POLY1305_BLOCK_SIZE * 2); + poly1305_2block_sse2(dctx->h, src, dctx->r, blocks, sctx->u); + src += POLY1305_BLOCK_SIZE * 2 * blocks; + srclen -= POLY1305_BLOCK_SIZE * 2 * blocks; + } + if (srclen >= POLY1305_BLOCK_SIZE) { + poly1305_block_sse2(dctx->h, src, dctx->r, 1); + srclen -= POLY1305_BLOCK_SIZE; + } + return srclen; +} + +static int poly1305_simd_update(struct shash_desc *desc, + const u8 *src, unsigned int srclen) +{ + struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); + unsigned int bytes; + + /* kernel_fpu_begin/end is costly, use fallback for small updates */ + if (srclen <= 288 || !may_use_simd()) + return crypto_poly1305_update(desc, src, srclen); + + kernel_fpu_begin(); + + if (unlikely(dctx->buflen)) { + bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen); + memcpy(dctx->buf + dctx->buflen, src, bytes); + src += bytes; + srclen -= bytes; + dctx->buflen += bytes; + + if (dctx->buflen == POLY1305_BLOCK_SIZE) { + poly1305_simd_blocks(dctx, dctx->buf, + POLY1305_BLOCK_SIZE); + dctx->buflen = 0; + } + } + + if (likely(srclen >= POLY1305_BLOCK_SIZE)) { + bytes = poly1305_simd_blocks(dctx, src, srclen); + src += srclen - bytes; + srclen = bytes; + } + + kernel_fpu_end(); + + if (unlikely(srclen)) { + dctx->buflen = srclen; + memcpy(dctx->buf, src, srclen); + } + + return 0; +} + +static struct shash_alg alg = { + .digestsize = POLY1305_DIGEST_SIZE, + .init = poly1305_simd_init, + .update = poly1305_simd_update, + .final = crypto_poly1305_final, + .setkey = crypto_poly1305_setkey, + .descsize = sizeof(struct poly1305_simd_desc_ctx), + .base = { + .cra_name = "poly1305", + .cra_driver_name = "poly1305-simd", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_alignmask = sizeof(u32) - 1, + .cra_blocksize = POLY1305_BLOCK_SIZE, + .cra_module = THIS_MODULE, + }, +}; + +static int __init poly1305_simd_mod_init(void) +{ + if (!cpu_has_xmm2) + return -ENODEV; + +#ifdef CONFIG_AS_AVX2 + poly1305_use_avx2 = cpu_has_avx && cpu_has_avx2 && + cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL); + alg.descsize = sizeof(struct poly1305_simd_desc_ctx); + if (poly1305_use_avx2) + alg.descsize += 10 * sizeof(u32); +#endif + return crypto_register_shash(&alg); +} + +static void __exit poly1305_simd_mod_exit(void) +{ + crypto_unregister_shash(&alg); +} + +module_init(poly1305_simd_mod_init); +module_exit(poly1305_simd_mod_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Martin Willi <martin@strongswan.org>"); +MODULE_DESCRIPTION("Poly1305 authenticator"); +MODULE_ALIAS_CRYPTO("poly1305"); +MODULE_ALIAS_CRYPTO("poly1305-simd"); diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c index 7d838dc4d888..6d198342e2de 100644 --- a/arch/x86/crypto/serpent_avx2_glue.c +++ b/arch/x86/crypto/serpent_avx2_glue.c @@ -542,7 +542,8 @@ static int __init init(void) pr_info("AVX2 instructions are not detected.\n"); return -ENODEV; } - if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) { + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_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 da7dafc9b16d..5dc37026c7ce 100644 --- a/arch/x86/crypto/serpent_avx_glue.c +++ b/arch/x86/crypto/serpent_avx_glue.c @@ -597,7 +597,8 @@ static int __init serpent_init(void) { const char *feature_name; - if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) { + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, + &feature_name)) { pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } diff --git a/arch/x86/crypto/sha1_ni_asm.S b/arch/x86/crypto/sha1_ni_asm.S new file mode 100644 index 000000000000..874a651b9e7d --- /dev/null +++ b/arch/x86/crypto/sha1_ni_asm.S @@ -0,0 +1,302 @@ +/* + * Intel SHA Extensions optimized implementation of a SHA-1 update function + * + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2015 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * Contact Information: + * Sean Gulley <sean.m.gulley@intel.com> + * Tim Chen <tim.c.chen@linux.intel.com> + * + * BSD LICENSE + * + * Copyright(c) 2015 Intel Corporation. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + */ + +#include <linux/linkage.h> + +#define DIGEST_PTR %rdi /* 1st arg */ +#define DATA_PTR %rsi /* 2nd arg */ +#define NUM_BLKS %rdx /* 3rd arg */ + +#define RSPSAVE %rax + +/* gcc conversion */ +#define FRAME_SIZE 32 /* space for 2x16 bytes */ + +#define ABCD %xmm0 +#define E0 %xmm1 /* Need two E's b/c they ping pong */ +#define E1 %xmm2 +#define MSG0 %xmm3 +#define MSG1 %xmm4 +#define MSG2 %xmm5 +#define MSG3 %xmm6 +#define SHUF_MASK %xmm7 + + +/* + * Intel SHA Extensions optimized implementation of a SHA-1 update function + * + * The function takes a pointer to the current hash values, a pointer to the + * input data, and a number of 64 byte blocks to process. Once all blocks have + * been processed, the digest pointer is updated with the resulting hash value. + * The function only processes complete blocks, there is no functionality to + * store partial blocks. All message padding and hash value initialization must + * be done outside the update function. + * + * The indented lines in the loop are instructions related to rounds processing. + * The non-indented lines are instructions related to the message schedule. + * + * void sha1_ni_transform(uint32_t *digest, const void *data, + uint32_t numBlocks) + * digest : pointer to digest + * data: pointer to input data + * numBlocks: Number of blocks to process + */ +.text +.align 32 +ENTRY(sha1_ni_transform) + mov %rsp, RSPSAVE + sub $FRAME_SIZE, %rsp + and $~0xF, %rsp + + shl $6, NUM_BLKS /* convert to bytes */ + jz .Ldone_hash + add DATA_PTR, NUM_BLKS /* pointer to end of data */ + + /* load initial hash values */ + pinsrd $3, 1*16(DIGEST_PTR), E0 + movdqu 0*16(DIGEST_PTR), ABCD + pand UPPER_WORD_MASK(%rip), E0 + pshufd $0x1B, ABCD, ABCD + + movdqa PSHUFFLE_BYTE_FLIP_MASK(%rip), SHUF_MASK + +.Lloop0: + /* Save hash values for addition after rounds */ + movdqa E0, (0*16)(%rsp) + movdqa ABCD, (1*16)(%rsp) + + /* Rounds 0-3 */ + movdqu 0*16(DATA_PTR), MSG0 + pshufb SHUF_MASK, MSG0 + paddd MSG0, E0 + movdqa ABCD, E1 + sha1rnds4 $0, E0, ABCD + + /* Rounds 4-7 */ + movdqu 1*16(DATA_PTR), MSG1 + pshufb SHUF_MASK, MSG1 + sha1nexte MSG1, E1 + movdqa ABCD, E0 + sha1rnds4 $0, E1, ABCD + sha1msg1 MSG1, MSG0 + + /* Rounds 8-11 */ + movdqu 2*16(DATA_PTR), MSG2 + pshufb SHUF_MASK, MSG2 + sha1nexte MSG2, E0 + movdqa ABCD, E1 + sha1rnds4 $0, E0, ABCD + sha1msg1 MSG2, MSG1 + pxor MSG2, MSG0 + + /* Rounds 12-15 */ + movdqu 3*16(DATA_PTR), MSG3 + pshufb SHUF_MASK, MSG3 + sha1nexte MSG3, E1 + movdqa ABCD, E0 + sha1msg2 MSG3, MSG0 + sha1rnds4 $0, E1, ABCD + sha1msg1 MSG3, MSG2 + pxor MSG3, MSG1 + + /* Rounds 16-19 */ + sha1nexte MSG0, E0 + movdqa ABCD, E1 + sha1msg2 MSG0, MSG1 + sha1rnds4 $0, E0, ABCD + sha1msg1 MSG0, MSG3 + pxor MSG0, MSG2 + + /* Rounds 20-23 */ + sha1nexte MSG1, E1 + movdqa ABCD, E0 + sha1msg2 MSG1, MSG2 + sha1rnds4 $1, E1, ABCD + sha1msg1 MSG1, MSG0 + pxor MSG1, MSG3 + + /* Rounds 24-27 */ + sha1nexte MSG2, E0 + movdqa ABCD, E1 + sha1msg2 MSG2, MSG3 + sha1rnds4 $1, E0, ABCD + sha1msg1 MSG2, MSG1 + pxor MSG2, MSG0 + + /* Rounds 28-31 */ + sha1nexte MSG3, E1 + movdqa ABCD, E0 + sha1msg2 MSG3, MSG0 + sha1rnds4 $1, E1, ABCD + sha1msg1 MSG3, MSG2 + pxor MSG3, MSG1 + + /* Rounds 32-35 */ + sha1nexte MSG0, E0 + movdqa ABCD, E1 + sha1msg2 MSG0, MSG1 + sha1rnds4 $1, E0, ABCD + sha1msg1 MSG0, MSG3 + pxor MSG0, MSG2 + + /* Rounds 36-39 */ + sha1nexte MSG1, E1 + movdqa ABCD, E0 + sha1msg2 MSG1, MSG2 + sha1rnds4 $1, E1, ABCD + sha1msg1 MSG1, MSG0 + pxor MSG1, MSG3 + + /* Rounds 40-43 */ + sha1nexte MSG2, E0 + movdqa ABCD, E1 + sha1msg2 MSG2, MSG3 + sha1rnds4 $2, E0, ABCD + sha1msg1 MSG2, MSG1 + pxor MSG2, MSG0 + + /* Rounds 44-47 */ + sha1nexte MSG3, E1 + movdqa ABCD, E0 + sha1msg2 MSG3, MSG0 + sha1rnds4 $2, E1, ABCD + sha1msg1 MSG3, MSG2 + pxor MSG3, MSG1 + + /* Rounds 48-51 */ + sha1nexte MSG0, E0 + movdqa ABCD, E1 + sha1msg2 MSG0, MSG1 + sha1rnds4 $2, E0, ABCD + sha1msg1 MSG0, MSG3 + pxor MSG0, MSG2 + + /* Rounds 52-55 */ + sha1nexte MSG1, E1 + movdqa ABCD, E0 + sha1msg2 MSG1, MSG2 + sha1rnds4 $2, E1, ABCD + sha1msg1 MSG1, MSG0 + pxor MSG1, MSG3 + + /* Rounds 56-59 */ + sha1nexte MSG2, E0 + movdqa ABCD, E1 + sha1msg2 MSG2, MSG3 + sha1rnds4 $2, E0, ABCD + sha1msg1 MSG2, MSG1 + pxor MSG2, MSG0 + + /* Rounds 60-63 */ + sha1nexte MSG3, E1 + movdqa ABCD, E0 + sha1msg2 MSG3, MSG0 + sha1rnds4 $3, E1, ABCD + sha1msg1 MSG3, MSG2 + pxor MSG3, MSG1 + + /* Rounds 64-67 */ + sha1nexte MSG0, E0 + movdqa ABCD, E1 + sha1msg2 MSG0, MSG1 + sha1rnds4 $3, E0, ABCD + sha1msg1 MSG0, MSG3 + pxor MSG0, MSG2 + + /* Rounds 68-71 */ + sha1nexte MSG1, E1 + movdqa ABCD, E0 + sha1msg2 MSG1, MSG2 + sha1rnds4 $3, E1, ABCD + pxor MSG1, MSG3 + + /* Rounds 72-75 */ + sha1nexte MSG2, E0 + movdqa ABCD, E1 + sha1msg2 MSG2, MSG3 + sha1rnds4 $3, E0, ABCD + + /* Rounds 76-79 */ + sha1nexte MSG3, E1 + movdqa ABCD, E0 + sha1rnds4 $3, E1, ABCD + + /* Add current hash values with previously saved */ + sha1nexte (0*16)(%rsp), E0 + paddd (1*16)(%rsp), ABCD + + /* Increment data pointer and loop if more to process */ + add $64, DATA_PTR + cmp NUM_BLKS, DATA_PTR + jne .Lloop0 + + /* Write hash values back in the correct order */ + pshufd $0x1B, ABCD, ABCD + movdqu ABCD, 0*16(DIGEST_PTR) + pextrd $3, E0, 1*16(DIGEST_PTR) + +.Ldone_hash: + mov RSPSAVE, %rsp + + ret +ENDPROC(sha1_ni_transform) + +.data + +.align 64 +PSHUFFLE_BYTE_FLIP_MASK: + .octa 0x000102030405060708090a0b0c0d0e0f +UPPER_WORD_MASK: + .octa 0xFFFFFFFF000000000000000000000000 diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c index 7c48e8b20848..dd14616b7739 100644 --- a/arch/x86/crypto/sha1_ssse3_glue.c +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -31,24 +31,11 @@ #include <crypto/sha1_base.h> #include <asm/fpu/api.h> +typedef void (sha1_transform_fn)(u32 *digest, const char *data, + unsigned int rounds); -asmlinkage void sha1_transform_ssse3(u32 *digest, const char *data, - unsigned int rounds); -#ifdef CONFIG_AS_AVX -asmlinkage void sha1_transform_avx(u32 *digest, const char *data, - unsigned int rounds); -#endif -#ifdef CONFIG_AS_AVX2 -#define SHA1_AVX2_BLOCK_OPTSIZE 4 /* optimal 4*64 bytes of SHA1 blocks */ - -asmlinkage void sha1_transform_avx2(u32 *digest, const char *data, - unsigned int rounds); -#endif - -static void (*sha1_transform_asm)(u32 *, const char *, unsigned int); - -static int sha1_ssse3_update(struct shash_desc *desc, const u8 *data, - unsigned int len) +static int sha1_update(struct shash_desc *desc, const u8 *data, + unsigned int len, sha1_transform_fn *sha1_xform) { struct sha1_state *sctx = shash_desc_ctx(desc); @@ -61,14 +48,14 @@ static int sha1_ssse3_update(struct shash_desc *desc, const u8 *data, kernel_fpu_begin(); sha1_base_do_update(desc, data, len, - (sha1_block_fn *)sha1_transform_asm); + (sha1_block_fn *)sha1_xform); kernel_fpu_end(); return 0; } -static int sha1_ssse3_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) +static int sha1_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out, sha1_transform_fn *sha1_xform) { if (!irq_fpu_usable()) return crypto_sha1_finup(desc, data, len, out); @@ -76,32 +63,37 @@ static int sha1_ssse3_finup(struct shash_desc *desc, const u8 *data, kernel_fpu_begin(); if (len) sha1_base_do_update(desc, data, len, - (sha1_block_fn *)sha1_transform_asm); - sha1_base_do_finalize(desc, (sha1_block_fn *)sha1_transform_asm); + (sha1_block_fn *)sha1_xform); + sha1_base_do_finalize(desc, (sha1_block_fn *)sha1_xform); kernel_fpu_end(); return sha1_base_finish(desc, out); } -/* Add padding and return the message digest. */ -static int sha1_ssse3_final(struct shash_desc *desc, u8 *out) +asmlinkage void sha1_transform_ssse3(u32 *digest, const char *data, + unsigned int rounds); + +static int sha1_ssse3_update(struct shash_desc *desc, const u8 *data, + unsigned int len) { - return sha1_ssse3_finup(desc, NULL, 0, out); + return sha1_update(desc, data, len, + (sha1_transform_fn *) sha1_transform_ssse3); } -#ifdef CONFIG_AS_AVX2 -static void sha1_apply_transform_avx2(u32 *digest, const char *data, - unsigned int rounds) +static int sha1_ssse3_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) { - /* Select the optimal transform based on data block size */ - if (rounds >= SHA1_AVX2_BLOCK_OPTSIZE) - sha1_transform_avx2(digest, data, rounds); - else - sha1_transform_avx(digest, data, rounds); + return sha1_finup(desc, data, len, out, + (sha1_transform_fn *) sha1_transform_ssse3); +} + +/* Add padding and return the message digest. */ +static int sha1_ssse3_final(struct shash_desc *desc, u8 *out) +{ + return sha1_ssse3_finup(desc, NULL, 0, out); } -#endif -static struct shash_alg alg = { +static struct shash_alg sha1_ssse3_alg = { .digestsize = SHA1_DIGEST_SIZE, .init = sha1_base_init, .update = sha1_ssse3_update, @@ -110,7 +102,7 @@ static struct shash_alg alg = { .descsize = sizeof(struct sha1_state), .base = { .cra_name = "sha1", - .cra_driver_name= "sha1-ssse3", + .cra_driver_name = "sha1-ssse3", .cra_priority = 150, .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA1_BLOCK_SIZE, @@ -118,10 +110,62 @@ static struct shash_alg alg = { } }; +static int register_sha1_ssse3(void) +{ + if (boot_cpu_has(X86_FEATURE_SSSE3)) + return crypto_register_shash(&sha1_ssse3_alg); + return 0; +} + +static void unregister_sha1_ssse3(void) +{ + if (boot_cpu_has(X86_FEATURE_SSSE3)) + crypto_unregister_shash(&sha1_ssse3_alg); +} + #ifdef CONFIG_AS_AVX -static bool __init avx_usable(void) +asmlinkage void sha1_transform_avx(u32 *digest, const char *data, + unsigned int rounds); + +static int sha1_avx_update(struct shash_desc *desc, const u8 *data, + unsigned int len) { - if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) { + return sha1_update(desc, data, len, + (sha1_transform_fn *) sha1_transform_avx); +} + +static int sha1_avx_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha1_finup(desc, data, len, out, + (sha1_transform_fn *) sha1_transform_avx); +} + +static int sha1_avx_final(struct shash_desc *desc, u8 *out) +{ + return sha1_avx_finup(desc, NULL, 0, out); +} + +static struct shash_alg sha1_avx_alg = { + .digestsize = SHA1_DIGEST_SIZE, + .init = sha1_base_init, + .update = sha1_avx_update, + .final = sha1_avx_final, + .finup = sha1_avx_finup, + .descsize = sizeof(struct sha1_state), + .base = { + .cra_name = "sha1", + .cra_driver_name = "sha1-avx", + .cra_priority = 160, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA1_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +}; + +static bool avx_usable(void) +{ + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) { if (cpu_has_avx) pr_info("AVX detected but unusable.\n"); return false; @@ -130,55 +174,197 @@ static bool __init avx_usable(void) return true; } -#ifdef CONFIG_AS_AVX2 -static bool __init avx2_usable(void) +static int register_sha1_avx(void) +{ + if (avx_usable()) + return crypto_register_shash(&sha1_avx_alg); + return 0; +} + +static void unregister_sha1_avx(void) { - if (avx_usable() && cpu_has_avx2 && boot_cpu_has(X86_FEATURE_BMI1) && - boot_cpu_has(X86_FEATURE_BMI2)) + if (avx_usable()) + crypto_unregister_shash(&sha1_avx_alg); +} + +#else /* CONFIG_AS_AVX */ +static inline int register_sha1_avx(void) { return 0; } +static inline void unregister_sha1_avx(void) { } +#endif /* CONFIG_AS_AVX */ + + +#if defined(CONFIG_AS_AVX2) && (CONFIG_AS_AVX) +#define SHA1_AVX2_BLOCK_OPTSIZE 4 /* optimal 4*64 bytes of SHA1 blocks */ + +asmlinkage void sha1_transform_avx2(u32 *digest, const char *data, + unsigned int rounds); + +static bool avx2_usable(void) +{ + if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2) + && boot_cpu_has(X86_FEATURE_BMI1) + && boot_cpu_has(X86_FEATURE_BMI2)) return true; return false; } + +static void sha1_apply_transform_avx2(u32 *digest, const char *data, + unsigned int rounds) +{ + /* Select the optimal transform based on data block size */ + if (rounds >= SHA1_AVX2_BLOCK_OPTSIZE) + sha1_transform_avx2(digest, data, rounds); + else + sha1_transform_avx(digest, data, rounds); +} + +static int sha1_avx2_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + return sha1_update(desc, data, len, + (sha1_transform_fn *) sha1_apply_transform_avx2); +} + +static int sha1_avx2_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha1_finup(desc, data, len, out, + (sha1_transform_fn *) sha1_apply_transform_avx2); +} + +static int sha1_avx2_final(struct shash_desc *desc, u8 *out) +{ + return sha1_avx2_finup(desc, NULL, 0, out); +} + +static struct shash_alg sha1_avx2_alg = { + .digestsize = SHA1_DIGEST_SIZE, + .init = sha1_base_init, + .update = sha1_avx2_update, + .final = sha1_avx2_final, + .finup = sha1_avx2_finup, + .descsize = sizeof(struct sha1_state), + .base = { + .cra_name = "sha1", + .cra_driver_name = "sha1-avx2", + .cra_priority = 170, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA1_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +}; + +static int register_sha1_avx2(void) +{ + if (avx2_usable()) + return crypto_register_shash(&sha1_avx2_alg); + return 0; +} + +static void unregister_sha1_avx2(void) +{ + if (avx2_usable()) + crypto_unregister_shash(&sha1_avx2_alg); +} + +#else +static inline int register_sha1_avx2(void) { return 0; } +static inline void unregister_sha1_avx2(void) { } #endif + +#ifdef CONFIG_AS_SHA1_NI +asmlinkage void sha1_ni_transform(u32 *digest, const char *data, + unsigned int rounds); + +static int sha1_ni_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + return sha1_update(desc, data, len, + (sha1_transform_fn *) sha1_ni_transform); +} + +static int sha1_ni_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha1_finup(desc, data, len, out, + (sha1_transform_fn *) sha1_ni_transform); +} + +static int sha1_ni_final(struct shash_desc *desc, u8 *out) +{ + return sha1_ni_finup(desc, NULL, 0, out); +} + +static struct shash_alg sha1_ni_alg = { + .digestsize = SHA1_DIGEST_SIZE, + .init = sha1_base_init, + .update = sha1_ni_update, + .final = sha1_ni_final, + .finup = sha1_ni_finup, + .descsize = sizeof(struct sha1_state), + .base = { + .cra_name = "sha1", + .cra_driver_name = "sha1-ni", + .cra_priority = 250, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA1_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +}; + +static int register_sha1_ni(void) +{ + if (boot_cpu_has(X86_FEATURE_SHA_NI)) + return crypto_register_shash(&sha1_ni_alg); + return 0; +} + +static void unregister_sha1_ni(void) +{ + if (boot_cpu_has(X86_FEATURE_SHA_NI)) + crypto_unregister_shash(&sha1_ni_alg); +} + +#else +static inline int register_sha1_ni(void) { return 0; } +static inline void unregister_sha1_ni(void) { } #endif static int __init sha1_ssse3_mod_init(void) { - char *algo_name; + if (register_sha1_ssse3()) + goto fail; - /* test for SSSE3 first */ - if (cpu_has_ssse3) { - sha1_transform_asm = sha1_transform_ssse3; - algo_name = "SSSE3"; + if (register_sha1_avx()) { + unregister_sha1_ssse3(); + goto fail; } -#ifdef CONFIG_AS_AVX - /* allow AVX to override SSSE3, it's a little faster */ - if (avx_usable()) { - sha1_transform_asm = sha1_transform_avx; - algo_name = "AVX"; -#ifdef CONFIG_AS_AVX2 - /* allow AVX2 to override AVX, it's a little faster */ - if (avx2_usable()) { - sha1_transform_asm = sha1_apply_transform_avx2; - algo_name = "AVX2"; - } -#endif + if (register_sha1_avx2()) { + unregister_sha1_avx(); + unregister_sha1_ssse3(); + goto fail; } -#endif - if (sha1_transform_asm) { - pr_info("Using %s optimized SHA-1 implementation\n", algo_name); - return crypto_register_shash(&alg); + if (register_sha1_ni()) { + unregister_sha1_avx2(); + unregister_sha1_avx(); + unregister_sha1_ssse3(); + goto fail; } - pr_info("Neither AVX nor AVX2 nor SSSE3 is available/usable.\n"); + return 0; +fail: return -ENODEV; } static void __exit sha1_ssse3_mod_fini(void) { - crypto_unregister_shash(&alg); + unregister_sha1_ni(); + unregister_sha1_avx2(); + unregister_sha1_avx(); + unregister_sha1_ssse3(); } module_init(sha1_ssse3_mod_init); diff --git a/arch/x86/crypto/sha256_ni_asm.S b/arch/x86/crypto/sha256_ni_asm.S new file mode 100644 index 000000000000..748cdf21a938 --- /dev/null +++ b/arch/x86/crypto/sha256_ni_asm.S @@ -0,0 +1,353 @@ +/* + * Intel SHA Extensions optimized implementation of a SHA-256 update function + * + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2015 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * Contact Information: + * Sean Gulley <sean.m.gulley@intel.com> + * Tim Chen <tim.c.chen@linux.intel.com> + * + * BSD LICENSE + * + * Copyright(c) 2015 Intel Corporation. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + */ + +#include <linux/linkage.h> + +#define DIGEST_PTR %rdi /* 1st arg */ +#define DATA_PTR %rsi /* 2nd arg */ +#define NUM_BLKS %rdx /* 3rd arg */ + +#define SHA256CONSTANTS %rax + +#define MSG %xmm0 +#define STATE0 %xmm1 +#define STATE1 %xmm2 +#define MSGTMP0 %xmm3 +#define MSGTMP1 %xmm4 +#define MSGTMP2 %xmm5 +#define MSGTMP3 %xmm6 +#define MSGTMP4 %xmm7 + +#define SHUF_MASK %xmm8 + +#define ABEF_SAVE %xmm9 +#define CDGH_SAVE %xmm10 + +/* + * Intel SHA Extensions optimized implementation of a SHA-256 update function + * + * The function takes a pointer to the current hash values, a pointer to the + * input data, and a number of 64 byte blocks to process. Once all blocks have + * been processed, the digest pointer is updated with the resulting hash value. + * The function only processes complete blocks, there is no functionality to + * store partial blocks. All message padding and hash value initialization must + * be done outside the update function. + * + * The indented lines in the loop are instructions related to rounds processing. + * The non-indented lines are instructions related to the message schedule. + * + * void sha256_ni_transform(uint32_t *digest, const void *data, + uint32_t numBlocks); + * digest : pointer to digest + * data: pointer to input data + * numBlocks: Number of blocks to process + */ + +.text +.align 32 +ENTRY(sha256_ni_transform) + + shl $6, NUM_BLKS /* convert to bytes */ + jz .Ldone_hash + add DATA_PTR, NUM_BLKS /* pointer to end of data */ + + /* + * load initial hash values + * Need to reorder these appropriately + * DCBA, HGFE -> ABEF, CDGH + */ + movdqu 0*16(DIGEST_PTR), STATE0 + movdqu 1*16(DIGEST_PTR), STATE1 + + pshufd $0xB1, STATE0, STATE0 /* CDAB */ + pshufd $0x1B, STATE1, STATE1 /* EFGH */ + movdqa STATE0, MSGTMP4 + palignr $8, STATE1, STATE0 /* ABEF */ + pblendw $0xF0, MSGTMP4, STATE1 /* CDGH */ + + movdqa PSHUFFLE_BYTE_FLIP_MASK(%rip), SHUF_MASK + lea K256(%rip), SHA256CONSTANTS + +.Lloop0: + /* Save hash values for addition after rounds */ + movdqa STATE0, ABEF_SAVE + movdqa STATE1, CDGH_SAVE + + /* Rounds 0-3 */ + movdqu 0*16(DATA_PTR), MSG + pshufb SHUF_MASK, MSG + movdqa MSG, MSGTMP0 + paddd 0*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + + /* Rounds 4-7 */ + movdqu 1*16(DATA_PTR), MSG + pshufb SHUF_MASK, MSG + movdqa MSG, MSGTMP1 + paddd 1*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP1, MSGTMP0 + + /* Rounds 8-11 */ + movdqu 2*16(DATA_PTR), MSG + pshufb SHUF_MASK, MSG + movdqa MSG, MSGTMP2 + paddd 2*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP2, MSGTMP1 + + /* Rounds 12-15 */ + movdqu 3*16(DATA_PTR), MSG + pshufb SHUF_MASK, MSG + movdqa MSG, MSGTMP3 + paddd 3*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP3, MSGTMP4 + palignr $4, MSGTMP2, MSGTMP4 + paddd MSGTMP4, MSGTMP0 + sha256msg2 MSGTMP3, MSGTMP0 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP3, MSGTMP2 + + /* Rounds 16-19 */ + movdqa MSGTMP0, MSG + paddd 4*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP0, MSGTMP4 + palignr $4, MSGTMP3, MSGTMP4 + paddd MSGTMP4, MSGTMP1 + sha256msg2 MSGTMP0, MSGTMP1 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP0, MSGTMP3 + + /* Rounds 20-23 */ + movdqa MSGTMP1, MSG + paddd 5*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP1, MSGTMP4 + palignr $4, MSGTMP0, MSGTMP4 + paddd MSGTMP4, MSGTMP2 + sha256msg2 MSGTMP1, MSGTMP2 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP1, MSGTMP0 + + /* Rounds 24-27 */ + movdqa MSGTMP2, MSG + paddd 6*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP2, MSGTMP4 + palignr $4, MSGTMP1, MSGTMP4 + paddd MSGTMP4, MSGTMP3 + sha256msg2 MSGTMP2, MSGTMP3 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP2, MSGTMP1 + + /* Rounds 28-31 */ + movdqa MSGTMP3, MSG + paddd 7*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP3, MSGTMP4 + palignr $4, MSGTMP2, MSGTMP4 + paddd MSGTMP4, MSGTMP0 + sha256msg2 MSGTMP3, MSGTMP0 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP3, MSGTMP2 + + /* Rounds 32-35 */ + movdqa MSGTMP0, MSG + paddd 8*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP0, MSGTMP4 + palignr $4, MSGTMP3, MSGTMP4 + paddd MSGTMP4, MSGTMP1 + sha256msg2 MSGTMP0, MSGTMP1 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP0, MSGTMP3 + + /* Rounds 36-39 */ + movdqa MSGTMP1, MSG + paddd 9*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP1, MSGTMP4 + palignr $4, MSGTMP0, MSGTMP4 + paddd MSGTMP4, MSGTMP2 + sha256msg2 MSGTMP1, MSGTMP2 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP1, MSGTMP0 + + /* Rounds 40-43 */ + movdqa MSGTMP2, MSG + paddd 10*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP2, MSGTMP4 + palignr $4, MSGTMP1, MSGTMP4 + paddd MSGTMP4, MSGTMP3 + sha256msg2 MSGTMP2, MSGTMP3 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP2, MSGTMP1 + + /* Rounds 44-47 */ + movdqa MSGTMP3, MSG + paddd 11*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP3, MSGTMP4 + palignr $4, MSGTMP2, MSGTMP4 + paddd MSGTMP4, MSGTMP0 + sha256msg2 MSGTMP3, MSGTMP0 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP3, MSGTMP2 + + /* Rounds 48-51 */ + movdqa MSGTMP0, MSG + paddd 12*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP0, MSGTMP4 + palignr $4, MSGTMP3, MSGTMP4 + paddd MSGTMP4, MSGTMP1 + sha256msg2 MSGTMP0, MSGTMP1 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP0, MSGTMP3 + + /* Rounds 52-55 */ + movdqa MSGTMP1, MSG + paddd 13*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP1, MSGTMP4 + palignr $4, MSGTMP0, MSGTMP4 + paddd MSGTMP4, MSGTMP2 + sha256msg2 MSGTMP1, MSGTMP2 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + + /* Rounds 56-59 */ + movdqa MSGTMP2, MSG + paddd 14*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP2, MSGTMP4 + palignr $4, MSGTMP1, MSGTMP4 + paddd MSGTMP4, MSGTMP3 + sha256msg2 MSGTMP2, MSGTMP3 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + + /* Rounds 60-63 */ + movdqa MSGTMP3, MSG + paddd 15*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + + /* Add current hash values with previously saved */ + paddd ABEF_SAVE, STATE0 + paddd CDGH_SAVE, STATE1 + + /* Increment data pointer and loop if more to process */ + add $64, DATA_PTR + cmp NUM_BLKS, DATA_PTR + jne .Lloop0 + + /* Write hash values back in the correct order */ + pshufd $0x1B, STATE0, STATE0 /* FEBA */ + pshufd $0xB1, STATE1, STATE1 /* DCHG */ + movdqa STATE0, MSGTMP4 + pblendw $0xF0, STATE1, STATE0 /* DCBA */ + palignr $8, MSGTMP4, STATE1 /* HGFE */ + + movdqu STATE0, 0*16(DIGEST_PTR) + movdqu STATE1, 1*16(DIGEST_PTR) + +.Ldone_hash: + + ret +ENDPROC(sha256_ni_transform) + +.data +.align 64 +K256: + .long 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5 + .long 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5 + .long 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3 + .long 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174 + .long 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc + .long 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da + .long 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7 + .long 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967 + .long 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13 + .long 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85 + .long 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3 + .long 0xd192e819,0xd6990624,0xf40e3585,0x106aa070 + .long 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5 + .long 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3 + .long 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208 + .long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2 + +PSHUFFLE_BYTE_FLIP_MASK: + .octa 0x0c0d0e0f08090a0b0405060700010203 diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c index f8097fc0d1d1..5f4d6086dc59 100644 --- a/arch/x86/crypto/sha256_ssse3_glue.c +++ b/arch/x86/crypto/sha256_ssse3_glue.c @@ -42,19 +42,10 @@ asmlinkage void sha256_transform_ssse3(u32 *digest, const char *data, u64 rounds); -#ifdef CONFIG_AS_AVX -asmlinkage void sha256_transform_avx(u32 *digest, const char *data, - u64 rounds); -#endif -#ifdef CONFIG_AS_AVX2 -asmlinkage void sha256_transform_rorx(u32 *digest, const char *data, - u64 rounds); -#endif - -static void (*sha256_transform_asm)(u32 *, const char *, u64); +typedef void (sha256_transform_fn)(u32 *digest, const char *data, u64 rounds); -static int sha256_ssse3_update(struct shash_desc *desc, const u8 *data, - unsigned int len) +static int sha256_update(struct shash_desc *desc, const u8 *data, + unsigned int len, sha256_transform_fn *sha256_xform) { struct sha256_state *sctx = shash_desc_ctx(desc); @@ -67,14 +58,14 @@ static int sha256_ssse3_update(struct shash_desc *desc, const u8 *data, kernel_fpu_begin(); sha256_base_do_update(desc, data, len, - (sha256_block_fn *)sha256_transform_asm); + (sha256_block_fn *)sha256_xform); kernel_fpu_end(); return 0; } -static int sha256_ssse3_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) +static int sha256_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out, sha256_transform_fn *sha256_xform) { if (!irq_fpu_usable()) return crypto_sha256_finup(desc, data, len, out); @@ -82,20 +73,32 @@ static int sha256_ssse3_finup(struct shash_desc *desc, const u8 *data, kernel_fpu_begin(); if (len) sha256_base_do_update(desc, data, len, - (sha256_block_fn *)sha256_transform_asm); - sha256_base_do_finalize(desc, (sha256_block_fn *)sha256_transform_asm); + (sha256_block_fn *)sha256_xform); + sha256_base_do_finalize(desc, (sha256_block_fn *)sha256_xform); kernel_fpu_end(); return sha256_base_finish(desc, out); } +static int sha256_ssse3_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + return sha256_update(desc, data, len, sha256_transform_ssse3); +} + +static int sha256_ssse3_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha256_finup(desc, data, len, out, sha256_transform_ssse3); +} + /* Add padding and return the message digest. */ static int sha256_ssse3_final(struct shash_desc *desc, u8 *out) { return sha256_ssse3_finup(desc, NULL, 0, out); } -static struct shash_alg algs[] = { { +static struct shash_alg sha256_ssse3_algs[] = { { .digestsize = SHA256_DIGEST_SIZE, .init = sha256_base_init, .update = sha256_ssse3_update, @@ -127,10 +130,77 @@ static struct shash_alg algs[] = { { } } }; +static int register_sha256_ssse3(void) +{ + if (boot_cpu_has(X86_FEATURE_SSSE3)) + return crypto_register_shashes(sha256_ssse3_algs, + ARRAY_SIZE(sha256_ssse3_algs)); + return 0; +} + +static void unregister_sha256_ssse3(void) +{ + if (boot_cpu_has(X86_FEATURE_SSSE3)) + crypto_unregister_shashes(sha256_ssse3_algs, + ARRAY_SIZE(sha256_ssse3_algs)); +} + #ifdef CONFIG_AS_AVX -static bool __init avx_usable(void) +asmlinkage void sha256_transform_avx(u32 *digest, const char *data, + u64 rounds); + +static int sha256_avx_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + return sha256_update(desc, data, len, sha256_transform_avx); +} + +static int sha256_avx_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha256_finup(desc, data, len, out, sha256_transform_avx); +} + +static int sha256_avx_final(struct shash_desc *desc, u8 *out) +{ + return sha256_avx_finup(desc, NULL, 0, out); +} + +static struct shash_alg sha256_avx_algs[] = { { + .digestsize = SHA256_DIGEST_SIZE, + .init = sha256_base_init, + .update = sha256_avx_update, + .final = sha256_avx_final, + .finup = sha256_avx_finup, + .descsize = sizeof(struct sha256_state), + .base = { + .cra_name = "sha256", + .cra_driver_name = "sha256-avx", + .cra_priority = 160, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA256_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +}, { + .digestsize = SHA224_DIGEST_SIZE, + .init = sha224_base_init, + .update = sha256_avx_update, + .final = sha256_avx_final, + .finup = sha256_avx_finup, + .descsize = sizeof(struct sha256_state), + .base = { + .cra_name = "sha224", + .cra_driver_name = "sha224-avx", + .cra_priority = 160, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA224_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +} }; + +static bool avx_usable(void) { - if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) { + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) { if (cpu_has_avx) pr_info("AVX detected but unusable.\n"); return false; @@ -138,47 +208,216 @@ static bool __init avx_usable(void) return true; } -#endif -static int __init sha256_ssse3_mod_init(void) +static int register_sha256_avx(void) { - /* test for SSSE3 first */ - if (cpu_has_ssse3) - sha256_transform_asm = sha256_transform_ssse3; + if (avx_usable()) + return crypto_register_shashes(sha256_avx_algs, + ARRAY_SIZE(sha256_avx_algs)); + return 0; +} -#ifdef CONFIG_AS_AVX - /* allow AVX to override SSSE3, it's a little faster */ - if (avx_usable()) { -#ifdef CONFIG_AS_AVX2 - if (boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_BMI2)) - sha256_transform_asm = sha256_transform_rorx; - else +static void unregister_sha256_avx(void) +{ + if (avx_usable()) + crypto_unregister_shashes(sha256_avx_algs, + ARRAY_SIZE(sha256_avx_algs)); +} + +#else +static inline int register_sha256_avx(void) { return 0; } +static inline void unregister_sha256_avx(void) { } #endif - sha256_transform_asm = sha256_transform_avx; + +#if defined(CONFIG_AS_AVX2) && defined(CONFIG_AS_AVX) +asmlinkage void sha256_transform_rorx(u32 *digest, const char *data, + u64 rounds); + +static int sha256_avx2_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + return sha256_update(desc, data, len, sha256_transform_rorx); +} + +static int sha256_avx2_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha256_finup(desc, data, len, out, sha256_transform_rorx); +} + +static int sha256_avx2_final(struct shash_desc *desc, u8 *out) +{ + return sha256_avx2_finup(desc, NULL, 0, out); +} + +static struct shash_alg sha256_avx2_algs[] = { { + .digestsize = SHA256_DIGEST_SIZE, + .init = sha256_base_init, + .update = sha256_avx2_update, + .final = sha256_avx2_final, + .finup = sha256_avx2_finup, + .descsize = sizeof(struct sha256_state), + .base = { + .cra_name = "sha256", + .cra_driver_name = "sha256-avx2", + .cra_priority = 170, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA256_BLOCK_SIZE, + .cra_module = THIS_MODULE, } -#endif +}, { + .digestsize = SHA224_DIGEST_SIZE, + .init = sha224_base_init, + .update = sha256_avx2_update, + .final = sha256_avx2_final, + .finup = sha256_avx2_finup, + .descsize = sizeof(struct sha256_state), + .base = { + .cra_name = "sha224", + .cra_driver_name = "sha224-avx2", + .cra_priority = 170, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA224_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +} }; - if (sha256_transform_asm) { -#ifdef CONFIG_AS_AVX - if (sha256_transform_asm == sha256_transform_avx) - pr_info("Using AVX optimized SHA-256 implementation\n"); -#ifdef CONFIG_AS_AVX2 - else if (sha256_transform_asm == sha256_transform_rorx) - pr_info("Using AVX2 optimized SHA-256 implementation\n"); +static bool avx2_usable(void) +{ + if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2) && + boot_cpu_has(X86_FEATURE_BMI2)) + return true; + + return false; +} + +static int register_sha256_avx2(void) +{ + if (avx2_usable()) + return crypto_register_shashes(sha256_avx2_algs, + ARRAY_SIZE(sha256_avx2_algs)); + return 0; +} + +static void unregister_sha256_avx2(void) +{ + if (avx2_usable()) + crypto_unregister_shashes(sha256_avx2_algs, + ARRAY_SIZE(sha256_avx2_algs)); +} + +#else +static inline int register_sha256_avx2(void) { return 0; } +static inline void unregister_sha256_avx2(void) { } #endif - else + +#ifdef CONFIG_AS_SHA256_NI +asmlinkage void sha256_ni_transform(u32 *digest, const char *data, + u64 rounds); /*unsigned int rounds);*/ + +static int sha256_ni_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + return sha256_update(desc, data, len, sha256_ni_transform); +} + +static int sha256_ni_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha256_finup(desc, data, len, out, sha256_ni_transform); +} + +static int sha256_ni_final(struct shash_desc *desc, u8 *out) +{ + return sha256_ni_finup(desc, NULL, 0, out); +} + +static struct shash_alg sha256_ni_algs[] = { { + .digestsize = SHA256_DIGEST_SIZE, + .init = sha256_base_init, + .update = sha256_ni_update, + .final = sha256_ni_final, + .finup = sha256_ni_finup, + .descsize = sizeof(struct sha256_state), + .base = { + .cra_name = "sha256", + .cra_driver_name = "sha256-ni", + .cra_priority = 250, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA256_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +}, { + .digestsize = SHA224_DIGEST_SIZE, + .init = sha224_base_init, + .update = sha256_ni_update, + .final = sha256_ni_final, + .finup = sha256_ni_finup, + .descsize = sizeof(struct sha256_state), + .base = { + .cra_name = "sha224", + .cra_driver_name = "sha224-ni", + .cra_priority = 250, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA224_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +} }; + +static int register_sha256_ni(void) +{ + if (boot_cpu_has(X86_FEATURE_SHA_NI)) + return crypto_register_shashes(sha256_ni_algs, + ARRAY_SIZE(sha256_ni_algs)); + return 0; +} + +static void unregister_sha256_ni(void) +{ + if (boot_cpu_has(X86_FEATURE_SHA_NI)) + crypto_unregister_shashes(sha256_ni_algs, + ARRAY_SIZE(sha256_ni_algs)); +} + +#else +static inline int register_sha256_ni(void) { return 0; } +static inline void unregister_sha256_ni(void) { } #endif - pr_info("Using SSSE3 optimized SHA-256 implementation\n"); - return crypto_register_shashes(algs, ARRAY_SIZE(algs)); + +static int __init sha256_ssse3_mod_init(void) +{ + if (register_sha256_ssse3()) + goto fail; + + if (register_sha256_avx()) { + unregister_sha256_ssse3(); + goto fail; } - pr_info("Neither AVX nor SSSE3 is available/usable.\n"); + if (register_sha256_avx2()) { + unregister_sha256_avx(); + unregister_sha256_ssse3(); + goto fail; + } + + if (register_sha256_ni()) { + unregister_sha256_avx2(); + unregister_sha256_avx(); + unregister_sha256_ssse3(); + goto fail; + } + + return 0; +fail: return -ENODEV; } static void __exit sha256_ssse3_mod_fini(void) { - crypto_unregister_shashes(algs, ARRAY_SIZE(algs)); + unregister_sha256_ni(); + unregister_sha256_avx2(); + unregister_sha256_avx(); + unregister_sha256_ssse3(); } module_init(sha256_ssse3_mod_init); diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c index 2edad7b81870..34e5083d6f36 100644 --- a/arch/x86/crypto/sha512_ssse3_glue.c +++ b/arch/x86/crypto/sha512_ssse3_glue.c @@ -41,19 +41,11 @@ asmlinkage void sha512_transform_ssse3(u64 *digest, const char *data, u64 rounds); -#ifdef CONFIG_AS_AVX -asmlinkage void sha512_transform_avx(u64 *digest, const char *data, - u64 rounds); -#endif -#ifdef CONFIG_AS_AVX2 -asmlinkage void sha512_transform_rorx(u64 *digest, const char *data, - u64 rounds); -#endif -static void (*sha512_transform_asm)(u64 *, const char *, u64); +typedef void (sha512_transform_fn)(u64 *digest, const char *data, u64 rounds); -static int sha512_ssse3_update(struct shash_desc *desc, const u8 *data, - unsigned int len) +static int sha512_update(struct shash_desc *desc, const u8 *data, + unsigned int len, sha512_transform_fn *sha512_xform) { struct sha512_state *sctx = shash_desc_ctx(desc); @@ -66,14 +58,14 @@ static int sha512_ssse3_update(struct shash_desc *desc, const u8 *data, kernel_fpu_begin(); sha512_base_do_update(desc, data, len, - (sha512_block_fn *)sha512_transform_asm); + (sha512_block_fn *)sha512_xform); kernel_fpu_end(); return 0; } -static int sha512_ssse3_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) +static int sha512_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out, sha512_transform_fn *sha512_xform) { if (!irq_fpu_usable()) return crypto_sha512_finup(desc, data, len, out); @@ -81,20 +73,32 @@ static int sha512_ssse3_finup(struct shash_desc *desc, const u8 *data, kernel_fpu_begin(); if (len) sha512_base_do_update(desc, data, len, - (sha512_block_fn *)sha512_transform_asm); - sha512_base_do_finalize(desc, (sha512_block_fn *)sha512_transform_asm); + (sha512_block_fn *)sha512_xform); + sha512_base_do_finalize(desc, (sha512_block_fn *)sha512_xform); kernel_fpu_end(); return sha512_base_finish(desc, out); } +static int sha512_ssse3_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + return sha512_update(desc, data, len, sha512_transform_ssse3); +} + +static int sha512_ssse3_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha512_finup(desc, data, len, out, sha512_transform_ssse3); +} + /* Add padding and return the message digest. */ static int sha512_ssse3_final(struct shash_desc *desc, u8 *out) { return sha512_ssse3_finup(desc, NULL, 0, out); } -static struct shash_alg algs[] = { { +static struct shash_alg sha512_ssse3_algs[] = { { .digestsize = SHA512_DIGEST_SIZE, .init = sha512_base_init, .update = sha512_ssse3_update, @@ -126,10 +130,27 @@ static struct shash_alg algs[] = { { } } }; +static int register_sha512_ssse3(void) +{ + if (boot_cpu_has(X86_FEATURE_SSSE3)) + return crypto_register_shashes(sha512_ssse3_algs, + ARRAY_SIZE(sha512_ssse3_algs)); + return 0; +} + +static void unregister_sha512_ssse3(void) +{ + if (boot_cpu_has(X86_FEATURE_SSSE3)) + crypto_unregister_shashes(sha512_ssse3_algs, + ARRAY_SIZE(sha512_ssse3_algs)); +} + #ifdef CONFIG_AS_AVX -static bool __init avx_usable(void) +asmlinkage void sha512_transform_avx(u64 *digest, const char *data, + u64 rounds); +static bool avx_usable(void) { - if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) { + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) { if (cpu_has_avx) pr_info("AVX detected but unusable.\n"); return false; @@ -137,47 +158,185 @@ static bool __init avx_usable(void) return true; } -#endif -static int __init sha512_ssse3_mod_init(void) +static int sha512_avx_update(struct shash_desc *desc, const u8 *data, + unsigned int len) { - /* test for SSSE3 first */ - if (cpu_has_ssse3) - sha512_transform_asm = sha512_transform_ssse3; + return sha512_update(desc, data, len, sha512_transform_avx); +} -#ifdef CONFIG_AS_AVX - /* allow AVX to override SSSE3, it's a little faster */ - if (avx_usable()) { -#ifdef CONFIG_AS_AVX2 - if (boot_cpu_has(X86_FEATURE_AVX2)) - sha512_transform_asm = sha512_transform_rorx; - else -#endif - sha512_transform_asm = sha512_transform_avx; +static int sha512_avx_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha512_finup(desc, data, len, out, sha512_transform_avx); +} + +/* Add padding and return the message digest. */ +static int sha512_avx_final(struct shash_desc *desc, u8 *out) +{ + return sha512_avx_finup(desc, NULL, 0, out); +} + +static struct shash_alg sha512_avx_algs[] = { { + .digestsize = SHA512_DIGEST_SIZE, + .init = sha512_base_init, + .update = sha512_avx_update, + .final = sha512_avx_final, + .finup = sha512_avx_finup, + .descsize = sizeof(struct sha512_state), + .base = { + .cra_name = "sha512", + .cra_driver_name = "sha512-avx", + .cra_priority = 160, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA512_BLOCK_SIZE, + .cra_module = THIS_MODULE, } -#endif +}, { + .digestsize = SHA384_DIGEST_SIZE, + .init = sha384_base_init, + .update = sha512_avx_update, + .final = sha512_avx_final, + .finup = sha512_avx_finup, + .descsize = sizeof(struct sha512_state), + .base = { + .cra_name = "sha384", + .cra_driver_name = "sha384-avx", + .cra_priority = 160, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA384_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +} }; - if (sha512_transform_asm) { -#ifdef CONFIG_AS_AVX - if (sha512_transform_asm == sha512_transform_avx) - pr_info("Using AVX optimized SHA-512 implementation\n"); -#ifdef CONFIG_AS_AVX2 - else if (sha512_transform_asm == sha512_transform_rorx) - pr_info("Using AVX2 optimized SHA-512 implementation\n"); +static int register_sha512_avx(void) +{ + if (avx_usable()) + return crypto_register_shashes(sha512_avx_algs, + ARRAY_SIZE(sha512_avx_algs)); + return 0; +} + +static void unregister_sha512_avx(void) +{ + if (avx_usable()) + crypto_unregister_shashes(sha512_avx_algs, + ARRAY_SIZE(sha512_avx_algs)); +} +#else +static inline int register_sha512_avx(void) { return 0; } +static inline void unregister_sha512_avx(void) { } #endif - else + +#if defined(CONFIG_AS_AVX2) && defined(CONFIG_AS_AVX) +asmlinkage void sha512_transform_rorx(u64 *digest, const char *data, + u64 rounds); + +static int sha512_avx2_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + return sha512_update(desc, data, len, sha512_transform_rorx); +} + +static int sha512_avx2_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha512_finup(desc, data, len, out, sha512_transform_rorx); +} + +/* Add padding and return the message digest. */ +static int sha512_avx2_final(struct shash_desc *desc, u8 *out) +{ + return sha512_avx2_finup(desc, NULL, 0, out); +} + +static struct shash_alg sha512_avx2_algs[] = { { + .digestsize = SHA512_DIGEST_SIZE, + .init = sha512_base_init, + .update = sha512_avx2_update, + .final = sha512_avx2_final, + .finup = sha512_avx2_finup, + .descsize = sizeof(struct sha512_state), + .base = { + .cra_name = "sha512", + .cra_driver_name = "sha512-avx2", + .cra_priority = 170, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA512_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +}, { + .digestsize = SHA384_DIGEST_SIZE, + .init = sha384_base_init, + .update = sha512_avx2_update, + .final = sha512_avx2_final, + .finup = sha512_avx2_finup, + .descsize = sizeof(struct sha512_state), + .base = { + .cra_name = "sha384", + .cra_driver_name = "sha384-avx2", + .cra_priority = 170, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA384_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +} }; + +static bool avx2_usable(void) +{ + if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2) && + boot_cpu_has(X86_FEATURE_BMI2)) + return true; + + return false; +} + +static int register_sha512_avx2(void) +{ + if (avx2_usable()) + return crypto_register_shashes(sha512_avx2_algs, + ARRAY_SIZE(sha512_avx2_algs)); + return 0; +} + +static void unregister_sha512_avx2(void) +{ + if (avx2_usable()) + crypto_unregister_shashes(sha512_avx2_algs, + ARRAY_SIZE(sha512_avx2_algs)); +} +#else +static inline int register_sha512_avx2(void) { return 0; } +static inline void unregister_sha512_avx2(void) { } #endif - pr_info("Using SSSE3 optimized SHA-512 implementation\n"); - return crypto_register_shashes(algs, ARRAY_SIZE(algs)); + +static int __init sha512_ssse3_mod_init(void) +{ + + if (register_sha512_ssse3()) + goto fail; + + if (register_sha512_avx()) { + unregister_sha512_ssse3(); + goto fail; } - pr_info("Neither AVX nor SSSE3 is available/usable.\n"); + if (register_sha512_avx2()) { + unregister_sha512_avx(); + unregister_sha512_ssse3(); + goto fail; + } + + return 0; +fail: return -ENODEV; } static void __exit sha512_ssse3_mod_fini(void) { - crypto_unregister_shashes(algs, ARRAY_SIZE(algs)); + unregister_sha512_avx2(); + unregister_sha512_avx(); + unregister_sha512_ssse3(); } module_init(sha512_ssse3_mod_init); diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c index c2bd0ce718ee..b7a3904b953c 100644 --- a/arch/x86/crypto/twofish_avx_glue.c +++ b/arch/x86/crypto/twofish_avx_glue.c @@ -558,7 +558,7 @@ static int __init twofish_init(void) { const char *feature_name; - if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) { + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_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 index 7a144971db79..bd55dedd7614 100644 --- a/arch/x86/entry/Makefile +++ b/arch/x86/entry/Makefile @@ -2,6 +2,7 @@ # Makefile for the x86 low level entry code # obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o +obj-y += common.o obj-y += vdso/ obj-y += vsyscall/ diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index f4e6308c4200..e32206e09868 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -1,3 +1,5 @@ +#include <linux/jump_label.h> + /* x86 function call convention, 64-bit: @@ -135,9 +137,6 @@ For 32-bit we have the following conventions - kernel is built with movq %rbp, 4*8+\offset(%rsp) movq %rbx, 5*8+\offset(%rsp) .endm - .macro SAVE_EXTRA_REGS_RBP offset=0 - movq %rbp, 4*8+\offset(%rsp) - .endm .macro RESTORE_EXTRA_REGS offset=0 movq 0*8+\offset(%rsp), %r15 @@ -193,12 +192,6 @@ For 32-bit we have the following conventions - kernel is built with .macro RESTORE_C_REGS_EXCEPT_RCX_R11 RESTORE_C_REGS_HELPER 1,0,0,1,1 .endm - .macro RESTORE_RSI_RDI - RESTORE_C_REGS_HELPER 0,0,0,0,0 - .endm - .macro RESTORE_RSI_RDI_RDX - RESTORE_C_REGS_HELPER 0,0,0,0,1 - .endm .macro REMOVE_PT_GPREGS_FROM_STACK addskip=0 subq $-(15*8+\addskip), %rsp @@ -241,3 +234,16 @@ For 32-bit we have the following conventions - kernel is built with #endif /* CONFIG_X86_64 */ +/* + * This does 'call enter_from_user_mode' unless we can avoid it based on + * kernel config or using the static jump infrastructure. + */ +.macro CALL_enter_from_user_mode +#ifdef CONFIG_CONTEXT_TRACKING +#ifdef HAVE_JUMP_LABEL + STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_enabled, def=0 +#endif + call enter_from_user_mode +.Lafter_call_\@: +#endif +.endm diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c new file mode 100644 index 000000000000..03663740c866 --- /dev/null +++ b/arch/x86/entry/common.c @@ -0,0 +1,486 @@ +/* + * common.c - C code for kernel entry and exit + * Copyright (c) 2015 Andrew Lutomirski + * GPL v2 + * + * Based on asm and ptrace code by many authors. The code here originated + * in ptrace.c and signal.c. + */ + +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/errno.h> +#include <linux/ptrace.h> +#include <linux/tracehook.h> +#include <linux/audit.h> +#include <linux/seccomp.h> +#include <linux/signal.h> +#include <linux/export.h> +#include <linux/context_tracking.h> +#include <linux/user-return-notifier.h> +#include <linux/uprobes.h> + +#include <asm/desc.h> +#include <asm/traps.h> +#include <asm/vdso.h> +#include <asm/uaccess.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/syscalls.h> + +static struct thread_info *pt_regs_to_thread_info(struct pt_regs *regs) +{ + unsigned long top_of_stack = + (unsigned long)(regs + 1) + TOP_OF_KERNEL_STACK_PADDING; + return (struct thread_info *)(top_of_stack - THREAD_SIZE); +} + +#ifdef CONFIG_CONTEXT_TRACKING +/* Called on entry from user mode with IRQs off. */ +__visible void enter_from_user_mode(void) +{ + CT_WARN_ON(ct_state() != CONTEXT_USER); + user_exit(); +} +#endif + +static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch) +{ +#ifdef CONFIG_X86_64 + if (arch == AUDIT_ARCH_X86_64) { + audit_syscall_entry(regs->orig_ax, regs->di, + regs->si, regs->dx, regs->r10); + } else +#endif + { + audit_syscall_entry(regs->orig_ax, regs->bx, + regs->cx, regs->dx, regs->si); + } +} + +/* + * We can return 0 to resume the syscall or anything else to go to phase + * 2. If we resume the syscall, we need to put something appropriate in + * regs->orig_ax. + * + * NB: We don't have full pt_regs here, but regs->orig_ax and regs->ax + * are fully functional. + * + * For phase 2's benefit, our return value is: + * 0: resume the syscall + * 1: go to phase 2; no seccomp phase 2 needed + * anything else: go to phase 2; pass return value to seccomp + */ +unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch) +{ + struct thread_info *ti = pt_regs_to_thread_info(regs); + unsigned long ret = 0; + u32 work; + + if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) + BUG_ON(regs != task_pt_regs(current)); + + work = ACCESS_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY; + +#ifdef CONFIG_CONTEXT_TRACKING + /* + * If TIF_NOHZ is set, we are required to call user_exit() before + * doing anything that could touch RCU. + */ + if (work & _TIF_NOHZ) { + enter_from_user_mode(); + work &= ~_TIF_NOHZ; + } +#endif + +#ifdef CONFIG_SECCOMP + /* + * Do seccomp first -- it should minimize exposure of other + * code, and keeping seccomp fast is probably more valuable + * than the rest of this. + */ + if (work & _TIF_SECCOMP) { + struct seccomp_data sd; + + sd.arch = arch; + sd.nr = regs->orig_ax; + sd.instruction_pointer = regs->ip; +#ifdef CONFIG_X86_64 + if (arch == AUDIT_ARCH_X86_64) { + sd.args[0] = regs->di; + sd.args[1] = regs->si; + sd.args[2] = regs->dx; + sd.args[3] = regs->r10; + sd.args[4] = regs->r8; + sd.args[5] = regs->r9; + } else +#endif + { + sd.args[0] = regs->bx; + sd.args[1] = regs->cx; + sd.args[2] = regs->dx; + sd.args[3] = regs->si; + sd.args[4] = regs->di; + sd.args[5] = regs->bp; + } + + BUILD_BUG_ON(SECCOMP_PHASE1_OK != 0); + BUILD_BUG_ON(SECCOMP_PHASE1_SKIP != 1); + + ret = seccomp_phase1(&sd); + if (ret == SECCOMP_PHASE1_SKIP) { + regs->orig_ax = -1; + ret = 0; + } else if (ret != SECCOMP_PHASE1_OK) { + return ret; /* Go directly to phase 2 */ + } + + work &= ~_TIF_SECCOMP; + } +#endif + + /* Do our best to finish without phase 2. */ + if (work == 0) + return ret; /* seccomp and/or nohz only (ret == 0 here) */ + +#ifdef CONFIG_AUDITSYSCALL + if (work == _TIF_SYSCALL_AUDIT) { + /* + * If there is no more work to be done except auditing, + * then audit in phase 1. Phase 2 always audits, so, if + * we audit here, then we can't go on to phase 2. + */ + do_audit_syscall_entry(regs, arch); + return 0; + } +#endif + + return 1; /* Something is enabled that we can't handle in phase 1 */ +} + +/* Returns the syscall nr to run (which should match regs->orig_ax). */ +long syscall_trace_enter_phase2(struct pt_regs *regs, u32 arch, + unsigned long phase1_result) +{ + struct thread_info *ti = pt_regs_to_thread_info(regs); + long ret = 0; + u32 work = ACCESS_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY; + + if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) + BUG_ON(regs != task_pt_regs(current)); + + /* + * If we stepped into a sysenter/syscall insn, it trapped in + * kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP. + * If user-mode had set TF itself, then it's still clear from + * do_debug() and we need to set it again to restore the user + * state. If we entered on the slow path, TF was already set. + */ + if (work & _TIF_SINGLESTEP) + regs->flags |= X86_EFLAGS_TF; + +#ifdef CONFIG_SECCOMP + /* + * Call seccomp_phase2 before running the other hooks so that + * they can see any changes made by a seccomp tracer. + */ + if (phase1_result > 1 && seccomp_phase2(phase1_result)) { + /* seccomp failures shouldn't expose any additional code. */ + return -1; + } +#endif + + if (unlikely(work & _TIF_SYSCALL_EMU)) + ret = -1L; + + if ((ret || test_thread_flag(TIF_SYSCALL_TRACE)) && + tracehook_report_syscall_entry(regs)) + ret = -1L; + + if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) + trace_sys_enter(regs, regs->orig_ax); + + do_audit_syscall_entry(regs, arch); + + return ret ?: regs->orig_ax; +} + +long syscall_trace_enter(struct pt_regs *regs) +{ + u32 arch = is_ia32_task() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; + unsigned long phase1_result = syscall_trace_enter_phase1(regs, arch); + + if (phase1_result == 0) + return regs->orig_ax; + else + return syscall_trace_enter_phase2(regs, arch, phase1_result); +} + +#define EXIT_TO_USERMODE_LOOP_FLAGS \ + (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ + _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY) + +static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) +{ + /* + * In order to return to user mode, we need to have IRQs off with + * none of _TIF_SIGPENDING, _TIF_NOTIFY_RESUME, _TIF_USER_RETURN_NOTIFY, + * _TIF_UPROBE, or _TIF_NEED_RESCHED set. Several of these flags + * can be set at any time on preemptable kernels if we have IRQs on, + * so we need to loop. Disabling preemption wouldn't help: doing the + * work to clear some of the flags can sleep. + */ + while (true) { + /* We have work to do. */ + local_irq_enable(); + + if (cached_flags & _TIF_NEED_RESCHED) + schedule(); + + if (cached_flags & _TIF_UPROBE) + uprobe_notify_resume(regs); + + /* deal with pending signal delivery */ + if (cached_flags & _TIF_SIGPENDING) + do_signal(regs); + + if (cached_flags & _TIF_NOTIFY_RESUME) { + clear_thread_flag(TIF_NOTIFY_RESUME); + tracehook_notify_resume(regs); + } + + if (cached_flags & _TIF_USER_RETURN_NOTIFY) + fire_user_return_notifiers(); + + /* Disable IRQs and retry */ + local_irq_disable(); + + cached_flags = READ_ONCE(pt_regs_to_thread_info(regs)->flags); + + if (!(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS)) + break; + + } +} + +/* Called with IRQs disabled. */ +__visible inline void prepare_exit_to_usermode(struct pt_regs *regs) +{ + u32 cached_flags; + + if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled())) + local_irq_disable(); + + lockdep_sys_exit(); + + cached_flags = + READ_ONCE(pt_regs_to_thread_info(regs)->flags); + + if (unlikely(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS)) + exit_to_usermode_loop(regs, cached_flags); + + user_enter(); +} + +#define SYSCALL_EXIT_WORK_FLAGS \ + (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ + _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT) + +static void syscall_slow_exit_work(struct pt_regs *regs, u32 cached_flags) +{ + bool step; + + audit_syscall_exit(regs); + + if (cached_flags & _TIF_SYSCALL_TRACEPOINT) + trace_sys_exit(regs, regs->ax); + + /* + * If TIF_SYSCALL_EMU is set, we only get here because of + * TIF_SINGLESTEP (i.e. this is PTRACE_SYSEMU_SINGLESTEP). + * We already reported this syscall instruction in + * syscall_trace_enter(). + */ + step = unlikely( + (cached_flags & (_TIF_SINGLESTEP | _TIF_SYSCALL_EMU)) + == _TIF_SINGLESTEP); + if (step || cached_flags & _TIF_SYSCALL_TRACE) + tracehook_report_syscall_exit(regs, step); +} + +/* + * Called with IRQs on and fully valid regs. Returns with IRQs off in a + * state such that we can immediately switch to user mode. + */ +__visible inline void syscall_return_slowpath(struct pt_regs *regs) +{ + struct thread_info *ti = pt_regs_to_thread_info(regs); + u32 cached_flags = READ_ONCE(ti->flags); + + CT_WARN_ON(ct_state() != CONTEXT_KERNEL); + + if (IS_ENABLED(CONFIG_PROVE_LOCKING) && + WARN(irqs_disabled(), "syscall %ld left IRQs disabled", regs->orig_ax)) + local_irq_enable(); + + /* + * First do one-time work. If these work items are enabled, we + * want to run them exactly once per syscall exit with IRQs on. + */ + if (unlikely(cached_flags & SYSCALL_EXIT_WORK_FLAGS)) + syscall_slow_exit_work(regs, cached_flags); + +#ifdef CONFIG_COMPAT + /* + * Compat syscalls set TS_COMPAT. Make sure we clear it before + * returning to user mode. + */ + ti->status &= ~TS_COMPAT; +#endif + + local_irq_disable(); + prepare_exit_to_usermode(regs); +} + +#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) +/* + * Does a 32-bit syscall. Called with IRQs on and does all entry and + * exit work and returns with IRQs off. This function is extremely hot + * in workloads that use it, and it's usually called from + * do_fast_syscall_32, so forcibly inline it to improve performance. + */ +#ifdef CONFIG_X86_32 +/* 32-bit kernels use a trap gate for INT80, and the asm code calls here. */ +__visible +#else +/* 64-bit kernels use do_syscall_32_irqs_off() instead. */ +static +#endif +__always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) +{ + struct thread_info *ti = pt_regs_to_thread_info(regs); + unsigned int nr = (unsigned int)regs->orig_ax; + +#ifdef CONFIG_IA32_EMULATION + ti->status |= TS_COMPAT; +#endif + + if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) { + /* + * Subtlety here: if ptrace pokes something larger than + * 2^32-1 into orig_ax, this truncates it. This may or + * may not be necessary, but it matches the old asm + * behavior. + */ + nr = syscall_trace_enter(regs); + } + + if (likely(nr < IA32_NR_syscalls)) { + /* + * It's possible that a 32-bit syscall implementation + * takes a 64-bit parameter but nonetheless assumes that + * the high bits are zero. Make sure we zero-extend all + * of the args. + */ + regs->ax = ia32_sys_call_table[nr]( + (unsigned int)regs->bx, (unsigned int)regs->cx, + (unsigned int)regs->dx, (unsigned int)regs->si, + (unsigned int)regs->di, (unsigned int)regs->bp); + } + + syscall_return_slowpath(regs); +} + +#ifdef CONFIG_X86_64 +/* Handles INT80 on 64-bit kernels */ +__visible void do_syscall_32_irqs_off(struct pt_regs *regs) +{ + local_irq_enable(); + do_syscall_32_irqs_on(regs); +} +#endif + +/* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */ +__visible long do_fast_syscall_32(struct pt_regs *regs) +{ + /* + * Called using the internal vDSO SYSENTER/SYSCALL32 calling + * convention. Adjust regs so it looks like we entered using int80. + */ + + unsigned long landing_pad = (unsigned long)current->mm->context.vdso + + vdso_image_32.sym_int80_landing_pad; + + /* + * SYSENTER loses EIP, and even SYSCALL32 needs us to skip forward + * so that 'regs->ip -= 2' lands back on an int $0x80 instruction. + * Fix it up. + */ + regs->ip = landing_pad; + + /* + * Fetch EBP from where the vDSO stashed it. + * + * WARNING: We are in CONTEXT_USER and RCU isn't paying attention! + */ + local_irq_enable(); + if ( +#ifdef CONFIG_X86_64 + /* + * Micro-optimization: the pointer we're following is explicitly + * 32 bits, so it can't be out of range. + */ + __get_user(*(u32 *)®s->bp, + (u32 __user __force *)(unsigned long)(u32)regs->sp) +#else + get_user(*(u32 *)®s->bp, + (u32 __user __force *)(unsigned long)(u32)regs->sp) +#endif + ) { + + /* User code screwed up. */ + local_irq_disable(); + regs->ax = -EFAULT; +#ifdef CONFIG_CONTEXT_TRACKING + enter_from_user_mode(); +#endif + prepare_exit_to_usermode(regs); + return 0; /* Keep it simple: use IRET. */ + } + + /* Now this is just like a normal syscall. */ + do_syscall_32_irqs_on(regs); + +#ifdef CONFIG_X86_64 + /* + * Opportunistic SYSRETL: if possible, try to return using SYSRETL. + * SYSRETL is available on all 64-bit CPUs, so we don't need to + * bother with SYSEXIT. + * + * Unlike 64-bit opportunistic SYSRET, we can't check that CX == IP, + * because the ECX fixup above will ensure that this is essentially + * never the case. + */ + return regs->cs == __USER32_CS && regs->ss == __USER_DS && + regs->ip == landing_pad && + (regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF)) == 0; +#else + /* + * Opportunistic SYSEXIT: if possible, try to return using SYSEXIT. + * + * Unlike 64-bit opportunistic SYSRET, we can't check that CX == IP, + * because the ECX fixup above will ensure that this is essentially + * never the case. + * + * We don't allow syscalls at all from VM86 mode, but we still + * need to check VM, because we might be returning from sys_vm86. + */ + return static_cpu_has(X86_FEATURE_SEP) && + regs->cs == __USER_CS && regs->ss == __USER_DS && + regs->ip == landing_pad && + (regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)) == 0; +#endif +} +#endif diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 21dc60a60b5f..77d8c5112900 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -3,7 +3,7 @@ * * entry_32.S contains the system-call and low-level fault and trap handling routines. * - * Stack layout in 'syscall_exit': + * Stack layout while running C code: * 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(), @@ -45,16 +45,6 @@ #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" /* @@ -163,13 +153,13 @@ #endif /* CONFIG_X86_32_LAZY_GS */ -.macro SAVE_ALL +.macro SAVE_ALL pt_regs_ax=%eax cld PUSH_GS pushl %fs pushl %es pushl %ds - pushl %eax + pushl \pt_regs_ax pushl %ebp pushl %edi pushl %esi @@ -221,7 +211,11 @@ ENTRY(ret_from_fork) popl %eax pushl $0x0202 # Reset kernel eflags popfl - jmp syscall_exit + + /* When we fork, we trace the syscall return in the child, too. */ + movl %esp, %eax + call syscall_return_slowpath + jmp restore_all END(ret_from_fork) ENTRY(ret_from_kernel_thread) @@ -234,7 +228,15 @@ ENTRY(ret_from_kernel_thread) movl PT_EBP(%esp), %eax call *PT_EBX(%esp) movl $0, PT_EAX(%esp) - jmp syscall_exit + + /* + * Kernel threads return to userspace as if returning from a syscall. + * We should check whether anything actually uses this path and, if so, + * consider switching it over to ret_from_fork. + */ + movl %esp, %eax + call syscall_return_slowpath + jmp restore_all ENDPROC(ret_from_kernel_thread) /* @@ -265,15 +267,10 @@ ret_from_intr: 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 + DISABLE_INTERRUPTS(CLBR_ANY) 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 + movl %esp, %eax + call prepare_exit_to_usermode jmp restore_all END(ret_from_exception) @@ -290,111 +287,50 @@ 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: + pushl $__USER_DS /* pt_regs->ss */ + pushl %ebp /* pt_regs->sp (stashed in bp) */ + pushfl /* pt_regs->flags (except IF = 0) */ + orl $X86_EFLAGS_IF, (%esp) /* Fix IF */ + pushl $__USER_CS /* pt_regs->cs */ + pushl $0 /* pt_regs->ip = 0 (placeholder) */ + pushl %eax /* pt_regs->orig_ax */ + SAVE_ALL pt_regs_ax=$-ENOSYS /* save rest */ + /* - * 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. + * User mode is traced as though IRQs are on, and SYSENTER + * turned them off. */ - 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 + + movl %esp, %eax + call do_fast_syscall_32 + /* XEN PV guests always use IRET path */ + ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ + "jmp .Lsyscall_32_done", X86_FEATURE_XENPV + +/* Opportunistic SYSEXIT */ + TRACE_IRQS_ON /* User mode traces as IRQs on. */ + movl PT_EIP(%esp), %edx /* pt_regs->ip */ + movl PT_OLDESP(%esp), %ecx /* pt_regs->sp */ 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 + popl %ebx /* pt_regs->bx */ + addl $2*4, %esp /* skip pt_regs->cx and pt_regs->dx */ + popl %esi /* pt_regs->si */ + popl %edi /* pt_regs->di */ + popl %ebp /* pt_regs->bp */ + popl %eax /* pt_regs->ax */ + + /* + * Return back to the vDSO, which will pop ecx and edx. + * Don't bother with DS and ES (they already contain __USER_DS). + */ + sti + sysexit .pushsection .fixup, "ax" 2: movl $0, PT_FS(%esp) @@ -407,27 +343,18 @@ 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 $_TIF_ALLWORK_MASK, %ecx # current->work - jnz syscall_exit_work + pushl %eax /* pt_regs->orig_ax */ + SAVE_ALL pt_regs_ax=$-ENOSYS /* save rest */ + + /* + * User mode is traced as though IRQs are on. Unlike the 64-bit + * case, INT80 is a trap gate on 32-bit kernels, so interrupts + * are already on (unless user code is messing around with iopl). + */ + + movl %esp, %eax + call do_syscall_32_irqs_on +.Lsyscall_32_done: restore_all: TRACE_IRQS_IRET @@ -504,99 +431,6 @@ ldt_ss: #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 @@ -719,11 +553,6 @@ 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) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 8cb3e438f21e..9d34d3cfceb6 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -33,7 +33,6 @@ #include <asm/paravirt.h> #include <asm/percpu.h> #include <asm/asm.h> -#include <asm/context_tracking.h> #include <asm/smap.h> #include <asm/pgtable_types.h> #include <linux/err.h> @@ -229,6 +228,11 @@ entry_SYSCALL_64_fastpath: */ USERGS_SYSRET64 +GLOBAL(int_ret_from_sys_call_irqs_off) + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_NONE) + jmp int_ret_from_sys_call + /* Do syscall entry tracing */ tracesys: movq %rsp, %rdi @@ -272,69 +276,11 @@ tracesys_phase2: * Has correct iret frame. */ 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 - /* 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) - jmp syscall_return - - /* - * 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 - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) - pushq %rdi - SCHEDULE_USER - popq %rdi - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - jmp int_with_check - - /* handle signals and tracing -- both require a full pt_regs */ -int_very_careful: - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) SAVE_EXTRA_REGS - /* Check for syscall exit trace */ - 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 -int_restore_rest: + movq %rsp, %rdi + call syscall_return_slowpath /* returns with IRQs disabled */ RESTORE_EXTRA_REGS - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - jmp int_with_check - -syscall_return: - /* The IRETQ could re-enable interrupts: */ - DISABLE_INTERRUPTS(CLBR_ANY) - TRACE_IRQS_IRETQ + TRACE_IRQS_IRETQ /* we're about to change IF */ /* * Try to use SYSRET instead of IRET if we're returning to @@ -445,20 +391,16 @@ GLOBAL(stub_execveat) jmp return_from_execve END(stub_execveat) -#if defined(CONFIG_X86_X32_ABI) || defined(CONFIG_IA32_EMULATION) +#if defined(CONFIG_X86_X32_ABI) .align 8 GLOBAL(stub_x32_execve) -GLOBAL(stub32_execve) call compat_sys_execve jmp return_from_execve -END(stub32_execve) END(stub_x32_execve) .align 8 GLOBAL(stub_x32_execveat) -GLOBAL(stub32_execveat) call compat_sys_execveat jmp return_from_execve -END(stub32_execveat) END(stub_x32_execveat) #endif @@ -555,23 +497,31 @@ END(irq_entries_start) /* 0(%rsp): ~(interrupt number) */ .macro interrupt func cld + ALLOC_PT_GPREGS_ON_STACK + SAVE_C_REGS + SAVE_EXTRA_REGS + + testb $3, CS(%rsp) + jz 1f + + /* + * IRQ from user mode. Switch to kernel gsbase and inform context + * tracking that we're in kernel mode. + */ + SWAPGS + /* - * Since nothing in interrupt handling code touches r12...r15 members - * of "struct pt_regs", and since interrupts can nest, we can save - * four stack slots and simultaneously provide - * an unwind-friendly stack layout by saving "truncated" pt_regs - * exactly up to rbp slot, without these members. + * We need to tell lockdep that IRQs are off. We can't do this until + * we fix gsbase, and we should do it before enter_from_user_mode + * (which can take locks). Since TRACE_IRQS_OFF idempotent, + * the simplest way to handle it is to just call it twice if + * we enter from user mode. There's no reason to optimize this since + * TRACE_IRQS_OFF is a no-op if lockdep is off. */ - ALLOC_PT_GPREGS_ON_STACK -RBP - SAVE_C_REGS -RBP - /* this goes to 0(%rsp) for unwinder, not for saving the value: */ - SAVE_EXTRA_REGS_RBP -RBP + TRACE_IRQS_OFF - leaq -RBP(%rsp), %rdi /* arg1 for \func (pointer to pt_regs) */ + CALL_enter_from_user_mode - testb $3, CS-RBP(%rsp) - jz 1f - SWAPGS 1: /* * Save previous stack pointer, optionally switch to interrupt stack. @@ -580,14 +530,14 @@ 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 + movq %rsp, %rdi incl PER_CPU_VAR(irq_count) cmovzq PER_CPU_VAR(irq_stack_ptr), %rsp - pushq %rsi + pushq %rdi /* We entered an interrupt context - irqs are off: */ TRACE_IRQS_OFF - call \func + call \func /* rdi points to pt_regs */ .endm /* @@ -606,34 +556,18 @@ ret_from_intr: decl PER_CPU_VAR(irq_count) /* Restore saved previous stack */ - popq %rsi - /* return code expects complete pt_regs - adjust rsp accordingly: */ - leaq -RBP(%rsi), %rsp + popq %rsp testb $3, CS(%rsp) jz retint_kernel + /* Interrupt came from user space */ -retint_user: - GET_THREAD_INFO(%rcx) - - /* %rcx: thread info. Interrupts are off. */ -retint_with_reschedule: - movl $_TIF_WORK_MASK, %edi -retint_check: - LOCKDEP_SYS_EXIT_IRQ - movl TI_flags(%rcx), %edx - andl %edi, %edx - jnz retint_careful - -retint_swapgs: /* return to user-space */ - /* - * The iretq could re-enable interrupts: - */ - DISABLE_INTERRUPTS(CLBR_ANY) +GLOBAL(retint_user) + mov %rsp,%rdi + call prepare_exit_to_usermode TRACE_IRQS_IRETQ - SWAPGS - jmp restore_c_regs_and_iret + jmp restore_regs_and_iret /* Returning to kernel space */ retint_kernel: @@ -657,6 +591,8 @@ retint_kernel: * At this label, code paths which return to kernel and to user, * which come from interrupts/exception and from syscalls, merge. */ +GLOBAL(restore_regs_and_iret) + RESTORE_EXTRA_REGS restore_c_regs_and_iret: RESTORE_C_REGS REMOVE_PT_GPREGS_FROM_STACK 8 @@ -707,37 +643,6 @@ native_irq_return_ldt: popq %rax jmp native_irq_return_iret #endif - - /* edi: workmask, edx: work */ -retint_careful: - bt $TIF_NEED_RESCHED, %edx - jnc retint_signal - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) - pushq %rdi - SCHEDULE_USER - popq %rdi - GET_THREAD_INFO(%rcx) - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - jmp retint_check - -retint_signal: - 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 - RESTORE_EXTRA_REGS - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - GET_THREAD_INFO(%rcx) - jmp retint_with_reschedule - END(common_interrupt) /* @@ -1143,12 +1048,26 @@ ENTRY(error_entry) SAVE_EXTRA_REGS 8 xorl %ebx, %ebx testb $3, CS+8(%rsp) - jz error_kernelspace + jz .Lerror_kernelspace - /* We entered from user mode */ +.Lerror_entry_from_usermode_swapgs: + /* + * We entered from user mode or we're pretending to have entered + * from user mode due to an IRET fault. + */ SWAPGS -error_entry_done: +.Lerror_entry_from_usermode_after_swapgs: + /* + * We need to tell lockdep that IRQs are off. We can't do this until + * we fix gsbase, and we should do it before enter_from_user_mode + * (which can take locks). + */ + TRACE_IRQS_OFF + CALL_enter_from_user_mode + ret + +.Lerror_entry_done: TRACE_IRQS_OFF ret @@ -1158,31 +1077,30 @@ error_entry_done: * truncated RIP for IRET exceptions returning to compat mode. Check * for these here too. */ -error_kernelspace: +.Lerror_kernelspace: incl %ebx leaq native_irq_return_iret(%rip), %rcx cmpq %rcx, RIP+8(%rsp) - je error_bad_iret + je .Lerror_bad_iret movl %ecx, %eax /* zero extend */ cmpq %rax, RIP+8(%rsp) - je bstep_iret + je .Lbstep_iret cmpq $gs_change, RIP+8(%rsp) - jne error_entry_done + jne .Lerror_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 + jmp .Lerror_entry_from_usermode_swapgs -bstep_iret: +.Lbstep_iret: /* Fix truncated RIP */ movq %rcx, RIP+8(%rsp) /* fall through */ -error_bad_iret: +.Lerror_bad_iret: /* * We came from an IRET to user mode, so we have user gsbase. * Switch to kernel gsbase: @@ -1198,7 +1116,7 @@ error_bad_iret: call fixup_bad_iret mov %rax, %rsp decl %ebx - jmp error_entry_done + jmp .Lerror_entry_from_usermode_after_swapgs END(error_entry) @@ -1209,7 +1127,6 @@ END(error_entry) */ ENTRY(error_exit) movl %ebx, %eax - RESTORE_EXTRA_REGS DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF testl %eax, %eax @@ -1219,7 +1136,18 @@ END(error_exit) /* Runs on exception stack */ ENTRY(nmi) + /* + * Fix up the exception frame if we're on Xen. + * PARAVIRT_ADJUST_EXCEPTION_FRAME is guaranteed to push at most + * one value to the stack on native, so it may clobber the rdx + * scratch slot, but it won't clobber any of the important + * slots past it. + * + * Xen is a different story, because the Xen frame itself overlaps + * the "NMI executing" variable. + */ PARAVIRT_ADJUST_EXCEPTION_FRAME + /* * We allow breakpoints in NMIs. If a breakpoint occurs, then * the iretq it performs will take us out of NMI context. @@ -1270,9 +1198,12 @@ ENTRY(nmi) * we don't want to enable interrupts, because then we'll end * up in an awkward situation in which IRQs are on but NMIs * are off. + * + * We also must not push anything to the stack before switching + * stacks lest we corrupt the "NMI executing" variable. */ - SWAPGS + SWAPGS_UNSAFE_STACK cld movq %rsp, %rdx movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index a7e257d9cb90..ff1c6d61f332 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -16,25 +16,8 @@ #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. * @@ -58,218 +41,88 @@ ENDPROC(native_usergs_sysret32) * 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. - */ + /* Interrupts are off on entry. */ 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 + /* + * User tracing code (ptrace or signal handlers) might assume that + * the saved RAX contains a 32-bit number when we're invoking a 32-bit + * syscall. Just in case the high bits are nonzero, zero-extend + * the syscall number. (This could almost certainly be deleted + * with no ill effects.) + */ 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 %rbp /* pt_regs->sp (stashed in bp) */ + + /* + * Push flags. This is nasty. First, interrupts are currently + * off, but we need pt_regs->flags to have IF set. Second, even + * if TF was set when SYSENTER started, it's clear by now. We fix + * that later using TIF_SINGLESTEP. + */ + pushfq /* pt_regs->flags (except IF = 0) */ + orl $X86_EFLAGS_IF, (%rsp) /* Fix saved flags */ + ASM_CLAC /* Clear AC after saving FLAGS */ + pushq $__USER32_CS /* pt_regs->cs */ - pushq %r10 /* pt_regs->ip = thread_info->sysenter_return */ + xorq %r8,%r8 + pushq %r8 /* pt_regs->ip = 0 (placeholder) */ 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 = 0 */ + pushq %r8 /* pt_regs->r9 = 0 */ + pushq %r8 /* pt_regs->r10 = 0 */ + pushq %r8 /* pt_regs->r11 = 0 */ + pushq %rbx /* pt_regs->rbx */ + pushq %rbp /* pt_regs->rbp (will be overwritten) */ + pushq %r8 /* pt_regs->r12 = 0 */ + pushq %r8 /* pt_regs->r13 = 0 */ + pushq %r8 /* pt_regs->r14 = 0 */ + pushq %r8 /* pt_regs->r15 = 0 */ 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 needs to happen before enabling interrupts so that + * we don't get preempted with NT set. * - * This code path is still called 'sysexit' because it pairs - * with 'sysenter' and it uses the SYSENTER calling convention. - */ - andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) - movl RIP(%rsp), %ecx /* User %eip */ - movq RAX(%rsp), %rax - RESTORE_RSI_RDI - xorl %edx, %edx /* Do not leak kernel information */ - xorq %r8, %r8 - xorq %r9, %r9 - xorq %r10, %r10 - movl EFLAGS(%rsp), %r11d /* User eflags */ - TRACE_IRQS_ON - - /* - * SYSRETL works even on Intel CPUs. Use it in preference to SYSEXIT, - * since it avoids a dicey window with interrupts enabled. + * NB.: .Lsysenter_fix_flags is a label with the code under it moved + * out-of-line as an optimization: NT is unlikely to be set in the + * majority of the cases and instead of polluting the I$ unnecessarily, + * we're keeping that code behind a branch which will predict as + * not-taken and therefore its instructions won't be fetched. */ - 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 + testl $X86_EFLAGS_NT, EFLAGS(%rsp) + jnz .Lsysenter_fix_flags +.Lsysenter_flags_fixed: /* - * 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: + * User mode is traced as though IRQs are on, and SYSENTER + * turned them off. */ - 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 + movq %rsp, %rdi + call do_fast_syscall_32 + /* XEN PV guests always use IRET path */ + ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ + "jmp .Lsyscall_32_done", X86_FEATURE_XENPV + jmp sysret32_from_system_call -sysenter_fix_flags: - pushq $(X86_EFLAGS_IF|X86_EFLAGS_FIXED) +.Lsysenter_fix_flags: + pushq $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 + jmp .Lsysenter_flags_fixed ENDPROC(entry_SYSENTER_compat) /* @@ -297,21 +150,14 @@ ENDPROC(entry_SYSENTER_compat) * 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. - */ + /* Interrupts are off on entry. */ SWAPGS_UNSAFE_STACK + + /* Stash user ESP and switch to the kernel 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 @@ -326,120 +172,69 @@ ENTRY(entry_SYSCALL_compat) pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ pushq %rdx /* pt_regs->dx */ - pushq %rbp /* pt_regs->cx */ - movl %ebp, %ecx + pushq %rbp /* pt_regs->cx (stashed in bp) */ pushq $-ENOSYS /* pt_regs->ax */ - sub $(10*8), %rsp /* pt_regs->r8-11, bp, bx, r12-15 not saved */ + xorq %r8,%r8 + pushq %r8 /* pt_regs->r8 = 0 */ + pushq %r8 /* pt_regs->r9 = 0 */ + pushq %r8 /* pt_regs->r10 = 0 */ + pushq %r8 /* pt_regs->r11 = 0 */ + pushq %rbx /* pt_regs->rbx */ + pushq %rbp /* pt_regs->rbp (will be overwritten) */ + pushq %r8 /* pt_regs->r12 = 0 */ + pushq %r8 /* pt_regs->r13 = 0 */ + pushq %r8 /* pt_regs->r14 = 0 */ + pushq %r8 /* pt_regs->r15 = 0 */ /* - * No need to do an access_ok check here because r8 has been - * 32-bit zero extended: + * User mode is traced as though IRQs are on, and SYSENTER + * turned them off. */ - 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). + movq %rsp, %rdi + call do_fast_syscall_32 + /* XEN PV guests always use IRET path */ + ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ + "jmp .Lsyscall_32_done", X86_FEATURE_XENPV + + /* Opportunistic SYSRET */ +sysret32_from_system_call: + TRACE_IRQS_ON /* User mode traces as IRQs on. */ + movq RBX(%rsp), %rbx /* pt_regs->rbx */ + movq RBP(%rsp), %rbp /* pt_regs->rbp */ + movq EFLAGS(%rsp), %r11 /* pt_regs->flags (in r11) */ + movq RIP(%rsp), %rcx /* pt_regs->ip (in rcx) */ + addq $RAX, %rsp /* Skip r8-r15 */ + popq %rax /* pt_regs->rax */ + popq %rdx /* Skip pt_regs->cx */ + popq %rdx /* pt_regs->dx */ + popq %rsi /* pt_regs->si */ + popq %rdi /* pt_regs->di */ + + /* + * USERGS_SYSRET32 does: + * GSBASE = user's GS base + * EIP = ECX + * RFLAGS = R11 + * CS = __USER32_CS + * SS = __USER_DS + * + * ECX will not match pt_regs->cx, but we're returning to a vDSO + * trampoline that will fix up RCX, so this is okay. * - * 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 + * R12-R15 are callee-saved, so they contain whatever was in them + * when the system call started, which is already known to user + * code. We zero R8-R10 to avoid info leaks. + */ + xorq %r8, %r8 + xorq %r9, %r9 + xorq %r10, %r10 + movq RSP-ORIG_RAX(%rsp), %rsp + swapgs + sysretl 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. * @@ -464,14 +259,17 @@ ia32_ret_from_sys_call: 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 */ + /* + * User tracing code (ptrace or signal handlers) might assume that + * the saved RAX contains a 32-bit number when we're invoking a 32-bit + * syscall. Just in case the high bits are nonzero, zero-extend + * the syscall number. (This could almost certainly be deleted + * with no ill effects.) + */ movl %eax, %eax /* Construct struct pt_regs on stack (iret frame is already on stack) */ @@ -481,67 +279,37 @@ ENTRY(entry_INT80_compat) 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 */ + xorq %r8,%r8 + pushq %r8 /* pt_regs->r8 = 0 */ + pushq %r8 /* pt_regs->r9 = 0 */ + pushq %r8 /* pt_regs->r10 = 0 */ + pushq %r8 /* pt_regs->r11 = 0 */ + pushq %rbx /* pt_regs->rbx */ + pushq %rbp /* pt_regs->rbp */ + pushq %r12 /* pt_regs->r12 */ + pushq %r13 /* pt_regs->r13 */ + pushq %r14 /* pt_regs->r14 */ + pushq %r15 /* pt_regs->r15 */ 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. + * User mode is traced as though IRQs are on, and the interrupt + * gate turned them off. */ - 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) + TRACE_IRQS_OFF - .macro PTREGSCALL label, func - ALIGN -GLOBAL(\label) - leaq \func(%rip), %rax - jmp ia32_ptregs_common - .endm + movq %rsp, %rdi + call do_syscall_32_irqs_off +.Lsyscall_32_done: - PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn - PTREGSCALL stub32_sigreturn, sys32_sigreturn - PTREGSCALL stub32_fork, sys_fork - PTREGSCALL stub32_vfork, sys_vfork + /* Go back to user mode. */ + TRACE_IRQS_ON + SWAPGS + jmp restore_regs_and_iret +END(entry_INT80_compat) 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). @@ -550,12 +318,4 @@ GLOBAL(stub32_clone) * 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) + jmp sys_clone diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c index 8ea34f94e973..9a6649857106 100644 --- a/arch/x86/entry/syscall_32.c +++ b/arch/x86/entry/syscall_32.c @@ -4,24 +4,21 @@ #include <linux/sys.h> #include <linux/cache.h> #include <asm/asm-offsets.h> +#include <asm/syscall.h> #ifdef CONFIG_IA32_EMULATION #define SYM(sym, compat) compat #else #define SYM(sym, compat) sym -#define ia32_sys_call_table sys_call_table -#define __NR_syscall_compat_max __NR_syscall_max #endif -#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void SYM(sym, compat)(void) ; +#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage long SYM(sym, compat)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; #include <asm/syscalls_32.h> #undef __SYSCALL_I386 #define __SYSCALL_I386(nr, sym, compat) [nr] = SYM(sym, compat), -typedef asmlinkage void (*sys_call_ptr_t)(void); - -extern asmlinkage void sys_ni_syscall(void); +extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); __visible const sys_call_ptr_t ia32_sys_call_table[__NR_syscall_compat_max+1] = { /* diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index 4ac730b37f0b..41283d22be7a 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -14,13 +14,13 @@ # define __SYSCALL_X32(nr, sym, compat) /* nothing */ #endif -#define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ; +#define __SYSCALL_64(nr, sym, compat) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; #include <asm/syscalls_64.h> #undef __SYSCALL_64 #define __SYSCALL_64(nr, sym, compat) [nr] = sym, -extern void sys_ni_syscall(void); +extern long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { /* diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index ef8187f9d28d..cb713df81180 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -8,7 +8,7 @@ # 0 i386 restart_syscall sys_restart_syscall 1 i386 exit sys_exit -2 i386 fork sys_fork stub32_fork +2 i386 fork sys_fork sys_fork 3 i386 read sys_read 4 i386 write sys_write 5 i386 open sys_open compat_sys_open @@ -17,7 +17,7 @@ 8 i386 creat sys_creat 9 i386 link sys_link 10 i386 unlink sys_unlink -11 i386 execve sys_execve stub32_execve +11 i386 execve sys_execve compat_sys_execve 12 i386 chdir sys_chdir 13 i386 time sys_time compat_sys_time 14 i386 mknod sys_mknod @@ -125,7 +125,7 @@ 116 i386 sysinfo sys_sysinfo compat_sys_sysinfo 117 i386 ipc sys_ipc compat_sys_ipc 118 i386 fsync sys_fsync -119 i386 sigreturn sys_sigreturn stub32_sigreturn +119 i386 sigreturn sys_sigreturn sys32_sigreturn 120 i386 clone sys_clone stub32_clone 121 i386 setdomainname sys_setdomainname 122 i386 uname sys_newuname @@ -179,7 +179,7 @@ 170 i386 setresgid sys_setresgid16 171 i386 getresgid sys_getresgid16 172 i386 prctl sys_prctl -173 i386 rt_sigreturn sys_rt_sigreturn stub32_rt_sigreturn +173 i386 rt_sigreturn sys_rt_sigreturn sys32_rt_sigreturn 174 i386 rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction 175 i386 rt_sigprocmask sys_rt_sigprocmask 176 i386 rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending @@ -196,7 +196,7 @@ 187 i386 sendfile sys_sendfile compat_sys_sendfile 188 i386 getpmsg 189 i386 putpmsg -190 i386 vfork sys_vfork stub32_vfork +190 i386 vfork sys_vfork sys_vfork 191 i386 ugetrlimit sys_getrlimit compat_sys_getrlimit 192 i386 mmap2 sys_mmap_pgoff 193 i386 truncate64 sys_truncate64 sys32_truncate64 @@ -364,4 +364,23 @@ 355 i386 getrandom sys_getrandom 356 i386 memfd_create sys_memfd_create 357 i386 bpf sys_bpf -358 i386 execveat sys_execveat stub32_execveat +358 i386 execveat sys_execveat compat_sys_execveat +359 i386 socket sys_socket +360 i386 socketpair sys_socketpair +361 i386 bind sys_bind +362 i386 connect sys_connect +363 i386 listen sys_listen +364 i386 accept4 sys_accept4 +365 i386 getsockopt sys_getsockopt compat_sys_getsockopt +366 i386 setsockopt sys_setsockopt compat_sys_setsockopt +367 i386 getsockname sys_getsockname +368 i386 getpeername sys_getpeername +369 i386 sendto sys_sendto +370 i386 sendmsg sys_sendmsg compat_sys_sendmsg +371 i386 recvfrom sys_recvfrom compat_sys_recvfrom +372 i386 recvmsg sys_recvmsg compat_sys_recvmsg +373 i386 shutdown sys_shutdown +374 i386 userfaultfd sys_userfaultfd +375 i386 membarrier sys_membarrier +376 i386 mlock2 sys_mlock2 +377 i386 copy_file_range sys_copy_file_range diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 9ef32d5f1b19..dc1040a50bdc 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -329,6 +329,10 @@ 320 common kexec_file_load sys_kexec_file_load 321 common bpf sys_bpf 322 64 execveat stub_execveat +323 common userfaultfd sys_userfaultfd +324 common membarrier sys_membarrier +325 common mlock2 sys_mlock2 +326 common copy_file_range sys_copy_file_range # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index e97032069f88..265c0ed68118 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -8,7 +8,7 @@ KASAN_SANITIZE := n VDSO64-$(CONFIG_X86_64) := y VDSOX32-$(CONFIG_X86_X32_ABI) := y VDSO32-$(CONFIG_X86_32) := y -VDSO32-$(CONFIG_COMPAT) := y +VDSO32-$(CONFIG_IA32_EMULATION) := y # files to link into the vdso vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o @@ -19,9 +19,7 @@ obj-y += vma.o # vDSO images to build vdso_img-$(VDSO64-y) += 64 vdso_img-$(VDSOX32-y) += x32 -vdso_img-$(VDSO32-y) += 32-int80 -vdso_img-$(CONFIG_COMPAT) += 32-syscall -vdso_img-$(VDSO32-y) += 32-sysenter +vdso_img-$(VDSO32-y) += 32 obj-$(VDSO32-y) += vdso32-setup.o @@ -69,7 +67,7 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \ $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \ -fno-omit-frame-pointer -foptimize-sibling-calls \ - -DDISABLE_BRANCH_PROFILING + -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO $(vobjs): KBUILD_CFLAGS += $(CFL) @@ -122,15 +120,6 @@ $(obj)/%.so: $(obj)/%.so.dbg $(obj)/vdsox32.so.dbg: $(src)/vdsox32.lds $(vobjx32s) FORCE $(call if_changed,vdso) -# -# Build multiple 32-bit vDSO images to choose from at boot time. -# -vdso32.so-$(VDSO32-y) += int80 -vdso32.so-$(CONFIG_COMPAT) += syscall -vdso32.so-$(VDSO32-y) += sysenter - -vdso32-images = $(vdso32.so-y:%=vdso32-%.so) - CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds) VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1 @@ -139,14 +128,12 @@ VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1 override obj-dirs = $(dir $(obj)) $(obj)/vdso32/ targets += vdso32/vdso32.lds -targets += vdso32/note.o vdso32/vclock_gettime.o $(vdso32.so-y:%=vdso32/%.o) +targets += vdso32/note.o vdso32/vclock_gettime.o vdso32/system_call.o targets += vdso32/vclock_gettime.o -$(obj)/vdso32.o: $(vdso32-images:%=$(obj)/%) - -KBUILD_AFLAGS_32 := $(filter-out -m64,$(KBUILD_AFLAGS)) -$(vdso32-images:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_32) -$(vdso32-images:%=$(obj)/%.dbg): asflags-$(CONFIG_X86_64) += -m32 +KBUILD_AFLAGS_32 := $(filter-out -m64,$(KBUILD_AFLAGS)) -DBUILD_VDSO +$(obj)/vdso32.so.dbg: KBUILD_AFLAGS = $(KBUILD_AFLAGS_32) +$(obj)/vdso32.so.dbg: asflags-$(CONFIG_X86_64) += -m32 KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_32 := $(filter-out -mcmodel=kernel,$(KBUILD_CFLAGS_32)) @@ -157,13 +144,13 @@ KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector) KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls) KBUILD_CFLAGS_32 += -fno-omit-frame-pointer KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING -$(vdso32-images:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32) +$(obj)/vdso32.so.dbg: KBUILD_CFLAGS = $(KBUILD_CFLAGS_32) -$(vdso32-images:%=$(obj)/%.dbg): $(obj)/vdso32-%.so.dbg: FORCE \ - $(obj)/vdso32/vdso32.lds \ - $(obj)/vdso32/vclock_gettime.o \ - $(obj)/vdso32/note.o \ - $(obj)/vdso32/%.o +$(obj)/vdso32.so.dbg: FORCE \ + $(obj)/vdso32/vdso32.lds \ + $(obj)/vdso32/vclock_gettime.o \ + $(obj)/vdso32/note.o \ + $(obj)/vdso32/system_call.o $(call if_changed,vdso) # @@ -175,7 +162,7 @@ quiet_cmd_vdso = VDSO $@ -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \ sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' -VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) \ +VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=both) \ $(call cc-ldoption, -Wl$(comma)--build-id) -Wl,-Bsymbolic $(LTO_CFLAGS) GCOV_PROFILE := n @@ -206,4 +193,4 @@ $(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso FORCE PHONY += vdso_install $(vdso_img_insttargets) vdso_install: $(vdso_img_insttargets) FORCE -clean-files := vdso32-syscall* vdso32-sysenter* vdso32-int80* vdso64* vdso-image-*.c vdsox32.so* +clean-files := vdso32.so vdso32.so.dbg vdso64* vdso-image-*.c vdsox32.so* diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index 9793322751e0..1a50e09c945b 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -17,8 +17,10 @@ #include <asm/vvar.h> #include <asm/unistd.h> #include <asm/msr.h> +#include <asm/pvclock.h> #include <linux/math64.h> #include <linux/time.h> +#include <linux/kernel.h> #define gtod (&VVAR(vsyscall_gtod_data)) @@ -36,12 +38,12 @@ static notrace cycle_t vread_hpet(void) } #endif -#ifndef BUILD_VDSO32 +#ifdef CONFIG_PARAVIRT_CLOCK +extern u8 pvclock_page + __attribute__((visibility("hidden"))); +#endif -#include <linux/kernel.h> -#include <asm/vsyscall.h> -#include <asm/fixmap.h> -#include <asm/pvclock.h> +#ifndef BUILD_VDSO32 notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { @@ -60,75 +62,6 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) return ret; } -#ifdef CONFIG_PARAVIRT_CLOCK - -static notrace const struct pvclock_vsyscall_time_info *get_pvti(int cpu) -{ - const struct pvclock_vsyscall_time_info *pvti_base; - int idx = cpu / (PAGE_SIZE/PVTI_SIZE); - int offset = cpu % (PAGE_SIZE/PVTI_SIZE); - - BUG_ON(PVCLOCK_FIXMAP_BEGIN + idx > PVCLOCK_FIXMAP_END); - - pvti_base = (struct pvclock_vsyscall_time_info *) - __fix_to_virt(PVCLOCK_FIXMAP_BEGIN+idx); - - return &pvti_base[offset]; -} - -static notrace cycle_t vread_pvclock(int *mode) -{ - const struct pvclock_vsyscall_time_info *pvti; - cycle_t ret; - u64 last; - u32 version; - u8 flags; - unsigned cpu, cpu1; - - - /* - * Note: hypervisor must guarantee that: - * 1. cpu ID number maps 1:1 to per-CPU pvclock time info. - * 2. that per-CPU pvclock time info is updated if the - * underlying CPU changes. - * 3. that version is increased whenever underlying CPU - * changes. - * - */ - do { - cpu = __getcpu() & VGETCPU_CPU_MASK; - /* TODO: We can put vcpu id into higher bits of pvti.version. - * This will save a couple of cycles by getting rid of - * __getcpu() calls (Gleb). - */ - - pvti = get_pvti(cpu); - - version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags); - - /* - * Test we're still on the cpu as well as the version. - * We could have been migrated just after the first - * vgetcpu but before fetching the version, so we - * wouldn't notice a version change. - */ - cpu1 = __getcpu() & VGETCPU_CPU_MASK; - } while (unlikely(cpu != cpu1 || - (pvti->pvti.version & 1) || - pvti->pvti.version != version)); - - if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT))) - *mode = VCLOCK_NONE; - - /* refer to tsc.c read_tsc() comment for rationale */ - last = gtod->cycle_last; - - if (likely(ret >= last)) - return ret; - - return last; -} -#endif #else @@ -162,37 +95,87 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) return ret; } -#ifdef CONFIG_PARAVIRT_CLOCK +#endif -static notrace cycle_t vread_pvclock(int *mode) +#ifdef CONFIG_PARAVIRT_CLOCK +static notrace const struct pvclock_vsyscall_time_info *get_pvti0(void) { - *mode = VCLOCK_NONE; - return 0; + return (const struct pvclock_vsyscall_time_info *)&pvclock_page; } -#endif - -#endif -notrace static cycle_t vread_tsc(void) +static notrace cycle_t vread_pvclock(int *mode) { + const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti; cycle_t ret; - u64 last; + u64 tsc, pvti_tsc; + u64 last, delta, pvti_system_time; + u32 version, pvti_tsc_to_system_mul, pvti_tsc_shift; /* - * Empirically, a fence (of type that depends on the CPU) - * before rdtsc is enough to ensure that rdtsc is ordered - * with respect to loads. The various CPU manuals are unclear - * as to whether rdtsc can be reordered with later loads, - * but no one has ever seen it happen. + * Note: The kernel and hypervisor must guarantee that cpu ID + * number maps 1:1 to per-CPU pvclock time info. + * + * Because the hypervisor is entirely unaware of guest userspace + * preemption, it cannot guarantee that per-CPU pvclock time + * info is updated if the underlying CPU changes or that that + * version is increased whenever underlying CPU changes. + * + * On KVM, we are guaranteed that pvti updates for any vCPU are + * atomic as seen by *all* vCPUs. This is an even stronger + * guarantee than we get with a normal seqlock. + * + * On Xen, we don't appear to have that guarantee, but Xen still + * supplies a valid seqlock using the version field. + * + * We only do pvclock vdso timing at all if + * PVCLOCK_TSC_STABLE_BIT is set, and we interpret that bit to + * mean that all vCPUs have matching pvti and that the TSC is + * synced, so we can just look at vCPU 0's pvti. */ - rdtsc_barrier(); - ret = (cycle_t)__native_read_tsc(); + do { + version = pvti->version; + + smp_rmb(); + + if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT))) { + *mode = VCLOCK_NONE; + return 0; + } + + tsc = rdtsc_ordered(); + pvti_tsc_to_system_mul = pvti->tsc_to_system_mul; + pvti_tsc_shift = pvti->tsc_shift; + pvti_system_time = pvti->system_time; + pvti_tsc = pvti->tsc_timestamp; + + /* Make sure that the version double-check is last. */ + smp_rmb(); + } while (unlikely((version & 1) || version != pvti->version)); + + delta = tsc - pvti_tsc; + ret = pvti_system_time + + pvclock_scale_delta(delta, pvti_tsc_to_system_mul, + pvti_tsc_shift); + + /* refer to vread_tsc() comment for rationale */ last = gtod->cycle_last; if (likely(ret >= last)) return ret; + return last; +} +#endif + +notrace static cycle_t vread_tsc(void) +{ + cycle_t ret = (cycle_t)rdtsc_ordered(); + u64 last = gtod->cycle_last; + + if (likely(ret >= last)) + return ret; + /* * GCC likes to generate cmov here, but this branch is extremely * predictable (it's just a funciton of time and the likely is diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S index de2c921025f5..4158acc17df0 100644 --- a/arch/x86/entry/vdso/vdso-layout.lds.S +++ b/arch/x86/entry/vdso/vdso-layout.lds.S @@ -25,7 +25,7 @@ SECTIONS * segment. */ - vvar_start = . - 2 * PAGE_SIZE; + vvar_start = . - 3 * PAGE_SIZE; vvar_page = vvar_start; /* Place all vvars at the offsets in asm/vvar.h. */ @@ -36,6 +36,7 @@ SECTIONS #undef EMIT_VVAR hpet_page = vvar_start + PAGE_SIZE; + pvclock_page = vvar_start + 2 * PAGE_SIZE; . = SIZEOF_HEADERS; diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c index 8627db24a7f6..491020b2826d 100644 --- a/arch/x86/entry/vdso/vdso2c.c +++ b/arch/x86/entry/vdso/vdso2c.c @@ -73,6 +73,7 @@ enum { sym_vvar_start, sym_vvar_page, sym_hpet_page, + sym_pvclock_page, sym_VDSO_FAKE_SECTION_TABLE_START, sym_VDSO_FAKE_SECTION_TABLE_END, }; @@ -80,6 +81,7 @@ enum { const int special_pages[] = { sym_vvar_page, sym_hpet_page, + sym_pvclock_page, }; struct vdso_sym { @@ -91,6 +93,7 @@ struct vdso_sym required_syms[] = { [sym_vvar_start] = {"vvar_start", true}, [sym_vvar_page] = {"vvar_page", true}, [sym_hpet_page] = {"hpet_page", true}, + [sym_pvclock_page] = {"pvclock_page", true}, [sym_VDSO_FAKE_SECTION_TABLE_START] = { "VDSO_FAKE_SECTION_TABLE_START", false }, @@ -98,10 +101,10 @@ struct vdso_sym required_syms[] = { "VDSO_FAKE_SECTION_TABLE_END", false }, {"VDSO32_NOTE_MASK", true}, - {"VDSO32_SYSENTER_RETURN", true}, {"__kernel_vsyscall", true}, {"__kernel_sigreturn", true}, {"__kernel_rt_sigreturn", true}, + {"int80_landing_pad", true}, }; __attribute__((format(printf, 1, 2))) __attribute__((noreturn)) diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c index e904c270573b..08a317a9ae4b 100644 --- a/arch/x86/entry/vdso/vdso32-setup.c +++ b/arch/x86/entry/vdso/vdso32-setup.c @@ -48,35 +48,9 @@ __setup("vdso32=", vdso32_setup); __setup_param("vdso=", vdso_setup, vdso32_setup, 0); #endif -#ifdef CONFIG_X86_64 - -#define vdso32_sysenter() (boot_cpu_has(X86_FEATURE_SYSENTER32)) -#define vdso32_syscall() (boot_cpu_has(X86_FEATURE_SYSCALL32)) - -#else /* CONFIG_X86_32 */ - -#define vdso32_sysenter() (boot_cpu_has(X86_FEATURE_SEP)) -#define vdso32_syscall() (0) - -#endif /* CONFIG_X86_64 */ - -#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT) -const struct vdso_image *selected_vdso32; -#endif - int __init sysenter_setup(void) { -#ifdef CONFIG_COMPAT - if (vdso32_syscall()) - selected_vdso32 = &vdso_image_32_syscall; - else -#endif - if (vdso32_sysenter()) - selected_vdso32 = &vdso_image_32_sysenter; - else - selected_vdso32 = &vdso_image_32_int80; - - init_vdso_image(selected_vdso32); + init_vdso_image(&vdso_image_32); return 0; } diff --git a/arch/x86/entry/vdso/vdso32/int80.S b/arch/x86/entry/vdso/vdso32/int80.S deleted file mode 100644 index b15b7c01aedb..000000000000 --- a/arch/x86/entry/vdso/vdso32/int80.S +++ /dev/null @@ -1,56 +0,0 @@ -/* - * Code for the vDSO. This version uses the old int $0x80 method. - * - * First get the common code for the sigreturn entry points. - * This must come first. - */ -#include "sigreturn.S" - - .text - .globl __kernel_vsyscall - .type __kernel_vsyscall,@function - ALIGN -__kernel_vsyscall: -.LSTART_vsyscall: - int $0x80 - ret -.LEND_vsyscall: - .size __kernel_vsyscall,.-.LSTART_vsyscall - .previous - - .section .eh_frame,"a",@progbits -.LSTARTFRAMEDLSI: - .long .LENDCIEDLSI-.LSTARTCIEDLSI -.LSTARTCIEDLSI: - .long 0 /* CIE ID */ - .byte 1 /* Version number */ - .string "zR" /* NUL-terminated augmentation string */ - .uleb128 1 /* Code alignment factor */ - .sleb128 -4 /* Data alignment factor */ - .byte 8 /* Return address register column */ - .uleb128 1 /* Augmentation value length */ - .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */ - .byte 0x0c /* DW_CFA_def_cfa */ - .uleb128 4 - .uleb128 4 - .byte 0x88 /* DW_CFA_offset, column 0x8 */ - .uleb128 1 - .align 4 -.LENDCIEDLSI: - .long .LENDFDEDLSI-.LSTARTFDEDLSI /* Length FDE */ -.LSTARTFDEDLSI: - .long .LSTARTFDEDLSI-.LSTARTFRAMEDLSI /* CIE pointer */ - .long .LSTART_vsyscall-. /* PC-relative start address */ - .long .LEND_vsyscall-.LSTART_vsyscall - .uleb128 0 - .align 4 -.LENDFDEDLSI: - .previous - - /* - * Pad out the segment to match the size of the sysenter.S version. - */ -VDSO32_vsyscall_eh_frame_size = 0x40 - .section .data,"aw",@progbits - .space VDSO32_vsyscall_eh_frame_size-(.LENDFDEDLSI-.LSTARTFRAMEDLSI), 0 - .previous diff --git a/arch/x86/entry/vdso/vdso32/syscall.S b/arch/x86/entry/vdso/vdso32/syscall.S deleted file mode 100644 index 6b286bb5251c..000000000000 --- a/arch/x86/entry/vdso/vdso32/syscall.S +++ /dev/null @@ -1,75 +0,0 @@ -/* - * Code for the vDSO. This version uses the syscall instruction. - * - * First get the common code for the sigreturn entry points. - * This must come first. - */ -#define SYSCALL_ENTER_KERNEL syscall -#include "sigreturn.S" - -#include <asm/segment.h> - - .text - .globl __kernel_vsyscall - .type __kernel_vsyscall,@function - ALIGN -__kernel_vsyscall: -.LSTART_vsyscall: - push %ebp -.Lpush_ebp: - movl %ecx, %ebp - syscall - movl %ebp, %ecx - popl %ebp -.Lpop_ebp: - ret -.LEND_vsyscall: - .size __kernel_vsyscall,.-.LSTART_vsyscall - - .section .eh_frame,"a",@progbits -.LSTARTFRAME: - .long .LENDCIE-.LSTARTCIE -.LSTARTCIE: - .long 0 /* CIE ID */ - .byte 1 /* Version number */ - .string "zR" /* NUL-terminated augmentation string */ - .uleb128 1 /* Code alignment factor */ - .sleb128 -4 /* Data alignment factor */ - .byte 8 /* Return address register column */ - .uleb128 1 /* Augmentation value length */ - .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */ - .byte 0x0c /* DW_CFA_def_cfa */ - .uleb128 4 - .uleb128 4 - .byte 0x88 /* DW_CFA_offset, column 0x8 */ - .uleb128 1 - .align 4 -.LENDCIE: - - .long .LENDFDE1-.LSTARTFDE1 /* Length FDE */ -.LSTARTFDE1: - .long .LSTARTFDE1-.LSTARTFRAME /* CIE pointer */ - .long .LSTART_vsyscall-. /* PC-relative start address */ - .long .LEND_vsyscall-.LSTART_vsyscall - .uleb128 0 /* Augmentation length */ - /* What follows are the instructions for the table generation. - We have to record all changes of the stack pointer. */ - .byte 0x40 + .Lpush_ebp-.LSTART_vsyscall /* DW_CFA_advance_loc */ - .byte 0x0e /* DW_CFA_def_cfa_offset */ - .uleb128 8 - .byte 0x85, 0x02 /* DW_CFA_offset %ebp -8 */ - .byte 0x40 + .Lpop_ebp-.Lpush_ebp /* DW_CFA_advance_loc */ - .byte 0xc5 /* DW_CFA_restore %ebp */ - .byte 0x0e /* DW_CFA_def_cfa_offset */ - .uleb128 4 - .align 4 -.LENDFDE1: - .previous - - /* - * Pad out the segment to match the size of the sysenter.S version. - */ -VDSO32_vsyscall_eh_frame_size = 0x40 - .section .data,"aw",@progbits - .space VDSO32_vsyscall_eh_frame_size-(.LENDFDE1-.LSTARTFRAME), 0 - .previous diff --git a/arch/x86/entry/vdso/vdso32/sysenter.S b/arch/x86/entry/vdso/vdso32/sysenter.S deleted file mode 100644 index e354bceee0e0..000000000000 --- a/arch/x86/entry/vdso/vdso32/sysenter.S +++ /dev/null @@ -1,116 +0,0 @@ -/* - * Code for the vDSO. This version uses the sysenter instruction. - * - * First get the common code for the sigreturn entry points. - * This must come first. - */ -#include "sigreturn.S" - -/* - * The caller puts arg2 in %ecx, which gets pushed. The kernel will use - * %ecx itself for arg2. The pushing is because the sysexit instruction - * (found in entry.S) requires that we clobber %ecx with the desired %esp. - * User code might expect that %ecx is unclobbered though, as it would be - * for returning via the iret instruction, so we must push and pop. - * - * The caller puts arg3 in %edx, which the sysexit instruction requires - * for %eip. Thus, exactly as for arg2, we must push and pop. - * - * Arg6 is different. The caller puts arg6 in %ebp. Since the sysenter - * instruction clobbers %esp, the user's %esp won't even survive entry - * into the kernel. We store %esp in %ebp. Code in entry.S must fetch - * arg6 from the stack. - * - * You can not use this vsyscall for the clone() syscall because the - * three words on the parent stack do not get copied to the child. - */ - .text - .globl __kernel_vsyscall - .type __kernel_vsyscall,@function - ALIGN -__kernel_vsyscall: -.LSTART_vsyscall: - push %ecx -.Lpush_ecx: - push %edx -.Lpush_edx: - push %ebp -.Lenter_kernel: - movl %esp,%ebp - sysenter - - /* 7: align return point with nop's to make disassembly easier */ - .space 7,0x90 - - /* 14: System call restart point is here! (SYSENTER_RETURN-2) */ - int $0x80 - /* 16: System call normal return point is here! */ -VDSO32_SYSENTER_RETURN: /* Symbol used by sysenter.c via vdso32-syms.h */ - pop %ebp -.Lpop_ebp: - pop %edx -.Lpop_edx: - pop %ecx -.Lpop_ecx: - ret -.LEND_vsyscall: - .size __kernel_vsyscall,.-.LSTART_vsyscall - .previous - - .section .eh_frame,"a",@progbits -.LSTARTFRAMEDLSI: - .long .LENDCIEDLSI-.LSTARTCIEDLSI -.LSTARTCIEDLSI: - .long 0 /* CIE ID */ - .byte 1 /* Version number */ - .string "zR" /* NUL-terminated augmentation string */ - .uleb128 1 /* Code alignment factor */ - .sleb128 -4 /* Data alignment factor */ - .byte 8 /* Return address register column */ - .uleb128 1 /* Augmentation value length */ - .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */ - .byte 0x0c /* DW_CFA_def_cfa */ - .uleb128 4 - .uleb128 4 - .byte 0x88 /* DW_CFA_offset, column 0x8 */ - .uleb128 1 - .align 4 -.LENDCIEDLSI: - .long .LENDFDEDLSI-.LSTARTFDEDLSI /* Length FDE */ -.LSTARTFDEDLSI: - .long .LSTARTFDEDLSI-.LSTARTFRAMEDLSI /* CIE pointer */ - .long .LSTART_vsyscall-. /* PC-relative start address */ - .long .LEND_vsyscall-.LSTART_vsyscall - .uleb128 0 - /* What follows are the instructions for the table generation. - We have to record all changes of the stack pointer. */ - .byte 0x40 + (.Lpush_ecx-.LSTART_vsyscall) /* DW_CFA_advance_loc */ - .byte 0x0e /* DW_CFA_def_cfa_offset */ - .byte 0x08 /* RA at offset 8 now */ - .byte 0x40 + (.Lpush_edx-.Lpush_ecx) /* DW_CFA_advance_loc */ - .byte 0x0e /* DW_CFA_def_cfa_offset */ - .byte 0x0c /* RA at offset 12 now */ - .byte 0x40 + (.Lenter_kernel-.Lpush_edx) /* DW_CFA_advance_loc */ - .byte 0x0e /* DW_CFA_def_cfa_offset */ - .byte 0x10 /* RA at offset 16 now */ - .byte 0x85, 0x04 /* DW_CFA_offset %ebp -16 */ - /* Finally the epilogue. */ - .byte 0x40 + (.Lpop_ebp-.Lenter_kernel) /* DW_CFA_advance_loc */ - .byte 0x0e /* DW_CFA_def_cfa_offset */ - .byte 0x0c /* RA at offset 12 now */ - .byte 0xc5 /* DW_CFA_restore %ebp */ - .byte 0x40 + (.Lpop_edx-.Lpop_ebp) /* DW_CFA_advance_loc */ - .byte 0x0e /* DW_CFA_def_cfa_offset */ - .byte 0x08 /* RA at offset 8 now */ - .byte 0x40 + (.Lpop_ecx-.Lpop_edx) /* DW_CFA_advance_loc */ - .byte 0x0e /* DW_CFA_def_cfa_offset */ - .byte 0x04 /* RA at offset 4 now */ - .align 4 -.LENDFDEDLSI: - .previous - - /* - * Emit a symbol with the size of this .eh_frame data, - * to verify it matches the other versions. - */ -VDSO32_vsyscall_eh_frame_size = (.LENDFDEDLSI-.LSTARTFRAMEDLSI) diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S new file mode 100644 index 000000000000..3a1d9297074b --- /dev/null +++ b/arch/x86/entry/vdso/vdso32/system_call.S @@ -0,0 +1,89 @@ +/* + * AT_SYSINFO entry point +*/ + +#include <asm/dwarf2.h> +#include <asm/cpufeature.h> +#include <asm/alternative-asm.h> + +/* + * First get the common code for the sigreturn entry points. + * This must come first. + */ +#include "sigreturn.S" + + .text + .globl __kernel_vsyscall + .type __kernel_vsyscall,@function + ALIGN +__kernel_vsyscall: + CFI_STARTPROC + /* + * Reshuffle regs so that all of any of the entry instructions + * will preserve enough state. + * + * A really nice entry sequence would be: + * pushl %edx + * pushl %ecx + * movl %esp, %ecx + * + * Unfortunately, naughty Android versions between July and December + * 2015 actually hardcode the traditional Linux SYSENTER entry + * sequence. That is severely broken for a number of reasons (ask + * anyone with an AMD CPU, for example). Nonetheless, we try to keep + * it working approximately as well as it ever worked. + * + * This link may eludicate some of the history: + * https://android-review.googlesource.com/#/q/Iac3295376d61ef83e713ac9b528f3b50aa780cd7 + * personally, I find it hard to understand what's going on there. + * + * Note to future user developers: DO NOT USE SYSENTER IN YOUR CODE. + * Execute an indirect call to the address in the AT_SYSINFO auxv + * entry. That is the ONLY correct way to make a fast 32-bit system + * call on Linux. (Open-coding int $0x80 is also fine, but it's + * slow.) + */ + pushl %ecx + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET ecx, 0 + pushl %edx + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET edx, 0 + pushl %ebp + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET ebp, 0 + + #define SYSENTER_SEQUENCE "movl %esp, %ebp; sysenter" + #define SYSCALL_SEQUENCE "movl %ecx, %ebp; syscall" + +#ifdef CONFIG_X86_64 + /* If SYSENTER (Intel) or SYSCALL32 (AMD) is available, use it. */ + ALTERNATIVE_2 "", SYSENTER_SEQUENCE, X86_FEATURE_SYSENTER32, \ + SYSCALL_SEQUENCE, X86_FEATURE_SYSCALL32 +#else + ALTERNATIVE "", SYSENTER_SEQUENCE, X86_FEATURE_SEP +#endif + + /* Enter using int $0x80 */ + int $0x80 +GLOBAL(int80_landing_pad) + + /* + * Restore EDX and ECX in case they were clobbered. EBP is not + * clobbered (the kernel restores it), but it's cleaner and + * probably faster to pop it than to adjust ESP using addl. + */ + popl %ebp + CFI_RESTORE ebp + CFI_ADJUST_CFA_OFFSET -4 + popl %edx + CFI_RESTORE edx + CFI_ADJUST_CFA_OFFSET -4 + popl %ecx + CFI_RESTORE ecx + CFI_ADJUST_CFA_OFFSET -4 + ret + CFI_ENDPROC + + .size __kernel_vsyscall,.-__kernel_vsyscall + .previous diff --git a/arch/x86/entry/vdso/vdso32/vclock_gettime.c b/arch/x86/entry/vdso/vdso32/vclock_gettime.c index 175cc72c0f68..87a86e017f0e 100644 --- a/arch/x86/entry/vdso/vdso32/vclock_gettime.c +++ b/arch/x86/entry/vdso/vdso32/vclock_gettime.c @@ -14,11 +14,13 @@ */ #undef CONFIG_64BIT #undef CONFIG_X86_64 +#undef CONFIG_PGTABLE_LEVELS #undef CONFIG_ILLEGAL_POINTER_VALUE #undef CONFIG_SPARSEMEM_VMEMMAP #undef CONFIG_NR_CPUS #define CONFIG_X86_32 1 +#define CONFIG_PGTABLE_LEVELS 2 #define CONFIG_PAGE_OFFSET 0 #define CONFIG_ILLEGAL_POINTER_VALUE 0 #define CONFIG_NR_CPUS 1 diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 1c9f750c3859..b8f69e264ac4 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -12,6 +12,7 @@ #include <linux/random.h> #include <linux/elf.h> #include <linux/cpu.h> +#include <asm/pvclock.h> #include <asm/vgtod.h> #include <asm/proto.h> #include <asm/vdso.h> @@ -100,6 +101,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) .name = "[vvar]", .pages = no_pages, }; + struct pvclock_vsyscall_time_info *pvti; if (calculate_addr) { addr = vdso_addr(current->mm->start_stack, @@ -169,6 +171,18 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) } #endif + pvti = pvclock_pvti_cpu0_va(); + if (pvti && image->sym_pvclock_page) { + ret = remap_pfn_range(vma, + text_start + image->sym_pvclock_page, + __pa(pvti) >> PAGE_SHIFT, + PAGE_SIZE, + PAGE_READONLY); + + if (ret) + goto up_fail; + } + up_fail: if (ret) current->mm->context.vdso = NULL; @@ -177,24 +191,13 @@ up_fail: return ret; } -#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT) +#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) static int load_vdso32(void) { - int ret; - if (vdso32_enabled != 1) /* Other values all mean "disabled" */ return 0; - ret = map_vdso(selected_vdso32, false); - if (ret) - return ret; - - if (selected_vdso32->sym_VDSO32_SYSENTER_RETURN) - current_thread_info()->sysenter_return = - current->mm->context.vdso + - selected_vdso32->sym_VDSO32_SYSENTER_RETURN; - - return 0; + return map_vdso(&vdso_image_32, false); } #endif @@ -219,8 +222,11 @@ int compat_arch_setup_additional_pages(struct linux_binprm *bprm, return map_vdso(&vdso_image_x32, true); } #endif - +#ifdef CONFIG_IA32_EMULATION return load_vdso32(); +#else + return 0; +#endif } #endif #else diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index 2dcc6ff6fdcc..174c2549939d 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -38,7 +38,14 @@ #define CREATE_TRACE_POINTS #include "vsyscall_trace.h" -static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE; +static enum { EMULATE, NATIVE, NONE } vsyscall_mode = +#if defined(CONFIG_LEGACY_VSYSCALL_NATIVE) + NATIVE; +#elif defined(CONFIG_LEGACY_VSYSCALL_NONE) + NONE; +#else + EMULATE; +#endif static int __init vsyscall_setup(char *str) { @@ -277,7 +284,7 @@ static const char *gate_vma_name(struct vm_area_struct *vma) { return "[vsyscall]"; } -static struct vm_operations_struct gate_vma_ops = { +static const struct vm_operations_struct gate_vma_ops = { .name = gate_vma_name, }; static struct vm_area_struct gate_vma = { @@ -290,7 +297,7 @@ static struct vm_area_struct gate_vma = { struct vm_area_struct *get_gate_vma(struct mm_struct *mm) { -#ifdef CONFIG_IA32_EMULATION +#ifdef CONFIG_COMPAT if (!mm || mm->context.ia32_compat) return NULL; #endif diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index ae3a29ae875b..0552884da18d 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -26,7 +26,7 @@ #include <asm/ptrace.h> #include <asm/ia32_unistd.h> #include <asm/user32.h> -#include <asm/sigcontext32.h> +#include <uapi/asm/sigcontext.h> #include <asm/proto.h> #include <asm/vdso.h> #include <asm/sigframe.h> @@ -34,99 +34,6 @@ #include <asm/sys_ia32.h> #include <asm/smap.h> -int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) -{ - int err = 0; - bool ia32 = test_thread_flag(TIF_IA32); - - if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t))) - return -EFAULT; - - put_user_try { - /* If you change siginfo_t structure, please make sure that - this code is fixed accordingly. - It should never copy any pad contained in the structure - to avoid security leaks, but must copy the generic - 3 ints plus the relevant union member. */ - put_user_ex(from->si_signo, &to->si_signo); - put_user_ex(from->si_errno, &to->si_errno); - put_user_ex((short)from->si_code, &to->si_code); - - if (from->si_code < 0) { - put_user_ex(from->si_pid, &to->si_pid); - put_user_ex(from->si_uid, &to->si_uid); - put_user_ex(ptr_to_compat(from->si_ptr), &to->si_ptr); - } else { - /* - * First 32bits of unions are always present: - * si_pid === si_band === si_tid === si_addr(LS half) - */ - put_user_ex(from->_sifields._pad[0], - &to->_sifields._pad[0]); - switch (from->si_code >> 16) { - case __SI_FAULT >> 16: - break; - case __SI_SYS >> 16: - put_user_ex(from->si_syscall, &to->si_syscall); - put_user_ex(from->si_arch, &to->si_arch); - break; - case __SI_CHLD >> 16: - if (ia32) { - put_user_ex(from->si_utime, &to->si_utime); - put_user_ex(from->si_stime, &to->si_stime); - } else { - put_user_ex(from->si_utime, &to->_sifields._sigchld_x32._utime); - put_user_ex(from->si_stime, &to->_sifields._sigchld_x32._stime); - } - put_user_ex(from->si_status, &to->si_status); - /* FALL THROUGH */ - default: - case __SI_KILL >> 16: - put_user_ex(from->si_uid, &to->si_uid); - break; - case __SI_POLL >> 16: - put_user_ex(from->si_fd, &to->si_fd); - break; - case __SI_TIMER >> 16: - put_user_ex(from->si_overrun, &to->si_overrun); - put_user_ex(ptr_to_compat(from->si_ptr), - &to->si_ptr); - break; - /* This is not generated by the kernel as of now. */ - case __SI_RT >> 16: - case __SI_MESGQ >> 16: - put_user_ex(from->si_uid, &to->si_uid); - put_user_ex(from->si_int, &to->si_int); - break; - } - } - } put_user_catch(err); - - return err; -} - -int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) -{ - int err = 0; - u32 ptr32; - - if (!access_ok(VERIFY_READ, from, sizeof(compat_siginfo_t))) - return -EFAULT; - - get_user_try { - get_user_ex(to->si_signo, &from->si_signo); - get_user_ex(to->si_errno, &from->si_errno); - get_user_ex(to->si_code, &from->si_code); - - get_user_ex(to->si_pid, &from->si_pid); - get_user_ex(to->si_uid, &from->si_uid); - get_user_ex(ptr32, &from->si_ptr); - to->si_ptr = compat_ptr(ptr32); - } get_user_catch(err); - - return err; -} - /* * Do a signal return; undo the signal stack. */ @@ -161,7 +68,7 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) } static int ia32_restore_sigcontext(struct pt_regs *regs, - struct sigcontext_ia32 __user *sc) + struct sigcontext_32 __user *sc) { unsigned int tmpflags, err = 0; void __user *buf; @@ -263,7 +170,7 @@ badframe: * Set up a signal frame. */ -static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc, +static int ia32_setup_sigcontext(struct sigcontext_32 __user *sc, void __user *fpstate, struct pt_regs *regs, unsigned int mask) { @@ -327,7 +234,7 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long fx_aligned, math_size; sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size); - *fpstate = (struct _fpstate_ia32 __user *) sp; + *fpstate = (struct _fpstate_32 __user *) sp; if (copy_fpstate_to_sigframe(*fpstate, (void __user *)fx_aligned, math_size) < 0) return (void __user *) -1L; @@ -382,7 +289,7 @@ int ia32_setup_frame(int sig, struct ksignal *ksig, /* Return stub is in 32bit vsyscall page */ if (current->mm->context.vdso) restorer = current->mm->context.vdso + - selected_vdso32->sym___kernel_sigreturn; + vdso_image_32.sym___kernel_sigreturn; else restorer = &frame->retcode; } @@ -461,7 +368,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig, restorer = ksig->ka.sa.sa_restorer; else restorer = current->mm->context.vdso + - selected_vdso32->sym___kernel_rt_sigreturn; + vdso_image_32.sym___kernel_rt_sigreturn; put_user_ex(ptr_to_compat(restorer), &frame->pretcode); /* diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 3a45668f6dc3..94c18ebfd68c 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -32,6 +32,10 @@ #include <asm/mpspec.h> #include <asm/realmode.h> +#ifdef CONFIG_ACPI_APEI +# include <asm/pgtable_types.h> +#endif + #ifdef CONFIG_ACPI extern int acpi_lapic; extern int acpi_ioapic; @@ -147,4 +151,23 @@ extern int x86_acpi_numa_init(void); #define acpi_unlazy_tlb(x) leave_mm(x) +#ifdef CONFIG_ACPI_APEI +static inline pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr) +{ + /* + * We currently have no way to look up the EFI memory map + * attributes for a region in a consistent way, because the + * memmap is discarded after efi_free_boot_services(). So if + * you call efi_mem_attributes() during boot and at runtime, + * you could theoretically see different attributes. + * + * Since we are yet to see any x86 platforms that require + * anything other than PAGE_KERNEL (some arm64 platforms + * require the equivalent of PAGE_KERNEL_NOCACHE), return that + * until we know differently. + */ + return PAGE_KERNEL; +} +#endif + #endif /* _ASM_X86_ACPI_H */ diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index 1a5da2e63aee..3c56ef1ae068 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -81,7 +81,7 @@ static inline struct amd_northbridge *node_to_amd_nb(int node) return (node < amd_northbridges.num) ? &amd_northbridges.nb[node] : NULL; } -static inline u16 amd_get_node_id(struct pci_dev *pdev) +static inline u16 amd_pci_dev_to_node_id(struct pci_dev *pdev) { struct pci_dev *misc; int i; diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index c8393634ca0c..c80f6b6f3da2 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -23,6 +23,11 @@ #define APIC_VERBOSE 1 #define APIC_DEBUG 2 +/* Macros for apic_extnmi which controls external NMI masking */ +#define APIC_EXTNMI_BSP 0 /* Default */ +#define APIC_EXTNMI_ALL 1 +#define APIC_EXTNMI_NONE 2 + /* * Define the default level of output to be very little * This can be turned up by using apic=verbose for more @@ -115,6 +120,59 @@ static inline bool apic_is_x2apic_enabled(void) return msr & X2APIC_ENABLE; } +extern void enable_IR_x2apic(void); + +extern int get_physical_broadcast(void); + +extern int lapic_get_maxlvt(void); +extern void clear_local_APIC(void); +extern void disconnect_bsp_APIC(int virt_wire_setup); +extern void disable_local_APIC(void); +extern void lapic_shutdown(void); +extern void sync_Arb_IDs(void); +extern void init_bsp_APIC(void); +extern void setup_local_APIC(void); +extern void init_apic_mappings(void); +void register_lapic_address(unsigned long address); +extern void setup_boot_APIC_clock(void); +extern void setup_secondary_APIC_clock(void); +extern int APIC_init_uniprocessor(void); + +#ifdef CONFIG_X86_64 +static inline int apic_force_enable(unsigned long addr) +{ + return -1; +} +#else +extern int apic_force_enable(unsigned long addr); +#endif + +extern int apic_bsp_setup(bool upmode); +extern void apic_ap_setup(void); + +/* + * On 32bit this is mach-xxx local + */ +#ifdef CONFIG_X86_64 +extern int apic_is_clustered_box(void); +#else +static inline int apic_is_clustered_box(void) +{ + return 0; +} +#endif + +extern int setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask); + +#else /* !CONFIG_X86_LOCAL_APIC */ +static inline void lapic_shutdown(void) { } +#define local_apic_timer_c2_ok 1 +static inline void init_apic_mappings(void) { } +static inline void disable_local_APIC(void) { } +# define setup_boot_APIC_clock x86_init_noop +# define setup_secondary_APIC_clock x86_init_noop +#endif /* !CONFIG_X86_LOCAL_APIC */ + #ifdef CONFIG_X86_X2APIC /* * Make previous memory operations globally visible before @@ -186,67 +244,14 @@ static inline int x2apic_enabled(void) } #define x2apic_supported() (cpu_has_x2apic) -#else +#else /* !CONFIG_X86_X2APIC */ static inline void check_x2apic(void) { } static inline void x2apic_setup(void) { } static inline int x2apic_enabled(void) { return 0; } #define x2apic_mode (0) #define x2apic_supported() (0) -#endif - -extern void enable_IR_x2apic(void); - -extern int get_physical_broadcast(void); - -extern int lapic_get_maxlvt(void); -extern void clear_local_APIC(void); -extern void disconnect_bsp_APIC(int virt_wire_setup); -extern void disable_local_APIC(void); -extern void lapic_shutdown(void); -extern void sync_Arb_IDs(void); -extern void init_bsp_APIC(void); -extern void setup_local_APIC(void); -extern void init_apic_mappings(void); -void register_lapic_address(unsigned long address); -extern void setup_boot_APIC_clock(void); -extern void setup_secondary_APIC_clock(void); -extern int APIC_init_uniprocessor(void); - -#ifdef CONFIG_X86_64 -static inline int apic_force_enable(unsigned long addr) -{ - return -1; -} -#else -extern int apic_force_enable(unsigned long addr); -#endif - -extern int apic_bsp_setup(bool upmode); -extern void apic_ap_setup(void); - -/* - * On 32bit this is mach-xxx local - */ -#ifdef CONFIG_X86_64 -extern int apic_is_clustered_box(void); -#else -static inline int apic_is_clustered_box(void) -{ - return 0; -} -#endif - -extern int setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask); - -#else /* !CONFIG_X86_LOCAL_APIC */ -static inline void lapic_shutdown(void) { } -#define local_apic_timer_c2_ok 1 -static inline void init_apic_mappings(void) { } -static inline void disable_local_APIC(void) { } -# define setup_boot_APIC_clock x86_init_noop -# define setup_secondary_APIC_clock x86_init_noop -#endif /* !CONFIG_X86_LOCAL_APIC */ +#endif /* !CONFIG_X86_X2APIC */ #ifdef CONFIG_X86_64 #define SET_APIC_ID(x) (apic->set_apic_id(x)) @@ -303,6 +308,7 @@ struct apic { unsigned int *apicid); /* ipi */ + void (*send_IPI)(int cpu, int vector); void (*send_IPI_mask)(const struct cpumask *mask, int vector); void (*send_IPI_mask_allbutself)(const struct cpumask *mask, int vector); @@ -313,7 +319,6 @@ struct apic { /* wakeup_secondary_cpu */ int (*wakeup_secondary_cpu)(int apicid, unsigned long start_eip); - bool wait_for_init_deassert; void (*inquire_remote_apic)(int apicid); /* apic ops */ @@ -378,7 +383,6 @@ extern struct apic *__apicdrivers[], *__apicdrivers_end[]; * APIC functionality to boot other CPUs - only used on SMP: */ #ifdef CONFIG_SMP -extern atomic_t init_deasserted; extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip); #endif diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h index 9686c3d9ff73..259a7c1ef709 100644 --- a/arch/x86/include/asm/arch_hweight.h +++ b/arch/x86/include/asm/arch_hweight.h @@ -21,7 +21,7 @@ * ARCH_HWEIGHT_CFLAGS in <arch/x86/Kconfig> for the respective * compiler switches. */ -static inline unsigned int __arch_hweight32(unsigned int w) +static __always_inline unsigned int __arch_hweight32(unsigned int w) { unsigned int res = 0; @@ -42,20 +42,23 @@ static inline unsigned int __arch_hweight8(unsigned int w) return __arch_hweight32(w & 0xff); } +#ifdef CONFIG_X86_32 static inline unsigned long __arch_hweight64(__u64 w) { - unsigned long res = 0; - -#ifdef CONFIG_X86_32 return __arch_hweight32((u32)w) + __arch_hweight32((u32)(w >> 32)); +} #else +static __always_inline unsigned long __arch_hweight64(__u64 w) +{ + unsigned long res = 0; + asm (ALTERNATIVE("call __sw_hweight64", POPCNT64, X86_FEATURE_POPCNT) : "="REG_OUT (res) : REG_IN (w)); -#endif /* CONFIG_X86_32 */ return res; } +#endif /* CONFIG_X86_32 */ #endif diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index e9168955c42f..3e8674288198 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -3,7 +3,6 @@ #include <linux/compiler.h> #include <linux/types.h> -#include <asm/processor.h> #include <asm/alternative.h> #include <asm/cmpxchg.h> #include <asm/rmwcc.h> @@ -24,7 +23,7 @@ */ static __always_inline int atomic_read(const atomic_t *v) { - return ACCESS_ONCE((v)->counter); + return READ_ONCE((v)->counter); } /** @@ -36,7 +35,7 @@ static __always_inline int atomic_read(const atomic_t *v) */ static __always_inline void atomic_set(atomic_t *v, int i) { - v->counter = i; + WRITE_ONCE(v->counter, i); } /** @@ -182,6 +181,21 @@ static inline int atomic_xchg(atomic_t *v, int new) return xchg(&v->counter, new); } +#define ATOMIC_OP(op) \ +static inline void atomic_##op(int i, atomic_t *v) \ +{ \ + asm volatile(LOCK_PREFIX #op"l %1,%0" \ + : "+m" (v->counter) \ + : "ir" (i) \ + : "memory"); \ +} + +ATOMIC_OP(and) +ATOMIC_OP(or) +ATOMIC_OP(xor) + +#undef ATOMIC_OP + /** * __atomic_add_unless - add unless the number is already a given value * @v: pointer of type atomic_t @@ -219,16 +233,6 @@ static __always_inline short int atomic_inc_short(short int *v) return *v; } -/* These are x86-specific, used by some header files */ -#define atomic_clear_mask(mask, addr) \ - asm volatile(LOCK_PREFIX "andl %0,%1" \ - : : "r" (~(mask)), "m" (*(addr)) : "memory") - -#define atomic_set_mask(mask, addr) \ - asm volatile(LOCK_PREFIX "orl %0,%1" \ - : : "r" ((unsigned)(mask)), "m" (*(addr)) \ - : "memory") - #ifdef CONFIG_X86_32 # include <asm/atomic64_32.h> #else diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index b154de75c90c..a984111135b1 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -3,7 +3,6 @@ #include <linux/compiler.h> #include <linux/types.h> -#include <asm/processor.h> //#include <asm/cmpxchg.h> /* An 64bit atomic type */ @@ -313,4 +312,18 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v) #undef alternative_atomic64 #undef __alternative_atomic64 +#define ATOMIC64_OP(op, c_op) \ +static inline void atomic64_##op(long long i, atomic64_t *v) \ +{ \ + long long old, c = 0; \ + while ((old = atomic64_cmpxchg(v, c, c c_op i)) != c) \ + c = old; \ +} + +ATOMIC64_OP(and, &) +ATOMIC64_OP(or, |) +ATOMIC64_OP(xor, ^) + +#undef ATOMIC64_OP + #endif /* _ASM_X86_ATOMIC64_32_H */ diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index b965f9e03f2a..037351022f54 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -18,7 +18,7 @@ */ static inline long atomic64_read(const atomic64_t *v) { - return ACCESS_ONCE((v)->counter); + return READ_ONCE((v)->counter); } /** @@ -30,7 +30,7 @@ static inline long atomic64_read(const atomic64_t *v) */ static inline void atomic64_set(atomic64_t *v, long i) { - v->counter = i; + WRITE_ONCE(v->counter, i); } /** @@ -220,4 +220,19 @@ static inline long atomic64_dec_if_positive(atomic64_t *v) return dec; } +#define ATOMIC64_OP(op) \ +static inline void atomic64_##op(long i, atomic64_t *v) \ +{ \ + asm volatile(LOCK_PREFIX #op"q %1,%0" \ + : "+m" (v->counter) \ + : "er" (i) \ + : "memory"); \ +} + +ATOMIC64_OP(and) +ATOMIC64_OP(or) +ATOMIC64_OP(xor) + +#undef ATOMIC64_OP + #endif /* _ASM_X86_ATOMIC64_64_H */ diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index e51a8f803f55..a584e1c50918 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -31,20 +31,10 @@ #endif #define dma_wmb() barrier() -#ifdef CONFIG_SMP -#define smp_mb() mb() -#define smp_rmb() dma_rmb() -#define smp_wmb() barrier() -#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 smp_store_mb(var, value) do { WRITE_ONCE(var, value); barrier(); } while (0) -#endif /* SMP */ - -#define read_barrier_depends() do { } while (0) -#define smp_read_barrier_depends() do { } while (0) +#define __smp_mb() mb() +#define __smp_rmb() dma_rmb() +#define __smp_wmb() barrier() +#define __smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0) #if defined(CONFIG_X86_PPRO_FENCE) @@ -53,33 +43,33 @@ * model and we should fall back to full barriers. */ -#define smp_store_release(p, v) \ +#define __smp_store_release(p, v) \ do { \ compiletime_assert_atomic_type(*p); \ - smp_mb(); \ - ACCESS_ONCE(*p) = (v); \ + __smp_mb(); \ + WRITE_ONCE(*p, v); \ } while (0) -#define smp_load_acquire(p) \ +#define __smp_load_acquire(p) \ ({ \ - typeof(*p) ___p1 = ACCESS_ONCE(*p); \ + typeof(*p) ___p1 = READ_ONCE(*p); \ compiletime_assert_atomic_type(*p); \ - smp_mb(); \ + __smp_mb(); \ ___p1; \ }) #else /* regular x86 TSO memory ordering */ -#define smp_store_release(p, v) \ +#define __smp_store_release(p, v) \ do { \ compiletime_assert_atomic_type(*p); \ barrier(); \ - ACCESS_ONCE(*p) = (v); \ + WRITE_ONCE(*p, v); \ } while (0) -#define smp_load_acquire(p) \ +#define __smp_load_acquire(p) \ ({ \ - typeof(*p) ___p1 = ACCESS_ONCE(*p); \ + typeof(*p) ___p1 = READ_ONCE(*p); \ compiletime_assert_atomic_type(*p); \ barrier(); \ ___p1; \ @@ -88,18 +78,9 @@ do { \ #endif /* Atomic operations are already serializing on x86 */ -#define smp_mb__before_atomic() barrier() -#define smp_mb__after_atomic() barrier() +#define __smp_mb__before_atomic() barrier() +#define __smp_mb__after_atomic() barrier() -/* - * Stop RDTSC speculation. This is needed when you need to use RDTSC - * (or get_cycles or vread that possibly accesses the TSC) in a defined - * code region. - */ -static __always_inline void rdtsc_barrier(void) -{ - alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, - "lfence", X86_FEATURE_LFENCE_RDTSC); -} +#include <asm-generic/barrier.h> #endif /* _ASM_X86_BARRIER_H */ diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index 4fa687a47a62..6b8d6e8cd449 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -27,7 +27,7 @@ #define BOOT_HEAP_SIZE 0x400000 #else /* !CONFIG_KERNEL_BZIP2 */ -#define BOOT_HEAP_SIZE 0x8000 +#define BOOT_HEAP_SIZE 0x10000 #endif /* !CONFIG_KERNEL_BZIP2 */ diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h index 9bf3ea14b9f0..e63aa38e85fb 100644 --- a/arch/x86/include/asm/cacheflush.h +++ b/arch/x86/include/asm/cacheflush.h @@ -89,6 +89,8 @@ int set_pages_rw(struct page *page, int numpages); void clflush_cache_range(void *addr, unsigned int size); +#define mmio_flush_range(addr, size) clflush_cache_range(addr, size) + #ifdef CONFIG_DEBUG_RODATA void mark_rodata_ro(void); extern const int rodata_test_data; @@ -109,75 +111,4 @@ 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/calgary.h b/arch/x86/include/asm/calgary.h index 0d467b338835..a8303ebe089f 100644 --- a/arch/x86/include/asm/calgary.h +++ b/arch/x86/include/asm/calgary.h @@ -31,7 +31,7 @@ #include <asm/types.h> struct iommu_table { - struct cal_chipset_ops *chip_ops; /* chipset specific funcs */ + const struct cal_chipset_ops *chip_ops; /* chipset specific funcs */ unsigned long it_base; /* mapped address of tce table */ unsigned long it_hint; /* Hint for next alloc */ unsigned long *it_map; /* A simple allocation bitmap for now */ diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h index f7e142926481..e4959d023af8 100644 --- a/arch/x86/include/asm/cmpxchg_32.h +++ b/arch/x86/include/asm/cmpxchg_32.h @@ -109,6 +109,6 @@ static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new) #endif -#define system_has_cmpxchg_double() cpu_has_cx8 +#define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX8) #endif /* _ASM_X86_CMPXCHG_32_H */ diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h index 1af94697aae5..caa23a34c963 100644 --- a/arch/x86/include/asm/cmpxchg_64.h +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -18,6 +18,6 @@ static inline void set_64bit(volatile u64 *ptr, u64 val) cmpxchg_local((ptr), (o), (n)); \ }) -#define system_has_cmpxchg_double() cpu_has_cx16 +#define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX16) #endif /* _ASM_X86_CMPXCHG_64_H */ diff --git a/arch/x86/include/asm/context_tracking.h b/arch/x86/include/asm/context_tracking.h deleted file mode 100644 index 1fe49704b146..000000000000 --- a/arch/x86/include/asm/context_tracking.h +++ /dev/null @@ -1,10 +0,0 @@ -#ifndef _ASM_X86_CONTEXT_TRACKING_H -#define _ASM_X86_CONTEXT_TRACKING_H - -#ifdef CONFIG_CONTEXT_TRACKING -# define SCHEDULE_USER call schedule_user -#else -# define SCHEDULE_USER call schedule -#endif - -#endif diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index bf2caa1dedc5..678637ad7476 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -36,4 +36,7 @@ extern int _debug_hotplug_cpu(int cpu, int action); int mwait_usable(const struct cpuinfo_x86 *); +unsigned int x86_family(unsigned int sig); +unsigned int x86_model(unsigned int sig); +unsigned int x86_stepping(unsigned int sig); #endif /* _ASM_X86_CPU_H */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 3d6606fb97d0..7ad8c9464297 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -12,7 +12,7 @@ #include <asm/disabled-features.h> #endif -#define NCAPINTS 13 /* N 32-bit words worth of info */ +#define NCAPINTS 16 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* @@ -119,6 +119,7 @@ #define X86_FEATURE_TM2 ( 4*32+ 8) /* Thermal Monitor 2 */ #define X86_FEATURE_SSSE3 ( 4*32+ 9) /* Supplemental SSE-3 */ #define X86_FEATURE_CID ( 4*32+10) /* Context ID */ +#define X86_FEATURE_SDBG ( 4*32+11) /* Silicon Debug */ #define X86_FEATURE_FMA ( 4*32+12) /* Fused multiply-add */ #define X86_FEATURE_CX16 ( 4*32+13) /* CMPXCHG16B */ #define X86_FEATURE_XTPR ( 4*32+14) /* Send Task Priority Messages */ @@ -176,25 +177,21 @@ #define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */ #define X86_FEATURE_BPEXT (6*32+26) /* data breakpoint extension */ #define X86_FEATURE_PERFCTR_L2 ( 6*32+28) /* L2 performance counter extensions */ +#define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */ /* * Auxiliary flags: Linux defined - For features scattered in various - * CPUID levels like 0x6, 0xA etc, word 7 + * CPUID levels like 0x6, 0xA etc, word 7. + * + * Reuse free bits when adding new feature flags! */ -#define X86_FEATURE_IDA ( 7*32+ 0) /* Intel Dynamic Acceleration */ -#define X86_FEATURE_ARAT ( 7*32+ 1) /* Always Running APIC Timer */ + #define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ #define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ -#define X86_FEATURE_PLN ( 7*32+ 5) /* Intel Power Limit Notification */ -#define X86_FEATURE_PTS ( 7*32+ 6) /* Intel Package Thermal Status */ -#define X86_FEATURE_DTHERM ( 7*32+ 7) /* Digital Thermal Sensor */ + #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ -#define X86_FEATURE_HWP ( 7*32+ 10) /* "hwp" Intel HWP */ -#define X86_FEATURE_HWP_NOITFY ( 7*32+ 11) /* Intel HWP_NOTIFY */ -#define X86_FEATURE_HWP_ACT_WINDOW ( 7*32+ 12) /* Intel HWP_ACT_WINDOW */ -#define X86_FEATURE_HWP_EPP ( 7*32+13) /* Intel HWP_EPP */ -#define X86_FEATURE_HWP_PKG_REQ ( 7*32+14) /* Intel HWP_PKG_REQ */ + #define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ /* Virtualization flags: Linux defined, word 8 */ @@ -203,17 +200,9 @@ #define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */ #define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */ #define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ -#define X86_FEATURE_NPT ( 8*32+ 5) /* AMD Nested Page Table support */ -#define X86_FEATURE_LBRV ( 8*32+ 6) /* AMD LBR Virtualization support */ -#define X86_FEATURE_SVML ( 8*32+ 7) /* "svm_lock" AMD SVM locking MSR */ -#define X86_FEATURE_NRIPS ( 8*32+ 8) /* "nrip_save" AMD SVM next_rip save */ -#define X86_FEATURE_TSCRATEMSR ( 8*32+ 9) /* "tsc_scale" AMD TSC scaling support */ -#define X86_FEATURE_VMCBCLEAN ( 8*32+10) /* "vmcb_clean" AMD VMCB clean bits support */ -#define X86_FEATURE_FLUSHBYASID ( 8*32+11) /* AMD flush-by-ASID support */ -#define X86_FEATURE_DECODEASSISTS ( 8*32+12) /* AMD Decode Assists support */ -#define X86_FEATURE_PAUSEFILTER ( 8*32+13) /* AMD filtered pause intercept */ -#define X86_FEATURE_PFTHRESHOLD ( 8*32+14) /* AMD pause filter threshold */ + #define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer vmmcall to vmcall */ +#define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ @@ -239,6 +228,7 @@ #define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ #define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ #define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */ +#define X86_FEATURE_SHA_NI ( 9*32+29) /* SHA1/SHA256 Instruction Extensions */ /* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */ #define X86_FEATURE_XSAVEOPT (10*32+ 0) /* XSAVEOPT */ @@ -252,6 +242,33 @@ /* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */ #define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */ +/* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */ +#define X86_FEATURE_CLZERO (13*32+0) /* CLZERO instruction */ + +/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */ +#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ +#define X86_FEATURE_IDA (14*32+ 1) /* Intel Dynamic Acceleration */ +#define X86_FEATURE_ARAT (14*32+ 2) /* Always Running APIC Timer */ +#define X86_FEATURE_PLN (14*32+ 4) /* Intel Power Limit Notification */ +#define X86_FEATURE_PTS (14*32+ 6) /* Intel Package Thermal Status */ +#define X86_FEATURE_HWP (14*32+ 7) /* Intel Hardware P-states */ +#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* HWP Notification */ +#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */ +#define X86_FEATURE_HWP_EPP (14*32+10) /* HWP Energy Perf. Preference */ +#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */ + +/* AMD SVM Feature Identification, CPUID level 0x8000000a (edx), word 15 */ +#define X86_FEATURE_NPT (15*32+ 0) /* Nested Page Table support */ +#define X86_FEATURE_LBRV (15*32+ 1) /* LBR Virtualization support */ +#define X86_FEATURE_SVML (15*32+ 2) /* "svm_lock" SVM locking MSR */ +#define X86_FEATURE_NRIPS (15*32+ 3) /* "nrip_save" SVM next_rip save */ +#define X86_FEATURE_TSCRATEMSR (15*32+ 4) /* "tsc_scale" TSC scaling support */ +#define X86_FEATURE_VMCBCLEAN (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */ +#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */ +#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */ +#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */ +#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ + /* * BUG word(s) */ @@ -272,6 +289,26 @@ #include <asm/asm.h> #include <linux/bitops.h> +enum cpuid_leafs +{ + CPUID_1_EDX = 0, + CPUID_8000_0001_EDX, + CPUID_8086_0001_EDX, + CPUID_LNX_1, + CPUID_1_ECX, + CPUID_C000_0001_EDX, + CPUID_8000_0001_ECX, + CPUID_LNX_2, + CPUID_LNX_3, + CPUID_7_0_EBX, + CPUID_D_1_EAX, + CPUID_F_0_EDX, + CPUID_F_1_EDX, + CPUID_8000_0008_EBX, + CPUID_6_EAX, + CPUID_8000_000A_EDX, +}; + #ifdef CONFIG_X86_FEATURE_NAMES extern const char * const x86_cap_flags[NCAPINTS*32]; extern const char * const x86_power_flags[32]; @@ -349,60 +386,31 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; } while (0) #define cpu_has_fpu boot_cpu_has(X86_FEATURE_FPU) -#define cpu_has_de boot_cpu_has(X86_FEATURE_DE) #define cpu_has_pse boot_cpu_has(X86_FEATURE_PSE) #define cpu_has_tsc boot_cpu_has(X86_FEATURE_TSC) #define cpu_has_pge boot_cpu_has(X86_FEATURE_PGE) #define cpu_has_apic boot_cpu_has(X86_FEATURE_APIC) -#define cpu_has_sep boot_cpu_has(X86_FEATURE_SEP) -#define cpu_has_mtrr boot_cpu_has(X86_FEATURE_MTRR) -#define cpu_has_mmx boot_cpu_has(X86_FEATURE_MMX) #define cpu_has_fxsr boot_cpu_has(X86_FEATURE_FXSR) #define cpu_has_xmm boot_cpu_has(X86_FEATURE_XMM) #define cpu_has_xmm2 boot_cpu_has(X86_FEATURE_XMM2) -#define cpu_has_xmm3 boot_cpu_has(X86_FEATURE_XMM3) -#define cpu_has_ssse3 boot_cpu_has(X86_FEATURE_SSSE3) #define cpu_has_aes boot_cpu_has(X86_FEATURE_AES) #define cpu_has_avx boot_cpu_has(X86_FEATURE_AVX) #define cpu_has_avx2 boot_cpu_has(X86_FEATURE_AVX2) -#define cpu_has_ht boot_cpu_has(X86_FEATURE_HT) -#define cpu_has_nx boot_cpu_has(X86_FEATURE_NX) -#define cpu_has_xstore boot_cpu_has(X86_FEATURE_XSTORE) -#define cpu_has_xstore_enabled boot_cpu_has(X86_FEATURE_XSTORE_EN) -#define cpu_has_xcrypt boot_cpu_has(X86_FEATURE_XCRYPT) -#define cpu_has_xcrypt_enabled boot_cpu_has(X86_FEATURE_XCRYPT_EN) -#define cpu_has_ace2 boot_cpu_has(X86_FEATURE_ACE2) -#define cpu_has_ace2_enabled boot_cpu_has(X86_FEATURE_ACE2_EN) -#define cpu_has_phe boot_cpu_has(X86_FEATURE_PHE) -#define cpu_has_phe_enabled boot_cpu_has(X86_FEATURE_PHE_EN) -#define cpu_has_pmm boot_cpu_has(X86_FEATURE_PMM) -#define cpu_has_pmm_enabled boot_cpu_has(X86_FEATURE_PMM_EN) -#define cpu_has_ds boot_cpu_has(X86_FEATURE_DS) -#define cpu_has_pebs boot_cpu_has(X86_FEATURE_PEBS) #define cpu_has_clflush boot_cpu_has(X86_FEATURE_CLFLUSH) -#define cpu_has_bts boot_cpu_has(X86_FEATURE_BTS) #define cpu_has_gbpages boot_cpu_has(X86_FEATURE_GBPAGES) #define cpu_has_arch_perfmon boot_cpu_has(X86_FEATURE_ARCH_PERFMON) #define cpu_has_pat boot_cpu_has(X86_FEATURE_PAT) -#define cpu_has_xmm4_1 boot_cpu_has(X86_FEATURE_XMM4_1) -#define cpu_has_xmm4_2 boot_cpu_has(X86_FEATURE_XMM4_2) #define cpu_has_x2apic boot_cpu_has(X86_FEATURE_X2APIC) #define cpu_has_xsave boot_cpu_has(X86_FEATURE_XSAVE) -#define cpu_has_xsaveopt boot_cpu_has(X86_FEATURE_XSAVEOPT) #define cpu_has_xsaves boot_cpu_has(X86_FEATURE_XSAVES) #define cpu_has_osxsave boot_cpu_has(X86_FEATURE_OSXSAVE) #define cpu_has_hypervisor boot_cpu_has(X86_FEATURE_HYPERVISOR) -#define cpu_has_pclmulqdq boot_cpu_has(X86_FEATURE_PCLMULQDQ) -#define cpu_has_perfctr_core boot_cpu_has(X86_FEATURE_PERFCTR_CORE) -#define cpu_has_perfctr_nb boot_cpu_has(X86_FEATURE_PERFCTR_NB) -#define cpu_has_perfctr_l2 boot_cpu_has(X86_FEATURE_PERFCTR_L2) -#define cpu_has_cx8 boot_cpu_has(X86_FEATURE_CX8) -#define cpu_has_cx16 boot_cpu_has(X86_FEATURE_CX16) -#define cpu_has_eager_fpu boot_cpu_has(X86_FEATURE_EAGER_FPU) -#define cpu_has_topoext boot_cpu_has(X86_FEATURE_TOPOEXT) -#define cpu_has_bpext boot_cpu_has(X86_FEATURE_BPEXT) - -#if __GNUC__ >= 4 +/* + * Do not add any more of those clumsy macros - use static_cpu_has_safe() for + * fast paths and boot_cpu_has() otherwise! + */ + +#if __GNUC__ >= 4 && defined(CONFIG_X86_FAST_FEATURE_TESTS) extern void warn_pre_alternatives(void); extern bool __static_cpu_has_safe(u16 bit); diff --git a/arch/x86/include/asm/delay.h b/arch/x86/include/asm/delay.h index 9b3b4f2754c7..36a760bda462 100644 --- a/arch/x86/include/asm/delay.h +++ b/arch/x86/include/asm/delay.h @@ -4,5 +4,6 @@ #include <asm-generic/delay.h> void use_tsc_delay(void); +void use_mwaitx_delay(void); #endif /* _ASM_X86_DELAY_H */ diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h index 03dd72957d2f..684ed6c3aa67 100644 --- a/arch/x86/include/asm/device.h +++ b/arch/x86/include/asm/device.h @@ -10,6 +10,16 @@ struct dev_archdata { #endif }; +#if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS) +struct dma_domain { + struct list_head node; + struct dma_map_ops *dma_ops; + int domain_nr; +}; +void add_dma_domain(struct dma_domain *domain); +void del_dma_domain(struct dma_domain *domain); +#endif + struct pdev_archdata { }; diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 1f5b7287d1ad..953b7263f844 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -12,7 +12,6 @@ #include <linux/dma-attrs.h> #include <asm/io.h> #include <asm/swiotlb.h> -#include <asm-generic/dma-coherent.h> #include <linux/dma-contiguous.h> #ifdef CONFIG_ISA @@ -41,24 +40,13 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev) #endif } -#include <asm-generic/dma-mapping-common.h> - -/* Make sure we keep the same behaviour */ -static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) -{ - struct dma_map_ops *ops = get_dma_ops(dev); - debug_dma_mapping_error(dev, dma_addr); - if (ops->mapping_error) - return ops->mapping_error(dev, dma_addr); - - return (dma_addr == DMA_ERROR_CODE); -} - -#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f) -#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h) +bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp); +#define arch_dma_alloc_attrs arch_dma_alloc_attrs +#define HAVE_ARCH_DMA_SUPPORTED 1 extern int dma_supported(struct device *hwdev, u64 mask); -extern int dma_set_mask(struct device *dev, u64 mask); + +#include <asm-generic/dma-mapping-common.h> extern void *dma_generic_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, gfp_t flag, @@ -125,16 +113,4 @@ static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp) return gfp; } -#define dma_alloc_coherent(d,s,h,f) dma_alloc_attrs(d,s,h,f,NULL) - -void * -dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t gfp, struct dma_attrs *attrs); - -#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL) - -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 new file mode 100644 index 000000000000..b7a1ab865d68 --- /dev/null +++ b/arch/x86/include/asm/dwarf2.h @@ -0,0 +1,84 @@ +#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__) +#ifndef BUILD_VDSO + /* + * 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 + * vmlinux.lds.S gets changed so it doesn't discard .eh_frame. + */ + .cfi_sections .debug_frame +#else + /* + * For the vDSO, emit both runtime unwind information and debug + * symbols for the .dbg file. + */ + .cfi_sections .eh_frame, .debug_frame +#endif +#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 + +#endif /* _ASM_X86_DWARF2_H */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 155162ea0e00..0010c78c4998 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -86,6 +86,18 @@ extern u64 asmlinkage efi_call(void *fp, ...); extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size, u32 type, u64 attribute); +#ifdef CONFIG_KASAN +/* + * CONFIG_KASAN may redefine memset to __memset. __memset function is present + * only in kernel binary. Since the EFI stub linked into a separate binary it + * doesn't have __memset(). So we should use standard memset from + * arch/x86/boot/compressed/string.c. The same applies to memcpy and memmove. + */ +#undef memcpy +#undef memset +#undef memmove +#endif + #endif /* CONFIG_X86_32 */ extern struct efi_scratch efi_scratch; @@ -93,6 +105,7 @@ extern void __init efi_set_executable(efi_memory_desc_t *md, bool executable); extern int __init efi_memblock_x86_reserve_range(void); extern pgd_t * __init efi_call_phys_prolog(void); extern void __init efi_call_phys_epilog(pgd_t *save_pgd); +extern void __init efi_print_memmap(void); extern void __init efi_unmap_memmap(void); extern void __init efi_memory_uc(u64 addr, unsigned long size); extern void __init efi_map_region(efi_memory_desc_t *md); diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index f161c189c27b..1514753fd435 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -78,7 +78,7 @@ typedef struct user_fxsr_struct elf_fpxregset_t; #ifdef CONFIG_X86_64 extern unsigned int vdso64_enabled; #endif -#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT) +#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) extern unsigned int vdso32_enabled; #endif @@ -171,11 +171,11 @@ do { \ static inline void elf_common_init(struct thread_struct *t, struct pt_regs *regs, const u16 ds) { - /* Commented-out registers are cleared in stub_execve */ - /*regs->ax = regs->bx =*/ regs->cx = regs->dx = 0; - regs->si = regs->di /*= regs->bp*/ = 0; + /* ax gets execve's return value. */ + /*regs->ax = */ regs->bx = regs->cx = regs->dx = 0; + regs->si = regs->di = regs->bp = 0; regs->r8 = regs->r9 = regs->r10 = regs->r11 = 0; - /*regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0;*/ + regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0; t->fs = t->gs = 0; t->fsindex = t->gsindex = 0; t->ds = t->es = ds; @@ -187,8 +187,8 @@ static inline void elf_common_init(struct thread_struct *t, #define COMPAT_ELF_PLAT_INIT(regs, load_addr) \ elf_common_init(¤t->thread, regs, __USER_DS) -void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp); -#define compat_start_thread start_thread_ia32 +void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp); +#define compat_start_thread compat_start_thread void set_personality_ia32(bool); #define COMPAT_SET_PERSONALITY(ex) \ @@ -328,7 +328,7 @@ else \ #define VDSO_ENTRY \ ((unsigned long)current->mm->context.vdso + \ - selected_vdso32->sym___kernel_vsyscall) + vdso_image_32.sym___kernel_vsyscall) struct linux_binprm; @@ -344,14 +344,9 @@ extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm, */ static inline int mmap_is_ia32(void) { -#ifdef CONFIG_X86_32 - return 1; -#endif -#ifdef CONFIG_IA32_EMULATION - if (test_thread_flag(TIF_ADDR32)) - return 1; -#endif - return 0; + return config_enabled(CONFIG_X86_32) || + (config_enabled(CONFIG_COMPAT) && + test_thread_flag(TIF_ADDR32)); } /* Do not change the values. See get_align_mask() */ diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index f80d70009ff8..6d7d0e52ed5a 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -19,7 +19,6 @@ #include <asm/acpi.h> #include <asm/apicdef.h> #include <asm/page.h> -#include <asm/pvclock.h> #ifdef CONFIG_X86_32 #include <linux/threads.h> #include <asm/kmap_types.h> @@ -72,10 +71,6 @@ enum fixed_addresses { #ifdef CONFIG_X86_VSYSCALL_EMULATION VSYSCALL_PAGE = (FIXADDR_TOP - VSYSCALL_ADDR) >> PAGE_SHIFT, #endif -#ifdef CONFIG_PARAVIRT_CLOCK - PVCLOCK_FIXMAP_BEGIN, - PVCLOCK_FIXMAP_END = PVCLOCK_FIXMAP_BEGIN+PVCLOCK_VSYSCALL_NR_PAGES-1, -#endif #endif FIX_DBGP_BASE, FIX_EARLYCON_MEM_BASE, diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 3c3550c3a4a3..0fd440df63f1 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -42,6 +42,7 @@ 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); +extern u64 fpu__get_supported_xfeatures_mask(void); /* * Debugging facility: @@ -224,18 +225,67 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu) #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) +#define XSTATE_OP(op, st, lmask, hmask, err) \ + asm volatile("1:" op "\n\t" \ + "xor %[err], %[err]\n" \ + "2:\n\t" \ + ".pushsection .fixup,\"ax\"\n\t" \ + "3: movl $-2,%[err]\n\t" \ + "jmp 2b\n\t" \ + ".popsection\n\t" \ + _ASM_EXTABLE(1b, 3b) \ + : [err] "=r" (err) \ + : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ + : "memory") + +/* + * If XSAVES is enabled, it replaces XSAVEOPT because it supports a 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. + * + * We use XSAVE as a fallback. + * + * The 661 label is defined in the ALTERNATIVE* macros as the address of the + * original instruction which gets replaced. We need to use it here as the + * address of the instruction where we might get an exception at. + */ +#define XSTATE_XSAVE(st, lmask, hmask, err) \ + asm volatile(ALTERNATIVE_2(XSAVE, \ + XSAVEOPT, X86_FEATURE_XSAVEOPT, \ + XSAVES, X86_FEATURE_XSAVES) \ + "\n" \ + "xor %[err], %[err]\n" \ + "3:\n" \ + ".pushsection .fixup,\"ax\"\n" \ + "4: movl $-2, %[err]\n" \ + "jmp 3b\n" \ + ".popsection\n" \ + _ASM_EXTABLE(661b, 4b) \ + : [err] "=r" (err) \ + : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ + : "memory") + +/* + * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact + * XSAVE area format. + */ +#define XSTATE_XRESTORE(st, lmask, hmask, err) \ + asm volatile(ALTERNATIVE(XRSTOR, \ + XRSTORS, X86_FEATURE_XSAVES) \ + "\n" \ + "xor %[err], %[err]\n" \ + "3:\n" \ + ".pushsection .fixup,\"ax\"\n" \ + "4: movl $-2, %[err]\n" \ + "jmp 3b\n" \ + ".popsection\n" \ + _ASM_EXTABLE(661b, 4b) \ + : [err] "=r" (err) \ + : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ + : "memory") /* * This function is called only during boot time when x86 caps are not set @@ -246,22 +296,14 @@ 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; + int err; 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"); + if (static_cpu_has_safe(X86_FEATURE_XSAVES)) + XSTATE_OP(XSAVES, xstate, lmask, hmask, err); else - asm volatile("1:"XSAVE"\n\t" - "2:\n\t" - xstate_fault(err) - : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) - : "memory"); + XSTATE_OP(XSAVE, xstate, lmask, hmask, err); /* We should never fault when copying to a kernel buffer: */ WARN_ON_FPU(err); @@ -276,22 +318,14 @@ 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; + int err; 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"); + if (static_cpu_has_safe(X86_FEATURE_XSAVES)) + XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); else - asm volatile("1:"XRSTOR"\n\t" - "2:\n\t" - xstate_fault(err) - : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) - : "memory"); + XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); /* We should never fault when copying from a kernel buffer: */ WARN_ON_FPU(err); @@ -305,33 +339,11 @@ static inline void copy_xregs_to_kernel(struct xregs_state *xstate) u64 mask = -1; u32 lmask = mask; u32 hmask = mask >> 32; - int err = 0; + int err; 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"); + XSTATE_XSAVE(xstate, lmask, hmask, err); /* We should never fault when copying to a kernel buffer: */ WARN_ON_FPU(err); @@ -344,23 +356,9 @@ static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask) { u32 lmask = mask; u32 hmask = mask >> 32; - int err = 0; + int err; - /* - * 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"); + XSTATE_XRESTORE(xstate, lmask, hmask, err); /* We should never fault when copying from a kernel buffer: */ WARN_ON_FPU(err); @@ -388,12 +386,10 @@ static inline int copy_xregs_to_user(struct xregs_state __user *buf) 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"); + stac(); + XSTATE_OP(XSAVE, buf, -1, -1, err); + clac(); + return err; } @@ -405,14 +401,12 @@ 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? */ + int err; + + stac(); + XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); + clac(); + return err; } diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h index 7358e9d61f1e..0e970d00dfcd 100644 --- a/arch/x86/include/asm/fpu/signal.h +++ b/arch/x86/include/asm/fpu/signal.h @@ -5,7 +5,7 @@ #define _ASM_X86_FPU_SIGNAL_H #ifdef CONFIG_X86_64 -# include <asm/sigcontext32.h> +# include <uapi/asm/sigcontext.h> # include <asm/user32.h> struct ksignal; int ia32_setup_rt_frame(int sig, struct ksignal *ksig, diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index c49c5173158e..1c6f6ac52ad0 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -95,63 +95,122 @@ struct swregs_state { /* * 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, +enum xfeature { + XFEATURE_FP, + XFEATURE_SSE, + /* + * Values above here are "legacy states". + * Those below are "extended states". + */ + XFEATURE_YMM, + XFEATURE_BNDREGS, + XFEATURE_BNDCSR, + XFEATURE_OPMASK, + XFEATURE_ZMM_Hi256, + XFEATURE_Hi16_ZMM, + + XFEATURE_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 XFEATURE_MASK_FP (1 << XFEATURE_FP) +#define XFEATURE_MASK_SSE (1 << XFEATURE_SSE) +#define XFEATURE_MASK_YMM (1 << XFEATURE_YMM) +#define XFEATURE_MASK_BNDREGS (1 << XFEATURE_BNDREGS) +#define XFEATURE_MASK_BNDCSR (1 << XFEATURE_BNDCSR) +#define XFEATURE_MASK_OPMASK (1 << XFEATURE_OPMASK) +#define XFEATURE_MASK_ZMM_Hi256 (1 << XFEATURE_ZMM_Hi256) +#define XFEATURE_MASK_Hi16_ZMM (1 << XFEATURE_Hi16_ZMM) + +#define XFEATURE_MASK_FPSSE (XFEATURE_MASK_FP | XFEATURE_MASK_SSE) +#define XFEATURE_MASK_AVX512 (XFEATURE_MASK_OPMASK \ + | XFEATURE_MASK_ZMM_Hi256 \ + | XFEATURE_MASK_Hi16_ZMM) + +#define FIRST_EXTENDED_XFEATURE XFEATURE_YMM -#define XSTATE_FPSSE (XSTATE_FP | XSTATE_SSE) -#define XSTATE_AVX512 (XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM) +struct reg_128_bit { + u8 regbytes[128/8]; +}; +struct reg_256_bit { + u8 regbytes[256/8]; +}; +struct reg_512_bit { + u8 regbytes[512/8]; +}; /* + * State component 2: + * * 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[]'. + * and are stored in 'struct fxregs_state::xmm_space[]' in the + * "legacy" area. * - * The high 128 bits are stored here: - * 16x 128 bits == 256 bytes. + * The high 128 bits are stored here. */ struct ymmh_struct { - u8 ymmh_space[256]; -}; - -/* We don't support LWP yet: */ -struct lwp_struct { - u8 reserved[128]; -}; + struct reg_128_bit hi_ymm[16]; +} __packed; /* Intel MPX support: */ -struct bndreg { + +struct mpx_bndreg { u64 lower_bound; u64 upper_bound; } __packed; +/* + * State component 3 is used for the 4 128-bit bounds registers + */ +struct mpx_bndreg_state { + struct mpx_bndreg bndreg[4]; +} __packed; -struct bndcsr { +/* + * State component 4 is used for the 64-bit user-mode MPX + * configuration register BNDCFGU and the 64-bit MPX status + * register BNDSTATUS. We call the pair "BNDCSR". + */ +struct mpx_bndcsr { u64 bndcfgu; u64 bndstatus; } __packed; -struct mpx_struct { - struct bndreg bndreg[4]; - struct bndcsr bndcsr; -}; +/* + * The BNDCSR state is padded out to be 64-bytes in size. + */ +struct mpx_bndcsr_state { + union { + struct mpx_bndcsr bndcsr; + u8 pad_to_64_bytes[64]; + }; +} __packed; + +/* AVX-512 Components: */ + +/* + * State component 5 is used for the 8 64-bit opmask registers + * k0-k7 (opmask state). + */ +struct avx_512_opmask_state { + u64 opmask_reg[8]; +} __packed; + +/* + * State component 6 is used for the upper 256 bits of the + * registers ZMM0-ZMM15. These 16 256-bit values are denoted + * ZMM0_H-ZMM15_H (ZMM_Hi256 state). + */ +struct avx_512_zmm_uppers_state { + struct reg_256_bit zmm_upper[16]; +} __packed; + +/* + * State component 7 is used for the 16 512-bit registers + * ZMM16-ZMM31 (Hi16_ZMM state). + */ +struct avx_512_hi16_state { + struct reg_512_bit hi16_zmm[16]; +} __packed; struct xstate_header { u64 xfeatures; @@ -159,22 +218,19 @@ struct xstate_header { 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. + * subsequent areas as defined by the xstate header. Not all CPUs + * support all the extensions, so the size of the extended area + * can vary quite a bit between CPUs. */ struct xregs_state { struct fxregs_state i387; struct xstate_header header; - u8 __reserved[XSTATE_RESERVE]; + u8 extended_state_area[0]; } __attribute__ ((packed, aligned (64))); /* @@ -182,7 +238,9 @@ struct xregs_state { * 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: + * member - which is the xsave area. The padding is there + * to ensure that statically-allocated task_structs (just + * the init_task today) have enough space. */ union fpregs_state { struct fregs_state fsave; diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 4656b25bb9a7..af30fdeb140d 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -6,7 +6,7 @@ #include <linux/uaccess.h> /* Bit 63 of XCR0 is reserved for future expansion */ -#define XSTATE_EXTEND_MASK (~(XSTATE_FPSSE | (1ULL << 63))) +#define XFEATURE_MASK_EXTEND (~(XFEATURE_MASK_FPSSE | (1ULL << 63))) #define XSTATE_CPUID 0x0000000d @@ -19,14 +19,19 @@ #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) +#define XFEATURE_MASK_LAZY (XFEATURE_MASK_FP | \ + XFEATURE_MASK_SSE) /* Supported features which require eager state saving */ -#define XSTATE_EAGER (XSTATE_BNDREGS | XSTATE_BNDCSR) +#define XFEATURE_MASK_EAGER (XFEATURE_MASK_BNDREGS | \ + XFEATURE_MASK_BNDCSR | \ + XFEATURE_MASK_YMM | \ + XFEATURE_MASK_OPMASK | \ + XFEATURE_MASK_ZMM_Hi256 | \ + XFEATURE_MASK_Hi16_ZMM) /* All currently supported features */ -#define XCNTXT_MASK (XSTATE_LAZY | XSTATE_EAGER) +#define XCNTXT_MASK (XFEATURE_MASK_LAZY | XFEATURE_MASK_EAGER) #ifdef CONFIG_X86_64 #define REX_PREFIX "0x48, " @@ -40,6 +45,7 @@ extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask); +void fpu__xstate_clear_all_cpu_caps(void); void *get_xsave_addr(struct xregs_state *xsave, int xstate); const void *get_xsave_field_ptr(int xstate_field); diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index f45acad3c4b6..24938852db30 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -3,9 +3,9 @@ #ifdef CONFIG_FUNCTION_TRACER #ifdef CC_USING_FENTRY -# define MCOUNT_ADDR ((long)(__fentry__)) +# define MCOUNT_ADDR ((unsigned long)(__fentry__)) #else -# define MCOUNT_ADDR ((long)(mcount)) +# define MCOUNT_ADDR ((unsigned long)(mcount)) #endif #define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */ diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h index 04e9d023168f..1c0b43724ce3 100644 --- a/arch/x86/include/asm/highmem.h +++ b/arch/x86/include/asm/highmem.h @@ -68,7 +68,6 @@ void *kmap_atomic(struct page *page); void __kunmap_atomic(void *kvaddr); void *kmap_atomic_pfn(unsigned long pfn); void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot); -struct page *kmap_atomic_to_page(void *ptr); #define flush_cache_kmaps() do { } while (0) diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h index 5fa9fb0f8809..cc285ec4b2c1 100644 --- a/arch/x86/include/asm/hpet.h +++ b/arch/x86/include/asm/hpet.h @@ -63,10 +63,10 @@ /* hpet memory map physical address */ extern unsigned long hpet_address; extern unsigned long force_hpet_address; -extern int boot_hpet_disable; +extern bool boot_hpet_disable; extern u8 hpet_blockid; -extern int hpet_force_user; -extern u8 hpet_msi_disable; +extern bool hpet_force_user; +extern bool hpet_msi_disable; extern int is_hpet_enabled(void); extern int hpet_enable(void); extern void hpet_disable(void); diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 6615032e19c8..1815b736269d 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -130,6 +130,11 @@ struct irq_alloc_info { char *uv_name; }; #endif +#if IS_ENABLED(CONFIG_VMD) + struct { + struct msi_desc *desc; + }; +#endif }; }; @@ -182,10 +187,10 @@ extern char irq_entries_start[]; #define trace_irq_entries_start irq_entries_start #endif -#define VECTOR_UNDEFINED (-1) -#define VECTOR_RETRIGGERED (-2) +#define VECTOR_UNUSED NULL +#define VECTOR_RETRIGGERED ((void *)~0UL) -typedef int vector_irq_t[NR_VECTORS]; +typedef struct irq_desc* vector_irq_t[NR_VECTORS]; DECLARE_PER_CPU(vector_irq_t, vector_irq); #endif /* !ASSEMBLY_ */ diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h index ccffa53750a8..39bcefc20de7 100644 --- a/arch/x86/include/asm/i8259.h +++ b/arch/x86/include/asm/i8259.h @@ -60,6 +60,7 @@ struct legacy_pic { void (*mask_all)(void); void (*restore_mask)(void); void (*init)(int auto_eoi); + int (*probe)(void); int (*irq_pending)(unsigned int irq); void (*make_irq)(unsigned int irq); }; diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h index d0e8e0141041..a9bdf5569ab3 100644 --- a/arch/x86/include/asm/ia32.h +++ b/arch/x86/include/asm/ia32.h @@ -10,7 +10,7 @@ * 32 bit structures for IA32 support. */ -#include <asm/sigcontext32.h> +#include <uapi/asm/sigcontext.h> /* signal.h */ @@ -18,16 +18,7 @@ struct ucontext_ia32 { unsigned int uc_flags; unsigned int uc_link; compat_stack_t uc_stack; - struct sigcontext_ia32 uc_mcontext; - compat_sigset_t uc_sigmask; /* mask last for extensibility */ -}; - -struct ucontext_x32 { - unsigned int uc_flags; - unsigned int uc_link; - compat_stack_t uc_stack; - unsigned int uc__pad0; /* needed for alignment */ - struct sigcontext uc_mcontext; /* the 64-bit sigcontext type */ + struct sigcontext_32 uc_mcontext; compat_sigset_t uc_sigmask; /* mask last for extensibility */ }; diff --git a/arch/x86/include/asm/intel_pt.h b/arch/x86/include/asm/intel_pt.h new file mode 100644 index 000000000000..e1a411786bf5 --- /dev/null +++ b/arch/x86/include/asm/intel_pt.h @@ -0,0 +1,10 @@ +#ifndef _ASM_X86_INTEL_PT_H +#define _ASM_X86_INTEL_PT_H + +#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) +void cpu_emergency_stop_pt(void); +#else +static inline void cpu_emergency_stop_pt(void) {} +#endif + +#endif /* _ASM_X86_INTEL_PT_H */ diff --git a/arch/x86/include/asm/intel_punit_ipc.h b/arch/x86/include/asm/intel_punit_ipc.h new file mode 100644 index 000000000000..201eb9dce595 --- /dev/null +++ b/arch/x86/include/asm/intel_punit_ipc.h @@ -0,0 +1,101 @@ +#ifndef _ASM_X86_INTEL_PUNIT_IPC_H_ +#define _ASM_X86_INTEL_PUNIT_IPC_H_ + +/* + * Three types of 8bit P-Unit IPC commands are supported, + * bit[7:6]: [00]: BIOS; [01]: GTD; [10]: ISPD. + */ +typedef enum { + BIOS_IPC = 0, + GTDRIVER_IPC, + ISPDRIVER_IPC, + RESERVED_IPC, +} IPC_TYPE; + +#define IPC_TYPE_OFFSET 6 +#define IPC_PUNIT_BIOS_CMD_BASE (BIOS_IPC << IPC_TYPE_OFFSET) +#define IPC_PUNIT_GTD_CMD_BASE (GTDDRIVER_IPC << IPC_TYPE_OFFSET) +#define IPC_PUNIT_ISPD_CMD_BASE (ISPDRIVER_IPC << IPC_TYPE_OFFSET) +#define IPC_PUNIT_CMD_TYPE_MASK (RESERVED_IPC << IPC_TYPE_OFFSET) + +/* BIOS => Pcode commands */ +#define IPC_PUNIT_BIOS_ZERO (IPC_PUNIT_BIOS_CMD_BASE | 0x00) +#define IPC_PUNIT_BIOS_VR_INTERFACE (IPC_PUNIT_BIOS_CMD_BASE | 0x01) +#define IPC_PUNIT_BIOS_READ_PCS (IPC_PUNIT_BIOS_CMD_BASE | 0x02) +#define IPC_PUNIT_BIOS_WRITE_PCS (IPC_PUNIT_BIOS_CMD_BASE | 0x03) +#define IPC_PUNIT_BIOS_READ_PCU_CONFIG (IPC_PUNIT_BIOS_CMD_BASE | 0x04) +#define IPC_PUNIT_BIOS_WRITE_PCU_CONFIG (IPC_PUNIT_BIOS_CMD_BASE | 0x05) +#define IPC_PUNIT_BIOS_READ_PL1_SETTING (IPC_PUNIT_BIOS_CMD_BASE | 0x06) +#define IPC_PUNIT_BIOS_WRITE_PL1_SETTING (IPC_PUNIT_BIOS_CMD_BASE | 0x07) +#define IPC_PUNIT_BIOS_TRIGGER_VDD_RAM (IPC_PUNIT_BIOS_CMD_BASE | 0x08) +#define IPC_PUNIT_BIOS_READ_TELE_INFO (IPC_PUNIT_BIOS_CMD_BASE | 0x09) +#define IPC_PUNIT_BIOS_READ_TELE_TRACE_CTRL (IPC_PUNIT_BIOS_CMD_BASE | 0x0a) +#define IPC_PUNIT_BIOS_WRITE_TELE_TRACE_CTRL (IPC_PUNIT_BIOS_CMD_BASE | 0x0b) +#define IPC_PUNIT_BIOS_READ_TELE_EVENT_CTRL (IPC_PUNIT_BIOS_CMD_BASE | 0x0c) +#define IPC_PUNIT_BIOS_WRITE_TELE_EVENT_CTRL (IPC_PUNIT_BIOS_CMD_BASE | 0x0d) +#define IPC_PUNIT_BIOS_READ_TELE_TRACE (IPC_PUNIT_BIOS_CMD_BASE | 0x0e) +#define IPC_PUNIT_BIOS_WRITE_TELE_TRACE (IPC_PUNIT_BIOS_CMD_BASE | 0x0f) +#define IPC_PUNIT_BIOS_READ_TELE_EVENT (IPC_PUNIT_BIOS_CMD_BASE | 0x10) +#define IPC_PUNIT_BIOS_WRITE_TELE_EVENT (IPC_PUNIT_BIOS_CMD_BASE | 0x11) +#define IPC_PUNIT_BIOS_READ_MODULE_TEMP (IPC_PUNIT_BIOS_CMD_BASE | 0x12) +#define IPC_PUNIT_BIOS_RESERVED (IPC_PUNIT_BIOS_CMD_BASE | 0x13) +#define IPC_PUNIT_BIOS_READ_VOLTAGE_OVER (IPC_PUNIT_BIOS_CMD_BASE | 0x14) +#define IPC_PUNIT_BIOS_WRITE_VOLTAGE_OVER (IPC_PUNIT_BIOS_CMD_BASE | 0x15) +#define IPC_PUNIT_BIOS_READ_RATIO_OVER (IPC_PUNIT_BIOS_CMD_BASE | 0x16) +#define IPC_PUNIT_BIOS_WRITE_RATIO_OVER (IPC_PUNIT_BIOS_CMD_BASE | 0x17) +#define IPC_PUNIT_BIOS_READ_VF_GL_CTRL (IPC_PUNIT_BIOS_CMD_BASE | 0x18) +#define IPC_PUNIT_BIOS_WRITE_VF_GL_CTRL (IPC_PUNIT_BIOS_CMD_BASE | 0x19) +#define IPC_PUNIT_BIOS_READ_FM_SOC_TEMP_THRESH (IPC_PUNIT_BIOS_CMD_BASE | 0x1a) +#define IPC_PUNIT_BIOS_WRITE_FM_SOC_TEMP_THRESH (IPC_PUNIT_BIOS_CMD_BASE | 0x1b) + +/* GT Driver => Pcode commands */ +#define IPC_PUNIT_GTD_ZERO (IPC_PUNIT_GTD_CMD_BASE | 0x00) +#define IPC_PUNIT_GTD_CONFIG (IPC_PUNIT_GTD_CMD_BASE | 0x01) +#define IPC_PUNIT_GTD_READ_ICCP_LIC_CDYN_SCAL (IPC_PUNIT_GTD_CMD_BASE | 0x02) +#define IPC_PUNIT_GTD_WRITE_ICCP_LIC_CDYN_SCAL (IPC_PUNIT_GTD_CMD_BASE | 0x03) +#define IPC_PUNIT_GTD_GET_WM_VAL (IPC_PUNIT_GTD_CMD_BASE | 0x06) +#define IPC_PUNIT_GTD_WRITE_CONFIG_WISHREQ (IPC_PUNIT_GTD_CMD_BASE | 0x07) +#define IPC_PUNIT_GTD_READ_REQ_DUTY_CYCLE (IPC_PUNIT_GTD_CMD_BASE | 0x16) +#define IPC_PUNIT_GTD_DIS_VOL_FREQ_CHG_REQUEST (IPC_PUNIT_GTD_CMD_BASE | 0x17) +#define IPC_PUNIT_GTD_DYNA_DUTY_CYCLE_CTRL (IPC_PUNIT_GTD_CMD_BASE | 0x1a) +#define IPC_PUNIT_GTD_DYNA_DUTY_CYCLE_TUNING (IPC_PUNIT_GTD_CMD_BASE | 0x1c) + +/* ISP Driver => Pcode commands */ +#define IPC_PUNIT_ISPD_ZERO (IPC_PUNIT_ISPD_CMD_BASE | 0x00) +#define IPC_PUNIT_ISPD_CONFIG (IPC_PUNIT_ISPD_CMD_BASE | 0x01) +#define IPC_PUNIT_ISPD_GET_ISP_LTR_VAL (IPC_PUNIT_ISPD_CMD_BASE | 0x02) +#define IPC_PUNIT_ISPD_ACCESS_IU_FREQ_BOUNDS (IPC_PUNIT_ISPD_CMD_BASE | 0x03) +#define IPC_PUNIT_ISPD_READ_CDYN_LEVEL (IPC_PUNIT_ISPD_CMD_BASE | 0x04) +#define IPC_PUNIT_ISPD_WRITE_CDYN_LEVEL (IPC_PUNIT_ISPD_CMD_BASE | 0x05) + +/* Error codes */ +#define IPC_PUNIT_ERR_SUCCESS 0 +#define IPC_PUNIT_ERR_INVALID_CMD 1 +#define IPC_PUNIT_ERR_INVALID_PARAMETER 2 +#define IPC_PUNIT_ERR_CMD_TIMEOUT 3 +#define IPC_PUNIT_ERR_CMD_LOCKED 4 +#define IPC_PUNIT_ERR_INVALID_VR_ID 5 +#define IPC_PUNIT_ERR_VR_ERR 6 + +#if IS_ENABLED(CONFIG_INTEL_PUNIT_IPC) + +int intel_punit_ipc_simple_command(int cmd, int para1, int para2); +int intel_punit_ipc_command(u32 cmd, u32 para1, u32 para2, u32 *in, u32 *out); + +#else + +static inline int intel_punit_ipc_simple_command(int cmd, + int para1, int para2) +{ + return -ENODEV; +} + +static inline int intel_punit_ipc_command(u32 cmd, u32 para1, u32 para2, + u32 *in, u32 *out) +{ + return -ENODEV; +} + +#endif /* CONFIG_INTEL_PUNIT_IPC */ + +#endif diff --git a/arch/x86/include/asm/intel_telemetry.h b/arch/x86/include/asm/intel_telemetry.h new file mode 100644 index 000000000000..ed65fe701de5 --- /dev/null +++ b/arch/x86/include/asm/intel_telemetry.h @@ -0,0 +1,147 @@ +/* + * Intel SOC Telemetry Driver Header File + * Copyright (C) 2015, Intel Corporation. + * All Rights Reserved. + * + * 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. + * + */ +#ifndef INTEL_TELEMETRY_H +#define INTEL_TELEMETRY_H + +#define TELEM_MAX_EVENTS_SRAM 28 +#define TELEM_MAX_OS_ALLOCATED_EVENTS 20 + +enum telemetry_unit { + TELEM_PSS = 0, + TELEM_IOSS, + TELEM_UNIT_NONE +}; + +struct telemetry_evtlog { + u32 telem_evtid; + u64 telem_evtlog; +}; + +struct telemetry_evtconfig { + /* Array of Event-IDs to Enable */ + u32 *evtmap; + + /* Number of Events (<29) in evtmap */ + u8 num_evts; + + /* Sampling period */ + u8 period; +}; + +struct telemetry_evtmap { + const char *name; + u32 evt_id; +}; + +struct telemetry_unit_config { + struct telemetry_evtmap *telem_evts; + void __iomem *regmap; + u32 ssram_base_addr; + u8 ssram_evts_used; + u8 curr_period; + u8 max_period; + u8 min_period; + u32 ssram_size; + +}; + +struct telemetry_plt_config { + struct telemetry_unit_config pss_config; + struct telemetry_unit_config ioss_config; + struct mutex telem_trace_lock; + struct mutex telem_lock; + bool telem_in_use; +}; + +struct telemetry_core_ops { + int (*get_sampling_period)(u8 *pss_min_period, u8 *pss_max_period, + u8 *ioss_min_period, u8 *ioss_max_period); + + int (*get_eventconfig)(struct telemetry_evtconfig *pss_evtconfig, + struct telemetry_evtconfig *ioss_evtconfig, + int pss_len, int ioss_len); + + int (*update_events)(struct telemetry_evtconfig pss_evtconfig, + struct telemetry_evtconfig ioss_evtconfig); + + int (*set_sampling_period)(u8 pss_period, u8 ioss_period); + + int (*get_trace_verbosity)(enum telemetry_unit telem_unit, + u32 *verbosity); + + int (*set_trace_verbosity)(enum telemetry_unit telem_unit, + u32 verbosity); + + int (*raw_read_eventlog)(enum telemetry_unit telem_unit, + struct telemetry_evtlog *evtlog, + int len, int log_all_evts); + + int (*read_eventlog)(enum telemetry_unit telem_unit, + struct telemetry_evtlog *evtlog, + int len, int log_all_evts); + + int (*add_events)(u8 num_pss_evts, u8 num_ioss_evts, + u32 *pss_evtmap, u32 *ioss_evtmap); + + int (*reset_events)(void); +}; + +int telemetry_set_pltdata(struct telemetry_core_ops *ops, + struct telemetry_plt_config *pltconfig); + +int telemetry_clear_pltdata(void); + +int telemetry_pltconfig_valid(void); + +int telemetry_get_evtname(enum telemetry_unit telem_unit, + const char **name, int len); + +int telemetry_update_events(struct telemetry_evtconfig pss_evtconfig, + struct telemetry_evtconfig ioss_evtconfig); + +int telemetry_add_events(u8 num_pss_evts, u8 num_ioss_evts, + u32 *pss_evtmap, u32 *ioss_evtmap); + +int telemetry_reset_events(void); + +int telemetry_get_eventconfig(struct telemetry_evtconfig *pss_config, + struct telemetry_evtconfig *ioss_config, + int pss_len, int ioss_len); + +int telemetry_read_events(enum telemetry_unit telem_unit, + struct telemetry_evtlog *evtlog, int len); + +int telemetry_raw_read_events(enum telemetry_unit telem_unit, + struct telemetry_evtlog *evtlog, int len); + +int telemetry_read_eventlog(enum telemetry_unit telem_unit, + struct telemetry_evtlog *evtlog, int len); + +int telemetry_raw_read_eventlog(enum telemetry_unit telem_unit, + struct telemetry_evtlog *evtlog, int len); + +int telemetry_get_sampling_period(u8 *pss_min_period, u8 *pss_max_period, + u8 *ioss_min_period, u8 *ioss_max_period); + +int telemetry_set_sampling_period(u8 pss_period, u8 ioss_period); + +int telemetry_set_trace_verbosity(enum telemetry_unit telem_unit, + u32 verbosity); + +int telemetry_get_trace_verbosity(enum telemetry_unit telem_unit, + u32 *verbosity); + +#endif /* INTEL_TELEMETRY_H */ diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index cc9c61bc1abe..de25aad07853 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -180,6 +180,8 @@ static inline unsigned int isa_virt_to_bus(volatile void *address) */ extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size); extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size); +#define ioremap_uc ioremap_uc + 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); @@ -248,12 +250,6 @@ 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); diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h index 57995f0596a6..b41ee164930a 100644 --- a/arch/x86/include/asm/iosf_mbi.h +++ b/arch/x86/include/asm/iosf_mbi.h @@ -1,5 +1,5 @@ /* - * iosf_mbi.h: Intel OnChip System Fabric MailBox access support + * Intel OnChip System Fabric MailBox access support */ #ifndef IOSF_MBI_SYMS_H @@ -16,6 +16,18 @@ #define MBI_MASK_LO 0x000000FF #define MBI_ENABLE 0xF0 +/* IOSF SB read/write opcodes */ +#define MBI_MMIO_READ 0x00 +#define MBI_MMIO_WRITE 0x01 +#define MBI_CFG_READ 0x04 +#define MBI_CFG_WRITE 0x05 +#define MBI_CR_READ 0x06 +#define MBI_CR_WRITE 0x07 +#define MBI_REG_READ 0x10 +#define MBI_REG_WRITE 0x11 +#define MBI_ESRAM_READ 0x12 +#define MBI_ESRAM_WRITE 0x13 + /* Baytrail available units */ #define BT_MBI_UNIT_AUNIT 0x00 #define BT_MBI_UNIT_SMC 0x01 @@ -28,50 +40,13 @@ #define BT_MBI_UNIT_SATA 0xA3 #define BT_MBI_UNIT_PCIE 0xA6 -/* Baytrail read/write opcodes */ -#define BT_MBI_AUNIT_READ 0x10 -#define BT_MBI_AUNIT_WRITE 0x11 -#define BT_MBI_SMC_READ 0x10 -#define BT_MBI_SMC_WRITE 0x11 -#define BT_MBI_CPU_READ 0x10 -#define BT_MBI_CPU_WRITE 0x11 -#define BT_MBI_BUNIT_READ 0x10 -#define BT_MBI_BUNIT_WRITE 0x11 -#define BT_MBI_PMC_READ 0x06 -#define BT_MBI_PMC_WRITE 0x07 -#define BT_MBI_GFX_READ 0x00 -#define BT_MBI_GFX_WRITE 0x01 -#define BT_MBI_SMIO_READ 0x06 -#define BT_MBI_SMIO_WRITE 0x07 -#define BT_MBI_USB_READ 0x06 -#define BT_MBI_USB_WRITE 0x07 -#define BT_MBI_SATA_READ 0x00 -#define BT_MBI_SATA_WRITE 0x01 -#define BT_MBI_PCIE_READ 0x00 -#define BT_MBI_PCIE_WRITE 0x01 - /* Quark available units */ #define QRK_MBI_UNIT_HBA 0x00 -#define QRK_MBI_UNIT_HB 0x03 +#define QRK_MBI_UNIT_HB 0x03 #define QRK_MBI_UNIT_RMU 0x04 -#define QRK_MBI_UNIT_MM 0x05 -#define QRK_MBI_UNIT_MMESRAM 0x05 +#define QRK_MBI_UNIT_MM 0x05 #define QRK_MBI_UNIT_SOC 0x31 -/* Quark read/write opcodes */ -#define QRK_MBI_HBA_READ 0x10 -#define QRK_MBI_HBA_WRITE 0x11 -#define QRK_MBI_HB_READ 0x10 -#define QRK_MBI_HB_WRITE 0x11 -#define QRK_MBI_RMU_READ 0x10 -#define QRK_MBI_RMU_WRITE 0x11 -#define QRK_MBI_MM_READ 0x10 -#define QRK_MBI_MM_WRITE 0x11 -#define QRK_MBI_MMESRAM_READ 0x12 -#define QRK_MBI_MMESRAM_WRITE 0x13 -#define QRK_MBI_SOC_READ 0x06 -#define QRK_MBI_SOC_WRITE 0x07 - #if IS_ENABLED(CONFIG_IOSF_MBI) bool iosf_mbi_available(void); diff --git a/arch/x86/include/asm/ipi.h b/arch/x86/include/asm/ipi.h index 615fa9061b57..cfc9a0d2d07c 100644 --- a/arch/x86/include/asm/ipi.h +++ b/arch/x86/include/asm/ipi.h @@ -119,6 +119,8 @@ static inline void native_apic_mem_write(APIC_ICR, cfg); } +extern void default_send_IPI_single(int cpu, int vector); +extern void default_send_IPI_single_phys(int cpu, int vector); extern void default_send_IPI_mask_sequence_phys(const struct cpumask *mask, int vector); extern void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask, diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 8008d06581c7..881b4768644a 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -36,7 +36,9 @@ extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void)); extern void (*x86_platform_ipi_callback)(void); extern void native_init_IRQ(void); -extern bool handle_irq(unsigned irq, struct pt_regs *regs); + +struct irq_desc; +extern bool handle_irq(struct irq_desc *desc, struct pt_regs *regs); extern __visible unsigned int do_IRQ(struct pt_regs *regs); diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h index 046c7fb1ca43..a210eba2727c 100644 --- a/arch/x86/include/asm/irq_remapping.h +++ b/arch/x86/include/asm/irq_remapping.h @@ -33,6 +33,11 @@ enum irq_remap_cap { IRQ_POSTING_CAP = 0, }; +struct vcpu_data { + u64 pi_desc_addr; /* Physical address of PI Descriptor */ + u32 vector; /* Guest vector of the interrupt */ +}; + #ifdef CONFIG_IRQ_REMAP extern bool irq_remapping_cap(enum irq_remap_cap cap); @@ -58,11 +63,6 @@ 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; } diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 4c2d2eb2060a..6ca9fd6234e1 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -117,16 +117,6 @@ #define FPU_IRQ 13 -#define FIRST_VM86_IRQ 3 -#define LAST_VM86_IRQ 15 - -#ifndef __ASSEMBLY__ -static inline int invalid_vm86_irq(int irq) -{ - return irq < FIRST_VM86_IRQ || irq > LAST_VM86_IRQ; -} -#endif - /* * Size the maximum number of interrupts. * diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h index a4c1cf7e93f8..adc54c12cbd1 100644 --- a/arch/x86/include/asm/jump_label.h +++ b/arch/x86/include/asm/jump_label.h @@ -1,12 +1,18 @@ #ifndef _ASM_X86_JUMP_LABEL_H #define _ASM_X86_JUMP_LABEL_H -#ifndef __ASSEMBLY__ - -#include <linux/stringify.h> -#include <linux/types.h> -#include <asm/nops.h> -#include <asm/asm.h> +#ifndef HAVE_JUMP_LABEL +/* + * For better or for worse, if jump labels (the gcc extension) are missing, + * then the entire static branch patching infrastructure is compiled out. + * If that happens, the code in here will malfunction. Raise a compiler + * error instead. + * + * In theory, jump labels and the static branch patching infrastructure + * could be decoupled to fix this. + */ +#error asm/jump_label.h included on a non-jump-label kernel +#endif #define JUMP_LABEL_NOP_SIZE 5 @@ -16,15 +22,40 @@ # define STATIC_KEY_INIT_NOP GENERIC_NOP5_ATOMIC #endif -static __always_inline bool arch_static_branch(struct static_key *key) +#include <asm/asm.h> +#include <asm/nops.h> + +#ifndef __ASSEMBLY__ + +#include <linux/stringify.h> +#include <linux/types.h> + +static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { asm_volatile_goto("1:" ".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t" ".pushsection __jump_table, \"aw\" \n\t" _ASM_ALIGN "\n\t" - _ASM_PTR "1b, %l[l_yes], %c0 \n\t" + _ASM_PTR "1b, %l[l_yes], %c0 + %c1 \n\t" ".popsection \n\t" - : : "i" (key) : : l_yes); + : : "i" (key), "i" (branch) : : l_yes); + + return false; +l_yes: + return true; +} + +static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) +{ + asm_volatile_goto("1:" + ".byte 0xe9\n\t .long %l[l_yes] - 2f\n\t" + "2:\n\t" + ".pushsection __jump_table, \"aw\" \n\t" + _ASM_ALIGN "\n\t" + _ASM_PTR "1b, %l[l_yes], %c0 + %c1 \n\t" + ".popsection \n\t" + : : "i" (key), "i" (branch) : : l_yes); + return false; l_yes: return true; @@ -42,5 +73,40 @@ struct jump_entry { jump_label_t key; }; -#endif /* __ASSEMBLY__ */ +#else /* __ASSEMBLY__ */ + +.macro STATIC_JUMP_IF_TRUE target, key, def +.Lstatic_jump_\@: + .if \def + /* Equivalent to "jmp.d32 \target" */ + .byte 0xe9 + .long \target - .Lstatic_jump_after_\@ +.Lstatic_jump_after_\@: + .else + .byte STATIC_KEY_INIT_NOP + .endif + .pushsection __jump_table, "aw" + _ASM_ALIGN + _ASM_PTR .Lstatic_jump_\@, \target, \key + .popsection +.endm + +.macro STATIC_JUMP_IF_FALSE target, key, def +.Lstatic_jump_\@: + .if \def + .byte STATIC_KEY_INIT_NOP + .else + /* Equivalent to "jmp.d32 \target" */ + .byte 0xe9 + .long \target - .Lstatic_jump_after_\@ +.Lstatic_jump_after_\@: + .endif + .pushsection __jump_table, "aw" + _ASM_ALIGN + _ASM_PTR .Lstatic_jump_\@, \target, \key + 1 + .popsection +.endm + +#endif /* __ASSEMBLY__ */ + #endif diff --git a/arch/x86/include/asm/kasan.h b/arch/x86/include/asm/kasan.h index 74a2a8dc9908..1410b567ecde 100644 --- a/arch/x86/include/asm/kasan.h +++ b/arch/x86/include/asm/kasan.h @@ -1,6 +1,9 @@ #ifndef _ASM_X86_KASAN_H #define _ASM_X86_KASAN_H +#include <linux/const.h> +#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL) + /* * Compiler uses shadow offset assuming that addresses start * from 0. Kernel addresses don't start from 0, so shadow diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h index 32ce71375b21..e5f5dc9787d5 100644 --- a/arch/x86/include/asm/kdebug.h +++ b/arch/x86/include/asm/kdebug.h @@ -29,11 +29,5 @@ extern void show_trace(struct task_struct *t, struct pt_regs *regs, extern void __show_regs(struct pt_regs *regs, int all); extern unsigned long oops_begin(void); extern void oops_end(unsigned long, struct pt_regs *, int signr); -#ifdef CONFIG_KEXEC -extern int in_crash_kexec; -#else -/* no crash dump is ever in progress if no crash kernel can be kexec'd */ -#define in_crash_kexec 0 -#endif #endif /* _ASM_X86_KDEBUG_H */ diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index e16466ec473c..e9cd7befcb76 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -112,6 +112,16 @@ struct x86_emulate_ops { struct x86_exception *fault); /* + * read_phys: Read bytes of standard (non-emulated/special) memory. + * Used for descriptor reading. + * @addr: [IN ] Physical address from which to read. + * @val: [OUT] Value read from memory. + * @bytes: [IN ] Number of bytes to read from memory. + */ + int (*read_phys)(struct x86_emulate_ctxt *ctxt, unsigned long addr, + void *val, unsigned int bytes); + + /* * write_std: Write bytes of standard (non-emulated/special) memory. * Used for descriptor writing. * @addr: [IN ] Linear address to which to write. diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 49ec9038ec14..44adbb819041 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -24,6 +24,8 @@ #include <linux/perf_event.h> #include <linux/pvclock_gtod.h> #include <linux/clocksource.h> +#include <linux/irqbypass.h> +#include <linux/hyperv.h> #include <asm/pvclock-abi.h> #include <asm/desc.h> @@ -40,9 +42,35 @@ #define KVM_PIO_PAGE_OFFSET 1 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2 +#define KVM_HALT_POLL_NS_DEFAULT 500000 #define KVM_IRQCHIP_NUM_PINS KVM_IOAPIC_NUM_PINS +/* x86-specific vcpu->requests bit members */ +#define KVM_REQ_MIGRATE_TIMER 8 +#define KVM_REQ_REPORT_TPR_ACCESS 9 +#define KVM_REQ_TRIPLE_FAULT 10 +#define KVM_REQ_MMU_SYNC 11 +#define KVM_REQ_CLOCK_UPDATE 12 +#define KVM_REQ_DEACTIVATE_FPU 13 +#define KVM_REQ_EVENT 14 +#define KVM_REQ_APF_HALT 15 +#define KVM_REQ_STEAL_UPDATE 16 +#define KVM_REQ_NMI 17 +#define KVM_REQ_PMU 18 +#define KVM_REQ_PMI 19 +#define KVM_REQ_SMI 20 +#define KVM_REQ_MASTERCLOCK_UPDATE 21 +#define KVM_REQ_MCLOCK_INPROGRESS 22 +#define KVM_REQ_SCAN_IOAPIC 23 +#define KVM_REQ_GLOBAL_CLOCK_UPDATE 24 +#define KVM_REQ_APIC_PAGE_RELOAD 25 +#define KVM_REQ_HV_CRASH 26 +#define KVM_REQ_IOAPIC_EOI_EXIT 27 +#define KVM_REQ_HV_RESET 28 +#define KVM_REQ_HV_EXIT 29 +#define KVM_REQ_HV_STIMER 30 + #define CR0_RESERVED_BITS \ (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \ @@ -175,6 +203,8 @@ enum { */ #define KVM_APIC_PV_EOI_PENDING 1 +struct kvm_kernel_irq_routing_entry; + /* * We don't want allocation failures within the mmu code, so we preallocate * enough memory for a single page fault in a cache. @@ -209,6 +239,10 @@ union kvm_mmu_page_role { }; }; +struct kvm_rmap_head { + unsigned long val; +}; + struct kvm_mmu_page { struct list_head link; struct hlist_node hash_link; @@ -226,7 +260,7 @@ struct kvm_mmu_page { bool unsync; int root_count; /* Currently serving as active root */ unsigned int unsync_children; - unsigned long parent_ptes; /* Reverse mapping for parent_pte */ + struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */ /* The page is obsolete if mmu_valid_gen != kvm->arch.mmu_valid_gen. */ unsigned long mmu_valid_gen; @@ -252,6 +286,11 @@ struct kvm_pio_request { int size; }; +struct rsvd_bits_validate { + u64 rsvd_bits_mask[2][4]; + u64 bad_mt_xwr; +}; + /* * x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level * 32-bit). The kvm_mmu structure abstracts the details of the current mmu @@ -289,8 +328,15 @@ struct kvm_mmu { u64 *pae_root; u64 *lm_root; - u64 rsvd_bits_mask[2][4]; - u64 bad_mt_xwr; + + /* + * check zero bits on shadow page table entries, these + * bits include not only hardware reserved bits but also + * the bits spte never used. + */ + struct rsvd_bits_validate shadow_zero_check; + + struct rsvd_bits_validate guest_rsvd_check; /* * Bitmap: bit set = last pte in walk @@ -358,6 +404,40 @@ struct kvm_mtrr { struct list_head head; }; +/* Hyper-V SynIC timer */ +struct kvm_vcpu_hv_stimer { + struct hrtimer timer; + int index; + u64 config; + u64 count; + u64 exp_time; + struct hv_message msg; + bool msg_pending; +}; + +/* Hyper-V synthetic interrupt controller (SynIC)*/ +struct kvm_vcpu_hv_synic { + u64 version; + u64 control; + u64 msg_page; + u64 evt_page; + atomic64_t sint[HV_SYNIC_SINT_COUNT]; + atomic_t sint_to_gsi[HV_SYNIC_SINT_COUNT]; + DECLARE_BITMAP(auto_eoi_bitmap, 256); + DECLARE_BITMAP(vec_bitmap, 256); + bool active; +}; + +/* Hyper-V per vcpu emulation context */ +struct kvm_vcpu_hv { + u64 hv_vapic; + s64 runtime_offset; + struct kvm_vcpu_hv_synic synic; + struct kvm_hyperv_exit exit; + struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT]; + DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT); +}; + struct kvm_vcpu_arch { /* * rip and regs accesses must go through @@ -378,6 +458,8 @@ struct kvm_vcpu_arch { u64 efer; u64 apic_base; struct kvm_lapic *apic; /* kernel irqchip context */ + bool apicv_active; + DECLARE_BITMAP(ioapic_handled_vectors, 256); unsigned long apic_attention; int32_t apic_arb_prio; int mp_state; @@ -482,6 +564,7 @@ struct kvm_vcpu_arch { u32 virtual_tsc_mult; u32 virtual_tsc_khz; s64 ia32_tsc_adjust_msr; + u64 tsc_scaling_ratio; atomic_t nmi_queued; /* unprocessed asynchronous NMIs */ unsigned nmi_pending; /* NMI queued after currently running handler */ @@ -514,8 +597,7 @@ struct kvm_vcpu_arch { /* used for guest single stepping over the given code position */ unsigned long singlestep_rip; - /* fields used by HYPER-V emulation */ - u64 hv_vapic; + struct kvm_vcpu_hv hyperv; cpumask_var_t wbinvd_dirty_mask; @@ -556,6 +638,9 @@ struct kvm_vcpu_arch { struct { bool pv_unhalted; } pv; + + int pending_ioapic_eoi; + int pending_external_vector; }; struct kvm_lpage_info { @@ -563,7 +648,7 @@ struct kvm_lpage_info { }; struct kvm_arch_memory_slot { - unsigned long *rmap[KVM_NR_PAGE_SIZES]; + struct kvm_rmap_head *rmap[KVM_NR_PAGE_SIZES]; struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1]; }; @@ -586,6 +671,17 @@ struct kvm_apic_map { struct kvm_lapic *logical_map[16][16]; }; +/* Hyper-V emulation context */ +struct kvm_hv { + u64 hv_guest_os_id; + u64 hv_hypercall; + u64 hv_tsc_page; + + /* Hyper-v based guest crash (NT kernel bugcheck) parameters */ + u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS]; + u64 hv_crash_ctl; +}; + struct kvm_arch { unsigned int n_used_mmu_pages; unsigned int n_requested_mmu_pages; @@ -645,18 +741,19 @@ struct kvm_arch { /* reads protected by irq_srcu, writes by irq_lock */ struct hlist_head mask_notifier_list; - /* fields used by HYPER-V emulation */ - u64 hv_guest_os_id; - u64 hv_hypercall; - u64 hv_tsc_page; + struct kvm_hv hyperv; #ifdef CONFIG_KVM_MMU_AUDIT int audit_point; #endif bool boot_vcpu_runs_old_kvmclock; + u32 bsp_vcpu_id; u64 disabled_quirks; + + bool irqchip_split; + u8 nr_reserved_ioapic_pins; }; struct kvm_vm_stat { @@ -686,6 +783,7 @@ struct kvm_vcpu_stat { u32 nmi_window_exits; u32 halt_exits; u32 halt_successful_poll; + u32 halt_attempted_poll; u32 halt_wakeup; u32 request_irq_exits; u32 irq_exits; @@ -739,7 +837,7 @@ struct kvm_x86_ops { 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); + void (*update_bp_intercept)(struct kvm_vcpu *vcpu); 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); @@ -792,7 +890,8 @@ struct kvm_x86_ops { void (*enable_nmi_window)(struct kvm_vcpu *vcpu); void (*enable_irq_window)(struct kvm_vcpu *vcpu); void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr); - int (*vm_has_apicv)(struct kvm *kvm); + bool (*get_enable_apicv)(void); + void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr); void (*hwapic_isr_update)(struct kvm *kvm, int isr); void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); @@ -806,7 +905,7 @@ struct kvm_x86_ops { int (*get_lpage_level)(void); bool (*rdtscp_supported)(void); bool (*invpcid_supported)(void); - void (*adjust_tsc_offset)(struct kvm_vcpu *vcpu, s64 adjustment, bool host); + void (*adjust_tsc_offset_guest)(struct kvm_vcpu *vcpu, s64 adjustment); void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); @@ -814,11 +913,9 @@ struct kvm_x86_ops { bool (*has_wbinvd_exit)(void); - void (*set_tsc_khz)(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale); u64 (*read_tsc_offset)(struct kvm_vcpu *vcpu); void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); - u64 (*compute_tsc_offset)(struct kvm_vcpu *vcpu, u64 target_tsc); u64 (*read_l1_tsc)(struct kvm_vcpu *vcpu, u64 host_tsc); void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2); @@ -860,6 +957,20 @@ struct kvm_x86_ops { gfn_t offset, unsigned long mask); /* pmu operations of sub-arch */ const struct kvm_pmu_ops *pmu_ops; + + /* + * Architecture specific hooks for vCPU blocking due to + * HLT instruction. + * Returns for .pre_block(): + * - 0 means continue to block the vCPU. + * - 1 means we cannot block the vCPU since some event + * happens during this period, such as, 'ON' bit in + * posted-interrupts descriptor is set. + */ + int (*pre_block)(struct kvm_vcpu *vcpu); + void (*post_block)(struct kvm_vcpu *vcpu); + int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq, + uint32_t guest_irq, bool set); }; struct kvm_arch_async_pf { @@ -871,17 +982,6 @@ struct kvm_arch_async_pf { extern struct kvm_x86_ops *kvm_x86_ops; -static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, - s64 adjustment) -{ - kvm_x86_ops->adjust_tsc_offset(vcpu, adjustment, false); -} - -static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment) -{ - kvm_x86_ops->adjust_tsc_offset(vcpu, adjustment, true); -} - int kvm_mmu_module_init(void); void kvm_mmu_module_exit(void); @@ -934,10 +1034,12 @@ u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu); /* control of guest tsc rate supported? */ extern bool kvm_has_tsc_control; -/* minimum supported tsc_khz for guests */ -extern u32 kvm_min_guest_tsc_khz; /* maximum supported tsc_khz for guests */ extern u32 kvm_max_guest_tsc_khz; +/* number of bits of the fractional part of the TSC scaling ratio */ +extern u8 kvm_tsc_scaling_ratio_frac_bits; +/* maximum allowed value of TSC scaling ratio */ +extern u64 kvm_max_tsc_scaling_ratio; enum emulation_result { EMULATE_DONE, /* no further processing */ @@ -1044,6 +1146,8 @@ gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception); +void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu); + int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code, @@ -1183,9 +1287,15 @@ void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, void kvm_define_shared_msr(unsigned index, u32 msr); int kvm_set_shared_msr(unsigned index, u64 val, u64 mask); +u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc); +u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc); + unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu); bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip); +void kvm_make_mclock_inprogress_request(struct kvm *kvm); +void kvm_make_scan_ioapic_request(struct kvm *kvm); + void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work); void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, @@ -1199,9 +1309,18 @@ void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err); int kvm_is_in_guest(void); -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); +int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size); +int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size); +bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu); +bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu); + +bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq, + struct kvm_vcpu **dest_vcpu); + +void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e, + struct kvm_lapic_irq *irq); + +static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} +static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/lguest.h b/arch/x86/include/asm/lguest.h index 3bbc07a57a31..73d0c9b92087 100644 --- a/arch/x86/include/asm/lguest.h +++ b/arch/x86/include/asm/lguest.h @@ -12,7 +12,9 @@ #define GUEST_PL 1 /* Page for Switcher text itself, then two pages per cpu */ -#define TOTAL_SWITCHER_PAGES (1 + 2 * nr_cpu_ids) +#define SWITCHER_TEXT_PAGES (1) +#define SWITCHER_STACK_PAGES (2 * nr_cpu_ids) +#define TOTAL_SWITCHER_PAGES (SWITCHER_TEXT_PAGES + SWITCHER_STACK_PAGES) /* Where we map the Switcher, in both Host and Guest. */ extern unsigned long switcher_addr; diff --git a/arch/x86/include/asm/math_emu.h b/arch/x86/include/asm/math_emu.h index 031f6266f425..0d9b14f60d2c 100644 --- a/arch/x86/include/asm/math_emu.h +++ b/arch/x86/include/asm/math_emu.h @@ -2,7 +2,6 @@ #define _ASM_X86_MATH_EMU_H #include <asm/ptrace.h> -#include <asm/vm86.h> /* This structure matches the layout of the data saved to the stack following a device-not-present interrupt, part of it saved @@ -10,9 +9,6 @@ */ struct math_emu_info { long ___orig_eip; - union { - struct pt_regs *regs; - struct kernel_vm86_regs *vm86; - }; + struct pt_regs *regs; }; #endif /* _ASM_X86_MATH_EMU_H */ diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 982dfc3679ad..2ea4527e462f 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -123,19 +123,27 @@ struct mca_config { }; struct mce_vendor_flags { - /* - * 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; + /* + * Indicates that overflow conditions are not fatal, when set. + */ + __u64 overflow_recov : 1, + + /* + * (AMD) SUCCOR stands for S/W UnCorrectable error COntainment and + * Recovery. It indicates support for data poisoning in HW and deferred + * error interrupts. + */ + succor : 1, + + /* + * (AMD) SMCA: This bit indicates support for Scalable MCA which expands + * the register space for each MCA bank and also increases number of + * banks. Also, to accommodate the new banks and registers, the MCA + * register space is moved to a new MSR range. + */ + smca : 1, + + __reserved_0 : 61; }; extern struct mce_vendor_flags mce_flags; @@ -151,10 +159,12 @@ extern int mce_p5_enabled; #ifdef CONFIG_X86_MCE int mcheck_init(void); void mcheck_cpu_init(struct cpuinfo_x86 *c); +void mcheck_cpu_clear(struct cpuinfo_x86 *c); void mcheck_vendor_init_severity(void); #else static inline int mcheck_init(void) { return 0; } static inline void mcheck_cpu_init(struct cpuinfo_x86 *c) {} +static inline void mcheck_cpu_clear(struct cpuinfo_x86 *c) {} static inline void mcheck_vendor_init_severity(void) {} #endif @@ -181,20 +191,18 @@ DECLARE_PER_CPU(struct device *, mce_device); #ifdef CONFIG_X86_MCE_INTEL void mce_intel_feature_init(struct cpuinfo_x86 *c); +void mce_intel_feature_clear(struct cpuinfo_x86 *c); 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 mce_intel_feature_clear(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 diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 9e6278c7140e..1e1b07a5a738 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -1,6 +1,7 @@ #ifndef _ASM_X86_MICROCODE_H #define _ASM_X86_MICROCODE_H +#include <asm/cpu.h> #include <linux/earlycpio.h> #define native_rdmsr(msr, val1, val2) \ @@ -27,7 +28,6 @@ struct cpu_signature { struct device; enum ucode_state { UCODE_ERROR, UCODE_OK, UCODE_NFOUND }; -extern bool dis_ucode_ldr; struct microcode_ops { enum ucode_state (*request_microcode_user) (int cpu, @@ -55,6 +55,12 @@ struct ucode_cpu_info { }; extern struct ucode_cpu_info ucode_cpu_info[]; +#ifdef CONFIG_MICROCODE +int __init microcode_init(void); +#else +static inline int __init microcode_init(void) { return 0; }; +#endif + #ifdef CONFIG_MICROCODE_INTEL extern struct microcode_ops * __init init_intel_microcode(void); #else @@ -75,7 +81,6 @@ static inline struct microcode_ops * __init init_amd_microcode(void) static inline void __exit exit_amd_microcode(void) {} #endif -#ifdef CONFIG_MICROCODE_EARLY #define MAX_UCODE_COUNT 128 #define QCHAR(a, b, c, d) ((a) + ((b) << 8) + ((c) << 16) + ((d) << 24)) @@ -91,14 +96,14 @@ static inline void __exit exit_amd_microcode(void) {} /* * In early loading microcode phase on BSP, boot_cpu_data is not set up yet. - * x86_vendor() gets vendor id for BSP. + * x86_cpuid_vendor() gets vendor id for BSP. * * In 32 bit AP case, accessing boot_cpu_data needs linear address. To simplify - * coding, we still use x86_vendor() to get vendor id for AP. + * coding, we still use x86_cpuid_vendor() to get vendor id for AP. * - * x86_vendor() gets vendor information directly from CPUID. + * x86_cpuid_vendor() gets vendor information directly from CPUID. */ -static inline int x86_vendor(void) +static inline int x86_cpuid_vendor(void) { u32 eax = 0x00000000; u32 ebx, ecx = 0, edx; @@ -114,58 +119,28 @@ static inline int x86_vendor(void) return X86_VENDOR_UNKNOWN; } -static inline unsigned int __x86_family(unsigned int sig) -{ - unsigned int x86; - - x86 = (sig >> 8) & 0xf; - - if (x86 == 0xf) - x86 += (sig >> 20) & 0xff; - - return x86; -} - -static inline unsigned int x86_family(void) +static inline unsigned int x86_cpuid_family(void) { u32 eax = 0x00000001; u32 ebx, ecx = 0, edx; native_cpuid(&eax, &ebx, &ecx, &edx); - return __x86_family(eax); -} - -static inline unsigned int x86_model(unsigned int sig) -{ - unsigned int x86, model; - - x86 = __x86_family(sig); - - model = (sig >> 4) & 0xf; - - if (x86 == 0x6 || x86 == 0xf) - model += ((sig >> 16) & 0xf) << 4; - - return model; + return x86_family(eax); } +#ifdef CONFIG_MICROCODE 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) {} -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; -} +static inline void __init load_ucode_bsp(void) { } +static inline void load_ucode_ap(void) { } +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 ac6d328977a6..adfc847a395e 100644 --- a/arch/x86/include/asm/microcode_amd.h +++ b/arch/x86/include/asm/microcode_amd.h @@ -64,7 +64,7 @@ extern enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, s #define PATCH_MAX_SIZE PAGE_SIZE extern u8 amd_ucode_patch[PATCH_MAX_SIZE]; -#ifdef CONFIG_MICROCODE_AMD_EARLY +#ifdef CONFIG_MICROCODE_AMD 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); @@ -76,4 +76,5 @@ static inline int __init save_microcode_in_initrd_amd(void) { return -EINVAL; } void reload_ucode_amd(void) {} #endif +extern bool check_current_patch_level(u32 *rev, bool early); #endif /* _ASM_X86_MICROCODE_AMD_H */ diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h index 7991c606125d..8559b0102ea1 100644 --- a/arch/x86/include/asm/microcode_intel.h +++ b/arch/x86/include/asm/microcode_intel.h @@ -57,7 +57,7 @@ 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 find_matching_signature(void *mc, unsigned int csig, int cpf); -#ifdef CONFIG_MICROCODE_INTEL_EARLY +#ifdef CONFIG_MICROCODE_INTEL extern void __init load_ucode_intel_bsp(void); extern void load_ucode_intel_ap(void); extern void show_ucode_info_early(void); @@ -71,13 +71,9 @@ static inline int __init save_microcode_in_initrd_intel(void) { return -EINVAL; static inline void reload_ucode_intel(void) {} #endif -#if defined(CONFIG_MICROCODE_INTEL_EARLY) && defined(CONFIG_HOTPLUG_CPU) +#ifdef CONFIG_HOTPLUG_CPU extern int save_mc_for_early(u8 *mc); #else -static inline int save_mc_for_early(u8 *mc) -{ - return 0; -} +static inline int save_mc_for_early(u8 *mc) { return 0; } #endif - #endif /* _ASM_X86_MICROCODE_INTEL_H */ diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 364d27481a52..55234d5e7160 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -9,7 +9,9 @@ * we put the segment information here. */ typedef struct { +#ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; +#endif #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 984abfe47edc..bfd9b2a35a0b 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -33,6 +33,7 @@ static inline void load_mm_cr4(struct mm_struct *mm) static inline void load_mm_cr4(struct mm_struct *mm) {} #endif +#ifdef CONFIG_MODIFY_LDT_SYSCALL /* * ldt_structs can be allocated, used, and freed, but they are never * modified while live. @@ -48,8 +49,23 @@ struct ldt_struct { int size; }; +/* + * Used for LDT copy/destruction. + */ +int init_new_context(struct task_struct *tsk, struct mm_struct *mm); +void destroy_context(struct mm_struct *mm); +#else /* CONFIG_MODIFY_LDT_SYSCALL */ +static inline int init_new_context(struct task_struct *tsk, + struct mm_struct *mm) +{ + return 0; +} +static inline void destroy_context(struct mm_struct *mm) {} +#endif + static inline void load_mm_ldt(struct mm_struct *mm) { +#ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; /* lockless_dereference synchronizes with smp_store_release */ @@ -73,17 +89,13 @@ static inline void load_mm_ldt(struct mm_struct *mm) set_ldt(ldt->entries, ldt->size); else clear_LDT(); +#else + clear_LDT(); +#endif DEBUG_LOCKS_WARN_ON(preemptible()); } -/* - * Used for LDT copy/destruction. - */ -int init_new_context(struct task_struct *tsk, struct mm_struct *mm); -void destroy_context(struct mm_struct *mm); - - static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) { #ifdef CONFIG_SMP @@ -104,8 +116,36 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, #endif cpumask_set_cpu(cpu, mm_cpumask(next)); - /* Re-load page tables */ + /* + * Re-load page tables. + * + * This logic has an ordering constraint: + * + * CPU 0: Write to a PTE for 'next' + * CPU 0: load bit 1 in mm_cpumask. if nonzero, send IPI. + * CPU 1: set bit 1 in next's mm_cpumask + * CPU 1: load from the PTE that CPU 0 writes (implicit) + * + * We need to prevent an outcome in which CPU 1 observes + * the new PTE value and CPU 0 observes bit 1 clear in + * mm_cpumask. (If that occurs, then the IPI will never + * be sent, and CPU 0's TLB will contain a stale entry.) + * + * The bad outcome can occur if either CPU's load is + * reordered before that CPU's store, so both CPUs must + * execute full barriers to prevent this from happening. + * + * Thus, switch_mm needs a full barrier between the + * store to mm_cpumask and any operation that could load + * from next->pgd. TLB fills are special and can happen + * due to instruction fetches or for no reason at all, + * and neither LOCK nor MFENCE orders them. + * Fortunately, load_cr3() is serializing and gives the + * ordering guarantee we need. + * + */ load_cr3(next->pgd); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); /* Stop flush ipis for the previous mm */ @@ -114,6 +154,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, /* Load per-mm CR4 state */ load_mm_cr4(next); +#ifdef CONFIG_MODIFY_LDT_SYSCALL /* * Load the LDT, if the LDT is different. * @@ -128,6 +169,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, */ if (unlikely(prev->context.ldt != next->context.ldt)) load_mm_ldt(next); +#endif } #ifdef CONFIG_SMP else { @@ -142,10 +184,14 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, * schedule, protecting us from simultaneous changes. */ cpumask_set_cpu(cpu, mm_cpumask(next)); + /* * We were in lazy tlb mode and leave_mm disabled * tlb flush IPI delivery. We must reload CR3 * to make sure to use no freed page tables. + * + * As above, load_cr3() is serializing and orders TLB + * fills with respect to the mm_cpumask write. */ load_cr3(next->pgd); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index c163215abb9a..aaf59b7da98a 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -7,6 +7,7 @@ struct ms_hyperv_info { u32 features; + u32 misc_features; u32 hints; }; @@ -20,4 +21,8 @@ void hyperv_vector_handler(struct pt_regs *regs); void hv_setup_vmbus_irq(void (*handler)(void)); void hv_remove_vmbus_irq(void); +void hv_setup_kexec_handler(void (*handler)(void)); +void hv_remove_kexec_handler(void); +void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs)); +void hv_remove_crash_handler(void); #endif diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h index 93724cc62177..eb4b09b41df5 100644 --- a/arch/x86/include/asm/msi.h +++ b/arch/x86/include/asm/msi.h @@ -1,7 +1,13 @@ #ifndef _ASM_X86_MSI_H #define _ASM_X86_MSI_H #include <asm/hw_irq.h> +#include <asm/irqdomain.h> typedef struct irq_alloc_info msi_alloc_info_t; +int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, + msi_alloc_info_t *arg); + +void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc); + #endif /* _ASM_X86_MSI_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 9ebc3d009373..b05402ef3b84 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -35,7 +35,7 @@ #define MSR_IA32_PERFCTR0 0x000000c1 #define MSR_IA32_PERFCTR1 0x000000c2 #define MSR_FSB_FREQ 0x000000cd -#define MSR_NHM_PLATFORM_INFO 0x000000ce +#define MSR_PLATFORM_INFO 0x000000ce #define MSR_NHM_SNB_PKG_CST_CFG_CTL 0x000000e2 #define NHM_C3_AUTO_DEMOTE (1UL << 25) @@ -44,7 +44,6 @@ #define SNB_C1_AUTO_UNDEMOTE (1UL << 27) #define SNB_C3_AUTO_UNDEMOTE (1UL << 28) -#define MSR_PLATFORM_INFO 0x000000ce #define MSR_MTRRcap 0x000000fe #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e @@ -73,6 +72,12 @@ #define MSR_LBR_CORE_FROM 0x00000040 #define MSR_LBR_CORE_TO 0x00000060 +#define MSR_LBR_INFO_0 0x00000dc0 /* ... 0xddf for _31 */ +#define LBR_INFO_MISPRED BIT_ULL(63) +#define LBR_INFO_IN_TX BIT_ULL(62) +#define LBR_INFO_ABORT BIT_ULL(61) +#define LBR_INFO_CYCLES 0xffff + #define MSR_IA32_PEBS_ENABLE 0x000003f1 #define MSR_IA32_DS_AREA 0x00000600 #define MSR_IA32_PERF_CAPABILITIES 0x00000345 @@ -80,13 +85,21 @@ #define MSR_IA32_RTIT_CTL 0x00000570 #define RTIT_CTL_TRACEEN BIT(0) +#define RTIT_CTL_CYCLEACC BIT(1) #define RTIT_CTL_OS BIT(2) #define RTIT_CTL_USR BIT(3) #define RTIT_CTL_CR3EN BIT(7) #define RTIT_CTL_TOPA BIT(8) +#define RTIT_CTL_MTC_EN BIT(9) #define RTIT_CTL_TSC_EN BIT(10) #define RTIT_CTL_DISRETC BIT(11) #define RTIT_CTL_BRANCH_EN BIT(13) +#define RTIT_CTL_MTC_RANGE_OFFSET 14 +#define RTIT_CTL_MTC_RANGE (0x0full << RTIT_CTL_MTC_RANGE_OFFSET) +#define RTIT_CTL_CYC_THRESH_OFFSET 19 +#define RTIT_CTL_CYC_THRESH (0x0full << RTIT_CTL_CYC_THRESH_OFFSET) +#define RTIT_CTL_PSB_FREQ_OFFSET 24 +#define RTIT_CTL_PSB_FREQ (0x0full << RTIT_CTL_PSB_FREQ_OFFSET) #define MSR_IA32_RTIT_STATUS 0x00000571 #define RTIT_STATUS_CONTEXTEN BIT(1) #define RTIT_STATUS_TRIGGEREN BIT(2) @@ -127,6 +140,8 @@ #define DEBUGCTLMSR_BTS_OFF_USR (1UL << 10) #define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI (1UL << 11) +#define MSR_PEBS_FRONTEND 0x000003f7 + #define MSR_IA32_POWER_CTL 0x000001fc #define MSR_IA32_MC0_CTL 0x00000400 @@ -170,6 +185,12 @@ #define MSR_PP1_ENERGY_STATUS 0x00000641 #define MSR_PP1_POLICY 0x00000642 +#define MSR_CONFIG_TDP_NOMINAL 0x00000648 +#define MSR_CONFIG_TDP_LEVEL_1 0x00000649 +#define MSR_CONFIG_TDP_LEVEL_2 0x0000064A +#define MSR_CONFIG_TDP_CONTROL 0x0000064B +#define MSR_TURBO_ACTIVATION_RATIO 0x0000064C + #define MSR_PKG_WEIGHTED_CORE_C0_RES 0x00000658 #define MSR_PKG_ANY_CORE_C0_RES 0x00000659 #define MSR_PKG_ANY_GFXE_C0_RES 0x0000065A @@ -184,6 +205,13 @@ #define MSR_GFX_PERF_LIMIT_REASONS 0x000006B0 #define MSR_RING_PERF_LIMIT_REASONS 0x000006B1 +/* Config TDP MSRs */ +#define MSR_CONFIG_TDP_NOMINAL 0x00000648 +#define MSR_CONFIG_TDP_LEVEL1 0x00000649 +#define MSR_CONFIG_TDP_LEVEL2 0x0000064A +#define MSR_CONFIG_TDP_CONTROL 0x0000064B +#define MSR_TURBO_ACTIVATION_RATIO 0x0000064C + /* Hardware P state interface */ #define MSR_PPERF 0x0000064e #define MSR_PERF_LIMIT_REASONS 0x0000064f @@ -293,6 +321,7 @@ #define MSR_F15H_PERF_CTR 0xc0010201 #define MSR_F15H_NB_PERF_CTL 0xc0010240 #define MSR_F15H_NB_PERF_CTR 0xc0010241 +#define MSR_F15H_IC_CFG 0xc0011021 /* Fam 10h MSRs */ #define MSR_FAM10H_MMIO_CONF_BASE 0xc0010058 @@ -311,6 +340,7 @@ /* C1E active bits in int pending message */ #define K8_INTP_C1E_ACTIVE_MASK 0x18000000 #define MSR_K8_TSEG_ADDR 0xc0010112 +#define MSR_K8_TSEG_MASK 0xc0010113 #define K8_MTRRFIXRANGE_DRAM_ENABLE 0x00040000 /* MtrrFixDramEn bit */ #define K8_MTRRFIXRANGE_DRAM_MODIFY 0x00080000 /* MtrrFixDramModEn bit */ #define K8_MTRR_RDMEM_WRMEM_MASK 0x18181818 /* Mask: RdMem|WrMem */ diff --git a/arch/x86/include/asm/msr-trace.h b/arch/x86/include/asm/msr-trace.h new file mode 100644 index 000000000000..7567225747d8 --- /dev/null +++ b/arch/x86/include/asm/msr-trace.h @@ -0,0 +1,57 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM msr + +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE msr-trace + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH asm/ + +#if !defined(_TRACE_MSR_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_MSR_H + +#include <linux/tracepoint.h> + +/* + * Tracing for x86 model specific registers. Directly maps to the + * RDMSR/WRMSR instructions. + */ + +DECLARE_EVENT_CLASS(msr_trace_class, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed), + TP_STRUCT__entry( + __field( unsigned, msr ) + __field( u64, val ) + __field( int, failed ) + ), + TP_fast_assign( + __entry->msr = msr; + __entry->val = val; + __entry->failed = failed; + ), + TP_printk("%x, value %llx%s", + __entry->msr, + __entry->val, + __entry->failed ? " #GP" : "") +); + +DEFINE_EVENT(msr_trace_class, read_msr, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed) +); + +DEFINE_EVENT(msr_trace_class, write_msr, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed) +); + +DEFINE_EVENT(msr_trace_class, rdpmc, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed) +); + +#endif /* _TRACE_MSR_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index e6a707eb5081..93fb7c1cffda 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -32,6 +32,16 @@ struct msr_regs_info { int err; }; +struct saved_msr { + bool valid; + struct msr_info info; +}; + +struct saved_msrs { + unsigned int num; + struct saved_msr *array; +}; + static inline unsigned long long native_read_tscp(unsigned int *aux) { unsigned long low, high; @@ -47,22 +57,44 @@ static inline unsigned long long native_read_tscp(unsigned int *aux) * it means rax *or* rdx. */ #ifdef CONFIG_X86_64 -#define DECLARE_ARGS(val, low, high) unsigned low, high -#define EAX_EDX_VAL(val, low, high) ((low) | ((u64)(high) << 32)) -#define EAX_EDX_ARGS(val, low, high) "a" (low), "d" (high) +/* Using 64-bit values saves one instruction clearing the high half of low */ +#define DECLARE_ARGS(val, low, high) unsigned long low, high +#define EAX_EDX_VAL(val, low, high) ((low) | (high) << 32) #define EAX_EDX_RET(val, low, high) "=a" (low), "=d" (high) #else #define DECLARE_ARGS(val, low, high) unsigned long long val #define EAX_EDX_VAL(val, low, high) (val) -#define EAX_EDX_ARGS(val, low, high) "A" (val) #define EAX_EDX_RET(val, low, high) "=A" (val) #endif +#ifdef CONFIG_TRACEPOINTS +/* + * Be very careful with includes. This header is prone to include loops. + */ +#include <asm/atomic.h> +#include <linux/tracepoint-defs.h> + +extern struct tracepoint __tracepoint_read_msr; +extern struct tracepoint __tracepoint_write_msr; +extern struct tracepoint __tracepoint_rdpmc; +#define msr_tracepoint_active(t) static_key_false(&(t).key) +extern void do_trace_write_msr(unsigned msr, u64 val, int failed); +extern void do_trace_read_msr(unsigned msr, u64 val, int failed); +extern void do_trace_rdpmc(unsigned msr, u64 val, int failed); +#else +#define msr_tracepoint_active(t) false +static inline void do_trace_write_msr(unsigned msr, u64 val, int failed) {} +static inline void do_trace_read_msr(unsigned msr, u64 val, int failed) {} +static inline void do_trace_rdpmc(unsigned msr, u64 val, int failed) {} +#endif + static inline unsigned long long native_read_msr(unsigned int msr) { DECLARE_ARGS(val, low, high); asm volatile("rdmsr" : EAX_EDX_RET(val, low, high) : "c" (msr)); + if (msr_tracepoint_active(__tracepoint_read_msr)) + do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), 0); return EAX_EDX_VAL(val, low, high); } @@ -79,6 +111,8 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr, _ASM_EXTABLE(2b, 3b) : [err] "=r" (*err), EAX_EDX_RET(val, low, high) : "c" (msr), [fault] "i" (-EIO)); + if (msr_tracepoint_active(__tracepoint_read_msr)) + do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), *err); return EAX_EDX_VAL(val, low, high); } @@ -86,6 +120,8 @@ static inline void native_write_msr(unsigned int msr, unsigned low, unsigned high) { asm volatile("wrmsr" : : "c" (msr), "a"(low), "d" (high) : "memory"); + if (msr_tracepoint_active(__tracepoint_read_msr)) + do_trace_write_msr(msr, ((u64)high << 32 | low), 0); } /* Can be uninlined because referenced by paravirt */ @@ -103,15 +139,24 @@ notrace static inline int native_write_msr_safe(unsigned int msr, : "c" (msr), "0" (low), "d" (high), [fault] "i" (-EIO) : "memory"); + if (msr_tracepoint_active(__tracepoint_read_msr)) + do_trace_write_msr(msr, ((u64)high << 32 | low), err); return err; } -extern unsigned long long native_read_tsc(void); - extern int rdmsr_safe_regs(u32 regs[8]); extern int wrmsr_safe_regs(u32 regs[8]); -static __always_inline unsigned long long __native_read_tsc(void) +/** + * rdtsc() - returns the current TSC without ordering constraints + * + * rdtsc() returns the result of RDTSC as a 64-bit integer. The + * only ordering constraint it supplies is the ordering implied by + * "asm volatile": it will put the RDTSC in the place you expect. The + * CPU can and will speculatively execute that RDTSC, though, so the + * results can be non-monotonic if compared on different CPUs. + */ +static __always_inline unsigned long long rdtsc(void) { DECLARE_ARGS(val, low, high); @@ -120,11 +165,42 @@ static __always_inline unsigned long long __native_read_tsc(void) return EAX_EDX_VAL(val, low, high); } +/** + * rdtsc_ordered() - read the current TSC in program order + * + * rdtsc_ordered() returns the result of RDTSC as a 64-bit integer. + * It is ordered like a load to a global in-memory counter. It should + * be impossible to observe non-monotonic rdtsc_unordered() behavior + * across multiple CPUs as long as the TSC is synced. + */ +static __always_inline unsigned long long rdtsc_ordered(void) +{ + /* + * The RDTSC instruction is not ordered relative to memory + * access. The Intel SDM and the AMD APM are both vague on this + * point, but empirically an RDTSC instruction can be + * speculatively executed before prior loads. An RDTSC + * immediately after an appropriate barrier appears to be + * ordered as a normal load, that is, it provides the same + * ordering guarantees as reading from a global memory location + * that some other imaginary CPU is updating continuously with a + * time stamp. + */ + alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, + "lfence", X86_FEATURE_LFENCE_RDTSC); + return rdtsc(); +} + +/* Deprecated, keep it for a cycle for easier merging: */ +#define rdtscll(now) do { (now) = rdtsc_ordered(); } while (0) + static inline unsigned long long native_read_pmc(int counter) { DECLARE_ARGS(val, low, high); asm volatile("rdpmc" : EAX_EDX_RET(val, low, high) : "c" (counter)); + if (msr_tracepoint_active(__tracepoint_rdpmc)) + do_trace_rdpmc(counter, EAX_EDX_VAL(val, low, high), 0); return EAX_EDX_VAL(val, low, high); } @@ -153,8 +229,10 @@ static inline void wrmsr(unsigned msr, unsigned low, unsigned high) #define rdmsrl(msr, val) \ ((val) = native_read_msr((msr))) -#define wrmsrl(msr, val) \ - native_write_msr((msr), (u32)((u64)(val)), (u32)((u64)(val) >> 32)) +static inline void wrmsrl(unsigned msr, u64 val) +{ + native_write_msr(msr, (u32)(val & 0xffffffffULL), (u32)(val >> 32)); +} /* wrmsr with exception handling */ static inline int wrmsr_safe(unsigned msr, unsigned low, unsigned high) @@ -180,12 +258,6 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p) return err; } -#define rdtscl(low) \ - ((low) = (u32)__native_read_tsc()) - -#define rdtscll(val) \ - ((val) = __native_read_tsc()) - #define rdpmc(counter, low, high) \ do { \ u64 _l = native_read_pmc((counter)); \ @@ -195,15 +267,6 @@ do { \ #define rdpmcl(counter, val) ((val) = native_read_pmc(counter)) -#define rdtscp(low, high, aux) \ -do { \ - unsigned long long _val = native_read_tscp(&(aux)); \ - (low) = (u32)_val; \ - (high) = (u32)(_val >> 32); \ -} while (0) - -#define rdtscpll(val, aux) (val) = native_read_tscp(&(aux)) - #endif /* !CONFIG_PARAVIRT */ /* diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index 653dfa7662e1..c70689b5e5aa 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -14,6 +14,9 @@ #define CPUID5_ECX_INTERRUPT_BREAK 0x2 #define MWAIT_ECX_INTERRUPT_BREAK 0x1 +#define MWAITX_ECX_TIMER_ENABLE BIT(1) +#define MWAITX_MAX_LOOPS ((u32)-1) +#define MWAITX_DISABLE_CSTATES 0xf static inline void __monitor(const void *eax, unsigned long ecx, unsigned long edx) @@ -23,6 +26,14 @@ static inline void __monitor(const void *eax, unsigned long ecx, :: "a" (eax), "c" (ecx), "d"(edx)); } +static inline void __monitorx(const void *eax, unsigned long ecx, + unsigned long edx) +{ + /* "monitorx %eax, %ecx, %edx;" */ + asm volatile(".byte 0x0f, 0x01, 0xfa;" + :: "a" (eax), "c" (ecx), "d"(edx)); +} + static inline void __mwait(unsigned long eax, unsigned long ecx) { /* "mwait %eax, %ecx;" */ @@ -30,6 +41,40 @@ static inline void __mwait(unsigned long eax, unsigned long ecx) :: "a" (eax), "c" (ecx)); } +/* + * MWAITX allows for a timer expiration to get the core out a wait state in + * addition to the default MWAIT exit condition of a store appearing at a + * monitored virtual address. + * + * Registers: + * + * MWAITX ECX[1]: enable timer if set + * MWAITX EBX[31:0]: max wait time expressed in SW P0 clocks. The software P0 + * frequency is the same as the TSC frequency. + * + * Below is a comparison between MWAIT and MWAITX on AMD processors: + * + * MWAIT MWAITX + * opcode 0f 01 c9 | 0f 01 fb + * ECX[0] value of RFLAGS.IF seen by instruction + * ECX[1] unused/#GP if set | enable timer if set + * ECX[31:2] unused/#GP if set + * EAX unused (reserve for hint) + * EBX[31:0] unused | max wait time (P0 clocks) + * + * MONITOR MONITORX + * opcode 0f 01 c8 | 0f 01 fa + * EAX (logical) address to monitor + * ECX #GP if not zero + */ +static inline void __mwaitx(unsigned long eax, unsigned long ebx, + unsigned long ecx) +{ + /* "mwaitx %eax, %ebx, %ecx;" */ + asm volatile(".byte 0x0f, 0x01, 0xfb;" + :: "a" (eax), "b" (ebx), "c" (ecx)); +} + static inline void __sti_mwait(unsigned long eax, unsigned long ecx) { trace_hardirqs_on(); diff --git a/arch/x86/include/asm/numachip/numachip.h b/arch/x86/include/asm/numachip/numachip.h index 1c6f7f6212c1..c64373a2d731 100644 --- a/arch/x86/include/asm/numachip/numachip.h +++ b/arch/x86/include/asm/numachip/numachip.h @@ -14,6 +14,7 @@ #ifndef _ASM_X86_NUMACHIP_NUMACHIP_H #define _ASM_X86_NUMACHIP_NUMACHIP_H +extern u8 numachip_system; extern int __init pci_numachip_init(void); #endif /* _ASM_X86_NUMACHIP_NUMACHIP_H */ diff --git a/arch/x86/include/asm/numachip/numachip_csr.h b/arch/x86/include/asm/numachip/numachip_csr.h index 660f843df928..29719eecdc2e 100644 --- a/arch/x86/include/asm/numachip/numachip_csr.h +++ b/arch/x86/include/asm/numachip/numachip_csr.h @@ -14,12 +14,8 @@ #ifndef _ASM_X86_NUMACHIP_NUMACHIP_CSR_H #define _ASM_X86_NUMACHIP_NUMACHIP_CSR_H -#include <linux/numa.h> -#include <linux/percpu.h> +#include <linux/smp.h> #include <linux/io.h> -#include <linux/swab.h> -#include <asm/types.h> -#include <asm/processor.h> #define CSR_NODE_SHIFT 16 #define CSR_NODE_BITS(p) (((unsigned long)(p)) << CSR_NODE_SHIFT) @@ -27,11 +23,8 @@ /* 32K CSR space, b15 indicates geo/non-geo */ #define CSR_OFFSET_MASK 0x7fffUL - -/* Global CSR space covers all 4K possible nodes with 64K CSR space per node */ -#define NUMACHIP_GCSR_BASE 0x3fff00000000ULL -#define NUMACHIP_GCSR_LIM 0x3fff0fffffffULL -#define NUMACHIP_GCSR_SIZE (NUMACHIP_GCSR_LIM - NUMACHIP_GCSR_BASE + 1) +#define CSR_G0_NODE_IDS (0x008 + (0 << 12)) +#define CSR_G3_EXT_IRQ_GEN (0x030 + (3 << 12)) /* * Local CSR space starts in global CSR space with "nodeid" = 0xfff0, however @@ -41,12 +34,7 @@ #define NUMACHIP_LCSR_BASE 0x3ffffe000000ULL #define NUMACHIP_LCSR_LIM 0x3fffffffffffULL #define NUMACHIP_LCSR_SIZE (NUMACHIP_LCSR_LIM - NUMACHIP_LCSR_BASE + 1) - -static inline void *gcsr_address(int node, unsigned long offset) -{ - return __va(NUMACHIP_GCSR_BASE | (1UL << 15) | - CSR_NODE_BITS(node & CSR_NODE_MASK) | (offset & CSR_OFFSET_MASK)); -} +#define NUMACHIP_LAPIC_BITS 8 static inline void *lcsr_address(unsigned long offset) { @@ -54,114 +42,57 @@ static inline void *lcsr_address(unsigned long offset) CSR_NODE_BITS(0xfff0) | (offset & CSR_OFFSET_MASK)); } -static inline unsigned int read_gcsr(int node, unsigned long offset) +static inline unsigned int read_lcsr(unsigned long offset) { - return swab32(readl(gcsr_address(node, offset))); + return swab32(readl(lcsr_address(offset))); } -static inline void write_gcsr(int node, unsigned long offset, unsigned int val) +static inline void write_lcsr(unsigned long offset, unsigned int val) { - writel(swab32(val), gcsr_address(node, offset)); + writel(swab32(val), lcsr_address(offset)); } -static inline unsigned int read_lcsr(unsigned long offset) +/* + * On NumaChip2, local CSR space is 16MB and starts at fixed offset below 4G + */ + +#define NUMACHIP2_LCSR_BASE 0xf0000000UL +#define NUMACHIP2_LCSR_SIZE 0x1000000UL +#define NUMACHIP2_APIC_ICR 0x100000 +#define NUMACHIP2_TIMER_DEADLINE 0x200000 +#define NUMACHIP2_TIMER_INT 0x200008 +#define NUMACHIP2_TIMER_NOW 0x200018 +#define NUMACHIP2_TIMER_RESET 0x200020 + +static inline void __iomem *numachip2_lcsr_address(unsigned long offset) { - return swab32(readl(lcsr_address(offset))); + return (void __iomem *)__va(NUMACHIP2_LCSR_BASE | + (offset & (NUMACHIP2_LCSR_SIZE - 1))); } -static inline void write_lcsr(unsigned long offset, unsigned int val) +static inline u32 numachip2_read32_lcsr(unsigned long offset) { - writel(swab32(val), lcsr_address(offset)); + return readl(numachip2_lcsr_address(offset)); } -/* ========================================================================= */ -/* CSR_G0_STATE_CLEAR */ -/* ========================================================================= */ - -#define CSR_G0_STATE_CLEAR (0x000 + (0 << 12)) -union numachip_csr_g0_state_clear { - unsigned int v; - struct numachip_csr_g0_state_clear_s { - unsigned int _state:2; - unsigned int _rsvd_2_6:5; - unsigned int _lost:1; - unsigned int _rsvd_8_31:24; - } s; -}; - -/* ========================================================================= */ -/* CSR_G0_NODE_IDS */ -/* ========================================================================= */ +static inline u64 numachip2_read64_lcsr(unsigned long offset) +{ + return readq(numachip2_lcsr_address(offset)); +} -#define CSR_G0_NODE_IDS (0x008 + (0 << 12)) -union numachip_csr_g0_node_ids { - unsigned int v; - struct numachip_csr_g0_node_ids_s { - unsigned int _initialid:16; - unsigned int _nodeid:12; - unsigned int _rsvd_28_31:4; - } s; -}; - -/* ========================================================================= */ -/* CSR_G3_EXT_IRQ_GEN */ -/* ========================================================================= */ +static inline void numachip2_write32_lcsr(unsigned long offset, u32 val) +{ + writel(val, numachip2_lcsr_address(offset)); +} -#define CSR_G3_EXT_IRQ_GEN (0x030 + (3 << 12)) -union numachip_csr_g3_ext_irq_gen { - unsigned int v; - struct numachip_csr_g3_ext_irq_gen_s { - unsigned int _vector:8; - unsigned int _msgtype:3; - unsigned int _index:5; - unsigned int _destination_apic_id:16; - } s; -}; - -/* ========================================================================= */ -/* CSR_G3_EXT_IRQ_STATUS */ -/* ========================================================================= */ - -#define CSR_G3_EXT_IRQ_STATUS (0x034 + (3 << 12)) -union numachip_csr_g3_ext_irq_status { - unsigned int v; - struct numachip_csr_g3_ext_irq_status_s { - unsigned int _result:32; - } s; -}; - -/* ========================================================================= */ -/* CSR_G3_EXT_IRQ_DEST */ -/* ========================================================================= */ - -#define CSR_G3_EXT_IRQ_DEST (0x038 + (3 << 12)) -union numachip_csr_g3_ext_irq_dest { - unsigned int v; - struct numachip_csr_g3_ext_irq_dest_s { - unsigned int _irq:8; - unsigned int _rsvd_8_31:24; - } s; -}; - -/* ========================================================================= */ -/* CSR_G3_NC_ATT_MAP_SELECT */ -/* ========================================================================= */ - -#define CSR_G3_NC_ATT_MAP_SELECT (0x7fc + (3 << 12)) -union numachip_csr_g3_nc_att_map_select { - unsigned int v; - struct numachip_csr_g3_nc_att_map_select_s { - unsigned int _upper_address_bits:4; - unsigned int _select_ram:4; - unsigned int _rsvd_8_31:24; - } s; -}; - -/* ========================================================================= */ -/* CSR_G3_NC_ATT_MAP_SELECT_0-255 */ -/* ========================================================================= */ - -#define CSR_G3_NC_ATT_MAP_SELECT_0 (0x800 + (3 << 12)) +static inline void numachip2_write64_lcsr(unsigned long offset, u64 val) +{ + writeq(val, numachip2_lcsr_address(offset)); +} -#endif /* _ASM_X86_NUMACHIP_NUMACHIP_CSR_H */ +static inline unsigned int numachip2_timer(void) +{ + return (smp_processor_id() % 48) << 6; +} +#endif /* _ASM_X86_NUMACHIP_NUMACHIP_CSR_H */ diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 4edd53b79a81..4928cf0d5af0 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -26,9 +26,6 @@ #define MCE_STACK 4 #define N_EXCEPTION_STACKS 4 /* hw limit: 7 */ -#define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT) -#define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1)) - /* * Set __PAGE_OFFSET to the most negative possible address + * PGDIR_SIZE*16 (pgd slot 272). The gap is to allow a space for a diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index c7c712f2648b..7bd0099384ca 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -5,20 +5,25 @@ #include <linux/types.h> /* PAGE_SHIFT determines the page size */ -#define PAGE_SHIFT 12 -#define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) -#define PAGE_MASK (~(PAGE_SIZE-1)) +#define PAGE_SHIFT 12 +#define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) +#define PAGE_MASK (~(PAGE_SIZE-1)) + +#define PMD_PAGE_SIZE (_AC(1, UL) << PMD_SHIFT) +#define PMD_PAGE_MASK (~(PMD_PAGE_SIZE-1)) + +#define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT) +#define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1)) #define __PHYSICAL_MASK ((phys_addr_t)((1ULL << __PHYSICAL_MASK_SHIFT) - 1)) #define __VIRTUAL_MASK ((1UL << __VIRTUAL_MASK_SHIFT) - 1) -/* Cast PAGE_MASK to a signed type so that it is sign-extended if +/* Cast *PAGE_MASK to a signed type so that it is sign-extended if virtual addresses are 32-bits but physical addresses are larger (ie, 32-bit PAE). */ #define PHYSICAL_PAGE_MASK (((signed long)PAGE_MASK) & __PHYSICAL_MASK) - -#define PMD_PAGE_SIZE (_AC(1, UL) << PMD_SHIFT) -#define PMD_PAGE_MASK (~(PMD_PAGE_SIZE-1)) +#define PHYSICAL_PMD_PAGE_MASK (((signed long)PMD_PAGE_MASK) & __PHYSICAL_MASK) +#define PHYSICAL_PUD_PAGE_MASK (((signed long)PUD_PAGE_MASK) & __PHYSICAL_MASK) #define HPAGE_SHIFT PMD_SHIFT #define HPAGE_SIZE (_AC(1,UL) << HPAGE_SHIFT) diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index d143bfad45d7..f6192502149e 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -19,6 +19,12 @@ static inline int paravirt_enabled(void) return pv_info.paravirt_enabled; } +static inline int paravirt_has_feature(unsigned int feature) +{ + WARN_ON_ONCE(!pv_info.paravirt_enabled); + return (pv_info.features & feature); +} + static inline void load_sp0(struct tss_struct *tss, struct thread_struct *thread) { @@ -153,7 +159,11 @@ do { \ val = paravirt_read_msr(msr, &_err); \ } while (0) -#define wrmsrl(msr, val) wrmsr(msr, (u32)((u64)(val)), ((u64)(val))>>32) +static inline void wrmsrl(unsigned msr, u64 val) +{ + wrmsr(msr, (u32)val, (u32)(val>>32)); +} + #define wrmsr_safe(msr, a, b) paravirt_write_msr(msr, a, b) /* rdmsr with exception handling */ @@ -174,19 +184,6 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p) return err; } -static inline u64 paravirt_read_tsc(void) -{ - return PVOP_CALL0(u64, pv_cpu_ops.read_tsc); -} - -#define rdtscl(low) \ -do { \ - u64 _l = paravirt_read_tsc(); \ - low = (int)_l; \ -} while (0) - -#define rdtscll(val) (val = paravirt_read_tsc()) - static inline unsigned long long paravirt_sched_clock(void) { return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock); @@ -215,27 +212,6 @@ do { \ #define rdpmcl(counter, val) ((val) = paravirt_read_pmc(counter)) -static inline unsigned long long paravirt_rdtscp(unsigned int *aux) -{ - return PVOP_CALL1(u64, pv_cpu_ops.read_tscp, aux); -} - -#define rdtscp(low, high, aux) \ -do { \ - int __aux; \ - unsigned long __val = paravirt_rdtscp(&__aux); \ - (low) = (u32)__val; \ - (high) = (u32)(__val >> 32); \ - (aux) = __aux; \ -} while (0) - -#define rdtscpll(val, aux) \ -do { \ - unsigned long __aux; \ - val = paravirt_rdtscp(&__aux); \ - (aux) = __aux; \ -} while (0) - static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries) { PVOP_VCALL2(pv_cpu_ops.alloc_ldt, ldt, entries); @@ -315,15 +291,6 @@ static inline void slow_down_io(void) #endif } -#ifdef CONFIG_SMP -static inline void startup_ipi_hook(int phys_apicid, unsigned long start_eip, - unsigned long start_esp) -{ - PVOP_VCALL3(pv_apic_ops.startup_ipi_hook, - phys_apicid, start_eip, start_esp); -} -#endif - static inline void paravirt_activate_mm(struct mm_struct *prev, struct mm_struct *next) { @@ -405,23 +372,6 @@ static inline void pte_update(struct mm_struct *mm, unsigned long addr, { PVOP_VCALL3(pv_mmu_ops.pte_update, mm, addr, ptep); } -static inline void pmd_update(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp) -{ - PVOP_VCALL3(pv_mmu_ops.pmd_update, mm, addr, pmdp); -} - -static inline void pte_update_defer(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) -{ - PVOP_VCALL3(pv_mmu_ops.pte_update_defer, mm, addr, ptep); -} - -static inline void pmd_update_defer(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp) -{ - PVOP_VCALL3(pv_mmu_ops.pmd_update_defer, mm, addr, pmdp); -} static inline pte_t __pte(pteval_t val) { @@ -952,23 +902,11 @@ extern void default_banner(void); call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) -#define USERGS_SYSRET32 \ - PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret32), \ - CLBR_NONE, \ - jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret32)) - #ifdef CONFIG_X86_32 #define GET_CR0_INTO_EAX \ push %ecx; push %edx; \ call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0); \ pop %edx; pop %ecx - -#define ENABLE_INTERRUPTS_SYSEXIT \ - PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_sysexit), \ - CLBR_NONE, \ - jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_irq_enable_sysexit)) - - #else /* !CONFIG_X86_32 */ /* diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index a6b8f9fadb06..77db5616a473 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -70,9 +70,14 @@ struct pv_info { #endif int paravirt_enabled; + unsigned int features; /* valid only if paravirt_enabled is set */ const char *name; }; +#define paravirt_has(x) paravirt_has_feature(PV_SUPPORTED_##x) +/* Supported features */ +#define PV_SUPPORTED_RTC (1<<0) + struct pv_init_ops { /* * Patch may replace one of the defined code sequences with @@ -97,7 +102,6 @@ struct pv_lazy_ops { struct pv_time_ops { unsigned long long (*sched_clock)(void); unsigned long long (*steal_clock)(int cpu); - unsigned long (*get_tsc_khz)(void); }; struct pv_cpu_ops { @@ -156,18 +160,7 @@ struct pv_cpu_ops { u64 (*read_msr)(unsigned int msr, int *err); int (*write_msr)(unsigned int msr, unsigned low, unsigned high); - u64 (*read_tsc)(void); 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 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 @@ -177,14 +170,6 @@ struct pv_cpu_ops { */ void (*usergs_sysret64)(void); - /* - * Switch to usermode gs and return to 32-bit usermode using - * sysret. Used to return to 32-on-64 compat processes. - * Other usermode register state, including %esp, must already - * be restored. - */ - void (*usergs_sysret32)(void); - /* Normal iret. Jump to this with the standard iret stack frame set up. */ void (*iret)(void); @@ -218,14 +203,6 @@ struct pv_irq_ops { #endif }; -struct pv_apic_ops { -#ifdef CONFIG_X86_LOCAL_APIC - void (*startup_ipi_hook)(int phys_apicid, - unsigned long start_eip, - unsigned long start_esp); -#endif -}; - struct pv_mmu_ops { unsigned long (*read_cr2)(void); void (*write_cr2)(unsigned long); @@ -277,12 +254,6 @@ struct pv_mmu_ops { pmd_t *pmdp, pmd_t pmdval); void (*pte_update)(struct mm_struct *mm, unsigned long addr, pte_t *ptep); - void (*pte_update_defer)(struct mm_struct *mm, - unsigned long addr, pte_t *ptep); - void (*pmd_update)(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp); - void (*pmd_update_defer)(struct mm_struct *mm, - unsigned long addr, pmd_t *pmdp); pte_t (*ptep_modify_prot_start)(struct mm_struct *mm, unsigned long addr, pte_t *ptep); @@ -357,7 +328,6 @@ struct paravirt_patch_template { struct pv_time_ops pv_time_ops; struct pv_cpu_ops pv_cpu_ops; struct pv_irq_ops pv_irq_ops; - struct pv_apic_ops pv_apic_ops; struct pv_mmu_ops pv_mmu_ops; struct pv_lock_ops pv_lock_ops; }; @@ -367,7 +337,6 @@ extern struct pv_init_ops pv_init_ops; extern struct pv_time_ops pv_time_ops; extern struct pv_cpu_ops pv_cpu_ops; extern struct pv_irq_ops pv_irq_ops; -extern struct pv_apic_ops pv_apic_ops; extern struct pv_mmu_ops pv_mmu_ops; extern struct pv_lock_ops pv_lock_ops; @@ -405,10 +374,8 @@ extern struct pv_lock_ops pv_lock_ops; __visible extern const char start_##ops##_##name[], end_##ops##_##name[]; \ asm(NATIVE_LABEL("start_", ops, name) code NATIVE_LABEL("end_", ops, name)) -unsigned paravirt_patch_nop(void); unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len); unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len); -unsigned paravirt_patch_ignore(unsigned len); unsigned paravirt_patch_call(void *insnbuf, const void *target, u16 tgt_clobbers, unsigned long addr, u16 site_clobbers, diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index 164e3f8d3c3d..46873fbd44e1 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -93,8 +93,6 @@ extern raw_spinlock_t pci_config_lock; extern int (*pcibios_enable_irq)(struct pci_dev *dev); extern void (*pcibios_disable_irq)(struct pci_dev *dev); -extern bool mp_should_keep_irq(struct device *dev); - struct pci_raw_ops { int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn, int reg, int len, u32 *val); @@ -153,11 +151,11 @@ extern struct list_head pci_mmcfg_list; #define PCI_MMCFG_BUS_OFFSET(bus) ((bus) << 20) /* - * AMD Fam10h CPUs are buggy, and cannot access MMIO config space - * on their northbrige except through the * %eax register. As such, you MUST - * NOT use normal IOMEM accesses, you need to only use the magic mmio-config - * accessor functions. - * In fact just use pci_config_*, nothing else please. + * On AMD Fam10h CPUs, all PCI MMIO configuration space accesses must use + * %eax. No other source or target registers may be used. The following + * mmio_config_* accessors enforce this. See "BIOS and Kernel Developer's + * Guide (BKDG) For AMD Family 10h Processors", rev. 3.48, sec 2.11.1, + * "MMIO Configuration Coding Requirements". */ static inline unsigned char mmio_config_readb(void __iomem *pos) { diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index dc0f6ed35b08..7bcb861a04e5 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -159,6 +159,13 @@ struct x86_pmu_capability { */ #define INTEL_PMC_IDX_FIXED_BTS (INTEL_PMC_IDX_FIXED + 16) +#define GLOBAL_STATUS_COND_CHG BIT_ULL(63) +#define GLOBAL_STATUS_BUFFER_OVF BIT_ULL(62) +#define GLOBAL_STATUS_UNC_OVF BIT_ULL(61) +#define GLOBAL_STATUS_ASIF BIT_ULL(60) +#define GLOBAL_STATUS_COUNTERS_FROZEN BIT_ULL(59) +#define GLOBAL_STATUS_LBRS_FROZEN BIT_ULL(58) + /* * IBS cpuid feature detection */ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 867da5bbb4a3..0687c4748b8f 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -19,6 +19,13 @@ #include <asm/x86_init.h> void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd); +void ptdump_walk_pgd_level_checkwx(void); + +#ifdef CONFIG_DEBUG_WX +#define debug_checkwx() ptdump_walk_pgd_level_checkwx() +#else +#define debug_checkwx() do { } while (0) +#endif /* * ZERO_PAGE is a global shared page that is always zero: used @@ -62,9 +69,6 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page); #define pmd_clear(pmd) native_pmd_clear(pmd) #define pte_update(mm, addr, ptep) do { } while (0) -#define pte_update_defer(mm, addr, ptep) do { } while (0) -#define pmd_update(mm, addr, ptep) do { } while (0) -#define pmd_update_defer(mm, addr, ptep) do { } while (0) #define pgd_val(x) native_pgd_val(x) #define __pgd(x) native_make_pgd(x) @@ -142,12 +146,12 @@ static inline unsigned long pte_pfn(pte_t pte) static inline unsigned long pmd_pfn(pmd_t pmd) { - return (pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT; + return (pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT; } static inline unsigned long pud_pfn(pud_t pud) { - return (pud_val(pud) & PTE_PFN_MASK) >> PAGE_SHIFT; + return (pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT; } #define pte_page(pte) pfn_to_page(pte_pfn(pte)) @@ -158,20 +162,22 @@ static inline int pmd_large(pmd_t pte) } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -static inline int pmd_trans_splitting(pmd_t pmd) -{ - return pmd_val(pmd) & _PAGE_SPLITTING; -} - static inline int pmd_trans_huge(pmd_t pmd) { - return pmd_val(pmd) & _PAGE_PSE; + return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; } static inline int has_transparent_hugepage(void) { return cpu_has_pse; } + +#ifdef __HAVE_ARCH_PTE_DEVMAP +static inline int pmd_devmap(pmd_t pmd) +{ + return !!(pmd_val(pmd) & _PAGE_DEVMAP); +} +#endif #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline pte_t pte_set_flags(pte_t pte, pteval_t set) @@ -248,6 +254,11 @@ static inline pte_t pte_mkspecial(pte_t pte) return pte_set_flags(pte, _PAGE_SPECIAL); } +static inline pte_t pte_mkdevmap(pte_t pte) +{ + return pte_set_flags(pte, _PAGE_SPECIAL|_PAGE_DEVMAP); +} + static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set) { pmdval_t v = native_pmd_val(pmd); @@ -267,6 +278,11 @@ static inline pmd_t pmd_mkold(pmd_t pmd) return pmd_clear_flags(pmd, _PAGE_ACCESSED); } +static inline pmd_t pmd_mkclean(pmd_t pmd) +{ + return pmd_clear_flags(pmd, _PAGE_DIRTY); +} + static inline pmd_t pmd_wrprotect(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_RW); @@ -277,6 +293,11 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd) return pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); } +static inline pmd_t pmd_mkdevmap(pmd_t pmd) +{ + return pmd_set_flags(pmd, _PAGE_DEVMAP); +} + static inline pmd_t pmd_mkhuge(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_PSE); @@ -318,6 +339,16 @@ static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY); } +static inline pte_t pte_clear_soft_dirty(pte_t pte) +{ + return pte_clear_flags(pte, _PAGE_SOFT_DIRTY); +} + +static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd) +{ + return pmd_clear_flags(pmd, _PAGE_SOFT_DIRTY); +} + #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ /* @@ -379,7 +410,9 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) return __pgprot(preservebits | addbits); } -#define pte_pgprot(x) __pgprot(pte_flags(x) & PTE_FLAGS_MASK) +#define pte_pgprot(x) __pgprot(pte_flags(x)) +#define pmd_pgprot(x) __pgprot(pmd_flags(x)) +#define pud_pgprot(x) __pgprot(pud_flags(x)) #define canon_pgprot(p) __pgprot(massage_pgprot(p)) @@ -446,6 +479,13 @@ static inline int pte_present(pte_t a) return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE); } +#ifdef __HAVE_ARCH_PTE_DEVMAP +static inline int pte_devmap(pte_t a) +{ + return (pte_flags(a) & _PAGE_DEVMAP) == _PAGE_DEVMAP; +} +#endif + #define pte_accessible pte_accessible static inline bool pte_accessible(struct mm_struct *mm, pte_t a) { @@ -502,14 +542,15 @@ static inline int pmd_none(pmd_t pmd) static inline unsigned long pmd_page_vaddr(pmd_t pmd) { - return (unsigned long)__va(pmd_val(pmd) & PTE_PFN_MASK); + return (unsigned long)__va(pmd_val(pmd) & pmd_pfn_mask(pmd)); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ -#define pmd_page(pmd) pfn_to_page((pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT) +#define pmd_page(pmd) \ + pfn_to_page((pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT) /* * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD] @@ -570,14 +611,15 @@ static inline int pud_present(pud_t pud) static inline unsigned long pud_page_vaddr(pud_t pud) { - return (unsigned long)__va((unsigned long)pud_val(pud) & PTE_PFN_MASK); + return (unsigned long)__va(pud_val(pud) & pud_pfn_mask(pud)); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ -#define pud_page(pud) pfn_to_page(pud_val(pud) >> PAGE_SHIFT) +#define pud_page(pud) \ + pfn_to_page((pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT) /* Find an entry in the second-level page table.. */ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) @@ -710,14 +752,9 @@ static inline void native_set_pmd_at(struct mm_struct *mm, unsigned long addr, * updates should either be sets, clears, or set_pte_atomic for P->P * transitions, which means this hook should only be called for user PTEs. * This hook implies a P->P protection or access change has taken place, which - * requires a subsequent TLB flush. The notification can optionally be delayed - * until the TLB flush event by using the pte_update_defer form of the - * interface, but care must be taken to assure that the flush happens while - * still holding the same page table lock so that the shadow and primary pages - * do not become out of sync on SMP. + * requires a subsequent TLB flush. */ #define pte_update(mm, addr, ptep) do { } while (0) -#define pte_update_defer(mm, addr, ptep) do { } while (0) #endif /* @@ -795,10 +832,6 @@ extern int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); -#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH -extern void pmdp_splitting_flush(struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmdp); - #define __HAVE_ARCH_PMD_WRITE static inline int pmd_write(pmd_t pmd) { @@ -809,9 +842,7 @@ static inline int pmd_write(pmd_t pmd) 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); - pmd_update(mm, addr, pmdp); - return pmd; + return native_pmdp_get_and_clear(pmdp); } #define __HAVE_ARCH_PMDP_SET_WRPROTECT @@ -819,7 +850,6 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp); - pmd_update(mm, addr, pmdp); } /* diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 13f310bfc09a..04c27a013165 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -22,10 +22,11 @@ #define _PAGE_BIT_PAT_LARGE 12 /* On 2MB or 1GB pages */ #define _PAGE_BIT_SPECIAL _PAGE_BIT_SOFTW1 #define _PAGE_BIT_CPA_TEST _PAGE_BIT_SOFTW1 -#define _PAGE_BIT_SPLITTING _PAGE_BIT_SOFTW2 /* only valid on a PSE pmd */ #define _PAGE_BIT_HIDDEN _PAGE_BIT_SOFTW3 /* hidden by kmemcheck */ #define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_SOFTW3 /* software dirty tracking */ -#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */ +#define _PAGE_BIT_SOFTW4 58 /* available for programmer */ +#define _PAGE_BIT_DEVMAP _PAGE_BIT_SOFTW4 +#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */ /* If _PAGE_BIT_PRESENT is clear, we use these: */ /* - if the user mapped it with PROT_NONE; pte_present gives true */ @@ -46,7 +47,6 @@ #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE) #define _PAGE_SPECIAL (_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL) #define _PAGE_CPA_TEST (_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST) -#define _PAGE_SPLITTING (_AT(pteval_t, 1) << _PAGE_BIT_SPLITTING) #define __HAVE_ARCH_PTE_SPECIAL #ifdef CONFIG_KMEMCHECK @@ -85,8 +85,11 @@ #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) #define _PAGE_NX (_AT(pteval_t, 1) << _PAGE_BIT_NX) +#define _PAGE_DEVMAP (_AT(u64, 1) << _PAGE_BIT_DEVMAP) +#define __HAVE_ARCH_PTE_DEVMAP #else #define _PAGE_NX (_AT(pteval_t, 0)) +#define _PAGE_DEVMAP (_AT(pteval_t, 0)) #endif #define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE) @@ -209,10 +212,10 @@ enum page_cache_mode { #include <linux/types.h> -/* PTE_PFN_MASK extracts the PFN from a (pte|pmd|pud|pgd)val_t */ +/* Extracts the PFN from a (pte|pmd|pud|pgd)val_t of a 4KB page */ #define PTE_PFN_MASK ((pteval_t)PHYSICAL_PAGE_MASK) -/* PTE_FLAGS_MASK extracts the flags from a (pte|pmd|pud|pgd)val_t */ +/* Extracts the flags from a (pte|pmd|pud|pgd)val_t of a 4KB page */ #define PTE_FLAGS_MASK (~PTE_PFN_MASK) typedef struct pgprot { pgprotval_t pgprot; } pgprot_t; @@ -276,14 +279,40 @@ static inline pmdval_t native_pmd_val(pmd_t pmd) } #endif +static inline pudval_t pud_pfn_mask(pud_t pud) +{ + if (native_pud_val(pud) & _PAGE_PSE) + return PHYSICAL_PUD_PAGE_MASK; + else + return PTE_PFN_MASK; +} + +static inline pudval_t pud_flags_mask(pud_t pud) +{ + return ~pud_pfn_mask(pud); +} + static inline pudval_t pud_flags(pud_t pud) { - return native_pud_val(pud) & PTE_FLAGS_MASK; + return native_pud_val(pud) & pud_flags_mask(pud); +} + +static inline pmdval_t pmd_pfn_mask(pmd_t pmd) +{ + if (native_pmd_val(pmd) & _PAGE_PSE) + return PHYSICAL_PMD_PAGE_MASK; + else + return PTE_PFN_MASK; +} + +static inline pmdval_t pmd_flags_mask(pmd_t pmd) +{ + return ~pmd_pfn_mask(pmd); } static inline pmdval_t pmd_flags(pmd_t pmd) { - return native_pmd_val(pmd) & PTE_FLAGS_MASK; + return native_pmd_val(pmd) & pmd_flags_mask(pmd); } static inline pte_t native_make_pte(pteval_t val) diff --git a/arch/x86/include/asm/platform_sst_audio.h b/arch/x86/include/asm/platform_sst_audio.h index 7249e6d0902d..5973a2f3db3d 100644 --- a/arch/x86/include/asm/platform_sst_audio.h +++ b/arch/x86/include/asm/platform_sst_audio.h @@ -55,6 +55,7 @@ enum sst_audio_device_id_mrfld { PIPE_MEDIA0_IN = 0x8F, PIPE_MEDIA1_IN = 0x90, PIPE_MEDIA2_IN = 0x91, + PIPE_MEDIA3_IN = 0x9C, PIPE_RSVD = 0xFF, }; diff --git a/arch/x86/include/asm/pmc_atom.h b/arch/x86/include/asm/pmc_atom.h index bc0fc0866553..aa8744c77c6d 100644 --- a/arch/x86/include/asm/pmc_atom.h +++ b/arch/x86/include/asm/pmc_atom.h @@ -18,6 +18,8 @@ /* ValleyView Power Control Unit PCI Device ID */ #define PCI_DEVICE_ID_VLV_PMC 0x0F1C +/* CherryTrail Power Control Unit PCI Device ID */ +#define PCI_DEVICE_ID_CHT_PMC 0x229C /* PMC Memory mapped IO registers */ #define PMC_BASE_ADDR_OFFSET 0x44 @@ -29,6 +31,10 @@ #define PMC_FUNC_DIS 0x34 #define PMC_FUNC_DIS_2 0x38 +/* CHT specific bits in FUNC_DIS2 register */ +#define BIT_FD_GMM BIT(3) +#define BIT_FD_ISH BIT(4) + /* S0ix wake event control */ #define PMC_S0IX_WAKE_EN 0x3C @@ -75,6 +81,21 @@ #define PMC_PSS_BIT_USB BIT(16) #define PMC_PSS_BIT_USB_SUS BIT(17) +/* CHT specific bits in PSS register */ +#define PMC_PSS_BIT_CHT_UFS BIT(7) +#define PMC_PSS_BIT_CHT_UXD BIT(11) +#define PMC_PSS_BIT_CHT_UXD_FD BIT(12) +#define PMC_PSS_BIT_CHT_UX_ENG BIT(15) +#define PMC_PSS_BIT_CHT_USB_SUS BIT(16) +#define PMC_PSS_BIT_CHT_GMM BIT(17) +#define PMC_PSS_BIT_CHT_ISH BIT(18) +#define PMC_PSS_BIT_CHT_DFX_MASTER BIT(26) +#define PMC_PSS_BIT_CHT_DFX_CLUSTER1 BIT(27) +#define PMC_PSS_BIT_CHT_DFX_CLUSTER2 BIT(28) +#define PMC_PSS_BIT_CHT_DFX_CLUSTER3 BIT(29) +#define PMC_PSS_BIT_CHT_DFX_CLUSTER4 BIT(30) +#define PMC_PSS_BIT_CHT_DFX_CLUSTER5 BIT(31) + /* These registers reflect D3 status of functions */ #define PMC_D3_STS_0 0xA0 @@ -117,6 +138,10 @@ #define BIT_USH_SS_PHY BIT(2) #define BIT_DFX BIT(3) +/* CHT specific bits in PMC_D3_STS_1 register */ +#define BIT_STS_GMM BIT(1) +#define BIT_STS_ISH BIT(2) + /* PMC I/O Registers */ #define ACPI_BASE_ADDR_OFFSET 0x40 #define ACPI_BASE_ADDR_MASK 0xFFFFFE00 @@ -126,4 +151,8 @@ #define SLEEP_TYPE_MASK 0xFFFFECFF #define SLEEP_TYPE_S5 0x1C00 #define SLEEP_ENABLE 0x2000 + +extern int pmc_atom_read(int offset, u32 *value); +extern int pmc_atom_write(int offset, u32 value); + #endif /* PMC_ATOM_H */ diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h new file mode 100644 index 000000000000..1544fabcd7f9 --- /dev/null +++ b/arch/x86/include/asm/pmem.h @@ -0,0 +1,148 @@ +/* + * Copyright(c) 2015 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#ifndef __ASM_X86_PMEM_H__ +#define __ASM_X86_PMEM_H__ + +#include <linux/uaccess.h> +#include <asm/cacheflush.h> +#include <asm/cpufeature.h> +#include <asm/special_insns.h> + +#ifdef CONFIG_ARCH_HAS_PMEM_API +/** + * 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(); +} + +/** + * __arch_wb_cache_pmem - write back a cache range with CLWB + * @vaddr: virtual start address + * @size: number of bytes to write back + * + * Write back a cache range using the CLWB (cache line write back) + * instruction. This function requires explicit ordering with an + * arch_wmb_pmem() call. This API is internal to the x86 PMEM implementation. + */ +static inline void __arch_wb_cache_pmem(void *vaddr, size_t size) +{ + u16 x86_clflush_size = boot_cpu_data.x86_clflush_size; + unsigned long clflush_mask = x86_clflush_size - 1; + void *vend = vaddr + size; + void *p; + + for (p = (void *)((unsigned long)vaddr & ~clflush_mask); + p < vend; p += x86_clflush_size) + clwb(p); +} + +/* + * copy_from_iter_nocache() on x86 only uses non-temporal stores for iovec + * iterators, so for other types (bvec & kvec) we must do a cache write-back. + */ +static inline bool __iter_needs_pmem_wb(struct iov_iter *i) +{ + return iter_is_iovec(i) == false; +} + +/** + * arch_copy_from_iter_pmem - copy data from an iterator to PMEM + * @addr: PMEM destination address + * @bytes: number of bytes to copy + * @i: iterator with source data + * + * Copy data from the iterator 'i' to the PMEM buffer starting at 'addr'. + * This function requires explicit ordering with an arch_wmb_pmem() call. + */ +static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes, + struct iov_iter *i) +{ + void *vaddr = (void __force *)addr; + size_t len; + + /* TODO: skip the write-back by always using non-temporal stores */ + len = copy_from_iter_nocache(vaddr, bytes, i); + + if (__iter_needs_pmem_wb(i)) + __arch_wb_cache_pmem(vaddr, bytes); + + return len; +} + +/** + * arch_clear_pmem - zero a PMEM memory range + * @addr: virtual start address + * @size: number of bytes to zero + * + * Write zeros into the memory range starting at 'addr' for 'size' bytes. + * This function requires explicit ordering with an arch_wmb_pmem() call. + */ +static inline void arch_clear_pmem(void __pmem *addr, size_t size) +{ + void *vaddr = (void __force *)addr; + + memset(vaddr, 0, size); + __arch_wb_cache_pmem(vaddr, size); +} + +static inline bool __arch_has_wmb_pmem(void) +{ + /* + * We require that wmb() be an 'sfence', that is only guaranteed on + * 64-bit builds + */ + return static_cpu_has(X86_FEATURE_PCOMMIT); +} +#endif /* CONFIG_ARCH_HAS_PMEM_API */ +#endif /* __ASM_X86_PMEM_H__ */ diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index dca71714f860..01bcde84d3e4 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -30,12 +30,9 @@ static __always_inline void preempt_count_set(int pc) /* * must be macros to avoid header recursion hell */ -#define init_task_preempt_count(p) do { \ - task_thread_info(p)->saved_preempt_count = PREEMPT_DISABLED; \ -} while (0) +#define init_task_preempt_count(p) do { } while (0) #define init_idle_preempt_count(p, cpu) do { \ - task_thread_info(p)->saved_preempt_count = PREEMPT_ENABLED; \ per_cpu(__preempt_count, (cpu)) = PREEMPT_ENABLED; \ } while (0) @@ -90,9 +87,9 @@ static __always_inline bool __preempt_count_dec_and_test(void) /* * Returns true when we need to resched and can (barring IRQ state). */ -static __always_inline bool should_resched(void) +static __always_inline bool should_resched(int preempt_offset) { - return unlikely(!raw_cpu_read_4(__preempt_count)); + return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset); } #ifdef CONFIG_PREEMPT diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 944f1785ed0d..2d5a50cb61a2 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -6,12 +6,12 @@ /* Forward declaration, a strange C thing */ struct task_struct; struct mm_struct; +struct vm86; -#include <asm/vm86.h> #include <asm/math_emu.h> #include <asm/segment.h> #include <asm/types.h> -#include <asm/sigcontext.h> +#include <uapi/asm/sigcontext.h> #include <asm/current.h> #include <asm/cpufeature.h> #include <asm/page.h> @@ -400,15 +400,9 @@ struct thread_struct { unsigned long cr2; unsigned long trap_nr; unsigned long error_code; -#ifdef CONFIG_X86_32 +#ifdef CONFIG_VM86 /* Virtual 86 mode info */ - struct vm86_struct __user *vm86_info; - unsigned long screen_bitmap; - unsigned long v86flags; - unsigned long v86mask; - unsigned long saved_sp0; - unsigned int saved_fs; - unsigned int saved_gs; + struct vm86 *vm86; #endif /* IO permissions: */ unsigned long *io_bitmap_ptr; @@ -478,6 +472,7 @@ static inline unsigned long current_top_of_stack(void) #else #define __cpuid native_cpuid #define paravirt_enabled() 0 +#define paravirt_has(x) 0 static inline void load_sp0(struct tss_struct *tss, struct thread_struct *thread) @@ -562,12 +557,12 @@ static inline unsigned int cpuid_edx(unsigned int op) } /* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ -static inline void rep_nop(void) +static __always_inline void rep_nop(void) { asm volatile("rep; nop" ::: "memory"); } -static inline void cpu_relax(void) +static __always_inline void cpu_relax(void) { rep_nop(); } @@ -651,14 +646,6 @@ static inline void update_debugctlmsr(unsigned long debugctlmsr) extern void set_task_blockstep(struct task_struct *task, bool on); -/* - * from system description table in BIOS. Mostly for MCA use, but - * others may find it useful: - */ -extern unsigned int machine_id; -extern unsigned int machine_submodel_id; -extern unsigned int BIOS_revision; - /* Boot loader type from the setup header: */ extern int bootloader_type; extern int bootloader_version; @@ -720,7 +707,6 @@ static inline void spin_lock_prefetch(const void *x) #define INIT_THREAD { \ .sp0 = TOP_OF_INIT_STACK, \ - .vm86_info = NULL, \ .sysenter_cs = __KERNEL_CS, \ .io_bitmap_ptr = NULL, \ } diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 5fabf1362942..6271281f947d 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -88,7 +88,6 @@ extern long syscall_trace_enter_phase2(struct pt_regs *, u32 arch, unsigned long phase1_result); extern long syscall_trace_enter(struct pt_regs *); -extern void syscall_trace_leave(struct pt_regs *); static inline unsigned long regs_return_value(struct pt_regs *regs) { diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h index 655e07a48f6c..67f08230103a 100644 --- a/arch/x86/include/asm/pvclock-abi.h +++ b/arch/x86/include/asm/pvclock-abi.h @@ -41,6 +41,7 @@ struct pvclock_wall_clock { #define PVCLOCK_TSC_STABLE_BIT (1 << 0) #define PVCLOCK_GUEST_STOPPED (1 << 1) +/* PVCLOCK_COUNTS_FROM_ZERO broke ABI and can't be used anymore. */ #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 628954ceede1..fdcc04020636 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -4,6 +4,15 @@ #include <linux/clocksource.h> #include <asm/pvclock-abi.h> +#ifdef CONFIG_KVM_GUEST +extern struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void); +#else +static inline struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void) +{ + return NULL; +} +#endif + /* some helper functions for xen and kvm pv clock sources */ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src); u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src); @@ -62,7 +71,7 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) static __always_inline u64 pvclock_get_nsec_offset(const struct pvclock_vcpu_time_info *src) { - u64 delta = __native_read_tsc() - src->tsc_timestamp; + u64 delta = rdtsc_ordered() - src->tsc_timestamp; return pvclock_scale_delta(delta, src->tsc_to_system_mul, src->tsc_shift); } @@ -76,13 +85,7 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, u8 ret_flags; version = src->version; - /* Note: emulated platforms which do not advertise SSE2 support - * result in kvmclock not using the necessary RDTSC barriers. - * Without barriers, it is possible that RDTSC instruction reads from - * the time stamp counter outside rdtsc_barrier protected section - * below, resulting in violation of monotonicity. - */ - rdtsc_barrier(); + offset = pvclock_get_nsec_offset(src); ret = src->system_time + offset; ret_flags = src->flags; @@ -97,10 +100,5 @@ struct pvclock_vsyscall_time_info { } __attribute__((__aligned__(SMP_CACHE_BYTES))); #define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info) -#define PVCLOCK_VSYSCALL_NR_PAGES (((NR_CPUS-1)/(PAGE_SIZE/PVTI_SIZE))+1) - -int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, - int size); -struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu); #endif /* _ASM_X86_PVCLOCK_H */ diff --git a/arch/x86/include/asm/qrwlock.h b/arch/x86/include/asm/qrwlock.h index ae0e241e228b..c537cbb038a7 100644 --- a/arch/x86/include/asm/qrwlock.h +++ b/arch/x86/include/asm/qrwlock.h @@ -2,16 +2,6 @@ #define _ASM_X86_QRWLOCK_H #include <asm-generic/qrwlock_types.h> - -#ifndef CONFIG_X86_PPRO_FENCE -#define queue_write_unlock queue_write_unlock -static inline void queue_write_unlock(struct qrwlock *lock) -{ - barrier(); - ACCESS_ONCE(*(u8 *)&lock->cnts) = 0; -} -#endif - #include <asm-generic/qrwlock.h> #endif /* _ASM_X86_QRWLOCK_H */ diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h index 9d51fae1cba3..eaba08076030 100644 --- a/arch/x86/include/asm/qspinlock.h +++ b/arch/x86/include/asm/qspinlock.h @@ -39,18 +39,27 @@ static inline void queued_spin_unlock(struct qspinlock *lock) } #endif -#define virt_queued_spin_lock virt_queued_spin_lock - -static inline bool virt_queued_spin_lock(struct qspinlock *lock) +#ifdef CONFIG_PARAVIRT +#define virt_spin_lock virt_spin_lock +static inline bool virt_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(); + /* + * On hypervisors without PARAVIRT_SPINLOCKS support we fall + * back to a Test-and-Set spinlock, because fair locks have + * horrible lock 'holder' preemption issues. + */ + + do { + while (atomic_read(&lock->val) != 0) + cpu_relax(); + } while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0); return true; } +#endif /* CONFIG_PARAVIRT */ #include <asm-generic/qspinlock.h> diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h index b002e711ba88..9f92c180ed2f 100644 --- a/arch/x86/include/asm/qspinlock_paravirt.h +++ b/arch/x86/include/asm/qspinlock_paravirt.h @@ -1,6 +1,65 @@ #ifndef __ASM_QSPINLOCK_PARAVIRT_H #define __ASM_QSPINLOCK_PARAVIRT_H +/* + * For x86-64, PV_CALLEE_SAVE_REGS_THUNK() saves and restores 8 64-bit + * registers. For i386, however, only 1 32-bit register needs to be saved + * and restored. So an optimized version of __pv_queued_spin_unlock() is + * hand-coded for 64-bit, but it isn't worthwhile to do it for 32-bit. + */ +#ifdef CONFIG_64BIT + +PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath); +#define __pv_queued_spin_unlock __pv_queued_spin_unlock +#define PV_UNLOCK "__raw_callee_save___pv_queued_spin_unlock" +#define PV_UNLOCK_SLOWPATH "__raw_callee_save___pv_queued_spin_unlock_slowpath" + +/* + * Optimized assembly version of __raw_callee_save___pv_queued_spin_unlock + * which combines the registers saving trunk and the body of the following + * C code: + * + * void __pv_queued_spin_unlock(struct qspinlock *lock) + * { + * struct __qspinlock *l = (void *)lock; + * u8 lockval = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0); + * + * if (likely(lockval == _Q_LOCKED_VAL)) + * return; + * pv_queued_spin_unlock_slowpath(lock, lockval); + * } + * + * For x86-64, + * rdi = lock (first argument) + * rsi = lockval (second argument) + * rdx = internal variable (set to 0) + */ +asm (".pushsection .text;" + ".globl " PV_UNLOCK ";" + ".align 4,0x90;" + PV_UNLOCK ": " + "push %rdx;" + "mov $0x1,%eax;" + "xor %edx,%edx;" + "lock cmpxchg %dl,(%rdi);" + "cmp $0x1,%al;" + "jne .slowpath;" + "pop %rdx;" + "ret;" + ".slowpath: " + "push %rsi;" + "movzbl %al,%esi;" + "call " PV_UNLOCK_SLOWPATH ";" + "pop %rsi;" + "pop %rdx;" + "ret;" + ".size " PV_UNLOCK ", .-" PV_UNLOCK ";" + ".popsection"); + +#else /* CONFIG_64BIT */ + +extern void __pv_queued_spin_unlock(struct qspinlock *lock); PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock); +#endif /* CONFIG_64BIT */ #endif diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index a82c4f1b4d83..2cb1cc253d51 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -25,5 +25,6 @@ void __noreturn machine_real_restart(unsigned int type); typedef void (*nmi_shootdown_cb)(int, struct pt_regs*); void nmi_shootdown_cpus(nmi_shootdown_cb callback); +void run_crash_ipi_callback(struct pt_regs *regs); #endif /* _ASM_X86_REBOOT_H */ diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h index 9dfce4e0417d..e6cd2c489dbb 100644 --- a/arch/x86/include/asm/sigcontext.h +++ b/arch/x86/include/asm/sigcontext.h @@ -1,79 +1,8 @@ #ifndef _ASM_X86_SIGCONTEXT_H #define _ASM_X86_SIGCONTEXT_H -#include <uapi/asm/sigcontext.h> - -#ifdef __i386__ -struct sigcontext { - unsigned short gs, __gsh; - unsigned short fs, __fsh; - unsigned short es, __esh; - unsigned short ds, __dsh; - unsigned long di; - unsigned long si; - unsigned long bp; - unsigned long sp; - unsigned long bx; - unsigned long dx; - unsigned long cx; - unsigned long ax; - unsigned long trapno; - unsigned long err; - unsigned long ip; - unsigned short cs, __csh; - unsigned long flags; - unsigned long sp_at_signal; - unsigned short ss, __ssh; +/* This is a legacy header - all kernel code includes <uapi/asm/sigcontext.h> directly. */ - /* - * fpstate is really (struct _fpstate *) or (struct _xstate *) - * depending on the FP_XSTATE_MAGIC1 encoded in the SW reserved - * bytes of (struct _fpstate) and FP_XSTATE_MAGIC2 present at the end - * of extended memory layout. See comments at the definition of - * (struct _fpx_sw_bytes) - */ - void __user *fpstate; /* zero when no FPU/extended context */ - unsigned long oldmask; - unsigned long cr2; -}; -#else /* __i386__ */ -struct sigcontext { - unsigned long r8; - unsigned long r9; - unsigned long r10; - unsigned long r11; - unsigned long r12; - unsigned long r13; - unsigned long r14; - unsigned long r15; - unsigned long di; - unsigned long si; - unsigned long bp; - unsigned long bx; - unsigned long dx; - unsigned long ax; - unsigned long cx; - unsigned long sp; - unsigned long ip; - unsigned long flags; - unsigned short cs; - unsigned short gs; - unsigned short fs; - unsigned short __pad0; - unsigned long err; - unsigned long trapno; - unsigned long oldmask; - unsigned long cr2; +#include <uapi/asm/sigcontext.h> - /* - * fpstate is really (struct _fpstate *) or (struct _xstate *) - * depending on the FP_XSTATE_MAGIC1 encoded in the SW reserved - * bytes of (struct _fpstate) and FP_XSTATE_MAGIC2 present at the end - * of extended memory layout. See comments at the definition of - * (struct _fpx_sw_bytes) - */ - void __user *fpstate; /* zero when no FPU/extended context */ - unsigned long reserved1[8]; -}; -#endif /* !__i386__ */ #endif /* _ASM_X86_SIGCONTEXT_H */ diff --git a/arch/x86/include/asm/sigframe.h b/arch/x86/include/asm/sigframe.h index 7c7c27c97daa..34edd1650bae 100644 --- a/arch/x86/include/asm/sigframe.h +++ b/arch/x86/include/asm/sigframe.h @@ -1,15 +1,14 @@ #ifndef _ASM_X86_SIGFRAME_H #define _ASM_X86_SIGFRAME_H -#include <asm/sigcontext.h> +#include <uapi/asm/sigcontext.h> #include <asm/siginfo.h> #include <asm/ucontext.h> +#include <linux/compat.h> #ifdef CONFIG_X86_32 #define sigframe_ia32 sigframe #define rt_sigframe_ia32 rt_sigframe -#define sigcontext_ia32 sigcontext -#define _fpstate_ia32 _fpstate #define ucontext_ia32 ucontext #else /* !CONFIG_X86_32 */ @@ -23,7 +22,7 @@ struct sigframe_ia32 { u32 pretcode; int sig; - struct sigcontext_ia32 sc; + struct sigcontext_32 sc; /* * fpstate is unused. fpstate is moved/allocated after * retcode[] below. This movement allows to have the FP state and the @@ -32,7 +31,7 @@ struct sigframe_ia32 { * the offset of extramask[] in the sigframe and thus prevent any * legacy application accessing/modifying it. */ - struct _fpstate_ia32 fpstate_unused; + struct _fpstate_32 fpstate_unused; #ifdef CONFIG_IA32_EMULATION unsigned int extramask[_COMPAT_NSIG_WORDS-1]; #else /* !CONFIG_IA32_EMULATION */ @@ -69,6 +68,15 @@ struct rt_sigframe { #ifdef CONFIG_X86_X32_ABI +struct ucontext_x32 { + unsigned int uc_flags; + unsigned int uc_link; + compat_stack_t uc_stack; + unsigned int uc__pad0; /* needed for alignment */ + struct sigcontext uc_mcontext; /* the 64-bit sigcontext type */ + compat_sigset_t uc_sigmask; /* mask last for extensibility */ +}; + struct rt_sigframe_x32 { u64 pretcode; struct ucontext_x32 uc; diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h index 31eab867e6d3..2138c9ae19ee 100644 --- a/arch/x86/include/asm/signal.h +++ b/arch/x86/include/asm/signal.h @@ -30,11 +30,11 @@ typedef sigset_t compat_sigset_t; #endif /* __ASSEMBLY__ */ #include <uapi/asm/signal.h> #ifndef __ASSEMBLY__ -extern void do_notify_resume(struct pt_regs *, void *, __u32); +extern void do_signal(struct pt_regs *regs); #define __ARCH_HAS_SA_RESTORER -#include <asm/sigcontext.h> +#include <uapi/asm/sigcontext.h> #ifdef __i386__ diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 222a6a3ca2b5..dfcf0727623b 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -21,15 +21,6 @@ extern int smp_num_siblings; extern unsigned int num_processors; -static inline bool cpu_has_ht_siblings(void) -{ - bool has_siblings = false; -#ifdef CONFIG_SMP - has_siblings = cpu_has_ht && smp_num_siblings > 1; -#endif - return has_siblings; -} - DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map); DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map); /* cpus sharing the last level cache: */ @@ -74,9 +65,6 @@ struct smp_ops { extern void set_cpu_sibling_map(int cpu); #ifdef CONFIG_SMP -#ifndef CONFIG_PARAVIRT -#define startup_ipi_hook(phys_apicid, start_eip, start_esp) do { } while (0) -#endif extern struct smp_ops smp_ops; static inline void smp_send_stop(void) diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index c2e00bb2a136..58505f01962f 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -72,7 +72,7 @@ static __always_inline void boot_init_stack_canary(void) * on during the bootup the random pool has true entropy too. */ get_random_bytes(&canary, sizeof(canary)); - tsc = __native_read_tsc(); + tsc = rdtsc(); canary += tsc + (tsc << 32UL); current->stack_canary = canary; diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index e4661196994e..ff8b9a17dc4b 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -27,12 +27,11 @@ static __always_inline void *__inline_memcpy(void *to, const void *from, size_t function. */ #define __HAVE_ARCH_MEMCPY 1 +extern void *memcpy(void *to, const void *from, size_t len); extern void *__memcpy(void *to, const void *from, size_t len); #ifndef CONFIG_KMEMCHECK -#if (__GNUC__ == 4 && __GNUC_MINOR__ >= 3) || __GNUC__ > 4 -extern void *memcpy(void *to, const void *from, size_t len); -#else +#if (__GNUC__ == 4 && __GNUC_MINOR__ < 3) || __GNUC__ < 4 #define memcpy(dst, src, len) \ ({ \ size_t __len = (len); \ diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index d1793f06854d..8e9dbe7b73a1 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -15,6 +15,7 @@ struct saved_context { unsigned long cr0, cr2, cr3, cr4; u64 misc_enable; bool misc_enable_saved; + struct saved_msrs saved_msrs; struct desc_ptr gdt_desc; struct desc_ptr idt; u16 ldt; diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h index 7ebf0ebe4e68..6136a18152af 100644 --- a/arch/x86/include/asm/suspend_64.h +++ b/arch/x86/include/asm/suspend_64.h @@ -24,6 +24,7 @@ struct saved_context { unsigned long cr0, cr2, cr3, cr4, cr8; u64 misc_enable; bool misc_enable_saved; + struct saved_msrs saved_msrs; unsigned long efer; u16 gdt_pad; /* Unused */ struct desc_ptr gdt_desc; diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index d7f3b3b78ac3..751bf4b7bf11 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 "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t" -#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t" +#define SAVE_CONTEXT "pushq %%rbp ; movq %%rsi,%%rbp\n\t" +#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp\t" #define __EXTRA_CLOBBER \ , "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \ - "r12", "r13", "r14", "r15" + "r12", "r13", "r14", "r15", "flags" #ifdef CONFIG_CC_STACKPROTECTOR #define __switch_canary \ @@ -100,7 +100,11 @@ do { \ #define __switch_canary_iparam #endif /* CC_STACKPROTECTOR */ -/* Save restore flags to clear handle leaking NT */ +/* + * 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. + */ #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/syscall.h b/arch/x86/include/asm/syscall.h index d6a756ae04c8..999b7cd2e78c 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -20,9 +20,21 @@ #include <asm/thread_info.h> /* for TS_COMPAT */ #include <asm/unistd.h> -typedef void (*sys_call_ptr_t)(void); +typedef asmlinkage long (*sys_call_ptr_t)(unsigned long, unsigned long, + unsigned long, unsigned long, + unsigned long, unsigned long); extern const sys_call_ptr_t sys_call_table[]; +#if defined(CONFIG_X86_32) +#define ia32_sys_call_table sys_call_table +#define __NR_syscall_compat_max __NR_syscall_max +#define IA32_NR_syscalls NR_syscalls +#endif + +#if defined(CONFIG_IA32_EMULATION) +extern const sys_call_ptr_t ia32_sys_call_table[]; +#endif + /* * Only the low 32 bits of orig_ax are meaningful, so we return int. * This importantly ignores the high bits on 64-bit, so comparisons diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index 592a6a672e07..91dfcafe27a6 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -37,6 +37,7 @@ asmlinkage long sys_get_thread_area(struct user_desc __user *); asmlinkage unsigned long sys_sigreturn(void); /* kernel/vm86_32.c */ +struct vm86_struct; asmlinkage long sys_vm86old(struct vm86_struct __user *); asmlinkage long sys_vm86(unsigned long, unsigned long); diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 225ee545e1a0..c7b551028740 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -27,14 +27,17 @@ * Without this offset, that can result in a page fault. (We are * careful that, in this case, the value we read doesn't matter.) * - * In vm86 mode, the hardware frame is much longer still, but we neither - * access the extra members from NMI context, nor do we write such a - * frame at sp0 at all. + * In vm86 mode, the hardware frame is much longer still, so add 16 + * bytes to make room for the real-mode segments. * * x86_64 has a fixed-length stack frame. */ #ifdef CONFIG_X86_32 -# define TOP_OF_KERNEL_STACK_PADDING 8 +# ifdef CONFIG_VM86 +# define TOP_OF_KERNEL_STACK_PADDING 16 +# else +# define TOP_OF_KERNEL_STACK_PADDING 8 +# endif #else # define TOP_OF_KERNEL_STACK_PADDING 0 #endif @@ -54,9 +57,7 @@ struct thread_info { __u32 flags; /* low level flags */ __u32 status; /* thread synchronous flags */ __u32 cpu; /* current CPU */ - int saved_preempt_count; mm_segment_t addr_limit; - void __user *sysenter_return; unsigned int sig_on_uaccess_error:1; unsigned int uaccess_err:1; /* uaccess failed */ }; @@ -66,7 +67,6 @@ struct thread_info { .task = &tsk, \ .flags = 0, \ .cpu = 0, \ - .saved_preempt_count = INIT_PREEMPT_COUNT, \ .addr_limit = KERNEL_DS, \ } @@ -140,27 +140,11 @@ struct thread_info { _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT | \ _TIF_NOHZ) -/* work to do in syscall_trace_leave() */ -#define _TIF_WORK_SYSCALL_EXIT \ - (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP | \ - _TIF_SYSCALL_TRACEPOINT | _TIF_NOHZ) - -/* work to do on interrupt/exception return */ -#define _TIF_WORK_MASK \ - (0x0000FFFF & \ - ~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT| \ - _TIF_SINGLESTEP|_TIF_SECCOMP|_TIF_SYSCALL_EMU)) - /* work to do on any return to user space */ #define _TIF_ALLWORK_MASK \ ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT | \ _TIF_NOHZ) -/* Only used for 64 bit */ -#define _TIF_DO_NOTIFY_MASK \ - (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | \ - _TIF_USER_RETURN_NOTIFY | _TIF_UPROBE) - /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW \ (_TIF_IO_BITMAP|_TIF_NOTSC|_TIF_BLOCKSTEP) diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index cd791948b286..6df2029405a3 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -261,6 +261,12 @@ static inline void reset_lazy_tlbstate(void) #endif /* SMP */ +/* Not inlined due to inc_irq_stat not being defined yet */ +#define flush_tlb_local() { \ + inc_irq_stat(irq_tlb_count); \ + local_flush_tlb(); \ +} + #ifndef CONFIG_PARAVIRT #define flush_tlb_others(mask, mm, start, end) \ native_flush_tlb_others(mask, mm, start, end) diff --git a/arch/x86/include/asm/trace/mpx.h b/arch/x86/include/asm/trace/mpx.h index 173dd3ba108c..0f492fc50bce 100644 --- a/arch/x86/include/asm/trace/mpx.h +++ b/arch/x86/include/asm/trace/mpx.h @@ -11,7 +11,7 @@ TRACE_EVENT(mpx_bounds_register_exception, TP_PROTO(void *addr_referenced, - const struct bndreg *bndreg), + const struct mpx_bndreg *bndreg), TP_ARGS(addr_referenced, bndreg), TP_STRUCT__entry( @@ -44,7 +44,7 @@ TRACE_EVENT(mpx_bounds_register_exception, TRACE_EVENT(bounds_exception_mpx, - TP_PROTO(const struct bndcsr *bndcsr), + TP_PROTO(const struct mpx_bndcsr *bndcsr), TP_ARGS(bndcsr), TP_STRUCT__entry( @@ -116,7 +116,8 @@ TRACE_EVENT(mpx_new_bounds_table, /* * This gets used outside of MPX-specific code, so we need a stub. */ -static inline void trace_bounds_exception_mpx(const struct bndcsr *bndcsr) +static inline +void trace_bounds_exception_mpx(const struct mpx_bndcsr *bndcsr) { } diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index c5380bea2a36..c3496619740a 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -112,8 +112,8 @@ asmlinkage void smp_threshold_interrupt(void); asmlinkage void smp_deferred_error_interrupt(void); #endif -extern enum ctx_state ist_enter(struct pt_regs *regs); -extern void ist_exit(struct pt_regs *regs, enum ctx_state prev_state); +extern void ist_enter(struct pt_regs *regs); +extern void ist_exit(struct pt_regs *regs); extern void ist_begin_non_atomic(struct pt_regs *regs); extern void ist_end_non_atomic(void); diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index 94605c0e9cee..6d7c5479bcea 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -21,28 +21,12 @@ extern void disable_TSC(void); static inline cycles_t get_cycles(void) { - unsigned long long ret = 0; - #ifndef CONFIG_X86_TSC if (!cpu_has_tsc) return 0; #endif - rdtscll(ret); - - return ret; -} -static __always_inline cycles_t vget_cycles(void) -{ - /* - * We only do VDSOs on TSC capable CPUs, so this shouldn't - * access boot_cpu_data (which is not VDSO-safe): - */ -#ifndef CONFIG_X86_TSC - if (!cpu_has_tsc) - return 0; -#endif - return (cycles_t)__native_read_tsc(); + return rdtsc(); } extern void tsc_init(void); @@ -51,6 +35,7 @@ extern int unsynchronized_tsc(void); extern int check_tsc_unstable(void); extern int check_tsc_disabled(void); extern unsigned long native_calibrate_tsc(void); +extern unsigned long long native_sched_clock_from_tsc(u64 tsc); extern int tsc_clocksource_reliable; diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index a8df874f3e88..660458af425d 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -51,13 +51,13 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un * limit, not add it to the address). */ if (__builtin_constant_p(size)) - return addr > limit - size; + return unlikely(addr > limit - size); /* Arbitrary sizes? Be careful about overflow */ addr += size; - if (addr < size) + if (unlikely(addr < size)) return true; - return addr > limit; + return unlikely(addr > limit); } #define __range_not_ok(addr, size, limit) \ @@ -182,7 +182,7 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) : "=a" (__ret_gu), "=r" (__val_gu) \ : "0" (ptr), "i" (sizeof(*(ptr)))); \ (x) = (__force __typeof__(*(ptr))) __val_gu; \ - __ret_gu; \ + __builtin_expect(__ret_gu, 0); \ }) #define __put_user_x(size, x, ptr, __ret_pu) \ @@ -278,7 +278,7 @@ extern void __put_user_8(void); __put_user_x(X, __pu_val, ptr, __ret_pu); \ break; \ } \ - __ret_pu; \ + __builtin_expect(__ret_pu, 0); \ }) #define __put_user_size(x, ptr, size, retval, errret) \ @@ -401,7 +401,7 @@ do { \ ({ \ int __pu_err; \ __put_user_size((x), (ptr), (size), __pu_err, -EFAULT); \ - __pu_err; \ + __builtin_expect(__pu_err, 0); \ }) #define __get_user_nocheck(x, ptr, size) \ @@ -410,7 +410,7 @@ do { \ unsigned long __gu_val; \ __get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ - __gu_err; \ + __builtin_expect(__gu_err, 0); \ }) /* FIXME: this hack is definitely wrong -AK */ @@ -745,5 +745,14 @@ copy_to_user(void __user *to, const void *from, unsigned long n) #undef __copy_from_user_overflow #undef __copy_to_user_overflow +/* + * We rely on the nested NMI work to allow atomic faults from the NMI path; the + * nested NMI paths are careful to preserve CR2. + * + * Caller must use pagefault_enable/disable, or run in interrupt context, + * and also do a uaccess_ok() check + */ +#define __copy_from_user_nmi __copy_from_user_inatomic + #endif /* _ASM_X86_UACCESS_H */ diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index a00ad8f2a657..ea7074784cc4 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -609,7 +609,7 @@ struct uv_cpu_nmi_s { DECLARE_PER_CPU(struct uv_cpu_nmi_s, uv_cpu_nmi); -#define uv_hub_nmi (uv_cpu_nmi.hub) +#define uv_hub_nmi this_cpu_read(uv_cpu_nmi.hub) #define uv_cpu_nmi_per(cpu) (per_cpu(uv_cpu_nmi, cpu)) #define uv_hub_nmi_per(cpu) (uv_cpu_nmi_per(cpu).hub) diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index 8021bd28c0f1..deabaf9759b6 100644 --- a/arch/x86/include/asm/vdso.h +++ b/arch/x86/include/asm/vdso.h @@ -22,11 +22,12 @@ struct vdso_image { long sym_vvar_page; long sym_hpet_page; + long sym_pvclock_page; long sym_VDSO32_NOTE_MASK; long sym___kernel_sigreturn; long sym___kernel_rt_sigreturn; long sym___kernel_vsyscall; - long sym_VDSO32_SYSENTER_RETURN; + long sym_int80_landing_pad; }; #ifdef CONFIG_X86_64 @@ -38,13 +39,7 @@ extern const struct vdso_image vdso_image_x32; #endif #if defined CONFIG_X86_32 || defined CONFIG_COMPAT -extern const struct vdso_image vdso_image_32_int80; -#ifdef CONFIG_COMPAT -extern const struct vdso_image vdso_image_32_syscall; -#endif -extern const struct vdso_image vdso_image_32_sysenter; - -extern const struct vdso_image *selected_vdso32; +extern const struct vdso_image vdso_image_32; #endif extern void __init init_vdso_image(const struct vdso_image *image); diff --git a/arch/x86/include/asm/vm86.h b/arch/x86/include/asm/vm86.h index 1d8de3f3feca..1e491f3af317 100644 --- a/arch/x86/include/asm/vm86.h +++ b/arch/x86/include/asm/vm86.h @@ -1,7 +1,6 @@ #ifndef _ASM_X86_VM86_H #define _ASM_X86_VM86_H - #include <asm/ptrace.h> #include <uapi/asm/vm86.h> @@ -28,43 +27,49 @@ struct kernel_vm86_regs { unsigned short gs, __gsh; }; -struct kernel_vm86_struct { - struct kernel_vm86_regs regs; -/* - * the below part remains on the kernel stack while we are in VM86 mode. - * 'tss.esp0' then contains the address of VM86_TSS_ESP0 below, and when we - * get forced back from VM86, the CPU and "SAVE_ALL" will restore the above - * 'struct kernel_vm86_regs' with the then actual values. - * Therefore, pt_regs in fact points to a complete 'kernel_vm86_struct' - * in kernelspace, hence we need not reget the data from userspace. - */ -#define VM86_TSS_ESP0 flags +struct vm86 { + struct vm86plus_struct __user *user_vm86; + struct pt_regs regs32; + unsigned long veflags; + unsigned long veflags_mask; + unsigned long saved_sp0; + unsigned long flags; unsigned long screen_bitmap; unsigned long cpu_type; struct revectored_struct int_revectored; struct revectored_struct int21_revectored; struct vm86plus_info_struct vm86plus; - struct pt_regs *regs32; /* here we save the pointer to the old regs */ -/* - * The below is not part of the structure, but the stack layout continues - * this way. In front of 'return-eip' may be some data, depending on - * compilation, so we don't rely on this and save the pointer to 'oldregs' - * in 'regs32' above. - * However, with GCC-2.7.2 and the current CFLAGS you see exactly this: - - long return-eip; from call to vm86() - struct pt_regs oldregs; user space registers as saved by syscall - */ }; #ifdef CONFIG_VM86 void handle_vm86_fault(struct kernel_vm86_regs *, long); int handle_vm86_trap(struct kernel_vm86_regs *, long, int); -struct pt_regs *save_v86_state(struct kernel_vm86_regs *); +void save_v86_state(struct kernel_vm86_regs *, int); struct task_struct; + +#define free_vm86(t) do { \ + struct thread_struct *__t = (t); \ + if (__t->vm86 != NULL) { \ + kfree(__t->vm86); \ + __t->vm86 = NULL; \ + } \ +} while (0) + +/* + * Support for VM86 programs to request interrupts for + * real mode hardware drivers: + */ +#define FIRST_VM86_IRQ 3 +#define LAST_VM86_IRQ 15 + +static inline int invalid_vm86_irq(int irq) +{ + return irq < FIRST_VM86_IRQ || irq > LAST_VM86_IRQ; +} + void release_vm86_irqs(struct task_struct *); #else @@ -77,6 +82,10 @@ static inline int handle_vm86_trap(struct kernel_vm86_regs *a, long b, int c) return 0; } +static inline void save_v86_state(struct kernel_vm86_regs *a, int b) { } + +#define free_vm86(t) do { } while(0) + #endif /* CONFIG_VM86 */ #endif /* _ASM_X86_VM86_H */ diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index da772edd19ab..14c63c7e8337 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -47,6 +47,7 @@ #define CPU_BASED_MOV_DR_EXITING 0x00800000 #define CPU_BASED_UNCOND_IO_EXITING 0x01000000 #define CPU_BASED_USE_IO_BITMAPS 0x02000000 +#define CPU_BASED_MONITOR_TRAP_FLAG 0x08000000 #define CPU_BASED_USE_MSR_BITMAPS 0x10000000 #define CPU_BASED_MONITOR_EXITING 0x20000000 #define CPU_BASED_PAUSE_EXITING 0x40000000 @@ -71,7 +72,8 @@ #define SECONDARY_EXEC_SHADOW_VMCS 0x00004000 #define SECONDARY_EXEC_ENABLE_PML 0x00020000 #define SECONDARY_EXEC_XSAVES 0x00100000 - +#define SECONDARY_EXEC_PCOMMIT 0x00200000 +#define SECONDARY_EXEC_TSC_SCALING 0x02000000 #define PIN_BASED_EXT_INTR_MASK 0x00000001 #define PIN_BASED_NMI_EXITING 0x00000008 @@ -166,6 +168,8 @@ enum vmcs_field { VMWRITE_BITMAP = 0x00002028, XSS_EXIT_BITMAP = 0x0000202C, XSS_EXIT_BITMAP_HIGH = 0x0000202D, + TSC_MULTIPLIER = 0x00002032, + TSC_MULTIPLIER_HIGH = 0x00002033, GUEST_PHYSICAL_ADDRESS = 0x00002400, GUEST_PHYSICAL_ADDRESS_HIGH = 0x00002401, VMCS_LINK_POINTER = 0x00002800, @@ -367,29 +371,29 @@ enum vmcs_field { #define TYPE_PHYSICAL_APIC_EVENT (10 << 12) #define TYPE_PHYSICAL_APIC_INST (15 << 12) -/* segment AR */ -#define SEGMENT_AR_L_MASK (1 << 13) - -#define AR_TYPE_ACCESSES_MASK 1 -#define AR_TYPE_READABLE_MASK (1 << 1) -#define AR_TYPE_WRITEABLE_MASK (1 << 2) -#define AR_TYPE_CODE_MASK (1 << 3) -#define AR_TYPE_MASK 0x0f -#define AR_TYPE_BUSY_64_TSS 11 -#define AR_TYPE_BUSY_32_TSS 11 -#define AR_TYPE_BUSY_16_TSS 3 -#define AR_TYPE_LDT 2 - -#define AR_UNUSABLE_MASK (1 << 16) -#define AR_S_MASK (1 << 4) -#define AR_P_MASK (1 << 7) -#define AR_L_MASK (1 << 13) -#define AR_DB_MASK (1 << 14) -#define AR_G_MASK (1 << 15) -#define AR_DPL_SHIFT 5 -#define AR_DPL(ar) (((ar) >> AR_DPL_SHIFT) & 3) - -#define AR_RESERVD_MASK 0xfffe0f00 +/* segment AR in VMCS -- these are different from what LAR reports */ +#define VMX_SEGMENT_AR_L_MASK (1 << 13) + +#define VMX_AR_TYPE_ACCESSES_MASK 1 +#define VMX_AR_TYPE_READABLE_MASK (1 << 1) +#define VMX_AR_TYPE_WRITEABLE_MASK (1 << 2) +#define VMX_AR_TYPE_CODE_MASK (1 << 3) +#define VMX_AR_TYPE_MASK 0x0f +#define VMX_AR_TYPE_BUSY_64_TSS 11 +#define VMX_AR_TYPE_BUSY_32_TSS 11 +#define VMX_AR_TYPE_BUSY_16_TSS 3 +#define VMX_AR_TYPE_LDT 2 + +#define VMX_AR_UNUSABLE_MASK (1 << 16) +#define VMX_AR_S_MASK (1 << 4) +#define VMX_AR_P_MASK (1 << 7) +#define VMX_AR_L_MASK (1 << 13) +#define VMX_AR_DB_MASK (1 << 14) +#define VMX_AR_G_MASK (1 << 15) +#define VMX_AR_DPL_SHIFT 5 +#define VMX_AR_DPL(ar) (((ar) >> VMX_AR_DPL_SHIFT) & 3) + +#define VMX_AR_RESERVD_MASK 0xfffe0f00 #define TSS_PRIVATE_MEMSLOT (KVM_USER_MEM_SLOTS + 0) #define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT (KVM_USER_MEM_SLOTS + 1) @@ -415,6 +419,7 @@ enum vmcs_field { #define VMX_EPT_EXTENT_CONTEXT_BIT (1ull << 25) #define VMX_EPT_EXTENT_GLOBAL_BIT (1ull << 26) +#define VMX_VPID_INVVPID_BIT (1ull << 0) /* (32 - 32) */ #define VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT (1ull << 9) /* (41 - 32) */ #define VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT (1ull << 10) /* (42 - 32) */ diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 48d34d28f5a6..1ae89a2721d6 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -1,7 +1,6 @@ #ifndef _ASM_X86_PLATFORM_H #define _ASM_X86_PLATFORM_H -#include <asm/pgtable_types.h> #include <asm/bootparam.h> struct mpc_bus; @@ -83,13 +82,11 @@ struct x86_init_paging { * struct x86_init_timers - platform specific timer setup * @setup_perpcu_clockev: set up the per cpu clock event device for the * boot cpu - * @tsc_pre_init: platform function called before TSC init * @timer_init: initialize the platform timer (default PIT/HPET) * @wallclock_init: init the wallclock device */ struct x86_init_timers { void (*setup_percpu_clockev)(void); - void (*tsc_pre_init)(void); void (*timer_init)(void); void (*wallclock_init)(void); }; diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h index 608a79d5a466..e6911caf5bbf 100644 --- a/arch/x86/include/asm/xen/events.h +++ b/arch/x86/include/asm/xen/events.h @@ -20,4 +20,15 @@ static inline int xen_irqs_disabled(struct pt_regs *regs) /* No need for a barrier -- XCHG is a barrier on x86. */ #define xchg_xen_ulong(ptr, val) xchg((ptr), (val)) +extern int xen_have_vector_callback; + +/* + * Events delivered via platform PCI interrupts are always + * routed to vcpu 0 and hence cannot be rebound. + */ +static inline bool xen_support_evtchn_rebind(void) +{ + return (!xen_hvm_domain() || xen_have_vector_callback); +} + #endif /* _ASM_X86_XEN_EVENTS_H */ diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index ca08a27b90b3..3bcdcc84259d 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -310,10 +310,10 @@ HYPERVISOR_mca(struct xen_mc *mc_op) } static inline int -HYPERVISOR_dom0_op(struct xen_platform_op *platform_op) +HYPERVISOR_platform_op(struct xen_platform_op *op) { - platform_op->interface_version = XENPF_INTERFACE_VERSION; - return _hypercall1(int, dom0_op, platform_op); + op->interface_version = XENPF_INTERFACE_VERSION; + return _hypercall1(int, platform_op, op); } static inline int @@ -336,10 +336,10 @@ HYPERVISOR_update_descriptor(u64 ma, u64 desc) return _hypercall4(int, update_descriptor, ma, ma>>32, desc, desc>>32); } -static inline int +static inline long HYPERVISOR_memory_op(unsigned int cmd, void *arg) { - return _hypercall2(int, memory_op, cmd, arg); + return _hypercall2(long, memory_op, cmd, arg); } static inline int @@ -465,6 +465,12 @@ HYPERVISOR_tmem_op( return _hypercall1(int, tmem_op, op); } +static inline int +HYPERVISOR_xenpmu_op(unsigned int op, void *arg) +{ + return _hypercall2(int, xenpmu_op, op, arg); +} + static inline void MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set) { diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index d866959e5685..8b2d4bea9962 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -57,4 +57,9 @@ static inline bool xen_x2apic_para_available(void) } #endif +#ifdef CONFIG_HOTPLUG_CPU +void xen_arch_register_cpu(int num); +void xen_arch_unregister_cpu(int num); +#endif + #endif /* _ASM_X86_XEN_HYPERVISOR_H */ diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h index 3400dbaec3c3..62ca03ef5c65 100644 --- a/arch/x86/include/asm/xen/interface.h +++ b/arch/x86/include/asm/xen/interface.h @@ -3,12 +3,38 @@ * * Guest OS interface to x86 Xen. * - * Copyright (c) 2004, K A Fraser + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * Copyright (c) 2004-2006, K A Fraser */ #ifndef _ASM_X86_XEN_INTERFACE_H #define _ASM_X86_XEN_INTERFACE_H +/* + * XEN_GUEST_HANDLE represents a guest pointer, when passed as a field + * in a struct in memory. + * XEN_GUEST_HANDLE_PARAM represent a guest pointer, when passed as an + * hypercall argument. + * XEN_GUEST_HANDLE_PARAM and XEN_GUEST_HANDLE are the same on X86 but + * they might not be on other architectures. + */ #ifdef __XEN__ #define __DEFINE_GUEST_HANDLE(name, type) \ typedef struct { type *p; } __guest_handle_ ## name @@ -88,13 +114,16 @@ DEFINE_GUEST_HANDLE(xen_ulong_t); * start of the GDT because some stupid OSes export hard-coded selector values * in their ABI. These hard-coded values are always near the start of the GDT, * so Xen places itself out of the way, at the far end of the GDT. + * + * NB The LDT is set using the MMUEXT_SET_LDT op of HYPERVISOR_mmuext_op */ #define FIRST_RESERVED_GDT_PAGE 14 #define FIRST_RESERVED_GDT_BYTE (FIRST_RESERVED_GDT_PAGE * 4096) #define FIRST_RESERVED_GDT_ENTRY (FIRST_RESERVED_GDT_BYTE / 8) /* - * Send an array of these to HYPERVISOR_set_trap_table() + * Send an array of these to HYPERVISOR_set_trap_table(). + * Terminate the array with a sentinel entry, with traps[].address==0. * The privilege level specifies which modes may enter a trap via a software * interrupt. On x86/64, since rings 1 and 2 are unavailable, we allocate * privilege levels as follows: @@ -118,10 +147,41 @@ struct trap_info { DEFINE_GUEST_HANDLE_STRUCT(trap_info); struct arch_shared_info { - unsigned long max_pfn; /* max pfn that appears in table */ - /* Frame containing list of mfns containing list of mfns containing p2m. */ - unsigned long pfn_to_mfn_frame_list_list; - unsigned long nmi_reason; + /* + * Number of valid entries in the p2m table(s) anchored at + * pfn_to_mfn_frame_list_list and/or p2m_vaddr. + */ + unsigned long max_pfn; + /* + * Frame containing list of mfns containing list of mfns containing p2m. + * A value of 0 indicates it has not yet been set up, ~0 indicates it + * has been set to invalid e.g. due to the p2m being too large for the + * 3-level p2m tree. In this case the linear mapper p2m list anchored + * at p2m_vaddr is to be used. + */ + xen_pfn_t pfn_to_mfn_frame_list_list; + unsigned long nmi_reason; + /* + * Following three fields are valid if p2m_cr3 contains a value + * different from 0. + * p2m_cr3 is the root of the address space where p2m_vaddr is valid. + * p2m_cr3 is in the same format as a cr3 value in the vcpu register + * state and holds the folded machine frame number (via xen_pfn_to_cr3) + * of a L3 or L4 page table. + * p2m_vaddr holds the virtual address of the linear p2m list. All + * entries in the range [0...max_pfn[ are accessible via this pointer. + * p2m_generation will be incremented by the guest before and after each + * change of the mappings of the p2m list. p2m_generation starts at 0 + * and a value with the least significant bit set indicates that a + * mapping update is in progress. This allows guest external software + * (e.g. in Dom0) to verify that read mappings are consistent and + * whether they have changed since the last check. + * Modifying a p2m element in the linear p2m list is allowed via an + * atomic write only. + */ + unsigned long p2m_cr3; /* cr3 value of the p2m address space */ + unsigned long p2m_vaddr; /* virtual address of the p2m list */ + unsigned long p2m_generation; /* generation count of p2m mapping */ }; #endif /* !__ASSEMBLY__ */ @@ -137,13 +197,31 @@ struct arch_shared_info { /* * The following is all CPU context. Note that the fpu_ctxt block is filled * in by FXSAVE if the CPU has feature FXSR; otherwise FSAVE is used. + * + * Also note that when calling DOMCTL_setvcpucontext and VCPU_initialise + * for HVM and PVH guests, not all information in this structure is updated: + * + * - For HVM guests, the structures read include: fpu_ctxt (if + * VGCT_I387_VALID is set), flags, user_regs, debugreg[*] + * + * - PVH guests are the same as HVM guests, but additionally use ctrlreg[3] to + * set cr3. All other fields not used should be set to 0. */ struct vcpu_guest_context { /* FPU registers come first so they can be aligned for FXSAVE/FXRSTOR. */ struct { char x[512]; } fpu_ctxt; /* User-level FPU registers */ -#define VGCF_I387_VALID (1<<0) -#define VGCF_HVM_GUEST (1<<1) -#define VGCF_IN_KERNEL (1<<2) +#define VGCF_I387_VALID (1<<0) +#define VGCF_IN_KERNEL (1<<2) +#define _VGCF_i387_valid 0 +#define VGCF_i387_valid (1<<_VGCF_i387_valid) +#define _VGCF_in_kernel 2 +#define VGCF_in_kernel (1<<_VGCF_in_kernel) +#define _VGCF_failsafe_disables_events 3 +#define VGCF_failsafe_disables_events (1<<_VGCF_failsafe_disables_events) +#define _VGCF_syscall_disables_events 4 +#define VGCF_syscall_disables_events (1<<_VGCF_syscall_disables_events) +#define _VGCF_online 5 +#define VGCF_online (1<<_VGCF_online) unsigned long flags; /* VGCF_* flags */ struct cpu_user_regs user_regs; /* User-level CPU registers */ struct trap_info trap_ctxt[256]; /* Virtual IDT */ @@ -172,6 +250,129 @@ struct vcpu_guest_context { #endif }; DEFINE_GUEST_HANDLE_STRUCT(vcpu_guest_context); + +/* AMD PMU registers and structures */ +struct xen_pmu_amd_ctxt { + /* + * Offsets to counter and control MSRs (relative to xen_pmu_arch.c.amd). + * For PV(H) guests these fields are RO. + */ + uint32_t counters; + uint32_t ctrls; + + /* Counter MSRs */ +#if defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + uint64_t regs[]; +#elif defined(__GNUC__) + uint64_t regs[0]; +#endif +}; + +/* Intel PMU registers and structures */ +struct xen_pmu_cntr_pair { + uint64_t counter; + uint64_t control; +}; + +struct xen_pmu_intel_ctxt { + /* + * Offsets to fixed and architectural counter MSRs (relative to + * xen_pmu_arch.c.intel). + * For PV(H) guests these fields are RO. + */ + uint32_t fixed_counters; + uint32_t arch_counters; + + /* PMU registers */ + uint64_t global_ctrl; + uint64_t global_ovf_ctrl; + uint64_t global_status; + uint64_t fixed_ctrl; + uint64_t ds_area; + uint64_t pebs_enable; + uint64_t debugctl; + + /* Fixed and architectural counter MSRs */ +#if defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + uint64_t regs[]; +#elif defined(__GNUC__) + uint64_t regs[0]; +#endif +}; + +/* Sampled domain's registers */ +struct xen_pmu_regs { + uint64_t ip; + uint64_t sp; + uint64_t flags; + uint16_t cs; + uint16_t ss; + uint8_t cpl; + uint8_t pad[3]; +}; + +/* PMU flags */ +#define PMU_CACHED (1<<0) /* PMU MSRs are cached in the context */ +#define PMU_SAMPLE_USER (1<<1) /* Sample is from user or kernel mode */ +#define PMU_SAMPLE_REAL (1<<2) /* Sample is from realmode */ +#define PMU_SAMPLE_PV (1<<3) /* Sample from a PV guest */ + +/* + * Architecture-specific information describing state of the processor at + * the time of PMU interrupt. + * Fields of this structure marked as RW for guest should only be written by + * the guest when PMU_CACHED bit in pmu_flags is set (which is done by the + * hypervisor during PMU interrupt). Hypervisor will read updated data in + * XENPMU_flush hypercall and clear PMU_CACHED bit. + */ +struct xen_pmu_arch { + union { + /* + * Processor's registers at the time of interrupt. + * WO for hypervisor, RO for guests. + */ + struct xen_pmu_regs regs; + /* + * Padding for adding new registers to xen_pmu_regs in + * the future + */ +#define XENPMU_REGS_PAD_SZ 64 + uint8_t pad[XENPMU_REGS_PAD_SZ]; + } r; + + /* WO for hypervisor, RO for guest */ + uint64_t pmu_flags; + + /* + * APIC LVTPC register. + * RW for both hypervisor and guest. + * Only APIC_LVT_MASKED bit is loaded by the hypervisor into hardware + * during XENPMU_flush or XENPMU_lvtpc_set. + */ + union { + uint32_t lapic_lvtpc; + uint64_t pad; + } l; + + /* + * Vendor-specific PMU registers. + * RW for both hypervisor and guest (see exceptions above). + * Guest's updates to this field are verified and then loaded by the + * hypervisor into hardware during XENPMU_flush + */ + union { + struct xen_pmu_amd_ctxt amd; + struct xen_pmu_intel_ctxt intel; + + /* + * Padding for contexts (fixed parts only, does not include + * MSR banks that are specified by offsets) + */ +#define XENPMU_CTXT_PAD_SZ 128 + uint8_t pad[XENPMU_CTXT_PAD_SZ]; + } c; +}; + #endif /* !__ASSEMBLY__ */ /* diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index c44a5d53e464..f5fb840b43e8 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -12,7 +12,7 @@ #include <asm/pgtable.h> #include <xen/interface/xen.h> -#include <xen/grant_table.h> +#include <xen/interface/grant_table.h> #include <xen/features.h> /* Xen machine address */ @@ -35,9 +35,7 @@ typedef struct xpaddr { #define FOREIGN_FRAME(m) ((m) | FOREIGN_FRAME_BIT) #define IDENTITY_FRAME(m) ((m) | IDENTITY_FRAME_BIT) -/* Maximum amount of memory we can handle in a domain in pages */ -#define MAX_DOMAIN_PAGES \ - ((unsigned long)((u64)CONFIG_XEN_MAX_DOMAIN_MEMORY * 1024 * 1024 * 1024 / PAGE_SIZE)) +#define P2M_PER_PAGE (PAGE_SIZE / sizeof(unsigned long)) extern unsigned long *machine_to_phys_mapping; extern unsigned long machine_to_phys_nr; @@ -45,11 +43,13 @@ extern unsigned long *xen_p2m_addr; extern unsigned long xen_p2m_size; extern unsigned long xen_max_p2m_pfn; +extern int xen_alloc_p2m_entry(unsigned long pfn); + extern unsigned long get_phys_to_machine(unsigned long pfn); extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn); extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn); -extern unsigned long set_phys_range_identity(unsigned long pfn_s, - unsigned long pfn_e); +extern unsigned long __init set_phys_range_identity(unsigned long pfn_s, + unsigned long pfn_e); extern int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, struct gnttab_map_grant_ref *kmap_ops, @@ -103,6 +103,11 @@ static inline unsigned long pfn_to_mfn(unsigned long pfn) { unsigned long mfn; + /* + * Some x86 code are still using pfn_to_mfn instead of + * pfn_to_mfn. This will have to be removed when we figured + * out which call. + */ if (xen_feature(XENFEAT_auto_translated_physmap)) return pfn; @@ -149,6 +154,11 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn) { unsigned long pfn; + /* + * Some x86 code are still using mfn_to_pfn instead of + * gfn_to_pfn. This will have to be removed when we figure + * out which call. + */ if (xen_feature(XENFEAT_auto_translated_physmap)) return mfn; @@ -178,6 +188,27 @@ static inline xpaddr_t machine_to_phys(xmaddr_t machine) return XPADDR(PFN_PHYS(mfn_to_pfn(PFN_DOWN(machine.maddr))) | offset); } +/* Pseudo-physical <-> Guest conversion */ +static inline unsigned long pfn_to_gfn(unsigned long pfn) +{ + if (xen_feature(XENFEAT_auto_translated_physmap)) + return pfn; + else + return pfn_to_mfn(pfn); +} + +static inline unsigned long gfn_to_pfn(unsigned long gfn) +{ + if (xen_feature(XENFEAT_auto_translated_physmap)) + return gfn; + else + return mfn_to_pfn(gfn); +} + +/* Pseudo-physical <-> Bus conversion */ +#define pfn_to_bfn(pfn) pfn_to_gfn(pfn) +#define bfn_to_pfn(bfn) gfn_to_pfn(bfn) + /* * We detect special mappings in one of two ways: * 1. If the MFN is an I/O page then Xen will set the m2p entry @@ -198,7 +229,7 @@ static inline xpaddr_t machine_to_phys(xmaddr_t machine) * require. In all the cases we care about, the FOREIGN_FRAME bit is * masked (e.g., pfn_to_mfn()) so behaviour there is correct. */ -static inline unsigned long mfn_to_local_pfn(unsigned long mfn) +static inline unsigned long bfn_to_local_pfn(unsigned long mfn) { unsigned long pfn; @@ -217,6 +248,10 @@ static inline unsigned long mfn_to_local_pfn(unsigned long mfn) #define virt_to_mfn(v) (pfn_to_mfn(virt_to_pfn(v))) #define mfn_to_virt(m) (__va(mfn_to_pfn(m) << PAGE_SHIFT)) +/* VIRT <-> GUEST conversion */ +#define virt_to_gfn(v) (pfn_to_gfn(virt_to_pfn(v))) +#define gfn_to_virt(g) (__va(gfn_to_pfn(g) << PAGE_SHIFT)) + static inline unsigned long pte_mfn(pte_t pte) { return (pte.pte & PTE_PFN_MASK) >> PAGE_SHIFT; @@ -263,8 +298,8 @@ void make_lowmem_page_readwrite(void *vaddr); #define xen_unmap(cookie) iounmap((cookie)) static inline bool xen_arch_need_swiotlb(struct device *dev, - unsigned long pfn, - unsigned long mfn) + phys_addr_t phys, + dma_addr_t dev_addr) { return false; } diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h index 5a08bc8bff33..c54beb44c4c1 100644 --- a/arch/x86/include/asm/xor_32.h +++ b/arch/x86/include/asm/xor_32.h @@ -553,7 +553,7 @@ do { \ if (cpu_has_xmm) { \ xor_speed(&xor_block_pIII_sse); \ xor_speed(&xor_block_sse_pf64); \ - } else if (cpu_has_mmx) { \ + } else if (boot_cpu_has(X86_FEATURE_MMX)) { \ xor_speed(&xor_block_pII_mmx); \ xor_speed(&xor_block_p5_mmx); \ } else { \ diff --git a/arch/x86/include/uapi/asm/bitsperlong.h b/arch/x86/include/uapi/asm/bitsperlong.h index b0ae1c4dc791..217909b4d6f5 100644 --- a/arch/x86/include/uapi/asm/bitsperlong.h +++ b/arch/x86/include/uapi/asm/bitsperlong.h @@ -1,7 +1,7 @@ #ifndef __ASM_X86_BITSPERLONG_H #define __ASM_X86_BITSPERLONG_H -#ifdef __x86_64__ +#if defined(__x86_64__) && !defined(__ILP32__) # define __BITS_PER_LONG 64 #else # define __BITS_PER_LONG 32 diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index ab456dc233b5..329254373479 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -120,7 +120,7 @@ struct boot_params { __u8 _pad3[16]; /* 0x070 */ __u8 hd0_info[16]; /* obsolete! */ /* 0x080 */ __u8 hd1_info[16]; /* obsolete! */ /* 0x090 */ - struct sys_desc_table sys_desc_table; /* 0x0a0 */ + struct sys_desc_table sys_desc_table; /* obsolete! */ /* 0x0a0 */ struct olpc_ofw_header olpc_ofw_header; /* 0x0b0 */ __u32 ext_ramdisk_image; /* 0x0c0 */ __u32 ext_ramdisk_size; /* 0x0c4 */ diff --git a/arch/x86/include/uapi/asm/e820.h b/arch/x86/include/uapi/asm/e820.h index 0f457e6eab18..9dafe59cf6e2 100644 --- a/arch/x86/include/uapi/asm/e820.h +++ b/arch/x86/include/uapi/asm/e820.h @@ -37,7 +37,7 @@ /* * This is a non-standardized way to represent ADR or NVDIMM regions that * persist over a reboot. The kernel will ignore their special capabilities - * unless the CONFIG_X86_PMEM_LEGACY=y option is set. + * unless the CONFIG_X86_PMEM_LEGACY option is set. * * ( Note that older platforms also used 6 for the same type of memory, * but newer versions switched to 12 as 6 was assigned differently. Some diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h index f36d56bd7632..7956412d09bd 100644 --- a/arch/x86/include/uapi/asm/hyperv.h +++ b/arch/x86/include/uapi/asm/hyperv.h @@ -27,6 +27,8 @@ #define HV_X64_MSR_VP_RUNTIME_AVAILABLE (1 << 0) /* Partition Reference Counter (HV_X64_MSR_TIME_REF_COUNT) available*/ #define HV_X64_MSR_TIME_REF_COUNT_AVAILABLE (1 << 1) +/* Partition reference TSC MSR is available */ +#define HV_X64_MSR_REFERENCE_TSC_AVAILABLE (1 << 9) /* A partition's reference time stamp counter (TSC) page */ #define HV_X64_MSR_REFERENCE_TSC 0x40000021 @@ -151,6 +153,12 @@ /* MSR used to provide vcpu index */ #define HV_X64_MSR_VP_INDEX 0x40000002 +/* MSR used to reset the guest OS. */ +#define HV_X64_MSR_RESET 0x40000003 + +/* MSR used to provide vcpu runtime in 100ns units */ +#define HV_X64_MSR_VP_RUNTIME 0x40000010 + /* MSR used to read the per-partition time reference counter */ #define HV_X64_MSR_TIME_REF_COUNT 0x40000020 @@ -249,4 +257,108 @@ typedef struct _HV_REFERENCE_TSC_PAGE { __s64 tsc_offset; } HV_REFERENCE_TSC_PAGE, *PHV_REFERENCE_TSC_PAGE; +/* Define the number of synthetic interrupt sources. */ +#define HV_SYNIC_SINT_COUNT (16) +/* Define the expected SynIC version. */ +#define HV_SYNIC_VERSION_1 (0x1) + +#define HV_SYNIC_CONTROL_ENABLE (1ULL << 0) +#define HV_SYNIC_SIMP_ENABLE (1ULL << 0) +#define HV_SYNIC_SIEFP_ENABLE (1ULL << 0) +#define HV_SYNIC_SINT_MASKED (1ULL << 16) +#define HV_SYNIC_SINT_AUTO_EOI (1ULL << 17) +#define HV_SYNIC_SINT_VECTOR_MASK (0xFF) + +#define HV_SYNIC_STIMER_COUNT (4) + +/* Define synthetic interrupt controller message constants. */ +#define HV_MESSAGE_SIZE (256) +#define HV_MESSAGE_PAYLOAD_BYTE_COUNT (240) +#define HV_MESSAGE_PAYLOAD_QWORD_COUNT (30) + +/* Define hypervisor message types. */ +enum hv_message_type { + HVMSG_NONE = 0x00000000, + + /* Memory access messages. */ + HVMSG_UNMAPPED_GPA = 0x80000000, + HVMSG_GPA_INTERCEPT = 0x80000001, + + /* Timer notification messages. */ + HVMSG_TIMER_EXPIRED = 0x80000010, + + /* Error messages. */ + HVMSG_INVALID_VP_REGISTER_VALUE = 0x80000020, + HVMSG_UNRECOVERABLE_EXCEPTION = 0x80000021, + HVMSG_UNSUPPORTED_FEATURE = 0x80000022, + + /* Trace buffer complete messages. */ + HVMSG_EVENTLOG_BUFFERCOMPLETE = 0x80000040, + + /* Platform-specific processor intercept messages. */ + HVMSG_X64_IOPORT_INTERCEPT = 0x80010000, + HVMSG_X64_MSR_INTERCEPT = 0x80010001, + HVMSG_X64_CPUID_INTERCEPT = 0x80010002, + HVMSG_X64_EXCEPTION_INTERCEPT = 0x80010003, + HVMSG_X64_APIC_EOI = 0x80010004, + HVMSG_X64_LEGACY_FP_ERROR = 0x80010005 +}; + +/* Define synthetic interrupt controller message flags. */ +union hv_message_flags { + __u8 asu8; + struct { + __u8 msg_pending:1; + __u8 reserved:7; + }; +}; + +/* Define port identifier type. */ +union hv_port_id { + __u32 asu32; + struct { + __u32 id:24; + __u32 reserved:8; + } u; +}; + +/* Define synthetic interrupt controller message header. */ +struct hv_message_header { + __u32 message_type; + __u8 payload_size; + union hv_message_flags message_flags; + __u8 reserved[2]; + union { + __u64 sender; + union hv_port_id port; + }; +}; + +/* Define synthetic interrupt controller message format. */ +struct hv_message { + struct hv_message_header header; + union { + __u64 payload[HV_MESSAGE_PAYLOAD_QWORD_COUNT]; + } u; +}; + +/* Define the synthetic interrupt message page layout. */ +struct hv_message_page { + struct hv_message sint_message[HV_SYNIC_SINT_COUNT]; +}; + +/* Define timer message payload structure. */ +struct hv_timer_message_payload { + __u32 timer_index; + __u32 reserved; + __u64 expiration_time; /* When the timer expired */ + __u64 delivery_time; /* When the message was delivered */ +}; + +#define HV_STIMER_ENABLE (1ULL << 0) +#define HV_STIMER_PERIODIC (1ULL << 1) +#define HV_STIMER_LAZY (1ULL << 2) +#define HV_STIMER_AUTOENABLE (1ULL << 3) +#define HV_STIMER_SINT(config) (__u8)(((config) >> 16) & 0x0F) + #endif diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h index a0eab85ce7b8..2184943341bf 100644 --- a/arch/x86/include/uapi/asm/mce.h +++ b/arch/x86/include/uapi/asm/mce.h @@ -2,7 +2,7 @@ #define _UAPI_ASM_X86_MCE_H #include <linux/types.h> -#include <asm/ioctls.h> +#include <linux/ioctl.h> /* Fields are zero when not available */ struct mce { @@ -15,7 +15,8 @@ struct mce { __u64 time; /* wall time_t when error was detected */ __u8 cpuvendor; /* cpu vendor as encoded in system.h */ __u8 inject_flags; /* software inject flags */ - __u16 pad; + __u8 severity; + __u8 pad; __u32 cpuid; /* CPUID 1 EAX */ __u8 cs; /* code segment */ __u8 bank; /* machine check bank */ diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h index 180a0c3c224d..79887abcb5e1 100644 --- a/arch/x86/include/uapi/asm/processor-flags.h +++ b/arch/x86/include/uapi/asm/processor-flags.h @@ -37,8 +37,6 @@ #define X86_EFLAGS_VM _BITUL(X86_EFLAGS_VM_BIT) #define X86_EFLAGS_AC_BIT 18 /* Alignment Check/Access Control */ #define X86_EFLAGS_AC _BITUL(X86_EFLAGS_AC_BIT) -#define X86_EFLAGS_AC_BIT 18 /* Alignment Check/Access Control */ -#define X86_EFLAGS_AC _BITUL(X86_EFLAGS_AC_BIT) #define X86_EFLAGS_VIF_BIT 19 /* Virtual Interrupt Flag */ #define X86_EFLAGS_VIF _BITUL(X86_EFLAGS_VIF_BIT) #define X86_EFLAGS_VIP_BIT 20 /* Virtual Interrupt Pending */ diff --git a/arch/x86/include/uapi/asm/sigcontext.h b/arch/x86/include/uapi/asm/sigcontext.h index 40836a9a7250..d485232f1e9f 100644 --- a/arch/x86/include/uapi/asm/sigcontext.h +++ b/arch/x86/include/uapi/asm/sigcontext.h @@ -1,221 +1,360 @@ #ifndef _UAPI_ASM_X86_SIGCONTEXT_H #define _UAPI_ASM_X86_SIGCONTEXT_H +/* + * Linux signal context definitions. The sigcontext includes a complex + * hierarchy of CPU and FPU state, available to user-space (on the stack) when + * a signal handler is executed. + * + * As over the years this ABI grew from its very simple roots towards + * supporting more and more CPU state organically, some of the details (which + * were rather clever hacks back in the days) became a bit quirky by today. + * + * The current ABI includes flexible provisions for future extensions, so we + * won't have to grow new quirks for quite some time. Promise! + */ + #include <linux/compiler.h> #include <linux/types.h> -#define FP_XSTATE_MAGIC1 0x46505853U -#define FP_XSTATE_MAGIC2 0x46505845U -#define FP_XSTATE_MAGIC2_SIZE sizeof(FP_XSTATE_MAGIC2) +#define FP_XSTATE_MAGIC1 0x46505853U +#define FP_XSTATE_MAGIC2 0x46505845U +#define FP_XSTATE_MAGIC2_SIZE sizeof(FP_XSTATE_MAGIC2) /* - * bytes 464..511 in the current 512byte layout of fxsave/fxrstor frame - * are reserved for SW usage. On cpu's supporting xsave/xrstor, these bytes - * are used to extended the fpstate pointer in the sigcontext, which now - * includes the extended state information along with fpstate information. + * Bytes 464..511 in the current 512-byte layout of the FXSAVE/FXRSTOR frame + * are reserved for SW usage. On CPUs supporting XSAVE/XRSTOR, these bytes are + * used to extend the fpstate pointer in the sigcontext, which now includes the + * extended state information along with fpstate information. + * + * If sw_reserved.magic1 == FP_XSTATE_MAGIC1 then there's a + * sw_reserved.extended_size bytes large extended context area present. (The + * last 32-bit word of this extended area (at the + * fpstate+extended_size-FP_XSTATE_MAGIC2_SIZE address) is set to + * FP_XSTATE_MAGIC2 so that you can sanity check your size calculations.) * - * Presence of FP_XSTATE_MAGIC1 at the beginning of this SW reserved - * area and FP_XSTATE_MAGIC2 at the end of memory layout - * (extended_size - FP_XSTATE_MAGIC2_SIZE) indicates the presence of the - * extended state information in the memory layout pointed by the fpstate - * pointer in sigcontext. + * This extended area typically grows with newer CPUs that have larger and + * larger XSAVE areas. */ struct _fpx_sw_bytes { - __u32 magic1; /* FP_XSTATE_MAGIC1 */ - __u32 extended_size; /* total size of the layout referred by - * fpstate pointer in the sigcontext. - */ - __u64 xfeatures; - /* feature bit mask (including fp/sse/extended - * state) that is present in the memory - * layout. - */ - __u32 xstate_size; /* actual xsave state size, based on the - * features saved in the layout. - * 'extended_size' will be greater than - * 'xstate_size'. - */ - __u32 padding[7]; /* for future use. */ + /* + * If set to FP_XSTATE_MAGIC1 then this is an xstate context. + * 0 if a legacy frame. + */ + __u32 magic1; + + /* + * Total size of the fpstate area: + * + * - if magic1 == 0 then it's sizeof(struct _fpstate) + * - if magic1 == FP_XSTATE_MAGIC1 then it's sizeof(struct _xstate) + * plus extensions (if any) + */ + __u32 extended_size; + + /* + * Feature bit mask (including FP/SSE/extended state) that is present + * in the memory layout: + */ + __u64 xfeatures; + + /* + * Actual XSAVE state size, based on the xfeatures saved in the layout. + * 'extended_size' is greater than 'xstate_size': + */ + __u32 xstate_size; + + /* For future use: */ + __u32 padding[7]; }; -#ifdef __i386__ /* - * As documented in the iBCS2 standard.. - * - * The first part of "struct _fpstate" is just the normal i387 - * hardware setup, the extra "status" word is used to save the - * coprocessor status word before entering the handler. + * As documented in the iBCS2 standard: * - * Pentium III FXSR, SSE support - * Gareth Hughes <gareth@valinux.com>, May 2000 + * The first part of "struct _fpstate" is just the normal i387 hardware setup, + * the extra "status" word is used to save the coprocessor status word before + * entering the handler. * - * The FPU state data structure has had to grow to accommodate the - * extended FPU state required by the Streaming SIMD Extensions. - * There is no documented standard to accomplish this at the moment. + * The FPU state data structure has had to grow to accommodate the extended FPU + * state required by the Streaming SIMD Extensions. There is no documented + * standard to accomplish this at the moment. */ + +/* 10-byte legacy floating point register: */ struct _fpreg { - unsigned short significand[4]; - unsigned short exponent; + __u16 significand[4]; + __u16 exponent; }; +/* 16-byte floating point register: */ struct _fpxreg { - unsigned short significand[4]; - unsigned short exponent; - unsigned short padding[3]; + __u16 significand[4]; + __u16 exponent; + __u16 padding[3]; }; +/* 16-byte XMM register: */ struct _xmmreg { - unsigned long element[4]; + __u32 element[4]; }; -struct _fpstate { - /* Regular FPU environment */ - unsigned long cw; - unsigned long sw; - unsigned long tag; - unsigned long ipoff; - unsigned long cssel; - unsigned long dataoff; - unsigned long datasel; - struct _fpreg _st[8]; - unsigned short status; - unsigned short magic; /* 0xffff = regular FPU data only */ +#define X86_FXSR_MAGIC 0x0000 + +/* + * The 32-bit FPU frame: + */ +struct _fpstate_32 { + /* Legacy FPU environment: */ + __u32 cw; + __u32 sw; + __u32 tag; + __u32 ipoff; + __u32 cssel; + __u32 dataoff; + __u32 datasel; + struct _fpreg _st[8]; + __u16 status; + __u16 magic; /* 0xffff: regular FPU data only */ + /* 0x0000: FXSR FPU data */ /* FXSR FPU environment */ - unsigned long _fxsr_env[6]; /* FXSR FPU env is ignored */ - unsigned long mxcsr; - unsigned long reserved; - struct _fpxreg _fxsr_st[8]; /* FXSR FPU reg data is ignored */ - struct _xmmreg _xmm[8]; - unsigned long padding1[44]; + __u32 _fxsr_env[6]; /* FXSR FPU env is ignored */ + __u32 mxcsr; + __u32 reserved; + struct _fpxreg _fxsr_st[8]; /* FXSR FPU reg data is ignored */ + struct _xmmreg _xmm[8]; /* First 8 XMM registers */ + union { + __u32 padding1[44]; /* Second 8 XMM registers plus padding */ + __u32 padding[44]; /* Alias name for old user-space */ + }; union { - unsigned long padding2[12]; - struct _fpx_sw_bytes sw_reserved; /* represents the extended - * state info */ + __u32 padding2[12]; + struct _fpx_sw_bytes sw_reserved; /* Potential extended state is encoded here */ }; }; -#define X86_FXSR_MAGIC 0x0000 - -#ifndef __KERNEL__ /* - * User-space might still rely on the old definition: + * The 64-bit FPU frame. (FXSAVE format and later) + * + * Note1: If sw_reserved.magic1 == FP_XSTATE_MAGIC1 then the structure is + * larger: 'struct _xstate'. Note that 'struct _xstate' embedds + * 'struct _fpstate' so that you can always assume the _fpstate portion + * exists so that you can check the magic value. + * + * Note2: Reserved fields may someday contain valuable data. Always + * save/restore them when you change signal frames. */ -struct sigcontext { - unsigned short gs, __gsh; - unsigned short fs, __fsh; - unsigned short es, __esh; - unsigned short ds, __dsh; - unsigned long edi; - unsigned long esi; - unsigned long ebp; - unsigned long esp; - unsigned long ebx; - unsigned long edx; - unsigned long ecx; - unsigned long eax; - unsigned long trapno; - unsigned long err; - unsigned long eip; - unsigned short cs, __csh; - unsigned long eflags; - unsigned long esp_at_signal; - unsigned short ss, __ssh; - struct _fpstate __user *fpstate; - unsigned long oldmask; - unsigned long cr2; -}; -#endif /* !__KERNEL__ */ - -#else /* __i386__ */ - -/* FXSAVE frame */ -/* Note: reserved1/2 may someday contain valuable data. Always save/restore - them when you change signal frames. */ -struct _fpstate { - __u16 cwd; - __u16 swd; - __u16 twd; /* Note this is not the same as the - 32bit/x87/FSAVE twd */ - __u16 fop; - __u64 rip; - __u64 rdp; - __u32 mxcsr; - __u32 mxcsr_mask; - __u32 st_space[32]; /* 8*16 bytes for each FP-reg */ - __u32 xmm_space[64]; /* 16*16 bytes for each XMM-reg */ - __u32 reserved2[12]; +struct _fpstate_64 { + __u16 cwd; + __u16 swd; + /* Note this is not the same as the 32-bit/x87/FSAVE twd: */ + __u16 twd; + __u16 fop; + __u64 rip; + __u64 rdp; + __u32 mxcsr; + __u32 mxcsr_mask; + __u32 st_space[32]; /* 8x FP registers, 16 bytes each */ + __u32 xmm_space[64]; /* 16x XMM registers, 16 bytes each */ + __u32 reserved2[12]; union { - __u32 reserved3[12]; - struct _fpx_sw_bytes sw_reserved; /* represents the extended - * state information */ + __u32 reserved3[12]; + struct _fpx_sw_bytes sw_reserved; /* Potential extended state is encoded here */ }; }; -#ifndef __KERNEL__ -/* - * User-space might still rely on the old definition: - */ -struct sigcontext { - __u64 r8; - __u64 r9; - __u64 r10; - __u64 r11; - __u64 r12; - __u64 r13; - __u64 r14; - __u64 r15; - __u64 rdi; - __u64 rsi; - __u64 rbp; - __u64 rbx; - __u64 rdx; - __u64 rax; - __u64 rcx; - __u64 rsp; - __u64 rip; - __u64 eflags; /* RFLAGS */ - __u16 cs; - __u16 gs; - __u16 fs; - __u16 __pad0; - __u64 err; - __u64 trapno; - __u64 oldmask; - __u64 cr2; - struct _fpstate __user *fpstate; /* zero when no FPU context */ -#ifdef __ILP32__ - __u32 __fpstate_pad; +#ifdef __i386__ +# define _fpstate _fpstate_32 +#else +# define _fpstate _fpstate_64 #endif - __u64 reserved1[8]; -}; -#endif /* !__KERNEL__ */ - -#endif /* !__i386__ */ struct _header { - __u64 xfeatures; - __u64 reserved1[2]; - __u64 reserved2[5]; + __u64 xfeatures; + __u64 reserved1[2]; + __u64 reserved2[5]; }; struct _ymmh_state { - /* 16 * 16 bytes for each YMMH-reg */ - __u32 ymmh_space[64]; + /* 16x YMM registers, 16 bytes each: */ + __u32 ymmh_space[64]; }; /* - * Extended state pointed by the fpstate pointer in the sigcontext. - * In addition to the fpstate, information encoded in the xstate_hdr - * indicates the presence of other extended state information - * supported by the processor and OS. + * Extended state pointed to by sigcontext::fpstate. + * + * In addition to the fpstate, information encoded in _xstate::xstate_hdr + * indicates the presence of other extended state information supported + * by the CPU and kernel: */ struct _xstate { - struct _fpstate fpstate; - struct _header xstate_hdr; - struct _ymmh_state ymmh; - /* new processor state extensions go here */ + struct _fpstate fpstate; + struct _header xstate_hdr; + struct _ymmh_state ymmh; + /* New processor state extensions go here: */ +}; + +/* + * The 32-bit signal frame: + */ +struct sigcontext_32 { + __u16 gs, __gsh; + __u16 fs, __fsh; + __u16 es, __esh; + __u16 ds, __dsh; + __u32 di; + __u32 si; + __u32 bp; + __u32 sp; + __u32 bx; + __u32 dx; + __u32 cx; + __u32 ax; + __u32 trapno; + __u32 err; + __u32 ip; + __u16 cs, __csh; + __u32 flags; + __u32 sp_at_signal; + __u16 ss, __ssh; + + /* + * fpstate is really (struct _fpstate *) or (struct _xstate *) + * depending on the FP_XSTATE_MAGIC1 encoded in the SW reserved + * bytes of (struct _fpstate) and FP_XSTATE_MAGIC2 present at the end + * of extended memory layout. See comments at the definition of + * (struct _fpx_sw_bytes) + */ + __u32 fpstate; /* Zero when no FPU/extended context */ + __u32 oldmask; + __u32 cr2; +}; + +/* + * The 64-bit signal frame: + */ +struct sigcontext_64 { + __u64 r8; + __u64 r9; + __u64 r10; + __u64 r11; + __u64 r12; + __u64 r13; + __u64 r14; + __u64 r15; + __u64 di; + __u64 si; + __u64 bp; + __u64 bx; + __u64 dx; + __u64 ax; + __u64 cx; + __u64 sp; + __u64 ip; + __u64 flags; + __u16 cs; + __u16 gs; + __u16 fs; + __u16 __pad0; + __u64 err; + __u64 trapno; + __u64 oldmask; + __u64 cr2; + + /* + * fpstate is really (struct _fpstate *) or (struct _xstate *) + * depending on the FP_XSTATE_MAGIC1 encoded in the SW reserved + * bytes of (struct _fpstate) and FP_XSTATE_MAGIC2 present at the end + * of extended memory layout. See comments at the definition of + * (struct _fpx_sw_bytes) + */ + __u64 fpstate; /* Zero when no FPU/extended context */ + __u64 reserved1[8]; +}; + +/* + * Create the real 'struct sigcontext' type: + */ +#ifdef __KERNEL__ +# ifdef __i386__ +# define sigcontext sigcontext_32 +# else +# define sigcontext sigcontext_64 +# endif +#endif + +/* + * The old user-space sigcontext definition, just in case user-space still + * relies on it. The kernel definition (in asm/sigcontext.h) has unified + * field names but otherwise the same layout. + */ +#ifndef __KERNEL__ + +#define _fpstate_ia32 _fpstate_32 +#define sigcontext_ia32 sigcontext_32 + + +# ifdef __i386__ +struct sigcontext { + __u16 gs, __gsh; + __u16 fs, __fsh; + __u16 es, __esh; + __u16 ds, __dsh; + __u32 edi; + __u32 esi; + __u32 ebp; + __u32 esp; + __u32 ebx; + __u32 edx; + __u32 ecx; + __u32 eax; + __u32 trapno; + __u32 err; + __u32 eip; + __u16 cs, __csh; + __u32 eflags; + __u32 esp_at_signal; + __u16 ss, __ssh; + struct _fpstate __user *fpstate; + __u32 oldmask; + __u32 cr2; }; +# else /* __x86_64__: */ +struct sigcontext { + __u64 r8; + __u64 r9; + __u64 r10; + __u64 r11; + __u64 r12; + __u64 r13; + __u64 r14; + __u64 r15; + __u64 rdi; + __u64 rsi; + __u64 rbp; + __u64 rbx; + __u64 rdx; + __u64 rax; + __u64 rcx; + __u64 rsp; + __u64 rip; + __u64 eflags; /* RFLAGS */ + __u16 cs; + __u16 gs; + __u16 fs; + __u16 __pad0; + __u64 err; + __u64 trapno; + __u64 oldmask; + __u64 cr2; + struct _fpstate __user *fpstate; /* Zero when no FPU context */ +# ifdef __ILP32__ + __u32 __fpstate_pad; +# endif + __u64 reserved1[8]; +}; +# endif /* __x86_64__ */ +#endif /* !__KERNEL__ */ #endif /* _UAPI_ASM_X86_SIGCONTEXT_H */ diff --git a/arch/x86/include/uapi/asm/sigcontext32.h b/arch/x86/include/uapi/asm/sigcontext32.h index ad1478c4ae12..a92b0f0dc09e 100644 --- a/arch/x86/include/uapi/asm/sigcontext32.h +++ b/arch/x86/include/uapi/asm/sigcontext32.h @@ -1,77 +1,8 @@ #ifndef _ASM_X86_SIGCONTEXT32_H #define _ASM_X86_SIGCONTEXT32_H -#include <linux/types.h> +/* This is a legacy file - all the type definitions are in sigcontext.h: */ -/* signal context for 32bit programs. */ - -#define X86_FXSR_MAGIC 0x0000 - -struct _fpreg { - unsigned short significand[4]; - unsigned short exponent; -}; - -struct _fpxreg { - unsigned short significand[4]; - unsigned short exponent; - unsigned short padding[3]; -}; - -struct _xmmreg { - __u32 element[4]; -}; - -/* FSAVE frame with extensions */ -struct _fpstate_ia32 { - /* Regular FPU environment */ - __u32 cw; - __u32 sw; - __u32 tag; /* not compatible to 64bit twd */ - __u32 ipoff; - __u32 cssel; - __u32 dataoff; - __u32 datasel; - struct _fpreg _st[8]; - unsigned short status; - unsigned short magic; /* 0xffff = regular FPU data only */ - - /* FXSR FPU environment */ - __u32 _fxsr_env[6]; - __u32 mxcsr; - __u32 reserved; - struct _fpxreg _fxsr_st[8]; - struct _xmmreg _xmm[8]; /* It's actually 16 */ - __u32 padding[44]; - union { - __u32 padding2[12]; - struct _fpx_sw_bytes sw_reserved; - }; -}; - -struct sigcontext_ia32 { - unsigned short gs, __gsh; - unsigned short fs, __fsh; - unsigned short es, __esh; - unsigned short ds, __dsh; - unsigned int di; - unsigned int si; - unsigned int bp; - unsigned int sp; - unsigned int bx; - unsigned int dx; - unsigned int cx; - unsigned int ax; - unsigned int trapno; - unsigned int err; - unsigned int ip; - unsigned short cs, __csh; - unsigned int flags; - unsigned int sp_at_signal; - unsigned short ss, __ssh; - unsigned int fpstate; /* really (struct _fpstate_ia32 *) */ - unsigned int oldmask; - unsigned int cr2; -}; +#include <asm/sigcontext.h> #endif /* _ASM_X86_SIGCONTEXT32_H */ diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index b5d7640abc5d..8a4add8e4639 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -100,6 +100,7 @@ { SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, \ { SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, \ { SVM_EXIT_EXCP_BASE + NM_VECTOR, "NM excp" }, \ + { SVM_EXIT_EXCP_BASE + AC_VECTOR, "AC excp" }, \ { SVM_EXIT_EXCP_BASE + MC_VECTOR, "MC excp" }, \ { SVM_EXIT_INTR, "interrupt" }, \ { SVM_EXIT_NMI, "nmi" }, \ diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index 1fe92181ee9e..5b15d94a33f8 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -58,6 +58,7 @@ #define EXIT_REASON_INVALID_STATE 33 #define EXIT_REASON_MSR_LOAD_FAIL 34 #define EXIT_REASON_MWAIT_INSTRUCTION 36 +#define EXIT_REASON_MONITOR_TRAP_FLAG 37 #define EXIT_REASON_MONITOR_INSTRUCTION 39 #define EXIT_REASON_PAUSE_INSTRUCTION 40 #define EXIT_REASON_MCE_DURING_VMENTRY 41 @@ -77,6 +78,7 @@ #define EXIT_REASON_PML_FULL 62 #define EXIT_REASON_XSAVES 63 #define EXIT_REASON_XRSTORS 64 +#define EXIT_REASON_PCOMMIT 65 #define VMX_EXIT_REASONS \ { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \ @@ -106,6 +108,7 @@ { EXIT_REASON_MSR_READ, "MSR_READ" }, \ { EXIT_REASON_MSR_WRITE, "MSR_WRITE" }, \ { EXIT_REASON_MWAIT_INSTRUCTION, "MWAIT_INSTRUCTION" }, \ + { EXIT_REASON_MONITOR_TRAP_FLAG, "MONITOR_TRAP_FLAG" }, \ { EXIT_REASON_MONITOR_INSTRUCTION, "MONITOR_INSTRUCTION" }, \ { EXIT_REASON_PAUSE_INSTRUCTION, "PAUSE_INSTRUCTION" }, \ { EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \ @@ -124,7 +127,8 @@ { EXIT_REASON_INVVPID, "INVVPID" }, \ { EXIT_REASON_INVPCID, "INVPCID" }, \ { EXIT_REASON_XSAVES, "XSAVES" }, \ - { EXIT_REASON_XRSTORS, "XRSTORS" } + { EXIT_REASON_XRSTORS, "XRSTORS" }, \ + { EXIT_REASON_PCOMMIT, "PCOMMIT" } #define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1 #define VMX_ABORT_LOAD_HOST_MSR_FAIL 4 diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 0f15af41bd80..b1b78ffe01d0 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -23,8 +23,10 @@ KASAN_SANITIZE_dumpstack_$(BITS).o := n CFLAGS_irq.o := -I$(src)/../include/asm/trace obj-y := process_$(BITS).o signal.o +obj-$(CONFIG_COMPAT) += signal_compat.o obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o -obj-y += time.o ioport.o ldt.o dumpstack.o nmi.o +obj-y += time.o ioport.o dumpstack.o nmi.o +obj-$(CONFIG_MODIFY_LDT_SYSCALL) += ldt.o obj-y += setup.o x86_init.o i8259.o irqinit.o jump_label.o obj-$(CONFIG_IRQ_WORK) += irq_work.o obj-y += probe_roms.o @@ -69,8 +71,8 @@ obj-$(CONFIG_LIVEPATCH) += livepatch.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o obj-$(CONFIG_X86_TSC) += trace_clock.o -obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o -obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o +obj-$(CONFIG_KEXEC_CORE) += machine_kexec_$(BITS).o +obj-$(CONFIG_KEXEC_CORE) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_KEXEC_FILE) += kexec-bzimage64.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o obj-y += kprobes/ @@ -92,7 +94,7 @@ obj-$(CONFIG_KVM_GUEST) += kvm.o kvmclock.o obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch_$(BITS).o obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o -obj-$(CONFIG_X86_PMEM_LEGACY) += pmem.o +obj-$(CONFIG_X86_PMEM_LEGACY_DEVICE) += pmem.o obj-$(CONFIG_PCSPKR_PLATFORM) += pcspeaker.o @@ -107,8 +109,6 @@ obj-$(CONFIG_EFI) += sysfb_efi.o obj-$(CONFIG_PERF_EVENTS) += perf_regs.o obj-$(CONFIG_TRACING) += tracepoint.o -obj-$(CONFIG_IOSF_MBI) += iosf_mbi.o -obj-$(CONFIG_PMC_ATOM) += pmc_atom.o ### # 64 bit specific files diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index e49ee24da85e..e75907601a41 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -445,6 +445,7 @@ static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger, polarity = acpi_sci_flags & ACPI_MADT_POLARITY_MASK; mp_override_legacy_irq(bus_irq, polarity, trigger, gsi); + acpi_penalize_sci_irq(bus_irq, trigger, polarity); /* * stash over-ride to indicate we've been here @@ -710,7 +711,7 @@ static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) #endif } -static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) +int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, int *pcpu) { int cpu; @@ -726,12 +727,6 @@ static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) *pcpu = cpu; return 0; } - -/* wrapper to silence section mismatch warning */ -int __ref acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, int *pcpu) -{ - return _acpi_map_lsapic(handle, physid, pcpu); -} EXPORT_SYMBOL(acpi_map_cpu); int acpi_unmap_cpu(int cpu) @@ -981,6 +976,8 @@ static int __init acpi_parse_madt_lapic_entries(void) { int count; int x2count = 0; + int ret; + struct acpi_subtable_proc madt_proc[2]; if (!cpu_has_apic) return -ENODEV; @@ -1004,10 +1001,22 @@ static int __init acpi_parse_madt_lapic_entries(void) acpi_parse_sapic, MAX_LOCAL_APIC); if (!count) { - x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC, - acpi_parse_x2apic, MAX_LOCAL_APIC); - count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC, - acpi_parse_lapic, MAX_LOCAL_APIC); + memset(madt_proc, 0, sizeof(madt_proc)); + madt_proc[0].id = ACPI_MADT_TYPE_LOCAL_APIC; + madt_proc[0].handler = acpi_parse_lapic; + madt_proc[1].id = ACPI_MADT_TYPE_LOCAL_X2APIC; + madt_proc[1].handler = acpi_parse_x2apic; + ret = acpi_table_parse_entries_array(ACPI_SIG_MADT, + sizeof(struct acpi_table_madt), + madt_proc, ARRAY_SIZE(madt_proc), MAX_LOCAL_APIC); + if (ret < 0) { + printk(KERN_ERR PREFIX + "Error parsing LAPIC/X2APIC entries\n"); + return ret; + } + + x2count = madt_proc[0].count; + count = madt_proc[1].count; } if (!count && !x2count) { printk(KERN_ERR PREFIX "No LAPIC entries present\n"); diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index c42827eb86cf..25f909362b7a 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -338,10 +338,15 @@ done: static void __init_or_module optimize_nops(struct alt_instr *a, u8 *instr) { + unsigned long flags; + if (instr[0] != 0x90) return; + local_irq_save(flags); add_nops(instr + (a->instrlen - a->padlen), a->padlen); + sync_core(); + local_irq_restore(flags); DUMP_BYTES(instr, a->instrlen, "%p: [%d:%d) optimized NOPs: ", instr, a->instrlen - a->padlen, a->padlen); diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index ede92c3364d3..222a57076039 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -263,7 +263,7 @@ static int apbt_clocksource_register(void) /* Verify whether apbt counter works */ t1 = dw_apb_clocksource_read(clocksource_apbt); - rdtscll(start); + start = rdtsc(); /* * We don't know the TSC frequency yet, but waiting for @@ -273,7 +273,7 @@ static int apbt_clocksource_register(void) */ do { rep_nop(); - rdtscll(now); + now = rdtsc(); } while ((now - start) < 200000UL); /* APBT is the only always on clocksource, it has to work! */ @@ -390,13 +390,13 @@ unsigned long apbt_quick_calibrate(void) old = dw_apb_clocksource_read(clocksource_apbt); old += loop; - t1 = __native_read_tsc(); + t1 = rdtsc(); do { new = dw_apb_clocksource_read(clocksource_apbt); } while (new < old); - t2 = __native_read_tsc(); + t2 = rdtsc(); shift = 5; if (unlikely(loop >> shift == 0)) { diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index cde732c1b495..8a5cddac7d44 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -82,6 +82,12 @@ physid_mask_t phys_cpu_present_map; static unsigned int disabled_cpu_apicid __read_mostly = BAD_APICID; /* + * This variable controls which CPUs receive external NMIs. By default, + * external NMIs are delivered only to the BSP. + */ +static int apic_extnmi = APIC_EXTNMI_BSP; + +/* * Map cpu index to physical APIC ID */ DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid, BAD_APICID); @@ -336,6 +342,13 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) apic_write(APIC_LVTT, lvtt_value); if (lvtt_value & APIC_LVT_TIMER_TSCDEADLINE) { + /* + * See Intel SDM: TSC-Deadline Mode chapter. In xAPIC mode, + * writing to the APIC LVTT and TSC_DEADLINE MSR isn't serialized. + * According to Intel, MFENCE can do the serialization here. + */ + asm volatile("mfence" : : : "memory"); + printk_once(KERN_DEBUG "TSC deadline timer enabled\n"); return; } @@ -457,45 +470,45 @@ static int lapic_next_deadline(unsigned long delta, { u64 tsc; - rdtscll(tsc); + tsc = rdtsc(); wrmsrl(MSR_IA32_TSC_DEADLINE, tsc + (((u64) delta) * TSC_DIVISOR)); return 0; } -/* - * Setup the lapic timer in periodic or oneshot mode - */ -static void lapic_timer_setup(enum clock_event_mode mode, - struct clock_event_device *evt) +static int lapic_timer_shutdown(struct clock_event_device *evt) { - unsigned long flags; unsigned int v; /* Lapic used as dummy for broadcast ? */ if (evt->features & CLOCK_EVT_FEAT_DUMMY) - return; + return 0; - local_irq_save(flags); + v = apic_read(APIC_LVTT); + v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR); + apic_write(APIC_LVTT, v); + apic_write(APIC_TMICT, 0); + return 0; +} - switch (mode) { - case CLOCK_EVT_MODE_PERIODIC: - case CLOCK_EVT_MODE_ONESHOT: - __setup_APIC_LVTT(lapic_timer_frequency, - mode != CLOCK_EVT_MODE_PERIODIC, 1); - break; - case CLOCK_EVT_MODE_UNUSED: - case CLOCK_EVT_MODE_SHUTDOWN: - v = apic_read(APIC_LVTT); - v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR); - apic_write(APIC_LVTT, v); - apic_write(APIC_TMICT, 0); - break; - case CLOCK_EVT_MODE_RESUME: - /* Nothing to do here */ - break; - } +static inline int +lapic_timer_set_periodic_oneshot(struct clock_event_device *evt, bool oneshot) +{ + /* Lapic used as dummy for broadcast ? */ + if (evt->features & CLOCK_EVT_FEAT_DUMMY) + return 0; - local_irq_restore(flags); + __setup_APIC_LVTT(lapic_timer_frequency, oneshot, 1); + return 0; +} + +static int lapic_timer_set_periodic(struct clock_event_device *evt) +{ + return lapic_timer_set_periodic_oneshot(evt, false); +} + +static int lapic_timer_set_oneshot(struct clock_event_device *evt) +{ + return lapic_timer_set_periodic_oneshot(evt, true); } /* @@ -513,15 +526,18 @@ static void lapic_timer_broadcast(const struct cpumask *mask) * The local apic timer can be used for any function which is CPU local. */ static struct clock_event_device lapic_clockevent = { - .name = "lapic", - .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT - | CLOCK_EVT_FEAT_C3STOP | CLOCK_EVT_FEAT_DUMMY, - .shift = 32, - .set_mode = lapic_timer_setup, - .set_next_event = lapic_next_event, - .broadcast = lapic_timer_broadcast, - .rating = 100, - .irq = -1, + .name = "lapic", + .features = CLOCK_EVT_FEAT_PERIODIC | + CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP + | CLOCK_EVT_FEAT_DUMMY, + .shift = 32, + .set_state_shutdown = lapic_timer_shutdown, + .set_state_periodic = lapic_timer_set_periodic, + .set_state_oneshot = lapic_timer_set_oneshot, + .set_next_event = lapic_next_event, + .broadcast = lapic_timer_broadcast, + .rating = 100, + .irq = -1, }; static DEFINE_PER_CPU(struct clock_event_device, lapic_events); @@ -592,7 +608,7 @@ static void __init lapic_cal_handler(struct clock_event_device *dev) unsigned long pm = acpi_pm_read_early(); if (cpu_has_tsc) - rdtscll(tsc); + tsc = rdtsc(); switch (lapic_cal_loops++) { case 0: @@ -778,7 +794,7 @@ static int __init calibrate_APIC_clock(void) * Setup the apic timer manually */ levt->event_handler = lapic_cal_handler; - lapic_timer_setup(CLOCK_EVT_MODE_PERIODIC, levt); + lapic_timer_set_periodic(levt); lapic_cal_loops = -1; /* Let the interrupts run */ @@ -788,7 +804,8 @@ static int __init calibrate_APIC_clock(void) cpu_relax(); /* Stop the lapic timer */ - lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, levt); + local_irq_disable(); + lapic_timer_shutdown(levt); /* Jiffies delta */ deltaj = lapic_cal_j2 - lapic_cal_j1; @@ -799,8 +816,8 @@ static int __init calibrate_APIC_clock(void) apic_printk(APIC_VERBOSE, "... jiffies result ok\n"); else levt->features |= CLOCK_EVT_FEAT_DUMMY; - } else - local_irq_enable(); + } + local_irq_enable(); if (levt->features & CLOCK_EVT_FEAT_DUMMY) { pr_warning("APIC timer disabled due to verification failure\n"); @@ -878,7 +895,7 @@ static void local_apic_timer_interrupt(void) if (!evt->event_handler) { pr_warning("Spurious LAPIC timer interrupt on cpu %d\n", cpu); /* Switch it off */ - lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, evt); + lapic_timer_shutdown(evt); return; } @@ -1150,6 +1167,8 @@ void __init init_bsp_APIC(void) value = APIC_DM_NMI; if (!lapic_is_integrated()) /* 82489DX */ value |= APIC_LVT_LEVEL_TRIGGER; + if (apic_extnmi == APIC_EXTNMI_NONE) + value |= APIC_LVT_MASKED; apic_write(APIC_LVT1, value); } @@ -1209,7 +1228,7 @@ void setup_local_APIC(void) long long max_loops = cpu_khz ? cpu_khz : 1000000; if (cpu_has_tsc) - rdtscll(tsc); + tsc = rdtsc(); if (disable_apic) { disable_ioapic_support(); @@ -1293,7 +1312,7 @@ void setup_local_APIC(void) } if (queued) { if (cpu_has_tsc && cpu_khz) { - rdtscll(ntsc); + ntsc = rdtsc(); max_loops = (cpu_khz << 10) - (ntsc - tsc); } else max_loops--; @@ -1367,9 +1386,11 @@ void setup_local_APIC(void) apic_write(APIC_LVT0, value); /* - * only the BP should see the LINT1 NMI signal, obviously. + * Only the BSP sees the LINT1 NMI signal by default. This can be + * modified by apic_extnmi= boot option. */ - if (!cpu) + if ((!cpu && apic_extnmi != APIC_EXTNMI_NONE) || + apic_extnmi == APIC_EXTNMI_ALL) value = APIC_DM_NMI; else value = APIC_DM_NMI | APIC_LVT_MASKED; @@ -1420,7 +1441,7 @@ enum { }; static int x2apic_state; -static inline void __x2apic_disable(void) +static void __x2apic_disable(void) { u64 msr; @@ -1436,7 +1457,7 @@ static inline void __x2apic_disable(void) printk_once(KERN_INFO "x2apic disabled\n"); } -static inline void __x2apic_enable(void) +static void __x2apic_enable(void) { u64 msr; @@ -1796,7 +1817,7 @@ int apic_version[MAX_LOCAL_APIC]; /* * This interrupt should _never_ happen with our APIC/SMP architecture */ -static inline void __smp_spurious_interrupt(u8 vector) +static void __smp_spurious_interrupt(u8 vector) { u32 v; @@ -1837,7 +1858,7 @@ __visible void smp_trace_spurious_interrupt(struct pt_regs *regs) /* * This interrupt should never happen with our APIC/SMP architecture */ -static inline void __smp_error_interrupt(struct pt_regs *regs) +static void __smp_error_interrupt(struct pt_regs *regs) { u32 v; u32 i = 0; @@ -2259,6 +2280,7 @@ static struct { unsigned int apic_tmict; unsigned int apic_tdcr; unsigned int apic_thmr; + unsigned int apic_cmci; } apic_pm_state; static int lapic_suspend(void) @@ -2288,6 +2310,10 @@ static int lapic_suspend(void) if (maxlvt >= 5) apic_pm_state.apic_thmr = apic_read(APIC_LVTTHMR); #endif +#ifdef CONFIG_X86_MCE_INTEL + if (maxlvt >= 6) + apic_pm_state.apic_cmci = apic_read(APIC_LVTCMCI); +#endif local_irq_save(flags); disable_local_APIC(); @@ -2344,10 +2370,14 @@ static void lapic_resume(void) apic_write(APIC_SPIV, apic_pm_state.apic_spiv); apic_write(APIC_LVT0, apic_pm_state.apic_lvt0); apic_write(APIC_LVT1, apic_pm_state.apic_lvt1); -#if defined(CONFIG_X86_MCE_INTEL) +#ifdef CONFIG_X86_THERMAL_VECTOR if (maxlvt >= 5) apic_write(APIC_LVTTHMR, apic_pm_state.apic_thmr); #endif +#ifdef CONFIG_X86_MCE_INTEL + if (maxlvt >= 6) + apic_write(APIC_LVTCMCI, apic_pm_state.apic_cmci); +#endif if (maxlvt >= 4) apic_write(APIC_LVTPC, apic_pm_state.apic_lvtpc); apic_write(APIC_LVTT, apic_pm_state.apic_lvtt); @@ -2537,3 +2567,23 @@ static int __init apic_set_disabled_cpu_apicid(char *arg) return 0; } early_param("disable_cpu_apicid", apic_set_disabled_cpu_apicid); + +static int __init apic_set_extnmi(char *arg) +{ + if (!arg) + return -EINVAL; + + if (!strncmp("all", arg, 3)) + apic_extnmi = APIC_EXTNMI_ALL; + else if (!strncmp("none", arg, 4)) + apic_extnmi = APIC_EXTNMI_NONE; + else if (!strncmp("bsp", arg, 3)) + apic_extnmi = APIC_EXTNMI_BSP; + else { + pr_warn("Unknown external NMI delivery mode `%s' ignored\n", arg); + return -EINVAL; + } + + return 0; +} +early_param("apic_extnmi", apic_set_extnmi); diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index de918c410eae..9968f30cca3e 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -185,13 +185,13 @@ static struct apic apic_flat = { .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .send_IPI = default_send_IPI_single, .send_IPI_mask = flat_send_IPI_mask, .send_IPI_mask_allbutself = flat_send_IPI_mask_allbutself, .send_IPI_allbutself = flat_send_IPI_allbutself, .send_IPI_all = flat_send_IPI_all, .send_IPI_self = apic_send_IPI_self, - .wait_for_init_deassert = false, .inquire_remote_apic = default_inquire_remote_apic, .read = native_apic_mem_read, @@ -231,17 +231,6 @@ static int physflat_acpi_madt_oem_check(char *oem_id, char *oem_table_id) return 0; } -static void physflat_send_IPI_mask(const struct cpumask *cpumask, int vector) -{ - default_send_IPI_mask_sequence_phys(cpumask, vector); -} - -static void physflat_send_IPI_mask_allbutself(const struct cpumask *cpumask, - int vector) -{ - default_send_IPI_mask_allbutself_phys(cpumask, vector); -} - static void physflat_send_IPI_allbutself(int vector) { default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector); @@ -249,7 +238,7 @@ static void physflat_send_IPI_allbutself(int vector) static void physflat_send_IPI_all(int vector) { - physflat_send_IPI_mask(cpu_online_mask, vector); + default_send_IPI_mask_sequence_phys(cpu_online_mask, vector); } static int physflat_probe(void) @@ -293,13 +282,13 @@ static struct apic apic_physflat = { .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, - .send_IPI_mask = physflat_send_IPI_mask, - .send_IPI_mask_allbutself = physflat_send_IPI_mask_allbutself, + .send_IPI = default_send_IPI_single_phys, + .send_IPI_mask = default_send_IPI_mask_sequence_phys, + .send_IPI_mask_allbutself = default_send_IPI_mask_allbutself_phys, .send_IPI_allbutself = physflat_send_IPI_allbutself, .send_IPI_all = physflat_send_IPI_all, .send_IPI_self = apic_send_IPI_self, - .wait_for_init_deassert = false, .inquire_remote_apic = default_inquire_remote_apic, .read = native_apic_mem_read, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index b205cdbdbe6a..331a7a07c48f 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -30,6 +30,7 @@ #include <asm/e820.h> static void noop_init_apic_ldr(void) { } +static void noop_send_IPI(int cpu, int vector) { } static void noop_send_IPI_mask(const struct cpumask *cpumask, int vector) { } static void noop_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector) { } static void noop_send_IPI_allbutself(int vector) { } @@ -144,6 +145,7 @@ struct apic apic_noop = { .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .send_IPI = noop_send_IPI, .send_IPI_mask = noop_send_IPI_mask, .send_IPI_mask_allbutself = noop_send_IPI_mask_allbutself, .send_IPI_allbutself = noop_send_IPI_allbutself, @@ -152,7 +154,6 @@ struct apic apic_noop = { .wakeup_secondary_cpu = noop_wakeup_secondary_cpu, - .wait_for_init_deassert = false, .inquire_remote_apic = NULL, .read = noop_apic_read, diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 017149cded07..c80c02c6ec49 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -11,30 +11,21 @@ * */ -#include <linux/errno.h> -#include <linux/threads.h> -#include <linux/cpumask.h> -#include <linux/string.h> -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/ctype.h> #include <linux/init.h> -#include <linux/hardirq.h> -#include <linux/delay.h> #include <asm/numachip/numachip.h> #include <asm/numachip/numachip_csr.h> -#include <asm/smp.h> -#include <asm/apic.h> #include <asm/ipi.h> #include <asm/apic_flat_64.h> #include <asm/pgtable.h> +#include <asm/pci_x86.h> -static int numachip_system __read_mostly; +u8 numachip_system __read_mostly; +static const struct apic apic_numachip1; +static const struct apic apic_numachip2; +static void (*numachip_apic_icr_write)(int apicid, unsigned int val) __read_mostly; -static const struct apic apic_numachip; - -static unsigned int get_apic_id(unsigned long x) +static unsigned int numachip1_get_apic_id(unsigned long x) { unsigned long value; unsigned int id = (x >> 24) & 0xff; @@ -47,7 +38,7 @@ static unsigned int get_apic_id(unsigned long x) return id; } -static unsigned long set_apic_id(unsigned int id) +static unsigned long numachip1_set_apic_id(unsigned int id) { unsigned long x; @@ -55,9 +46,17 @@ static unsigned long set_apic_id(unsigned int id) return x; } -static unsigned int read_xapic_id(void) +static unsigned int numachip2_get_apic_id(unsigned long x) +{ + u64 mcfg; + + rdmsrl(MSR_FAM10H_MMIO_CONF_BASE, mcfg); + return ((mcfg >> (28 - 8)) & 0xfff00) | (x >> 24); +} + +static unsigned long numachip2_set_apic_id(unsigned int id) { - return get_apic_id(apic_read(APIC_ID)); + return id << 24; } static int numachip_apic_id_valid(int apicid) @@ -68,7 +67,7 @@ static int numachip_apic_id_valid(int apicid) static int numachip_apic_id_registered(void) { - return physid_isset(read_xapic_id(), phys_cpu_present_map); + return 1; } static int numachip_phys_pkg_id(int initial_apic_id, int index_msb) @@ -76,37 +75,48 @@ static int numachip_phys_pkg_id(int initial_apic_id, int index_msb) return initial_apic_id >> index_msb; } -static int numachip_wakeup_secondary(int phys_apicid, unsigned long start_rip) +static void numachip1_apic_icr_write(int apicid, unsigned int val) { - union numachip_csr_g3_ext_irq_gen int_gen; - - int_gen.s._destination_apic_id = phys_apicid; - int_gen.s._vector = 0; - int_gen.s._msgtype = APIC_DM_INIT >> 8; - int_gen.s._index = 0; - - write_lcsr(CSR_G3_EXT_IRQ_GEN, int_gen.v); + write_lcsr(CSR_G3_EXT_IRQ_GEN, (apicid << 16) | val); +} - int_gen.s._msgtype = APIC_DM_STARTUP >> 8; - int_gen.s._vector = start_rip >> 12; +static void numachip2_apic_icr_write(int apicid, unsigned int val) +{ + numachip2_write32_lcsr(NUMACHIP2_APIC_ICR, (apicid << 12) | val); +} - write_lcsr(CSR_G3_EXT_IRQ_GEN, int_gen.v); +static int numachip_wakeup_secondary(int phys_apicid, unsigned long start_rip) +{ + numachip_apic_icr_write(phys_apicid, APIC_DM_INIT); + numachip_apic_icr_write(phys_apicid, APIC_DM_STARTUP | + (start_rip >> 12)); - atomic_set(&init_deasserted, 1); return 0; } static void numachip_send_IPI_one(int cpu, int vector) { - union numachip_csr_g3_ext_irq_gen int_gen; - int apicid = per_cpu(x86_cpu_to_apicid, cpu); - - int_gen.s._destination_apic_id = apicid; - int_gen.s._vector = vector; - int_gen.s._msgtype = (vector == NMI_VECTOR ? APIC_DM_NMI : APIC_DM_FIXED) >> 8; - int_gen.s._index = 0; + int local_apicid, apicid = per_cpu(x86_cpu_to_apicid, cpu); + unsigned int dmode; + + preempt_disable(); + local_apicid = __this_cpu_read(x86_cpu_to_apicid); + + /* Send via local APIC where non-local part matches */ + if (!((apicid ^ local_apicid) >> NUMACHIP_LAPIC_BITS)) { + unsigned long flags; + + local_irq_save(flags); + __default_send_IPI_dest_field(apicid, vector, + APIC_DEST_PHYSICAL); + local_irq_restore(flags); + preempt_enable(); + return; + } + preempt_enable(); - write_lcsr(CSR_G3_EXT_IRQ_GEN, int_gen.v); + dmode = (vector == NMI_VECTOR) ? APIC_DM_NMI : APIC_DM_FIXED; + numachip_apic_icr_write(apicid, dmode | vector); } static void numachip_send_IPI_mask(const struct cpumask *mask, int vector) @@ -150,9 +160,14 @@ static void numachip_send_IPI_self(int vector) apic_write(APIC_SELF_IPI, vector); } -static int __init numachip_probe(void) +static int __init numachip1_probe(void) { - return apic == &apic_numachip; + return apic == &apic_numachip1; +} + +static int __init numachip2_probe(void) +{ + return apic == &apic_numachip2; } static void fixup_cpu_id(struct cpuinfo_x86 *c, int node) @@ -173,11 +188,19 @@ static void fixup_cpu_id(struct cpuinfo_x86 *c, int node) static int __init numachip_system_init(void) { - if (!numachip_system) + /* Map the LCSR area and set up the apic_icr_write function */ + switch (numachip_system) { + case 1: + init_extra_mapping_uc(NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_SIZE); + numachip_apic_icr_write = numachip1_apic_icr_write; + break; + case 2: + init_extra_mapping_uc(NUMACHIP2_LCSR_BASE, NUMACHIP2_LCSR_SIZE); + numachip_apic_icr_write = numachip2_apic_icr_write; + break; + default: return 0; - - init_extra_mapping_uc(NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_SIZE); - init_extra_mapping_uc(NUMACHIP_GCSR_BASE, NUMACHIP_GCSR_SIZE); + } x86_cpuinit.fixup_cpu_id = fixup_cpu_id; x86_init.pci.arch_init = pci_numachip_init; @@ -186,21 +209,95 @@ static int __init numachip_system_init(void) } early_initcall(numachip_system_init); -static int numachip_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +static int numachip1_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { - if (!strncmp(oem_id, "NUMASC", 6)) { - numachip_system = 1; - return 1; - } + if ((strncmp(oem_id, "NUMASC", 6) != 0) || + (strncmp(oem_table_id, "NCONNECT", 8) != 0)) + return 0; - return 0; + numachip_system = 1; + + return 1; +} + +static int numachip2_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +{ + if ((strncmp(oem_id, "NUMASC", 6) != 0) || + (strncmp(oem_table_id, "NCONECT2", 8) != 0)) + return 0; + + numachip_system = 2; + + return 1; +} + +/* APIC IPIs are queued */ +static void numachip_apic_wait_icr_idle(void) +{ } -static const struct apic apic_numachip __refconst = { +/* APIC NMI IPIs are queued */ +static u32 numachip_safe_apic_wait_icr_idle(void) +{ + return 0; +} +static const struct apic apic_numachip1 __refconst = { .name = "NumaConnect system", - .probe = numachip_probe, - .acpi_madt_oem_check = numachip_acpi_madt_oem_check, + .probe = numachip1_probe, + .acpi_madt_oem_check = numachip1_acpi_madt_oem_check, + .apic_id_valid = numachip_apic_id_valid, + .apic_id_registered = numachip_apic_id_registered, + + .irq_delivery_mode = dest_Fixed, + .irq_dest_mode = 0, /* physical */ + + .target_cpus = online_target_cpus, + .disable_esr = 0, + .dest_logical = 0, + .check_apicid_used = NULL, + + .vector_allocation_domain = default_vector_allocation_domain, + .init_apic_ldr = flat_init_apic_ldr, + + .ioapic_phys_id_map = NULL, + .setup_apic_routing = NULL, + .cpu_present_to_apicid = default_cpu_present_to_apicid, + .apicid_to_cpu_present = NULL, + .check_phys_apicid_present = default_check_phys_apicid_present, + .phys_pkg_id = numachip_phys_pkg_id, + + .get_apic_id = numachip1_get_apic_id, + .set_apic_id = numachip1_set_apic_id, + .apic_id_mask = 0xffU << 24, + + .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + + .send_IPI = numachip_send_IPI_one, + .send_IPI_mask = numachip_send_IPI_mask, + .send_IPI_mask_allbutself = numachip_send_IPI_mask_allbutself, + .send_IPI_allbutself = numachip_send_IPI_allbutself, + .send_IPI_all = numachip_send_IPI_all, + .send_IPI_self = numachip_send_IPI_self, + + .wakeup_secondary_cpu = numachip_wakeup_secondary, + .inquire_remote_apic = NULL, /* REMRD not supported */ + + .read = native_apic_mem_read, + .write = native_apic_mem_write, + .eoi_write = native_apic_mem_write, + .icr_read = native_apic_icr_read, + .icr_write = native_apic_icr_write, + .wait_icr_idle = numachip_apic_wait_icr_idle, + .safe_wait_icr_idle = numachip_safe_apic_wait_icr_idle, +}; + +apic_driver(apic_numachip1); + +static const struct apic apic_numachip2 __refconst = { + .name = "NumaConnect2 system", + .probe = numachip2_probe, + .acpi_madt_oem_check = numachip2_acpi_madt_oem_check, .apic_id_valid = numachip_apic_id_valid, .apic_id_registered = numachip_apic_id_registered, @@ -222,12 +319,13 @@ static const struct apic apic_numachip __refconst = { .check_phys_apicid_present = default_check_phys_apicid_present, .phys_pkg_id = numachip_phys_pkg_id, - .get_apic_id = get_apic_id, - .set_apic_id = set_apic_id, + .get_apic_id = numachip2_get_apic_id, + .set_apic_id = numachip2_set_apic_id, .apic_id_mask = 0xffU << 24, .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .send_IPI = numachip_send_IPI_one, .send_IPI_mask = numachip_send_IPI_mask, .send_IPI_mask_allbutself = numachip_send_IPI_mask_allbutself, .send_IPI_allbutself = numachip_send_IPI_allbutself, @@ -235,7 +333,6 @@ static const struct apic apic_numachip __refconst = { .send_IPI_self = numachip_send_IPI_self, .wakeup_secondary_cpu = numachip_wakeup_secondary, - .wait_for_init_deassert = false, .inquire_remote_apic = NULL, /* REMRD not supported */ .read = native_apic_mem_read, @@ -243,8 +340,8 @@ static const struct apic apic_numachip __refconst = { .eoi_write = native_apic_mem_write, .icr_read = native_apic_icr_read, .icr_write = native_apic_icr_write, - .wait_icr_idle = native_apic_wait_icr_idle, - .safe_wait_icr_idle = native_safe_apic_wait_icr_idle, + .wait_icr_idle = numachip_apic_wait_icr_idle, + .safe_wait_icr_idle = numachip_safe_apic_wait_icr_idle, }; -apic_driver(apic_numachip); +apic_driver(apic_numachip2); diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index c4a8d63f8220..cf9bd896c12d 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -96,11 +96,6 @@ static int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb) return cpuid_apic >> index_msb; } -static inline void bigsmp_send_IPI_mask(const struct cpumask *mask, int vector) -{ - default_send_IPI_mask_sequence_phys(mask, vector); -} - static void bigsmp_send_IPI_allbutself(int vector) { default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector); @@ -108,7 +103,7 @@ static void bigsmp_send_IPI_allbutself(int vector) static void bigsmp_send_IPI_all(int vector) { - bigsmp_send_IPI_mask(cpu_online_mask, vector); + default_send_IPI_mask_sequence_phys(cpu_online_mask, vector); } static int dmi_bigsmp; /* can be set by dmi scanners */ @@ -180,13 +175,13 @@ static struct apic apic_bigsmp = { .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, - .send_IPI_mask = bigsmp_send_IPI_mask, + .send_IPI = default_send_IPI_single_phys, + .send_IPI_mask = default_send_IPI_mask_sequence_phys, .send_IPI_mask_allbutself = NULL, .send_IPI_allbutself = bigsmp_send_IPI_allbutself, .send_IPI_all = bigsmp_send_IPI_all, .send_IPI_self = default_send_IPI_self, - .wait_for_init_deassert = true, .inquire_remote_apic = default_inquire_remote_apic, .read = native_apic_mem_read, diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index 6873ab925d00..045e424fb368 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -28,146 +28,21 @@ u64 hw_nmi_get_sample_period(int watchdog_thresh) #endif #ifdef arch_trigger_all_cpu_backtrace -/* For reliability, we're prepared to waste bits here. */ -static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; -static cpumask_t printtrace_mask; - -#define NMI_BUF_SIZE 4096 - -struct nmi_seq_buf { - unsigned char buffer[NMI_BUF_SIZE]; - struct seq_buf seq; -}; - -/* Safe printing in NMI context */ -static DEFINE_PER_CPU(struct nmi_seq_buf, nmi_print_seq); - -/* "in progress" flag of arch_trigger_all_cpu_backtrace */ -static unsigned long backtrace_flag; - -static void print_seq_line(struct nmi_seq_buf *s, int start, int end) +static void nmi_raise_cpu_backtrace(cpumask_t *mask) { - const char *buf = s->buffer + start; - - printk("%.*s", (end - start) + 1, buf); + apic->send_IPI_mask(mask, NMI_VECTOR); } void arch_trigger_all_cpu_backtrace(bool include_self) { - struct nmi_seq_buf *s; - int len; - int cpu; - int i; - int this_cpu = get_cpu(); - - if (test_and_set_bit(0, &backtrace_flag)) { - /* - * If there is already a trigger_all_cpu_backtrace() in progress - * (backtrace_flag == 1), don't output double cpu dump infos. - */ - put_cpu(); - return; - } - - cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask); - if (!include_self) - cpumask_clear_cpu(this_cpu, to_cpumask(backtrace_mask)); - - cpumask_copy(&printtrace_mask, to_cpumask(backtrace_mask)); - /* - * Set up per_cpu seq_buf buffers that the NMIs running on the other - * CPUs will write to. - */ - for_each_cpu(cpu, to_cpumask(backtrace_mask)) { - s = &per_cpu(nmi_print_seq, cpu); - seq_buf_init(&s->seq, s->buffer, NMI_BUF_SIZE); - } - - if (!cpumask_empty(to_cpumask(backtrace_mask))) { - pr_info("sending NMI to %s CPUs:\n", - (include_self ? "all" : "other")); - apic->send_IPI_mask(to_cpumask(backtrace_mask), NMI_VECTOR); - } - - /* Wait for up to 10 seconds for all CPUs to do the backtrace */ - for (i = 0; i < 10 * 1000; i++) { - if (cpumask_empty(to_cpumask(backtrace_mask))) - break; - mdelay(1); - touch_softlockup_watchdog(); - } - - /* - * Now that all the NMIs have triggered, we can dump out their - * back traces safely to the console. - */ - for_each_cpu(cpu, &printtrace_mask) { - int last_i = 0; - - s = &per_cpu(nmi_print_seq, cpu); - len = seq_buf_used(&s->seq); - if (!len) - continue; - - /* Print line by line. */ - for (i = 0; i < len; i++) { - if (s->buffer[i] == '\n') { - print_seq_line(s, last_i, i); - last_i = i + 1; - } - } - /* Check if there was a partial line. */ - if (last_i < len) { - print_seq_line(s, last_i, len - 1); - pr_cont("\n"); - } - } - - clear_bit(0, &backtrace_flag); - smp_mb__after_atomic(); - put_cpu(); -} - -/* - * It is not safe to call printk() directly from NMI handlers. - * It may be fine if the NMI detected a lock up and we have no choice - * but to do so, but doing a NMI on all other CPUs to get a back trace - * can be done with a sysrq-l. We don't want that to lock up, which - * can happen if the NMI interrupts a printk in progress. - * - * Instead, we redirect the vprintk() to this nmi_vprintk() that writes - * the content into a per cpu seq_buf buffer. Then when the NMIs are - * all done, we can safely dump the contents of the seq_buf to a printk() - * from a non NMI context. - */ -static int nmi_vprintk(const char *fmt, va_list args) -{ - struct nmi_seq_buf *s = this_cpu_ptr(&nmi_print_seq); - unsigned int len = seq_buf_used(&s->seq); - - seq_buf_vprintf(&s->seq, fmt, args); - return seq_buf_used(&s->seq) - len; + nmi_trigger_all_cpu_backtrace(include_self, nmi_raise_cpu_backtrace); } static int arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs) { - int cpu; - - cpu = smp_processor_id(); - - if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) { - printk_func_t printk_func_save = this_cpu_read(printk_func); - - /* Replace printk to write into the NMI seq */ - this_cpu_write(printk_func, nmi_vprintk); - printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu); - show_regs(regs); - this_cpu_write(printk_func, printk_func_save); - - cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); + if (nmi_cpu_backtrace(regs)) return NMI_HANDLED; - } return NMI_DONE; } diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 206052e55517..f25321894ad2 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -529,7 +529,7 @@ static void __eoi_ioapic_pin(int apic, int pin, int vector) } } -void eoi_ioapic_pin(int vector, struct mp_chip_data *data) +static void eoi_ioapic_pin(int vector, struct mp_chip_data *data) { unsigned long flags; struct irq_pin_list *entry; @@ -2522,6 +2522,7 @@ void __init setup_ioapic_dest(void) int pin, ioapic, irq, irq_entry; const struct cpumask *mask; struct irq_data *idata; + struct irq_chip *chip; if (skip_ioapic_setup == 1) return; @@ -2541,13 +2542,15 @@ void __init setup_ioapic_dest(void) * Honour affinities which have been set in early boot */ if (!irqd_can_balance(idata) || irqd_affinity_was_set(idata)) - mask = idata->affinity; + mask = irq_data_get_affinity_mask(idata); else mask = apic->target_cpus(); - irq_set_affinity(irq, mask); + chip = irq_data_get_irq_chip(idata); + /* Might be lapic_chip for irq 0 */ + if (chip->irq_set_affinity) + chip->irq_set_affinity(idata, mask, false); } - } #endif @@ -2906,6 +2909,7 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, struct irq_data *irq_data; struct mp_chip_data *data; struct irq_alloc_info *info = arg; + unsigned long flags; if (!info || nr_irqs > 1) return -EINVAL; @@ -2938,11 +2942,14 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, cfg = irqd_cfg(irq_data); add_pin_to_irq_node(data, ioapic_alloc_attr_node(info), ioapic, pin); + + local_irq_save(flags); 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); + local_irq_restore(flags); apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> IRQ %d Mode:%i Active:%i Dest:%d)\n", diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index 62071569bd50..eb45fc9b6124 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -18,6 +18,16 @@ #include <asm/proto.h> #include <asm/ipi.h> +void default_send_IPI_single_phys(int cpu, int vector) +{ + unsigned long flags; + + local_irq_save(flags); + __default_send_IPI_dest_field(per_cpu(x86_cpu_to_apicid, cpu), + vector, APIC_DEST_PHYSICAL); + local_irq_restore(flags); +} + void default_send_IPI_mask_sequence_phys(const struct cpumask *mask, int vector) { unsigned long query_cpu; @@ -55,6 +65,14 @@ void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask, local_irq_restore(flags); } +/* + * Helper function for APICs which insist on cpumasks + */ +void default_send_IPI_single(int cpu, int vector) +{ + apic->send_IPI_mask(cpumask_of(cpu), vector); +} + #ifdef CONFIG_X86_32 void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 1a9d735e09c6..ade25320df96 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -96,8 +96,8 @@ static irq_hw_number_t pci_msi_get_hwirq(struct msi_domain_info *info, return arg->msi_hwirq; } -static int pci_msi_prepare(struct irq_domain *domain, struct device *dev, - int nvec, msi_alloc_info_t *arg) +int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, + msi_alloc_info_t *arg) { struct pci_dev *pdev = to_pci_dev(dev); struct msi_desc *desc = first_pci_msi_entry(pdev); @@ -113,11 +113,13 @@ static int pci_msi_prepare(struct irq_domain *domain, struct device *dev, return 0; } +EXPORT_SYMBOL_GPL(pci_msi_prepare); -static void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) +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); } +EXPORT_SYMBOL_GPL(pci_msi_set_desc); static struct msi_domain_ops pci_msi_domain_ops = { .get_hwirq = pci_msi_get_hwirq, @@ -264,7 +266,7 @@ static inline int hpet_dev_id(struct irq_domain *domain) static void hpet_msi_write_msg(struct irq_data *data, struct msi_msg *msg) { - hpet_msi_write(data->handler_data, msg); + hpet_msi_write(irq_data_get_irq_handler_data(data), msg); } static struct irq_chip hpet_msi_controller = { diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index bda488680dbc..f316e34abb42 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -105,13 +105,13 @@ static struct apic apic_default = { .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .send_IPI = default_send_IPI_single, .send_IPI_mask = default_send_IPI_mask_logical, .send_IPI_mask_allbutself = default_send_IPI_mask_allbutself_logical, .send_IPI_allbutself = default_send_IPI_allbutself, .send_IPI_all = default_send_IPI_all, .send_IPI_self = default_send_IPI_self, - .wait_for_init_deassert = true, .inquire_remote_apic = default_inquire_remote_apic, .read = native_apic_mem_read, diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 2683f36e4e0a..908cb37da171 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -29,6 +29,7 @@ struct apic_chip_data { }; struct irq_domain *x86_vector_domain; +EXPORT_SYMBOL_GPL(x86_vector_domain); static DEFINE_RAW_SPINLOCK(vector_lock); static cpumask_var_t vector_cpumask; static struct irq_chip lapic_controller; @@ -66,6 +67,7 @@ struct irq_cfg *irqd_cfg(struct irq_data *irq_data) return data ? &data->cfg : NULL; } +EXPORT_SYMBOL_GPL(irqd_cfg); struct irq_cfg *irq_cfg(unsigned int irq) { @@ -169,8 +171,7 @@ next: goto next; for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) { - if (per_cpu(vector_irq, new_cpu)[vector] > - VECTOR_UNDEFINED) + if (!IS_ERR_OR_NULL(per_cpu(vector_irq, new_cpu)[vector])) goto next; } /* Found one! */ @@ -182,7 +183,7 @@ next: cpumask_intersects(d->old_domain, cpu_online_mask); } for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) - per_cpu(vector_irq, new_cpu)[vector] = irq; + per_cpu(vector_irq, new_cpu)[vector] = irq_to_desc(irq); d->cfg.vector = vector; cpumask_copy(d->domain, vector_cpumask); err = 0; @@ -224,15 +225,16 @@ static int assign_irq_vector_policy(int irq, int node, static void clear_irq_vector(int irq, struct apic_chip_data *data) { - int cpu, vector; + struct irq_desc *desc; unsigned long flags; + int cpu, vector; raw_spin_lock_irqsave(&vector_lock, flags); BUG_ON(!data->cfg.vector); vector = data->cfg.vector; for_each_cpu_and(cpu, data->domain, cpu_online_mask) - per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; + per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED; data->cfg.vector = 0; cpumask_clear(data->domain); @@ -242,12 +244,13 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data) return; } + desc = irq_to_desc(irq); 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) + if (per_cpu(vector_irq, cpu)[vector] != desc) continue; - per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; + per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED; break; } } @@ -296,7 +299,7 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, struct irq_alloc_info *info = arg; struct apic_chip_data *data; struct irq_data *irq_data; - int i, err; + int i, err, node; if (disable_apic) return -ENXIO; @@ -308,12 +311,13 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, for (i = 0; i < nr_irqs; i++) { irq_data = irq_domain_get_irq_data(domain, virq + i); BUG_ON(!irq_data); + node = irq_data_get_node(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); + data = alloc_apic_chip_data(node); if (!data) { err = -ENOMEM; goto error; @@ -322,8 +326,7 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, 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); + err = assign_irq_vector_policy(virq + i, node, data, info); if (err) goto error; } @@ -360,7 +363,11 @@ int __init arch_probe_nr_irqs(void) if (nr < nr_irqs) nr_irqs = nr; - return nr_legacy_irqs(); + /* + * We don't know if PIC is present at this point so we need to do + * probe() to get the right number of legacy IRQs. + */ + return legacy_pic->probe(); } #ifdef CONFIG_X86_IO_APIC @@ -403,32 +410,32 @@ int __init arch_early_irq_init(void) return arch_early_ioapic_init(); } +/* Initialize vector_irq on a new cpu */ static void __setup_vector_irq(int cpu) { - /* Initialize vector_irq on a new cpu */ - int irq, vector; struct apic_chip_data *data; + struct irq_desc *desc; + int irq, vector; /* Mark the inuse vectors */ - for_each_active_irq(irq) { - data = apic_chip_data(irq_get_irq_data(irq)); - if (!data) - continue; + for_each_irq_desc(irq, desc) { + struct irq_data *idata = irq_desc_get_irq_data(desc); - if (!cpumask_test_cpu(cpu, data->domain)) + data = apic_chip_data(idata); + if (!data || !cpumask_test_cpu(cpu, data->domain)) continue; vector = data->cfg.vector; - per_cpu(vector_irq, cpu)[vector] = irq; + per_cpu(vector_irq, cpu)[vector] = desc; } /* Mark the free vectors */ for (vector = 0; vector < NR_VECTORS; ++vector) { - irq = per_cpu(vector_irq, cpu)[vector]; - if (irq <= VECTOR_UNDEFINED) + desc = per_cpu(vector_irq, cpu)[vector]; + if (IS_ERR_OR_NULL(desc)) continue; - data = apic_chip_data(irq_get_irq_data(irq)); + data = apic_chip_data(irq_desc_get_irq_data(desc)); if (!cpumask_test_cpu(cpu, data->domain)) - per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; + per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED; } } @@ -448,7 +455,7 @@ void setup_vector_irq(int cpu) * legacy vector to irq mapping: */ for (irq = 0; irq < nr_legacy_irqs(); irq++) - per_cpu(vector_irq, cpu)[ISA_IRQ_VECTOR(irq)] = irq; + per_cpu(vector_irq, cpu)[ISA_IRQ_VECTOR(irq)] = irq_to_desc(irq); __setup_vector_irq(cpu); } @@ -488,9 +495,8 @@ static int apic_set_affinity(struct irq_data *irq_data, err = assign_irq_vector(irq, data, dest); if (err) { - struct irq_data *top = irq_get_irq_data(irq); - - if (assign_irq_vector(irq, data, top->affinity)) + if (assign_irq_vector(irq, data, + irq_data_get_affinity_mask(irq_data))) pr_err("Failed to recover vector for irq %d\n", irq); return err; } @@ -538,27 +544,30 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) entering_ack_irq(); + /* Prevent vectors vanishing under us */ + raw_spin_lock(&vector_lock); + me = smp_processor_id(); for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { - int irq; - unsigned int irr; - struct irq_desc *desc; struct apic_chip_data *data; + struct irq_desc *desc; + unsigned int irr; - irq = __this_cpu_read(vector_irq[vector]); - - if (irq <= VECTOR_UNDEFINED) + retry: + desc = __this_cpu_read(vector_irq[vector]); + if (IS_ERR_OR_NULL(desc)) continue; - desc = irq_to_desc(irq); - if (!desc) - continue; + if (!raw_spin_trylock(&desc->lock)) { + raw_spin_unlock(&vector_lock); + cpu_relax(); + raw_spin_lock(&vector_lock); + goto retry; + } - data = apic_chip_data(&desc->irq_data); + data = apic_chip_data(irq_desc_get_irq_data(desc)); if (!data) - continue; - - raw_spin_lock(&desc->lock); + goto unlock; /* * Check if the irq migration is in progress. If so, we @@ -583,11 +592,13 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) apic->send_IPI_self(IRQ_MOVE_CLEANUP_VECTOR); goto unlock; } - __this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED); + __this_cpu_write(vector_irq[vector], VECTOR_UNUSED); unlock: raw_spin_unlock(&desc->lock); } + raw_spin_unlock(&vector_lock); + exiting_irq(); } diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index ab3219b3fbda..aca8b75c1552 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -23,6 +23,14 @@ static inline u32 x2apic_cluster(int cpu) return per_cpu(x86_cpu_to_logical_apicid, cpu) >> 16; } +static void x2apic_send_IPI(int cpu, int vector) +{ + u32 dest = per_cpu(x86_cpu_to_logical_apicid, cpu); + + x2apic_wrmsr_fence(); + __x2apic_send_IPI_dest(dest, vector, APIC_DEST_LOGICAL); +} + static void __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) { @@ -182,7 +190,7 @@ update_clusterinfo(struct notifier_block *nfb, unsigned long action, void *hcpu) return notifier_from_errno(err); } -static struct notifier_block __refdata x2apic_cpu_notifier = { +static struct notifier_block x2apic_cpu_notifier = { .notifier_call = update_clusterinfo, }; @@ -266,13 +274,13 @@ static struct apic apic_x2apic_cluster = { .cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and, + .send_IPI = x2apic_send_IPI, .send_IPI_mask = x2apic_send_IPI_mask, .send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself, .send_IPI_allbutself = x2apic_send_IPI_allbutself, .send_IPI_all = x2apic_send_IPI_all, .send_IPI_self = x2apic_send_IPI_self, - .wait_for_init_deassert = false, .inquire_remote_apic = NULL, .read = native_apic_msr_read, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 3ffd925655e0..a1242e2c12e6 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -36,6 +36,14 @@ static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id) return x2apic_enabled() && (x2apic_phys || x2apic_fadt_phys()); } +static void x2apic_send_IPI(int cpu, int vector) +{ + u32 dest = per_cpu(x86_cpu_to_apicid, cpu); + + x2apic_wrmsr_fence(); + __x2apic_send_IPI_dest(dest, vector, APIC_DEST_PHYSICAL); +} + static void __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) { @@ -122,13 +130,13 @@ static struct apic apic_x2apic_phys = { .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .send_IPI = x2apic_send_IPI, .send_IPI_mask = x2apic_send_IPI_mask, .send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself, .send_IPI_allbutself = x2apic_send_IPI_allbutself, .send_IPI_all = x2apic_send_IPI_all, .send_IPI_self = x2apic_send_IPI_self, - .wait_for_init_deassert = false, .inquire_remote_apic = NULL, .read = native_apic_msr_read, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index c8d92950bc04..d760c6bb37b5 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -248,7 +248,6 @@ static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip) APIC_DM_STARTUP; uv_write_global_mmr64(pnode, UVH_IPI_INT, val); - atomic_set(&init_deasserted, 1); return 0; } @@ -407,6 +406,7 @@ static struct apic __refdata apic_x2apic_uv_x = { .cpu_mask_to_apicid_and = uv_cpu_mask_to_apicid_and, + .send_IPI = uv_send_IPI_one, .send_IPI_mask = uv_send_IPI_mask, .send_IPI_mask_allbutself = uv_send_IPI_mask_allbutself, .send_IPI_allbutself = uv_send_IPI_allbutself, @@ -414,7 +414,6 @@ static struct apic __refdata apic_x2apic_uv_x = { .send_IPI_self = uv_send_IPI_self, .wakeup_secondary_cpu = uv_wakeup_secondary, - .wait_for_init_deassert = false, .inquire_remote_apic = NULL, .read = native_apic_msr_read, diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 927ec9235947..052c9c3026cc 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -919,7 +919,7 @@ recalc: } else if (jiffies_since_last_check > idle_period) { unsigned int idle_percentage; - idle_percentage = stime - last_stime; + idle_percentage = cputime_to_jiffies(stime - last_stime); idle_percentage *= 100; idle_percentage /= jiffies_since_last_check; use_apm_idle = (idle_percentage > idle_threshold); diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 8e3d22a1af94..84a7524b202c 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -43,18 +43,15 @@ void common(void) { #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); + OFFSET(IA32_SIGCONTEXT_ax, sigcontext_32, ax); + OFFSET(IA32_SIGCONTEXT_bx, sigcontext_32, bx); + OFFSET(IA32_SIGCONTEXT_cx, sigcontext_32, cx); + OFFSET(IA32_SIGCONTEXT_dx, sigcontext_32, dx); + OFFSET(IA32_SIGCONTEXT_si, sigcontext_32, si); + OFFSET(IA32_SIGCONTEXT_di, sigcontext_32, di); + OFFSET(IA32_SIGCONTEXT_bp, sigcontext_32, bp); + OFFSET(IA32_SIGCONTEXT_sp, sigcontext_32, sp); + OFFSET(IA32_SIGCONTEXT_ip, sigcontext_32, ip); BLANK(); OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext); @@ -68,9 +65,6 @@ 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_64.c b/arch/x86/kernel/asm-offsets_64.c index d8f42f902a0f..f2edafb5f24e 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -23,7 +23,6 @@ int main(void) { #ifdef CONFIG_PARAVIRT OFFSET(PV_IRQ_adjust_exception_frame, pv_irq_ops, adjust_exception_frame); - OFFSET(PV_CPU_usergs_sysret32, pv_cpu_ops, usergs_sysret32); OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64); OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs); BLANK(); diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c index 58118e207a69..145863d4d343 100644 --- a/arch/x86/kernel/check.c +++ b/arch/x86/kernel/check.c @@ -1,4 +1,4 @@ -#include <linux/module.h> +#include <linux/init.h> #include <linux/sched.h> #include <linux/kthread.h> #include <linux/workqueue.h> @@ -163,6 +163,5 @@ static int start_periodic_check_for_corruption(void) schedule_delayed_work(&bios_check_work, 0); return 0; } - -module_init(start_periodic_check_for_corruption); +device_initcall(start_periodic_check_for_corruption); diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 9bff68798836..58031303e304 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -41,11 +41,14 @@ obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_knc.o perf_event_p4.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_rapl.o perf_event_intel_cqm.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_pt.o perf_event_intel_bts.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_cstate.o obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += perf_event_intel_uncore.o \ perf_event_intel_uncore_snb.o \ perf_event_intel_uncore_snbep.o \ perf_event_intel_uncore_nhmex.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_msr.o +obj-$(CONFIG_CPU_SUP_AMD) += perf_event_msr.o endif diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index dd3a4baffe50..a07956a08936 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -11,6 +11,7 @@ #include <asm/cpu.h> #include <asm/smp.h> #include <asm/pci-direct.h> +#include <asm/delay.h> #ifdef CONFIG_X86_64 # include <asm/mmconfig.h> @@ -114,7 +115,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) const int K6_BUG_LOOP = 1000000; int n; void (*f_vide)(void); - unsigned long d, d2; + u64 d, d2; printk(KERN_INFO "AMD K6 stepping B detected - "); @@ -125,10 +126,10 @@ static void init_amd_k6(struct cpuinfo_x86 *c) n = K6_BUG_LOOP; f_vide = vide; - rdtscl(d); + d = rdtsc(); while (n--) f_vide(); - rdtscl(d2); + d2 = rdtsc(); d = d2-d; if (d > 20*K6_BUG_LOOP) @@ -303,7 +304,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c) int cpu = smp_processor_id(); /* get information required for multi-node processors */ - if (cpu_has_topoext) { + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { u32 eax, ebx, ecx, edx; cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); @@ -351,6 +352,7 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c) #ifdef CONFIG_SMP unsigned bits; int cpu = smp_processor_id(); + unsigned int socket_id, core_complex_id; bits = c->x86_coreid_bits; /* Low order bits define the core id (index of core in socket) */ @@ -360,6 +362,18 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c) /* use socket ID also for last level cache */ per_cpu(cpu_llc_id, cpu) = c->phys_proc_id; amd_get_topology(c); + + /* + * Fix percpu cpu_llc_id here as LLC topology is different + * for Fam17h systems. + */ + if (c->x86 != 0x17 || !cpuid_edx(0x80000006)) + return; + + socket_id = (c->apicid >> bits) - 1; + core_complex_id = (c->apicid & ((1 << bits) - 1)) >> 3; + + per_cpu(cpu_llc_id, cpu) = (socket_id << 3) | core_complex_id; #endif } @@ -420,8 +434,7 @@ static void srat_detect_node(struct cpuinfo_x86 *c) */ int ht_nodeid = c->initial_apicid; - if (ht_nodeid >= 0 && - __apicid_to_node[ht_nodeid] != NUMA_NO_NODE) + if (__apicid_to_node[ht_nodeid] != NUMA_NO_NODE) node = __apicid_to_node[ht_nodeid]; /* Pick a nearby node */ if (!node_online(node)) @@ -506,6 +519,9 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) /* A random value per boot for bit slice [12:upper_bit) */ va_align.bits = get_random_int() & va_align.mask; } + + if (cpu_has(c, X86_FEATURE_MWAITX)) + use_mwaitx_delay(); } static void early_init_amd(struct cpuinfo_x86 *c) @@ -661,9 +677,9 @@ static void init_amd_bd(struct cpuinfo_x86 *c) * Disable it on the affected CPUs. */ if ((c->x86_model >= 0x02) && (c->x86_model < 0x20)) { - if (!rdmsrl_safe(0xc0011021, &value) && !(value & 0x1E)) { + if (!rdmsrl_safe(MSR_F15H_IC_CFG, &value) && !(value & 0x1E)) { value |= 0x1E; - wrmsrl_safe(0xc0011021, value); + wrmsrl_safe(MSR_F15H_IC_CFG, value); } } } @@ -905,7 +921,7 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) void set_dr_addr_mask(unsigned long mask, int dr) { - if (!cpu_has_bpext) + if (!boot_cpu_has(X86_FEATURE_BPEXT)) return; switch (dr) { diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index d8fba5c15fbd..ae20be6e483c 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -43,7 +43,7 @@ static void init_c3(struct cpuinfo_x86 *c) /* store Centaur Extended Feature Flags as * word 5 of the CPU capability bit array */ - c->x86_capability[5] = cpuid_edx(0xC0000001); + c->x86_capability[CPUID_C000_0001_EDX] = cpuid_edx(0xC0000001); } #ifdef CONFIG_X86_32 /* Cyrix III family needs CX8 & PGE explicitly enabled. */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index cb9e5df42dd2..37830de8f60a 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -13,6 +13,7 @@ #include <linux/kgdb.h> #include <linux/smp.h> #include <linux/io.h> +#include <linux/syscore_ops.h> #include <asm/stackprotector.h> #include <asm/perf_event.h> @@ -272,10 +273,9 @@ __setup("nosmap", setup_disable_smap); static __always_inline void setup_smap(struct cpuinfo_x86 *c) { - unsigned long eflags; + unsigned long eflags = native_save_fl(); /* This should have been cleared long ago */ - raw_local_save_flags(eflags); BUG_ON(eflags & X86_EFLAGS_AC); if (cpu_has(c, X86_FEATURE_SMAP)) { @@ -581,14 +581,9 @@ void cpu_detect(struct cpuinfo_x86 *c) u32 junk, tfms, cap0, misc; cpuid(0x00000001, &tfms, &misc, &junk, &cap0); - c->x86 = (tfms >> 8) & 0xf; - c->x86_model = (tfms >> 4) & 0xf; - c->x86_mask = tfms & 0xf; - - if (c->x86 == 0xf) - c->x86 += (tfms >> 20) & 0xff; - if (c->x86 >= 0x6) - c->x86_model += ((tfms >> 16) & 0xf) << 4; + c->x86 = x86_family(tfms); + c->x86_model = x86_model(tfms); + c->x86_mask = x86_stepping(tfms); if (cap0 & (1<<19)) { c->x86_clflush_size = ((misc >> 8) & 0xff) * 8; @@ -599,50 +594,47 @@ void cpu_detect(struct cpuinfo_x86 *c) void get_cpu_cap(struct cpuinfo_x86 *c) { - u32 tfms, xlvl; - u32 ebx; + u32 eax, ebx, ecx, edx; /* Intel-defined flags: level 0x00000001 */ if (c->cpuid_level >= 0x00000001) { - u32 capability, excap; + cpuid(0x00000001, &eax, &ebx, &ecx, &edx); - cpuid(0x00000001, &tfms, &ebx, &excap, &capability); - c->x86_capability[0] = capability; - c->x86_capability[4] = excap; + c->x86_capability[CPUID_1_ECX] = ecx; + c->x86_capability[CPUID_1_EDX] = edx; } /* Additional Intel-defined flags: level 0x00000007 */ if (c->cpuid_level >= 0x00000007) { - u32 eax, ebx, ecx, edx; - cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx); - c->x86_capability[9] = ebx; + c->x86_capability[CPUID_7_0_EBX] = ebx; + + c->x86_capability[CPUID_6_EAX] = cpuid_eax(0x00000006); } /* Extended state features: level 0x0000000d */ if (c->cpuid_level >= 0x0000000d) { - u32 eax, ebx, ecx, edx; - cpuid_count(0x0000000d, 1, &eax, &ebx, &ecx, &edx); - c->x86_capability[10] = eax; + c->x86_capability[CPUID_D_1_EAX] = eax; } /* Additional Intel-defined flags: level 0x0000000F */ if (c->cpuid_level >= 0x0000000F) { - u32 eax, ebx, ecx, edx; /* QoS sub-leaf, EAX=0Fh, ECX=0 */ cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx); - c->x86_capability[11] = edx; + c->x86_capability[CPUID_F_0_EDX] = edx; + if (cpu_has(c, X86_FEATURE_CQM_LLC)) { /* will be overridden if occupancy monitoring exists */ c->x86_cache_max_rmid = ebx; /* QoS sub-leaf, EAX=0Fh, ECX=1 */ cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx); - c->x86_capability[12] = edx; + c->x86_capability[CPUID_F_1_EDX] = edx; + if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) { c->x86_cache_max_rmid = ecx; c->x86_cache_occ_scale = ebx; @@ -654,21 +646,24 @@ void get_cpu_cap(struct cpuinfo_x86 *c) } /* AMD-defined flags: level 0x80000001 */ - xlvl = cpuid_eax(0x80000000); - c->extended_cpuid_level = xlvl; + eax = cpuid_eax(0x80000000); + c->extended_cpuid_level = eax; - if ((xlvl & 0xffff0000) == 0x80000000) { - if (xlvl >= 0x80000001) { - c->x86_capability[1] = cpuid_edx(0x80000001); - c->x86_capability[6] = cpuid_ecx(0x80000001); + if ((eax & 0xffff0000) == 0x80000000) { + if (eax >= 0x80000001) { + cpuid(0x80000001, &eax, &ebx, &ecx, &edx); + + c->x86_capability[CPUID_8000_0001_ECX] = ecx; + c->x86_capability[CPUID_8000_0001_EDX] = edx; } } if (c->extended_cpuid_level >= 0x80000008) { - u32 eax = cpuid_eax(0x80000008); + cpuid(0x80000008, &eax, &ebx, &ecx, &edx); c->x86_virt_bits = (eax >> 8) & 0xff; c->x86_phys_bits = eax & 0xff; + c->x86_capability[CPUID_8000_0008_EBX] = ebx; } #ifdef CONFIG_X86_32 else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36)) @@ -678,6 +673,9 @@ void get_cpu_cap(struct cpuinfo_x86 *c) if (c->extended_cpuid_level >= 0x80000007) c->x86_power = cpuid_edx(0x80000007); + if (c->extended_cpuid_level >= 0x8000000a) + c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); + init_scattered_cpuid_features(c); } @@ -1109,10 +1107,10 @@ void print_cpu_info(struct cpuinfo_x86 *c) else printk(KERN_CONT "%d86", c->x86); - printk(KERN_CONT " (fam: %02x, model: %02x", c->x86, c->x86_model); + printk(KERN_CONT " (family: 0x%x, model: 0x%x", c->x86, c->x86_model); if (c->x86_mask || c->cpuid_level >= 0) - printk(KERN_CONT ", stepping: %02x)\n", c->x86_mask); + printk(KERN_CONT ", stepping: 0x%x)\n", c->x86_mask); else printk(KERN_CONT ")\n"); @@ -1184,11 +1182,11 @@ void syscall_init(void) * They both write to the same internal register. STAR allows to * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip. */ - wrmsrl(MSR_STAR, ((u64)__USER32_CS)<<48 | ((u64)__KERNEL_CS)<<32); - wrmsrl(MSR_LSTAR, entry_SYSCALL_64); + wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS); + wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); #ifdef CONFIG_IA32_EMULATION - wrmsrl(MSR_CSTAR, entry_SYSCALL_compat); + wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat); /* * This only works on Intel CPUs. * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP. @@ -1199,7 +1197,7 @@ void syscall_init(void) wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat); #else - wrmsrl(MSR_CSTAR, ignore_sysret); + wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret); wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG); wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); wrmsrl_safe(MSR_IA32_SYSENTER_EIP, 0ULL); @@ -1442,7 +1440,9 @@ void cpu_init(void) printk(KERN_INFO "Initializing CPU#%d\n", cpu); - if (cpu_feature_enabled(X86_FEATURE_VME) || cpu_has_tsc || cpu_has_de) + if (cpu_feature_enabled(X86_FEATURE_VME) || + cpu_has_tsc || + boot_cpu_has(X86_FEATURE_DE)) cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); load_current_idt(); @@ -1488,3 +1488,20 @@ inline bool __static_cpu_has_safe(u16 bit) return boot_cpu_has(bit); } EXPORT_SYMBOL_GPL(__static_cpu_has_safe); + +static void bsp_resume(void) +{ + if (this_cpu->c_bsp_resume) + this_cpu->c_bsp_resume(&boot_cpu_data); +} + +static struct syscore_ops cpu_syscore_ops = { + .resume = bsp_resume, +}; + +static int __init init_cpu_syscore(void) +{ + register_syscore_ops(&cpu_syscore_ops); + return 0; +} +core_initcall(init_cpu_syscore); diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index c37dc37e8317..2584265d4745 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -13,6 +13,7 @@ struct cpu_dev { void (*c_init)(struct cpuinfo_x86 *); void (*c_identify)(struct cpuinfo_x86 *); void (*c_detect_tlb)(struct cpuinfo_x86 *); + void (*c_bsp_resume)(struct cpuinfo_x86 *); int c_x86_vendor; #ifdef CONFIG_X86_32 /* Optional vendor specific routine to obtain the cache size. */ diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 50163fa9034f..565648bc1a0a 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -97,6 +97,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) switch (c->x86_model) { case 0x27: /* Penwell */ case 0x35: /* Cloverview */ + case 0x4a: /* Merrifield */ set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC_S3); break; default: @@ -371,6 +372,36 @@ static void detect_vmx_virtcap(struct cpuinfo_x86 *c) } } +static void init_intel_energy_perf(struct cpuinfo_x86 *c) +{ + u64 epb; + + /* + * Initialize MSR_IA32_ENERGY_PERF_BIAS if not already initialized. + * (x86_energy_perf_policy(8) is available to change it at run-time.) + */ + if (!cpu_has(c, X86_FEATURE_EPB)) + return; + + rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb); + if ((epb & 0xF) != ENERGY_PERF_BIAS_PERFORMANCE) + return; + + pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n"); + pr_warn_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n"); + epb = (epb & ~0xF) | ENERGY_PERF_BIAS_NORMAL; + wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb); +} + +static void intel_bsp_resume(struct cpuinfo_x86 *c) +{ + /* + * MSR_IA32_ENERGY_PERF_BIAS is lost across suspend/resume, + * so reinitialize it properly like during bootup: + */ + init_intel_energy_perf(c); +} + static void init_intel(struct cpuinfo_x86 *c) { unsigned int l2 = 0; @@ -414,7 +445,8 @@ static void init_intel(struct cpuinfo_x86 *c) if (cpu_has_xmm2) set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); - if (cpu_has_ds) { + + if (boot_cpu_has(X86_FEATURE_DS)) { unsigned int l1; rdmsr(MSR_IA32_MISC_ENABLE, l1, l2); if (!(l1 & (1<<11))) @@ -478,21 +510,7 @@ static void init_intel(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_VMX)) detect_vmx_virtcap(c); - /* - * Initialize MSR_IA32_ENERGY_PERF_BIAS if BIOS did not. - * x86_energy_perf_policy(8) is available to change it at run-time - */ - if (cpu_has(c, X86_FEATURE_EPB)) { - u64 epb; - - rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb); - if ((epb & 0xF) == ENERGY_PERF_BIAS_PERFORMANCE) { - pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n"); - pr_warn_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n"); - epb = (epb & ~0xF) | ENERGY_PERF_BIAS_NORMAL; - wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb); - } - } + init_intel_energy_perf(c); } #ifdef CONFIG_X86_32 @@ -747,6 +765,7 @@ static const struct cpu_dev intel_cpu_dev = { .c_detect_tlb = intel_detect_tlb, .c_early_init = early_init_intel, .c_init = init_intel, + .c_bsp_resume = intel_bsp_resume, .c_x86_vendor = X86_VENDOR_INTEL, }; diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index be4febc58b94..0b6c52388cf4 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -157,7 +157,7 @@ struct _cpuid4_info_regs { struct amd_northbridge *nb; }; -unsigned short num_cache_leaves; +static unsigned short num_cache_leaves; /* AMD doesn't have CPUID4. Emulate it here to report the same information to the user. This makes some assumptions about the machine: @@ -326,7 +326,7 @@ static void amd_calc_l3_indices(struct amd_northbridge *nb) * * @returns: the disabled index if used or negative value if slot free. */ -int amd_get_l3_disable_slot(struct amd_northbridge *nb, unsigned slot) +static int amd_get_l3_disable_slot(struct amd_northbridge *nb, unsigned slot) { unsigned int reg = 0; @@ -403,8 +403,8 @@ static void amd_l3_disable_index(struct amd_northbridge *nb, int cpu, * * @return: 0 on success, error status on failure */ -int amd_set_l3_disable_slot(struct amd_northbridge *nb, int cpu, unsigned slot, - unsigned long index) +static int amd_set_l3_disable_slot(struct amd_northbridge *nb, int cpu, + unsigned slot, unsigned long index) { int ret = 0; @@ -591,7 +591,7 @@ cpuid4_cache_lookup_regs(int index, struct _cpuid4_info_regs *this_leaf) unsigned edx; if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { - if (cpu_has_topoext) + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) cpuid_count(0x8000001d, index, &eax.full, &ebx.full, &ecx.full, &edx); else @@ -637,7 +637,7 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c) void init_amd_cacheinfo(struct cpuinfo_x86 *c) { - if (cpu_has_topoext) { + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { num_cache_leaves = find_num_cache_leaves(c); } else if (c->extended_cpuid_level >= 0x80000006) { if (cpuid_edx(0x80000006) & 0xf000) @@ -809,7 +809,7 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index, struct cacheinfo *this_leaf; int i, sibling; - if (cpu_has_topoext) { + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { unsigned int apicid, nshared, first, last; this_leaf = this_cpu_ci->info_list + index; diff --git a/arch/x86/kernel/cpu/intel_pt.h b/arch/x86/kernel/cpu/intel_pt.h index 1c338b0eba05..336878a5d205 100644 --- a/arch/x86/kernel/cpu/intel_pt.h +++ b/arch/x86/kernel/cpu/intel_pt.h @@ -25,32 +25,11 @@ */ #define TOPA_PMI_MARGIN 512 -/* - * Table of Physical Addresses bits - */ -enum topa_sz { - TOPA_4K = 0, - TOPA_8K, - TOPA_16K, - TOPA_32K, - TOPA_64K, - TOPA_128K, - TOPA_256K, - TOPA_512K, - TOPA_1MB, - TOPA_2MB, - TOPA_4MB, - TOPA_8MB, - TOPA_16MB, - TOPA_32MB, - TOPA_64MB, - TOPA_128MB, - TOPA_SZ_END, -}; +#define TOPA_SHIFT 12 -static inline unsigned int sizes(enum topa_sz tsz) +static inline unsigned int sizes(unsigned int tsz) { - return 1 << (tsz + 12); + return 1 << (tsz + TOPA_SHIFT); }; struct topa_entry { @@ -66,20 +45,26 @@ struct topa_entry { u64 rsvd4 : 16; }; -#define TOPA_SHIFT 12 -#define PT_CPUID_LEAVES 2 +#define PT_CPUID_LEAVES 2 +#define PT_CPUID_REGS_NUM 4 /* number of regsters (eax, ebx, ecx, edx) */ enum pt_capabilities { PT_CAP_max_subleaf = 0, PT_CAP_cr3_filtering, + PT_CAP_psb_cyc, + PT_CAP_mtc, PT_CAP_topa_output, PT_CAP_topa_multiple_entries, + PT_CAP_single_range_output, PT_CAP_payloads_lip, + PT_CAP_mtc_periods, + PT_CAP_cycle_thresholds, + PT_CAP_psb_periods, }; struct pt_pmu { struct pmu pmu; - u32 caps[4 * PT_CPUID_LEAVES]; + u32 caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES]; }; /** diff --git a/arch/x86/kernel/cpu/mcheck/Makefile b/arch/x86/kernel/cpu/mcheck/Makefile index bb34b03af252..a3311c886194 100644 --- a/arch/x86/kernel/cpu/mcheck/Makefile +++ b/arch/x86/kernel/cpu/mcheck/Makefile @@ -1,4 +1,4 @@ -obj-y = mce.o mce-severity.o +obj-y = mce.o mce-severity.o mce-genpool.o obj-$(CONFIG_X86_ANCIENT_MCE) += winchip.o p5.o obj-$(CONFIG_X86_MCE_INTEL) += mce_intel.o diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c index a1aef9533154..34c89a3e8260 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-apei.c +++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c @@ -57,7 +57,6 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err) m.addr = mem_err->physical_addr; mce_log(&m); - mce_notify_irq(); } EXPORT_SYMBOL_GPL(apei_mce_report_mem_error); diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c new file mode 100644 index 000000000000..0a850100c594 --- /dev/null +++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c @@ -0,0 +1,99 @@ +/* + * MCE event pool management in MCE context + * + * Copyright (C) 2015 Intel Corp. + * Author: Chen, Gong <gong.chen@linux.intel.com> + * + * This file is licensed under GPLv2. + */ +#include <linux/smp.h> +#include <linux/mm.h> +#include <linux/genalloc.h> +#include <linux/llist.h> +#include "mce-internal.h" + +/* + * printk() is not safe in MCE context. This is a lock-less memory allocator + * used to save error information organized in a lock-less list. + * + * This memory pool is only to be used to save MCE records in MCE context. + * MCE events are rare, so a fixed size memory pool should be enough. Use + * 2 pages to save MCE events for now (~80 MCE records at most). + */ +#define MCE_POOLSZ (2 * PAGE_SIZE) + +static struct gen_pool *mce_evt_pool; +static LLIST_HEAD(mce_event_llist); +static char gen_pool_buf[MCE_POOLSZ]; + +void mce_gen_pool_process(void) +{ + struct llist_node *head; + struct mce_evt_llist *node; + struct mce *mce; + + head = llist_del_all(&mce_event_llist); + if (!head) + return; + + head = llist_reverse_order(head); + llist_for_each_entry(node, head, llnode) { + mce = &node->mce; + atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce); + gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node)); + } +} + +bool mce_gen_pool_empty(void) +{ + return llist_empty(&mce_event_llist); +} + +int mce_gen_pool_add(struct mce *mce) +{ + struct mce_evt_llist *node; + + if (!mce_evt_pool) + return -EINVAL; + + node = (void *)gen_pool_alloc(mce_evt_pool, sizeof(*node)); + if (!node) { + pr_warn_ratelimited("MCE records pool full!\n"); + return -ENOMEM; + } + + memcpy(&node->mce, mce, sizeof(*mce)); + llist_add(&node->llnode, &mce_event_llist); + + return 0; +} + +static int mce_gen_pool_create(void) +{ + struct gen_pool *tmpp; + int ret = -ENOMEM; + + tmpp = gen_pool_create(ilog2(sizeof(struct mce_evt_llist)), -1); + if (!tmpp) + goto out; + + ret = gen_pool_add(tmpp, (unsigned long)gen_pool_buf, MCE_POOLSZ, -1); + if (ret) { + gen_pool_destroy(tmpp); + goto out; + } + + mce_evt_pool = tmpp; + +out: + return ret; +} + +int mce_gen_pool_init(void) +{ + /* Just init mce_gen_pool once. */ + if (mce_evt_pool) + return 0; + + return mce_gen_pool_create(); +} diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index fe32074b865b..547720efd923 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -13,6 +13,8 @@ enum severity_level { MCE_PANIC_SEVERITY, }; +extern struct atomic_notifier_head x86_mce_decoder_chain; + #define ATTR_LEN 16 #define INITIAL_CHECK_INTERVAL 5 * 60 /* 5 minutes */ @@ -24,6 +26,16 @@ struct mce_bank { char attrname[ATTR_LEN]; /* attribute name */ }; +struct mce_evt_llist { + struct llist_node llnode; + struct mce mce; +}; + +void mce_gen_pool_process(void); +bool mce_gen_pool_empty(void); +int mce_gen_pool_add(struct mce *mce); +int mce_gen_pool_init(void); + extern int (*mce_severity)(struct mce *a, int tolerant, char **msg, bool is_excp); struct dentry *mce_get_debugfs_dir(void); @@ -67,3 +79,5 @@ static inline int apei_clear_mce(u64 record_id) return -EINVAL; } #endif + +void mce_inject_log(struct mce *m); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index df919ff103c3..a006f4cd792b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -52,11 +52,11 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex); -#define rcu_dereference_check_mce(p) \ +#define mce_log_get_idx_check(p) \ ({ \ - rcu_lockdep_assert(rcu_read_lock_sched_held() || \ - lockdep_is_held(&mce_chrdev_read_mutex), \ - "suspicious rcu_dereference_check_mce() usage"); \ + RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ + !lockdep_is_held(&mce_chrdev_read_mutex), \ + "suspicious mce_log_get_idx_check() usage"); \ smp_load_acquire(&(p)); \ }) @@ -110,7 +110,8 @@ DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = { */ mce_banks_t mce_banks_ce_disabled; -static DEFINE_PER_CPU(struct work_struct, mce_work); +static struct work_struct mce_work; +static struct irq_work mce_irq_work; static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); @@ -118,14 +119,14 @@ static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); * CPU/chipset specific EDAC code can register a notifier call here to print * MCE errors in a human-readable form. */ -static ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain); +ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain); /* Do initial initialization of a struct mce */ void mce_setup(struct mce *m) { memset(m, 0, sizeof(struct mce)); m->cpu = m->extcpu = smp_processor_id(); - rdtscll(m->tsc); + m->tsc = rdtsc(); /* We hope get_seconds stays lockless */ m->time = get_seconds(); m->cpuvendor = boot_cpu_data.x86_vendor; @@ -157,12 +158,13 @@ void mce_log(struct mce *mce) /* Emit the trace record: */ trace_mce_record(mce); - atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce); + if (!mce_gen_pool_add(mce)) + irq_work_queue(&mce_irq_work); mce->finished = 0; wmb(); for (;;) { - entry = rcu_dereference_check_mce(mcelog.next); + entry = mce_log_get_idx_check(mcelog.next); for (;;) { /* @@ -196,48 +198,23 @@ void mce_log(struct mce *mce) set_bit(0, &mce_need_notify); } -static void drain_mcelog_buffer(void) +void mce_inject_log(struct mce *m) { - unsigned int next, i, prev = 0; - - next = ACCESS_ONCE(mcelog.next); - - do { - struct mce *m; - - /* drain what was logged during boot */ - for (i = prev; i < next; i++) { - unsigned long start = jiffies; - unsigned retries = 1; - - m = &mcelog.entry[i]; - - while (!m->finished) { - if (time_after_eq(jiffies, start + 2*retries)) - retries++; - - cpu_relax(); - - if (!m->finished && retries >= 4) { - pr_err("skipping error being logged currently!\n"); - break; - } - } - smp_rmb(); - atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m); - } - - memset(mcelog.entry + prev, 0, (next - prev) * sizeof(*m)); - prev = next; - next = cmpxchg(&mcelog.next, prev, 0); - } while (next != prev); + mutex_lock(&mce_chrdev_read_mutex); + mce_log(m); + mutex_unlock(&mce_chrdev_read_mutex); } +EXPORT_SYMBOL_GPL(mce_inject_log); +static struct notifier_block mce_srao_nb; void mce_register_decode_chain(struct notifier_block *nb) { + /* Ensure SRAO notifier has the highest priority in the decode chain. */ + if (nb != &mce_srao_nb && nb->priority == INT_MAX) + nb->priority -= 1; + atomic_notifier_chain_register(&x86_mce_decoder_chain, nb); - drain_mcelog_buffer(); } EXPORT_SYMBOL_GPL(mce_register_decode_chain); @@ -461,61 +438,6 @@ static inline void mce_gather_info(struct mce *m, struct pt_regs *regs) } } -/* - * Simple lockless ring to communicate PFNs from the exception handler with the - * process context work function. This is vastly simplified because there's - * only a single reader and a single writer. - */ -#define MCE_RING_SIZE 16 /* we use one entry less */ - -struct mce_ring { - unsigned short start; - unsigned short end; - unsigned long ring[MCE_RING_SIZE]; -}; -static DEFINE_PER_CPU(struct mce_ring, mce_ring); - -/* Runs with CPU affinity in workqueue */ -static int mce_ring_empty(void) -{ - struct mce_ring *r = this_cpu_ptr(&mce_ring); - - return r->start == r->end; -} - -static int mce_ring_get(unsigned long *pfn) -{ - struct mce_ring *r; - int ret = 0; - - *pfn = 0; - get_cpu(); - r = this_cpu_ptr(&mce_ring); - if (r->start == r->end) - goto out; - *pfn = r->ring[r->start]; - r->start = (r->start + 1) % MCE_RING_SIZE; - ret = 1; -out: - put_cpu(); - return ret; -} - -/* Always runs in MCE context with preempt off */ -static int mce_ring_add(unsigned long pfn) -{ - struct mce_ring *r = this_cpu_ptr(&mce_ring); - unsigned next; - - next = (r->end + 1) % MCE_RING_SIZE; - if (next == r->start) - return -1; - r->ring[r->end] = pfn; - wmb(); - r->end = next; - return 0; -} - int mce_available(struct cpuinfo_x86 *c) { if (mca_cfg.disabled) @@ -525,12 +447,10 @@ int mce_available(struct cpuinfo_x86 *c) static void mce_schedule_work(void) { - if (!mce_ring_empty()) - schedule_work(this_cpu_ptr(&mce_work)); + if (!mce_gen_pool_empty() && keventd_up()) + schedule_work(&mce_work); } -static DEFINE_PER_CPU(struct irq_work, mce_irq_work); - static void mce_irq_work_cb(struct irq_work *entry) { mce_notify_irq(); @@ -551,8 +471,51 @@ static void mce_report_event(struct pt_regs *regs) return; } - irq_work_queue(this_cpu_ptr(&mce_irq_work)); + irq_work_queue(&mce_irq_work); +} + +/* + * Check if the address reported by the CPU is in a format we can parse. + * It would be possible to add code for most other cases, but all would + * be somewhat complicated (e.g. segment offset would require an instruction + * parser). So only support physical addresses up to page granuality for now. + */ +static int mce_usable_address(struct mce *m) +{ + if (!(m->status & MCI_STATUS_MISCV) || !(m->status & MCI_STATUS_ADDRV)) + return 0; + + /* Checks after this one are Intel-specific: */ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return 1; + + if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT) + return 0; + if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS) + return 0; + return 1; +} + +static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct mce *mce = (struct mce *)data; + unsigned long pfn; + + if (!mce) + return NOTIFY_DONE; + + if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) { + pfn = mce->addr >> PAGE_SHIFT; + memory_failure(pfn, MCE_VECTOR, 0); + } + + return NOTIFY_OK; } +static struct notifier_block mce_srao_nb = { + .notifier_call = srao_decode_notifier, + .priority = INT_MAX, +}; /* * Read ADDR and MISC registers. @@ -580,10 +543,10 @@ static bool memory_error(struct mce *m) struct cpuinfo_x86 *c = &boot_cpu_data; if (c->x86_vendor == X86_VENDOR_AMD) { - /* - * coming soon - */ - return false; + /* ErrCodeExt[20:16] */ + u8 xec = (m->status >> 16) & 0x1f; + + return (xec == 0x0 || xec == 0x8); } else if (c->x86_vendor == X86_VENDOR_INTEL) { /* * Intel SDM Volume 3B - 15.9.2 Compound Error Codes @@ -625,7 +588,7 @@ DEFINE_PER_CPU(unsigned, mce_poll_count); */ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) { - bool error_logged = false; + bool error_seen = false; struct mce m; int severity; int i; @@ -659,6 +622,8 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) (m.status & (mca_cfg.ser ? MCI_STATUS_S : MCI_STATUS_UC))) continue; + error_seen = true; + mce_read_aux(&m, i); if (!(flags & MCP_TIMESTAMP)) @@ -666,24 +631,24 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) severity = mce_severity(&m, mca_cfg.tolerant, NULL, false); - /* - * In the cases where we don't have a valid address after all, - * do not add it into the ring buffer. - */ - if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) { - if (m.status & MCI_STATUS_ADDRV) { - mce_ring_add(m.addr >> PAGE_SHIFT); - mce_schedule_work(); - } - } + if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) + if (m.status & MCI_STATUS_ADDRV) + m.severity = severity; /* * Don't get the IP here because it's unlikely to * have anything to do with the actual error location. */ - if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) { - error_logged = true; + if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) mce_log(&m); + else if (mce_usable_address(&m)) { + /* + * Although we skipped logging this, we still want + * to take action. Add to the pool so the registered + * notifiers will see it. + */ + if (!mce_gen_pool_add(&m)) + mce_schedule_work(); } /* @@ -699,7 +664,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) sync_core(); - return error_logged; + return error_seen; } EXPORT_SYMBOL_GPL(machine_check_poll); @@ -986,23 +951,6 @@ reset: return ret; } -/* - * Check if the address reported by the CPU is in a format we can parse. - * It would be possible to add code for most other cases, but all would - * be somewhat complicated (e.g. segment offset would require an instruction - * parser). So only support physical addresses up to page granuality for now. - */ -static int mce_usable_address(struct mce *m) -{ - if (!(m->status & MCI_STATUS_MISCV) || !(m->status & MCI_STATUS_ADDRV)) - return 0; - if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT) - return 0; - if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS) - return 0; - return 1; -} - static void mce_clear_state(unsigned long *toclear) { int i; @@ -1029,7 +977,6 @@ void do_machine_check(struct pt_regs *regs, long error_code) { struct mca_config *cfg = &mca_cfg; struct mce m, *final; - enum ctx_state prev_state; int i; int worst = 0; int severity; @@ -1055,7 +1002,18 @@ void do_machine_check(struct pt_regs *regs, long error_code) int flags = MF_ACTION_REQUIRED; int lmce = 0; - prev_state = ist_enter(regs); + /* If this CPU is offline, just bail out. */ + if (cpu_is_offline(smp_processor_id())) { + u64 mcgstatus; + + mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); + if (mcgstatus & MCG_STATUS_RIPV) { + mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); + return; + } + } + + ist_enter(regs); this_cpu_inc(mce_exception_count); @@ -1143,15 +1101,8 @@ void do_machine_check(struct pt_regs *regs, long error_code) mce_read_aux(&m, i); - /* - * Action optional error. Queue address for later processing. - * When the ring overflows we just ignore the AO error. - * RED-PEN add some logging mechanism when - * usable_address or mce_add_ring fails. - * RED-PEN don't ignore overflow for mca_cfg.tolerant == 0 - */ - if (severity == MCE_AO_SEVERITY && mce_usable_address(&m)) - mce_ring_add(m.addr >> PAGE_SHIFT); + /* assuming valid severity level != 0 */ + m.severity = severity; mce_log(&m); @@ -1227,7 +1178,7 @@ out: local_irq_disable(); ist_end_non_atomic(); done: - ist_exit(regs, prev_state); + ist_exit(regs); } EXPORT_SYMBOL_GPL(do_machine_check); @@ -1247,14 +1198,11 @@ int memory_failure(unsigned long pfn, int vector, int flags) /* * Action optional processing happens here (picking up * from the list of faulting pages that do_machine_check() - * placed into the "ring"). + * placed into the genpool). */ static void mce_process_work(struct work_struct *dummy) { - unsigned long pfn; - - while (mce_ring_get(&pfn)) - memory_failure(pfn, MCE_VECTOR, 0); + mce_gen_pool_process(); } #ifdef CONFIG_X86_MCE_INTEL @@ -1651,6 +1599,8 @@ static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c) winchip_mcheck_init(c); return 1; break; + default: + return 0; } return 0; @@ -1670,6 +1620,8 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) mce_amd_feature_init(c); mce_flags.overflow_recov = !!(ebx & BIT(0)); mce_flags.succor = !!(ebx & BIT(1)); + mce_flags.smca = !!(ebx & BIT(3)); + break; } @@ -1678,6 +1630,17 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) } } +static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c) +{ + switch (c->x86_vendor) { + case X86_VENDOR_INTEL: + mce_intel_feature_clear(c); + break; + default: + break; + } +} + static void mce_start_timer(unsigned int cpu, struct timer_list *t) { unsigned long iv = check_interval * HZ; @@ -1731,13 +1694,36 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c) return; } + if (mce_gen_pool_init()) { + mca_cfg.disabled = true; + pr_emerg("Couldn't allocate MCE records pool!\n"); + return; + } + machine_check_vector = do_machine_check; __mcheck_cpu_init_generic(); __mcheck_cpu_init_vendor(c); __mcheck_cpu_init_timer(); - INIT_WORK(this_cpu_ptr(&mce_work), mce_process_work); - init_irq_work(this_cpu_ptr(&mce_irq_work), &mce_irq_work_cb); +} + +/* + * Called for each booted CPU to clear some machine checks opt-ins + */ +void mcheck_cpu_clear(struct cpuinfo_x86 *c) +{ + if (mca_cfg.disabled) + return; + + if (!mce_available(c)) + return; + + /* + * Possibly to clear general settings generic to x86 + * __mcheck_cpu_clear_generic(c); + */ + __mcheck_cpu_clear_vendor(c); + } /* @@ -1784,7 +1770,7 @@ static void collect_tscs(void *data) { unsigned long *cpu_tsc = (unsigned long *)data; - rdtscll(cpu_tsc[smp_processor_id()]); + cpu_tsc[smp_processor_id()] = rdtsc(); } static int mce_apei_read_done; @@ -1850,7 +1836,7 @@ static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf, goto out; } - next = rcu_dereference_check_mce(mcelog.next); + next = mce_log_get_idx_check(mcelog.next); /* Only supports full reads right now */ err = -EINVAL; @@ -2056,8 +2042,12 @@ __setup("mce", mcheck_enable); int __init mcheck_init(void) { mcheck_intel_therm_init(); + mce_register_decode_chain(&mce_srao_nb); mcheck_vendor_init_severity(); + INIT_WORK(&mce_work, mce_process_work); + init_irq_work(&mce_irq_work, mce_irq_work_cb); + return 0; } @@ -2069,7 +2059,7 @@ int __init mcheck_init(void) * Disable machine checks on suspend and shutdown. We can't really handle * them later. */ -static int mce_disable_error_reporting(void) +static void mce_disable_error_reporting(void) { int i; @@ -2079,17 +2069,32 @@ static int mce_disable_error_reporting(void) if (b->init) wrmsrl(MSR_IA32_MCx_CTL(i), 0); } - return 0; + return; +} + +static void vendor_disable_error_reporting(void) +{ + /* + * Don't clear on Intel CPUs. Some of these MSRs are socket-wide. + * Disabling them for just a single offlined CPU is bad, since it will + * inhibit reporting for all shared resources on the socket like the + * last level cache (LLC), the integrated memory controller (iMC), etc. + */ + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) + return; + + mce_disable_error_reporting(); } static int mce_syscore_suspend(void) { - return mce_disable_error_reporting(); + vendor_disable_error_reporting(); + return 0; } static void mce_syscore_shutdown(void) { - mce_disable_error_reporting(); + vendor_disable_error_reporting(); } /* @@ -2369,19 +2374,14 @@ static void mce_device_remove(unsigned int cpu) static void mce_disable_cpu(void *h) { unsigned long action = *(unsigned long *)h; - int i; if (!mce_available(raw_cpu_ptr(&cpu_info))) return; if (!(action & CPU_TASKS_FROZEN)) cmci_clear(); - for (i = 0; i < mca_cfg.banks; i++) { - struct mce_bank *b = &mce_banks[i]; - if (b->init) - wrmsrl(MSR_IA32_MCx_CTL(i), 0); - } + vendor_disable_error_reporting(); } static void mce_reenable_cpu(void *h) @@ -2591,5 +2591,20 @@ static int __init mcheck_debugfs_init(void) return 0; } -late_initcall(mcheck_debugfs_init); +#else +static int __init mcheck_debugfs_init(void) { return -EINVAL; } #endif + +static int __init mcheck_late_init(void) +{ + mcheck_debugfs_init(); + + /* + * Flush out everything that has been logged during early boot, now that + * everything has been initialized (workqueues, decoders, ...). + */ + mce_schedule_work(); + + return 0; +} +late_initcall(mcheck_late_init); diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 844f56c5616d..1e8bb6c94f14 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -146,6 +146,27 @@ void mce_intel_hcpu_update(unsigned long cpu) per_cpu(cmci_storm_state, cpu) = CMCI_STORM_NONE; } +static void cmci_toggle_interrupt_mode(bool on) +{ + unsigned long flags, *owned; + int bank; + u64 val; + + raw_spin_lock_irqsave(&cmci_discover_lock, flags); + owned = this_cpu_ptr(mce_banks_owned); + for_each_set_bit(bank, owned, MAX_NR_BANKS) { + rdmsrl(MSR_IA32_MCx_CTL2(bank), val); + + if (on) + val |= MCI_CTL2_CMCI_EN; + else + val &= ~MCI_CTL2_CMCI_EN; + + wrmsrl(MSR_IA32_MCx_CTL2(bank), val); + } + raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); +} + unsigned long cmci_intel_adjust_timer(unsigned long interval) { if ((this_cpu_read(cmci_backoff_cnt) > 0) && @@ -175,7 +196,7 @@ unsigned long cmci_intel_adjust_timer(unsigned long interval) */ if (!atomic_read(&cmci_storm_on_cpus)) { __this_cpu_write(cmci_storm_state, CMCI_STORM_NONE); - cmci_reenable(); + cmci_toggle_interrupt_mode(true); cmci_recheck(); } return CMCI_POLL_INTERVAL; @@ -186,22 +207,6 @@ unsigned long cmci_intel_adjust_timer(unsigned long interval) } } -static void cmci_storm_disable_banks(void) -{ - unsigned long flags, *owned; - int bank; - u64 val; - - raw_spin_lock_irqsave(&cmci_discover_lock, flags); - owned = this_cpu_ptr(mce_banks_owned); - for_each_set_bit(bank, owned, MAX_NR_BANKS) { - rdmsrl(MSR_IA32_MCx_CTL2(bank), val); - val &= ~MCI_CTL2_CMCI_EN; - wrmsrl(MSR_IA32_MCx_CTL2(bank), val); - } - raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); -} - static bool cmci_storm_detect(void) { unsigned int cnt = __this_cpu_read(cmci_storm_cnt); @@ -223,7 +228,7 @@ static bool cmci_storm_detect(void) if (cnt <= CMCI_STORM_THRESHOLD) return false; - cmci_storm_disable_banks(); + cmci_toggle_interrupt_mode(false); __this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE); r = atomic_add_return(1, &cmci_storm_on_cpus); mce_timer_kick(CMCI_STORM_INTERVAL); @@ -246,7 +251,6 @@ static void intel_threshold_interrupt(void) return; machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)); - mce_notify_irq(); } /* @@ -435,7 +439,7 @@ static void intel_init_cmci(void) cmci_recheck(); } -void intel_init_lmce(void) +static void intel_init_lmce(void) { u64 val; @@ -448,9 +452,26 @@ void intel_init_lmce(void) wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN); } +static void intel_clear_lmce(void) +{ + u64 val; + + if (!lmce_supported()) + return; + + rdmsrl(MSR_IA32_MCG_EXT_CTL, val); + val &= ~MCG_EXT_CTL_LMCE_EN; + wrmsrl(MSR_IA32_MCG_EXT_CTL, val); +} + void mce_intel_feature_init(struct cpuinfo_x86 *c) { intel_init_thermal(c); intel_init_cmci(); intel_init_lmce(); } + +void mce_intel_feature_clear(struct cpuinfo_x86 *c) +{ + intel_clear_lmce(); +} diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c index 737b0ad4e61a..12402e10aeff 100644 --- a/arch/x86/kernel/cpu/mcheck/p5.c +++ b/arch/x86/kernel/cpu/mcheck/p5.c @@ -19,10 +19,9 @@ int mce_p5_enabled __read_mostly; /* Machine check handler for Pentium class Intel CPUs: */ static void pentium_machine_check(struct pt_regs *regs, long error_code) { - enum ctx_state prev_state; u32 loaddr, hi, lotype; - prev_state = ist_enter(regs); + ist_enter(regs); rdmsr(MSR_IA32_P5_MC_ADDR, loaddr, hi); rdmsr(MSR_IA32_P5_MC_TYPE, lotype, hi); @@ -39,7 +38,7 @@ static void pentium_machine_check(struct pt_regs *regs, long error_code) add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); - ist_exit(regs, prev_state); + ist_exit(regs); } /* Set up machine check reporting for processors with Intel style MCE: */ diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 1af51b1586d7..2c5aaf8c2e2f 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -503,14 +503,6 @@ void intel_init_thermal(struct cpuinfo_x86 *c) return; } - /* Check whether a vector already exists */ - if (h & APIC_VECTOR_MASK) { - printk(KERN_DEBUG - "CPU%d: Thermal LVT vector (%#x) already installed\n", - cpu, (h & APIC_VECTOR_MASK)); - return; - } - /* early Pentium M models use different method for enabling TM2 */ if (cpu_has(c, X86_FEATURE_TM2)) { if (c->x86 == 6 && (c->x86_model == 9 || c->x86_model == 13)) { diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c index 44f138296fbe..01dd8702880b 100644 --- a/arch/x86/kernel/cpu/mcheck/winchip.c +++ b/arch/x86/kernel/cpu/mcheck/winchip.c @@ -15,12 +15,12 @@ /* Machine check handler for WinChip C6: */ static void winchip_machine_check(struct pt_regs *regs, long error_code) { - enum ctx_state prev_state = ist_enter(regs); + ist_enter(regs); printk(KERN_EMERG "CPU0: Machine Check Exception.\n"); add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); - ist_exit(regs, prev_state); + ist_exit(regs); } /* Set up machine check reporting on the Winchip C6 series */ diff --git a/arch/x86/kernel/cpu/microcode/Makefile b/arch/x86/kernel/cpu/microcode/Makefile index 285c85427c32..220b1a508513 100644 --- a/arch/x86/kernel/cpu/microcode/Makefile +++ b/arch/x86/kernel/cpu/microcode/Makefile @@ -2,6 +2,3 @@ microcode-y := core.o obj-$(CONFIG_MICROCODE) += microcode.o microcode-$(CONFIG_MICROCODE_INTEL) += intel.o intel_lib.o microcode-$(CONFIG_MICROCODE_AMD) += amd.o -obj-$(CONFIG_MICROCODE_EARLY) += core_early.o -obj-$(CONFIG_MICROCODE_INTEL_EARLY) += intel_early.o -obj-$(CONFIG_MICROCODE_AMD_EARLY) += amd_early.o diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 12829c3ced3c..2233f8a76615 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -1,5 +1,9 @@ /* * AMD CPU Microcode Update Driver for Linux + * + * This driver allows to upgrade microcode on F10h AMD + * CPUs and later. + * * Copyright (C) 2008-2011 Advanced Micro Devices Inc. * * Author: Peter Oruba <peter.oruba@amd.com> @@ -7,34 +11,31 @@ * Based on work by: * Tigran Aivazian <tigran@aivazian.fsnet.co.uk> * - * Maintainers: - * Andreas Herrmann <herrmann.der.user@googlemail.com> - * Borislav Petkov <bp@alien8.de> + * early loader: + * Copyright (C) 2013 Advanced Micro Devices, Inc. * - * This driver allows to upgrade microcode on F10h AMD - * CPUs and later. + * Author: Jacob Shin <jacob.shin@amd.com> + * Fixes: Borislav Petkov <bp@suse.de> * * Licensed under the terms of the GNU General Public * License version 2. See file COPYING for details. */ +#define pr_fmt(fmt) "microcode: " fmt -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - +#include <linux/earlycpio.h> #include <linux/firmware.h> #include <linux/uaccess.h> #include <linux/vmalloc.h> +#include <linux/initrd.h> #include <linux/kernel.h> -#include <linux/module.h> #include <linux/pci.h> +#include <asm/microcode_amd.h> #include <asm/microcode.h> #include <asm/processor.h> +#include <asm/setup.h> +#include <asm/cpu.h> #include <asm/msr.h> -#include <asm/microcode_amd.h> - -MODULE_DESCRIPTION("AMD Microcode Update Driver"); -MODULE_AUTHOR("Peter Oruba"); -MODULE_LICENSE("GPL v2"); static struct equiv_cpu_entry *equiv_cpu_table; @@ -47,6 +48,432 @@ struct ucode_patch { static LIST_HEAD(pcache); +/* + * This points to the current valid container of microcode patches which we will + * save from the initrd before jettisoning its contents. + */ +static u8 *container; +static size_t container_size; + +static u32 ucode_new_rev; +u8 amd_ucode_patch[PATCH_MAX_SIZE]; +static u16 this_equiv_id; + +static struct cpio_data ucode_cpio; + +/* + * Microcode patch container file is prepended to the initrd in cpio format. + * See Documentation/x86/early-microcode.txt + */ +static __initdata char ucode_path[] = "kernel/x86/microcode/AuthenticAMD.bin"; + +static struct cpio_data __init find_ucode_in_initrd(void) +{ + long offset = 0; + char *path; + void *start; + size_t size; + +#ifdef CONFIG_X86_32 + struct boot_params *p; + + /* + * On 32-bit, early load occurs before paging is turned on so we need + * to use physical addresses. + */ + p = (struct boot_params *)__pa_nodebug(&boot_params); + path = (char *)__pa_nodebug(ucode_path); + start = (void *)p->hdr.ramdisk_image; + size = p->hdr.ramdisk_size; +#else + path = ucode_path; + start = (void *)(boot_params.hdr.ramdisk_image + PAGE_OFFSET); + size = boot_params.hdr.ramdisk_size; +#endif + + return find_cpio_data(path, start, size, &offset); +} + +static size_t compute_container_size(u8 *data, u32 total_size) +{ + size_t size = 0; + u32 *header = (u32 *)data; + + if (header[0] != UCODE_MAGIC || + header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */ + header[2] == 0) /* size */ + return size; + + size = header[2] + CONTAINER_HDR_SZ; + total_size -= size; + data += size; + + while (total_size) { + u16 patch_size; + + header = (u32 *)data; + + if (header[0] != UCODE_UCODE_TYPE) + break; + + /* + * Sanity-check patch size. + */ + patch_size = header[1]; + if (patch_size > PATCH_MAX_SIZE) + break; + + size += patch_size + SECTION_HDR_SIZE; + data += patch_size + SECTION_HDR_SIZE; + total_size -= patch_size + SECTION_HDR_SIZE; + } + + return size; +} + +/* + * Early load occurs before we can vmalloc(). So we look for the microcode + * patch container file in initrd, traverse equivalent cpu table, look for a + * matching microcode patch, and update, all in initrd memory in place. + * When vmalloc() is available for use later -- on 64-bit during first AP load, + * and on 32-bit during save_microcode_in_initrd_amd() -- we can call + * load_microcode_amd() to save equivalent cpu table and microcode patches in + * kernel heap memory. + */ +static void apply_ucode_in_initrd(void *ucode, size_t size, bool save_patch) +{ + struct equiv_cpu_entry *eq; + size_t *cont_sz; + u32 *header; + u8 *data, **cont; + u8 (*patch)[PATCH_MAX_SIZE]; + u16 eq_id = 0; + int offset, left; + u32 rev, eax, ebx, ecx, edx; + u32 *new_rev; + +#ifdef CONFIG_X86_32 + new_rev = (u32 *)__pa_nodebug(&ucode_new_rev); + cont_sz = (size_t *)__pa_nodebug(&container_size); + cont = (u8 **)__pa_nodebug(&container); + patch = (u8 (*)[PATCH_MAX_SIZE])__pa_nodebug(&amd_ucode_patch); +#else + new_rev = &ucode_new_rev; + cont_sz = &container_size; + cont = &container; + patch = &amd_ucode_patch; +#endif + + data = ucode; + left = size; + header = (u32 *)data; + + /* find equiv cpu table */ + if (header[0] != UCODE_MAGIC || + header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */ + header[2] == 0) /* size */ + return; + + eax = 0x00000001; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + + while (left > 0) { + eq = (struct equiv_cpu_entry *)(data + CONTAINER_HDR_SZ); + + *cont = data; + + /* Advance past the container header */ + offset = header[2] + CONTAINER_HDR_SZ; + data += offset; + left -= offset; + + eq_id = find_equiv_id(eq, eax); + if (eq_id) { + this_equiv_id = eq_id; + *cont_sz = compute_container_size(*cont, left + offset); + + /* + * truncate how much we need to iterate over in the + * ucode update loop below + */ + left = *cont_sz - offset; + break; + } + + /* + * support multiple container files appended together. if this + * one does not have a matching equivalent cpu entry, we fast + * forward to the next container file. + */ + while (left > 0) { + header = (u32 *)data; + if (header[0] == UCODE_MAGIC && + header[1] == UCODE_EQUIV_CPU_TABLE_TYPE) + break; + + offset = header[1] + SECTION_HDR_SIZE; + data += offset; + left -= offset; + } + + /* mark where the next microcode container file starts */ + offset = data - (u8 *)ucode; + ucode = data; + } + + if (!eq_id) { + *cont = NULL; + *cont_sz = 0; + return; + } + + if (check_current_patch_level(&rev, true)) + return; + + while (left > 0) { + struct microcode_amd *mc; + + header = (u32 *)data; + if (header[0] != UCODE_UCODE_TYPE || /* type */ + header[1] == 0) /* size */ + break; + + mc = (struct microcode_amd *)(data + SECTION_HDR_SIZE); + + if (eq_id == mc->hdr.processor_rev_id && rev < mc->hdr.patch_id) { + + if (!__apply_microcode_amd(mc)) { + rev = mc->hdr.patch_id; + *new_rev = rev; + + if (save_patch) + memcpy(patch, mc, + min_t(u32, header[1], PATCH_MAX_SIZE)); + } + } + + offset = header[1] + SECTION_HDR_SIZE; + data += offset; + left -= offset; + } +} + +static bool __init load_builtin_amd_microcode(struct cpio_data *cp, + unsigned int family) +{ +#ifdef CONFIG_X86_64 + char fw_name[36] = "amd-ucode/microcode_amd.bin"; + + if (family >= 0x15) + snprintf(fw_name, sizeof(fw_name), + "amd-ucode/microcode_amd_fam%.2xh.bin", 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; + size_t *size; + +#ifdef CONFIG_X86_32 + data = (void **)__pa_nodebug(&ucode_cpio.data); + size = (size_t *)__pa_nodebug(&ucode_cpio.size); +#else + data = &ucode_cpio.data; + size = &ucode_cpio.size; +#endif + + cp = find_ucode_in_initrd(); + if (!cp.data) { + if (!load_builtin_amd_microcode(&cp, family)) + return; + } + + *data = cp.data; + *size = cp.size; + + apply_ucode_in_initrd(cp.data, cp.size, true); +} + +#ifdef CONFIG_X86_32 +/* + * On 32-bit, since AP's early load occurs before paging is turned on, we + * cannot traverse cpu_equiv_table and pcache in kernel heap memory. So during + * cold boot, AP will apply_ucode_in_initrd() just like the BSP. During + * save_microcode_in_initrd_amd() BSP's patch is copied to amd_ucode_patch, + * which is used upon resume from suspend. + */ +void load_ucode_amd_ap(void) +{ + struct microcode_amd *mc; + size_t *usize; + void **ucode; + + mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch); + if (mc->hdr.patch_id && mc->hdr.processor_rev_id) { + __apply_microcode_amd(mc); + return; + } + + ucode = (void *)__pa_nodebug(&container); + usize = (size_t *)__pa_nodebug(&container_size); + + if (!*ucode || !*usize) + return; + + apply_ucode_in_initrd(*ucode, *usize, false); +} + +static void __init collect_cpu_sig_on_bsp(void *arg) +{ + unsigned int cpu = smp_processor_id(); + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + + uci->cpu_sig.sig = cpuid_eax(0x00000001); +} + +static void __init get_bsp_sig(void) +{ + unsigned int bsp = boot_cpu_data.cpu_index; + struct ucode_cpu_info *uci = ucode_cpu_info + bsp; + + if (!uci->cpu_sig.sig) + smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1); +} +#else +void load_ucode_amd_ap(void) +{ + unsigned int cpu = smp_processor_id(); + struct equiv_cpu_entry *eq; + struct microcode_amd *mc; + u32 rev, eax; + u16 eq_id; + + /* Exit if called on the BSP. */ + if (!cpu) + return; + + if (!container) + return; + + /* + * 64-bit runs with paging enabled, thus early==false. + */ + if (check_current_patch_level(&rev, false)) + return; + + eax = cpuid_eax(0x00000001); + eq = (struct equiv_cpu_entry *)(container + CONTAINER_HDR_SZ); + + eq_id = find_equiv_id(eq, eax); + if (!eq_id) + return; + + if (eq_id == this_equiv_id) { + mc = (struct microcode_amd *)amd_ucode_patch; + + if (mc && rev < mc->hdr.patch_id) { + if (!__apply_microcode_amd(mc)) + ucode_new_rev = mc->hdr.patch_id; + } + + } else { + if (!ucode_cpio.data) + return; + + /* + * AP has a different equivalence ID than BSP, looks like + * mixed-steppings silicon so go through the ucode blob anew. + */ + apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size, false); + } +} +#endif + +int __init save_microcode_in_initrd_amd(void) +{ + unsigned long cont; + int retval = 0; + enum ucode_state ret; + u8 *cont_va; + u32 eax; + + if (!container) + return -EINVAL; + +#ifdef CONFIG_X86_32 + get_bsp_sig(); + cont = (unsigned long)container; + cont_va = __va(container); +#else + /* + * We need the physical address of the container for both bitness since + * boot_params.hdr.ramdisk_image is a physical address. + */ + cont = __pa(container); + cont_va = container; +#endif + + /* + * Take into account the fact that the ramdisk might get relocated and + * therefore we need to recompute the container's position in virtual + * memory space. + */ + if (relocated_ramdisk) + container = (u8 *)(__va(relocated_ramdisk) + + (cont - boot_params.hdr.ramdisk_image)); + else + container = cont_va; + + if (ucode_new_rev) + pr_info("microcode: updated early to new patch_level=0x%08x\n", + ucode_new_rev); + + eax = cpuid_eax(0x00000001); + eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); + + ret = load_microcode_amd(smp_processor_id(), eax, container, container_size); + if (ret != UCODE_OK) + retval = -EINVAL; + + /* + * This will be freed any msec now, stash patches for the current + * family and switch to patch cache for cpu hotplug, etc later. + */ + container = NULL; + container_size = 0; + + return retval; +} + +void reload_ucode_amd(void) +{ + struct microcode_amd *mc; + u32 rev; + + /* + * early==false because this is a syscore ->resume path and by + * that time paging is long enabled. + */ + if (check_current_patch_level(&rev, false)) + return; + + mc = (struct microcode_amd *)amd_ucode_patch; + + if (mc && rev < mc->hdr.patch_id) { + if (!__apply_microcode_amd(mc)) { + ucode_new_rev = mc->hdr.patch_id; + pr_info("microcode: reload patch_level=0x%08x\n", + ucode_new_rev); + } + } +} static u16 __find_equiv_id(unsigned int cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; @@ -177,6 +604,53 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size, return patch_size; } +/* + * Those patch levels cannot be updated to newer ones and thus should be final. + */ +static u32 final_levels[] = { + 0x01000098, + 0x0100009f, + 0x010000af, + 0, /* T-101 terminator */ +}; + +/* + * Check the current patch level on this CPU. + * + * @rev: Use it to return the patch level. It is set to 0 in the case of + * error. + * + * Returns: + * - true: if update should stop + * - false: otherwise + */ +bool check_current_patch_level(u32 *rev, bool early) +{ + u32 lvl, dummy, i; + bool ret = false; + u32 *levels; + + native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy); + + if (IS_ENABLED(CONFIG_X86_32) && early) + levels = (u32 *)__pa_nodebug(&final_levels); + else + levels = final_levels; + + for (i = 0; levels[i]; i++) { + if (lvl == levels[i]) { + lvl = 0; + ret = true; + break; + } + } + + if (rev) + *rev = lvl; + + return ret; +} + int __apply_microcode_amd(struct microcode_amd *mc_amd) { u32 rev, dummy; @@ -197,7 +671,7 @@ int apply_microcode_amd(int cpu) struct microcode_amd *mc_amd; struct ucode_cpu_info *uci; struct ucode_patch *p; - u32 rev, dummy; + u32 rev; BUG_ON(raw_smp_processor_id() != cpu); @@ -210,7 +684,8 @@ int apply_microcode_amd(int cpu) mc_amd = p->data; uci->mc = p->data; - rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); + if (check_current_patch_level(&rev, false)) + return -1; /* need to apply patch? */ if (rev >= mc_amd->hdr.patch_id) { @@ -387,7 +862,7 @@ enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t s if (ret != UCODE_OK) cleanup(); -#if defined(CONFIG_MICROCODE_AMD_EARLY) && defined(CONFIG_X86_32) +#ifdef CONFIG_X86_32 /* save BSP's matching patch for early load */ if (cpu_data(cpu).cpu_index == boot_cpu_data.cpu_index) { struct ucode_patch *p = find_patch(cpu); @@ -475,7 +950,7 @@ static struct microcode_ops microcode_amd_ops = { struct microcode_ops * __init init_amd_microcode(void) { - struct cpuinfo_x86 *c = &cpu_data(0); + struct cpuinfo_x86 *c = &boot_cpu_data; if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) { pr_warning("AMD CPU family 0x%x not supported\n", c->x86); diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c deleted file mode 100644 index e8a215a9a345..000000000000 --- a/arch/x86/kernel/cpu/microcode/amd_early.c +++ /dev/null @@ -1,440 +0,0 @@ -/* - * Copyright (C) 2013 Advanced Micro Devices, Inc. - * - * Author: Jacob Shin <jacob.shin@amd.com> - * Fixes: Borislav Petkov <bp@suse.de> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/earlycpio.h> -#include <linux/initrd.h> - -#include <asm/cpu.h> -#include <asm/setup.h> -#include <asm/microcode_amd.h> - -/* - * This points to the current valid container of microcode patches which we will - * save from the initrd before jettisoning its contents. - */ -static u8 *container; -static size_t container_size; - -static u32 ucode_new_rev; -u8 amd_ucode_patch[PATCH_MAX_SIZE]; -static u16 this_equiv_id; - -static struct cpio_data ucode_cpio; - -/* - * Microcode patch container file is prepended to the initrd in cpio format. - * See Documentation/x86/early-microcode.txt - */ -static __initdata char ucode_path[] = "kernel/x86/microcode/AuthenticAMD.bin"; - -static struct cpio_data __init find_ucode_in_initrd(void) -{ - long offset = 0; - char *path; - void *start; - size_t size; - -#ifdef CONFIG_X86_32 - struct boot_params *p; - - /* - * On 32-bit, early load occurs before paging is turned on so we need - * to use physical addresses. - */ - p = (struct boot_params *)__pa_nodebug(&boot_params); - path = (char *)__pa_nodebug(ucode_path); - start = (void *)p->hdr.ramdisk_image; - size = p->hdr.ramdisk_size; -#else - path = ucode_path; - start = (void *)(boot_params.hdr.ramdisk_image + PAGE_OFFSET); - size = boot_params.hdr.ramdisk_size; -#endif - - return find_cpio_data(path, start, size, &offset); -} - -static size_t compute_container_size(u8 *data, u32 total_size) -{ - size_t size = 0; - u32 *header = (u32 *)data; - - if (header[0] != UCODE_MAGIC || - header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */ - header[2] == 0) /* size */ - return size; - - size = header[2] + CONTAINER_HDR_SZ; - total_size -= size; - data += size; - - while (total_size) { - u16 patch_size; - - header = (u32 *)data; - - if (header[0] != UCODE_UCODE_TYPE) - break; - - /* - * Sanity-check patch size. - */ - patch_size = header[1]; - if (patch_size > PATCH_MAX_SIZE) - break; - - size += patch_size + SECTION_HDR_SIZE; - data += patch_size + SECTION_HDR_SIZE; - total_size -= patch_size + SECTION_HDR_SIZE; - } - - return size; -} - -/* - * Early load occurs before we can vmalloc(). So we look for the microcode - * patch container file in initrd, traverse equivalent cpu table, look for a - * matching microcode patch, and update, all in initrd memory in place. - * When vmalloc() is available for use later -- on 64-bit during first AP load, - * and on 32-bit during save_microcode_in_initrd_amd() -- we can call - * load_microcode_amd() to save equivalent cpu table and microcode patches in - * kernel heap memory. - */ -static void apply_ucode_in_initrd(void *ucode, size_t size, bool save_patch) -{ - struct equiv_cpu_entry *eq; - size_t *cont_sz; - u32 *header; - u8 *data, **cont; - u8 (*patch)[PATCH_MAX_SIZE]; - u16 eq_id = 0; - int offset, left; - u32 rev, eax, ebx, ecx, edx; - u32 *new_rev; - -#ifdef CONFIG_X86_32 - new_rev = (u32 *)__pa_nodebug(&ucode_new_rev); - cont_sz = (size_t *)__pa_nodebug(&container_size); - cont = (u8 **)__pa_nodebug(&container); - patch = (u8 (*)[PATCH_MAX_SIZE])__pa_nodebug(&amd_ucode_patch); -#else - new_rev = &ucode_new_rev; - cont_sz = &container_size; - cont = &container; - patch = &amd_ucode_patch; -#endif - - data = ucode; - left = size; - header = (u32 *)data; - - /* find equiv cpu table */ - if (header[0] != UCODE_MAGIC || - header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */ - header[2] == 0) /* size */ - return; - - eax = 0x00000001; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - - while (left > 0) { - eq = (struct equiv_cpu_entry *)(data + CONTAINER_HDR_SZ); - - *cont = data; - - /* Advance past the container header */ - offset = header[2] + CONTAINER_HDR_SZ; - data += offset; - left -= offset; - - eq_id = find_equiv_id(eq, eax); - if (eq_id) { - this_equiv_id = eq_id; - *cont_sz = compute_container_size(*cont, left + offset); - - /* - * truncate how much we need to iterate over in the - * ucode update loop below - */ - left = *cont_sz - offset; - break; - } - - /* - * support multiple container files appended together. if this - * one does not have a matching equivalent cpu entry, we fast - * forward to the next container file. - */ - while (left > 0) { - header = (u32 *)data; - if (header[0] == UCODE_MAGIC && - header[1] == UCODE_EQUIV_CPU_TABLE_TYPE) - break; - - offset = header[1] + SECTION_HDR_SIZE; - data += offset; - left -= offset; - } - - /* mark where the next microcode container file starts */ - offset = data - (u8 *)ucode; - ucode = data; - } - - if (!eq_id) { - *cont = NULL; - *cont_sz = 0; - return; - } - - /* find ucode and update if needed */ - - native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax); - - while (left > 0) { - struct microcode_amd *mc; - - header = (u32 *)data; - if (header[0] != UCODE_UCODE_TYPE || /* type */ - header[1] == 0) /* size */ - break; - - mc = (struct microcode_amd *)(data + SECTION_HDR_SIZE); - - if (eq_id == mc->hdr.processor_rev_id && rev < mc->hdr.patch_id) { - - if (!__apply_microcode_amd(mc)) { - rev = mc->hdr.patch_id; - *new_rev = rev; - - if (save_patch) - memcpy(patch, mc, - min_t(u32, header[1], PATCH_MAX_SIZE)); - } - } - - offset = header[1] + SECTION_HDR_SIZE; - data += offset; - left -= offset; - } -} - -static bool __init load_builtin_amd_microcode(struct cpio_data *cp, - unsigned int family) -{ -#ifdef CONFIG_X86_64 - char fw_name[36] = "amd-ucode/microcode_amd.bin"; - - if (family >= 0x15) - snprintf(fw_name, sizeof(fw_name), - "amd-ucode/microcode_amd_fam%.2xh.bin", 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; - size_t *size; - -#ifdef CONFIG_X86_32 - data = (void **)__pa_nodebug(&ucode_cpio.data); - size = (size_t *)__pa_nodebug(&ucode_cpio.size); -#else - data = &ucode_cpio.data; - size = &ucode_cpio.size; -#endif - - cp = find_ucode_in_initrd(); - if (!cp.data) { - if (!load_builtin_amd_microcode(&cp, family)) - return; - } - - *data = cp.data; - *size = cp.size; - - apply_ucode_in_initrd(cp.data, cp.size, true); -} - -#ifdef CONFIG_X86_32 -/* - * On 32-bit, since AP's early load occurs before paging is turned on, we - * cannot traverse cpu_equiv_table and pcache in kernel heap memory. So during - * cold boot, AP will apply_ucode_in_initrd() just like the BSP. During - * save_microcode_in_initrd_amd() BSP's patch is copied to amd_ucode_patch, - * which is used upon resume from suspend. - */ -void load_ucode_amd_ap(void) -{ - struct microcode_amd *mc; - size_t *usize; - void **ucode; - - mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch); - if (mc->hdr.patch_id && mc->hdr.processor_rev_id) { - __apply_microcode_amd(mc); - return; - } - - ucode = (void *)__pa_nodebug(&container); - usize = (size_t *)__pa_nodebug(&container_size); - - if (!*ucode || !*usize) - return; - - apply_ucode_in_initrd(*ucode, *usize, false); -} - -static void __init collect_cpu_sig_on_bsp(void *arg) -{ - unsigned int cpu = smp_processor_id(); - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - - uci->cpu_sig.sig = cpuid_eax(0x00000001); -} - -static void __init get_bsp_sig(void) -{ - unsigned int bsp = boot_cpu_data.cpu_index; - struct ucode_cpu_info *uci = ucode_cpu_info + bsp; - - if (!uci->cpu_sig.sig) - smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1); -} -#else -void load_ucode_amd_ap(void) -{ - unsigned int cpu = smp_processor_id(); - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - struct equiv_cpu_entry *eq; - struct microcode_amd *mc; - u32 rev, eax; - u16 eq_id; - - /* Exit if called on the BSP. */ - if (!cpu) - return; - - if (!container) - return; - - rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax); - - uci->cpu_sig.rev = rev; - uci->cpu_sig.sig = eax; - - eax = cpuid_eax(0x00000001); - eq = (struct equiv_cpu_entry *)(container + CONTAINER_HDR_SZ); - - eq_id = find_equiv_id(eq, eax); - if (!eq_id) - return; - - if (eq_id == this_equiv_id) { - mc = (struct microcode_amd *)amd_ucode_patch; - - if (mc && rev < mc->hdr.patch_id) { - if (!__apply_microcode_amd(mc)) - ucode_new_rev = mc->hdr.patch_id; - } - - } else { - if (!ucode_cpio.data) - return; - - /* - * AP has a different equivalence ID than BSP, looks like - * mixed-steppings silicon so go through the ucode blob anew. - */ - apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size, false); - } -} -#endif - -int __init save_microcode_in_initrd_amd(void) -{ - unsigned long cont; - int retval = 0; - enum ucode_state ret; - u8 *cont_va; - u32 eax; - - if (!container) - return -EINVAL; - -#ifdef CONFIG_X86_32 - get_bsp_sig(); - cont = (unsigned long)container; - cont_va = __va(container); -#else - /* - * We need the physical address of the container for both bitness since - * boot_params.hdr.ramdisk_image is a physical address. - */ - cont = __pa(container); - cont_va = container; -#endif - - /* - * Take into account the fact that the ramdisk might get relocated and - * therefore we need to recompute the container's position in virtual - * memory space. - */ - if (relocated_ramdisk) - container = (u8 *)(__va(relocated_ramdisk) + - (cont - boot_params.hdr.ramdisk_image)); - else - container = cont_va; - - if (ucode_new_rev) - pr_info("microcode: updated early to new patch_level=0x%08x\n", - ucode_new_rev); - - eax = cpuid_eax(0x00000001); - eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); - - ret = load_microcode_amd(smp_processor_id(), eax, container, container_size); - if (ret != UCODE_OK) - retval = -EINVAL; - - /* - * This will be freed any msec now, stash patches for the current - * family and switch to patch cache for cpu hotplug, etc later. - */ - container = NULL; - container_size = 0; - - return retval; -} - -void reload_ucode_amd(void) -{ - struct microcode_amd *mc; - u32 rev, eax; - - rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax); - - mc = (struct microcode_amd *)amd_ucode_patch; - - if (mc && rev < mc->hdr.patch_id) { - if (!__apply_microcode_amd(mc)) { - ucode_new_rev = mc->hdr.patch_id; - pr_info("microcode: reload patch_level=0x%08x\n", - ucode_new_rev); - } - } -} diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 6236a54a63f4..faec7120c508 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -5,6 +5,12 @@ * 2006 Shaohua Li <shaohua.li@intel.com> * 2013-2015 Borislav Petkov <bp@alien8.de> * + * X86 CPU microcode early update for Linux: + * + * 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 upgrade microcode on x86 processors. * * This program is free software; you can redistribute it and/or @@ -13,34 +19,39 @@ * 2 of the License, or (at your option) any later version. */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#define pr_fmt(fmt) "microcode: " fmt #include <linux/platform_device.h> +#include <linux/syscore_ops.h> #include <linux/miscdevice.h> #include <linux/capability.h> +#include <linux/firmware.h> #include <linux/kernel.h> -#include <linux/module.h> #include <linux/mutex.h> #include <linux/cpu.h> #include <linux/fs.h> #include <linux/mm.h> -#include <linux/syscore_ops.h> -#include <asm/microcode.h> -#include <asm/processor.h> +#include <asm/microcode_intel.h> #include <asm/cpu_device_id.h> +#include <asm/microcode_amd.h> #include <asm/perf_event.h> +#include <asm/microcode.h> +#include <asm/processor.h> +#include <asm/cmdline.h> -MODULE_DESCRIPTION("Microcode Update Driver"); -MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>"); -MODULE_LICENSE("GPL"); - -#define MICROCODE_VERSION "2.00" +#define MICROCODE_VERSION "2.01" static struct microcode_ops *microcode_ops; -bool dis_ucode_ldr; -module_param(dis_ucode_ldr, bool, 0); +static bool dis_ucode_ldr; + +static int __init disable_loader(char *str) +{ + dis_ucode_ldr = true; + return 1; +} +__setup("dis_ucode_ldr", disable_loader); /* * Synchronization. @@ -68,6 +79,150 @@ struct cpu_info_ctx { int err; }; +static bool __init check_loader_disabled_bsp(void) +{ +#ifdef CONFIG_X86_32 + const char *cmdline = (const char *)__pa_nodebug(boot_command_line); + const char *opt = "dis_ucode_ldr"; + const char *option = (const char *)__pa_nodebug(opt); + bool *res = (bool *)__pa_nodebug(&dis_ucode_ldr); + +#else /* CONFIG_X86_64 */ + const char *cmdline = boot_command_line; + const char *option = "dis_ucode_ldr"; + bool *res = &dis_ucode_ldr; +#endif + + if (cmdline_find_option_bool(cmdline, option)) + *res = true; + + 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; + unsigned int family; + + if (check_loader_disabled_bsp()) + return; + + if (!have_cpuid_p()) + return; + + vendor = x86_cpuid_vendor(); + family = x86_cpuid_family(); + + switch (vendor) { + case X86_VENDOR_INTEL: + if (family >= 6) + load_ucode_intel_bsp(); + break; + case X86_VENDOR_AMD: + if (family >= 0x10) + load_ucode_amd_bsp(family); + break; + default: + break; + } +} + +static bool check_loader_disabled_ap(void) +{ +#ifdef CONFIG_X86_32 + return *((bool *)__pa_nodebug(&dis_ucode_ldr)); +#else + return dis_ucode_ldr; +#endif +} + +void load_ucode_ap(void) +{ + int vendor, family; + + if (check_loader_disabled_ap()) + return; + + if (!have_cpuid_p()) + return; + + vendor = x86_cpuid_vendor(); + family = x86_cpuid_family(); + + switch (vendor) { + case X86_VENDOR_INTEL: + if (family >= 6) + load_ucode_intel_ap(); + break; + case X86_VENDOR_AMD: + if (family >= 0x10) + load_ucode_amd_ap(); + break; + default: + break; + } +} + +int __init save_microcode_in_initrd(void) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + + switch (c->x86_vendor) { + case X86_VENDOR_INTEL: + if (c->x86 >= 6) + save_microcode_in_initrd_intel(); + break; + case X86_VENDOR_AMD: + if (c->x86 >= 0x10) + save_microcode_in_initrd_amd(); + break; + default: + break; + } + + return 0; +} + +void reload_early_microcode(void) +{ + int vendor, family; + + vendor = x86_cpuid_vendor(); + family = x86_cpuid_family(); + + switch (vendor) { + case X86_VENDOR_INTEL: + if (family >= 6) + reload_ucode_intel(); + break; + case X86_VENDOR_AMD: + if (family >= 0x10) + reload_ucode_amd(); + break; + default: + break; + } +} + static void collect_cpu_info_local(void *arg) { struct cpu_info_ctx *ctx = arg; @@ -210,9 +365,6 @@ static void __exit microcode_dev_exit(void) { misc_deregister(µcode_dev); } - -MODULE_ALIAS_MISCDEV(MICROCODE_MINOR); -MODULE_ALIAS("devname:cpu/microcode"); #else #define microcode_dev_init() 0 #define microcode_dev_exit() do { } while (0) @@ -377,17 +529,16 @@ static int mc_device_add(struct device *dev, struct subsys_interface *sif) return err; } -static int mc_device_remove(struct device *dev, struct subsys_interface *sif) +static void mc_device_remove(struct device *dev, struct subsys_interface *sif) { int cpu = dev->id; if (!cpu_online(cpu)) - return 0; + return; pr_debug("CPU%d removed\n", cpu); microcode_fini_cpu(cpu); sysfs_remove_group(&dev->kobj, &mc_attr_group); - return 0; } static struct subsys_interface mc_cpu_interface = { @@ -460,24 +611,10 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) return NOTIFY_OK; } -static struct notifier_block __refdata mc_cpu_notifier = { +static struct notifier_block mc_cpu_notifier = { .notifier_call = mc_cpu_callback, }; -#ifdef MODULE -/* Autoload on Intel and AMD systems */ -static const struct x86_cpu_id __initconst microcode_id[] = { -#ifdef CONFIG_MICROCODE_INTEL - { X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, }, -#endif -#ifdef CONFIG_MICROCODE_AMD - { X86_VENDOR_AMD, X86_FAMILY_ANY, X86_MODEL_ANY, }, -#endif - {} -}; -MODULE_DEVICE_TABLE(x86cpu, microcode_id); -#endif - static struct attribute *cpu_root_microcode_attrs[] = { &dev_attr_reload.attr, NULL @@ -488,9 +625,9 @@ static struct attribute_group cpu_root_microcode_group = { .attrs = cpu_root_microcode_attrs, }; -static int __init microcode_init(void) +int __init microcode_init(void) { - struct cpuinfo_x86 *c = &cpu_data(0); + struct cpuinfo_x86 *c = &boot_cpu_data; int error; if (paravirt_enabled() || dis_ucode_ldr) @@ -561,35 +698,4 @@ static int __init microcode_init(void) return error; } -module_init(microcode_init); - -static void __exit microcode_exit(void) -{ - struct cpuinfo_x86 *c = &cpu_data(0); - - microcode_dev_exit(); - - unregister_hotcpu_notifier(&mc_cpu_notifier); - unregister_syscore_ops(&mc_syscore_ops); - - sysfs_remove_group(&cpu_subsys.dev_root->kobj, - &cpu_root_microcode_group); - - get_online_cpus(); - mutex_lock(µcode_mutex); - - subsys_interface_unregister(&mc_cpu_interface); - - mutex_unlock(µcode_mutex); - put_online_cpus(); - - platform_device_unregister(microcode_pdev); - - microcode_ops = NULL; - - if (c->x86_vendor == X86_VENDOR_AMD) - exit_amd_microcode(); - - pr_info("Microcode Update Driver: v" MICROCODE_VERSION " removed.\n"); -} -module_exit(microcode_exit); +late_initcall(microcode_init); diff --git a/arch/x86/kernel/cpu/microcode/core_early.c b/arch/x86/kernel/cpu/microcode/core_early.c deleted file mode 100644 index 8ebc421d6299..000000000000 --- a/arch/x86/kernel/cpu/microcode/core_early.c +++ /dev/null @@ -1,170 +0,0 @@ -/* - * X86 CPU microcode early update for Linux - * - * 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, - * Pentium III, Xeon, Pentium 4, etc. - * - * Reference: Section 9.11 of Volume 3, IA-32 Intel Architecture - * Software Developer's Manual. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ -#include <linux/module.h> -#include <linux/firmware.h> -#include <asm/microcode.h> -#include <asm/microcode_intel.h> -#include <asm/microcode_amd.h> -#include <asm/processor.h> -#include <asm/cmdline.h> - -static bool __init check_loader_disabled_bsp(void) -{ -#ifdef CONFIG_X86_32 - const char *cmdline = (const char *)__pa_nodebug(boot_command_line); - const char *opt = "dis_ucode_ldr"; - const char *option = (const char *)__pa_nodebug(opt); - bool *res = (bool *)__pa_nodebug(&dis_ucode_ldr); - -#else /* CONFIG_X86_64 */ - const char *cmdline = boot_command_line; - const char *option = "dis_ucode_ldr"; - bool *res = &dis_ucode_ldr; -#endif - - if (cmdline_find_option_bool(cmdline, option)) - *res = true; - - 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; - unsigned int family; - - if (check_loader_disabled_bsp()) - return; - - if (!have_cpuid_p()) - return; - - vendor = x86_vendor(); - family = x86_family(); - - switch (vendor) { - case X86_VENDOR_INTEL: - if (family >= 6) - load_ucode_intel_bsp(); - break; - case X86_VENDOR_AMD: - if (family >= 0x10) - load_ucode_amd_bsp(family); - break; - default: - break; - } -} - -static bool check_loader_disabled_ap(void) -{ -#ifdef CONFIG_X86_32 - return *((bool *)__pa_nodebug(&dis_ucode_ldr)); -#else - return dis_ucode_ldr; -#endif -} - -void load_ucode_ap(void) -{ - int vendor, family; - - if (check_loader_disabled_ap()) - return; - - if (!have_cpuid_p()) - return; - - vendor = x86_vendor(); - family = x86_family(); - - switch (vendor) { - case X86_VENDOR_INTEL: - if (family >= 6) - load_ucode_intel_ap(); - break; - case X86_VENDOR_AMD: - if (family >= 0x10) - load_ucode_amd_ap(); - break; - default: - break; - } -} - -int __init save_microcode_in_initrd(void) -{ - struct cpuinfo_x86 *c = &boot_cpu_data; - - switch (c->x86_vendor) { - case X86_VENDOR_INTEL: - if (c->x86 >= 6) - save_microcode_in_initrd_intel(); - break; - case X86_VENDOR_AMD: - if (c->x86 >= 0x10) - save_microcode_in_initrd_amd(); - break; - default: - break; - } - - return 0; -} - -void reload_early_microcode(void) -{ - int vendor, family; - - vendor = x86_vendor(); - family = x86_family(); - - switch (vendor) { - case X86_VENDOR_INTEL: - if (family >= 6) - reload_ucode_intel(); - break; - case X86_VENDOR_AMD: - if (family >= 0x10) - reload_ucode_amd(); - break; - default: - break; - } -} diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 969dc17eb1b4..ee81c544ee0d 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -4,27 +4,800 @@ * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk> * 2006 Shaohua Li <shaohua.li@intel.com> * + * Intel CPU microcode early update for Linux + * + * Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com> + * H Peter Anvin" <hpa@zytor.com> + * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +/* + * This needs to be before all headers so that pr_debug in printk.h doesn't turn + * printk calls into no_printk(). + * + *#define DEBUG + */ +#define pr_fmt(fmt) "microcode: " fmt +#include <linux/earlycpio.h> #include <linux/firmware.h> #include <linux/uaccess.h> -#include <linux/kernel.h> -#include <linux/module.h> #include <linux/vmalloc.h> +#include <linux/initrd.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/cpu.h> +#include <linux/mm.h> #include <asm/microcode_intel.h> #include <asm/processor.h> +#include <asm/tlbflush.h> +#include <asm/setup.h> #include <asm/msr.h> -MODULE_DESCRIPTION("Microcode Update Driver"); -MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>"); -MODULE_LICENSE("GPL"); +static unsigned long mc_saved_in_initrd[MAX_UCODE_COUNT]; +static struct mc_saved_data { + unsigned int mc_saved_count; + struct microcode_intel **mc_saved; +} mc_saved_data; + +static enum ucode_state +load_microcode_early(struct microcode_intel **saved, + unsigned int num_saved, struct ucode_cpu_info *uci) +{ + struct microcode_intel *ucode_ptr, *new_mc = NULL; + struct microcode_header_intel *mc_hdr; + int new_rev, ret, i; + + new_rev = uci->cpu_sig.rev; + + for (i = 0; i < num_saved; i++) { + ucode_ptr = saved[i]; + mc_hdr = (struct microcode_header_intel *)ucode_ptr; + + ret = has_newer_microcode(ucode_ptr, + uci->cpu_sig.sig, + uci->cpu_sig.pf, + new_rev); + if (!ret) + continue; + + new_rev = mc_hdr->rev; + new_mc = ucode_ptr; + } + + if (!new_mc) + return UCODE_NFOUND; + + uci->mc = (struct microcode_intel *)new_mc; + return UCODE_OK; +} + +static inline void +copy_initrd_ptrs(struct microcode_intel **mc_saved, unsigned long *initrd, + unsigned long off, int num_saved) +{ + int i; + + for (i = 0; i < num_saved; i++) + mc_saved[i] = (struct microcode_intel *)(initrd[i] + off); +} + +#ifdef CONFIG_X86_32 +static void +microcode_phys(struct microcode_intel **mc_saved_tmp, + struct mc_saved_data *mc_saved_data) +{ + int i; + struct microcode_intel ***mc_saved; + + mc_saved = (struct microcode_intel ***) + __pa_nodebug(&mc_saved_data->mc_saved); + for (i = 0; i < mc_saved_data->mc_saved_count; i++) { + struct microcode_intel *p; + + p = *(struct microcode_intel **) + __pa_nodebug(mc_saved_data->mc_saved + i); + mc_saved_tmp[i] = (struct microcode_intel *)__pa_nodebug(p); + } +} +#endif + +static enum ucode_state +load_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd, + unsigned long initrd_start, struct ucode_cpu_info *uci) +{ + struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT]; + unsigned int count = mc_saved_data->mc_saved_count; + + if (!mc_saved_data->mc_saved) { + copy_initrd_ptrs(mc_saved_tmp, initrd, initrd_start, count); + + return load_microcode_early(mc_saved_tmp, count, uci); + } else { +#ifdef CONFIG_X86_32 + microcode_phys(mc_saved_tmp, mc_saved_data); + return load_microcode_early(mc_saved_tmp, count, uci); +#else + return load_microcode_early(mc_saved_data->mc_saved, + count, uci); +#endif + } +} + +/* + * Given CPU signature and a microcode patch, this function finds if the + * microcode patch has matching family and model with the CPU. + */ +static enum ucode_state +matching_model_microcode(struct microcode_header_intel *mc_header, + unsigned long sig) +{ + unsigned int fam, model; + unsigned int fam_ucode, model_ucode; + struct extended_sigtable *ext_header; + unsigned long total_size = get_totalsize(mc_header); + unsigned long data_size = get_datasize(mc_header); + int ext_sigcount, i; + struct extended_signature *ext_sig; + + fam = x86_family(sig); + model = x86_model(sig); + + fam_ucode = x86_family(mc_header->sig); + model_ucode = x86_model(mc_header->sig); + + if (fam == fam_ucode && model == model_ucode) + return UCODE_OK; + + /* Look for ext. headers: */ + if (total_size <= data_size + MC_HEADER_SIZE) + return UCODE_NFOUND; + + ext_header = (void *) mc_header + data_size + MC_HEADER_SIZE; + ext_sig = (void *)ext_header + EXT_HEADER_SIZE; + ext_sigcount = ext_header->count; + + for (i = 0; i < ext_sigcount; i++) { + fam_ucode = x86_family(ext_sig->sig); + model_ucode = x86_model(ext_sig->sig); + + if (fam == fam_ucode && model == model_ucode) + return UCODE_OK; + + ext_sig++; + } + return UCODE_NFOUND; +} + +static int +save_microcode(struct mc_saved_data *mc_saved_data, + struct microcode_intel **mc_saved_src, + unsigned int mc_saved_count) +{ + int i, j; + struct microcode_intel **saved_ptr; + int ret; + + if (!mc_saved_count) + return -EINVAL; + + /* + * Copy new microcode data. + */ + saved_ptr = kcalloc(mc_saved_count, sizeof(struct microcode_intel *), GFP_KERNEL); + if (!saved_ptr) + return -ENOMEM; + + for (i = 0; i < mc_saved_count; i++) { + struct microcode_header_intel *mc_hdr; + struct microcode_intel *mc; + unsigned long size; + + if (!mc_saved_src[i]) { + ret = -EINVAL; + goto err; + } + + mc = mc_saved_src[i]; + mc_hdr = &mc->hdr; + size = get_totalsize(mc_hdr); + + saved_ptr[i] = kmalloc(size, GFP_KERNEL); + if (!saved_ptr[i]) { + ret = -ENOMEM; + goto err; + } + + memcpy(saved_ptr[i], mc, size); + } + + /* + * Point to newly saved microcode. + */ + mc_saved_data->mc_saved = saved_ptr; + mc_saved_data->mc_saved_count = mc_saved_count; + + return 0; + +err: + for (j = 0; j <= i; j++) + kfree(saved_ptr[j]); + kfree(saved_ptr); + + return ret; +} + +/* + * A microcode patch in ucode_ptr is saved into mc_saved + * - if it has matching signature and newer revision compared to an existing + * patch mc_saved. + * - or if it is a newly discovered microcode patch. + * + * The microcode patch should have matching model with CPU. + * + * Returns: The updated number @num_saved of saved microcode patches. + */ +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; + int found = 0, i; + + mc_hdr = (struct microcode_header_intel *)ucode_ptr; + + for (i = 0; i < num_saved; i++) { + mc_saved_hdr = (struct microcode_header_intel *)mc_saved[i]; + sig = mc_saved_hdr->sig; + pf = mc_saved_hdr->pf; + + if (!find_matching_signature(ucode_ptr, sig, pf)) + continue; + + found = 1; + + if (mc_hdr->rev <= mc_saved_hdr->rev) + continue; + + /* + * Found an older ucode saved earlier. Replace it with + * this newer one. + */ + mc_saved[i] = (struct microcode_intel *)ucode_ptr; + break; + } + + /* Newly detected microcode, save it to memory. */ + if (i >= num_saved && !found) + mc_saved[num_saved++] = (struct microcode_intel *)ucode_ptr; + + return num_saved; +} + +/* + * Get microcode matching with BSP's model. Only CPUs with the same model as + * BSP can stay in the platform. + */ +static enum ucode_state __init +get_matching_model_microcode(int cpu, unsigned long start, + void *data, size_t size, + struct mc_saved_data *mc_saved_data, + unsigned long *mc_saved_in_initrd, + struct ucode_cpu_info *uci) +{ + u8 *ucode_ptr = data; + unsigned int leftover = size; + enum ucode_state state = UCODE_OK; + unsigned int mc_size; + struct microcode_header_intel *mc_header; + struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT]; + unsigned int mc_saved_count = mc_saved_data->mc_saved_count; + int i; + + while (leftover && mc_saved_count < ARRAY_SIZE(mc_saved_tmp)) { + + if (leftover < sizeof(mc_header)) + break; + + mc_header = (struct microcode_header_intel *)ucode_ptr; + + mc_size = get_totalsize(mc_header); + if (!mc_size || mc_size > leftover || + microcode_sanity_check(ucode_ptr, 0) < 0) + break; + + leftover -= mc_size; + + /* + * Since APs with same family and model as the BSP may boot in + * the platform, we need to find and save microcode patches + * with the same family and model as the BSP. + */ + if (matching_model_microcode(mc_header, uci->cpu_sig.sig) != + UCODE_OK) { + ucode_ptr += mc_size; + continue; + } + + mc_saved_count = _save_mc(mc_saved_tmp, ucode_ptr, mc_saved_count); + + ucode_ptr += mc_size; + } + + if (leftover) { + state = UCODE_ERROR; + goto out; + } + + if (mc_saved_count == 0) { + state = UCODE_NFOUND; + goto out; + } + + for (i = 0; i < mc_saved_count; i++) + mc_saved_in_initrd[i] = (unsigned long)mc_saved_tmp[i] - start; + + mc_saved_data->mc_saved_count = mc_saved_count; +out: + return state; +} + +static int collect_cpu_info_early(struct ucode_cpu_info *uci) +{ + unsigned int val[2]; + unsigned int family, model; + struct cpu_signature csig; + unsigned int eax, ebx, ecx, edx; + + csig.sig = 0; + csig.pf = 0; + csig.rev = 0; + + memset(uci, 0, sizeof(*uci)); + + eax = 0x00000001; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + csig.sig = eax; + + family = x86_family(csig.sig); + model = x86_model(csig.sig); + + if ((model >= 5) || (family > 6)) { + /* get processor flags from MSR 0x17 */ + native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]); + csig.pf = 1 << ((val[1] >> 18) & 7); + } + native_wrmsr(MSR_IA32_UCODE_REV, 0, 0); + + /* As documented in the SDM: Do a CPUID 1 here */ + sync_core(); + + /* get the current revision from MSR 0x8B */ + native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); + + csig.rev = val[1]; + + uci->cpu_sig = csig; + uci->valid = 1; + + return 0; +} + +static void show_saved_mc(void) +{ +#ifdef DEBUG + int i, j; + unsigned int sig, pf, rev, total_size, data_size, date; + struct ucode_cpu_info uci; + + if (mc_saved_data.mc_saved_count == 0) { + pr_debug("no microcode data saved.\n"); + return; + } + pr_debug("Total microcode saved: %d\n", mc_saved_data.mc_saved_count); + + collect_cpu_info_early(&uci); + + sig = uci.cpu_sig.sig; + pf = uci.cpu_sig.pf; + rev = uci.cpu_sig.rev; + pr_debug("CPU: sig=0x%x, pf=0x%x, rev=0x%x\n", sig, pf, rev); + + for (i = 0; i < mc_saved_data.mc_saved_count; i++) { + struct microcode_header_intel *mc_saved_header; + struct extended_sigtable *ext_header; + int ext_sigcount; + struct extended_signature *ext_sig; + + mc_saved_header = (struct microcode_header_intel *) + mc_saved_data.mc_saved[i]; + sig = mc_saved_header->sig; + pf = mc_saved_header->pf; + rev = mc_saved_header->rev; + total_size = get_totalsize(mc_saved_header); + data_size = get_datasize(mc_saved_header); + date = mc_saved_header->date; + + pr_debug("mc_saved[%d]: sig=0x%x, pf=0x%x, rev=0x%x, toal size=0x%x, date = %04x-%02x-%02x\n", + i, sig, pf, rev, total_size, + date & 0xffff, + date >> 24, + (date >> 16) & 0xff); + + /* Look for ext. headers: */ + if (total_size <= data_size + MC_HEADER_SIZE) + continue; + + ext_header = (void *) mc_saved_header + data_size + MC_HEADER_SIZE; + ext_sigcount = ext_header->count; + ext_sig = (void *)ext_header + EXT_HEADER_SIZE; + + for (j = 0; j < ext_sigcount; j++) { + sig = ext_sig->sig; + pf = ext_sig->pf; + + pr_debug("\tExtended[%d]: sig=0x%x, pf=0x%x\n", + j, sig, pf); + + ext_sig++; + } + + } +#endif +} + +#ifdef CONFIG_HOTPLUG_CPU +static DEFINE_MUTEX(x86_cpu_microcode_mutex); +/* + * Save this mc into mc_saved_data. So it will be loaded early when a CPU is + * hot added or resumes. + * + * Please make sure this mc should be a valid microcode patch before calling + * this function. + */ +int save_mc_for_early(u8 *mc) +{ + struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT]; + unsigned int mc_saved_count_init; + unsigned int mc_saved_count; + struct microcode_intel **mc_saved; + int ret = 0; + int i; + + /* + * Hold hotplug lock so mc_saved_data is not accessed by a CPU in + * hotplug. + */ + mutex_lock(&x86_cpu_microcode_mutex); + + mc_saved_count_init = mc_saved_data.mc_saved_count; + mc_saved_count = mc_saved_data.mc_saved_count; + mc_saved = mc_saved_data.mc_saved; + + if (mc_saved && mc_saved_count) + memcpy(mc_saved_tmp, mc_saved, + mc_saved_count * sizeof(struct microcode_intel *)); + /* + * Save the microcode patch mc in mc_save_tmp structure if it's a newer + * version. + */ + mc_saved_count = _save_mc(mc_saved_tmp, mc, mc_saved_count); + + /* + * Save the mc_save_tmp in global mc_saved_data. + */ + ret = save_microcode(&mc_saved_data, mc_saved_tmp, mc_saved_count); + if (ret) { + pr_err("Cannot save microcode patch.\n"); + goto out; + } + + show_saved_mc(); + + /* + * Free old saved microcode data. + */ + if (mc_saved) { + for (i = 0; i < mc_saved_count_init; i++) + kfree(mc_saved[i]); + kfree(mc_saved); + } + +out: + mutex_unlock(&x86_cpu_microcode_mutex); + + return ret; +} +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; + char name[30]; + + native_cpuid(&eax, &ebx, &ecx, &edx); + + sprintf(name, "intel-ucode/%02x-%02x-%02x", + x86_family(eax), x86_model(eax), x86_stepping(eax)); + + return get_builtin_firmware(cp, name); +#else + return false; +#endif +} + +static __initdata char ucode_name[] = "kernel/x86/microcode/GenuineIntel.bin"; +static __init enum ucode_state +scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd, + unsigned long start, unsigned long size, + struct ucode_cpu_info *uci) +{ + struct cpio_data cd; + long offset = 0; +#ifdef CONFIG_X86_32 + char *p = (char *)__pa_nodebug(ucode_name); +#else + char *p = ucode_name; +#endif + + cd.data = NULL; + cd.size = 0; + + cd = find_cpio_data(p, (void *)start, size, &offset); + 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); +} + +/* + * Print ucode update info. + */ +static void +print_ucode_info(struct ucode_cpu_info *uci, unsigned int date) +{ + int cpu = smp_processor_id(); + + pr_info("CPU%d microcode updated early to revision 0x%x, date = %04x-%02x-%02x\n", + cpu, + uci->cpu_sig.rev, + date & 0xffff, + date >> 24, + (date >> 16) & 0xff); +} + +#ifdef CONFIG_X86_32 + +static int delay_ucode_info; +static int current_mc_date; + +/* + * Print early updated ucode info after printk works. This is delayed info dump. + */ +void show_ucode_info_early(void) +{ + struct ucode_cpu_info uci; + + if (delay_ucode_info) { + collect_cpu_info_early(&uci); + print_ucode_info(&uci, current_mc_date); + delay_ucode_info = 0; + } +} + +/* + * At this point, we can not call printk() yet. Keep microcode patch number in + * mc_saved_data.mc_saved and delay printing microcode info in + * show_ucode_info_early() until printk() works. + */ +static void print_ucode(struct ucode_cpu_info *uci) +{ + struct microcode_intel *mc_intel; + int *delay_ucode_info_p; + int *current_mc_date_p; + + mc_intel = uci->mc; + if (mc_intel == NULL) + return; + + delay_ucode_info_p = (int *)__pa_nodebug(&delay_ucode_info); + current_mc_date_p = (int *)__pa_nodebug(¤t_mc_date); + + *delay_ucode_info_p = 1; + *current_mc_date_p = mc_intel->hdr.date; +} +#else + +/* + * Flush global tlb. We only do this in x86_64 where paging has been enabled + * already and PGE should be enabled as well. + */ +static inline void flush_tlb_early(void) +{ + __native_flush_tlb_global_irq_disabled(); +} + +static inline void print_ucode(struct ucode_cpu_info *uci) +{ + struct microcode_intel *mc_intel; + + mc_intel = uci->mc; + if (mc_intel == NULL) + return; + + print_ucode_info(uci, mc_intel->hdr.date); +} +#endif + +static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) +{ + struct microcode_intel *mc_intel; + unsigned int val[2]; + + mc_intel = uci->mc; + if (mc_intel == NULL) + return 0; + + /* write microcode via MSR 0x79 */ + native_wrmsr(MSR_IA32_UCODE_WRITE, + (unsigned long) mc_intel->bits, + (unsigned long) mc_intel->bits >> 16 >> 16); + native_wrmsr(MSR_IA32_UCODE_REV, 0, 0); + + /* As documented in the SDM: Do a CPUID 1 here */ + sync_core(); + + /* get the current revision from MSR 0x8B */ + native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); + if (val[1] != mc_intel->hdr.rev) + return -1; + +#ifdef CONFIG_X86_64 + /* Flush global tlb. This is precaution. */ + flush_tlb_early(); +#endif + uci->cpu_sig.rev = val[1]; + + if (early) + print_ucode(uci); + else + print_ucode_info(uci, mc_intel->hdr.date); + + return 0; +} + +/* + * This function converts microcode patch offsets previously stored in + * mc_saved_in_initrd to pointers and stores the pointers in mc_saved_data. + */ +int __init save_microcode_in_initrd_intel(void) +{ + unsigned int count = mc_saved_data.mc_saved_count; + struct microcode_intel *mc_saved[MAX_UCODE_COUNT]; + int ret = 0; + + if (count == 0) + return ret; + + copy_initrd_ptrs(mc_saved, mc_saved_in_initrd, initrd_start, count); + ret = save_microcode(&mc_saved_data, mc_saved, count); + if (ret) + pr_err("Cannot save microcode patches from initrd.\n"); + + show_saved_mc(); + + return ret; +} + +static void __init +_load_ucode_intel_bsp(struct mc_saved_data *mc_saved_data, + unsigned long *initrd, + unsigned long start, unsigned long size) +{ + struct ucode_cpu_info uci; + enum ucode_state ret; + + collect_cpu_info_early(&uci); + + ret = scan_microcode(mc_saved_data, initrd, start, size, &uci); + if (ret != UCODE_OK) + return; + + ret = load_microcode(mc_saved_data, initrd, start, &uci); + if (ret != UCODE_OK) + return; + + apply_microcode_early(&uci, true); +} + +void __init load_ucode_intel_bsp(void) +{ + u64 start, size; +#ifdef CONFIG_X86_32 + struct boot_params *p; + + p = (struct boot_params *)__pa_nodebug(&boot_params); + start = p->hdr.ramdisk_image; + size = p->hdr.ramdisk_size; + + _load_ucode_intel_bsp( + (struct mc_saved_data *)__pa_nodebug(&mc_saved_data), + (unsigned long *)__pa_nodebug(&mc_saved_in_initrd), + start, size); +#else + start = boot_params.hdr.ramdisk_image + PAGE_OFFSET; + size = boot_params.hdr.ramdisk_size; + + _load_ucode_intel_bsp(&mc_saved_data, mc_saved_in_initrd, start, size); +#endif +} + +void load_ucode_intel_ap(void) +{ + struct mc_saved_data *mc_saved_data_p; + struct ucode_cpu_info uci; + unsigned long *mc_saved_in_initrd_p; + unsigned long initrd_start_addr; + enum ucode_state ret; +#ifdef CONFIG_X86_32 + unsigned long *initrd_start_p; + + mc_saved_in_initrd_p = + (unsigned long *)__pa_nodebug(mc_saved_in_initrd); + mc_saved_data_p = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data); + initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start); + initrd_start_addr = (unsigned long)__pa_nodebug(*initrd_start_p); +#else + mc_saved_data_p = &mc_saved_data; + mc_saved_in_initrd_p = mc_saved_in_initrd; + initrd_start_addr = initrd_start; +#endif + + /* + * If there is no valid ucode previously saved in memory, no need to + * update ucode on this AP. + */ + if (mc_saved_data_p->mc_saved_count == 0) + return; + + collect_cpu_info_early(&uci); + ret = load_microcode(mc_saved_data_p, mc_saved_in_initrd_p, + initrd_start_addr, &uci); + + if (ret != UCODE_OK) + return; + + apply_microcode_early(&uci, true); +} + +void reload_ucode_intel(void) +{ + struct ucode_cpu_info uci; + enum ucode_state ret; + + if (!mc_saved_data.mc_saved_count) + return; + + collect_cpu_info_early(&uci); + + ret = load_microcode_early(mc_saved_data.mc_saved, + mc_saved_data.mc_saved_count, &uci); + if (ret != UCODE_OK) + return; + + apply_microcode_early(&uci, false); +} static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) { @@ -264,7 +1037,7 @@ static struct microcode_ops microcode_intel_ops = { struct microcode_ops * __init init_intel_microcode(void) { - struct cpuinfo_x86 *c = &cpu_data(0); + struct cpuinfo_x86 *c = &boot_cpu_data; if (c->x86_vendor != X86_VENDOR_INTEL || c->x86 < 6 || cpu_has(c, X86_FEATURE_IA64)) { diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c deleted file mode 100644 index 8187b7247d1c..000000000000 --- a/arch/x86/kernel/cpu/microcode/intel_early.c +++ /dev/null @@ -1,808 +0,0 @@ -/* - * Intel CPU microcode early update for Linux - * - * Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com> - * H Peter Anvin" <hpa@zytor.com> - * - * This allows to early upgrade microcode on Intel processors - * belonging to IA-32 family - PentiumPro, Pentium II, - * Pentium III, Xeon, Pentium 4, etc. - * - * Reference: Section 9.11 of Volume 3, IA-32 Intel Architecture - * Software Developer's Manual. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -/* - * This needs to be before all headers so that pr_debug in printk.h doesn't turn - * printk calls into no_printk(). - * - *#define DEBUG - */ - -#include <linux/module.h> -#include <linux/mm.h> -#include <linux/slab.h> -#include <linux/earlycpio.h> -#include <linux/initrd.h> -#include <linux/cpu.h> -#include <asm/msr.h> -#include <asm/microcode_intel.h> -#include <asm/processor.h> -#include <asm/tlbflush.h> -#include <asm/setup.h> - -#undef pr_fmt -#define pr_fmt(fmt) "microcode: " fmt - -static unsigned long mc_saved_in_initrd[MAX_UCODE_COUNT]; -static struct mc_saved_data { - unsigned int mc_saved_count; - struct microcode_intel **mc_saved; -} mc_saved_data; - -static enum ucode_state -load_microcode_early(struct microcode_intel **saved, - unsigned int num_saved, struct ucode_cpu_info *uci) -{ - struct microcode_intel *ucode_ptr, *new_mc = NULL; - struct microcode_header_intel *mc_hdr; - int new_rev, ret, i; - - new_rev = uci->cpu_sig.rev; - - for (i = 0; i < num_saved; i++) { - ucode_ptr = saved[i]; - mc_hdr = (struct microcode_header_intel *)ucode_ptr; - - ret = has_newer_microcode(ucode_ptr, - uci->cpu_sig.sig, - uci->cpu_sig.pf, - new_rev); - if (!ret) - continue; - - new_rev = mc_hdr->rev; - new_mc = ucode_ptr; - } - - if (!new_mc) - return UCODE_NFOUND; - - uci->mc = (struct microcode_intel *)new_mc; - return UCODE_OK; -} - -static inline void -copy_initrd_ptrs(struct microcode_intel **mc_saved, unsigned long *initrd, - unsigned long off, int num_saved) -{ - int i; - - for (i = 0; i < num_saved; i++) - mc_saved[i] = (struct microcode_intel *)(initrd[i] + off); -} - -#ifdef CONFIG_X86_32 -static void -microcode_phys(struct microcode_intel **mc_saved_tmp, - struct mc_saved_data *mc_saved_data) -{ - int i; - struct microcode_intel ***mc_saved; - - mc_saved = (struct microcode_intel ***) - __pa_nodebug(&mc_saved_data->mc_saved); - for (i = 0; i < mc_saved_data->mc_saved_count; i++) { - struct microcode_intel *p; - - p = *(struct microcode_intel **) - __pa_nodebug(mc_saved_data->mc_saved + i); - mc_saved_tmp[i] = (struct microcode_intel *)__pa_nodebug(p); - } -} -#endif - -static enum ucode_state -load_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd, - unsigned long initrd_start, struct ucode_cpu_info *uci) -{ - struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT]; - unsigned int count = mc_saved_data->mc_saved_count; - - if (!mc_saved_data->mc_saved) { - copy_initrd_ptrs(mc_saved_tmp, initrd, initrd_start, count); - - return load_microcode_early(mc_saved_tmp, count, uci); - } else { -#ifdef CONFIG_X86_32 - microcode_phys(mc_saved_tmp, mc_saved_data); - return load_microcode_early(mc_saved_tmp, count, uci); -#else - return load_microcode_early(mc_saved_data->mc_saved, - count, uci); -#endif - } -} - -/* - * Given CPU signature and a microcode patch, this function finds if the - * microcode patch has matching family and model with the CPU. - */ -static enum ucode_state -matching_model_microcode(struct microcode_header_intel *mc_header, - unsigned long sig) -{ - unsigned int fam, model; - unsigned int fam_ucode, model_ucode; - struct extended_sigtable *ext_header; - unsigned long total_size = get_totalsize(mc_header); - unsigned long data_size = get_datasize(mc_header); - int ext_sigcount, i; - struct extended_signature *ext_sig; - - fam = __x86_family(sig); - model = x86_model(sig); - - fam_ucode = __x86_family(mc_header->sig); - model_ucode = x86_model(mc_header->sig); - - if (fam == fam_ucode && model == model_ucode) - return UCODE_OK; - - /* Look for ext. headers: */ - if (total_size <= data_size + MC_HEADER_SIZE) - return UCODE_NFOUND; - - ext_header = (void *) mc_header + data_size + MC_HEADER_SIZE; - ext_sig = (void *)ext_header + EXT_HEADER_SIZE; - ext_sigcount = ext_header->count; - - for (i = 0; i < ext_sigcount; i++) { - fam_ucode = __x86_family(ext_sig->sig); - model_ucode = x86_model(ext_sig->sig); - - if (fam == fam_ucode && model == model_ucode) - return UCODE_OK; - - ext_sig++; - } - return UCODE_NFOUND; -} - -static int -save_microcode(struct mc_saved_data *mc_saved_data, - struct microcode_intel **mc_saved_src, - unsigned int mc_saved_count) -{ - int i, j; - struct microcode_intel **saved_ptr; - int ret; - - if (!mc_saved_count) - return -EINVAL; - - /* - * Copy new microcode data. - */ - saved_ptr = kcalloc(mc_saved_count, sizeof(struct microcode_intel *), GFP_KERNEL); - if (!saved_ptr) - return -ENOMEM; - - for (i = 0; i < mc_saved_count; i++) { - struct microcode_header_intel *mc_hdr; - struct microcode_intel *mc; - unsigned long size; - - if (!mc_saved_src[i]) { - ret = -EINVAL; - goto err; - } - - mc = mc_saved_src[i]; - mc_hdr = &mc->hdr; - size = get_totalsize(mc_hdr); - - saved_ptr[i] = kmalloc(size, GFP_KERNEL); - if (!saved_ptr[i]) { - ret = -ENOMEM; - goto err; - } - - memcpy(saved_ptr[i], mc, size); - } - - /* - * Point to newly saved microcode. - */ - mc_saved_data->mc_saved = saved_ptr; - mc_saved_data->mc_saved_count = mc_saved_count; - - return 0; - -err: - for (j = 0; j <= i; j++) - kfree(saved_ptr[j]); - kfree(saved_ptr); - - return ret; -} - -/* - * A microcode patch in ucode_ptr is saved into mc_saved - * - if it has matching signature and newer revision compared to an existing - * patch mc_saved. - * - or if it is a newly discovered microcode patch. - * - * The microcode patch should have matching model with CPU. - * - * Returns: The updated number @num_saved of saved microcode patches. - */ -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; - int found = 0, i; - - mc_hdr = (struct microcode_header_intel *)ucode_ptr; - - for (i = 0; i < num_saved; i++) { - mc_saved_hdr = (struct microcode_header_intel *)mc_saved[i]; - sig = mc_saved_hdr->sig; - pf = mc_saved_hdr->pf; - - if (!find_matching_signature(ucode_ptr, sig, pf)) - continue; - - found = 1; - - if (mc_hdr->rev <= mc_saved_hdr->rev) - continue; - - /* - * Found an older ucode saved earlier. Replace it with - * this newer one. - */ - mc_saved[i] = (struct microcode_intel *)ucode_ptr; - break; - } - - /* Newly detected microcode, save it to memory. */ - if (i >= num_saved && !found) - mc_saved[num_saved++] = (struct microcode_intel *)ucode_ptr; - - return num_saved; -} - -/* - * Get microcode matching with BSP's model. Only CPUs with the same model as - * BSP can stay in the platform. - */ -static enum ucode_state __init -get_matching_model_microcode(int cpu, unsigned long start, - void *data, size_t size, - struct mc_saved_data *mc_saved_data, - unsigned long *mc_saved_in_initrd, - struct ucode_cpu_info *uci) -{ - u8 *ucode_ptr = data; - unsigned int leftover = size; - enum ucode_state state = UCODE_OK; - unsigned int mc_size; - struct microcode_header_intel *mc_header; - struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT]; - unsigned int mc_saved_count = mc_saved_data->mc_saved_count; - int i; - - while (leftover && mc_saved_count < ARRAY_SIZE(mc_saved_tmp)) { - - if (leftover < sizeof(mc_header)) - break; - - mc_header = (struct microcode_header_intel *)ucode_ptr; - - mc_size = get_totalsize(mc_header); - if (!mc_size || mc_size > leftover || - microcode_sanity_check(ucode_ptr, 0) < 0) - break; - - leftover -= mc_size; - - /* - * Since APs with same family and model as the BSP may boot in - * the platform, we need to find and save microcode patches - * with the same family and model as the BSP. - */ - if (matching_model_microcode(mc_header, uci->cpu_sig.sig) != - UCODE_OK) { - ucode_ptr += mc_size; - continue; - } - - mc_saved_count = _save_mc(mc_saved_tmp, ucode_ptr, mc_saved_count); - - ucode_ptr += mc_size; - } - - if (leftover) { - state = UCODE_ERROR; - goto out; - } - - if (mc_saved_count == 0) { - state = UCODE_NFOUND; - goto out; - } - - for (i = 0; i < mc_saved_count; i++) - mc_saved_in_initrd[i] = (unsigned long)mc_saved_tmp[i] - start; - - mc_saved_data->mc_saved_count = mc_saved_count; -out: - return state; -} - -static int collect_cpu_info_early(struct ucode_cpu_info *uci) -{ - unsigned int val[2]; - unsigned int family, model; - struct cpu_signature csig; - unsigned int eax, ebx, ecx, edx; - - csig.sig = 0; - csig.pf = 0; - csig.rev = 0; - - memset(uci, 0, sizeof(*uci)); - - eax = 0x00000001; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - csig.sig = eax; - - family = __x86_family(csig.sig); - model = x86_model(csig.sig); - - if ((model >= 5) || (family > 6)) { - /* get processor flags from MSR 0x17 */ - native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]); - csig.pf = 1 << ((val[1] >> 18) & 7); - } - native_wrmsr(MSR_IA32_UCODE_REV, 0, 0); - - /* As documented in the SDM: Do a CPUID 1 here */ - sync_core(); - - /* get the current revision from MSR 0x8B */ - native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); - - csig.rev = val[1]; - - uci->cpu_sig = csig; - uci->valid = 1; - - return 0; -} - -#ifdef DEBUG -static void __ref show_saved_mc(void) -{ - int i, j; - unsigned int sig, pf, rev, total_size, data_size, date; - struct ucode_cpu_info uci; - - if (mc_saved_data.mc_saved_count == 0) { - pr_debug("no microcode data saved.\n"); - return; - } - pr_debug("Total microcode saved: %d\n", mc_saved_data.mc_saved_count); - - collect_cpu_info_early(&uci); - - sig = uci.cpu_sig.sig; - pf = uci.cpu_sig.pf; - rev = uci.cpu_sig.rev; - pr_debug("CPU: sig=0x%x, pf=0x%x, rev=0x%x\n", sig, pf, rev); - - for (i = 0; i < mc_saved_data.mc_saved_count; i++) { - struct microcode_header_intel *mc_saved_header; - struct extended_sigtable *ext_header; - int ext_sigcount; - struct extended_signature *ext_sig; - - mc_saved_header = (struct microcode_header_intel *) - mc_saved_data.mc_saved[i]; - sig = mc_saved_header->sig; - pf = mc_saved_header->pf; - rev = mc_saved_header->rev; - total_size = get_totalsize(mc_saved_header); - data_size = get_datasize(mc_saved_header); - date = mc_saved_header->date; - - pr_debug("mc_saved[%d]: sig=0x%x, pf=0x%x, rev=0x%x, toal size=0x%x, date = %04x-%02x-%02x\n", - i, sig, pf, rev, total_size, - date & 0xffff, - date >> 24, - (date >> 16) & 0xff); - - /* Look for ext. headers: */ - if (total_size <= data_size + MC_HEADER_SIZE) - continue; - - ext_header = (void *) mc_saved_header + data_size + MC_HEADER_SIZE; - ext_sigcount = ext_header->count; - ext_sig = (void *)ext_header + EXT_HEADER_SIZE; - - for (j = 0; j < ext_sigcount; j++) { - sig = ext_sig->sig; - pf = ext_sig->pf; - - pr_debug("\tExtended[%d]: sig=0x%x, pf=0x%x\n", - j, sig, pf); - - ext_sig++; - } - - } -} -#else -static inline void show_saved_mc(void) -{ -} -#endif - -#if defined(CONFIG_MICROCODE_INTEL_EARLY) && defined(CONFIG_HOTPLUG_CPU) -static DEFINE_MUTEX(x86_cpu_microcode_mutex); -/* - * Save this mc into mc_saved_data. So it will be loaded early when a CPU is - * hot added or resumes. - * - * Please make sure this mc should be a valid microcode patch before calling - * this function. - */ -int save_mc_for_early(u8 *mc) -{ - struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT]; - unsigned int mc_saved_count_init; - unsigned int mc_saved_count; - struct microcode_intel **mc_saved; - int ret = 0; - int i; - - /* - * Hold hotplug lock so mc_saved_data is not accessed by a CPU in - * hotplug. - */ - mutex_lock(&x86_cpu_microcode_mutex); - - mc_saved_count_init = mc_saved_data.mc_saved_count; - mc_saved_count = mc_saved_data.mc_saved_count; - mc_saved = mc_saved_data.mc_saved; - - if (mc_saved && mc_saved_count) - memcpy(mc_saved_tmp, mc_saved, - mc_saved_count * sizeof(struct microcode_intel *)); - /* - * Save the microcode patch mc in mc_save_tmp structure if it's a newer - * version. - */ - mc_saved_count = _save_mc(mc_saved_tmp, mc, mc_saved_count); - - /* - * Save the mc_save_tmp in global mc_saved_data. - */ - ret = save_microcode(&mc_saved_data, mc_saved_tmp, mc_saved_count); - if (ret) { - pr_err("Cannot save microcode patch.\n"); - goto out; - } - - show_saved_mc(); - - /* - * Free old saved microcode data. - */ - if (mc_saved) { - for (i = 0; i < mc_saved_count_init; i++) - kfree(mc_saved[i]); - kfree(mc_saved); - } - -out: - mutex_unlock(&x86_cpu_microcode_mutex); - - return ret; -} -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, "intel-ucode/%02x-%02x-%02x", family, model, stepping); - - return get_builtin_firmware(cp, name); -#else - return false; -#endif -} - -static __initdata char ucode_name[] = "kernel/x86/microcode/GenuineIntel.bin"; -static __init enum ucode_state -scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd, - unsigned long start, unsigned long size, - struct ucode_cpu_info *uci) -{ - struct cpio_data cd; - long offset = 0; -#ifdef CONFIG_X86_32 - char *p = (char *)__pa_nodebug(ucode_name); -#else - char *p = ucode_name; -#endif - - cd.data = NULL; - cd.size = 0; - - cd = find_cpio_data(p, (void *)start, size, &offset); - 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); -} - -/* - * Print ucode update info. - */ -static void -print_ucode_info(struct ucode_cpu_info *uci, unsigned int date) -{ - int cpu = smp_processor_id(); - - pr_info("CPU%d microcode updated early to revision 0x%x, date = %04x-%02x-%02x\n", - cpu, - uci->cpu_sig.rev, - date & 0xffff, - date >> 24, - (date >> 16) & 0xff); -} - -#ifdef CONFIG_X86_32 - -static int delay_ucode_info; -static int current_mc_date; - -/* - * Print early updated ucode info after printk works. This is delayed info dump. - */ -void show_ucode_info_early(void) -{ - struct ucode_cpu_info uci; - - if (delay_ucode_info) { - collect_cpu_info_early(&uci); - print_ucode_info(&uci, current_mc_date); - delay_ucode_info = 0; - } -} - -/* - * At this point, we can not call printk() yet. Keep microcode patch number in - * mc_saved_data.mc_saved and delay printing microcode info in - * show_ucode_info_early() until printk() works. - */ -static void print_ucode(struct ucode_cpu_info *uci) -{ - struct microcode_intel *mc_intel; - int *delay_ucode_info_p; - int *current_mc_date_p; - - mc_intel = uci->mc; - if (mc_intel == NULL) - return; - - delay_ucode_info_p = (int *)__pa_nodebug(&delay_ucode_info); - current_mc_date_p = (int *)__pa_nodebug(¤t_mc_date); - - *delay_ucode_info_p = 1; - *current_mc_date_p = mc_intel->hdr.date; -} -#else - -/* - * Flush global tlb. We only do this in x86_64 where paging has been enabled - * already and PGE should be enabled as well. - */ -static inline void flush_tlb_early(void) -{ - __native_flush_tlb_global_irq_disabled(); -} - -static inline void print_ucode(struct ucode_cpu_info *uci) -{ - struct microcode_intel *mc_intel; - - mc_intel = uci->mc; - if (mc_intel == NULL) - return; - - print_ucode_info(uci, mc_intel->hdr.date); -} -#endif - -static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) -{ - struct microcode_intel *mc_intel; - unsigned int val[2]; - - mc_intel = uci->mc; - if (mc_intel == NULL) - return 0; - - /* write microcode via MSR 0x79 */ - native_wrmsr(MSR_IA32_UCODE_WRITE, - (unsigned long) mc_intel->bits, - (unsigned long) mc_intel->bits >> 16 >> 16); - native_wrmsr(MSR_IA32_UCODE_REV, 0, 0); - - /* As documented in the SDM: Do a CPUID 1 here */ - sync_core(); - - /* get the current revision from MSR 0x8B */ - native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); - if (val[1] != mc_intel->hdr.rev) - return -1; - -#ifdef CONFIG_X86_64 - /* Flush global tlb. This is precaution. */ - flush_tlb_early(); -#endif - uci->cpu_sig.rev = val[1]; - - if (early) - print_ucode(uci); - else - print_ucode_info(uci, mc_intel->hdr.date); - - return 0; -} - -/* - * This function converts microcode patch offsets previously stored in - * mc_saved_in_initrd to pointers and stores the pointers in mc_saved_data. - */ -int __init save_microcode_in_initrd_intel(void) -{ - unsigned int count = mc_saved_data.mc_saved_count; - struct microcode_intel *mc_saved[MAX_UCODE_COUNT]; - int ret = 0; - - if (count == 0) - return ret; - - copy_initrd_ptrs(mc_saved, mc_saved_in_initrd, initrd_start, count); - ret = save_microcode(&mc_saved_data, mc_saved, count); - if (ret) - pr_err("Cannot save microcode patches from initrd.\n"); - - show_saved_mc(); - - return ret; -} - -static void __init -_load_ucode_intel_bsp(struct mc_saved_data *mc_saved_data, - unsigned long *initrd, - unsigned long start, unsigned long size) -{ - struct ucode_cpu_info uci; - enum ucode_state ret; - - collect_cpu_info_early(&uci); - - ret = scan_microcode(mc_saved_data, initrd, start, size, &uci); - if (ret != UCODE_OK) - return; - - ret = load_microcode(mc_saved_data, initrd, start, &uci); - if (ret != UCODE_OK) - return; - - apply_microcode_early(&uci, true); -} - -void __init load_ucode_intel_bsp(void) -{ - u64 start, size; -#ifdef CONFIG_X86_32 - struct boot_params *p; - - p = (struct boot_params *)__pa_nodebug(&boot_params); - start = p->hdr.ramdisk_image; - size = p->hdr.ramdisk_size; - - _load_ucode_intel_bsp( - (struct mc_saved_data *)__pa_nodebug(&mc_saved_data), - (unsigned long *)__pa_nodebug(&mc_saved_in_initrd), - start, size); -#else - start = boot_params.hdr.ramdisk_image + PAGE_OFFSET; - size = boot_params.hdr.ramdisk_size; - - _load_ucode_intel_bsp(&mc_saved_data, mc_saved_in_initrd, start, size); -#endif -} - -void load_ucode_intel_ap(void) -{ - struct mc_saved_data *mc_saved_data_p; - struct ucode_cpu_info uci; - unsigned long *mc_saved_in_initrd_p; - unsigned long initrd_start_addr; - enum ucode_state ret; -#ifdef CONFIG_X86_32 - unsigned long *initrd_start_p; - - mc_saved_in_initrd_p = - (unsigned long *)__pa_nodebug(mc_saved_in_initrd); - mc_saved_data_p = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data); - initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start); - initrd_start_addr = (unsigned long)__pa_nodebug(*initrd_start_p); -#else - mc_saved_data_p = &mc_saved_data; - mc_saved_in_initrd_p = mc_saved_in_initrd; - initrd_start_addr = initrd_start; -#endif - - /* - * If there is no valid ucode previously saved in memory, no need to - * update ucode on this AP. - */ - if (mc_saved_data_p->mc_saved_count == 0) - return; - - collect_cpu_info_early(&uci); - ret = load_microcode(mc_saved_data_p, mc_saved_in_initrd_p, - initrd_start_addr, &uci); - - if (ret != UCODE_OK) - return; - - apply_microcode_early(&uci, true); -} - -void reload_ucode_intel(void) -{ - struct ucode_cpu_info uci; - enum ucode_state ret; - - if (!mc_saved_data.mc_saved_count) - return; - - collect_cpu_info_early(&uci); - - ret = load_microcode_early(mc_saved_data.mc_saved, - mc_saved_data.mc_saved_count, &uci); - if (ret != UCODE_OK) - return; - - apply_microcode_early(&uci, false); -} diff --git a/arch/x86/kernel/cpu/microcode/intel_lib.c b/arch/x86/kernel/cpu/microcode/intel_lib.c index 1883d252ff7d..b96896bcbdaf 100644 --- a/arch/x86/kernel/cpu/microcode/intel_lib.c +++ b/arch/x86/kernel/cpu/microcode/intel_lib.c @@ -25,7 +25,6 @@ #include <linux/firmware.h> #include <linux/uaccess.h> #include <linux/kernel.h> -#include <linux/module.h> #include <asm/microcode_intel.h> #include <asm/processor.h> diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index aad4bd84b475..20e242ea1bc4 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -18,6 +18,7 @@ #include <linux/efi.h> #include <linux/interrupt.h> #include <linux/irq.h> +#include <linux/kexec.h> #include <asm/processor.h> #include <asm/hypervisor.h> #include <asm/hyperv.h> @@ -28,12 +29,15 @@ #include <asm/i8259.h> #include <asm/apic.h> #include <asm/timer.h> +#include <asm/reboot.h> struct ms_hyperv_info ms_hyperv; EXPORT_SYMBOL_GPL(ms_hyperv); #if IS_ENABLED(CONFIG_HYPERV) static void (*vmbus_handler)(void); +static void (*hv_kexec_handler)(void); +static void (*hv_crash_handler)(struct pt_regs *regs); void hyperv_vector_handler(struct pt_regs *regs) { @@ -67,7 +71,47 @@ void hv_remove_vmbus_irq(void) } EXPORT_SYMBOL_GPL(hv_setup_vmbus_irq); EXPORT_SYMBOL_GPL(hv_remove_vmbus_irq); -#endif + +void hv_setup_kexec_handler(void (*handler)(void)) +{ + hv_kexec_handler = handler; +} +EXPORT_SYMBOL_GPL(hv_setup_kexec_handler); + +void hv_remove_kexec_handler(void) +{ + hv_kexec_handler = NULL; +} +EXPORT_SYMBOL_GPL(hv_remove_kexec_handler); + +void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs)) +{ + hv_crash_handler = handler; +} +EXPORT_SYMBOL_GPL(hv_setup_crash_handler); + +void hv_remove_crash_handler(void) +{ + hv_crash_handler = NULL; +} +EXPORT_SYMBOL_GPL(hv_remove_crash_handler); + +#ifdef CONFIG_KEXEC_CORE +static void hv_machine_shutdown(void) +{ + if (kexec_in_progress && hv_kexec_handler) + hv_kexec_handler(); + native_machine_shutdown(); +} + +static void hv_machine_crash_shutdown(struct pt_regs *regs) +{ + if (hv_crash_handler) + hv_crash_handler(regs); + native_machine_crash_shutdown(regs); +} +#endif /* CONFIG_KEXEC_CORE */ +#endif /* CONFIG_HYPERV */ static uint32_t __init ms_hyperv_platform(void) { @@ -114,6 +158,7 @@ static void __init ms_hyperv_init_platform(void) * Extract the features and hints */ ms_hyperv.features = cpuid_eax(HYPERV_CPUID_FEATURES); + ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES); ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO); printk(KERN_INFO "HyperV: features 0x%x, hints 0x%x\n", @@ -141,6 +186,11 @@ static void __init ms_hyperv_init_platform(void) no_timer_check = 1; #endif +#if IS_ENABLED(CONFIG_HYPERV) && defined(CONFIG_KEXEC_CORE) + machine_ops.shutdown = hv_machine_shutdown; + machine_ops.crash_shutdown = hv_machine_crash_shutdown; +#endif + mark_tsc_unstable("running on Hyper-V"); } const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 70d7c93f4550..0d98503c2245 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -593,9 +593,16 @@ mtrr_calc_range_state(u64 chunk_size, u64 gran_size, unsigned long x_remove_base, unsigned long x_remove_size, int i) { - static struct range range_new[RANGE_NUM]; + /* + * range_new should really be an automatic variable, but + * putting 4096 bytes on the stack is frowned upon, to put it + * mildly. It is safe to make it a static __initdata variable, + * since mtrr_calc_range_state is only called during init and + * there's no way it will call itself recursively. + */ + static struct range range_new[RANGE_NUM] __initdata; unsigned long range_sums_new; - static int nr_range_new; + int nr_range_new; int num_reg; /* Convert ranges to var ranges state: */ diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 3b533cf37c74..c870af161008 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -349,7 +349,7 @@ static void get_fixed_ranges(mtrr_type *frs) void mtrr_save_fixed_ranges(void *info) { - if (cpu_has_mtrr) + if (boot_cpu_has(X86_FEATURE_MTRR)) get_fixed_ranges(mtrr_state.fixed_ranges); } diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index e7ed0d8ebacb..5c3d149ee91c 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -448,7 +448,6 @@ int mtrr_add(unsigned long base, unsigned long size, unsigned int type, return mtrr_add_page(base >> PAGE_SHIFT, size >> PAGE_SHIFT, type, increment); } -EXPORT_SYMBOL(mtrr_add); /** * mtrr_del_page - delete a memory type region @@ -537,7 +536,6 @@ int mtrr_del(int reg, unsigned long base, unsigned long size) return -EINVAL; return mtrr_del_page(reg, base >> PAGE_SHIFT, size >> PAGE_SHIFT); } -EXPORT_SYMBOL(mtrr_del); /** * arch_phys_wc_add - add a WC MTRR and handle errors if PAT is unavailable @@ -684,7 +682,7 @@ void __init mtrr_bp_init(void) phys_addr = 32; - if (cpu_has_mtrr) { + if (boot_cpu_has(X86_FEATURE_MTRR)) { mtrr_if = &generic_mtrr_ops; size_or_mask = SIZE_OR_MASK_BITS(36); size_and_mask = 0x00f00000; diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 9469dfa55607..1b443db2db50 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -5,7 +5,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com> * Copyright (C) 2009 Google, Inc., Stephane Eranian * @@ -482,6 +482,9 @@ int x86_pmu_hw_config(struct perf_event *event) /* Support for IP fixup */ if (x86_pmu.lbr_nr || x86_pmu.intel_cap.pebs_format >= 2) precise++; + + if (x86_pmu.pebs_prec_dist) + precise++; } if (event->attr.precise_ip > precise) @@ -1175,7 +1178,7 @@ static int x86_pmu_add(struct perf_event *event, int flags) * skip the schedulability test here, it will be performed * at commit time (->commit_txn) as a whole. */ - if (cpuc->group_flag & PERF_EVENT_TXN) + if (cpuc->txn_flags & PERF_PMU_TXN_ADD) goto done_collect; ret = x86_pmu.schedule_events(cpuc, n, assign); @@ -1326,7 +1329,7 @@ static void x86_pmu_del(struct perf_event *event, int flags) * XXX assumes any ->del() called during a TXN will only be on * an event added during that same TXN. */ - if (cpuc->group_flag & PERF_EVENT_TXN) + if (cpuc->txn_flags & PERF_PMU_TXN_ADD) return; /* @@ -1531,6 +1534,7 @@ static void __init filter_events(struct attribute **attrs) { struct device_attribute *d; struct perf_pmu_events_attr *pmu_attr; + int offset = 0; int i, j; for (i = 0; attrs[i]; i++) { @@ -1539,7 +1543,7 @@ static void __init filter_events(struct attribute **attrs) /* str trumps id */ if (pmu_attr->event_str) continue; - if (x86_pmu.event_map(i)) + if (x86_pmu.event_map(i + offset)) continue; for (j = i; attrs[j]; j++) @@ -1547,11 +1551,19 @@ static void __init filter_events(struct attribute **attrs) /* Check the shifted attr. */ i--; + + /* + * event_map() is index based, the attrs array is organized + * by increasing event index. If we shift the events, then + * we need to compensate for the event_map(), otherwise + * we are looking up the wrong event in the map + */ + offset++; } } /* Merge two pointer arrays */ -static __init struct attribute **merge_attr(struct attribute **a, struct attribute **b) +__init struct attribute **merge_attr(struct attribute **a, struct attribute **b) { struct attribute **new; int j, i; @@ -1748,11 +1760,22 @@ static inline void x86_pmu_read(struct perf_event *event) * Start group events scheduling transaction * Set the flag to make pmu::enable() not perform the * schedulability test, it will be performed at commit time + * + * We only support PERF_PMU_TXN_ADD transactions. Save the + * transaction flags but otherwise ignore non-PERF_PMU_TXN_ADD + * transactions. */ -static void x86_pmu_start_txn(struct pmu *pmu) +static void x86_pmu_start_txn(struct pmu *pmu, unsigned int txn_flags) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + WARN_ON_ONCE(cpuc->txn_flags); /* txn already in flight */ + + cpuc->txn_flags = txn_flags; + if (txn_flags & ~PERF_PMU_TXN_ADD) + return; + perf_pmu_disable(pmu); - __this_cpu_or(cpu_hw_events.group_flag, PERF_EVENT_TXN); __this_cpu_write(cpu_hw_events.n_txn, 0); } @@ -1763,7 +1786,16 @@ static void x86_pmu_start_txn(struct pmu *pmu) */ static void x86_pmu_cancel_txn(struct pmu *pmu) { - __this_cpu_and(cpu_hw_events.group_flag, ~PERF_EVENT_TXN); + unsigned int txn_flags; + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + WARN_ON_ONCE(!cpuc->txn_flags); /* no txn in flight */ + + txn_flags = cpuc->txn_flags; + cpuc->txn_flags = 0; + if (txn_flags & ~PERF_PMU_TXN_ADD) + return; + /* * Truncate collected array by the number of events added in this * transaction. See x86_pmu_add() and x86_pmu_*_txn(). @@ -1786,6 +1818,13 @@ static int x86_pmu_commit_txn(struct pmu *pmu) int assign[X86_PMC_IDX_MAX]; int n, ret; + WARN_ON_ONCE(!cpuc->txn_flags); /* no txn in flight */ + + if (cpuc->txn_flags & ~PERF_PMU_TXN_ADD) { + cpuc->txn_flags = 0; + return 0; + } + n = cpuc->n_events; if (!x86_pmu_initialized()) @@ -1801,7 +1840,7 @@ static int x86_pmu_commit_txn(struct pmu *pmu) */ memcpy(cpuc->assign, assign, n*sizeof(int)); - cpuc->group_flag &= ~PERF_EVENT_TXN; + cpuc->txn_flags = 0; perf_pmu_enable(pmu); return 0; } @@ -2179,6 +2218,7 @@ static unsigned long get_segment_base(unsigned int segment) int idx = segment >> 3; if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) { +#ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; if (idx > LDT_ENTRIES) @@ -2190,6 +2230,9 @@ static unsigned long get_segment_base(unsigned int segment) return 0; desc = &ldt->entries[idx]; +#else + return 0; +#endif } else { if (idx > GDT_ENTRIES) return 0; @@ -2200,7 +2243,7 @@ static unsigned long get_segment_base(unsigned int segment) return get_desc_base(desc); } -#ifdef CONFIG_COMPAT +#ifdef CONFIG_IA32_EMULATION #include <asm/compat.h> @@ -2219,12 +2262,19 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) ss_base = get_segment_base(regs->ss); fp = compat_ptr(ss_base + regs->bp); + pagefault_disable(); while (entry->nr < PERF_MAX_STACK_DEPTH) { unsigned long bytes; frame.next_frame = 0; frame.return_address = 0; - bytes = copy_from_user_nmi(&frame, fp, sizeof(frame)); + if (!access_ok(VERIFY_READ, fp, 8)) + break; + + bytes = __copy_from_user_nmi(&frame.next_frame, fp, 4); + if (bytes != 0) + break; + bytes = __copy_from_user_nmi(&frame.return_address, fp+4, 4); if (bytes != 0) break; @@ -2234,6 +2284,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) perf_callchain_store(entry, cs_base + frame.return_address); fp = compat_ptr(ss_base + frame.next_frame); } + pagefault_enable(); return 1; } #else @@ -2271,12 +2322,19 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) if (perf_callchain_user32(regs, entry)) return; + pagefault_disable(); while (entry->nr < PERF_MAX_STACK_DEPTH) { unsigned long bytes; frame.next_frame = NULL; frame.return_address = 0; - bytes = copy_from_user_nmi(&frame, fp, sizeof(frame)); + if (!access_ok(VERIFY_READ, fp, 16)) + break; + + bytes = __copy_from_user_nmi(&frame.next_frame, fp, 8); + if (bytes != 0) + break; + bytes = __copy_from_user_nmi(&frame.return_address, fp+8, 8); if (bytes != 0) break; @@ -2284,8 +2342,9 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) break; perf_callchain_store(entry, frame.return_address); - fp = frame.next_frame; + fp = (void __user *)frame.next_frame; } + pagefault_enable(); } /* diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 3e7fd27dfe20..7bb61e32fb29 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -5,7 +5,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com> * Copyright (C) 2009 Google, Inc., Stephane Eranian * @@ -14,17 +14,7 @@ #include <linux/perf_event.h> -#if 0 -#undef wrmsrl -#define wrmsrl(msr, val) \ -do { \ - unsigned int _msr = (msr); \ - u64 _val = (val); \ - trace_printk("wrmsrl(%x, %Lx)\n", (unsigned int)(_msr), \ - (unsigned long long)(_val)); \ - native_write_msr((_msr), (u32)(_val), (u32)(_val >> 32)); \ -} while (0) -#endif +/* To enable MSR tracing please use the generic trace points. */ /* * | NHM/WSM | SNB | @@ -47,6 +37,7 @@ enum extra_reg_type { EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */ EXTRA_REG_LBR = 2, /* lbr_select */ EXTRA_REG_LDLAT = 3, /* ld_lat_threshold */ + EXTRA_REG_FE = 4, /* fe_* */ EXTRA_REG_MAX /* number of entries needed */ }; @@ -165,7 +156,7 @@ struct intel_excl_cntrs { unsigned core_id; /* per-core: core id */ }; -#define MAX_LBR_ENTRIES 16 +#define MAX_LBR_ENTRIES 32 enum { X86_PERF_KFREE_SHARED = 0, @@ -195,7 +186,7 @@ struct cpu_hw_events { int n_excl; /* the number of exclusive events */ - unsigned int group_flag; + unsigned int txn_flags; int is_fake; /* @@ -317,6 +308,10 @@ struct cpu_hw_events { #define INTEL_UEVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK) +/* Constraint on specific umask bit only + event */ +#define INTEL_UBIT_EVENT_CONSTRAINT(c, n) \ + EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT|(c)) + /* Like UEVENT_CONSTRAINT, but match flags too */ #define INTEL_FLAGS_UEVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS) @@ -386,7 +381,7 @@ struct cpu_hw_events { /* Check flags and event code/umask, and set the HSW N/A flag */ #define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(code, n) \ __EVENT_CONSTRAINT(code, n, \ - INTEL_ARCH_EVENT_MASK|INTEL_ARCH_EVENT_MASK, \ + INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_NA_HSW) @@ -588,12 +583,14 @@ struct x86_pmu { bts_active :1, pebs :1, pebs_active :1, - pebs_broken :1; + pebs_broken :1, + pebs_prec_dist :1; int pebs_record_size; void (*drain_pebs)(struct pt_regs *regs); struct event_constraint *pebs_constraints; void (*pebs_aliases)(struct perf_event *event); int max_pebs_events; + unsigned long free_running_flags; /* * Intel LBR @@ -624,6 +621,8 @@ struct x86_pmu { struct x86_perf_task_context { u64 lbr_from[MAX_LBR_ENTRIES]; u64 lbr_to[MAX_LBR_ENTRIES]; + u64 lbr_info[MAX_LBR_ENTRIES]; + int tos; int lbr_callstack_users; int lbr_stack_state; }; @@ -793,6 +792,8 @@ static inline void set_linear_ip(struct pt_regs *regs, unsigned long ip) ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event); ssize_t intel_event_sysfs_show(char *page, u64 config); +struct attribute **merge_attr(struct attribute **a, struct attribute **b); + #ifdef CONFIG_CPU_SUP_AMD int amd_pmu_init(void); @@ -808,20 +809,6 @@ static inline int amd_pmu_init(void) #ifdef CONFIG_CPU_SUP_INTEL -static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event) -{ - /* user explicitly requested branch sampling */ - if (has_branch_stack(event)) - return true; - - /* implicit branch sampling to correct PEBS skid */ - if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1 && - x86_pmu.intel_cap.pebs_format < 2) - return true; - - return false; -} - static inline bool intel_pmu_has_bts(struct perf_event *event) { if (event->attr.config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS && @@ -873,6 +860,8 @@ extern struct event_constraint intel_ivb_pebs_event_constraints[]; extern struct event_constraint intel_hsw_pebs_event_constraints[]; +extern struct event_constraint intel_skl_pebs_event_constraints[]; + struct event_constraint *intel_pebs_constraints(struct perf_event *event); void intel_pmu_pebs_enable(struct perf_event *event); @@ -911,6 +900,10 @@ void intel_pmu_lbr_init_snb(void); void intel_pmu_lbr_init_hsw(void); +void intel_pmu_lbr_init_skl(void); + +void intel_pmu_lbr_init_knl(void); + int intel_pmu_setup_lbr_filter(struct perf_event *event); void intel_pt_interrupt(void); @@ -934,6 +927,7 @@ static inline int is_ht_workaround_enabled(void) { return !!(x86_pmu.flags & PMU_FL_EXCL_ENABLED); } + #else /* CONFIG_CPU_SUP_INTEL */ static inline void reserve_ds_buffers(void) diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 1cee5d2d7ece..58610539b048 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -18,7 +18,7 @@ static __initconst const u64 amd_hw_cache_event_ids [ C(RESULT_MISS) ] = 0x0141, /* Data Cache Misses */ }, [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */ + [ C(RESULT_ACCESS) ] = 0, [ C(RESULT_MISS) ] = 0, }, [ C(OP_PREFETCH) ] = { @@ -160,7 +160,7 @@ static inline int amd_pmu_addr_offset(int index, bool eventsel) if (offset) return offset; - if (!cpu_has_perfctr_core) + if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE)) offset = index; else offset = index << 1; @@ -652,7 +652,7 @@ static __initconst const struct x86_pmu amd_pmu = { static int __init amd_core_pmu_init(void) { - if (!cpu_has_perfctr_core) + if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE)) return 0; switch (boot_cpu_data.x86) { diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c index cc6cedb8f25d..49742746a6c9 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c @@ -523,10 +523,10 @@ static int __init amd_uncore_init(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) goto fail_nodev; - if (!cpu_has_topoext) + if (!boot_cpu_has(X86_FEATURE_TOPOEXT)) goto fail_nodev; - if (cpu_has_perfctr_nb) { + if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) { amd_uncore_nb = alloc_percpu(struct amd_uncore *); if (!amd_uncore_nb) { ret = -ENOMEM; @@ -540,7 +540,7 @@ static int __init amd_uncore_init(void) ret = 0; } - if (cpu_has_perfctr_l2) { + if (boot_cpu_has(X86_FEATURE_PERFCTR_L2)) { amd_uncore_l2 = alloc_percpu(struct amd_uncore *); if (!amd_uncore_l2) { ret = -ENOMEM; @@ -583,10 +583,11 @@ fail_online: /* amd_uncore_nb/l2 should have been freed by cleanup_cpu_online */ amd_uncore_nb = amd_uncore_l2 = NULL; - if (cpu_has_perfctr_l2) + + if (boot_cpu_has(X86_FEATURE_PERFCTR_L2)) perf_pmu_unregister(&amd_l2_pmu); fail_l2: - if (cpu_has_perfctr_nb) + if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) perf_pmu_unregister(&amd_nb_pmu); if (amd_uncore_l2) free_percpu(amd_uncore_l2); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 6326ae24e4d5..a667078a5180 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -12,7 +12,7 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/export.h> -#include <linux/watchdog.h> +#include <linux/nmi.h> #include <asm/cpufeature.h> #include <asm/hardirq.h> @@ -177,6 +177,22 @@ static struct event_constraint intel_slm_event_constraints[] __read_mostly = EVENT_CONSTRAINT_END }; +struct event_constraint intel_skl_event_constraints[] = { + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ + FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ + INTEL_UEVENT_CONSTRAINT(0x1c0, 0x2), /* INST_RETIRED.PREC_DIST */ + EVENT_CONSTRAINT_END +}; + +static struct extra_reg intel_knl_extra_regs[] __read_mostly = { + INTEL_UEVENT_EXTRA_REG(0x01b7, + MSR_OFFCORE_RSP_0, 0x7f9ffbffffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x02b7, + MSR_OFFCORE_RSP_1, 0x3f9ffbffffull, RSP_1), + EVENT_EXTRA_END +}; + static struct extra_reg intel_snb_extra_regs[] __read_mostly = { /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0), @@ -193,6 +209,18 @@ static struct extra_reg intel_snbep_extra_regs[] __read_mostly = { EVENT_EXTRA_END }; +static struct extra_reg intel_skl_extra_regs[] __read_mostly = { + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), + /* + * Note the low 8 bits eventsel code is not a continuous field, containing + * some #GPing bits. These are masked out. + */ + INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE), + EVENT_EXTRA_END +}; + EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3"); EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3"); EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2"); @@ -212,7 +240,7 @@ static struct event_constraint intel_hsw_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ - INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.* */ + INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ @@ -235,7 +263,7 @@ struct event_constraint intel_bdw_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */ - INTEL_EVENT_CONSTRAINT(0xa3, 0x4), /* CYCLE_ACTIVITY.* */ + INTEL_UBIT_EVENT_CONSTRAINT(0x8a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */ EVENT_CONSTRAINT_END }; @@ -244,6 +272,200 @@ static u64 intel_pmu_event_map(int hw_event) return intel_perfmon_event_map[hw_event]; } +/* + * Notes on the events: + * - data reads do not include code reads (comparable to earlier tables) + * - data counts include speculative execution (except L1 write, dtlb, bpu) + * - remote node access includes remote memory, remote cache, remote mmio. + * - prefetches are not included in the counts. + * - icache miss does not include decoded icache + */ + +#define SKL_DEMAND_DATA_RD BIT_ULL(0) +#define SKL_DEMAND_RFO BIT_ULL(1) +#define SKL_ANY_RESPONSE BIT_ULL(16) +#define SKL_SUPPLIER_NONE BIT_ULL(17) +#define SKL_L3_MISS_LOCAL_DRAM BIT_ULL(26) +#define SKL_L3_MISS_REMOTE_HOP0_DRAM BIT_ULL(27) +#define SKL_L3_MISS_REMOTE_HOP1_DRAM BIT_ULL(28) +#define SKL_L3_MISS_REMOTE_HOP2P_DRAM BIT_ULL(29) +#define SKL_L3_MISS (SKL_L3_MISS_LOCAL_DRAM| \ + SKL_L3_MISS_REMOTE_HOP0_DRAM| \ + SKL_L3_MISS_REMOTE_HOP1_DRAM| \ + SKL_L3_MISS_REMOTE_HOP2P_DRAM) +#define SKL_SPL_HIT BIT_ULL(30) +#define SKL_SNOOP_NONE BIT_ULL(31) +#define SKL_SNOOP_NOT_NEEDED BIT_ULL(32) +#define SKL_SNOOP_MISS BIT_ULL(33) +#define SKL_SNOOP_HIT_NO_FWD BIT_ULL(34) +#define SKL_SNOOP_HIT_WITH_FWD BIT_ULL(35) +#define SKL_SNOOP_HITM BIT_ULL(36) +#define SKL_SNOOP_NON_DRAM BIT_ULL(37) +#define SKL_ANY_SNOOP (SKL_SPL_HIT|SKL_SNOOP_NONE| \ + SKL_SNOOP_NOT_NEEDED|SKL_SNOOP_MISS| \ + SKL_SNOOP_HIT_NO_FWD|SKL_SNOOP_HIT_WITH_FWD| \ + SKL_SNOOP_HITM|SKL_SNOOP_NON_DRAM) +#define SKL_DEMAND_READ SKL_DEMAND_DATA_RD +#define SKL_SNOOP_DRAM (SKL_SNOOP_NONE| \ + SKL_SNOOP_NOT_NEEDED|SKL_SNOOP_MISS| \ + SKL_SNOOP_HIT_NO_FWD|SKL_SNOOP_HIT_WITH_FWD| \ + SKL_SNOOP_HITM|SKL_SPL_HIT) +#define SKL_DEMAND_WRITE SKL_DEMAND_RFO +#define SKL_LLC_ACCESS SKL_ANY_RESPONSE +#define SKL_L3_MISS_REMOTE (SKL_L3_MISS_REMOTE_HOP0_DRAM| \ + SKL_L3_MISS_REMOTE_HOP1_DRAM| \ + SKL_L3_MISS_REMOTE_HOP2P_DRAM) + +static __initconst const u64 skl_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x81d0, /* MEM_INST_RETIRED.ALL_LOADS */ + [ C(RESULT_MISS) ] = 0x151, /* L1D.REPLACEMENT */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_INST_RETIRED.ALL_STORES */ + [ C(RESULT_MISS) ] = 0x0, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(L1I ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x283, /* ICACHE_64B.MISS */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + [ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + [ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x81d0, /* MEM_INST_RETIRED.ALL_LOADS */ + [ C(RESULT_MISS) ] = 0x608, /* DTLB_LOAD_MISSES.WALK_COMPLETED */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_INST_RETIRED.ALL_STORES */ + [ C(RESULT_MISS) ] = 0x649, /* DTLB_STORE_MISSES.WALK_COMPLETED */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x2085, /* ITLB_MISSES.STLB_HIT */ + [ C(RESULT_MISS) ] = 0xe85, /* ITLB_MISSES.WALK_COMPLETED */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0xc4, /* BR_INST_RETIRED.ALL_BRANCHES */ + [ C(RESULT_MISS) ] = 0xc5, /* BR_MISP_RETIRED.ALL_BRANCHES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + [ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + [ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, +}; + +static __initconst const u64 skl_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = SKL_DEMAND_READ| + SKL_LLC_ACCESS|SKL_ANY_SNOOP, + [ C(RESULT_MISS) ] = SKL_DEMAND_READ| + SKL_L3_MISS|SKL_ANY_SNOOP| + SKL_SUPPLIER_NONE, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = SKL_DEMAND_WRITE| + SKL_LLC_ACCESS|SKL_ANY_SNOOP, + [ C(RESULT_MISS) ] = SKL_DEMAND_WRITE| + SKL_L3_MISS|SKL_ANY_SNOOP| + SKL_SUPPLIER_NONE, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = SKL_DEMAND_READ| + SKL_L3_MISS_LOCAL_DRAM|SKL_SNOOP_DRAM, + [ C(RESULT_MISS) ] = SKL_DEMAND_READ| + SKL_L3_MISS_REMOTE|SKL_SNOOP_DRAM, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = SKL_DEMAND_WRITE| + SKL_L3_MISS_LOCAL_DRAM|SKL_SNOOP_DRAM, + [ C(RESULT_MISS) ] = SKL_DEMAND_WRITE| + SKL_L3_MISS_REMOTE|SKL_SNOOP_DRAM, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, +}; + #define SNB_DMND_DATA_RD (1ULL << 0) #define SNB_DMND_RFO (1ULL << 1) #define SNB_DMND_IFETCH (1ULL << 2) @@ -1114,7 +1336,7 @@ static struct extra_reg intel_slm_extra_regs[] __read_mostly = { /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x768005ffffull, RSP_0), - INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x768005ffffull, RSP_1), + INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x368005ffffull, RSP_1), EVENT_EXTRA_END }; @@ -1243,6 +1465,42 @@ static __initconst const u64 slm_hw_cache_event_ids }, }; +#define KNL_OT_L2_HITE BIT_ULL(19) /* Other Tile L2 Hit */ +#define KNL_OT_L2_HITF BIT_ULL(20) /* Other Tile L2 Hit */ +#define KNL_MCDRAM_LOCAL BIT_ULL(21) +#define KNL_MCDRAM_FAR BIT_ULL(22) +#define KNL_DDR_LOCAL BIT_ULL(23) +#define KNL_DDR_FAR BIT_ULL(24) +#define KNL_DRAM_ANY (KNL_MCDRAM_LOCAL | KNL_MCDRAM_FAR | \ + KNL_DDR_LOCAL | KNL_DDR_FAR) +#define KNL_L2_READ SLM_DMND_READ +#define KNL_L2_WRITE SLM_DMND_WRITE +#define KNL_L2_PREFETCH SLM_DMND_PREFETCH +#define KNL_L2_ACCESS SLM_LLC_ACCESS +#define KNL_L2_MISS (KNL_OT_L2_HITE | KNL_OT_L2_HITF | \ + KNL_DRAM_ANY | SNB_SNP_ANY | \ + SNB_NON_DRAM) + +static __initconst const u64 knl_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = KNL_L2_READ | KNL_L2_ACCESS, + [C(RESULT_MISS)] = 0, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = KNL_L2_WRITE | KNL_L2_ACCESS, + [C(RESULT_MISS)] = KNL_L2_WRITE | KNL_L2_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = KNL_L2_PREFETCH | KNL_L2_ACCESS, + [C(RESULT_MISS)] = KNL_L2_PREFETCH | KNL_L2_MISS, + }, + }, +}; + /* * Use from PMIs where the LBRs are already disabled. */ @@ -1594,6 +1852,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) loops = 0; again: + intel_pmu_lbr_read(); intel_pmu_ack_status(status); if (++loops > 100) { static bool warned = false; @@ -1608,16 +1867,16 @@ again: inc_irq_stat(apic_perf_irqs); - intel_pmu_lbr_read(); /* - * CondChgd bit 63 doesn't mean any overflow status. Ignore - * and clear the bit. + * Ignore a range of extra bits in status that do not indicate + * overflow by themselves. */ - if (__test_and_clear_bit(63, (unsigned long *)&status)) { - if (!status) - goto done; - } + status &= ~(GLOBAL_STATUS_COND_CHG | + GLOBAL_STATUS_ASIF | + GLOBAL_STATUS_LBRS_FROZEN); + if (!status) + goto done; /* * PEBS overflow sets bit 62 in the global status register @@ -1699,18 +1958,22 @@ intel_bts_constraints(struct perf_event *event) return NULL; } -static int intel_alt_er(int idx) +static int intel_alt_er(int idx, u64 config) { + int alt_idx; if (!(x86_pmu.flags & PMU_FL_HAS_RSP_1)) return idx; if (idx == EXTRA_REG_RSP_0) - return EXTRA_REG_RSP_1; + alt_idx = EXTRA_REG_RSP_1; if (idx == EXTRA_REG_RSP_1) - return EXTRA_REG_RSP_0; + alt_idx = EXTRA_REG_RSP_0; - return idx; + if (config & ~x86_pmu.extra_regs[alt_idx].valid_mask) + return idx; + + return alt_idx; } static void intel_fixup_er(struct perf_event *event, int idx) @@ -1799,7 +2062,7 @@ again: */ c = NULL; } else { - idx = intel_alt_er(idx); + idx = intel_alt_er(idx, reg->config); if (idx != reg->idx) { raw_spin_unlock_irqrestore(&era->lock, flags); goto again; @@ -2102,9 +2365,12 @@ static struct event_constraint * intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) { - struct event_constraint *c1 = cpuc->event_constraint[idx]; + struct event_constraint *c1 = NULL; struct event_constraint *c2; + if (idx >= 0) /* fake does < 0 */ + c1 = cpuc->event_constraint[idx]; + /* * first time only * - static constraint: no change across incremental scheduling calls @@ -2253,6 +2519,53 @@ static void intel_pebs_aliases_snb(struct perf_event *event) } } +static void intel_pebs_aliases_precdist(struct perf_event *event) +{ + if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) { + /* + * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P + * (0x003c) so that we can use it with PEBS. + * + * The regular CPU_CLK_UNHALTED.THREAD_P event (0x003c) isn't + * PEBS capable. However we can use INST_RETIRED.PREC_DIST + * (0x01c0), which is a PEBS capable event, to get the same + * count. + * + * The PREC_DIST event has special support to minimize sample + * shadowing effects. One drawback is that it can be + * only programmed on counter 1, but that seems like an + * acceptable trade off. + */ + u64 alt_config = X86_CONFIG(.event=0xc0, .umask=0x01, .inv=1, .cmask=16); + + alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK); + event->hw.config = alt_config; + } +} + +static void intel_pebs_aliases_ivb(struct perf_event *event) +{ + if (event->attr.precise_ip < 3) + return intel_pebs_aliases_snb(event); + return intel_pebs_aliases_precdist(event); +} + +static void intel_pebs_aliases_skl(struct perf_event *event) +{ + if (event->attr.precise_ip < 3) + return intel_pebs_aliases_core2(event); + return intel_pebs_aliases_precdist(event); +} + +static unsigned long intel_pmu_free_running_flags(struct perf_event *event) +{ + unsigned long flags = x86_pmu.free_running_flags; + + if (event->attr.use_clockid) + flags &= ~PERF_SAMPLE_TIME; + return flags; +} + static int intel_pmu_hw_config(struct perf_event *event) { int ret = x86_pmu_hw_config(event); @@ -2263,7 +2576,8 @@ static int intel_pmu_hw_config(struct perf_event *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)) + if (!(event->attr.sample_type & + ~intel_pmu_free_running_flags(event))) event->hw.flags |= PERF_X86_EVENT_FREERUNNING; } if (x86_pmu.pebs_aliases) @@ -2664,6 +2978,8 @@ PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63"); PMU_FORMAT_ATTR(ldlat, "config1:0-15"); +PMU_FORMAT_ATTR(frontend, "config1:0-23"); + static struct attribute *intel_arch3_formats_attr[] = { &format_attr_event.attr, &format_attr_umask.attr, @@ -2680,6 +2996,11 @@ static struct attribute *intel_arch3_formats_attr[] = { NULL, }; +static struct attribute *skl_format_attr[] = { + &format_attr_frontend.attr, + NULL, +}; + static __initconst const struct x86_pmu core_pmu = { .name = "core", .handle_irq = x86_pmu_handle_irq, @@ -2694,6 +3015,8 @@ static __initconst const struct x86_pmu core_pmu = { .event_map = intel_pmu_event_map, .max_events = ARRAY_SIZE(intel_perfmon_event_map), .apic = 1, + .free_running_flags = PEBS_FREERUNNING_FLAGS, + /* * Intel PMCs cannot be accessed sanely above 32-bit width, * so we install an artificial 1<<31 period regardless of @@ -2732,6 +3055,7 @@ static __initconst const struct x86_pmu intel_pmu = { .event_map = intel_pmu_event_map, .max_events = ARRAY_SIZE(intel_perfmon_event_map), .apic = 1, + .free_running_flags = PEBS_FREERUNNING_FLAGS, /* * Intel PMCs cannot be accessed sanely above 32 bit width, * so we install an artificial 1<<31 period regardless of @@ -3090,6 +3414,7 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_gen_event_constraints; x86_pmu.pebs_constraints = intel_atom_pebs_event_constraints; + x86_pmu.pebs_aliases = intel_pebs_aliases_core2; pr_cont("Atom events, "); break; @@ -3189,7 +3514,8 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_ivb_event_constraints; x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints; - x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + x86_pmu.pebs_aliases = intel_pebs_aliases_ivb; + x86_pmu.pebs_prec_dist = true; if (boot_cpu_data.x86_model == 62) x86_pmu.extra_regs = intel_snbep_extra_regs; else @@ -3222,7 +3548,8 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_hsw_event_constraints; x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints; x86_pmu.extra_regs = intel_snbep_extra_regs; - x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + x86_pmu.pebs_aliases = intel_pebs_aliases_ivb; + x86_pmu.pebs_prec_dist = true; /* all extra regs are per-cpu when HT is on */ x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.flags |= PMU_FL_NO_HT_SHARING; @@ -3257,7 +3584,8 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_bdw_event_constraints; x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints; x86_pmu.extra_regs = intel_snbep_extra_regs; - x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + x86_pmu.pebs_aliases = intel_pebs_aliases_ivb; + x86_pmu.pebs_prec_dist = true; /* all extra regs are per-cpu when HT is on */ x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.flags |= PMU_FL_NO_HT_SHARING; @@ -3269,6 +3597,49 @@ __init int intel_pmu_init(void) pr_cont("Broadwell events, "); break; + case 87: /* Knights Landing Xeon Phi */ + memcpy(hw_cache_event_ids, + slm_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, + knl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); + intel_pmu_lbr_init_knl(); + + x86_pmu.event_constraints = intel_slm_event_constraints; + x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints; + x86_pmu.extra_regs = intel_knl_extra_regs; + + /* all extra regs are per-cpu when HT is on */ + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_NO_HT_SHARING; + + pr_cont("Knights Landing events, "); + break; + + case 78: /* 14nm Skylake Mobile */ + case 94: /* 14nm Skylake Desktop */ + x86_pmu.late_ack = true; + memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); + intel_pmu_lbr_init_skl(); + + x86_pmu.event_constraints = intel_skl_event_constraints; + x86_pmu.pebs_constraints = intel_skl_pebs_event_constraints; + x86_pmu.extra_regs = intel_skl_extra_regs; + x86_pmu.pebs_aliases = intel_pebs_aliases_skl; + x86_pmu.pebs_prec_dist = true; + /* all extra regs are per-cpu when HT is on */ + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_NO_HT_SHARING; + + x86_pmu.hw_config = hsw_hw_config; + x86_pmu.get_event_constraints = hsw_get_event_constraints; + x86_pmu.format_attrs = merge_attr(intel_arch3_formats_attr, + skl_format_attr); + WARN_ON(!x86_pmu.format_attrs); + x86_pmu.cpu_events = hsw_events_attrs; + pr_cont("Skylake events, "); + break; + default: switch (x86_pmu.version) { case 1: @@ -3338,7 +3709,7 @@ __init int intel_pmu_init(void) */ if (x86_pmu.extra_regs) { for (er = x86_pmu.extra_regs; er->msr; er++) { - er->extra_msr_access = check_msr(er->msr, 0x1ffUL); + er->extra_msr_access = check_msr(er->msr, 0x11UL); /* Disable LBR select mapping */ if ((er->idx == EXTRA_REG_LBR) && !er->extra_msr_access) x86_pmu.lbr_sel_map = NULL; @@ -3377,7 +3748,10 @@ static __init int fixup_ht_bug(void) return 0; } - watchdog_nmi_disable_all(); + if (lockup_detector_suspend() != 0) { + pr_debug("failed to disable PMU erratum BJ122, BV98, HSD29 workaround\n"); + return 0; + } x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED); @@ -3385,7 +3759,7 @@ static __init int fixup_ht_bug(void) x86_pmu.commit_scheduling = NULL; x86_pmu.stop_scheduling = NULL; - watchdog_nmi_enable_all(); + lockup_detector_resume(); get_online_cpus(); diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/kernel/cpu/perf_event_intel_bts.c index 43dd672d788b..2cad71d1b14c 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_bts.c +++ b/arch/x86/kernel/cpu/perf_event_intel_bts.c @@ -62,9 +62,6 @@ struct bts_buffer { struct pmu bts_pmu; -void intel_pmu_enable_bts(u64 config); -void intel_pmu_disable_bts(void); - static size_t buf_size(struct page *page) { return 1 << (PAGE_SHIFT + page_private(page)); @@ -225,6 +222,7 @@ static void __bts_event_start(struct perf_event *event) if (!buf || bts_buffer_is_full(buf, bts)) return; + event->hw.itrace_started = 1; event->hw.state = 0; if (!buf->snapshot) @@ -497,6 +495,19 @@ static int bts_event_init(struct perf_event *event) if (x86_add_exclusive(x86_lbr_exclusive_bts)) return -EBUSY; + /* + * BTS leaks kernel addresses even when CPL0 tracing is + * disabled, so disallow intel_bts driver for unprivileged + * users on paranoid systems since it provides trace data + * to the user in a zero-copy fashion. + * + * Note that the default paranoia setting permits unprivileged + * users to profile the kernel. + */ + if (event->attr.exclude_kernel && perf_paranoid_kernel() && + !capable(CAP_SYS_ADMIN)) + return -EACCES; + ret = x86_reserve_hardware(); if (ret) { x86_del_exclusive(x86_lbr_exclusive_bts); diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c index 377e8f8ed391..a316ca96f1b6 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c +++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c @@ -298,7 +298,7 @@ static bool __match_event(struct perf_event *a, struct perf_event *b) static inline struct perf_cgroup *event_to_cgroup(struct perf_event *event) { if (event->attach_state & PERF_ATTACH_TASK) - return perf_cgroup_from_task(event->hw.target); + return perf_cgroup_from_task(event->hw.target, event->ctx); return event->cgrp; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_cstate.c b/arch/x86/kernel/cpu/perf_event_intel_cstate.c new file mode 100644 index 000000000000..75a38b5a2e26 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_cstate.c @@ -0,0 +1,694 @@ +/* + * perf_event_intel_cstate.c: support cstate residency counters + * + * Copyright (C) 2015, Intel Corp. + * Author: Kan Liang (kan.liang@intel.com) + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Library General Public + * License as published by the Free Software Foundation; either + * version 2 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Library General Public License for more details. + * + */ + +/* + * This file export cstate related free running (read-only) counters + * for perf. These counters may be use simultaneously by other tools, + * such as turbostat. However, it still make sense to implement them + * in perf. Because we can conveniently collect them together with + * other events, and allow to use them from tools without special MSR + * access code. + * + * The events only support system-wide mode counting. There is no + * sampling support because it is not supported by the hardware. + * + * According to counters' scope and category, two PMUs are registered + * with the perf_event core subsystem. + * - 'cstate_core': The counter is available for each physical core. + * The counters include CORE_C*_RESIDENCY. + * - 'cstate_pkg': The counter is available for each physical package. + * The counters include PKG_C*_RESIDENCY. + * + * All of these counters are specified in the Intel® 64 and IA-32 + * Architectures Software Developer.s Manual Vol3b. + * + * Model specific counters: + * MSR_CORE_C1_RES: CORE C1 Residency Counter + * perf code: 0x00 + * Available model: SLM,AMT + * Scope: Core (each processor core has a MSR) + * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter + * perf code: 0x01 + * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL + * Scope: Core + * MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter + * perf code: 0x02 + * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,SKL + * Scope: Core + * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter + * perf code: 0x03 + * Available model: SNB,IVB,HSW,BDW,SKL + * Scope: Core + * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. + * perf code: 0x00 + * Available model: SNB,IVB,HSW,BDW,SKL + * Scope: Package (physical package) + * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. + * perf code: 0x01 + * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL + * Scope: Package (physical package) + * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. + * perf code: 0x02 + * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,SKL + * Scope: Package (physical package) + * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. + * perf code: 0x03 + * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL + * Scope: Package (physical package) + * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter. + * perf code: 0x04 + * Available model: HSW ULT only + * Scope: Package (physical package) + * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter. + * perf code: 0x05 + * Available model: HSW ULT only + * Scope: Package (physical package) + * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. + * perf code: 0x06 + * Available model: HSW ULT only + * Scope: Package (physical package) + * + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/perf_event.h> +#include <asm/cpu_device_id.h> +#include "perf_event.h" + +#define DEFINE_CSTATE_FORMAT_ATTR(_var, _name, _format) \ +static ssize_t __cstate_##_var##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, \ + char *page) \ +{ \ + BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ + return sprintf(page, _format "\n"); \ +} \ +static struct kobj_attribute format_attr_##_var = \ + __ATTR(_name, 0444, __cstate_##_var##_show, NULL) + +static ssize_t cstate_get_attr_cpumask(struct device *dev, + struct device_attribute *attr, + char *buf); + +struct perf_cstate_msr { + u64 msr; + struct perf_pmu_events_attr *attr; + bool (*test)(int idx); +}; + + +/* cstate_core PMU */ + +static struct pmu cstate_core_pmu; +static bool has_cstate_core; + +enum perf_cstate_core_id { + /* + * cstate_core events + */ + PERF_CSTATE_CORE_C1_RES = 0, + PERF_CSTATE_CORE_C3_RES, + PERF_CSTATE_CORE_C6_RES, + PERF_CSTATE_CORE_C7_RES, + + PERF_CSTATE_CORE_EVENT_MAX, +}; + +bool test_core(int idx) +{ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || + boot_cpu_data.x86 != 6) + return false; + + switch (boot_cpu_data.x86_model) { + case 30: /* 45nm Nehalem */ + case 26: /* 45nm Nehalem-EP */ + case 46: /* 45nm Nehalem-EX */ + + case 37: /* 32nm Westmere */ + case 44: /* 32nm Westmere-EP */ + case 47: /* 32nm Westmere-EX */ + if (idx == PERF_CSTATE_CORE_C3_RES || + idx == PERF_CSTATE_CORE_C6_RES) + return true; + break; + case 42: /* 32nm SandyBridge */ + case 45: /* 32nm SandyBridge-E/EN/EP */ + + case 58: /* 22nm IvyBridge */ + case 62: /* 22nm IvyBridge-EP/EX */ + + case 60: /* 22nm Haswell Core */ + case 63: /* 22nm Haswell Server */ + case 69: /* 22nm Haswell ULT */ + case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */ + + case 61: /* 14nm Broadwell Core-M */ + case 86: /* 14nm Broadwell Xeon D */ + case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */ + case 79: /* 14nm Broadwell Server */ + + case 78: /* 14nm Skylake Mobile */ + case 94: /* 14nm Skylake Desktop */ + if (idx == PERF_CSTATE_CORE_C3_RES || + idx == PERF_CSTATE_CORE_C6_RES || + idx == PERF_CSTATE_CORE_C7_RES) + return true; + break; + case 55: /* 22nm Atom "Silvermont" */ + case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */ + case 76: /* 14nm Atom "Airmont" */ + if (idx == PERF_CSTATE_CORE_C1_RES || + idx == PERF_CSTATE_CORE_C6_RES) + return true; + break; + } + + return false; +} + +PMU_EVENT_ATTR_STRING(c1-residency, evattr_cstate_core_c1, "event=0x00"); +PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_core_c3, "event=0x01"); +PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_core_c6, "event=0x02"); +PMU_EVENT_ATTR_STRING(c7-residency, evattr_cstate_core_c7, "event=0x03"); + +static struct perf_cstate_msr core_msr[] = { + [PERF_CSTATE_CORE_C1_RES] = { MSR_CORE_C1_RES, &evattr_cstate_core_c1, test_core, }, + [PERF_CSTATE_CORE_C3_RES] = { MSR_CORE_C3_RESIDENCY, &evattr_cstate_core_c3, test_core, }, + [PERF_CSTATE_CORE_C6_RES] = { MSR_CORE_C6_RESIDENCY, &evattr_cstate_core_c6, test_core, }, + [PERF_CSTATE_CORE_C7_RES] = { MSR_CORE_C7_RESIDENCY, &evattr_cstate_core_c7, test_core, }, +}; + +static struct attribute *core_events_attrs[PERF_CSTATE_CORE_EVENT_MAX + 1] = { + NULL, +}; + +static struct attribute_group core_events_attr_group = { + .name = "events", + .attrs = core_events_attrs, +}; + +DEFINE_CSTATE_FORMAT_ATTR(core_event, event, "config:0-63"); +static struct attribute *core_format_attrs[] = { + &format_attr_core_event.attr, + NULL, +}; + +static struct attribute_group core_format_attr_group = { + .name = "format", + .attrs = core_format_attrs, +}; + +static cpumask_t cstate_core_cpu_mask; +static DEVICE_ATTR(cpumask, S_IRUGO, cstate_get_attr_cpumask, NULL); + +static struct attribute *cstate_cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static struct attribute_group cpumask_attr_group = { + .attrs = cstate_cpumask_attrs, +}; + +static const struct attribute_group *core_attr_groups[] = { + &core_events_attr_group, + &core_format_attr_group, + &cpumask_attr_group, + NULL, +}; + +/* cstate_core PMU end */ + + +/* cstate_pkg PMU */ + +static struct pmu cstate_pkg_pmu; +static bool has_cstate_pkg; + +enum perf_cstate_pkg_id { + /* + * cstate_pkg events + */ + PERF_CSTATE_PKG_C2_RES = 0, + PERF_CSTATE_PKG_C3_RES, + PERF_CSTATE_PKG_C6_RES, + PERF_CSTATE_PKG_C7_RES, + PERF_CSTATE_PKG_C8_RES, + PERF_CSTATE_PKG_C9_RES, + PERF_CSTATE_PKG_C10_RES, + + PERF_CSTATE_PKG_EVENT_MAX, +}; + +bool test_pkg(int idx) +{ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || + boot_cpu_data.x86 != 6) + return false; + + switch (boot_cpu_data.x86_model) { + case 30: /* 45nm Nehalem */ + case 26: /* 45nm Nehalem-EP */ + case 46: /* 45nm Nehalem-EX */ + + case 37: /* 32nm Westmere */ + case 44: /* 32nm Westmere-EP */ + case 47: /* 32nm Westmere-EX */ + if (idx == PERF_CSTATE_CORE_C3_RES || + idx == PERF_CSTATE_CORE_C6_RES || + idx == PERF_CSTATE_CORE_C7_RES) + return true; + break; + case 42: /* 32nm SandyBridge */ + case 45: /* 32nm SandyBridge-E/EN/EP */ + + case 58: /* 22nm IvyBridge */ + case 62: /* 22nm IvyBridge-EP/EX */ + + case 60: /* 22nm Haswell Core */ + case 63: /* 22nm Haswell Server */ + case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */ + + case 61: /* 14nm Broadwell Core-M */ + case 86: /* 14nm Broadwell Xeon D */ + case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */ + case 79: /* 14nm Broadwell Server */ + + case 78: /* 14nm Skylake Mobile */ + case 94: /* 14nm Skylake Desktop */ + if (idx == PERF_CSTATE_PKG_C2_RES || + idx == PERF_CSTATE_PKG_C3_RES || + idx == PERF_CSTATE_PKG_C6_RES || + idx == PERF_CSTATE_PKG_C7_RES) + return true; + break; + case 55: /* 22nm Atom "Silvermont" */ + case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */ + case 76: /* 14nm Atom "Airmont" */ + if (idx == PERF_CSTATE_CORE_C6_RES) + return true; + break; + case 69: /* 22nm Haswell ULT */ + if (idx == PERF_CSTATE_PKG_C2_RES || + idx == PERF_CSTATE_PKG_C3_RES || + idx == PERF_CSTATE_PKG_C6_RES || + idx == PERF_CSTATE_PKG_C7_RES || + idx == PERF_CSTATE_PKG_C8_RES || + idx == PERF_CSTATE_PKG_C9_RES || + idx == PERF_CSTATE_PKG_C10_RES) + return true; + break; + } + + return false; +} + +PMU_EVENT_ATTR_STRING(c2-residency, evattr_cstate_pkg_c2, "event=0x00"); +PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_pkg_c3, "event=0x01"); +PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_pkg_c6, "event=0x02"); +PMU_EVENT_ATTR_STRING(c7-residency, evattr_cstate_pkg_c7, "event=0x03"); +PMU_EVENT_ATTR_STRING(c8-residency, evattr_cstate_pkg_c8, "event=0x04"); +PMU_EVENT_ATTR_STRING(c9-residency, evattr_cstate_pkg_c9, "event=0x05"); +PMU_EVENT_ATTR_STRING(c10-residency, evattr_cstate_pkg_c10, "event=0x06"); + +static struct perf_cstate_msr pkg_msr[] = { + [PERF_CSTATE_PKG_C2_RES] = { MSR_PKG_C2_RESIDENCY, &evattr_cstate_pkg_c2, test_pkg, }, + [PERF_CSTATE_PKG_C3_RES] = { MSR_PKG_C3_RESIDENCY, &evattr_cstate_pkg_c3, test_pkg, }, + [PERF_CSTATE_PKG_C6_RES] = { MSR_PKG_C6_RESIDENCY, &evattr_cstate_pkg_c6, test_pkg, }, + [PERF_CSTATE_PKG_C7_RES] = { MSR_PKG_C7_RESIDENCY, &evattr_cstate_pkg_c7, test_pkg, }, + [PERF_CSTATE_PKG_C8_RES] = { MSR_PKG_C8_RESIDENCY, &evattr_cstate_pkg_c8, test_pkg, }, + [PERF_CSTATE_PKG_C9_RES] = { MSR_PKG_C9_RESIDENCY, &evattr_cstate_pkg_c9, test_pkg, }, + [PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY, &evattr_cstate_pkg_c10, test_pkg, }, +}; + +static struct attribute *pkg_events_attrs[PERF_CSTATE_PKG_EVENT_MAX + 1] = { + NULL, +}; + +static struct attribute_group pkg_events_attr_group = { + .name = "events", + .attrs = pkg_events_attrs, +}; + +DEFINE_CSTATE_FORMAT_ATTR(pkg_event, event, "config:0-63"); +static struct attribute *pkg_format_attrs[] = { + &format_attr_pkg_event.attr, + NULL, +}; +static struct attribute_group pkg_format_attr_group = { + .name = "format", + .attrs = pkg_format_attrs, +}; + +static cpumask_t cstate_pkg_cpu_mask; + +static const struct attribute_group *pkg_attr_groups[] = { + &pkg_events_attr_group, + &pkg_format_attr_group, + &cpumask_attr_group, + NULL, +}; + +/* cstate_pkg PMU end*/ + +static ssize_t cstate_get_attr_cpumask(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct pmu *pmu = dev_get_drvdata(dev); + + if (pmu == &cstate_core_pmu) + return cpumap_print_to_pagebuf(true, buf, &cstate_core_cpu_mask); + else if (pmu == &cstate_pkg_pmu) + return cpumap_print_to_pagebuf(true, buf, &cstate_pkg_cpu_mask); + else + return 0; +} + +static int cstate_pmu_event_init(struct perf_event *event) +{ + u64 cfg = event->attr.config; + int ret = 0; + + if (event->attr.type != event->pmu->type) + return -ENOENT; + + /* unsupported modes and filters */ + if (event->attr.exclude_user || + event->attr.exclude_kernel || + event->attr.exclude_hv || + event->attr.exclude_idle || + event->attr.exclude_host || + event->attr.exclude_guest || + event->attr.sample_period) /* no sampling */ + return -EINVAL; + + if (event->pmu == &cstate_core_pmu) { + if (cfg >= PERF_CSTATE_CORE_EVENT_MAX) + return -EINVAL; + if (!core_msr[cfg].attr) + return -EINVAL; + event->hw.event_base = core_msr[cfg].msr; + } else if (event->pmu == &cstate_pkg_pmu) { + if (cfg >= PERF_CSTATE_PKG_EVENT_MAX) + return -EINVAL; + if (!pkg_msr[cfg].attr) + return -EINVAL; + event->hw.event_base = pkg_msr[cfg].msr; + } else + return -ENOENT; + + /* must be done before validate_group */ + event->hw.config = cfg; + event->hw.idx = -1; + + return ret; +} + +static inline u64 cstate_pmu_read_counter(struct perf_event *event) +{ + u64 val; + + rdmsrl(event->hw.event_base, val); + return val; +} + +static void cstate_pmu_event_update(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + u64 prev_raw_count, new_raw_count; + +again: + prev_raw_count = local64_read(&hwc->prev_count); + new_raw_count = cstate_pmu_read_counter(event); + + if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, + new_raw_count) != prev_raw_count) + goto again; + + local64_add(new_raw_count - prev_raw_count, &event->count); +} + +static void cstate_pmu_event_start(struct perf_event *event, int mode) +{ + local64_set(&event->hw.prev_count, cstate_pmu_read_counter(event)); +} + +static void cstate_pmu_event_stop(struct perf_event *event, int mode) +{ + cstate_pmu_event_update(event); +} + +static void cstate_pmu_event_del(struct perf_event *event, int mode) +{ + cstate_pmu_event_stop(event, PERF_EF_UPDATE); +} + +static int cstate_pmu_event_add(struct perf_event *event, int mode) +{ + if (mode & PERF_EF_START) + cstate_pmu_event_start(event, mode); + + return 0; +} + +static void cstate_cpu_exit(int cpu) +{ + int i, id, target; + + /* cpu exit for cstate core */ + if (has_cstate_core) { + id = topology_core_id(cpu); + target = -1; + + for_each_online_cpu(i) { + if (i == cpu) + continue; + if (id == topology_core_id(i)) { + target = i; + break; + } + } + if (cpumask_test_and_clear_cpu(cpu, &cstate_core_cpu_mask) && target >= 0) + cpumask_set_cpu(target, &cstate_core_cpu_mask); + WARN_ON(cpumask_empty(&cstate_core_cpu_mask)); + if (target >= 0) + perf_pmu_migrate_context(&cstate_core_pmu, cpu, target); + } + + /* cpu exit for cstate pkg */ + if (has_cstate_pkg) { + id = topology_physical_package_id(cpu); + target = -1; + + for_each_online_cpu(i) { + if (i == cpu) + continue; + if (id == topology_physical_package_id(i)) { + target = i; + break; + } + } + if (cpumask_test_and_clear_cpu(cpu, &cstate_pkg_cpu_mask) && target >= 0) + cpumask_set_cpu(target, &cstate_pkg_cpu_mask); + WARN_ON(cpumask_empty(&cstate_pkg_cpu_mask)); + if (target >= 0) + perf_pmu_migrate_context(&cstate_pkg_pmu, cpu, target); + } +} + +static void cstate_cpu_init(int cpu) +{ + int i, id; + + /* cpu init for cstate core */ + if (has_cstate_core) { + id = topology_core_id(cpu); + for_each_cpu(i, &cstate_core_cpu_mask) { + if (id == topology_core_id(i)) + break; + } + if (i >= nr_cpu_ids) + cpumask_set_cpu(cpu, &cstate_core_cpu_mask); + } + + /* cpu init for cstate pkg */ + if (has_cstate_pkg) { + id = topology_physical_package_id(cpu); + for_each_cpu(i, &cstate_pkg_cpu_mask) { + if (id == topology_physical_package_id(i)) + break; + } + if (i >= nr_cpu_ids) + cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask); + } +} + +static int cstate_cpu_notifier(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + unsigned int cpu = (long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_UP_PREPARE: + break; + case CPU_STARTING: + cstate_cpu_init(cpu); + break; + case CPU_UP_CANCELED: + case CPU_DYING: + break; + case CPU_ONLINE: + case CPU_DEAD: + break; + case CPU_DOWN_PREPARE: + cstate_cpu_exit(cpu); + break; + default: + break; + } + + return NOTIFY_OK; +} + +/* + * Probe the cstate events and insert the available one into sysfs attrs + * Return false if there is no available events. + */ +static bool cstate_probe_msr(struct perf_cstate_msr *msr, + struct attribute **events_attrs, + int max_event_nr) +{ + int i, j = 0; + u64 val; + + /* Probe the cstate events. */ + for (i = 0; i < max_event_nr; i++) { + if (!msr[i].test(i) || rdmsrl_safe(msr[i].msr, &val)) + msr[i].attr = NULL; + } + + /* List remaining events in the sysfs attrs. */ + for (i = 0; i < max_event_nr; i++) { + if (msr[i].attr) + events_attrs[j++] = &msr[i].attr->attr.attr; + } + events_attrs[j] = NULL; + + return (j > 0) ? true : false; +} + +static int __init cstate_init(void) +{ + /* SLM has different MSR for PKG C6 */ + switch (boot_cpu_data.x86_model) { + case 55: + case 76: + case 77: + pkg_msr[PERF_CSTATE_PKG_C6_RES].msr = MSR_PKG_C7_RESIDENCY; + } + + if (cstate_probe_msr(core_msr, core_events_attrs, PERF_CSTATE_CORE_EVENT_MAX)) + has_cstate_core = true; + + if (cstate_probe_msr(pkg_msr, pkg_events_attrs, PERF_CSTATE_PKG_EVENT_MAX)) + has_cstate_pkg = true; + + return (has_cstate_core || has_cstate_pkg) ? 0 : -ENODEV; +} + +static void __init cstate_cpumask_init(void) +{ + int cpu; + + cpu_notifier_register_begin(); + + for_each_online_cpu(cpu) + cstate_cpu_init(cpu); + + __perf_cpu_notifier(cstate_cpu_notifier); + + cpu_notifier_register_done(); +} + +static struct pmu cstate_core_pmu = { + .attr_groups = core_attr_groups, + .name = "cstate_core", + .task_ctx_nr = perf_invalid_context, + .event_init = cstate_pmu_event_init, + .add = cstate_pmu_event_add, /* must have */ + .del = cstate_pmu_event_del, /* must have */ + .start = cstate_pmu_event_start, + .stop = cstate_pmu_event_stop, + .read = cstate_pmu_event_update, + .capabilities = PERF_PMU_CAP_NO_INTERRUPT, +}; + +static struct pmu cstate_pkg_pmu = { + .attr_groups = pkg_attr_groups, + .name = "cstate_pkg", + .task_ctx_nr = perf_invalid_context, + .event_init = cstate_pmu_event_init, + .add = cstate_pmu_event_add, /* must have */ + .del = cstate_pmu_event_del, /* must have */ + .start = cstate_pmu_event_start, + .stop = cstate_pmu_event_stop, + .read = cstate_pmu_event_update, + .capabilities = PERF_PMU_CAP_NO_INTERRUPT, +}; + +static void __init cstate_pmus_register(void) +{ + int err; + + if (has_cstate_core) { + err = perf_pmu_register(&cstate_core_pmu, cstate_core_pmu.name, -1); + if (WARN_ON(err)) + pr_info("Failed to register PMU %s error %d\n", + cstate_core_pmu.name, err); + } + + if (has_cstate_pkg) { + err = perf_pmu_register(&cstate_pkg_pmu, cstate_pkg_pmu.name, -1); + if (WARN_ON(err)) + pr_info("Failed to register PMU %s error %d\n", + cstate_pkg_pmu.name, err); + } +} + +static int __init cstate_pmu_init(void) +{ + int err; + + if (cpu_has_hypervisor) + return -ENODEV; + + err = cstate_init(); + if (err) + return err; + + cstate_cpumask_init(); + + cstate_pmus_register(); + + return 0; +} + +device_initcall(cstate_pmu_init); diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 71fc40238843..10602f0a438f 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -224,6 +224,19 @@ union hsw_tsx_tuning { #define PEBS_HSW_TSX_FLAGS 0xff00000000ULL +/* Same as HSW, plus TSC */ + +struct pebs_record_skl { + u64 flags, ip; + u64 ax, bx, cx, dx; + u64 si, di, bp, sp; + u64 r8, r9, r10, r11; + u64 r12, r13, r14, r15; + u64 status, dla, dse, lat; + u64 real_ip, tsx_tuning; + u64 tsc; +}; + void init_debug_store_on_cpu(int cpu) { struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; @@ -497,10 +510,11 @@ int intel_pmu_drain_bts_buffer(void) u64 flags; }; struct perf_event *event = cpuc->events[INTEL_PMC_IDX_FIXED_BTS]; - struct bts_record *at, *top; + struct bts_record *at, *base, *top; struct perf_output_handle handle; struct perf_event_header header; struct perf_sample_data data; + unsigned long skip = 0; struct pt_regs regs; if (!event) @@ -509,10 +523,10 @@ int intel_pmu_drain_bts_buffer(void) if (!x86_pmu.bts_active) return 0; - at = (struct bts_record *)(unsigned long)ds->bts_buffer_base; - top = (struct bts_record *)(unsigned long)ds->bts_index; + base = (struct bts_record *)(unsigned long)ds->bts_buffer_base; + top = (struct bts_record *)(unsigned long)ds->bts_index; - if (top <= at) + if (top <= base) return 0; memset(®s, 0, sizeof(regs)); @@ -522,16 +536,43 @@ int intel_pmu_drain_bts_buffer(void) perf_sample_data_init(&data, 0, event->hw.last_period); /* + * BTS leaks kernel addresses in branches across the cpl boundary, + * such as traps or system calls, so unless the user is asking for + * kernel tracing (and right now it's not possible), we'd need to + * filter them out. But first we need to count how many of those we + * have in the current batch. This is an extra O(n) pass, however, + * it's much faster than the other one especially considering that + * n <= 2560 (BTS_BUFFER_SIZE / BTS_RECORD_SIZE * 15/16; see the + * alloc_bts_buffer()). + */ + for (at = base; at < top; at++) { + /* + * Note that right now *this* BTS code only works if + * attr::exclude_kernel is set, but let's keep this extra + * check here in case that changes. + */ + if (event->attr.exclude_kernel && + (kernel_ip(at->from) || kernel_ip(at->to))) + skip++; + } + + /* * Prepare a generic sample, i.e. fill in the invariant fields. * We will overwrite the from and to address before we output * the sample. */ perf_prepare_sample(&header, &data, event, ®s); - if (perf_output_begin(&handle, event, header.size * (top - at))) + if (perf_output_begin(&handle, event, header.size * + (top - base - skip))) return 1; - for (; at < top; at++) { + for (at = base; at < top; at++) { + /* Filter out any records that contain kernel addresses. */ + if (event->attr.exclude_kernel && + (kernel_ip(at->from) || kernel_ip(at->to))) + continue; + data.ip = at->from; data.addr = at->to; @@ -579,6 +620,8 @@ struct event_constraint intel_atom_pebs_event_constraints[] = { INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01), + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0x1), EVENT_CONSTRAINT_END }; @@ -645,6 +688,8 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = { INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -659,6 +704,8 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x01cd, 0xf), /* MEM_TRANS_RETIRED.* */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ @@ -675,6 +722,29 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; +struct event_constraint intel_skl_pebs_event_constraints[] = { + INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x2), /* INST_RETIRED.PREC_DIST */ + /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), + /* INST_RETIRED.TOTAL_CYCLES_PS (inv=1, cmask=16) (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f), + INTEL_PLD_CONSTRAINT(0x1cd, 0xf), /* MEM_TRANS_RETIRED.* */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x22d0, 0xf), /* MEM_INST_RETIRED.LOCK_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd1, 0xf), /* MEM_LOAD_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd2, 0xf), /* MEM_LOAD_L3_HIT_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd3, 0xf), /* MEM_LOAD_L3_MISS_RETIRED.* */ + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), + EVENT_CONSTRAINT_END +}; + struct event_constraint *intel_pebs_constraints(struct perf_event *event) { struct event_constraint *c; @@ -754,6 +824,11 @@ 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; + bool large_pebs = ds->pebs_interrupt_threshold > + ds->pebs_buffer_base + x86_pmu.pebs_record_size; + + if (large_pebs) + intel_pmu_drain_pebs_buffer(); cpuc->pebs_enabled &= ~(1ULL << hwc->idx); @@ -762,12 +837,8 @@ 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 (large_pebs && !pebs_is_enabled(cpuc)) + perf_sched_cb_dec(event->ctx->pmu); if (cpuc->enabled) wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); @@ -885,7 +956,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) return 0; } -static inline u64 intel_hsw_weight(struct pebs_record_hsw *pebs) +static inline u64 intel_hsw_weight(struct pebs_record_skl *pebs) { if (pebs->tsx_tuning) { union hsw_tsx_tuning tsx = { .value = pebs->tsx_tuning }; @@ -894,7 +965,7 @@ static inline u64 intel_hsw_weight(struct pebs_record_hsw *pebs) return 0; } -static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs) +static inline u64 intel_hsw_transaction(struct pebs_record_skl *pebs) { u64 txn = (pebs->tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32; @@ -918,7 +989,7 @@ static void setup_pebs_sample_data(struct perf_event *event, * unconditionally access the 'extra' entries. */ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - struct pebs_record_hsw *pebs = __pebs; + struct pebs_record_skl *pebs = __pebs; u64 sample_type; int fll, fst, dsrc; int fl = event->hw.flags; @@ -1016,6 +1087,16 @@ static void setup_pebs_sample_data(struct perf_event *event, data->txn = intel_hsw_transaction(pebs); } + /* + * v3 supplies an accurate time stamp, so we use that + * for the time stamp. + * + * We can only do this for the default trace clock. + */ + if (x86_pmu.intel_cap.pebs_format >= 3 && + event->attr.use_clockid == 0) + data->time = native_sched_clock_from_tsc(pebs->tsc); + if (has_branch_stack(event)) data->br_stack = &cpuc->lbr_stack; } @@ -1027,6 +1108,13 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit) void *at; u64 pebs_status; + /* + * fmt0 does not have a status bitfield (does not use + * perf_record_nhm format) + */ + if (x86_pmu.intel_cap.pebs_format < 1) + return base; + if (base == NULL) return NULL; @@ -1112,7 +1200,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) if (!event->attr.precise_ip) return; - n = (top - at) / x86_pmu.pebs_record_size; + n = top - at; if (n <= 0) return; @@ -1142,6 +1230,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) for (at = base; at < top; at += x86_pmu.pebs_record_size) { struct pebs_record_nhm *p = at; + u64 pebs_status; /* PEBS v3 has accurate status bits */ if (x86_pmu.intel_cap.pebs_format >= 3) { @@ -1152,12 +1241,26 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) continue; } - bit = find_first_bit((unsigned long *)&p->status, + pebs_status = p->status & cpuc->pebs_enabled; + pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1; + + /* + * On some CPUs the PEBS status can be zero when PEBS is + * racing with clearing of GLOBAL_STATUS. + * + * Normally we would drop that record, but in the + * case when there is only a single active PEBS event + * we can assume it's for that event. + */ + if (!pebs_status && cpuc->pebs_enabled && + !(cpuc->pebs_enabled & (cpuc->pebs_enabled-1))) + pebs_status = cpuc->pebs_enabled; + + bit = find_first_bit((unsigned long *)&pebs_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 @@ -1172,27 +1275,21 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) * 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; - } + if (p->status != (1ULL << bit)) { + for_each_set_bit(i, (unsigned long *)&pebs_status, + x86_pmu.max_pebs_events) + error[i]++; + continue; } + counts[bit]++; } 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); @@ -1245,6 +1342,14 @@ void __init intel_ds_init(void) x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm; break; + case 3: + pr_cont("PEBS fmt3%c, ", pebs_type); + x86_pmu.pebs_record_size = + sizeof(struct pebs_record_skl); + x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm; + x86_pmu.free_running_flags |= PERF_SAMPLE_TIME; + break; + default: printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type); x86_pmu.pebs = 0; diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index 452a7bd2dedb..653f88d25987 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -13,7 +13,8 @@ enum { LBR_FORMAT_EIP = 0x02, LBR_FORMAT_EIP_FLAGS = 0x03, LBR_FORMAT_EIP_FLAGS2 = 0x04, - LBR_FORMAT_MAX_KNOWN = LBR_FORMAT_EIP_FLAGS2, + LBR_FORMAT_INFO = 0x05, + LBR_FORMAT_MAX_KNOWN = LBR_FORMAT_INFO, }; static enum { @@ -41,6 +42,13 @@ static enum { #define LBR_FAR_BIT 8 /* do not capture far branches */ #define LBR_CALL_STACK_BIT 9 /* enable call stack */ +/* + * Following bit only exists in Linux; we mask it out before writing it to + * the actual MSR. But it helps the constraint perf code to understand + * that this is a separate configuration. + */ +#define LBR_NO_INFO_BIT 63 /* don't read LBR_INFO. */ + #define LBR_KERNEL (1 << LBR_KERNEL_BIT) #define LBR_USER (1 << LBR_USER_BIT) #define LBR_JCC (1 << LBR_JCC_BIT) @@ -51,6 +59,7 @@ static enum { #define LBR_IND_JMP (1 << LBR_IND_JMP_BIT) #define LBR_FAR (1 << LBR_FAR_BIT) #define LBR_CALL_STACK (1 << LBR_CALL_STACK_BIT) +#define LBR_NO_INFO (1ULL << LBR_NO_INFO_BIT) #define LBR_PLM (LBR_KERNEL | LBR_USER) @@ -140,13 +149,20 @@ static void __intel_pmu_lbr_enable(bool pmi) u64 debugctl, lbr_select = 0, orig_debugctl; /* + * No need to unfreeze manually, as v4 can do that as part + * of the GLOBAL_STATUS ack. + */ + if (pmi && x86_pmu.version >= 4) + return; + + /* * No need to reprogram LBR_SELECT in a PMI, as it * did not change. */ - if (cpuc->lbr_sel && !pmi) { - lbr_select = cpuc->lbr_sel->config; + if (cpuc->lbr_sel) + lbr_select = cpuc->lbr_sel->config & x86_pmu.lbr_sel_mask; + if (!pmi && cpuc->lbr_sel) wrmsrl(MSR_LBR_SELECT, lbr_select); - } rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); orig_debugctl = debugctl; @@ -186,6 +202,8 @@ static void intel_pmu_lbr_reset_64(void) for (i = 0; i < x86_pmu.lbr_nr; i++) { wrmsrl(x86_pmu.lbr_from + i, 0); wrmsrl(x86_pmu.lbr_to + i, 0); + if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) + wrmsrl(MSR_LBR_INFO_0 + i, 0); } } @@ -229,12 +247,15 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx) } mask = x86_pmu.lbr_nr - 1; - tos = intel_pmu_lbr_tos(); - for (i = 0; i < x86_pmu.lbr_nr; i++) { + tos = task_ctx->tos; + for (i = 0; i < tos; i++) { lbr_idx = (tos - i) & mask; wrmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]); wrmsrl(x86_pmu.lbr_to + lbr_idx, task_ctx->lbr_to[i]); + if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) + wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]); } + wrmsrl(x86_pmu.lbr_tos, tos); task_ctx->lbr_stack_state = LBR_NONE; } @@ -251,11 +272,14 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx) mask = x86_pmu.lbr_nr - 1; tos = intel_pmu_lbr_tos(); - for (i = 0; i < x86_pmu.lbr_nr; i++) { + for (i = 0; i < tos; i++) { lbr_idx = (tos - i) & mask; rdmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]); rdmsrl(x86_pmu.lbr_to + lbr_idx, task_ctx->lbr_to[i]); + if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) + rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]); } + task_ctx->tos = tos; task_ctx->lbr_stack_state = LBR_VALID; } @@ -406,21 +430,40 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) */ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) { + bool need_info = false; unsigned long mask = x86_pmu.lbr_nr - 1; int lbr_format = x86_pmu.intel_cap.lbr_format; u64 tos = intel_pmu_lbr_tos(); int i; int out = 0; + int num = x86_pmu.lbr_nr; - for (i = 0; i < x86_pmu.lbr_nr; i++) { + if (cpuc->lbr_sel) { + need_info = !(cpuc->lbr_sel->config & LBR_NO_INFO); + if (cpuc->lbr_sel->config & LBR_CALL_STACK) + num = tos; + } + + for (i = 0; i < num; i++) { unsigned long lbr_idx = (tos - i) & mask; u64 from, to, mis = 0, pred = 0, in_tx = 0, abort = 0; int skip = 0; + u16 cycles = 0; int lbr_flags = lbr_desc[lbr_format]; rdmsrl(x86_pmu.lbr_from + lbr_idx, from); rdmsrl(x86_pmu.lbr_to + lbr_idx, to); + if (lbr_format == LBR_FORMAT_INFO && need_info) { + u64 info; + + rdmsrl(MSR_LBR_INFO_0 + lbr_idx, info); + mis = !!(info & LBR_INFO_MISPRED); + pred = !mis; + in_tx = !!(info & LBR_INFO_IN_TX); + abort = !!(info & LBR_INFO_ABORT); + cycles = (info & LBR_INFO_CYCLES); + } if (lbr_flags & LBR_EIP_FLAGS) { mis = !!(from & LBR_FROM_FLAG_MISPRED); pred = !mis; @@ -450,6 +493,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) cpuc->lbr_entries[out].predicted = pred; cpuc->lbr_entries[out].in_tx = in_tx; cpuc->lbr_entries[out].abort = abort; + cpuc->lbr_entries[out].cycles = cycles; cpuc->lbr_entries[out].reserved = 0; out++; } @@ -525,6 +569,8 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event) if (br_type & PERF_SAMPLE_BRANCH_IND_JUMP) mask |= X86_BR_IND_JMP; + if (br_type & PERF_SAMPLE_BRANCH_CALL) + mask |= X86_BR_CALL | X86_BR_ZERO_CALL; /* * stash actual user request into reg, it may * be used by fixup code for some CPU @@ -556,6 +602,7 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) if (v != LBR_IGN) mask |= v; } + reg = &event->hw.branch_reg; reg->idx = EXTRA_REG_LBR; @@ -566,6 +613,11 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) */ reg->config = mask ^ x86_pmu.lbr_sel_mask; + if ((br_type & PERF_SAMPLE_BRANCH_NO_CYCLES) && + (br_type & PERF_SAMPLE_BRANCH_NO_FLAGS) && + (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)) + reg->config |= LBR_NO_INFO; + return 0; } @@ -860,6 +912,7 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { [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, + [PERF_SAMPLE_BRANCH_CALL_SHIFT] = LBR_REL_CALL, }; static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { @@ -875,6 +928,7 @@ static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { [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, + [PERF_SAMPLE_BRANCH_CALL_SHIFT] = LBR_REL_CALL, }; /* core */ @@ -947,6 +1001,26 @@ void intel_pmu_lbr_init_hsw(void) pr_cont("16-deep LBR, "); } +/* skylake */ +__init void intel_pmu_lbr_init_skl(void) +{ + x86_pmu.lbr_nr = 32; + x86_pmu.lbr_tos = MSR_LBR_TOS; + x86_pmu.lbr_from = MSR_LBR_NHM_FROM; + x86_pmu.lbr_to = MSR_LBR_NHM_TO; + + x86_pmu.lbr_sel_mask = LBR_SEL_MASK; + x86_pmu.lbr_sel_map = hsw_lbr_sel_map; + + /* + * SW branch filter usage: + * - support syscall, sysret capture. + * That requires LBR_FAR but that means far + * jmp need to be filtered out + */ + pr_cont("32-deep LBR, "); +} + /* atom */ void __init intel_pmu_lbr_init_atom(void) { @@ -972,3 +1046,17 @@ void __init intel_pmu_lbr_init_atom(void) */ pr_cont("8-deep LBR, "); } + +/* Knights Landing */ +void intel_pmu_lbr_init_knl(void) +{ + x86_pmu.lbr_nr = 8; + x86_pmu.lbr_tos = MSR_LBR_TOS; + x86_pmu.lbr_from = MSR_LBR_NHM_FROM; + x86_pmu.lbr_to = MSR_LBR_NHM_TO; + + x86_pmu.lbr_sel_mask = LBR_SEL_MASK; + x86_pmu.lbr_sel_map = snb_lbr_sel_map; + + pr_cont("8-deep LBR, "); +} diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c index 183de719628d..c0bbd1033b7c 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_pt.c +++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c @@ -27,6 +27,7 @@ #include <asm/perf_event.h> #include <asm/insn.h> #include <asm/io.h> +#include <asm/intel_pt.h> #include "perf_event.h" #include "intel_pt.h" @@ -65,15 +66,21 @@ static struct pt_cap_desc { } pt_caps[] = { PT_CAP(max_subleaf, 0, CR_EAX, 0xffffffff), PT_CAP(cr3_filtering, 0, CR_EBX, BIT(0)), + PT_CAP(psb_cyc, 0, CR_EBX, BIT(1)), + PT_CAP(mtc, 0, CR_EBX, BIT(3)), PT_CAP(topa_output, 0, CR_ECX, BIT(0)), PT_CAP(topa_multiple_entries, 0, CR_ECX, BIT(1)), + PT_CAP(single_range_output, 0, CR_ECX, BIT(2)), PT_CAP(payloads_lip, 0, CR_ECX, BIT(31)), + PT_CAP(mtc_periods, 1, CR_EAX, 0xffff0000), + PT_CAP(cycle_thresholds, 1, CR_EBX, 0xffff), + PT_CAP(psb_periods, 1, CR_EBX, 0xffff0000), }; static u32 pt_cap_get(enum pt_capabilities cap) { struct pt_cap_desc *cd = &pt_caps[cap]; - u32 c = pt_pmu.caps[cd->leaf * 4 + cd->reg]; + u32 c = pt_pmu.caps[cd->leaf * PT_CPUID_REGS_NUM + cd->reg]; unsigned int shift = __ffs(cd->mask); return (c & cd->mask) >> shift; @@ -94,12 +101,22 @@ static struct attribute_group pt_cap_group = { .name = "caps", }; +PMU_FORMAT_ATTR(cyc, "config:1" ); +PMU_FORMAT_ATTR(mtc, "config:9" ); PMU_FORMAT_ATTR(tsc, "config:10" ); PMU_FORMAT_ATTR(noretcomp, "config:11" ); +PMU_FORMAT_ATTR(mtc_period, "config:14-17" ); +PMU_FORMAT_ATTR(cyc_thresh, "config:19-22" ); +PMU_FORMAT_ATTR(psb_period, "config:24-27" ); static struct attribute *pt_formats_attr[] = { + &format_attr_cyc.attr, + &format_attr_mtc.attr, &format_attr_tsc.attr, &format_attr_noretcomp.attr, + &format_attr_mtc_period.attr, + &format_attr_cyc_thresh.attr, + &format_attr_psb_period.attr, NULL, }; @@ -123,16 +140,13 @@ static int __init pt_pmu_hw_init(void) long i; attrs = NULL; - ret = -ENODEV; - if (!test_cpu_cap(&boot_cpu_data, X86_FEATURE_INTEL_PT)) - goto fail; for (i = 0; i < PT_CPUID_LEAVES; i++) { cpuid_count(20, i, - &pt_pmu.caps[CR_EAX + i*4], - &pt_pmu.caps[CR_EBX + i*4], - &pt_pmu.caps[CR_ECX + i*4], - &pt_pmu.caps[CR_EDX + i*4]); + &pt_pmu.caps[CR_EAX + i*PT_CPUID_REGS_NUM], + &pt_pmu.caps[CR_EBX + i*PT_CPUID_REGS_NUM], + &pt_pmu.caps[CR_ECX + i*PT_CPUID_REGS_NUM], + &pt_pmu.caps[CR_EDX + i*PT_CPUID_REGS_NUM]); } ret = -ENOMEM; @@ -170,15 +184,65 @@ fail: return ret; } -#define PT_CONFIG_MASK (RTIT_CTL_TSC_EN | RTIT_CTL_DISRETC) +#define RTIT_CTL_CYC_PSB (RTIT_CTL_CYCLEACC | \ + RTIT_CTL_CYC_THRESH | \ + RTIT_CTL_PSB_FREQ) + +#define RTIT_CTL_MTC (RTIT_CTL_MTC_EN | \ + RTIT_CTL_MTC_RANGE) + +#define PT_CONFIG_MASK (RTIT_CTL_TSC_EN | \ + RTIT_CTL_DISRETC | \ + RTIT_CTL_CYC_PSB | \ + RTIT_CTL_MTC) static bool pt_event_valid(struct perf_event *event) { u64 config = event->attr.config; + u64 allowed, requested; if ((config & PT_CONFIG_MASK) != config) return false; + if (config & RTIT_CTL_CYC_PSB) { + if (!pt_cap_get(PT_CAP_psb_cyc)) + return false; + + allowed = pt_cap_get(PT_CAP_psb_periods); + requested = (config & RTIT_CTL_PSB_FREQ) >> + RTIT_CTL_PSB_FREQ_OFFSET; + if (requested && (!(allowed & BIT(requested)))) + return false; + + allowed = pt_cap_get(PT_CAP_cycle_thresholds); + requested = (config & RTIT_CTL_CYC_THRESH) >> + RTIT_CTL_CYC_THRESH_OFFSET; + if (requested && (!(allowed & BIT(requested)))) + return false; + } + + if (config & RTIT_CTL_MTC) { + /* + * In the unlikely case that CPUID lists valid mtc periods, + * but not the mtc capability, drop out here. + * + * Spec says that setting mtc period bits while mtc bit in + * CPUID is 0 will #GP, so better safe than sorry. + */ + if (!pt_cap_get(PT_CAP_mtc)) + return false; + + allowed = pt_cap_get(PT_CAP_mtc_periods); + if (!allowed) + return false; + + requested = (config & RTIT_CTL_MTC_RANGE) >> + RTIT_CTL_MTC_RANGE_OFFSET; + + if (!(allowed & BIT(requested))) + return false; + } + return true; } @@ -191,6 +255,11 @@ static void pt_config(struct perf_event *event) { u64 reg; + if (!event->hw.itrace_started) { + event->hw.itrace_started = 1; + wrmsrl(MSR_IA32_RTIT_STATUS, 0); + } + reg = RTIT_CTL_TOPA | RTIT_CTL_BRANCH_EN | RTIT_CTL_TRACEEN; if (!event->attr.exclude_kernel) @@ -910,7 +979,6 @@ void intel_pt_interrupt(void) pt_config_buffer(buf->cur->table, buf->cur_idx, buf->output_off); - wrmsrl(MSR_IA32_RTIT_STATUS, 0); pt_config(event); } } @@ -934,7 +1002,6 @@ static void pt_event_start(struct perf_event *event, int mode) pt_config_buffer(buf->cur->table, buf->cur_idx, buf->output_off); - wrmsrl(MSR_IA32_RTIT_STATUS, 0); pt_config(event); } @@ -1056,11 +1123,23 @@ static int pt_event_init(struct perf_event *event) return 0; } +void cpu_emergency_stop_pt(void) +{ + struct pt *pt = this_cpu_ptr(&pt_ctx); + + if (pt->handle.event) + pt_event_stop(pt->handle.event, PERF_EF_UPDATE); +} + static __init int pt_init(void) { int ret, cpu, prior_warn = 0; BUILD_BUG_ON(sizeof(struct topa) > PAGE_SIZE); + + if (!test_cpu_cap(&boot_cpu_data, X86_FEATURE_INTEL_PT)) + return -ENODEV; + get_online_cpus(); for_each_online_cpu(cpu) { u64 ctl; diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c index 5cbd4e64feb5..24a351ad628d 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -63,7 +63,7 @@ #define INTEL_RAPL_PP1 0x4 /* pseudo-encoding */ #define NR_RAPL_DOMAINS 0x4 -static const char *rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { +static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { "pp0-core", "package", "dram", @@ -86,6 +86,10 @@ static const char *rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { 1<<RAPL_IDX_RAM_NRG_STAT|\ 1<<RAPL_IDX_PP1_NRG_STAT) +/* Knights Landing has PKG, RAM */ +#define RAPL_IDX_KNL (1<<RAPL_IDX_PKG_NRG_STAT|\ + 1<<RAPL_IDX_RAM_NRG_STAT) + /* * event code: LSB 8 bits, passed in attr->config * any other bit is reserved @@ -103,19 +107,13 @@ static ssize_t __rapl_##_var##_show(struct kobject *kobj, \ static struct kobj_attribute format_attr_##_var = \ __ATTR(_name, 0444, __rapl_##_var##_show, NULL) -#define RAPL_EVENT_DESC(_name, _config) \ -{ \ - .attr = __ATTR(_name, 0444, rapl_event_show, NULL), \ - .config = _config, \ -} - #define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */ -#define RAPL_EVENT_ATTR_STR(_name, v, str) \ -static struct perf_pmu_events_attr event_attr_##v = { \ - .attr = __ATTR(_name, 0444, rapl_sysfs_show, NULL), \ - .id = 0, \ - .event_str = str, \ +#define RAPL_EVENT_ATTR_STR(_name, v, str) \ +static struct perf_pmu_events_attr event_attr_##v = { \ + .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \ + .id = 0, \ + .event_str = str, \ }; struct rapl_pmu { @@ -407,19 +405,6 @@ static struct attribute_group rapl_pmu_attr_group = { .attrs = rapl_pmu_attrs, }; -static ssize_t rapl_sysfs_show(struct device *dev, - struct device_attribute *attr, - char *page) -{ - struct perf_pmu_events_attr *pmu_attr = \ - container_of(attr, struct perf_pmu_events_attr, attr); - - if (pmu_attr->event_str) - return sprintf(page, "%s", pmu_attr->event_str); - - return 0; -} - RAPL_EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01"); RAPL_EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02"); RAPL_EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03"); @@ -486,6 +471,18 @@ static struct attribute *rapl_events_hsw_attr[] = { NULL, }; +static struct attribute *rapl_events_knl_attr[] = { + EVENT_PTR(rapl_pkg), + EVENT_PTR(rapl_ram), + + EVENT_PTR(rapl_pkg_unit), + EVENT_PTR(rapl_ram_unit), + + EVENT_PTR(rapl_pkg_scale), + EVENT_PTR(rapl_ram_scale), + NULL, +}; + static struct attribute_group rapl_pmu_events_group = { .name = "events", .attrs = NULL, /* patched at runtime */ @@ -730,6 +727,10 @@ static int __init rapl_pmu_init(void) rapl_cntr_mask = RAPL_IDX_SRV; rapl_pmu_events_group.attrs = rapl_events_srv_attr; break; + case 87: /* Knights Landing */ + rapl_add_quirk(rapl_hsw_server_quirk); + rapl_cntr_mask = RAPL_IDX_KNL; + rapl_pmu_events_group.attrs = rapl_events_knl_attr; default: /* unsupported */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 21b5e38c921b..f97f8075bf04 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -7,7 +7,8 @@ struct intel_uncore_type **uncore_pci_uncores = empty_uncore; static bool pcidrv_registered; struct pci_driver *uncore_pci_driver; /* pci bus to socket mapping */ -int uncore_pcibus_to_physid[256] = { [0 ... 255] = -1, }; +DEFINE_RAW_SPINLOCK(pci2phy_map_lock); +struct list_head pci2phy_map_head = LIST_HEAD_INIT(pci2phy_map_head); struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX]; static DEFINE_RAW_SPINLOCK(uncore_box_lock); @@ -20,6 +21,59 @@ static struct event_constraint uncore_constraint_fixed = struct event_constraint uncore_constraint_empty = EVENT_CONSTRAINT(0, 0, 0); +int uncore_pcibus_to_physid(struct pci_bus *bus) +{ + struct pci2phy_map *map; + int phys_id = -1; + + raw_spin_lock(&pci2phy_map_lock); + list_for_each_entry(map, &pci2phy_map_head, list) { + if (map->segment == pci_domain_nr(bus)) { + phys_id = map->pbus_to_physid[bus->number]; + break; + } + } + raw_spin_unlock(&pci2phy_map_lock); + + return phys_id; +} + +struct pci2phy_map *__find_pci2phy_map(int segment) +{ + struct pci2phy_map *map, *alloc = NULL; + int i; + + lockdep_assert_held(&pci2phy_map_lock); + +lookup: + list_for_each_entry(map, &pci2phy_map_head, list) { + if (map->segment == segment) + goto end; + } + + if (!alloc) { + raw_spin_unlock(&pci2phy_map_lock); + alloc = kmalloc(sizeof(struct pci2phy_map), GFP_KERNEL); + raw_spin_lock(&pci2phy_map_lock); + + if (!alloc) + return NULL; + + goto lookup; + } + + map = alloc; + alloc = NULL; + map->segment = segment; + for (i = 0; i < 256; i++) + map->pbus_to_physid[i] = -1; + list_add_tail(&map->list, &pci2phy_map_head); + +end: + kfree(alloc); + return map; +} + ssize_t uncore_event_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -809,7 +863,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id int phys_id; bool first_box = false; - phys_id = uncore_pcibus_to_physid[pdev->bus->number]; + phys_id = uncore_pcibus_to_physid(pdev->bus); if (phys_id < 0) return -ENODEV; @@ -830,6 +884,15 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id * each box has a different function id. */ pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)]; + /* Knights Landing uses a common PCI device ID for multiple instances of + * an uncore PMU device type. There is only one entry per device type in + * the knl_uncore_pci_ids table inspite of multiple devices present for + * some device types. Hence PCI device idx would be 0 for all devices. + * So increment pmu pointer to point to an unused array element. + */ + if (boot_cpu_data.x86_model == 87) + while (pmu->func_id >= 0) + pmu++; if (pmu->func_id < 0) pmu->func_id = pdev->devfn; else @@ -856,9 +919,10 @@ static void uncore_pci_remove(struct pci_dev *pdev) { struct intel_uncore_box *box = pci_get_drvdata(pdev); struct intel_uncore_pmu *pmu; - int i, cpu, phys_id = uncore_pcibus_to_physid[pdev->bus->number]; + int i, cpu, phys_id; bool last_box = false; + phys_id = uncore_pcibus_to_physid(pdev->bus); box = pci_get_drvdata(pdev); if (!box) { for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) { @@ -911,6 +975,10 @@ static int __init uncore_pci_init(void) case 63: /* Haswell-EP */ ret = hswep_uncore_pci_init(); break; + case 79: /* BDX-EP */ + case 86: /* BDX-DE */ + ret = bdx_uncore_pci_init(); + break; case 42: /* Sandy Bridge */ ret = snb_uncore_pci_init(); break; @@ -924,6 +992,9 @@ static int __init uncore_pci_init(void) case 61: /* Broadwell */ ret = bdw_uncore_pci_init(); break; + case 87: /* Knights Landing */ + ret = knl_uncore_pci_init(); + break; default: return 0; } @@ -1209,6 +1280,11 @@ static int __init uncore_cpu_init(void) break; case 42: /* Sandy Bridge */ case 58: /* Ivy Bridge */ + case 60: /* Haswell */ + case 69: /* Haswell */ + case 70: /* Haswell */ + case 61: /* Broadwell */ + case 71: /* Broadwell */ snb_uncore_cpu_init(); break; case 45: /* Sandy Bridge-EP */ @@ -1224,6 +1300,13 @@ static int __init uncore_cpu_init(void) case 63: /* Haswell-EP */ hswep_uncore_cpu_init(); break; + case 79: /* BDX-EP */ + case 86: /* BDX-DE */ + bdx_uncore_cpu_init(); + break; + case 87: /* Knights Landing */ + knl_uncore_cpu_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 0f77f0a196e4..07aa2d6bd710 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -117,6 +117,15 @@ struct uncore_event_desc { const char *config; }; +struct pci2phy_map { + struct list_head list; + int segment; + int pbus_to_physid[256]; +}; + +int uncore_pcibus_to_physid(struct pci_bus *bus); +struct pci2phy_map *__find_pci2phy_map(int segment); + ssize_t uncore_event_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf); @@ -317,7 +326,8 @@ u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx); extern struct intel_uncore_type **uncore_msr_uncores; extern struct intel_uncore_type **uncore_pci_uncores; extern struct pci_driver *uncore_pci_driver; -extern int uncore_pcibus_to_physid[256]; +extern raw_spinlock_t pci2phy_map_lock; +extern struct list_head pci2phy_map_head; extern struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX]; extern struct event_constraint uncore_constraint_empty; @@ -328,6 +338,7 @@ int hsw_uncore_pci_init(void); int bdw_uncore_pci_init(void); void snb_uncore_cpu_init(void); void nhm_uncore_cpu_init(void); +int snb_pci2phy_map_init(int devid); /* perf_event_intel_uncore_snbep.c */ int snbep_uncore_pci_init(void); @@ -336,6 +347,10 @@ int ivbep_uncore_pci_init(void); void ivbep_uncore_cpu_init(void); int hswep_uncore_pci_init(void); void hswep_uncore_cpu_init(void); +int bdx_uncore_pci_init(void); +void bdx_uncore_cpu_init(void); +int knl_uncore_pci_init(void); +void knl_uncore_cpu_init(void); /* perf_event_intel_uncore_nhmex.c */ void nhmex_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 b005a78c7012..0b934820fafd 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c @@ -45,6 +45,11 @@ #define SNB_UNC_CBO_0_PER_CTR0 0x706 #define SNB_UNC_CBO_MSR_OFFSET 0x10 +/* SNB ARB register */ +#define SNB_UNC_ARB_PER_CTR0 0x3b0 +#define SNB_UNC_ARB_PERFEVTSEL0 0x3b2 +#define SNB_UNC_ARB_MSR_OFFSET 0x10 + /* NHM global control register */ #define NHM_UNC_PERF_GLOBAL_CTL 0x391 #define NHM_UNC_FIXED_CTR 0x394 @@ -115,7 +120,7 @@ static struct intel_uncore_ops snb_uncore_msr_ops = { .read_counter = uncore_msr_read_counter, }; -static struct event_constraint snb_uncore_cbox_constraints[] = { +static struct event_constraint snb_uncore_arb_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x80, 0x1), UNCORE_EVENT_CONSTRAINT(0x83, 0x1), EVENT_CONSTRAINT_END @@ -134,14 +139,28 @@ static struct intel_uncore_type snb_uncore_cbox = { .single_fixed = 1, .event_mask = SNB_UNC_RAW_EVENT_MASK, .msr_offset = SNB_UNC_CBO_MSR_OFFSET, - .constraints = snb_uncore_cbox_constraints, .ops = &snb_uncore_msr_ops, .format_group = &snb_uncore_format_group, .event_descs = snb_uncore_events, }; +static struct intel_uncore_type snb_uncore_arb = { + .name = "arb", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 44, + .perf_ctr = SNB_UNC_ARB_PER_CTR0, + .event_ctl = SNB_UNC_ARB_PERFEVTSEL0, + .event_mask = SNB_UNC_RAW_EVENT_MASK, + .msr_offset = SNB_UNC_ARB_MSR_OFFSET, + .constraints = snb_uncore_arb_constraints, + .ops = &snb_uncore_msr_ops, + .format_group = &snb_uncore_format_group, +}; + static struct intel_uncore_type *snb_msr_uncores[] = { &snb_uncore_cbox, + &snb_uncore_arb, NULL, }; @@ -398,18 +417,28 @@ static void snb_uncore_imc_event_del(struct perf_event *event, int flags) } } -static int snb_pci2phy_map_init(int devid) +int snb_pci2phy_map_init(int devid) { struct pci_dev *dev = NULL; - int bus; + struct pci2phy_map *map; + int bus, segment; dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, dev); if (!dev) return -ENOTTY; bus = dev->bus->number; - - uncore_pcibus_to_physid[bus] = 0; + segment = pci_domain_nr(dev->bus); + + raw_spin_lock(&pci2phy_map_lock); + map = __find_pci2phy_map(segment); + if (!map) { + raw_spin_unlock(&pci2phy_map_lock); + pci_dev_put(dev); + return -ENOMEM; + } + map->pbus_to_physid[bus] = 0; + raw_spin_unlock(&pci2phy_map_lock); pci_dev_put(dev); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c index 6d6e85dd5849..33acb884ccf1 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c @@ -209,31 +209,98 @@ #define HSWEP_PCU_MSR_PMON_BOX_CTL 0x710 #define HSWEP_PCU_MSR_PMON_BOX_FILTER 0x715 +/* KNL Ubox */ +#define KNL_U_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_U_MSR_PMON_RAW_EVENT_MASK | \ + SNBEP_CBO_PMON_CTL_TID_EN) +/* KNL CHA */ +#define KNL_CHA_MSR_OFFSET 0xc +#define KNL_CHA_MSR_PMON_CTL_QOR (1 << 16) +#define KNL_CHA_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK | \ + KNL_CHA_MSR_PMON_CTL_QOR) +#define KNL_CHA_MSR_PMON_BOX_FILTER_TID 0x1ff +#define KNL_CHA_MSR_PMON_BOX_FILTER_STATE (7 << 18) +#define KNL_CHA_MSR_PMON_BOX_FILTER_OP (0xfffffe2aULL << 32) + +/* KNL EDC/MC UCLK */ +#define KNL_UCLK_MSR_PMON_CTR0_LOW 0x400 +#define KNL_UCLK_MSR_PMON_CTL0 0x420 +#define KNL_UCLK_MSR_PMON_BOX_CTL 0x430 +#define KNL_UCLK_MSR_PMON_UCLK_FIXED_LOW 0x44c +#define KNL_UCLK_MSR_PMON_UCLK_FIXED_CTL 0x454 +#define KNL_PMON_FIXED_CTL_EN 0x1 + +/* KNL EDC */ +#define KNL_EDC0_ECLK_MSR_PMON_CTR0_LOW 0xa00 +#define KNL_EDC0_ECLK_MSR_PMON_CTL0 0xa20 +#define KNL_EDC0_ECLK_MSR_PMON_BOX_CTL 0xa30 +#define KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_LOW 0xa3c +#define KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_CTL 0xa44 + +/* KNL MC */ +#define KNL_MC0_CH0_MSR_PMON_CTR0_LOW 0xb00 +#define KNL_MC0_CH0_MSR_PMON_CTL0 0xb20 +#define KNL_MC0_CH0_MSR_PMON_BOX_CTL 0xb30 +#define KNL_MC0_CH0_MSR_PMON_FIXED_LOW 0xb3c +#define KNL_MC0_CH0_MSR_PMON_FIXED_CTL 0xb44 + +/* KNL IRP */ +#define KNL_IRP_PCI_PMON_BOX_CTL 0xf0 +#define KNL_IRP_PCI_PMON_RAW_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \ + KNL_CHA_MSR_PMON_CTL_QOR) +/* KNL PCU */ +#define KNL_PCU_PMON_CTL_EV_SEL_MASK 0x0000007f +#define KNL_PCU_PMON_CTL_USE_OCC_CTR (1 << 7) +#define KNL_PCU_MSR_PMON_CTL_TRESH_MASK 0x3f000000 +#define KNL_PCU_MSR_PMON_RAW_EVENT_MASK \ + (KNL_PCU_PMON_CTL_EV_SEL_MASK | \ + KNL_PCU_PMON_CTL_USE_OCC_CTR | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_CBO_PMON_CTL_TID_EN | \ + SNBEP_PMON_CTL_EV_SEL_EXT | \ + SNBEP_PMON_CTL_INVERT | \ + KNL_PCU_MSR_PMON_CTL_TRESH_MASK | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET) DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(event2, event, "config:0-6"); DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21"); +DEFINE_UNCORE_FORMAT_ATTR(use_occ_ctr, use_occ_ctr, "config:7"); DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31"); +DEFINE_UNCORE_FORMAT_ATTR(thresh6, thresh, "config:24-29"); DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28"); DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15"); DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30"); DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51"); +DEFINE_UNCORE_FORMAT_ATTR(occ_edge_det, occ_edge_det, "config:31"); DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4"); DEFINE_UNCORE_FORMAT_ATTR(filter_tid2, filter_tid, "config1:0"); DEFINE_UNCORE_FORMAT_ATTR(filter_tid3, filter_tid, "config1:0-5"); +DEFINE_UNCORE_FORMAT_ATTR(filter_tid4, filter_tid, "config1:0-8"); DEFINE_UNCORE_FORMAT_ATTR(filter_cid, filter_cid, "config1:5"); DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8"); DEFINE_UNCORE_FORMAT_ATTR(filter_link2, filter_link, "config1:6-8"); +DEFINE_UNCORE_FORMAT_ATTR(filter_link3, filter_link, "config1:12"); DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17"); DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47"); DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22"); DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22"); DEFINE_UNCORE_FORMAT_ATTR(filter_state3, filter_state, "config1:17-23"); +DEFINE_UNCORE_FORMAT_ATTR(filter_state4, filter_state, "config1:18-20"); +DEFINE_UNCORE_FORMAT_ATTR(filter_local, filter_local, "config1:33"); +DEFINE_UNCORE_FORMAT_ATTR(filter_all_op, filter_all_op, "config1:35"); +DEFINE_UNCORE_FORMAT_ATTR(filter_nnm, filter_nnm, "config1:37"); DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31"); DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60"); +DEFINE_UNCORE_FORMAT_ATTR(filter_opc3, filter_opc, "config1:41-60"); DEFINE_UNCORE_FORMAT_ATTR(filter_nc, filter_nc, "config1:62"); DEFINE_UNCORE_FORMAT_ATTR(filter_c6, filter_c6, "config1:61"); DEFINE_UNCORE_FORMAT_ATTR(filter_isoc, filter_isoc, "config1:63"); @@ -315,8 +382,9 @@ static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct pe static void snbep_uncore_pci_init_box(struct intel_uncore_box *box) { struct pci_dev *pdev = box->pci_dev; + int box_ctl = uncore_pci_box_ctl(box); - pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, SNBEP_PMON_BOX_CTL_INT); + pci_write_config_dword(pdev, box_ctl, SNBEP_PMON_BOX_CTL_INT); } static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box) @@ -1087,7 +1155,8 @@ static struct pci_driver snbep_uncore_pci_driver = { static int snbep_pci2phy_map_init(int devid) { struct pci_dev *ubox_dev = NULL; - int i, bus, nodeid; + int i, bus, nodeid, segment; + struct pci2phy_map *map; int err = 0; u32 config = 0; @@ -1106,16 +1175,27 @@ static int snbep_pci2phy_map_init(int devid) err = pci_read_config_dword(ubox_dev, 0x54, &config); if (err) break; + + segment = pci_domain_nr(ubox_dev->bus); + raw_spin_lock(&pci2phy_map_lock); + map = __find_pci2phy_map(segment); + if (!map) { + raw_spin_unlock(&pci2phy_map_lock); + err = -ENOMEM; + break; + } + /* * every three bits in the Node ID mapping register maps * to a particular node. */ for (i = 0; i < 8; i++) { if (nodeid == ((config >> (3 * i)) & 0x7)) { - uncore_pcibus_to_physid[bus] = i; + map->pbus_to_physid[bus] = i; break; } } + raw_spin_unlock(&pci2phy_map_lock); } if (!err) { @@ -1123,13 +1203,17 @@ static int snbep_pci2phy_map_init(int devid) * For PCI bus with no UBOX device, find the next bus * that has UBOX device and use its mapping. */ - i = -1; - for (bus = 255; bus >= 0; bus--) { - if (uncore_pcibus_to_physid[bus] >= 0) - i = uncore_pcibus_to_physid[bus]; - else - uncore_pcibus_to_physid[bus] = i; + raw_spin_lock(&pci2phy_map_lock); + list_for_each_entry(map, &pci2phy_map_head, list) { + i = -1; + for (bus = 255; bus >= 0; bus--) { + if (map->pbus_to_physid[bus] >= 0) + i = map->pbus_to_physid[bus]; + else + map->pbus_to_physid[bus] = i; + } } + raw_spin_unlock(&pci2phy_map_lock); } pci_dev_put(ubox_dev); @@ -1712,6 +1796,419 @@ int ivbep_uncore_pci_init(void) } /* end of IvyTown uncore support */ +/* KNL uncore support */ +static struct attribute *knl_uncore_ubox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh5.attr, + NULL, +}; + +static struct attribute_group knl_uncore_ubox_format_group = { + .name = "format", + .attrs = knl_uncore_ubox_formats_attr, +}; + +static struct intel_uncore_type knl_uncore_ubox = { + .name = "ubox", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = HSWEP_U_MSR_PMON_CTR0, + .event_ctl = HSWEP_U_MSR_PMON_CTL0, + .event_mask = KNL_U_MSR_PMON_RAW_EVENT_MASK, + .fixed_ctr = HSWEP_U_MSR_PMON_UCLK_FIXED_CTR, + .fixed_ctl = HSWEP_U_MSR_PMON_UCLK_FIXED_CTL, + .ops = &snbep_uncore_msr_ops, + .format_group = &knl_uncore_ubox_format_group, +}; + +static struct attribute *knl_uncore_cha_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_qor.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + &format_attr_filter_tid4.attr, + &format_attr_filter_link3.attr, + &format_attr_filter_state4.attr, + &format_attr_filter_local.attr, + &format_attr_filter_all_op.attr, + &format_attr_filter_nnm.attr, + &format_attr_filter_opc3.attr, + &format_attr_filter_nc.attr, + &format_attr_filter_isoc.attr, + NULL, +}; + +static struct attribute_group knl_uncore_cha_format_group = { + .name = "format", + .attrs = knl_uncore_cha_formats_attr, +}; + +static struct event_constraint knl_uncore_cha_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x11, 0x1), + UNCORE_EVENT_CONSTRAINT(0x1f, 0x1), + UNCORE_EVENT_CONSTRAINT(0x36, 0x1), + EVENT_CONSTRAINT_END +}; + +static struct extra_reg knl_uncore_cha_extra_regs[] = { + SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, + SNBEP_CBO_PMON_CTL_TID_EN, 0x1), + SNBEP_CBO_EVENT_EXTRA_REG(0x3d, 0xff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x35, 0xff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x36, 0xff, 0x4), + EVENT_EXTRA_END +}; + +static u64 knl_cha_filter_mask(int fields) +{ + u64 mask = 0; + + if (fields & 0x1) + mask |= KNL_CHA_MSR_PMON_BOX_FILTER_TID; + if (fields & 0x2) + mask |= KNL_CHA_MSR_PMON_BOX_FILTER_STATE; + if (fields & 0x4) + mask |= KNL_CHA_MSR_PMON_BOX_FILTER_OP; + return mask; +} + +static struct event_constraint * +knl_cha_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + return __snbep_cbox_get_constraint(box, event, knl_cha_filter_mask); +} + +static int knl_cha_hw_config(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct extra_reg *er; + int idx = 0; + + for (er = knl_uncore_cha_extra_regs; er->msr; er++) { + if (er->event != (event->hw.config & er->config_mask)) + continue; + idx |= er->idx; + } + + if (idx) { + reg1->reg = HSWEP_C0_MSR_PMON_BOX_FILTER0 + + KNL_CHA_MSR_OFFSET * box->pmu->pmu_idx; + reg1->config = event->attr.config1 & knl_cha_filter_mask(idx); + reg1->idx = idx; + } + return 0; +} + +static void hswep_cbox_enable_event(struct intel_uncore_box *box, + struct perf_event *event); + +static struct intel_uncore_ops knl_uncore_cha_ops = { + .init_box = snbep_uncore_msr_init_box, + .disable_box = snbep_uncore_msr_disable_box, + .enable_box = snbep_uncore_msr_enable_box, + .disable_event = snbep_uncore_msr_disable_event, + .enable_event = hswep_cbox_enable_event, + .read_counter = uncore_msr_read_counter, + .hw_config = knl_cha_hw_config, + .get_constraint = knl_cha_get_constraint, + .put_constraint = snbep_cbox_put_constraint, +}; + +static struct intel_uncore_type knl_uncore_cha = { + .name = "cha", + .num_counters = 4, + .num_boxes = 38, + .perf_ctr_bits = 48, + .event_ctl = HSWEP_C0_MSR_PMON_CTL0, + .perf_ctr = HSWEP_C0_MSR_PMON_CTR0, + .event_mask = KNL_CHA_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_C0_MSR_PMON_BOX_CTL, + .msr_offset = KNL_CHA_MSR_OFFSET, + .num_shared_regs = 1, + .constraints = knl_uncore_cha_constraints, + .ops = &knl_uncore_cha_ops, + .format_group = &knl_uncore_cha_format_group, +}; + +static struct attribute *knl_uncore_pcu_formats_attr[] = { + &format_attr_event2.attr, + &format_attr_use_occ_ctr.attr, + &format_attr_occ_sel.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh6.attr, + &format_attr_occ_invert.attr, + &format_attr_occ_edge_det.attr, + NULL, +}; + +static struct attribute_group knl_uncore_pcu_format_group = { + .name = "format", + .attrs = knl_uncore_pcu_formats_attr, +}; + +static struct intel_uncore_type knl_uncore_pcu = { + .name = "pcu", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = HSWEP_PCU_MSR_PMON_CTR0, + .event_ctl = HSWEP_PCU_MSR_PMON_CTL0, + .event_mask = KNL_PCU_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_PCU_MSR_PMON_BOX_CTL, + .ops = &snbep_uncore_msr_ops, + .format_group = &knl_uncore_pcu_format_group, +}; + +static struct intel_uncore_type *knl_msr_uncores[] = { + &knl_uncore_ubox, + &knl_uncore_cha, + &knl_uncore_pcu, + NULL, +}; + +void knl_uncore_cpu_init(void) +{ + uncore_msr_uncores = knl_msr_uncores; +} + +static void knl_uncore_imc_enable_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + int box_ctl = uncore_pci_box_ctl(box); + + pci_write_config_dword(pdev, box_ctl, 0); +} + +static void knl_uncore_imc_enable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + if ((event->attr.config & SNBEP_PMON_CTL_EV_SEL_MASK) + == UNCORE_FIXED_EVENT) + pci_write_config_dword(pdev, hwc->config_base, + hwc->config | KNL_PMON_FIXED_CTL_EN); + else + pci_write_config_dword(pdev, hwc->config_base, + hwc->config | SNBEP_PMON_CTL_EN); +} + +static struct intel_uncore_ops knl_uncore_imc_ops = { + .init_box = snbep_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = knl_uncore_imc_enable_box, + .read_counter = snbep_uncore_pci_read_counter, + .enable_event = knl_uncore_imc_enable_event, + .disable_event = snbep_uncore_pci_disable_event, +}; + +static struct intel_uncore_type knl_uncore_imc_uclk = { + .name = "imc_uclk", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = KNL_UCLK_MSR_PMON_CTR0_LOW, + .event_ctl = KNL_UCLK_MSR_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .fixed_ctr = KNL_UCLK_MSR_PMON_UCLK_FIXED_LOW, + .fixed_ctl = KNL_UCLK_MSR_PMON_UCLK_FIXED_CTL, + .box_ctl = KNL_UCLK_MSR_PMON_BOX_CTL, + .ops = &knl_uncore_imc_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct intel_uncore_type knl_uncore_imc_dclk = { + .name = "imc", + .num_counters = 4, + .num_boxes = 6, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = KNL_MC0_CH0_MSR_PMON_CTR0_LOW, + .event_ctl = KNL_MC0_CH0_MSR_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .fixed_ctr = KNL_MC0_CH0_MSR_PMON_FIXED_LOW, + .fixed_ctl = KNL_MC0_CH0_MSR_PMON_FIXED_CTL, + .box_ctl = KNL_MC0_CH0_MSR_PMON_BOX_CTL, + .ops = &knl_uncore_imc_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct intel_uncore_type knl_uncore_edc_uclk = { + .name = "edc_uclk", + .num_counters = 4, + .num_boxes = 8, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = KNL_UCLK_MSR_PMON_CTR0_LOW, + .event_ctl = KNL_UCLK_MSR_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .fixed_ctr = KNL_UCLK_MSR_PMON_UCLK_FIXED_LOW, + .fixed_ctl = KNL_UCLK_MSR_PMON_UCLK_FIXED_CTL, + .box_ctl = KNL_UCLK_MSR_PMON_BOX_CTL, + .ops = &knl_uncore_imc_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct intel_uncore_type knl_uncore_edc_eclk = { + .name = "edc_eclk", + .num_counters = 4, + .num_boxes = 8, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = KNL_EDC0_ECLK_MSR_PMON_CTR0_LOW, + .event_ctl = KNL_EDC0_ECLK_MSR_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .fixed_ctr = KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_LOW, + .fixed_ctl = KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_CTL, + .box_ctl = KNL_EDC0_ECLK_MSR_PMON_BOX_CTL, + .ops = &knl_uncore_imc_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct event_constraint knl_uncore_m2pcie_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type knl_uncore_m2pcie = { + .name = "m2pcie", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .constraints = knl_uncore_m2pcie_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct attribute *knl_uncore_irp_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_qor.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute_group knl_uncore_irp_format_group = { + .name = "format", + .attrs = knl_uncore_irp_formats_attr, +}; + +static struct intel_uncore_type knl_uncore_irp = { + .name = "irp", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = KNL_IRP_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = KNL_IRP_PCI_PMON_BOX_CTL, + .ops = &snbep_uncore_pci_ops, + .format_group = &knl_uncore_irp_format_group, +}; + +enum { + KNL_PCI_UNCORE_MC_UCLK, + KNL_PCI_UNCORE_MC_DCLK, + KNL_PCI_UNCORE_EDC_UCLK, + KNL_PCI_UNCORE_EDC_ECLK, + KNL_PCI_UNCORE_M2PCIE, + KNL_PCI_UNCORE_IRP, +}; + +static struct intel_uncore_type *knl_pci_uncores[] = { + [KNL_PCI_UNCORE_MC_UCLK] = &knl_uncore_imc_uclk, + [KNL_PCI_UNCORE_MC_DCLK] = &knl_uncore_imc_dclk, + [KNL_PCI_UNCORE_EDC_UCLK] = &knl_uncore_edc_uclk, + [KNL_PCI_UNCORE_EDC_ECLK] = &knl_uncore_edc_eclk, + [KNL_PCI_UNCORE_M2PCIE] = &knl_uncore_m2pcie, + [KNL_PCI_UNCORE_IRP] = &knl_uncore_irp, + NULL, +}; + +/* + * KNL uses a common PCI device ID for multiple instances of an Uncore PMU + * device type. prior to KNL, each instance of a PMU device type had a unique + * device ID. + * + * PCI Device ID Uncore PMU Devices + * ---------------------------------- + * 0x7841 MC0 UClk, MC1 UClk + * 0x7843 MC0 DClk CH 0, MC0 DClk CH 1, MC0 DClk CH 2, + * MC1 DClk CH 0, MC1 DClk CH 1, MC1 DClk CH 2 + * 0x7833 EDC0 UClk, EDC1 UClk, EDC2 UClk, EDC3 UClk, + * EDC4 UClk, EDC5 UClk, EDC6 UClk, EDC7 UClk + * 0x7835 EDC0 EClk, EDC1 EClk, EDC2 EClk, EDC3 EClk, + * EDC4 EClk, EDC5 EClk, EDC6 EClk, EDC7 EClk + * 0x7817 M2PCIe + * 0x7814 IRP +*/ + +static const struct pci_device_id knl_uncore_pci_ids[] = { + { /* MC UClk */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7841), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_MC_UCLK, 0), + }, + { /* MC DClk Channel */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7843), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_MC_DCLK, 0), + }, + { /* EDC UClk */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7833), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_EDC_UCLK, 0), + }, + { /* EDC EClk */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7835), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_EDC_ECLK, 0), + }, + { /* M2PCIe */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7817), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_M2PCIE, 0), + }, + { /* IRP */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7814), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_IRP, 0), + }, + { /* end: all zeroes */ } +}; + +static struct pci_driver knl_uncore_pci_driver = { + .name = "knl_uncore", + .id_table = knl_uncore_pci_ids, +}; + +int knl_uncore_pci_init(void) +{ + int ret; + + /* All KNL PCI based PMON units are on the same PCI bus except IRP */ + ret = snb_pci2phy_map_init(0x7814); /* IRP */ + if (ret) + return ret; + ret = snb_pci2phy_map_init(0x7817); /* M2PCIe */ + if (ret) + return ret; + uncore_pci_uncores = knl_pci_uncores; + uncore_pci_driver = &knl_uncore_pci_driver; + return 0; +} + +/* end of KNL uncore support */ + /* Haswell-EP uncore support */ static struct attribute *hswep_uncore_ubox_formats_attr[] = { &format_attr_event.attr, @@ -2215,7 +2712,7 @@ static struct intel_uncore_type *hswep_pci_uncores[] = { NULL, }; -static DEFINE_PCI_DEVICE_TABLE(hswep_uncore_pci_ids) = { +static const struct pci_device_id hswep_uncore_pci_ids[] = { { /* Home Agent 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f30), .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_HA, 0), @@ -2321,3 +2818,309 @@ int hswep_uncore_pci_init(void) return 0; } /* end of Haswell-EP uncore support */ + +/* BDX uncore support */ + +static struct intel_uncore_type bdx_uncore_ubox = { + .name = "ubox", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = HSWEP_U_MSR_PMON_CTR0, + .event_ctl = HSWEP_U_MSR_PMON_CTL0, + .event_mask = SNBEP_U_MSR_PMON_RAW_EVENT_MASK, + .fixed_ctr = HSWEP_U_MSR_PMON_UCLK_FIXED_CTR, + .fixed_ctl = HSWEP_U_MSR_PMON_UCLK_FIXED_CTL, + .num_shared_regs = 1, + .ops = &ivbep_uncore_msr_ops, + .format_group = &ivbep_uncore_ubox_format_group, +}; + +static struct event_constraint bdx_uncore_cbox_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x09, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x1), + UNCORE_EVENT_CONSTRAINT(0x36, 0x1), + UNCORE_EVENT_CONSTRAINT(0x3e, 0x1), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type bdx_uncore_cbox = { + .name = "cbox", + .num_counters = 4, + .num_boxes = 24, + .perf_ctr_bits = 48, + .event_ctl = HSWEP_C0_MSR_PMON_CTL0, + .perf_ctr = HSWEP_C0_MSR_PMON_CTR0, + .event_mask = SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_C0_MSR_PMON_BOX_CTL, + .msr_offset = HSWEP_CBO_MSR_OFFSET, + .num_shared_regs = 1, + .constraints = bdx_uncore_cbox_constraints, + .ops = &hswep_uncore_cbox_ops, + .format_group = &hswep_uncore_cbox_format_group, +}; + +static struct intel_uncore_type bdx_uncore_sbox = { + .name = "sbox", + .num_counters = 4, + .num_boxes = 4, + .perf_ctr_bits = 48, + .event_ctl = HSWEP_S0_MSR_PMON_CTL0, + .perf_ctr = HSWEP_S0_MSR_PMON_CTR0, + .event_mask = HSWEP_S_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_S0_MSR_PMON_BOX_CTL, + .msr_offset = HSWEP_SBOX_MSR_OFFSET, + .ops = &hswep_uncore_sbox_msr_ops, + .format_group = &hswep_uncore_sbox_format_group, +}; + +static struct intel_uncore_type *bdx_msr_uncores[] = { + &bdx_uncore_ubox, + &bdx_uncore_cbox, + &bdx_uncore_sbox, + &hswep_uncore_pcu, + NULL, +}; + +void bdx_uncore_cpu_init(void) +{ + if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) + bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + uncore_msr_uncores = bdx_msr_uncores; +} + +static struct intel_uncore_type bdx_uncore_ha = { + .name = "ha", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type bdx_uncore_imc = { + .name = "imc", + .num_counters = 5, + .num_boxes = 8, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, + .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL, + .event_descs = hswep_uncore_imc_events, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type bdx_uncore_irp = { + .name = "irp", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .ops = &hswep_uncore_irp_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct intel_uncore_type bdx_uncore_qpi = { + .name = "qpi", + .num_counters = 4, + .num_boxes = 3, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &snbep_uncore_qpi_ops, + .format_group = &snbep_uncore_qpi_format_group, +}; + +static struct event_constraint bdx_uncore_r2pcie_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x10, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x3), + UNCORE_EVENT_CONSTRAINT(0x13, 0x1), + UNCORE_EVENT_CONSTRAINT(0x23, 0x1), + UNCORE_EVENT_CONSTRAINT(0x25, 0x1), + UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x28, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type bdx_uncore_r2pcie = { + .name = "r2pcie", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .constraints = bdx_uncore_r2pcie_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct event_constraint bdx_uncore_r3qpi_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x01, 0x7), + UNCORE_EVENT_CONSTRAINT(0x07, 0x7), + UNCORE_EVENT_CONSTRAINT(0x08, 0x7), + UNCORE_EVENT_CONSTRAINT(0x09, 0x7), + UNCORE_EVENT_CONSTRAINT(0x0a, 0x7), + UNCORE_EVENT_CONSTRAINT(0x0e, 0x7), + UNCORE_EVENT_CONSTRAINT(0x10, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x3), + UNCORE_EVENT_CONSTRAINT(0x13, 0x1), + UNCORE_EVENT_CONSTRAINT(0x14, 0x3), + UNCORE_EVENT_CONSTRAINT(0x15, 0x3), + UNCORE_EVENT_CONSTRAINT(0x1f, 0x3), + UNCORE_EVENT_CONSTRAINT(0x20, 0x3), + UNCORE_EVENT_CONSTRAINT(0x21, 0x3), + UNCORE_EVENT_CONSTRAINT(0x22, 0x3), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x25, 0x3), + UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x28, 0x3), + UNCORE_EVENT_CONSTRAINT(0x29, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2e, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2f, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + UNCORE_EVENT_CONSTRAINT(0x36, 0x3), + UNCORE_EVENT_CONSTRAINT(0x37, 0x3), + UNCORE_EVENT_CONSTRAINT(0x38, 0x3), + UNCORE_EVENT_CONSTRAINT(0x39, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type bdx_uncore_r3qpi = { + .name = "r3qpi", + .num_counters = 3, + .num_boxes = 3, + .perf_ctr_bits = 48, + .constraints = bdx_uncore_r3qpi_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +enum { + BDX_PCI_UNCORE_HA, + BDX_PCI_UNCORE_IMC, + BDX_PCI_UNCORE_IRP, + BDX_PCI_UNCORE_QPI, + BDX_PCI_UNCORE_R2PCIE, + BDX_PCI_UNCORE_R3QPI, +}; + +static struct intel_uncore_type *bdx_pci_uncores[] = { + [BDX_PCI_UNCORE_HA] = &bdx_uncore_ha, + [BDX_PCI_UNCORE_IMC] = &bdx_uncore_imc, + [BDX_PCI_UNCORE_IRP] = &bdx_uncore_irp, + [BDX_PCI_UNCORE_QPI] = &bdx_uncore_qpi, + [BDX_PCI_UNCORE_R2PCIE] = &bdx_uncore_r2pcie, + [BDX_PCI_UNCORE_R3QPI] = &bdx_uncore_r3qpi, + NULL, +}; + +static const struct pci_device_id bdx_uncore_pci_ids[] = { + { /* Home Agent 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f30), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_HA, 0), + }, + { /* Home Agent 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f38), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_HA, 1), + }, + { /* MC0 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb0), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 0), + }, + { /* MC0 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb1), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 1), + }, + { /* MC0 Channel 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb4), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 2), + }, + { /* MC0 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb5), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 3), + }, + { /* MC1 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd0), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 4), + }, + { /* MC1 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd1), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 5), + }, + { /* MC1 Channel 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd4), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 6), + }, + { /* MC1 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd5), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 7), + }, + { /* IRP */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f39), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IRP, 0), + }, + { /* QPI0 Port 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f32), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_QPI, 0), + }, + { /* QPI0 Port 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f33), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_QPI, 1), + }, + { /* QPI1 Port 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f3a), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_QPI, 2), + }, + { /* R2PCIe */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f34), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R2PCIE, 0), + }, + { /* R3QPI0 Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f36), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R3QPI, 0), + }, + { /* R3QPI0 Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f37), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R3QPI, 1), + }, + { /* R3QPI1 Link 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f3e), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R3QPI, 2), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f86), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 0), + }, + { /* QPI Port 1 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f96), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 1), + }, + { /* QPI Port 2 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2), + }, + { /* end: all zeroes */ } +}; + +static struct pci_driver bdx_uncore_pci_driver = { + .name = "bdx_uncore", + .id_table = bdx_uncore_pci_ids, +}; + +int bdx_uncore_pci_init(void) +{ + int ret = snbep_pci2phy_map_init(0x6f1e); + + if (ret) + return ret; + uncore_pci_uncores = bdx_pci_uncores; + uncore_pci_driver = &bdx_uncore_pci_driver; + return 0; +} + +/* end of BDX uncore support */ diff --git a/arch/x86/kernel/cpu/perf_event_msr.c b/arch/x86/kernel/cpu/perf_event_msr.c new file mode 100644 index 000000000000..ec863b9a9f78 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_msr.c @@ -0,0 +1,241 @@ +#include <linux/perf_event.h> + +enum perf_msr_id { + PERF_MSR_TSC = 0, + PERF_MSR_APERF = 1, + PERF_MSR_MPERF = 2, + PERF_MSR_PPERF = 3, + PERF_MSR_SMI = 4, + + PERF_MSR_EVENT_MAX, +}; + +static bool test_aperfmperf(int idx) +{ + return boot_cpu_has(X86_FEATURE_APERFMPERF); +} + +static bool test_intel(int idx) +{ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || + boot_cpu_data.x86 != 6) + return false; + + switch (boot_cpu_data.x86_model) { + case 30: /* 45nm Nehalem */ + case 26: /* 45nm Nehalem-EP */ + case 46: /* 45nm Nehalem-EX */ + + case 37: /* 32nm Westmere */ + case 44: /* 32nm Westmere-EP */ + case 47: /* 32nm Westmere-EX */ + + case 42: /* 32nm SandyBridge */ + case 45: /* 32nm SandyBridge-E/EN/EP */ + + case 58: /* 22nm IvyBridge */ + case 62: /* 22nm IvyBridge-EP/EX */ + + case 60: /* 22nm Haswell Core */ + case 63: /* 22nm Haswell Server */ + case 69: /* 22nm Haswell ULT */ + case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */ + + case 61: /* 14nm Broadwell Core-M */ + case 86: /* 14nm Broadwell Xeon D */ + case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */ + case 79: /* 14nm Broadwell Server */ + + case 55: /* 22nm Atom "Silvermont" */ + case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */ + case 76: /* 14nm Atom "Airmont" */ + if (idx == PERF_MSR_SMI) + return true; + break; + + case 78: /* 14nm Skylake Mobile */ + case 94: /* 14nm Skylake Desktop */ + if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF) + return true; + break; + } + + return false; +} + +struct perf_msr { + u64 msr; + struct perf_pmu_events_attr *attr; + bool (*test)(int idx); +}; + +PMU_EVENT_ATTR_STRING(tsc, evattr_tsc, "event=0x00"); +PMU_EVENT_ATTR_STRING(aperf, evattr_aperf, "event=0x01"); +PMU_EVENT_ATTR_STRING(mperf, evattr_mperf, "event=0x02"); +PMU_EVENT_ATTR_STRING(pperf, evattr_pperf, "event=0x03"); +PMU_EVENT_ATTR_STRING(smi, evattr_smi, "event=0x04"); + +static struct perf_msr msr[] = { + [PERF_MSR_TSC] = { 0, &evattr_tsc, NULL, }, + [PERF_MSR_APERF] = { MSR_IA32_APERF, &evattr_aperf, test_aperfmperf, }, + [PERF_MSR_MPERF] = { MSR_IA32_MPERF, &evattr_mperf, test_aperfmperf, }, + [PERF_MSR_PPERF] = { MSR_PPERF, &evattr_pperf, test_intel, }, + [PERF_MSR_SMI] = { MSR_SMI_COUNT, &evattr_smi, test_intel, }, +}; + +static struct attribute *events_attrs[PERF_MSR_EVENT_MAX + 1] = { + NULL, +}; + +static struct attribute_group events_attr_group = { + .name = "events", + .attrs = events_attrs, +}; + +PMU_FORMAT_ATTR(event, "config:0-63"); +static struct attribute *format_attrs[] = { + &format_attr_event.attr, + NULL, +}; +static struct attribute_group format_attr_group = { + .name = "format", + .attrs = format_attrs, +}; + +static const struct attribute_group *attr_groups[] = { + &events_attr_group, + &format_attr_group, + NULL, +}; + +static int msr_event_init(struct perf_event *event) +{ + u64 cfg = event->attr.config; + + if (event->attr.type != event->pmu->type) + return -ENOENT; + + if (cfg >= PERF_MSR_EVENT_MAX) + return -EINVAL; + + /* unsupported modes and filters */ + if (event->attr.exclude_user || + event->attr.exclude_kernel || + event->attr.exclude_hv || + event->attr.exclude_idle || + event->attr.exclude_host || + event->attr.exclude_guest || + event->attr.sample_period) /* no sampling */ + return -EINVAL; + + if (!msr[cfg].attr) + return -EINVAL; + + event->hw.idx = -1; + event->hw.event_base = msr[cfg].msr; + event->hw.config = cfg; + + return 0; +} + +static inline u64 msr_read_counter(struct perf_event *event) +{ + u64 now; + + if (event->hw.event_base) + rdmsrl(event->hw.event_base, now); + else + rdtscll(now); + + return now; +} +static void msr_event_update(struct perf_event *event) +{ + u64 prev, now; + s64 delta; + + /* Careful, an NMI might modify the previous event value. */ +again: + prev = local64_read(&event->hw.prev_count); + now = msr_read_counter(event); + + if (local64_cmpxchg(&event->hw.prev_count, prev, now) != prev) + goto again; + + delta = now - prev; + if (unlikely(event->hw.event_base == MSR_SMI_COUNT)) + delta = sign_extend64(delta, 31); + + local64_add(now - prev, &event->count); +} + +static void msr_event_start(struct perf_event *event, int flags) +{ + u64 now; + + now = msr_read_counter(event); + local64_set(&event->hw.prev_count, now); +} + +static void msr_event_stop(struct perf_event *event, int flags) +{ + msr_event_update(event); +} + +static void msr_event_del(struct perf_event *event, int flags) +{ + msr_event_stop(event, PERF_EF_UPDATE); +} + +static int msr_event_add(struct perf_event *event, int flags) +{ + if (flags & PERF_EF_START) + msr_event_start(event, flags); + + return 0; +} + +static struct pmu pmu_msr = { + .task_ctx_nr = perf_sw_context, + .attr_groups = attr_groups, + .event_init = msr_event_init, + .add = msr_event_add, + .del = msr_event_del, + .start = msr_event_start, + .stop = msr_event_stop, + .read = msr_event_update, + .capabilities = PERF_PMU_CAP_NO_INTERRUPT, +}; + +static int __init msr_init(void) +{ + int i, j = 0; + + if (!boot_cpu_has(X86_FEATURE_TSC)) { + pr_cont("no MSR PMU driver.\n"); + return 0; + } + + /* Probe the MSRs. */ + for (i = PERF_MSR_TSC + 1; i < PERF_MSR_EVENT_MAX; i++) { + u64 val; + + /* + * Virt sucks arse; you cannot tell if a R/O MSR is present :/ + */ + if (!msr[i].test(i) || rdmsrl_safe(msr[i].msr, &val)) + msr[i].attr = NULL; + } + + /* List remaining MSRs in the sysfs attrs. */ + for (i = 0; i < PERF_MSR_EVENT_MAX; i++) { + if (msr[i].attr) + events_attrs[j++] = &msr[i].attr->attr.attr; + } + events_attrs[j] = NULL; + + perf_pmu_register(&pmu_msr, "msr", -1); + + return 0; +} +device_initcall(msr_init); diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c index 136ac74dee82..819d94982e07 100644 --- a/arch/x86/kernel/cpu/rdrand.c +++ b/arch/x86/kernel/cpu/rdrand.c @@ -33,28 +33,27 @@ static int __init x86_rdrand_setup(char *s) __setup("nordrand", x86_rdrand_setup); /* - * Force a reseed cycle; we are architecturally guaranteed a reseed - * after no more than 512 128-bit chunks of random data. This also - * acts as a test of the CPU capability. + * RDRAND has Built-In-Self-Test (BIST) that runs on every invocation. + * Run the instruction a few times as a sanity check. + * If it fails, it is simple to disable RDRAND here. */ -#define RESEED_LOOP ((512*128)/sizeof(unsigned long)) +#define SANITY_CHECK_LOOPS 8 void x86_init_rdrand(struct cpuinfo_x86 *c) { #ifdef CONFIG_ARCH_RANDOM unsigned long tmp; - int i, count, ok; + int i; if (!cpu_has(c, X86_FEATURE_RDRAND)) - return; /* Nothing to do */ + return; - for (count = i = 0; i < RESEED_LOOP; i++) { - ok = rdrand_long(&tmp); - if (ok) - count++; + for (i = 0; i < SANITY_CHECK_LOOPS; i++) { + if (!rdrand_long(&tmp)) { + clear_cpu_cap(c, X86_FEATURE_RDRAND); + printk_once(KERN_WARNING "rdrand: disabled\n"); + return; + } } - - if (count != RESEED_LOOP) - clear_cpu_cap(c, X86_FEATURE_RDRAND); #endif } diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 3d423a101fae..8cb57df9398d 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -31,32 +31,12 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c) const struct cpuid_bit *cb; static const struct cpuid_bit cpuid_bits[] = { - { X86_FEATURE_DTHERM, CR_EAX, 0, 0x00000006, 0 }, - { X86_FEATURE_IDA, CR_EAX, 1, 0x00000006, 0 }, - { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006, 0 }, - { X86_FEATURE_PLN, CR_EAX, 4, 0x00000006, 0 }, - { X86_FEATURE_PTS, CR_EAX, 6, 0x00000006, 0 }, - { X86_FEATURE_HWP, CR_EAX, 7, 0x00000006, 0 }, - { X86_FEATURE_HWP_NOITFY, CR_EAX, 8, 0x00000006, 0 }, - { X86_FEATURE_HWP_ACT_WINDOW, CR_EAX, 9, 0x00000006, 0 }, - { X86_FEATURE_HWP_EPP, CR_EAX,10, 0x00000006, 0 }, - { X86_FEATURE_HWP_PKG_REQ, CR_EAX,11, 0x00000006, 0 }, { X86_FEATURE_INTEL_PT, CR_EBX,25, 0x00000007, 0 }, { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 }, { X86_FEATURE_CPB, CR_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_PROC_FEEDBACK, CR_EDX,11, 0x80000007, 0 }, - { X86_FEATURE_NPT, CR_EDX, 0, 0x8000000a, 0 }, - { X86_FEATURE_LBRV, CR_EDX, 1, 0x8000000a, 0 }, - { X86_FEATURE_SVML, CR_EDX, 2, 0x8000000a, 0 }, - { X86_FEATURE_NRIPS, CR_EDX, 3, 0x8000000a, 0 }, - { X86_FEATURE_TSCRATEMSR, CR_EDX, 4, 0x8000000a, 0 }, - { X86_FEATURE_VMCBCLEAN, CR_EDX, 5, 0x8000000a, 0 }, - { X86_FEATURE_FLUSHBYASID, CR_EDX, 6, 0x8000000a, 0 }, - { X86_FEATURE_DECODEASSISTS, CR_EDX, 7, 0x8000000a, 0 }, - { X86_FEATURE_PAUSEFILTER, CR_EDX,10, 0x8000000a, 0 }, - { X86_FEATURE_PFTHRESHOLD, CR_EDX,12, 0x8000000a, 0 }, { 0, 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index 3fa0e5ad86b4..252da7aceca6 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -12,7 +12,7 @@ static void early_init_transmeta(struct cpuinfo_x86 *c) xlvl = cpuid_eax(0x80860000); if ((xlvl & 0xffff0000) == 0x80860000) { if (xlvl >= 0x80860001) - c->x86_capability[2] = cpuid_edx(0x80860001); + c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001); } } @@ -82,7 +82,7 @@ static void init_transmeta(struct cpuinfo_x86 *c) /* Unhide possibly hidden capability flags */ rdmsr(0x80860004, cap_mask, uk); wrmsr(0x80860004, ~0, uk); - c->x86_capability[0] = cpuid_edx(0x00000001); + c->x86_capability[CPUID_1_EDX] = cpuid_edx(0x00000001); wrmsr(0x80860004, cap_mask, uk); /* All Transmeta CPUs have a constant TSC */ diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index 83741a71558f..2836de390f95 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -58,28 +58,6 @@ static void cpuid_smp_cpuid(void *cmd_block) &cmd->eax, &cmd->ebx, &cmd->ecx, &cmd->edx); } -static loff_t cpuid_seek(struct file *file, loff_t offset, int orig) -{ - loff_t ret; - struct inode *inode = file->f_mapping->host; - - mutex_lock(&inode->i_mutex); - switch (orig) { - case 0: - file->f_pos = offset; - ret = file->f_pos; - break; - case 1: - file->f_pos += offset; - ret = file->f_pos; - break; - default: - ret = -EINVAL; - } - mutex_unlock(&inode->i_mutex); - return ret; -} - static ssize_t cpuid_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -132,7 +110,7 @@ static int cpuid_open(struct inode *inode, struct file *file) */ static const struct file_operations cpuid_fops = { .owner = THIS_MODULE, - .llseek = cpuid_seek, + .llseek = no_seek_end_llseek, .read = cpuid_read, .open = cpuid_open, }; @@ -170,7 +148,7 @@ static int cpuid_class_cpu_callback(struct notifier_block *nfb, return notifier_from_errno(err); } -static struct notifier_block __refdata cpuid_class_cpu_notifier = +static struct notifier_block cpuid_class_cpu_notifier = { .notifier_call = cpuid_class_cpu_callback, }; diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index e068d6683dba..58f34319b29a 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -35,6 +35,7 @@ #include <asm/cpu.h> #include <asm/reboot.h> #include <asm/virtext.h> +#include <asm/intel_pt.h> /* Alignment required for elf header segment */ #define ELF_CORE_HEADER_ALIGN 4096 @@ -75,8 +76,6 @@ struct crash_memmap_data { unsigned int type; }; -int in_crash_kexec; - /* * This is used to VMCLEAR all VMCSs loaded on the * processor. And when loading kvm_intel module, the @@ -127,12 +126,16 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs) cpu_emergency_vmxoff(); cpu_emergency_svm_disable(); + /* + * Disable Intel PT to stop its logging + */ + cpu_emergency_stop_pt(); + disable_local_APIC(); } static void kdump_nmi_shootdown_cpus(void) { - in_crash_kexec = 1; nmi_shootdown_cpus(kdump_nmi_callback); disable_local_APIC(); @@ -172,6 +175,11 @@ void native_machine_crash_shutdown(struct pt_regs *regs) cpu_emergency_vmxoff(); cpu_emergency_svm_disable(); + /* + * Disable Intel PT to stop its logging + */ + cpu_emergency_stop_pt(); + #ifdef CONFIG_X86_IO_APIC /* Prevent crash_kexec() from deadlocking on ioapic_lock. */ ioapic_zap_locks(); @@ -185,10 +193,9 @@ void native_machine_crash_shutdown(struct pt_regs *regs) } #ifdef CONFIG_KEXEC_FILE -static int get_nr_ram_ranges_callback(unsigned long start_pfn, - unsigned long nr_pfn, void *arg) +static int get_nr_ram_ranges_callback(u64 start, u64 end, void *arg) { - int *nr_ranges = arg; + unsigned int *nr_ranges = arg; (*nr_ranges)++; return 0; @@ -214,7 +221,7 @@ static void fill_up_crash_elf_data(struct crash_elf_data *ced, ced->image = image; - walk_system_ram_range(0, -1, &nr_ranges, + walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback); ced->max_nr_ranges = nr_ranges; diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index a102564d08eb..569c1e4f96fe 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -911,7 +911,7 @@ void __init finish_e820_parsing(void) } } -static inline const char *e820_type_to_string(int e820_type) +static const char *e820_type_to_string(int e820_type) { switch (e820_type) { case E820_RESERVED_KERN: diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 9f9cc682e561..bca14c899137 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -547,6 +547,7 @@ static const struct pci_device_id intel_stolen_ids[] __initconst = { INTEL_CHV_IDS(&chv_stolen_funcs), INTEL_SKL_IDS(&gen9_stolen_funcs), INTEL_BXT_IDS(&gen9_stolen_funcs), + INTEL_KBL_IDS(&gen9_stolen_funcs), }; static void __init intel_graphics_stolen(int num, int slot, int func) @@ -584,7 +585,7 @@ static void __init intel_graphics_stolen(int num, int slot, int func) static void __init force_disable_hpet(int num, int slot, int func) { #ifdef CONFIG_HPET_TIMER - boot_hpet_disable = 1; + boot_hpet_disable = true; pr_info("x86/hpet: Will disable the HPET for this platform because it's not reliable\n"); #endif } diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index eec40f595ab9..21bf92490a7b 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -195,14 +195,14 @@ static __init void early_serial_init(char *s) #ifdef CONFIG_PCI static void mem32_serial_out(unsigned long addr, int offset, int value) { - u32 *vaddr = (u32 *)addr; + u32 __iomem *vaddr = (u32 __iomem *)addr; /* shift implied by pointer type */ writel(value, vaddr + offset); } static unsigned int mem32_serial_in(unsigned long addr, int offset) { - u32 *vaddr = (u32 *)addr; + u32 __iomem *vaddr = (u32 __iomem *)addr; /* shift implied by pointer type */ return readl(vaddr + offset); } @@ -316,7 +316,7 @@ static struct console early_serial_console = { .index = -1, }; -static inline void early_console_register(struct console *con, int keep_early) +static void early_console_register(struct console *con, int keep_early) { if (con->index != -1) { printk(KERN_CRIT "ERROR: earlyprintk= %s already used\n", diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index ce95676abd60..4d38416e2a7f 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -110,7 +110,7 @@ static void init_espfix_random(void) */ if (!arch_get_random_long(&rand)) { /* The constant is an arbitrary large prime */ - rdtscll(rand); + rand = rdtsc(); rand *= 0xc345c6b72fd16123UL; } diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index d14e9ac3235a..6d9f0a7ef4c8 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -3,8 +3,11 @@ */ #include <asm/fpu/internal.h> #include <asm/tlbflush.h> +#include <asm/setup.h> +#include <asm/cmdline.h> #include <linux/sched.h> +#include <linux/init.h> /* * Initialize the TS bit in CR0 according to the style of context-switches @@ -12,7 +15,7 @@ */ static void fpu__init_cpu_ctx_switch(void) { - if (!cpu_has_eager_fpu) + if (!boot_cpu_has(X86_FEATURE_EAGER_FPU)) stts(); else clts(); @@ -143,9 +146,18 @@ static void __init fpu__init_system_generic(void) unsigned int xstate_size; EXPORT_SYMBOL_GPL(xstate_size); -/* Enforce that 'MEMBER' is the last field of 'TYPE': */ +/* Get alignment of the TYPE. */ +#define TYPE_ALIGN(TYPE) offsetof(struct { char x; TYPE test; }, test) + +/* + * Enforce that 'MEMBER' is the last field of 'TYPE'. + * + * Align the computed size with alignment of the TYPE, + * because that's how C aligns structs. + */ #define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER) \ - BUILD_BUG_ON(sizeof(TYPE) != offsetofend(TYPE, MEMBER)) + BUILD_BUG_ON(sizeof(TYPE) != ALIGN(offsetofend(TYPE, MEMBER), \ + TYPE_ALIGN(TYPE))) /* * We append the 'struct fpu' to the task_struct: @@ -188,7 +200,7 @@ static void __init fpu__init_task_struct_size(void) */ static void __init fpu__init_system_xstate_size_legacy(void) { - static int on_boot_cpu = 1; + static int on_boot_cpu __initdata = 1; WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; @@ -261,24 +273,56 @@ static void __init fpu__init_system_xstate_size_legacy(void) */ static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO; -static int __init eager_fpu_setup(char *s) +/* + * Find supported xfeatures based on cpu features and command-line input. + * This must be called after fpu__init_parse_early_param() is called and + * xfeatures_mask is enumerated. + */ +u64 __init fpu__get_supported_xfeatures_mask(void) { - if (!strcmp(s, "on")) - eagerfpu = ENABLE; - else if (!strcmp(s, "off")) - eagerfpu = DISABLE; - else if (!strcmp(s, "auto")) - eagerfpu = AUTO; - return 1; + /* Support all xfeatures known to us */ + if (eagerfpu != DISABLE) + return XCNTXT_MASK; + + /* Warning of xfeatures being disabled for no eagerfpu mode */ + if (xfeatures_mask & XFEATURE_MASK_EAGER) { + pr_err("x86/fpu: eagerfpu switching disabled, disabling the following xstate features: 0x%llx.\n", + xfeatures_mask & XFEATURE_MASK_EAGER); + } + + /* Return a mask that masks out all features requiring eagerfpu mode */ + return ~XFEATURE_MASK_EAGER; +} + +/* + * Disable features dependent on eagerfpu. + */ +static void __init fpu__clear_eager_fpu_features(void) +{ + setup_clear_cpu_cap(X86_FEATURE_MPX); + 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("eagerfpu=", eager_fpu_setup); /* * Pick the FPU context switching strategy: + * + * When eagerfpu is AUTO or ENABLE, we ensure it is ENABLE if either of + * the following is true: + * + * (1) the cpu has xsaveopt, as it has the optimization and doing eager + * FPU switching has a relatively low cost compared to a plain xsave; + * (2) the cpu has xsave features (e.g. MPX) that depend on eager FPU + * switching. Should the kernel boot with noxsaveopt, we support MPX + * with eager FPU switching at a higher cost. */ static void __init fpu__init_system_ctx_switch(void) { - static bool on_boot_cpu = 1; + static bool on_boot_cpu __initdata = 1; WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; @@ -286,19 +330,11 @@ static void __init fpu__init_system_ctx_switch(void) WARN_ON_FPU(current->thread.fpu.fpstate_active); current_thread_info()->status = 0; - /* Auto enable eagerfpu for xsaveopt */ - if (cpu_has_xsaveopt && eagerfpu != DISABLE) + if (boot_cpu_has(X86_FEATURE_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 (xfeatures_mask & XFEATURE_MASK_EAGER) + eagerfpu = ENABLE; if (eagerfpu == ENABLE) setup_force_cpu_cap(X86_FEATURE_EAGER_FPU); @@ -307,11 +343,48 @@ static void __init fpu__init_system_ctx_switch(void) } /* + * We parse fpu parameters early because fpu__init_system() is executed + * before parse_early_param(). + */ +static void __init fpu__init_parse_early_param(void) +{ + /* + * No need to check "eagerfpu=auto" again, since it is the + * initial default. + */ + if (cmdline_find_option_bool(boot_command_line, "eagerfpu=off")) { + eagerfpu = DISABLE; + fpu__clear_eager_fpu_features(); + } else if (cmdline_find_option_bool(boot_command_line, "eagerfpu=on")) { + eagerfpu = ENABLE; + } + + if (cmdline_find_option_bool(boot_command_line, "no387")) + setup_clear_cpu_cap(X86_FEATURE_FPU); + + if (cmdline_find_option_bool(boot_command_line, "nofxsr")) { + setup_clear_cpu_cap(X86_FEATURE_FXSR); + setup_clear_cpu_cap(X86_FEATURE_FXSR_OPT); + setup_clear_cpu_cap(X86_FEATURE_XMM); + } + + if (cmdline_find_option_bool(boot_command_line, "noxsave")) + fpu__xstate_clear_all_cpu_caps(); + + if (cmdline_find_option_bool(boot_command_line, "noxsaveopt")) + setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); + + if (cmdline_find_option_bool(boot_command_line, "noxsaves")) + setup_clear_cpu_cap(X86_FEATURE_XSAVES); +} + +/* * 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_parse_early_param(); fpu__init_system_early_generic(c); /* @@ -335,72 +408,3 @@ void __init fpu__init_system(struct cpuinfo_x86 *c) 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 index dc60810c1c74..0bc3490420c5 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -66,7 +66,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, * presence of FP and SSE state. */ if (cpu_has_xsave) - fpu->state.xsave.header.xfeatures |= XSTATE_FPSSE; + fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FPSSE; return ret; } @@ -326,7 +326,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, * presence of FP. */ if (cpu_has_xsave) - fpu->state.xsave.header.xfeatures |= XSTATE_FP; + fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FP; return ret; } diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 50ec9af1bd51..31c6a60505e6 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -56,7 +56,7 @@ 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; + struct _fpstate_32 __user *fp = buf; convert_from_fxsr(&env, tsk); @@ -107,7 +107,7 @@ static inline int save_xstate_epilog(void __user *buf, int ia32_frame) * header as well as change any contents in the memory layout. * xrestore as part of sigreturn will capture all the changes. */ - xfeatures |= XSTATE_FPSSE; + xfeatures |= XFEATURE_MASK_FPSSE; err |= __put_user(xfeatures, (__u32 *)&x->header.xfeatures); @@ -165,7 +165,7 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) 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; + (struct _fpstate_32 __user *) buf) ? -1 : 1; if (fpregs_active()) { /* Save the live register state to the user directly. */ @@ -207,7 +207,7 @@ sanitize_restored_xstate(struct task_struct *tsk, * layout and not enabled by the OS. */ if (fx_only) - header->xfeatures = XSTATE_FPSSE; + header->xfeatures = XFEATURE_MASK_FPSSE; else header->xfeatures &= (xfeatures_mask & xfeatures); } @@ -230,7 +230,7 @@ static inline int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_ { if (use_xsave()) { if ((unsigned long)buf % 64 || fx_only) { - u64 init_bv = xfeatures_mask & ~XSTATE_FPSSE; + u64 init_bv = xfeatures_mask & ~XFEATURE_MASK_FPSSE; copy_kernel_to_xregs(&init_fpstate.xsave, init_bv); return copy_user_to_fxregs(buf); } else { @@ -385,20 +385,19 @@ fpu__alloc_mathframe(unsigned long sp, int ia32_frame, */ 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)) { + if (config_enabled(CONFIG_IA32_EMULATION) || + config_enabled(CONFIG_X86_32)) { + int fsave_header_size = sizeof(struct fregs_state); + fx_sw_reserved_ia32 = fx_sw_reserved; - fx_sw_reserved_ia32.extended_size += fsave_header_size; + fx_sw_reserved_ia32.extended_size = size + fsave_header_size; } } diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 62fc001c7846..d425cda5ae6d 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -31,12 +31,29 @@ static const char *xfeature_names[] = */ 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_offsets[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1}; +static unsigned int xstate_sizes[XFEATURE_MAX] = { [ 0 ... XFEATURE_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; +/* + * Clear all of the X86_FEATURE_* bits that are unavailable + * when the CPU has no XSAVE support. + */ +void fpu__xstate_clear_all_cpu_caps(void) +{ + 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); + setup_clear_cpu_cap(X86_FEATURE_XGETBV1); +} /* * Return whether the system supports a given xfeature. @@ -53,7 +70,7 @@ int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name) /* * 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 + * asks about "XFEATURE_MASK_SSE | XFEATURE_MASK_YMM" we'll print the * missing AVX feature - this is the most informative message * to users: */ @@ -112,7 +129,7 @@ void fpstate_sanitize_xstate(struct fpu *fpu) /* * FP is in init state */ - if (!(xfeatures & XSTATE_FP)) { + if (!(xfeatures & XFEATURE_MASK_FP)) { fx->cwd = 0x37f; fx->swd = 0; fx->twd = 0; @@ -125,7 +142,7 @@ void fpstate_sanitize_xstate(struct fpu *fpu) /* * SSE is in init state */ - if (!(xfeatures & XSTATE_SSE)) + if (!(xfeatures & XFEATURE_MASK_SSE)) memset(&fx->xmm_space[0], 0, 256); /* @@ -169,25 +186,43 @@ void fpu__init_cpu_xstate(void) } /* + * Note that in the future we will likely need a pair of + * functions here: one for user xstates and the other for + * system xstates. For now, they are the same. + */ +static int xfeature_enabled(enum xfeature xfeature) +{ + return !!(xfeatures_mask & (1UL << xfeature)); +} + +/* * 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; + u32 eax, ebx, ecx, edx, i; + /* start at the beginnning of the "extended state" */ + unsigned int last_good_offset = offsetof(struct xregs_state, + extended_state_area); + + for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { + if (!xfeature_enabled(i)) + continue; + + cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); + xstate_offsets[i] = ebx; + xstate_sizes[i] = eax; + /* + * In our xstate size checks, we assume that the + * highest-numbered xstate feature has the + * highest offset in the buffer. Ensure it does. + */ + WARN_ONCE(last_good_offset > xstate_offsets[i], + "x86/fpu: misordered xstate at %d\n", last_good_offset); + last_good_offset = xstate_offsets[i]; - printk(KERN_INFO "x86/fpu: xstate_offset[%d]: %04x, xstate_sizes[%d]: %04x\n", leaf, ebx, leaf, eax); + printk(KERN_INFO "x86/fpu: xstate_offset[%d]: %4d, xstate_sizes[%d]: %4d\n", i, ebx, i, eax); } } @@ -204,14 +239,14 @@ static void __init print_xstate_feature(u64 xstate_mask) */ 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); + print_xstate_feature(XFEATURE_MASK_FP); + print_xstate_feature(XFEATURE_MASK_SSE); + print_xstate_feature(XFEATURE_MASK_YMM); + print_xstate_feature(XFEATURE_MASK_BNDREGS); + print_xstate_feature(XFEATURE_MASK_BNDCSR); + print_xstate_feature(XFEATURE_MASK_OPMASK); + print_xstate_feature(XFEATURE_MASK_ZMM_Hi256); + print_xstate_feature(XFEATURE_MASK_Hi16_ZMM); } /* @@ -233,8 +268,8 @@ static void __init setup_xstate_comp(void) 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)) { + for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { + if (xfeature_enabled(i)) { xstate_comp_offsets[i] = xstate_offsets[i]; xstate_comp_sizes[i] = xstate_sizes[i]; } @@ -242,15 +277,16 @@ static void __init setup_xstate_comp(void) return; } - xstate_comp_offsets[2] = FXSAVE_SIZE + XSAVE_HDR_SIZE; + xstate_comp_offsets[FIRST_EXTENDED_XFEATURE] = + FXSAVE_SIZE + XSAVE_HDR_SIZE; - for (i = 2; i < xfeatures_nr; i++) { - if (test_bit(i, (unsigned long *)&xfeatures_mask)) + for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { + if (xfeature_enabled(i)) xstate_comp_sizes[i] = xstate_sizes[i]; else xstate_comp_sizes[i] = 0; - if (i > 2) + if (i > FIRST_EXTENDED_XFEATURE) xstate_comp_offsets[i] = xstate_comp_offsets[i-1] + xstate_comp_sizes[i-1]; @@ -262,7 +298,7 @@ static void __init setup_xstate_comp(void) */ static void __init setup_init_fpu_buf(void) { - static int on_boot_cpu = 1; + static int on_boot_cpu __initdata = 1; WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; @@ -290,27 +326,280 @@ static void __init setup_init_fpu_buf(void) copy_xregs_to_kernel_booting(&init_fpstate.xsave); } +static int xfeature_is_supervisor(int xfeature_nr) +{ + /* + * We currently do not support supervisor states, but if + * we did, we could find out like this. + * + * SDM says: If state component i is a user state component, + * ECX[0] return 0; if state component i is a supervisor + * state component, ECX[0] returns 1. + u32 eax, ebx, ecx, edx; + cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx; + return !!(ecx & 1); + */ + return 0; +} +/* +static int xfeature_is_user(int xfeature_nr) +{ + return !xfeature_is_supervisor(xfeature_nr); +} +*/ + +/* + * This check is important because it is easy to get XSTATE_* + * confused with XSTATE_BIT_*. + */ +#define CHECK_XFEATURE(nr) do { \ + WARN_ON(nr < FIRST_EXTENDED_XFEATURE); \ + WARN_ON(nr >= XFEATURE_MAX); \ +} while (0) + +/* + * We could cache this like xstate_size[], but we only use + * it here, so it would be a waste of space. + */ +static int xfeature_is_aligned(int xfeature_nr) +{ + u32 eax, ebx, ecx, edx; + + CHECK_XFEATURE(xfeature_nr); + cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx); + /* + * The value returned by ECX[1] indicates the alignment + * of state component i when the compacted format + * of the extended region of an XSAVE area is used + */ + return !!(ecx & 2); +} + +static int xfeature_uncompacted_offset(int xfeature_nr) +{ + u32 eax, ebx, ecx, edx; + + CHECK_XFEATURE(xfeature_nr); + cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx); + return ebx; +} + +static int xfeature_size(int xfeature_nr) +{ + u32 eax, ebx, ecx, edx; + + CHECK_XFEATURE(xfeature_nr); + cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx); + return eax; +} + +/* + * 'XSAVES' implies two different things: + * 1. saving of supervisor/system state + * 2. using the compacted format + * + * Use this function when dealing with the compacted format so + * that it is obvious which aspect of 'XSAVES' is being handled + * by the calling code. + */ +static int using_compacted_format(void) +{ + return cpu_has_xsaves; +} + +static void __xstate_dump_leaves(void) +{ + int i; + u32 eax, ebx, ecx, edx; + static int should_dump = 1; + + if (!should_dump) + return; + should_dump = 0; + /* + * Dump out a few leaves past the ones that we support + * just in case there are some goodies up there + */ + for (i = 0; i < XFEATURE_MAX + 10; i++) { + cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); + pr_warn("CPUID[%02x, %02x]: eax=%08x ebx=%08x ecx=%08x edx=%08x\n", + XSTATE_CPUID, i, eax, ebx, ecx, edx); + } +} + +#define XSTATE_WARN_ON(x) do { \ + if (WARN_ONCE(x, "XSAVE consistency problem, dumping leaves")) { \ + __xstate_dump_leaves(); \ + } \ +} while (0) + +#define XCHECK_SZ(sz, nr, nr_macro, __struct) do { \ + if ((nr == nr_macro) && \ + WARN_ONCE(sz != sizeof(__struct), \ + "%s: struct is %zu bytes, cpu state %d bytes\n", \ + __stringify(nr_macro), sizeof(__struct), sz)) { \ + __xstate_dump_leaves(); \ + } \ +} while (0) + +/* + * We have a C struct for each 'xstate'. We need to ensure + * that our software representation matches what the CPU + * tells us about the state's size. + */ +static void check_xstate_against_struct(int nr) +{ + /* + * Ask the CPU for the size of the state. + */ + int sz = xfeature_size(nr); + /* + * Match each CPU state with the corresponding software + * structure. + */ + XCHECK_SZ(sz, nr, XFEATURE_YMM, struct ymmh_struct); + XCHECK_SZ(sz, nr, XFEATURE_BNDREGS, struct mpx_bndreg_state); + XCHECK_SZ(sz, nr, XFEATURE_BNDCSR, struct mpx_bndcsr_state); + XCHECK_SZ(sz, nr, XFEATURE_OPMASK, struct avx_512_opmask_state); + XCHECK_SZ(sz, nr, XFEATURE_ZMM_Hi256, struct avx_512_zmm_uppers_state); + XCHECK_SZ(sz, nr, XFEATURE_Hi16_ZMM, struct avx_512_hi16_state); + + /* + * Make *SURE* to add any feature numbers in below if + * there are "holes" in the xsave state component + * numbers. + */ + if ((nr < XFEATURE_YMM) || + (nr >= XFEATURE_MAX)) { + WARN_ONCE(1, "no structure for xstate: %d\n", nr); + XSTATE_WARN_ON(1); + } +} + +/* + * This essentially double-checks what the cpu told us about + * how large the XSAVE buffer needs to be. We are recalculating + * it to be safe. + */ +static void do_extra_xstate_size_checks(void) +{ + int paranoid_xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE; + int i; + + for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { + if (!xfeature_enabled(i)) + continue; + + check_xstate_against_struct(i); + /* + * Supervisor state components can be managed only by + * XSAVES, which is compacted-format only. + */ + if (!using_compacted_format()) + XSTATE_WARN_ON(xfeature_is_supervisor(i)); + + /* Align from the end of the previous feature */ + if (xfeature_is_aligned(i)) + paranoid_xstate_size = ALIGN(paranoid_xstate_size, 64); + /* + * The offset of a given state in the non-compacted + * format is given to us in a CPUID leaf. We check + * them for being ordered (increasing offsets) in + * setup_xstate_features(). + */ + if (!using_compacted_format()) + paranoid_xstate_size = xfeature_uncompacted_offset(i); + /* + * The compacted-format offset always depends on where + * the previous state ended. + */ + paranoid_xstate_size += xfeature_size(i); + } + XSTATE_WARN_ON(paranoid_xstate_size != xstate_size); +} + /* * Calculate total size of enabled xstates in XCR0/xfeatures_mask. + * + * Note the SDM's wording here. "sub-function 0" only enumerates + * the size of the *user* states. If we use it to size a buffer + * that we use 'XSAVES' on, we could potentially overflow the + * buffer because 'XSAVES' saves system states too. + * + * Note that we do not currently set any bits on IA32_XSS so + * 'XCR0 | IA32_XSS == XCR0' for now. */ -static void __init init_xstate_size(void) +static unsigned int __init calculate_xstate_size(void) { unsigned int eax, ebx, ecx, edx; - int i; + unsigned int calculated_xstate_size; if (!cpu_has_xsaves) { + /* + * - CPUID function 0DH, sub-function 0: + * EBX enumerates the size (in bytes) required by + * the XSAVE instruction for an XSAVE area + * containing all the *user* state components + * corresponding to bits currently set in XCR0. + */ cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); - xstate_size = ebx; - return; + calculated_xstate_size = ebx; + } else { + /* + * - CPUID function 0DH, sub-function 1: + * EBX enumerates the size (in bytes) required by + * the XSAVES instruction for an XSAVE area + * containing all the state components + * corresponding to bits currently set in + * XCR0 | IA32_XSS. + */ + cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx); + calculated_xstate_size = ebx; } + return calculated_xstate_size; +} - 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; - } - } +/* + * Will the runtime-enumerated 'xstate_size' fit in the init + * task's statically-allocated buffer? + */ +static bool is_supported_xstate_size(unsigned int test_xstate_size) +{ + if (test_xstate_size <= sizeof(union fpregs_state)) + return true; + + pr_warn("x86/fpu: xstate buffer too small (%zu < %d), disabling xsave\n", + sizeof(union fpregs_state), test_xstate_size); + return false; +} + +static int init_xstate_size(void) +{ + /* Recompute the context size for enabled features: */ + unsigned int possible_xstate_size = calculate_xstate_size(); + + /* Ensure we have the space to store all enabled: */ + if (!is_supported_xstate_size(possible_xstate_size)) + return -EINVAL; + + /* + * The size is OK, we are definitely going to use xsave, + * make it known to the world that we need more space. + */ + xstate_size = possible_xstate_size; + do_extra_xstate_size_checks(); + return 0; +} + +/* + * We enabled the XSAVE hardware, but something went wrong and + * we can not use it. Disable it. + */ +static void fpu__init_disable_system_xstate(void) +{ + xfeatures_mask = 0; + cr4_clear_bits(X86_CR4_OSXSAVE); + fpu__xstate_clear_all_cpu_caps(); } /* @@ -320,7 +609,8 @@ static void __init init_xstate_size(void) void __init fpu__init_system_xstate(void) { unsigned int eax, ebx, ecx, edx; - static int on_boot_cpu = 1; + static int on_boot_cpu __initdata = 1; + int err; WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; @@ -338,26 +628,28 @@ void __init fpu__init_system_xstate(void) cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); xfeatures_mask = eax + ((u64)edx << 32); - if ((xfeatures_mask & XSTATE_FPSSE) != XSTATE_FPSSE) { + if ((xfeatures_mask & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_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; + xfeatures_mask &= fpu__get_supported_xfeatures_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(); + err = init_xstate_size(); + if (err) { + /* something went wrong, boot without any XSAVE support */ + fpu__init_disable_system_xstate(); + return; + } 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", + pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n", xfeatures_mask, xstate_size, cpu_has_xsaves ? "compacted" : "standard"); @@ -388,7 +680,7 @@ void fpu__resume_cpu(void) * 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...) + * XFEATURE_MASK_FP, XFEATURE_MASK_SSE, etc...) * Output: * address of the state in the xsave area, or NULL if the * field is not present in the xsave buffer. @@ -402,7 +694,6 @@ void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature) 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 @@ -439,8 +730,8 @@ EXPORT_SYMBOL_GPL(get_xsave_addr); * 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...) + * @xsave_state: state which is defined in xsave.h (e.g. XFEATURE_MASK_FP, + * XFEATURE_MASK_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'. diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 8b7b0a51e742..29408d6d6626 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -105,14 +105,14 @@ ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code, { unsigned char replaced[MCOUNT_INSN_SIZE]; + ftrace_expected = old_code; + /* - * Note: Due to modules and __init, code can - * disappear and change, we need to protect against faulting - * as well as code changing. We do this by using the - * probe_kernel_* functions. - * - * No real locking needed, this code is run through - * kstop_machine, or before SMP starts. + * Note: + * We are paranoid about modifying text, as if a bug was to happen, it + * could cause us to read or write to someplace that could cause harm. + * Carefully read and modify the code with probe_kernel_*(), and make + * sure what we read is what we expected it to be before modifying it. */ /* read the text we want to modify */ @@ -154,6 +154,8 @@ int ftrace_make_nop(struct module *mod, if (addr == MCOUNT_ADDR) return ftrace_modify_code_direct(rec->ip, old, new); + ftrace_expected = NULL; + /* Normal cases use add_brk_on_nop */ WARN_ONCE(1, "invalid use of ftrace_make_nop"); return -EINVAL; @@ -220,6 +222,7 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { WARN_ON(1); + ftrace_expected = NULL; return -EINVAL; } @@ -314,6 +317,8 @@ static int add_break(unsigned long ip, const char *old) if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) return -EFAULT; + ftrace_expected = old; + /* Make sure it is what we expect it to be */ if (memcmp(replaced, old, MCOUNT_INSN_SIZE) != 0) return -EINVAL; @@ -413,6 +418,8 @@ static int remove_breakpoint(struct dyn_ftrace *rec) ftrace_addr = ftrace_get_addr_curr(rec); nop = ftrace_call_replace(ip, ftrace_addr); + ftrace_expected = nop; + if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) return -EINVAL; } @@ -556,6 +563,7 @@ void ftrace_replace_code(int enable) run_sync(); report = "updating code"; + count = 0; for_ftrace_rec_iter(iter) { rec = ftrace_rec_iter_record(iter); @@ -563,11 +571,13 @@ void ftrace_replace_code(int enable) ret = add_update(rec, enable); if (ret) goto remove_breakpoints; + count++; } run_sync(); report = "removing breakpoints"; + count = 0; for_ftrace_rec_iter(iter) { rec = ftrace_rec_iter_record(iter); @@ -575,6 +585,7 @@ void ftrace_replace_code(int enable) ret = finish_update(rec, enable); if (ret) goto remove_breakpoints; + count++; } run_sync(); diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 0e2d96ffd158..6bc9ae24b6d2 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -152,7 +152,7 @@ ENTRY(startup_32) movl %eax, pa(olpc_ofw_pgd) #endif -#ifdef CONFIG_MICROCODE_EARLY +#ifdef CONFIG_MICROCODE /* Early load ucode on BSP. */ call load_ucode_bsp #endif @@ -311,12 +311,11 @@ ENTRY(startup_32_smp) movl %eax,%ss leal -__PAGE_OFFSET(%ecx),%esp -#ifdef CONFIG_MICROCODE_EARLY +#ifdef CONFIG_MICROCODE /* Early load ucode on AP. */ call load_ucode_ap #endif - default_entry: #define CR0_STATE (X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \ X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \ diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 1d40ca8a73f2..ffdc0e860390 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -65,6 +65,9 @@ startup_64: * tables and then reload them. */ + /* Sanitize CPU configuration */ + call verify_cpu + /* * Compute the delta between the address I am compiled to run at and the * address I am actually running at. @@ -174,6 +177,9 @@ ENTRY(secondary_startup_64) * after the boot processor executes this code. */ + /* Sanitize CPU configuration */ + call verify_cpu + movq $(init_level4_pgt - __START_KERNEL_map), %rax 1: @@ -288,6 +294,8 @@ ENTRY(secondary_startup_64) pushq %rax # target address in negative space lretq +#include "verify_cpu.S" + #ifdef CONFIG_HOTPLUG_CPU /* * Boot CPU0 entry point. It's called from play_dead(). Everything has been set diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 10757d0a3fcf..b8e6ff5cd5d0 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -37,10 +37,10 @@ */ unsigned long hpet_address; u8 hpet_blockid; /* OS timer block num */ -u8 hpet_msi_disable; +bool hpet_msi_disable; #ifdef CONFIG_PCI_MSI -static unsigned long hpet_num_timers; +static unsigned int hpet_num_timers; #endif static void __iomem *hpet_virt_address; @@ -86,9 +86,9 @@ static inline void hpet_clear_mapping(void) /* * HPET command line enable / disable */ -int boot_hpet_disable; -int hpet_force_user; -static int hpet_verbose; +bool boot_hpet_disable; +bool hpet_force_user; +static bool hpet_verbose; static int __init hpet_setup(char *str) { @@ -98,11 +98,11 @@ static int __init hpet_setup(char *str) if (next) *next++ = 0; if (!strncmp("disable", str, 7)) - boot_hpet_disable = 1; + boot_hpet_disable = true; if (!strncmp("force", str, 5)) - hpet_force_user = 1; + hpet_force_user = true; if (!strncmp("verbose", str, 7)) - hpet_verbose = 1; + hpet_verbose = true; str = next; } return 1; @@ -111,7 +111,7 @@ __setup("hpet=", hpet_setup); static int __init disable_hpet(char *str) { - boot_hpet_disable = 1; + boot_hpet_disable = true; return 1; } __setup("nohpet", disable_hpet); @@ -124,7 +124,7 @@ static inline int is_hpet_capable(void) /* * HPET timer interrupt enable / disable */ -static int hpet_legacy_int_enabled; +static bool hpet_legacy_int_enabled; /** * is_hpet_enabled - check whether the hpet timer interrupt is enabled @@ -226,26 +226,11 @@ static void hpet_reserve_platform_timers(unsigned int id) { } */ static unsigned long hpet_freq; -static void hpet_legacy_set_mode(enum clock_event_mode mode, - struct clock_event_device *evt); -static int hpet_legacy_next_event(unsigned long delta, - struct clock_event_device *evt); - -/* - * The hpet clock event device - */ -static struct clock_event_device hpet_clockevent = { - .name = "hpet", - .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT, - .set_mode = hpet_legacy_set_mode, - .set_next_event = hpet_legacy_next_event, - .irq = 0, - .rating = 50, -}; +static struct clock_event_device hpet_clockevent; static void hpet_stop_counter(void) { - unsigned long cfg = hpet_readl(HPET_CFG); + u32 cfg = hpet_readl(HPET_CFG); cfg &= ~HPET_CFG_ENABLE; hpet_writel(cfg, HPET_CFG); } @@ -287,7 +272,7 @@ static void hpet_enable_legacy_int(void) cfg |= HPET_CFG_LEGACY; hpet_writel(cfg, HPET_CFG); - hpet_legacy_int_enabled = 1; + hpet_legacy_int_enabled = true; } static void hpet_legacy_clockevent_register(void) @@ -306,64 +291,74 @@ static void hpet_legacy_clockevent_register(void) printk(KERN_DEBUG "hpet clockevent registered\n"); } -static void hpet_set_mode(enum clock_event_mode mode, - struct clock_event_device *evt, int timer) +static int hpet_set_periodic(struct clock_event_device *evt, int timer) { unsigned int cfg, cmp, now; uint64_t delta; - switch (mode) { - case CLOCK_EVT_MODE_PERIODIC: - hpet_stop_counter(); - delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * evt->mult; - delta >>= evt->shift; - now = hpet_readl(HPET_COUNTER); - cmp = now + (unsigned int) delta; - cfg = hpet_readl(HPET_Tn_CFG(timer)); - cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC | - HPET_TN_SETVAL | HPET_TN_32BIT; - hpet_writel(cfg, HPET_Tn_CFG(timer)); - hpet_writel(cmp, HPET_Tn_CMP(timer)); - udelay(1); - /* - * HPET on AMD 81xx needs a second write (with HPET_TN_SETVAL - * cleared) to T0_CMP to set the period. The HPET_TN_SETVAL - * bit is automatically cleared after the first write. - * (See AMD-8111 HyperTransport I/O Hub Data Sheet, - * Publication # 24674) - */ - hpet_writel((unsigned int) delta, HPET_Tn_CMP(timer)); - hpet_start_counter(); - hpet_print_config(); - break; + hpet_stop_counter(); + delta = ((uint64_t)(NSEC_PER_SEC / HZ)) * evt->mult; + delta >>= evt->shift; + now = hpet_readl(HPET_COUNTER); + cmp = now + (unsigned int)delta; + cfg = hpet_readl(HPET_Tn_CFG(timer)); + cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC | HPET_TN_SETVAL | + HPET_TN_32BIT; + hpet_writel(cfg, HPET_Tn_CFG(timer)); + hpet_writel(cmp, HPET_Tn_CMP(timer)); + udelay(1); + /* + * HPET on AMD 81xx needs a second write (with HPET_TN_SETVAL + * cleared) to T0_CMP to set the period. The HPET_TN_SETVAL + * bit is automatically cleared after the first write. + * (See AMD-8111 HyperTransport I/O Hub Data Sheet, + * Publication # 24674) + */ + hpet_writel((unsigned int)delta, HPET_Tn_CMP(timer)); + hpet_start_counter(); + hpet_print_config(); - case CLOCK_EVT_MODE_ONESHOT: - cfg = hpet_readl(HPET_Tn_CFG(timer)); - cfg &= ~HPET_TN_PERIODIC; - cfg |= HPET_TN_ENABLE | HPET_TN_32BIT; - hpet_writel(cfg, HPET_Tn_CFG(timer)); - break; + return 0; +} - case CLOCK_EVT_MODE_UNUSED: - case CLOCK_EVT_MODE_SHUTDOWN: - cfg = hpet_readl(HPET_Tn_CFG(timer)); - cfg &= ~HPET_TN_ENABLE; - hpet_writel(cfg, HPET_Tn_CFG(timer)); - break; +static int hpet_set_oneshot(struct clock_event_device *evt, int timer) +{ + unsigned int cfg; - case CLOCK_EVT_MODE_RESUME: - if (timer == 0) { - hpet_enable_legacy_int(); - } else { - struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); - 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); - } - hpet_print_config(); - break; + cfg = hpet_readl(HPET_Tn_CFG(timer)); + cfg &= ~HPET_TN_PERIODIC; + cfg |= HPET_TN_ENABLE | HPET_TN_32BIT; + hpet_writel(cfg, HPET_Tn_CFG(timer)); + + return 0; +} + +static int hpet_shutdown(struct clock_event_device *evt, int timer) +{ + unsigned int cfg; + + cfg = hpet_readl(HPET_Tn_CFG(timer)); + cfg &= ~HPET_TN_ENABLE; + hpet_writel(cfg, HPET_Tn_CFG(timer)); + + return 0; +} + +static int hpet_resume(struct clock_event_device *evt, int timer) +{ + if (!timer) { + hpet_enable_legacy_int(); + } else { + struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); + + 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); } + hpet_print_config(); + + return 0; } static int hpet_next_event(unsigned long delta, @@ -403,10 +398,24 @@ static int hpet_next_event(unsigned long delta, return res < HPET_MIN_CYCLES ? -ETIME : 0; } -static void hpet_legacy_set_mode(enum clock_event_mode mode, - struct clock_event_device *evt) +static int hpet_legacy_shutdown(struct clock_event_device *evt) +{ + return hpet_shutdown(evt, 0); +} + +static int hpet_legacy_set_oneshot(struct clock_event_device *evt) { - hpet_set_mode(mode, evt, 0); + return hpet_set_oneshot(evt, 0); +} + +static int hpet_legacy_set_periodic(struct clock_event_device *evt) +{ + return hpet_set_periodic(evt, 0); +} + +static int hpet_legacy_resume(struct clock_event_device *evt) +{ + return hpet_resume(evt, 0); } static int hpet_legacy_next_event(unsigned long delta, @@ -416,6 +425,22 @@ static int hpet_legacy_next_event(unsigned long delta, } /* + * The hpet clock event device + */ +static struct clock_event_device hpet_clockevent = { + .name = "hpet", + .features = CLOCK_EVT_FEAT_PERIODIC | + CLOCK_EVT_FEAT_ONESHOT, + .set_state_periodic = hpet_legacy_set_periodic, + .set_state_oneshot = hpet_legacy_set_oneshot, + .set_state_shutdown = hpet_legacy_shutdown, + .tick_resume = hpet_legacy_resume, + .set_next_event = hpet_legacy_next_event, + .irq = 0, + .rating = 50, +}; + +/* * HPET MSI Support */ #ifdef CONFIG_PCI_MSI @@ -426,7 +451,7 @@ static struct irq_domain *hpet_domain; void hpet_msi_unmask(struct irq_data *data) { - struct hpet_dev *hdev = data->handler_data; + struct hpet_dev *hdev = irq_data_get_irq_handler_data(data); unsigned int cfg; /* unmask it */ @@ -437,7 +462,7 @@ void hpet_msi_unmask(struct irq_data *data) void hpet_msi_mask(struct irq_data *data) { - struct hpet_dev *hdev = data->handler_data; + struct hpet_dev *hdev = irq_data_get_irq_handler_data(data); unsigned int cfg; /* mask it */ @@ -459,11 +484,32 @@ void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg) msg->address_hi = 0; } -static void hpet_msi_set_mode(enum clock_event_mode mode, - struct clock_event_device *evt) +static int hpet_msi_shutdown(struct clock_event_device *evt) { struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); - hpet_set_mode(mode, evt, hdev->num); + + return hpet_shutdown(evt, hdev->num); +} + +static int hpet_msi_set_oneshot(struct clock_event_device *evt) +{ + struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); + + return hpet_set_oneshot(evt, hdev->num); +} + +static int hpet_msi_set_periodic(struct clock_event_device *evt) +{ + struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); + + return hpet_set_periodic(evt, hdev->num); +} + +static int hpet_msi_resume(struct clock_event_device *evt) +{ + struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); + + return hpet_resume(evt, hdev->num); } static int hpet_msi_next_event(unsigned long delta, @@ -523,10 +569,14 @@ static void init_one_hpet_msi_clockevent(struct hpet_dev *hdev, int cpu) evt->rating = 110; evt->features = CLOCK_EVT_FEAT_ONESHOT; - if (hdev->flags & HPET_DEV_PERI_CAP) + if (hdev->flags & HPET_DEV_PERI_CAP) { evt->features |= CLOCK_EVT_FEAT_PERIODIC; + evt->set_state_periodic = hpet_msi_set_periodic; + } - evt->set_mode = hpet_msi_set_mode; + evt->set_state_shutdown = hpet_msi_shutdown; + evt->set_state_oneshot = hpet_msi_set_oneshot; + evt->tick_resume = hpet_msi_resume; evt->set_next_event = hpet_msi_next_event; evt->cpumask = cpumask_of(hdev->cpu); @@ -735,7 +785,7 @@ static int hpet_clocksource_register(void) /* Verify whether hpet counter works */ t1 = hpet_readl(HPET_COUNTER); - rdtscll(start); + start = rdtsc(); /* * We don't know the TSC frequency yet, but waiting for @@ -745,7 +795,7 @@ static int hpet_clocksource_register(void) */ do { rep_nop(); - rdtscll(now); + now = rdtsc(); } while ((now - start) < 200000UL); if (t1 == hpet_readl(HPET_COUNTER)) { @@ -933,7 +983,7 @@ void hpet_disable(void) cfg = *hpet_boot_cfg; else if (hpet_legacy_int_enabled) { cfg &= ~HPET_CFG_LEGACY; - hpet_legacy_int_enabled = 0; + hpet_legacy_int_enabled = false; } cfg &= ~HPET_CFG_ENABLE; hpet_writel(cfg, HPET_CFG); @@ -1071,8 +1121,7 @@ EXPORT_SYMBOL_GPL(hpet_rtc_timer_init); static void hpet_disable_rtc_channel(void) { - unsigned long cfg; - cfg = hpet_readl(HPET_T1_CFG); + u32 cfg = hpet_readl(HPET_T1_CFG); cfg &= ~HPET_TN_ENABLE; hpet_writel(cfg, HPET_T1_CFG); } diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 7114ba220fd4..2bcfb5f2bc44 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -32,6 +32,7 @@ #include <linux/irqflags.h> #include <linux/notifier.h> #include <linux/kallsyms.h> +#include <linux/kprobes.h> #include <linux/percpu.h> #include <linux/kdebug.h> #include <linux/kernel.h> @@ -179,7 +180,11 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp) va = info->address; len = bp->attr.bp_len; - return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE); + /* + * We don't need to worry about va + len - 1 overflowing: + * we already require that va is aligned to a multiple of len. + */ + return (va >= TASK_SIZE_MAX) || ((va + len - 1) >= TASK_SIZE_MAX); } int arch_bp_generic_fields(int x86_len, int x86_type, @@ -243,6 +248,20 @@ static int arch_build_bp_info(struct perf_event *bp) info->type = X86_BREAKPOINT_RW; break; case HW_BREAKPOINT_X: + /* + * We don't allow kernel breakpoints in places that are not + * acceptable for kprobes. On non-kprobes kernels, we don't + * allow kernel breakpoints at all. + */ + if (bp->attr.bp_addr >= TASK_SIZE_MAX) { +#ifdef CONFIG_KPROBES + if (within_kprobe_blacklist(bp->attr.bp_addr)) + return -EINVAL; +#else + return -EINVAL; +#endif + } + info->type = X86_BREAKPOINT_EXECUTE; /* * x86 inst breakpoints need to have a specific undefined len. @@ -276,10 +295,22 @@ static int arch_build_bp_info(struct perf_event *bp) break; #endif default: + /* AMD range breakpoint */ if (!is_power_of_2(bp->attr.bp_len)) return -EINVAL; - if (!cpu_has_bpext) + if (bp->attr.bp_addr & (bp->attr.bp_len - 1)) + return -EINVAL; + + if (!boot_cpu_has(X86_FEATURE_BPEXT)) return -EOPNOTSUPP; + + /* + * It's impossible to use a range breakpoint to fake out + * user vs kernel detection because bp_len - 1 can't + * have the high bit set. If we ever allow range instruction + * breakpoints, then we'll have to check for kprobe-blacklisted + * addresses anywhere in the range. + */ info->mask = bp->attr.bp_len - 1; info->len = X86_BREAKPOINT_LEN_1; } diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c index f2b96de3c7c1..efb82f07b29c 100644 --- a/arch/x86/kernel/i8253.c +++ b/arch/x86/kernel/i8253.c @@ -34,7 +34,7 @@ static int __init init_pit_clocksource(void) * - when local APIC timer is active (PIT is switched off) */ if (num_possible_cpus() > 1 || is_hpet_enabled() || - i8253_clockevent.mode != CLOCK_EVT_MODE_PERIODIC) + !clockevent_state_periodic(&i8253_clockevent)) return 0; return clocksource_i8253_init(); diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 16cb827a5b27..be22f5a2192e 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -295,16 +295,11 @@ static void unmask_8259A(void) raw_spin_unlock_irqrestore(&i8259A_lock, flags); } -static void init_8259A(int auto_eoi) +static int probe_8259A(void) { unsigned long flags; unsigned char probe_val = ~(1 << PIC_CASCADE_IR); unsigned char new_val; - - i8259A_auto_eoi = auto_eoi; - - raw_spin_lock_irqsave(&i8259A_lock, flags); - /* * Check to see if we have a PIC. * Mask all except the cascade and read @@ -312,16 +307,28 @@ static void init_8259A(int auto_eoi) * have a PIC, we will read 0xff as opposed to the * value we wrote. */ + raw_spin_lock_irqsave(&i8259A_lock, flags); + outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-2 */ outb(probe_val, PIC_MASTER_IMR); new_val = inb(PIC_MASTER_IMR); if (new_val != probe_val) { printk(KERN_INFO "Using NULL legacy PIC\n"); legacy_pic = &null_legacy_pic; - raw_spin_unlock_irqrestore(&i8259A_lock, flags); - return; } + raw_spin_unlock_irqrestore(&i8259A_lock, flags); + return nr_legacy_irqs(); +} + +static void init_8259A(int auto_eoi) +{ + unsigned long flags; + + i8259A_auto_eoi = auto_eoi; + + raw_spin_lock_irqsave(&i8259A_lock, flags); + outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */ /* @@ -379,6 +386,10 @@ static int legacy_pic_irq_pending_noop(unsigned int irq) { return 0; } +static int legacy_pic_probe(void) +{ + return 0; +} struct legacy_pic null_legacy_pic = { .nr_legacy_irqs = 0, @@ -388,6 +399,7 @@ struct legacy_pic null_legacy_pic = { .mask_all = legacy_pic_noop, .restore_mask = legacy_pic_noop, .init = legacy_pic_int_noop, + .probe = legacy_pic_probe, .irq_pending = legacy_pic_irq_pending_noop, .make_irq = legacy_pic_uint_noop, }; @@ -400,6 +412,7 @@ struct legacy_pic default_legacy_pic = { .mask_all = mask_8259A, .restore_mask = unmask_8259A, .init = init_8259A, + .probe = probe_8259A, .irq_pending = i8259A_irq_pending, .make_irq = make_8259A_irq, }; diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index c7dfe1be784e..f8062aaf5df9 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -139,10 +139,13 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_puts(p, " Machine check polls\n"); #endif #if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN) - seq_printf(p, "%*s: ", prec, "HYP"); - for_each_online_cpu(j) - seq_printf(p, "%10u ", irq_stats(j)->irq_hv_callback_count); - seq_puts(p, " Hypervisor callback interrupts\n"); + if (test_bit(HYPERVISOR_CALLBACK_VECTOR, used_vectors)) { + seq_printf(p, "%*s: ", prec, "HYP"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", + irq_stats(j)->irq_hv_callback_count); + seq_puts(p, " Hypervisor callback interrupts\n"); + } #endif seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count)); #if defined(CONFIG_X86_IO_APIC) @@ -211,24 +214,38 @@ u64 arch_irq_stat(void) __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); - + struct irq_desc * desc; /* high bit used in ret_from_ code */ unsigned vector = ~regs->orig_ax; - unsigned irq; + + /* + * NB: Unlike exception entries, IRQ entries do not reliably + * handle context tracking in the low-level entry code. This is + * because syscall entries execute briefly with IRQs on before + * updating context tracking state, so we can take an IRQ from + * kernel mode with CONTEXT_USER. The low-level entry code only + * updates the context if we came from user mode, so we won't + * switch to CONTEXT_KERNEL. We'll fix that once the syscall + * code is cleaned up enough that we can cleanly defer enabling + * IRQs. + */ entering_irq(); - irq = __this_cpu_read(vector_irq[vector]); + /* entering_irq() tells RCU that we're not quiescent. Check it. */ + RCU_LOCKDEP_WARN(!rcu_is_watching(), "IRQ failed to wake up RCU"); + + desc = __this_cpu_read(vector_irq[vector]); - if (!handle_irq(irq, regs)) { + if (!handle_irq(desc, regs)) { ack_APIC_irq(); - if (irq != VECTOR_RETRIGGERED) { - pr_emerg_ratelimited("%s: %d.%d No irq handler for vector (irq %d)\n", + if (desc != VECTOR_RETRIGGERED) { + pr_emerg_ratelimited("%s: %d.%d No irq handler for vector\n", __func__, smp_processor_id(), - vector, irq); + vector); } else { - __this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED); + __this_cpu_write(vector_irq[vector], VECTOR_UNUSED); } } @@ -330,10 +347,10 @@ static struct cpumask affinity_new, online_new; */ int check_irq_vectors_for_cpu_disable(void) { - int irq, cpu; unsigned int this_cpu, vector, this_count, count; struct irq_desc *desc; struct irq_data *data; + int cpu; this_cpu = smp_processor_id(); cpumask_copy(&online_new, cpu_online_mask); @@ -341,47 +358,43 @@ int check_irq_vectors_for_cpu_disable(void) this_count = 0; for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { - irq = __this_cpu_read(vector_irq[vector]); - if (irq >= 0) { - desc = irq_to_desc(irq); - 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)) { - raw_spin_unlock(&desc->lock); - continue; - } + desc = __this_cpu_read(vector_irq[vector]); + if (IS_ERR_OR_NULL(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, + irq_data_get_affinity_mask(data)); + cpumask_clear_cpu(this_cpu, &affinity_new); + /* Do not count inactive or per-cpu irqs. */ + if (!irq_desc_has_action(desc) || irqd_is_per_cpu(data)) { raw_spin_unlock(&desc->lock); - /* - * A single irq may be mapped to multiple - * cpu's vector_irq[] (for example IOAPIC cluster - * mode). In this case we have two - * possibilities: - * - * 1) the resulting affinity mask is empty; that is - * this the down'd cpu is the last cpu in the irq's - * affinity mask, or - * - * 2) the resulting affinity mask is no longer - * a subset of the online cpus but the affinity - * mask is not zero; that is the down'd cpu is the - * last online cpu in a user set affinity mask. - */ - if (cpumask_empty(&affinity_new) || - !cpumask_subset(&affinity_new, &online_new)) - this_count++; + continue; } + + raw_spin_unlock(&desc->lock); + /* + * A single irq may be mapped to multiple cpu's + * vector_irq[] (for example IOAPIC cluster mode). In + * this case we have two possibilities: + * + * 1) the resulting affinity mask is empty; that is + * this the down'd cpu is the last cpu in the irq's + * affinity mask, or + * + * 2) the resulting affinity mask is no longer a + * subset of the online cpus but the affinity mask is + * not zero; that is the down'd cpu is the last online + * cpu in a user set affinity mask. + */ + if (cpumask_empty(&affinity_new) || + !cpumask_subset(&affinity_new, &online_new)) + this_count++; } count = 0; @@ -400,8 +413,8 @@ int check_irq_vectors_for_cpu_disable(void) for (vector = FIRST_EXTERNAL_VECTOR; vector < first_system_vector; vector++) { if (!test_bit(vector, used_vectors) && - per_cpu(vector_irq, cpu)[vector] < 0) - count++; + IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector])) + count++; } } @@ -437,7 +450,7 @@ void fixup_irqs(void) raw_spin_lock(&desc->lock); data = irq_desc_get_irq_data(desc); - affinity = data->affinity; + affinity = irq_data_get_affinity_mask(data); if (!irq_has_action(irq) || irqd_is_per_cpu(data) || cpumask_subset(affinity, cpu_online_mask)) { raw_spin_unlock(&desc->lock); @@ -505,14 +518,13 @@ void fixup_irqs(void) for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { unsigned int irr; - if (__this_cpu_read(vector_irq[vector]) <= VECTOR_UNDEFINED) + if (IS_ERR_OR_NULL(__this_cpu_read(vector_irq[vector]))) continue; irr = apic_read(APIC_IRR + (vector / 32 * 0x10)); if (irr & (1 << (vector % 32))) { - irq = __this_cpu_read(vector_irq[vector]); + desc = __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); @@ -523,7 +535,7 @@ void fixup_irqs(void) raw_spin_unlock(&desc->lock); } if (__this_cpu_read(vector_irq[vector]) != VECTOR_RETRIGGERED) - __this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED); + __this_cpu_write(vector_irq[vector], VECTOR_UNUSED); } } #endif diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index cd74f5978ab9..38da8f29a9c8 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -68,11 +68,10 @@ static inline void *current_stack(void) return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1)); } -static inline int -execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) +static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) { struct irq_stack *curstk, *irqstk; - u32 *isp, *prev_esp, arg1, arg2; + u32 *isp, *prev_esp, arg1; curstk = (struct irq_stack *) current_stack(); irqstk = __this_cpu_read(hardirq_stack); @@ -98,8 +97,8 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) asm volatile("xchgl %%ebx,%%esp \n" "call *%%edi \n" "movl %%ebx,%%esp \n" - : "=a" (arg1), "=d" (arg2), "=b" (isp) - : "0" (irq), "1" (desc), "2" (isp), + : "=a" (arg1), "=b" (isp) + : "0" (desc), "1" (isp), "D" (desc->handle_irq) : "memory", "cc", "ecx"); return 1; @@ -148,21 +147,17 @@ void do_softirq_own_stack(void) call_on_stack(__do_softirq, isp); } -bool handle_irq(unsigned irq, struct pt_regs *regs) +bool handle_irq(struct irq_desc *desc, struct pt_regs *regs) { - struct irq_desc *desc; - int overflow; + int overflow = check_stack_overflow(); - overflow = check_stack_overflow(); - - desc = irq_to_desc(irq); - if (unlikely(!desc)) + if (IS_ERR_OR_NULL(desc)) return false; - if (user_mode(regs) || !execute_on_irq_stack(overflow, desc, irq)) { + if (user_mode(regs) || !execute_on_irq_stack(overflow, desc)) { if (unlikely(overflow)) print_stack_overflow(); - desc->handle_irq(irq, desc); + generic_handle_irq_desc(desc); } return true; diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index bc4604e500a3..206d0b90a3ab 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -68,16 +68,13 @@ static inline void stack_overflow_check(struct pt_regs *regs) #endif } -bool handle_irq(unsigned irq, struct pt_regs *regs) +bool handle_irq(struct irq_desc *desc, struct pt_regs *regs) { - struct irq_desc *desc; - stack_overflow_check(regs); - desc = irq_to_desc(irq); - if (unlikely(!desc)) + if (IS_ERR_OR_NULL(desc)) return false; - generic_handle_irq_desc(irq, desc); + generic_handle_irq_desc(desc); return true; } diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c index dc5fa6a1e8d6..3512ba607361 100644 --- a/arch/x86/kernel/irq_work.c +++ b/arch/x86/kernel/irq_work.c @@ -1,7 +1,7 @@ /* * x86 specific code for irq_work * - * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra */ #include <linux/kernel.h> diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index a3a5e158ed69..1423ab1b0312 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -52,7 +52,7 @@ static struct irqaction irq2 = { }; DEFINE_PER_CPU(vector_irq_t, vector_irq) = { - [0 ... NR_VECTORS - 1] = VECTOR_UNDEFINED, + [0 ... NR_VECTORS - 1] = VECTOR_UNUSED, }; int vector_used_by_percpu_irq(unsigned int vector) @@ -60,7 +60,7 @@ int vector_used_by_percpu_irq(unsigned int vector) int cpu; for_each_online_cpu(cpu) { - if (per_cpu(vector_irq, cpu)[vector] > VECTOR_UNDEFINED) + if (!IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector])) return 1; } @@ -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)[ISA_IRQ_VECTOR(i)] = i; + per_cpu(vector_irq, 0)[ISA_IRQ_VECTOR(i)] = irq_to_desc(i); x86_init.irqs.intr_init(); } diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index 26d5a55a2736..e565e0e4d216 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -45,7 +45,7 @@ static void __jump_label_transform(struct jump_entry *entry, const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP }; const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5]; - if (type == JUMP_LABEL_ENABLE) { + if (type == JUMP_LABEL_JMP) { if (init) { /* * Jump label is enabled for the first time. diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index ca83f7ac388b..0f8a6bbaaa44 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -223,9 +223,6 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params, memset(¶ms->hd0_info, 0, sizeof(params->hd0_info)); memset(¶ms->hd1_info, 0, sizeof(params->hd1_info)); - /* Default sysdesc table */ - params->sys_desc_table.length = 0; - if (image->type == KEXEC_TYPE_CRASH) { ret = crash_setup_memmap_entries(image, params); if (ret) @@ -536,7 +533,9 @@ static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len) int ret; ret = verify_pefile_signature(kernel, kernel_len, - system_trusted_keyring, &trusted); + system_trusted_keyring, + VERIFYING_KEXEC_PE_SIGNATURE, + &trusted); if (ret < 0) return ret; if (!trusted) diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index d6178d9791db..44256a62702b 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -511,26 +511,31 @@ single_step_cont(struct pt_regs *regs, struct die_args *args) return NOTIFY_STOP; } -static int was_in_debug_nmi[NR_CPUS]; +static DECLARE_BITMAP(was_in_debug_nmi, NR_CPUS); static int kgdb_nmi_handler(unsigned int cmd, struct pt_regs *regs) { + int cpu; + switch (cmd) { case NMI_LOCAL: if (atomic_read(&kgdb_active) != -1) { /* KGDB CPU roundup */ - kgdb_nmicallback(raw_smp_processor_id(), regs); - was_in_debug_nmi[raw_smp_processor_id()] = 1; + cpu = raw_smp_processor_id(); + kgdb_nmicallback(cpu, regs); + set_bit(cpu, was_in_debug_nmi); touch_nmi_watchdog(); + return NMI_HANDLED; } break; case NMI_UNKNOWN: - if (was_in_debug_nmi[raw_smp_processor_id()]) { - was_in_debug_nmi[raw_smp_processor_id()] = 0; + cpu = raw_smp_processor_id(); + + if (__test_and_clear_bit(cpu, was_in_debug_nmi)) return NMI_HANDLED; - } + break; default: /* do nothing */ diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 49487b488061..72cef58693c7 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -32,6 +32,7 @@ static int kvmclock = 1; static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME; static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK; +static cycle_t kvm_sched_clock_offset; static int parse_no_kvmclock(char *arg) { @@ -44,6 +45,11 @@ early_param("no-kvmclock", parse_no_kvmclock); static struct pvclock_vsyscall_time_info *hv_clock; static struct pvclock_wall_clock wall_clock; +struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void) +{ + return hv_clock; +} + /* * The wallclock is the time of day when we booted. Since then, some time may * have elapsed since the hypervisor wrote the data. So we try to account for @@ -92,6 +98,29 @@ static cycle_t kvm_clock_get_cycles(struct clocksource *cs) return kvm_clock_read(); } +static cycle_t kvm_sched_clock_read(void) +{ + return kvm_clock_read() - kvm_sched_clock_offset; +} + +static inline void kvm_sched_clock_init(bool stable) +{ + if (!stable) { + pv_time_ops.sched_clock = kvm_clock_read; + return; + } + + kvm_sched_clock_offset = kvm_clock_read(); + pv_time_ops.sched_clock = kvm_sched_clock_read; + set_sched_clock_stable(); + + printk(KERN_INFO "kvm-clock: using sched offset of %llu cycles\n", + kvm_sched_clock_offset); + + BUILD_BUG_ON(sizeof(kvm_sched_clock_offset) > + sizeof(((struct pvclock_vcpu_time_info *)NULL)->system_time)); +} + /* * If we don't do that, there is the possibility that the guest * will calibrate under heavy load - thus, getting a lower lpj - @@ -200,7 +229,7 @@ static void kvm_setup_secondary_clock(void) * kind of shutdown from our side, we unregister the clock by writting anything * that does not have the 'enable' bit set in the msr */ -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE static void kvm_crash_shutdown(struct pt_regs *regs) { native_write_msr(msr_kvm_system_time, 0, 0); @@ -248,7 +277,17 @@ void __init kvmclock_init(void) memblock_free(mem, size); return; } - pv_time_ops.sched_clock = kvm_clock_read; + + if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) + pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT); + + cpu = get_cpu(); + vcpu_time = &hv_clock[cpu].pvti; + flags = pvclock_read_flags(vcpu_time); + + kvm_sched_clock_init(flags & PVCLOCK_TSC_STABLE_BIT); + put_cpu(); + x86_platform.calibrate_tsc = kvm_get_tsc_khz; x86_platform.get_wallclock = kvm_get_wallclock; x86_platform.set_wallclock = kvm_set_wallclock; @@ -259,29 +298,18 @@ void __init kvmclock_init(void) x86_platform.save_sched_clock_state = kvm_save_sched_clock_state; x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state; machine_ops.shutdown = kvm_shutdown; -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE machine_ops.crash_shutdown = kvm_crash_shutdown; #endif kvm_get_preset_lpj(); clocksource_register_hz(&kvm_clock, NSEC_PER_SEC); pv_info.name = "KVM"; - - if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_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) { #ifdef CONFIG_X86_64 int cpu; - int ret; u8 flags; struct pvclock_vcpu_time_info *vcpu_time; unsigned int size; @@ -301,11 +329,6 @@ int __init kvm_setup_vsyscall_timeinfo(void) return 1; } - if ((ret = pvclock_init_vsyscall(hv_clock, size))) { - put_cpu(); - return ret; - } - put_cpu(); kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK; diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index 2bcc0525f1c1..6acc9dd91f36 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -58,7 +58,7 @@ static struct ldt_struct *alloc_ldt_struct(int size) if (alloc_size > PAGE_SIZE) new_ldt->entries = vzalloc(alloc_size); else - new_ldt->entries = kzalloc(PAGE_SIZE, GFP_KERNEL); + new_ldt->entries = (void *)get_zeroed_page(GFP_KERNEL); if (!new_ldt->entries) { kfree(new_ldt); @@ -95,7 +95,7 @@ static void free_ldt_struct(struct ldt_struct *ldt) if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE) vfree(ldt->entries); else - kfree(ldt->entries); + free_page((unsigned long)ldt->entries); kfree(ldt); } diff --git a/arch/x86/kernel/livepatch.c b/arch/x86/kernel/livepatch.c index ff3c3101d003..92fc1a51f994 100644 --- a/arch/x86/kernel/livepatch.c +++ b/arch/x86/kernel/livepatch.c @@ -20,8 +20,6 @@ #include <linux/module.h> #include <linux/uaccess.h> -#include <asm/cacheflush.h> -#include <asm/page_types.h> #include <asm/elf.h> #include <asm/livepatch.h> @@ -38,12 +36,10 @@ int klp_write_module_reloc(struct module *mod, unsigned long type, unsigned long loc, unsigned long value) { - int ret, numpages, size = 4; - bool readonly; + size_t size = 4; unsigned long val; - unsigned long core = (unsigned long)mod->module_core; - unsigned long core_ro_size = mod->core_ro_size; - unsigned long core_size = mod->core_size; + unsigned long core = (unsigned long)mod->core_layout.base; + unsigned long core_size = mod->core_layout.size; switch (type) { case R_X86_64_NONE: @@ -70,21 +66,5 @@ int klp_write_module_reloc(struct module *mod, unsigned long type, /* loc does not point to any symbol inside the module */ return -EINVAL; - if (loc < core + core_ro_size) - readonly = true; - else - readonly = false; - - /* determine if the relocation spans a page boundary */ - numpages = ((loc & PAGE_MASK) == ((loc + size) & PAGE_MASK)) ? 1 : 2; - - if (readonly) - set_memory_rw(loc & PAGE_MASK, numpages); - - ret = probe_kernel_write((void *)loc, &val, size); - - if (readonly) - set_memory_ro(loc & PAGE_MASK, numpages); - - return ret; + return probe_kernel_write((void *)loc, &val, size); } diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S index 94ea120fa21f..87e1762e2bca 100644 --- a/arch/x86/kernel/mcount_64.S +++ b/arch/x86/kernel/mcount_64.S @@ -278,6 +278,12 @@ trace: /* save_mcount_regs fills in first two parameters */ save_mcount_regs + /* + * When DYNAMIC_FTRACE is not defined, ARCH_SUPPORTS_FTRACE_OPS is not + * set (see include/asm/ftrace.h and include/linux/ftrace.h). Only the + * ip and parent ip are used and the list function is called when + * function tracing is enabled. + */ call *ftrace_trace_function restore_mcount_regs diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 113e70784854..64f9616f93f1 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -45,28 +45,6 @@ static struct class *msr_class; -static loff_t msr_seek(struct file *file, loff_t offset, int orig) -{ - loff_t ret; - struct inode *inode = file_inode(file); - - mutex_lock(&inode->i_mutex); - switch (orig) { - case SEEK_SET: - file->f_pos = offset; - ret = file->f_pos; - break; - case SEEK_CUR: - file->f_pos += offset; - ret = file->f_pos; - break; - default: - ret = -EINVAL; - } - mutex_unlock(&inode->i_mutex); - return ret; -} - static ssize_t msr_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -194,7 +172,7 @@ static int msr_open(struct inode *inode, struct file *file) */ static const struct file_operations msr_fops = { .owner = THIS_MODULE, - .llseek = msr_seek, + .llseek = no_seek_end_llseek, .read = msr_read, .write = msr_write, .open = msr_open, diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index d05bd2e2ee91..8a2cdd736fa4 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -29,6 +29,7 @@ #include <asm/mach_traps.h> #include <asm/nmi.h> #include <asm/x86_init.h> +#include <asm/reboot.h> #define CREATE_TRACE_POINTS #include <trace/events/nmi.h> @@ -110,7 +111,7 @@ static void nmi_max_handler(struct irq_work *w) a->handler, whole_msecs, decimal_msecs); } -static int nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b) +static int nmi_handle(unsigned int type, struct pt_regs *regs) { struct nmi_desc *desc = nmi_to_desc(type); struct nmiaction *a; @@ -213,7 +214,7 @@ static void pci_serr_error(unsigned char reason, struct pt_regs *regs) { /* check to see if anyone registered against these types of errors */ - if (nmi_handle(NMI_SERR, regs, false)) + if (nmi_handle(NMI_SERR, regs)) return; pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n", @@ -231,7 +232,7 @@ pci_serr_error(unsigned char reason, struct pt_regs *regs) #endif if (panic_on_unrecovered_nmi) - panic("NMI: Not continuing"); + nmi_panic(regs, "NMI: Not continuing"); pr_emerg("Dazed and confused, but trying to continue\n"); @@ -247,7 +248,7 @@ io_check_error(unsigned char reason, struct pt_regs *regs) unsigned long i; /* check to see if anyone registered against these types of errors */ - if (nmi_handle(NMI_IO_CHECK, regs, false)) + if (nmi_handle(NMI_IO_CHECK, regs)) return; pr_emerg( @@ -255,8 +256,16 @@ io_check_error(unsigned char reason, struct pt_regs *regs) reason, smp_processor_id()); show_regs(regs); - if (panic_on_io_nmi) - panic("NMI IOCK error: Not continuing"); + if (panic_on_io_nmi) { + nmi_panic(regs, "NMI IOCK error: Not continuing"); + + /* + * If we end up here, it means we have received an NMI while + * processing panic(). Simply return without delaying and + * re-enabling NMIs. + */ + return; + } /* Re-enable the IOCK line, wait for a few seconds */ reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK; @@ -284,7 +293,7 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs) * as only the first one is ever run (unless it can actually determine * if it caused the NMI) */ - handled = nmi_handle(NMI_UNKNOWN, regs, false); + handled = nmi_handle(NMI_UNKNOWN, regs); if (handled) { __this_cpu_add(nmi_stats.unknown, handled); return; @@ -297,7 +306,7 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs) pr_emerg("Do you have a strange power saving mode enabled?\n"); if (unknown_nmi_panic || panic_on_unrecovered_nmi) - panic("NMI: Not continuing"); + nmi_panic(regs, "NMI: Not continuing"); pr_emerg("Dazed and confused, but trying to continue\n"); } @@ -332,7 +341,7 @@ static void default_do_nmi(struct pt_regs *regs) __this_cpu_write(last_nmi_rip, regs->ip); - handled = nmi_handle(NMI_LOCAL, regs, b2b); + handled = nmi_handle(NMI_LOCAL, regs); __this_cpu_add(nmi_stats.normal, handled); if (handled) { /* @@ -348,8 +357,19 @@ static void default_do_nmi(struct pt_regs *regs) return; } - /* Non-CPU-specific NMI: NMI sources can be processed on any CPU */ - raw_spin_lock(&nmi_reason_lock); + /* + * Non-CPU-specific NMI: NMI sources can be processed on any CPU. + * + * Another CPU may be processing panic routines while holding + * nmi_reason_lock. Check if the CPU issued the IPI for crash dumping, + * and if so, call its callback directly. If there is no CPU preparing + * crash dump, we simply loop here. + */ + while (!raw_spin_trylock(&nmi_reason_lock)) { + run_crash_ipi_callback(regs); + cpu_relax(); + } + reason = x86_platform.get_nmi_reason(); if (reason & NMI_REASON_MASK) { diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 58bcfb67c01f..f08ac28b8136 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -41,10 +41,18 @@ #include <asm/timer.h> #include <asm/special_insns.h> -/* nop stub */ -void _paravirt_nop(void) -{ -} +/* + * nop stub, which must not clobber anything *including the stack* to + * avoid confusing the entry prologues. + */ +extern void _paravirt_nop(void); +asm (".pushsection .entry.text, \"ax\"\n" + ".global _paravirt_nop\n" + "_paravirt_nop:\n\t" + "ret\n\t" + ".size _paravirt_nop, . - _paravirt_nop\n\t" + ".type _paravirt_nop, @function\n\t" + ".popsection"); /* identity function, which can be inlined */ u32 _paravirt_ident_32(u32 x) @@ -66,16 +74,6 @@ void __init default_banner(void) /* Undefined instruction for dealing with missing ops pointers. */ static const unsigned char ud2a[] = { 0x0f, 0x0b }; -unsigned paravirt_patch_nop(void) -{ - return 0; -} - -unsigned paravirt_patch_ignore(unsigned len) -{ - return len; -} - struct branch { unsigned char opcode; u32 delta; @@ -125,7 +123,6 @@ static void *get_call_destination(u8 type) .pv_time_ops = pv_time_ops, .pv_cpu_ops = pv_cpu_ops, .pv_irq_ops = pv_irq_ops, - .pv_apic_ops = pv_apic_ops, .pv_mmu_ops = pv_mmu_ops, #ifdef CONFIG_PARAVIRT_SPINLOCKS .pv_lock_ops = pv_lock_ops, @@ -144,8 +141,7 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf, /* If there's no function, patch it with a ud2a (BUG) */ ret = paravirt_patch_insns(insnbuf, len, ud2a, ud2a+sizeof(ud2a)); else if (opfunc == _paravirt_nop) - /* If the operation is a nop, then nop the callsite */ - ret = paravirt_patch_nop(); + ret = 0; /* identity functions just return their single argument */ else if (opfunc == _paravirt_ident_32) @@ -154,10 +150,6 @@ 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 */ ret = paravirt_patch_jmp(insnbuf, opfunc, addr, len); @@ -212,8 +204,6 @@ static u64 native_steal_clock(int cpu) /* These are in entry.S */ extern void native_iret(void); -extern void native_irq_enable_sysexit(void); -extern void native_usergs_sysret32(void); extern void native_usergs_sysret64(void); static struct resource reserve_ioports = { @@ -351,9 +341,7 @@ __visible struct pv_cpu_ops pv_cpu_ops = { .wbinvd = native_wbinvd, .read_msr = native_read_msr_safe, .write_msr = native_write_msr_safe, - .read_tsc = native_read_tsc, .read_pmc = native_read_pmc, - .read_tscp = native_read_tscp, .load_tr_desc = native_load_tr_desc, .set_ldt = native_set_ldt, .load_gdt = native_load_gdt, @@ -373,13 +361,7 @@ __visible struct pv_cpu_ops pv_cpu_ops = { .load_sp0 = native_load_sp0, -#if defined(CONFIG_X86_32) - .irq_enable_sysexit = native_irq_enable_sysexit, -#endif #ifdef CONFIG_X86_64 -#ifdef CONFIG_IA32_EMULATION - .usergs_sysret32 = native_usergs_sysret32, -#endif .usergs_sysret64 = native_usergs_sysret64, #endif .iret = native_iret, @@ -397,12 +379,6 @@ NOKPROBE_SYMBOL(native_get_debugreg); NOKPROBE_SYMBOL(native_set_debugreg); NOKPROBE_SYMBOL(native_load_idt); -struct pv_apic_ops pv_apic_ops = { -#ifdef CONFIG_X86_LOCAL_APIC - .startup_ipi_hook = paravirt_nop, -#endif -}; - #if defined(CONFIG_X86_32) && !defined(CONFIG_X86_PAE) /* 32-bit pagetable entries */ #define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_32) @@ -438,9 +414,6 @@ struct pv_mmu_ops pv_mmu_ops = { .set_pmd = native_set_pmd, .set_pmd_at = native_set_pmd_at, .pte_update = paravirt_nop, - .pte_update_defer = paravirt_nop, - .pmd_update = paravirt_nop, - .pmd_update_defer = paravirt_nop, .ptep_modify_prot_start = __ptep_modify_prot_start, .ptep_modify_prot_commit = __ptep_modify_prot_commit, @@ -486,6 +459,5 @@ struct pv_mmu_ops pv_mmu_ops = { EXPORT_SYMBOL_GPL(pv_time_ops); EXPORT_SYMBOL (pv_cpu_ops); EXPORT_SYMBOL (pv_mmu_ops); -EXPORT_SYMBOL_GPL(pv_apic_ops); EXPORT_SYMBOL_GPL(pv_info); EXPORT_SYMBOL (pv_irq_ops); diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c index e1b013696dde..158dc0650d5d 100644 --- a/arch/x86/kernel/paravirt_patch_32.c +++ b/arch/x86/kernel/paravirt_patch_32.c @@ -5,12 +5,10 @@ DEF_NATIVE(pv_irq_ops, irq_enable, "sti"); DEF_NATIVE(pv_irq_ops, restore_fl, "push %eax; popf"); DEF_NATIVE(pv_irq_ops, save_fl, "pushf; pop %eax"); DEF_NATIVE(pv_cpu_ops, iret, "iret"); -DEF_NATIVE(pv_cpu_ops, irq_enable_sysexit, "sti; sysexit"); DEF_NATIVE(pv_mmu_ops, read_cr2, "mov %cr2, %eax"); DEF_NATIVE(pv_mmu_ops, write_cr3, "mov %eax, %cr3"); DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax"); 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)"); @@ -47,12 +45,10 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_irq_ops, restore_fl); PATCH_SITE(pv_irq_ops, save_fl); PATCH_SITE(pv_cpu_ops, iret); - PATCH_SITE(pv_cpu_ops, irq_enable_sysexit); PATCH_SITE(pv_mmu_ops, read_cr2); PATCH_SITE(pv_mmu_ops, read_cr3); PATCH_SITE(pv_mmu_ops, write_cr3); PATCH_SITE(pv_cpu_ops, clts); - PATCH_SITE(pv_cpu_ops, read_tsc); #if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock): if (pv_is_native_spin_unlock()) { diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index 8aa05583bc42..e70087a04cc8 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -13,9 +13,7 @@ DEF_NATIVE(pv_mmu_ops, flush_tlb_single, "invlpg (%rdi)"); DEF_NATIVE(pv_cpu_ops, clts, "clts"); DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd"); -DEF_NATIVE(pv_cpu_ops, irq_enable_sysexit, "swapgs; sti; sysexit"); DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq"); -DEF_NATIVE(pv_cpu_ops, usergs_sysret32, "swapgs; sysretl"); DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs"); DEF_NATIVE(, mov32, "mov %edi, %eax"); @@ -55,7 +53,6 @@ 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, usergs_sysret32); PATCH_SITE(pv_cpu_ops, usergs_sysret64); PATCH_SITE(pv_cpu_ops, swapgs); PATCH_SITE(pv_mmu_ops, read_cr2); diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 0497f719977d..833b1d329c47 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -180,13 +180,13 @@ static void calioc2_dump_error_regs(struct iommu_table *tbl); static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl); static void get_tce_space_from_tar(void); -static struct cal_chipset_ops calgary_chip_ops = { +static const struct cal_chipset_ops calgary_chip_ops = { .handle_quirks = calgary_handle_quirks, .tce_cache_blast = calgary_tce_cache_blast, .dump_error_regs = calgary_dump_error_regs }; -static struct cal_chipset_ops calioc2_chip_ops = { +static const struct cal_chipset_ops calioc2_chip_ops = { .handle_quirks = calioc2_handle_quirks, .tce_cache_blast = calioc2_tce_cache_blast, .dump_error_regs = calioc2_dump_error_regs diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 353972c1946c..6ba014c61d62 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -58,17 +58,6 @@ EXPORT_SYMBOL(x86_dma_fallback_dev); /* Number of entries preallocated for DMA-API debugging */ #define PREALLOC_DMA_DEBUG_ENTRIES 65536 -int dma_set_mask(struct device *dev, u64 mask) -{ - if (!dev->dma_mask || !dma_supported(dev, mask)) - return -EIO; - - *dev->dma_mask = mask; - - return 0; -} -EXPORT_SYMBOL(dma_set_mask); - void __init pci_iommu_alloc(void) { struct iommu_table_entry *p; @@ -101,7 +90,7 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size, again: page = NULL; /* CMA can be used only in the context which permits sleeping */ - if (flag & __GFP_WAIT) { + if (gfpflags_allow_blocking(flag)) { page = dma_alloc_from_contiguous(dev, count, get_order(size)); if (page && page_to_phys(page) + size > dma_mask) { dma_release_from_contiguous(dev, page, count); @@ -140,50 +129,20 @@ 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) +bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp) { - struct dma_map_ops *ops = get_dma_ops(dev); + if (!*dev) + *dev = &x86_dma_fallback_dev; - WARN_ON(irqs_disabled()); /* for portability */ + *gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); + *gfp = dma_alloc_coherent_gfp_flags(*dev, *gfp); - if (dma_release_from_coherent(dev, get_order(size), vaddr)) - return; + if (!is_device_dma_capable(*dev)) + return false; + return true; - debug_dma_free_coherent(dev, size, vaddr, bus); - if (ops->free) - ops->free(dev, size, vaddr, bus, attrs); } -EXPORT_SYMBOL(dma_free_attrs); +EXPORT_SYMBOL(arch_dma_alloc_attrs); /* * See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index adf0392d549a..7c577a178859 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -88,7 +88,7 @@ int __init pci_swiotlb_detect_4gb(void) { /* don't initialize swiotlb if iommu=off (no_iommu=1) */ #ifdef CONFIG_X86_64 - if (!no_iommu && max_pfn > MAX_DMA32_PFN) + if (!no_iommu && max_possible_pfn > MAX_DMA32_PFN) swiotlb = 1; #endif return swiotlb; diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c index 64f90f53bb85..14415aff1813 100644 --- a/arch/x86/kernel/pmem.c +++ b/arch/x86/kernel/pmem.c @@ -3,80 +3,29 @@ * Copyright (c) 2015, Intel Corporation. */ #include <linux/platform_device.h> -#include <linux/libnvdimm.h> #include <linux/module.h> -#include <asm/e820.h> +#include <linux/ioport.h> -static void e820_pmem_release(struct device *dev) +static int found(u64 start, u64 end, void *data) { - struct nvdimm_bus *nvdimm_bus = dev->platform_data; - - if (nvdimm_bus) - nvdimm_bus_unregister(nvdimm_bus); + return 1; } -static struct platform_device e820_pmem = { - .name = "e820_pmem", - .id = -1, - .dev = { - .release = e820_pmem_release, - }, -}; - -static const struct attribute_group *e820_pmem_attribute_groups[] = { - &nvdimm_bus_attribute_group, - NULL, -}; - -static const struct attribute_group *e820_pmem_region_attribute_groups[] = { - &nd_region_attribute_group, - &nd_device_attribute_group, - NULL, -}; - static __init int register_e820_pmem(void) { - 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; - - 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; + char *pmem = "Persistent Memory (legacy)"; + struct platform_device *pdev; + int rc; + + rc = walk_iomem_res(pmem, IORESOURCE_MEM, 0, -1, NULL, found); + if (rc <= 0) + return 0; + + /* + * See drivers/nvdimm/e820.c for the implementation, this is + * simply here to trigger the module to load on demand. + */ + pdev = platform_device_alloc("e820_pmem", -1); + return platform_device_add(pdev); } device_initcall(register_e820_pmem); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index c27cad726765..9f7c21c22477 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -29,6 +29,8 @@ #include <asm/debugreg.h> #include <asm/nmi.h> #include <asm/tlbflush.h> +#include <asm/mce.h> +#include <asm/vm86.h> /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, @@ -82,6 +84,9 @@ EXPORT_SYMBOL_GPL(idle_notifier_unregister); int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { memcpy(dst, src, arch_task_struct_size); +#ifdef CONFIG_VM86 + dst->thread.vm86 = NULL; +#endif return fpu__copy(&dst->thread.fpu, &src->thread.fpu); } @@ -110,6 +115,8 @@ void exit_thread(void) kfree(bp); } + free_vm86(t); + fpu__drop(fpu); } @@ -319,6 +326,7 @@ void stop_this_cpu(void *dummy) */ set_cpu_online(smp_processor_id(), false); disable_local_APIC(); + mcheck_cpu_clear(this_cpu_ptr(&cpu_info)); for (;;) halt(); @@ -501,3 +509,58 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) return randomize_range(mm->brk, range_end, 0) ? : mm->brk; } +/* + * Called from fs/proc with a reference on @p to find the function + * which called into schedule(). This needs to be done carefully + * because the task might wake up and we might look at a stack + * changing under us. + */ +unsigned long get_wchan(struct task_struct *p) +{ + unsigned long start, bottom, top, sp, fp, ip; + int count = 0; + + if (!p || p == current || p->state == TASK_RUNNING) + return 0; + + start = (unsigned long)task_stack_page(p); + if (!start) + return 0; + + /* + * Layout of the stack page: + * + * ----------- topmax = start + THREAD_SIZE - sizeof(unsigned long) + * PADDING + * ----------- top = topmax - TOP_OF_KERNEL_STACK_PADDING + * stack + * ----------- bottom = start + sizeof(thread_info) + * thread_info + * ----------- start + * + * The tasks stack pointer points at the location where the + * framepointer is stored. The data on the stack is: + * ... IP FP ... IP FP + * + * We need to read FP and IP, so we need to adjust the upper + * bound by another unsigned long. + */ + top = start + THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING; + top -= 2 * sizeof(unsigned long); + bottom = start + sizeof(struct thread_info); + + sp = READ_ONCE(p->thread.sp); + if (sp < bottom || sp > top) + return 0; + + fp = READ_ONCE_NOCHECK(*(unsigned long *)sp); + do { + if (fp < bottom || fp > top) + return 0; + ip = READ_ONCE_NOCHECK(*(unsigned long *)(fp + sizeof(unsigned long))); + if (!in_sched_functions(ip)) + return ip; + fp = READ_ONCE_NOCHECK(*(unsigned long *)fp); + } while (count++ < 16 && p->state != TASK_RUNNING); + return 0; +} diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index f73c962fe636..9f950917528b 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -53,6 +53,7 @@ #include <asm/syscalls.h> #include <asm/debugreg.h> #include <asm/switch_to.h> +#include <asm/vm86.h> asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); asmlinkage void ret_from_kernel_thread(void) __asm__("ret_from_kernel_thread"); @@ -279,14 +280,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) set_iopl_mask(next->iopl); /* - * If it were not for PREEMPT_ACTIVE we could guarantee that the - * preempt_count of all tasks was equal here and this would not be - * needed. - */ - task_thread_info(prev_p)->saved_preempt_count = this_cpu_read(__preempt_count); - this_cpu_write(__preempt_count, task_thread_info(next_p)->saved_preempt_count); - - /* * Now maybe handle debug registers and/or IO bitmaps */ if (unlikely(task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV || @@ -323,31 +316,3 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) return prev_p; } - -#define top_esp (THREAD_SIZE - sizeof(unsigned long)) -#define top_ebp (THREAD_SIZE - 2*sizeof(unsigned long)) - -unsigned long get_wchan(struct task_struct *p) -{ - unsigned long bp, sp, ip; - unsigned long stack_page; - int count = 0; - if (!p || p == current || p->state == TASK_RUNNING) - return 0; - stack_page = (unsigned long)task_stack_page(p); - sp = p->thread.sp; - if (!stack_page || sp < stack_page || sp > top_esp+stack_page) - return 0; - /* include/asm-i386/system.h:switch_to() pushes bp last. */ - bp = *(unsigned long *) sp; - do { - if (bp < stack_page || bp > top_ebp+stack_page) - return 0; - ip = *(unsigned long *) (bp+4); - if (!in_sched_functions(ip)) - return ip; - bp = *(unsigned long *) bp; - } while (count++ < 16); - return 0; -} - diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index f6b916387590..b9d99e0f82c4 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -121,13 +121,15 @@ void __show_regs(struct pt_regs *regs, int all) void release_thread(struct task_struct *dead_task) { if (dead_task->mm) { +#ifdef CONFIG_MODIFY_LDT_SYSCALL 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.ldt->entries, dead_task->mm->context.ldt->size); BUG(); } +#endif } } @@ -248,8 +250,8 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) __USER_CS, __USER_DS, 0); } -#ifdef CONFIG_IA32_EMULATION -void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp) +#ifdef CONFIG_COMPAT +void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp) { start_thread_common(regs, new_ip, new_sp, test_thread_flag(TIF_X32) @@ -330,7 +332,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) /* * Switch FS and GS. * - * These are even more complicated than FS and GS: they have + * These are even more complicated than DS and ES: they have * 64-bit bases are that controlled by arch_prctl. Those bases * only differ from the values in the GDT or LDT if the selector * is 0. @@ -399,14 +401,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) */ this_cpu_write(current_task, next_p); - /* - * If it were not for PREEMPT_ACTIVE we could guarantee that the - * preempt_count of all tasks was equal here and this would not be - * needed. - */ - task_thread_info(prev_p)->saved_preempt_count = this_cpu_read(__preempt_count); - this_cpu_write(__preempt_count, task_thread_info(next_p)->saved_preempt_count); - /* Reload esp0 and ss1. This changes current_thread_info(). */ load_sp0(tss, next); @@ -497,30 +491,6 @@ void set_personality_ia32(bool x32) } EXPORT_SYMBOL_GPL(set_personality_ia32); -unsigned long get_wchan(struct task_struct *p) -{ - unsigned long stack; - u64 fp, ip; - int count = 0; - - if (!p || p == current || p->state == TASK_RUNNING) - return 0; - stack = (unsigned long)task_stack_page(p); - if (p->thread.sp < stack || p->thread.sp >= stack+THREAD_SIZE) - return 0; - fp = *(u64 *)(p->thread.sp); - do { - if (fp < (unsigned long)stack || - fp >= (unsigned long)stack+THREAD_SIZE) - return 0; - ip = *(u64 *)(fp+8); - if (!in_sched_functions(ip)) - return ip; - fp = *(u64 *)fp; - } while (count++ < 16); - return 0; -} - long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) { int ret = 0; diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 9be72bc3613f..32e9d9cbb884 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -37,12 +37,10 @@ #include <asm/proto.h> #include <asm/hw_breakpoint.h> #include <asm/traps.h> +#include <asm/syscall.h> #include "tls.h" -#define CREATE_TRACE_POINTS -#include <trace/events/syscalls.h> - enum x86_regset { REGSET_GENERAL, REGSET_FP, @@ -126,21 +124,6 @@ const char *regs_query_register_name(unsigned int offset) return NULL; } -static const int arg_offs_table[] = { -#ifdef CONFIG_X86_32 - [0] = offsetof(struct pt_regs, ax), - [1] = offsetof(struct pt_regs, dx), - [2] = offsetof(struct pt_regs, cx) -#else /* CONFIG_X86_64 */ - [0] = offsetof(struct pt_regs, di), - [1] = offsetof(struct pt_regs, si), - [2] = offsetof(struct pt_regs, dx), - [3] = offsetof(struct pt_regs, cx), - [4] = offsetof(struct pt_regs, r8), - [5] = offsetof(struct pt_regs, r9) -#endif -}; - /* * does not yet catch signals sent when the child dies. * in exit.c or in signal.c. @@ -1123,6 +1106,73 @@ static int genregs32_set(struct task_struct *target, return ret; } +static long ia32_arch_ptrace(struct task_struct *child, compat_long_t request, + compat_ulong_t caddr, compat_ulong_t cdata) +{ + unsigned long addr = caddr; + unsigned long data = cdata; + void __user *datap = compat_ptr(data); + int ret; + __u32 val; + + switch (request) { + case PTRACE_PEEKUSR: + ret = getreg32(child, addr, &val); + if (ret == 0) + ret = put_user(val, (__u32 __user *)datap); + break; + + case PTRACE_POKEUSR: + ret = putreg32(child, addr, data); + break; + + case PTRACE_GETREGS: /* Get all gp regs from the child. */ + return copy_regset_to_user(child, &user_x86_32_view, + REGSET_GENERAL, + 0, sizeof(struct user_regs_struct32), + datap); + + case PTRACE_SETREGS: /* Set all gp regs in the child. */ + return copy_regset_from_user(child, &user_x86_32_view, + REGSET_GENERAL, 0, + sizeof(struct user_regs_struct32), + datap); + + case PTRACE_GETFPREGS: /* Get the child FPU state. */ + return copy_regset_to_user(child, &user_x86_32_view, + REGSET_FP, 0, + sizeof(struct user_i387_ia32_struct), + datap); + + case PTRACE_SETFPREGS: /* Set the child FPU state. */ + return copy_regset_from_user( + child, &user_x86_32_view, REGSET_FP, + 0, sizeof(struct user_i387_ia32_struct), datap); + + case PTRACE_GETFPXREGS: /* Get the child extended FPU state. */ + return copy_regset_to_user(child, &user_x86_32_view, + REGSET_XFP, 0, + sizeof(struct user32_fxsr_struct), + datap); + + case PTRACE_SETFPXREGS: /* Set the child extended FPU state. */ + return copy_regset_from_user(child, &user_x86_32_view, + REGSET_XFP, 0, + sizeof(struct user32_fxsr_struct), + datap); + + case PTRACE_GET_THREAD_AREA: + case PTRACE_SET_THREAD_AREA: + return arch_ptrace(child, request, addr, data); + + default: + return compat_ptrace_request(child, request, addr, data); + } + + return ret; +} +#endif /* CONFIG_IA32_EMULATION */ + #ifdef CONFIG_X86_X32_ABI static long x32_arch_ptrace(struct task_struct *child, compat_long_t request, compat_ulong_t caddr, @@ -1211,78 +1261,21 @@ static long x32_arch_ptrace(struct task_struct *child, } #endif +#ifdef CONFIG_COMPAT long compat_arch_ptrace(struct task_struct *child, compat_long_t request, compat_ulong_t caddr, compat_ulong_t cdata) { - unsigned long addr = caddr; - unsigned long data = cdata; - void __user *datap = compat_ptr(data); - int ret; - __u32 val; - #ifdef CONFIG_X86_X32_ABI if (!is_ia32_task()) return x32_arch_ptrace(child, request, caddr, cdata); #endif - - switch (request) { - case PTRACE_PEEKUSR: - ret = getreg32(child, addr, &val); - if (ret == 0) - ret = put_user(val, (__u32 __user *)datap); - break; - - case PTRACE_POKEUSR: - ret = putreg32(child, addr, data); - break; - - case PTRACE_GETREGS: /* Get all gp regs from the child. */ - return copy_regset_to_user(child, &user_x86_32_view, - REGSET_GENERAL, - 0, sizeof(struct user_regs_struct32), - datap); - - case PTRACE_SETREGS: /* Set all gp regs in the child. */ - return copy_regset_from_user(child, &user_x86_32_view, - REGSET_GENERAL, 0, - sizeof(struct user_regs_struct32), - datap); - - case PTRACE_GETFPREGS: /* Get the child FPU state. */ - return copy_regset_to_user(child, &user_x86_32_view, - REGSET_FP, 0, - sizeof(struct user_i387_ia32_struct), - datap); - - case PTRACE_SETFPREGS: /* Set the child FPU state. */ - return copy_regset_from_user( - child, &user_x86_32_view, REGSET_FP, - 0, sizeof(struct user_i387_ia32_struct), datap); - - case PTRACE_GETFPXREGS: /* Get the child extended FPU state. */ - return copy_regset_to_user(child, &user_x86_32_view, - REGSET_XFP, 0, - sizeof(struct user32_fxsr_struct), - datap); - - case PTRACE_SETFPXREGS: /* Set the child extended FPU state. */ - return copy_regset_from_user(child, &user_x86_32_view, - REGSET_XFP, 0, - sizeof(struct user32_fxsr_struct), - datap); - - case PTRACE_GET_THREAD_AREA: - case PTRACE_SET_THREAD_AREA: - return arch_ptrace(child, request, addr, data); - - default: - return compat_ptrace_request(child, request, addr, data); - } - - return ret; +#ifdef CONFIG_IA32_EMULATION + return ia32_arch_ptrace(child, request, caddr, cdata); +#else + return 0; +#endif } - -#endif /* CONFIG_IA32_EMULATION */ +#endif /* CONFIG_COMPAT */ #ifdef CONFIG_X86_64 @@ -1434,201 +1427,3 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, /* Send us the fake SIGTRAP */ force_sig_info(SIGTRAP, &info, tsk); } - -static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch) -{ -#ifdef CONFIG_X86_64 - if (arch == AUDIT_ARCH_X86_64) { - audit_syscall_entry(regs->orig_ax, regs->di, - regs->si, regs->dx, regs->r10); - } else -#endif - { - audit_syscall_entry(regs->orig_ax, regs->bx, - regs->cx, regs->dx, regs->si); - } -} - -/* - * We can return 0 to resume the syscall or anything else to go to phase - * 2. If we resume the syscall, we need to put something appropriate in - * regs->orig_ax. - * - * NB: We don't have full pt_regs here, but regs->orig_ax and regs->ax - * are fully functional. - * - * For phase 2's benefit, our return value is: - * 0: resume the syscall - * 1: go to phase 2; no seccomp phase 2 needed - * anything else: go to phase 2; pass return value to seccomp - */ -unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch) -{ - unsigned long ret = 0; - u32 work; - - BUG_ON(regs != task_pt_regs(current)); - - work = ACCESS_ONCE(current_thread_info()->flags) & - _TIF_WORK_SYSCALL_ENTRY; - - /* - * If TIF_NOHZ is set, we are required to call user_exit() before - * doing anything that could touch RCU. - */ - if (work & _TIF_NOHZ) { - user_exit(); - work &= ~_TIF_NOHZ; - } - -#ifdef CONFIG_SECCOMP - /* - * Do seccomp first -- it should minimize exposure of other - * code, and keeping seccomp fast is probably more valuable - * than the rest of this. - */ - if (work & _TIF_SECCOMP) { - struct seccomp_data sd; - - sd.arch = arch; - sd.nr = regs->orig_ax; - sd.instruction_pointer = regs->ip; -#ifdef CONFIG_X86_64 - if (arch == AUDIT_ARCH_X86_64) { - sd.args[0] = regs->di; - sd.args[1] = regs->si; - sd.args[2] = regs->dx; - sd.args[3] = regs->r10; - sd.args[4] = regs->r8; - sd.args[5] = regs->r9; - } else -#endif - { - sd.args[0] = regs->bx; - sd.args[1] = regs->cx; - sd.args[2] = regs->dx; - sd.args[3] = regs->si; - sd.args[4] = regs->di; - sd.args[5] = regs->bp; - } - - BUILD_BUG_ON(SECCOMP_PHASE1_OK != 0); - BUILD_BUG_ON(SECCOMP_PHASE1_SKIP != 1); - - ret = seccomp_phase1(&sd); - if (ret == SECCOMP_PHASE1_SKIP) { - regs->orig_ax = -1; - ret = 0; - } else if (ret != SECCOMP_PHASE1_OK) { - return ret; /* Go directly to phase 2 */ - } - - work &= ~_TIF_SECCOMP; - } -#endif - - /* Do our best to finish without phase 2. */ - if (work == 0) - return ret; /* seccomp and/or nohz only (ret == 0 here) */ - -#ifdef CONFIG_AUDITSYSCALL - if (work == _TIF_SYSCALL_AUDIT) { - /* - * If there is no more work to be done except auditing, - * then audit in phase 1. Phase 2 always audits, so, if - * we audit here, then we can't go on to phase 2. - */ - do_audit_syscall_entry(regs, arch); - return 0; - } -#endif - - return 1; /* Something is enabled that we can't handle in phase 1 */ -} - -/* Returns the syscall nr to run (which should match regs->orig_ax). */ -long syscall_trace_enter_phase2(struct pt_regs *regs, u32 arch, - unsigned long phase1_result) -{ - long ret = 0; - u32 work = ACCESS_ONCE(current_thread_info()->flags) & - _TIF_WORK_SYSCALL_ENTRY; - - BUG_ON(regs != task_pt_regs(current)); - - /* - * If we stepped into a sysenter/syscall insn, it trapped in - * kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP. - * If user-mode had set TF itself, then it's still clear from - * do_debug() and we need to set it again to restore the user - * state. If we entered on the slow path, TF was already set. - */ - if (work & _TIF_SINGLESTEP) - regs->flags |= X86_EFLAGS_TF; - -#ifdef CONFIG_SECCOMP - /* - * Call seccomp_phase2 before running the other hooks so that - * they can see any changes made by a seccomp tracer. - */ - if (phase1_result > 1 && seccomp_phase2(phase1_result)) { - /* seccomp failures shouldn't expose any additional code. */ - return -1; - } -#endif - - if (unlikely(work & _TIF_SYSCALL_EMU)) - ret = -1L; - - if ((ret || test_thread_flag(TIF_SYSCALL_TRACE)) && - tracehook_report_syscall_entry(regs)) - ret = -1L; - - if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) - trace_sys_enter(regs, regs->orig_ax); - - do_audit_syscall_entry(regs, arch); - - return ret ?: regs->orig_ax; -} - -long syscall_trace_enter(struct pt_regs *regs) -{ - u32 arch = is_ia32_task() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; - unsigned long phase1_result = syscall_trace_enter_phase1(regs, arch); - - if (phase1_result == 0) - return regs->orig_ax; - else - return syscall_trace_enter_phase2(regs, arch, phase1_result); -} - -void syscall_trace_leave(struct pt_regs *regs) -{ - bool step; - - /* - * We may come here right after calling schedule_user() - * or do_notify_resume(), in which case we can be in RCU - * user mode. - */ - user_exit(); - - audit_syscall_exit(regs); - - if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) - trace_sys_exit(regs, regs->ax); - - /* - * If TIF_SYSCALL_EMU is set, we only get here because of - * TIF_SINGLESTEP (i.e. this is PTRACE_SYSEMU_SINGLESTEP). - * We already reported this syscall instruction in - * syscall_trace_enter(). - */ - step = unlikely(test_thread_flag(TIF_SINGLESTEP)) && - !test_thread_flag(TIF_SYSCALL_EMU); - if (step || test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall_exit(regs, step); - - user_enter(); -} diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 2f355d229a58..99bfc025111d 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -140,27 +140,3 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); } - -#ifdef CONFIG_X86_64 -/* - * Initialize the generic pvclock vsyscall state. This will allocate - * a/some page(s) for the per-vcpu pvclock information, set up a - * fixmap mapping for the page(s) - */ - -int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, - int size) -{ - int idx; - - WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE); - - for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) { - __set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx, - __pa(i) + (idx*PAGE_SIZE), - PAGE_KERNEL_VVAR); - } - - return 0; -} -#endif diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 176a0f99d4da..cc457ff818ad 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -524,7 +524,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E6XX_CU, */ static void force_disable_hpet_msi(struct pci_dev *unused) { - hpet_msi_disable = 1; + hpet_msi_disable = true; } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS, diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 86db4bcd7ce5..ab0adc0fa5db 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -182,6 +182,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "iMac9,1"), }, }, + { /* Handle problems with rebooting on the iMac10,1. */ + .callback = set_pci_reboot, + .ident = "Apple iMac10,1", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "iMac10,1"), + }, + }, /* ASRock */ { /* Handle problems with rebooting on ASRock Q1900DC-ITX */ @@ -673,7 +681,7 @@ struct machine_ops machine_ops = { .emergency_restart = native_machine_emergency_restart, .restart = native_machine_restart, .halt = native_machine_halt, -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE .crash_shutdown = native_machine_crash_shutdown, #endif }; @@ -703,7 +711,7 @@ void machine_halt(void) machine_ops.halt(); } -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE void machine_crash_shutdown(struct pt_regs *regs) { machine_ops.crash_shutdown(regs); @@ -718,6 +726,7 @@ static int crashing_cpu; static nmi_shootdown_cb shootdown_callback; static atomic_t waiting_for_crash_ipi; +static int crash_ipi_issued; static int crash_nmi_callback(unsigned int val, struct pt_regs *regs) { @@ -780,6 +789,9 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback) smp_send_nmi_allbutself(); + /* Kick CPUs looping in NMI context. */ + WRITE_ONCE(crash_ipi_issued, 1); + msecs = 1000; /* Wait at most a second for the other cpus to stop */ while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) { mdelay(1); @@ -788,9 +800,35 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback) /* Leave the nmi callback set */ } + +/* + * Check if the crash dumping IPI got issued and if so, call its callback + * directly. This function is used when we have already been in NMI handler. + * It doesn't return. + */ +void run_crash_ipi_callback(struct pt_regs *regs) +{ + if (crash_ipi_issued) + crash_nmi_callback(0, regs); +} + +/* Override the weak function in kernel/panic.c */ +void nmi_panic_self_stop(struct pt_regs *regs) +{ + while (1) { + /* If no CPU is preparing crash dump, we simply loop here. */ + run_crash_ipi_callback(regs); + cpu_relax(); + } +} + #else /* !CONFIG_SMP */ void nmi_shootdown_cpus(nmi_shootdown_cb callback) { /* No other CPUs to shoot down */ } + +void run_crash_ipi_callback(struct pt_regs *regs) +{ +} #endif diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index cd9685235df9..4af8d063fb36 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -200,6 +200,9 @@ static __init int add_rtc_cmos(void) } #endif + if (paravirt_enabled() && !paravirt_has(RTC)) + return -ENODEV; + platform_device_register(&rtc_device); dev_info(&rtc_device.dev, "registered platform RTC device (no PNP device found)\n"); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 80f874bf999e..d3d80e6d42a2 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -111,6 +111,7 @@ #include <asm/mce.h> #include <asm/alternative.h> #include <asm/prom.h> +#include <asm/microcode.h> /* * max_low_pfn_mapped: highest direct mapped pfn under 4GB @@ -317,15 +318,12 @@ static u64 __init get_ramdisk_size(void) return ramdisk_size; } -#define MAX_MAP_CHUNK (NR_FIX_BTMAPS << PAGE_SHIFT) static void __init relocate_initrd(void) { /* Assume only end is not page aligned */ u64 ramdisk_image = get_ramdisk_image(); u64 ramdisk_size = get_ramdisk_size(); u64 area_size = PAGE_ALIGN(ramdisk_size); - unsigned long slop, clen, mapaddr; - char *p, *q; /* We need to move the initrd down into directly mapped mem */ relocated_ramdisk = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped), @@ -343,25 +341,8 @@ static void __init relocate_initrd(void) printk(KERN_INFO "Allocated new RAMDISK: [mem %#010llx-%#010llx]\n", relocated_ramdisk, relocated_ramdisk + ramdisk_size - 1); - q = (char *)initrd_start; - - /* Copy the initrd */ - while (ramdisk_size) { - slop = ramdisk_image & ~PAGE_MASK; - clen = ramdisk_size; - if (clen > MAX_MAP_CHUNK-slop) - clen = MAX_MAP_CHUNK-slop; - mapaddr = ramdisk_image & PAGE_MASK; - p = early_memremap(mapaddr, clen+slop); - memcpy(q, p+slop, clen); - early_memunmap(p, clen+slop); - q += clen; - ramdisk_image += clen; - ramdisk_size -= clen; - } + copy_from_early_mem((void *)initrd_start, ramdisk_image, ramdisk_size); - ramdisk_image = get_ramdisk_image(); - ramdisk_size = get_ramdisk_size(); printk(KERN_INFO "Move RAMDISK from [mem %#010llx-%#010llx] to" " [mem %#010llx-%#010llx]\n", ramdisk_image, ramdisk_image + ramdisk_size - 1, @@ -498,7 +479,10 @@ static void __init memblock_x86_reserve_range_setup_data(void) * --------- Crashkernel reservation ------------------------------ */ -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE + +/* 16M alignment for crash kernel regions */ +#define CRASH_ALIGN (16 << 20) /* * Keep the crash kernel below this limit. On 32 bits earlier kernels @@ -506,28 +490,25 @@ static void __init memblock_x86_reserve_range_setup_data(void) * On 64bit, old kexec-tools need to under 896MiB. */ #ifdef CONFIG_X86_32 -# define CRASH_KERNEL_ADDR_LOW_MAX (512 << 20) -# define CRASH_KERNEL_ADDR_HIGH_MAX (512 << 20) +# define CRASH_ADDR_LOW_MAX (512 << 20) +# define CRASH_ADDR_HIGH_MAX (512 << 20) #else -# define CRASH_KERNEL_ADDR_LOW_MAX (896UL<<20) -# define CRASH_KERNEL_ADDR_HIGH_MAX MAXMEM +# define CRASH_ADDR_LOW_MAX (896UL << 20) +# define CRASH_ADDR_HIGH_MAX MAXMEM #endif -static void __init reserve_crashkernel_low(void) +static int __init reserve_crashkernel_low(void) { #ifdef CONFIG_X86_64 - const unsigned long long alignment = 16<<20; /* 16M */ - unsigned long long low_base = 0, low_size = 0; + unsigned long long base, low_base = 0, low_size = 0; unsigned long total_low_mem; - unsigned long long base; - bool auto_set = false; int ret; - total_low_mem = memblock_mem_size(1UL<<(32-PAGE_SHIFT)); + total_low_mem = memblock_mem_size(1UL << (32 - PAGE_SHIFT)); + /* crashkernel=Y,low */ - ret = parse_crashkernel_low(boot_command_line, total_low_mem, - &low_size, &base); - if (ret != 0) { + ret = parse_crashkernel_low(boot_command_line, total_low_mem, &low_size, &base); + if (ret) { /* * two parts from lib/swiotlb.c: * -swiotlb size: user-specified with swiotlb= or default. @@ -537,52 +518,52 @@ static void __init reserve_crashkernel_low(void) * make sure we allocate enough extra low memory so that we * don't run out of DMA buffers for 32-bit devices. */ - low_size = max(swiotlb_size_or_default() + (8UL<<20), 256UL<<20); - auto_set = true; + low_size = max(swiotlb_size_or_default() + (8UL << 20), 256UL << 20); } else { /* passed with crashkernel=0,low ? */ if (!low_size) - return; + return 0; } - low_base = memblock_find_in_range(low_size, (1ULL<<32), - low_size, alignment); - + low_base = memblock_find_in_range(low_size, 1ULL << 32, low_size, CRASH_ALIGN); if (!low_base) { - if (!auto_set) - pr_info("crashkernel low reservation failed - No suitable area found.\n"); + pr_err("Cannot reserve %ldMB crashkernel low memory, please try smaller size.\n", + (unsigned long)(low_size >> 20)); + return -ENOMEM; + } - return; + ret = memblock_reserve(low_base, low_size); + if (ret) { + pr_err("%s: Error reserving crashkernel low memblock.\n", __func__); + return ret; } - memblock_reserve(low_base, low_size); pr_info("Reserving %ldMB of low memory at %ldMB for crashkernel (System low RAM: %ldMB)\n", - (unsigned long)(low_size >> 20), - (unsigned long)(low_base >> 20), - (unsigned long)(total_low_mem >> 20)); + (unsigned long)(low_size >> 20), + (unsigned long)(low_base >> 20), + (unsigned long)(total_low_mem >> 20)); + crashk_low_res.start = low_base; crashk_low_res.end = low_base + low_size - 1; insert_resource(&iomem_resource, &crashk_low_res); #endif + return 0; } static void __init reserve_crashkernel(void) { - const unsigned long long alignment = 16<<20; /* 16M */ - unsigned long long total_mem; - unsigned long long crash_size, crash_base; + unsigned long long crash_size, crash_base, total_mem; bool high = false; int ret; total_mem = memblock_phys_mem_size(); /* crashkernel=XM */ - ret = parse_crashkernel(boot_command_line, total_mem, - &crash_size, &crash_base); + ret = parse_crashkernel(boot_command_line, total_mem, &crash_size, &crash_base); if (ret != 0 || crash_size <= 0) { /* crashkernel=X,high */ ret = parse_crashkernel_high(boot_command_line, total_mem, - &crash_size, &crash_base); + &crash_size, &crash_base); if (ret != 0 || crash_size <= 0) return; high = true; @@ -593,11 +574,10 @@ static void __init reserve_crashkernel(void) /* * kexec want bzImage is below CRASH_KERNEL_ADDR_MAX */ - crash_base = memblock_find_in_range(alignment, - high ? CRASH_KERNEL_ADDR_HIGH_MAX : - CRASH_KERNEL_ADDR_LOW_MAX, - crash_size, alignment); - + crash_base = memblock_find_in_range(CRASH_ALIGN, + high ? CRASH_ADDR_HIGH_MAX + : CRASH_ADDR_LOW_MAX, + crash_size, CRASH_ALIGN); if (!crash_base) { pr_info("crashkernel reservation failed - No suitable area found.\n"); return; @@ -607,26 +587,32 @@ static void __init reserve_crashkernel(void) unsigned long long start; start = memblock_find_in_range(crash_base, - crash_base + crash_size, crash_size, 1<<20); + crash_base + crash_size, + crash_size, 1 << 20); if (start != crash_base) { pr_info("crashkernel reservation failed - memory is in use.\n"); return; } } - memblock_reserve(crash_base, crash_size); + ret = memblock_reserve(crash_base, crash_size); + if (ret) { + pr_err("%s: Error reserving crashkernel memblock.\n", __func__); + return; + } - printk(KERN_INFO "Reserving %ldMB of memory at %ldMB " - "for crashkernel (System RAM: %ldMB)\n", - (unsigned long)(crash_size >> 20), - (unsigned long)(crash_base >> 20), - (unsigned long)(total_mem >> 20)); + if (crash_base >= (1ULL << 32) && reserve_crashkernel_low()) { + memblock_free(crash_base, crash_size); + return; + } + + pr_info("Reserving %ldMB of memory at %ldMB for crashkernel (System RAM: %ldMB)\n", + (unsigned long)(crash_size >> 20), + (unsigned long)(crash_base >> 20), + (unsigned long)(total_mem >> 20)); crashk_res.start = crash_base; crashk_res.end = crash_base + crash_size - 1; insert_resource(&iomem_resource, &crashk_res); - - if (crash_base >= (1ULL<<32)) - reserve_crashkernel_low(); } #else static void __init reserve_crashkernel(void) @@ -916,11 +902,6 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_X86_32 apm_info.bios = boot_params.apm_bios_info; ist_info = boot_params.ist_info; - if (boot_params.sys_desc_table.length != 0) { - machine_id = boot_params.sys_desc_table.table[0]; - machine_submodel_id = boot_params.sys_desc_table.table[1]; - BIOS_revision = boot_params.sys_desc_table.table[2]; - } #endif saved_video_mode = boot_params.hdr.vid_mode; bootloader_type = boot_params.hdr.type_of_loader; @@ -1067,6 +1048,8 @@ void __init setup_arch(char **cmdline_p) if (mtrr_trim_uncached_memory(max_pfn)) max_pfn = e820_end_of_ram_pfn(); + max_possible_pfn = max_pfn; + #ifdef CONFIG_X86_32 /* max_low_pfn get updated here */ find_low_pfn_range(); @@ -1104,8 +1087,10 @@ void __init setup_arch(char **cmdline_p) memblock_set_current_limit(ISA_END_ADDRESS); memblock_x86_fill(); - if (efi_enabled(EFI_BOOT)) + if (efi_enabled(EFI_BOOT)) { + efi_fake_memmap(); efi_find_mirror(); + } /* * The EFI specification says that boot service code won't be called @@ -1198,6 +1183,14 @@ void __init setup_arch(char **cmdline_p) clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, swapper_pg_dir + KERNEL_PGD_BOUNDARY, KERNEL_PGD_PTRS); + + /* + * sync back low identity map too. It is used for example + * in the 32-bit EFI stub. + */ + clone_pgd_range(initial_page_table, + swapper_pg_dir + KERNEL_PGD_BOUNDARY, + min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY)); #endif tboot_probe(); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 71820c42b6ce..cb6282c3638f 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -31,11 +31,11 @@ #include <asm/vdso.h> #include <asm/mce.h> #include <asm/sighandling.h> +#include <asm/vm86.h> #ifdef CONFIG_X86_64 #include <asm/proto.h> #include <asm/ia32_unistd.h> -#include <asm/sys_ia32.h> #endif /* CONFIG_X86_64 */ #include <asm/syscall.h> @@ -63,6 +63,7 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc) { + unsigned long buf_val; void __user *buf; unsigned int tmpflags; unsigned int err = 0; @@ -107,7 +108,8 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc) regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); regs->orig_ax = -1; /* disable syscall checks */ - get_user_ex(buf, &sc->fpstate); + get_user_ex(buf_val, &sc->fpstate); + buf = (void __user *)buf_val; } get_user_catch(err); err |= fpu__restore_sig(buf, config_enabled(CONFIG_X86_32)); @@ -196,7 +198,7 @@ static unsigned long align_sigframe(unsigned long sp) return sp; } -static inline void __user * +static void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, void __user **fpstate) { @@ -299,7 +301,7 @@ __setup_frame(int sig, struct ksignal *ksig, sigset_t *set, if (current->mm->context.vdso) restorer = current->mm->context.vdso + - selected_vdso32->sym___kernel_sigreturn; + vdso_image_32.sym___kernel_sigreturn; else restorer = &frame->retcode; if (ksig->ka.sa.sa_flags & SA_RESTORER) @@ -363,7 +365,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, /* Set up to return from userspace. */ restorer = current->mm->context.vdso + - selected_vdso32->sym___kernel_rt_sigreturn; + vdso_image_32.sym___kernel_rt_sigreturn; if (ksig->ka.sa.sa_flags & SA_RESTORER) restorer = ksig->ka.sa.sa_restorer; put_user_ex(restorer, &frame->pretcode); @@ -632,6 +634,9 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) bool stepping, failed; struct fpu *fpu = ¤t->thread.fpu; + if (v8086_mode(regs)) + save_v86_state((struct kernel_vm86_regs *) regs, VM86_SIGNAL); + /* Are we from a system call? */ if (syscall_get_nr(current, regs) >= 0) { /* If so, check system call restarting.. */ @@ -685,19 +690,22 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) signal_setup_done(failed, ksig, stepping); } -#ifdef CONFIG_X86_32 -#define NR_restart_syscall __NR_restart_syscall -#else /* !CONFIG_X86_32 */ -#define NR_restart_syscall \ - test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall : __NR_restart_syscall -#endif /* CONFIG_X86_32 */ +static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) +{ +#if defined(CONFIG_X86_32) || !defined(CONFIG_X86_64) + return __NR_restart_syscall; +#else /* !CONFIG_X86_32 && CONFIG_X86_64 */ + return test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall : + __NR_restart_syscall | (regs->orig_ax & __X32_SYSCALL_BIT); +#endif /* CONFIG_X86_32 || !CONFIG_X86_64 */ +} /* * Note that 'init' is a special process: it doesn't get signals it doesn't * want to handle. Thus you cannot kill init even with a SIGKILL even by * mistake. */ -static void do_signal(struct pt_regs *regs) +void do_signal(struct pt_regs *regs) { struct ksignal ksig; @@ -719,7 +727,7 @@ static void do_signal(struct pt_regs *regs) break; case -ERESTART_RESTARTBLOCK: - regs->ax = NR_restart_syscall; + regs->ax = get_nr_restart_syscall(regs); regs->ip -= 2; break; } @@ -732,32 +740,6 @@ static void do_signal(struct pt_regs *regs) restore_saved_sigmask(); } -/* - * notification of userspace execution resumption - * - triggered by the TIF_WORK_MASK flags - */ -__visible void -do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) -{ - user_exit(); - - if (thread_info_flags & _TIF_UPROBE) - uprobe_notify_resume(regs); - - /* deal with pending signal delivery */ - if (thread_info_flags & _TIF_SIGPENDING) - do_signal(regs); - - if (thread_info_flags & _TIF_NOTIFY_RESUME) { - clear_thread_flag(TIF_NOTIFY_RESUME); - tracehook_notify_resume(regs); - } - if (thread_info_flags & _TIF_USER_RETURN_NOTIFY) - fire_user_return_notifiers(); - - user_enter(); -} - void signal_fault(struct pt_regs *regs, void __user *frame, char *where) { struct task_struct *me = current; diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c new file mode 100644 index 000000000000..dc3c0b1c816f --- /dev/null +++ b/arch/x86/kernel/signal_compat.c @@ -0,0 +1,95 @@ +#include <linux/compat.h> +#include <linux/uaccess.h> + +int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) +{ + int err = 0; + bool ia32 = test_thread_flag(TIF_IA32); + + if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t))) + return -EFAULT; + + put_user_try { + /* If you change siginfo_t structure, please make sure that + this code is fixed accordingly. + It should never copy any pad contained in the structure + to avoid security leaks, but must copy the generic + 3 ints plus the relevant union member. */ + put_user_ex(from->si_signo, &to->si_signo); + put_user_ex(from->si_errno, &to->si_errno); + put_user_ex((short)from->si_code, &to->si_code); + + if (from->si_code < 0) { + put_user_ex(from->si_pid, &to->si_pid); + put_user_ex(from->si_uid, &to->si_uid); + put_user_ex(ptr_to_compat(from->si_ptr), &to->si_ptr); + } else { + /* + * First 32bits of unions are always present: + * si_pid === si_band === si_tid === si_addr(LS half) + */ + put_user_ex(from->_sifields._pad[0], + &to->_sifields._pad[0]); + switch (from->si_code >> 16) { + case __SI_FAULT >> 16: + break; + case __SI_SYS >> 16: + put_user_ex(from->si_syscall, &to->si_syscall); + put_user_ex(from->si_arch, &to->si_arch); + break; + case __SI_CHLD >> 16: + if (ia32) { + put_user_ex(from->si_utime, &to->si_utime); + put_user_ex(from->si_stime, &to->si_stime); + } else { + put_user_ex(from->si_utime, &to->_sifields._sigchld_x32._utime); + put_user_ex(from->si_stime, &to->_sifields._sigchld_x32._stime); + } + put_user_ex(from->si_status, &to->si_status); + /* FALL THROUGH */ + default: + case __SI_KILL >> 16: + put_user_ex(from->si_uid, &to->si_uid); + break; + case __SI_POLL >> 16: + put_user_ex(from->si_fd, &to->si_fd); + break; + case __SI_TIMER >> 16: + put_user_ex(from->si_overrun, &to->si_overrun); + put_user_ex(ptr_to_compat(from->si_ptr), + &to->si_ptr); + break; + /* This is not generated by the kernel as of now. */ + case __SI_RT >> 16: + case __SI_MESGQ >> 16: + put_user_ex(from->si_uid, &to->si_uid); + put_user_ex(from->si_int, &to->si_int); + break; + } + } + } put_user_catch(err); + + return err; +} + +int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) +{ + int err = 0; + u32 ptr32; + + if (!access_ok(VERIFY_READ, from, sizeof(compat_siginfo_t))) + return -EFAULT; + + get_user_try { + get_user_ex(to->si_signo, &from->si_signo); + get_user_ex(to->si_errno, &from->si_errno); + get_user_ex(to->si_code, &from->si_code); + + get_user_ex(to->si_pid, &from->si_pid); + get_user_ex(to->si_uid, &from->si_uid); + get_user_ex(ptr32, &from->si_ptr); + to->si_ptr = compat_ptr(ptr32); + } get_user_catch(err); + + return err; +} diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 15aaa69bbb5e..658777cf3851 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -30,6 +30,7 @@ #include <asm/proto.h> #include <asm/apic.h> #include <asm/nmi.h> +#include <asm/mce.h> #include <asm/trace/irq_vectors.h> /* * Some notes on x86 processor bugs affecting SMP operation: @@ -124,12 +125,12 @@ static void native_smp_send_reschedule(int cpu) WARN_ON(1); return; } - apic->send_IPI_mask(cpumask_of(cpu), RESCHEDULE_VECTOR); + apic->send_IPI(cpu, RESCHEDULE_VECTOR); } void native_send_call_func_single_ipi(int cpu) { - apic->send_IPI_mask(cpumask_of(cpu), CALL_FUNCTION_SINGLE_VECTOR); + apic->send_IPI(cpu, CALL_FUNCTION_SINGLE_VECTOR); } void native_send_call_func_ipi(const struct cpumask *mask) @@ -243,6 +244,7 @@ static void native_stop_other_cpus(int wait) finish: local_irq_save(flags); disable_local_APIC(); + mcheck_cpu_clear(this_cpu_ptr(&cpu_info)); local_irq_restore(flags); } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index b1f3ed9c7a9e..24d57f77b3c1 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -97,8 +97,6 @@ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); EXPORT_PER_CPU_SYMBOL(cpu_info); -atomic_t init_deasserted; - static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip) { unsigned long flags; @@ -146,16 +144,11 @@ static void smp_callin(void) /* * If waken up by an INIT in an 82489DX configuration - * we may get here before an INIT-deassert IPI reaches - * our local APIC. We have to wait for the IPI or we'll - * lock up on an APIC access. - * - * Since CPU0 is not wakened up by INIT, it doesn't wait for the IPI. + * cpu_callout_mask guarantees we don't get here before + * an INIT_deassert IPI reaches our local APIC, so it is + * now safe to touch our local APIC. */ cpuid = smp_processor_id(); - if (apic->wait_for_init_deassert && cpuid) - while (!atomic_read(&init_deasserted)) - cpu_relax(); /* * (This works even if the APIC is not enabled.) @@ -311,7 +304,7 @@ do { \ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) { - if (cpu_has_topoext) { + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { int cpu1 = c->cpu_index, cpu2 = o->cpu_index; if (c->phys_proc_id == o->phys_proc_id && @@ -516,7 +509,7 @@ void __inquire_remote_apic(int apicid) */ #define UDELAY_10MS_DEFAULT 10000 -static unsigned int init_udelay = UDELAY_10MS_DEFAULT; +static unsigned int init_udelay = UINT_MAX; static int __init cpu_init_udelay(char *str) { @@ -529,13 +522,17 @@ 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) + if (init_udelay != UINT_MAX) 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))) + ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF))) { init_udelay = 0; + return; + } + /* else, use legacy delay */ + init_udelay = UDELAY_10MS_DEFAULT; } /* @@ -620,7 +617,6 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) send_status = safe_apic_wait_icr_idle(); mb(); - atomic_set(&init_deasserted, 1); /* * Should we send STARTUP IPIs ? @@ -634,13 +630,6 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) num_starts = 0; /* - * Paravirt / VMI wants a startup IPI hook here to set up the - * target processor state. - */ - startup_ipi_hook(phys_apicid, (unsigned long) start_secondary, - stack_start); - - /* * Run STARTUP IPI loop. */ pr_debug("#startup loops: %d\n", num_starts); @@ -665,7 +654,10 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) /* * Give the other CPU some time to accept the IPI. */ - udelay(300); + if (init_udelay == 0) + udelay(10); + else + udelay(300); pr_debug("Startup point 1\n"); @@ -675,7 +667,10 @@ 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 (init_udelay == 0) + udelay(10); + else + udelay(200); if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */ apic_write(APIC_ESR, 0); @@ -859,8 +854,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) * the targeted processor. */ - atomic_set(&init_deasserted, 0); - if (get_uv_system_type() != UV_NON_UNIQUE_APIC) { pr_debug("Setting warm reset code and vector.\n"); @@ -898,7 +891,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) if (!boot_error) { /* - * Wait 10s total for a response from AP + * Wait 10s total for first sign of life from AP */ boot_error = -1; timeout = jiffies + 10*HZ; @@ -911,7 +904,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) boot_error = 0; break; } - udelay(100); schedule(); } } @@ -927,7 +919,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) * for the MTRR work(triggered by the AP coming online) * to be completed in the stop machine context. */ - udelay(100); schedule(); } } @@ -1358,7 +1349,7 @@ static void remove_siblinginfo(int cpu) cpumask_clear_cpu(cpu, cpu_sibling_setup_mask); } -static void __ref remove_cpu_from_maps(int cpu) +static void remove_cpu_from_maps(int cpu) { set_cpu_online(cpu, false); cpumask_clear_cpu(cpu, cpu_callout_mask); diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 0ccb53a9fcd9..c9a073866ca7 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -18,6 +18,7 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re return addr; } +#ifdef CONFIG_MODIFY_LDT_SYSCALL /* * We'll assume that the code segments in the GDT * are all zero-based. That is largely true: the @@ -45,6 +46,7 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re } mutex_unlock(&child->mm->context.lock); } +#endif return addr; } diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index 649b010da00b..12cbe2b88c0f 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -57,7 +57,7 @@ __setup("cpu0_hotplug", enable_cpu0_hotplug); * * This is only called for debugging CPU offline/online feature. */ -int __ref _debug_hotplug_cpu(int cpu, int action) +int _debug_hotplug_cpu(int cpu, int action) { struct device *dev = get_cpu_device(cpu); int ret; @@ -104,7 +104,7 @@ static int __init debug_hotplug_cpu(void) late_initcall_sync(debug_hotplug_cpu); #endif /* CONFIG_DEBUG_HOTPLUG_CPU0 */ -int __ref arch_register_cpu(int num) +int arch_register_cpu(int num) { struct cpuinfo_x86 *c = &cpu_data(num); diff --git a/arch/x86/kernel/trace_clock.c b/arch/x86/kernel/trace_clock.c index 25b993729f9b..80bb24d9b880 100644 --- a/arch/x86/kernel/trace_clock.c +++ b/arch/x86/kernel/trace_clock.c @@ -12,10 +12,5 @@ */ u64 notrace trace_clock_x86_tsc(void) { - u64 ret; - - rdtsc_barrier(); - rdtscll(ret); - - return ret; + return rdtsc_ordered(); } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index f5791927aa64..ade185a46b1d 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -62,6 +62,7 @@ #include <asm/fpu/xstate.h> #include <asm/trace/mpx.h> #include <asm/mpx.h> +#include <asm/vm86.h> #ifdef CONFIG_X86_64 #include <asm/x86_init.h> @@ -108,13 +109,10 @@ static inline void preempt_conditional_cli(struct pt_regs *regs) preempt_count_dec(); } -enum ctx_state ist_enter(struct pt_regs *regs) +void ist_enter(struct pt_regs *regs) { - enum ctx_state prev_state; - if (user_mode(regs)) { - /* Other than that, we're just an exception. */ - prev_state = exception_enter(); + RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); } else { /* * We might have interrupted pretty much anything. In @@ -123,32 +121,25 @@ enum ctx_state ist_enter(struct pt_regs *regs) * but we need to notify RCU. */ rcu_nmi_enter(); - prev_state = CONTEXT_KERNEL; /* the value is irrelevant. */ } /* - * We are atomic because we're on the IST stack (or we're on x86_32, - * in which case we still shouldn't schedule). - * - * This must be after exception_enter(), because exception_enter() - * won't do anything if in_interrupt() returns true. + * We are atomic because we're on the IST stack; or we're on + * x86_32, in which case we still shouldn't schedule; or we're + * on x86_64 and entered from user mode, in which case we're + * still atomic unless ist_begin_non_atomic is called. */ preempt_count_add(HARDIRQ_OFFSET); /* This code is a bit fragile. Test it. */ - rcu_lockdep_assert(rcu_is_watching(), "ist_enter didn't work"); - - return prev_state; + RCU_LOCKDEP_WARN(!rcu_is_watching(), "ist_enter didn't work"); } -void ist_exit(struct pt_regs *regs, enum ctx_state prev_state) +void ist_exit(struct pt_regs *regs) { - /* Must be before exception_exit. */ preempt_count_sub(HARDIRQ_OFFSET); - if (user_mode(regs)) - return exception_exit(prev_state); - else + if (!user_mode(regs)) rcu_nmi_exit(); } @@ -162,7 +153,7 @@ void ist_exit(struct pt_regs *regs, enum ctx_state prev_state) * a double fault, it can be safe to schedule. ist_begin_non_atomic() * begins a non-atomic section within an ist_enter()/ist_exit() region. * Callers are responsible for enabling interrupts themselves inside - * the non-atomic section, and callers must call is_end_non_atomic() + * the non-atomic section, and callers must call ist_end_non_atomic() * before ist_exit(). */ void ist_begin_non_atomic(struct pt_regs *regs) @@ -289,17 +280,16 @@ NOKPROBE_SYMBOL(do_trap); static void do_error_trap(struct pt_regs *regs, long error_code, char *str, unsigned long trapnr, int signr) { - enum ctx_state prev_state = exception_enter(); siginfo_t info; + RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); + if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) != NOTIFY_STOP) { conditional_sti(regs); do_trap(trapnr, signr, str, regs, error_code, fill_trap_info(regs, signr, trapnr, &info)); } - - exception_exit(prev_state); } #define DO_ERROR(trapnr, signr, str, name) \ @@ -351,7 +341,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) } #endif - ist_enter(regs); /* Discard prev_state because we won't return. */ + ist_enter(regs); notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV); tsk->thread.error_code = error_code; @@ -371,14 +361,13 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) { - enum ctx_state prev_state; - const struct bndcsr *bndcsr; + const struct mpx_bndcsr *bndcsr; siginfo_t *info; - prev_state = exception_enter(); + RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); if (notify_die(DIE_TRAP, "bounds", regs, error_code, X86_TRAP_BR, SIGSEGV) == NOTIFY_STOP) - goto exit; + return; conditional_sti(regs); if (!user_mode(regs)) @@ -395,7 +384,7 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) * which is all zeros which indicates MPX was not * responsible for the exception. */ - bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR); + bndcsr = get_xsave_field_ptr(XFEATURE_MASK_BNDCSR); if (!bndcsr) goto exit_trap; @@ -435,9 +424,8 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) die("bounds", regs, error_code); } -exit: - exception_exit(prev_state); return; + exit_trap: /* * This path out is for all the cases where we could not @@ -447,35 +435,33 @@ exit_trap: * time.. */ do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, NULL); - exception_exit(prev_state); } dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code) { struct task_struct *tsk; - enum ctx_state prev_state; - prev_state = exception_enter(); + RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); conditional_sti(regs); if (v8086_mode(regs)) { local_irq_enable(); handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code); - goto exit; + return; } tsk = current; if (!user_mode(regs)) { if (fixup_exception(regs)) - goto exit; + return; tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_GP; if (notify_die(DIE_GPF, "general protection fault", regs, error_code, X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP) die("general protection fault", regs, error_code); - goto exit; + return; } tsk->thread.error_code = error_code; @@ -491,16 +477,12 @@ do_general_protection(struct pt_regs *regs, long error_code) } force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk); -exit: - exception_exit(prev_state); } NOKPROBE_SYMBOL(do_general_protection); /* May run on IST stack. */ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) { - enum ctx_state prev_state; - #ifdef CONFIG_DYNAMIC_FTRACE /* * ftrace must be first, everything else may cause a recursive crash. @@ -513,7 +495,8 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) if (poke_int3_handler(regs)) return; - prev_state = ist_enter(regs); + ist_enter(regs); + RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, SIGTRAP) == NOTIFY_STOP) @@ -539,7 +522,7 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) preempt_conditional_cli(regs); debug_stack_usage_dec(); exit: - ist_exit(regs, prev_state); + ist_exit(regs); } NOKPROBE_SYMBOL(do_int3); @@ -615,12 +598,11 @@ NOKPROBE_SYMBOL(fixup_bad_iret); dotraplinkage void do_debug(struct pt_regs *regs, long error_code) { struct task_struct *tsk = current; - enum ctx_state prev_state; int user_icebp = 0; unsigned long dr6; int si_code; - prev_state = ist_enter(regs); + ist_enter(regs); get_debugreg(dr6, 6); @@ -695,7 +677,7 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) debug_stack_usage_dec(); exit: - ist_exit(regs, prev_state); + ist_exit(regs); } NOKPROBE_SYMBOL(do_debug); @@ -747,21 +729,15 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr) dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code) { - enum ctx_state prev_state; - - prev_state = exception_enter(); + RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); math_error(regs, error_code, X86_TRAP_MF); - exception_exit(prev_state); } dotraplinkage void do_simd_coprocessor_error(struct pt_regs *regs, long error_code) { - enum ctx_state prev_state; - - prev_state = exception_enter(); + RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); math_error(regs, error_code, X86_TRAP_XF); - exception_exit(prev_state); } dotraplinkage void @@ -773,9 +749,7 @@ do_spurious_interrupt_bug(struct pt_regs *regs, long error_code) dotraplinkage void do_device_not_available(struct pt_regs *regs, long error_code) { - enum ctx_state prev_state; - - prev_state = exception_enter(); + RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); BUG_ON(use_eager_fpu()); #ifdef CONFIG_MATH_EMULATION @@ -786,7 +760,6 @@ do_device_not_available(struct pt_regs *regs, long error_code) info.regs = regs; math_emulate(&info); - exception_exit(prev_state); return; } #endif @@ -794,7 +767,6 @@ do_device_not_available(struct pt_regs *regs, long error_code) #ifdef CONFIG_X86_32 conditional_sti(regs); #endif - exception_exit(prev_state); } NOKPROBE_SYMBOL(do_device_not_available); @@ -802,9 +774,8 @@ NOKPROBE_SYMBOL(do_device_not_available); dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) { siginfo_t info; - enum ctx_state prev_state; - prev_state = exception_enter(); + RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); local_irq_enable(); info.si_signo = SIGILL; @@ -816,7 +787,6 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code, &info); } - exception_exit(prev_state); } #endif diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 7437b41f6a47..3d743da828d3 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -21,6 +21,7 @@ #include <asm/hypervisor.h> #include <asm/nmi.h> #include <asm/x86_init.h> +#include <asm/geode.h> unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ EXPORT_SYMBOL(cpu_khz); @@ -38,7 +39,7 @@ static int __read_mostly tsc_unstable; erroneous rdtsc usage on !cpu_has_tsc processors */ static int __read_mostly tsc_disabled = -1; -static struct static_key __use_tsc = STATIC_KEY_INIT; +static DEFINE_STATIC_KEY_FALSE(__use_tsc); int tsc_clocksource_reliable; @@ -167,21 +168,20 @@ static void cyc2ns_write_end(int cpu, struct cyc2ns_data *data) * ns = cycles * cyc2ns_scale / SC * * And since SC is a constant power of two, we can convert the div - * into a shift. + * into a shift. The larger SC is, the more accurate the conversion, but + * cyc2ns_scale needs to be a 32-bit value so that 32-bit multiplication + * (64-bit result) can be used. * - * We can use khz divisor instead of mhz to keep a better precision, since - * cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits. + * We can use khz divisor instead of mhz to keep a better precision. * (mathieu.desnoyers@polymtl.ca) * * -johnstul@us.ibm.com "math is hard, lets go shopping!" */ -#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */ - static void cyc2ns_data_init(struct cyc2ns_data *data) { data->cyc2ns_mul = 0; - data->cyc2ns_shift = CYC2NS_SCALE_FACTOR; + data->cyc2ns_shift = 0; data->cyc2ns_offset = 0; data->__count = 0; } @@ -215,14 +215,14 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc) if (likely(data == tail)) { ns = data->cyc2ns_offset; - ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR); + ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift); } else { data->__count++; barrier(); ns = data->cyc2ns_offset; - ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR); + ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift); barrier(); @@ -248,7 +248,7 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) data = cyc2ns_write_begin(cpu); - rdtscll(tsc_now); + tsc_now = rdtsc(); ns_now = cycles_2_ns(tsc_now); /* @@ -256,12 +256,22 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) * time function is continuous; see the comment near struct * cyc2ns_data. */ - data->cyc2ns_mul = - DIV_ROUND_CLOSEST(NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR, - cpu_khz); - data->cyc2ns_shift = CYC2NS_SCALE_FACTOR; + clocks_calc_mult_shift(&data->cyc2ns_mul, &data->cyc2ns_shift, cpu_khz, + NSEC_PER_MSEC, 0); + + /* + * cyc2ns_shift is exported via arch_perf_update_userpage() where it is + * not expected to be greater than 31 due to the original published + * conversion algorithm shifting a 32-bit value (now specifies a 64-bit + * value) - refer perf_event_mmap_page documentation in perf_event.h. + */ + if (data->cyc2ns_shift == 32) { + data->cyc2ns_shift = 31; + data->cyc2ns_mul >>= 1; + } + data->cyc2ns_offset = ns_now - - mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR); + mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, data->cyc2ns_shift); cyc2ns_write_end(cpu, data); @@ -274,7 +284,12 @@ done: */ u64 native_sched_clock(void) { - u64 tsc_now; + if (static_branch_likely(&__use_tsc)) { + u64 tsc_now = rdtsc(); + + /* return the value in ns */ + return cycles_2_ns(tsc_now); + } /* * Fall back to jiffies if there's no TSC available: @@ -284,16 +299,17 @@ u64 native_sched_clock(void) * very important for it to be as fast as the platform * can achieve it. ) */ - if (!static_key_false(&__use_tsc)) { - /* No locking but a rare wrong value is not a big deal: */ - return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ); - } - /* read the Time Stamp Counter: */ - rdtscll(tsc_now); + /* No locking but a rare wrong value is not a big deal: */ + return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ); +} - /* return the value in ns */ - return cycles_2_ns(tsc_now); +/* + * Generate a sched_clock if you already have a TSC value. + */ +u64 native_sched_clock_from_tsc(u64 tsc) +{ + return cycles_2_ns(tsc); } /* We need to define a real function for sched_clock, to override the @@ -308,12 +324,6 @@ unsigned long long sched_clock(void) __attribute__((alias("native_sched_clock"))); #endif -unsigned long long native_read_tsc(void) -{ - return __native_read_tsc(); -} -EXPORT_SYMBOL(native_read_tsc); - int check_tsc_unstable(void) { return tsc_unstable; @@ -976,7 +986,7 @@ static struct clocksource clocksource_tsc; */ static cycle_t read_tsc(struct clocksource *cs) { - return (cycle_t)get_cycles(); + return (cycle_t)rdtsc_ordered(); } /* @@ -1013,15 +1023,17 @@ EXPORT_SYMBOL_GPL(mark_tsc_unstable); static void __init check_system_tsc_reliable(void) { -#ifdef CONFIG_MGEODE_LX - /* RTSC counts during suspend */ +#if defined(CONFIG_MGEODEGX1) || defined(CONFIG_MGEODE_LX) || defined(CONFIG_X86_GENERIC) + if (is_geode_lx()) { + /* RTSC counts during suspend */ #define RTSC_SUSP 0x100 - unsigned long res_low, res_high; + unsigned long res_low, res_high; - rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high); - /* Geode_LX - the OLPC CPU has a very reliable TSC */ - if (res_low & RTSC_SUSP) - tsc_clocksource_reliable = 1; + rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high); + /* Geode_LX - the OLPC CPU has a very reliable TSC */ + if (res_low & RTSC_SUSP) + tsc_clocksource_reliable = 1; + } #endif if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) tsc_clocksource_reliable = 1; @@ -1173,8 +1185,6 @@ void __init tsc_init(void) u64 lpj; int cpu; - x86_init.timers.tsc_pre_init(); - if (!cpu_has_tsc) { setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; @@ -1210,7 +1220,7 @@ void __init tsc_init(void) /* now allow native_sched_clock() to use rdtsc */ tsc_disabled = 0; - static_key_slow_inc(&__use_tsc); + static_branch_enable(&__use_tsc); if (!no_sched_irq_time) enable_sched_clock_irqtime(); diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index dd8d0791dfb5..78083bf23ed1 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -39,16 +39,15 @@ static cycles_t max_warp; static int nr_warps; /* - * TSC-warp measurement loop running on both CPUs: + * TSC-warp measurement loop running on both CPUs. This is not called + * if there is no TSC. */ static void check_tsc_warp(unsigned int timeout) { cycles_t start, now, prev, end; int i; - rdtsc_barrier(); - start = get_cycles(); - rdtsc_barrier(); + start = rdtsc_ordered(); /* * The measurement runs for 'timeout' msecs: */ @@ -63,9 +62,7 @@ static void check_tsc_warp(unsigned int timeout) */ arch_spin_lock(&sync_lock); prev = last_tsc; - rdtsc_barrier(); - now = get_cycles(); - rdtsc_barrier(); + now = rdtsc_ordered(); last_tsc = now; arch_spin_unlock(&sync_lock); @@ -126,7 +123,7 @@ void check_tsc_sync_source(int cpu) /* * No need to check if we already know that the TSC is not - * synchronized: + * synchronized or if we have no TSC. */ if (unsynchronized_tsc()) return; @@ -190,6 +187,7 @@ void check_tsc_sync_target(void) { int cpus = 2; + /* Also aborts if there is no TSC. */ if (unsynchronized_tsc() || tsc_clocksource_reliable) return; diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 66476244731e..bf4db6eaec8f 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -985,3 +985,12 @@ arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs return -1; } + +bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx, + struct pt_regs *regs) +{ + if (ctx == RP_CHECK_CALL) /* sp was just decremented by "call" insn */ + return regs->sp < ret->stack; + else + return regs->sp <= ret->stack; +} diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S index b9242bacbe59..07efb35ee4bc 100644 --- a/arch/x86/kernel/verify_cpu.S +++ b/arch/x86/kernel/verify_cpu.S @@ -34,10 +34,11 @@ #include <asm/msr-index.h> verify_cpu: - pushfl # Save caller passed flags - pushl $0 # Kill any dangerous flags - popfl + pushf # Save caller passed flags + push $0 # Kill any dangerous flags + popf +#ifndef __x86_64__ pushfl # standard way to check for cpuid popl %eax movl %eax,%ebx @@ -47,30 +48,31 @@ verify_cpu: pushfl popl %eax cmpl %eax,%ebx - jz verify_cpu_no_longmode # cpu has no cpuid + jz .Lverify_cpu_no_longmode # cpu has no cpuid +#endif movl $0x0,%eax # See if cpuid 1 is implemented cpuid cmpl $0x1,%eax - jb verify_cpu_no_longmode # no cpuid 1 + jb .Lverify_cpu_no_longmode # no cpuid 1 xor %di,%di cmpl $0x68747541,%ebx # AuthenticAMD - jnz verify_cpu_noamd + jnz .Lverify_cpu_noamd cmpl $0x69746e65,%edx - jnz verify_cpu_noamd + jnz .Lverify_cpu_noamd cmpl $0x444d4163,%ecx - jnz verify_cpu_noamd + jnz .Lverify_cpu_noamd mov $1,%di # cpu is from AMD - jmp verify_cpu_check + jmp .Lverify_cpu_check -verify_cpu_noamd: +.Lverify_cpu_noamd: cmpl $0x756e6547,%ebx # GenuineIntel? - jnz verify_cpu_check + jnz .Lverify_cpu_check cmpl $0x49656e69,%edx - jnz verify_cpu_check + jnz .Lverify_cpu_check cmpl $0x6c65746e,%ecx - jnz verify_cpu_check + jnz .Lverify_cpu_check # only call IA32_MISC_ENABLE when: # family > 6 || (family == 6 && model >= 0xd) @@ -81,59 +83,59 @@ verify_cpu_noamd: andl $0x0ff00f00, %eax # mask family and extended family shrl $8, %eax cmpl $6, %eax - ja verify_cpu_clear_xd # family > 6, ok - jb verify_cpu_check # family < 6, skip + ja .Lverify_cpu_clear_xd # family > 6, ok + jb .Lverify_cpu_check # family < 6, skip andl $0x000f00f0, %ecx # mask model and extended model shrl $4, %ecx cmpl $0xd, %ecx - jb verify_cpu_check # family == 6, model < 0xd, skip + jb .Lverify_cpu_check # family == 6, model < 0xd, skip -verify_cpu_clear_xd: +.Lverify_cpu_clear_xd: movl $MSR_IA32_MISC_ENABLE, %ecx rdmsr btrl $2, %edx # clear MSR_IA32_MISC_ENABLE_XD_DISABLE - jnc verify_cpu_check # only write MSR if bit was changed + jnc .Lverify_cpu_check # only write MSR if bit was changed wrmsr -verify_cpu_check: +.Lverify_cpu_check: movl $0x1,%eax # Does the cpu have what it takes cpuid andl $REQUIRED_MASK0,%edx xorl $REQUIRED_MASK0,%edx - jnz verify_cpu_no_longmode + jnz .Lverify_cpu_no_longmode movl $0x80000000,%eax # See if extended cpuid is implemented cpuid cmpl $0x80000001,%eax - jb verify_cpu_no_longmode # no extended cpuid + jb .Lverify_cpu_no_longmode # no extended cpuid movl $0x80000001,%eax # Does the cpu have what it takes cpuid andl $REQUIRED_MASK1,%edx xorl $REQUIRED_MASK1,%edx - jnz verify_cpu_no_longmode + jnz .Lverify_cpu_no_longmode -verify_cpu_sse_test: +.Lverify_cpu_sse_test: movl $1,%eax cpuid andl $SSE_MASK,%edx cmpl $SSE_MASK,%edx - je verify_cpu_sse_ok + je .Lverify_cpu_sse_ok test %di,%di - jz verify_cpu_no_longmode # only try to force SSE on AMD + jz .Lverify_cpu_no_longmode # only try to force SSE on AMD movl $MSR_K7_HWCR,%ecx rdmsr btr $15,%eax # enable SSE wrmsr xor %di,%di # don't loop - jmp verify_cpu_sse_test # try again + jmp .Lverify_cpu_sse_test # try again -verify_cpu_no_longmode: - popfl # Restore caller passed flags +.Lverify_cpu_no_longmode: + popf # Restore caller passed flags movl $1,%eax ret -verify_cpu_sse_ok: - popfl # Restore caller passed flags +.Lverify_cpu_sse_ok: + popf # Restore caller passed flags xorl %eax, %eax ret diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index fc9db6ef2a95..e574b8546518 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -44,11 +44,15 @@ #include <linux/ptrace.h> #include <linux/audit.h> #include <linux/stddef.h> +#include <linux/slab.h> +#include <linux/security.h> #include <asm/uaccess.h> #include <asm/io.h> #include <asm/tlbflush.h> #include <asm/irq.h> +#include <asm/traps.h> +#include <asm/vm86.h> /* * Known problems: @@ -66,10 +70,6 @@ */ -#define KVM86 ((struct kernel_vm86_struct *)regs) -#define VMPI KVM86->vm86plus - - /* * 8- and 16-bit register defines.. */ @@ -81,8 +81,8 @@ /* * virtual flags (16 and 32-bit versions) */ -#define VFLAGS (*(unsigned short *)&(current->thread.v86flags)) -#define VEFLAGS (current->thread.v86flags) +#define VFLAGS (*(unsigned short *)&(current->thread.vm86->veflags)) +#define VEFLAGS (current->thread.vm86->veflags) #define set_flags(X, new, mask) \ ((X) = ((X) & ~(mask)) | ((new) & (mask))) @@ -90,46 +90,13 @@ #define SAFE_MASK (0xDD5) #define RETURN_MASK (0xDFF) -/* convert kernel_vm86_regs to vm86_regs */ -static int copy_vm86_regs_to_user(struct vm86_regs __user *user, - const struct kernel_vm86_regs *regs) -{ - int ret = 0; - - /* - * kernel_vm86_regs is missing gs, so copy everything up to - * (but not including) orig_eax, and then rest including orig_eax. - */ - ret += copy_to_user(user, regs, offsetof(struct kernel_vm86_regs, pt.orig_ax)); - ret += copy_to_user(&user->orig_eax, ®s->pt.orig_ax, - sizeof(struct kernel_vm86_regs) - - offsetof(struct kernel_vm86_regs, pt.orig_ax)); - - return ret; -} - -/* convert vm86_regs to kernel_vm86_regs */ -static int copy_vm86_regs_from_user(struct kernel_vm86_regs *regs, - const struct vm86_regs __user *user, - unsigned extra) -{ - int ret = 0; - - /* copy ax-fs inclusive */ - ret += copy_from_user(regs, user, offsetof(struct kernel_vm86_regs, pt.orig_ax)); - /* copy orig_ax-__gsh+extra */ - ret += copy_from_user(®s->pt.orig_ax, &user->orig_eax, - sizeof(struct kernel_vm86_regs) - - offsetof(struct kernel_vm86_regs, pt.orig_ax) + - extra); - return ret; -} - -struct pt_regs *save_v86_state(struct kernel_vm86_regs *regs) +void save_v86_state(struct kernel_vm86_regs *regs, int retval) { struct tss_struct *tss; - struct pt_regs *ret; - unsigned long tmp; + struct task_struct *tsk = current; + struct vm86plus_struct __user *user; + struct vm86 *vm86 = current->thread.vm86; + long err = 0; /* * This gets called from entry.S with interrupts disabled, but @@ -138,31 +105,57 @@ struct pt_regs *save_v86_state(struct kernel_vm86_regs *regs) */ local_irq_enable(); - if (!current->thread.vm86_info) { - pr_alert("no vm86_info: BAD\n"); + if (!vm86 || !vm86->user_vm86) { + pr_alert("no user_vm86: BAD\n"); + do_exit(SIGSEGV); + } + set_flags(regs->pt.flags, VEFLAGS, X86_EFLAGS_VIF | vm86->veflags_mask); + user = vm86->user_vm86; + + if (!access_ok(VERIFY_WRITE, user, vm86->vm86plus.is_vm86pus ? + sizeof(struct vm86plus_struct) : + sizeof(struct vm86_struct))) { + pr_alert("could not access userspace vm86 info\n"); do_exit(SIGSEGV); } - set_flags(regs->pt.flags, VEFLAGS, X86_EFLAGS_VIF | current->thread.v86mask); - tmp = copy_vm86_regs_to_user(¤t->thread.vm86_info->regs, regs); - tmp += put_user(current->thread.screen_bitmap, ¤t->thread.vm86_info->screen_bitmap); - if (tmp) { - pr_alert("could not access userspace vm86_info\n"); + + put_user_try { + put_user_ex(regs->pt.bx, &user->regs.ebx); + put_user_ex(regs->pt.cx, &user->regs.ecx); + put_user_ex(regs->pt.dx, &user->regs.edx); + put_user_ex(regs->pt.si, &user->regs.esi); + put_user_ex(regs->pt.di, &user->regs.edi); + put_user_ex(regs->pt.bp, &user->regs.ebp); + put_user_ex(regs->pt.ax, &user->regs.eax); + put_user_ex(regs->pt.ip, &user->regs.eip); + put_user_ex(regs->pt.cs, &user->regs.cs); + put_user_ex(regs->pt.flags, &user->regs.eflags); + put_user_ex(regs->pt.sp, &user->regs.esp); + put_user_ex(regs->pt.ss, &user->regs.ss); + put_user_ex(regs->es, &user->regs.es); + put_user_ex(regs->ds, &user->regs.ds); + put_user_ex(regs->fs, &user->regs.fs); + put_user_ex(regs->gs, &user->regs.gs); + + put_user_ex(vm86->screen_bitmap, &user->screen_bitmap); + } put_user_catch(err); + if (err) { + pr_alert("could not access userspace vm86 info\n"); do_exit(SIGSEGV); } tss = &per_cpu(cpu_tss, get_cpu()); - current->thread.sp0 = current->thread.saved_sp0; - current->thread.sysenter_cs = __KERNEL_CS; - load_sp0(tss, ¤t->thread); - current->thread.saved_sp0 = 0; + tsk->thread.sp0 = vm86->saved_sp0; + tsk->thread.sysenter_cs = __KERNEL_CS; + load_sp0(tss, &tsk->thread); + vm86->saved_sp0 = 0; put_cpu(); - ret = KVM86->regs32; + memcpy(®s->pt, &vm86->regs32, sizeof(struct pt_regs)); - ret->fs = current->thread.saved_fs; - set_user_gs(ret, current->thread.saved_gs); + lazy_load_gs(vm86->regs32.gs); - return ret; + regs->pt.ax = retval; } static void mark_screen_rdonly(struct mm_struct *mm) @@ -182,7 +175,11 @@ static void mark_screen_rdonly(struct mm_struct *mm) if (pud_none_or_clear_bad(pud)) goto out; pmd = pmd_offset(pud, 0xA0000); - split_huge_page_pmd_mm(mm, 0xA0000, pmd); + + if (pmd_trans_huge(*pmd)) { + struct vm_area_struct *vma = find_vma(mm, 0xA0000); + split_huge_pmd(vma, pmd, 0xA0000); + } if (pmd_none_or_clear_bad(pmd)) goto out; pte = pte_offset_map_lock(mm, pmd, 0xA0000, &ptl); @@ -200,45 +197,16 @@ out: static int do_vm86_irq_handling(int subfunction, int irqnumber); -static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk); +static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus); -SYSCALL_DEFINE1(vm86old, struct vm86_struct __user *, v86) +SYSCALL_DEFINE1(vm86old, struct vm86_struct __user *, user_vm86) { - struct kernel_vm86_struct info; /* declare this _on top_, - * this avoids wasting of stack space. - * This remains on the stack until we - * return to 32 bit user space. - */ - struct task_struct *tsk = current; - int tmp; - - if (tsk->thread.saved_sp0) - return -EPERM; - tmp = copy_vm86_regs_from_user(&info.regs, &v86->regs, - offsetof(struct kernel_vm86_struct, vm86plus) - - sizeof(info.regs)); - if (tmp) - return -EFAULT; - memset(&info.vm86plus, 0, (int)&info.regs32 - (int)&info.vm86plus); - info.regs32 = current_pt_regs(); - tsk->thread.vm86_info = v86; - do_sys_vm86(&info, tsk); - return 0; /* we never return here */ + return do_sys_vm86((struct vm86plus_struct __user *) user_vm86, false); } SYSCALL_DEFINE2(vm86, unsigned long, cmd, unsigned long, arg) { - struct kernel_vm86_struct info; /* declare this _on top_, - * this avoids wasting of stack space. - * This remains on the stack until we - * return to 32 bit user space. - */ - struct task_struct *tsk; - int tmp; - struct vm86plus_struct __user *v86; - - tsk = current; switch (cmd) { case VM86_REQUEST_IRQ: case VM86_FREE_IRQ: @@ -256,114 +224,161 @@ SYSCALL_DEFINE2(vm86, unsigned long, cmd, unsigned long, arg) } /* we come here only for functions VM86_ENTER, VM86_ENTER_NO_BYPASS */ - if (tsk->thread.saved_sp0) - return -EPERM; - v86 = (struct vm86plus_struct __user *)arg; - tmp = copy_vm86_regs_from_user(&info.regs, &v86->regs, - offsetof(struct kernel_vm86_struct, regs32) - - sizeof(info.regs)); - if (tmp) - return -EFAULT; - info.regs32 = current_pt_regs(); - info.vm86plus.is_vm86pus = 1; - tsk->thread.vm86_info = (struct vm86_struct __user *)v86; - do_sys_vm86(&info, tsk); - return 0; /* we never return here */ + return do_sys_vm86((struct vm86plus_struct __user *) arg, true); } -static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk) +static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) { struct tss_struct *tss; -/* - * make sure the vm86() system call doesn't try to do anything silly - */ - info->regs.pt.ds = 0; - info->regs.pt.es = 0; - info->regs.pt.fs = 0; -#ifndef CONFIG_X86_32_LAZY_GS - info->regs.pt.gs = 0; -#endif + struct task_struct *tsk = current; + struct vm86 *vm86 = tsk->thread.vm86; + struct kernel_vm86_regs vm86regs; + struct pt_regs *regs = current_pt_regs(); + unsigned long err = 0; + + err = security_mmap_addr(0); + if (err) { + /* + * vm86 cannot virtualize the address space, so vm86 users + * need to manage the low 1MB themselves using mmap. Given + * that BIOS places important data in the first page, vm86 + * is essentially useless if mmap_min_addr != 0. DOSEMU, + * for example, won't even bother trying to use vm86 if it + * can't map a page at virtual address 0. + * + * To reduce the available kernel attack surface, simply + * disallow vm86(old) for users who cannot mmap at va 0. + * + * The implementation of security_mmap_addr will allow + * suitably privileged users to map va 0 even if + * vm.mmap_min_addr is set above 0, and we want this + * behavior for vm86 as well, as it ensures that legacy + * tools like vbetool will not fail just because of + * vm.mmap_min_addr. + */ + pr_info_once("Denied a call to vm86(old) from %s[%d] (uid: %d). Set the vm.mmap_min_addr sysctl to 0 and/or adjust LSM mmap_min_addr policy to enable vm86 if you are using a vm86-based DOS emulator.\n", + current->comm, task_pid_nr(current), + from_kuid_munged(&init_user_ns, current_uid())); + return -EPERM; + } + + if (!vm86) { + if (!(vm86 = kzalloc(sizeof(*vm86), GFP_KERNEL))) + return -ENOMEM; + tsk->thread.vm86 = vm86; + } + if (vm86->saved_sp0) + return -EPERM; + + if (!access_ok(VERIFY_READ, user_vm86, plus ? + sizeof(struct vm86_struct) : + sizeof(struct vm86plus_struct))) + return -EFAULT; + + memset(&vm86regs, 0, sizeof(vm86regs)); + get_user_try { + unsigned short seg; + get_user_ex(vm86regs.pt.bx, &user_vm86->regs.ebx); + get_user_ex(vm86regs.pt.cx, &user_vm86->regs.ecx); + get_user_ex(vm86regs.pt.dx, &user_vm86->regs.edx); + get_user_ex(vm86regs.pt.si, &user_vm86->regs.esi); + get_user_ex(vm86regs.pt.di, &user_vm86->regs.edi); + get_user_ex(vm86regs.pt.bp, &user_vm86->regs.ebp); + get_user_ex(vm86regs.pt.ax, &user_vm86->regs.eax); + get_user_ex(vm86regs.pt.ip, &user_vm86->regs.eip); + get_user_ex(seg, &user_vm86->regs.cs); + vm86regs.pt.cs = seg; + get_user_ex(vm86regs.pt.flags, &user_vm86->regs.eflags); + get_user_ex(vm86regs.pt.sp, &user_vm86->regs.esp); + get_user_ex(seg, &user_vm86->regs.ss); + vm86regs.pt.ss = seg; + get_user_ex(vm86regs.es, &user_vm86->regs.es); + get_user_ex(vm86regs.ds, &user_vm86->regs.ds); + get_user_ex(vm86regs.fs, &user_vm86->regs.fs); + get_user_ex(vm86regs.gs, &user_vm86->regs.gs); + + get_user_ex(vm86->flags, &user_vm86->flags); + get_user_ex(vm86->screen_bitmap, &user_vm86->screen_bitmap); + get_user_ex(vm86->cpu_type, &user_vm86->cpu_type); + } get_user_catch(err); + if (err) + return err; + + if (copy_from_user(&vm86->int_revectored, + &user_vm86->int_revectored, + sizeof(struct revectored_struct))) + return -EFAULT; + if (copy_from_user(&vm86->int21_revectored, + &user_vm86->int21_revectored, + sizeof(struct revectored_struct))) + return -EFAULT; + if (plus) { + if (copy_from_user(&vm86->vm86plus, &user_vm86->vm86plus, + sizeof(struct vm86plus_info_struct))) + return -EFAULT; + vm86->vm86plus.is_vm86pus = 1; + } else + memset(&vm86->vm86plus, 0, + sizeof(struct vm86plus_info_struct)); + + memcpy(&vm86->regs32, regs, sizeof(struct pt_regs)); + vm86->user_vm86 = user_vm86; /* * The flags register is also special: we cannot trust that the user * has set it up safely, so this makes sure interrupt etc flags are * inherited from protected mode. */ - VEFLAGS = info->regs.pt.flags; - info->regs.pt.flags &= SAFE_MASK; - info->regs.pt.flags |= info->regs32->flags & ~SAFE_MASK; - info->regs.pt.flags |= X86_VM_MASK; + VEFLAGS = vm86regs.pt.flags; + vm86regs.pt.flags &= SAFE_MASK; + vm86regs.pt.flags |= regs->flags & ~SAFE_MASK; + vm86regs.pt.flags |= X86_VM_MASK; - switch (info->cpu_type) { + vm86regs.pt.orig_ax = regs->orig_ax; + + switch (vm86->cpu_type) { case CPU_286: - tsk->thread.v86mask = 0; + vm86->veflags_mask = 0; break; case CPU_386: - tsk->thread.v86mask = X86_EFLAGS_NT | X86_EFLAGS_IOPL; + vm86->veflags_mask = X86_EFLAGS_NT | X86_EFLAGS_IOPL; break; case CPU_486: - tsk->thread.v86mask = X86_EFLAGS_AC | X86_EFLAGS_NT | X86_EFLAGS_IOPL; + vm86->veflags_mask = X86_EFLAGS_AC | X86_EFLAGS_NT | X86_EFLAGS_IOPL; break; default: - tsk->thread.v86mask = X86_EFLAGS_ID | X86_EFLAGS_AC | X86_EFLAGS_NT | X86_EFLAGS_IOPL; + vm86->veflags_mask = X86_EFLAGS_ID | X86_EFLAGS_AC | X86_EFLAGS_NT | X86_EFLAGS_IOPL; break; } /* - * Save old state, set default return value (%ax) to 0 (VM86_SIGNAL) + * Save old state */ - info->regs32->ax = VM86_SIGNAL; - tsk->thread.saved_sp0 = tsk->thread.sp0; - tsk->thread.saved_fs = info->regs32->fs; - tsk->thread.saved_gs = get_user_gs(info->regs32); + vm86->saved_sp0 = tsk->thread.sp0; + lazy_save_gs(vm86->regs32.gs); tss = &per_cpu(cpu_tss, get_cpu()); - tsk->thread.sp0 = (unsigned long) &info->VM86_TSS_ESP0; - if (cpu_has_sep) + /* make room for real-mode segments */ + tsk->thread.sp0 += 16; + + if (static_cpu_has_safe(X86_FEATURE_SEP)) tsk->thread.sysenter_cs = 0; + load_sp0(tss, &tsk->thread); put_cpu(); - tsk->thread.screen_bitmap = info->screen_bitmap; - if (info->flags & VM86_SCREEN_BITMAP) + if (vm86->flags & VM86_SCREEN_BITMAP) mark_screen_rdonly(tsk->mm); - /*call __audit_syscall_exit since we do not exit via the normal paths */ -#ifdef CONFIG_AUDITSYSCALL - if (unlikely(current->audit_context)) - __audit_syscall_exit(1, 0); -#endif - - __asm__ __volatile__( - "movl %0,%%esp\n\t" - "movl %1,%%ebp\n\t" -#ifdef CONFIG_X86_32_LAZY_GS - "mov %2, %%gs\n\t" -#endif - "jmp resume_userspace" - : /* no outputs */ - :"r" (&info->regs), "r" (task_thread_info(tsk)), "r" (0)); - /* we never return here */ -} - -static inline void return_to_32bit(struct kernel_vm86_regs *regs16, int retval) -{ - struct pt_regs *regs32; - - regs32 = save_v86_state(regs16); - regs32->ax = retval; - __asm__ __volatile__("movl %0,%%esp\n\t" - "movl %1,%%ebp\n\t" - "jmp resume_userspace" - : : "r" (regs32), "r" (current_thread_info())); + memcpy((struct kernel_vm86_regs *)regs, &vm86regs, sizeof(vm86regs)); + force_iret(); + return regs->ax; } static inline void set_IF(struct kernel_vm86_regs *regs) { VEFLAGS |= X86_EFLAGS_VIF; - if (VEFLAGS & X86_EFLAGS_VIP) - return_to_32bit(regs, VM86_STI); } static inline void clear_IF(struct kernel_vm86_regs *regs) @@ -395,7 +410,7 @@ static inline void clear_AC(struct kernel_vm86_regs *regs) static inline void set_vflags_long(unsigned long flags, struct kernel_vm86_regs *regs) { - set_flags(VEFLAGS, flags, current->thread.v86mask); + set_flags(VEFLAGS, flags, current->thread.vm86->veflags_mask); set_flags(regs->pt.flags, flags, SAFE_MASK); if (flags & X86_EFLAGS_IF) set_IF(regs); @@ -405,7 +420,7 @@ static inline void set_vflags_long(unsigned long flags, struct kernel_vm86_regs static inline void set_vflags_short(unsigned short flags, struct kernel_vm86_regs *regs) { - set_flags(VFLAGS, flags, current->thread.v86mask); + set_flags(VFLAGS, flags, current->thread.vm86->veflags_mask); set_flags(regs->pt.flags, flags, SAFE_MASK); if (flags & X86_EFLAGS_IF) set_IF(regs); @@ -420,7 +435,7 @@ static inline unsigned long get_vflags(struct kernel_vm86_regs *regs) if (VEFLAGS & X86_EFLAGS_VIF) flags |= X86_EFLAGS_IF; flags |= X86_EFLAGS_IOPL; - return flags | (VEFLAGS & current->thread.v86mask); + return flags | (VEFLAGS & current->thread.vm86->veflags_mask); } static inline int is_revectored(int nr, struct revectored_struct *bitmap) @@ -518,12 +533,13 @@ static void do_int(struct kernel_vm86_regs *regs, int i, { unsigned long __user *intr_ptr; unsigned long segoffs; + struct vm86 *vm86 = current->thread.vm86; if (regs->pt.cs == BIOSSEG) goto cannot_handle; - if (is_revectored(i, &KVM86->int_revectored)) + if (is_revectored(i, &vm86->int_revectored)) goto cannot_handle; - if (i == 0x21 && is_revectored(AH(regs), &KVM86->int21_revectored)) + if (i == 0x21 && is_revectored(AH(regs), &vm86->int21_revectored)) goto cannot_handle; intr_ptr = (unsigned long __user *) (i << 2); if (get_user(segoffs, intr_ptr)) @@ -542,18 +558,16 @@ static void do_int(struct kernel_vm86_regs *regs, int i, return; cannot_handle: - return_to_32bit(regs, VM86_INTx + (i << 8)); + save_v86_state(regs, VM86_INTx + (i << 8)); } int handle_vm86_trap(struct kernel_vm86_regs *regs, long error_code, int trapno) { - if (VMPI.is_vm86pus) { + struct vm86 *vm86 = current->thread.vm86; + + if (vm86->vm86plus.is_vm86pus) { if ((trapno == 3) || (trapno == 1)) { - KVM86->regs32->ax = VM86_TRAP + (trapno << 8); - /* setting this flag forces the code in entry_32.S to - the path where we call save_v86_state() and change - the stack pointer to KVM86->regs32 */ - set_thread_flag(TIF_NOTIFY_RESUME); + save_v86_state(regs, VM86_TRAP + (trapno << 8)); return 0; } do_int(regs, trapno, (unsigned char __user *) (regs->pt.ss << 4), SP(regs)); @@ -574,16 +588,11 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code) unsigned char __user *ssp; unsigned short ip, sp, orig_flags; int data32, pref_done; + struct vm86plus_info_struct *vmpi = ¤t->thread.vm86->vm86plus; #define CHECK_IF_IN_TRAP \ - if (VMPI.vm86dbg_active && VMPI.vm86dbg_TFpendig) \ + if (vmpi->vm86dbg_active && vmpi->vm86dbg_TFpendig) \ newflags |= X86_EFLAGS_TF -#define VM86_FAULT_RETURN do { \ - if (VMPI.force_return_for_pic && (VEFLAGS & (X86_EFLAGS_IF | X86_EFLAGS_VIF))) \ - return_to_32bit(regs, VM86_PICRETURN); \ - if (orig_flags & X86_EFLAGS_TF) \ - handle_vm86_trap(regs, 0, 1); \ - return; } while (0) orig_flags = *(unsigned short *)®s->pt.flags; @@ -622,7 +631,7 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code) SP(regs) -= 2; } IP(regs) = ip; - VM86_FAULT_RETURN; + goto vm86_fault_return; /* popf */ case 0x9d: @@ -642,16 +651,18 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code) else set_vflags_short(newflags, regs); - VM86_FAULT_RETURN; + goto check_vip; } /* int xx */ case 0xcd: { int intno = popb(csp, ip, simulate_sigsegv); IP(regs) = ip; - if (VMPI.vm86dbg_active) { - if ((1 << (intno & 7)) & VMPI.vm86dbg_intxxtab[intno >> 3]) - return_to_32bit(regs, VM86_INTx + (intno << 8)); + if (vmpi->vm86dbg_active) { + if ((1 << (intno & 7)) & vmpi->vm86dbg_intxxtab[intno >> 3]) { + save_v86_state(regs, VM86_INTx + (intno << 8)); + return; + } } do_int(regs, intno, ssp, sp); return; @@ -682,14 +693,14 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code) } else { set_vflags_short(newflags, regs); } - VM86_FAULT_RETURN; + goto check_vip; } /* cli */ case 0xfa: IP(regs) = ip; clear_IF(regs); - VM86_FAULT_RETURN; + goto vm86_fault_return; /* sti */ /* @@ -701,12 +712,27 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code) case 0xfb: IP(regs) = ip; set_IF(regs); - VM86_FAULT_RETURN; + goto check_vip; default: - return_to_32bit(regs, VM86_UNKNOWN); + save_v86_state(regs, VM86_UNKNOWN); + } + + return; + +check_vip: + if (VEFLAGS & X86_EFLAGS_VIP) { + save_v86_state(regs, VM86_STI); + return; } +vm86_fault_return: + if (vmpi->force_return_for_pic && (VEFLAGS & (X86_EFLAGS_IF | X86_EFLAGS_VIF))) { + save_v86_state(regs, VM86_PICRETURN); + return; + } + if (orig_flags & X86_EFLAGS_TF) + handle_vm86_trap(regs, 0, X86_TRAP_DB); return; simulate_sigsegv: @@ -720,7 +746,7 @@ simulate_sigsegv: * should be a mixture of the two, but how do we * get the information? [KD] */ - return_to_32bit(regs, VM86_UNKNOWN); + save_v86_state(regs, VM86_UNKNOWN); } /* ---------------- vm86 special IRQ passing stuff ----------------- */ diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 00bf300fd846..74e4bf11f562 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -364,7 +364,7 @@ INIT_PER_CPU(irq_stack_union); #endif /* CONFIG_X86_32 */ -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE #include <asm/kexec.h> . = ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE, diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 3839628d962e..dad5fe9633a3 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -68,7 +68,6 @@ struct x86_init_ops x86_init __initdata = { .timers = { .setup_percpu_clockev = setup_boot_APIC_clock, - .tsc_pre_init = x86_init_noop, .timer_init = hpet_time_init, .wallclock_init = x86_init_noop, }, diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index d8a1d56276e1..639a6e34500c 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -28,6 +28,8 @@ config KVM select ANON_INODES select HAVE_KVM_IRQCHIP select HAVE_KVM_IRQFD + select IRQ_BYPASS_MANAGER + select HAVE_KVM_IRQ_BYPASS select HAVE_KVM_IRQ_ROUTING select HAVE_KVM_EVENTFD select KVM_APIC_ARCHITECTURE diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 67d215cb8953..a1ff508bb423 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -12,7 +12,9 @@ kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \ kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ - i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o + i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \ + hyperv.o + kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += assigned-dev.o iommu.o kvm-intel-y += vmx.o pmu_intel.o kvm-amd-y += svm.o pmu_amd.o diff --git a/arch/x86/kvm/assigned-dev.c b/arch/x86/kvm/assigned-dev.c index d090ecf08809..9dc091acd5fb 100644 --- a/arch/x86/kvm/assigned-dev.c +++ b/arch/x86/kvm/assigned-dev.c @@ -21,6 +21,7 @@ #include <linux/fs.h> #include "irq.h" #include "assigned-dev.h" +#include "trace/events/kvm.h" struct kvm_assigned_dev_kernel { struct kvm_irq_ack_notifier ack_notifier; @@ -131,7 +132,42 @@ static irqreturn_t kvm_assigned_dev_thread_intx(int irq, void *dev_id) return IRQ_HANDLED; } -#ifdef __KVM_HAVE_MSI +/* + * Deliver an IRQ in an atomic context if we can, or return a failure, + * user can retry in a process context. + * Return value: + * -EWOULDBLOCK - Can't deliver in atomic context: retry in a process context. + * Other values - No need to retry. + */ +static int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, + int level) +{ + struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS]; + struct kvm_kernel_irq_routing_entry *e; + int ret = -EINVAL; + int idx; + + trace_kvm_set_irq(irq, level, irq_source_id); + + /* + * Injection into either PIC or IOAPIC might need to scan all CPUs, + * which would need to be retried from thread context; when same GSI + * is connected to both PIC and IOAPIC, we'd have to report a + * partial failure here. + * Since there's no easy way to do this, we only support injecting MSI + * which is limited to 1:1 GSI mapping. + */ + idx = srcu_read_lock(&kvm->irq_srcu); + if (kvm_irq_map_gsi(kvm, entries, irq) > 0) { + e = &entries[0]; + ret = kvm_arch_set_irq_inatomic(e, kvm, irq_source_id, + irq, level); + } + srcu_read_unlock(&kvm->irq_srcu, idx); + return ret; +} + + static irqreturn_t kvm_assigned_dev_msi(int irq, void *dev_id) { struct kvm_assigned_dev_kernel *assigned_dev = dev_id; @@ -150,9 +186,7 @@ static irqreturn_t kvm_assigned_dev_thread_msi(int irq, void *dev_id) return IRQ_HANDLED; } -#endif -#ifdef __KVM_HAVE_MSIX static irqreturn_t kvm_assigned_dev_msix(int irq, void *dev_id) { struct kvm_assigned_dev_kernel *assigned_dev = dev_id; @@ -183,7 +217,6 @@ static irqreturn_t kvm_assigned_dev_thread_msix(int irq, void *dev_id) return IRQ_HANDLED; } -#endif /* Ack the irq line for an assigned device */ static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian) @@ -386,7 +419,6 @@ static int assigned_device_enable_host_intx(struct kvm *kvm, return 0; } -#ifdef __KVM_HAVE_MSI static int assigned_device_enable_host_msi(struct kvm *kvm, struct kvm_assigned_dev_kernel *dev) { @@ -408,9 +440,7 @@ static int assigned_device_enable_host_msi(struct kvm *kvm, return 0; } -#endif -#ifdef __KVM_HAVE_MSIX static int assigned_device_enable_host_msix(struct kvm *kvm, struct kvm_assigned_dev_kernel *dev) { @@ -443,8 +473,6 @@ err: return r; } -#endif - static int assigned_device_enable_guest_intx(struct kvm *kvm, struct kvm_assigned_dev_kernel *dev, struct kvm_assigned_irq *irq) @@ -454,7 +482,6 @@ static int assigned_device_enable_guest_intx(struct kvm *kvm, return 0; } -#ifdef __KVM_HAVE_MSI static int assigned_device_enable_guest_msi(struct kvm *kvm, struct kvm_assigned_dev_kernel *dev, struct kvm_assigned_irq *irq) @@ -463,9 +490,7 @@ static int assigned_device_enable_guest_msi(struct kvm *kvm, dev->ack_notifier.gsi = -1; return 0; } -#endif -#ifdef __KVM_HAVE_MSIX static int assigned_device_enable_guest_msix(struct kvm *kvm, struct kvm_assigned_dev_kernel *dev, struct kvm_assigned_irq *irq) @@ -474,7 +499,6 @@ static int assigned_device_enable_guest_msix(struct kvm *kvm, dev->ack_notifier.gsi = -1; return 0; } -#endif static int assign_host_irq(struct kvm *kvm, struct kvm_assigned_dev_kernel *dev, @@ -492,16 +516,12 @@ static int assign_host_irq(struct kvm *kvm, case KVM_DEV_IRQ_HOST_INTX: r = assigned_device_enable_host_intx(kvm, dev); break; -#ifdef __KVM_HAVE_MSI case KVM_DEV_IRQ_HOST_MSI: r = assigned_device_enable_host_msi(kvm, dev); break; -#endif -#ifdef __KVM_HAVE_MSIX case KVM_DEV_IRQ_HOST_MSIX: r = assigned_device_enable_host_msix(kvm, dev); break; -#endif default: r = -EINVAL; } @@ -534,16 +554,12 @@ static int assign_guest_irq(struct kvm *kvm, case KVM_DEV_IRQ_GUEST_INTX: r = assigned_device_enable_guest_intx(kvm, dev, irq); break; -#ifdef __KVM_HAVE_MSI case KVM_DEV_IRQ_GUEST_MSI: r = assigned_device_enable_guest_msi(kvm, dev, irq); break; -#endif -#ifdef __KVM_HAVE_MSIX case KVM_DEV_IRQ_GUEST_MSIX: r = assigned_device_enable_guest_msix(kvm, dev, irq); break; -#endif default: r = -EINVAL; } @@ -826,7 +842,6 @@ out: } -#ifdef __KVM_HAVE_MSIX static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm, struct kvm_assigned_msix_nr *entry_nr) { @@ -906,7 +921,6 @@ msix_entry_out: return r; } -#endif static int kvm_vm_ioctl_set_pci_irq_mask(struct kvm *kvm, struct kvm_assigned_pci_dev *assigned_dev) @@ -1012,7 +1026,6 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, goto out; break; } -#ifdef __KVM_HAVE_MSIX case KVM_ASSIGN_SET_MSIX_NR: { struct kvm_assigned_msix_nr entry_nr; r = -EFAULT; @@ -1033,7 +1046,6 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, goto out; break; } -#endif case KVM_ASSIGN_SET_INTX_MASK: { struct kvm_assigned_pci_dev assigned_dev; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 2fbea2544f24..6525e926f566 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -30,7 +30,7 @@ static u32 xstate_required_size(u64 xstate_bv, bool compacted) int feature_bit = 0; u32 ret = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; - xstate_bv &= XSTATE_EXTEND_MASK; + xstate_bv &= XFEATURE_MASK_EXTEND; while (xstate_bv) { if (xstate_bv & 0x1) { u32 eax, ebx, ecx, edx, offset; @@ -51,7 +51,7 @@ u64 kvm_supported_xcr0(void) u64 xcr0 = KVM_SUPPORTED_XCR0 & host_xcr0; if (!kvm_x86_ops->mpx_supported()) - xcr0 &= ~(XSTATE_BNDREGS | XSTATE_BNDCSR); + xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR); return xcr0; } @@ -348,7 +348,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) | F(BMI2) | F(ERMS) | f_invpcid | F(RTM) | f_mpx | F(RDSEED) | F(ADX) | F(SMAP) | F(AVX512F) | F(AVX512PF) | F(AVX512ER) | - F(AVX512CD); + F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(PCOMMIT); /* cpuid 0xD.1.eax */ const u32 kvm_supported_word10_x86_features = diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index dd05b9cef6ae..c8eda1498121 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -2,6 +2,7 @@ #define ARCH_X86_KVM_CPUID_H #include "x86.h" +#include <asm/cpu.h> int kvm_update_cpuid(struct kvm_vcpu *vcpu); struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, @@ -38,6 +39,14 @@ static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu) return best && (best->ecx & bit(X86_FEATURE_XSAVE)); } +static inline bool guest_cpuid_has_mtrr(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 1, 0); + return best && (best->edx & bit(X86_FEATURE_MTRR)); +} + static inline bool guest_cpuid_has_tsc_adjust(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; @@ -133,4 +142,74 @@ static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu) best = kvm_find_cpuid_entry(vcpu, 7, 0); return best && (best->ebx & bit(X86_FEATURE_MPX)); } + +static inline bool guest_cpuid_has_pcommit(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 7, 0); + return best && (best->ebx & bit(X86_FEATURE_PCOMMIT)); +} + +static inline bool guest_cpuid_has_rdtscp(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); + return best && (best->edx & bit(X86_FEATURE_RDTSCP)); +} + +/* + * NRIPS is provided through cpuidfn 0x8000000a.edx bit 3 + */ +#define BIT_NRIPS 3 + +static inline bool guest_cpuid_has_nrips(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x8000000a, 0); + + /* + * NRIPS is a scattered cpuid feature, so we can't use + * X86_FEATURE_NRIPS here (X86_FEATURE_NRIPS would be bit + * position 8, not 3). + */ + return best && (best->edx & bit(BIT_NRIPS)); +} +#undef BIT_NRIPS + +static inline int guest_cpuid_family(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x1, 0); + if (!best) + return -1; + + return x86_family(best->eax); +} + +static inline int guest_cpuid_model(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x1, 0); + if (!best) + return -1; + + return x86_model(best->eax); +} + +static inline int guest_cpuid_stepping(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x1, 0); + if (!best) + return -1; + + return x86_stepping(best->eax); +} + #endif diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index e7a4fde5d631..1505587d06e9 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -650,6 +650,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, u16 sel; la = seg_base(ctxt, addr.seg) + addr.ea; + *linear = la; *max_size = 0; switch (mode) { case X86EMUL_MODE_PROT64: @@ -693,7 +694,6 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, } if (insn_aligned(ctxt, size) && ((la & (size - 1)) != 0)) return emulate_gp(ctxt, 0); - *linear = la; return X86EMUL_CONTINUE; bad: if (addr.seg == VCPU_SREG_SS) @@ -2272,8 +2272,8 @@ static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt) #define GET_SMSTATE(type, smbase, offset) \ ({ \ type __val; \ - int r = ctxt->ops->read_std(ctxt, smbase + offset, &__val, \ - sizeof(__val), NULL); \ + int r = ctxt->ops->read_phys(ctxt, smbase + offset, &__val, \ + sizeof(__val)); \ if (r != X86EMUL_CONTINUE) \ return X86EMUL_UNHANDLEABLE; \ __val; \ @@ -2418,7 +2418,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase) u64 val, cr0, cr4; u32 base3; u16 selector; - int i; + int i, r; for (i = 0; i < 16; i++) *reg_write(ctxt, i) = GET_SMSTATE(u64, smbase, 0x7ff8 - i * 8); @@ -2460,13 +2460,17 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase) dt.address = GET_SMSTATE(u64, smbase, 0x7e68); ctxt->ops->set_gdt(ctxt, &dt); + r = rsm_enter_protected_mode(ctxt, cr0, cr4); + if (r != X86EMUL_CONTINUE) + return r; + for (i = 0; i < 6; i++) { - int r = rsm_load_seg_64(ctxt, smbase, i); + r = rsm_load_seg_64(ctxt, smbase, i); if (r != X86EMUL_CONTINUE) return r; } - return rsm_enter_protected_mode(ctxt, cr0, cr4); + return X86EMUL_CONTINUE; } static int em_rsm(struct x86_emulate_ctxt *ctxt) @@ -2480,17 +2484,36 @@ static int em_rsm(struct x86_emulate_ctxt *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/CR3/CR4/EFER. It's all a bit more complicated if the vCPU + * supports long mode. */ + cr4 = ctxt->ops->get_cr(ctxt, 4); + if (emulator_has_longmode(ctxt)) { + struct desc_struct cs_desc; + + /* Zero CR4.PCIDE before CR0.PG. */ + if (cr4 & X86_CR4_PCIDE) { + ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE); + cr4 &= ~X86_CR4_PCIDE; + } + + /* A 32-bit code segment is required to clear EFER.LMA. */ + memset(&cs_desc, 0, sizeof(cs_desc)); + cs_desc.type = 0xb; + cs_desc.s = cs_desc.g = cs_desc.p = 1; + ctxt->ops->set_segment(ctxt, 0, &cs_desc, 0, VCPU_SREG_CS); + } + + /* For the 64-bit case, this will clear EFER.LMA. */ 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); + + /* Now clear CR4.PAE (which must be done before clearing EFER.LME). */ if (cr4 & X86_CR4_PAE) ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE); + + /* And finally go back to 32-bit mode. */ efer = 0; ctxt->ops->set_msr(ctxt, MSR_EFER, efer); @@ -4451,7 +4474,7 @@ 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), - II(No64 | EmulateOnUD | ImplicitOps, em_rsm, rsm), + II(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), diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c new file mode 100644 index 000000000000..c58ba67175ac --- /dev/null +++ b/arch/x86/kvm/hyperv.c @@ -0,0 +1,1104 @@ +/* + * KVM Microsoft Hyper-V emulation + * + * derived from arch/x86/kvm/x86.c + * + * Copyright (C) 2006 Qumranet, Inc. + * Copyright (C) 2008 Qumranet, Inc. + * Copyright IBM Corporation, 2008 + * Copyright 2010 Red Hat, Inc. and/or its affiliates. + * Copyright (C) 2015 Andrey Smetanin <asmetanin@virtuozzo.com> + * + * Authors: + * Avi Kivity <avi@qumranet.com> + * Yaniv Kamay <yaniv@qumranet.com> + * Amit Shah <amit.shah@qumranet.com> + * Ben-Ami Yassour <benami@il.ibm.com> + * Andrey Smetanin <asmetanin@virtuozzo.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include "x86.h" +#include "lapic.h" +#include "ioapic.h" +#include "hyperv.h" + +#include <linux/kvm_host.h> +#include <linux/highmem.h> +#include <asm/apicdef.h> +#include <trace/events/kvm.h> + +#include "trace.h" + +static inline u64 synic_read_sint(struct kvm_vcpu_hv_synic *synic, int sint) +{ + return atomic64_read(&synic->sint[sint]); +} + +static inline int synic_get_sint_vector(u64 sint_value) +{ + if (sint_value & HV_SYNIC_SINT_MASKED) + return -1; + return sint_value & HV_SYNIC_SINT_VECTOR_MASK; +} + +static bool synic_has_vector_connected(struct kvm_vcpu_hv_synic *synic, + int vector) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(synic->sint); i++) { + if (synic_get_sint_vector(synic_read_sint(synic, i)) == vector) + return true; + } + return false; +} + +static bool synic_has_vector_auto_eoi(struct kvm_vcpu_hv_synic *synic, + int vector) +{ + int i; + u64 sint_value; + + for (i = 0; i < ARRAY_SIZE(synic->sint); i++) { + sint_value = synic_read_sint(synic, i); + if (synic_get_sint_vector(sint_value) == vector && + sint_value & HV_SYNIC_SINT_AUTO_EOI) + return true; + } + return false; +} + +static int synic_set_sint(struct kvm_vcpu_hv_synic *synic, int sint, + u64 data, bool host) +{ + int vector; + + vector = data & HV_SYNIC_SINT_VECTOR_MASK; + if (vector < 16 && !host) + return 1; + /* + * Guest may configure multiple SINTs to use the same vector, so + * we maintain a bitmap of vectors handled by synic, and a + * bitmap of vectors with auto-eoi behavior. The bitmaps are + * updated here, and atomically queried on fast paths. + */ + + atomic64_set(&synic->sint[sint], data); + + if (synic_has_vector_connected(synic, vector)) + __set_bit(vector, synic->vec_bitmap); + else + __clear_bit(vector, synic->vec_bitmap); + + if (synic_has_vector_auto_eoi(synic, vector)) + __set_bit(vector, synic->auto_eoi_bitmap); + else + __clear_bit(vector, synic->auto_eoi_bitmap); + + /* Load SynIC vectors into EOI exit bitmap */ + kvm_make_request(KVM_REQ_SCAN_IOAPIC, synic_to_vcpu(synic)); + return 0; +} + +static struct kvm_vcpu_hv_synic *synic_get(struct kvm *kvm, u32 vcpu_id) +{ + struct kvm_vcpu *vcpu; + struct kvm_vcpu_hv_synic *synic; + + if (vcpu_id >= atomic_read(&kvm->online_vcpus)) + return NULL; + vcpu = kvm_get_vcpu(kvm, vcpu_id); + if (!vcpu) + return NULL; + synic = vcpu_to_synic(vcpu); + return (synic->active) ? synic : NULL; +} + +static void synic_clear_sint_msg_pending(struct kvm_vcpu_hv_synic *synic, + u32 sint) +{ + struct kvm_vcpu *vcpu = synic_to_vcpu(synic); + struct page *page; + gpa_t gpa; + struct hv_message *msg; + struct hv_message_page *msg_page; + + gpa = synic->msg_page & PAGE_MASK; + page = kvm_vcpu_gfn_to_page(vcpu, gpa >> PAGE_SHIFT); + if (is_error_page(page)) { + vcpu_err(vcpu, "Hyper-V SynIC can't get msg page, gpa 0x%llx\n", + gpa); + return; + } + msg_page = kmap_atomic(page); + + msg = &msg_page->sint_message[sint]; + msg->header.message_flags.msg_pending = 0; + + kunmap_atomic(msg_page); + kvm_release_page_dirty(page); + kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT); +} + +static void kvm_hv_notify_acked_sint(struct kvm_vcpu *vcpu, u32 sint) +{ + struct kvm *kvm = vcpu->kvm; + struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu); + struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu); + struct kvm_vcpu_hv_stimer *stimer; + int gsi, idx, stimers_pending; + + trace_kvm_hv_notify_acked_sint(vcpu->vcpu_id, sint); + + if (synic->msg_page & HV_SYNIC_SIMP_ENABLE) + synic_clear_sint_msg_pending(synic, sint); + + /* Try to deliver pending Hyper-V SynIC timers messages */ + stimers_pending = 0; + for (idx = 0; idx < ARRAY_SIZE(hv_vcpu->stimer); idx++) { + stimer = &hv_vcpu->stimer[idx]; + if (stimer->msg_pending && + (stimer->config & HV_STIMER_ENABLE) && + HV_STIMER_SINT(stimer->config) == sint) { + set_bit(stimer->index, + hv_vcpu->stimer_pending_bitmap); + stimers_pending++; + } + } + if (stimers_pending) + kvm_make_request(KVM_REQ_HV_STIMER, vcpu); + + idx = srcu_read_lock(&kvm->irq_srcu); + gsi = atomic_read(&synic->sint_to_gsi[sint]); + if (gsi != -1) + kvm_notify_acked_gsi(kvm, gsi); + srcu_read_unlock(&kvm->irq_srcu, idx); +} + +static void synic_exit(struct kvm_vcpu_hv_synic *synic, u32 msr) +{ + struct kvm_vcpu *vcpu = synic_to_vcpu(synic); + struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv; + + hv_vcpu->exit.type = KVM_EXIT_HYPERV_SYNIC; + hv_vcpu->exit.u.synic.msr = msr; + hv_vcpu->exit.u.synic.control = synic->control; + hv_vcpu->exit.u.synic.evt_page = synic->evt_page; + hv_vcpu->exit.u.synic.msg_page = synic->msg_page; + + kvm_make_request(KVM_REQ_HV_EXIT, vcpu); +} + +static int synic_set_msr(struct kvm_vcpu_hv_synic *synic, + u32 msr, u64 data, bool host) +{ + struct kvm_vcpu *vcpu = synic_to_vcpu(synic); + int ret; + + if (!synic->active) + return 1; + + trace_kvm_hv_synic_set_msr(vcpu->vcpu_id, msr, data, host); + + ret = 0; + switch (msr) { + case HV_X64_MSR_SCONTROL: + synic->control = data; + if (!host) + synic_exit(synic, msr); + break; + case HV_X64_MSR_SVERSION: + if (!host) { + ret = 1; + break; + } + synic->version = data; + break; + case HV_X64_MSR_SIEFP: + if (data & HV_SYNIC_SIEFP_ENABLE) + if (kvm_clear_guest(vcpu->kvm, + data & PAGE_MASK, PAGE_SIZE)) { + ret = 1; + break; + } + synic->evt_page = data; + if (!host) + synic_exit(synic, msr); + break; + case HV_X64_MSR_SIMP: + if (data & HV_SYNIC_SIMP_ENABLE) + if (kvm_clear_guest(vcpu->kvm, + data & PAGE_MASK, PAGE_SIZE)) { + ret = 1; + break; + } + synic->msg_page = data; + if (!host) + synic_exit(synic, msr); + break; + case HV_X64_MSR_EOM: { + int i; + + for (i = 0; i < ARRAY_SIZE(synic->sint); i++) + kvm_hv_notify_acked_sint(vcpu, i); + break; + } + case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15: + ret = synic_set_sint(synic, msr - HV_X64_MSR_SINT0, data, host); + break; + default: + ret = 1; + break; + } + return ret; +} + +static int synic_get_msr(struct kvm_vcpu_hv_synic *synic, u32 msr, u64 *pdata) +{ + int ret; + + if (!synic->active) + return 1; + + ret = 0; + switch (msr) { + case HV_X64_MSR_SCONTROL: + *pdata = synic->control; + break; + case HV_X64_MSR_SVERSION: + *pdata = synic->version; + break; + case HV_X64_MSR_SIEFP: + *pdata = synic->evt_page; + break; + case HV_X64_MSR_SIMP: + *pdata = synic->msg_page; + break; + case HV_X64_MSR_EOM: + *pdata = 0; + break; + case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15: + *pdata = atomic64_read(&synic->sint[msr - HV_X64_MSR_SINT0]); + break; + default: + ret = 1; + break; + } + return ret; +} + +int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint) +{ + struct kvm_vcpu *vcpu = synic_to_vcpu(synic); + struct kvm_lapic_irq irq; + int ret, vector; + + if (sint >= ARRAY_SIZE(synic->sint)) + return -EINVAL; + + vector = synic_get_sint_vector(synic_read_sint(synic, sint)); + if (vector < 0) + return -ENOENT; + + memset(&irq, 0, sizeof(irq)); + irq.dest_id = kvm_apic_id(vcpu->arch.apic); + irq.dest_mode = APIC_DEST_PHYSICAL; + irq.delivery_mode = APIC_DM_FIXED; + irq.vector = vector; + irq.level = 1; + + ret = kvm_irq_delivery_to_apic(vcpu->kvm, NULL, &irq, NULL); + trace_kvm_hv_synic_set_irq(vcpu->vcpu_id, sint, irq.vector, ret); + return ret; +} + +int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint) +{ + struct kvm_vcpu_hv_synic *synic; + + synic = synic_get(kvm, vcpu_id); + if (!synic) + return -EINVAL; + + return synic_set_irq(synic, sint); +} + +void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector) +{ + struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu); + int i; + + trace_kvm_hv_synic_send_eoi(vcpu->vcpu_id, vector); + + for (i = 0; i < ARRAY_SIZE(synic->sint); i++) + if (synic_get_sint_vector(synic_read_sint(synic, i)) == vector) + kvm_hv_notify_acked_sint(vcpu, i); +} + +static int kvm_hv_set_sint_gsi(struct kvm *kvm, u32 vcpu_id, u32 sint, int gsi) +{ + struct kvm_vcpu_hv_synic *synic; + + synic = synic_get(kvm, vcpu_id); + if (!synic) + return -EINVAL; + + if (sint >= ARRAY_SIZE(synic->sint_to_gsi)) + return -EINVAL; + + atomic_set(&synic->sint_to_gsi[sint], gsi); + return 0; +} + +void kvm_hv_irq_routing_update(struct kvm *kvm) +{ + struct kvm_irq_routing_table *irq_rt; + struct kvm_kernel_irq_routing_entry *e; + u32 gsi; + + irq_rt = srcu_dereference_check(kvm->irq_routing, &kvm->irq_srcu, + lockdep_is_held(&kvm->irq_lock)); + + for (gsi = 0; gsi < irq_rt->nr_rt_entries; gsi++) { + hlist_for_each_entry(e, &irq_rt->map[gsi], link) { + if (e->type == KVM_IRQ_ROUTING_HV_SINT) + kvm_hv_set_sint_gsi(kvm, e->hv_sint.vcpu, + e->hv_sint.sint, gsi); + } + } +} + +static void synic_init(struct kvm_vcpu_hv_synic *synic) +{ + int i; + + memset(synic, 0, sizeof(*synic)); + synic->version = HV_SYNIC_VERSION_1; + for (i = 0; i < ARRAY_SIZE(synic->sint); i++) { + atomic64_set(&synic->sint[i], HV_SYNIC_SINT_MASKED); + atomic_set(&synic->sint_to_gsi[i], -1); + } +} + +static u64 get_time_ref_counter(struct kvm *kvm) +{ + return div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100); +} + +static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer, + bool vcpu_kick) +{ + struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer); + + set_bit(stimer->index, + vcpu_to_hv_vcpu(vcpu)->stimer_pending_bitmap); + kvm_make_request(KVM_REQ_HV_STIMER, vcpu); + if (vcpu_kick) + kvm_vcpu_kick(vcpu); +} + +static void stimer_cleanup(struct kvm_vcpu_hv_stimer *stimer) +{ + struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer); + + trace_kvm_hv_stimer_cleanup(stimer_to_vcpu(stimer)->vcpu_id, + stimer->index); + + hrtimer_cancel(&stimer->timer); + clear_bit(stimer->index, + vcpu_to_hv_vcpu(vcpu)->stimer_pending_bitmap); + stimer->msg_pending = false; + stimer->exp_time = 0; +} + +static enum hrtimer_restart stimer_timer_callback(struct hrtimer *timer) +{ + struct kvm_vcpu_hv_stimer *stimer; + + stimer = container_of(timer, struct kvm_vcpu_hv_stimer, timer); + trace_kvm_hv_stimer_callback(stimer_to_vcpu(stimer)->vcpu_id, + stimer->index); + stimer_mark_pending(stimer, true); + + return HRTIMER_NORESTART; +} + +/* + * stimer_start() assumptions: + * a) stimer->count is not equal to 0 + * b) stimer->config has HV_STIMER_ENABLE flag + */ +static int stimer_start(struct kvm_vcpu_hv_stimer *stimer) +{ + u64 time_now; + ktime_t ktime_now; + + time_now = get_time_ref_counter(stimer_to_vcpu(stimer)->kvm); + ktime_now = ktime_get(); + + if (stimer->config & HV_STIMER_PERIODIC) { + if (stimer->exp_time) { + if (time_now >= stimer->exp_time) { + u64 remainder; + + div64_u64_rem(time_now - stimer->exp_time, + stimer->count, &remainder); + stimer->exp_time = + time_now + (stimer->count - remainder); + } + } else + stimer->exp_time = time_now + stimer->count; + + trace_kvm_hv_stimer_start_periodic( + stimer_to_vcpu(stimer)->vcpu_id, + stimer->index, + time_now, stimer->exp_time); + + hrtimer_start(&stimer->timer, + ktime_add_ns(ktime_now, + 100 * (stimer->exp_time - time_now)), + HRTIMER_MODE_ABS); + return 0; + } + stimer->exp_time = stimer->count; + if (time_now >= stimer->count) { + /* + * Expire timer according to Hypervisor Top-Level Functional + * specification v4(15.3.1): + * "If a one shot is enabled and the specified count is in + * the past, it will expire immediately." + */ + stimer_mark_pending(stimer, false); + return 0; + } + + trace_kvm_hv_stimer_start_one_shot(stimer_to_vcpu(stimer)->vcpu_id, + stimer->index, + time_now, stimer->count); + + hrtimer_start(&stimer->timer, + ktime_add_ns(ktime_now, 100 * (stimer->count - time_now)), + HRTIMER_MODE_ABS); + return 0; +} + +static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config, + bool host) +{ + trace_kvm_hv_stimer_set_config(stimer_to_vcpu(stimer)->vcpu_id, + stimer->index, config, host); + + stimer_cleanup(stimer); + if ((stimer->config & HV_STIMER_ENABLE) && HV_STIMER_SINT(config) == 0) + config &= ~HV_STIMER_ENABLE; + stimer->config = config; + stimer_mark_pending(stimer, false); + return 0; +} + +static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count, + bool host) +{ + trace_kvm_hv_stimer_set_count(stimer_to_vcpu(stimer)->vcpu_id, + stimer->index, count, host); + + stimer_cleanup(stimer); + stimer->count = count; + if (stimer->count == 0) + stimer->config &= ~HV_STIMER_ENABLE; + else if (stimer->config & HV_STIMER_AUTOENABLE) + stimer->config |= HV_STIMER_ENABLE; + stimer_mark_pending(stimer, false); + return 0; +} + +static int stimer_get_config(struct kvm_vcpu_hv_stimer *stimer, u64 *pconfig) +{ + *pconfig = stimer->config; + return 0; +} + +static int stimer_get_count(struct kvm_vcpu_hv_stimer *stimer, u64 *pcount) +{ + *pcount = stimer->count; + return 0; +} + +static int synic_deliver_msg(struct kvm_vcpu_hv_synic *synic, u32 sint, + struct hv_message *src_msg) +{ + struct kvm_vcpu *vcpu = synic_to_vcpu(synic); + struct page *page; + gpa_t gpa; + struct hv_message *dst_msg; + int r; + struct hv_message_page *msg_page; + + if (!(synic->msg_page & HV_SYNIC_SIMP_ENABLE)) + return -ENOENT; + + gpa = synic->msg_page & PAGE_MASK; + page = kvm_vcpu_gfn_to_page(vcpu, gpa >> PAGE_SHIFT); + if (is_error_page(page)) + return -EFAULT; + + msg_page = kmap_atomic(page); + dst_msg = &msg_page->sint_message[sint]; + if (sync_cmpxchg(&dst_msg->header.message_type, HVMSG_NONE, + src_msg->header.message_type) != HVMSG_NONE) { + dst_msg->header.message_flags.msg_pending = 1; + r = -EAGAIN; + } else { + memcpy(&dst_msg->u.payload, &src_msg->u.payload, + src_msg->header.payload_size); + dst_msg->header.message_type = src_msg->header.message_type; + dst_msg->header.payload_size = src_msg->header.payload_size; + r = synic_set_irq(synic, sint); + if (r >= 1) + r = 0; + else if (r == 0) + r = -EFAULT; + } + kunmap_atomic(msg_page); + kvm_release_page_dirty(page); + kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT); + return r; +} + +static int stimer_send_msg(struct kvm_vcpu_hv_stimer *stimer) +{ + struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer); + struct hv_message *msg = &stimer->msg; + struct hv_timer_message_payload *payload = + (struct hv_timer_message_payload *)&msg->u.payload; + + payload->expiration_time = stimer->exp_time; + payload->delivery_time = get_time_ref_counter(vcpu->kvm); + return synic_deliver_msg(vcpu_to_synic(vcpu), + HV_STIMER_SINT(stimer->config), msg); +} + +static void stimer_expiration(struct kvm_vcpu_hv_stimer *stimer) +{ + int r; + + stimer->msg_pending = true; + r = stimer_send_msg(stimer); + trace_kvm_hv_stimer_expiration(stimer_to_vcpu(stimer)->vcpu_id, + stimer->index, r); + if (!r) { + stimer->msg_pending = false; + if (!(stimer->config & HV_STIMER_PERIODIC)) + stimer->config &= ~HV_STIMER_ENABLE; + } +} + +void kvm_hv_process_stimers(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu); + struct kvm_vcpu_hv_stimer *stimer; + u64 time_now, exp_time; + int i; + + for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++) + if (test_and_clear_bit(i, hv_vcpu->stimer_pending_bitmap)) { + stimer = &hv_vcpu->stimer[i]; + if (stimer->config & HV_STIMER_ENABLE) { + exp_time = stimer->exp_time; + + if (exp_time) { + time_now = + get_time_ref_counter(vcpu->kvm); + if (time_now >= exp_time) + stimer_expiration(stimer); + } + + if ((stimer->config & HV_STIMER_ENABLE) && + stimer->count) + stimer_start(stimer); + else + stimer_cleanup(stimer); + } + } +} + +void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu); + int i; + + for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++) + stimer_cleanup(&hv_vcpu->stimer[i]); +} + +static void stimer_prepare_msg(struct kvm_vcpu_hv_stimer *stimer) +{ + struct hv_message *msg = &stimer->msg; + struct hv_timer_message_payload *payload = + (struct hv_timer_message_payload *)&msg->u.payload; + + memset(&msg->header, 0, sizeof(msg->header)); + msg->header.message_type = HVMSG_TIMER_EXPIRED; + msg->header.payload_size = sizeof(*payload); + + payload->timer_index = stimer->index; + payload->expiration_time = 0; + payload->delivery_time = 0; +} + +static void stimer_init(struct kvm_vcpu_hv_stimer *stimer, int timer_index) +{ + memset(stimer, 0, sizeof(*stimer)); + stimer->index = timer_index; + hrtimer_init(&stimer->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + stimer->timer.function = stimer_timer_callback; + stimer_prepare_msg(stimer); +} + +void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu); + int i; + + synic_init(&hv_vcpu->synic); + + bitmap_zero(hv_vcpu->stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT); + for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++) + stimer_init(&hv_vcpu->stimer[i], i); +} + +int kvm_hv_activate_synic(struct kvm_vcpu *vcpu) +{ + /* + * Hyper-V SynIC auto EOI SINT's are + * not compatible with APICV, so deactivate APICV + */ + kvm_vcpu_deactivate_apicv(vcpu); + vcpu_to_synic(vcpu)->active = true; + return 0; +} + +static bool kvm_hv_msr_partition_wide(u32 msr) +{ + bool r = false; + + switch (msr) { + case HV_X64_MSR_GUEST_OS_ID: + case HV_X64_MSR_HYPERCALL: + case HV_X64_MSR_REFERENCE_TSC: + case HV_X64_MSR_TIME_REF_COUNT: + case HV_X64_MSR_CRASH_CTL: + case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: + case HV_X64_MSR_RESET: + r = true; + break; + } + + return r; +} + +static int kvm_hv_msr_get_crash_data(struct kvm_vcpu *vcpu, + u32 index, u64 *pdata) +{ + struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + + if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param))) + return -EINVAL; + + *pdata = hv->hv_crash_param[index]; + return 0; +} + +static int kvm_hv_msr_get_crash_ctl(struct kvm_vcpu *vcpu, u64 *pdata) +{ + struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + + *pdata = hv->hv_crash_ctl; + return 0; +} + +static int kvm_hv_msr_set_crash_ctl(struct kvm_vcpu *vcpu, u64 data, bool host) +{ + struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + + if (host) + hv->hv_crash_ctl = data & HV_X64_MSR_CRASH_CTL_NOTIFY; + + if (!host && (data & HV_X64_MSR_CRASH_CTL_NOTIFY)) { + + vcpu_debug(vcpu, "hv crash (0x%llx 0x%llx 0x%llx 0x%llx 0x%llx)\n", + hv->hv_crash_param[0], + hv->hv_crash_param[1], + hv->hv_crash_param[2], + hv->hv_crash_param[3], + hv->hv_crash_param[4]); + + /* Send notification about crash to user space */ + kvm_make_request(KVM_REQ_HV_CRASH, vcpu); + } + + return 0; +} + +static int kvm_hv_msr_set_crash_data(struct kvm_vcpu *vcpu, + u32 index, u64 data) +{ + struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + + if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param))) + return -EINVAL; + + hv->hv_crash_param[index] = data; + return 0; +} + +static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, + bool host) +{ + struct kvm *kvm = vcpu->kvm; + struct kvm_hv *hv = &kvm->arch.hyperv; + + switch (msr) { + case HV_X64_MSR_GUEST_OS_ID: + hv->hv_guest_os_id = data; + /* setting guest os id to zero disables hypercall page */ + if (!hv->hv_guest_os_id) + hv->hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE; + break; + case HV_X64_MSR_HYPERCALL: { + u64 gfn; + unsigned long addr; + u8 instructions[4]; + + /* if guest os id is not set hypercall should remain disabled */ + if (!hv->hv_guest_os_id) + break; + if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) { + hv->hv_hypercall = data; + break; + } + gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT; + addr = gfn_to_hva(kvm, gfn); + if (kvm_is_error_hva(addr)) + return 1; + kvm_x86_ops->patch_hypercall(vcpu, instructions); + ((unsigned char *)instructions)[3] = 0xc3; /* ret */ + if (__copy_to_user((void __user *)addr, instructions, 4)) + return 1; + hv->hv_hypercall = data; + mark_page_dirty(kvm, gfn); + break; + } + case HV_X64_MSR_REFERENCE_TSC: { + u64 gfn; + HV_REFERENCE_TSC_PAGE tsc_ref; + + memset(&tsc_ref, 0, sizeof(tsc_ref)); + hv->hv_tsc_page = data; + if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE)) + break; + gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; + if (kvm_write_guest( + kvm, + gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT, + &tsc_ref, sizeof(tsc_ref))) + return 1; + mark_page_dirty(kvm, gfn); + break; + } + case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: + return kvm_hv_msr_set_crash_data(vcpu, + msr - HV_X64_MSR_CRASH_P0, + data); + case HV_X64_MSR_CRASH_CTL: + return kvm_hv_msr_set_crash_ctl(vcpu, data, host); + case HV_X64_MSR_RESET: + if (data == 1) { + vcpu_debug(vcpu, "hyper-v reset requested\n"); + kvm_make_request(KVM_REQ_HV_RESET, vcpu); + } + break; + default: + vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n", + msr, data); + return 1; + } + return 0; +} + +/* Calculate cpu time spent by current task in 100ns units */ +static u64 current_task_runtime_100ns(void) +{ + cputime_t utime, stime; + + task_cputime_adjusted(current, &utime, &stime); + return div_u64(cputime_to_nsecs(utime + stime), 100); +} + +static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) +{ + struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv; + + switch (msr) { + case HV_X64_MSR_APIC_ASSIST_PAGE: { + u64 gfn; + unsigned long addr; + + if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) { + hv->hv_vapic = data; + if (kvm_lapic_enable_pv_eoi(vcpu, 0)) + return 1; + break; + } + gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT; + 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; + hv->hv_vapic = data; + kvm_vcpu_mark_page_dirty(vcpu, gfn); + if (kvm_lapic_enable_pv_eoi(vcpu, + gfn_to_gpa(gfn) | KVM_MSR_ENABLED)) + return 1; + break; + } + case HV_X64_MSR_EOI: + return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data); + case HV_X64_MSR_ICR: + return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data); + case HV_X64_MSR_TPR: + return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data); + case HV_X64_MSR_VP_RUNTIME: + if (!host) + return 1; + hv->runtime_offset = data - current_task_runtime_100ns(); + break; + case HV_X64_MSR_SCONTROL: + case HV_X64_MSR_SVERSION: + case HV_X64_MSR_SIEFP: + case HV_X64_MSR_SIMP: + case HV_X64_MSR_EOM: + case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15: + return synic_set_msr(vcpu_to_synic(vcpu), msr, data, host); + case HV_X64_MSR_STIMER0_CONFIG: + case HV_X64_MSR_STIMER1_CONFIG: + case HV_X64_MSR_STIMER2_CONFIG: + case HV_X64_MSR_STIMER3_CONFIG: { + int timer_index = (msr - HV_X64_MSR_STIMER0_CONFIG)/2; + + return stimer_set_config(vcpu_to_stimer(vcpu, timer_index), + data, host); + } + case HV_X64_MSR_STIMER0_COUNT: + case HV_X64_MSR_STIMER1_COUNT: + case HV_X64_MSR_STIMER2_COUNT: + case HV_X64_MSR_STIMER3_COUNT: { + int timer_index = (msr - HV_X64_MSR_STIMER0_COUNT)/2; + + return stimer_set_count(vcpu_to_stimer(vcpu, timer_index), + data, host); + } + default: + vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n", + msr, data); + return 1; + } + + return 0; +} + +static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + u64 data = 0; + struct kvm *kvm = vcpu->kvm; + struct kvm_hv *hv = &kvm->arch.hyperv; + + switch (msr) { + case HV_X64_MSR_GUEST_OS_ID: + data = hv->hv_guest_os_id; + break; + case HV_X64_MSR_HYPERCALL: + data = hv->hv_hypercall; + break; + case HV_X64_MSR_TIME_REF_COUNT: + data = get_time_ref_counter(kvm); + break; + case HV_X64_MSR_REFERENCE_TSC: + data = hv->hv_tsc_page; + break; + case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: + return kvm_hv_msr_get_crash_data(vcpu, + msr - HV_X64_MSR_CRASH_P0, + pdata); + case HV_X64_MSR_CRASH_CTL: + return kvm_hv_msr_get_crash_ctl(vcpu, pdata); + case HV_X64_MSR_RESET: + data = 0; + break; + default: + vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + return 1; + } + + *pdata = data; + return 0; +} + +static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + u64 data = 0; + struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv; + + switch (msr) { + case HV_X64_MSR_VP_INDEX: { + int r; + struct kvm_vcpu *v; + + kvm_for_each_vcpu(r, v, vcpu->kvm) { + if (v == vcpu) { + data = r; + break; + } + } + break; + } + case HV_X64_MSR_EOI: + return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata); + case HV_X64_MSR_ICR: + return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata); + case HV_X64_MSR_TPR: + return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata); + case HV_X64_MSR_APIC_ASSIST_PAGE: + data = hv->hv_vapic; + break; + case HV_X64_MSR_VP_RUNTIME: + data = current_task_runtime_100ns() + hv->runtime_offset; + break; + case HV_X64_MSR_SCONTROL: + case HV_X64_MSR_SVERSION: + case HV_X64_MSR_SIEFP: + case HV_X64_MSR_SIMP: + case HV_X64_MSR_EOM: + case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15: + return synic_get_msr(vcpu_to_synic(vcpu), msr, pdata); + case HV_X64_MSR_STIMER0_CONFIG: + case HV_X64_MSR_STIMER1_CONFIG: + case HV_X64_MSR_STIMER2_CONFIG: + case HV_X64_MSR_STIMER3_CONFIG: { + int timer_index = (msr - HV_X64_MSR_STIMER0_CONFIG)/2; + + return stimer_get_config(vcpu_to_stimer(vcpu, timer_index), + pdata); + } + case HV_X64_MSR_STIMER0_COUNT: + case HV_X64_MSR_STIMER1_COUNT: + case HV_X64_MSR_STIMER2_COUNT: + case HV_X64_MSR_STIMER3_COUNT: { + int timer_index = (msr - HV_X64_MSR_STIMER0_COUNT)/2; + + return stimer_get_count(vcpu_to_stimer(vcpu, timer_index), + pdata); + } + default: + vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + return 1; + } + *pdata = data; + return 0; +} + +int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) +{ + if (kvm_hv_msr_partition_wide(msr)) { + int r; + + mutex_lock(&vcpu->kvm->lock); + r = kvm_hv_set_msr_pw(vcpu, msr, data, host); + mutex_unlock(&vcpu->kvm->lock); + return r; + } else + return kvm_hv_set_msr(vcpu, msr, data, host); +} + +int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + if (kvm_hv_msr_partition_wide(msr)) { + int r; + + mutex_lock(&vcpu->kvm->lock); + r = kvm_hv_get_msr_pw(vcpu, msr, pdata); + mutex_unlock(&vcpu->kvm->lock); + return r; + } else + return kvm_hv_get_msr(vcpu, msr, pdata); +} + +bool kvm_hv_hypercall_enabled(struct kvm *kvm) +{ + return kvm->arch.hyperv.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE; +} + +int kvm_hv_hypercall(struct kvm_vcpu *vcpu) +{ + u64 param, ingpa, outgpa, ret; + uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0; + bool fast, longmode; + + /* + * hypercall generates UD from non zero cpl and real mode + * per HYPER-V spec + */ + if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 0; + } + + longmode = is_64_bit_mode(vcpu); + + if (!longmode) { + param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) | + (kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff); + ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) | + (kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff); + outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) | + (kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff); + } +#ifdef CONFIG_X86_64 + else { + param = kvm_register_read(vcpu, VCPU_REGS_RCX); + ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX); + outgpa = kvm_register_read(vcpu, VCPU_REGS_R8); + } +#endif + + code = param & 0xffff; + fast = (param >> 16) & 0x1; + rep_cnt = (param >> 32) & 0xfff; + rep_idx = (param >> 48) & 0xfff; + + trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa); + + switch (code) { + case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT: + kvm_vcpu_on_spin(vcpu); + break; + default: + res = HV_STATUS_INVALID_HYPERCALL_CODE; + break; + } + + ret = res | (((u64)rep_done & 0xfff) << 32); + if (longmode) { + kvm_register_write(vcpu, VCPU_REGS_RAX, ret); + } else { + kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32); + kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff); + } + + return 1; +} diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h new file mode 100644 index 000000000000..60eccd4bd1d3 --- /dev/null +++ b/arch/x86/kvm/hyperv.h @@ -0,0 +1,87 @@ +/* + * KVM Microsoft Hyper-V emulation + * + * derived from arch/x86/kvm/x86.c + * + * Copyright (C) 2006 Qumranet, Inc. + * Copyright (C) 2008 Qumranet, Inc. + * Copyright IBM Corporation, 2008 + * Copyright 2010 Red Hat, Inc. and/or its affiliates. + * Copyright (C) 2015 Andrey Smetanin <asmetanin@virtuozzo.com> + * + * Authors: + * Avi Kivity <avi@qumranet.com> + * Yaniv Kamay <yaniv@qumranet.com> + * Amit Shah <amit.shah@qumranet.com> + * Ben-Ami Yassour <benami@il.ibm.com> + * Andrey Smetanin <asmetanin@virtuozzo.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#ifndef __ARCH_X86_KVM_HYPERV_H__ +#define __ARCH_X86_KVM_HYPERV_H__ + +static inline struct kvm_vcpu_hv *vcpu_to_hv_vcpu(struct kvm_vcpu *vcpu) +{ + return &vcpu->arch.hyperv; +} + +static inline struct kvm_vcpu *hv_vcpu_to_vcpu(struct kvm_vcpu_hv *hv_vcpu) +{ + struct kvm_vcpu_arch *arch; + + arch = container_of(hv_vcpu, struct kvm_vcpu_arch, hyperv); + return container_of(arch, struct kvm_vcpu, arch); +} + +static inline struct kvm_vcpu_hv_synic *vcpu_to_synic(struct kvm_vcpu *vcpu) +{ + return &vcpu->arch.hyperv.synic; +} + +static inline struct kvm_vcpu *synic_to_vcpu(struct kvm_vcpu_hv_synic *synic) +{ + return hv_vcpu_to_vcpu(container_of(synic, struct kvm_vcpu_hv, synic)); +} + +int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host); +int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); + +bool kvm_hv_hypercall_enabled(struct kvm *kvm); +int kvm_hv_hypercall(struct kvm_vcpu *vcpu); + +void kvm_hv_irq_routing_update(struct kvm *kvm); +int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint); +void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector); +int kvm_hv_activate_synic(struct kvm_vcpu *vcpu); + +void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu); +void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu); + +static inline struct kvm_vcpu_hv_stimer *vcpu_to_stimer(struct kvm_vcpu *vcpu, + int timer_index) +{ + return &vcpu_to_hv_vcpu(vcpu)->stimer[timer_index]; +} + +static inline struct kvm_vcpu *stimer_to_vcpu(struct kvm_vcpu_hv_stimer *stimer) +{ + struct kvm_vcpu_hv *hv_vcpu; + + hv_vcpu = container_of(stimer - stimer->index, struct kvm_vcpu_hv, + stimer[0]); + return hv_vcpu_to_vcpu(hv_vcpu); +} + +static inline bool kvm_hv_has_stimer_pending(struct kvm_vcpu *vcpu) +{ + return !bitmap_empty(vcpu->arch.hyperv.stimer_pending_bitmap, + HV_SYNIC_STIMER_COUNT); +} + +void kvm_hv_process_stimers(struct kvm_vcpu *vcpu); + +#endif diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index f90952f64e79..b0ea42b78ccd 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -35,6 +35,7 @@ #include <linux/kvm_host.h> #include <linux/slab.h> +#include "ioapic.h" #include "irq.h" #include "i8254.h" #include "x86.h" @@ -333,7 +334,8 @@ static void create_pit_timer(struct kvm *kvm, u32 val, int is_period) struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state; s64 interval; - if (!irqchip_in_kernel(kvm) || ps->flags & KVM_PIT_FLAGS_HPET_LEGACY) + if (!ioapic_in_kernel(kvm) || + ps->flags & KVM_PIT_FLAGS_HPET_LEGACY) return; interval = muldiv64(val, NSEC_PER_SEC, KVM_PIT_FREQ); @@ -418,6 +420,7 @@ void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val, int hpet_legacy_s u8 saved_mode; if (hpet_legacy_start) { /* save existing mode for later reenablement */ + WARN_ON(channel != 0); saved_mode = kvm->arch.vpit->pit_state.channels[0].mode; kvm->arch.vpit->pit_state.channels[0].mode = 0xff; /* disable timer */ pit_load_count(kvm, channel, val); diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index fef922ff2635..7cc2360f1848 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -651,15 +651,10 @@ fail_unlock: return NULL; } -void kvm_destroy_pic(struct kvm *kvm) +void kvm_destroy_pic(struct kvm_pic *vpic) { - struct kvm_pic *vpic = kvm->arch.vpic; - - if (vpic) { - kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_master); - kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_slave); - kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_eclr); - kvm->arch.vpic = NULL; - kfree(vpic); - } + kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_master); + kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_slave); + kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_eclr); + kfree(vpic); } diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 856f79105bb5..1facfd60b04a 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -233,21 +233,7 @@ static void kvm_ioapic_inject_all(struct kvm_ioapic *ioapic, unsigned long irr) } -static void update_handled_vectors(struct kvm_ioapic *ioapic) -{ - DECLARE_BITMAP(handled_vectors, 256); - int i; - - memset(handled_vectors, 0, sizeof(handled_vectors)); - for (i = 0; i < IOAPIC_NUM_PINS; ++i) - __set_bit(ioapic->redirtbl[i].fields.vector, handled_vectors); - memcpy(ioapic->handled_vectors, handled_vectors, - sizeof(handled_vectors)); - smp_wmb(); -} - -void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap, - u32 *tmr) +void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors) { struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic; union kvm_ioapic_redirect_entry *e; @@ -260,13 +246,11 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap, kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index) || index == RTC_GSI) { if (kvm_apic_match_dest(vcpu, NULL, 0, - e->fields.dest_id, e->fields.dest_mode)) { + e->fields.dest_id, e->fields.dest_mode) || + (e->fields.trig_mode == IOAPIC_EDGE_TRIG && + kvm_apic_pending_eoi(vcpu, e->fields.vector))) __set_bit(e->fields.vector, - (unsigned long *)eoi_exit_bitmap); - if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG) - __set_bit(e->fields.vector, - (unsigned long *)tmr); - } + ioapic_handled_vectors); } } spin_unlock(&ioapic->lock); @@ -315,7 +299,6 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) e->bits |= (u32) val; e->fields.remote_irr = 0; } - update_handled_vectors(ioapic); mask_after = e->fields.mask; if (mask_before != mask_after) kvm_fire_mask_notifiers(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index, mask_after); @@ -599,7 +582,6 @@ static void kvm_ioapic_reset(struct kvm_ioapic *ioapic) ioapic->id = 0; memset(ioapic->irq_eoi, 0x00, IOAPIC_NUM_PINS); rtc_irq_eoi_tracking_reset(ioapic); - update_handled_vectors(ioapic); } static const struct kvm_io_device_ops ioapic_mmio_ops = { @@ -628,8 +610,10 @@ int kvm_ioapic_init(struct kvm *kvm) if (ret < 0) { kvm->arch.vioapic = NULL; kfree(ioapic); + return ret; } + kvm_vcpu_request_scan_ioapic(kvm); return ret; } @@ -666,7 +650,6 @@ int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) memcpy(ioapic, state, sizeof(struct kvm_ioapic_state)); ioapic->irr = 0; ioapic->irr_delivered = 0; - update_handled_vectors(ioapic); kvm_vcpu_request_scan_ioapic(kvm); kvm_ioapic_inject_all(ioapic, state->irr); spin_unlock(&ioapic->lock); diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index ca0b0b4e6256..2d16dc251d81 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -9,6 +9,7 @@ struct kvm; struct kvm_vcpu; #define IOAPIC_NUM_PINS KVM_IOAPIC_NUM_PINS +#define MAX_NR_RESERVED_IOAPIC_PINS KVM_MAX_IRQ_ROUTES #define IOAPIC_VERSION_ID 0x11 /* IOAPIC version */ #define IOAPIC_EDGE_TRIG 0 #define IOAPIC_LEVEL_TRIG 1 @@ -73,7 +74,6 @@ struct kvm_ioapic { struct kvm *kvm; void (*ack_notifier)(void *opaque, int irq); spinlock_t lock; - DECLARE_BITMAP(handled_vectors, 256); struct rtc_status rtc_status; struct delayed_work eoi_inject; u32 irq_eoi[IOAPIC_NUM_PINS]; @@ -98,11 +98,12 @@ static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm) return kvm->arch.vioapic; } -static inline bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector) +static inline int ioapic_in_kernel(struct kvm *kvm) { - struct kvm_ioapic *ioapic = kvm->arch.vioapic; - smp_rmb(); - return test_bit(vector, ioapic->handled_vectors); + int ret; + + ret = (ioapic_irqchip(kvm) != NULL); + return ret; } void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu); @@ -120,7 +121,8 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, unsigned long *dest_map); int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); -void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap, - u32 *tmr); - +void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, + ulong *ioapic_handled_vectors); +void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, + ulong *ioapic_handled_vectors); #endif diff --git a/arch/x86/kvm/iommu.c b/arch/x86/kvm/iommu.c index 5c520ebf6343..a22a488b4622 100644 --- a/arch/x86/kvm/iommu.c +++ b/arch/x86/kvm/iommu.c @@ -43,11 +43,11 @@ static int kvm_iommu_unmap_memslots(struct kvm *kvm); static void kvm_iommu_put_pages(struct kvm *kvm, gfn_t base_gfn, unsigned long npages); -static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn, +static kvm_pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn, unsigned long npages) { gfn_t end_gfn; - pfn_t pfn; + kvm_pfn_t pfn; pfn = gfn_to_pfn_memslot(slot, gfn); end_gfn = gfn + npages; @@ -62,7 +62,8 @@ static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn, return pfn; } -static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages) +static void kvm_unpin_pages(struct kvm *kvm, kvm_pfn_t pfn, + unsigned long npages) { unsigned long i; @@ -73,7 +74,7 @@ static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages) int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) { gfn_t gfn, end_gfn; - pfn_t pfn; + kvm_pfn_t pfn; int r = 0; struct iommu_domain *domain = kvm->arch.iommu_domain; int flags; @@ -275,7 +276,7 @@ static void kvm_iommu_put_pages(struct kvm *kvm, { struct iommu_domain *domain; gfn_t end_gfn, gfn; - pfn_t pfn; + kvm_pfn_t pfn; u64 phys; domain = kvm->arch.iommu_domain; diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index a1ec6a50a05a..3982b479bb5f 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -38,14 +38,27 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) EXPORT_SYMBOL(kvm_cpu_has_pending_timer); /* + * check if there is a pending userspace external interrupt + */ +static int pending_userspace_extint(struct kvm_vcpu *v) +{ + return v->arch.pending_external_vector != -1; +} + +/* * check if there is pending interrupt from * non-APIC source without intack. */ static int kvm_cpu_has_extint(struct kvm_vcpu *v) { - if (kvm_apic_accept_pic_intr(v)) - return pic_irqchip(v->kvm)->output; /* PIC */ - else + u8 accept = kvm_apic_accept_pic_intr(v); + + if (accept) { + if (irqchip_split(v->kvm)) + return pending_userspace_extint(v); + else + return pic_irqchip(v->kvm)->output; + } else return 0; } @@ -57,13 +70,13 @@ static int kvm_cpu_has_extint(struct kvm_vcpu *v) */ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) { - if (!irqchip_in_kernel(v->kvm)) + if (!lapic_in_kernel(v)) return v->arch.interrupt.pending; if (kvm_cpu_has_extint(v)) return 1; - if (kvm_apic_vid_enabled(v->kvm)) + if (kvm_vcpu_apicv_active(v)) return 0; return kvm_apic_has_interrupt(v) != -1; /* LAPIC */ @@ -75,7 +88,7 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) */ int kvm_cpu_has_interrupt(struct kvm_vcpu *v) { - if (!irqchip_in_kernel(v->kvm)) + if (!lapic_in_kernel(v)) return v->arch.interrupt.pending; if (kvm_cpu_has_extint(v)) @@ -91,9 +104,16 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt); */ static int kvm_cpu_get_extint(struct kvm_vcpu *v) { - if (kvm_cpu_has_extint(v)) - return kvm_pic_read_irq(v->kvm); /* PIC */ - return -1; + if (kvm_cpu_has_extint(v)) { + if (irqchip_split(v->kvm)) { + int vector = v->arch.pending_external_vector; + + v->arch.pending_external_vector = -1; + return vector; + } else + return kvm_pic_read_irq(v->kvm); /* PIC */ + } else + return -1; } /* @@ -103,7 +123,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v) { int vector; - if (!irqchip_in_kernel(v->kvm)) + if (!lapic_in_kernel(v)) return v->arch.interrupt.nr; vector = kvm_cpu_get_extint(v); diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index ad68c73008c5..ae5c78f2337d 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -74,7 +74,7 @@ struct kvm_pic { }; struct kvm_pic *kvm_create_pic(struct kvm *kvm); -void kvm_destroy_pic(struct kvm *kvm); +void kvm_destroy_pic(struct kvm_pic *vpic); int kvm_pic_read_irq(struct kvm *kvm); void kvm_pic_update_irq(struct kvm_pic *s); @@ -83,15 +83,40 @@ static inline struct kvm_pic *pic_irqchip(struct kvm *kvm) return kvm->arch.vpic; } -static inline int irqchip_in_kernel(struct kvm *kvm) +static inline int pic_in_kernel(struct kvm *kvm) { int ret; ret = (pic_irqchip(kvm) != NULL); + return ret; +} + +static inline int irqchip_split(struct kvm *kvm) +{ + return kvm->arch.irqchip_split; +} + +static inline int irqchip_in_kernel(struct kvm *kvm) +{ + struct kvm_pic *vpic = pic_irqchip(kvm); + bool ret; + + ret = (vpic != NULL); + ret |= irqchip_split(kvm); + + /* Read vpic before kvm->irq_routing. */ smp_rmb(); return ret; } +static inline int lapic_in_kernel(struct kvm_vcpu *vcpu) +{ + /* Same as irqchip_in_kernel(vcpu->kvm), but with less + * pointer chasing and no unnecessary memory barriers. + */ + return vcpu->arch.apic != NULL; +} + void kvm_pic_reset(struct kvm_kpic_state *s); void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 9efff9e5b58c..8fc89efb5250 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -33,6 +33,8 @@ #include "lapic.h" +#include "hyperv.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) @@ -91,8 +93,8 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, return r; } -static inline void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e, - struct kvm_lapic_irq *irq) +void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e, + struct kvm_lapic_irq *irq) { trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data); @@ -108,6 +110,7 @@ static inline void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e, irq->level = 1; irq->shorthand = 0; } +EXPORT_SYMBOL_GPL(kvm_set_msi_irq); int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) @@ -123,12 +126,16 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, } -static int kvm_set_msi_inatomic(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm) +int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int irq_source_id, int level, + bool line_status) { struct kvm_lapic_irq irq; int r; + if (unlikely(e->type != KVM_IRQ_ROUTING_MSI)) + return -EWOULDBLOCK; + kvm_set_msi_irq(e, &irq); if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL)) @@ -137,42 +144,6 @@ static int kvm_set_msi_inatomic(struct kvm_kernel_irq_routing_entry *e, return -EWOULDBLOCK; } -/* - * Deliver an IRQ in an atomic context if we can, or return a failure, - * user can retry in a process context. - * Return value: - * -EWOULDBLOCK - Can't deliver in atomic context: retry in a process context. - * Other values - No need to retry. - */ -int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level) -{ - struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS]; - struct kvm_kernel_irq_routing_entry *e; - int ret = -EINVAL; - int idx; - - trace_kvm_set_irq(irq, level, irq_source_id); - - /* - * Injection into either PIC or IOAPIC might need to scan all CPUs, - * which would need to be retried from thread context; when same GSI - * is connected to both PIC and IOAPIC, we'd have to report a - * partial failure here. - * Since there's no easy way to do this, we only support injecting MSI - * which is limited to 1:1 GSI mapping. - */ - idx = srcu_read_lock(&kvm->irq_srcu); - if (kvm_irq_map_gsi(kvm, entries, irq) > 0) { - e = &entries[0]; - if (likely(e->type == KVM_IRQ_ROUTING_MSI)) - ret = kvm_set_msi_inatomic(e, kvm); - else - ret = -EWOULDBLOCK; - } - srcu_read_unlock(&kvm->irq_srcu, idx); - return ret; -} - int kvm_request_irq_source_id(struct kvm *kvm) { unsigned long *bitmap = &kvm->arch.irq_sources_bitmap; @@ -208,7 +179,7 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) goto unlock; } clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap); - if (!irqchip_in_kernel(kvm)) + if (!ioapic_in_kernel(kvm)) goto unlock; kvm_ioapic_clear_all(kvm->arch.vioapic, irq_source_id); @@ -250,6 +221,16 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin, srcu_read_unlock(&kvm->irq_srcu, idx); } +static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int irq_source_id, int level, + bool line_status) +{ + if (!level) + return -1; + + return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint); +} + int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue) { @@ -288,6 +269,11 @@ int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e, e->msi.address_hi = ue->u.msi.address_hi; e->msi.data = ue->u.msi.data; break; + case KVM_IRQ_ROUTING_HV_SINT: + e->set = kvm_hv_set_sint; + e->hv_sint.vcpu = ue->u.hv_sint.vcpu; + e->hv_sint.sint = ue->u.hv_sint.sint; + break; default: goto out; } @@ -297,6 +283,33 @@ out: return r; } +bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq, + struct kvm_vcpu **dest_vcpu) +{ + int i, r = 0; + struct kvm_vcpu *vcpu; + + if (kvm_intr_is_single_vcpu_fast(kvm, irq, dest_vcpu)) + return true; + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (!kvm_apic_present(vcpu)) + continue; + + if (!kvm_apic_match_dest(vcpu, NULL, irq->shorthand, + irq->dest_id, irq->dest_mode)) + continue; + + if (++r == 2) + return false; + + *dest_vcpu = vcpu; + } + + return r == 1; +} +EXPORT_SYMBOL_GPL(kvm_intr_is_single_vcpu); + #define IOAPIC_ROUTING_ENTRY(irq) \ { .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP, \ .u.irqchip = { .irqchip = KVM_IRQCHIP_IOAPIC, .pin = (irq) } } @@ -328,3 +341,72 @@ int kvm_setup_default_irq_routing(struct kvm *kvm) return kvm_set_irq_routing(kvm, default_routing, ARRAY_SIZE(default_routing), 0); } + +static const struct kvm_irq_routing_entry empty_routing[] = {}; + +int kvm_setup_empty_irq_routing(struct kvm *kvm) +{ + return kvm_set_irq_routing(kvm, empty_routing, 0, 0); +} + +void kvm_arch_post_irq_routing_update(struct kvm *kvm) +{ + if (ioapic_in_kernel(kvm) || !irqchip_in_kernel(kvm)) + return; + kvm_make_scan_ioapic_request(kvm); +} + +void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, + ulong *ioapic_handled_vectors) +{ + struct kvm *kvm = vcpu->kvm; + struct kvm_kernel_irq_routing_entry *entry; + struct kvm_irq_routing_table *table; + u32 i, nr_ioapic_pins; + int idx; + + /* kvm->irq_routing must be read after clearing + * KVM_SCAN_IOAPIC. */ + smp_mb(); + idx = srcu_read_lock(&kvm->irq_srcu); + table = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); + nr_ioapic_pins = min_t(u32, table->nr_rt_entries, + kvm->arch.nr_reserved_ioapic_pins); + for (i = 0; i < nr_ioapic_pins; ++i) { + hlist_for_each_entry(entry, &table->map[i], link) { + u32 dest_id, dest_mode; + bool level; + + if (entry->type != KVM_IRQ_ROUTING_MSI) + continue; + dest_id = (entry->msi.address_lo >> 12) & 0xff; + dest_mode = (entry->msi.address_lo >> 2) & 0x1; + level = entry->msi.data & MSI_DATA_TRIGGER_LEVEL; + if (level && kvm_apic_match_dest(vcpu, NULL, 0, + dest_id, dest_mode)) { + u32 vector = entry->msi.data & 0xff; + + __set_bit(vector, + ioapic_handled_vectors); + } + } + } + srcu_read_unlock(&kvm->irq_srcu, idx); +} + +int kvm_arch_set_irq(struct kvm_kernel_irq_routing_entry *irq, struct kvm *kvm, + int irq_source_id, int level, bool line_status) +{ + switch (irq->type) { + case KVM_IRQ_ROUTING_HV_SINT: + return kvm_hv_set_sint(irq, kvm, irq_source_id, level, + line_status); + default: + return -EWOULDBLOCK; + } +} + +void kvm_arch_irq_routing_update(struct kvm *kvm) +{ + kvm_hv_irq_routing_update(kvm); +} diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 2a5ca97c263b..36591faed13b 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -41,6 +41,7 @@ #include "trace.h" #include "x86.h" #include "cpuid.h" +#include "hyperv.h" #ifndef CONFIG_X86_64 #define mod_64(x, y) ((x) - (y) * div64_u64(x, y)) @@ -128,11 +129,6 @@ static inline int apic_enabled(struct kvm_lapic *apic) (LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \ APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER) -static inline int kvm_apic_id(struct kvm_lapic *apic) -{ - return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff; -} - /* The logical map is definitely wrong if we have multiple * modes at the same time. (Physical map is always right.) */ @@ -209,7 +205,7 @@ out: if (old) kfree_rcu(old, rcu); - kvm_vcpu_request_scan_ioapic(kvm); + kvm_make_scan_ioapic_request(kvm); } static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) @@ -348,6 +344,8 @@ void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir) struct kvm_lapic *apic = vcpu->arch.apic; __kvm_apic_update_irr(pir, apic->regs); + + kvm_make_request(KVM_REQ_EVENT, vcpu); } EXPORT_SYMBOL_GPL(kvm_apic_update_irr); @@ -377,7 +375,8 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic) if (!apic->irr_pending) return -1; - kvm_x86_ops->sync_pir_to_irr(apic->vcpu); + if (apic->vcpu->arch.apicv_active) + kvm_x86_ops->sync_pir_to_irr(apic->vcpu); result = apic_search_irr(apic); ASSERT(result == -1 || result >= 16); @@ -390,7 +389,7 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) vcpu = apic->vcpu; - if (unlikely(kvm_apic_vid_enabled(vcpu->kvm))) { + if (unlikely(vcpu->arch.apicv_active)) { /* try to update RVI */ apic_clear_vector(vec, apic->regs + APIC_IRR); kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -416,7 +415,7 @@ static inline void apic_set_isr(int vec, struct kvm_lapic *apic) * because the processor can modify ISR under the hood. Instead * just set SVI. */ - if (unlikely(kvm_x86_ops->hwapic_isr_update)) + if (unlikely(vcpu->arch.apicv_active)) kvm_x86_ops->hwapic_isr_update(vcpu->kvm, vec); else { ++apic->isr_count; @@ -464,7 +463,7 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) * on the other hand isr_count and highest_isr_cache are unused * and must be left alone. */ - if (unlikely(kvm_x86_ops->hwapic_isr_update)) + if (unlikely(vcpu->arch.apicv_active)) kvm_x86_ops->hwapic_isr_update(vcpu->kvm, apic_find_highest_isr(apic)); else { @@ -551,15 +550,6 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu) __clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); } -void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr) -{ - struct kvm_lapic *apic = vcpu->arch.apic; - int i; - - for (i = 0; i < 8; i++) - apic_set_reg(apic, APIC_TMR + 0x10 * i, tmr[i]); -} - static void apic_update_ppr(struct kvm_lapic *apic) { u32 tpr, isrv, ppr, old_ppr; @@ -764,6 +754,65 @@ out: return ret; } +bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq, + struct kvm_vcpu **dest_vcpu) +{ + struct kvm_apic_map *map; + bool ret = false; + struct kvm_lapic *dst = NULL; + + if (irq->shorthand) + return false; + + rcu_read_lock(); + map = rcu_dereference(kvm->arch.apic_map); + + if (!map) + goto out; + + if (irq->dest_mode == APIC_DEST_PHYSICAL) { + if (irq->dest_id == 0xFF) + goto out; + + if (irq->dest_id >= ARRAY_SIZE(map->phys_map)) + goto out; + + dst = map->phys_map[irq->dest_id]; + if (dst && kvm_apic_present(dst->vcpu)) + *dest_vcpu = dst->vcpu; + else + goto out; + } else { + u16 cid; + unsigned long bitmap = 1; + int i, r = 0; + + if (!kvm_apic_logical_map_valid(map)) + goto out; + + apic_logical_id(map, irq->dest_id, &cid, (u16 *)&bitmap); + + if (cid >= ARRAY_SIZE(map->logical_map)) + goto out; + + for_each_set_bit(i, &bitmap, 16) { + dst = map->logical_map[cid][i]; + if (++r == 2) + goto out; + } + + if (dst && kvm_apic_present(dst->vcpu)) + *dest_vcpu = dst->vcpu; + else + goto out; + } + + ret = true; +out: + rcu_read_unlock(); + return ret; +} + /* * Add a pending IRQ into lapic. * Return 1 if successfully added and 0 if discarded. @@ -781,6 +830,9 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, case APIC_DM_LOWEST: vcpu->arch.apic_arb_prio++; case APIC_DM_FIXED: + if (unlikely(trig_mode && !level)) + break; + /* FIXME add logic for vcpu on reset */ if (unlikely(!apic_enabled(apic))) break; @@ -790,7 +842,14 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, if (dest_map) __set_bit(vcpu->vcpu_id, dest_map); - if (kvm_x86_ops->deliver_posted_interrupt) + if (apic_test_vector(vector, apic->regs + APIC_TMR) != !!trig_mode) { + if (trig_mode) + apic_set_vector(vector, apic->regs + APIC_TMR); + else + apic_clear_vector(vector, apic->regs + APIC_TMR); + } + + if (vcpu->arch.apicv_active) kvm_x86_ops->deliver_posted_interrupt(vcpu, vector); else { apic_set_irr(vector, apic); @@ -868,16 +927,32 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2) return vcpu1->arch.apic_arb_prio - vcpu2->arch.apic_arb_prio; } +static bool kvm_ioapic_handles_vector(struct kvm_lapic *apic, int vector) +{ + return test_bit(vector, apic->vcpu->arch.ioapic_handled_vectors); +} + static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector) { - if (kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) { - int trigger_mode; - if (apic_test_vector(vector, apic->regs + APIC_TMR)) - trigger_mode = IOAPIC_LEVEL_TRIG; - else - trigger_mode = IOAPIC_EDGE_TRIG; - kvm_ioapic_update_eoi(apic->vcpu, vector, trigger_mode); + int trigger_mode; + + /* Eoi the ioapic only if the ioapic doesn't own the vector. */ + if (!kvm_ioapic_handles_vector(apic, vector)) + return; + + /* Request a KVM exit to inform the userspace IOAPIC. */ + if (irqchip_split(apic->vcpu->kvm)) { + apic->vcpu->arch.pending_ioapic_eoi = vector; + kvm_make_request(KVM_REQ_IOAPIC_EOI_EXIT, apic->vcpu); + return; } + + if (apic_test_vector(vector, apic->regs + APIC_TMR)) + trigger_mode = IOAPIC_LEVEL_TRIG; + else + trigger_mode = IOAPIC_EDGE_TRIG; + + kvm_ioapic_update_eoi(apic->vcpu, vector, trigger_mode); } static int apic_set_eoi(struct kvm_lapic *apic) @@ -896,6 +971,9 @@ static int apic_set_eoi(struct kvm_lapic *apic) apic_clear_isr(vector, apic); apic_update_ppr(apic); + if (test_bit(vector, vcpu_to_synic(apic->vcpu)->vec_bitmap)) + kvm_hv_synic_send_eoi(apic->vcpu, vector); + kvm_ioapic_send_eoi(apic, vector); kvm_make_request(KVM_REQ_EVENT, apic->vcpu); return vector; @@ -1147,7 +1225,7 @@ static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu) int vec = reg & APIC_VECTOR_MASK; void *bitmap = apic->regs + APIC_ISR; - if (kvm_x86_ops->deliver_posted_interrupt) + if (vcpu->arch.apicv_active) bitmap = apic->regs + APIC_IRR; if (apic_test_vector(vec, bitmap)) @@ -1172,7 +1250,7 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu) tsc_deadline = apic->lapic_timer.expired_tscdeadline; apic->lapic_timer.expired_tscdeadline = 0; - guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, native_read_tsc()); + guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline); /* __delay is delay_tsc whenever the hardware has TSC, thus always. */ @@ -1240,7 +1318,7 @@ static void start_apic_timer(struct kvm_lapic *apic) local_irq_save(flags); now = apic->lapic_timer.timer.base->get_time(); - guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, native_read_tsc()); + guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); if (likely(tscdeadline > guest_tsc)) { ns = (tscdeadline - guest_tsc) * 1000000ULL; do_div(ns, this_tsc_khz); @@ -1615,8 +1693,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) apic_set_reg(apic, APIC_ISR + 0x10 * i, 0); apic_set_reg(apic, APIC_TMR + 0x10 * i, 0); } - apic->irr_pending = kvm_apic_vid_enabled(vcpu->kvm); - apic->isr_count = kvm_x86_ops->hwapic_isr_update ? 1 : 0; + apic->irr_pending = vcpu->arch.apicv_active; + apic->isr_count = vcpu->arch.apicv_active ? 1 : 0; apic->highest_isr_cache = -1; update_divide_count(apic); atomic_set(&apic->lapic_timer.pending, 0); @@ -1805,6 +1883,12 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) apic_set_isr(vector, apic); apic_update_ppr(apic); apic_clear_irr(vector, apic); + + if (test_bit(vector, vcpu_to_synic(vcpu)->auto_eoi_bitmap)) { + apic_clear_isr(vector, apic); + apic_update_ppr(apic); + } + return vector; } @@ -1828,17 +1912,20 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu, update_divide_count(apic); start_apic_timer(apic); apic->irr_pending = true; - apic->isr_count = kvm_x86_ops->hwapic_isr_update ? + apic->isr_count = vcpu->arch.apicv_active ? 1 : count_vectors(apic->regs + APIC_ISR); apic->highest_isr_cache = -1; - if (kvm_x86_ops->hwapic_irr_update) + if (vcpu->arch.apicv_active) { kvm_x86_ops->hwapic_irr_update(vcpu, apic_find_highest_irr(apic)); - if (unlikely(kvm_x86_ops->hwapic_isr_update)) kvm_x86_ops->hwapic_isr_update(vcpu->kvm, apic_find_highest_isr(apic)); + } kvm_make_request(KVM_REQ_EVENT, vcpu); - kvm_rtc_eoi_tracking_restore_one(vcpu); + if (ioapic_in_kernel(vcpu->kvm)) + kvm_rtc_eoi_tracking_restore_one(vcpu); + + vcpu->arch.apic_arb_prio = 0; } void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) @@ -1900,8 +1987,9 @@ void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu) if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention)) return; - kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data, - sizeof(u32)); + if (kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data, + sizeof(u32))) + return; apic_set_tpr(vcpu->arch.apic, data & 0xff); } @@ -1921,7 +2009,7 @@ static void apic_sync_pv_eoi_to_guest(struct kvm_vcpu *vcpu, /* Cache not set: could be safe but we don't bother. */ apic->highest_isr_cache == -1 || /* Need EOI to update ioapic. */ - kvm_ioapic_handles_vector(vcpu->kvm, apic->highest_isr_cache)) { + kvm_ioapic_handles_vector(apic, apic->highest_isr_cache)) { /* * PV EOI was disabled by apic_sync_pv_eoi_from_guest * so we need not do anything here. @@ -1977,7 +2065,7 @@ int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data) struct kvm_lapic *apic = vcpu->arch.apic; u32 reg = (msr - APIC_BASE_MSR) << 4; - if (!irqchip_in_kernel(vcpu->kvm) || !apic_x2apic_mode(apic)) + if (!lapic_in_kernel(vcpu) || !apic_x2apic_mode(apic)) return 1; if (reg == APIC_ICR2) @@ -1994,7 +2082,7 @@ int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data) struct kvm_lapic *apic = vcpu->arch.apic; u32 reg = (msr - APIC_BASE_MSR) << 4, low, high = 0; - if (!irqchip_in_kernel(vcpu->kvm) || !apic_x2apic_mode(apic)) + if (!lapic_in_kernel(vcpu) || !apic_x2apic_mode(apic)) return 1; if (reg == APIC_DFR || reg == APIC_ICR2) { diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 71952748222a..41bdb35b4b67 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -57,7 +57,6 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value); u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu); void kvm_apic_set_version(struct kvm_vcpu *vcpu); -void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr); void __kvm_apic_update_irr(u32 *pir, void *regs); void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir); int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, @@ -91,7 +90,7 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data); static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu) { - return vcpu->arch.hv_vapic & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE; + return vcpu->arch.hyperv.hv_vapic & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE; } int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data); @@ -144,9 +143,9 @@ static inline int apic_x2apic_mode(struct kvm_lapic *apic) return apic->vcpu->arch.apic_base & X2APIC_ENABLE; } -static inline bool kvm_apic_vid_enabled(struct kvm *kvm) +static inline bool kvm_vcpu_apicv_active(struct kvm_vcpu *vcpu) { - return kvm_x86_ops->vm_has_apicv(kvm); + return vcpu->arch.apic && vcpu->arch.apicv_active; } static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu) @@ -165,8 +164,15 @@ 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); } +static inline int kvm_apic_id(struct kvm_lapic *apic) +{ + return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff; +} + bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector); void wait_lapic_expire(struct kvm_vcpu *vcpu); +bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq, + struct kvm_vcpu **dest_vcpu); #endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 44171462bd2a..95a955de5964 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -259,7 +259,7 @@ static unsigned get_mmio_spte_access(u64 spte) } static bool set_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, - pfn_t pfn, unsigned access) + kvm_pfn_t pfn, unsigned access) { if (unlikely(is_noslot_pfn(pfn))) { mark_mmio_spte(vcpu, sptep, gfn, access); @@ -311,11 +311,6 @@ static int is_large_pte(u64 pte) return pte & PT_PAGE_SIZE_MASK; } -static int is_rmap_spte(u64 pte) -{ - return is_shadow_present_pte(pte); -} - static int is_last_spte(u64 pte, int level) { if (level == PT_PAGE_TABLE_LEVEL) @@ -325,7 +320,7 @@ static int is_last_spte(u64 pte, int level) return 0; } -static pfn_t spte_to_pfn(u64 pte) +static kvm_pfn_t spte_to_pfn(u64 pte) { return (pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; } @@ -357,12 +352,6 @@ static u64 __get_spte_lockless(u64 *sptep) { return ACCESS_ONCE(*sptep); } - -static bool __check_direct_spte_mmio_pf(u64 spte) -{ - /* It is valid if the spte is zapped. */ - return spte == 0ull; -} #else union split_spte { struct { @@ -478,23 +467,6 @@ retry: return spte.spte; } - -static bool __check_direct_spte_mmio_pf(u64 spte) -{ - union split_spte sspte = (union split_spte)spte; - u32 high_mmio_mask = shadow_mmio_mask >> 32; - - /* It is valid if the spte is zapped. */ - if (spte == 0ull) - return true; - - /* It is valid if the spte is being zapped. */ - if (sspte.spte_low == 0ull && - (sspte.spte_high & high_mmio_mask) == high_mmio_mask) - return true; - - return false; -} #endif static bool spte_is_locklessly_modifiable(u64 spte) @@ -563,7 +535,7 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte) u64 old_spte = *sptep; bool ret = false; - WARN_ON(!is_rmap_spte(new_spte)); + WARN_ON(!is_shadow_present_pte(new_spte)); if (!is_shadow_present_pte(old_spte)) { mmu_spte_set(sptep, new_spte); @@ -610,7 +582,7 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte) */ static int mmu_spte_clear_track_bits(u64 *sptep) { - pfn_t pfn; + kvm_pfn_t pfn; u64 old_spte = *sptep; if (!spte_has_volatile_bits(old_spte)) @@ -618,7 +590,7 @@ static int mmu_spte_clear_track_bits(u64 *sptep) else old_spte = __update_clear_spte_slow(sptep, 0ull); - if (!is_rmap_spte(old_spte)) + if (!is_shadow_present_pte(old_spte)) return 0; pfn = spte_to_pfn(old_spte); @@ -841,14 +813,11 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm->arch.indirect_shadow_pages--; } -static int has_wrprotected_page(struct kvm_vcpu *vcpu, - gfn_t gfn, - int level) +static int __has_wrprotected_page(gfn_t gfn, int level, + struct kvm_memory_slot *slot) { - struct kvm_memory_slot *slot; struct kvm_lpage_info *linfo; - slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); if (slot) { linfo = lpage_info_slot(gfn, slot, level); return linfo->write_count; @@ -857,6 +826,14 @@ static int has_wrprotected_page(struct kvm_vcpu *vcpu, return 1; } +static int has_wrprotected_page(struct kvm_vcpu *vcpu, gfn_t gfn, int level) +{ + struct kvm_memory_slot *slot; + + slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + return __has_wrprotected_page(gfn, level, slot); +} + static int host_mapping_level(struct kvm *kvm, gfn_t gfn) { unsigned long page_size; @@ -874,6 +851,17 @@ static int host_mapping_level(struct kvm *kvm, gfn_t gfn) return ret; } +static inline bool memslot_valid_for_gpte(struct kvm_memory_slot *slot, + bool no_dirty_log) +{ + if (!slot || slot->flags & KVM_MEMSLOT_INVALID) + return false; + if (no_dirty_log && slot->dirty_bitmap) + return false; + + return true; +} + static struct kvm_memory_slot * gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn, bool no_dirty_log) @@ -881,21 +869,25 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_memory_slot *slot; slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); - if (!slot || slot->flags & KVM_MEMSLOT_INVALID || - (no_dirty_log && slot->dirty_bitmap)) + if (!memslot_valid_for_gpte(slot, no_dirty_log)) slot = NULL; return slot; } -static bool mapping_level_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t large_gfn) -{ - return !gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true); -} - -static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn) +static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn, + bool *force_pt_level) { int host_level, level, max_level; + struct kvm_memory_slot *slot; + + if (unlikely(*force_pt_level)) + return PT_PAGE_TABLE_LEVEL; + + slot = kvm_vcpu_gfn_to_memslot(vcpu, large_gfn); + *force_pt_level = !memslot_valid_for_gpte(slot, true); + if (unlikely(*force_pt_level)) + return PT_PAGE_TABLE_LEVEL; host_level = host_mapping_level(vcpu->kvm, large_gfn); @@ -905,43 +897,42 @@ 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, large_gfn, level)) + if (__has_wrprotected_page(large_gfn, level, slot)) break; return level - 1; } /* - * Pte mapping structures: + * About rmap_head encoding: * - * If pte_list bit zero is zero, then pte_list point to the spte. - * - * If pte_list bit zero is one, (then pte_list & ~1) points to a struct + * If the bit zero of rmap_head->val is clear, then it points to the only spte + * in this rmap chain. Otherwise, (rmap_head->val & ~1) points to a struct * pte_list_desc containing more mappings. - * - * Returns the number of pte entries before the spte was added or zero if - * the spte was not added. - * + */ + +/* + * Returns the number of pointers in the rmap chain, not counting the new one. */ static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte, - unsigned long *pte_list) + struct kvm_rmap_head *rmap_head) { struct pte_list_desc *desc; int i, count = 0; - if (!*pte_list) { + if (!rmap_head->val) { rmap_printk("pte_list_add: %p %llx 0->1\n", spte, *spte); - *pte_list = (unsigned long)spte; - } else if (!(*pte_list & 1)) { + rmap_head->val = (unsigned long)spte; + } else if (!(rmap_head->val & 1)) { rmap_printk("pte_list_add: %p %llx 1->many\n", spte, *spte); desc = mmu_alloc_pte_list_desc(vcpu); - desc->sptes[0] = (u64 *)*pte_list; + desc->sptes[0] = (u64 *)rmap_head->val; desc->sptes[1] = spte; - *pte_list = (unsigned long)desc | 1; + rmap_head->val = (unsigned long)desc | 1; ++count; } else { rmap_printk("pte_list_add: %p %llx many->many\n", spte, *spte); - desc = (struct pte_list_desc *)(*pte_list & ~1ul); + desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); while (desc->sptes[PTE_LIST_EXT-1] && desc->more) { desc = desc->more; count += PTE_LIST_EXT; @@ -958,8 +949,9 @@ static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte, } static void -pte_list_desc_remove_entry(unsigned long *pte_list, struct pte_list_desc *desc, - int i, struct pte_list_desc *prev_desc) +pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head, + struct pte_list_desc *desc, int i, + struct pte_list_desc *prev_desc) { int j; @@ -970,43 +962,43 @@ pte_list_desc_remove_entry(unsigned long *pte_list, struct pte_list_desc *desc, if (j != 0) return; if (!prev_desc && !desc->more) - *pte_list = (unsigned long)desc->sptes[0]; + rmap_head->val = (unsigned long)desc->sptes[0]; else if (prev_desc) prev_desc->more = desc->more; else - *pte_list = (unsigned long)desc->more | 1; + rmap_head->val = (unsigned long)desc->more | 1; mmu_free_pte_list_desc(desc); } -static void pte_list_remove(u64 *spte, unsigned long *pte_list) +static void pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head) { struct pte_list_desc *desc; struct pte_list_desc *prev_desc; int i; - if (!*pte_list) { + if (!rmap_head->val) { printk(KERN_ERR "pte_list_remove: %p 0->BUG\n", spte); BUG(); - } else if (!(*pte_list & 1)) { + } else if (!(rmap_head->val & 1)) { rmap_printk("pte_list_remove: %p 1->0\n", spte); - if ((u64 *)*pte_list != spte) { + if ((u64 *)rmap_head->val != spte) { printk(KERN_ERR "pte_list_remove: %p 1->BUG\n", spte); BUG(); } - *pte_list = 0; + rmap_head->val = 0; } else { rmap_printk("pte_list_remove: %p many->many\n", spte); - desc = (struct pte_list_desc *)(*pte_list & ~1ul); + desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); prev_desc = NULL; while (desc) { - for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i) + for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i) { if (desc->sptes[i] == spte) { - pte_list_desc_remove_entry(pte_list, - desc, i, - prev_desc); + pte_list_desc_remove_entry(rmap_head, + desc, i, prev_desc); return; } + } prev_desc = desc; desc = desc->more; } @@ -1015,28 +1007,8 @@ static void pte_list_remove(u64 *spte, unsigned long *pte_list) } } -typedef void (*pte_list_walk_fn) (u64 *spte); -static void pte_list_walk(unsigned long *pte_list, pte_list_walk_fn fn) -{ - struct pte_list_desc *desc; - int i; - - if (!*pte_list) - return; - - if (!(*pte_list & 1)) - return fn((u64 *)*pte_list); - - desc = (struct pte_list_desc *)(*pte_list & ~1ul); - while (desc) { - for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i) - fn(desc->sptes[i]); - desc = desc->more; - } -} - -static unsigned long *__gfn_to_rmap(gfn_t gfn, int level, - struct kvm_memory_slot *slot) +static struct kvm_rmap_head *__gfn_to_rmap(gfn_t gfn, int level, + struct kvm_memory_slot *slot) { unsigned long idx; @@ -1044,10 +1016,8 @@ static unsigned long *__gfn_to_rmap(gfn_t gfn, int level, return &slot->arch.rmap[level - PT_PAGE_TABLE_LEVEL][idx]; } -/* - * Take gfn and return the reverse mapping to it. - */ -static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, struct kvm_mmu_page *sp) +static struct kvm_rmap_head *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, + struct kvm_mmu_page *sp) { struct kvm_memslots *slots; struct kvm_memory_slot *slot; @@ -1068,24 +1038,24 @@ static bool rmap_can_add(struct kvm_vcpu *vcpu) static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) { struct kvm_mmu_page *sp; - unsigned long *rmapp; + struct kvm_rmap_head *rmap_head; sp = page_header(__pa(spte)); kvm_mmu_page_set_gfn(sp, spte - sp->spt, gfn); - rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp); - return pte_list_add(vcpu, spte, rmapp); + rmap_head = gfn_to_rmap(vcpu->kvm, gfn, sp); + return pte_list_add(vcpu, spte, rmap_head); } static void rmap_remove(struct kvm *kvm, u64 *spte) { struct kvm_mmu_page *sp; gfn_t gfn; - unsigned long *rmapp; + struct kvm_rmap_head *rmap_head; sp = page_header(__pa(spte)); gfn = kvm_mmu_page_get_gfn(sp, spte - sp->spt); - rmapp = gfn_to_rmap(kvm, gfn, sp); - pte_list_remove(spte, rmapp); + rmap_head = gfn_to_rmap(kvm, gfn, sp); + pte_list_remove(spte, rmap_head); } /* @@ -1105,19 +1075,26 @@ struct rmap_iterator { * * Returns sptep if found, NULL otherwise. */ -static u64 *rmap_get_first(unsigned long rmap, struct rmap_iterator *iter) +static u64 *rmap_get_first(struct kvm_rmap_head *rmap_head, + struct rmap_iterator *iter) { - if (!rmap) + u64 *sptep; + + if (!rmap_head->val) return NULL; - if (!(rmap & 1)) { + if (!(rmap_head->val & 1)) { iter->desc = NULL; - return (u64 *)rmap; + sptep = (u64 *)rmap_head->val; + goto out; } - iter->desc = (struct pte_list_desc *)(rmap & ~1ul); + iter->desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); iter->pos = 0; - return iter->desc->sptes[iter->pos]; + sptep = iter->desc->sptes[iter->pos]; +out: + BUG_ON(!is_shadow_present_pte(*sptep)); + return sptep; } /* @@ -1127,14 +1104,14 @@ static u64 *rmap_get_first(unsigned long rmap, struct rmap_iterator *iter) */ static u64 *rmap_get_next(struct rmap_iterator *iter) { + u64 *sptep; + if (iter->desc) { if (iter->pos < PTE_LIST_EXT - 1) { - u64 *sptep; - ++iter->pos; sptep = iter->desc->sptes[iter->pos]; if (sptep) - return sptep; + goto out; } iter->desc = iter->desc->more; @@ -1142,17 +1119,20 @@ static u64 *rmap_get_next(struct rmap_iterator *iter) if (iter->desc) { iter->pos = 0; /* desc->sptes[0] cannot be NULL */ - return iter->desc->sptes[iter->pos]; + sptep = iter->desc->sptes[iter->pos]; + goto out; } } return NULL; +out: + BUG_ON(!is_shadow_present_pte(*sptep)); + return sptep; } -#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_)) +#define for_each_rmap_spte(_rmap_head_, _iter_, _spte_) \ + for (_spte_ = rmap_get_first(_rmap_head_, _iter_); \ + _spte_; _spte_ = rmap_get_next(_iter_)) static void drop_spte(struct kvm *kvm, u64 *sptep) { @@ -1210,14 +1190,15 @@ static bool spte_write_protect(struct kvm *kvm, u64 *sptep, bool pt_protect) return mmu_spte_update(sptep, spte); } -static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp, +static bool __rmap_write_protect(struct kvm *kvm, + struct kvm_rmap_head *rmap_head, bool pt_protect) { u64 *sptep; struct rmap_iterator iter; bool flush = false; - for_each_rmap_spte(rmapp, &iter, sptep) + for_each_rmap_spte(rmap_head, &iter, sptep) flush |= spte_write_protect(kvm, sptep, pt_protect); return flush; @@ -1234,13 +1215,13 @@ static bool spte_clear_dirty(struct kvm *kvm, u64 *sptep) return mmu_spte_update(sptep, spte); } -static bool __rmap_clear_dirty(struct kvm *kvm, unsigned long *rmapp) +static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) { u64 *sptep; struct rmap_iterator iter; bool flush = false; - for_each_rmap_spte(rmapp, &iter, sptep) + for_each_rmap_spte(rmap_head, &iter, sptep) flush |= spte_clear_dirty(kvm, sptep); return flush; @@ -1257,13 +1238,13 @@ static bool spte_set_dirty(struct kvm *kvm, u64 *sptep) return mmu_spte_update(sptep, spte); } -static bool __rmap_set_dirty(struct kvm *kvm, unsigned long *rmapp) +static bool __rmap_set_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) { u64 *sptep; struct rmap_iterator iter; bool flush = false; - for_each_rmap_spte(rmapp, &iter, sptep) + for_each_rmap_spte(rmap_head, &iter, sptep) flush |= spte_set_dirty(kvm, sptep); return flush; @@ -1283,12 +1264,12 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { - unsigned long *rmapp; + struct kvm_rmap_head *rmap_head; while (mask) { - rmapp = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), - PT_PAGE_TABLE_LEVEL, slot); - __rmap_write_protect(kvm, rmapp, false); + rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), + PT_PAGE_TABLE_LEVEL, slot); + __rmap_write_protect(kvm, rmap_head, false); /* clear the first set bit */ mask &= mask - 1; @@ -1308,12 +1289,12 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { - unsigned long *rmapp; + struct kvm_rmap_head *rmap_head; while (mask) { - rmapp = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), - PT_PAGE_TABLE_LEVEL, slot); - __rmap_clear_dirty(kvm, rmapp); + rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), + PT_PAGE_TABLE_LEVEL, slot); + __rmap_clear_dirty(kvm, rmap_head); /* clear the first set bit */ mask &= mask - 1; @@ -1345,28 +1326,27 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn) { struct kvm_memory_slot *slot; - unsigned long *rmapp; + struct kvm_rmap_head *rmap_head; int i; bool write_protected = false; slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { - rmapp = __gfn_to_rmap(gfn, i, slot); - write_protected |= __rmap_write_protect(vcpu->kvm, rmapp, true); + rmap_head = __gfn_to_rmap(gfn, i, slot); + write_protected |= __rmap_write_protect(vcpu->kvm, rmap_head, true); } return write_protected; } -static bool kvm_zap_rmapp(struct kvm *kvm, unsigned long *rmapp) +static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head) { u64 *sptep; struct rmap_iterator iter; bool flush = false; - while ((sptep = rmap_get_first(*rmapp, &iter))) { - BUG_ON(!(*sptep & PT_PRESENT_MASK)); + while ((sptep = rmap_get_first(rmap_head, &iter))) { rmap_printk("%s: spte %p %llx.\n", __func__, sptep, *sptep); drop_spte(kvm, sptep); @@ -1376,14 +1356,14 @@ static bool kvm_zap_rmapp(struct kvm *kvm, unsigned long *rmapp) return flush; } -static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, +static int kvm_unmap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, struct kvm_memory_slot *slot, gfn_t gfn, int level, unsigned long data) { - return kvm_zap_rmapp(kvm, rmapp); + return kvm_zap_rmapp(kvm, rmap_head); } -static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, +static int kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, struct kvm_memory_slot *slot, gfn_t gfn, int level, unsigned long data) { @@ -1392,13 +1372,13 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, int need_flush = 0; u64 new_spte; pte_t *ptep = (pte_t *)data; - pfn_t new_pfn; + kvm_pfn_t new_pfn; WARN_ON(pte_huge(*ptep)); new_pfn = pte_pfn(*ptep); restart: - for_each_rmap_spte(rmapp, &iter, sptep) { + for_each_rmap_spte(rmap_head, &iter, sptep) { rmap_printk("kvm_set_pte_rmapp: spte %p %llx gfn %llx (%d)\n", sptep, *sptep, gfn, level); @@ -1436,11 +1416,11 @@ struct slot_rmap_walk_iterator { /* output fields. */ gfn_t gfn; - unsigned long *rmap; + struct kvm_rmap_head *rmap; int level; /* private field. */ - unsigned long *end_rmap; + struct kvm_rmap_head *end_rmap; }; static void @@ -1499,7 +1479,7 @@ static int kvm_handle_hva_range(struct kvm *kvm, unsigned long end, unsigned long data, int (*handler)(struct kvm *kvm, - unsigned long *rmapp, + struct kvm_rmap_head *rmap_head, struct kvm_memory_slot *slot, gfn_t gfn, int level, @@ -1543,7 +1523,8 @@ static int kvm_handle_hva_range(struct kvm *kvm, static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, unsigned long data, - int (*handler)(struct kvm *kvm, unsigned long *rmapp, + int (*handler)(struct kvm *kvm, + struct kvm_rmap_head *rmap_head, struct kvm_memory_slot *slot, gfn_t gfn, int level, unsigned long data)) @@ -1566,7 +1547,7 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp); } -static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, +static int kvm_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, struct kvm_memory_slot *slot, gfn_t gfn, int level, unsigned long data) { @@ -1576,18 +1557,19 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, BUG_ON(!shadow_accessed_mask); - for_each_rmap_spte(rmapp, &iter, sptep) + for_each_rmap_spte(rmap_head, &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; } -static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp, +static int kvm_test_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, struct kvm_memory_slot *slot, gfn_t gfn, int level, unsigned long data) { @@ -1603,11 +1585,12 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp, if (!shadow_accessed_mask) goto out; - for_each_rmap_spte(rmapp, &iter, sptep) + for_each_rmap_spte(rmap_head, &iter, sptep) { if (*sptep & shadow_accessed_mask) { young = 1; break; } + } out: return young; } @@ -1616,14 +1599,14 @@ out: static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) { - unsigned long *rmapp; + struct kvm_rmap_head *rmap_head; struct kvm_mmu_page *sp; sp = page_header(__pa(spte)); - rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp); + rmap_head = gfn_to_rmap(vcpu->kvm, gfn, sp); - kvm_unmap_rmapp(vcpu->kvm, rmapp, NULL, gfn, sp->role.level, 0); + kvm_unmap_rmapp(vcpu->kvm, rmap_head, NULL, gfn, sp->role.level, 0); kvm_flush_remote_tlbs(vcpu->kvm); } @@ -1723,8 +1706,7 @@ static void drop_parent_pte(struct kvm_mmu_page *sp, mmu_spte_clear_no_track(parent_pte); } -static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, - u64 *parent_pte, int direct) +static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, int direct) { struct kvm_mmu_page *sp; @@ -1740,8 +1722,6 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, * this feature. See the comments in kvm_zap_obsolete_pages(). */ list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages); - sp->parent_ptes = 0; - mmu_page_add_parent_pte(vcpu, sp, parent_pte); kvm_mod_used_mmu_pages(vcpu->kvm, +1); return sp; } @@ -1749,7 +1729,12 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, static void mark_unsync(u64 *spte); static void kvm_mmu_mark_parents_unsync(struct kvm_mmu_page *sp) { - pte_list_walk(&sp->parent_ptes, mark_unsync); + u64 *sptep; + struct rmap_iterator iter; + + for_each_rmap_spte(&sp->parent_ptes, &iter, sptep) { + mark_unsync(sptep); + } } static void mark_unsync(u64 *spte) @@ -1809,6 +1794,13 @@ static int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp, return (pvec->nr == KVM_PAGE_ARRAY_NR); } +static inline void clear_unsync_child_bit(struct kvm_mmu_page *sp, int idx) +{ + --sp->unsync_children; + WARN_ON((int)sp->unsync_children < 0); + __clear_bit(idx, sp->unsync_child_bitmap); +} + static int __mmu_unsync_walk(struct kvm_mmu_page *sp, struct kvm_mmu_pages *pvec) { @@ -1818,8 +1810,10 @@ static int __mmu_unsync_walk(struct kvm_mmu_page *sp, struct kvm_mmu_page *child; u64 ent = sp->spt[i]; - if (!is_shadow_present_pte(ent) || is_large_pte(ent)) - goto clear_child_bitmap; + if (!is_shadow_present_pte(ent) || is_large_pte(ent)) { + clear_unsync_child_bit(sp, i); + continue; + } child = page_header(ent & PT64_BASE_ADDR_MASK); @@ -1828,28 +1822,21 @@ static int __mmu_unsync_walk(struct kvm_mmu_page *sp, return -ENOSPC; ret = __mmu_unsync_walk(child, pvec); - if (!ret) - goto clear_child_bitmap; - else if (ret > 0) + if (!ret) { + clear_unsync_child_bit(sp, i); + continue; + } else if (ret > 0) { nr_unsync_leaf += ret; - else + } else return ret; } else if (child->unsync) { nr_unsync_leaf++; if (mmu_pages_add(pvec, child, i)) return -ENOSPC; } else - goto clear_child_bitmap; - - continue; - -clear_child_bitmap: - __clear_bit(i, sp->unsync_child_bitmap); - sp->unsync_children--; - WARN_ON((int)sp->unsync_children < 0); + clear_unsync_child_bit(sp, i); } - return nr_unsync_leaf; } @@ -2012,9 +1999,7 @@ static void mmu_pages_clear_parents(struct mmu_page_path *parents) if (!sp) return; - --sp->unsync_children; - WARN_ON((int)sp->unsync_children < 0); - __clear_bit(idx, sp->unsync_child_bitmap); + clear_unsync_child_bit(sp, idx); level++; } while (level < PT64_ROOT_LEVEL-1 && !sp->unsync_children); } @@ -2056,14 +2041,6 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu, } } -static void init_shadow_page_table(struct kvm_mmu_page *sp) -{ - int i; - - for (i = 0; i < PT64_ENT_PER_PAGE; ++i) - sp->spt[i] = 0ull; -} - static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp) { sp->write_flooding_count = 0; @@ -2086,8 +2063,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, gva_t gaddr, unsigned level, int direct, - unsigned access, - u64 *parent_pte) + unsigned access) { union kvm_mmu_page_role role; unsigned quadrant; @@ -2119,21 +2095,18 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, if (sp->unsync && kvm_sync_page_transient(vcpu, sp)) break; - mmu_page_add_parent_pte(vcpu, sp, parent_pte); - if (sp->unsync_children) { + if (sp->unsync_children) kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); - kvm_mmu_mark_parents_unsync(sp); - } else if (sp->unsync) - kvm_mmu_mark_parents_unsync(sp); __clear_sp_write_flooding_count(sp); trace_kvm_mmu_get_page(sp, false); return sp; } + ++vcpu->kvm->stat.mmu_cache_miss; - sp = kvm_mmu_alloc_page(vcpu, parent_pte, direct); - if (!sp) - return sp; + + sp = kvm_mmu_alloc_page(vcpu, direct); + sp->gfn = gfn; sp->role = role; hlist_add_head(&sp->hash_link, @@ -2147,7 +2120,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, account_shadowed(vcpu->kvm, sp); } sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen; - init_shadow_page_table(sp); + clear_page(sp->spt); trace_kvm_mmu_get_page(sp, true); return sp; } @@ -2201,7 +2174,8 @@ static void shadow_walk_next(struct kvm_shadow_walk_iterator *iterator) return __shadow_walk_next(iterator, *iterator->sptep); } -static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp, bool accessed) +static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep, + struct kvm_mmu_page *sp) { u64 spte; @@ -2209,12 +2183,14 @@ static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp, bool accessed) VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK); spte = __pa(sp->spt) | PT_PRESENT_MASK | PT_WRITABLE_MASK | - shadow_user_mask | shadow_x_mask; - - if (accessed) - spte |= shadow_accessed_mask; + shadow_user_mask | shadow_x_mask | shadow_accessed_mask; mmu_spte_set(sptep, spte); + + mmu_page_add_parent_pte(vcpu, sp, sptep); + + if (sp->unsync_children || sp->unsync) + mark_unsync(sptep); } static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, @@ -2273,17 +2249,12 @@ static void kvm_mmu_page_unlink_children(struct kvm *kvm, mmu_page_zap_pte(kvm, sp, sp->spt + i); } -static void kvm_mmu_put_page(struct kvm_mmu_page *sp, u64 *parent_pte) -{ - mmu_page_remove_parent_pte(sp, parent_pte); -} - static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp) { u64 *sptep; struct rmap_iterator iter; - while ((sptep = rmap_get_first(sp->parent_ptes, &iter))) + while ((sptep = rmap_get_first(&sp->parent_ptes, &iter))) drop_parent_pte(sp, sptep); } @@ -2479,7 +2450,7 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, return 0; } -static bool kvm_is_mmio_pfn(pfn_t pfn) +static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) { if (pfn_valid(pfn)) return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn)); @@ -2489,7 +2460,7 @@ static bool kvm_is_mmio_pfn(pfn_t pfn) static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, int level, - gfn_t gfn, pfn_t pfn, bool speculative, + gfn_t gfn, kvm_pfn_t pfn, bool speculative, bool can_unsync, bool host_writable) { u64 spte; @@ -2567,18 +2538,18 @@ done: return ret; } -static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, - unsigned pte_access, int write_fault, int *emulate, - int level, gfn_t gfn, pfn_t pfn, bool speculative, - bool host_writable) +static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, + int write_fault, int level, gfn_t gfn, kvm_pfn_t pfn, + bool speculative, bool host_writable) { int was_rmapped = 0; int rmap_count; + bool emulate = false; pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__, *sptep, write_fault, gfn); - if (is_rmap_spte(*sptep)) { + if (is_shadow_present_pte(*sptep)) { /* * If we overwrite a PTE page pointer with a 2MB PMD, unlink * the parent of the now unreachable PTE. @@ -2603,12 +2574,12 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (set_spte(vcpu, sptep, pte_access, level, gfn, pfn, speculative, true, host_writable)) { if (write_fault) - *emulate = 1; + emulate = true; kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); } - if (unlikely(is_mmio_spte(*sptep) && emulate)) - *emulate = 1; + if (unlikely(is_mmio_spte(*sptep))) + emulate = true; pgprintk("%s: setting spte %llx\n", __func__, *sptep); pgprintk("instantiating %s PTE (%s) at %llx (%llx) addr %p\n", @@ -2627,9 +2598,11 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, } kvm_release_pfn_clean(pfn); + + return emulate; } -static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, +static kvm_pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, bool no_dirty_log) { struct kvm_memory_slot *slot; @@ -2661,9 +2634,8 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, return -1; for (i = 0; i < ret; i++, gfn++, start++) - mmu_set_spte(vcpu, start, access, 0, NULL, - sp->role.level, gfn, page_to_pfn(pages[i]), - true, true); + mmu_set_spte(vcpu, start, access, 0, sp->role.level, gfn, + page_to_pfn(pages[i]), true, true); return 0; } @@ -2711,9 +2683,8 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) __direct_pte_prefetch(vcpu, sp, sptep); } -static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, - int map_writable, int level, gfn_t gfn, pfn_t pfn, - bool prefault) +static int __direct_map(struct kvm_vcpu *vcpu, int write, int map_writable, + int level, gfn_t gfn, kvm_pfn_t pfn, bool prefault) { struct kvm_shadow_walk_iterator iterator; struct kvm_mmu_page *sp; @@ -2725,9 +2696,9 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) { if (iterator.level == level) { - mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, - write, &emulate, level, gfn, pfn, - prefault, map_writable); + emulate = mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, + write, level, gfn, pfn, prefault, + map_writable); direct_pte_prefetch(vcpu, iterator.sptep); ++vcpu->stat.pf_fixed; break; @@ -2740,10 +2711,9 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, base_addr &= PT64_LVL_ADDR_MASK(iterator.level); pseudo_gfn = base_addr >> PAGE_SHIFT; sp = kvm_mmu_get_page(vcpu, pseudo_gfn, iterator.addr, - iterator.level - 1, - 1, ACC_ALL, iterator.sptep); + iterator.level - 1, 1, ACC_ALL); - link_shadow_page(iterator.sptep, sp, true); + link_shadow_page(vcpu, iterator.sptep, sp); } } return emulate; @@ -2762,7 +2732,7 @@ static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct * send_sig_info(SIGBUS, &info, tsk); } -static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, pfn_t pfn) +static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) { /* * Do not cache the mmio info caused by writing the readonly gfn @@ -2782,9 +2752,10 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, pfn_t pfn) } static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, - gfn_t *gfnp, pfn_t *pfnp, int *levelp) + gfn_t *gfnp, kvm_pfn_t *pfnp, + int *levelp) { - pfn_t pfn = *pfnp; + kvm_pfn_t pfn = *pfnp; gfn_t gfn = *gfnp; int level = *levelp; @@ -2823,7 +2794,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, } static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, - pfn_t pfn, unsigned access, int *ret_val) + kvm_pfn_t pfn, unsigned access, int *ret_val) { bool ret = true; @@ -2922,7 +2893,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, * If the mapping has been changed, let the vcpu fault on the * same address again. */ - if (!is_rmap_spte(spte)) { + if (!is_shadow_present_pte(spte)) { ret = true; goto exit; } @@ -2977,7 +2948,7 @@ exit: } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gva_t gva, pfn_t *pfn, bool write, bool *writable); + gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable); static void make_mmu_pages_available(struct kvm_vcpu *vcpu); static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, @@ -2985,14 +2956,13 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, { int r; int level; - int force_pt_level; - pfn_t pfn; + bool force_pt_level = false; + kvm_pfn_t pfn; unsigned long mmu_seq; bool map_writable, write = error_code & PFERR_WRITE_MASK; - force_pt_level = mapping_level_dirty_bitmap(vcpu, gfn); + level = mapping_level(vcpu, gfn, &force_pt_level); if (likely(!force_pt_level)) { - level = mapping_level(vcpu, gfn); /* * This path builds a PAE pagetable - so we can map * 2mb pages at maximum. Therefore check if the level @@ -3002,8 +2972,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, level = PT_DIRECTORY_LEVEL; gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); - } else - level = PT_PAGE_TABLE_LEVEL; + } if (fast_page_fault(vcpu, v, level, error_code)) return 0; @@ -3023,11 +2992,9 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, make_mmu_pages_available(vcpu); if (likely(!force_pt_level)) transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level); - r = __direct_map(vcpu, v, write, map_writable, level, gfn, pfn, - prefault); + r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault); spin_unlock(&vcpu->kvm->mmu_lock); - return r; out_unlock: @@ -3102,8 +3069,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) { spin_lock(&vcpu->kvm->mmu_lock); make_mmu_pages_available(vcpu); - sp = kvm_mmu_get_page(vcpu, 0, 0, PT64_ROOT_LEVEL, - 1, ACC_ALL, NULL); + sp = kvm_mmu_get_page(vcpu, 0, 0, PT64_ROOT_LEVEL, 1, ACC_ALL); ++sp->root_count; spin_unlock(&vcpu->kvm->mmu_lock); vcpu->arch.mmu.root_hpa = __pa(sp->spt); @@ -3115,9 +3081,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) spin_lock(&vcpu->kvm->mmu_lock); make_mmu_pages_available(vcpu); sp = kvm_mmu_get_page(vcpu, i << (30 - PAGE_SHIFT), - i << 30, - PT32_ROOT_LEVEL, 1, ACC_ALL, - NULL); + i << 30, PT32_ROOT_LEVEL, 1, ACC_ALL); root = __pa(sp->spt); ++sp->root_count; spin_unlock(&vcpu->kvm->mmu_lock); @@ -3154,7 +3118,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) spin_lock(&vcpu->kvm->mmu_lock); make_mmu_pages_available(vcpu); sp = kvm_mmu_get_page(vcpu, root_gfn, 0, PT64_ROOT_LEVEL, - 0, ACC_ALL, NULL); + 0, ACC_ALL); root = __pa(sp->spt); ++sp->root_count; spin_unlock(&vcpu->kvm->mmu_lock); @@ -3187,9 +3151,8 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) } spin_lock(&vcpu->kvm->mmu_lock); make_mmu_pages_available(vcpu); - sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, - PT32_ROOT_LEVEL, 0, - ACC_ALL, NULL); + sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, PT32_ROOT_LEVEL, + 0, ACC_ALL); root = __pa(sp->spt); ++sp->root_count; spin_unlock(&vcpu->kvm->mmu_lock); @@ -3291,54 +3254,90 @@ static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr, return vcpu->arch.nested_mmu.translate_gpa(vcpu, vaddr, access, exception); } -static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct) +static bool +__is_rsvd_bits_set(struct rsvd_bits_validate *rsvd_check, u64 pte, int level) { - if (direct) - return vcpu_match_mmio_gpa(vcpu, addr); + int bit7 = (pte >> 7) & 1, low6 = pte & 0x3f; - return vcpu_match_mmio_gva(vcpu, addr); + return (pte & rsvd_check->rsvd_bits_mask[bit7][level-1]) | + ((rsvd_check->bad_mt_xwr & (1ull << low6)) != 0); } +static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level) +{ + return __is_rsvd_bits_set(&mmu->guest_rsvd_check, gpte, level); +} -/* - * On direct hosts, the last spte is only allows two states - * for mmio page fault: - * - It is the mmio spte - * - It is zapped or it is being zapped. - * - * This function completely checks the spte when the last spte - * is not the mmio spte. - */ -static bool check_direct_spte_mmio_pf(u64 spte) +static bool is_shadow_zero_bits_set(struct kvm_mmu *mmu, u64 spte, int level) +{ + return __is_rsvd_bits_set(&mmu->shadow_zero_check, spte, level); +} + +static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct) { - return __check_direct_spte_mmio_pf(spte); + if (direct) + return vcpu_match_mmio_gpa(vcpu, addr); + + return vcpu_match_mmio_gva(vcpu, addr); } -static u64 walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr) +/* return true if reserved bit is detected on spte. */ +static bool +walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) { struct kvm_shadow_walk_iterator iterator; - u64 spte = 0ull; + u64 sptes[PT64_ROOT_LEVEL], spte = 0ull; + int root, leaf; + bool reserved = false; if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) - return spte; + goto exit; walk_shadow_page_lockless_begin(vcpu); - for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) + + for (shadow_walk_init(&iterator, vcpu, addr), + leaf = root = iterator.level; + shadow_walk_okay(&iterator); + __shadow_walk_next(&iterator, spte)) { + spte = mmu_spte_get_lockless(iterator.sptep); + + sptes[leaf - 1] = spte; + leaf--; + if (!is_shadow_present_pte(spte)) break; + + reserved |= is_shadow_zero_bits_set(&vcpu->arch.mmu, spte, + iterator.level); + } + walk_shadow_page_lockless_end(vcpu); - return spte; + if (reserved) { + pr_err("%s: detect reserved bits on spte, addr 0x%llx, dump hierarchy:\n", + __func__, addr); + while (root > leaf) { + pr_err("------ spte 0x%llx level %d.\n", + sptes[root - 1], root); + root--; + } + } +exit: + *sptep = spte; + return reserved; } -int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct) +int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct) { u64 spte; + bool reserved; if (quickly_check_mmio_pf(vcpu, addr, direct)) return RET_MMIO_PF_EMULATE; - spte = walk_shadow_page_get_mmio_spte(vcpu, addr); + reserved = walk_shadow_page_get_mmio_spte(vcpu, addr, &spte); + if (WARN_ON(reserved)) + return RET_MMIO_PF_BUG; if (is_mmio_spte(spte)) { gfn_t gfn = get_mmio_spte_gfn(spte); @@ -3356,29 +3355,12 @@ int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct) } /* - * It's ok if the gva is remapped by other cpus on shadow guest, - * it's a BUG if the gfn is not a mmio page. - */ - if (direct && !check_direct_spte_mmio_pf(spte)) - return RET_MMIO_PF_BUG; - - /* * If the page table is zapped by other cpus, let CPU fault again on * the address. */ return RET_MMIO_PF_RETRY; } -EXPORT_SYMBOL_GPL(handle_mmio_page_fault_common); - -static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, - u32 error_code, bool direct) -{ - int ret; - - ret = handle_mmio_page_fault_common(vcpu, addr, direct); - WARN_ON(ret == RET_MMIO_PF_BUG); - return ret; -} +EXPORT_SYMBOL_GPL(handle_mmio_page_fault); static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code, bool prefault) @@ -3389,7 +3371,7 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code); if (unlikely(error_code & PFERR_RSVD_MASK)) { - r = handle_mmio_page_fault(vcpu, gva, error_code, true); + r = handle_mmio_page_fault(vcpu, gva, true); if (likely(r != RET_MMIO_PF_INVALID)) return r; @@ -3421,7 +3403,7 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) static bool can_do_async_pf(struct kvm_vcpu *vcpu) { - if (unlikely(!irqchip_in_kernel(vcpu->kvm) || + if (unlikely(!lapic_in_kernel(vcpu) || kvm_event_needs_reinjection(vcpu))) return false; @@ -3429,7 +3411,7 @@ 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) + gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable) { struct kvm_memory_slot *slot; bool async; @@ -3467,10 +3449,10 @@ check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level) static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, bool prefault) { - pfn_t pfn; + kvm_pfn_t pfn; int r; int level; - int force_pt_level; + bool force_pt_level; gfn_t gfn = gpa >> PAGE_SHIFT; unsigned long mmu_seq; int write = error_code & PFERR_WRITE_MASK; @@ -3479,7 +3461,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); if (unlikely(error_code & PFERR_RSVD_MASK)) { - r = handle_mmio_page_fault(vcpu, gpa, error_code, true); + r = handle_mmio_page_fault(vcpu, gpa, true); if (likely(r != RET_MMIO_PF_INVALID)) return r; @@ -3489,20 +3471,15 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, if (r) return r; - 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; - + force_pt_level = !check_hugepage_cache_consistency(vcpu, gfn, + PT_DIRECTORY_LEVEL); + level = mapping_level(vcpu, gfn, &force_pt_level); 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; + } if (fast_page_fault(vcpu, gpa, level, error_code)) return 0; @@ -3522,8 +3499,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, make_mmu_pages_available(vcpu); if (likely(!force_pt_level)) transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level); - r = __direct_map(vcpu, gpa, write, map_writable, - level, gfn, pfn, prefault); + r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault); spin_unlock(&vcpu->kvm->mmu_lock); return r; @@ -3604,111 +3580,195 @@ static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gp #include "paging_tmpl.h" #undef PTTYPE -static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, - struct kvm_mmu *context) +static void +__reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, + struct rsvd_bits_validate *rsvd_check, + int maxphyaddr, int level, bool nx, bool gbpages, + bool pse, bool amd) { - int maxphyaddr = cpuid_maxphyaddr(vcpu); u64 exb_bit_rsvd = 0; u64 gbpages_bit_rsvd = 0; u64 nonleaf_bit8_rsvd = 0; - context->bad_mt_xwr = 0; + rsvd_check->bad_mt_xwr = 0; - if (!context->nx) + if (!nx) exb_bit_rsvd = rsvd_bits(63, 63); - if (!guest_cpuid_has_gbpages(vcpu)) + if (!gbpages) gbpages_bit_rsvd = rsvd_bits(7, 7); /* * Non-leaf PML4Es and PDPEs reserve bit 8 (which would be the G bit for * leaf entries) on AMD CPUs only. */ - if (guest_cpuid_is_amd(vcpu)) + if (amd) nonleaf_bit8_rsvd = rsvd_bits(8, 8); - switch (context->root_level) { + switch (level) { case PT32_ROOT_LEVEL: /* no rsvd bits for 2 level 4K page table entries */ - context->rsvd_bits_mask[0][1] = 0; - context->rsvd_bits_mask[0][0] = 0; - context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0]; + rsvd_check->rsvd_bits_mask[0][1] = 0; + rsvd_check->rsvd_bits_mask[0][0] = 0; + rsvd_check->rsvd_bits_mask[1][0] = + rsvd_check->rsvd_bits_mask[0][0]; - if (!is_pse(vcpu)) { - context->rsvd_bits_mask[1][1] = 0; + if (!pse) { + rsvd_check->rsvd_bits_mask[1][1] = 0; break; } if (is_cpuid_PSE36()) /* 36bits PSE 4MB page */ - context->rsvd_bits_mask[1][1] = rsvd_bits(17, 21); + rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(17, 21); else /* 32 bits PSE 4MB page */ - context->rsvd_bits_mask[1][1] = rsvd_bits(13, 21); + rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(13, 21); break; case PT32E_ROOT_LEVEL: - context->rsvd_bits_mask[0][2] = + rsvd_check->rsvd_bits_mask[0][2] = rsvd_bits(maxphyaddr, 63) | rsvd_bits(5, 8) | rsvd_bits(1, 2); /* PDPTE */ - context->rsvd_bits_mask[0][1] = exb_bit_rsvd | + rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 62); /* PDE */ - context->rsvd_bits_mask[0][0] = exb_bit_rsvd | + rsvd_check->rsvd_bits_mask[0][0] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 62); /* PTE */ - context->rsvd_bits_mask[1][1] = exb_bit_rsvd | + rsvd_check->rsvd_bits_mask[1][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 62) | rsvd_bits(13, 20); /* large page */ - context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0]; + rsvd_check->rsvd_bits_mask[1][0] = + rsvd_check->rsvd_bits_mask[0][0]; break; case PT64_ROOT_LEVEL: - context->rsvd_bits_mask[0][3] = exb_bit_rsvd | - nonleaf_bit8_rsvd | rsvd_bits(7, 7) | rsvd_bits(maxphyaddr, 51); - context->rsvd_bits_mask[0][2] = exb_bit_rsvd | - nonleaf_bit8_rsvd | gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51); - context->rsvd_bits_mask[0][1] = exb_bit_rsvd | + rsvd_check->rsvd_bits_mask[0][3] = exb_bit_rsvd | + nonleaf_bit8_rsvd | rsvd_bits(7, 7) | + rsvd_bits(maxphyaddr, 51); + rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd | + nonleaf_bit8_rsvd | gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51); - context->rsvd_bits_mask[0][0] = exb_bit_rsvd | + rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51); - context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3]; - context->rsvd_bits_mask[1][2] = exb_bit_rsvd | + rsvd_check->rsvd_bits_mask[0][0] = exb_bit_rsvd | + rsvd_bits(maxphyaddr, 51); + rsvd_check->rsvd_bits_mask[1][3] = + rsvd_check->rsvd_bits_mask[0][3]; + rsvd_check->rsvd_bits_mask[1][2] = exb_bit_rsvd | gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51) | rsvd_bits(13, 29); - context->rsvd_bits_mask[1][1] = exb_bit_rsvd | + rsvd_check->rsvd_bits_mask[1][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51) | rsvd_bits(13, 20); /* large page */ - context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0]; + rsvd_check->rsvd_bits_mask[1][0] = + rsvd_check->rsvd_bits_mask[0][0]; break; } } -static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, - struct kvm_mmu *context, bool execonly) +static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, + struct kvm_mmu *context) { - int maxphyaddr = cpuid_maxphyaddr(vcpu); - int pte; + __reset_rsvds_bits_mask(vcpu, &context->guest_rsvd_check, + cpuid_maxphyaddr(vcpu), context->root_level, + context->nx, guest_cpuid_has_gbpages(vcpu), + is_pse(vcpu), guest_cpuid_is_amd(vcpu)); +} - context->rsvd_bits_mask[0][3] = +static void +__reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, + int maxphyaddr, bool execonly) +{ + u64 bad_mt_xwr; + + rsvd_check->rsvd_bits_mask[0][3] = rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7); - context->rsvd_bits_mask[0][2] = + rsvd_check->rsvd_bits_mask[0][2] = rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6); - context->rsvd_bits_mask[0][1] = + rsvd_check->rsvd_bits_mask[0][1] = rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6); - context->rsvd_bits_mask[0][0] = rsvd_bits(maxphyaddr, 51); + rsvd_check->rsvd_bits_mask[0][0] = rsvd_bits(maxphyaddr, 51); /* large page */ - context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3]; - context->rsvd_bits_mask[1][2] = + rsvd_check->rsvd_bits_mask[1][3] = rsvd_check->rsvd_bits_mask[0][3]; + rsvd_check->rsvd_bits_mask[1][2] = rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 29); - context->rsvd_bits_mask[1][1] = + rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 20); - context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0]; - - for (pte = 0; pte < 64; pte++) { - int rwx_bits = pte & 7; - int mt = pte >> 3; - if (mt == 0x2 || mt == 0x3 || mt == 0x7 || - rwx_bits == 0x2 || rwx_bits == 0x6 || - (rwx_bits == 0x4 && !execonly)) - context->bad_mt_xwr |= (1ull << pte); + rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0]; + + bad_mt_xwr = 0xFFull << (2 * 8); /* bits 3..5 must not be 2 */ + bad_mt_xwr |= 0xFFull << (3 * 8); /* bits 3..5 must not be 3 */ + bad_mt_xwr |= 0xFFull << (7 * 8); /* bits 3..5 must not be 7 */ + bad_mt_xwr |= REPEAT_BYTE(1ull << 2); /* bits 0..2 must not be 010 */ + bad_mt_xwr |= REPEAT_BYTE(1ull << 6); /* bits 0..2 must not be 110 */ + if (!execonly) { + /* bits 0..2 must not be 100 unless VMX capabilities allow it */ + bad_mt_xwr |= REPEAT_BYTE(1ull << 4); } + rsvd_check->bad_mt_xwr = bad_mt_xwr; +} + +static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, + struct kvm_mmu *context, bool execonly) +{ + __reset_rsvds_bits_mask_ept(&context->guest_rsvd_check, + cpuid_maxphyaddr(vcpu), execonly); +} + +/* + * the page table on host is the shadow page table for the page + * table in guest or amd nested guest, its mmu features completely + * follow the features in guest. + */ +void +reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) +{ + /* + * Passing "true" to the last argument is okay; it adds a check + * on bit 8 of the SPTEs which KVM doesn't use anyway. + */ + __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check, + boot_cpu_data.x86_phys_bits, + context->shadow_root_level, context->nx, + guest_cpuid_has_gbpages(vcpu), is_pse(vcpu), + true); +} +EXPORT_SYMBOL_GPL(reset_shadow_zero_bits_mask); + +static inline bool boot_cpu_is_amd(void) +{ + WARN_ON_ONCE(!tdp_enabled); + return shadow_x_mask == 0; +} + +/* + * the direct page table on host, use as much mmu features as + * possible, however, kvm currently does not do execution-protection. + */ +static void +reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, + struct kvm_mmu *context) +{ + if (boot_cpu_is_amd()) + __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check, + boot_cpu_data.x86_phys_bits, + context->shadow_root_level, false, + cpu_has_gbpages, true, true); + else + __reset_rsvds_bits_mask_ept(&context->shadow_zero_check, + boot_cpu_data.x86_phys_bits, + false); + +} + +/* + * as the comments in reset_shadow_zero_bits_mask() except it + * is the shadow page table for intel nested guest. + */ +static void +reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, + struct kvm_mmu *context, bool execonly) +{ + __reset_rsvds_bits_mask_ept(&context->shadow_zero_check, + boot_cpu_data.x86_phys_bits, execonly); } static void update_permission_bitmask(struct kvm_vcpu *vcpu, @@ -3889,6 +3949,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) update_permission_bitmask(vcpu, context, false); update_last_pte_bitmap(vcpu, context); + reset_tdp_shadow_zero_bits_mask(vcpu, context); } void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu) @@ -3916,6 +3977,7 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu) context->base_role.smap_andnot_wp = smap && !is_write_protection(vcpu); context->base_role.smm = is_smm(vcpu); + reset_shadow_zero_bits_mask(vcpu, context); } EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu); @@ -3939,6 +4001,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly) update_permission_bitmask(vcpu, context, true); reset_rsvds_bits_mask_ept(vcpu, context, execonly); + reset_ept_shadow_zero_bits_mask(vcpu, context, execonly); } EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu); @@ -3962,10 +4025,12 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu) g_context->inject_page_fault = kvm_inject_page_fault; /* - * Note that arch.mmu.gva_to_gpa translates l2_gva to l1_gpa. The - * translation of l2_gpa to l1_gpa addresses is done using the - * arch.nested_mmu.gva_to_gpa function. Basically the gva_to_gpa - * functions between mmu and nested_mmu are swapped. + * Note that arch.mmu.gva_to_gpa translates l2_gpa to l1_gpa using + * L1's nested page tables (e.g. EPT12). The nested translation + * of l2_gva to l1_gpa is done by arch.nested_mmu.gva_to_gpa using + * L2's page tables as the first level of translation and L1's + * nested page tables as the second level of translation. Basically + * the gva_to_gpa functions between mmu and nested_mmu are swapped. */ if (!is_paging(vcpu)) { g_context->nx = false; @@ -4399,7 +4464,7 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu) } /* The return value indicates if tlb flush on all vcpus is needed. */ -typedef bool (*slot_level_handler) (struct kvm *kvm, unsigned long *rmap); +typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head); /* The caller should hold mmu-lock before calling this function. */ static bool @@ -4493,9 +4558,10 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) spin_unlock(&kvm->mmu_lock); } -static bool slot_rmap_write_protect(struct kvm *kvm, unsigned long *rmapp) +static bool slot_rmap_write_protect(struct kvm *kvm, + struct kvm_rmap_head *rmap_head) { - return __rmap_write_protect(kvm, rmapp, false); + return __rmap_write_protect(kvm, rmap_head, false); } void kvm_mmu_slot_remove_write_access(struct kvm *kvm, @@ -4531,16 +4597,16 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, } static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, - unsigned long *rmapp) + struct kvm_rmap_head *rmap_head) { u64 *sptep; struct rmap_iterator iter; int need_tlb_flush = 0; - pfn_t pfn; + kvm_pfn_t pfn; struct kvm_mmu_page *sp; restart: - for_each_rmap_spte(rmapp, &iter, sptep) { + for_each_rmap_spte(rmap_head, &iter, sptep) { sp = page_header(__pa(sptep)); pfn = spte_to_pfn(*sptep); @@ -4860,28 +4926,6 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm) return nr_mmu_pages; } -int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]) -{ - struct kvm_shadow_walk_iterator iterator; - u64 spte; - int nr_sptes = 0; - - if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) - return nr_sptes; - - walk_shadow_page_lockless_begin(vcpu); - for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) { - sptes[iterator.level-1] = spte; - nr_sptes++; - if (!is_shadow_present_pte(spte)) - break; - } - walk_shadow_page_lockless_end(vcpu); - - return nr_sptes; -} -EXPORT_SYMBOL_GPL(kvm_mmu_get_spte_hierarchy); - void kvm_mmu_destroy(struct kvm_vcpu *vcpu) { kvm_mmu_unload(vcpu); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 398d21c0f6dd..55ffb7b0f95e 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -50,17 +50,19 @@ static inline u64 rsvd_bits(int s, int e) return ((1ULL << (e - s + 1)) - 1) << s; } -int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]); void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask); +void +reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context); + /* - * Return values of handle_mmio_page_fault_common: + * Return values of handle_mmio_page_fault: * RET_MMIO_PF_EMULATE: it is a real mmio page fault, emulate the instruction * directly. * RET_MMIO_PF_INVALID: invalid spte is detected then let the real page * fault path update the mmio spte. * RET_MMIO_PF_RETRY: let CPU fault again on the address. - * RET_MMIO_PF_BUG: bug is detected. + * RET_MMIO_PF_BUG: a bug was detected (and a WARN was printed). */ enum { RET_MMIO_PF_EMULATE = 1, @@ -69,7 +71,7 @@ enum { RET_MMIO_PF_BUG = -1 }; -int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct); +int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct); void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu); void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly); diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c index 03d518e499a6..dcce533d420c 100644 --- a/arch/x86/kvm/mmu_audit.c +++ b/arch/x86/kvm/mmu_audit.c @@ -97,7 +97,7 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level) { struct kvm_mmu_page *sp; gfn_t gfn; - pfn_t pfn; + kvm_pfn_t pfn; hpa_t hpa; sp = page_header(__pa(sptep)); @@ -129,7 +129,7 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level) 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_rmap_head *rmap_head; struct kvm_mmu_page *rev_sp; struct kvm_memslots *slots; struct kvm_memory_slot *slot; @@ -150,8 +150,8 @@ static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) return; } - rmapp = __gfn_to_rmap(gfn, rev_sp->role.level, slot); - if (!*rmapp) { + rmap_head = __gfn_to_rmap(gfn, rev_sp->role.level, slot); + if (!rmap_head->val) { if (!__ratelimit(&ratelimit_state)) return; audit_printk(kvm, "no rmap for writable spte %llx\n", @@ -183,7 +183,7 @@ static void check_mappings_rmap(struct kvm *kvm, struct kvm_mmu_page *sp) return; for (i = 0; i < PT64_ENT_PER_PAGE; ++i) { - if (!is_rmap_spte(sp->spt[i])) + if (!is_shadow_present_pte(sp->spt[i])) continue; inspect_spte_has_rmap(kvm, sp->spt + i); @@ -192,7 +192,7 @@ static void check_mappings_rmap(struct kvm *kvm, struct kvm_mmu_page *sp) static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp) { - unsigned long *rmapp; + struct kvm_rmap_head *rmap_head; u64 *sptep; struct rmap_iterator iter; struct kvm_memslots *slots; @@ -203,13 +203,14 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp) 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); + rmap_head = __gfn_to_rmap(sp->gfn, PT_PAGE_TABLE_LEVEL, slot); - for_each_rmap_spte(rmapp, &iter, sptep) + for_each_rmap_spte(rmap_head, &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) diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 9e8bf13572e6..3f8c732117ec 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -120,14 +120,22 @@ 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) +static u8 mtrr_disabled_type(struct kvm_vcpu *vcpu) { /* * 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. + * + * However, virtual machines can be run with CPUID such that + * there are no MTRRs. In that case, the firmware will never + * enable MTRRs and it is obviously undesirable to run the + * guest entirely with UC memory and we use WB. */ - return MTRR_TYPE_UNCACHABLE; + if (guest_cpuid_has_mtrr(vcpu)) + return MTRR_TYPE_UNCACHABLE; + else + return MTRR_TYPE_WRBACK; } /* @@ -267,7 +275,7 @@ static int fixed_mtrr_addr_to_seg(u64 addr) for (seg = 0; seg < seg_num; seg++) { mtrr_seg = &fixed_seg_table[seg]; - if (mtrr_seg->start >= addr && addr < mtrr_seg->end) + if (mtrr_seg->start <= addr && addr < mtrr_seg->end) return seg; } @@ -300,7 +308,6 @@ static void var_mtrr_range(struct kvm_mtrr_range *range, u64 *start, u64 *end) *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. @@ -356,10 +363,14 @@ static void set_var_mtrr_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data) if (var_mtrr_range_is_valid(cur)) list_del(&mtrr_state->var_ranges[index].node); + /* Extend the mask with all 1 bits to the left, since those + * bits must implicitly be 0. The bits are then cleared + * when reading them. + */ if (!is_mtrr_mask) cur->base = data; else - cur->mask = data; + cur->mask = data | (-1LL << cpuid_maxphyaddr(vcpu)); /* add it to the list if it's enabled. */ if (var_mtrr_range_is_valid(cur)) { @@ -426,6 +437,8 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) *pdata = vcpu->arch.mtrr_state.var_ranges[index].base; else *pdata = vcpu->arch.mtrr_state.var_ranges[index].mask; + + *pdata &= (1ULL << cpuid_maxphyaddr(vcpu)) - 1; } return 0; @@ -670,7 +683,7 @@ u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) } if (iter.mtrr_disabled) - return mtrr_disabled_type(); + return mtrr_disabled_type(vcpu); /* not contained in any MTRRs. */ if (type == -1) diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 0f67d7e24800..6c9fed957cce 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -128,14 +128,6 @@ static inline void FNAME(protect_clean_gpte)(unsigned *access, unsigned gpte) *access &= mask; } -static bool FNAME(is_rsvd_bits_set)(struct kvm_mmu *mmu, u64 gpte, int level) -{ - int bit7 = (gpte >> 7) & 1, low6 = gpte & 0x3f; - - return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) | - ((mmu->bad_mt_xwr & (1ull << low6)) != 0); -} - static inline int FNAME(is_present_gpte)(unsigned long pte) { #if PTTYPE != PTTYPE_EPT @@ -172,7 +164,7 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, u64 gpte) { - if (FNAME(is_rsvd_bits_set)(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL)) + if (is_rsvd_bits_set(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL)) goto no_present; if (!FNAME(is_present_gpte)(gpte)) @@ -353,8 +345,7 @@ retry_walk: if (unlikely(!FNAME(is_present_gpte)(pte))) goto error; - if (unlikely(FNAME(is_rsvd_bits_set)(mmu, pte, - walker->level))) { + if (unlikely(is_rsvd_bits_set(mmu, pte, walker->level))) { errcode |= PFERR_RSVD_MASK | PFERR_PRESENT_MASK; goto error; } @@ -465,7 +456,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, { unsigned pte_access; gfn_t gfn; - pfn_t pfn; + kvm_pfn_t pfn; if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte)) return false; @@ -484,8 +475,8 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, * we call mmu_set_spte() with host_writable = true because * pte_prefetch_gfn_to_pfn always gets a writable pfn. */ - mmu_set_spte(vcpu, spte, pte_access, 0, NULL, PT_PAGE_TABLE_LEVEL, - gfn, pfn, true, true); + mmu_set_spte(vcpu, spte, pte_access, 0, PT_PAGE_TABLE_LEVEL, gfn, pfn, + true, true); return true; } @@ -560,12 +551,12 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, struct guest_walker *gw, int write_fault, int hlevel, - pfn_t pfn, bool map_writable, bool prefault) + kvm_pfn_t pfn, bool map_writable, bool prefault) { struct kvm_mmu_page *sp = NULL; struct kvm_shadow_walk_iterator it; unsigned direct_access, access = gw->pt_access; - int top_level, emulate = 0; + int top_level, emulate; direct_access = gw->pte_access; @@ -596,7 +587,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, if (!is_shadow_present_pte(*it.sptep)) { table_gfn = gw->table_gfn[it.level - 2]; sp = kvm_mmu_get_page(vcpu, table_gfn, addr, it.level-1, - false, access, it.sptep); + false, access); } /* @@ -607,7 +598,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, goto out_gpte_changed; if (sp) - link_shadow_page(it.sptep, sp, PT_GUEST_ACCESSED_MASK); + link_shadow_page(vcpu, it.sptep, sp); } for (; @@ -626,20 +617,18 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, direct_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); sp = kvm_mmu_get_page(vcpu, direct_gfn, addr, it.level-1, - true, direct_access, it.sptep); - link_shadow_page(it.sptep, sp, PT_GUEST_ACCESSED_MASK); + true, direct_access); + link_shadow_page(vcpu, it.sptep, sp); } clear_sp_write_flooding_count(it.sptep); - mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault, &emulate, - it.level, gw->gfn, pfn, prefault, map_writable); + emulate = mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault, + it.level, gw->gfn, pfn, prefault, map_writable); FNAME(pte_prefetch)(vcpu, gw, it.sptep); return emulate; out_gpte_changed: - if (sp) - kvm_mmu_put_page(sp, it.sptep); kvm_release_pfn_clean(pfn); return 0; } @@ -705,17 +694,16 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, int user_fault = error_code & PFERR_USER_MASK; struct guest_walker walker; int r; - pfn_t pfn; + kvm_pfn_t pfn; int level = PT_PAGE_TABLE_LEVEL; - int force_pt_level; + bool force_pt_level = false; unsigned long mmu_seq; bool map_writable, is_self_change_mapping; pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code); if (unlikely(error_code & PFERR_RSVD_MASK)) { - r = handle_mmio_page_fault(vcpu, addr, error_code, - mmu_is_nested(vcpu)); + r = handle_mmio_page_fault(vcpu, addr, mmu_is_nested(vcpu)); if (likely(r != RET_MMIO_PF_INVALID)) return r; @@ -752,15 +740,14 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu, &walker, user_fault, &vcpu->arch.write_fault_to_shadow_pgtable); - if (walker.level >= PT_DIRECTORY_LEVEL) - force_pt_level = mapping_level_dirty_bitmap(vcpu, walker.gfn) - || is_self_change_mapping; - else - force_pt_level = 1; - if (!force_pt_level) { - level = min(walker.level, mapping_level(vcpu, walker.gfn)); - walker.gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE(level) - 1); - } + if (walker.level >= PT_DIRECTORY_LEVEL && !is_self_change_mapping) { + level = mapping_level(vcpu, walker.gfn, &force_pt_level); + if (likely(!force_pt_level)) { + level = min(walker.level, level); + walker.gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE(level) - 1); + } + } else + force_pt_level = true; mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c index 886aa25a7131..39b91127ef07 100644 --- a/arch/x86/kvm/pmu_amd.c +++ b/arch/x86/kvm/pmu_amd.c @@ -133,8 +133,6 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) /* 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; } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 8e0c0844c6b9..c13a64b7d789 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -86,6 +86,7 @@ static const u32 host_save_user_msrs[] = { MSR_FS_BASE, #endif MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, + MSR_TSC_AUX, }; #define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs) @@ -135,6 +136,7 @@ struct vcpu_svm { uint64_t asid_generation; uint64_t sysenter_esp; uint64_t sysenter_eip; + uint64_t tsc_aux; u64 next_rip; @@ -158,7 +160,8 @@ struct vcpu_svm { unsigned long int3_rip; u32 apf_reason; - u64 tsc_ratio; + /* cached guest cpuid flags for faster access */ + bool nrips_enabled : 1; }; static DEFINE_PER_CPU(u64, current_tsc_ratio); @@ -202,6 +205,7 @@ module_param(npt, int, S_IRUGO); static int nested = true; module_param(nested, int, S_IRUGO); +static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); static void svm_flush_tlb(struct kvm_vcpu *vcpu); static void svm_complete_interrupts(struct vcpu_svm *svm); @@ -210,7 +214,6 @@ static int nested_svm_intercept(struct vcpu_svm *svm); static int nested_svm_vmexit(struct vcpu_svm *svm); static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code); -static u64 __scale_tsc(u64 ratio, u64 tsc); enum { VMCB_INTERCEPTS, /* Intercept vectors, TSC offset, @@ -513,7 +516,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); if (svm->vmcb->control.next_rip != 0) { - WARN_ON(!static_cpu_has(X86_FEATURE_NRIPS)); + WARN_ON_ONCE(!static_cpu_has(X86_FEATURE_NRIPS)); svm->next_rip = svm->vmcb->control.next_rip; } @@ -865,64 +868,6 @@ 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; @@ -948,20 +893,9 @@ static __init int svm_hardware_setup(void) kvm_enable_efer_bits(EFER_FFXSR); if (boot_cpu_has(X86_FEATURE_TSCRATEMSR)) { - u64 max; - kvm_has_tsc_control = true; - - /* - * Make sure the user can only configure tsc_khz values that - * fit into a signed integer. - * A min value is not calculated needed because it will always - * be 1 on all machines and a value of 0 is used to disable - * tsc-scaling for the vcpu. - */ - max = min(0x7fffffffULL, __scale_tsc(tsc_khz, TSC_RATIO_MAX)); - - kvm_max_guest_tsc_khz = max; + kvm_max_tsc_scaling_ratio = TSC_RATIO_MAX; + kvm_tsc_scaling_ratio_frac_bits = 32; } if (nested) { @@ -989,7 +923,6 @@ static __init int svm_hardware_setup(void) } else kvm_disable_tdp(); - build_mtrr2protval(); return 0; err: @@ -1026,68 +959,6 @@ static void init_sys_seg(struct vmcb_seg *seg, uint32_t type) seg->base = 0; } -static u64 __scale_tsc(u64 ratio, u64 tsc) -{ - u64 mult, frac, _tsc; - - mult = ratio >> 32; - frac = ratio & ((1ULL << 32) - 1); - - _tsc = tsc; - _tsc *= mult; - _tsc += (tsc >> 32) * frac; - _tsc += ((tsc & ((1ULL << 32) - 1)) * frac) >> 32; - - return _tsc; -} - -static u64 svm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc) -{ - struct vcpu_svm *svm = to_svm(vcpu); - u64 _tsc = tsc; - - if (svm->tsc_ratio != TSC_RATIO_DEFAULT) - _tsc = __scale_tsc(svm->tsc_ratio, tsc); - - return _tsc; -} - -static void svm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) -{ - struct vcpu_svm *svm = to_svm(vcpu); - u64 ratio; - u64 khz; - - /* Guest TSC same frequency as host TSC? */ - if (!scale) { - svm->tsc_ratio = TSC_RATIO_DEFAULT; - return; - } - - /* TSC scaling supported? */ - if (!boot_cpu_has(X86_FEATURE_TSCRATEMSR)) { - if (user_tsc_khz > tsc_khz) { - vcpu->arch.tsc_catchup = 1; - vcpu->arch.tsc_always_catchup = 1; - } else - WARN(1, "user requested TSC rate below hardware speed\n"); - return; - } - - khz = user_tsc_khz; - - /* TSC scaling required - calculate ratio */ - ratio = khz << 32; - do_div(ratio, tsc_khz); - - if (ratio == 0 || ratio & TSC_RATIO_RSVD) { - WARN_ONCE(1, "Invalid TSC ratio - virtual-tsc-khz=%u\n", - user_tsc_khz); - return; - } - svm->tsc_ratio = ratio; -} - static u64 svm_read_tsc_offset(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1114,16 +985,10 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) mark_dirty(svm->vmcb, VMCB_INTERCEPTS); } -static void svm_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool host) +static void svm_adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment) { struct vcpu_svm *svm = to_svm(vcpu); - if (host) { - if (svm->tsc_ratio != TSC_RATIO_DEFAULT) - WARN_ON(adjustment < 0); - adjustment = svm_scale_tsc(vcpu, (u64)adjustment); - } - svm->vmcb->control.tsc_offset += adjustment; if (is_guest_mode(vcpu)) svm->nested.hsave->control.tsc_offset += adjustment; @@ -1135,49 +1000,7 @@ static void svm_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool ho mark_dirty(svm->vmcb, VMCB_INTERCEPTS); } -static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) -{ - u64 tsc; - - tsc = svm_scale_tsc(vcpu, native_read_tsc()); - - return target_tsc - tsc; -} - -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) +static void init_vmcb(struct vcpu_svm *svm) { struct vmcb_control_area *control = &svm->vmcb->control; struct vmcb_save_area *save = &svm->vmcb->save; @@ -1198,6 +1021,8 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event) set_exception_intercept(svm, PF_VECTOR); set_exception_intercept(svm, UD_VECTOR); set_exception_intercept(svm, MC_VECTOR); + set_exception_intercept(svm, AC_VECTOR); + set_exception_intercept(svm, DB_VECTOR); set_intercept(svm, INTERCEPT_INTR); set_intercept(svm, INTERCEPT_NMI); @@ -1248,8 +1073,7 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event) init_sys_seg(&save->ldtr, SEG_TYPE_LDT); init_sys_seg(&save->tr, SEG_TYPE_BUSY_TSS16); - if (!init_event) - svm_set_efer(&svm->vcpu, 0); + svm_set_efer(&svm->vcpu, 0); save->dr6 = 0xffff0ff0; kvm_set_rflags(&svm->vcpu, 2); save->rip = 0x0000fff0; @@ -1259,7 +1083,8 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event) * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0. * It also updates the guest-visible cr0 value. */ - (void)kvm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET); + svm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET); + kvm_mmu_reset_context(&svm->vcpu); save->cr4 = X86_CR4_PAE; /* rdx = ?? */ @@ -1272,7 +1097,6 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event) clr_cr_intercept(svm, INTERCEPT_CR3_READ); clr_cr_intercept(svm, INTERCEPT_CR3_WRITE); save->g_pat = svm->vcpu.arch.pat; - svm_set_guest_pat(svm, &save->g_pat); save->cr3 = 0; save->cr4 = 0; } @@ -1303,7 +1127,7 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) if (kvm_vcpu_is_reset_bsp(&svm->vcpu)) svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP; } - init_vmcb(svm, init_event); + init_vmcb(svm); kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy); kvm_register_write(vcpu, VCPU_REGS_RDX, eax); @@ -1324,8 +1148,6 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) goto out; } - svm->tsc_ratio = TSC_RATIO_DEFAULT; - err = kvm_vcpu_init(&svm->vcpu, kvm, id); if (err) goto free_svm; @@ -1359,7 +1181,7 @@ 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, false); + init_vmcb(svm); svm_init_osvw(&svm->vcpu); @@ -1411,11 +1233,16 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); - if (static_cpu_has(X86_FEATURE_TSCRATEMSR) && - svm->tsc_ratio != __this_cpu_read(current_tsc_ratio)) { - __this_cpu_write(current_tsc_ratio, svm->tsc_ratio); - wrmsrl(MSR_AMD64_TSC_RATIO, svm->tsc_ratio); + if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) { + u64 tsc_ratio = vcpu->arch.tsc_scaling_ratio; + if (tsc_ratio != __this_cpu_read(current_tsc_ratio)) { + __this_cpu_write(current_tsc_ratio, tsc_ratio); + wrmsrl(MSR_AMD64_TSC_RATIO, tsc_ratio); + } } + /* This assumes that the kernel never uses MSR_TSC_AUX */ + if (static_cpu_has(X86_FEATURE_RDTSCP)) + wrmsrl(MSR_TSC_AUX, svm->tsc_aux); } static void svm_vcpu_put(struct kvm_vcpu *vcpu) @@ -1733,20 +1560,13 @@ static void svm_set_segment(struct kvm_vcpu *vcpu, mark_dirty(svm->vmcb, VMCB_SEG); } -static void update_db_bp_intercept(struct kvm_vcpu *vcpu) +static void update_bp_intercept(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - clr_exception_intercept(svm, DB_VECTOR); clr_exception_intercept(svm, BP_VECTOR); - if (svm->nmi_singlestep) - set_exception_intercept(svm, DB_VECTOR); - if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) { - if (vcpu->guest_debug & - (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) - set_exception_intercept(svm, DB_VECTOR); if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) set_exception_intercept(svm, BP_VECTOR); } else @@ -1852,7 +1672,6 @@ static int db_interception(struct vcpu_svm *svm) if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP)) svm->vmcb->save.rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); - update_db_bp_intercept(&svm->vcpu); } if (svm->vcpu.guest_debug & @@ -1887,6 +1706,12 @@ static int ud_interception(struct vcpu_svm *svm) return 1; } +static int ac_interception(struct vcpu_svm *svm) +{ + kvm_queue_exception_e(&svm->vcpu, AC_VECTOR, 0); + return 1; +} + static void svm_fpu_activate(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1981,7 +1806,7 @@ static int shutdown_interception(struct vcpu_svm *svm) * so reinitialize it. */ clear_page(svm->vmcb); - init_vmcb(svm, false); + init_vmcb(svm); kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; return 0; @@ -2106,6 +1931,7 @@ static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu) vcpu->arch.mmu.get_pdptr = nested_svm_get_tdp_pdptr; vcpu->arch.mmu.inject_page_fault = nested_svm_inject_npf_exit; vcpu->arch.mmu.shadow_root_level = get_npt_level(); + reset_shadow_zero_bits_mask(vcpu, &vcpu->arch.mmu); vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu; } @@ -2455,7 +2281,9 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) nested_vmcb->control.exit_info_2 = vmcb->control.exit_info_2; nested_vmcb->control.exit_int_info = vmcb->control.exit_int_info; nested_vmcb->control.exit_int_info_err = vmcb->control.exit_int_info_err; - nested_vmcb->control.next_rip = vmcb->control.next_rip; + + if (svm->nrips_enabled) + nested_vmcb->control.next_rip = vmcb->control.next_rip; /* * If we emulate a VMRUN/#VMEXIT in the same host #vmexit cycle we have @@ -3150,7 +2978,7 @@ static int cr8_write_interception(struct vcpu_svm *svm) u8 cr8_prev = kvm_get_cr8(&svm->vcpu); /* instruction emulation calls kvm_set_cr8() */ r = cr_interception(svm); - if (irqchip_in_kernel(svm->vcpu.kvm)) + if (lapic_in_kernel(&svm->vcpu)) return r; if (cr8_prev <= kvm_get_cr8(&svm->vcpu)) return r; @@ -3161,8 +2989,7 @@ static int cr8_write_interception(struct vcpu_svm *svm) static u64 svm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) { struct vmcb *vmcb = get_host_vmcb(to_svm(vcpu)); - return vmcb->control.tsc_offset + - svm_scale_tsc(vcpu, host_tsc); + return vmcb->control.tsc_offset + host_tsc; } static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) @@ -3172,7 +2999,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) switch (msr_info->index) { case MSR_IA32_TSC: { msr_info->data = svm->vmcb->control.tsc_offset + - svm_scale_tsc(vcpu, native_read_tsc()); + kvm_scale_tsc(vcpu, rdtsc()); break; } @@ -3202,6 +3029,11 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_SYSENTER_ESP: msr_info->data = svm->sysenter_esp; break; + case MSR_TSC_AUX: + if (!boot_cpu_has(X86_FEATURE_RDTSCP)) + return 1; + msr_info->data = svm->tsc_aux; + break; /* * Nobody will change the following 5 values in the VMCB so we can * safely return them on rdmsr. They will always be 0 until LBRV is @@ -3231,6 +3063,23 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_UCODE_REV: msr_info->data = 0x01000065; break; + case MSR_F15H_IC_CFG: { + + int family, model; + + family = guest_cpuid_family(vcpu); + model = guest_cpuid_model(vcpu); + + if (family < 0 || model < 0) + return kvm_get_msr_common(vcpu, msr_info); + + msr_info->data = 0; + + if (family == 0x15 && + (model >= 0x2 && model < 0x20)) + msr_info->data = 0x1E; + } + break; default: return kvm_get_msr_common(vcpu, msr_info); } @@ -3323,6 +3172,18 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) svm->sysenter_esp = data; svm->vmcb->save.sysenter_esp = data; break; + case MSR_TSC_AUX: + if (!boot_cpu_has(X86_FEATURE_RDTSCP)) + return 1; + + /* + * This is rare, so we update the MSR here instead of using + * direct_access_msrs. Doing that would require a rdmsr in + * svm_vcpu_put. + */ + svm->tsc_aux = data; + wrmsrl(MSR_TSC_AUX, svm->tsc_aux); + break; case MSR_IA32_DEBUGCTLMSR: if (!boot_cpu_has(X86_FEATURE_LBRV)) { vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTL 0x%llx, nop\n", @@ -3347,16 +3208,6 @@ 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); } @@ -3394,24 +3245,11 @@ static int msr_interception(struct vcpu_svm *svm) static int interrupt_window_interception(struct vcpu_svm *svm) { - struct kvm_run *kvm_run = svm->vcpu.run; - kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); svm_clear_vintr(svm); svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; mark_dirty(svm->vmcb, VMCB_INTR); ++svm->vcpu.stat.irq_window_exits; - /* - * If the user space waits to inject interrupts, exit as soon as - * possible - */ - if (!irqchip_in_kernel(svm->vcpu.kvm) && - kvm_run->request_interrupt_window && - !kvm_cpu_has_interrupt(&svm->vcpu)) { - kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; - return 0; - } - return 1; } @@ -3471,6 +3309,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception, [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception, [SVM_EXIT_EXCP_BASE + MC_VECTOR] = mc_interception, + [SVM_EXIT_EXCP_BASE + AC_VECTOR] = ac_interception, [SVM_EXIT_INTR] = intr_interception, [SVM_EXIT_NMI] = nmi_interception, [SVM_EXIT_SMI] = nop_on_interception, @@ -3622,6 +3461,8 @@ static int handle_exit(struct kvm_vcpu *vcpu) struct kvm_run *kvm_run = vcpu->run; u32 exit_code = svm->vmcb->control.exit_code; + trace_kvm_exit(exit_code, vcpu, KVM_ISA_SVM); + if (!is_cr_intercept(svm, INTERCEPT_CR0_WRITE)) vcpu->arch.cr0 = svm->vmcb->save.cr0; if (npt_enabled) @@ -3759,9 +3600,13 @@ static void svm_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) return; } -static int svm_vm_has_apicv(struct kvm *kvm) +static bool svm_get_enable_apicv(void) +{ + return false; +} + +static void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) { - return 0; } static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) @@ -3854,7 +3699,6 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu) */ svm->nmi_singlestep = true; svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF); - update_db_bp_intercept(vcpu); } static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr) @@ -4093,8 +3937,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; - trace_kvm_exit(svm->vmcb->control.exit_code, vcpu, KVM_ISA_SVM); - if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_before_handle_nmi(&svm->vcpu); @@ -4191,8 +4033,17 @@ static bool svm_has_high_real_mode_segbase(void) return true; } +static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) +{ + return 0; +} + static void svm_cpuid_update(struct kvm_vcpu *vcpu) { + struct vcpu_svm *svm = to_svm(vcpu); + + /* Update nrips enabled cache */ + svm->nrips_enabled = !!guest_cpuid_has_nrips(&svm->vcpu); } static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) @@ -4229,7 +4080,7 @@ static int svm_get_lpage_level(void) static bool svm_rdtscp_supported(void) { - return false; + return boot_cpu_has(X86_FEATURE_RDTSCP); } static bool svm_invpcid_supported(void) @@ -4471,7 +4322,7 @@ static struct kvm_x86_ops svm_x86_ops = { .vcpu_load = svm_vcpu_load, .vcpu_put = svm_vcpu_put, - .update_db_bp_intercept = update_db_bp_intercept, + .update_bp_intercept = update_bp_intercept, .get_msr = svm_get_msr, .set_msr = svm_set_msr, .get_segment_base = svm_get_segment_base, @@ -4520,7 +4371,8 @@ static struct kvm_x86_ops svm_x86_ops = { .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, .set_virtual_x2apic_mode = svm_set_virtual_x2apic_mode, - .vm_has_apicv = svm_vm_has_apicv, + .get_enable_apicv = svm_get_enable_apicv, + .refresh_apicv_exec_ctrl = svm_refresh_apicv_exec_ctrl, .load_eoi_exitmap = svm_load_eoi_exitmap, .sync_pir_to_irr = svm_sync_pir_to_irr, @@ -4543,11 +4395,9 @@ static struct kvm_x86_ops svm_x86_ops = { .has_wbinvd_exit = svm_has_wbinvd_exit, - .set_tsc_khz = svm_set_tsc_khz, .read_tsc_offset = svm_read_tsc_offset, .write_tsc_offset = svm_write_tsc_offset, - .adjust_tsc_offset = svm_adjust_tsc_offset, - .compute_tsc_offset = svm_compute_tsc_offset, + .adjust_tsc_offset_guest = svm_adjust_tsc_offset_guest, .read_l1_tsc = svm_read_l1_tsc, .set_tdp_cr3 = set_tdp_cr3, diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 4eae7c35ddf5..ad9f6a23f139 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -129,6 +129,24 @@ TRACE_EVENT(kvm_pio, ); /* + * Tracepoint for fast mmio. + */ +TRACE_EVENT(kvm_fast_mmio, + TP_PROTO(u64 gpa), + TP_ARGS(gpa), + + TP_STRUCT__entry( + __field(u64, gpa) + ), + + TP_fast_assign( + __entry->gpa = gpa; + ), + + TP_printk("fast mmio at gpa 0x%llx", __entry->gpa) +); + +/* * Tracepoint for cpuid. */ TRACE_EVENT(kvm_cpuid, @@ -250,7 +268,7 @@ TRACE_EVENT(kvm_inj_virq, #define kvm_trace_sym_exc \ EXS(DE), EXS(DB), EXS(BP), EXS(OF), EXS(BR), EXS(UD), EXS(NM), \ EXS(DF), EXS(TS), EXS(NP), EXS(SS), EXS(GP), EXS(PF), \ - EXS(MF), EXS(MC) + EXS(MF), EXS(AC), EXS(MC) /* * Tracepoint for kvm interrupt injection: @@ -974,6 +992,302 @@ TRACE_EVENT(kvm_enter_smm, __entry->smbase) ); +/* + * Tracepoint for VT-d posted-interrupts. + */ +TRACE_EVENT(kvm_pi_irte_update, + TP_PROTO(unsigned int vcpu_id, unsigned int gsi, + unsigned int gvec, u64 pi_desc_addr, bool set), + TP_ARGS(vcpu_id, gsi, gvec, pi_desc_addr, set), + + TP_STRUCT__entry( + __field( unsigned int, vcpu_id ) + __field( unsigned int, gsi ) + __field( unsigned int, gvec ) + __field( u64, pi_desc_addr ) + __field( bool, set ) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->gsi = gsi; + __entry->gvec = gvec; + __entry->pi_desc_addr = pi_desc_addr; + __entry->set = set; + ), + + TP_printk("VT-d PI is %s for this irq, vcpu %u, gsi: 0x%x, " + "gvec: 0x%x, pi_desc_addr: 0x%llx", + __entry->set ? "enabled and being updated" : "disabled", + __entry->vcpu_id, + __entry->gsi, + __entry->gvec, + __entry->pi_desc_addr) +); + +/* + * Tracepoint for kvm_hv_notify_acked_sint. + */ +TRACE_EVENT(kvm_hv_notify_acked_sint, + TP_PROTO(int vcpu_id, u32 sint), + TP_ARGS(vcpu_id, sint), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(u32, sint) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->sint = sint; + ), + + TP_printk("vcpu_id %d sint %u", __entry->vcpu_id, __entry->sint) +); + +/* + * Tracepoint for synic_set_irq. + */ +TRACE_EVENT(kvm_hv_synic_set_irq, + TP_PROTO(int vcpu_id, u32 sint, int vector, int ret), + TP_ARGS(vcpu_id, sint, vector, ret), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(u32, sint) + __field(int, vector) + __field(int, ret) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->sint = sint; + __entry->vector = vector; + __entry->ret = ret; + ), + + TP_printk("vcpu_id %d sint %u vector %d ret %d", + __entry->vcpu_id, __entry->sint, __entry->vector, + __entry->ret) +); + +/* + * Tracepoint for kvm_hv_synic_send_eoi. + */ +TRACE_EVENT(kvm_hv_synic_send_eoi, + TP_PROTO(int vcpu_id, int vector), + TP_ARGS(vcpu_id, vector), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(u32, sint) + __field(int, vector) + __field(int, ret) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->vector = vector; + ), + + TP_printk("vcpu_id %d vector %d", __entry->vcpu_id, __entry->vector) +); + +/* + * Tracepoint for synic_set_msr. + */ +TRACE_EVENT(kvm_hv_synic_set_msr, + TP_PROTO(int vcpu_id, u32 msr, u64 data, bool host), + TP_ARGS(vcpu_id, msr, data, host), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(u32, msr) + __field(u64, data) + __field(bool, host) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->msr = msr; + __entry->data = data; + __entry->host = host + ), + + TP_printk("vcpu_id %d msr 0x%x data 0x%llx host %d", + __entry->vcpu_id, __entry->msr, __entry->data, __entry->host) +); + +/* + * Tracepoint for stimer_set_config. + */ +TRACE_EVENT(kvm_hv_stimer_set_config, + TP_PROTO(int vcpu_id, int timer_index, u64 config, bool host), + TP_ARGS(vcpu_id, timer_index, config, host), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(int, timer_index) + __field(u64, config) + __field(bool, host) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->timer_index = timer_index; + __entry->config = config; + __entry->host = host; + ), + + TP_printk("vcpu_id %d timer %d config 0x%llx host %d", + __entry->vcpu_id, __entry->timer_index, __entry->config, + __entry->host) +); + +/* + * Tracepoint for stimer_set_count. + */ +TRACE_EVENT(kvm_hv_stimer_set_count, + TP_PROTO(int vcpu_id, int timer_index, u64 count, bool host), + TP_ARGS(vcpu_id, timer_index, count, host), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(int, timer_index) + __field(u64, count) + __field(bool, host) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->timer_index = timer_index; + __entry->count = count; + __entry->host = host; + ), + + TP_printk("vcpu_id %d timer %d count %llu host %d", + __entry->vcpu_id, __entry->timer_index, __entry->count, + __entry->host) +); + +/* + * Tracepoint for stimer_start(periodic timer case). + */ +TRACE_EVENT(kvm_hv_stimer_start_periodic, + TP_PROTO(int vcpu_id, int timer_index, u64 time_now, u64 exp_time), + TP_ARGS(vcpu_id, timer_index, time_now, exp_time), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(int, timer_index) + __field(u64, time_now) + __field(u64, exp_time) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->timer_index = timer_index; + __entry->time_now = time_now; + __entry->exp_time = exp_time; + ), + + TP_printk("vcpu_id %d timer %d time_now %llu exp_time %llu", + __entry->vcpu_id, __entry->timer_index, __entry->time_now, + __entry->exp_time) +); + +/* + * Tracepoint for stimer_start(one-shot timer case). + */ +TRACE_EVENT(kvm_hv_stimer_start_one_shot, + TP_PROTO(int vcpu_id, int timer_index, u64 time_now, u64 count), + TP_ARGS(vcpu_id, timer_index, time_now, count), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(int, timer_index) + __field(u64, time_now) + __field(u64, count) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->timer_index = timer_index; + __entry->time_now = time_now; + __entry->count = count; + ), + + TP_printk("vcpu_id %d timer %d time_now %llu count %llu", + __entry->vcpu_id, __entry->timer_index, __entry->time_now, + __entry->count) +); + +/* + * Tracepoint for stimer_timer_callback. + */ +TRACE_EVENT(kvm_hv_stimer_callback, + TP_PROTO(int vcpu_id, int timer_index), + TP_ARGS(vcpu_id, timer_index), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(int, timer_index) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->timer_index = timer_index; + ), + + TP_printk("vcpu_id %d timer %d", + __entry->vcpu_id, __entry->timer_index) +); + +/* + * Tracepoint for stimer_expiration. + */ +TRACE_EVENT(kvm_hv_stimer_expiration, + TP_PROTO(int vcpu_id, int timer_index, int msg_send_result), + TP_ARGS(vcpu_id, timer_index, msg_send_result), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(int, timer_index) + __field(int, msg_send_result) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->timer_index = timer_index; + __entry->msg_send_result = msg_send_result; + ), + + TP_printk("vcpu_id %d timer %d msg send result %d", + __entry->vcpu_id, __entry->timer_index, + __entry->msg_send_result) +); + +/* + * Tracepoint for stimer_cleanup. + */ +TRACE_EVENT(kvm_hv_stimer_cleanup, + TP_PROTO(int vcpu_id, int timer_index), + TP_ARGS(vcpu_id, timer_index), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(int, timer_index) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->timer_index = timer_index; + ), + + TP_printk("vcpu_id %d timer %d", + __entry->vcpu_id, __entry->timer_index) +); + #endif /* _TRACE_KVM_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 83b7b5cd75d5..e2951b6edbbc 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -19,6 +19,7 @@ #include "irq.h" #include "mmu.h" #include "cpuid.h" +#include "lapic.h" #include <linux/kvm_host.h> #include <linux/module.h> @@ -35,6 +36,7 @@ #include "kvm_cache_regs.h" #include "x86.h" +#include <asm/cpu.h> #include <asm/io.h> #include <asm/desc.h> #include <asm/vmx.h> @@ -45,6 +47,7 @@ #include <asm/debugreg.h> #include <asm/kexec.h> #include <asm/apic.h> +#include <asm/irq_remapping.h> #include "trace.h" #include "pmu.h" @@ -105,6 +108,8 @@ static u64 __read_mostly host_xss; static bool __read_mostly enable_pml = 1; module_param_named(pml, enable_pml, bool, S_IRUGO); +#define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL + #define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD) #define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST (X86_CR0_WP | X86_CR0_NE) #define KVM_VM_CR0_ALWAYS_ON \ @@ -424,6 +429,9 @@ struct nested_vmx { /* to migrate it to L2 if VM_ENTRY_LOAD_DEBUG_CONTROLS is off */ u64 vmcs01_debugctl; + u16 vpid02; + u16 last_vpid; + u32 nested_vmx_procbased_ctls_low; u32 nested_vmx_procbased_ctls_high; u32 nested_vmx_true_procbased_ctls_low; @@ -440,14 +448,33 @@ struct nested_vmx { u32 nested_vmx_misc_low; u32 nested_vmx_misc_high; u32 nested_vmx_ept_caps; + u32 nested_vmx_vpid_caps; }; #define POSTED_INTR_ON 0 +#define POSTED_INTR_SN 1 + /* Posted-Interrupt Descriptor */ struct pi_desc { u32 pir[8]; /* Posted interrupt requested */ - u32 control; /* bit 0 of control is outstanding notification bit */ - u32 rsvd[7]; + union { + struct { + /* bit 256 - Outstanding Notification */ + u16 on : 1, + /* bit 257 - Suppress Notification */ + sn : 1, + /* bit 271:258 - Reserved */ + rsvd_1 : 14; + /* bit 279:272 - Notification Vector */ + u8 nv; + /* bit 287:280 - Reserved */ + u8 rsvd_2; + /* bit 319:288 - Notification Destination */ + u32 ndst; + }; + u64 control; + }; + u32 rsvd[6]; } __aligned(64); static bool pi_test_and_set_on(struct pi_desc *pi_desc) @@ -467,6 +494,30 @@ static int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); } +static inline void pi_clear_sn(struct pi_desc *pi_desc) +{ + return clear_bit(POSTED_INTR_SN, + (unsigned long *)&pi_desc->control); +} + +static inline void pi_set_sn(struct pi_desc *pi_desc) +{ + return set_bit(POSTED_INTR_SN, + (unsigned long *)&pi_desc->control); +} + +static inline int pi_test_on(struct pi_desc *pi_desc) +{ + return test_bit(POSTED_INTR_ON, + (unsigned long *)&pi_desc->control); +} + +static inline int pi_test_sn(struct pi_desc *pi_desc) +{ + return test_bit(POSTED_INTR_SN, + (unsigned long *)&pi_desc->control); +} + struct vcpu_vmx { struct kvm_vcpu vcpu; unsigned long host_rsp; @@ -532,8 +583,6 @@ struct vcpu_vmx { s64 vnmi_blocked_time; u32 exit_reason; - bool rdtscp_enabled; - /* Posted interrupt descriptor */ struct pi_desc pi_desc; @@ -563,6 +612,11 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) return container_of(vcpu, struct vcpu_vmx, vcpu); } +static struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) +{ + return &(to_vmx(vcpu)->pi_desc); +} + #define VMCS12_OFFSET(x) offsetof(struct vmcs12, x) #define FIELD(number, name) [number] = VMCS12_OFFSET(name) #define FIELD64(number, name) [number] = VMCS12_OFFSET(name), \ @@ -809,7 +863,6 @@ static void kvm_cpu_vmxon(u64 addr); static void kvm_cpu_vmxoff(void); static bool vmx_mpx_supported(void); static bool vmx_xsaves_supported(void); -static int vmx_vm_has_apicv(struct kvm *kvm); static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr); static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); @@ -817,7 +870,6 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); static bool guest_state_valid(struct kvm_vcpu *vcpu); static u32 vmx_segment_access_rights(struct kvm_segment *var); -static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu); static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx); static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx); static int alloc_identity_pagetable(struct kvm *kvm); @@ -831,6 +883,13 @@ static DEFINE_PER_CPU(struct vmcs *, current_vmcs); static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu); static DEFINE_PER_CPU(struct desc_ptr, host_gdt); +/* + * We maintian a per-CPU linked-list of vCPU, so in wakeup_handler() we + * can find which vCPU should be waken up. + */ +static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu); +static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock); + static unsigned long *vmx_io_bitmap_a; static unsigned long *vmx_io_bitmap_b; static unsigned long *vmx_msr_bitmap_legacy; @@ -946,9 +1005,9 @@ static inline bool cpu_has_vmx_tpr_shadow(void) return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW; } -static inline bool vm_need_tpr_shadow(struct kvm *kvm) +static inline bool cpu_need_tpr_shadow(struct kvm_vcpu *vcpu) { - return (cpu_has_vmx_tpr_shadow()) && (irqchip_in_kernel(kvm)); + return cpu_has_vmx_tpr_shadow() && lapic_in_kernel(vcpu); } static inline bool cpu_has_secondary_exec_ctrls(void) @@ -983,7 +1042,8 @@ static inline bool cpu_has_vmx_virtual_intr_delivery(void) static inline bool cpu_has_vmx_posted_intr(void) { - return vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR; + return IS_ENABLED(CONFIG_X86_LOCAL_APIC) && + vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR; } static inline bool cpu_has_vmx_apicv(void) @@ -1062,9 +1122,9 @@ static inline bool cpu_has_vmx_ple(void) SECONDARY_EXEC_PAUSE_LOOP_EXITING; } -static inline bool vm_need_virtualize_apic_accesses(struct kvm *kvm) +static inline bool cpu_need_virtualize_apic_accesses(struct kvm_vcpu *vcpu) { - return flexpriority_enabled && irqchip_in_kernel(kvm); + return flexpriority_enabled && lapic_in_kernel(vcpu); } static inline bool cpu_has_vmx_vpid(void) @@ -1113,6 +1173,12 @@ static inline bool cpu_has_vmx_pml(void) return vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_ENABLE_PML; } +static inline bool cpu_has_vmx_tsc_scaling(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_TSC_SCALING; +} + static inline bool report_flexpriority(void) { return flexpriority_enabled; @@ -1157,6 +1223,11 @@ static inline bool nested_cpu_has_virt_x2apic_mode(struct vmcs12 *vmcs12) return nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE); } +static inline bool nested_cpu_has_vpid(struct vmcs12 *vmcs12) +{ + return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_VPID); +} + static inline bool nested_cpu_has_apic_reg_virt(struct vmcs12 *vmcs12) { return nested_cpu_has2(vmcs12, SECONDARY_EXEC_APIC_REGISTER_VIRT); @@ -1264,7 +1335,7 @@ static void vmcs_load(struct vmcs *vmcs) vmcs, phys_addr); } -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE /* * This bitmap is used to indicate whether the vmclear * operation is enabled on all cpus. All disabled by @@ -1302,7 +1373,7 @@ static void crash_vmclear_local_loaded_vmcss(void) #else static inline void crash_enable_local_vmclear(int cpu) { } static inline void crash_disable_local_vmclear(int cpu) { } -#endif /* CONFIG_KEXEC */ +#endif /* CONFIG_KEXEC_CORE */ static void __loaded_vmcs_clear(void *arg) { @@ -1337,13 +1408,13 @@ static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs) __loaded_vmcs_clear, loaded_vmcs, 1); } -static inline void vpid_sync_vcpu_single(struct vcpu_vmx *vmx) +static inline void vpid_sync_vcpu_single(int vpid) { - if (vmx->vpid == 0) + if (vpid == 0) return; if (cpu_has_vmx_invvpid_single()) - __invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vmx->vpid, 0); + __invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vpid, 0); } static inline void vpid_sync_vcpu_global(void) @@ -1352,10 +1423,10 @@ static inline void vpid_sync_vcpu_global(void) __invvpid(VMX_VPID_EXTENT_ALL_CONTEXT, 0, 0); } -static inline void vpid_sync_context(struct vcpu_vmx *vmx) +static inline void vpid_sync_context(int vpid) { if (cpu_has_vmx_invvpid_single()) - vpid_sync_vcpu_single(vmx); + vpid_sync_vcpu_single(vpid); else vpid_sync_vcpu_global(); } @@ -1376,7 +1447,51 @@ static inline void ept_sync_context(u64 eptp) } } -static __always_inline unsigned long vmcs_readl(unsigned long field) +static __always_inline void vmcs_check16(unsigned long field) +{ + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2000, + "16-bit accessor invalid for 64-bit field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001, + "16-bit accessor invalid for 64-bit high field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000, + "16-bit accessor invalid for 32-bit high field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000, + "16-bit accessor invalid for natural width field"); +} + +static __always_inline void vmcs_check32(unsigned long field) +{ + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0, + "32-bit accessor invalid for 16-bit field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000, + "32-bit accessor invalid for natural width field"); +} + +static __always_inline void vmcs_check64(unsigned long field) +{ + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0, + "64-bit accessor invalid for 16-bit field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001, + "64-bit accessor invalid for 64-bit high field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000, + "64-bit accessor invalid for 32-bit field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000, + "64-bit accessor invalid for natural width field"); +} + +static __always_inline void vmcs_checkl(unsigned long field) +{ + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0, + "Natural width accessor invalid for 16-bit field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2000, + "Natural width accessor invalid for 64-bit field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001, + "Natural width accessor invalid for 64-bit high field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000, + "Natural width accessor invalid for 32-bit field"); +} + +static __always_inline unsigned long __vmcs_readl(unsigned long field) { unsigned long value; @@ -1387,23 +1502,32 @@ static __always_inline unsigned long vmcs_readl(unsigned long field) static __always_inline u16 vmcs_read16(unsigned long field) { - return vmcs_readl(field); + vmcs_check16(field); + return __vmcs_readl(field); } static __always_inline u32 vmcs_read32(unsigned long field) { - return vmcs_readl(field); + vmcs_check32(field); + return __vmcs_readl(field); } static __always_inline u64 vmcs_read64(unsigned long field) { + vmcs_check64(field); #ifdef CONFIG_X86_64 - return vmcs_readl(field); + return __vmcs_readl(field); #else - return vmcs_readl(field) | ((u64)vmcs_readl(field+1) << 32); + return __vmcs_readl(field) | ((u64)__vmcs_readl(field+1) << 32); #endif } +static __always_inline unsigned long vmcs_readl(unsigned long field) +{ + vmcs_checkl(field); + return __vmcs_readl(field); +} + static noinline void vmwrite_error(unsigned long field, unsigned long value) { printk(KERN_ERR "vmwrite error: reg %lx value %lx (err %d)\n", @@ -1411,7 +1535,7 @@ static noinline void vmwrite_error(unsigned long field, unsigned long value) dump_stack(); } -static void vmcs_writel(unsigned long field, unsigned long value) +static __always_inline void __vmcs_writel(unsigned long field, unsigned long value) { u8 error; @@ -1421,33 +1545,46 @@ static void vmcs_writel(unsigned long field, unsigned long value) vmwrite_error(field, value); } -static void vmcs_write16(unsigned long field, u16 value) +static __always_inline void vmcs_write16(unsigned long field, u16 value) { - vmcs_writel(field, value); + vmcs_check16(field); + __vmcs_writel(field, value); } -static void vmcs_write32(unsigned long field, u32 value) +static __always_inline void vmcs_write32(unsigned long field, u32 value) { - vmcs_writel(field, value); + vmcs_check32(field); + __vmcs_writel(field, value); } -static void vmcs_write64(unsigned long field, u64 value) +static __always_inline void vmcs_write64(unsigned long field, u64 value) { - vmcs_writel(field, value); + vmcs_check64(field); + __vmcs_writel(field, value); #ifndef CONFIG_X86_64 asm volatile (""); - vmcs_writel(field+1, value >> 32); + __vmcs_writel(field+1, value >> 32); #endif } -static void vmcs_clear_bits(unsigned long field, u32 mask) +static __always_inline void vmcs_writel(unsigned long field, unsigned long value) { - vmcs_writel(field, vmcs_readl(field) & ~mask); + vmcs_checkl(field); + __vmcs_writel(field, value); } -static void vmcs_set_bits(unsigned long field, u32 mask) +static __always_inline void vmcs_clear_bits(unsigned long field, u32 mask) { - vmcs_writel(field, vmcs_readl(field) | mask); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x2000, + "vmcs_clear_bits does not support 64-bit fields"); + __vmcs_writel(field, __vmcs_readl(field) & ~mask); +} + +static __always_inline void vmcs_set_bits(unsigned long field, u32 mask) +{ + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x2000, + "vmcs_set_bits does not support 64-bit fields"); + __vmcs_writel(field, __vmcs_readl(field) | mask); } static inline void vm_entry_controls_init(struct vcpu_vmx *vmx, u32 val) @@ -1567,7 +1704,7 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) u32 eb; eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) | - (1u << NM_VECTOR) | (1u << DB_VECTOR); + (1u << NM_VECTOR) | (1u << DB_VECTOR) | (1u << AC_VECTOR); if ((vcpu->guest_debug & (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) == (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) @@ -1895,6 +2032,52 @@ static void vmx_load_host_state(struct vcpu_vmx *vmx) preempt_enable(); } +static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) +{ + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + struct pi_desc old, new; + unsigned int dest; + + if (!kvm_arch_has_assigned_device(vcpu->kvm) || + !irq_remapping_cap(IRQ_POSTING_CAP)) + return; + + do { + old.control = new.control = pi_desc->control; + + /* + * If 'nv' field is POSTED_INTR_WAKEUP_VECTOR, there + * are two possible cases: + * 1. After running 'pre_block', context switch + * happened. For this case, 'sn' was set in + * vmx_vcpu_put(), so we need to clear it here. + * 2. After running 'pre_block', we were blocked, + * and woken up by some other guy. For this case, + * we don't need to do anything, 'pi_post_block' + * will do everything for us. However, we cannot + * check whether it is case #1 or case #2 here + * (maybe, not needed), so we also clear sn here, + * I think it is not a big deal. + */ + if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR) { + if (vcpu->cpu != cpu) { + dest = cpu_physical_id(cpu); + + if (x2apic_enabled()) + new.ndst = dest; + else + new.ndst = (dest << 8) & 0xFF00; + } + + /* set 'NV' to 'notification vector' */ + new.nv = POSTED_INTR_VECTOR; + } + + /* Allow posting non-urgent interrupts */ + new.sn = 0; + } while (cmpxchg(&pi_desc->control, old.control, + new.control) != old.control); +} /* * Switches to specified vcpu, until a matching vcpu_put(), but assumes * vcpu mutex is already taken. @@ -1943,12 +2126,35 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ + + /* Setup TSC multiplier */ + if (cpu_has_vmx_tsc_scaling()) + vmcs_write64(TSC_MULTIPLIER, + vcpu->arch.tsc_scaling_ratio); + vmx->loaded_vmcs->cpu = cpu; } + + vmx_vcpu_pi_load(vcpu, cpu); +} + +static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu) +{ + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + + if (!kvm_arch_has_assigned_device(vcpu->kvm) || + !irq_remapping_cap(IRQ_POSTING_CAP)) + return; + + /* Set SN when the vCPU is preempted */ + if (vcpu->preempted) + pi_set_sn(pi_desc); } static void vmx_vcpu_put(struct kvm_vcpu *vcpu) { + vmx_vcpu_pi_put(vcpu); + __vmx_load_host_state(to_vmx(vcpu)); if (!vmm_exclusive) { __loaded_vmcs_clear(to_vmx(vcpu)->loaded_vmcs); @@ -2207,7 +2413,7 @@ static void setup_msrs(struct vcpu_vmx *vmx) if (index >= 0) move_msr_up(vmx, index, save_nmsrs++); index = __find_msr_index(vmx, MSR_TSC_AUX); - if (index >= 0 && vmx->rdtscp_enabled) + if (index >= 0 && guest_cpuid_has_rdtscp(&vmx->vcpu)) move_msr_up(vmx, index, save_nmsrs++); /* * MSR_STAR is only needed on long mode guests, and only @@ -2230,15 +2436,16 @@ static void setup_msrs(struct vcpu_vmx *vmx) /* * reads and returns guest's timestamp counter "register" - * guest_tsc = host_tsc + tsc_offset -- 21.3 + * guest_tsc = (host_tsc * tsc multiplier) >> 48 + tsc_offset + * -- Intel TSC Scaling for Virtualization White Paper, sec 1.3 */ -static u64 guest_read_tsc(void) +static u64 guest_read_tsc(struct kvm_vcpu *vcpu) { u64 host_tsc, tsc_offset; - rdtscll(host_tsc); + host_tsc = rdtsc(); tsc_offset = vmcs_read64(TSC_OFFSET); - return host_tsc + tsc_offset; + return kvm_scale_tsc(vcpu, host_tsc) + tsc_offset; } /* @@ -2255,22 +2462,6 @@ static u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) return host_tsc + tsc_offset; } -/* - * Engage any workarounds for mis-matched TSC rates. Currently limited to - * software catchup for faster rates on slower CPUs. - */ -static void vmx_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) -{ - if (!scale) - return; - - if (user_tsc_khz > tsc_khz) { - vcpu->arch.tsc_catchup = 1; - vcpu->arch.tsc_always_catchup = 1; - } else - WARN(1, "user requested TSC rate below hardware speed\n"); -} - static u64 vmx_read_tsc_offset(struct kvm_vcpu *vcpu) { return vmcs_read64(TSC_OFFSET); @@ -2302,7 +2493,7 @@ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) } } -static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool host) +static void vmx_adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment) { u64 offset = vmcs_read64(TSC_OFFSET); @@ -2315,11 +2506,6 @@ static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool ho offset + adjustment); } -static u64 vmx_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) -{ - return target_tsc - native_read_tsc(); -} - static bool guest_cpuid_has_vmx(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best = kvm_find_cpuid_entry(vcpu, 1, 0); @@ -2377,7 +2563,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) vmx->nested.nested_vmx_pinbased_ctls_high |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | PIN_BASED_VMX_PREEMPTION_TIMER; - if (vmx_vm_has_apicv(vmx->vcpu.kvm)) + if (kvm_vcpu_apicv_active(&vmx->vcpu)) vmx->nested.nested_vmx_pinbased_ctls_high |= PIN_BASED_POSTED_INTR; @@ -2443,10 +2629,10 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) CPU_BASED_CR8_LOAD_EXITING | CPU_BASED_CR8_STORE_EXITING | #endif CPU_BASED_MOV_DR_EXITING | CPU_BASED_UNCOND_IO_EXITING | - CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_EXITING | - CPU_BASED_RDPMC_EXITING | CPU_BASED_RDTSC_EXITING | - CPU_BASED_PAUSE_EXITING | CPU_BASED_TPR_SHADOW | - CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; + CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_TRAP_FLAG | + CPU_BASED_MONITOR_EXITING | CPU_BASED_RDPMC_EXITING | + CPU_BASED_RDTSC_EXITING | CPU_BASED_PAUSE_EXITING | + CPU_BASED_TPR_SHADOW | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; /* * We can allow some features even when not supported by the * hardware. For example, L1 can specify an MSR bitmap - and we @@ -2471,10 +2657,12 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | + SECONDARY_EXEC_ENABLE_VPID | SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_WBINVD_EXITING | - SECONDARY_EXEC_XSAVES; + SECONDARY_EXEC_XSAVES | + SECONDARY_EXEC_PCOMMIT; if (enable_ept) { /* nested EPT: emulate EPT also to L1 */ @@ -2493,6 +2681,12 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) } else vmx->nested.nested_vmx_ept_caps = 0; + if (enable_vpid) + vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT | + VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT; + else + vmx->nested.nested_vmx_vpid_caps = 0; + if (enable_unrestricted_guest) vmx->nested.nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_UNRESTRICTED_GUEST; @@ -2608,7 +2802,8 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) break; case MSR_IA32_VMX_EPT_VPID_CAP: /* Currently, no nested vpid support */ - *pdata = vmx->nested.nested_vmx_ept_caps; + *pdata = vmx->nested.nested_vmx_ept_caps | + ((u64)vmx->nested.nested_vmx_vpid_caps << 32); break; default: return 1; @@ -2642,7 +2837,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_EFER: return kvm_get_msr_common(vcpu, msr_info); case MSR_IA32_TSC: - msr_info->data = guest_read_tsc(); + msr_info->data = guest_read_tsc(vcpu); break; case MSR_IA32_SYSENTER_CS: msr_info->data = vmcs_read32(GUEST_SYSENTER_CS); @@ -2673,7 +2868,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.ia32_xss; break; case MSR_TSC_AUX: - if (!to_vmx(vcpu)->rdtscp_enabled) + if (!guest_cpuid_has_rdtscp(vcpu) && !msr_info->host_initiated) return 1; /* Otherwise falls through */ default: @@ -2779,7 +2974,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) clear_atomic_switch_msr(vmx, MSR_IA32_XSS); break; case MSR_TSC_AUX: - if (!vmx->rdtscp_enabled) + if (!guest_cpuid_has_rdtscp(vcpu) && !msr_info->host_initiated) return 1; /* Check reserved bit, higher 32 bits should be zero */ if ((data >> 32) != 0) @@ -2874,6 +3069,8 @@ static int hardware_enable(void) return -EBUSY; INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu)); + INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu)); + spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); /* * Now we can enable the vmclear operation in kdump @@ -3015,7 +3212,9 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_SHADOW_VMCS | SECONDARY_EXEC_XSAVES | - SECONDARY_EXEC_ENABLE_PML; + SECONDARY_EXEC_ENABLE_PML | + SECONDARY_EXEC_PCOMMIT | + SECONDARY_EXEC_TSC_SCALING; if (adjust_vmx_controls(min2, opt2, MSR_IA32_VMX_PROCBASED_CTLS2, &_cpu_based_2nd_exec_control) < 0) @@ -3150,7 +3349,7 @@ static struct vmcs *alloc_vmcs_cpu(int cpu) struct page *pages; struct vmcs *vmcs; - pages = alloc_pages_exact_node(node, GFP_KERNEL, vmcs_config.order); + pages = __alloc_pages_node(node, GFP_KERNEL, vmcs_config.order); if (!pages) return NULL; vmcs = page_address(pages); @@ -3423,12 +3622,12 @@ static void enter_lmode(struct kvm_vcpu *vcpu) vmx_segment_cache_clear(to_vmx(vcpu)); guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES); - if ((guest_tr_ar & AR_TYPE_MASK) != AR_TYPE_BUSY_64_TSS) { + if ((guest_tr_ar & VMX_AR_TYPE_MASK) != VMX_AR_TYPE_BUSY_64_TSS) { pr_debug_ratelimited("%s: tss fixup for long mode. \n", __func__); vmcs_write32(GUEST_TR_AR_BYTES, - (guest_tr_ar & ~AR_TYPE_MASK) - | AR_TYPE_BUSY_64_TSS); + (guest_tr_ar & ~VMX_AR_TYPE_MASK) + | VMX_AR_TYPE_BUSY_64_TSS); } vmx_set_efer(vcpu, vcpu->arch.efer | EFER_LMA); } @@ -3441,9 +3640,9 @@ static void exit_lmode(struct kvm_vcpu *vcpu) #endif -static void vmx_flush_tlb(struct kvm_vcpu *vcpu) +static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid) { - vpid_sync_context(to_vmx(vcpu)); + vpid_sync_context(vpid); if (enable_ept) { if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) return; @@ -3451,6 +3650,11 @@ static void vmx_flush_tlb(struct kvm_vcpu *vcpu) } } +static void vmx_flush_tlb(struct kvm_vcpu *vcpu) +{ + __vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid); +} + static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) { ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits; @@ -3644,20 +3848,21 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (!is_paging(vcpu)) { hw_cr4 &= ~X86_CR4_PAE; hw_cr4 |= X86_CR4_PSE; - /* - * SMEP/SMAP is disabled if CPU is in non-paging mode - * in hardware. However KVM always uses paging mode to - * emulate guest non-paging mode with TDP. - * To emulate this behavior, SMEP/SMAP needs to be - * manually disabled when guest switches to non-paging - * mode. - */ - hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP); } else if (!(cr4 & X86_CR4_PAE)) { hw_cr4 &= ~X86_CR4_PAE; } } + if (!enable_unrestricted_guest && !is_paging(vcpu)) + /* + * SMEP/SMAP is disabled if CPU is in non-paging mode in + * hardware. However KVM always uses paging mode without + * unrestricted guest. + * To emulate this behavior, SMEP/SMAP needs to be manually + * disabled when guest switches to non-paging mode. + */ + hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP); + vmcs_writel(CR4_READ_SHADOW, cr4); vmcs_writel(GUEST_CR4, hw_cr4); return 0; @@ -3719,7 +3924,7 @@ static int vmx_get_cpl(struct kvm_vcpu *vcpu) return 0; else { int ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS); - return AR_DPL(ar); + return VMX_AR_DPL(ar); } } @@ -3847,11 +4052,11 @@ static bool code_segment_valid(struct kvm_vcpu *vcpu) if (cs.unusable) return false; - if (~cs.type & (AR_TYPE_CODE_MASK|AR_TYPE_ACCESSES_MASK)) + if (~cs.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_ACCESSES_MASK)) return false; if (!cs.s) return false; - if (cs.type & AR_TYPE_WRITEABLE_MASK) { + if (cs.type & VMX_AR_TYPE_WRITEABLE_MASK) { if (cs.dpl > cs_rpl) return false; } else { @@ -3901,7 +4106,7 @@ static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg) return false; if (!var.present) return false; - if (~var.type & (AR_TYPE_CODE_MASK|AR_TYPE_WRITEABLE_MASK)) { + if (~var.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_WRITEABLE_MASK)) { if (var.dpl < rpl) /* DPL < RPL */ return false; } @@ -4046,7 +4251,7 @@ out: static int init_rmode_identity_map(struct kvm *kvm) { int i, idx, r = 0; - pfn_t identity_map_pfn; + kvm_pfn_t identity_map_pfn; u32 tmp; if (!enable_ept) @@ -4105,17 +4310,13 @@ static void seg_setup(int seg) static int alloc_apic_access_page(struct kvm *kvm) { struct page *page; - struct kvm_userspace_memory_region kvm_userspace_mem; int r = 0; mutex_lock(&kvm->slots_lock); if (kvm->arch.apic_access_page_done) goto out; - kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT; - kvm_userspace_mem.flags = 0; - kvm_userspace_mem.guest_phys_addr = APIC_DEFAULT_PHYS_BASE; - kvm_userspace_mem.memory_size = PAGE_SIZE; - r = __x86_set_memory_region(kvm, &kvm_userspace_mem); + r = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, + APIC_DEFAULT_PHYS_BASE, PAGE_SIZE); if (r) goto out; @@ -4140,44 +4341,38 @@ static int alloc_identity_pagetable(struct kvm *kvm) { /* Called with kvm->slots_lock held. */ - struct kvm_userspace_memory_region kvm_userspace_mem; int r = 0; BUG_ON(kvm->arch.ept_identity_pagetable_done); - kvm_userspace_mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT; - kvm_userspace_mem.flags = 0; - kvm_userspace_mem.guest_phys_addr = - kvm->arch.ept_identity_map_addr; - kvm_userspace_mem.memory_size = PAGE_SIZE; - r = __x86_set_memory_region(kvm, &kvm_userspace_mem); + r = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, + kvm->arch.ept_identity_map_addr, PAGE_SIZE); return r; } -static void allocate_vpid(struct vcpu_vmx *vmx) +static int allocate_vpid(void) { int vpid; - vmx->vpid = 0; if (!enable_vpid) - return; + return 0; spin_lock(&vmx_vpid_lock); vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS); - if (vpid < VMX_NR_VPIDS) { - vmx->vpid = vpid; + if (vpid < VMX_NR_VPIDS) __set_bit(vpid, vmx_vpid_bitmap); - } + else + vpid = 0; spin_unlock(&vmx_vpid_lock); + return vpid; } -static void free_vpid(struct vcpu_vmx *vmx) +static void free_vpid(int vpid) { - if (!enable_vpid) + if (!enable_vpid || vpid == 0) return; spin_lock(&vmx_vpid_lock); - if (vmx->vpid != 0) - __clear_bit(vmx->vpid, vmx_vpid_bitmap); + __clear_bit(vpid, vmx_vpid_bitmap); spin_unlock(&vmx_vpid_lock); } @@ -4332,9 +4527,9 @@ static void vmx_disable_intercept_msr_write_x2apic(u32 msr) msr, MSR_TYPE_W); } -static int vmx_vm_has_apicv(struct kvm *kvm) +static bool vmx_get_enable_apicv(void) { - return enable_apicv && irqchip_in_kernel(kvm); + return enable_apicv; } static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) @@ -4378,6 +4573,22 @@ static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu) { #ifdef CONFIG_SMP if (vcpu->mode == IN_GUEST_MODE) { + struct vcpu_vmx *vmx = to_vmx(vcpu); + + /* + * Currently, we don't support urgent interrupt, + * all interrupts are recognized as non-urgent + * interrupt, so we cannot post interrupts when + * 'SN' is set. + * + * If the vcpu is in guest mode, it means it is + * running instead of being scheduled out and + * waiting in the run queue, and that's the only + * case when 'SN' is set currently, warning if + * 'SN' is set. + */ + WARN_ON_ONCE(pi_test_sn(&vmx->pi_desc)); + apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), POSTED_INTR_VECTOR); return true; @@ -4440,11 +4651,6 @@ static void vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) kvm_apic_update_irr(vcpu, vmx->pi_desc.pir); } -static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu) -{ - return; -} - /* * Set up the vmcs's constant host-state fields, i.e., host-state fields that * will not change in the lifetime of the guest. @@ -4514,11 +4720,18 @@ static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx) { u32 pin_based_exec_ctrl = vmcs_config.pin_based_exec_ctrl; - if (!vmx_vm_has_apicv(vmx->vcpu.kvm)) + if (!kvm_vcpu_apicv_active(&vmx->vcpu)) pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR; return pin_based_exec_ctrl; } +static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, vmx_pin_based_exec_ctrl(vmx)); +} + static u32 vmx_exec_control(struct vcpu_vmx *vmx) { u32 exec_control = vmcs_config.cpu_based_exec_ctrl; @@ -4526,7 +4739,7 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx) if (vmx->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT) exec_control &= ~CPU_BASED_MOV_DR_EXITING; - if (!vm_need_tpr_shadow(vmx->vcpu.kvm)) { + if (!cpu_need_tpr_shadow(&vmx->vcpu)) { exec_control &= ~CPU_BASED_TPR_SHADOW; #ifdef CONFIG_X86_64 exec_control |= CPU_BASED_CR8_STORE_EXITING | @@ -4543,7 +4756,7 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx) static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) { u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl; - if (!vm_need_virtualize_apic_accesses(vmx->vcpu.kvm)) + if (!cpu_need_virtualize_apic_accesses(&vmx->vcpu)) exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; if (vmx->vpid == 0) exec_control &= ~SECONDARY_EXEC_ENABLE_VPID; @@ -4557,7 +4770,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST; if (!ple_gap) exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING; - if (!vmx_vm_has_apicv(vmx->vcpu.kvm)) + if (!kvm_vcpu_apicv_active(&vmx->vcpu)) exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; @@ -4567,8 +4780,12 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) a current VMCS12 */ exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS; - /* PML is enabled/disabled in creating/destorying vcpu */ - exec_control &= ~SECONDARY_EXEC_ENABLE_PML; + + if (!enable_pml) + exec_control &= ~SECONDARY_EXEC_ENABLE_PML; + + /* Currently, we allow L1 guest to directly run pcommit instruction. */ + exec_control &= ~SECONDARY_EXEC_PCOMMIT; return exec_control; } @@ -4613,12 +4830,11 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, vmx_exec_control(vmx)); - if (cpu_has_secondary_exec_ctrls()) { + if (cpu_has_secondary_exec_ctrls()) vmcs_write32(SECONDARY_VM_EXEC_CONTROL, vmx_secondary_exec_control(vmx)); - } - if (vmx_vm_has_apicv(vmx->vcpu.kvm)) { + if (kvm_vcpu_apicv_active(&vmx->vcpu)) { vmcs_write64(EOI_EXIT_BITMAP0, 0); vmcs_write64(EOI_EXIT_BITMAP1, 0); vmcs_write64(EOI_EXIT_BITMAP2, 0); @@ -4626,7 +4842,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write16(GUEST_INTR_STATUS, 0); - vmcs_write64(POSTED_INTR_NV, POSTED_INTR_VECTOR); + vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR); vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->pi_desc))); } @@ -4718,7 +4934,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) seg_setup(VCPU_SREG_CS); vmcs_write16(GUEST_CS_SELECTOR, 0xf000); - vmcs_write32(GUEST_CS_BASE, 0xffff0000); + vmcs_writel(GUEST_CS_BASE, 0xffff0000ul); seg_setup(VCPU_SREG_DS); seg_setup(VCPU_SREG_ES); @@ -4754,7 +4970,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); - vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0); + vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, 0); setup_msrs(vmx); @@ -4762,7 +4978,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) if (cpu_has_vmx_tpr_shadow() && !init_event) { vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0); - if (vm_need_tpr_shadow(vcpu->kvm)) + if (cpu_need_tpr_shadow(vcpu)) vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, __pa(vcpu->arch.apic->regs)); vmcs_write32(TPR_THRESHOLD, 0); @@ -4770,7 +4986,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); - if (vmx_vm_has_apicv(vcpu->kvm)) + if (kvm_vcpu_apicv_active(vcpu)) memset(&vmx->pi_desc, 0, sizeof(struct pi_desc)); if (vmx->vpid != 0) @@ -4780,12 +4996,11 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) 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_set_efer(vcpu, 0); vmx_fpu_activate(vcpu); update_exception_bitmap(vcpu); - vpid_sync_context(vmx); + vpid_sync_context(vmx->vpid); } /* @@ -4949,14 +5164,9 @@ static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu) static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) { int ret; - struct kvm_userspace_memory_region tss_mem = { - .slot = TSS_PRIVATE_MEMSLOT, - .guest_phys_addr = addr, - .memory_size = PAGE_SIZE * 3, - .flags = 0, - }; - ret = x86_set_memory_region(kvm, &tss_mem); + ret = x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, addr, + PAGE_SIZE * 3); if (ret) return ret; kvm->arch.tss_addr = addr; @@ -5118,6 +5328,9 @@ static int handle_exception(struct kvm_vcpu *vcpu) return handle_rmode_exception(vcpu, ex_no, error_code); switch (ex_no) { + case AC_VECTOR: + kvm_queue_exception_e(vcpu, AC_VECTOR, error_code); + return 1; case DB_VECTOR: dr6 = vmcs_readl(EXIT_QUALIFICATION); if (!(vcpu->guest_debug & @@ -5310,7 +5523,7 @@ static int handle_cr(struct kvm_vcpu *vcpu) u8 cr8 = (u8)val; err = kvm_set_cr8(vcpu, cr8); kvm_complete_insn_gp(vcpu, err); - if (irqchip_in_kernel(vcpu->kvm)) + if (lapic_in_kernel(vcpu)) return 1; if (cr8_prev <= cr8) return 1; @@ -5524,17 +5737,6 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu) kvm_make_request(KVM_REQ_EVENT, vcpu); ++vcpu->stat.irq_window_exits; - - /* - * If the user space waits to inject interrupts, exit as soon as - * possible - */ - if (!irqchip_in_kernel(vcpu->kvm) && - vcpu->run->request_interrupt_window && - !kvm_cpu_has_interrupt(vcpu)) { - vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; - return 0; - } return 1; } @@ -5759,82 +5961,19 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); } -static u64 ept_rsvd_mask(u64 spte, int level) -{ - int i; - u64 mask = 0; - - for (i = 51; i > boot_cpu_data.x86_phys_bits; i--) - mask |= (1ULL << i); - - if (level == 4) - /* bits 7:3 reserved */ - mask |= 0xf8; - else if (spte & (1ULL << 7)) - /* - * 1GB/2MB page, bits 29:12 or 20:12 reserved respectively, - * level == 1 if the hypervisor is using the ignored bit 7. - */ - mask |= (PAGE_SIZE << ((level - 1) * 9)) - PAGE_SIZE; - else if (level > 1) - /* bits 6:3 reserved */ - mask |= 0x78; - - return mask; -} - -static void ept_misconfig_inspect_spte(struct kvm_vcpu *vcpu, u64 spte, - int level) -{ - printk(KERN_ERR "%s: spte 0x%llx level %d\n", __func__, spte, level); - - /* 010b (write-only) */ - WARN_ON((spte & 0x7) == 0x2); - - /* 110b (write/execute) */ - WARN_ON((spte & 0x7) == 0x6); - - /* 100b (execute-only) and value not supported by logical processor */ - if (!cpu_has_vmx_ept_execute_only()) - WARN_ON((spte & 0x7) == 0x4); - - /* not 000b */ - if ((spte & 0x7)) { - u64 rsvd_bits = spte & ept_rsvd_mask(spte, level); - - if (rsvd_bits != 0) { - printk(KERN_ERR "%s: rsvd_bits = 0x%llx\n", - __func__, rsvd_bits); - WARN_ON(1); - } - - /* bits 5:3 are _not_ reserved for large page or leaf page */ - if ((rsvd_bits & 0x38) == 0) { - u64 ept_mem_type = (spte & 0x38) >> 3; - - if (ept_mem_type == 2 || ept_mem_type == 3 || - ept_mem_type == 7) { - printk(KERN_ERR "%s: ept_mem_type=0x%llx\n", - __func__, ept_mem_type); - WARN_ON(1); - } - } - } -} - static int handle_ept_misconfig(struct kvm_vcpu *vcpu) { - u64 sptes[4]; - int nr_sptes, i, ret; + int ret; gpa_t gpa; gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); if (!kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { skip_emulated_instruction(vcpu); + trace_kvm_fast_mmio(gpa); return 1; } - ret = handle_mmio_page_fault_common(vcpu, gpa, true); + ret = handle_mmio_page_fault(vcpu, gpa, true); if (likely(ret == RET_MMIO_PF_EMULATE)) return x86_emulate_instruction(vcpu, gpa, 0, NULL, 0) == EMULATE_DONE; @@ -5846,13 +5985,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) return 1; /* It is the real ept misconfig */ - printk(KERN_ERR "EPT: Misconfiguration.\n"); - printk(KERN_ERR "EPT: GPA: 0x%llx\n", gpa); - - nr_sptes = kvm_mmu_get_spte_hierarchy(vcpu, gpa, sptes); - - for (i = PT64_ROOT_LEVEL; i > PT64_ROOT_LEVEL - nr_sptes; --i) - ept_misconfig_inspect_spte(vcpu, sptes[i-1], i); + WARN_ON(1); vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; vcpu->run->hw.hardware_exit_reason = EXIT_REASON_EPT_MISCONFIG; @@ -5994,6 +6127,25 @@ static void update_ple_window_actual_max(void) ple_window_grow, INT_MIN); } +/* + * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR. + */ +static void wakeup_handler(void) +{ + struct kvm_vcpu *vcpu; + int cpu = smp_processor_id(); + + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); + list_for_each_entry(vcpu, &per_cpu(blocked_vcpu_on_cpu, cpu), + blocked_vcpu_list) { + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + + if (pi_test_on(pi_desc) == 1) + kvm_vcpu_kick(vcpu); + } + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); +} + static __init int hardware_setup(void) { int r = -ENOMEM, i, msr; @@ -6112,13 +6264,10 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_apicv()) enable_apicv = 0; - if (enable_apicv) - kvm_x86_ops->update_cr8_intercept = NULL; - else { - kvm_x86_ops->hwapic_irr_update = NULL; - kvm_x86_ops->hwapic_isr_update = NULL; - kvm_x86_ops->deliver_posted_interrupt = NULL; - kvm_x86_ops->sync_pir_to_irr = vmx_sync_pir_to_irr_dummy; + if (cpu_has_vmx_tsc_scaling()) { + kvm_has_tsc_control = true; + kvm_max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX; + kvm_tsc_scaling_ratio_frac_bits = 48; } vmx_disable_intercept_for_msr(MSR_FS_BASE, false); @@ -6134,6 +6283,8 @@ static __init int hardware_setup(void) memcpy(vmx_msr_bitmap_longmode_x2apic, vmx_msr_bitmap_longmode, PAGE_SIZE); + set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ + if (enable_apicv) { for (msr = 0x800; msr <= 0x8ff; msr++) vmx_disable_intercept_msr_read_x2apic(msr); @@ -6178,6 +6329,8 @@ static __init int hardware_setup(void) kvm_x86_ops->enable_log_dirty_pt_masked = NULL; } + kvm_set_posted_intr_wakeup_handler(wakeup_handler); + return alloc_kvm_area(); out8: @@ -6246,6 +6399,11 @@ static int handle_mwait(struct kvm_vcpu *vcpu) return handle_nop(vcpu); } +static int handle_monitor_trap(struct kvm_vcpu *vcpu) +{ + return 1; +} + static int handle_monitor(struct kvm_vcpu *vcpu) { printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n"); @@ -6408,8 +6566,12 @@ static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer) */ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, - u32 vmx_instruction_info, gva_t *ret) + u32 vmx_instruction_info, bool wr, gva_t *ret) { + gva_t off; + bool exn; + struct kvm_segment s; + /* * According to Vol. 3B, "Information for VM Exits Due to Instruction * Execution", on an exit, vmx_instruction_info holds most of the @@ -6434,22 +6596,63 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, /* Addr = segment_base + offset */ /* offset = base + [index * scale] + displacement */ - *ret = vmx_get_segment_base(vcpu, seg_reg); + off = exit_qualification; /* holds the displacement */ if (base_is_valid) - *ret += kvm_register_read(vcpu, base_reg); + off += kvm_register_read(vcpu, base_reg); if (index_is_valid) - *ret += kvm_register_read(vcpu, index_reg)<<scaling; - *ret += exit_qualification; /* holds the displacement */ + off += kvm_register_read(vcpu, index_reg)<<scaling; + vmx_get_segment(vcpu, &s, seg_reg); + *ret = s.base + off; if (addr_size == 1) /* 32 bit */ *ret &= 0xffffffff; - /* - * TODO: throw #GP (and return 1) in various cases that the VM* - * instructions require it - e.g., offset beyond segment limit, - * unusable or unreadable/unwritable segment, non-canonical 64-bit - * address, and so on. Currently these are not checked. - */ + /* Checks for #GP/#SS exceptions. */ + exn = false; + if (is_protmode(vcpu)) { + /* Protected mode: apply checks for segment validity in the + * following order: + * - segment type check (#GP(0) may be thrown) + * - usability check (#GP(0)/#SS(0)) + * - limit check (#GP(0)/#SS(0)) + */ + if (wr) + /* #GP(0) if the destination operand is located in a + * read-only data segment or any code segment. + */ + exn = ((s.type & 0xa) == 0 || (s.type & 8)); + else + /* #GP(0) if the source operand is located in an + * execute-only code segment + */ + exn = ((s.type & 0xa) == 8); + } + if (exn) { + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return 1; + } + if (is_long_mode(vcpu)) { + /* Long mode: #GP(0)/#SS(0) if the memory address is in a + * non-canonical form. This is an only check for long mode. + */ + exn = is_noncanonical_address(*ret); + } else if (is_protmode(vcpu)) { + /* Protected mode: #GP(0)/#SS(0) if the segment is unusable. + */ + exn = (s.unusable != 0); + /* Protected mode: #GP(0)/#SS(0) if the memory + * operand is outside the segment limit. + */ + exn = exn || (off + sizeof(u64) > s.limit); + } + if (exn) { + kvm_queue_exception_e(vcpu, + seg_reg == VCPU_SREG_SS ? + SS_VECTOR : GP_VECTOR, + 0); + return 1; + } + return 0; } @@ -6471,7 +6674,7 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason, int maxphyaddr = cpuid_maxphyaddr(vcpu); if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), - vmcs_read32(VMX_INSTRUCTION_INFO), &gva)) + vmcs_read32(VMX_INSTRUCTION_INFO), false, &gva)) return 1; if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr, @@ -6659,7 +6862,6 @@ static int nested_vmx_check_permission(struct kvm_vcpu *vcpu) static inline void nested_release_vmcs12(struct vcpu_vmx *vmx) { - u32 exec_control; if (vmx->nested.current_vmptr == -1ull) return; @@ -6672,9 +6874,8 @@ static inline void nested_release_vmcs12(struct vcpu_vmx *vmx) they were modified */ copy_shadow_to_vmcs12(vmx); vmx->nested.sync_shadow_vmcs = false; - exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); - exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS; - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); + vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, + SECONDARY_EXEC_SHADOW_VMCS); vmcs_write64(VMCS_LINK_POINTER, -1ull); } vmx->nested.posted_intr_nv = -1; @@ -6694,6 +6895,7 @@ static void free_nested(struct vcpu_vmx *vmx) return; vmx->nested.vmxon = false; + free_vpid(vmx->nested.vpid02); nested_release_vmcs12(vmx); if (enable_shadow_vmcs) free_vmcs(vmx->nested.current_shadow_vmcs); @@ -6999,7 +7201,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu) field_value); } else { if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, &gva)) + vmx_instruction_info, true, &gva)) return 1; /* _system ok, as nested_vmx_check_permission verified cpl=0 */ kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, gva, @@ -7036,7 +7238,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) (((vmx_instruction_info) >> 3) & 0xf)); else { if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, &gva)) + vmx_instruction_info, false, &gva)) return 1; if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &field_value, (is_64_bit_mode(vcpu) ? 8 : 4), &e)) { @@ -7070,7 +7272,6 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); gpa_t vmptr; - u32 exec_control; if (!nested_vmx_check_permission(vcpu)) return 1; @@ -7102,9 +7303,8 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) vmx->nested.current_vmcs12 = new_vmcs12; vmx->nested.current_vmcs12_page = page; if (enable_shadow_vmcs) { - exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); - exec_control |= SECONDARY_EXEC_SHADOW_VMCS; - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); + vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, + SECONDARY_EXEC_SHADOW_VMCS); vmcs_write64(VMCS_LINK_POINTER, __pa(vmx->nested.current_shadow_vmcs)); vmx->nested.sync_shadow_vmcs = true; @@ -7128,7 +7328,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu) return 1; if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, &vmcs_gva)) + vmx_instruction_info, true, &vmcs_gva)) return 1; /* ok to use *_system, as nested_vmx_check_permission verified cpl=0 */ if (kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, vmcs_gva, @@ -7184,7 +7384,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) * operand is read even if it isn't needed (e.g., for type==global) */ if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), - vmx_instruction_info, &gva)) + vmx_instruction_info, false, &gva)) return 1; if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand, sizeof(operand), &e)) { @@ -7210,7 +7410,58 @@ static int handle_invept(struct kvm_vcpu *vcpu) static int handle_invvpid(struct kvm_vcpu *vcpu) { - kvm_queue_exception(vcpu, UD_VECTOR); + struct vcpu_vmx *vmx = to_vmx(vcpu); + u32 vmx_instruction_info; + unsigned long type, types; + gva_t gva; + struct x86_exception e; + int vpid; + + if (!(vmx->nested.nested_vmx_secondary_ctls_high & + SECONDARY_EXEC_ENABLE_VPID) || + !(vmx->nested.nested_vmx_vpid_caps & VMX_VPID_INVVPID_BIT)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + + if (!nested_vmx_check_permission(vcpu)) + return 1; + + vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); + type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf); + + types = (vmx->nested.nested_vmx_vpid_caps >> 8) & 0x7; + + if (!(types & (1UL << type))) { + nested_vmx_failValid(vcpu, + VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + return 1; + } + + /* according to the intel vmx instruction reference, the memory + * operand is read even if it isn't needed (e.g., for type==global) + */ + if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), + vmx_instruction_info, false, &gva)) + return 1; + if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vpid, + sizeof(u32), &e)) { + kvm_inject_page_fault(vcpu, &e); + return 1; + } + + switch (type) { + case VMX_VPID_EXTENT_ALL_CONTEXT: + __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02); + nested_vmx_succeed(vcpu); + break; + default: + /* Trap single context invalidation invvpid calls */ + BUG_ON(1); + break; + } + + skip_emulated_instruction(vcpu); return 1; } @@ -7239,6 +7490,13 @@ static int handle_pml_full(struct kvm_vcpu *vcpu) return 1; } +static int handle_pcommit(struct kvm_vcpu *vcpu) +{ + /* we never catch pcommit instruct for L1 guest. */ + WARN_ON(1); + return 1; +} + /* * The exit handlers return 1 if the exit was handled fully and guest execution * may resume. Otherwise they set the kvm_run parameter to indicate what needs @@ -7282,12 +7540,14 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig, [EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause, [EXIT_REASON_MWAIT_INSTRUCTION] = handle_mwait, + [EXIT_REASON_MONITOR_TRAP_FLAG] = handle_monitor_trap, [EXIT_REASON_MONITOR_INSTRUCTION] = handle_monitor, [EXIT_REASON_INVEPT] = handle_invept, [EXIT_REASON_INVVPID] = handle_invvpid, [EXIT_REASON_XSAVES] = handle_xsaves, [EXIT_REASON_XRSTORS] = handle_xrstors, [EXIT_REASON_PML_FULL] = handle_pml_full, + [EXIT_REASON_PCOMMIT] = handle_pcommit, }; static const int kvm_vmx_max_exit_handlers = @@ -7542,6 +7802,8 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) return true; case EXIT_REASON_MWAIT_INSTRUCTION: return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING); + case EXIT_REASON_MONITOR_TRAP_FLAG: + return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_TRAP_FLAG); case EXIT_REASON_MONITOR_INSTRUCTION: return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_EXITING); case EXIT_REASON_PAUSE_INSTRUCTION: @@ -7587,6 +7849,8 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) * the XSS exit bitmap in vmcs12. */ return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES); + case EXIT_REASON_PCOMMIT: + return nested_cpu_has2(vmcs12, SECONDARY_EXEC_PCOMMIT); default: return true; } @@ -7598,10 +7862,9 @@ static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2) *info2 = vmcs_read32(VM_EXIT_INTR_INFO); } -static int vmx_enable_pml(struct vcpu_vmx *vmx) +static int vmx_create_pml_buffer(struct vcpu_vmx *vmx) { struct page *pml_pg; - u32 exec_control; pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!pml_pg) @@ -7612,24 +7875,15 @@ static int vmx_enable_pml(struct vcpu_vmx *vmx) vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg)); vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); - exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); - exec_control |= SECONDARY_EXEC_ENABLE_PML; - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); - return 0; } -static void vmx_disable_pml(struct vcpu_vmx *vmx) +static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx) { - u32 exec_control; - - ASSERT(vmx->pml_pg); - __free_page(vmx->pml_pg); - vmx->pml_pg = NULL; - - exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); - exec_control &= ~SECONDARY_EXEC_ENABLE_PML; - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); + if (vmx->pml_pg) { + __free_page(vmx->pml_pg); + vmx->pml_pg = NULL; + } } static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu) @@ -7705,7 +7959,7 @@ static void dump_vmcs(void) 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); + u64 efer = vmcs_read64(GUEST_IA32_EFER); int i, n; if (cpu_has_secondary_exec_ctrls()) @@ -7721,10 +7975,10 @@ static void dump_vmcs(void) 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("PDPTR0 = 0x%016llx PDPTR1 = 0x%016llx\n", + vmcs_read64(GUEST_PDPTR0), vmcs_read64(GUEST_PDPTR1)); + pr_err("PDPTR2 = 0x%016llx PDPTR3 = 0x%016llx\n", + vmcs_read64(GUEST_PDPTR2), vmcs_read64(GUEST_PDPTR3)); } pr_err("RSP = 0x%016lx RIP = 0x%016lx\n", vmcs_readl(GUEST_RSP), vmcs_readl(GUEST_RIP)); @@ -7745,16 +7999,16 @@ static void dump_vmcs(void) 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), + pr_err("EFER = 0x%016llx PAT = 0x%016llx\n", + efer, vmcs_read64(GUEST_IA32_PAT)); + pr_err("DebugCtl = 0x%016llx DebugExceptions = 0x%016lx\n", + vmcs_read64(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)); + pr_err("PerfGlobCtl = 0x%016llx\n", + vmcs_read64(GUEST_IA32_PERF_GLOBAL_CTRL)); if (vmentry_ctl & VM_ENTRY_LOAD_BNDCFGS) - pr_err("BndCfgS = 0x%016lx\n", vmcs_readl(GUEST_BNDCFGS)); + pr_err("BndCfgS = 0x%016llx\n", vmcs_read64(GUEST_BNDCFGS)); pr_err("Interruptibility = %08x ActivityState = %08x\n", vmcs_read32(GUEST_INTERRUPTIBILITY_INFO), vmcs_read32(GUEST_ACTIVITY_STATE)); @@ -7783,11 +8037,12 @@ static void dump_vmcs(void) 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)); + pr_err("EFER = 0x%016llx PAT = 0x%016llx\n", + vmcs_read64(HOST_IA32_EFER), + vmcs_read64(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("PerfGlobCtl = 0x%016llx\n", + vmcs_read64(HOST_IA32_PERF_GLOBAL_CTRL)); pr_err("*** Control State ***\n"); pr_err("PinBased=%08x CPUBased=%08x SecondaryExec=%08x\n", @@ -7810,13 +8065,16 @@ static void dump_vmcs(void) 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)); + pr_err("TSC Offset = 0x%016llx\n", vmcs_read64(TSC_OFFSET)); + if (secondary_exec_control & SECONDARY_EXEC_TSC_SCALING) + pr_err("TSC Multiplier = 0x%016llx\n", + vmcs_read64(TSC_MULTIPLIER)); 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)); + pr_err("EPT pointer = 0x%016llx\n", vmcs_read64(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", @@ -7843,6 +8101,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) u32 exit_reason = vmx->exit_reason; u32 vectoring_info = vmx->idt_vectoring_info; + trace_kvm_exit(exit_reason, vcpu, KVM_ISA_VMX); + /* * Flush logged GPAs PML buffer, this will make dirty_bitmap more * updated. Another good is, in kvm_vm_ioctl_get_dirty_log, before @@ -7953,10 +8213,10 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) * apicv */ if (!cpu_has_vmx_virtualize_x2apic_mode() || - !vmx_vm_has_apicv(vcpu->kvm)) + !kvm_vcpu_apicv_active(vcpu)) return; - if (!vm_need_tpr_shadow(vcpu->kvm)) + if (!cpu_need_tpr_shadow(vcpu)) return; sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); @@ -8060,7 +8320,7 @@ static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) { - if (!vmx_vm_has_apicv(vcpu->kvm)) + if (!kvm_vcpu_apicv_active(vcpu)) return; vmcs_write64(EOI_EXIT_BITMAP0, eoi_exit_bitmap[0]); @@ -8468,7 +8728,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->launched = 1; vmx->exit_reason = vmcs_read32(VM_EXIT_REASON); - trace_kvm_exit(vmx->exit_reason, vcpu, KVM_ISA_VMX); /* * the KVM_REQ_EVENT optimization bit is only on for one entry, and if @@ -8506,8 +8765,8 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); if (enable_pml) - vmx_disable_pml(vmx); - free_vpid(vmx); + vmx_destroy_pml_buffer(vmx); + free_vpid(vmx->vpid); leave_guest_mode(vcpu); vmx_load_vmcs01(vcpu); free_nested(vmx); @@ -8526,7 +8785,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (!vmx) return ERR_PTR(-ENOMEM); - allocate_vpid(vmx); + vmx->vpid = allocate_vpid(); err = kvm_vcpu_init(&vmx->vcpu, kvm, id); if (err) @@ -8559,7 +8818,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) put_cpu(); if (err) goto free_vmcs; - if (vm_need_virtualize_apic_accesses(kvm)) { + if (cpu_need_virtualize_apic_accesses(&vmx->vcpu)) { err = alloc_apic_access_page(kvm); if (err) goto free_vmcs; @@ -8574,8 +8833,10 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) goto free_vmcs; } - if (nested) + if (nested) { nested_vmx_setup_ctls_msrs(vmx); + vmx->nested.vpid02 = allocate_vpid(); + } vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = -1ull; @@ -8588,7 +8849,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) * for the guest, etc. */ if (enable_pml) { - err = vmx_enable_pml(vmx); + err = vmx_create_pml_buffer(vmx); if (err) goto free_vmcs; } @@ -8596,13 +8857,14 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) return &vmx->vcpu; free_vmcs: + free_vpid(vmx->nested.vpid02); free_loaded_vmcs(vmx->loaded_vmcs); free_msrs: kfree(vmx->guest_msrs); uninit_vcpu: kvm_vcpu_uninit(&vmx->vcpu); free_vcpu: - free_vpid(vmx); + free_vpid(vmx->vpid); kmem_cache_free(kvm_vcpu_cache, vmx); return ERR_PTR(err); } @@ -8632,17 +8894,22 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) u64 ipat = 0; /* For VT-d and EPT combination - * 1. MMIO: guest may want to apply WC, trust it. + * 1. MMIO: always map as UC * 2. EPT with VT-d: * a. VT-d without snooping control feature: can't guarantee the - * result, try to trust guest. So the same as item 1. + * result, try to trust guest. * 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 && !kvm_arch_has_noncoherent_dma(vcpu->kvm)) { + if (is_mmio) { + cache = MTRR_TYPE_UNCACHABLE; + goto exit; + } + + if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) { ipat = VMX_EPT_IPAT_BIT; cache = MTRR_TYPE_WRBACK; goto exit; @@ -8672,49 +8939,68 @@ static int vmx_get_lpage_level(void) return PT_PDPE_LEVEL; } +static void vmcs_set_secondary_exec_control(u32 new_ctl) +{ + /* + * These bits in the secondary execution controls field + * are dynamic, the others are mostly based on the hypervisor + * architecture and the guest's CPUID. Do not touch the + * dynamic bits. + */ + u32 mask = + SECONDARY_EXEC_SHADOW_VMCS | + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + + u32 cur_ctl = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); + + vmcs_write32(SECONDARY_VM_EXEC_CONTROL, + (new_ctl & ~mask) | (cur_ctl & mask)); +} + static void vmx_cpuid_update(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 exec_control; + u32 secondary_exec_ctl = vmx_secondary_exec_control(vmx); - vmx->rdtscp_enabled = false; if (vmx_rdtscp_supported()) { - exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); - if (exec_control & SECONDARY_EXEC_RDTSCP) { - best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); - if (best && (best->edx & bit(X86_FEATURE_RDTSCP))) - vmx->rdtscp_enabled = true; - else { - exec_control &= ~SECONDARY_EXEC_RDTSCP; - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, - exec_control); - } + bool rdtscp_enabled = guest_cpuid_has_rdtscp(vcpu); + if (!rdtscp_enabled) + secondary_exec_ctl &= ~SECONDARY_EXEC_RDTSCP; + + if (nested) { + if (rdtscp_enabled) + vmx->nested.nested_vmx_secondary_ctls_high |= + SECONDARY_EXEC_RDTSCP; + else + vmx->nested.nested_vmx_secondary_ctls_high &= + ~SECONDARY_EXEC_RDTSCP; } - if (nested && !vmx->rdtscp_enabled) - vmx->nested.nested_vmx_secondary_ctls_high &= - ~SECONDARY_EXEC_RDTSCP; } /* Exposing INVPCID only when PCID is exposed */ best = kvm_find_cpuid_entry(vcpu, 0x7, 0); if (vmx_invpcid_supported() && - best && (best->ebx & bit(X86_FEATURE_INVPCID)) && - guest_cpuid_has_pcid(vcpu)) { - exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); - exec_control |= SECONDARY_EXEC_ENABLE_INVPCID; - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, - exec_control); - } else { - if (cpu_has_secondary_exec_ctrls()) { - exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); - exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID; - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, - exec_control); - } + (!best || !(best->ebx & bit(X86_FEATURE_INVPCID)) || + !guest_cpuid_has_pcid(vcpu))) { + secondary_exec_ctl &= ~SECONDARY_EXEC_ENABLE_INVPCID; + if (best) best->ebx &= ~bit(X86_FEATURE_INVPCID); } + + if (cpu_has_secondary_exec_ctrls()) + vmcs_set_secondary_exec_control(secondary_exec_ctl); + + if (static_cpu_has(X86_FEATURE_PCOMMIT) && nested) { + if (guest_cpuid_has_pcommit(vcpu)) + vmx->nested.nested_vmx_secondary_ctls_high |= + SECONDARY_EXEC_PCOMMIT; + else + vmx->nested.nested_vmx_secondary_ctls_high &= + ~SECONDARY_EXEC_PCOMMIT; + } } static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) @@ -9281,7 +9567,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) */ vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv; vmx->nested.pi_pending = false; - vmcs_write64(POSTED_INTR_NV, POSTED_INTR_VECTOR); + vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR); vmcs_write64(POSTED_INTR_DESC_ADDR, page_to_phys(vmx->nested.pi_desc_page) + (unsigned long)(vmcs12->posted_intr_desc_addr & @@ -9322,13 +9608,13 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (cpu_has_secondary_exec_ctrls()) { exec_control = vmx_secondary_exec_control(vmx); - if (!vmx->rdtscp_enabled) - exec_control &= ~SECONDARY_EXEC_RDTSCP; + /* Take the following fields only from vmcs12 */ exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | - SECONDARY_EXEC_APIC_REGISTER_VIRT); + SECONDARY_EXEC_APIC_REGISTER_VIRT | + SECONDARY_EXEC_PCOMMIT); if (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) exec_control |= vmcs12->secondary_vm_exec_control; @@ -9347,7 +9633,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs_write64(APIC_ACCESS_ADDR, page_to_phys(vmx->nested.apic_access_page)); } else if (!(nested_cpu_has_virt_x2apic_mode(vmcs12)) && - (vm_need_virtualize_apic_accesses(vmx->vcpu.kvm))) { + cpu_need_virtualize_apic_accesses(&vmx->vcpu)) { exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; kvm_vcpu_reload_apic_access_page(vcpu); @@ -9457,12 +9743,24 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (enable_vpid) { /* - * Trivially support vpid by letting L2s share their parent - * L1's vpid. TODO: move to a more elaborate solution, giving - * each L2 its own vpid and exposing the vpid feature to L1. + * There is no direct mapping between vpid02 and vpid12, the + * vpid02 is per-vCPU for L0 and reused while the value of + * vpid12 is changed w/ one invvpid during nested vmentry. + * The vpid12 is allocated by L1 for L2, so it will not + * influence global bitmap(for vpid01 and vpid02 allocation) + * even if spawn a lot of nested vCPUs. */ - vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); - vmx_flush_tlb(vcpu); + if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) { + vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02); + if (vmcs12->virtual_processor_id != vmx->nested.last_vpid) { + vmx->nested.last_vpid = vmcs12->virtual_processor_id; + __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02); + } + } else { + vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); + vmx_flush_tlb(vcpu); + } + } if (nested_cpu_has_ept(vmcs12)) { @@ -9930,7 +10228,7 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * Additionally, restore L2's PDPTR to vmcs12. */ if (enable_ept) { - vmcs12->guest_cr3 = vmcs_read64(GUEST_CR3); + vmcs12->guest_cr3 = vmcs_readl(GUEST_CR3); vmcs12->guest_pdptr0 = vmcs_read64(GUEST_PDPTR0); vmcs12->guest_pdptr1 = vmcs_read64(GUEST_PDPTR1); vmcs12->guest_pdptr2 = vmcs_read64(GUEST_PDPTR2); @@ -10302,6 +10600,201 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm, kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask); } +/* + * This routine does the following things for vCPU which is going + * to be blocked if VT-d PI is enabled. + * - Store the vCPU to the wakeup list, so when interrupts happen + * we can find the right vCPU to wake up. + * - Change the Posted-interrupt descriptor as below: + * 'NDST' <-- vcpu->pre_pcpu + * 'NV' <-- POSTED_INTR_WAKEUP_VECTOR + * - If 'ON' is set during this process, which means at least one + * interrupt is posted for this vCPU, we cannot block it, in + * this case, return 1, otherwise, return 0. + * + */ +static int vmx_pre_block(struct kvm_vcpu *vcpu) +{ + unsigned long flags; + unsigned int dest; + struct pi_desc old, new; + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + + if (!kvm_arch_has_assigned_device(vcpu->kvm) || + !irq_remapping_cap(IRQ_POSTING_CAP)) + return 0; + + vcpu->pre_pcpu = vcpu->cpu; + spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock, + vcpu->pre_pcpu), flags); + list_add_tail(&vcpu->blocked_vcpu_list, + &per_cpu(blocked_vcpu_on_cpu, + vcpu->pre_pcpu)); + spin_unlock_irqrestore(&per_cpu(blocked_vcpu_on_cpu_lock, + vcpu->pre_pcpu), flags); + + do { + old.control = new.control = pi_desc->control; + + /* + * We should not block the vCPU if + * an interrupt is posted for it. + */ + if (pi_test_on(pi_desc) == 1) { + spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock, + vcpu->pre_pcpu), flags); + list_del(&vcpu->blocked_vcpu_list); + spin_unlock_irqrestore( + &per_cpu(blocked_vcpu_on_cpu_lock, + vcpu->pre_pcpu), flags); + vcpu->pre_pcpu = -1; + + return 1; + } + + WARN((pi_desc->sn == 1), + "Warning: SN field of posted-interrupts " + "is set before blocking\n"); + + /* + * Since vCPU can be preempted during this process, + * vcpu->cpu could be different with pre_pcpu, we + * need to set pre_pcpu as the destination of wakeup + * notification event, then we can find the right vCPU + * to wakeup in wakeup handler if interrupts happen + * when the vCPU is in blocked state. + */ + dest = cpu_physical_id(vcpu->pre_pcpu); + + if (x2apic_enabled()) + new.ndst = dest; + else + new.ndst = (dest << 8) & 0xFF00; + + /* set 'NV' to 'wakeup vector' */ + new.nv = POSTED_INTR_WAKEUP_VECTOR; + } while (cmpxchg(&pi_desc->control, old.control, + new.control) != old.control); + + return 0; +} + +static void vmx_post_block(struct kvm_vcpu *vcpu) +{ + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + struct pi_desc old, new; + unsigned int dest; + unsigned long flags; + + if (!kvm_arch_has_assigned_device(vcpu->kvm) || + !irq_remapping_cap(IRQ_POSTING_CAP)) + return; + + do { + old.control = new.control = pi_desc->control; + + dest = cpu_physical_id(vcpu->cpu); + + if (x2apic_enabled()) + new.ndst = dest; + else + new.ndst = (dest << 8) & 0xFF00; + + /* Allow posting non-urgent interrupts */ + new.sn = 0; + + /* set 'NV' to 'notification vector' */ + new.nv = POSTED_INTR_VECTOR; + } while (cmpxchg(&pi_desc->control, old.control, + new.control) != old.control); + + if(vcpu->pre_pcpu != -1) { + spin_lock_irqsave( + &per_cpu(blocked_vcpu_on_cpu_lock, + vcpu->pre_pcpu), flags); + list_del(&vcpu->blocked_vcpu_list); + spin_unlock_irqrestore( + &per_cpu(blocked_vcpu_on_cpu_lock, + vcpu->pre_pcpu), flags); + vcpu->pre_pcpu = -1; + } +} + +/* + * vmx_update_pi_irte - set IRTE for Posted-Interrupts + * + * @kvm: kvm + * @host_irq: host irq of the interrupt + * @guest_irq: gsi of the interrupt + * @set: set or unset PI + * returns 0 on success, < 0 on failure + */ +static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq, + uint32_t guest_irq, bool set) +{ + struct kvm_kernel_irq_routing_entry *e; + struct kvm_irq_routing_table *irq_rt; + struct kvm_lapic_irq irq; + struct kvm_vcpu *vcpu; + struct vcpu_data vcpu_info; + int idx, ret = -EINVAL; + + if (!kvm_arch_has_assigned_device(kvm) || + !irq_remapping_cap(IRQ_POSTING_CAP)) + return 0; + + idx = srcu_read_lock(&kvm->irq_srcu); + irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); + BUG_ON(guest_irq >= irq_rt->nr_rt_entries); + + hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) { + if (e->type != KVM_IRQ_ROUTING_MSI) + continue; + /* + * VT-d PI cannot support posting multicast/broadcast + * interrupts to a vCPU, we still use interrupt remapping + * for these kind of interrupts. + * + * For lowest-priority interrupts, we only support + * those with single CPU as the destination, e.g. user + * configures the interrupts via /proc/irq or uses + * irqbalance to make the interrupts single-CPU. + * + * We will support full lowest-priority interrupt later. + */ + + kvm_set_msi_irq(e, &irq); + if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) + continue; + + vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu)); + vcpu_info.vector = irq.vector; + + trace_kvm_pi_irte_update(vcpu->vcpu_id, e->gsi, + vcpu_info.vector, vcpu_info.pi_desc_addr, set); + + if (set) + ret = irq_set_vcpu_affinity(host_irq, &vcpu_info); + else { + /* suppress notification event before unposting */ + pi_set_sn(vcpu_to_pi_desc(vcpu)); + ret = irq_set_vcpu_affinity(host_irq, NULL); + pi_clear_sn(vcpu_to_pi_desc(vcpu)); + } + + if (ret < 0) { + printk(KERN_INFO "%s: failed to update PI IRTE\n", + __func__); + goto out; + } + } + + ret = 0; +out: + srcu_read_unlock(&kvm->irq_srcu, idx); + return ret; +} + static struct kvm_x86_ops vmx_x86_ops = { .cpu_has_kvm_support = cpu_has_kvm_support, .disabled_by_bios = vmx_disabled_by_bios, @@ -10321,7 +10814,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .vcpu_load = vmx_vcpu_load, .vcpu_put = vmx_vcpu_put, - .update_db_bp_intercept = update_exception_bitmap, + .update_bp_intercept = update_exception_bitmap, .get_msr = vmx_get_msr, .set_msr = vmx_set_msr, .get_segment_base = vmx_get_segment_base, @@ -10371,7 +10864,8 @@ static struct kvm_x86_ops vmx_x86_ops = { .update_cr8_intercept = update_cr8_intercept, .set_virtual_x2apic_mode = vmx_set_virtual_x2apic_mode, .set_apic_access_page_addr = vmx_set_apic_access_page_addr, - .vm_has_apicv = vmx_vm_has_apicv, + .get_enable_apicv = vmx_get_enable_apicv, + .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, .load_eoi_exitmap = vmx_load_eoi_exitmap, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, @@ -10395,11 +10889,9 @@ static struct kvm_x86_ops vmx_x86_ops = { .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, - .set_tsc_khz = vmx_set_tsc_khz, .read_tsc_offset = vmx_read_tsc_offset, .write_tsc_offset = vmx_write_tsc_offset, - .adjust_tsc_offset = vmx_adjust_tsc_offset, - .compute_tsc_offset = vmx_compute_tsc_offset, + .adjust_tsc_offset_guest = vmx_adjust_tsc_offset_guest, .read_l1_tsc = vmx_read_l1_tsc, .set_tdp_cr3 = vmx_set_cr3, @@ -10418,7 +10910,12 @@ static struct kvm_x86_ops vmx_x86_ops = { .flush_log_dirty = vmx_flush_log_dirty, .enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked, + .pre_block = vmx_pre_block, + .post_block = vmx_post_block, + .pmu_ops = &intel_pmu_ops, + + .update_pi_irte = vmx_update_pi_irte, }; static int __init vmx_init(void) @@ -10428,7 +10925,7 @@ static int __init vmx_init(void) if (r) return r; -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE rcu_assign_pointer(crash_vmclear_loaded_vmcss, crash_vmclear_local_loaded_vmcss); #endif @@ -10438,7 +10935,7 @@ static int __init vmx_init(void) static void __exit vmx_exit(void) { -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL); synchronize_rcu(); #endif diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 8f0f6eca69da..4244c2baf57d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -29,6 +29,7 @@ #include "cpuid.h" #include "assigned-dev.h" #include "pmu.h" +#include "hyperv.h" #include <linux/clocksource.h> #include <linux/interrupt.h> @@ -50,6 +51,8 @@ #include <linux/pci.h> #include <linux/timekeeper_internal.h> #include <linux/pvclock_gtod.h> +#include <linux/kvm_irqfd.h> +#include <linux/irqbypass.h> #include <trace/events/kvm.h> #define CREATE_TRACE_POINTS @@ -63,6 +66,7 @@ #include <asm/fpu/internal.h> /* Ugh! */ #include <asm/pvclock.h> #include <asm/div64.h> +#include <asm/irq_remapping.h> #define MAX_IO_MSRS 256 #define KVM_MAX_MCE_BANKS 32 @@ -89,10 +93,10 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu); static void process_nmi(struct kvm_vcpu *vcpu); static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); -struct kvm_x86_ops *kvm_x86_ops; +struct kvm_x86_ops *kvm_x86_ops __read_mostly; EXPORT_SYMBOL_GPL(kvm_x86_ops); -static bool ignore_msrs = 0; +static bool __read_mostly ignore_msrs = 0; module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR); unsigned int min_timer_period_us = 500; @@ -101,20 +105,25 @@ 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; +bool __read_mostly kvm_has_tsc_control; EXPORT_SYMBOL_GPL(kvm_has_tsc_control); -u32 kvm_max_guest_tsc_khz; +u32 __read_mostly kvm_max_guest_tsc_khz; EXPORT_SYMBOL_GPL(kvm_max_guest_tsc_khz); +u8 __read_mostly kvm_tsc_scaling_ratio_frac_bits; +EXPORT_SYMBOL_GPL(kvm_tsc_scaling_ratio_frac_bits); +u64 __read_mostly kvm_max_tsc_scaling_ratio; +EXPORT_SYMBOL_GPL(kvm_max_tsc_scaling_ratio); +static u64 __read_mostly kvm_default_tsc_scaling_ratio; /* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */ -static u32 tsc_tolerance_ppm = 250; +static u32 __read_mostly tsc_tolerance_ppm = 250; module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); /* lapic timer advance (tscdeadline mode only) in nanoseconds */ -unsigned int lapic_timer_advance_ns = 0; +unsigned int __read_mostly lapic_timer_advance_ns = 0; module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR); -static bool backwards_tsc_observed = false; +static bool __read_mostly backwards_tsc_observed = false; #define KVM_NR_SHARED_MSRS 16 @@ -148,6 +157,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "nmi_window", VCPU_STAT(nmi_window_exits) }, { "halt_exits", VCPU_STAT(halt_exits) }, { "halt_successful_poll", VCPU_STAT(halt_successful_poll) }, + { "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) }, { "halt_wakeup", VCPU_STAT(halt_wakeup) }, { "hypercalls", VCPU_STAT(hypercalls) }, { "request_irq", VCPU_STAT(request_irq_exits) }, @@ -221,11 +231,9 @@ static void shared_msr_update(unsigned slot, u32 msr) void kvm_define_shared_msr(unsigned slot, u32 msr) { BUG_ON(slot >= KVM_NR_SHARED_MSRS); + shared_msrs_global.msrs[slot] = msr; if (slot >= shared_msrs_global.nr) shared_msrs_global.nr = slot + 1; - shared_msrs_global.msrs[slot] = msr; - /* we need ensured the shared_msr_global have been updated */ - smp_wmb(); } EXPORT_SYMBOL_GPL(kvm_define_shared_msr); @@ -526,7 +534,8 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) } for (i = 0; i < ARRAY_SIZE(pdpte); ++i) { if (is_present_gpte(pdpte[i]) && - (pdpte[i] & vcpu->arch.mmu.rsvd_bits_mask[0][2])) { + (pdpte[i] & + vcpu->arch.mmu.guest_rsvd_check.rsvd_bits_mask[0][2])) { ret = 0; goto out; } @@ -621,7 +630,9 @@ 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) + if (((cr0 ^ old_cr0) & X86_CR0_CD) && + kvm_arch_has_noncoherent_dma(vcpu->kvm) && + !kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) kvm_zap_gfn_range(vcpu->kvm, 0, ~0ULL); return 0; @@ -662,9 +673,9 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) /* Only support XCR_XFEATURE_ENABLED_MASK(xcr0) now */ if (index != XCR_XFEATURE_ENABLED_MASK) return 1; - if (!(xcr0 & XSTATE_FP)) + if (!(xcr0 & XFEATURE_MASK_FP)) return 1; - if ((xcr0 & XSTATE_YMM) && !(xcr0 & XSTATE_SSE)) + if ((xcr0 & XFEATURE_MASK_YMM) && !(xcr0 & XFEATURE_MASK_SSE)) return 1; /* @@ -672,23 +683,24 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) * saving. However, xcr0 bit 0 is always set, even if the * emulated CPU does not support XSAVE (see fx_init). */ - valid_bits = vcpu->arch.guest_supported_xcr0 | XSTATE_FP; + valid_bits = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FP; if (xcr0 & ~valid_bits) return 1; - if ((!(xcr0 & XSTATE_BNDREGS)) != (!(xcr0 & XSTATE_BNDCSR))) + if ((!(xcr0 & XFEATURE_MASK_BNDREGS)) != + (!(xcr0 & XFEATURE_MASK_BNDCSR))) return 1; - if (xcr0 & XSTATE_AVX512) { - if (!(xcr0 & XSTATE_YMM)) + if (xcr0 & XFEATURE_MASK_AVX512) { + if (!(xcr0 & XFEATURE_MASK_YMM)) return 1; - if ((xcr0 & XSTATE_AVX512) != XSTATE_AVX512) + if ((xcr0 & XFEATURE_MASK_AVX512) != XFEATURE_MASK_AVX512) return 1; } kvm_put_guest_xcr0(vcpu); vcpu->arch.xcr0 = xcr0; - if ((xcr0 ^ old_xcr0) & XSTATE_EXTEND_MASK) + if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND) kvm_update_cpuid(vcpu); return 0; } @@ -787,7 +799,7 @@ int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8) { if (cr8 & CR8_RESERVED_BITS) return 1; - if (irqchip_in_kernel(vcpu->kvm)) + if (lapic_in_kernel(vcpu)) kvm_lapic_set_tpr(vcpu, cr8); else vcpu->arch.cr8 = cr8; @@ -797,7 +809,7 @@ EXPORT_SYMBOL_GPL(kvm_set_cr8); unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu) { - if (irqchip_in_kernel(vcpu->kvm)) + if (lapic_in_kernel(vcpu)) return kvm_lapic_get_cr8(vcpu); else return vcpu->arch.cr8; @@ -939,7 +951,7 @@ static u32 msrs_to_save[] = { MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, - MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS + MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, }; static unsigned num_msrs_to_save; @@ -949,6 +961,13 @@ static u32 emulated_msrs[] = { 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_CRASH_P0, HV_X64_MSR_CRASH_P1, HV_X64_MSR_CRASH_P2, + HV_X64_MSR_CRASH_P3, HV_X64_MSR_CRASH_P4, HV_X64_MSR_CRASH_CTL, + HV_X64_MSR_RESET, + HV_X64_MSR_VP_INDEX, + HV_X64_MSR_VP_RUNTIME, + HV_X64_MSR_SCONTROL, + HV_X64_MSR_STIMER0_CONFIG, HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, MSR_KVM_PV_EOI_EN, @@ -1150,7 +1169,8 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) ++version; - kvm_write_guest(kvm, wall_clock, &version, sizeof(version)); + if (kvm_write_guest(kvm, wall_clock, &version, sizeof(version))) + return; /* * The guest calculates current wall clock time by adding @@ -1217,11 +1237,6 @@ static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz, __func__, base_khz, scaled_khz, shift, *pmultiplier); } -static inline u64 get_kernel_ns(void) -{ - return ktime_get_boot_ns(); -} - #ifdef CONFIG_X86_64 static atomic_t kvm_guest_has_master_clock = ATOMIC_INIT(0); #endif @@ -1242,14 +1257,53 @@ static u32 adjust_tsc_khz(u32 khz, s32 ppm) return v; } -static void kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz) +static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) +{ + u64 ratio; + + /* Guest TSC same frequency as host TSC? */ + if (!scale) { + vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio; + return 0; + } + + /* TSC scaling supported? */ + if (!kvm_has_tsc_control) { + if (user_tsc_khz > tsc_khz) { + vcpu->arch.tsc_catchup = 1; + vcpu->arch.tsc_always_catchup = 1; + return 0; + } else { + WARN(1, "user requested TSC rate below hardware speed\n"); + return -1; + } + } + + /* TSC scaling required - calculate ratio */ + ratio = mul_u64_u32_div(1ULL << kvm_tsc_scaling_ratio_frac_bits, + user_tsc_khz, tsc_khz); + + if (ratio == 0 || ratio >= kvm_max_tsc_scaling_ratio) { + WARN_ONCE(1, "Invalid TSC scaling ratio - virtual-tsc-khz=%u\n", + user_tsc_khz); + return -1; + } + + vcpu->arch.tsc_scaling_ratio = ratio; + return 0; +} + +static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz) { u32 thresh_lo, thresh_hi; int use_scaling = 0; /* tsc_khz can be zero if TSC calibration fails */ - if (this_tsc_khz == 0) - return; + if (this_tsc_khz == 0) { + /* set tsc_scaling_ratio to a safe value */ + vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio; + return -1; + } /* Compute a scale to convert nanoseconds in TSC cycles */ kvm_get_time_scale(this_tsc_khz, NSEC_PER_SEC / 1000, @@ -1269,7 +1323,7 @@ static void kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz) pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", this_tsc_khz, thresh_lo, thresh_hi); use_scaling = 1; } - kvm_x86_ops->set_tsc_khz(vcpu, this_tsc_khz, use_scaling); + return set_tsc_khz(vcpu, this_tsc_khz, use_scaling); } static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) @@ -1315,6 +1369,48 @@ static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset) vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset; } +/* + * Multiply tsc by a fixed point number represented by ratio. + * + * The most significant 64-N bits (mult) of ratio represent the + * integral part of the fixed point number; the remaining N bits + * (frac) represent the fractional part, ie. ratio represents a fixed + * point number (mult + frac * 2^(-N)). + * + * N equals to kvm_tsc_scaling_ratio_frac_bits. + */ +static inline u64 __scale_tsc(u64 ratio, u64 tsc) +{ + return mul_u64_u64_shr(tsc, ratio, kvm_tsc_scaling_ratio_frac_bits); +} + +u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc) +{ + u64 _tsc = tsc; + u64 ratio = vcpu->arch.tsc_scaling_ratio; + + if (ratio != kvm_default_tsc_scaling_ratio) + _tsc = __scale_tsc(ratio, tsc); + + return _tsc; +} +EXPORT_SYMBOL_GPL(kvm_scale_tsc); + +static u64 kvm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) +{ + u64 tsc; + + tsc = kvm_scale_tsc(vcpu, rdtsc()); + + return target_tsc - tsc; +} + +u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) +{ + return kvm_x86_ops->read_l1_tsc(vcpu, kvm_scale_tsc(vcpu, host_tsc)); +} +EXPORT_SYMBOL_GPL(kvm_read_l1_tsc); + void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) { struct kvm *kvm = vcpu->kvm; @@ -1326,7 +1422,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) u64 data = msr->data; raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); - offset = kvm_x86_ops->compute_tsc_offset(vcpu, data); + offset = kvm_compute_tsc_offset(vcpu, data); ns = get_kernel_ns(); elapsed = ns - kvm->arch.last_tsc_nsec; @@ -1383,7 +1479,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) } else { u64 delta = nsec_to_cycles(vcpu, elapsed); data += delta; - offset = kvm_x86_ops->compute_tsc_offset(vcpu, data); + offset = kvm_compute_tsc_offset(vcpu, data); pr_debug("kvm: adjusted tsc offset by %llu\n", delta); } matched = true; @@ -1440,24 +1536,26 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) EXPORT_SYMBOL_GPL(kvm_write_tsc); -#ifdef CONFIG_X86_64 +static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, + s64 adjustment) +{ + kvm_x86_ops->adjust_tsc_offset_guest(vcpu, adjustment); +} -static cycle_t read_tsc(void) +static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment) { - cycle_t ret; - u64 last; + if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio) + WARN_ON(adjustment < 0); + adjustment = kvm_scale_tsc(vcpu, (u64) adjustment); + kvm_x86_ops->adjust_tsc_offset_guest(vcpu, adjustment); +} - /* - * Empirically, a fence (of type that depends on the CPU) - * before rdtsc is enough to ensure that rdtsc is ordered - * with respect to loads. The various CPU manuals are unclear - * as to whether rdtsc can be reordered with later loads, - * but no one has ever seen it happen. - */ - rdtsc_barrier(); - ret = (cycle_t)vget_cycles(); +#ifdef CONFIG_X86_64 - last = pvclock_gtod_data.clock.cycle_last; +static cycle_t read_tsc(void) +{ + cycle_t ret = (cycle_t)rdtsc_ordered(); + u64 last = pvclock_gtod_data.clock.cycle_last; if (likely(ret >= last)) return ret; @@ -1588,6 +1686,11 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm) #endif } +void kvm_make_mclock_inprogress_request(struct kvm *kvm) +{ + kvm_make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS); +} + static void kvm_gen_update_masterclock(struct kvm *kvm) { #ifdef CONFIG_X86_64 @@ -1613,7 +1716,7 @@ static void kvm_gen_update_masterclock(struct kvm *kvm) static int kvm_guest_time_update(struct kvm_vcpu *v) { - unsigned long flags, this_tsc_khz; + unsigned long flags, this_tsc_khz, tgt_tsc_khz; struct kvm_vcpu_arch *vcpu = &v->arch; struct kvm_arch *ka = &v->kvm->arch; s64 kernel_ns; @@ -1646,11 +1749,11 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) return 1; } if (!use_master_clock) { - host_tsc = native_read_tsc(); + host_tsc = rdtsc(); kernel_ns = get_kernel_ns(); } - tsc_timestamp = kvm_x86_ops->read_l1_tsc(v, host_tsc); + tsc_timestamp = kvm_read_l1_tsc(v, host_tsc); /* * We may have to catch up the TSC to match elapsed wall clock @@ -1676,7 +1779,9 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) return 0; if (unlikely(vcpu->hw_tsc_khz != this_tsc_khz)) { - kvm_get_time_scale(NSEC_PER_SEC / 1000, this_tsc_khz, + tgt_tsc_khz = kvm_has_tsc_control ? + vcpu->virtual_tsc_khz : this_tsc_khz; + kvm_get_time_scale(NSEC_PER_SEC / 1000, tgt_tsc_khz, &vcpu->hv_clock.tsc_shift, &vcpu->hv_clock.tsc_to_system_mul); vcpu->hw_tsc_khz = this_tsc_khz; @@ -1722,8 +1827,6 @@ 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; @@ -1869,123 +1972,6 @@ out: return r; } -static bool kvm_hv_hypercall_enabled(struct kvm *kvm) -{ - return kvm->arch.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE; -} - -static bool kvm_hv_msr_partition_wide(u32 msr) -{ - bool r = false; - switch (msr) { - case HV_X64_MSR_GUEST_OS_ID: - case HV_X64_MSR_HYPERCALL: - case HV_X64_MSR_REFERENCE_TSC: - case HV_X64_MSR_TIME_REF_COUNT: - r = true; - break; - } - - return r; -} - -static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data) -{ - struct kvm *kvm = vcpu->kvm; - - switch (msr) { - case HV_X64_MSR_GUEST_OS_ID: - kvm->arch.hv_guest_os_id = data; - /* setting guest os id to zero disables hypercall page */ - if (!kvm->arch.hv_guest_os_id) - kvm->arch.hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE; - break; - case HV_X64_MSR_HYPERCALL: { - u64 gfn; - unsigned long addr; - u8 instructions[4]; - - /* if guest os id is not set hypercall should remain disabled */ - if (!kvm->arch.hv_guest_os_id) - break; - if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) { - kvm->arch.hv_hypercall = data; - break; - } - gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT; - addr = gfn_to_hva(kvm, gfn); - if (kvm_is_error_hva(addr)) - return 1; - kvm_x86_ops->patch_hypercall(vcpu, instructions); - ((unsigned char *)instructions)[3] = 0xc3; /* ret */ - if (__copy_to_user((void __user *)addr, instructions, 4)) - return 1; - kvm->arch.hv_hypercall = data; - mark_page_dirty(kvm, gfn); - break; - } - case HV_X64_MSR_REFERENCE_TSC: { - u64 gfn; - HV_REFERENCE_TSC_PAGE tsc_ref; - memset(&tsc_ref, 0, sizeof(tsc_ref)); - kvm->arch.hv_tsc_page = data; - if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE)) - break; - gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; - if (kvm_write_guest(kvm, gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT, - &tsc_ref, sizeof(tsc_ref))) - return 1; - mark_page_dirty(kvm, gfn); - break; - } - default: - vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x " - "data 0x%llx\n", msr, data); - return 1; - } - return 0; -} - -static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data) -{ - switch (msr) { - case HV_X64_MSR_APIC_ASSIST_PAGE: { - u64 gfn; - unsigned long addr; - - if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) { - vcpu->arch.hv_vapic = data; - if (kvm_lapic_enable_pv_eoi(vcpu, 0)) - return 1; - break; - } - gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT; - 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; - kvm_vcpu_mark_page_dirty(vcpu, gfn); - if (kvm_lapic_enable_pv_eoi(vcpu, gfn_to_gpa(gfn) | KVM_MSR_ENABLED)) - return 1; - break; - } - case HV_X64_MSR_EOI: - return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data); - case HV_X64_MSR_ICR: - return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data); - case HV_X64_MSR_TPR: - return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data); - default: - vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x " - "data 0x%llx\n", msr, data); - return 1; - } - - return 0; -} - static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) { gpa_t gpa = data & ~0x3f; @@ -2030,6 +2016,8 @@ static void accumulate_steal_time(struct kvm_vcpu *vcpu) static void record_steal_time(struct kvm_vcpu *vcpu) { + accumulate_steal_time(vcpu); + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; @@ -2138,8 +2126,6 @@ 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; @@ -2182,12 +2168,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!(data & KVM_MSR_ENABLED)) break; - vcpu->arch.st.last_steal = current->sched_info.run_delay; - - preempt_disable(); - accumulate_steal_time(vcpu); - preempt_enable(); - kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); break; @@ -2224,15 +2204,11 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) */ break; case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: - if (kvm_hv_msr_partition_wide(msr)) { - int r; - mutex_lock(&vcpu->kvm->lock); - r = set_msr_hyperv_pw(vcpu, msr, data); - mutex_unlock(&vcpu->kvm->lock); - return r; - } else - return set_msr_hyperv(vcpu, msr, data); - break; + case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: + case HV_X64_MSR_CRASH_CTL: + case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT: + return kvm_hv_set_msr_common(vcpu, msr, data, + msr_info->host_initiated); case MSR_IA32_BBL_CR_CTL3: /* Drop writes to this legacy MSR -- see rdmsr * counterpart for further detail. @@ -2315,68 +2291,6 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) return 0; } -static int get_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) -{ - u64 data = 0; - struct kvm *kvm = vcpu->kvm; - - switch (msr) { - case HV_X64_MSR_GUEST_OS_ID: - data = kvm->arch.hv_guest_os_id; - break; - case HV_X64_MSR_HYPERCALL: - data = kvm->arch.hv_hypercall; - break; - case HV_X64_MSR_TIME_REF_COUNT: { - data = - div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100); - break; - } - case HV_X64_MSR_REFERENCE_TSC: - data = kvm->arch.hv_tsc_page; - break; - default: - vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); - return 1; - } - - *pdata = data; - return 0; -} - -static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) -{ - u64 data = 0; - - switch (msr) { - case HV_X64_MSR_VP_INDEX: { - int r; - struct kvm_vcpu *v; - kvm_for_each_vcpu(r, v, vcpu->kvm) { - if (v == vcpu) { - data = r; - break; - } - } - break; - } - case HV_X64_MSR_EOI: - return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata); - case HV_X64_MSR_ICR: - return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata); - case HV_X64_MSR_TPR: - return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata); - case HV_X64_MSR_APIC_ASSIST_PAGE: - data = vcpu->arch.hv_vapic; - break; - default: - vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); - return 1; - } - *pdata = data; - return 0; -} - int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { switch (msr_info->index) { @@ -2388,6 +2302,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_LASTINTFROMIP: case MSR_IA32_LASTINTTOIP: case MSR_K8_SYSCFG: + case MSR_K8_TSEG_ADDR: + case MSR_K8_TSEG_MASK: case MSR_K7_HWCR: case MSR_VM_HSAVE_PA: case MSR_K8_INT_PENDING_MSG: @@ -2493,14 +2409,11 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = 0x20000000; break; case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: - if (kvm_hv_msr_partition_wide(msr_info->index)) { - int r; - mutex_lock(&vcpu->kvm->lock); - 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_info->index, &msr_info->data); + case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: + case HV_X64_MSR_CRASH_CTL: + case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT: + return kvm_hv_get_msr_common(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 @@ -2638,6 +2551,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV: case KVM_CAP_HYPERV_VAPIC: case KVM_CAP_HYPERV_SPIN: + case KVM_CAP_HYPERV_SYNIC: case KVM_CAP_PCI_SEGMENT: case KVM_CAP_DEBUGREGS: case KVM_CAP_X86_ROBUST_SINGLESTEP: @@ -2651,6 +2565,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_TSC_DEADLINE_TIMER: case KVM_CAP_ENABLE_CAP_VM: case KVM_CAP_DISABLE_QUIRKS: + case KVM_CAP_SET_BOOT_CPU_ID: + case KVM_CAP_SPLIT_IRQCHIP: #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT case KVM_CAP_ASSIGN_DEV_IRQ: case KVM_CAP_PCI_2_3: @@ -2788,6 +2704,11 @@ static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu) return kvm_arch_has_noncoherent_dma(vcpu->kvm); } +static inline void kvm_migrate_timers(struct kvm_vcpu *vcpu) +{ + set_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests); +} + void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { /* Address WBINVD may be executed by guest */ @@ -2810,11 +2731,11 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) { s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 : - native_read_tsc() - vcpu->arch.last_host_tsc; + rdtsc() - vcpu->arch.last_host_tsc; if (tsc_delta < 0) mark_tsc_unstable("KVM discovered backwards TSC"); if (check_tsc_unstable()) { - u64 offset = kvm_x86_ops->compute_tsc_offset(vcpu, + u64 offset = kvm_compute_tsc_offset(vcpu, vcpu->arch.last_guest_tsc); kvm_x86_ops->write_tsc_offset(vcpu, offset); vcpu->arch.tsc_catchup = 1; @@ -2830,7 +2751,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) vcpu->cpu = cpu; } - accumulate_steal_time(vcpu); kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); } @@ -2838,13 +2758,15 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { kvm_x86_ops->vcpu_put(vcpu); kvm_put_guest_fpu(vcpu); - vcpu->arch.last_host_tsc = native_read_tsc(); + vcpu->arch.last_host_tsc = rdtsc(); } static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { - kvm_x86_ops->sync_pir_to_irr(vcpu); + if (vcpu->arch.apicv_active) + kvm_x86_ops->sync_pir_to_irr(vcpu); + memcpy(s->regs, vcpu->arch.apic->regs, sizeof *s); return 0; @@ -2859,17 +2781,50 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, return 0; } +static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu) +{ + return (!lapic_in_kernel(vcpu) || + kvm_apic_accept_pic_intr(vcpu)); +} + +/* + * if userspace requested an interrupt window, check that the + * interrupt window is open. + * + * No need to exit to userspace if we already have an interrupt queued. + */ +static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu) +{ + return kvm_arch_interrupt_allowed(vcpu) && + !kvm_cpu_has_interrupt(vcpu) && + !kvm_event_needs_reinjection(vcpu) && + kvm_cpu_accept_dm_intr(vcpu); +} + static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq) { if (irq->irq >= KVM_NR_INTERRUPTS) return -EINVAL; - if (irqchip_in_kernel(vcpu->kvm)) + + if (!irqchip_in_kernel(vcpu->kvm)) { + kvm_queue_interrupt(vcpu, irq->irq, false); + kvm_make_request(KVM_REQ_EVENT, vcpu); + return 0; + } + + /* + * With in-kernel LAPIC, we only use this to inject EXTINT, so + * fail for in-kernel 8259. + */ + if (pic_in_kernel(vcpu->kvm)) return -ENXIO; - kvm_queue_interrupt(vcpu, irq->irq, false); - kvm_make_request(KVM_REQ_EVENT, vcpu); + if (vcpu->arch.pending_external_vector != -1) + return -EEXIST; + vcpu->arch.pending_external_vector = irq->irq; + kvm_make_request(KVM_REQ_EVENT, vcpu); return 0; } @@ -3108,7 +3063,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu) * Copy each region from the possibly compacted offset to the * non-compacted offset. */ - valid = xstate_bv & ~XSTATE_FPSSE; + valid = xstate_bv & ~XFEATURE_MASK_FPSSE; while (valid) { u64 feature = valid & -valid; int index = fls64(feature) - 1; @@ -3146,7 +3101,7 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) * Copy each region from the non-compacted offset to the * possibly compacted offset. */ - valid = xstate_bv & ~XSTATE_FPSSE; + valid = xstate_bv & ~XFEATURE_MASK_FPSSE; while (valid) { u64 feature = valid & -valid; int index = fls64(feature) - 1; @@ -3174,7 +3129,7 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, &vcpu->arch.guest_fpu.state.fxsave, sizeof(struct fxregs_state)); *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] = - XSTATE_FPSSE; + XFEATURE_MASK_FPSSE; } } @@ -3194,7 +3149,7 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, return -EINVAL; load_xsave(vcpu, (u8 *)guest_xsave->region); } else { - if (xstate_bv & ~XSTATE_FPSSE) + if (xstate_bv & ~XFEATURE_MASK_FPSSE) return -EINVAL; memcpy(&vcpu->arch.guest_fpu.state.fxsave, guest_xsave->region, sizeof(struct fxregs_state)); @@ -3254,6 +3209,20 @@ static int kvm_set_guest_paused(struct kvm_vcpu *vcpu) return 0; } +static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, + struct kvm_enable_cap *cap) +{ + if (cap->flags) + return -EINVAL; + + switch (cap->cap) { + case KVM_CAP_HYPERV_SYNIC: + return kvm_hv_activate_synic(vcpu); + default: + return -EINVAL; + } +} + long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -3378,7 +3347,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, struct kvm_vapic_addr va; r = -EINVAL; - if (!irqchip_in_kernel(vcpu->kvm)) + if (!lapic_in_kernel(vcpu)) goto out; r = -EFAULT; if (copy_from_user(&va, argp, sizeof va)) @@ -3505,9 +3474,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (user_tsc_khz == 0) user_tsc_khz = tsc_khz; - kvm_set_tsc_khz(vcpu, user_tsc_khz); + if (!kvm_set_tsc_khz(vcpu, user_tsc_khz)) + r = 0; - r = 0; goto out; } case KVM_GET_TSC_KHZ: { @@ -3518,6 +3487,15 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_set_guest_paused(vcpu); goto out; } + case KVM_ENABLE_CAP: { + struct kvm_enable_cap cap; + + r = -EFAULT; + if (copy_from_user(&cap, argp, sizeof(cap))) + goto out; + r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap); + break; + } default: r = -EINVAL; } @@ -3627,41 +3605,38 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps) { - int r = 0; - mutex_lock(&kvm->arch.vpit->pit_state.lock); memcpy(ps, &kvm->arch.vpit->pit_state, sizeof(struct kvm_pit_state)); mutex_unlock(&kvm->arch.vpit->pit_state.lock); - return r; + return 0; } static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps) { - int r = 0; - + int i; mutex_lock(&kvm->arch.vpit->pit_state.lock); memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state)); - kvm_pit_load_count(kvm, 0, ps->channels[0].count, 0); + for (i = 0; i < 3; i++) + kvm_pit_load_count(kvm, i, ps->channels[i].count, 0); mutex_unlock(&kvm->arch.vpit->pit_state.lock); - return r; + return 0; } static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) { - int r = 0; - mutex_lock(&kvm->arch.vpit->pit_state.lock); memcpy(ps->channels, &kvm->arch.vpit->pit_state.channels, sizeof(ps->channels)); ps->flags = kvm->arch.vpit->pit_state.flags; mutex_unlock(&kvm->arch.vpit->pit_state.lock); memset(&ps->reserved, 0, sizeof(ps->reserved)); - return r; + return 0; } static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) { - int r = 0, start = 0; + int start = 0; + int i; u32 prev_legacy, cur_legacy; mutex_lock(&kvm->arch.vpit->pit_state.lock); prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY; @@ -3671,9 +3646,11 @@ static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) memcpy(&kvm->arch.vpit->pit_state.channels, &ps->channels, sizeof(kvm->arch.vpit->pit_state.channels)); kvm->arch.vpit->pit_state.flags = ps->flags; - kvm_pit_load_count(kvm, 0, kvm->arch.vpit->pit_state.channels[0].count, start); + for (i = 0; i < 3; i++) + kvm_pit_load_count(kvm, i, kvm->arch.vpit->pit_state.channels[i].count, + start && i == 0); mutex_unlock(&kvm->arch.vpit->pit_state.lock); - return r; + return 0; } static int kvm_vm_ioctl_reinject(struct kvm *kvm, @@ -3758,6 +3735,28 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, kvm->arch.disabled_quirks = cap->args[0]; r = 0; break; + case KVM_CAP_SPLIT_IRQCHIP: { + mutex_lock(&kvm->lock); + r = -EINVAL; + if (cap->args[0] > MAX_NR_RESERVED_IOAPIC_PINS) + goto split_irqchip_unlock; + r = -EEXIST; + if (irqchip_in_kernel(kvm)) + goto split_irqchip_unlock; + if (atomic_read(&kvm->online_vcpus)) + goto split_irqchip_unlock; + r = kvm_setup_empty_irq_routing(kvm); + if (r) + goto split_irqchip_unlock; + /* Pairs with irqchip_in_kernel. */ + smp_wmb(); + kvm->arch.irqchip_split = true; + kvm->arch.nr_reserved_ioapic_pins = cap->args[0]; + r = 0; +split_irqchip_unlock: + mutex_unlock(&kvm->lock); + break; + } default: r = -EINVAL; break; @@ -3817,30 +3816,25 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_ioapic_init(kvm); if (r) { mutex_lock(&kvm->slots_lock); - kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, - &vpic->dev_master); - kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, - &vpic->dev_slave); - kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, - &vpic->dev_eclr); + kvm_destroy_pic(vpic); mutex_unlock(&kvm->slots_lock); - kfree(vpic); goto create_irqchip_unlock; } } else goto create_irqchip_unlock; - smp_wmb(); - kvm->arch.vpic = vpic; - smp_wmb(); r = kvm_setup_default_irq_routing(kvm); if (r) { mutex_lock(&kvm->slots_lock); mutex_lock(&kvm->irq_lock); kvm_ioapic_destroy(kvm); - kvm_destroy_pic(kvm); + kvm_destroy_pic(vpic); mutex_unlock(&kvm->irq_lock); mutex_unlock(&kvm->slots_lock); + goto create_irqchip_unlock; } + /* Write kvm->irq_routing before kvm->arch.vpic. */ + smp_wmb(); + kvm->arch.vpic = vpic; create_irqchip_unlock: mutex_unlock(&kvm->lock); break; @@ -3876,7 +3870,7 @@ long kvm_arch_vm_ioctl(struct file *filp, } r = -ENXIO; - if (!irqchip_in_kernel(kvm)) + if (!irqchip_in_kernel(kvm) || irqchip_split(kvm)) goto get_irqchip_out; r = kvm_vm_ioctl_get_irqchip(kvm, chip); if (r) @@ -3900,7 +3894,7 @@ long kvm_arch_vm_ioctl(struct file *filp, } r = -ENXIO; - if (!irqchip_in_kernel(kvm)) + if (!irqchip_in_kernel(kvm) || irqchip_split(kvm)) goto set_irqchip_out; r = kvm_vm_ioctl_set_irqchip(kvm, chip); if (r) @@ -3967,6 +3961,15 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_vm_ioctl_reinject(kvm, &control); break; } + case KVM_SET_BOOT_CPU_ID: + r = 0; + mutex_lock(&kvm->lock); + if (atomic_read(&kvm->online_vcpus) != 0) + r = -EBUSY; + else + kvm->arch.bsp_vcpu_id = arg; + mutex_unlock(&kvm->lock); + break; case KVM_XEN_HVM_CONFIG: { r = -EFAULT; if (copy_from_user(&kvm->arch.xen_hvm_config, argp, @@ -4044,16 +4047,17 @@ static void kvm_init_msr_list(void) /* * Even MSRs that are valid in the host may not be exposed - * to the guests in some cases. We could work around this - * in VMX with the generic MSR save/load machinery, but it - * is not really worthwhile since it will really only - * happen with nested virtualization. + * to the guests in some cases. */ switch (msrs_to_save[i]) { case MSR_IA32_BNDCFGS: if (!kvm_x86_ops->mpx_supported()) continue; break; + case MSR_TSC_AUX: + if (!kvm_x86_ops->rdtscp_supported()) + continue; + break; default: break; } @@ -4258,6 +4262,15 @@ static int kvm_read_guest_virt_system(struct x86_emulate_ctxt *ctxt, return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, 0, exception); } +static int kvm_read_guest_phys_system(struct x86_emulate_ctxt *ctxt, + unsigned long addr, void *val, unsigned int bytes) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + int r = kvm_vcpu_read_guest(vcpu, addr, val, bytes); + + return r < 0 ? X86EMUL_IO_NEEDED : X86EMUL_CONTINUE; +} + int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val, unsigned int bytes, @@ -4993,6 +5006,7 @@ static const struct x86_emulate_ops emulate_ops = { .write_gpr = emulator_write_gpr, .read_std = kvm_read_guest_virt_system, .write_std = kvm_write_guest_virt_system, + .read_phys = kvm_read_guest_phys_system, .fetch = kvm_fetch_guest_virt, .read_emulated = emulator_read_emulated, .write_emulated = emulator_write_emulated, @@ -5134,7 +5148,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, int emulation_type) { gpa_t gpa = cr2; - pfn_t pfn; + kvm_pfn_t pfn; if (emulation_type & EMULTYPE_NO_REEXECUTE) return false; @@ -5865,7 +5879,7 @@ void kvm_arch_exit(void) int kvm_vcpu_halt(struct kvm_vcpu *vcpu) { ++vcpu->stat.halt_exits; - if (irqchip_in_kernel(vcpu->kvm)) { + if (lapic_in_kernel(vcpu)) { vcpu->arch.mp_state = KVM_MP_STATE_HALTED; return 1; } else { @@ -5882,66 +5896,6 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_emulate_halt); -int kvm_hv_hypercall(struct kvm_vcpu *vcpu) -{ - u64 param, ingpa, outgpa, ret; - uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0; - bool fast, longmode; - - /* - * hypercall generates UD from non zero cpl and real mode - * per HYPER-V spec - */ - if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) { - kvm_queue_exception(vcpu, UD_VECTOR); - return 0; - } - - longmode = is_64_bit_mode(vcpu); - - if (!longmode) { - param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) | - (kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff); - ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) | - (kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff); - outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) | - (kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff); - } -#ifdef CONFIG_X86_64 - else { - param = kvm_register_read(vcpu, VCPU_REGS_RCX); - ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX); - outgpa = kvm_register_read(vcpu, VCPU_REGS_R8); - } -#endif - - code = param & 0xffff; - fast = (param >> 16) & 0x1; - rep_cnt = (param >> 32) & 0xfff; - rep_idx = (param >> 48) & 0xfff; - - trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa); - - switch (code) { - case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT: - kvm_vcpu_on_spin(vcpu); - break; - default: - res = HV_STATUS_INVALID_HYPERCALL_CODE; - break; - } - - ret = res | (((u64)rep_done & 0xfff) << 32); - if (longmode) { - kvm_register_write(vcpu, VCPU_REGS_RAX, ret); - } else { - kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32); - kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff); - } - - return 1; -} - /* * kvm_pv_kick_cpu_op: Kick a vcpu. * @@ -5960,6 +5914,12 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL); } +void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu) +{ + vcpu->arch.apicv_active = false; + kvm_x86_ops->refresh_apicv_exec_ctrl(vcpu); +} + int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) { unsigned long nr, a0, a1, a2, a3, ret; @@ -6024,17 +5984,10 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) return emulator_write_emulated(ctxt, rip, instruction, 3, NULL); } -/* - * Check if userspace requested an interrupt window, and that the - * interrupt window is open. - * - * No need to exit to userspace if we already have an interrupt queued. - */ static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu) { - return (!irqchip_in_kernel(vcpu->kvm) && !kvm_cpu_has_interrupt(vcpu) && - vcpu->run->request_interrupt_window && - kvm_arch_interrupt_allowed(vcpu)); + return vcpu->run->request_interrupt_window && + likely(!pic_in_kernel(vcpu->kvm)); } static void post_kvm_run_save(struct kvm_vcpu *vcpu) @@ -6045,13 +5998,9 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) 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)) - kvm_run->ready_for_interrupt_injection = 1; - else - kvm_run->ready_for_interrupt_injection = - kvm_arch_interrupt_allowed(vcpu) && - !kvm_cpu_has_interrupt(vcpu) && - !kvm_event_needs_reinjection(vcpu); + kvm_run->ready_for_interrupt_injection = + pic_in_kernel(vcpu->kvm) || + kvm_vcpu_ready_for_interrupt_injection(vcpu); } static void update_cr8_intercept(struct kvm_vcpu *vcpu) @@ -6064,6 +6013,9 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) if (!vcpu->arch.apic) return; + if (vcpu->arch.apicv_active) + return; + if (!vcpu->arch.apic->vapic_addr) max_irr = kvm_lapic_find_highest_irr(vcpu); else @@ -6201,6 +6153,7 @@ static void process_smi_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n) put_smstate(u32, buf, offset, process_smi_get_segment_flags(&seg)); } +#ifdef CONFIG_X86_64 static void process_smi_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n) { struct kvm_segment seg; @@ -6216,6 +6169,7 @@ static void process_smi_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n) put_smstate(u32, buf, offset + 4, seg.limit); put_smstate(u64, buf, offset + 8, seg.base); } +#endif static void process_smi_save_state_32(struct kvm_vcpu *vcpu, char *buf) { @@ -6398,20 +6352,30 @@ static void process_smi(struct kvm_vcpu *vcpu) kvm_mmu_reset_context(vcpu); } +void kvm_make_scan_ioapic_request(struct kvm *kvm) +{ + kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC); +} + static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) { u64 eoi_exit_bitmap[4]; - u32 tmr[8]; if (!kvm_apic_hw_enabled(vcpu->arch.apic)) return; - memset(eoi_exit_bitmap, 0, 32); - memset(tmr, 0, 32); + bitmap_zero(vcpu->arch.ioapic_handled_vectors, 256); - kvm_ioapic_scan_entry(vcpu, eoi_exit_bitmap, tmr); + if (irqchip_split(vcpu->kvm)) + kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); + else { + if (vcpu->arch.apicv_active) + kvm_x86_ops->sync_pir_to_irr(vcpu); + kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); + } + bitmap_or((ulong *)eoi_exit_bitmap, vcpu->arch.ioapic_handled_vectors, + vcpu_to_synic(vcpu)->vec_bitmap, 256); kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap); - kvm_apic_update_tmr(vcpu, tmr); } static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu) @@ -6424,7 +6388,7 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) { struct page *page = NULL; - if (!irqchip_in_kernel(vcpu->kvm)) + if (!lapic_in_kernel(vcpu)) return; if (!kvm_x86_ops->set_apic_access_page_addr) @@ -6462,8 +6426,10 @@ void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, static int vcpu_enter_guest(struct kvm_vcpu *vcpu) { int r; - bool req_int_win = !irqchip_in_kernel(vcpu->kvm) && - vcpu->run->request_interrupt_window; + bool req_int_win = + dm_request_for_irq_injection(vcpu) && + kvm_cpu_accept_dm_intr(vcpu); + bool req_immediate_exit = false; if (vcpu->requests) { @@ -6514,10 +6480,61 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_pmu_handle_event(vcpu); if (kvm_check_request(KVM_REQ_PMI, vcpu)) kvm_pmu_deliver_pmi(vcpu); + if (kvm_check_request(KVM_REQ_IOAPIC_EOI_EXIT, vcpu)) { + BUG_ON(vcpu->arch.pending_ioapic_eoi > 255); + if (test_bit(vcpu->arch.pending_ioapic_eoi, + vcpu->arch.ioapic_handled_vectors)) { + vcpu->run->exit_reason = KVM_EXIT_IOAPIC_EOI; + vcpu->run->eoi.vector = + vcpu->arch.pending_ioapic_eoi; + r = 0; + goto out; + } + } if (kvm_check_request(KVM_REQ_SCAN_IOAPIC, vcpu)) vcpu_scan_ioapic(vcpu); if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu)) kvm_vcpu_reload_apic_access_page(vcpu); + if (kvm_check_request(KVM_REQ_HV_CRASH, vcpu)) { + vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; + vcpu->run->system_event.type = KVM_SYSTEM_EVENT_CRASH; + r = 0; + goto out; + } + if (kvm_check_request(KVM_REQ_HV_RESET, vcpu)) { + vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; + vcpu->run->system_event.type = KVM_SYSTEM_EVENT_RESET; + r = 0; + goto out; + } + if (kvm_check_request(KVM_REQ_HV_EXIT, vcpu)) { + vcpu->run->exit_reason = KVM_EXIT_HYPERV; + vcpu->run->hyperv = vcpu->arch.hyperv.exit; + r = 0; + goto out; + } + + /* + * KVM_REQ_HV_STIMER has to be processed after + * KVM_REQ_CLOCK_UPDATE, because Hyper-V SynIC timers + * depend on the guest clock being up-to-date + */ + if (kvm_check_request(KVM_REQ_HV_STIMER, vcpu)) + kvm_hv_process_stimers(vcpu); + } + + /* + * KVM_REQ_EVENT is not set when posted interrupts are set by + * VT-d hardware, so we have to update RVI unconditionally. + */ + if (kvm_lapic_enabled(vcpu)) { + /* + * Update architecture specific hints for APIC + * virtual interrupt delivery. + */ + if (vcpu->arch.apicv_active) + kvm_x86_ops->hwapic_irr_update(vcpu, + kvm_lapic_find_highest_irr(vcpu)); } if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) { @@ -6536,13 +6553,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_x86_ops->enable_irq_window(vcpu); if (kvm_lapic_enabled(vcpu)) { - /* - * Update architecture specific hints for APIC - * virtual interrupt delivery. - */ - if (kvm_x86_ops->hwapic_irr_update) - kvm_x86_ops->hwapic_irr_update(vcpu, - kvm_lapic_find_highest_irr(vcpu)); update_cr8_intercept(vcpu); kvm_lapic_sync_to_vapic(vcpu); } @@ -6585,6 +6595,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (req_immediate_exit) smp_send_reschedule(vcpu->cpu); + trace_kvm_entry(vcpu->vcpu_id); + wait_lapic_expire(vcpu); __kvm_guest_enter(); if (unlikely(vcpu->arch.switch_db_regs)) { @@ -6597,8 +6609,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } - trace_kvm_entry(vcpu->vcpu_id); - wait_lapic_expire(vcpu); kvm_x86_ops->run(vcpu); /* @@ -6626,8 +6636,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (hw_breakpoint_active()) hw_breakpoint_restore(); - vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, - native_read_tsc()); + vcpu->arch.last_guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); @@ -6678,10 +6687,15 @@ out: static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) { - if (!kvm_arch_vcpu_runnable(vcpu)) { + if (!kvm_arch_vcpu_runnable(vcpu) && + (!kvm_x86_ops->pre_block || kvm_x86_ops->pre_block(vcpu) == 0)) { srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); kvm_vcpu_block(vcpu); vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + + if (kvm_x86_ops->post_block) + kvm_x86_ops->post_block(vcpu); + if (!kvm_check_request(KVM_REQ_UNHALT, vcpu)) return 1; } @@ -6704,6 +6718,12 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) return 1; } +static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) +{ + return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && + !vcpu->arch.apf.halted); +} + static int vcpu_run(struct kvm_vcpu *vcpu) { int r; @@ -6712,11 +6732,12 @@ static int vcpu_run(struct kvm_vcpu *vcpu) vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); for (;;) { - if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && - !vcpu->arch.apf.halted) + if (kvm_vcpu_running(vcpu)) { r = vcpu_enter_guest(vcpu); - else + } else { r = vcpu_block(kvm, vcpu); + } + if (r <= 0) break; @@ -6724,9 +6745,10 @@ static int vcpu_run(struct kvm_vcpu *vcpu) if (kvm_cpu_has_pending_timer(vcpu)) kvm_inject_pending_timer_irqs(vcpu); - if (dm_request_for_irq_injection(vcpu)) { - r = -EINTR; - vcpu->run->exit_reason = KVM_EXIT_INTR; + if (dm_request_for_irq_injection(vcpu) && + kvm_vcpu_ready_for_interrupt_injection(vcpu)) { + r = 0; + vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; ++vcpu->stat.request_irq_exits; break; } @@ -6853,7 +6875,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } /* re-sync apic's tpr */ - if (!irqchip_in_kernel(vcpu->kvm)) { + if (!lapic_in_kernel(vcpu)) { if (kvm_set_cr8(vcpu, kvm_run->cr8) != 0) { r = -EINVAL; goto out; @@ -7177,7 +7199,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, */ kvm_set_rflags(vcpu, rflags); - kvm_x86_ops->update_db_bp_intercept(vcpu); + kvm_x86_ops->update_bp_intercept(vcpu); r = 0; @@ -7251,7 +7273,7 @@ static void fx_init(struct kvm_vcpu *vcpu) /* * Ensure guest xcr0 is valid for loading */ - vcpu->arch.xcr0 = XSTATE_FP; + vcpu->arch.xcr0 = XFEATURE_MASK_FP; vcpu->arch.cr0 |= X86_CR0_ET; } @@ -7436,7 +7458,7 @@ int kvm_arch_hardware_enable(void) if (ret != 0) return ret; - local_tsc = native_read_tsc(); + local_tsc = rdtsc(); stable = !check_tsc_unstable(); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_for_each_vcpu(i, vcpu, kvm) { @@ -7526,6 +7548,20 @@ int kvm_arch_hardware_setup(void) if (r != 0) return r; + if (kvm_has_tsc_control) { + /* + * Make sure the user can only configure tsc_khz values that + * fit into a signed integer. + * A min value is not calculated needed because it will always + * be 1 on all machines. + */ + u64 max = min(0x7fffffffULL, + __scale_tsc(kvm_max_tsc_scaling_ratio, tsc_khz)); + kvm_max_guest_tsc_khz = max; + + kvm_default_tsc_scaling_ratio = 1ULL << kvm_tsc_scaling_ratio_frac_bits; + } + kvm_init_msr_list(); return 0; } @@ -7540,9 +7576,20 @@ void kvm_arch_check_processor_compat(void *rtn) kvm_x86_ops->check_processor_compatibility(rtn); } +bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu) +{ + return vcpu->kvm->arch.bsp_vcpu_id == vcpu->vcpu_id; +} +EXPORT_SYMBOL_GPL(kvm_vcpu_is_reset_bsp); + +bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu) +{ + return (vcpu->arch.apic_base & MSR_IA32_APICBASE_BSP) != 0; +} + bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) { - return irqchip_in_kernel(vcpu->kvm) == (vcpu->arch.apic != NULL); + return irqchip_in_kernel(vcpu->kvm) == lapic_in_kernel(vcpu); } struct static_key kvm_no_apic_vcpu __read_mostly; @@ -7556,6 +7603,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) BUG_ON(vcpu->kvm == NULL); kvm = vcpu->kvm; + vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(); vcpu->arch.pv.pv_unhalted = false; vcpu->arch.emulate_ctxt.ops = &emulate_ops; if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_reset_bsp(vcpu)) @@ -7611,6 +7659,10 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) kvm_async_pf_hash_reset(vcpu); kvm_pmu_init(vcpu); + vcpu->arch.pending_external_vector = -1; + + kvm_hv_vcpu_init(vcpu); + return 0; fail_free_mce_banks: @@ -7629,6 +7681,7 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) { int idx; + kvm_hv_vcpu_uninit(vcpu); kvm_pmu_destroy(vcpu); kfree(vcpu->arch.mce_banks); kvm_free_lapic(vcpu); @@ -7636,7 +7689,7 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) kvm_mmu_destroy(vcpu); srcu_read_unlock(&vcpu->kvm->srcu, idx); free_page((unsigned long)vcpu->arch.pio_data); - if (!irqchip_in_kernel(vcpu->kvm)) + if (!lapic_in_kernel(vcpu)) static_key_slow_dec(&kvm_no_apic_vcpu); } @@ -7714,34 +7767,66 @@ 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 __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) { int i, r; + unsigned long hva; + struct kvm_memslots *slots = kvm_memslots(kvm); + struct kvm_memory_slot *slot, old; /* Called with kvm->slots_lock held. */ - BUG_ON(mem->slot >= KVM_MEM_SLOTS_NUM); + if (WARN_ON(id >= KVM_MEM_SLOTS_NUM)) + return -EINVAL; + + slot = id_to_memslot(slots, id); + if (size) { + if (WARN_ON(slot->npages)) + return -EEXIST; + + /* + * MAP_SHARED to prevent internal slot pages from being moved + * by fork()/COW. + */ + hva = vm_mmap(NULL, 0, size, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, 0); + if (IS_ERR((void *)hva)) + return PTR_ERR((void *)hva); + } else { + if (!slot->npages) + return 0; + + hva = 0; + } + old = *slot; for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - struct kvm_userspace_memory_region m = *mem; + struct kvm_userspace_memory_region m; - m.slot |= i << 16; + m.slot = id | (i << 16); + m.flags = 0; + m.guest_phys_addr = gpa; + m.userspace_addr = hva; + m.memory_size = size; r = __kvm_set_memory_region(kvm, &m); if (r < 0) return r; } + if (!size) { + r = vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE); + WARN_ON(r < 0); + } + 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 x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) { int r; mutex_lock(&kvm->slots_lock); - r = __x86_set_memory_region(kvm, mem); + r = __x86_set_memory_region(kvm, id, gpa, size); mutex_unlock(&kvm->slots_lock); return r; @@ -7756,16 +7841,9 @@ void kvm_arch_destroy_vm(struct kvm *kvm) * unless the the memory map has changed due to process exit * or fd copying. */ - struct kvm_userspace_memory_region mem; - memset(&mem, 0, sizeof(mem)); - mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT; - x86_set_memory_region(kvm, &mem); - - mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT; - x86_set_memory_region(kvm, &mem); - - mem.slot = TSS_PRIVATE_MEMSLOT; - x86_set_memory_region(kvm, &mem); + x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, 0, 0); + x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, 0, 0); + x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0); } kvm_iommu_unmap_guest(kvm); kfree(kvm->arch.vpic); @@ -7868,27 +7946,6 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, enum kvm_mr_change change) { - /* - * Only private memory slots need to be mapped here since - * KVM_SET_MEMORY_REGION ioctl is no longer supported. - */ - if ((memslot->id >= KVM_USER_MEM_SLOTS) && (change == KVM_MR_CREATE)) { - unsigned long userspace_addr; - - /* - * MAP_SHARED to prevent internal slot pages from being moved - * by fork()/COW. - */ - userspace_addr = vm_mmap(NULL, 0, memslot->npages * PAGE_SIZE, - PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_ANONYMOUS, 0); - - if (IS_ERR((void *)userspace_addr)) - return PTR_ERR((void *)userspace_addr); - - memslot->userspace_addr = userspace_addr; - } - return 0; } @@ -7950,17 +8007,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, { int nr_mmu_pages = 0; - if (change == KVM_MR_DELETE && old->id >= KVM_USER_MEM_SLOTS) { - int ret; - - ret = vm_munmap(old->userspace_addr, - old->npages * PAGE_SIZE); - if (ret < 0) - printk(KERN_WARNING - "kvm_vm_ioctl_set_memory_region: " - "failed to munmap memory\n"); - } - if (!kvm->arch.n_requested_mmu_pages) nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm); @@ -8009,19 +8055,39 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, kvm_mmu_invalidate_zap_all_pages(kvm); } +static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) +{ + if (!list_empty_careful(&vcpu->async_pf.done)) + return true; + + if (kvm_apic_has_events(vcpu)) + return true; + + if (vcpu->arch.pv.pv_unhalted) + return true; + + if (atomic_read(&vcpu->arch.nmi_queued)) + return true; + + if (test_bit(KVM_REQ_SMI, &vcpu->requests)) + return true; + + if (kvm_arch_interrupt_allowed(vcpu) && + kvm_cpu_has_interrupt(vcpu)) + return true; + + if (kvm_hv_has_stimer_pending(vcpu)) + return true; + + return false; +} + int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) kvm_x86_ops->check_nested_events(vcpu, false); - return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && - !vcpu->arch.apf.halted) - || !list_empty_careful(&vcpu->async_pf.done) - || kvm_apic_has_events(vcpu) - || vcpu->arch.pv.pv_unhalted - || atomic_read(&vcpu->arch.nmi_queued) || - (kvm_arch_interrupt_allowed(vcpu) && - kvm_cpu_has_interrupt(vcpu)); + return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu); } int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) @@ -8253,7 +8319,59 @@ bool kvm_arch_has_noncoherent_dma(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma); +int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, + struct irq_bypass_producer *prod) +{ + struct kvm_kernel_irqfd *irqfd = + container_of(cons, struct kvm_kernel_irqfd, consumer); + + if (kvm_x86_ops->update_pi_irte) { + irqfd->producer = prod; + return kvm_x86_ops->update_pi_irte(irqfd->kvm, + prod->irq, irqfd->gsi, 1); + } + + return -EINVAL; +} + +void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, + struct irq_bypass_producer *prod) +{ + int ret; + struct kvm_kernel_irqfd *irqfd = + container_of(cons, struct kvm_kernel_irqfd, consumer); + + if (!kvm_x86_ops->update_pi_irte) { + WARN_ON(irqfd->producer != NULL); + return; + } + + WARN_ON(irqfd->producer != prod); + irqfd->producer = NULL; + + /* + * When producer of consumer is unregistered, we change back to + * remapped mode, so we can re-use the current implementation + * when the irq is masked/disabed or the consumer side (KVM + * int this case doesn't want to receive the interrupts. + */ + ret = kvm_x86_ops->update_pi_irte(irqfd->kvm, prod->irq, irqfd->gsi, 0); + if (ret) + printk(KERN_INFO "irq bypass consumer (token %p) unregistration" + " fails: %d\n", irqfd->consumer.token, ret); +} + +int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, + uint32_t guest_irq, bool set) +{ + if (!kvm_x86_ops->update_pi_irte) + return -EINVAL; + + return kvm_x86_ops->update_pi_irte(kvm, host_irq, guest_irq, set); +} + EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_msr); @@ -8268,3 +8386,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pml_full); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pi_irte_update); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 0ca2f3e4803c..f2afa5fe48a6 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -147,6 +147,11 @@ static inline void kvm_register_writel(struct kvm_vcpu *vcpu, return kvm_register_write(vcpu, reg, val); } +static inline u64 get_kernel_ns(void) +{ + return ktime_get_boot_ns(); +} + static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk) { return !(kvm->arch.disabled_quirks & quirk); @@ -175,9 +180,9 @@ 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 \ - | XSTATE_AVX512) +#define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ + | XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \ + | XFEATURE_MASK_BNDCSR | XFEATURE_MASK_AVX512) extern u64 host_xcr0; extern u64 kvm_supported_xcr0(void); diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index f2dc08c003eb..4ba229ac3f4f 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -835,16 +835,46 @@ static struct irq_chip lguest_irq_controller = { .irq_unmask = enable_lguest_irq, }; +/* + * Interrupt descriptors are allocated as-needed, but low-numbered ones are + * reserved by the generic x86 code. So we ignore irq_alloc_desc_at if it + * tells us the irq is already used: other errors (ie. ENOMEM) we take + * seriously. + */ +static int lguest_setup_irq(unsigned int irq) +{ + struct irq_desc *desc; + int err; + + /* Returns -ve error or vector number. */ + err = irq_alloc_desc_at(irq, 0); + if (err < 0 && err != -EEXIST) + return err; + + /* + * Tell the Linux infrastructure that the interrupt is + * controlled by our level-based lguest interrupt controller. + */ + irq_set_chip_and_handler_name(irq, &lguest_irq_controller, + handle_level_irq, "level"); + + /* Some systems map "vectors" to interrupts weirdly. Not us! */ + desc = irq_to_desc(irq); + __this_cpu_write(vector_irq[FIRST_EXTERNAL_VECTOR + irq], desc); + return 0; +} + static int lguest_enable_irq(struct pci_dev *dev) { + int err; u8 line = 0; /* We literally use the PCI interrupt line as the irq number. */ pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &line); - irq_set_chip_and_handler_name(line, &lguest_irq_controller, - handle_level_irq, "level"); - dev->irq = line; - return 0; + err = lguest_setup_irq(line); + if (!err) + dev->irq = line; + return err; } /* We don't do hotplug PCI, so this shouldn't be called. */ @@ -855,17 +885,13 @@ static void lguest_disable_irq(struct pci_dev *dev) /* * This sets up the Interrupt Descriptor Table (IDT) entry for each hardware - * interrupt (except 128, which is used for system calls), and then tells the - * Linux infrastructure that each interrupt is controlled by our level-based - * lguest interrupt controller. + * interrupt (except 128, which is used for system calls). */ static void __init lguest_init_IRQ(void) { unsigned int i; 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 != IA32_SYSCALL_VECTOR) set_intr_gate(i, irq_entries_start + 8 * (i - FIRST_EXTERNAL_VECTOR)); @@ -879,26 +905,6 @@ static void __init lguest_init_IRQ(void) } /* - * Interrupt descriptors are allocated as-needed, but low-numbered ones are - * reserved by the generic x86 code. So we ignore irq_alloc_desc_at if it - * tells us the irq is already used: other errors (ie. ENOMEM) we take - * seriously. - */ -int lguest_setup_irq(unsigned int irq) -{ - int err; - - /* Returns -ve error or vector number. */ - err = irq_alloc_desc_at(irq, 0); - if (err < 0 && err != -EEXIST) - return err; - - irq_set_chip_and_handler_name(irq, &lguest_irq_controller, - handle_level_irq, "level"); - return 0; -} - -/* * Time. * * It would be far better for everyone if the Guest had its own clock, but @@ -985,23 +991,11 @@ static int lguest_clockevent_set_next_event(unsigned long delta, return 0; } -static void lguest_clockevent_set_mode(enum clock_event_mode mode, - struct clock_event_device *evt) +static int lguest_clockevent_shutdown(struct clock_event_device *evt) { - switch (mode) { - case CLOCK_EVT_MODE_UNUSED: - case CLOCK_EVT_MODE_SHUTDOWN: - /* A 0 argument shuts the clock down. */ - hcall(LHCALL_SET_CLOCKEVENT, 0, 0, 0, 0); - break; - case CLOCK_EVT_MODE_ONESHOT: - /* This is what we expect. */ - break; - case CLOCK_EVT_MODE_PERIODIC: - BUG(); - case CLOCK_EVT_MODE_RESUME: - break; - } + /* A 0 argument shuts the clock down. */ + hcall(LHCALL_SET_CLOCKEVENT, 0, 0, 0, 0); + return 0; } /* This describes our primitive timer chip. */ @@ -1009,7 +1003,7 @@ static struct clock_event_device lguest_clockevent = { .name = "lguest", .features = CLOCK_EVT_FEAT_ONESHOT, .set_next_event = lguest_clockevent_set_next_event, - .set_mode = lguest_clockevent_set_mode, + .set_state_shutdown = lguest_clockevent_shutdown, .rating = INT_MAX, .mult = 1, .shift = 0, @@ -1021,7 +1015,7 @@ static struct clock_event_device lguest_clockevent = { * This is the Guest timer interrupt handler (hardware interrupt 0). We just * call the clockevent infrastructure and it does whatever needs doing. */ -static void lguest_time_irq(unsigned int irq, struct irq_desc *desc) +static void lguest_time_irq(struct irq_desc *desc) { unsigned long flags; @@ -1040,7 +1034,8 @@ static void lguest_time_irq(unsigned int irq, struct irq_desc *desc) static void lguest_time_init(void) { /* Set up the timer interrupt (0) to go to our simple timer routine */ - lguest_setup_irq(0); + if (lguest_setup_irq(0) != 0) + panic("Could not set up timer irq"); irq_set_handler(0, lguest_time_irq); clocksource_register_hz(&lguest_clock, NSEC_PER_SEC); @@ -1419,6 +1414,7 @@ __init void lguest_init(void) pv_info.kernel_rpl = 1; /* Everyone except Xen runs with this set. */ pv_info.shared_kernel_pmd = 1; + pv_info.features = 0; /* * We set up all the lguest overrides for sensitive operations. These @@ -1477,7 +1473,6 @@ __init void lguest_init(void) pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode; pv_mmu_ops.lazy_mode.flush = paravirt_flush_lazy_mmu; pv_mmu_ops.pte_update = lguest_pte_update; - pv_mmu_ops.pte_update_defer = lguest_pte_update; #ifdef CONFIG_X86_LOCAL_APIC /* APIC read/write intercepts */ diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index f2587888d987..a501fa25da41 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -16,7 +16,7 @@ clean-files := inat-tables.c obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o -lib-y := delay.o misc.o cmdline.o +lib-y := delay.o misc.o cmdline.o cpu.o lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o lib-y += memcpy_$(BITS).o lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o diff --git a/arch/x86/lib/cpu.c b/arch/x86/lib/cpu.c new file mode 100644 index 000000000000..aa417a97511c --- /dev/null +++ b/arch/x86/lib/cpu.c @@ -0,0 +1,35 @@ +#include <linux/module.h> + +unsigned int x86_family(unsigned int sig) +{ + unsigned int x86; + + x86 = (sig >> 8) & 0xf; + + if (x86 == 0xf) + x86 += (sig >> 20) & 0xff; + + return x86; +} +EXPORT_SYMBOL_GPL(x86_family); + +unsigned int x86_model(unsigned int sig) +{ + unsigned int fam, model; + + fam = x86_family(sig); + + model = (sig >> 4) & 0xf; + + if (fam >= 0x6) + model += ((sig >> 16) & 0xf) << 4; + + return model; +} +EXPORT_SYMBOL_GPL(x86_model); + +unsigned int x86_stepping(unsigned int sig) +{ + return sig & 0xf; +} +EXPORT_SYMBOL_GPL(x86_stepping); diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index 39d6a3db0b96..e912b2f6d36e 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -20,6 +20,7 @@ #include <asm/processor.h> #include <asm/delay.h> #include <asm/timer.h> +#include <asm/mwait.h> #ifdef CONFIG_SMP # include <asm/smp.h> @@ -49,16 +50,14 @@ static void delay_loop(unsigned long loops) /* TSC based delay: */ static void delay_tsc(unsigned long __loops) { - u32 bclock, now, loops = __loops; + u64 bclock, now, loops = __loops; int cpu; preempt_disable(); cpu = smp_processor_id(); - rdtsc_barrier(); - rdtscl(bclock); + bclock = rdtsc_ordered(); for (;;) { - rdtsc_barrier(); - rdtscl(now); + now = rdtsc_ordered(); if ((now - bclock) >= loops) break; @@ -79,14 +78,51 @@ static void delay_tsc(unsigned long __loops) if (unlikely(cpu != smp_processor_id())) { loops -= (now - bclock); cpu = smp_processor_id(); - rdtsc_barrier(); - rdtscl(bclock); + bclock = rdtsc_ordered(); } } preempt_enable(); } /* + * On some AMD platforms, MWAITX has a configurable 32-bit timer, that + * counts with TSC frequency. The input value is the loop of the + * counter, it will exit when the timer expires. + */ +static void delay_mwaitx(unsigned long __loops) +{ + u64 start, end, delay, loops = __loops; + + start = rdtsc_ordered(); + + for (;;) { + delay = min_t(u64, MWAITX_MAX_LOOPS, loops); + + /* + * Use cpu_tss as a cacheline-aligned, seldomly + * accessed per-cpu variable as the monitor target. + */ + __monitorx(this_cpu_ptr(&cpu_tss), 0, 0); + + /* + * AMD, like Intel, supports the EAX hint and EAX=0xf + * means, do not enter any deep C-state and we use it + * here in delay() to minimize wakeup latency. + */ + __mwaitx(MWAITX_DISABLE_CSTATES, delay, MWAITX_ECX_TIMER_ENABLE); + + end = rdtsc_ordered(); + + if (loops <= end - start) + break; + + loops -= end - start; + + start = end; + } +} + +/* * Since we calibrate only once at boot, this * function should be set once at boot and not changed */ @@ -94,13 +130,19 @@ static void (*delay_fn)(unsigned long) = delay_loop; void use_tsc_delay(void) { - delay_fn = delay_tsc; + if (delay_fn == delay_loop) + delay_fn = delay_tsc; +} + +void use_mwaitx_delay(void) +{ + delay_fn = delay_mwaitx; } int read_current_timer(unsigned long *timer_val) { if (delay_fn == delay_tsc) { - rdtscll(*timer_val); + *timer_val = rdtsc(); return 0; } return -1; diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c index 43623739c7cf..004c861b1648 100644 --- a/arch/x86/lib/msr.c +++ b/arch/x86/lib/msr.c @@ -1,6 +1,8 @@ #include <linux/module.h> #include <linux/preempt.h> #include <asm/msr.h> +#define CREATE_TRACE_POINTS +#include <asm/msr-trace.h> struct msr *msrs_alloc(void) { @@ -108,3 +110,27 @@ int msr_clear_bit(u32 msr, u8 bit) { return __flip_bit(msr, bit, false); } + +#ifdef CONFIG_TRACEPOINTS +void do_trace_write_msr(unsigned msr, u64 val, int failed) +{ + trace_write_msr(msr, val, failed); +} +EXPORT_SYMBOL(do_trace_write_msr); +EXPORT_TRACEPOINT_SYMBOL(write_msr); + +void do_trace_read_msr(unsigned msr, u64 val, int failed) +{ + trace_read_msr(msr, val, failed); +} +EXPORT_SYMBOL(do_trace_read_msr); +EXPORT_TRACEPOINT_SYMBOL(read_msr); + +void do_trace_rdpmc(unsigned counter, u64 val, int failed) +{ + trace_rdpmc(counter, val, failed); +} +EXPORT_SYMBOL(do_trace_rdpmc); +EXPORT_TRACEPOINT_SYMBOL(rdpmc); + +#endif diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index 816488c0b97e..d388de72eaca 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -353,8 +353,12 @@ AVXcode: 1 17: vmovhps Mq,Vq (v1) | vmovhpd Mq,Vq (66),(v1) 18: Grp16 (1A) 19: -1a: BNDCL Ev,Gv | BNDCU Ev,Gv | BNDMOV Gv,Ev | BNDLDX Gv,Ev,Gv -1b: BNDCN Ev,Gv | BNDMOV Ev,Gv | BNDMK Gv,Ev | BNDSTX Ev,GV,Gv +# Intel SDM opcode map does not list MPX instructions. For now using Gv for +# bnd registers and Ev for everything else is OK because the instruction +# decoder does not use the information except as an indication that there is +# a ModR/M byte. +1a: BNDCL Gv,Ev (F3) | BNDCU Gv,Ev (F2) | BNDMOV Gv,Ev (66) | BNDLDX Gv,Ev +1b: BNDCN Gv,Ev (F2) | BNDMOV Ev,Gv (66) | BNDMK Gv,Ev (F3) | BNDSTX Ev,Gv 1c: 1d: 1e: @@ -732,6 +736,12 @@ bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1) be: vfnmsub231ps/d Vx,Hx,Wx (66),(v) bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1) # 0x0f 0x38 0xc0-0xff +c8: sha1nexte Vdq,Wdq +c9: sha1msg1 Vdq,Wdq +ca: sha1msg2 Vdq,Wdq +cb: sha256rnds2 Vdq,Wdq +cc: sha256msg1 Vdq,Wdq +cd: sha256msg2 Vdq,Wdq db: VAESIMC Vdq,Wdq (66),(v1) dc: VAESENC Vdq,Hdq,Wdq (66),(v1) dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1) @@ -790,6 +800,7 @@ AVXcode: 3 61: vpcmpestri Vdq,Wdq,Ib (66),(v1) 62: vpcmpistrm Vdq,Wdq,Ib (66),(v1) 63: vpcmpistri Vdq,Wdq,Ib (66),(v1) +cc: sha1rnds4 Vdq,Wdq,Ib df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1) f0: RORX Gy,Ey,Ib (F2),(v) EndTable @@ -874,7 +885,7 @@ GrpTable: Grp7 2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) 3: LIDT Ms 4: SMSW Mw/Rv -5: +5: rdpkru (110),(11B) | wrpkru (111),(11B) 6: LMSW Ew 7: INVLPG Mb | SWAPGS (o64),(000),(11B) | RDTSCP (001),(11B) EndTable @@ -888,6 +899,9 @@ EndTable GrpTable: Grp9 1: CMPXCHG8B/16B Mq/Mdq +3: xrstors +4: xsavec +5: xsaves 6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B) 7: VMPTRST Mq | VMPTRST Mq (F3) | RDSEED Rv (11B) EndTable @@ -932,8 +946,8 @@ GrpTable: Grp15 3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B) 4: XSAVE 5: XRSTOR | lfence (11B) -6: XSAVEOPT | mfence (11B) -7: clflush | sfence (11B) +6: XSAVEOPT | clwb (66) | mfence (11B) +7: clflush | clflushopt (66) | sfence (11B) | pcommit (66),(11B) EndTable GrpTable: Grp16 diff --git a/arch/x86/math-emu/fpu_aux.c b/arch/x86/math-emu/fpu_aux.c index dd76a05729b0..024f6e971174 100644 --- a/arch/x86/math-emu/fpu_aux.c +++ b/arch/x86/math-emu/fpu_aux.c @@ -169,6 +169,76 @@ void fxch_i(void) fpu_tag_word = tag_word; } +static void fcmovCC(void) +{ + /* fcmovCC st(i) */ + int i = FPU_rm; + FPU_REG *st0_ptr = &st(0); + FPU_REG *sti_ptr = &st(i); + long tag_word = fpu_tag_word; + int regnr = top & 7; + int regnri = (top + i) & 7; + u_char sti_tag = (tag_word >> (regnri * 2)) & 3; + + if (sti_tag == TAG_Empty) { + FPU_stack_underflow(); + clear_C1(); + return; + } + reg_copy(sti_ptr, st0_ptr); + tag_word &= ~(3 << (regnr * 2)); + tag_word |= (sti_tag << (regnr * 2)); + fpu_tag_word = tag_word; +} + +void fcmovb(void) +{ + if (FPU_EFLAGS & X86_EFLAGS_CF) + fcmovCC(); +} + +void fcmove(void) +{ + if (FPU_EFLAGS & X86_EFLAGS_ZF) + fcmovCC(); +} + +void fcmovbe(void) +{ + if (FPU_EFLAGS & (X86_EFLAGS_CF|X86_EFLAGS_ZF)) + fcmovCC(); +} + +void fcmovu(void) +{ + if (FPU_EFLAGS & X86_EFLAGS_PF) + fcmovCC(); +} + +void fcmovnb(void) +{ + if (!(FPU_EFLAGS & X86_EFLAGS_CF)) + fcmovCC(); +} + +void fcmovne(void) +{ + if (!(FPU_EFLAGS & X86_EFLAGS_ZF)) + fcmovCC(); +} + +void fcmovnbe(void) +{ + if (!(FPU_EFLAGS & (X86_EFLAGS_CF|X86_EFLAGS_ZF))) + fcmovCC(); +} + +void fcmovnu(void) +{ + if (!(FPU_EFLAGS & X86_EFLAGS_PF)) + fcmovCC(); +} + void ffree_(void) { /* ffree st(i) */ diff --git a/arch/x86/math-emu/fpu_emu.h b/arch/x86/math-emu/fpu_emu.h index 4dae511c85ad..afbc4d805d66 100644 --- a/arch/x86/math-emu/fpu_emu.h +++ b/arch/x86/math-emu/fpu_emu.h @@ -71,7 +71,7 @@ #include "fpu_system.h" -#include <asm/sigcontext.h> /* for struct _fpstate */ +#include <uapi/asm/sigcontext.h> /* for struct _fpstate */ #include <asm/math_emu.h> #include <linux/linkage.h> diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c index 3d8f2e421466..e945fedf1de2 100644 --- a/arch/x86/math-emu/fpu_entry.c +++ b/arch/x86/math-emu/fpu_entry.c @@ -40,49 +40,33 @@ #define __BAD__ FPU_illegal /* Illegal on an 80486, causes SIGILL */ -#ifndef NO_UNDOC_CODE /* Un-documented FPU op-codes supported by default. */ +/* fcmovCC and f(u)comi(p) are enabled if CPUID(1).EDX(15) "cmov" is set */ -/* WARNING: These codes are not documented by Intel in their 80486 manual - and may not work on FPU clones or later Intel FPUs. */ - -/* Changes to support the un-doc codes provided by Linus Torvalds. */ - -#define _d9_d8_ fstp_i /* unofficial code (19) */ -#define _dc_d0_ fcom_st /* unofficial code (14) */ -#define _dc_d8_ fcompst /* unofficial code (1c) */ -#define _dd_c8_ fxch_i /* unofficial code (0d) */ -#define _de_d0_ fcompst /* unofficial code (16) */ -#define _df_c0_ ffreep /* unofficial code (07) ffree + pop */ -#define _df_c8_ fxch_i /* unofficial code (0f) */ -#define _df_d0_ fstp_i /* unofficial code (17) */ -#define _df_d8_ fstp_i /* unofficial code (1f) */ +/* WARNING: "u" entries are not documented by Intel in their 80486 manual + and may not work on FPU clones or later Intel FPUs. + Changes to support them provided by Linus Torvalds. */ static FUNC const st_instr_table[64] = { - fadd__, fld_i_, __BAD__, __BAD__, fadd_i, ffree_, faddp_, _df_c0_, - fmul__, fxch_i, __BAD__, __BAD__, fmul_i, _dd_c8_, fmulp_, _df_c8_, - fcom_st, fp_nop, __BAD__, __BAD__, _dc_d0_, fst_i_, _de_d0_, _df_d0_, - fcompst, _d9_d8_, __BAD__, __BAD__, _dc_d8_, fstp_i, fcompp, _df_d8_, - fsub__, FPU_etc, __BAD__, finit_, fsubri, fucom_, fsubrp, fstsw_, - fsubr_, fconst, fucompp, __BAD__, fsub_i, fucomp, fsubp_, __BAD__, - fdiv__, FPU_triga, __BAD__, __BAD__, fdivri, __BAD__, fdivrp, __BAD__, - fdivr_, FPU_trigb, __BAD__, __BAD__, fdiv_i, __BAD__, fdivp_, __BAD__, +/* Opcode: d8 d9 da db */ +/* dc dd de df */ +/* c0..7 */ fadd__, fld_i_, fcmovb, fcmovnb, +/* c0..7 */ fadd_i, ffree_, faddp_, ffreep,/*u*/ +/* c8..f */ fmul__, fxch_i, fcmove, fcmovne, +/* c8..f */ fmul_i, fxch_i,/*u*/ fmulp_, fxch_i,/*u*/ +/* d0..7 */ fcom_st, fp_nop, fcmovbe, fcmovnbe, +/* d0..7 */ fcom_st,/*u*/ fst_i_, fcompst,/*u*/ fstp_i,/*u*/ +/* d8..f */ fcompst, fstp_i,/*u*/ fcmovu, fcmovnu, +/* d8..f */ fcompst,/*u*/ fstp_i, fcompp, fstp_i,/*u*/ +/* e0..7 */ fsub__, FPU_etc, __BAD__, finit_, +/* e0..7 */ fsubri, fucom_, fsubrp, fstsw_, +/* e8..f */ fsubr_, fconst, fucompp, fucomi_, +/* e8..f */ fsub_i, fucomp, fsubp_, fucomip, +/* f0..7 */ fdiv__, FPU_triga, __BAD__, fcomi_, +/* f0..7 */ fdivri, __BAD__, fdivrp, fcomip, +/* f8..f */ fdivr_, FPU_trigb, __BAD__, __BAD__, +/* f8..f */ fdiv_i, __BAD__, fdivp_, __BAD__, }; -#else /* Support only documented FPU op-codes */ - -static FUNC const st_instr_table[64] = { - fadd__, fld_i_, __BAD__, __BAD__, fadd_i, ffree_, faddp_, __BAD__, - fmul__, fxch_i, __BAD__, __BAD__, fmul_i, __BAD__, fmulp_, __BAD__, - fcom_st, fp_nop, __BAD__, __BAD__, __BAD__, fst_i_, __BAD__, __BAD__, - fcompst, __BAD__, __BAD__, __BAD__, __BAD__, fstp_i, fcompp, __BAD__, - fsub__, FPU_etc, __BAD__, finit_, fsubri, fucom_, fsubrp, fstsw_, - fsubr_, fconst, fucompp, __BAD__, fsub_i, fucomp, fsubp_, __BAD__, - fdiv__, FPU_triga, __BAD__, __BAD__, fdivri, __BAD__, fdivrp, __BAD__, - fdivr_, FPU_trigb, __BAD__, __BAD__, fdiv_i, __BAD__, fdivp_, __BAD__, -}; - -#endif /* NO_UNDOC_CODE */ - #define _NONE_ 0 /* Take no special action */ #define _REG0_ 1 /* Need to check for not empty st(0) */ #define _REGI_ 2 /* Need to check for not empty st(0) and st(rm) */ @@ -94,36 +78,18 @@ static FUNC const st_instr_table[64] = { #define _REGIc 0 /* Compare st(0) and st(rm) */ #define _REGIn 0 /* Uses st(0) and st(rm), but handle checks later */ -#ifndef NO_UNDOC_CODE - -/* Un-documented FPU op-codes supported by default. (see above) */ - static u_char const type_table[64] = { - _REGI_, _NONE_, _null_, _null_, _REGIi, _REGi_, _REGIp, _REGi_, - _REGI_, _REGIn, _null_, _null_, _REGIi, _REGI_, _REGIp, _REGI_, - _REGIc, _NONE_, _null_, _null_, _REGIc, _REG0_, _REGIc, _REG0_, - _REGIc, _REG0_, _null_, _null_, _REGIc, _REG0_, _REGIc, _REG0_, - _REGI_, _NONE_, _null_, _NONE_, _REGIi, _REGIc, _REGIp, _NONE_, - _REGI_, _NONE_, _REGIc, _null_, _REGIi, _REGIc, _REGIp, _null_, - _REGI_, _NONE_, _null_, _null_, _REGIi, _null_, _REGIp, _null_, - _REGI_, _NONE_, _null_, _null_, _REGIi, _null_, _REGIp, _null_ +/* Opcode: d8 d9 da db dc dd de df */ +/* c0..7 */ _REGI_, _NONE_, _REGIn, _REGIn, _REGIi, _REGi_, _REGIp, _REGi_, +/* c8..f */ _REGI_, _REGIn, _REGIn, _REGIn, _REGIi, _REGI_, _REGIp, _REGI_, +/* d0..7 */ _REGIc, _NONE_, _REGIn, _REGIn, _REGIc, _REG0_, _REGIc, _REG0_, +/* d8..f */ _REGIc, _REG0_, _REGIn, _REGIn, _REGIc, _REG0_, _REGIc, _REG0_, +/* e0..7 */ _REGI_, _NONE_, _null_, _NONE_, _REGIi, _REGIc, _REGIp, _NONE_, +/* e8..f */ _REGI_, _NONE_, _REGIc, _REGIc, _REGIi, _REGIc, _REGIp, _REGIc, +/* f0..7 */ _REGI_, _NONE_, _null_, _REGIc, _REGIi, _null_, _REGIp, _REGIc, +/* f8..f */ _REGI_, _NONE_, _null_, _null_, _REGIi, _null_, _REGIp, _null_, }; -#else /* Support only documented FPU op-codes */ - -static u_char const type_table[64] = { - _REGI_, _NONE_, _null_, _null_, _REGIi, _REGi_, _REGIp, _null_, - _REGI_, _REGIn, _null_, _null_, _REGIi, _null_, _REGIp, _null_, - _REGIc, _NONE_, _null_, _null_, _null_, _REG0_, _null_, _null_, - _REGIc, _null_, _null_, _null_, _null_, _REG0_, _REGIc, _null_, - _REGI_, _NONE_, _null_, _NONE_, _REGIi, _REGIc, _REGIp, _NONE_, - _REGI_, _NONE_, _REGIc, _null_, _REGIi, _REGIc, _REGIp, _null_, - _REGI_, _NONE_, _null_, _null_, _REGIi, _null_, _REGIp, _null_, - _REGI_, _NONE_, _null_, _null_, _REGIi, _null_, _REGIp, _null_ -}; - -#endif /* NO_UNDOC_CODE */ - #ifdef RE_ENTRANT_CHECKING u_char emulating = 0; #endif /* RE_ENTRANT_CHECKING */ diff --git a/arch/x86/math-emu/fpu_proto.h b/arch/x86/math-emu/fpu_proto.h index 9779df436b7d..caff438b9c1d 100644 --- a/arch/x86/math-emu/fpu_proto.h +++ b/arch/x86/math-emu/fpu_proto.h @@ -46,6 +46,14 @@ extern void fstsw_(void); extern void fp_nop(void); extern void fld_i_(void); extern void fxch_i(void); +extern void fcmovb(void); +extern void fcmove(void); +extern void fcmovbe(void); +extern void fcmovu(void); +extern void fcmovnb(void); +extern void fcmovne(void); +extern void fcmovnbe(void); +extern void fcmovnu(void); extern void ffree_(void); extern void ffreep(void); extern void fst_i_(void); @@ -108,6 +116,10 @@ extern void fcompp(void); extern void fucom_(void); extern void fucomp(void); extern void fucompp(void); +extern void fcomi_(void); +extern void fcomip(void); +extern void fucomi_(void); +extern void fucomip(void); /* reg_constant.c */ extern void fconst(void); /* reg_ld_str.c */ diff --git a/arch/x86/math-emu/get_address.c b/arch/x86/math-emu/get_address.c index 8300db71c2a6..8db26591d91a 100644 --- a/arch/x86/math-emu/get_address.c +++ b/arch/x86/math-emu/get_address.c @@ -20,6 +20,7 @@ #include <linux/stddef.h> #include <asm/uaccess.h> +#include <asm/vm86.h> #include "fpu_system.h" #include "exception.h" diff --git a/arch/x86/math-emu/load_store.c b/arch/x86/math-emu/load_store.c index 2931ff355218..95228ff042c0 100644 --- a/arch/x86/math-emu/load_store.c +++ b/arch/x86/math-emu/load_store.c @@ -33,11 +33,12 @@ #define pop_0() { FPU_settag0(TAG_Empty); top++; } +/* index is a 5-bit value: (3-bit FPU_modrm.reg field | opcode[2,1]) */ static u_char const type_table[32] = { - _PUSH_, _PUSH_, _PUSH_, _PUSH_, - _null_, _null_, _null_, _null_, - _REG0_, _REG0_, _REG0_, _REG0_, - _REG0_, _REG0_, _REG0_, _REG0_, + _PUSH_, _PUSH_, _PUSH_, _PUSH_, /* /0: d9:fld f32, db:fild m32, dd:fld f64, df:fild m16 */ + _null_, _REG0_, _REG0_, _REG0_, /* /1: d9:undef, db,dd,df:fisttp m32/64/16 */ + _REG0_, _REG0_, _REG0_, _REG0_, /* /2: d9:fst f32, db:fist m32, dd:fst f64, df:fist m16 */ + _REG0_, _REG0_, _REG0_, _REG0_, /* /3: d9:fstp f32, db:fistp m32, dd:fstp f64, df:fistp m16 */ _NONE_, _null_, _NONE_, _PUSH_, _NONE_, _PUSH_, _null_, _PUSH_, _NONE_, _null_, _NONE_, _REG0_, @@ -45,15 +46,19 @@ static u_char const type_table[32] = { }; u_char const data_sizes_16[32] = { - 4, 4, 8, 2, 0, 0, 0, 0, - 4, 4, 8, 2, 4, 4, 8, 2, + 4, 4, 8, 2, + 0, 4, 8, 2, /* /1: d9:undef, db,dd,df:fisttp */ + 4, 4, 8, 2, + 4, 4, 8, 2, 14, 0, 94, 10, 2, 10, 0, 8, 14, 0, 94, 10, 2, 10, 2, 8 }; static u_char const data_sizes_32[32] = { - 4, 4, 8, 2, 0, 0, 0, 0, - 4, 4, 8, 2, 4, 4, 8, 2, + 4, 4, 8, 2, + 0, 4, 8, 2, /* /1: d9:undef, db,dd,df:fisttp */ + 4, 4, 8, 2, + 4, 4, 8, 2, 28, 0, 108, 10, 2, 10, 0, 8, 28, 0, 108, 10, 2, 10, 2, 8 }; @@ -65,6 +70,7 @@ int FPU_load_store(u_char type, fpu_addr_modes addr_modes, FPU_REG *st0_ptr; u_char st0_tag = TAG_Empty; /* This is just to stop a gcc warning. */ u_char loaded_tag; + int sv_cw; st0_ptr = NULL; /* Initialized just to stop compiler warnings. */ @@ -111,7 +117,8 @@ int FPU_load_store(u_char type, fpu_addr_modes addr_modes, } switch (type) { - case 000: /* fld m32real */ + /* type is a 5-bit value: (3-bit FPU_modrm.reg field | opcode[2,1]) */ + case 000: /* fld m32real (d9 /0) */ clear_C1(); loaded_tag = FPU_load_single((float __user *)data_address, &loaded_data); @@ -123,13 +130,13 @@ int FPU_load_store(u_char type, fpu_addr_modes addr_modes, } FPU_copy_to_reg0(&loaded_data, loaded_tag); break; - case 001: /* fild m32int */ + case 001: /* fild m32int (db /0) */ clear_C1(); loaded_tag = FPU_load_int32((long __user *)data_address, &loaded_data); FPU_copy_to_reg0(&loaded_data, loaded_tag); break; - case 002: /* fld m64real */ + case 002: /* fld m64real (dd /0) */ clear_C1(); loaded_tag = FPU_load_double((double __user *)data_address, @@ -142,12 +149,44 @@ int FPU_load_store(u_char type, fpu_addr_modes addr_modes, } FPU_copy_to_reg0(&loaded_data, loaded_tag); break; - case 003: /* fild m16int */ + case 003: /* fild m16int (df /0) */ clear_C1(); loaded_tag = FPU_load_int16((short __user *)data_address, &loaded_data); FPU_copy_to_reg0(&loaded_data, loaded_tag); break; + /* case 004: undefined (d9 /1) */ + /* fisttp are enabled if CPUID(1).ECX(0) "sse3" is set */ + case 005: /* fisttp m32int (db /1) */ + clear_C1(); + sv_cw = control_word; + control_word |= RC_CHOP; + if (FPU_store_int32 + (st0_ptr, st0_tag, (long __user *)data_address)) + pop_0(); /* pop only if the number was actually stored + (see the 80486 manual p16-28) */ + control_word = sv_cw; + break; + case 006: /* fisttp m64int (dd /1) */ + clear_C1(); + sv_cw = control_word; + control_word |= RC_CHOP; + if (FPU_store_int64 + (st0_ptr, st0_tag, (long long __user *)data_address)) + pop_0(); /* pop only if the number was actually stored + (see the 80486 manual p16-28) */ + control_word = sv_cw; + break; + case 007: /* fisttp m16int (df /1) */ + clear_C1(); + sv_cw = control_word; + control_word |= RC_CHOP; + if (FPU_store_int16 + (st0_ptr, st0_tag, (short __user *)data_address)) + pop_0(); /* pop only if the number was actually stored + (see the 80486 manual p16-28) */ + control_word = sv_cw; + break; case 010: /* fst m32real */ clear_C1(); FPU_store_single(st0_ptr, st0_tag, diff --git a/arch/x86/math-emu/reg_compare.c b/arch/x86/math-emu/reg_compare.c index ecce55fc2e2e..b77360fdbf4a 100644 --- a/arch/x86/math-emu/reg_compare.c +++ b/arch/x86/math-emu/reg_compare.c @@ -249,6 +249,54 @@ static int compare_st_st(int nr) return 0; } +static int compare_i_st_st(int nr) +{ + int f, c; + FPU_REG *st_ptr; + + if (!NOT_EMPTY(0) || !NOT_EMPTY(nr)) { + FPU_EFLAGS |= (X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF); + /* Stack fault */ + EXCEPTION(EX_StackUnder); + return !(control_word & CW_Invalid); + } + + partial_status &= ~SW_C0; + st_ptr = &st(nr); + c = compare(st_ptr, FPU_gettagi(nr)); + if (c & COMP_NaN) { + FPU_EFLAGS |= (X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF); + EXCEPTION(EX_Invalid); + return !(control_word & CW_Invalid); + } + + switch (c & 7) { + case COMP_A_lt_B: + f = X86_EFLAGS_CF; + break; + case COMP_A_eq_B: + f = X86_EFLAGS_ZF; + break; + case COMP_A_gt_B: + f = 0; + break; + case COMP_No_Comp: + f = X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF; + break; +#ifdef PARANOID + default: + EXCEPTION(EX_INTERNAL | 0x122); + f = 0; + break; +#endif /* PARANOID */ + } + FPU_EFLAGS = (FPU_EFLAGS & ~(X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF)) | f; + if (c & COMP_Denormal) { + return denormal_operand() < 0; + } + return 0; +} + static int compare_u_st_st(int nr) { int f = 0, c; @@ -299,6 +347,58 @@ static int compare_u_st_st(int nr) return 0; } +static int compare_ui_st_st(int nr) +{ + int f = 0, c; + FPU_REG *st_ptr; + + if (!NOT_EMPTY(0) || !NOT_EMPTY(nr)) { + FPU_EFLAGS |= (X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF); + /* Stack fault */ + EXCEPTION(EX_StackUnder); + return !(control_word & CW_Invalid); + } + + partial_status &= ~SW_C0; + st_ptr = &st(nr); + c = compare(st_ptr, FPU_gettagi(nr)); + if (c & COMP_NaN) { + FPU_EFLAGS |= (X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF); + if (c & COMP_SNaN) { /* This is the only difference between + un-ordered and ordinary comparisons */ + EXCEPTION(EX_Invalid); + return !(control_word & CW_Invalid); + } + return 0; + } + + switch (c & 7) { + case COMP_A_lt_B: + f = X86_EFLAGS_CF; + break; + case COMP_A_eq_B: + f = X86_EFLAGS_ZF; + break; + case COMP_A_gt_B: + f = 0; + break; + case COMP_No_Comp: + f = X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF; + break; +#ifdef PARANOID + default: + EXCEPTION(EX_INTERNAL | 0x123); + f = 0; + break; +#endif /* PARANOID */ + } + FPU_EFLAGS = (FPU_EFLAGS & ~(X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF)) | f; + if (c & COMP_Denormal) { + return denormal_operand() < 0; + } + return 0; +} + /*---------------------------------------------------------------------------*/ void fcom_st(void) @@ -348,3 +448,31 @@ void fucompp(void) } else FPU_illegal(); } + +/* P6+ compare-to-EFLAGS ops */ + +void fcomi_(void) +{ + /* fcomi st(i) */ + compare_i_st_st(FPU_rm); +} + +void fcomip(void) +{ + /* fcomip st(i) */ + if (!compare_i_st_st(FPU_rm)) + FPU_pop(); +} + +void fucomi_(void) +{ + /* fucomi st(i) */ + compare_ui_st_st(FPU_rm); +} + +void fucomip(void) +{ + /* fucomip st(i) */ + if (!compare_ui_st_st(FPU_rm)) + FPU_pop(); +} diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index a482d105172b..f9d38a48e3c8 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -14,7 +14,8 @@ obj-$(CONFIG_SMP) += tlb.o obj-$(CONFIG_X86_32) += pgtable_32.o iomap_32.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o -obj-$(CONFIG_X86_PTDUMP) += dump_pagetables.o +obj-$(CONFIG_X86_PTDUMP_CORE) += dump_pagetables.o +obj-$(CONFIG_X86_PTDUMP) += debug_pagetables.o obj-$(CONFIG_HIGHMEM) += highmem_32.o diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c new file mode 100644 index 000000000000..bfcffdf6c577 --- /dev/null +++ b/arch/x86/mm/debug_pagetables.c @@ -0,0 +1,46 @@ +#include <linux/debugfs.h> +#include <linux/module.h> +#include <linux/seq_file.h> +#include <asm/pgtable.h> + +static int ptdump_show(struct seq_file *m, void *v) +{ + ptdump_walk_pgd_level(m, NULL); + return 0; +} + +static int ptdump_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, ptdump_show, NULL); +} + +static const struct file_operations ptdump_fops = { + .owner = THIS_MODULE, + .open = ptdump_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static struct dentry *pe; + +static int __init pt_dump_debug_init(void) +{ + pe = debugfs_create_file("kernel_page_tables", S_IRUSR, NULL, NULL, + &ptdump_fops); + if (!pe) + return -ENOMEM; + + return 0; +} + +static void __exit pt_dump_debug_exit(void) +{ + debugfs_remove_recursive(pe); +} + +module_init(pt_dump_debug_init); +module_exit(pt_dump_debug_exit); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>"); +MODULE_DESCRIPTION("Kernel debugging helper that dumps pagetables"); diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index f0cedf3395af..4a6f1d9b5106 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -32,6 +32,8 @@ struct pg_state { const struct addr_marker *marker; unsigned long lines; bool to_dmesg; + bool check_wx; + unsigned long wx_pages; }; struct addr_marker { @@ -87,7 +89,7 @@ static struct addr_marker address_markers[] = { { 0/* VMALLOC_START */, "vmalloc() Area" }, { 0/*VMALLOC_END*/, "vmalloc() End" }, # ifdef CONFIG_HIGHMEM - { 0/*PKMAP_BASE*/, "Persisent kmap() Area" }, + { 0/*PKMAP_BASE*/, "Persistent kmap() Area" }, # endif { 0/*FIXADDR_START*/, "Fixmap Area" }, #endif @@ -155,7 +157,7 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg) pt_dump_cont_printf(m, dmsg, " "); if ((level == 4 && pr & _PAGE_PAT) || ((level == 3 || level == 2) && pr & _PAGE_PAT_LARGE)) - pt_dump_cont_printf(m, dmsg, "pat "); + pt_dump_cont_printf(m, dmsg, "PAT "); else pt_dump_cont_printf(m, dmsg, " "); if (pr & _PAGE_GLOBAL) @@ -198,8 +200,8 @@ static void note_page(struct seq_file *m, struct pg_state *st, * we have now. "break" is either changing perms, levels or * address space marker. */ - prot = pgprot_val(new_prot) & PTE_FLAGS_MASK; - cur = pgprot_val(st->current_prot) & PTE_FLAGS_MASK; + prot = pgprot_val(new_prot); + cur = pgprot_val(st->current_prot); if (!st->level) { /* First entry */ @@ -214,6 +216,16 @@ static void note_page(struct seq_file *m, struct pg_state *st, const char *unit = units; unsigned long delta; int width = sizeof(unsigned long) * 2; + pgprotval_t pr = pgprot_val(st->current_prot); + + if (st->check_wx && (pr & _PAGE_RW) && !(pr & _PAGE_NX)) { + WARN_ONCE(1, + "x86/mm: Found insecure W+X mapping at address %p/%pS\n", + (void *)st->start_address, + (void *)st->start_address); + st->wx_pages += (st->current_address - + st->start_address) / PAGE_SIZE; + } /* * Now print the actual finished series @@ -269,13 +281,13 @@ static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr, { int i; pte_t *start; + pgprotval_t prot; start = (pte_t *) pmd_page_vaddr(addr); for (i = 0; i < PTRS_PER_PTE; i++) { - pgprot_t prot = pte_pgprot(*start); - + prot = pte_flags(*start); st->current_address = normalize_addr(P + i * PTE_LEVEL_MULT); - note_page(m, st, prot, 4); + note_page(m, st, __pgprot(prot), 4); start++; } } @@ -287,18 +299,19 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr, { int i; pmd_t *start; + pgprotval_t prot; start = (pmd_t *) pud_page_vaddr(addr); for (i = 0; i < PTRS_PER_PMD; i++) { st->current_address = normalize_addr(P + i * PMD_LEVEL_MULT); if (!pmd_none(*start)) { - pgprotval_t prot = pmd_val(*start) & PTE_FLAGS_MASK; - - if (pmd_large(*start) || !pmd_present(*start)) + if (pmd_large(*start) || !pmd_present(*start)) { + prot = pmd_flags(*start); note_page(m, st, __pgprot(prot), 3); - else + } else { walk_pte_level(m, st, *start, P + i * PMD_LEVEL_MULT); + } } else note_page(m, st, __pgprot(0), 3); start++; @@ -318,19 +331,20 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr, { int i; pud_t *start; + pgprotval_t prot; start = (pud_t *) pgd_page_vaddr(addr); for (i = 0; i < PTRS_PER_PUD; i++) { st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT); if (!pud_none(*start)) { - pgprotval_t prot = pud_val(*start) & PTE_FLAGS_MASK; - - if (pud_large(*start) || !pud_present(*start)) + if (pud_large(*start) || !pud_present(*start)) { + prot = pud_flags(*start); note_page(m, st, __pgprot(prot), 2); - else + } else { walk_pmd_level(m, st, *start, P + i * PUD_LEVEL_MULT); + } } else note_page(m, st, __pgprot(0), 2); @@ -344,13 +358,30 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr, #define pgd_none(a) pud_none(__pud(pgd_val(a))) #endif -void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd) +#ifdef CONFIG_X86_64 +static inline bool is_hypervisor_range(int idx) +{ + /* + * ffff800000000000 - ffff87ffffffffff is reserved for + * the hypervisor. + */ + return paravirt_enabled() && + (idx >= pgd_index(__PAGE_OFFSET) - 16) && + (idx < pgd_index(__PAGE_OFFSET)); +} +#else +static inline bool is_hypervisor_range(int idx) { return false; } +#endif + +static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, + bool checkwx) { #ifdef CONFIG_X86_64 pgd_t *start = (pgd_t *) &init_level4_pgt; #else pgd_t *start = swapper_pg_dir; #endif + pgprotval_t prot; int i; struct pg_state st = {}; @@ -359,16 +390,20 @@ void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd) st.to_dmesg = true; } + st.check_wx = checkwx; + if (checkwx) + st.wx_pages = 0; + for (i = 0; i < PTRS_PER_PGD; i++) { st.current_address = normalize_addr(i * PGD_LEVEL_MULT); - if (!pgd_none(*start)) { - pgprotval_t prot = pgd_val(*start) & PTE_FLAGS_MASK; - - if (pgd_large(*start) || !pgd_present(*start)) + if (!pgd_none(*start) && !is_hypervisor_range(i)) { + if (pgd_large(*start) || !pgd_present(*start)) { + prot = pgd_flags(*start); note_page(m, &st, __pgprot(prot), 1); - else + } else { walk_pud_level(m, &st, *start, i * PGD_LEVEL_MULT); + } } else note_page(m, &st, __pgprot(0), 1); @@ -378,30 +413,28 @@ void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd) /* Flush out the last page */ st.current_address = normalize_addr(PTRS_PER_PGD*PGD_LEVEL_MULT); note_page(m, &st, __pgprot(0), 0); + if (!checkwx) + return; + if (st.wx_pages) + pr_info("x86/mm: Checked W+X mappings: FAILED, %lu W+X pages found.\n", + st.wx_pages); + else + pr_info("x86/mm: Checked W+X mappings: passed, no W+X pages found.\n"); } -static int ptdump_show(struct seq_file *m, void *v) +void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd) { - ptdump_walk_pgd_level(m, NULL); - return 0; + ptdump_walk_pgd_level_core(m, pgd, false); } +EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level); -static int ptdump_open(struct inode *inode, struct file *filp) +void ptdump_walk_pgd_level_checkwx(void) { - return single_open(filp, ptdump_show, NULL); + ptdump_walk_pgd_level_core(NULL, NULL, true); } -static const struct file_operations ptdump_fops = { - .open = ptdump_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static int pt_dump_init(void) +static int __init pt_dump_init(void) { - struct dentry *pe; - #ifdef CONFIG_X86_32 /* Not a compile-time constant on x86-32 */ address_markers[VMALLOC_START_NR].start_address = VMALLOC_START; @@ -412,11 +445,6 @@ static int pt_dump_init(void) address_markers[FIXADDR_START_NR].start_address = FIXADDR_START; #endif - pe = debugfs_create_file("kernel_page_tables", 0600, NULL, NULL, - &ptdump_fops); - if (!pe) - return -ENOMEM; - return 0; } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 9dc909841739..eef44d9a3f77 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -20,6 +20,7 @@ #include <asm/kmemcheck.h> /* kmemcheck_*(), ... */ #include <asm/fixmap.h> /* VSYSCALL_ADDR */ #include <asm/vsyscall.h> /* emulate_vsyscall */ +#include <asm/vm86.h> /* struct vm86 */ #define CREATE_TRACE_POINTS #include <asm/trace/exceptions.h> @@ -301,14 +302,16 @@ static inline void check_v8086_mode(struct pt_regs *regs, unsigned long address, struct task_struct *tsk) { +#ifdef CONFIG_VM86 unsigned long bit; - if (!v8086_mode(regs)) + if (!v8086_mode(regs) || !tsk->thread.vm86) return; bit = (address - 0xA0000) >> PAGE_SHIFT; if (bit < 32) - tsk->thread.screen_bitmap |= 1 << bit; + tsk->thread.vm86->screen_bitmap |= 1 << bit; +#endif } static bool low_pfn(unsigned long pfn) diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index 81bf3d2af3eb..6d5eb5900372 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -9,6 +9,7 @@ #include <linux/vmstat.h> #include <linux/highmem.h> #include <linux/swap.h> +#include <linux/memremap.h> #include <asm/pgtable.h> @@ -63,6 +64,16 @@ retry: #endif } +static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages) +{ + while ((*nr) - nr_start) { + struct page *page = pages[--(*nr)]; + + ClearPageReferenced(page); + put_page(page); + } +} + /* * The performance critical leaf functions are made noinline otherwise gcc * inlines everything into a single function which results in too much @@ -71,7 +82,9 @@ retry: static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { + struct dev_pagemap *pgmap = NULL; unsigned long mask; + int nr_start = *nr; pte_t *ptep; mask = _PAGE_PRESENT|_PAGE_USER; @@ -89,13 +102,21 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, return 0; } - if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) { + page = pte_page(pte); + if (pte_devmap(pte)) { + pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); + if (unlikely(!pgmap)) { + undo_dev_pagemap(nr, nr_start, pages); + pte_unmap(ptep); + return 0; + } + } else if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) { pte_unmap(ptep); return 0; } VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - page = pte_page(pte); get_page(page); + put_dev_pagemap(pgmap); SetPageReferenced(page); pages[*nr] = page; (*nr)++; @@ -114,31 +135,58 @@ static inline void get_head_page_multiple(struct page *page, int nr) SetPageReferenced(page); } +static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr, + unsigned long end, struct page **pages, int *nr) +{ + int nr_start = *nr; + unsigned long pfn = pmd_pfn(pmd); + struct dev_pagemap *pgmap = NULL; + + pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT; + do { + struct page *page = pfn_to_page(pfn); + + pgmap = get_dev_pagemap(pfn, pgmap); + if (unlikely(!pgmap)) { + undo_dev_pagemap(nr, nr_start, pages); + return 0; + } + SetPageReferenced(page); + pages[*nr] = page; + get_page(page); + put_dev_pagemap(pgmap); + (*nr)++; + pfn++; + } while (addr += PAGE_SIZE, addr != end); + return 1; +} + static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { unsigned long mask; - pte_t pte = *(pte_t *)&pmd; struct page *head, *page; int refs; mask = _PAGE_PRESENT|_PAGE_USER; if (write) mask |= _PAGE_RW; - if ((pte_flags(pte) & mask) != mask) + if ((pmd_flags(pmd) & mask) != mask) return 0; + + VM_BUG_ON(!pfn_valid(pmd_pfn(pmd))); + if (pmd_devmap(pmd)) + return __gup_device_huge_pmd(pmd, addr, end, pages, nr); + /* hugepages are never "special" */ - VM_BUG_ON(pte_flags(pte) & _PAGE_SPECIAL); - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + VM_BUG_ON(pmd_flags(pmd) & _PAGE_SPECIAL); refs = 0; - head = pte_page(pte); + head = pmd_page(pmd); page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); do { VM_BUG_ON_PAGE(compound_head(page) != head, page); pages[*nr] = page; - if (PageTail(page)) - get_huge_page_tail(page); (*nr)++; page++; refs++; @@ -159,18 +207,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, pmd_t pmd = *pmdp; next = pmd_addr_end(addr, end); - /* - * The pmd_trans_splitting() check below explains why - * pmdp_splitting_flush has to flush the tlb, to stop - * this gup-fast code from running while we set the - * splitting bit in the pmd. Returning zero will take - * the slow path that will call wait_split_huge_page() - * if the pmd is still in splitting state. gup-fast - * can't because it has irq disabled and - * wait_split_huge_page() would never return as the - * tlb flush IPI wouldn't run. - */ - if (pmd_none(pmd) || pmd_trans_splitting(pmd)) + if (pmd_none(pmd)) return 0; if (unlikely(pmd_large(pmd) || !pmd_present(pmd))) { /* @@ -195,27 +232,24 @@ static noinline int gup_huge_pud(pud_t pud, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { unsigned long mask; - pte_t pte = *(pte_t *)&pud; struct page *head, *page; int refs; mask = _PAGE_PRESENT|_PAGE_USER; if (write) mask |= _PAGE_RW; - if ((pte_flags(pte) & mask) != mask) + if ((pud_flags(pud) & mask) != mask) return 0; /* hugepages are never "special" */ - VM_BUG_ON(pte_flags(pte) & _PAGE_SPECIAL); - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + VM_BUG_ON(pud_flags(pud) & _PAGE_SPECIAL); + VM_BUG_ON(!pfn_valid(pud_pfn(pud))); refs = 0; - head = pte_page(pte); + head = pud_page(pud); page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT); do { VM_BUG_ON_PAGE(compound_head(page) != head, page); pages[*nr] = page; - if (PageTail(page)) - get_huge_page_tail(page); (*nr)++; page++; refs++; diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index eecb207a2037..a6d739258137 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -104,20 +104,6 @@ void __kunmap_atomic(void *kvaddr) } EXPORT_SYMBOL(__kunmap_atomic); -struct page *kmap_atomic_to_page(void *ptr) -{ - unsigned long idx, vaddr = (unsigned long)ptr; - pte_t *pte; - - if (vaddr < FIXADDR_START) - return virt_to_page(ptr); - - idx = virt_to_fix(vaddr); - pte = kmap_pte - (idx - FIX_KMAP_BEGIN); - return pte_page(*pte); -} -EXPORT_SYMBOL(kmap_atomic_to_page); - void __init set_highmem_pages_init(void) { struct zone *zone; diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 8533b46e6bee..493f54172b4a 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -30,8 +30,11 @@ /* * Tables translating between page_cache_type_t and pte encoding. * - * Minimal supported modes are defined statically, they are modified - * during bootup if more supported cache modes are available. + * The default values are defined statically as minimal supported mode; + * WC and WT fall back to UC-. pat_init() updates these values to support + * more cache modes, WC and WT, when it is safe to do so. See pat_init() + * for the details. Note, __early_ioremap() used during early boot-time + * takes pgprot_t (pte encoding) and does not use these tables. * * Index into __cachemode2pte_tbl[] is the cachemode. * @@ -351,7 +354,7 @@ static int __meminit split_mem_range(struct map_range *mr, int nr_range, } for (i = 0; i < nr_range; i++) - printk(KERN_DEBUG " [mem %#010lx-%#010lx] page %s\n", + pr_debug(" [mem %#010lx-%#010lx] page %s\n", mr[i].start, mr[i].end - 1, page_size_string(&mr[i])); @@ -398,7 +401,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, unsigned long ret = 0; int nr_range, i; - pr_info("init_memory_mapping: [mem %#010lx-%#010lx]\n", + pr_debug("init_memory_mapping: [mem %#010lx-%#010lx]\n", start, end - 1); memset(mr, 0, sizeof(mr)); @@ -690,14 +693,12 @@ void free_initmem(void) #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { -#ifdef CONFIG_MICROCODE_EARLY /* * Remember, initrd memory may contain microcode or other useful things. * Before we lose initrd mem, we need to find a place to hold them * now that normal virtual memory is enabled. */ save_microcode_in_initrd(); -#endif /* * end could be not aligned, and We can not align that, diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 8340e45c891a..cb4ef3de61f9 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -137,6 +137,7 @@ page_table_range_init_count(unsigned long start, unsigned long end) vaddr = start; pgd_idx = pgd_index(vaddr); + pmd_idx = pmd_index(vaddr); for ( ; (pgd_idx < PTRS_PER_PGD) && (vaddr != end); pgd_idx++) { for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end); @@ -822,11 +823,11 @@ void __init mem_init(void) } #ifdef CONFIG_MEMORY_HOTPLUG -int arch_add_memory(int nid, u64 start, u64 size) +int arch_add_memory(int nid, u64 start, u64 size, bool for_device) { struct pglist_data *pgdata = NODE_DATA(nid); struct zone *zone = pgdata->node_zones + - zone_for_memory(nid, start, size, ZONE_HIGHMEM); + zone_for_memory(nid, start, size, ZONE_HIGHMEM, for_device); unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; @@ -956,6 +957,8 @@ void mark_rodata_ro(void) set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); #endif mark_nxdata_nx(); + if (__supported_pte_mask & _PAGE_NX) + debug_checkwx(); } #endif diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 3fba623e3ba5..5488d21123bd 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -30,6 +30,7 @@ #include <linux/module.h> #include <linux/memory.h> #include <linux/memory_hotplug.h> +#include <linux/memremap.h> #include <linux/nmi.h> #include <linux/gfp.h> #include <linux/kcore.h> @@ -687,11 +688,11 @@ static void update_end_of_memory_vars(u64 start, u64 size) * Memory is added always to NORMAL zone. This means you will never get * additional DMA/DMA32 memory. */ -int arch_add_memory(int nid, u64 start, u64 size) +int arch_add_memory(int nid, u64 start, u64 size, bool for_device) { struct pglist_data *pgdat = NODE_DATA(nid); struct zone *zone = pgdat->node_zones + - zone_for_memory(nid, start, size, ZONE_NORMAL); + zone_for_memory(nid, start, size, ZONE_NORMAL, for_device); unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; int ret; @@ -714,6 +715,12 @@ static void __meminit free_pagetable(struct page *page, int order) { unsigned long magic; unsigned int nr_pages = 1 << order; + struct vmem_altmap *altmap = to_vmem_altmap((unsigned long) page); + + if (altmap) { + vmem_altmap_free(altmap, nr_pages); + return; + } /* bootmem page has reserved flag */ if (PageReserved(page)) { @@ -814,8 +821,7 @@ remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end, if (phys_addr < (phys_addr_t)0x40000000) return; - if (IS_ALIGNED(addr, PAGE_SIZE) && - IS_ALIGNED(next, PAGE_SIZE)) { + if (PAGE_ALIGNED(addr) && PAGE_ALIGNED(next)) { /* * Do not free direct mapping pages since they were * freed when offlining, or simplely not in use. @@ -1018,13 +1024,19 @@ int __ref arch_remove_memory(u64 start, u64 size) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; + struct page *page = pfn_to_page(start_pfn); + struct vmem_altmap *altmap; struct zone *zone; int ret; - zone = page_zone(pfn_to_page(start_pfn)); - kernel_physical_mapping_remove(start, start + size); + /* With altmap the first mapped page is offset from @start */ + altmap = to_vmem_altmap((unsigned long) page); + if (altmap) + page += vmem_altmap_offset(altmap); + zone = page_zone(page); ret = __remove_pages(zone, start_pfn, nr_pages); WARN_ON_ONCE(ret); + kernel_physical_mapping_remove(start, start + size); return ret; } @@ -1132,7 +1144,7 @@ void mark_rodata_ro(void) * has been zapped already via cleanup_highmem(). */ all_end = roundup((unsigned long)_brk_end, PMD_SIZE); - set_memory_nx(rodata_start, (all_end - rodata_start) >> PAGE_SHIFT); + set_memory_nx(text_end, (all_end - text_end) >> PAGE_SHIFT); rodata_test(); @@ -1150,6 +1162,8 @@ void mark_rodata_ro(void) free_init_pages("unused kernel", (unsigned long) __va(__pa_symbol(rodata_end)), (unsigned long) __va(__pa_symbol(_sdata))); + + debug_checkwx(); } #endif @@ -1234,7 +1248,7 @@ static void __meminitdata *p_start, *p_end; static int __meminitdata node_start; static int __meminit vmemmap_populate_hugepages(unsigned long start, - unsigned long end, int node) + unsigned long end, int node, struct vmem_altmap *altmap) { unsigned long addr; unsigned long next; @@ -1257,7 +1271,7 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, if (pmd_none(*pmd)) { void *p; - p = vmemmap_alloc_block_buf(PMD_SIZE, node); + p = __vmemmap_alloc_block_buf(PMD_SIZE, node, altmap); if (p) { pte_t entry; @@ -1268,7 +1282,7 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, /* check to see if we have contiguous blocks */ if (p_end != p || node_start != node) { if (p_start) - printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n", + pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n", addr_start, addr_end-1, p_start, p_end-1, node_start); addr_start = addr; node_start = node; @@ -1278,7 +1292,8 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, addr_end = addr + PMD_SIZE; p_end = p + PMD_SIZE; continue; - } + } else if (altmap) + return -ENOMEM; /* no fallback */ } else if (pmd_large(*pmd)) { vmemmap_verify((pte_t *)pmd, node, addr, next); continue; @@ -1292,11 +1307,16 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) { + struct vmem_altmap *altmap = to_vmem_altmap(start); int err; if (cpu_has_pse) - err = vmemmap_populate_hugepages(start, end, node); - else + err = vmemmap_populate_hugepages(start, end, node, altmap); + else if (altmap) { + pr_err_once("%s: no cpu support for altmap allocations\n", + __func__); + err = -ENOMEM; + } else err = vmemmap_populate_basepages(start, end, node); if (!err) sync_global_pgds(start, end - 1, 0); @@ -1366,7 +1386,7 @@ void register_page_bootmem_memmap(unsigned long section_nr, void __meminit vmemmap_populate_print_last(void) { if (p_start) { - printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n", + pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n", addr_start, addr_end-1, p_start, p_end-1, node_start); p_start = NULL; p_end = NULL; diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index b9c78f3bcd67..0d8d53d1f5cc 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -194,8 +194,8 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, * Check if the request spans more than any BAR in the iomem resource * tree. */ - WARN_ONCE(iomem_map_sanity_check(unaligned_phys_addr, unaligned_size), - KERN_INFO "Info: mapping multiple BARs. Your kernel is fine."); + if (iomem_map_sanity_check(unaligned_phys_addr, unaligned_size)) + pr_warn("caller %pS mapping multiple BARs\n", caller); return ret_addr; err_free_area: diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index e1840f3db5b5..d470cf219a2d 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -12,20 +12,6 @@ extern pgd_t early_level4_pgt[PTRS_PER_PGD]; extern struct range pfn_mapped[E820_X_MAX]; -static pud_t kasan_zero_pud[PTRS_PER_PUD] __page_aligned_bss; -static pmd_t kasan_zero_pmd[PTRS_PER_PMD] __page_aligned_bss; -static pte_t kasan_zero_pte[PTRS_PER_PTE] __page_aligned_bss; - -/* - * This page used as early shadow. We don't use empty_zero_page - * at early stages, stack instrumentation could write some garbage - * to this page. - * Latter we reuse it as zero shadow for large ranges of memory - * that allowed to access, but not instrumented by kasan - * (vmalloc/vmemmap ...). - */ -static unsigned char kasan_zero_page[PAGE_SIZE] __page_aligned_bss; - static int __init map_range(struct range *range) { unsigned long start; @@ -62,106 +48,6 @@ static void __init kasan_map_early_shadow(pgd_t *pgd) } } -static int __init zero_pte_populate(pmd_t *pmd, unsigned long addr, - unsigned long end) -{ - pte_t *pte = pte_offset_kernel(pmd, addr); - - while (addr + PAGE_SIZE <= end) { - WARN_ON(!pte_none(*pte)); - set_pte(pte, __pte(__pa_nodebug(kasan_zero_page) - | __PAGE_KERNEL_RO)); - addr += PAGE_SIZE; - pte = pte_offset_kernel(pmd, addr); - } - return 0; -} - -static int __init zero_pmd_populate(pud_t *pud, unsigned long addr, - unsigned long end) -{ - int ret = 0; - pmd_t *pmd = pmd_offset(pud, addr); - - while (IS_ALIGNED(addr, PMD_SIZE) && addr + PMD_SIZE <= end) { - WARN_ON(!pmd_none(*pmd)); - set_pmd(pmd, __pmd(__pa_nodebug(kasan_zero_pte) - | _KERNPG_TABLE)); - addr += PMD_SIZE; - pmd = pmd_offset(pud, addr); - } - if (addr < end) { - if (pmd_none(*pmd)) { - void *p = vmemmap_alloc_block(PAGE_SIZE, NUMA_NO_NODE); - if (!p) - return -ENOMEM; - set_pmd(pmd, __pmd(__pa_nodebug(p) | _KERNPG_TABLE)); - } - ret = zero_pte_populate(pmd, addr, end); - } - return ret; -} - - -static int __init zero_pud_populate(pgd_t *pgd, unsigned long addr, - unsigned long end) -{ - int ret = 0; - pud_t *pud = pud_offset(pgd, addr); - - while (IS_ALIGNED(addr, PUD_SIZE) && addr + PUD_SIZE <= end) { - WARN_ON(!pud_none(*pud)); - set_pud(pud, __pud(__pa_nodebug(kasan_zero_pmd) - | _KERNPG_TABLE)); - addr += PUD_SIZE; - pud = pud_offset(pgd, addr); - } - - if (addr < end) { - if (pud_none(*pud)) { - void *p = vmemmap_alloc_block(PAGE_SIZE, NUMA_NO_NODE); - if (!p) - return -ENOMEM; - set_pud(pud, __pud(__pa_nodebug(p) | _KERNPG_TABLE)); - } - ret = zero_pmd_populate(pud, addr, end); - } - return ret; -} - -static int __init zero_pgd_populate(unsigned long addr, unsigned long end) -{ - int ret = 0; - pgd_t *pgd = pgd_offset_k(addr); - - while (IS_ALIGNED(addr, PGDIR_SIZE) && addr + PGDIR_SIZE <= end) { - WARN_ON(!pgd_none(*pgd)); - set_pgd(pgd, __pgd(__pa_nodebug(kasan_zero_pud) - | _KERNPG_TABLE)); - addr += PGDIR_SIZE; - pgd = pgd_offset_k(addr); - } - - if (addr < end) { - if (pgd_none(*pgd)) { - void *p = vmemmap_alloc_block(PAGE_SIZE, NUMA_NO_NODE); - if (!p) - return -ENOMEM; - set_pgd(pgd, __pgd(__pa_nodebug(p) | _KERNPG_TABLE)); - } - ret = zero_pud_populate(pgd, addr, end); - } - return ret; -} - - -static void __init populate_zero_shadow(const void *start, const void *end) -{ - if (zero_pgd_populate((unsigned long)start, (unsigned long)end)) - panic("kasan: unable to map zero shadow!"); -} - - #ifdef CONFIG_KASAN_INLINE static int kasan_die_handler(struct notifier_block *self, unsigned long val, @@ -213,7 +99,7 @@ void __init kasan_init(void) clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END); - populate_zero_shadow((void *)KASAN_SHADOW_START, + kasan_populate_zero_shadow((void *)KASAN_SHADOW_START, kasan_mem_to_shadow((void *)PAGE_OFFSET)); for (i = 0; i < E820_X_MAX; i++) { @@ -223,14 +109,15 @@ void __init kasan_init(void) if (map_range(&pfn_mapped[i])) panic("kasan: unable to allocate shadow!"); } - populate_zero_shadow(kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM), - kasan_mem_to_shadow((void *)__START_KERNEL_map)); + kasan_populate_zero_shadow( + kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM), + kasan_mem_to_shadow((void *)__START_KERNEL_map)); vmemmap_populate((unsigned long)kasan_mem_to_shadow(_stext), (unsigned long)kasan_mem_to_shadow(_end), NUMA_NO_NODE); - populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END), + kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END), (void *)KASAN_SHADOW_END); memset(kasan_zero_page, 0, PAGE_SIZE); @@ -239,5 +126,5 @@ void __init kasan_init(void) __flush_tlb_all(); init_task.kasan_depth = 0; - pr_info("Kernel address sanitizer initialized\n"); + pr_info("KernelAddressSanitizer initialized\n"); } diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 844b06d67df4..96bd1e2bffaf 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -69,14 +69,14 @@ unsigned long arch_mmap_rnd(void) { unsigned long rnd; - /* - * 8 bits of randomness in 32bit mmaps, 20 address space bits - * 28 bits of randomness in 64bit mmaps, 40 address space bits - */ if (mmap_is_ia32()) - rnd = (unsigned long)get_random_int() % (1<<8); +#ifdef CONFIG_COMPAT + rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_compat_bits) - 1); +#else + rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1); +#endif else - rnd = (unsigned long)get_random_int() % (1<<28); + rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1); return rnd << PAGE_SHIFT; } diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index db1b0bc5017c..b2fd67da1701 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -42,58 +42,21 @@ static inline unsigned long mpx_bt_size_bytes(struct mm_struct *mm) */ static unsigned long mpx_mmap(unsigned long len) { - unsigned long ret; - unsigned long addr, pgoff; struct mm_struct *mm = current->mm; - vm_flags_t vm_flags; - struct vm_area_struct *vma; + unsigned long addr, populate; /* Only bounds table can be allocated here */ if (len != mpx_bt_size_bytes(mm)) return -EINVAL; down_write(&mm->mmap_sem); - - /* Too many mappings? */ - if (mm->map_count > sysctl_max_map_count) { - ret = -ENOMEM; - goto out; - } - - /* Obtain the address to map to. we verify (or select) it and ensure - * that it represents a valid section of the address space. - */ - addr = get_unmapped_area(NULL, 0, len, 0, MAP_ANONYMOUS | MAP_PRIVATE); - if (addr & ~PAGE_MASK) { - ret = addr; - goto out; - } - - vm_flags = VM_READ | VM_WRITE | VM_MPX | - mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; - - /* Set pgoff according to addr for anon_vma */ - pgoff = addr >> PAGE_SHIFT; - - ret = mmap_region(NULL, addr, len, vm_flags, pgoff); - if (IS_ERR_VALUE(ret)) - goto out; - - vma = find_vma(mm, ret); - if (!vma) { - ret = -ENOMEM; - goto out; - } - - if (vm_flags & VM_LOCKED) { - up_write(&mm->mmap_sem); - mm_populate(ret, len); - return ret; - } - -out: + addr = do_mmap(NULL, 0, len, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, VM_MPX, 0, &populate); up_write(&mm->mmap_sem); - return ret; + if (populate) + mm_populate(addr, populate); + + return addr; } enum reg_type { @@ -138,19 +101,19 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs, switch (type) { case REG_TYPE_RM: regno = X86_MODRM_RM(insn->modrm.value); - if (X86_REX_B(insn->rex_prefix.value) == 1) + if (X86_REX_B(insn->rex_prefix.value)) regno += 8; break; case REG_TYPE_INDEX: regno = X86_SIB_INDEX(insn->sib.value); - if (X86_REX_X(insn->rex_prefix.value) == 1) + if (X86_REX_X(insn->rex_prefix.value)) regno += 8; break; case REG_TYPE_BASE: regno = X86_SIB_BASE(insn->sib.value); - if (X86_REX_B(insn->rex_prefix.value) == 1) + if (X86_REX_B(insn->rex_prefix.value)) regno += 8; break; @@ -274,7 +237,8 @@ bad_opcode: */ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs) { - const struct bndreg *bndregs, *bndreg; + const struct mpx_bndreg_state *bndregs; + const struct mpx_bndreg *bndreg; siginfo_t *info = NULL; struct insn insn; uint8_t bndregno; @@ -295,13 +259,13 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs) goto err_out; } /* get bndregs field from current task's xsave area */ - bndregs = get_xsave_field_ptr(XSTATE_BNDREGS); + bndregs = get_xsave_field_ptr(XFEATURE_MASK_BNDREGS); if (!bndregs) { err = -EINVAL; goto err_out; } /* now go select the individual register in the set of 4 */ - bndreg = &bndregs[bndregno]; + bndreg = &bndregs->bndreg[bndregno]; info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) { @@ -343,7 +307,7 @@ err_out: static __user void *mpx_get_bounds_dir(void) { - const struct bndcsr *bndcsr; + const struct mpx_bndcsr *bndcsr; if (!cpu_feature_enabled(X86_FEATURE_MPX)) return MPX_INVALID_BOUNDS_DIR; @@ -352,7 +316,7 @@ static __user void *mpx_get_bounds_dir(void) * The bounds directory pointer is stored in a register * only accessible if we first do an xsave. */ - bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR); + bndcsr = get_xsave_field_ptr(XFEATURE_MASK_BNDCSR); if (!bndcsr) return MPX_INVALID_BOUNDS_DIR; @@ -526,10 +490,10 @@ out_unmap: static int do_mpx_bt_fault(void) { unsigned long bd_entry, bd_base; - const struct bndcsr *bndcsr; + const struct mpx_bndcsr *bndcsr; struct mm_struct *mm = current->mm; - bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR); + bndcsr = get_xsave_field_ptr(XFEATURE_MASK_BNDCSR); if (!bndcsr) return -EINVAL; /* @@ -622,6 +586,29 @@ static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm, } /* + * We only want to do a 4-byte get_user() on 32-bit. Otherwise, + * we might run off the end of the bounds table if we are on + * a 64-bit kernel and try to get 8 bytes. + */ +int get_user_bd_entry(struct mm_struct *mm, unsigned long *bd_entry_ret, + long __user *bd_entry_ptr) +{ + u32 bd_entry_32; + int ret; + + if (is_64bit_mm(mm)) + return get_user(*bd_entry_ret, bd_entry_ptr); + + /* + * Note that get_user() uses the type of the *pointer* to + * establish the size of the get, not the destination. + */ + ret = get_user(bd_entry_32, (u32 __user *)bd_entry_ptr); + *bd_entry_ret = bd_entry_32; + return ret; +} + +/* * Get the base of bounds tables pointed by specific bounds * directory entry. */ @@ -641,7 +628,7 @@ static int get_bt_addr(struct mm_struct *mm, int need_write = 0; pagefault_disable(); - ret = get_user(bd_entry, bd_entry_ptr); + ret = get_user_bd_entry(mm, &bd_entry, bd_entry_ptr); pagefault_enable(); if (!ret) break; @@ -736,11 +723,23 @@ static unsigned long mpx_get_bt_entry_offset_bytes(struct mm_struct *mm, */ 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; + unsigned long long virt_space; + unsigned long long GB = (1ULL << 30); + + /* + * This covers 32-bit emulation as well as 32-bit kernels + * running on 64-bit harware. + */ + if (!is_64bit_mm(mm)) + return (4ULL * GB) / MPX_BD_NR_ENTRIES_32; + + /* + * 'x86_virt_bits' returns what the hardware is capable + * of, and returns the full >32-bit adddress space when + * running 32-bit kernels on 64-bit hardware. + */ + virt_space = (1ULL << boot_cpu_data.x86_virt_bits); + return virt_space / MPX_BD_NR_ENTRIES_64; } /* diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 4053bb58bf92..c3b3f653ed0c 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -246,8 +246,10 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi) bi->start = max(bi->start, low); bi->end = min(bi->end, high); - /* and there's no empty block */ - if (bi->start >= bi->end) + /* and there's no empty or non-exist block */ + if (bi->start >= bi->end || + !memblock_overlaps_region(&memblock.memory, + bi->start, bi->end - bi->start)) numa_remove_memblk_from(i--, mi); } diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c index 8ff686aa7e8c..5f169d5d76a8 100644 --- a/arch/x86/mm/pageattr-test.c +++ b/arch/x86/mm/pageattr-test.c @@ -8,6 +8,7 @@ #include <linux/kthread.h> #include <linux/random.h> #include <linux/kernel.h> +#include <linux/init.h> #include <linux/mm.h> #include <linux/vmalloc.h> @@ -256,5 +257,4 @@ static int start_pageattr_test(void) return 0; } - -module_init(start_pageattr_test); +device_initcall(start_pageattr_test); diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 727158cb3b3c..fc6a4c8f6e2a 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -4,7 +4,6 @@ */ #include <linux/highmem.h> #include <linux/bootmem.h> -#include <linux/module.h> #include <linux/sched.h> #include <linux/mm.h> #include <linux/interrupt.h> @@ -67,6 +66,9 @@ void update_page_count(int level, unsigned long pages) static void split_page_count(int level) { + if (direct_pages_count[level] == 0) + return; + direct_pages_count[level]--; direct_pages_count[level - 1] += PTRS_PER_PTE; } @@ -130,14 +132,16 @@ within(unsigned long addr, unsigned long start, unsigned long end) */ void clflush_cache_range(void *vaddr, unsigned int size) { - unsigned long clflush_mask = boot_cpu_data.x86_clflush_size - 1; + const unsigned long clflush_size = boot_cpu_data.x86_clflush_size; + void *p = (void *)((unsigned long)vaddr & ~(clflush_size - 1)); void *vend = vaddr + size; - void *p; + + if (p >= vend) + return; mb(); - for (p = (void *)((unsigned long)vaddr & ~clflush_mask); - p < vend; p += boot_cpu_data.x86_clflush_size) + for (; p < vend; p += clflush_size) clflushopt(p); mb(); @@ -415,18 +419,28 @@ pmd_t *lookup_pmd_address(unsigned long address) phys_addr_t slow_virt_to_phys(void *__virt_addr) { unsigned long virt_addr = (unsigned long)__virt_addr; - phys_addr_t phys_addr; - unsigned long offset; + unsigned long phys_addr, offset; enum pg_level level; - unsigned long pmask; pte_t *pte; pte = lookup_address(virt_addr, &level); BUG_ON(!pte); - pmask = page_level_mask(level); - offset = virt_addr & ~pmask; - phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; - return (phys_addr | offset); + + switch (level) { + case PG_LEVEL_1G: + phys_addr = pud_pfn(*(pud_t *)pte) << PAGE_SHIFT; + offset = virt_addr & ~PUD_PAGE_MASK; + break; + case PG_LEVEL_2M: + phys_addr = pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT; + offset = virt_addr & ~PMD_PAGE_MASK; + break; + default: + phys_addr = pte_pfn(*pte) << PAGE_SHIFT; + offset = virt_addr & ~PAGE_MASK; + } + + return (phys_addr_t)(phys_addr | offset); } EXPORT_SYMBOL_GPL(slow_virt_to_phys); @@ -459,7 +473,7 @@ static int try_preserve_large_page(pte_t *kpte, unsigned long address, struct cpa_data *cpa) { - unsigned long nextpage_addr, numpages, pmask, psize, addr, pfn; + unsigned long nextpage_addr, numpages, pmask, psize, addr, pfn, old_pfn; pte_t new_pte, old_pte, *tmp; pgprot_t old_prot, new_prot, req_prot; int i, do_split = 1; @@ -479,17 +493,21 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, switch (level) { case PG_LEVEL_2M: -#ifdef CONFIG_X86_64 + old_prot = pmd_pgprot(*(pmd_t *)kpte); + old_pfn = pmd_pfn(*(pmd_t *)kpte); + break; case PG_LEVEL_1G: -#endif - psize = page_level_size(level); - pmask = page_level_mask(level); + old_prot = pud_pgprot(*(pud_t *)kpte); + old_pfn = pud_pfn(*(pud_t *)kpte); break; default: do_split = -EINVAL; goto out_unlock; } + psize = page_level_size(level); + pmask = page_level_mask(level); + /* * Calculate the number of pages, which fit into this large * page starting at address: @@ -505,7 +523,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * up accordingly. */ old_pte = *kpte; - old_prot = req_prot = pgprot_large_2_4k(pte_pgprot(old_pte)); + req_prot = pgprot_large_2_4k(old_prot); pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr); pgprot_val(req_prot) |= pgprot_val(cpa->mask_set); @@ -531,10 +549,10 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, req_prot = canon_pgprot(req_prot); /* - * old_pte points to the large page base address. So we need + * old_pfn points to the large page base pfn. So we need * to add the offset of the virtual address: */ - pfn = pte_pfn(old_pte) + ((address & (psize - 1)) >> PAGE_SHIFT); + pfn = old_pfn + ((address & (psize - 1)) >> PAGE_SHIFT); cpa->pfn = pfn; new_prot = static_protections(req_prot, address, pfn); @@ -545,7 +563,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * the pages in the range we try to preserve: */ addr = address & pmask; - pfn = pte_pfn(old_pte); + pfn = old_pfn; for (i = 0; i < (psize >> PAGE_SHIFT); i++, addr += PAGE_SIZE, pfn++) { pgprot_t chk_prot = static_protections(req_prot, addr, pfn); @@ -575,7 +593,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * The address is aligned and the number of pages * covers the full page. */ - new_pte = pfn_pte(pte_pfn(old_pte), new_prot); + new_pte = pfn_pte(old_pfn, new_prot); __set_pmd_pte(kpte, address, new_pte); cpa->flags |= CPA_FLUSHTLB; do_split = 0; @@ -592,7 +610,7 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, struct page *base) { pte_t *pbase = (pte_t *)page_address(base); - unsigned long pfn, pfninc = 1; + unsigned long ref_pfn, pfn, pfninc = 1; unsigned int i, level; pte_t *tmp; pgprot_t ref_prot; @@ -609,26 +627,33 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, } paravirt_alloc_pte(&init_mm, page_to_pfn(base)); - ref_prot = pte_pgprot(pte_clrhuge(*kpte)); - /* promote PAT bit to correct position */ - if (level == PG_LEVEL_2M) + switch (level) { + case PG_LEVEL_2M: + ref_prot = pmd_pgprot(*(pmd_t *)kpte); + /* clear PSE and promote PAT bit to correct position */ ref_prot = pgprot_large_2_4k(ref_prot); + ref_pfn = pmd_pfn(*(pmd_t *)kpte); + break; -#ifdef CONFIG_X86_64 - if (level == PG_LEVEL_1G) { + case PG_LEVEL_1G: + ref_prot = pud_pgprot(*(pud_t *)kpte); + ref_pfn = pud_pfn(*(pud_t *)kpte); pfninc = PMD_PAGE_SIZE >> PAGE_SHIFT; + /* - * Set the PSE flags only if the PRESENT flag is set + * Clear the PSE flags if the PRESENT flag is not set * otherwise pmd_present/pmd_huge will return true * even on a non present pmd. */ - if (pgprot_val(ref_prot) & _PAGE_PRESENT) - pgprot_val(ref_prot) |= _PAGE_PSE; - else + if (!(pgprot_val(ref_prot) & _PAGE_PRESENT)) pgprot_val(ref_prot) &= ~_PAGE_PSE; + break; + + default: + spin_unlock(&pgd_lock); + return 1; } -#endif /* * Set the GLOBAL flags only if the PRESENT flag is set @@ -644,13 +669,16 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, /* * Get the target pfn from the original entry: */ - pfn = pte_pfn(*kpte); + pfn = ref_pfn; for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc) set_pte(&pbase[i], pfn_pte(pfn, canon_pgprot(ref_prot))); - if (pfn_range_is_mapped(PFN_DOWN(__pa(address)), - PFN_DOWN(__pa(address)) + 1)) - split_page_count(level); + if (virt_addr_valid(address)) { + unsigned long pfn = PFN_DOWN(__pa(address)); + + if (pfn_range_is_mapped(pfn, pfn + 1)) + split_page_count(level); + } /* * Install the new, split up pagetable. diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 188e3e07eeeb..f4ae536b0914 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -12,6 +12,7 @@ #include <linux/debugfs.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/pfn_t.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/fs.h> @@ -586,7 +587,7 @@ int free_memtype(u64 start, u64 end) entry = rbt_memtype_erase(start, end); spin_unlock(&memtype_lock); - if (!entry) { + if (IS_ERR(entry)) { pr_info("x86/PAT: %s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n", current->comm, current->pid, start, end - 1); return -EINVAL; @@ -949,7 +950,7 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, } int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, - unsigned long pfn) + pfn_t pfn) { enum page_cache_mode pcm; @@ -957,7 +958,7 @@ int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, return 0; /* Set prot based on lookup */ - pcm = lookup_memtype((resource_size_t)pfn << PAGE_SHIFT); + pcm = lookup_memtype(pfn_t_to_phys(pfn)); *prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) | cachemode2protval(pcm)); @@ -992,6 +993,16 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, vma->vm_flags &= ~VM_PAT; } +/* + * untrack_pfn_moved is called, while mremapping a pfnmap for a new region, + * with the old vma after its pfnmap page table has been removed. The new + * vma has a new pfnmap to the same pfn & cache type with VM_PAT set. + */ +void untrack_pfn_moved(struct vm_area_struct *vma) +{ + vma->vm_flags &= ~VM_PAT; +} + pgprot_t pgprot_writecombine(pgprot_t prot) { return __pgprot(pgprot_val(prot) | diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c index 63931080366a..2f7702253ccf 100644 --- a/arch/x86/mm/pat_rbtree.c +++ b/arch/x86/mm/pat_rbtree.c @@ -98,8 +98,13 @@ static struct memtype *memtype_rb_lowest_match(struct rb_root *root, return last_lower; /* Returns NULL if there is no overlap */ } -static struct memtype *memtype_rb_exact_match(struct rb_root *root, - u64 start, u64 end) +enum { + MEMTYPE_EXACT_MATCH = 0, + MEMTYPE_END_MATCH = 1 +}; + +static struct memtype *memtype_rb_match(struct rb_root *root, + u64 start, u64 end, int match_type) { struct memtype *match; @@ -107,7 +112,12 @@ static struct memtype *memtype_rb_exact_match(struct rb_root *root, while (match != NULL && match->start < end) { struct rb_node *node; - if (match->start == start && match->end == end) + if ((match_type == MEMTYPE_EXACT_MATCH) && + (match->start == start) && (match->end == end)) + return match; + + if ((match_type == MEMTYPE_END_MATCH) && + (match->start < start) && (match->end == end)) return match; node = rb_next(&match->rb); @@ -117,7 +127,7 @@ static struct memtype *memtype_rb_exact_match(struct rb_root *root, match = NULL; } - return NULL; /* Returns NULL if there is no exact match */ + return NULL; /* Returns NULL if there is no match */ } static int memtype_rb_check_conflict(struct rb_root *root, @@ -210,12 +220,36 @@ struct memtype *rbt_memtype_erase(u64 start, u64 end) { struct memtype *data; - data = memtype_rb_exact_match(&memtype_rbroot, start, end); - if (!data) - goto out; + /* + * Since the memtype_rbroot tree allows overlapping ranges, + * rbt_memtype_erase() checks with EXACT_MATCH first, i.e. free + * a whole node for the munmap case. If no such entry is found, + * it then checks with END_MATCH, i.e. shrink the size of a node + * from the end for the mremap case. + */ + data = memtype_rb_match(&memtype_rbroot, start, end, + MEMTYPE_EXACT_MATCH); + if (!data) { + data = memtype_rb_match(&memtype_rbroot, start, end, + MEMTYPE_END_MATCH); + if (!data) + return ERR_PTR(-EINVAL); + } + + if (data->start == start) { + /* munmap: erase this node */ + rb_erase_augmented(&data->rb, &memtype_rbroot, + &memtype_rb_augment_cb); + } else { + /* mremap: update the end value of this node */ + rb_erase_augmented(&data->rb, &memtype_rbroot, + &memtype_rb_augment_cb); + data->end = start; + data->subtree_max_end = data->end; + memtype_rb_insert(&memtype_rbroot, data); + return NULL; + } - rb_erase_augmented(&data->rb, &memtype_rbroot, &memtype_rb_augment_cb); -out: return data; } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index fb0a9dd1d6e4..4eb287e25043 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -414,7 +414,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, if (changed && dirty) { *ptep = entry; - pte_update_defer(vma->vm_mm, address, ptep); + pte_update(vma->vm_mm, address, ptep); } return changed; @@ -431,7 +431,6 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, if (changed && dirty) { *pmdp = entry; - pmd_update_defer(vma->vm_mm, address, pmdp); /* * We had a write-protection fault here and changed the pmd * to to more permissive. No need to flush the TLB for that, @@ -469,9 +468,6 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma, ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, (unsigned long *)pmdp); - if (ret) - pmd_update(vma->vm_mm, addr, pmdp); - return ret; } #endif @@ -509,20 +505,6 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma, return young; } - -void pmdp_splitting_flush(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp) -{ - int set; - VM_BUG_ON(address & ~HPAGE_PMD_MASK); - set = !test_and_set_bit(_PAGE_BIT_SPLITTING, - (unsigned long *)pmdp); - if (set) { - pmd_update(vma->vm_mm, address, pmdp); - /* need tlb flush only to serialize against gup-fast */ - flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); - } -} #endif /** diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c index 90555bf60aa4..92e2eacb3321 100644 --- a/arch/x86/mm/setup_nx.c +++ b/arch/x86/mm/setup_nx.c @@ -31,7 +31,7 @@ early_param("noexec", noexec_setup); void x86_configure_nx(void) { - if (cpu_has_nx && !disable_nx) + if (boot_cpu_has(X86_FEATURE_NX) && !disable_nx) __supported_pte_mask |= _PAGE_NX; else __supported_pte_mask &= ~_PAGE_NX; @@ -39,7 +39,7 @@ void x86_configure_nx(void) void __init x86_report_nx(void) { - if (!cpu_has_nx) { + if (!boot_cpu_has(X86_FEATURE_NX)) { printk(KERN_NOTICE "Notice: NX (Execute Disable) protection " "missing in CPU!\n"); } else { diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index 66338a60aa6e..b5f821881465 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -192,16 +192,19 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) node_set(node, numa_nodes_parsed); - pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s\n", + pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s%s\n", node, pxm, (unsigned long long) start, (unsigned long long) end - 1, - hotpluggable ? " hotplug" : ""); + hotpluggable ? " hotplug" : "", + ma->flags & ACPI_SRAT_MEM_NON_VOLATILE ? " non-volatile" : ""); /* Mark hotplug range in memblock. */ if (hotpluggable && memblock_mark_hotplug(start, ma->length)) pr_warn("SRAT: Failed to mark hotplug range [mem %#010Lx-%#010Lx] in memblock\n", (unsigned long long)start, (unsigned long long)end - 1); + max_possible_pfn = max(max_possible_pfn, PFN_UP(end - 1)); + return 0; out_err_bad_srat: bad_srat(); diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 90b924acd982..8f4cc3dfac32 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -140,6 +140,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask, info.flush_end = end; count_vm_tlb_event(NR_TLB_REMOTE_FLUSH); + trace_tlb_flush(TLB_REMOTE_SEND_IPI, end - start); if (is_uv_system()) { unsigned int cpu; @@ -160,7 +161,10 @@ void flush_tlb_current_task(void) preempt_disable(); count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); + + /* This is an implicit full barrier that synchronizes with switch_mm. */ local_flush_tlb(); + trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL); if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL); @@ -187,17 +191,29 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long base_pages_to_flush = TLB_FLUSH_ALL; preempt_disable(); - if (current->active_mm != mm) + if (current->active_mm != mm) { + /* Synchronize with switch_mm. */ + smp_mb(); + goto out; + } if (!current->mm) { leave_mm(smp_processor_id()); + + /* Synchronize with switch_mm. */ + smp_mb(); + goto out; } if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB)) base_pages_to_flush = (end - start) >> PAGE_SHIFT; + /* + * Both branches below are implicit full barriers (MOV to CR or + * INVLPG) that synchronize with switch_mm. + */ if (base_pages_to_flush > tlb_single_page_flush_ceiling) { base_pages_to_flush = TLB_FLUSH_ALL; count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); @@ -227,10 +243,18 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start) preempt_disable(); if (current->active_mm == mm) { - if (current->mm) + if (current->mm) { + /* + * Implicit full barrier (INVLPG) that synchronizes + * with switch_mm. + */ __flush_tlb_one(start); - else + } else { leave_mm(smp_processor_id()); + + /* Synchronize with switch_mm. */ + smp_mb(); + } } if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index be2e7a2b10d7..4286f3618bd0 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -193,7 +193,7 @@ struct jit_context { 32 /* space for rbx, r13, r14, r15 */ + \ 8 /* space for skb_copy_bits() buffer */) -#define PROLOGUE_SIZE 51 +#define PROLOGUE_SIZE 48 /* emit x64 prologue code for BPF program and check it's size. * bpf_tail_call helper will skip it while jumping into another program @@ -229,11 +229,15 @@ static void emit_prologue(u8 **pprog) /* mov qword ptr [rbp-X],r15 */ 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 the tail call counter (tail_call_cnt): for eBPF tail calls + * we need to reset the counter to 0. It's done in two instructions, + * resetting rax register to 0 (xor on eax gets 0 extended), and + * moving it to the counter location. + */ - /* clear tail_cnt: mov qword ptr [rbp-X], rax */ + /* xor eax, eax */ + EMIT2(0x31, 0xc0); + /* mov qword ptr [rbp-X], rax */ EMIT3_off32(0x48, 0x89, 0x85, -STACKSIZE + 32); BUILD_BUG_ON(cnt != PROLOGUE_SIZE); @@ -246,7 +250,7 @@ static void emit_prologue(u8 **pprog) * goto out; * if (++tail_call_cnt > MAX_TAIL_CALL_CNT) * goto out; - * prog = array->prog[index]; + * prog = array->ptrs[index]; * if (prog == NULL) * goto out; * goto *(prog->bpf_func + prologue_size); @@ -284,9 +288,9 @@ static void emit_bpf_tail_call(u8 **pprog) EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ EMIT2_off32(0x89, 0x85, -STACKSIZE + 36); /* mov dword ptr [rbp - 516], eax */ - /* prog = array->prog[index]; */ + /* prog = array->ptrs[index]; */ EMIT4_off32(0x48, 0x8D, 0x84, 0xD6, /* lea rax, [rsi + rdx * 8 + offsetof(...)] */ - offsetof(struct bpf_array, prog)); + offsetof(struct bpf_array, ptrs)); EMIT3(0x48, 0x8B, 0x00); /* mov rax, qword ptr [rax] */ /* if (prog == NULL) @@ -315,6 +319,26 @@ static void emit_bpf_tail_call(u8 **pprog) *pprog = prog; } + +static void emit_load_skb_data_hlen(u8 **pprog) +{ + u8 *prog = *pprog; + int cnt = 0; + + /* r9d = skb->len - skb->data_len (headlen) + * r10 = skb->data + */ + /* mov %r9d, off32(%rdi) */ + EMIT3_off32(0x44, 0x8b, 0x8f, offsetof(struct sk_buff, len)); + + /* sub %r9d, off32(%rdi) */ + EMIT3_off32(0x44, 0x2b, 0x8f, offsetof(struct sk_buff, data_len)); + + /* mov %r10, off32(%rdi) */ + EMIT3_off32(0x4c, 0x8b, 0x97, offsetof(struct sk_buff, data)); + *pprog = prog; +} + static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, int oldproglen, struct jit_context *ctx) { @@ -329,36 +353,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, emit_prologue(&prog); - if (seen_ld_abs) { - /* r9d : skb->len - skb->data_len (headlen) - * r10 : skb->data - */ - if (is_imm8(offsetof(struct sk_buff, len))) - /* mov %r9d, off8(%rdi) */ - EMIT4(0x44, 0x8b, 0x4f, - offsetof(struct sk_buff, len)); - else - /* mov %r9d, off32(%rdi) */ - EMIT3_off32(0x44, 0x8b, 0x8f, - offsetof(struct sk_buff, len)); - - if (is_imm8(offsetof(struct sk_buff, data_len))) - /* sub %r9d, off8(%rdi) */ - EMIT4(0x44, 0x2b, 0x4f, - offsetof(struct sk_buff, data_len)); - else - EMIT3_off32(0x44, 0x2b, 0x8f, - offsetof(struct sk_buff, data_len)); - - if (is_imm8(offsetof(struct sk_buff, data))) - /* mov %r10, off8(%rdi) */ - EMIT4(0x4c, 0x8b, 0x57, - offsetof(struct sk_buff, data)); - else - /* mov %r10, off32(%rdi) */ - EMIT3_off32(0x4c, 0x8b, 0x97, - offsetof(struct sk_buff, data)); - } + if (seen_ld_abs) + emit_load_skb_data_hlen(&prog); for (i = 0; i < insn_cnt; i++, insn++) { const s32 imm32 = insn->imm; @@ -367,6 +363,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 b1 = 0, b2 = 0, b3 = 0; s64 jmp_offset; u8 jmp_cond; + bool reload_skb_data; int ilen; u8 *func; @@ -462,6 +459,18 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, } case BPF_ALU | BPF_MOV | BPF_K: + /* optimization: if imm32 is zero, use 'xor <dst>,<dst>' + * to save 3 bytes. + */ + if (imm32 == 0) { + if (is_ereg(dst_reg)) + EMIT1(add_2mod(0x40, dst_reg, dst_reg)); + b2 = 0x31; /* xor */ + b3 = 0xC0; + EMIT2(b2, add_2reg(b3, dst_reg, dst_reg)); + break; + } + /* mov %eax, imm32 */ if (is_ereg(dst_reg)) EMIT1(add_1mod(0x40, dst_reg)); @@ -476,6 +485,20 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, return -EINVAL; } + /* optimization: if imm64 is zero, use 'xor <dst>,<dst>' + * to save 7 bytes. + */ + if (insn[0].imm == 0 && insn[1].imm == 0) { + b1 = add_2mod(0x48, dst_reg, dst_reg); + b2 = 0x31; /* xor */ + b3 = 0xC0; + EMIT3(b1, b2, add_2reg(b3, dst_reg, dst_reg)); + + insn++; + i++; + break; + } + /* movabsq %rax, imm64 */ EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg)); EMIT(insn[0].imm, 4); @@ -818,12 +841,18 @@ xadd: if (is_imm8(insn->off)) func = (u8 *) __bpf_call_base + imm32; jmp_offset = func - (image + addrs[i]); if (seen_ld_abs) { - EMIT2(0x41, 0x52); /* push %r10 */ - EMIT2(0x41, 0x51); /* push %r9 */ - /* need to adjust jmp offset, since - * pop %r9, pop %r10 take 4 bytes after call insn - */ - jmp_offset += 4; + reload_skb_data = bpf_helper_changes_skb_data(func); + if (reload_skb_data) { + EMIT1(0x57); /* push %rdi */ + jmp_offset += 22; /* pop, mov, sub, mov */ + } else { + EMIT2(0x41, 0x52); /* push %r10 */ + EMIT2(0x41, 0x51); /* push %r9 */ + /* need to adjust jmp offset, since + * pop %r9, pop %r10 take 4 bytes after call insn + */ + jmp_offset += 4; + } } if (!imm32 || !is_simm32(jmp_offset)) { pr_err("unsupported bpf func %d addr %p image %p\n", @@ -832,8 +861,13 @@ xadd: if (is_imm8(insn->off)) } EMIT1_off32(0xE8, jmp_offset); if (seen_ld_abs) { - EMIT2(0x41, 0x59); /* pop %r9 */ - EMIT2(0x41, 0x5A); /* pop %r10 */ + if (reload_skb_data) { + EMIT1(0x5F); /* pop %rdi */ + emit_load_skb_data_hlen(&prog); + } else { + EMIT2(0x41, 0x59); /* pop %r9 */ + EMIT2(0x41, 0x5A); /* pop %r10 */ + } } break; @@ -1099,13 +1133,13 @@ void bpf_int_jit_compile(struct bpf_prog *prog) } if (bpf_jit_enable > 1) - bpf_jit_dump(prog->len, proglen, 0, image); + bpf_jit_dump(prog->len, proglen, pass + 1, image); if (image) { bpf_flush_icache(header, image + proglen); set_memory_ro((unsigned long)header, header->pages); prog->bpf_func = (void *)image; - prog->jited = true; + prog->jited = 1; } out: kfree(addrs); diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile index 5c6fc3577a49..97062a635b77 100644 --- a/arch/x86/pci/Makefile +++ b/arch/x86/pci/Makefile @@ -23,6 +23,8 @@ obj-y += bus_numa.o obj-$(CONFIG_AMD_NB) += amd_bus.o obj-$(CONFIG_PCI_CNB20LE_QUIRK) += broadcom_bus.o +obj-$(CONFIG_VMD) += vmd.o + ifeq ($(CONFIG_PCI_DEBUG),y) EXTRA_CFLAGS += -DDEBUG endif diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index ff9911707160..3cd69832d7f4 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -4,16 +4,15 @@ #include <linux/irq.h> #include <linux/dmi.h> #include <linux/slab.h> +#include <linux/pci-acpi.h> #include <asm/numa.h> #include <asm/pci_x86.h> struct pci_root_info { - struct acpi_device *bridge; - char name[16]; + struct acpi_pci_root_info common; struct pci_sysdata sd; #ifdef CONFIG_PCI_MMCONFIG bool mcfg_added; - u16 segment; u8 start_bus; u8 end_bus; #endif @@ -178,15 +177,18 @@ static int check_segment(u16 seg, struct device *dev, char *estr) return 0; } -static int setup_mcfg_map(struct pci_root_info *info, u16 seg, u8 start, - u8 end, phys_addr_t addr) +static int setup_mcfg_map(struct acpi_pci_root_info *ci) { - int result; - struct device *dev = &info->bridge->dev; + int result, seg; + struct pci_root_info *info; + struct acpi_pci_root *root = ci->root; + struct device *dev = &ci->bridge->dev; - info->start_bus = start; - info->end_bus = end; + info = container_of(ci, struct pci_root_info, common); + info->start_bus = (u8)root->secondary.start; + info->end_bus = (u8)root->secondary.end; info->mcfg_added = false; + seg = info->sd.domain; /* return success if MMCFG is not in use */ if (raw_pci_ext_ops && raw_pci_ext_ops != &pci_mmcfg) @@ -195,7 +197,8 @@ static int setup_mcfg_map(struct pci_root_info *info, u16 seg, u8 start, if (!(pci_probe & PCI_PROBE_MMCONF)) return check_segment(seg, dev, "MMCONFIG is disabled,"); - result = pci_mmconfig_insert(dev, seg, start, end, addr); + result = pci_mmconfig_insert(dev, seg, info->start_bus, info->end_bus, + root->mcfg_addr); if (result == 0) { /* enable MMCFG if it hasn't been enabled yet */ if (raw_pci_ext_ops == NULL) @@ -208,134 +211,55 @@ static int setup_mcfg_map(struct pci_root_info *info, u16 seg, u8 start, return 0; } -static void teardown_mcfg_map(struct pci_root_info *info) +static void teardown_mcfg_map(struct acpi_pci_root_info *ci) { + struct pci_root_info *info; + + info = container_of(ci, struct pci_root_info, common); if (info->mcfg_added) { - pci_mmconfig_delete(info->segment, info->start_bus, - info->end_bus); + pci_mmconfig_delete(info->sd.domain, + info->start_bus, info->end_bus); info->mcfg_added = false; } } #else -static int setup_mcfg_map(struct pci_root_info *info, - u16 seg, u8 start, u8 end, - phys_addr_t addr) +static int setup_mcfg_map(struct acpi_pci_root_info *ci) { return 0; } -static void teardown_mcfg_map(struct pci_root_info *info) + +static void teardown_mcfg_map(struct acpi_pci_root_info *ci) { } #endif -static void validate_resources(struct device *dev, struct list_head *crs_res, - unsigned long type) +static int pci_acpi_root_get_node(struct acpi_pci_root *root) { - LIST_HEAD(list); - struct resource *res1, *res2, *root = NULL; - struct resource_entry *tmp, *entry, *entry2; - - BUG_ON((type & (IORESOURCE_MEM | IORESOURCE_IO)) == 0); - root = (type & IORESOURCE_MEM) ? &iomem_resource : &ioport_resource; - - list_splice_init(crs_res, &list); - resource_list_for_each_entry_safe(entry, tmp, &list) { - bool free = false; - resource_size_t end; - - res1 = entry->res; - if (!(res1->flags & type)) - goto next; - - /* Exclude non-addressable range or non-addressable portion */ - end = min(res1->end, root->end); - if (end <= res1->start) { - dev_info(dev, "host bridge window %pR (ignored, not CPU addressable)\n", - res1); - free = true; - goto next; - } else if (res1->end != end) { - dev_info(dev, "host bridge window %pR ([%#llx-%#llx] ignored, not CPU addressable)\n", - res1, (unsigned long long)end + 1, - (unsigned long long)res1->end); - res1->end = end; - } - - resource_list_for_each_entry(entry2, crs_res) { - res2 = entry2->res; - if (!(res2->flags & type)) - continue; - - /* - * I don't like throwing away windows because then - * our resources no longer match the ACPI _CRS, but - * the kernel resource tree doesn't allow overlaps. - */ - if (resource_overlaps(res1, res2)) { - res2->start = min(res1->start, res2->start); - res2->end = max(res1->end, res2->end); - dev_info(dev, "host bridge window expanded to %pR; %pR ignored\n", - res2, res1); - free = true; - goto next; - } - } + int busnum = root->secondary.start; + struct acpi_device *device = root->device; + int node = acpi_get_node(device->handle); -next: - resource_list_del(entry); - if (free) - resource_list_free_entry(entry); - else - resource_list_add_tail(entry, crs_res); + if (node == NUMA_NO_NODE) { + node = x86_pci_root_bus_node(busnum); + if (node != 0 && node != NUMA_NO_NODE) + dev_info(&device->dev, FW_BUG "no _PXM; falling back to node %d from hardware (may be inconsistent with ACPI node numbers)\n", + node); } + if (node != NUMA_NO_NODE && !node_online(node)) + node = NUMA_NO_NODE; + + return node; } -static void add_resources(struct pci_root_info *info, - struct list_head *resources, - struct list_head *crs_res) +static int pci_acpi_root_init_info(struct acpi_pci_root_info *ci) { - struct resource_entry *entry, *tmp; - struct resource *res, *conflict, *root = NULL; - - validate_resources(&info->bridge->dev, crs_res, IORESOURCE_MEM); - validate_resources(&info->bridge->dev, crs_res, IORESOURCE_IO); - - resource_list_for_each_entry_safe(entry, tmp, crs_res) { - res = entry->res; - if (res->flags & IORESOURCE_MEM) - root = &iomem_resource; - else if (res->flags & IORESOURCE_IO) - root = &ioport_resource; - else - BUG_ON(res); - - conflict = insert_resource_conflict(root, res); - if (conflict) { - dev_info(&info->bridge->dev, - "ignoring host bridge window %pR (conflicts with %s %pR)\n", - res, conflict->name, conflict); - resource_list_destroy_entry(entry); - } - } - - list_splice_tail(crs_res, resources); + return setup_mcfg_map(ci); } -static void release_pci_root_info(struct pci_host_bridge *bridge) +static void pci_acpi_root_release_info(struct acpi_pci_root_info *ci) { - struct resource *res; - struct resource_entry *entry; - struct pci_root_info *info = bridge->release_data; - - resource_list_for_each_entry(entry, &bridge->windows) { - res = entry->res; - if (res->parent && - (res->flags & (IORESOURCE_MEM | IORESOURCE_IO))) - release_resource(res); - } - - teardown_mcfg_map(info); - kfree(info); + teardown_mcfg_map(ci); + kfree(container_of(ci, struct pci_root_info, common)); } /* @@ -358,50 +282,47 @@ static bool resource_is_pcicfg_ioport(struct resource *res) res->start == 0xCF8 && res->end == 0xCFF; } -static void probe_pci_root_info(struct pci_root_info *info, - struct acpi_device *device, - int busnum, int domain, - struct list_head *list) +static int pci_acpi_root_prepare_resources(struct acpi_pci_root_info *ci) { - int ret; + struct acpi_device *device = ci->bridge; + int busnum = ci->root->secondary.start; struct resource_entry *entry, *tmp; + int status; - sprintf(info->name, "PCI Bus %04x:%02x", domain, busnum); - info->bridge = device; - ret = acpi_dev_get_resources(device, list, - acpi_dev_filter_resource_type_cb, - (void *)(IORESOURCE_IO | IORESOURCE_MEM)); - if (ret < 0) - dev_warn(&device->dev, - "failed to parse _CRS method, error code %d\n", ret); - else if (ret == 0) - dev_dbg(&device->dev, - "no IO and memory resources present in _CRS\n"); - else - resource_list_for_each_entry_safe(entry, tmp, list) { - if ((entry->res->flags & IORESOURCE_DISABLED) || - resource_is_pcicfg_ioport(entry->res)) + status = acpi_pci_probe_root_resources(ci); + if (pci_use_crs) { + resource_list_for_each_entry_safe(entry, tmp, &ci->resources) + if (resource_is_pcicfg_ioport(entry->res)) resource_list_destroy_entry(entry); - else - entry->res->name = info->name; - } + return status; + } + + resource_list_for_each_entry_safe(entry, tmp, &ci->resources) { + dev_printk(KERN_DEBUG, &device->dev, + "host bridge window %pR (ignored)\n", entry->res); + resource_list_destroy_entry(entry); + } + x86_pci_root_bus_resources(busnum, &ci->resources); + + return 0; } +static struct acpi_pci_root_ops acpi_pci_root_ops = { + .pci_ops = &pci_root_ops, + .init_info = pci_acpi_root_init_info, + .release_info = pci_acpi_root_release_info, + .prepare_resources = pci_acpi_root_prepare_resources, +}; + struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) { - struct acpi_device *device = root->device; - struct pci_root_info *info; int domain = root->segment; int busnum = root->secondary.start; - struct resource_entry *res_entry; - LIST_HEAD(crs_res); - LIST_HEAD(resources); + int node = pci_acpi_root_get_node(root); struct pci_bus *bus; - struct pci_sysdata *sd; - int node; if (pci_ignore_seg) - domain = 0; + root->segment = domain = 0; if (domain && !pci_domains_supported) { printk(KERN_WARNING "pci_bus %04x:%02x: " @@ -410,71 +331,33 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) return NULL; } - node = acpi_get_node(device->handle); - if (node == NUMA_NO_NODE) { - node = x86_pci_root_bus_node(busnum); - if (node != 0 && node != NUMA_NO_NODE) - dev_info(&device->dev, FW_BUG "no _PXM; falling back to node %d from hardware (may be inconsistent with ACPI node numbers)\n", - node); - } - - if (node != NUMA_NO_NODE && !node_online(node)) - node = NUMA_NO_NODE; - - info = kzalloc_node(sizeof(*info), GFP_KERNEL, node); - if (!info) { - printk(KERN_WARNING "pci_bus %04x:%02x: " - "ignored (out of memory)\n", domain, busnum); - return NULL; - } - - sd = &info->sd; - sd->domain = domain; - sd->node = node; - sd->companion = device; - bus = pci_find_bus(domain, busnum); if (bus) { /* * If the desired bus has been scanned already, replace * its bus->sysdata. */ - memcpy(bus->sysdata, sd, sizeof(*sd)); - kfree(info); - } else { - /* insert busn res at first */ - pci_add_resource(&resources, &root->secondary); + struct pci_sysdata sd = { + .domain = domain, + .node = node, + .companion = root->device + }; - /* - * _CRS with no apertures is normal, so only fall back to - * defaults or native bridge info if we're ignoring _CRS. - */ - probe_pci_root_info(info, device, busnum, domain, &crs_res); - if (pci_use_crs) { - add_resources(info, &resources, &crs_res); - } else { - resource_list_for_each_entry(res_entry, &crs_res) - dev_printk(KERN_DEBUG, &device->dev, - "host bridge window %pR (ignored)\n", - res_entry->res); - resource_list_free(&crs_res); - x86_pci_root_bus_resources(busnum, &resources); - } - - if (!setup_mcfg_map(info, domain, (u8)root->secondary.start, - (u8)root->secondary.end, root->mcfg_addr)) - bus = pci_create_root_bus(NULL, busnum, &pci_root_ops, - sd, &resources); - - if (bus) { - pci_scan_child_bus(bus); - pci_set_host_bridge_release( - to_pci_host_bridge(bus->bridge), - release_pci_root_info, info); - } else { - resource_list_free(&resources); - teardown_mcfg_map(info); - kfree(info); + memcpy(bus->sysdata, &sd, sizeof(sd)); + } else { + struct pci_root_info *info; + + info = kzalloc_node(sizeof(*info), GFP_KERNEL, node); + if (!info) + dev_err(&root->device->dev, + "pci_bus %04x:%02x: ignored (out of memory)\n", + domain, busnum); + else { + info->sd.domain = domain; + info->sd.node = node; + info->sd.companion = root->device; + bus = acpi_pci_root_create(root, &acpi_pci_root_ops, + &info->common, &info->sd); } } @@ -487,9 +370,6 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) pcie_bus_configure_settings(child); } - if (bus && node != NUMA_NO_NODE) - dev_printk(KERN_DEBUG, &bus->dev, "on NUMA node %d\n", node); - return bus; } diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c index 7bcf06a7cd12..6eb3c8af96e2 100644 --- a/arch/x86/pci/bus_numa.c +++ b/arch/x86/pci/bus_numa.c @@ -50,18 +50,9 @@ void x86_pci_root_bus_resources(int bus, struct list_head *resources) if (!found) pci_add_resource(resources, &info->busn); - list_for_each_entry(root_res, &info->resources, list) { - struct resource *res; - struct resource *root; + list_for_each_entry(root_res, &info->resources, list) + pci_add_resource(resources, &root_res->res); - res = &root_res->res; - pci_add_resource(resources, res); - if (res->flags & IORESOURCE_IO) - root = &ioport_resource; - else - root = &iomem_resource; - insert_resource(root, res); - } return; default_resources: diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 8fd6f44aee83..2879efc73a96 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -641,6 +641,43 @@ unsigned int pcibios_assign_all_busses(void) return (pci_probe & PCI_ASSIGN_ALL_BUSSES) ? 1 : 0; } +#if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS) +static LIST_HEAD(dma_domain_list); +static DEFINE_SPINLOCK(dma_domain_list_lock); + +void add_dma_domain(struct dma_domain *domain) +{ + spin_lock(&dma_domain_list_lock); + list_add(&domain->node, &dma_domain_list); + spin_unlock(&dma_domain_list_lock); +} +EXPORT_SYMBOL_GPL(add_dma_domain); + +void del_dma_domain(struct dma_domain *domain) +{ + spin_lock(&dma_domain_list_lock); + list_del(&domain->node); + spin_unlock(&dma_domain_list_lock); +} +EXPORT_SYMBOL_GPL(del_dma_domain); + +static void set_dma_domain_ops(struct pci_dev *pdev) +{ + struct dma_domain *domain; + + spin_lock(&dma_domain_list_lock); + list_for_each_entry(domain, &dma_domain_list, node) { + if (pci_domain_nr(pdev->bus) == domain->domain_nr) { + pdev->dev.archdata.dma_ops = domain->dma_ops; + break; + } + } + spin_unlock(&dma_domain_list_lock); +} +#else +static void set_dma_domain_ops(struct pci_dev *pdev) {} +#endif + int pcibios_add_device(struct pci_dev *dev) { struct setup_data *data; @@ -670,27 +707,34 @@ int pcibios_add_device(struct pci_dev *dev) pa_data = data->next; iounmap(data); } + set_dma_domain_ops(dev); return 0; } -int pcibios_enable_device(struct pci_dev *dev, int mask) +int pcibios_alloc_irq(struct pci_dev *dev) { - int err; - - if ((err = pci_enable_resources(dev, mask)) < 0) - return err; + /* + * If the PCI device was already claimed by core code and has + * MSI enabled, probing of the pcibios IRQ will overwrite + * dev->irq. So bail out if MSI is already enabled. + */ + if (pci_dev_msi_enabled(dev)) + return -EBUSY; - if (!pci_dev_msi_enabled(dev)) - return pcibios_enable_irq(dev); - return 0; + return pcibios_enable_irq(dev); } -void pcibios_disable_device (struct pci_dev *dev) +void pcibios_free_irq(struct pci_dev *dev) { - if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq) + if (pcibios_disable_irq) pcibios_disable_irq(dev); } +int pcibios_enable_device(struct pci_dev *dev, int mask) +{ + return pci_enable_resources(dev, mask); +} + int pci_ext_cfg_avail(void) { if (raw_pci_ext_ops) diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 9a2b7101ae8a..e58565556703 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -62,19 +62,6 @@ static void pci_fixup_umc_ide(struct pci_dev *d) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_UMC, PCI_DEVICE_ID_UMC_UM8886BF, pci_fixup_umc_ide); -static void pci_fixup_ncr53c810(struct pci_dev *d) -{ - /* - * NCR 53C810 returns class code 0 (at least on some systems). - * Fix class to be PCI_CLASS_STORAGE_SCSI - */ - if (!d->class) { - dev_warn(&d->dev, "Fixing NCR 53C810 class code\n"); - d->class = PCI_CLASS_STORAGE_SCSI << 8; - } -} -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NCR, PCI_DEVICE_ID_NCR_53C810, pci_fixup_ncr53c810); - static void pci_fixup_latency(struct pci_dev *d) { /* diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 27062303c881..0d24e7c10145 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -35,6 +35,9 @@ #define PCIE_CAP_OFFSET 0x100 +/* Quirks for the listed devices */ +#define PCI_DEVICE_ID_INTEL_MRFL_MMC 0x1190 + /* Fixed BAR fields */ #define PCIE_VNDR_CAP_ID_FIXED_BAR 0x00 /* Fixed BAR (TBD) */ #define PCI_FIXED_BAR_0_SIZE 0x04 @@ -210,22 +213,41 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) { struct irq_alloc_info info; int polarity; + int ret; - if (dev->irq_managed && dev->irq > 0) + if (pci_has_managed_irq(dev)) return 0; - if (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_TANGIER) - polarity = 0; /* active high */ - else - polarity = 1; /* active low */ + switch (intel_mid_identify_cpu()) { + case INTEL_MID_CPU_CHIP_TANGIER: + polarity = IOAPIC_POL_HIGH; + + /* Special treatment for IRQ0 */ + if (dev->irq == 0) { + /* + * TNG has IRQ0 assigned to eMMC controller. But there + * are also other devices with bogus PCI configuration + * that have IRQ0 assigned. This check ensures that + * eMMC gets it. + */ + if (dev->device != PCI_DEVICE_ID_INTEL_MRFL_MMC) + return -EBUSY; + } + break; + default: + polarity = IOAPIC_POL_LOW; + break; + } + 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_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC, &info) < 0) - return -EBUSY; + ret = mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC, &info); + if (ret < 0) + return ret; dev->irq_managed = 1; @@ -234,14 +256,17 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) static void intel_mid_pci_irq_disable(struct pci_dev *dev) { - if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed && - dev->irq > 0) { + if (pci_has_managed_irq(dev)) { mp_unmap_irq(dev->irq); dev->irq_managed = 0; + /* + * Don't reset dev->irq here, otherwise + * intel_mid_pci_irq_enable() will fail on next call. + */ } } -struct pci_ops intel_mid_pci_ops = { +static struct pci_ops intel_mid_pci_ops = { .read = pci_read, .write = pci_write, }; diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 9bd115484745..32e70343e6fd 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -1202,7 +1202,7 @@ static int pirq_enable_irq(struct pci_dev *dev) struct pci_dev *temp_dev; int irq; - if (dev->irq_managed && dev->irq > 0) + if (pci_has_managed_irq(dev)) return 0; irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, @@ -1230,8 +1230,7 @@ static int pirq_enable_irq(struct pci_dev *dev) } dev = temp_dev; if (irq >= 0) { - dev->irq_managed = 1; - dev->irq = irq; + pci_set_managed_irq(dev, irq); dev_info(&dev->dev, "PCI->APIC IRQ transform: " "INT %c -> IRQ %d\n", 'A' + pin - 1, irq); return 0; @@ -1257,24 +1256,10 @@ static int pirq_enable_irq(struct pci_dev *dev) return 0; } -bool mp_should_keep_irq(struct device *dev) -{ - if (dev->power.is_prepared) - return true; -#ifdef CONFIG_PM - if (dev->power.runtime_status == RPM_SUSPENDING) - return true; -#endif - - return false; -} - static void pirq_disable_irq(struct pci_dev *dev) { - if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) && - dev->irq_managed && dev->irq) { + if (io_apic_assign_pci_irqs && pci_has_managed_irq(dev)) { mp_unmap_irq(dev->irq); - dev->irq = 0; - dev->irq_managed = 0; + pci_reset_managed_irq(dev); } } diff --git a/arch/x86/pci/legacy.c b/arch/x86/pci/legacy.c index 5b662c0faf8c..ea6f3802c17b 100644 --- a/arch/x86/pci/legacy.c +++ b/arch/x86/pci/legacy.c @@ -54,7 +54,7 @@ void pcibios_scan_specific_bus(int busn) } EXPORT_SYMBOL_GPL(pcibios_scan_specific_bus); -int __init pci_subsys_init(void) +static int __init pci_subsys_init(void) { /* * The init function returns an non zero value when diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index 9b83b9051ae7..9770e55e768f 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -180,6 +180,7 @@ static int pci_bios_read(unsigned int seg, unsigned int bus, unsigned long result = 0; unsigned long flags; unsigned long bx = (bus << 8) | devfn; + u16 number = 0, mask = 0; WARN_ON(seg); if (!value || (bus > 255) || (devfn > 255) || (reg > 255)) @@ -189,53 +190,35 @@ static int pci_bios_read(unsigned int seg, unsigned int bus, switch (len) { case 1: - __asm__("lcall *(%%esi); cld\n\t" - "jc 1f\n\t" - "xor %%ah, %%ah\n" - "1:" - : "=c" (*value), - "=a" (result) - : "1" (PCIBIOS_READ_CONFIG_BYTE), - "b" (bx), - "D" ((long)reg), - "S" (&pci_indirect)); - /* - * Zero-extend the result beyond 8 bits, do not trust the - * BIOS having done it: - */ - *value &= 0xff; + number = PCIBIOS_READ_CONFIG_BYTE; + mask = 0xff; break; case 2: - __asm__("lcall *(%%esi); cld\n\t" - "jc 1f\n\t" - "xor %%ah, %%ah\n" - "1:" - : "=c" (*value), - "=a" (result) - : "1" (PCIBIOS_READ_CONFIG_WORD), - "b" (bx), - "D" ((long)reg), - "S" (&pci_indirect)); - /* - * Zero-extend the result beyond 16 bits, do not trust the - * BIOS having done it: - */ - *value &= 0xffff; + number = PCIBIOS_READ_CONFIG_WORD; + mask = 0xffff; break; case 4: - __asm__("lcall *(%%esi); cld\n\t" - "jc 1f\n\t" - "xor %%ah, %%ah\n" - "1:" - : "=c" (*value), - "=a" (result) - : "1" (PCIBIOS_READ_CONFIG_DWORD), - "b" (bx), - "D" ((long)reg), - "S" (&pci_indirect)); + number = PCIBIOS_READ_CONFIG_DWORD; break; } + __asm__("lcall *(%%esi); cld\n\t" + "jc 1f\n\t" + "xor %%ah, %%ah\n" + "1:" + : "=c" (*value), + "=a" (result) + : "1" (number), + "b" (bx), + "D" ((long)reg), + "S" (&pci_indirect)); + /* + * Zero-extend the result beyond 8 or 16 bits, do not trust the + * BIOS having done it: + */ + if (mask) + *value &= mask; + raw_spin_unlock_irqrestore(&pci_config_lock, flags); return (int)((result & 0xff00) >> 8); @@ -247,6 +230,7 @@ static int pci_bios_write(unsigned int seg, unsigned int bus, unsigned long result = 0; unsigned long flags; unsigned long bx = (bus << 8) | devfn; + u16 number = 0; WARN_ON(seg); if ((bus > 255) || (devfn > 255) || (reg > 255)) @@ -256,43 +240,27 @@ static int pci_bios_write(unsigned int seg, unsigned int bus, switch (len) { case 1: - __asm__("lcall *(%%esi); cld\n\t" - "jc 1f\n\t" - "xor %%ah, %%ah\n" - "1:" - : "=a" (result) - : "0" (PCIBIOS_WRITE_CONFIG_BYTE), - "c" (value), - "b" (bx), - "D" ((long)reg), - "S" (&pci_indirect)); + number = PCIBIOS_WRITE_CONFIG_BYTE; break; case 2: - __asm__("lcall *(%%esi); cld\n\t" - "jc 1f\n\t" - "xor %%ah, %%ah\n" - "1:" - : "=a" (result) - : "0" (PCIBIOS_WRITE_CONFIG_WORD), - "c" (value), - "b" (bx), - "D" ((long)reg), - "S" (&pci_indirect)); + number = PCIBIOS_WRITE_CONFIG_WORD; break; case 4: - __asm__("lcall *(%%esi); cld\n\t" - "jc 1f\n\t" - "xor %%ah, %%ah\n" - "1:" - : "=a" (result) - : "0" (PCIBIOS_WRITE_CONFIG_DWORD), - "c" (value), - "b" (bx), - "D" ((long)reg), - "S" (&pci_indirect)); + number = PCIBIOS_WRITE_CONFIG_DWORD; break; } + __asm__("lcall *(%%esi); cld\n\t" + "jc 1f\n\t" + "xor %%ah, %%ah\n" + "1:" + : "=a" (result) + : "0" (number), + "c" (value), + "b" (bx), + "D" ((long)reg), + "S" (&pci_indirect)); + raw_spin_unlock_irqrestore(&pci_config_lock, flags); return (int)((result & 0xff00) >> 8); diff --git a/arch/x86/pci/vmd.c b/arch/x86/pci/vmd.c new file mode 100644 index 000000000000..d57e48016f15 --- /dev/null +++ b/arch/x86/pci/vmd.c @@ -0,0 +1,723 @@ +/* + * Volume Management Device driver + * 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/device.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/msi.h> +#include <linux/pci.h> +#include <linux/rculist.h> +#include <linux/rcupdate.h> + +#include <asm/irqdomain.h> +#include <asm/device.h> +#include <asm/msi.h> +#include <asm/msidef.h> + +#define VMD_CFGBAR 0 +#define VMD_MEMBAR1 2 +#define VMD_MEMBAR2 4 + +/* + * Lock for manipulating VMD IRQ lists. + */ +static DEFINE_RAW_SPINLOCK(list_lock); + +/** + * struct vmd_irq - private data to map driver IRQ to the VMD shared vector + * @node: list item for parent traversal. + * @rcu: RCU callback item for freeing. + * @irq: back pointer to parent. + * @virq: the virtual IRQ value provided to the requesting driver. + * + * Every MSI/MSI-X IRQ requested for a device in a VMD domain will be mapped to + * a VMD IRQ using this structure. + */ +struct vmd_irq { + struct list_head node; + struct rcu_head rcu; + struct vmd_irq_list *irq; + unsigned int virq; +}; + +/** + * struct vmd_irq_list - list of driver requested IRQs mapping to a VMD vector + * @irq_list: the list of irq's the VMD one demuxes to. + * @vmd_vector: the h/w IRQ assigned to the VMD. + * @index: index into the VMD MSI-X table; used for message routing. + * @count: number of child IRQs assigned to this vector; used to track + * sharing. + */ +struct vmd_irq_list { + struct list_head irq_list; + struct vmd_dev *vmd; + unsigned int vmd_vector; + unsigned int index; + unsigned int count; +}; + +struct vmd_dev { + struct pci_dev *dev; + + spinlock_t cfg_lock; + char __iomem *cfgbar; + + int msix_count; + struct msix_entry *msix_entries; + struct vmd_irq_list *irqs; + + struct pci_sysdata sysdata; + struct resource resources[3]; + struct irq_domain *irq_domain; + struct pci_bus *bus; + +#ifdef CONFIG_X86_DEV_DMA_OPS + struct dma_map_ops dma_ops; + struct dma_domain dma_domain; +#endif +}; + +static inline struct vmd_dev *vmd_from_bus(struct pci_bus *bus) +{ + return container_of(bus->sysdata, struct vmd_dev, sysdata); +} + +/* + * Drivers managing a device in a VMD domain allocate their own IRQs as before, + * but the MSI entry for the hardware it's driving will be programmed with a + * destination ID for the VMD MSI-X table. The VMD muxes interrupts in its + * domain into one of its own, and the VMD driver de-muxes these for the + * handlers sharing that VMD IRQ. The vmd irq_domain provides the operations + * and irq_chip to set this up. + */ +static void vmd_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct vmd_irq *vmdirq = data->chip_data; + struct vmd_irq_list *irq = vmdirq->irq; + + msg->address_hi = MSI_ADDR_BASE_HI; + msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_DEST_ID(irq->index); + msg->data = 0; +} + +/* + * We rely on MSI_FLAG_USE_DEF_CHIP_OPS to set the IRQ mask/unmask ops. + */ +static void vmd_irq_enable(struct irq_data *data) +{ + struct vmd_irq *vmdirq = data->chip_data; + + raw_spin_lock(&list_lock); + list_add_tail_rcu(&vmdirq->node, &vmdirq->irq->irq_list); + raw_spin_unlock(&list_lock); + + data->chip->irq_unmask(data); +} + +static void vmd_irq_disable(struct irq_data *data) +{ + struct vmd_irq *vmdirq = data->chip_data; + + data->chip->irq_mask(data); + + raw_spin_lock(&list_lock); + list_del_rcu(&vmdirq->node); + raw_spin_unlock(&list_lock); +} + +/* + * XXX: Stubbed until we develop acceptable way to not create conflicts with + * other devices sharing the same vector. + */ +static int vmd_irq_set_affinity(struct irq_data *data, + const struct cpumask *dest, bool force) +{ + return -EINVAL; +} + +static struct irq_chip vmd_msi_controller = { + .name = "VMD-MSI", + .irq_enable = vmd_irq_enable, + .irq_disable = vmd_irq_disable, + .irq_compose_msi_msg = vmd_compose_msi_msg, + .irq_set_affinity = vmd_irq_set_affinity, +}; + +static irq_hw_number_t vmd_get_hwirq(struct msi_domain_info *info, + msi_alloc_info_t *arg) +{ + return 0; +} + +/* + * XXX: We can be even smarter selecting the best IRQ once we solve the + * affinity problem. + */ +static struct vmd_irq_list *vmd_next_irq(struct vmd_dev *vmd) +{ + int i, best = 0; + + raw_spin_lock(&list_lock); + for (i = 1; i < vmd->msix_count; i++) + if (vmd->irqs[i].count < vmd->irqs[best].count) + best = i; + vmd->irqs[best].count++; + raw_spin_unlock(&list_lock); + + return &vmd->irqs[best]; +} + +static int vmd_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 vmd_dev *vmd = vmd_from_bus(msi_desc_to_pci_dev(arg->desc)->bus); + struct vmd_irq *vmdirq = kzalloc(sizeof(*vmdirq), GFP_KERNEL); + + if (!vmdirq) + return -ENOMEM; + + INIT_LIST_HEAD(&vmdirq->node); + vmdirq->irq = vmd_next_irq(vmd); + vmdirq->virq = virq; + + irq_domain_set_info(domain, virq, vmdirq->irq->vmd_vector, info->chip, + vmdirq, handle_simple_irq, vmd, NULL); + return 0; +} + +static void vmd_msi_free(struct irq_domain *domain, + struct msi_domain_info *info, unsigned int virq) +{ + struct vmd_irq *vmdirq = irq_get_chip_data(virq); + + /* XXX: Potential optimization to rebalance */ + raw_spin_lock(&list_lock); + vmdirq->irq->count--; + raw_spin_unlock(&list_lock); + + kfree_rcu(vmdirq, rcu); +} + +static int vmd_msi_prepare(struct irq_domain *domain, struct device *dev, + int nvec, msi_alloc_info_t *arg) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct vmd_dev *vmd = vmd_from_bus(pdev->bus); + + if (nvec > vmd->msix_count) + return vmd->msix_count; + + memset(arg, 0, sizeof(*arg)); + return 0; +} + +static void vmd_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) +{ + arg->desc = desc; +} + +static struct msi_domain_ops vmd_msi_domain_ops = { + .get_hwirq = vmd_get_hwirq, + .msi_init = vmd_msi_init, + .msi_free = vmd_msi_free, + .msi_prepare = vmd_msi_prepare, + .set_desc = vmd_set_desc, +}; + +static struct msi_domain_info vmd_msi_domain_info = { + .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_PCI_MSIX, + .ops = &vmd_msi_domain_ops, + .chip = &vmd_msi_controller, +}; + +#ifdef CONFIG_X86_DEV_DMA_OPS +/* + * VMD replaces the requester ID with its own. DMA mappings for devices in a + * VMD domain need to be mapped for the VMD, not the device requiring + * the mapping. + */ +static struct device *to_vmd_dev(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct vmd_dev *vmd = vmd_from_bus(pdev->bus); + + return &vmd->dev->dev; +} + +static struct dma_map_ops *vmd_dma_ops(struct device *dev) +{ + return to_vmd_dev(dev)->archdata.dma_ops; +} + +static void *vmd_alloc(struct device *dev, size_t size, dma_addr_t *addr, + gfp_t flag, struct dma_attrs *attrs) +{ + return vmd_dma_ops(dev)->alloc(to_vmd_dev(dev), size, addr, flag, + attrs); +} + +static void vmd_free(struct device *dev, size_t size, void *vaddr, + dma_addr_t addr, struct dma_attrs *attrs) +{ + return vmd_dma_ops(dev)->free(to_vmd_dev(dev), size, vaddr, addr, + attrs); +} + +static int vmd_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t addr, size_t size, + struct dma_attrs *attrs) +{ + return vmd_dma_ops(dev)->mmap(to_vmd_dev(dev), vma, cpu_addr, addr, + size, attrs); +} + +static int vmd_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t addr, size_t size, + struct dma_attrs *attrs) +{ + return vmd_dma_ops(dev)->get_sgtable(to_vmd_dev(dev), sgt, cpu_addr, + addr, size, attrs); +} + +static dma_addr_t vmd_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + return vmd_dma_ops(dev)->map_page(to_vmd_dev(dev), page, offset, size, + dir, attrs); +} + +static void vmd_unmap_page(struct device *dev, dma_addr_t addr, size_t size, + enum dma_data_direction dir, struct dma_attrs *attrs) +{ + vmd_dma_ops(dev)->unmap_page(to_vmd_dev(dev), addr, size, dir, attrs); +} + +static int vmd_map_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, struct dma_attrs *attrs) +{ + return vmd_dma_ops(dev)->map_sg(to_vmd_dev(dev), sg, nents, dir, attrs); +} + +static void vmd_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, struct dma_attrs *attrs) +{ + vmd_dma_ops(dev)->unmap_sg(to_vmd_dev(dev), sg, nents, dir, attrs); +} + +static void vmd_sync_single_for_cpu(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir) +{ + vmd_dma_ops(dev)->sync_single_for_cpu(to_vmd_dev(dev), addr, size, dir); +} + +static void vmd_sync_single_for_device(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir) +{ + vmd_dma_ops(dev)->sync_single_for_device(to_vmd_dev(dev), addr, size, + dir); +} + +static void vmd_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir) +{ + vmd_dma_ops(dev)->sync_sg_for_cpu(to_vmd_dev(dev), sg, nents, dir); +} + +static void vmd_sync_sg_for_device(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir) +{ + vmd_dma_ops(dev)->sync_sg_for_device(to_vmd_dev(dev), sg, nents, dir); +} + +static int vmd_mapping_error(struct device *dev, dma_addr_t addr) +{ + return vmd_dma_ops(dev)->mapping_error(to_vmd_dev(dev), addr); +} + +static int vmd_dma_supported(struct device *dev, u64 mask) +{ + return vmd_dma_ops(dev)->dma_supported(to_vmd_dev(dev), mask); +} + +#ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK +static u64 vmd_get_required_mask(struct device *dev) +{ + return vmd_dma_ops(dev)->get_required_mask(to_vmd_dev(dev)); +} +#endif + +static void vmd_teardown_dma_ops(struct vmd_dev *vmd) +{ + struct dma_domain *domain = &vmd->dma_domain; + + if (vmd->dev->dev.archdata.dma_ops) + del_dma_domain(domain); +} + +#define ASSIGN_VMD_DMA_OPS(source, dest, fn) \ + do { \ + if (source->fn) \ + dest->fn = vmd_##fn; \ + } while (0) + +static void vmd_setup_dma_ops(struct vmd_dev *vmd) +{ + const struct dma_map_ops *source = vmd->dev->dev.archdata.dma_ops; + struct dma_map_ops *dest = &vmd->dma_ops; + struct dma_domain *domain = &vmd->dma_domain; + + domain->domain_nr = vmd->sysdata.domain; + domain->dma_ops = dest; + + if (!source) + return; + ASSIGN_VMD_DMA_OPS(source, dest, alloc); + ASSIGN_VMD_DMA_OPS(source, dest, free); + ASSIGN_VMD_DMA_OPS(source, dest, mmap); + ASSIGN_VMD_DMA_OPS(source, dest, get_sgtable); + ASSIGN_VMD_DMA_OPS(source, dest, map_page); + ASSIGN_VMD_DMA_OPS(source, dest, unmap_page); + ASSIGN_VMD_DMA_OPS(source, dest, map_sg); + ASSIGN_VMD_DMA_OPS(source, dest, unmap_sg); + ASSIGN_VMD_DMA_OPS(source, dest, sync_single_for_cpu); + ASSIGN_VMD_DMA_OPS(source, dest, sync_single_for_device); + ASSIGN_VMD_DMA_OPS(source, dest, sync_sg_for_cpu); + ASSIGN_VMD_DMA_OPS(source, dest, sync_sg_for_device); + ASSIGN_VMD_DMA_OPS(source, dest, mapping_error); + ASSIGN_VMD_DMA_OPS(source, dest, dma_supported); +#ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK + ASSIGN_VMD_DMA_OPS(source, dest, get_required_mask); +#endif + add_dma_domain(domain); +} +#undef ASSIGN_VMD_DMA_OPS +#else +static void vmd_teardown_dma_ops(struct vmd_dev *vmd) {} +static void vmd_setup_dma_ops(struct vmd_dev *vmd) {} +#endif + +static char __iomem *vmd_cfg_addr(struct vmd_dev *vmd, struct pci_bus *bus, + unsigned int devfn, int reg, int len) +{ + char __iomem *addr = vmd->cfgbar + + (bus->number << 20) + (devfn << 12) + reg; + + if ((addr - vmd->cfgbar) + len >= + resource_size(&vmd->dev->resource[VMD_CFGBAR])) + return NULL; + + return addr; +} + +/* + * CPU may deadlock if config space is not serialized on some versions of this + * hardware, so all config space access is done under a spinlock. + */ +static int vmd_pci_read(struct pci_bus *bus, unsigned int devfn, int reg, + int len, u32 *value) +{ + struct vmd_dev *vmd = vmd_from_bus(bus); + char __iomem *addr = vmd_cfg_addr(vmd, bus, devfn, reg, len); + unsigned long flags; + int ret = 0; + + if (!addr) + return -EFAULT; + + spin_lock_irqsave(&vmd->cfg_lock, flags); + switch (len) { + case 1: + *value = readb(addr); + break; + case 2: + *value = readw(addr); + break; + case 4: + *value = readl(addr); + break; + default: + ret = -EINVAL; + break; + } + spin_unlock_irqrestore(&vmd->cfg_lock, flags); + return ret; +} + +/* + * VMD h/w converts non-posted config writes to posted memory writes. The + * read-back in this function forces the completion so it returns only after + * the config space was written, as expected. + */ +static int vmd_pci_write(struct pci_bus *bus, unsigned int devfn, int reg, + int len, u32 value) +{ + struct vmd_dev *vmd = vmd_from_bus(bus); + char __iomem *addr = vmd_cfg_addr(vmd, bus, devfn, reg, len); + unsigned long flags; + int ret = 0; + + if (!addr) + return -EFAULT; + + spin_lock_irqsave(&vmd->cfg_lock, flags); + switch (len) { + case 1: + writeb(value, addr); + readb(addr); + break; + case 2: + writew(value, addr); + readw(addr); + break; + case 4: + writel(value, addr); + readl(addr); + break; + default: + ret = -EINVAL; + break; + } + spin_unlock_irqrestore(&vmd->cfg_lock, flags); + return ret; +} + +static struct pci_ops vmd_ops = { + .read = vmd_pci_read, + .write = vmd_pci_write, +}; + +/* + * VMD domains start at 0x1000 to not clash with ACPI _SEG domains. + */ +static int vmd_find_free_domain(void) +{ + int domain = 0xffff; + struct pci_bus *bus = NULL; + + while ((bus = pci_find_next_bus(bus)) != NULL) + domain = max_t(int, domain, pci_domain_nr(bus)); + return domain + 1; +} + +static int vmd_enable_domain(struct vmd_dev *vmd) +{ + struct pci_sysdata *sd = &vmd->sysdata; + struct resource *res; + u32 upper_bits; + unsigned long flags; + LIST_HEAD(resources); + + res = &vmd->dev->resource[VMD_CFGBAR]; + vmd->resources[0] = (struct resource) { + .name = "VMD CFGBAR", + .start = res->start, + .end = (resource_size(res) >> 20) - 1, + .flags = IORESOURCE_BUS | IORESOURCE_PCI_FIXED, + }; + + res = &vmd->dev->resource[VMD_MEMBAR1]; + upper_bits = upper_32_bits(res->end); + flags = res->flags & ~IORESOURCE_SIZEALIGN; + if (!upper_bits) + flags &= ~IORESOURCE_MEM_64; + vmd->resources[1] = (struct resource) { + .name = "VMD MEMBAR1", + .start = res->start, + .end = res->end, + .flags = flags, + }; + + res = &vmd->dev->resource[VMD_MEMBAR2]; + upper_bits = upper_32_bits(res->end); + flags = res->flags & ~IORESOURCE_SIZEALIGN; + if (!upper_bits) + flags &= ~IORESOURCE_MEM_64; + vmd->resources[2] = (struct resource) { + .name = "VMD MEMBAR2", + .start = res->start + 0x2000, + .end = res->end, + .flags = flags, + }; + + sd->domain = vmd_find_free_domain(); + if (sd->domain < 0) + return sd->domain; + + sd->node = pcibus_to_node(vmd->dev->bus); + + vmd->irq_domain = pci_msi_create_irq_domain(NULL, &vmd_msi_domain_info, + NULL); + if (!vmd->irq_domain) + return -ENODEV; + + pci_add_resource(&resources, &vmd->resources[0]); + pci_add_resource(&resources, &vmd->resources[1]); + pci_add_resource(&resources, &vmd->resources[2]); + vmd->bus = pci_create_root_bus(&vmd->dev->dev, 0, &vmd_ops, sd, + &resources); + if (!vmd->bus) { + pci_free_resource_list(&resources); + irq_domain_remove(vmd->irq_domain); + return -ENODEV; + } + + vmd_setup_dma_ops(vmd); + dev_set_msi_domain(&vmd->bus->dev, vmd->irq_domain); + pci_rescan_bus(vmd->bus); + + WARN(sysfs_create_link(&vmd->dev->dev.kobj, &vmd->bus->dev.kobj, + "domain"), "Can't create symlink to domain\n"); + return 0; +} + +static irqreturn_t vmd_irq(int irq, void *data) +{ + struct vmd_irq_list *irqs = data; + struct vmd_irq *vmdirq; + + rcu_read_lock(); + list_for_each_entry_rcu(vmdirq, &irqs->irq_list, node) + generic_handle_irq(vmdirq->virq); + rcu_read_unlock(); + + return IRQ_HANDLED; +} + +static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id) +{ + struct vmd_dev *vmd; + int i, err; + + if (resource_size(&dev->resource[VMD_CFGBAR]) < (1 << 20)) + return -ENOMEM; + + vmd = devm_kzalloc(&dev->dev, sizeof(*vmd), GFP_KERNEL); + if (!vmd) + return -ENOMEM; + + vmd->dev = dev; + err = pcim_enable_device(dev); + if (err < 0) + return err; + + vmd->cfgbar = pcim_iomap(dev, VMD_CFGBAR, 0); + if (!vmd->cfgbar) + return -ENOMEM; + + pci_set_master(dev); + if (dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(64)) && + dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32))) + return -ENODEV; + + vmd->msix_count = pci_msix_vec_count(dev); + if (vmd->msix_count < 0) + return -ENODEV; + + vmd->irqs = devm_kcalloc(&dev->dev, vmd->msix_count, sizeof(*vmd->irqs), + GFP_KERNEL); + if (!vmd->irqs) + return -ENOMEM; + + vmd->msix_entries = devm_kcalloc(&dev->dev, vmd->msix_count, + sizeof(*vmd->msix_entries), + GFP_KERNEL); + if (!vmd->msix_entries) + return -ENOMEM; + for (i = 0; i < vmd->msix_count; i++) + vmd->msix_entries[i].entry = i; + + vmd->msix_count = pci_enable_msix_range(vmd->dev, vmd->msix_entries, 1, + vmd->msix_count); + if (vmd->msix_count < 0) + return vmd->msix_count; + + for (i = 0; i < vmd->msix_count; i++) { + INIT_LIST_HEAD(&vmd->irqs[i].irq_list); + vmd->irqs[i].vmd_vector = vmd->msix_entries[i].vector; + vmd->irqs[i].index = i; + + err = devm_request_irq(&dev->dev, vmd->irqs[i].vmd_vector, + vmd_irq, 0, "vmd", &vmd->irqs[i]); + if (err) + return err; + } + + spin_lock_init(&vmd->cfg_lock); + pci_set_drvdata(dev, vmd); + err = vmd_enable_domain(vmd); + if (err) + return err; + + dev_info(&vmd->dev->dev, "Bound to PCI domain %04x\n", + vmd->sysdata.domain); + return 0; +} + +static void vmd_remove(struct pci_dev *dev) +{ + struct vmd_dev *vmd = pci_get_drvdata(dev); + + pci_set_drvdata(dev, NULL); + sysfs_remove_link(&vmd->dev->dev.kobj, "domain"); + pci_stop_root_bus(vmd->bus); + pci_remove_root_bus(vmd->bus); + vmd_teardown_dma_ops(vmd); + irq_domain_remove(vmd->irq_domain); +} + +#ifdef CONFIG_PM +static int vmd_suspend(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + + pci_save_state(pdev); + return 0; +} + +static int vmd_resume(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + + pci_restore_state(pdev); + return 0; +} +#endif +static SIMPLE_DEV_PM_OPS(vmd_dev_pm_ops, vmd_suspend, vmd_resume); + +static const struct pci_device_id vmd_ids[] = { + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x201d),}, + {0,} +}; +MODULE_DEVICE_TABLE(pci, vmd_ids); + +static struct pci_driver vmd_drv = { + .name = "vmd", + .id_table = vmd_ids, + .probe = vmd_probe, + .remove = vmd_remove, + .driver = { + .pm = &vmd_dev_pm_ops, + }, +}; +module_pci_driver(vmd_drv); + +MODULE_AUTHOR("Intel Corporation"); +MODULE_LICENSE("GPL v2"); +MODULE_VERSION("0.6"); diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index d22f4b5bbc04..ff31ab464213 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -179,7 +179,7 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) if (ret) goto error; i = 0; - list_for_each_entry(msidesc, &dev->msi_list, list) { + for_each_pci_msi_entry(msidesc, dev) { irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i], (type == PCI_CAP_ID_MSI) ? nvec : 1, (type == PCI_CAP_ID_MSIX) ? @@ -230,7 +230,7 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) if (type == PCI_CAP_ID_MSI && nvec > 1) return 1; - list_for_each_entry(msidesc, &dev->msi_list, list) { + for_each_pci_msi_entry(msidesc, dev) { __pci_read_msi_msg(msidesc, &msg); pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) | ((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff); @@ -274,7 +274,7 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) int ret = 0; struct msi_desc *msidesc; - list_for_each_entry(msidesc, &dev->msi_list, list) { + for_each_pci_msi_entry(msidesc, dev) { struct physdev_map_pirq map_irq; domid_t domid; @@ -386,7 +386,7 @@ static void xen_teardown_msi_irqs(struct pci_dev *dev) { struct msi_desc *msidesc; - msidesc = list_entry(dev->msi_list.next, struct msi_desc, list); + msidesc = first_pci_msi_entry(dev); if (msidesc->msi_attrib.is_msix) xen_pci_frontend_disable_msix(dev); else diff --git a/arch/x86/platform/Makefile b/arch/x86/platform/Makefile index f1a6c8e86ddd..184842ef332e 100644 --- a/arch/x86/platform/Makefile +++ b/arch/x86/platform/Makefile @@ -5,6 +5,7 @@ obj-y += efi/ obj-y += geode/ obj-y += goldfish/ obj-y += iris/ +obj-y += intel/ obj-y += intel-mid/ obj-y += intel-quark/ obj-y += olpc/ diff --git a/arch/x86/platform/atom/Makefile b/arch/x86/platform/atom/Makefile index 0a3a40cbc794..40983f5b0858 100644 --- a/arch/x86/platform/atom/Makefile +++ b/arch/x86/platform/atom/Makefile @@ -1 +1,2 @@ -obj-$(CONFIG_PUNIT_ATOM_DEBUG) += punit_atom_debug.o +obj-$(CONFIG_PMC_ATOM) += pmc_atom.o +obj-$(CONFIG_PUNIT_ATOM_DEBUG) += punit_atom_debug.o diff --git a/arch/x86/kernel/pmc_atom.c b/arch/x86/platform/atom/pmc_atom.c index d66a4fe6caee..964ff4fc61f9 100644 --- a/arch/x86/kernel/pmc_atom.c +++ b/arch/x86/platform/atom/pmc_atom.c @@ -15,7 +15,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/module.h> #include <linux/init.h> #include <linux/pci.h> #include <linux/device.h> @@ -25,80 +24,149 @@ #include <asm/pmc_atom.h> +struct pmc_bit_map { + const char *name; + u32 bit_mask; +}; + +struct pmc_reg_map { + const struct pmc_bit_map *d3_sts_0; + const struct pmc_bit_map *d3_sts_1; + const struct pmc_bit_map *func_dis; + const struct pmc_bit_map *func_dis_2; + const struct pmc_bit_map *pss; +}; + struct pmc_dev { u32 base_addr; void __iomem *regmap; + const struct pmc_reg_map *map; #ifdef CONFIG_DEBUG_FS struct dentry *dbgfs_dir; #endif /* CONFIG_DEBUG_FS */ + bool init; }; static struct pmc_dev pmc_device; static u32 acpi_base_addr; -struct pmc_bit_map { - const char *name; - u32 bit_mask; +static const struct pmc_bit_map d3_sts_0_map[] = { + {"LPSS1_F0_DMA", BIT_LPSS1_F0_DMA}, + {"LPSS1_F1_PWM1", BIT_LPSS1_F1_PWM1}, + {"LPSS1_F2_PWM2", BIT_LPSS1_F2_PWM2}, + {"LPSS1_F3_HSUART1", BIT_LPSS1_F3_HSUART1}, + {"LPSS1_F4_HSUART2", BIT_LPSS1_F4_HSUART2}, + {"LPSS1_F5_SPI", BIT_LPSS1_F5_SPI}, + {"LPSS1_F6_Reserved", BIT_LPSS1_F6_XXX}, + {"LPSS1_F7_Reserved", BIT_LPSS1_F7_XXX}, + {"SCC_EMMC", BIT_SCC_EMMC}, + {"SCC_SDIO", BIT_SCC_SDIO}, + {"SCC_SDCARD", BIT_SCC_SDCARD}, + {"SCC_MIPI", BIT_SCC_MIPI}, + {"HDA", BIT_HDA}, + {"LPE", BIT_LPE}, + {"OTG", BIT_OTG}, + {"USH", BIT_USH}, + {"GBE", BIT_GBE}, + {"SATA", BIT_SATA}, + {"USB_EHCI", BIT_USB_EHCI}, + {"SEC", BIT_SEC}, + {"PCIE_PORT0", BIT_PCIE_PORT0}, + {"PCIE_PORT1", BIT_PCIE_PORT1}, + {"PCIE_PORT2", BIT_PCIE_PORT2}, + {"PCIE_PORT3", BIT_PCIE_PORT3}, + {"LPSS2_F0_DMA", BIT_LPSS2_F0_DMA}, + {"LPSS2_F1_I2C1", BIT_LPSS2_F1_I2C1}, + {"LPSS2_F2_I2C2", BIT_LPSS2_F2_I2C2}, + {"LPSS2_F3_I2C3", BIT_LPSS2_F3_I2C3}, + {"LPSS2_F3_I2C4", BIT_LPSS2_F4_I2C4}, + {"LPSS2_F5_I2C5", BIT_LPSS2_F5_I2C5}, + {"LPSS2_F6_I2C6", BIT_LPSS2_F6_I2C6}, + {"LPSS2_F7_I2C7", BIT_LPSS2_F7_I2C7}, + {}, +}; + +static struct pmc_bit_map byt_d3_sts_1_map[] = { + {"SMB", BIT_SMB}, + {"OTG_SS_PHY", BIT_OTG_SS_PHY}, + {"USH_SS_PHY", BIT_USH_SS_PHY}, + {"DFX", BIT_DFX}, + {}, }; -static const struct pmc_bit_map dev_map[] = { - {"0 - LPSS1_F0_DMA", BIT_LPSS1_F0_DMA}, - {"1 - LPSS1_F1_PWM1", BIT_LPSS1_F1_PWM1}, - {"2 - LPSS1_F2_PWM2", BIT_LPSS1_F2_PWM2}, - {"3 - LPSS1_F3_HSUART1", BIT_LPSS1_F3_HSUART1}, - {"4 - LPSS1_F4_HSUART2", BIT_LPSS1_F4_HSUART2}, - {"5 - LPSS1_F5_SPI", BIT_LPSS1_F5_SPI}, - {"6 - LPSS1_F6_Reserved", BIT_LPSS1_F6_XXX}, - {"7 - LPSS1_F7_Reserved", BIT_LPSS1_F7_XXX}, - {"8 - SCC_EMMC", BIT_SCC_EMMC}, - {"9 - SCC_SDIO", BIT_SCC_SDIO}, - {"10 - SCC_SDCARD", BIT_SCC_SDCARD}, - {"11 - SCC_MIPI", BIT_SCC_MIPI}, - {"12 - HDA", BIT_HDA}, - {"13 - LPE", BIT_LPE}, - {"14 - OTG", BIT_OTG}, - {"15 - USH", BIT_USH}, - {"16 - GBE", BIT_GBE}, - {"17 - SATA", BIT_SATA}, - {"18 - USB_EHCI", BIT_USB_EHCI}, - {"19 - SEC", BIT_SEC}, - {"20 - PCIE_PORT0", BIT_PCIE_PORT0}, - {"21 - PCIE_PORT1", BIT_PCIE_PORT1}, - {"22 - PCIE_PORT2", BIT_PCIE_PORT2}, - {"23 - PCIE_PORT3", BIT_PCIE_PORT3}, - {"24 - LPSS2_F0_DMA", BIT_LPSS2_F0_DMA}, - {"25 - LPSS2_F1_I2C1", BIT_LPSS2_F1_I2C1}, - {"26 - LPSS2_F2_I2C2", BIT_LPSS2_F2_I2C2}, - {"27 - LPSS2_F3_I2C3", BIT_LPSS2_F3_I2C3}, - {"28 - LPSS2_F3_I2C4", BIT_LPSS2_F4_I2C4}, - {"29 - LPSS2_F5_I2C5", BIT_LPSS2_F5_I2C5}, - {"30 - LPSS2_F6_I2C6", BIT_LPSS2_F6_I2C6}, - {"31 - LPSS2_F7_I2C7", BIT_LPSS2_F7_I2C7}, - {"32 - SMB", BIT_SMB}, - {"33 - OTG_SS_PHY", BIT_OTG_SS_PHY}, - {"34 - USH_SS_PHY", BIT_USH_SS_PHY}, - {"35 - DFX", BIT_DFX}, +static struct pmc_bit_map cht_d3_sts_1_map[] = { + {"SMB", BIT_SMB}, + {"GMM", BIT_STS_GMM}, + {"ISH", BIT_STS_ISH}, + {}, }; -static const struct pmc_bit_map pss_map[] = { - {"0 - GBE", PMC_PSS_BIT_GBE}, - {"1 - SATA", PMC_PSS_BIT_SATA}, - {"2 - HDA", PMC_PSS_BIT_HDA}, - {"3 - SEC", PMC_PSS_BIT_SEC}, - {"4 - PCIE", PMC_PSS_BIT_PCIE}, - {"5 - LPSS", PMC_PSS_BIT_LPSS}, - {"6 - LPE", PMC_PSS_BIT_LPE}, - {"7 - DFX", PMC_PSS_BIT_DFX}, - {"8 - USH_CTRL", PMC_PSS_BIT_USH_CTRL}, - {"9 - USH_SUS", PMC_PSS_BIT_USH_SUS}, - {"10 - USH_VCCS", PMC_PSS_BIT_USH_VCCS}, - {"11 - USH_VCCA", PMC_PSS_BIT_USH_VCCA}, - {"12 - OTG_CTRL", PMC_PSS_BIT_OTG_CTRL}, - {"13 - OTG_VCCS", PMC_PSS_BIT_OTG_VCCS}, - {"14 - OTG_VCCA_CLK", PMC_PSS_BIT_OTG_VCCA_CLK}, - {"15 - OTG_VCCA", PMC_PSS_BIT_OTG_VCCA}, - {"16 - USB", PMC_PSS_BIT_USB}, - {"17 - USB_SUS", PMC_PSS_BIT_USB_SUS}, +static struct pmc_bit_map cht_func_dis_2_map[] = { + {"SMB", BIT_SMB}, + {"GMM", BIT_FD_GMM}, + {"ISH", BIT_FD_ISH}, + {}, +}; + +static const struct pmc_bit_map byt_pss_map[] = { + {"GBE", PMC_PSS_BIT_GBE}, + {"SATA", PMC_PSS_BIT_SATA}, + {"HDA", PMC_PSS_BIT_HDA}, + {"SEC", PMC_PSS_BIT_SEC}, + {"PCIE", PMC_PSS_BIT_PCIE}, + {"LPSS", PMC_PSS_BIT_LPSS}, + {"LPE", PMC_PSS_BIT_LPE}, + {"DFX", PMC_PSS_BIT_DFX}, + {"USH_CTRL", PMC_PSS_BIT_USH_CTRL}, + {"USH_SUS", PMC_PSS_BIT_USH_SUS}, + {"USH_VCCS", PMC_PSS_BIT_USH_VCCS}, + {"USH_VCCA", PMC_PSS_BIT_USH_VCCA}, + {"OTG_CTRL", PMC_PSS_BIT_OTG_CTRL}, + {"OTG_VCCS", PMC_PSS_BIT_OTG_VCCS}, + {"OTG_VCCA_CLK", PMC_PSS_BIT_OTG_VCCA_CLK}, + {"OTG_VCCA", PMC_PSS_BIT_OTG_VCCA}, + {"USB", PMC_PSS_BIT_USB}, + {"USB_SUS", PMC_PSS_BIT_USB_SUS}, + {}, +}; + +static const struct pmc_bit_map cht_pss_map[] = { + {"SATA", PMC_PSS_BIT_SATA}, + {"HDA", PMC_PSS_BIT_HDA}, + {"SEC", PMC_PSS_BIT_SEC}, + {"PCIE", PMC_PSS_BIT_PCIE}, + {"LPSS", PMC_PSS_BIT_LPSS}, + {"LPE", PMC_PSS_BIT_LPE}, + {"UFS", PMC_PSS_BIT_CHT_UFS}, + {"UXD", PMC_PSS_BIT_CHT_UXD}, + {"UXD_FD", PMC_PSS_BIT_CHT_UXD_FD}, + {"UX_ENG", PMC_PSS_BIT_CHT_UX_ENG}, + {"USB_SUS", PMC_PSS_BIT_CHT_USB_SUS}, + {"GMM", PMC_PSS_BIT_CHT_GMM}, + {"ISH", PMC_PSS_BIT_CHT_ISH}, + {"DFX_MASTER", PMC_PSS_BIT_CHT_DFX_MASTER}, + {"DFX_CLUSTER1", PMC_PSS_BIT_CHT_DFX_CLUSTER1}, + {"DFX_CLUSTER2", PMC_PSS_BIT_CHT_DFX_CLUSTER2}, + {"DFX_CLUSTER3", PMC_PSS_BIT_CHT_DFX_CLUSTER3}, + {"DFX_CLUSTER4", PMC_PSS_BIT_CHT_DFX_CLUSTER4}, + {"DFX_CLUSTER5", PMC_PSS_BIT_CHT_DFX_CLUSTER5}, + {}, +}; + +static const struct pmc_reg_map byt_reg_map = { + .d3_sts_0 = d3_sts_0_map, + .d3_sts_1 = byt_d3_sts_1_map, + .func_dis = d3_sts_0_map, + .func_dis_2 = byt_d3_sts_1_map, + .pss = byt_pss_map, +}; + +static const struct pmc_reg_map cht_reg_map = { + .d3_sts_0 = d3_sts_0_map, + .d3_sts_1 = cht_d3_sts_1_map, + .func_dis = d3_sts_0_map, + .func_dis_2 = cht_func_dis_2_map, + .pss = cht_pss_map, }; static inline u32 pmc_reg_read(struct pmc_dev *pmc, int reg_offset) @@ -111,6 +179,30 @@ static inline void pmc_reg_write(struct pmc_dev *pmc, int reg_offset, u32 val) writel(val, pmc->regmap + reg_offset); } +int pmc_atom_read(int offset, u32 *value) +{ + struct pmc_dev *pmc = &pmc_device; + + if (!pmc->init) + return -ENODEV; + + *value = pmc_reg_read(pmc, offset); + return 0; +} +EXPORT_SYMBOL_GPL(pmc_atom_read); + +int pmc_atom_write(int offset, u32 value) +{ + struct pmc_dev *pmc = &pmc_device; + + if (!pmc->init) + return -ENODEV; + + pmc_reg_write(pmc, offset, value); + return 0; +} +EXPORT_SYMBOL_GPL(pmc_atom_write); + static void pmc_power_off(void) { u16 pm1_cnt_port; @@ -142,37 +234,39 @@ static void pmc_hw_reg_setup(struct pmc_dev *pmc) } #ifdef CONFIG_DEBUG_FS +static void pmc_dev_state_print(struct seq_file *s, int reg_index, + u32 sts, const struct pmc_bit_map *sts_map, + u32 fd, const struct pmc_bit_map *fd_map) +{ + int offset = PMC_REG_BIT_WIDTH * reg_index; + int index; + + for (index = 0; sts_map[index].name; index++) { + seq_printf(s, "Dev: %-2d - %-32s\tState: %s [%s]\n", + offset + index, sts_map[index].name, + fd_map[index].bit_mask & fd ? "Disabled" : "Enabled ", + sts_map[index].bit_mask & sts ? "D3" : "D0"); + } +} + static int pmc_dev_state_show(struct seq_file *s, void *unused) { struct pmc_dev *pmc = s->private; - u32 func_dis, func_dis_2, func_dis_index; - u32 d3_sts_0, d3_sts_1, d3_sts_index; - int dev_num, dev_index, reg_index; + const struct pmc_reg_map *m = pmc->map; + u32 func_dis, func_dis_2; + u32 d3_sts_0, d3_sts_1; func_dis = pmc_reg_read(pmc, PMC_FUNC_DIS); func_dis_2 = pmc_reg_read(pmc, PMC_FUNC_DIS_2); d3_sts_0 = pmc_reg_read(pmc, PMC_D3_STS_0); d3_sts_1 = pmc_reg_read(pmc, PMC_D3_STS_1); - dev_num = ARRAY_SIZE(dev_map); - - for (dev_index = 0; dev_index < dev_num; dev_index++) { - reg_index = dev_index / PMC_REG_BIT_WIDTH; - if (reg_index) { - func_dis_index = func_dis_2; - d3_sts_index = d3_sts_1; - } else { - func_dis_index = func_dis; - d3_sts_index = d3_sts_0; - } - - seq_printf(s, "Dev: %-32s\tState: %s [%s]\n", - dev_map[dev_index].name, - dev_map[dev_index].bit_mask & func_dis_index ? - "Disabled" : "Enabled ", - dev_map[dev_index].bit_mask & d3_sts_index ? - "D3" : "D0"); - } + /* Low part */ + pmc_dev_state_print(s, 0, d3_sts_0, m->d3_sts_0, func_dis, m->func_dis); + + /* High part */ + pmc_dev_state_print(s, 1, d3_sts_1, m->d3_sts_1, func_dis_2, m->func_dis_2); + return 0; } @@ -191,13 +285,14 @@ static const struct file_operations pmc_dev_state_ops = { static int pmc_pss_state_show(struct seq_file *s, void *unused) { struct pmc_dev *pmc = s->private; + const struct pmc_bit_map *map = pmc->map->pss; u32 pss = pmc_reg_read(pmc, PMC_PSS); - int pss_index; + int index; - for (pss_index = 0; pss_index < ARRAY_SIZE(pss_map); pss_index++) { - seq_printf(s, "Island: %-32s\tState: %s\n", - pss_map[pss_index].name, - pss_map[pss_index].bit_mask & pss ? "Off" : "On"); + for (index = 0; map[index].name; index++) { + seq_printf(s, "Island: %-2d - %-32s\tState: %s\n", + index, map[index].name, + map[index].bit_mask & pss ? "Off" : "On"); } return 0; } @@ -250,7 +345,7 @@ static void pmc_dbgfs_unregister(struct pmc_dev *pmc) debugfs_remove_recursive(pmc->dbgfs_dir); } -static int pmc_dbgfs_register(struct pmc_dev *pmc, struct pci_dev *pdev) +static int pmc_dbgfs_register(struct pmc_dev *pmc) { struct dentry *dir, *f; @@ -262,24 +357,18 @@ static int pmc_dbgfs_register(struct pmc_dev *pmc, struct pci_dev *pdev) f = debugfs_create_file("dev_state", S_IFREG | S_IRUGO, dir, pmc, &pmc_dev_state_ops); - if (!f) { - dev_err(&pdev->dev, "dev_state register failed\n"); + if (!f) goto err; - } f = debugfs_create_file("pss_state", S_IFREG | S_IRUGO, dir, pmc, &pmc_pss_state_ops); - if (!f) { - dev_err(&pdev->dev, "pss_state register failed\n"); + if (!f) goto err; - } f = debugfs_create_file("sleep_state", S_IFREG | S_IRUGO, dir, pmc, &pmc_sleep_tmr_ops); - if (!f) { - dev_err(&pdev->dev, "sleep_state register failed\n"); + if (!f) goto err; - } return 0; err: @@ -287,15 +376,16 @@ err: return -ENODEV; } #else -static int pmc_dbgfs_register(struct pmc_dev *pmc, struct pci_dev *pdev) +static int pmc_dbgfs_register(struct pmc_dev *pmc) { return 0; } #endif /* CONFIG_DEBUG_FS */ -static int pmc_setup_dev(struct pci_dev *pdev) +static int pmc_setup_dev(struct pci_dev *pdev, const struct pci_device_id *ent) { struct pmc_dev *pmc = &pmc_device; + const struct pmc_reg_map *map = (struct pmc_reg_map *)ent->driver_data; int ret; /* Obtain ACPI base address */ @@ -315,32 +405,30 @@ static int pmc_setup_dev(struct pci_dev *pdev) return -ENOMEM; } + pmc->map = map; + /* PMC hardware registers setup */ pmc_hw_reg_setup(pmc); - ret = pmc_dbgfs_register(pmc, pdev); - if (ret) { - iounmap(pmc->regmap); - } + ret = pmc_dbgfs_register(pmc); + if (ret) + dev_warn(&pdev->dev, "debugfs register failed\n"); + pmc->init = true; return ret; } /* * Data for PCI driver interface * - * This data only exists for exporting the supported - * PCI ids via MODULE_DEVICE_TABLE. We do not actually - * register a pci_driver, because lpc_ich will register - * a driver on the same PCI id. + * used by pci_match_id() call below. */ static const struct pci_device_id pmc_pci_ids[] = { - { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_VLV_PMC) }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_VLV_PMC), (kernel_ulong_t)&byt_reg_map }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_CHT_PMC), (kernel_ulong_t)&cht_reg_map }, { 0, }, }; -MODULE_DEVICE_TABLE(pci, pmc_pci_ids); - static int __init pmc_atom_init(void) { struct pci_dev *pdev = NULL; @@ -357,15 +445,16 @@ static int __init pmc_atom_init(void) for_each_pci_dev(pdev) { ent = pci_match_id(pmc_pci_ids, pdev); if (ent) - return pmc_setup_dev(pdev); + return pmc_setup_dev(pdev, ent); } /* Device not found. */ return -ENODEV; } -module_init(pmc_atom_init); -/* no module_exit, this driver shouldn't be unloaded */ +device_initcall(pmc_atom_init); +/* MODULE_AUTHOR("Aubrey Li <aubrey.li@linux.intel.com>"); MODULE_DESCRIPTION("Intel Atom SOC Power Management Controller Interface"); MODULE_LICENSE("GPL v2"); +*/ diff --git a/arch/x86/platform/atom/punit_atom_debug.c b/arch/x86/platform/atom/punit_atom_debug.c index 5ca8ead91579..81c769e80614 100644 --- a/arch/x86/platform/atom/punit_atom_debug.c +++ b/arch/x86/platform/atom/punit_atom_debug.c @@ -25,8 +25,6 @@ #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 */ @@ -85,9 +83,8 @@ static int punit_dev_state_show(struct seq_file *seq_file, void *unused) 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); + status = iosf_mbi_read(BT_MBI_UNIT_PMC, MBI_REG_READ, + punit_devp->reg, &punit_pwr_status); if (status) { seq_printf(seq_file, "%9s : Read Failed\n", punit_devp->name); diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c index d7f997f7c26d..ea48449b2e63 100644 --- a/arch/x86/platform/efi/efi-bgrt.c +++ b/arch/x86/platform/efi/efi-bgrt.c @@ -50,11 +50,16 @@ void __init efi_bgrt_init(void) bgrt_tab->version); return; } - if (bgrt_tab->status != 1) { - pr_err("Ignoring BGRT: invalid status %u (expected 1)\n", + if (bgrt_tab->status & 0xfe) { + pr_err("Ignoring BGRT: reserved status bits are non-zero %u\n", bgrt_tab->status); return; } + if (bgrt_tab->status != 1) { + pr_debug("Ignoring BGRT: invalid status %u (expected 1)\n", + bgrt_tab->status); + return; + } if (bgrt_tab->image_type != 0) { pr_err("Ignoring BGRT: invalid image type %u (expected 0)\n", bgrt_tab->image_type); diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index e4308fe6afe8..ad285404ea7f 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -194,7 +194,7 @@ static void __init do_add_efi_memmap(void) int __init efi_memblock_x86_reserve_range(void) { struct efi_info *e = &boot_params.efi_info; - unsigned long pmap; + phys_addr_t pmap; if (efi_enabled(EFI_PARAVIRT)) return 0; @@ -209,7 +209,7 @@ int __init efi_memblock_x86_reserve_range(void) #else pmap = (e->efi_memmap | ((__u64)e->efi_memmap_hi << 32)); #endif - memmap.phys_map = (void *)pmap; + memmap.phys_map = pmap; memmap.nr_map = e->efi_memmap_size / e->efi_memdesc_size; memmap.desc_size = e->efi_memdesc_size; @@ -222,7 +222,7 @@ int __init efi_memblock_x86_reserve_range(void) return 0; } -static void __init print_efi_memmap(void) +void __init efi_print_memmap(void) { #ifdef EFI_DEBUG efi_memory_desc_t *md; @@ -524,7 +524,7 @@ void __init efi_init(void) return; if (efi_enabled(EFI_DBG)) - print_efi_memmap(); + efi_print_memmap(); efi_esrt_init(); } @@ -650,7 +650,7 @@ static void __init get_systab_virt_addr(efi_memory_desc_t *md) static void __init save_runtime_map(void) { -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE efi_memory_desc_t *md; void *tmp, *p, *q = NULL; int count = 0; @@ -705,6 +705,70 @@ out: } /* + * Iterate the EFI memory map in reverse order because the regions + * will be mapped top-down. The end result is the same as if we had + * mapped things forward, but doesn't require us to change the + * existing implementation of efi_map_region(). + */ +static inline void *efi_map_next_entry_reverse(void *entry) +{ + /* Initial call */ + if (!entry) + return memmap.map_end - memmap.desc_size; + + entry -= memmap.desc_size; + if (entry < memmap.map) + return NULL; + + return entry; +} + +/* + * efi_map_next_entry - Return the next EFI memory map descriptor + * @entry: Previous EFI memory map descriptor + * + * This is a helper function to iterate over the EFI memory map, which + * we do in different orders depending on the current configuration. + * + * To begin traversing the memory map @entry must be %NULL. + * + * Returns %NULL when we reach the end of the memory map. + */ +static void *efi_map_next_entry(void *entry) +{ + if (!efi_enabled(EFI_OLD_MEMMAP) && efi_enabled(EFI_64BIT)) { + /* + * Starting in UEFI v2.5 the EFI_PROPERTIES_TABLE + * config table feature requires us to map all entries + * in the same order as they appear in the EFI memory + * map. That is to say, entry N must have a lower + * virtual address than entry N+1. This is because the + * firmware toolchain leaves relative references in + * the code/data sections, which are split and become + * separate EFI memory regions. Mapping things + * out-of-order leads to the firmware accessing + * unmapped addresses. + * + * Since we need to map things this way whether or not + * the kernel actually makes use of + * EFI_PROPERTIES_TABLE, let's just switch to this + * scheme by default for 64-bit. + */ + return efi_map_next_entry_reverse(entry); + } + + /* Initial call */ + if (!entry) + return memmap.map; + + entry += memmap.desc_size; + if (entry >= memmap.map_end) + return NULL; + + return entry; +} + +/* * Map the efi memory ranges of the runtime services and update new_mmap with * virtual addresses. */ @@ -714,7 +778,8 @@ static void * __init efi_map_regions(int *count, int *pg_shift) unsigned long left = 0; efi_memory_desc_t *md; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { + p = NULL; + while ((p = efi_map_next_entry(p))) { md = p; if (!(md->attribute & EFI_MEMORY_RUNTIME)) { #ifdef CONFIG_X86_64 @@ -748,7 +813,7 @@ static void * __init efi_map_regions(int *count, int *pg_shift) static void __init kexec_enter_virtual_mode(void) { -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE efi_memory_desc_t *md; void *p; @@ -952,24 +1017,6 @@ u32 efi_mem_type(unsigned long phys_addr) return 0; } -u64 efi_mem_attributes(unsigned long phys_addr) -{ - efi_memory_desc_t *md; - void *p; - - if (!efi_enabled(EFI_MEMMAP)) - return 0; - - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - md = p; - if ((md->phys_addr <= phys_addr) && - (phys_addr < (md->phys_addr + - (md->num_pages << EFI_PAGE_SHIFT)))) - return md->attribute; - } - return 0; -} - static int __init arch_parse_efi_cmdline(char *str) { if (!str) { @@ -979,8 +1026,6 @@ static int __init arch_parse_efi_cmdline(char *str) if (parse_option_str(str, "old_map")) set_bit(EFI_OLD_MEMMAP, &efi.flags); - if (parse_option_str(str, "debug")) - set_bit(EFI_DBG, &efi.flags); return 0; } diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c index 01d54ea766c1..1bbc21e2e4ae 100644 --- a/arch/x86/platform/intel-mid/intel-mid.c +++ b/arch/x86/platform/intel-mid/intel-mid.c @@ -61,7 +61,7 @@ enum intel_mid_timer_options intel_mid_timer_options; /* intel_mid_ops to store sub arch ops */ -struct intel_mid_ops *intel_mid_ops; +static struct intel_mid_ops *intel_mid_ops; /* getter function for sub arch ops*/ static void *(*get_intel_mid_ops[])(void) = INTEL_MID_OPS_INIT; enum intel_mid_cpu_type __intel_mid_cpu_chip; diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c index ce992e8cc065..5ee360a951ce 100644 --- a/arch/x86/platform/intel-mid/sfi.c +++ b/arch/x86/platform/intel-mid/sfi.c @@ -197,10 +197,9 @@ static int __init sfi_parse_gpio(struct sfi_table_header *table) num = SFI_GET_NUM_ENTRIES(sb, struct sfi_gpio_table_entry); pentry = (struct sfi_gpio_table_entry *)sb->pentry; - gpio_table = kmalloc(num * sizeof(*pentry), GFP_KERNEL); + gpio_table = kmemdup(pentry, num * sizeof(*pentry), GFP_KERNEL); if (!gpio_table) return -1; - memcpy(gpio_table, pentry, num * sizeof(*pentry)); gpio_num_entry = num; pr_debug("GPIO pin info:\n"); diff --git a/arch/x86/platform/intel-quark/imr.c b/arch/x86/platform/intel-quark/imr.c index 0ee619f9fcb7..c1bdafaac3ca 100644 --- a/arch/x86/platform/intel-quark/imr.c +++ b/arch/x86/platform/intel-quark/imr.c @@ -111,23 +111,19 @@ static int imr_read(struct imr_device *idev, u32 imr_id, struct imr_regs *imr) u32 reg = imr_id * IMR_NUM_REGS + idev->reg_base; int ret; - ret = iosf_mbi_read(QRK_MBI_UNIT_MM, QRK_MBI_MM_READ, - reg++, &imr->addr_lo); + ret = iosf_mbi_read(QRK_MBI_UNIT_MM, MBI_REG_READ, reg++, &imr->addr_lo); if (ret) return ret; - ret = iosf_mbi_read(QRK_MBI_UNIT_MM, QRK_MBI_MM_READ, - reg++, &imr->addr_hi); + ret = iosf_mbi_read(QRK_MBI_UNIT_MM, MBI_REG_READ, reg++, &imr->addr_hi); if (ret) return ret; - ret = iosf_mbi_read(QRK_MBI_UNIT_MM, QRK_MBI_MM_READ, - reg++, &imr->rmask); + ret = iosf_mbi_read(QRK_MBI_UNIT_MM, MBI_REG_READ, reg++, &imr->rmask); if (ret) return ret; - return iosf_mbi_read(QRK_MBI_UNIT_MM, QRK_MBI_MM_READ, - reg++, &imr->wmask); + return iosf_mbi_read(QRK_MBI_UNIT_MM, MBI_REG_READ, reg++, &imr->wmask); } /** @@ -151,31 +147,27 @@ static int imr_write(struct imr_device *idev, u32 imr_id, local_irq_save(flags); - ret = iosf_mbi_write(QRK_MBI_UNIT_MM, QRK_MBI_MM_WRITE, reg++, - imr->addr_lo); + ret = iosf_mbi_write(QRK_MBI_UNIT_MM, MBI_REG_WRITE, reg++, imr->addr_lo); if (ret) goto failed; - ret = iosf_mbi_write(QRK_MBI_UNIT_MM, QRK_MBI_MM_WRITE, - reg++, imr->addr_hi); + ret = iosf_mbi_write(QRK_MBI_UNIT_MM, MBI_REG_WRITE, reg++, imr->addr_hi); if (ret) goto failed; - ret = iosf_mbi_write(QRK_MBI_UNIT_MM, QRK_MBI_MM_WRITE, - reg++, imr->rmask); + ret = iosf_mbi_write(QRK_MBI_UNIT_MM, MBI_REG_WRITE, reg++, imr->rmask); if (ret) goto failed; - ret = iosf_mbi_write(QRK_MBI_UNIT_MM, QRK_MBI_MM_WRITE, - reg++, imr->wmask); + ret = iosf_mbi_write(QRK_MBI_UNIT_MM, MBI_REG_WRITE, reg++, imr->wmask); if (ret) goto failed; /* Lock bit must be set separately to addr_lo address bits. */ if (lock) { imr->addr_lo |= IMR_LOCK; - ret = iosf_mbi_write(QRK_MBI_UNIT_MM, QRK_MBI_MM_WRITE, - reg - IMR_NUM_REGS, imr->addr_lo); + ret = iosf_mbi_write(QRK_MBI_UNIT_MM, MBI_REG_WRITE, + reg - IMR_NUM_REGS, imr->addr_lo); if (ret) goto failed; } diff --git a/arch/x86/platform/intel/Makefile b/arch/x86/platform/intel/Makefile new file mode 100644 index 000000000000..b878032fbc82 --- /dev/null +++ b/arch/x86/platform/intel/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_IOSF_MBI) += iosf_mbi.o diff --git a/arch/x86/kernel/iosf_mbi.c b/arch/x86/platform/intel/iosf_mbi.c index 82f8d02f0df2..edf2c54bf131 100644 --- a/arch/x86/kernel/iosf_mbi.c +++ b/arch/x86/platform/intel/iosf_mbi.c @@ -30,7 +30,9 @@ #define PCI_DEVICE_ID_BAYTRAIL 0x0F00 #define PCI_DEVICE_ID_BRASWELL 0x2280 #define PCI_DEVICE_ID_QUARK_X1000 0x0958 +#define PCI_DEVICE_ID_TANGIER 0x1170 +static struct pci_dev *mbi_pdev; static DEFINE_SPINLOCK(iosf_mbi_lock); static inline u32 iosf_mbi_form_mcr(u8 op, u8 port, u8 offset) @@ -38,8 +40,6 @@ static inline u32 iosf_mbi_form_mcr(u8 op, u8 port, u8 offset) return (op << 24) | (port << 16) | (offset << 8) | MBI_ENABLE; } -static struct pci_dev *mbi_pdev; /* one mbi device */ - static int iosf_mbi_pci_read_mdr(u32 mcrx, u32 mcr, u32 *mdr) { int result; @@ -104,7 +104,7 @@ int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr) unsigned long flags; int ret; - /*Access to the GFX unit is handled by GPU code */ + /* Access to the GFX unit is handled by GPU code */ if (port == BT_MBI_UNIT_GFX) { WARN_ON(1); return -EPERM; @@ -127,7 +127,7 @@ int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr) unsigned long flags; int ret; - /*Access to the GFX unit is handled by GPU code */ + /* Access to the GFX unit is handled by GPU code */ if (port == BT_MBI_UNIT_GFX) { WARN_ON(1); return -EPERM; @@ -151,7 +151,7 @@ int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask) unsigned long flags; int ret; - /*Access to the GFX unit is handled by GPU code */ + /* Access to the GFX unit is handled by GPU code */ if (port == BT_MBI_UNIT_GFX) { WARN_ON(1); return -EPERM; @@ -240,17 +240,17 @@ static void iosf_sideband_debug_init(void) /* mdr */ d = debugfs_create_x32("mdr", 0660, iosf_dbg, &dbg_mdr); - if (IS_ERR_OR_NULL(d)) + if (!d) goto cleanup; /* mcrx */ - debugfs_create_x32("mcrx", 0660, iosf_dbg, &dbg_mcrx); - if (IS_ERR_OR_NULL(d)) + d = debugfs_create_x32("mcrx", 0660, iosf_dbg, &dbg_mcrx); + if (!d) goto cleanup; /* mcr - initiates mailbox tranaction */ - debugfs_create_file("mcr", 0660, iosf_dbg, &dbg_mcr, &iosf_mcr_fops); - if (IS_ERR_OR_NULL(d)) + d = debugfs_create_file("mcr", 0660, iosf_dbg, &dbg_mcr, &iosf_mcr_fops); + if (!d) goto cleanup; return; @@ -292,6 +292,7 @@ static const struct pci_device_id iosf_mbi_pci_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BAYTRAIL) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BRASWELL) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_QUARK_X1000) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_TANGIER) }, { 0, }, }; MODULE_DEVICE_TABLE(pci, iosf_mbi_pci_ids); @@ -314,10 +315,8 @@ static void __exit iosf_mbi_exit(void) iosf_debugfs_remove(); pci_unregister_driver(&iosf_mbi_pci_driver); - if (mbi_pdev) { - pci_dev_put(mbi_pdev); - mbi_pdev = NULL; - } + pci_dev_put(mbi_pdev); + mbi_pdev = NULL; } module_init(iosf_mbi_init); diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c index 8570abe68be1..e1c24631afbb 100644 --- a/arch/x86/platform/uv/uv_irq.c +++ b/arch/x86/platform/uv/uv_irq.c @@ -89,7 +89,7 @@ static int uv_domain_alloc(struct irq_domain *domain, unsigned int virq, return -EINVAL; chip_data = kmalloc_node(sizeof(*chip_data), GFP_KERNEL, - irq_data->node); + irq_data_get_node(irq_data)); if (!chip_data) return -ENOMEM; diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index 020c101c255f..8dd80050d705 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -28,6 +28,7 @@ #include <linux/nmi.h> #include <linux/sched.h> #include <linux/slab.h> +#include <linux/clocksource.h> #include <asm/apic.h> #include <asm/current.h> @@ -376,38 +377,42 @@ static void uv_nmi_wait(int master) atomic_read(&uv_nmi_cpus_in_nmi), num_online_cpus()); } +/* Dump Instruction Pointer header */ static void uv_nmi_dump_cpu_ip_hdr(void) { - printk(KERN_DEFAULT - "\nUV: %4s %6s %-32s %s (Note: PID 0 not listed)\n", + pr_info("\nUV: %4s %6s %-32s %s (Note: PID 0 not listed)\n", "CPU", "PID", "COMMAND", "IP"); } +/* Dump Instruction Pointer info */ static void uv_nmi_dump_cpu_ip(int cpu, struct pt_regs *regs) { - printk(KERN_DEFAULT "UV: %4d %6d %-32.32s ", - cpu, current->pid, current->comm); - + pr_info("UV: %4d %6d %-32.32s ", cpu, current->pid, current->comm); printk_address(regs->ip); } -/* Dump this cpu's state */ +/* + * Dump this CPU's state. If action was set to "kdump" and the crash_kexec + * failed, then we provide "dump" as an alternate action. Action "dump" now + * also includes the show "ips" (instruction pointers) action whereas the + * action "ips" only displays instruction pointers for the non-idle CPU's. + * This is an abbreviated form of the "ps" command. + */ static void uv_nmi_dump_state_cpu(int cpu, struct pt_regs *regs) { const char *dots = " ................................. "; - if (uv_nmi_action_is("ips")) { - if (cpu == 0) - uv_nmi_dump_cpu_ip_hdr(); + if (cpu == 0) + uv_nmi_dump_cpu_ip_hdr(); - if (current->pid != 0) - uv_nmi_dump_cpu_ip(cpu, regs); + if (current->pid != 0 || !uv_nmi_action_is("ips")) + uv_nmi_dump_cpu_ip(cpu, regs); - } else if (uv_nmi_action_is("dump")) { - printk(KERN_DEFAULT - "UV:%sNMI process trace for CPU %d\n", dots, cpu); + if (uv_nmi_action_is("dump")) { + pr_info("UV:%sNMI process trace for CPU %d\n", dots, cpu); show_regs(regs); } + this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_DUMP_DONE); } @@ -469,8 +474,7 @@ static void uv_nmi_dump_state(int cpu, struct pt_regs *regs, int master) uv_nmi_trigger_dump(tcpu); } if (ignored) - printk(KERN_DEFAULT "UV: %d CPUs ignored NMI\n", - ignored); + pr_alert("UV: %d CPUs ignored NMI\n", ignored); console_loglevel = saved_console_loglevel; pr_alert("UV: process trace complete\n"); @@ -492,8 +496,9 @@ static void uv_nmi_touch_watchdogs(void) touch_nmi_watchdog(); } -#if defined(CONFIG_KEXEC) static atomic_t uv_nmi_kexec_failed; + +#if defined(CONFIG_KEXEC_CORE) static void uv_nmi_kdump(int cpu, int master, struct pt_regs *regs) { /* Call crash to dump system state */ @@ -502,10 +507,9 @@ static void uv_nmi_kdump(int cpu, int master, struct pt_regs *regs) crash_kexec(regs); pr_emerg("UV: crash_kexec unexpectedly returned, "); + atomic_set(&uv_nmi_kexec_failed, 1); if (!kexec_crash_image) { pr_cont("crash kernel not loaded\n"); - atomic_set(&uv_nmi_kexec_failed, 1); - uv_nmi_sync_exit(1); return; } pr_cont("kexec busy, stalling cpus while waiting\n"); @@ -514,18 +518,16 @@ static void uv_nmi_kdump(int cpu, int master, struct pt_regs *regs) /* If crash exec fails the slaves should return, otherwise stall */ while (atomic_read(&uv_nmi_kexec_failed) == 0) mdelay(10); - - /* Crash kernel most likely not loaded, return in an orderly fashion */ - uv_nmi_sync_exit(0); } -#else /* !CONFIG_KEXEC */ +#else /* !CONFIG_KEXEC_CORE */ static inline void uv_nmi_kdump(int cpu, int master, struct pt_regs *regs) { if (master) pr_err("UV: NMI kdump: KEXEC not supported in this kernel\n"); + atomic_set(&uv_nmi_kexec_failed, 1); } -#endif /* !CONFIG_KEXEC */ +#endif /* !CONFIG_KEXEC_CORE */ #ifdef CONFIG_KGDB #ifdef CONFIG_KGDB_KDB @@ -613,9 +615,14 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs) master = (atomic_read(&uv_nmi_cpu) == cpu); /* If NMI action is "kdump", then attempt to do it */ - if (uv_nmi_action_is("kdump")) + if (uv_nmi_action_is("kdump")) { uv_nmi_kdump(cpu, master, regs); + /* Unexpected return, revert action to "dump" */ + if (master) + strncpy(uv_nmi_action, "dump", strlen(uv_nmi_action)); + } + /* Pause as all cpus enter the NMI handler */ uv_nmi_wait(master); @@ -640,6 +647,7 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs) atomic_set(&uv_nmi_cpus_in_nmi, -1); atomic_set(&uv_nmi_cpu, -1); atomic_set(&uv_in_nmi, 0); + atomic_set(&uv_nmi_kexec_failed, 0); } uv_nmi_touch_watchdogs(); diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c index a244237f3cfa..2b158a9fa1d7 100644 --- a/arch/x86/platform/uv/uv_time.c +++ b/arch/x86/platform/uv/uv_time.c @@ -32,8 +32,7 @@ static cycle_t uv_read_rtc(struct clocksource *cs); static int uv_rtc_next_event(unsigned long, struct clock_event_device *); -static void uv_rtc_timer_setup(enum clock_event_mode, - struct clock_event_device *); +static int uv_rtc_shutdown(struct clock_event_device *evt); static struct clocksource clocksource_uv = { .name = RTC_NAME, @@ -44,14 +43,14 @@ static struct clocksource clocksource_uv = { }; static struct clock_event_device clock_event_device_uv = { - .name = RTC_NAME, - .features = CLOCK_EVT_FEAT_ONESHOT, - .shift = 20, - .rating = 400, - .irq = -1, - .set_next_event = uv_rtc_next_event, - .set_mode = uv_rtc_timer_setup, - .event_handler = NULL, + .name = RTC_NAME, + .features = CLOCK_EVT_FEAT_ONESHOT, + .shift = 20, + .rating = 400, + .irq = -1, + .set_next_event = uv_rtc_next_event, + .set_state_shutdown = uv_rtc_shutdown, + .event_handler = NULL, }; static DEFINE_PER_CPU(struct clock_event_device, cpu_ced); @@ -321,24 +320,14 @@ static int uv_rtc_next_event(unsigned long delta, } /* - * Setup the RTC timer in oneshot mode + * Shutdown the RTC timer */ -static void uv_rtc_timer_setup(enum clock_event_mode mode, - struct clock_event_device *evt) +static int uv_rtc_shutdown(struct clock_event_device *evt) { int ced_cpu = cpumask_first(evt->cpumask); - switch (mode) { - case CLOCK_EVT_MODE_PERIODIC: - case CLOCK_EVT_MODE_ONESHOT: - case CLOCK_EVT_MODE_RESUME: - /* Nothing to do here yet */ - break; - case CLOCK_EVT_MODE_UNUSED: - case CLOCK_EVT_MODE_SHUTDOWN: - uv_rtc_unset_timer(ced_cpu, 1); - break; - } + uv_rtc_unset_timer(ced_cpu, 1); + return 0; } static void uv_rtc_interrupt(void) diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 9ab52791fed5..d5f64996394a 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -23,6 +23,7 @@ #include <asm/debugreg.h> #include <asm/cpu.h> #include <asm/mmu_context.h> +#include <linux/dmi.h> #ifdef CONFIG_X86_32 __visible unsigned long saved_context_ebx; @@ -32,6 +33,29 @@ __visible unsigned long saved_context_eflags; #endif struct saved_context saved_context; +static void msr_save_context(struct saved_context *ctxt) +{ + struct saved_msr *msr = ctxt->saved_msrs.array; + struct saved_msr *end = msr + ctxt->saved_msrs.num; + + while (msr < end) { + msr->valid = !rdmsrl_safe(msr->info.msr_no, &msr->info.reg.q); + msr++; + } +} + +static void msr_restore_context(struct saved_context *ctxt) +{ + struct saved_msr *msr = ctxt->saved_msrs.array; + struct saved_msr *end = msr + ctxt->saved_msrs.num; + + while (msr < end) { + if (msr->valid) + wrmsrl(msr->info.msr_no, msr->info.reg.q); + msr++; + } +} + /** * __save_processor_state - save CPU registers before creating a * hibernation image and before restoring the memory state from it @@ -111,6 +135,7 @@ static void __save_processor_state(struct saved_context *ctxt) #endif ctxt->misc_enable_saved = !rdmsrl_safe(MSR_IA32_MISC_ENABLE, &ctxt->misc_enable); + msr_save_context(ctxt); } /* Needed by apm.c */ @@ -229,6 +254,7 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) x86_platform.restore_sched_clock_state(); mtrr_bp_restore(); perf_restore_debug_store(); + msr_restore_context(ctxt); } /* Needed by apm.c */ @@ -320,3 +346,69 @@ static int __init bsp_pm_check_init(void) } core_initcall(bsp_pm_check_init); + +static int msr_init_context(const u32 *msr_id, const int total_num) +{ + int i = 0; + struct saved_msr *msr_array; + + if (saved_context.saved_msrs.array || saved_context.saved_msrs.num > 0) { + pr_err("x86/pm: MSR quirk already applied, please check your DMI match table.\n"); + return -EINVAL; + } + + msr_array = kmalloc_array(total_num, sizeof(struct saved_msr), GFP_KERNEL); + if (!msr_array) { + pr_err("x86/pm: Can not allocate memory to save/restore MSRs during suspend.\n"); + return -ENOMEM; + } + + for (i = 0; i < total_num; i++) { + msr_array[i].info.msr_no = msr_id[i]; + msr_array[i].valid = false; + msr_array[i].info.reg.q = 0; + } + saved_context.saved_msrs.num = total_num; + saved_context.saved_msrs.array = msr_array; + + return 0; +} + +/* + * The following section is a quirk framework for problematic BIOSen: + * Sometimes MSRs are modified by the BIOSen after suspended to + * RAM, this might cause unexpected behavior after wakeup. + * Thus we save/restore these specified MSRs across suspend/resume + * in order to work around it. + * + * For any further problematic BIOSen/platforms, + * please add your own function similar to msr_initialize_bdw. + */ +static int msr_initialize_bdw(const struct dmi_system_id *d) +{ + /* Add any extra MSR ids into this array. */ + u32 bdw_msr_id[] = { MSR_IA32_THERM_CONTROL }; + + pr_info("x86/pm: %s detected, MSR saving is needed during suspending.\n", d->ident); + return msr_init_context(bdw_msr_id, ARRAY_SIZE(bdw_msr_id)); +} + +static struct dmi_system_id msr_save_dmi_table[] = { + { + .callback = msr_initialize_bdw, + .ident = "BROADWELL BDX_EP", + .matches = { + DMI_MATCH(DMI_PRODUCT_NAME, "GRANTLEY"), + DMI_MATCH(DMI_PRODUCT_VERSION, "E63448-400"), + }, + }, + {} +}; + +static int pm_check_save_msr(void) +{ + dmi_check_system(msr_save_dmi_table); + return 0; +} + +device_initcall(pm_check_save_msr); diff --git a/arch/x86/ras/Kconfig b/arch/x86/ras/Kconfig new file mode 100644 index 000000000000..df280da34825 --- /dev/null +++ b/arch/x86/ras/Kconfig @@ -0,0 +1,9 @@ +config AMD_MCE_INJ + tristate "Simple MCE injection interface for AMD processors" + depends on RAS && EDAC_DECODE_MCE && DEBUG_FS && AMD_NB + default n + help + This is a simple debugfs interface to inject MCEs and test different + aspects of the MCE handling code. + + WARNING: Do not even assume this interface is staying stable! diff --git a/arch/x86/ras/Makefile b/arch/x86/ras/Makefile new file mode 100644 index 000000000000..dd2c98b84037 --- /dev/null +++ b/arch/x86/ras/Makefile @@ -0,0 +1,2 @@ +obj-$(CONFIG_AMD_MCE_INJ) += mce_amd_inj.o + diff --git a/arch/x86/ras/mce_amd_inj.c b/arch/x86/ras/mce_amd_inj.c new file mode 100644 index 000000000000..55d38cfa46c2 --- /dev/null +++ b/arch/x86/ras/mce_amd_inj.c @@ -0,0 +1,464 @@ +/* + * A simple MCE injection facility for testing different aspects of the RAS + * code. This driver should be built as module so that it can be loaded + * on production kernels for testing purposes. + * + * This file may be distributed under the terms of the GNU General Public + * License version 2. + * + * Copyright (c) 2010-15: Borislav Petkov <bp@alien8.de> + * Advanced Micro Devices Inc. + */ + +#include <linux/kobject.h> +#include <linux/debugfs.h> +#include <linux/device.h> +#include <linux/module.h> +#include <linux/cpu.h> +#include <linux/string.h> +#include <linux/uaccess.h> +#include <linux/pci.h> + +#include <asm/mce.h> +#include <asm/amd_nb.h> +#include <asm/irq_vectors.h> + +#include "../kernel/cpu/mcheck/mce-internal.h" + +/* + * Collect all the MCi_XXX settings + */ +static struct mce i_mce; +static struct dentry *dfs_inj; + +static u8 n_banks; + +#define MAX_FLAG_OPT_SIZE 3 +#define NBCFG 0x44 + +enum injection_type { + SW_INJ = 0, /* SW injection, simply decode the error */ + HW_INJ, /* Trigger a #MC */ + DFR_INT_INJ, /* Trigger Deferred error interrupt */ + THR_INT_INJ, /* Trigger threshold interrupt */ + N_INJ_TYPES, +}; + +static const char * const flags_options[] = { + [SW_INJ] = "sw", + [HW_INJ] = "hw", + [DFR_INT_INJ] = "df", + [THR_INT_INJ] = "th", + NULL +}; + +/* Set default injection to SW_INJ */ +static enum injection_type inj_type = SW_INJ; + +#define MCE_INJECT_SET(reg) \ +static int inj_##reg##_set(void *data, u64 val) \ +{ \ + struct mce *m = (struct mce *)data; \ + \ + m->reg = val; \ + return 0; \ +} + +MCE_INJECT_SET(status); +MCE_INJECT_SET(misc); +MCE_INJECT_SET(addr); + +#define MCE_INJECT_GET(reg) \ +static int inj_##reg##_get(void *data, u64 *val) \ +{ \ + struct mce *m = (struct mce *)data; \ + \ + *val = m->reg; \ + return 0; \ +} + +MCE_INJECT_GET(status); +MCE_INJECT_GET(misc); +MCE_INJECT_GET(addr); + +DEFINE_SIMPLE_ATTRIBUTE(status_fops, inj_status_get, inj_status_set, "%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(misc_fops, inj_misc_get, inj_misc_set, "%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(addr_fops, inj_addr_get, inj_addr_set, "%llx\n"); + +/* + * Caller needs to be make sure this cpu doesn't disappear + * from under us, i.e.: get_cpu/put_cpu. + */ +static int toggle_hw_mce_inject(unsigned int cpu, bool enable) +{ + u32 l, h; + int err; + + err = rdmsr_on_cpu(cpu, MSR_K7_HWCR, &l, &h); + if (err) { + pr_err("%s: error reading HWCR\n", __func__); + return err; + } + + enable ? (l |= BIT(18)) : (l &= ~BIT(18)); + + err = wrmsr_on_cpu(cpu, MSR_K7_HWCR, l, h); + if (err) + pr_err("%s: error writing HWCR\n", __func__); + + return err; +} + +static int __set_inj(const char *buf) +{ + int i; + + for (i = 0; i < N_INJ_TYPES; i++) { + if (!strncmp(flags_options[i], buf, strlen(flags_options[i]))) { + inj_type = i; + return 0; + } + } + return -EINVAL; +} + +static ssize_t flags_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[MAX_FLAG_OPT_SIZE]; + int n; + + n = sprintf(buf, "%s\n", flags_options[inj_type]); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, n); +} + +static ssize_t flags_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[MAX_FLAG_OPT_SIZE], *__buf; + int err; + + if (cnt > MAX_FLAG_OPT_SIZE) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt - 1] = 0; + + /* strip whitespace */ + __buf = strstrip(buf); + + err = __set_inj(__buf); + if (err) { + pr_err("%s: Invalid flags value: %s\n", __func__, __buf); + return err; + } + + *ppos += cnt; + + return cnt; +} + +static const struct file_operations flags_fops = { + .read = flags_read, + .write = flags_write, + .llseek = generic_file_llseek, +}; + +/* + * On which CPU to inject? + */ +MCE_INJECT_GET(extcpu); + +static int inj_extcpu_set(void *data, u64 val) +{ + struct mce *m = (struct mce *)data; + + if (val >= nr_cpu_ids || !cpu_online(val)) { + pr_err("%s: Invalid CPU: %llu\n", __func__, val); + return -EINVAL; + } + m->extcpu = val; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(extcpu_fops, inj_extcpu_get, inj_extcpu_set, "%llu\n"); + +static void trigger_mce(void *info) +{ + asm volatile("int $18"); +} + +static void trigger_dfr_int(void *info) +{ + asm volatile("int %0" :: "i" (DEFERRED_ERROR_VECTOR)); +} + +static void trigger_thr_int(void *info) +{ + asm volatile("int %0" :: "i" (THRESHOLD_APIC_VECTOR)); +} + +static u32 get_nbc_for_node(int node_id) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + u32 cores_per_node; + + cores_per_node = c->x86_max_cores / amd_get_nodes_per_socket(); + + return cores_per_node * node_id; +} + +static void toggle_nb_mca_mst_cpu(u16 nid) +{ + struct pci_dev *F3 = node_to_amd_nb(nid)->misc; + u32 val; + int err; + + if (!F3) + return; + + err = pci_read_config_dword(F3, NBCFG, &val); + if (err) { + pr_err("%s: Error reading F%dx%03x.\n", + __func__, PCI_FUNC(F3->devfn), NBCFG); + return; + } + + if (val & BIT(27)) + return; + + pr_err("%s: Set D18F3x44[NbMcaToMstCpuEn] which BIOS hasn't done.\n", + __func__); + + val |= BIT(27); + err = pci_write_config_dword(F3, NBCFG, val); + if (err) + pr_err("%s: Error writing F%dx%03x.\n", + __func__, PCI_FUNC(F3->devfn), NBCFG); +} + +static void do_inject(void) +{ + u64 mcg_status = 0; + unsigned int cpu = i_mce.extcpu; + u8 b = i_mce.bank; + + if (i_mce.misc) + i_mce.status |= MCI_STATUS_MISCV; + + if (inj_type == SW_INJ) { + mce_inject_log(&i_mce); + return; + } + + /* prep MCE global settings for the injection */ + mcg_status = MCG_STATUS_MCIP | MCG_STATUS_EIPV; + + if (!(i_mce.status & MCI_STATUS_PCC)) + mcg_status |= MCG_STATUS_RIPV; + + /* + * Ensure necessary status bits for deferred errors: + * - MCx_STATUS[Deferred]: make sure it is a deferred error + * - MCx_STATUS[UC] cleared: deferred errors are _not_ UC + */ + if (inj_type == DFR_INT_INJ) { + i_mce.status |= MCI_STATUS_DEFERRED; + i_mce.status |= (i_mce.status & ~MCI_STATUS_UC); + } + + /* + * For multi node CPUs, logging and reporting of bank 4 errors happens + * only on the node base core. Refer to D18F3x44[NbMcaToMstCpuEn] for + * Fam10h and later BKDGs. + */ + if (static_cpu_has(X86_FEATURE_AMD_DCM) && b == 4) { + toggle_nb_mca_mst_cpu(amd_get_nb_id(cpu)); + cpu = get_nbc_for_node(amd_get_nb_id(cpu)); + } + + get_online_cpus(); + if (!cpu_online(cpu)) + goto err; + + toggle_hw_mce_inject(cpu, true); + + wrmsr_on_cpu(cpu, MSR_IA32_MCG_STATUS, + (u32)mcg_status, (u32)(mcg_status >> 32)); + + wrmsr_on_cpu(cpu, MSR_IA32_MCx_STATUS(b), + (u32)i_mce.status, (u32)(i_mce.status >> 32)); + + wrmsr_on_cpu(cpu, MSR_IA32_MCx_ADDR(b), + (u32)i_mce.addr, (u32)(i_mce.addr >> 32)); + + wrmsr_on_cpu(cpu, MSR_IA32_MCx_MISC(b), + (u32)i_mce.misc, (u32)(i_mce.misc >> 32)); + + toggle_hw_mce_inject(cpu, false); + + switch (inj_type) { + case DFR_INT_INJ: + smp_call_function_single(cpu, trigger_dfr_int, NULL, 0); + break; + case THR_INT_INJ: + smp_call_function_single(cpu, trigger_thr_int, NULL, 0); + break; + default: + smp_call_function_single(cpu, trigger_mce, NULL, 0); + } + +err: + put_online_cpus(); + +} + +/* + * This denotes into which bank we're injecting and triggers + * the injection, at the same time. + */ +static int inj_bank_set(void *data, u64 val) +{ + struct mce *m = (struct mce *)data; + + if (val >= n_banks) { + pr_err("Non-existent MCE bank: %llu\n", val); + return -EINVAL; + } + + m->bank = val; + do_inject(); + + return 0; +} + +MCE_INJECT_GET(bank); + +DEFINE_SIMPLE_ATTRIBUTE(bank_fops, inj_bank_get, inj_bank_set, "%llu\n"); + +static const char readme_msg[] = +"Description of the files and their usages:\n" +"\n" +"Note1: i refers to the bank number below.\n" +"Note2: See respective BKDGs for the exact bit definitions of the files below\n" +"as they mirror the hardware registers.\n" +"\n" +"status:\t Set MCi_STATUS: the bits in that MSR control the error type and\n" +"\t attributes of the error which caused the MCE.\n" +"\n" +"misc:\t Set MCi_MISC: provide auxiliary info about the error. It is mostly\n" +"\t used for error thresholding purposes and its validity is indicated by\n" +"\t MCi_STATUS[MiscV].\n" +"\n" +"addr:\t Error address value to be written to MCi_ADDR. Log address information\n" +"\t associated with the error.\n" +"\n" +"cpu:\t The CPU to inject the error on.\n" +"\n" +"bank:\t Specify the bank you want to inject the error into: the number of\n" +"\t banks in a processor varies and is family/model-specific, therefore, the\n" +"\t supplied value is sanity-checked. Setting the bank value also triggers the\n" +"\t injection.\n" +"\n" +"flags:\t Injection type to be performed. Writing to this file will trigger a\n" +"\t real machine check, an APIC interrupt or invoke the error decoder routines\n" +"\t for AMD processors.\n" +"\n" +"\t Allowed error injection types:\n" +"\t - \"sw\": Software error injection. Decode error to a human-readable \n" +"\t format only. Safe to use.\n" +"\t - \"hw\": Hardware error injection. Causes the #MC exception handler to \n" +"\t handle the error. Be warned: might cause system panic if MCi_STATUS[PCC] \n" +"\t is set. Therefore, consider setting (debugfs_mountpoint)/mce/fake_panic \n" +"\t before injecting.\n" +"\t - \"df\": Trigger APIC interrupt for Deferred error. Causes deferred \n" +"\t error APIC interrupt handler to handle the error if the feature is \n" +"\t is present in hardware. \n" +"\t - \"th\": Trigger APIC interrupt for Threshold errors. Causes threshold \n" +"\t APIC interrupt handler to handle the error. \n" +"\n"; + +static ssize_t +inj_readme_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return simple_read_from_buffer(ubuf, cnt, ppos, + readme_msg, strlen(readme_msg)); +} + +static const struct file_operations readme_fops = { + .read = inj_readme_read, +}; + +static struct dfs_node { + char *name; + struct dentry *d; + const struct file_operations *fops; + umode_t perm; +} dfs_fls[] = { + { .name = "status", .fops = &status_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "misc", .fops = &misc_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "addr", .fops = &addr_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "bank", .fops = &bank_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "flags", .fops = &flags_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "cpu", .fops = &extcpu_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "README", .fops = &readme_fops, .perm = S_IRUSR | S_IRGRP | S_IROTH }, +}; + +static int __init init_mce_inject(void) +{ + int i; + u64 cap; + + rdmsrl(MSR_IA32_MCG_CAP, cap); + n_banks = cap & MCG_BANKCNT_MASK; + + dfs_inj = debugfs_create_dir("mce-inject", NULL); + if (!dfs_inj) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(dfs_fls); i++) { + dfs_fls[i].d = debugfs_create_file(dfs_fls[i].name, + dfs_fls[i].perm, + dfs_inj, + &i_mce, + dfs_fls[i].fops); + + if (!dfs_fls[i].d) + goto err_dfs_add; + } + + return 0; + +err_dfs_add: + while (--i >= 0) + debugfs_remove(dfs_fls[i].d); + + debugfs_remove(dfs_inj); + dfs_inj = NULL; + + return -ENOMEM; +} + +static void __exit exit_mce_inject(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(dfs_fls); i++) + debugfs_remove(dfs_fls[i].d); + + memset(&dfs_fls, 0, sizeof(dfs_fls)); + + debugfs_remove(dfs_inj); + dfs_inj = NULL; +} +module_init(init_mce_inject); +module_exit(exit_mce_inject); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Borislav Petkov <bp@alien8.de>"); +MODULE_AUTHOR("AMD Inc."); +MODULE_DESCRIPTION("MCE injection facility for RAS testing"); diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile index a8fecc226946..3ee2bb6b440b 100644 --- a/arch/x86/um/Makefile +++ b/arch/x86/um/Makefile @@ -17,7 +17,7 @@ obj-y = bug.o bugs_$(BITS).o delay.o fault.o ksyms.o ldt.o \ ifeq ($(CONFIG_X86_32),y) obj-y += checksum_32.o -obj-$(CONFIG_BINFMT_ELF) += elfcore.o +obj-$(CONFIG_ELF_CORE) += elfcore.o subarch-y = ../lib/string_32.o ../lib/atomic64_32.o ../lib/atomic64_cx8_32.o subarch-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += ../lib/rwsem.o diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h index b9531d343134..174781a404ff 100644 --- a/arch/x86/um/asm/barrier.h +++ b/arch/x86/um/asm/barrier.h @@ -36,26 +36,6 @@ #endif /* CONFIG_X86_PPRO_FENCE */ #define dma_wmb() barrier() -#define smp_mb() barrier() -#define smp_rmb() barrier() -#define smp_wmb() barrier() - -#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) - -/* - * Stop RDTSC speculation. This is needed when you need to use RDTSC - * (or get_cycles or vread that possibly accesses the TSC) in a defined - * code region. - * - * (Could use an alternative three way for this if there was one.) - */ -static inline void rdtsc_barrier(void) -{ - alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, - "lfence", X86_FEATURE_LFENCE_RDTSC); -} +#include <asm-generic/barrier.h> #endif diff --git a/arch/x86/um/asm/syscall.h b/arch/x86/um/asm/syscall.h index 9fe77b7b5a0e..11ab90dc5f14 100644 --- a/arch/x86/um/asm/syscall.h +++ b/arch/x86/um/asm/syscall.h @@ -1,8 +1,13 @@ #ifndef __UM_ASM_SYSCALL_H #define __UM_ASM_SYSCALL_H +#include <asm/syscall-generic.h> #include <uapi/linux/audit.h> +typedef asmlinkage long (*sys_call_ptr_t)(unsigned long, unsigned long, + unsigned long, unsigned long, + unsigned long, unsigned long); + static inline int syscall_get_arch(void) { #ifdef CONFIG_X86_32 diff --git a/arch/x86/um/ldt.c b/arch/x86/um/ldt.c index 9701a4fd7bf2..836a1eb5df43 100644 --- a/arch/x86/um/ldt.c +++ b/arch/x86/um/ldt.c @@ -12,7 +12,10 @@ #include <skas.h> #include <sysdep/tls.h> -extern int modify_ldt(int func, void *ptr, unsigned long bytecount); +static inline int modify_ldt (int func, void *ptr, unsigned long bytecount) +{ + return syscall(__NR_modify_ldt, func, ptr, bytecount); +} static long write_ldt_entry(struct mm_id *mm_idp, int func, struct user_desc *desc, void **addr, int done) diff --git a/arch/x86/um/ptrace_32.c b/arch/x86/um/ptrace_32.c index a29756f2d940..47c78d5e5c32 100644 --- a/arch/x86/um/ptrace_32.c +++ b/arch/x86/um/ptrace_32.c @@ -68,6 +68,7 @@ static const int reg_offsets[] = { [EFL] = HOST_EFLAGS, [UESP] = HOST_SP, [SS] = HOST_SS, + [ORIG_EAX] = HOST_ORIG_AX, }; int putreg(struct task_struct *child, int regno, unsigned long value) @@ -83,6 +84,7 @@ int putreg(struct task_struct *child, int regno, unsigned long value) case EAX: case EIP: case UESP: + case ORIG_EAX: break; case FS: if (value && (value & 3) != 3) @@ -108,9 +110,6 @@ int putreg(struct task_struct *child, int regno, unsigned long value) value &= FLAG_MASK; child->thread.regs.regs.gp[HOST_EFLAGS] |= value; return 0; - case ORIG_EAX: - child->thread.regs.regs.syscall = value; - return 0; default : panic("Bad register in putreg() : %d\n", regno); } @@ -143,8 +142,6 @@ unsigned long getreg(struct task_struct *child, int regno) regno >>= 2; switch (regno) { - case ORIG_EAX: - return child->thread.regs.regs.syscall; case FS: case GS: case DS: @@ -163,6 +160,7 @@ unsigned long getreg(struct task_struct *child, int regno) case EDI: case EBP: case EFL: + case ORIG_EAX: break; default: panic("Bad register in getreg() : %d\n", regno); diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c index 06934a8a4872..14fcd01ed992 100644 --- a/arch/x86/um/signal.c +++ b/arch/x86/um/signal.c @@ -211,7 +211,7 @@ static int copy_sc_from_user(struct pt_regs *regs, if (err) return 1; - err = convert_fxsr_from_user(&fpx, sc.fpstate); + err = convert_fxsr_from_user(&fpx, (void *)sc.fpstate); if (err) return 1; @@ -227,7 +227,7 @@ static int copy_sc_from_user(struct pt_regs *regs, { struct user_i387_struct fp; - err = copy_from_user(&fp, sc.fpstate, + err = copy_from_user(&fp, (void *)sc.fpstate, sizeof(struct user_i387_struct)); if (err) return 1; @@ -291,7 +291,7 @@ static int copy_sc_to_user(struct sigcontext __user *to, #endif #undef PUTREG sc.oldmask = mask; - sc.fpstate = to_fp; + sc.fpstate = (unsigned long)to_fp; err = copy_to_user(to, &sc, sizeof(struct sigcontext)); if (err) @@ -468,12 +468,10 @@ long sys_sigreturn(void) struct sigframe __user *frame = (struct sigframe __user *)(sp - 8); sigset_t set; struct sigcontext __user *sc = &frame->sc; - unsigned long __user *oldmask = &sc->oldmask; - unsigned long __user *extramask = frame->extramask; int sig_size = (_NSIG_WORDS - 1) * sizeof(unsigned long); - if (copy_from_user(&set.sig[0], oldmask, sizeof(set.sig[0])) || - copy_from_user(&set.sig[1], extramask, sig_size)) + if (copy_from_user(&set.sig[0], &sc->oldmask, sizeof(set.sig[0])) || + copy_from_user(&set.sig[1], frame->extramask, sig_size)) goto segfault; set_current_blocked(&set); @@ -505,6 +503,7 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, { struct rt_sigframe __user *frame; int err = 0, sig = ksig->sig; + unsigned long fp_to; frame = (struct rt_sigframe __user *) round_down(stack_top - sizeof(struct rt_sigframe), 16); @@ -526,7 +525,10 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, err |= __save_altstack(&frame->uc.uc_stack, PT_REGS_SP(regs)); err |= copy_sc_to_user(&frame->uc.uc_mcontext, &frame->fpstate, regs, set->sig[0]); - err |= __put_user(&frame->fpstate, &frame->uc.uc_mcontext.fpstate); + + fp_to = (unsigned long)&frame->fpstate; + + err |= __put_user(fp_to, &frame->uc.uc_mcontext.fpstate); if (sizeof(*set) == 16) { err |= __put_user(set->sig[0], &frame->uc.uc_sigmask.sig[0]); err |= __put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]); diff --git a/arch/x86/um/stub_32.S b/arch/x86/um/stub_32.S index b972649d3a18..98816804e131 100644 --- a/arch/x86/um/stub_32.S +++ b/arch/x86/um/stub_32.S @@ -1,6 +1,5 @@ #include <as-layout.h> - .globl syscall_stub .section .__syscall_stub, "ax" .globl batch_syscall_stub diff --git a/arch/x86/um/stub_64.S b/arch/x86/um/stub_64.S index 7160b20172d0..ba914b3b8cc4 100644 --- a/arch/x86/um/stub_64.S +++ b/arch/x86/um/stub_64.S @@ -1,25 +1,9 @@ #include <as-layout.h> - .globl syscall_stub .section .__syscall_stub, "ax" -syscall_stub: - syscall - /* We don't have 64-bit constants, so this constructs the address - * we need. - */ - movq $(STUB_DATA >> 32), %rbx - salq $32, %rbx - movq $(STUB_DATA & 0xffffffff), %rcx - or %rcx, %rbx - movq %rax, (%rbx) - int3 - .globl batch_syscall_stub batch_syscall_stub: - mov $(STUB_DATA >> 32), %rbx - sal $32, %rbx - mov $(STUB_DATA & 0xffffffff), %rax - or %rax, %rbx + mov $(STUB_DATA), %rbx /* load pointer to first operation */ mov %rbx, %rsp add $0x10, %rsp diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c index bd16d6c370ec..439c0994b696 100644 --- a/arch/x86/um/sys_call_table_32.c +++ b/arch/x86/um/sys_call_table_32.c @@ -7,6 +7,7 @@ #include <linux/sys.h> #include <linux/cache.h> #include <generated/user_constants.h> +#include <asm/syscall.h> #define __NO_STUBS @@ -24,15 +25,13 @@ #define old_mmap sys_old_mmap -#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void sym(void) ; +#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; #include <asm/syscalls_32.h> #undef __SYSCALL_I386 #define __SYSCALL_I386(nr, sym, compat) [ nr ] = sym, -typedef asmlinkage void (*sys_call_ptr_t)(void); - -extern asmlinkage void sys_ni_syscall(void); +extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = { /* diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c index a75d8700472a..b74ea6c2c0e7 100644 --- a/arch/x86/um/sys_call_table_64.c +++ b/arch/x86/um/sys_call_table_64.c @@ -7,6 +7,7 @@ #include <linux/sys.h> #include <linux/cache.h> #include <generated/user_constants.h> +#include <asm/syscall.h> #define __NO_STUBS @@ -37,15 +38,13 @@ #define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat) #define __SYSCALL_X32(nr, sym, compat) /* Not supported */ -#define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ; +#define __SYSCALL_64(nr, sym, compat) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; #include <asm/syscalls_64.h> #undef __SYSCALL_64 #define __SYSCALL_64(nr, sym, compat) [ nr ] = sym, -typedef void (*sys_call_ptr_t)(void); - -extern void sys_ni_syscall(void); +extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = { /* diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 484145368a24..c7b15f3e2cf3 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -7,6 +7,7 @@ config XEN depends on PARAVIRT select PARAVIRT_CLOCK select XEN_HAVE_PVMMU + select XEN_HAVE_VPMU depends on X86_64 || (X86_32 && X86_PAE) depends on X86_LOCAL_APIC && X86_TSC help @@ -23,14 +24,18 @@ config XEN_PVHVM def_bool y depends on XEN && PCI && X86_LOCAL_APIC -config XEN_MAX_DOMAIN_MEMORY - int - default 500 if X86_64 - default 64 if X86_32 - depends on XEN - help - This only affects the sizing of some bss arrays, the unused - portions of which are freed. +config XEN_512GB + bool "Limit Xen pv-domain memory to 512GB" + depends on XEN && X86_64 + default y + help + Limit paravirtualized user domains to 512GB of RAM. + + The Xen tools and crash dump analysis tools might not support + pv-domains with more than 512 GB of RAM. This option controls the + default setting of the kernel to use only up to 512 GB or more. + It is always possible to change the default via specifying the + boot parameter "xen_512gb_limit". config XEN_SAVE_RESTORE bool diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 4b6e29ac0968..e47e52787d32 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -13,7 +13,7 @@ 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 apic.o + p2m.o apic.o pmu.o obj-$(CONFIG_EVENT_TRACING) += trace.o diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c index 70e060ad879a..abf4901c917b 100644 --- a/arch/x86/xen/apic.c +++ b/arch/x86/xen/apic.c @@ -7,6 +7,7 @@ #include <xen/xen.h> #include <xen/interface/physdev.h> #include "xen-ops.h" +#include "pmu.h" #include "smp.h" static unsigned int xen_io_apic_read(unsigned apic, unsigned reg) @@ -63,7 +64,7 @@ static u32 xen_apic_read(u32 reg) if (reg != APIC_ID) return 0; - ret = HYPERVISOR_dom0_op(&op); + ret = HYPERVISOR_platform_op(&op); if (ret) return 0; @@ -72,6 +73,11 @@ static u32 xen_apic_read(u32 reg) static void xen_apic_write(u32 reg, u32 val) { + if (reg == APIC_LVTPC) { + (void)pmu_apic_update(reg); + return; + } + /* Warn to see if there's any stray references */ WARN(1,"register: %x, value: %x\n", reg, val); } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 11d6fb4e8483..d09e4c9d7cc5 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -33,6 +33,10 @@ #include <linux/memblock.h> #include <linux/edd.h> +#ifdef CONFIG_KEXEC_CORE +#include <linux/kexec.h> +#endif + #include <xen/xen.h> #include <xen/events.h> #include <xen/interface/xen.h> @@ -71,6 +75,7 @@ #include <asm/mwait.h> #include <asm/pci_x86.h> #include <asm/pat.h> +#include <asm/cpu.h> #ifdef CONFIG_ACPI #include <linux/acpi.h> @@ -84,6 +89,7 @@ #include "mmu.h" #include "smp.h" #include "multicalls.h" +#include "pmu.h" EXPORT_SYMBOL_GPL(hypercall_page); @@ -409,7 +415,7 @@ static bool __init xen_check_mwait(void) set_xen_guest_handle(op.u.set_pminfo.pdc, buf); - if ((HYPERVISOR_dom0_op(&op) == 0) && + if ((HYPERVISOR_platform_op(&op) == 0) && (buf[2] & (ACPI_PDC_C_C1_FFH | ACPI_PDC_C_C2C3_FFH))) { cpuid_leaf5_ecx_val = cx; cpuid_leaf5_edx_val = dx; @@ -1010,8 +1016,7 @@ static void xen_write_cr0(unsigned long cr0) static void xen_write_cr4(unsigned long cr4) { - cr4 &= ~X86_CR4_PGE; - cr4 &= ~X86_CR4_PSE; + cr4 &= ~(X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PCE); native_write_cr4(cr4); } @@ -1030,6 +1035,9 @@ static u64 xen_read_msr_safe(unsigned int msr, int *err) { u64 val; + if (pmu_msr_read(msr, &val, err)) + return val; + val = native_read_msr_safe(msr, err); switch (msr) { case MSR_IA32_APICBASE: @@ -1074,9 +1082,11 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) /* Fast syscall setup is all done in hypercalls, so these are all ignored. Stub them out here to stop Xen console noise. */ + break; default: - ret = native_write_msr_safe(msr, low, high); + if (!pmu_msr_write(msr, low, high, &ret)) + ret = native_write_msr_safe(msr, low, high); } return ret; @@ -1182,7 +1192,7 @@ static const struct pv_info xen_info __initconst = { #ifdef CONFIG_X86_64 .extra_user_64bit_cs = FLAT_USER_CS64, #endif - + .features = 0, .name = "Xen", }; @@ -1215,17 +1225,11 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .read_msr = xen_read_msr_safe, .write_msr = xen_write_msr_safe, - .read_tsc = native_read_tsc, - .read_pmc = native_read_pmc, - - .read_tscp = native_read_tscp, + .read_pmc = xen_read_pmc, .iret = xen_iret, #ifdef CONFIG_X86_64 - .usergs_sysret32 = xen_sysret32, .usergs_sysret64 = xen_sysret64, -#else - .irq_enable_sysexit = xen_sysexit, #endif .load_tr_desc = paravirt_nop, @@ -1258,15 +1262,13 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .end_context_switch = xen_end_context_switch, }; -static const struct pv_apic_ops xen_apic_ops __initconst = { -#ifdef CONFIG_X86_LOCAL_APIC - .startup_ipi_hook = paravirt_nop, -#endif -}; - static void xen_reboot(int reason) { struct sched_shutdown r = { .reason = reason }; + int cpu; + + for_each_online_cpu(cpu) + xen_pmu_finish(cpu); if (HYPERVISOR_sched_op(SCHEDOP_shutdown, &r)) BUG(); @@ -1363,7 +1365,7 @@ static void __init xen_boot_params_init_edd(void) info->params.length = sizeof(info->params); set_xen_guest_handle(op.u.firmware_info.u.disk_info.edd_params, &info->params); - ret = HYPERVISOR_dom0_op(&op); + ret = HYPERVISOR_platform_op(&op); if (ret) break; @@ -1381,7 +1383,7 @@ static void __init xen_boot_params_init_edd(void) op.u.firmware_info.type = XEN_FW_DISK_MBR_SIGNATURE; for (nr = 0; nr < EDD_MBR_SIG_MAX; nr++) { op.u.firmware_info.index = nr; - ret = HYPERVISOR_dom0_op(&op); + ret = HYPERVISOR_platform_op(&op); if (ret) break; mbr_signature[nr] = op.u.firmware_info.u.disk_mbr_signature.mbr_signature; @@ -1524,8 +1526,9 @@ asmlinkage __visible void __init xen_start_kernel(void) /* Install Xen paravirt ops */ pv_info = xen_info; + if (xen_initial_domain()) + pv_info.features |= PV_SUPPORTED_RTC; pv_init_ops = xen_init_ops; - pv_apic_ops = xen_apic_ops; if (!xen_pvh_domain()) { pv_cpu_ops = xen_cpu_ops; @@ -1610,7 +1613,9 @@ asmlinkage __visible void __init xen_start_kernel(void) early_boot_irqs_disabled = true; xen_raw_console_write("mapping kernel into physical memory\n"); - xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base, xen_start_info->nr_pages); + xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base, + xen_start_info->nr_pages); + xen_reserve_special_pages(); /* * Modify the cache mode translation tables to match Xen's PAT @@ -1685,7 +1690,7 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_start_info->console.domU.mfn = 0; xen_start_info->console.domU.evtchn = 0; - if (HYPERVISOR_dom0_op(&op) == 0) + if (HYPERVISOR_platform_op(&op) == 0) boot_params.kbd_status = op.u.firmware_info.u.kbd_shift_flags; /* Make sure ACS will be enabled */ @@ -1800,6 +1805,21 @@ static struct notifier_block xen_hvm_cpu_notifier = { .notifier_call = xen_hvm_cpu_notify, }; +#ifdef CONFIG_KEXEC_CORE +static void xen_hvm_shutdown(void) +{ + native_machine_shutdown(); + if (kexec_in_progress) + xen_reboot(SHUTDOWN_soft_reset); +} + +static void xen_hvm_crash_shutdown(struct pt_regs *regs) +{ + native_machine_crash_shutdown(regs); + xen_reboot(SHUTDOWN_soft_reset); +} +#endif + static void __init xen_hvm_guest_init(void) { if (xen_pv_domain()) @@ -1819,6 +1839,10 @@ static void __init xen_hvm_guest_init(void) x86_init.irqs.intr_init = xen_init_IRQ; xen_hvm_init_time_ops(); xen_hvm_init_mmu_ops(); +#ifdef CONFIG_KEXEC_CORE + machine_ops.shutdown = xen_hvm_shutdown; + machine_ops.crash_shutdown = xen_hvm_crash_shutdown; +#endif } #endif @@ -1854,8 +1878,10 @@ EXPORT_SYMBOL_GPL(xen_hvm_need_lapic); static void xen_set_cpu_features(struct cpuinfo_x86 *c) { - if (xen_pv_domain()) + if (xen_pv_domain()) { clear_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); + set_cpu_cap(c, X86_FEATURE_XENPV); + } } const struct hypervisor_x86 x86_hyper_xen = { @@ -1868,3 +1894,17 @@ const struct hypervisor_x86 x86_hyper_xen = { .set_cpu_features = xen_set_cpu_features, }; EXPORT_SYMBOL(x86_hyper_xen); + +#ifdef CONFIG_HOTPLUG_CPU +void xen_arch_register_cpu(int num) +{ + arch_register_cpu(num); +} +EXPORT_SYMBOL(xen_arch_register_cpu); + +void xen_arch_unregister_cpu(int num) +{ + arch_unregister_cpu(num); +} +EXPORT_SYMBOL(xen_arch_unregister_cpu); +#endif diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c index 1580e7a5a4cf..e079500b17f3 100644 --- a/arch/x86/xen/grant-table.c +++ b/arch/x86/xen/grant-table.c @@ -133,7 +133,7 @@ static int __init xlated_setup_gnttab_pages(void) kfree(pages); return -ENOMEM; } - rc = alloc_xenballooned_pages(nr_grant_frames, pages, 0 /* lowmem */); + rc = alloc_xenballooned_pages(nr_grant_frames, pages); if (rc) { pr_warn("%s Couldn't balloon alloc %ld pfns rc:%d\n", __func__, nr_grant_frames, rc); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index dd151b2045b0..c913ca4f6958 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -116,6 +116,7 @@ static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss; DEFINE_PER_CPU(unsigned long, xen_cr3); /* cr3 stored as physaddr */ DEFINE_PER_CPU(unsigned long, xen_current_cr3); /* actual vcpu cr3 */ +static phys_addr_t xen_pt_base, xen_pt_size __initdata; /* * Just beyond the highest usermode address. STACK_TOP_MAX has a @@ -1093,6 +1094,16 @@ static void xen_exit_mmap(struct mm_struct *mm) static void xen_post_allocator_init(void); +static void __init pin_pagetable_pfn(unsigned cmd, unsigned long pfn) +{ + struct mmuext_op op; + + op.cmd = cmd; + op.arg1.mfn = pfn_to_mfn(pfn); + if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF)) + BUG(); +} + #ifdef CONFIG_X86_64 static void __init xen_cleanhighmap(unsigned long vaddr, unsigned long vaddr_end) @@ -1114,6 +1125,83 @@ static void __init xen_cleanhighmap(unsigned long vaddr, xen_mc_flush(); } +/* + * Make a page range writeable and free it. + */ +static void __init xen_free_ro_pages(unsigned long paddr, unsigned long size) +{ + void *vaddr = __va(paddr); + void *vaddr_end = vaddr + size; + + for (; vaddr < vaddr_end; vaddr += PAGE_SIZE) + make_lowmem_page_readwrite(vaddr); + + memblock_free(paddr, size); +} + +static void __init xen_cleanmfnmap_free_pgtbl(void *pgtbl, bool unpin) +{ + unsigned long pa = __pa(pgtbl) & PHYSICAL_PAGE_MASK; + + if (unpin) + pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(pa)); + ClearPagePinned(virt_to_page(__va(pa))); + xen_free_ro_pages(pa, PAGE_SIZE); +} + +/* + * Since it is well isolated we can (and since it is perhaps large we should) + * also free the page tables mapping the initial P->M table. + */ +static void __init xen_cleanmfnmap(unsigned long vaddr) +{ + unsigned long va = vaddr & PMD_MASK; + unsigned long pa; + pgd_t *pgd = pgd_offset_k(va); + pud_t *pud_page = pud_offset(pgd, 0); + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + unsigned int i; + bool unpin; + + unpin = (vaddr == 2 * PGDIR_SIZE); + set_pgd(pgd, __pgd(0)); + do { + pud = pud_page + pud_index(va); + if (pud_none(*pud)) { + va += PUD_SIZE; + } else if (pud_large(*pud)) { + pa = pud_val(*pud) & PHYSICAL_PAGE_MASK; + xen_free_ro_pages(pa, PUD_SIZE); + va += PUD_SIZE; + } else { + pmd = pmd_offset(pud, va); + if (pmd_large(*pmd)) { + pa = pmd_val(*pmd) & PHYSICAL_PAGE_MASK; + xen_free_ro_pages(pa, PMD_SIZE); + } else if (!pmd_none(*pmd)) { + pte = pte_offset_kernel(pmd, va); + set_pmd(pmd, __pmd(0)); + for (i = 0; i < PTRS_PER_PTE; ++i) { + if (pte_none(pte[i])) + break; + pa = pte_pfn(pte[i]) << PAGE_SHIFT; + xen_free_ro_pages(pa, PAGE_SIZE); + } + xen_cleanmfnmap_free_pgtbl(pte, unpin); + } + va += PMD_SIZE; + if (pmd_index(va)) + continue; + set_pud(pud, __pud(0)); + xen_cleanmfnmap_free_pgtbl(pmd, unpin); + } + + } while (pud_index(va) || pmd_index(va)); + xen_cleanmfnmap_free_pgtbl(pud_page, unpin); +} + static void __init xen_pagetable_p2m_free(void) { unsigned long size; @@ -1128,18 +1216,31 @@ static void __init xen_pagetable_p2m_free(void) /* using __ka address and sticking INVALID_P2M_ENTRY! */ memset((void *)xen_start_info->mfn_list, 0xff, size); - /* We should be in __ka space. */ - BUG_ON(xen_start_info->mfn_list < __START_KERNEL_map); addr = xen_start_info->mfn_list; - /* We roundup to the PMD, which means that if anybody at this stage is - * using the __ka address of xen_start_info or xen_start_info->shared_info - * they are in going to crash. Fortunatly we have already revectored - * in xen_setup_kernel_pagetable and in xen_setup_shared_info. */ + /* + * We could be in __ka space. + * We roundup to the PMD, which means that if anybody at this stage is + * using the __ka address of xen_start_info or + * xen_start_info->shared_info they are in going to crash. Fortunatly + * we have already revectored in xen_setup_kernel_pagetable and in + * xen_setup_shared_info. + */ size = roundup(size, PMD_SIZE); - xen_cleanhighmap(addr, addr + size); - size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long)); - memblock_free(__pa(xen_start_info->mfn_list), size); + if (addr >= __START_KERNEL_map) { + xen_cleanhighmap(addr, addr + size); + size = PAGE_ALIGN(xen_start_info->nr_pages * + sizeof(unsigned long)); + memblock_free(__pa(addr), size); + } else { + xen_cleanmfnmap(addr); + } +} + +static void __init xen_pagetable_cleanhighmap(void) +{ + unsigned long size; + unsigned long addr; /* At this stage, cleanup_highmap has already cleaned __ka space * from _brk_limit way up to the max_pfn_mapped (which is the end of @@ -1172,6 +1273,8 @@ static void __init xen_pagetable_p2m_setup(void) #ifdef CONFIG_X86_64 xen_pagetable_p2m_free(); + + xen_pagetable_cleanhighmap(); #endif /* And revector! Bye bye old array */ xen_start_info->mfn_list = (unsigned long)xen_p2m_addr; @@ -1461,6 +1564,24 @@ static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte) #else /* CONFIG_X86_64 */ static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte) { + unsigned long pfn; + + if (xen_feature(XENFEAT_writable_page_tables) || + xen_feature(XENFEAT_auto_translated_physmap) || + xen_start_info->mfn_list >= __START_KERNEL_map) + return pte; + + /* + * Pages belonging to the initial p2m list mapped outside the default + * address range must be mapped read-only. This region contains the + * page tables for mapping the p2m list, too, and page tables MUST be + * mapped read-only. + */ + pfn = pte_pfn(pte); + if (pfn >= xen_start_info->first_p2m_pfn && + pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames) + pte = __pte_ma(pte_val_ma(pte) & ~_PAGE_RW); + return pte; } #endif /* CONFIG_X86_64 */ @@ -1489,15 +1610,6 @@ static void __init xen_set_pte_init(pte_t *ptep, pte_t pte) native_set_pte(ptep, pte); } -static void __init pin_pagetable_pfn(unsigned cmd, unsigned long pfn) -{ - struct mmuext_op op; - op.cmd = cmd; - op.arg1.mfn = pfn_to_mfn(pfn); - if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF)) - BUG(); -} - /* Early in boot, while setting up the initial pagetable, assume everything is pinned. */ static void __init xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn) @@ -1815,7 +1927,10 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) * mappings. Considering that on Xen after the kernel mappings we * have the mappings of some pages that don't exist in pfn space, we * set max_pfn_mapped to the last real pfn mapped. */ - max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list)); + if (xen_start_info->mfn_list < __START_KERNEL_map) + max_pfn_mapped = xen_start_info->first_p2m_pfn; + else + max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list)); pt_base = PFN_DOWN(__pa(xen_start_info->pt_base)); pt_end = pt_base + xen_start_info->nr_pt_frames; @@ -1855,6 +1970,11 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) /* Graft it onto L4[511][510] */ copy_page(level2_kernel_pgt, l2); + /* Copy the initial P->M table mappings if necessary. */ + i = pgd_index(xen_start_info->mfn_list); + if (i && i < pgd_index(__START_KERNEL_map)) + init_level4_pgt[i] = ((pgd_t *)xen_start_info->pt_base)[i]; + if (!xen_feature(XENFEAT_auto_translated_physmap)) { /* Make pagetable pieces RO */ set_page_prot(init_level4_pgt, PAGE_KERNEL_RO); @@ -1894,10 +2014,192 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) check_pt_base(&pt_base, &pt_end, addr[i]); /* Our (by three pages) smaller Xen pagetable that we are using */ - memblock_reserve(PFN_PHYS(pt_base), (pt_end - pt_base) * PAGE_SIZE); + xen_pt_base = PFN_PHYS(pt_base); + xen_pt_size = (pt_end - pt_base) * PAGE_SIZE; + memblock_reserve(xen_pt_base, xen_pt_size); + /* Revector the xen_start_info */ xen_start_info = (struct start_info *)__va(__pa(xen_start_info)); } + +/* + * Read a value from a physical address. + */ +static unsigned long __init xen_read_phys_ulong(phys_addr_t addr) +{ + unsigned long *vaddr; + unsigned long val; + + vaddr = early_memremap_ro(addr, sizeof(val)); + val = *vaddr; + early_memunmap(vaddr, sizeof(val)); + return val; +} + +/* + * Translate a virtual address to a physical one without relying on mapped + * page tables. + */ +static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr) +{ + phys_addr_t pa; + pgd_t pgd; + pud_t pud; + pmd_t pmd; + pte_t pte; + + pa = read_cr3(); + pgd = native_make_pgd(xen_read_phys_ulong(pa + pgd_index(vaddr) * + sizeof(pgd))); + if (!pgd_present(pgd)) + return 0; + + pa = pgd_val(pgd) & PTE_PFN_MASK; + pud = native_make_pud(xen_read_phys_ulong(pa + pud_index(vaddr) * + sizeof(pud))); + if (!pud_present(pud)) + return 0; + pa = pud_pfn(pud) << PAGE_SHIFT; + if (pud_large(pud)) + return pa + (vaddr & ~PUD_MASK); + + pmd = native_make_pmd(xen_read_phys_ulong(pa + pmd_index(vaddr) * + sizeof(pmd))); + if (!pmd_present(pmd)) + return 0; + pa = pmd_pfn(pmd) << PAGE_SHIFT; + if (pmd_large(pmd)) + return pa + (vaddr & ~PMD_MASK); + + pte = native_make_pte(xen_read_phys_ulong(pa + pte_index(vaddr) * + sizeof(pte))); + if (!pte_present(pte)) + return 0; + pa = pte_pfn(pte) << PAGE_SHIFT; + + return pa | (vaddr & ~PAGE_MASK); +} + +/* + * Find a new area for the hypervisor supplied p2m list and relocate the p2m to + * this area. + */ +void __init xen_relocate_p2m(void) +{ + phys_addr_t size, new_area, pt_phys, pmd_phys, pud_phys; + unsigned long p2m_pfn, p2m_pfn_end, n_frames, pfn, pfn_end; + int n_pte, n_pt, n_pmd, n_pud, idx_pte, idx_pt, idx_pmd, idx_pud; + pte_t *pt; + pmd_t *pmd; + pud_t *pud; + pgd_t *pgd; + unsigned long *new_p2m; + + size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long)); + n_pte = roundup(size, PAGE_SIZE) >> PAGE_SHIFT; + n_pt = roundup(size, PMD_SIZE) >> PMD_SHIFT; + n_pmd = roundup(size, PUD_SIZE) >> PUD_SHIFT; + n_pud = roundup(size, PGDIR_SIZE) >> PGDIR_SHIFT; + n_frames = n_pte + n_pt + n_pmd + n_pud; + + new_area = xen_find_free_area(PFN_PHYS(n_frames)); + if (!new_area) { + xen_raw_console_write("Can't find new memory area for p2m needed due to E820 map conflict\n"); + BUG(); + } + + /* + * Setup the page tables for addressing the new p2m list. + * We have asked the hypervisor to map the p2m list at the user address + * PUD_SIZE. It may have done so, or it may have used a kernel space + * address depending on the Xen version. + * To avoid any possible virtual address collision, just use + * 2 * PUD_SIZE for the new area. + */ + pud_phys = new_area; + pmd_phys = pud_phys + PFN_PHYS(n_pud); + pt_phys = pmd_phys + PFN_PHYS(n_pmd); + p2m_pfn = PFN_DOWN(pt_phys) + n_pt; + + pgd = __va(read_cr3()); + new_p2m = (unsigned long *)(2 * PGDIR_SIZE); + for (idx_pud = 0; idx_pud < n_pud; idx_pud++) { + pud = early_memremap(pud_phys, PAGE_SIZE); + clear_page(pud); + for (idx_pmd = 0; idx_pmd < min(n_pmd, PTRS_PER_PUD); + idx_pmd++) { + pmd = early_memremap(pmd_phys, PAGE_SIZE); + clear_page(pmd); + for (idx_pt = 0; idx_pt < min(n_pt, PTRS_PER_PMD); + idx_pt++) { + pt = early_memremap(pt_phys, PAGE_SIZE); + clear_page(pt); + for (idx_pte = 0; + idx_pte < min(n_pte, PTRS_PER_PTE); + idx_pte++) { + set_pte(pt + idx_pte, + pfn_pte(p2m_pfn, PAGE_KERNEL)); + p2m_pfn++; + } + n_pte -= PTRS_PER_PTE; + early_memunmap(pt, PAGE_SIZE); + make_lowmem_page_readonly(__va(pt_phys)); + pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, + PFN_DOWN(pt_phys)); + set_pmd(pmd + idx_pt, + __pmd(_PAGE_TABLE | pt_phys)); + pt_phys += PAGE_SIZE; + } + n_pt -= PTRS_PER_PMD; + early_memunmap(pmd, PAGE_SIZE); + make_lowmem_page_readonly(__va(pmd_phys)); + pin_pagetable_pfn(MMUEXT_PIN_L2_TABLE, + PFN_DOWN(pmd_phys)); + set_pud(pud + idx_pmd, __pud(_PAGE_TABLE | pmd_phys)); + pmd_phys += PAGE_SIZE; + } + n_pmd -= PTRS_PER_PUD; + early_memunmap(pud, PAGE_SIZE); + make_lowmem_page_readonly(__va(pud_phys)); + pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(pud_phys)); + set_pgd(pgd + 2 + idx_pud, __pgd(_PAGE_TABLE | pud_phys)); + pud_phys += PAGE_SIZE; + } + + /* Now copy the old p2m info to the new area. */ + memcpy(new_p2m, xen_p2m_addr, size); + xen_p2m_addr = new_p2m; + + /* Release the old p2m list and set new list info. */ + p2m_pfn = PFN_DOWN(xen_early_virt_to_phys(xen_start_info->mfn_list)); + BUG_ON(!p2m_pfn); + p2m_pfn_end = p2m_pfn + PFN_DOWN(size); + + if (xen_start_info->mfn_list < __START_KERNEL_map) { + pfn = xen_start_info->first_p2m_pfn; + pfn_end = xen_start_info->first_p2m_pfn + + xen_start_info->nr_p2m_frames; + set_pgd(pgd + 1, __pgd(0)); + } else { + pfn = p2m_pfn; + pfn_end = p2m_pfn_end; + } + + memblock_free(PFN_PHYS(pfn), PAGE_SIZE * (pfn_end - pfn)); + while (pfn < pfn_end) { + if (pfn == p2m_pfn) { + pfn = p2m_pfn_end; + continue; + } + make_lowmem_page_readwrite(__va(PFN_PHYS(pfn))); + pfn++; + } + + xen_start_info->mfn_list = (unsigned long)xen_p2m_addr; + xen_start_info->first_p2m_pfn = PFN_DOWN(new_area); + xen_start_info->nr_p2m_frames = n_frames; +} + #else /* !CONFIG_X86_64 */ static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD); static RESERVE_BRK_ARRAY(pmd_t, swapper_kernel_pmd, PTRS_PER_PMD); @@ -1938,18 +2240,41 @@ static void __init xen_write_cr3_init(unsigned long cr3) pv_mmu_ops.write_cr3 = &xen_write_cr3; } +/* + * For 32 bit domains xen_start_info->pt_base is the pgd address which might be + * not the first page table in the page table pool. + * Iterate through the initial page tables to find the real page table base. + */ +static phys_addr_t xen_find_pt_base(pmd_t *pmd) +{ + phys_addr_t pt_base, paddr; + unsigned pmdidx; + + pt_base = min(__pa(xen_start_info->pt_base), __pa(pmd)); + + for (pmdidx = 0; pmdidx < PTRS_PER_PMD; pmdidx++) + if (pmd_present(pmd[pmdidx]) && !pmd_large(pmd[pmdidx])) { + paddr = m2p(pmd[pmdidx].pmd); + pt_base = min(pt_base, paddr); + } + + return pt_base; +} + void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) { pmd_t *kernel_pmd; + kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd); + + xen_pt_base = xen_find_pt_base(kernel_pmd); + xen_pt_size = xen_start_info->nr_pt_frames * PAGE_SIZE; + initial_kernel_pmd = extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE); - max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) + - xen_start_info->nr_pt_frames * PAGE_SIZE + - 512*1024); + max_pfn_mapped = PFN_DOWN(xen_pt_base + xen_pt_size + 512 * 1024); - kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd); copy_page(initial_kernel_pmd, kernel_pmd); xen_map_identity_early(initial_kernel_pmd, max_pfn); @@ -1968,11 +2293,33 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) PFN_DOWN(__pa(initial_page_table))); xen_write_cr3(__pa(initial_page_table)); - memblock_reserve(__pa(xen_start_info->pt_base), - xen_start_info->nr_pt_frames * PAGE_SIZE); + memblock_reserve(xen_pt_base, xen_pt_size); } #endif /* CONFIG_X86_64 */ +void __init xen_reserve_special_pages(void) +{ + phys_addr_t paddr; + + memblock_reserve(__pa(xen_start_info), PAGE_SIZE); + if (xen_start_info->store_mfn) { + paddr = PFN_PHYS(mfn_to_pfn(xen_start_info->store_mfn)); + memblock_reserve(paddr, PAGE_SIZE); + } + if (!xen_initial_domain()) { + paddr = PFN_PHYS(mfn_to_pfn(xen_start_info->console.domU.mfn)); + memblock_reserve(paddr, PAGE_SIZE); + } +} + +void __init xen_pt_check_e820(void) +{ + if (xen_is_e820_reserved(xen_pt_base, xen_pt_size)) { + xen_raw_console_write("Xen hypervisor allocated page table memory conflicts with E820 map\n"); + BUG(); + } +} + static unsigned char dummy_mapping[PAGE_SIZE] __page_aligned_bss; static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) @@ -2089,7 +2436,6 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .flush_tlb_others = xen_flush_tlb_others, .pte_update = paravirt_nop, - .pte_update_defer = paravirt_nop, .pgd_alloc = xen_pgd_alloc, .pgd_free = xen_pgd_free, @@ -2148,14 +2494,9 @@ void __init xen_init_mmu_ops(void) { x86_init.paging.pagetable_init = xen_pagetable_init; - /* Optimization - we can use the HVM one but it has no idea which - * VCPUs are descheduled - which means that it will needlessly IPI - * them. Xen knows so let it do the job. - */ - if (xen_feature(XENFEAT_auto_translated_physmap)) { - pv_mmu_ops.flush_tlb_others = xen_flush_tlb_others; + if (xen_feature(XENFEAT_auto_translated_physmap)) return; - } + pv_mmu_ops = xen_mmu_ops; memset(dummy_mapping, 0xff, PAGE_SIZE); @@ -2465,9 +2806,9 @@ static int remap_area_mfn_pte_fn(pte_t *ptep, pgtable_t token, return 0; } -static int do_remap_mfn(struct vm_area_struct *vma, +static int do_remap_gfn(struct vm_area_struct *vma, unsigned long addr, - xen_pfn_t *mfn, int nr, + xen_pfn_t *gfn, int nr, int *err_ptr, pgprot_t prot, unsigned domid, struct page **pages) @@ -2483,14 +2824,14 @@ static int do_remap_mfn(struct vm_area_struct *vma, if (xen_feature(XENFEAT_auto_translated_physmap)) { #ifdef CONFIG_XEN_PVH /* We need to update the local page tables and the xen HAP */ - return xen_xlate_remap_gfn_array(vma, addr, mfn, nr, err_ptr, + return xen_xlate_remap_gfn_array(vma, addr, gfn, nr, err_ptr, prot, domid, pages); #else return -EINVAL; #endif } - rmd.mfn = mfn; + rmd.mfn = gfn; rmd.prot = prot; /* We use the err_ptr to indicate if there we are doing a contigious * mapping or a discontigious mapping. */ @@ -2518,8 +2859,8 @@ static int do_remap_mfn(struct vm_area_struct *vma, batch_left, &done, domid); /* - * @err_ptr may be the same buffer as @mfn, so - * only clear it after each chunk of @mfn is + * @err_ptr may be the same buffer as @gfn, so + * only clear it after each chunk of @gfn is * used. */ if (err_ptr) { @@ -2541,6 +2882,7 @@ static int do_remap_mfn(struct vm_area_struct *vma, addr += range; if (err_ptr) err_ptr += batch; + cond_resched(); } out: @@ -2549,19 +2891,19 @@ out: return err < 0 ? err : mapped; } -int xen_remap_domain_mfn_range(struct vm_area_struct *vma, +int xen_remap_domain_gfn_range(struct vm_area_struct *vma, unsigned long addr, - xen_pfn_t mfn, int nr, + xen_pfn_t gfn, int nr, pgprot_t prot, unsigned domid, struct page **pages) { - return do_remap_mfn(vma, addr, &mfn, nr, NULL, prot, domid, pages); + return do_remap_gfn(vma, addr, &gfn, nr, NULL, prot, domid, pages); } -EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range); +EXPORT_SYMBOL_GPL(xen_remap_domain_gfn_range); -int xen_remap_domain_mfn_array(struct vm_area_struct *vma, +int xen_remap_domain_gfn_array(struct vm_area_struct *vma, unsigned long addr, - xen_pfn_t *mfn, int nr, + xen_pfn_t *gfn, int nr, int *err_ptr, pgprot_t prot, unsigned domid, struct page **pages) { @@ -2570,13 +2912,13 @@ int xen_remap_domain_mfn_array(struct vm_area_struct *vma, * cause of "wrong memory was mapped in". */ BUG_ON(err_ptr == NULL); - return do_remap_mfn(vma, addr, mfn, nr, err_ptr, prot, domid, pages); + return do_remap_gfn(vma, addr, gfn, nr, err_ptr, prot, domid, pages); } -EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_array); +EXPORT_SYMBOL_GPL(xen_remap_domain_gfn_array); /* Returns: 0 success */ -int xen_unmap_domain_mfn_range(struct vm_area_struct *vma, +int xen_unmap_domain_gfn_range(struct vm_area_struct *vma, int numpgs, struct page **pages) { if (!pages || !xen_feature(XENFEAT_auto_translated_physmap)) @@ -2588,4 +2930,4 @@ int xen_unmap_domain_mfn_range(struct vm_area_struct *vma, return -EINVAL; #endif } -EXPORT_SYMBOL_GPL(xen_unmap_domain_mfn_range); +EXPORT_SYMBOL_GPL(xen_unmap_domain_gfn_range); diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 8b7f18e200aa..cab9f766bb06 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -79,10 +79,14 @@ #include <xen/balloon.h> #include <xen/grant_table.h> -#include "p2m.h" #include "multicalls.h" #include "xen-ops.h" +#define P2M_MID_PER_PAGE (PAGE_SIZE / sizeof(unsigned long *)) +#define P2M_TOP_PER_PAGE (PAGE_SIZE / sizeof(unsigned long **)) + +#define MAX_P2M_PFN (P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE) + #define PMDS_PER_MID_PAGE (P2M_MID_PER_PAGE / PTRS_PER_PTE) unsigned long *xen_p2m_addr __read_mostly; @@ -108,6 +112,15 @@ static unsigned long *p2m_identity; static pte_t *p2m_missing_pte; static pte_t *p2m_identity_pte; +/* + * Hint at last populated PFN. + * + * Used to set HYPERVISOR_shared_info->arch.max_pfn so the toolstack + * can avoid scanning the whole P2M (which may be sized to account for + * hotplugged memory). + */ +static unsigned long xen_p2m_last_pfn; + static inline unsigned p2m_top_index(unsigned long pfn) { BUG_ON(pfn >= MAX_P2M_PFN); @@ -199,7 +212,8 @@ void __ref xen_build_mfn_list_list(void) unsigned int level, topidx, mididx; unsigned long *mid_mfn_p; - if (xen_feature(XENFEAT_auto_translated_physmap)) + if (xen_feature(XENFEAT_auto_translated_physmap) || + xen_start_info->flags & SIF_VIRT_P2M_4TOOLS) return; /* Pre-initialize p2m_top_mfn to be completely missing */ @@ -260,9 +274,16 @@ void xen_setup_mfn_list_list(void) BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info); - HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = - virt_to_mfn(p2m_top_mfn); - HYPERVISOR_shared_info->arch.max_pfn = xen_max_p2m_pfn; + if (xen_start_info->flags & SIF_VIRT_P2M_4TOOLS) + HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = ~0UL; + else + HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = + virt_to_mfn(p2m_top_mfn); + HYPERVISOR_shared_info->arch.max_pfn = xen_p2m_last_pfn; + HYPERVISOR_shared_info->arch.p2m_generation = 0; + HYPERVISOR_shared_info->arch.p2m_vaddr = (unsigned long)xen_p2m_addr; + HYPERVISOR_shared_info->arch.p2m_cr3 = + xen_pfn_to_cr3(virt_to_mfn(swapper_pg_dir)); } /* Set up p2m_top to point to the domain-builder provided p2m pages */ @@ -394,6 +415,8 @@ void __init xen_vmalloc_p2m_tree(void) static struct vm_struct vm; unsigned long p2m_limit; + xen_p2m_last_pfn = xen_max_p2m_pfn; + p2m_limit = (phys_addr_t)P2M_LIMIT * 1024 * 1024 * 1024 / PAGE_SIZE; vm.flags = VM_ALLOC; vm.size = ALIGN(sizeof(unsigned long) * max(xen_max_p2m_pfn, p2m_limit), @@ -478,8 +501,12 @@ static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *pte_pg) ptechk = lookup_address(vaddr, &level); if (ptechk == pte_pg) { + HYPERVISOR_shared_info->arch.p2m_generation++; + wmb(); /* Tools are synchronizing via p2m_generation. */ set_pmd(pmdp, __pmd(__pa(pte_newpg[i]) | _KERNPG_TABLE)); + wmb(); /* Tools are synchronizing via p2m_generation. */ + HYPERVISOR_shared_info->arch.p2m_generation++; pte_newpg[i] = NULL; } @@ -503,9 +530,9 @@ static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *pte_pg) * the new pages are installed with cmpxchg; if we lose the race then * simply free the page we allocated and use the one that's there. */ -static bool alloc_p2m(unsigned long pfn) +int xen_alloc_p2m_entry(unsigned long pfn) { - unsigned topidx, mididx; + unsigned topidx; unsigned long *top_mfn_p, *mid_mfn; pte_t *ptep, *pte_pg; unsigned int level; @@ -513,8 +540,8 @@ static bool alloc_p2m(unsigned long pfn) unsigned long addr = (unsigned long)(xen_p2m_addr + pfn); unsigned long p2m_pfn; - topidx = p2m_top_index(pfn); - mididx = p2m_mid_index(pfn); + if (xen_feature(XENFEAT_auto_translated_physmap)) + return 0; ptep = lookup_address(addr, &level); BUG_ON(!ptep || level != PG_LEVEL_4K); @@ -524,10 +551,11 @@ static bool alloc_p2m(unsigned long pfn) /* PMD level is missing, allocate a new one */ ptep = alloc_p2m_pmd(addr, pte_pg); if (!ptep) - return false; + return -ENOMEM; } - if (p2m_top_mfn) { + if (p2m_top_mfn && pfn < MAX_P2M_PFN) { + topidx = p2m_top_index(pfn); top_mfn_p = &p2m_top_mfn[topidx]; mid_mfn = ACCESS_ONCE(p2m_top_mfn_p[topidx]); @@ -541,7 +569,7 @@ static bool alloc_p2m(unsigned long pfn) mid_mfn = alloc_p2m_page(); if (!mid_mfn) - return false; + return -ENOMEM; p2m_mid_mfn_init(mid_mfn, p2m_missing); @@ -567,7 +595,7 @@ static bool alloc_p2m(unsigned long pfn) p2m = alloc_p2m_page(); if (!p2m) - return false; + return -ENOMEM; if (p2m_pfn == PFN_DOWN(__pa(p2m_missing))) p2m_init(p2m); @@ -577,10 +605,14 @@ static bool alloc_p2m(unsigned long pfn) spin_lock_irqsave(&p2m_update_lock, flags); if (pte_pfn(*ptep) == p2m_pfn) { + HYPERVISOR_shared_info->arch.p2m_generation++; + wmb(); /* Tools are synchronizing via p2m_generation. */ set_pte(ptep, pfn_pte(PFN_DOWN(__pa(p2m)), PAGE_KERNEL)); + wmb(); /* Tools are synchronizing via p2m_generation. */ + HYPERVISOR_shared_info->arch.p2m_generation++; if (mid_mfn) - mid_mfn[mididx] = virt_to_mfn(p2m); + mid_mfn[p2m_mid_index(pfn)] = virt_to_mfn(p2m); p2m = NULL; } @@ -590,8 +622,15 @@ static bool alloc_p2m(unsigned long pfn) free_p2m_page(p2m); } - return true; + /* Expanded the p2m? */ + if (pfn > xen_p2m_last_pfn) { + xen_p2m_last_pfn = pfn; + HYPERVISOR_shared_info->arch.max_pfn = xen_p2m_last_pfn; + } + + return 0; } +EXPORT_SYMBOL(xen_alloc_p2m_entry); unsigned long __init set_phys_range_identity(unsigned long pfn_s, unsigned long pfn_e) @@ -630,6 +669,11 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) return true; } + /* + * The interface requires atomic updates on p2m elements. + * xen_safe_write_ulong() is using __put_user which does an atomic + * store via asm(). + */ if (likely(!xen_safe_write_ulong(xen_p2m_addr + pfn, mfn))) return true; @@ -648,7 +692,10 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) { if (unlikely(!__set_phys_to_machine(pfn, mfn))) { - if (!alloc_p2m(pfn)) + int ret; + + ret = xen_alloc_p2m_entry(pfn); + if (ret < 0) return false; return __set_phys_to_machine(pfn, mfn); diff --git a/arch/x86/xen/p2m.h b/arch/x86/xen/p2m.h deleted file mode 100644 index ad8aee24ab72..000000000000 --- a/arch/x86/xen/p2m.h +++ /dev/null @@ -1,15 +0,0 @@ -#ifndef _XEN_P2M_H -#define _XEN_P2M_H - -#define P2M_PER_PAGE (PAGE_SIZE / sizeof(unsigned long)) -#define P2M_MID_PER_PAGE (PAGE_SIZE / sizeof(unsigned long *)) -#define P2M_TOP_PER_PAGE (PAGE_SIZE / sizeof(unsigned long **)) - -#define MAX_P2M_PFN (P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE) - -#define MAX_REMAP_RANGES 10 - -extern unsigned long __init set_phys_range_identity(unsigned long pfn_s, - unsigned long pfn_e); - -#endif /* _XEN_P2M_H */ diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c index a8261716d58d..9586ff32810c 100644 --- a/arch/x86/xen/platform-pci-unplug.c +++ b/arch/x86/xen/platform-pci-unplug.c @@ -68,7 +68,7 @@ static int check_platform_magic(void) return 0; } -bool xen_has_pv_devices() +bool xen_has_pv_devices(void) { if (!xen_domain()) return false; diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c new file mode 100644 index 000000000000..724a08740a04 --- /dev/null +++ b/arch/x86/xen/pmu.c @@ -0,0 +1,570 @@ +#include <linux/types.h> +#include <linux/interrupt.h> + +#include <asm/xen/hypercall.h> +#include <xen/page.h> +#include <xen/interface/xen.h> +#include <xen/interface/vcpu.h> +#include <xen/interface/xenpmu.h> + +#include "xen-ops.h" +#include "pmu.h" + +/* x86_pmu.handle_irq definition */ +#include "../kernel/cpu/perf_event.h" + +#define XENPMU_IRQ_PROCESSING 1 +struct xenpmu { + /* Shared page between hypervisor and domain */ + struct xen_pmu_data *xenpmu_data; + + uint8_t flags; +}; +static DEFINE_PER_CPU(struct xenpmu, xenpmu_shared); +#define get_xenpmu_data() (this_cpu_ptr(&xenpmu_shared)->xenpmu_data) +#define get_xenpmu_flags() (this_cpu_ptr(&xenpmu_shared)->flags) + +/* Macro for computing address of a PMU MSR bank */ +#define field_offset(ctxt, field) ((void *)((uintptr_t)ctxt + \ + (uintptr_t)ctxt->field)) + +/* AMD PMU */ +#define F15H_NUM_COUNTERS 6 +#define F10H_NUM_COUNTERS 4 + +static __read_mostly uint32_t amd_counters_base; +static __read_mostly uint32_t amd_ctrls_base; +static __read_mostly int amd_msr_step; +static __read_mostly int k7_counters_mirrored; +static __read_mostly int amd_num_counters; + +/* Intel PMU */ +#define MSR_TYPE_COUNTER 0 +#define MSR_TYPE_CTRL 1 +#define MSR_TYPE_GLOBAL 2 +#define MSR_TYPE_ARCH_COUNTER 3 +#define MSR_TYPE_ARCH_CTRL 4 + +/* Number of general pmu registers (CPUID.EAX[0xa].EAX[8..15]) */ +#define PMU_GENERAL_NR_SHIFT 8 +#define PMU_GENERAL_NR_BITS 8 +#define PMU_GENERAL_NR_MASK (((1 << PMU_GENERAL_NR_BITS) - 1) \ + << PMU_GENERAL_NR_SHIFT) + +/* Number of fixed pmu registers (CPUID.EDX[0xa].EDX[0..4]) */ +#define PMU_FIXED_NR_SHIFT 0 +#define PMU_FIXED_NR_BITS 5 +#define PMU_FIXED_NR_MASK (((1 << PMU_FIXED_NR_BITS) - 1) \ + << PMU_FIXED_NR_SHIFT) + +/* Alias registers (0x4c1) for full-width writes to PMCs */ +#define MSR_PMC_ALIAS_MASK (~(MSR_IA32_PERFCTR0 ^ MSR_IA32_PMC0)) + +#define INTEL_PMC_TYPE_SHIFT 30 + +static __read_mostly int intel_num_arch_counters, intel_num_fixed_counters; + + +static void xen_pmu_arch_init(void) +{ + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { + + switch (boot_cpu_data.x86) { + case 0x15: + amd_num_counters = F15H_NUM_COUNTERS; + amd_counters_base = MSR_F15H_PERF_CTR; + amd_ctrls_base = MSR_F15H_PERF_CTL; + amd_msr_step = 2; + k7_counters_mirrored = 1; + break; + case 0x10: + case 0x12: + case 0x14: + case 0x16: + default: + amd_num_counters = F10H_NUM_COUNTERS; + amd_counters_base = MSR_K7_PERFCTR0; + amd_ctrls_base = MSR_K7_EVNTSEL0; + amd_msr_step = 1; + k7_counters_mirrored = 0; + break; + } + } else { + uint32_t eax, ebx, ecx, edx; + + cpuid(0xa, &eax, &ebx, &ecx, &edx); + + intel_num_arch_counters = (eax & PMU_GENERAL_NR_MASK) >> + PMU_GENERAL_NR_SHIFT; + intel_num_fixed_counters = (edx & PMU_FIXED_NR_MASK) >> + PMU_FIXED_NR_SHIFT; + } +} + +static inline uint32_t get_fam15h_addr(u32 addr) +{ + switch (addr) { + case MSR_K7_PERFCTR0: + case MSR_K7_PERFCTR1: + case MSR_K7_PERFCTR2: + case MSR_K7_PERFCTR3: + return MSR_F15H_PERF_CTR + (addr - MSR_K7_PERFCTR0); + case MSR_K7_EVNTSEL0: + case MSR_K7_EVNTSEL1: + case MSR_K7_EVNTSEL2: + case MSR_K7_EVNTSEL3: + return MSR_F15H_PERF_CTL + (addr - MSR_K7_EVNTSEL0); + default: + break; + } + + return addr; +} + +static inline bool is_amd_pmu_msr(unsigned int msr) +{ + if ((msr >= MSR_F15H_PERF_CTL && + msr < MSR_F15H_PERF_CTR + (amd_num_counters * 2)) || + (msr >= MSR_K7_EVNTSEL0 && + msr < MSR_K7_PERFCTR0 + amd_num_counters)) + return true; + + return false; +} + +static int is_intel_pmu_msr(u32 msr_index, int *type, int *index) +{ + u32 msr_index_pmc; + + switch (msr_index) { + case MSR_CORE_PERF_FIXED_CTR_CTRL: + case MSR_IA32_DS_AREA: + case MSR_IA32_PEBS_ENABLE: + *type = MSR_TYPE_CTRL; + return true; + + case MSR_CORE_PERF_GLOBAL_CTRL: + case MSR_CORE_PERF_GLOBAL_STATUS: + case MSR_CORE_PERF_GLOBAL_OVF_CTRL: + *type = MSR_TYPE_GLOBAL; + return true; + + default: + + if ((msr_index >= MSR_CORE_PERF_FIXED_CTR0) && + (msr_index < MSR_CORE_PERF_FIXED_CTR0 + + intel_num_fixed_counters)) { + *index = msr_index - MSR_CORE_PERF_FIXED_CTR0; + *type = MSR_TYPE_COUNTER; + return true; + } + + if ((msr_index >= MSR_P6_EVNTSEL0) && + (msr_index < MSR_P6_EVNTSEL0 + intel_num_arch_counters)) { + *index = msr_index - MSR_P6_EVNTSEL0; + *type = MSR_TYPE_ARCH_CTRL; + return true; + } + + msr_index_pmc = msr_index & MSR_PMC_ALIAS_MASK; + if ((msr_index_pmc >= MSR_IA32_PERFCTR0) && + (msr_index_pmc < MSR_IA32_PERFCTR0 + + intel_num_arch_counters)) { + *type = MSR_TYPE_ARCH_COUNTER; + *index = msr_index_pmc - MSR_IA32_PERFCTR0; + return true; + } + return false; + } +} + +static bool xen_intel_pmu_emulate(unsigned int msr, u64 *val, int type, + int index, bool is_read) +{ + uint64_t *reg = NULL; + struct xen_pmu_intel_ctxt *ctxt; + uint64_t *fix_counters; + struct xen_pmu_cntr_pair *arch_cntr_pair; + struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); + uint8_t xenpmu_flags = get_xenpmu_flags(); + + + if (!xenpmu_data || !(xenpmu_flags & XENPMU_IRQ_PROCESSING)) + return false; + + ctxt = &xenpmu_data->pmu.c.intel; + + switch (msr) { + case MSR_CORE_PERF_GLOBAL_OVF_CTRL: + reg = &ctxt->global_ovf_ctrl; + break; + case MSR_CORE_PERF_GLOBAL_STATUS: + reg = &ctxt->global_status; + break; + case MSR_CORE_PERF_GLOBAL_CTRL: + reg = &ctxt->global_ctrl; + break; + case MSR_CORE_PERF_FIXED_CTR_CTRL: + reg = &ctxt->fixed_ctrl; + break; + default: + switch (type) { + case MSR_TYPE_COUNTER: + fix_counters = field_offset(ctxt, fixed_counters); + reg = &fix_counters[index]; + break; + case MSR_TYPE_ARCH_COUNTER: + arch_cntr_pair = field_offset(ctxt, arch_counters); + reg = &arch_cntr_pair[index].counter; + break; + case MSR_TYPE_ARCH_CTRL: + arch_cntr_pair = field_offset(ctxt, arch_counters); + reg = &arch_cntr_pair[index].control; + break; + default: + return false; + } + } + + if (reg) { + if (is_read) + *val = *reg; + else { + *reg = *val; + + if (msr == MSR_CORE_PERF_GLOBAL_OVF_CTRL) + ctxt->global_status &= (~(*val)); + } + return true; + } + + return false; +} + +static bool xen_amd_pmu_emulate(unsigned int msr, u64 *val, bool is_read) +{ + uint64_t *reg = NULL; + int i, off = 0; + struct xen_pmu_amd_ctxt *ctxt; + uint64_t *counter_regs, *ctrl_regs; + struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); + uint8_t xenpmu_flags = get_xenpmu_flags(); + + if (!xenpmu_data || !(xenpmu_flags & XENPMU_IRQ_PROCESSING)) + return false; + + if (k7_counters_mirrored && + ((msr >= MSR_K7_EVNTSEL0) && (msr <= MSR_K7_PERFCTR3))) + msr = get_fam15h_addr(msr); + + ctxt = &xenpmu_data->pmu.c.amd; + for (i = 0; i < amd_num_counters; i++) { + if (msr == amd_ctrls_base + off) { + ctrl_regs = field_offset(ctxt, ctrls); + reg = &ctrl_regs[i]; + break; + } else if (msr == amd_counters_base + off) { + counter_regs = field_offset(ctxt, counters); + reg = &counter_regs[i]; + break; + } + off += amd_msr_step; + } + + if (reg) { + if (is_read) + *val = *reg; + else + *reg = *val; + + return true; + } + return false; +} + +bool pmu_msr_read(unsigned int msr, uint64_t *val, int *err) +{ + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { + if (is_amd_pmu_msr(msr)) { + if (!xen_amd_pmu_emulate(msr, val, 1)) + *val = native_read_msr_safe(msr, err); + return true; + } + } else { + int type, index; + + if (is_intel_pmu_msr(msr, &type, &index)) { + if (!xen_intel_pmu_emulate(msr, val, type, index, 1)) + *val = native_read_msr_safe(msr, err); + return true; + } + } + + return false; +} + +bool pmu_msr_write(unsigned int msr, uint32_t low, uint32_t high, int *err) +{ + uint64_t val = ((uint64_t)high << 32) | low; + + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { + if (is_amd_pmu_msr(msr)) { + if (!xen_amd_pmu_emulate(msr, &val, 0)) + *err = native_write_msr_safe(msr, low, high); + return true; + } + } else { + int type, index; + + if (is_intel_pmu_msr(msr, &type, &index)) { + if (!xen_intel_pmu_emulate(msr, &val, type, index, 0)) + *err = native_write_msr_safe(msr, low, high); + return true; + } + } + + return false; +} + +static unsigned long long xen_amd_read_pmc(int counter) +{ + struct xen_pmu_amd_ctxt *ctxt; + uint64_t *counter_regs; + struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); + uint8_t xenpmu_flags = get_xenpmu_flags(); + + if (!xenpmu_data || !(xenpmu_flags & XENPMU_IRQ_PROCESSING)) { + uint32_t msr; + int err; + + msr = amd_counters_base + (counter * amd_msr_step); + return native_read_msr_safe(msr, &err); + } + + ctxt = &xenpmu_data->pmu.c.amd; + counter_regs = field_offset(ctxt, counters); + return counter_regs[counter]; +} + +static unsigned long long xen_intel_read_pmc(int counter) +{ + struct xen_pmu_intel_ctxt *ctxt; + uint64_t *fixed_counters; + struct xen_pmu_cntr_pair *arch_cntr_pair; + struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); + uint8_t xenpmu_flags = get_xenpmu_flags(); + + if (!xenpmu_data || !(xenpmu_flags & XENPMU_IRQ_PROCESSING)) { + uint32_t msr; + int err; + + if (counter & (1 << INTEL_PMC_TYPE_SHIFT)) + msr = MSR_CORE_PERF_FIXED_CTR0 + (counter & 0xffff); + else + msr = MSR_IA32_PERFCTR0 + counter; + + return native_read_msr_safe(msr, &err); + } + + ctxt = &xenpmu_data->pmu.c.intel; + if (counter & (1 << INTEL_PMC_TYPE_SHIFT)) { + fixed_counters = field_offset(ctxt, fixed_counters); + return fixed_counters[counter & 0xffff]; + } + + arch_cntr_pair = field_offset(ctxt, arch_counters); + return arch_cntr_pair[counter].counter; +} + +unsigned long long xen_read_pmc(int counter) +{ + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + return xen_amd_read_pmc(counter); + else + return xen_intel_read_pmc(counter); +} + +int pmu_apic_update(uint32_t val) +{ + int ret; + struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); + + if (!xenpmu_data) { + pr_warn_once("%s: pmudata not initialized\n", __func__); + return -EINVAL; + } + + xenpmu_data->pmu.l.lapic_lvtpc = val; + + if (get_xenpmu_flags() & XENPMU_IRQ_PROCESSING) + return 0; + + ret = HYPERVISOR_xenpmu_op(XENPMU_lvtpc_set, NULL); + + return ret; +} + +/* perf callbacks */ +static int xen_is_in_guest(void) +{ + const struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); + + if (!xenpmu_data) { + pr_warn_once("%s: pmudata not initialized\n", __func__); + return 0; + } + + if (!xen_initial_domain() || (xenpmu_data->domain_id >= DOMID_SELF)) + return 0; + + return 1; +} + +static int xen_is_user_mode(void) +{ + const struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); + + if (!xenpmu_data) { + pr_warn_once("%s: pmudata not initialized\n", __func__); + return 0; + } + + if (xenpmu_data->pmu.pmu_flags & PMU_SAMPLE_PV) + return (xenpmu_data->pmu.pmu_flags & PMU_SAMPLE_USER); + else + return !!(xenpmu_data->pmu.r.regs.cpl & 3); +} + +static unsigned long xen_get_guest_ip(void) +{ + const struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); + + if (!xenpmu_data) { + pr_warn_once("%s: pmudata not initialized\n", __func__); + return 0; + } + + return xenpmu_data->pmu.r.regs.ip; +} + +static struct perf_guest_info_callbacks xen_guest_cbs = { + .is_in_guest = xen_is_in_guest, + .is_user_mode = xen_is_user_mode, + .get_guest_ip = xen_get_guest_ip, +}; + +/* Convert registers from Xen's format to Linux' */ +static void xen_convert_regs(const struct xen_pmu_regs *xen_regs, + struct pt_regs *regs, uint64_t pmu_flags) +{ + regs->ip = xen_regs->ip; + regs->cs = xen_regs->cs; + regs->sp = xen_regs->sp; + + if (pmu_flags & PMU_SAMPLE_PV) { + if (pmu_flags & PMU_SAMPLE_USER) + regs->cs |= 3; + else + regs->cs &= ~3; + } else { + if (xen_regs->cpl) + regs->cs |= 3; + else + regs->cs &= ~3; + } +} + +irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id) +{ + int err, ret = IRQ_NONE; + struct pt_regs regs; + const struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); + uint8_t xenpmu_flags = get_xenpmu_flags(); + + if (!xenpmu_data) { + pr_warn_once("%s: pmudata not initialized\n", __func__); + return ret; + } + + this_cpu_ptr(&xenpmu_shared)->flags = + xenpmu_flags | XENPMU_IRQ_PROCESSING; + xen_convert_regs(&xenpmu_data->pmu.r.regs, ®s, + xenpmu_data->pmu.pmu_flags); + if (x86_pmu.handle_irq(®s)) + ret = IRQ_HANDLED; + + /* Write out cached context to HW */ + err = HYPERVISOR_xenpmu_op(XENPMU_flush, NULL); + this_cpu_ptr(&xenpmu_shared)->flags = xenpmu_flags; + if (err) { + pr_warn_once("%s: failed hypercall, err: %d\n", __func__, err); + return IRQ_NONE; + } + + return ret; +} + +bool is_xen_pmu(int cpu) +{ + return (get_xenpmu_data() != NULL); +} + +void xen_pmu_init(int cpu) +{ + int err; + struct xen_pmu_params xp; + unsigned long pfn; + struct xen_pmu_data *xenpmu_data; + + BUILD_BUG_ON(sizeof(struct xen_pmu_data) > PAGE_SIZE); + + if (xen_hvm_domain()) + return; + + xenpmu_data = (struct xen_pmu_data *)get_zeroed_page(GFP_KERNEL); + if (!xenpmu_data) { + pr_err("VPMU init: No memory\n"); + return; + } + pfn = virt_to_pfn(xenpmu_data); + + xp.val = pfn_to_mfn(pfn); + xp.vcpu = cpu; + xp.version.maj = XENPMU_VER_MAJ; + xp.version.min = XENPMU_VER_MIN; + err = HYPERVISOR_xenpmu_op(XENPMU_init, &xp); + if (err) + goto fail; + + per_cpu(xenpmu_shared, cpu).xenpmu_data = xenpmu_data; + per_cpu(xenpmu_shared, cpu).flags = 0; + + if (cpu == 0) { + perf_register_guest_info_callbacks(&xen_guest_cbs); + xen_pmu_arch_init(); + } + + return; + +fail: + pr_warn_once("Could not initialize VPMU for cpu %d, error %d\n", + cpu, err); + free_pages((unsigned long)xenpmu_data, 0); +} + +void xen_pmu_finish(int cpu) +{ + struct xen_pmu_params xp; + + if (xen_hvm_domain()) + return; + + xp.vcpu = cpu; + xp.version.maj = XENPMU_VER_MAJ; + xp.version.min = XENPMU_VER_MIN; + + (void)HYPERVISOR_xenpmu_op(XENPMU_finish, &xp); + + free_pages((unsigned long)per_cpu(xenpmu_shared, cpu).xenpmu_data, 0); + per_cpu(xenpmu_shared, cpu).xenpmu_data = NULL; +} diff --git a/arch/x86/xen/pmu.h b/arch/x86/xen/pmu.h new file mode 100644 index 000000000000..af5f0ad94078 --- /dev/null +++ b/arch/x86/xen/pmu.h @@ -0,0 +1,15 @@ +#ifndef __XEN_PMU_H +#define __XEN_PMU_H + +#include <xen/interface/xenpmu.h> + +irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id); +void xen_pmu_init(int cpu); +void xen_pmu_finish(int cpu); +bool is_xen_pmu(int cpu); +bool pmu_msr_read(unsigned int msr, uint64_t *val, int *err); +bool pmu_msr_write(unsigned int msr, uint32_t low, uint32_t high, int *err); +int pmu_apic_update(uint32_t reg); +unsigned long long xen_read_pmc(int counter); + +#endif /* __XEN_PMU_H */ diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 55f388ef481a..7ab29518a3b9 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -27,17 +27,23 @@ #include <xen/interface/memory.h> #include <xen/interface/physdev.h> #include <xen/features.h> +#include <xen/hvc-console.h> #include "xen-ops.h" #include "vdso.h" -#include "p2m.h" #include "mmu.h" +#define GB(x) ((uint64_t)(x) * 1024 * 1024 * 1024) + /* Amount of extra memory space we add to the e820 ranges */ struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; /* Number of pages released from the initial allocation. */ unsigned long xen_released_pages; +/* E820 map used during setting up memory. */ +static struct e820entry xen_e820_map[E820MAX] __initdata; +static u32 xen_e820_map_entries __initdata; + /* * Buffer used to remap identity mapped pages. We only need the virtual space. * The physical page behind this address is remapped as needed to different @@ -64,62 +70,89 @@ static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY; */ #define EXTRA_MEM_RATIO (10) -static void __init xen_add_extra_mem(phys_addr_t start, phys_addr_t size) +static bool xen_512gb_limit __initdata = IS_ENABLED(CONFIG_XEN_512GB); + +static void __init xen_parse_512gb(void) +{ + bool val = false; + char *arg; + + arg = strstr(xen_start_info->cmd_line, "xen_512gb_limit"); + if (!arg) + return; + + arg = strstr(xen_start_info->cmd_line, "xen_512gb_limit="); + if (!arg) + val = true; + else if (strtobool(arg + strlen("xen_512gb_limit="), &val)) + return; + + xen_512gb_limit = val; +} + +static void __init xen_add_extra_mem(unsigned long start_pfn, + unsigned long n_pfns) { int i; + /* + * No need to check for zero size, should happen rarely and will only + * write a new entry regarded to be unused due to zero size. + */ for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { /* Add new region. */ - if (xen_extra_mem[i].size == 0) { - xen_extra_mem[i].start = start; - xen_extra_mem[i].size = size; + if (xen_extra_mem[i].n_pfns == 0) { + xen_extra_mem[i].start_pfn = start_pfn; + xen_extra_mem[i].n_pfns = n_pfns; break; } /* Append to existing region. */ - if (xen_extra_mem[i].start + xen_extra_mem[i].size == start) { - xen_extra_mem[i].size += size; + if (xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns == + start_pfn) { + xen_extra_mem[i].n_pfns += n_pfns; break; } } if (i == XEN_EXTRA_MEM_MAX_REGIONS) printk(KERN_WARNING "Warning: not enough extra memory regions\n"); - memblock_reserve(start, size); + memblock_reserve(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns)); } -static void __init xen_del_extra_mem(phys_addr_t start, phys_addr_t size) +static void __init xen_del_extra_mem(unsigned long start_pfn, + unsigned long n_pfns) { int i; - phys_addr_t start_r, size_r; + unsigned long start_r, size_r; for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { - start_r = xen_extra_mem[i].start; - size_r = xen_extra_mem[i].size; + start_r = xen_extra_mem[i].start_pfn; + size_r = xen_extra_mem[i].n_pfns; /* Start of region. */ - if (start_r == start) { - BUG_ON(size > size_r); - xen_extra_mem[i].start += size; - xen_extra_mem[i].size -= size; + if (start_r == start_pfn) { + BUG_ON(n_pfns > size_r); + xen_extra_mem[i].start_pfn += n_pfns; + xen_extra_mem[i].n_pfns -= n_pfns; break; } /* End of region. */ - if (start_r + size_r == start + size) { - BUG_ON(size > size_r); - xen_extra_mem[i].size -= size; + if (start_r + size_r == start_pfn + n_pfns) { + BUG_ON(n_pfns > size_r); + xen_extra_mem[i].n_pfns -= n_pfns; break; } /* Mid of region. */ - if (start > start_r && start < start_r + size_r) { - BUG_ON(start + size > start_r + size_r); - xen_extra_mem[i].size = start - start_r; + if (start_pfn > start_r && start_pfn < start_r + size_r) { + BUG_ON(start_pfn + n_pfns > start_r + size_r); + xen_extra_mem[i].n_pfns = start_pfn - start_r; /* Calling memblock_reserve() again is okay. */ - xen_add_extra_mem(start + size, start_r + size_r - - (start + size)); + xen_add_extra_mem(start_pfn + n_pfns, start_r + size_r - + (start_pfn + n_pfns)); break; } } - memblock_free(start, size); + memblock_free(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns)); } /* @@ -130,11 +163,10 @@ static void __init xen_del_extra_mem(phys_addr_t start, phys_addr_t size) unsigned long __ref xen_chk_extra_mem(unsigned long pfn) { int i; - phys_addr_t addr = PFN_PHYS(pfn); for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { - if (addr >= xen_extra_mem[i].start && - addr < xen_extra_mem[i].start + xen_extra_mem[i].size) + if (pfn >= xen_extra_mem[i].start_pfn && + pfn < xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns) return INVALID_P2M_ENTRY; } @@ -150,10 +182,10 @@ void __init xen_inv_extra_mem(void) int i; for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { - if (!xen_extra_mem[i].size) + if (!xen_extra_mem[i].n_pfns) continue; - pfn_s = PFN_DOWN(xen_extra_mem[i].start); - pfn_e = PFN_UP(xen_extra_mem[i].start + xen_extra_mem[i].size); + pfn_s = xen_extra_mem[i].start_pfn; + pfn_e = pfn_s + xen_extra_mem[i].n_pfns; for (pfn = pfn_s; pfn < pfn_e; pfn++) set_phys_to_machine(pfn, INVALID_P2M_ENTRY); } @@ -164,15 +196,13 @@ void __init xen_inv_extra_mem(void) * This function updates min_pfn with the pfn found and returns * the size of that range or zero if not found. */ -static unsigned long __init xen_find_pfn_range( - const struct e820entry *list, size_t map_size, - unsigned long *min_pfn) +static unsigned long __init xen_find_pfn_range(unsigned long *min_pfn) { - const struct e820entry *entry; + const struct e820entry *entry = xen_e820_map; unsigned int i; unsigned long done = 0; - for (i = 0, entry = list; i < map_size; i++, entry++) { + for (i = 0; i < xen_e820_map_entries; i++, entry++) { unsigned long s_pfn; unsigned long e_pfn; @@ -182,7 +212,7 @@ static unsigned long __init xen_find_pfn_range( e_pfn = PFN_DOWN(entry->addr + entry->size); /* We only care about E820 after this */ - if (e_pfn < *min_pfn) + if (e_pfn <= *min_pfn) continue; s_pfn = PFN_UP(entry->addr); @@ -221,7 +251,7 @@ static int __init xen_free_mfn(unsigned long mfn) * as a fallback if the remapping fails. */ static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn, - unsigned long end_pfn, unsigned long nr_pages, unsigned long *released) + unsigned long end_pfn, unsigned long nr_pages) { unsigned long pfn, end; int ret; @@ -241,7 +271,7 @@ static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn, WARN(ret != 1, "Failed to release pfn %lx err=%d\n", pfn, ret); if (ret == 1) { - (*released)++; + xen_released_pages++; if (!__set_phys_to_machine(pfn, INVALID_P2M_ENTRY)) break; } else @@ -356,9 +386,8 @@ static void __init xen_do_set_identity_and_remap_chunk( * to Xen and not remapped. */ static unsigned long __init xen_set_identity_and_remap_chunk( - const struct e820entry *list, size_t map_size, unsigned long start_pfn, - unsigned long end_pfn, unsigned long nr_pages, unsigned long remap_pfn, - unsigned long *released, unsigned long *remapped) + unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages, + unsigned long remap_pfn) { unsigned long pfn; unsigned long i = 0; @@ -379,12 +408,11 @@ static unsigned long __init xen_set_identity_and_remap_chunk( if (cur_pfn + size > nr_pages) size = nr_pages - cur_pfn; - remap_range_size = xen_find_pfn_range(list, map_size, - &remap_pfn); + remap_range_size = xen_find_pfn_range(&remap_pfn); if (!remap_range_size) { pr_warning("Unable to find available pfn range, not remapping identity pages\n"); xen_set_identity_and_release_chunk(cur_pfn, - cur_pfn + left, nr_pages, released); + cur_pfn + left, nr_pages); break; } /* Adjust size to fit in current e820 RAM region */ @@ -396,7 +424,6 @@ static unsigned long __init xen_set_identity_and_remap_chunk( /* Update variables to reflect new mappings. */ i += size; remap_pfn += size; - *remapped += size; } /* @@ -411,15 +438,11 @@ static unsigned long __init xen_set_identity_and_remap_chunk( return remap_pfn; } -static void __init xen_set_identity_and_remap( - const struct e820entry *list, size_t map_size, unsigned long nr_pages, - unsigned long *released, unsigned long *remapped) +static void __init xen_set_identity_and_remap(unsigned long nr_pages) { phys_addr_t start = 0; unsigned long last_pfn = nr_pages; - const struct e820entry *entry; - unsigned long num_released = 0; - unsigned long num_remapped = 0; + const struct e820entry *entry = xen_e820_map; int i; /* @@ -433,9 +456,9 @@ static void __init xen_set_identity_and_remap( * example) the DMI tables in a reserved region that begins on * a non-page boundary. */ - for (i = 0, entry = list; i < map_size; i++, entry++) { + for (i = 0; i < xen_e820_map_entries; i++, entry++) { phys_addr_t end = entry->addr + entry->size; - if (entry->type == E820_RAM || i == map_size - 1) { + if (entry->type == E820_RAM || i == xen_e820_map_entries - 1) { unsigned long start_pfn = PFN_DOWN(start); unsigned long end_pfn = PFN_UP(end); @@ -444,17 +467,13 @@ static void __init xen_set_identity_and_remap( if (start_pfn < end_pfn) last_pfn = xen_set_identity_and_remap_chunk( - list, map_size, start_pfn, - end_pfn, nr_pages, last_pfn, - &num_released, &num_remapped); + start_pfn, end_pfn, nr_pages, + last_pfn); start = end; } } - *released = num_released; - *remapped = num_remapped; - - pr_info("Released %ld page(s)\n", num_released); + pr_info("Released %ld page(s)\n", xen_released_pages); } /* @@ -494,7 +513,7 @@ void __init xen_remap_memory(void) } else if (pfn_s + len == xen_remap_buf.target_pfn) { len += xen_remap_buf.size; } else { - xen_del_extra_mem(PFN_PHYS(pfn_s), PFN_PHYS(len)); + xen_del_extra_mem(pfn_s, len); pfn_s = xen_remap_buf.target_pfn; len = xen_remap_buf.size; } @@ -504,18 +523,35 @@ void __init xen_remap_memory(void) } if (pfn_s != ~0UL && len) - xen_del_extra_mem(PFN_PHYS(pfn_s), PFN_PHYS(len)); + xen_del_extra_mem(pfn_s, len); set_pte_mfn(buf, mfn_save, PAGE_KERNEL); pr_info("Remapped %ld page(s)\n", remapped); } +static unsigned long __init xen_get_pages_limit(void) +{ + unsigned long limit; + +#ifdef CONFIG_X86_32 + limit = GB(64) / PAGE_SIZE; +#else + limit = MAXMEM / PAGE_SIZE; + if (!xen_initial_domain() && xen_512gb_limit) + limit = GB(512) / PAGE_SIZE; +#endif + return limit; +} + static unsigned long __init xen_get_max_pages(void) { - unsigned long max_pages = MAX_DOMAIN_PAGES; + unsigned long max_pages, limit; domid_t domid = DOMID_SELF; - int ret; + long ret; + + limit = xen_get_pages_limit(); + max_pages = limit; /* * For the initial domain we use the maximum reservation as @@ -532,7 +568,7 @@ static unsigned long __init xen_get_max_pages(void) max_pages = ret; } - return min(max_pages, MAX_DOMAIN_PAGES); + return min(max_pages, limit); } static void __init xen_align_and_add_e820_region(phys_addr_t start, @@ -549,39 +585,188 @@ static void __init xen_align_and_add_e820_region(phys_addr_t start, e820_add_region(start, end - start, type); } -static void __init xen_ignore_unusable(struct e820entry *list, size_t map_size) +static void __init xen_ignore_unusable(void) { - struct e820entry *entry; + struct e820entry *entry = xen_e820_map; unsigned int i; - for (i = 0, entry = list; i < map_size; i++, entry++) { + for (i = 0; i < xen_e820_map_entries; i++, entry++) { if (entry->type == E820_UNUSABLE) entry->type = E820_RAM; } } +static unsigned long __init xen_count_remap_pages(unsigned long max_pfn) +{ + unsigned long extra = 0; + unsigned long start_pfn, end_pfn; + const struct e820entry *entry = xen_e820_map; + int i; + + end_pfn = 0; + for (i = 0; i < xen_e820_map_entries; i++, entry++) { + start_pfn = PFN_DOWN(entry->addr); + /* Adjacent regions on non-page boundaries handling! */ + end_pfn = min(end_pfn, start_pfn); + + if (start_pfn >= max_pfn) + return extra + max_pfn - end_pfn; + + /* Add any holes in map to result. */ + extra += start_pfn - end_pfn; + + end_pfn = PFN_UP(entry->addr + entry->size); + end_pfn = min(end_pfn, max_pfn); + + if (entry->type != E820_RAM) + extra += end_pfn - start_pfn; + } + + return extra; +} + +bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size) +{ + struct e820entry *entry; + unsigned mapcnt; + phys_addr_t end; + + if (!size) + return false; + + end = start + size; + entry = xen_e820_map; + + for (mapcnt = 0; mapcnt < xen_e820_map_entries; mapcnt++) { + if (entry->type == E820_RAM && entry->addr <= start && + (entry->addr + entry->size) >= end) + return false; + + entry++; + } + + return true; +} + +/* + * Find a free area in physical memory not yet reserved and compliant with + * E820 map. + * Used to relocate pre-allocated areas like initrd or p2m list which are in + * conflict with the to be used E820 map. + * In case no area is found, return 0. Otherwise return the physical address + * of the area which is already reserved for convenience. + */ +phys_addr_t __init xen_find_free_area(phys_addr_t size) +{ + unsigned mapcnt; + phys_addr_t addr, start; + struct e820entry *entry = xen_e820_map; + + for (mapcnt = 0; mapcnt < xen_e820_map_entries; mapcnt++, entry++) { + if (entry->type != E820_RAM || entry->size < size) + continue; + start = entry->addr; + for (addr = start; addr < start + size; addr += PAGE_SIZE) { + if (!memblock_is_reserved(addr)) + continue; + start = addr + PAGE_SIZE; + if (start + size > entry->addr + entry->size) + break; + } + if (addr >= start + size) { + memblock_reserve(start, size); + return start; + } + } + + return 0; +} + +/* + * Like memcpy, but with physical addresses for dest and src. + */ +static void __init xen_phys_memcpy(phys_addr_t dest, phys_addr_t src, + phys_addr_t n) +{ + phys_addr_t dest_off, src_off, dest_len, src_len, len; + void *from, *to; + + while (n) { + dest_off = dest & ~PAGE_MASK; + src_off = src & ~PAGE_MASK; + dest_len = n; + if (dest_len > (NR_FIX_BTMAPS << PAGE_SHIFT) - dest_off) + dest_len = (NR_FIX_BTMAPS << PAGE_SHIFT) - dest_off; + src_len = n; + if (src_len > (NR_FIX_BTMAPS << PAGE_SHIFT) - src_off) + src_len = (NR_FIX_BTMAPS << PAGE_SHIFT) - src_off; + len = min(dest_len, src_len); + to = early_memremap(dest - dest_off, dest_len + dest_off); + from = early_memremap(src - src_off, src_len + src_off); + memcpy(to, from, len); + early_memunmap(to, dest_len + dest_off); + early_memunmap(from, src_len + src_off); + n -= len; + dest += len; + src += len; + } +} + +/* + * Reserve Xen mfn_list. + */ +static void __init xen_reserve_xen_mfnlist(void) +{ + phys_addr_t start, size; + + if (xen_start_info->mfn_list >= __START_KERNEL_map) { + start = __pa(xen_start_info->mfn_list); + size = PFN_ALIGN(xen_start_info->nr_pages * + sizeof(unsigned long)); + } else { + start = PFN_PHYS(xen_start_info->first_p2m_pfn); + size = PFN_PHYS(xen_start_info->nr_p2m_frames); + } + + if (!xen_is_e820_reserved(start, size)) { + memblock_reserve(start, size); + return; + } + +#ifdef CONFIG_X86_32 + /* + * Relocating the p2m on 32 bit system to an arbitrary virtual address + * is not supported, so just give up. + */ + xen_raw_console_write("Xen hypervisor allocated p2m list conflicts with E820 map\n"); + BUG(); +#else + xen_relocate_p2m(); +#endif +} + /** * machine_specific_memory_setup - Hook for machine specific memory setup. **/ char * __init xen_memory_setup(void) { - static struct e820entry map[E820MAX] __initdata; - - unsigned long max_pfn = xen_start_info->nr_pages; - phys_addr_t mem_end; + unsigned long max_pfn, pfn_s, n_pfns; + phys_addr_t mem_end, addr, size, chunk_size; + u32 type; int rc; struct xen_memory_map memmap; unsigned long max_pages; unsigned long extra_pages = 0; - unsigned long remapped_pages; int i; int op; - max_pfn = min(MAX_DOMAIN_PAGES, max_pfn); + xen_parse_512gb(); + max_pfn = xen_get_pages_limit(); + max_pfn = min(max_pfn, xen_start_info->nr_pages); mem_end = PFN_PHYS(max_pfn); memmap.nr_entries = E820MAX; - set_xen_guest_handle(memmap.buffer, map); + set_xen_guest_handle(memmap.buffer, xen_e820_map); op = xen_initial_domain() ? XENMEM_machine_memory_map : @@ -590,15 +775,16 @@ char * __init xen_memory_setup(void) if (rc == -ENOSYS) { BUG_ON(xen_initial_domain()); memmap.nr_entries = 1; - map[0].addr = 0ULL; - map[0].size = mem_end; + xen_e820_map[0].addr = 0ULL; + xen_e820_map[0].size = mem_end; /* 8MB slack (to balance backend allocations). */ - map[0].size += 8ULL << 20; - map[0].type = E820_RAM; + xen_e820_map[0].size += 8ULL << 20; + xen_e820_map[0].type = E820_RAM; rc = 0; } BUG_ON(rc); BUG_ON(memmap.nr_entries == 0); + xen_e820_map_entries = memmap.nr_entries; /* * Xen won't allow a 1:1 mapping to be created to UNUSABLE @@ -609,24 +795,19 @@ char * __init xen_memory_setup(void) * a patch in the future. */ if (xen_initial_domain()) - xen_ignore_unusable(map, memmap.nr_entries); + xen_ignore_unusable(); /* Make sure the Xen-supplied memory map is well-ordered. */ - sanitize_e820_map(map, memmap.nr_entries, &memmap.nr_entries); + sanitize_e820_map(xen_e820_map, ARRAY_SIZE(xen_e820_map), + &xen_e820_map_entries); max_pages = xen_get_max_pages(); - if (max_pages > max_pfn) - extra_pages += max_pages - max_pfn; - /* - * Set identity map on non-RAM pages and prepare remapping the - * underlying RAM. - */ - xen_set_identity_and_remap(map, memmap.nr_entries, max_pfn, - &xen_released_pages, &remapped_pages); + /* How many extra pages do we need due to remapping? */ + max_pages += xen_count_remap_pages(max_pfn); - extra_pages += xen_released_pages; - extra_pages += remapped_pages; + if (max_pages > max_pfn) + extra_pages += max_pages - max_pfn; /* * Clamp the amount of extra memory to a EXTRA_MEM_RATIO @@ -635,46 +816,57 @@ char * __init xen_memory_setup(void) * is limited to the max size of lowmem, so that it doesn't * get completely filled. * + * Make sure we have no memory above max_pages, as this area + * isn't handled by the p2m management. + * * In principle there could be a problem in lowmem systems if * the initial memory is also very large with respect to * lowmem, but we won't try to deal with that here. */ - extra_pages = min(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)), - extra_pages); + extra_pages = min3(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)), + extra_pages, max_pages - max_pfn); i = 0; - while (i < memmap.nr_entries) { - phys_addr_t addr = map[i].addr; - phys_addr_t size = map[i].size; - u32 type = map[i].type; + addr = xen_e820_map[0].addr; + size = xen_e820_map[0].size; + while (i < xen_e820_map_entries) { + bool discard = false; + + chunk_size = size; + type = xen_e820_map[i].type; if (type == E820_RAM) { if (addr < mem_end) { - size = min(size, mem_end - addr); + chunk_size = min(size, mem_end - addr); } else if (extra_pages) { - size = min(size, PFN_PHYS(extra_pages)); - extra_pages -= PFN_DOWN(size); - xen_add_extra_mem(addr, size); - xen_max_p2m_pfn = PFN_DOWN(addr + size); + chunk_size = min(size, PFN_PHYS(extra_pages)); + pfn_s = PFN_UP(addr); + n_pfns = PFN_DOWN(addr + chunk_size) - pfn_s; + extra_pages -= n_pfns; + xen_add_extra_mem(pfn_s, n_pfns); + xen_max_p2m_pfn = pfn_s + n_pfns; } else - type = E820_UNUSABLE; + discard = true; } - xen_align_and_add_e820_region(addr, size, type); + if (!discard) + xen_align_and_add_e820_region(addr, chunk_size, type); - map[i].addr += size; - map[i].size -= size; - if (map[i].size == 0) + addr += chunk_size; + size -= chunk_size; + if (size == 0) { i++; + if (i < xen_e820_map_entries) { + addr = xen_e820_map[i].addr; + size = xen_e820_map[i].size; + } + } } /* * Set the rest as identity mapped, in case PCI BARs are * located here. - * - * PFNs above MAX_P2M_PFN are considered identity mapped as - * well. */ - set_phys_range_identity(map[i-1].addr / PAGE_SIZE, ~0ul); + set_phys_range_identity(addr / PAGE_SIZE, ~0ul); /* * In domU, the ISA region is normal, usable memory, but we @@ -684,34 +876,53 @@ char * __init xen_memory_setup(void) e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS, E820_RESERVED); + sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); + /* - * Reserve Xen bits: - * - mfn_list - * - xen_start_info - * See comment above "struct start_info" in <xen/interface/xen.h> - * We tried to make the the memblock_reserve more selective so - * that it would be clear what region is reserved. Sadly we ran - * in the problem wherein on a 64-bit hypervisor with a 32-bit - * initial domain, the pt_base has the cr3 value which is not - * neccessarily where the pagetable starts! As Jan put it: " - * Actually, the adjustment turns out to be correct: The page - * tables for a 32-on-64 dom0 get allocated in the order "first L1", - * "first L2", "first L3", so the offset to the page table base is - * indeed 2. When reading xen/include/public/xen.h's comment - * very strictly, this is not a violation (since there nothing is said - * that the first thing in the page table space is pointed to by - * pt_base; I admit that this seems to be implied though, namely - * do I think that it is implied that the page table space is the - * range [pt_base, pt_base + nt_pt_frames), whereas that - * range here indeed is [pt_base - 2, pt_base - 2 + nt_pt_frames), - * which - without a priori knowledge - the kernel would have - * difficulty to figure out)." - so lets just fall back to the - * easy way and reserve the whole region. + * Check whether the kernel itself conflicts with the target E820 map. + * Failing now is better than running into weird problems later due + * to relocating (and even reusing) pages with kernel text or data. */ - memblock_reserve(__pa(xen_start_info->mfn_list), - xen_start_info->pt_base - xen_start_info->mfn_list); + if (xen_is_e820_reserved(__pa_symbol(_text), + __pa_symbol(__bss_stop) - __pa_symbol(_text))) { + xen_raw_console_write("Xen hypervisor allocated kernel memory conflicts with E820 map\n"); + BUG(); + } - sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); + /* + * Check for a conflict of the hypervisor supplied page tables with + * the target E820 map. + */ + xen_pt_check_e820(); + + xen_reserve_xen_mfnlist(); + + /* Check for a conflict of the initrd with the target E820 map. */ + if (xen_is_e820_reserved(boot_params.hdr.ramdisk_image, + boot_params.hdr.ramdisk_size)) { + phys_addr_t new_area, start, size; + + new_area = xen_find_free_area(boot_params.hdr.ramdisk_size); + if (!new_area) { + xen_raw_console_write("Can't find new memory area for initrd needed due to E820 map conflict\n"); + BUG(); + } + + start = boot_params.hdr.ramdisk_image; + size = boot_params.hdr.ramdisk_size; + xen_phys_memcpy(new_area, start, size); + pr_info("initrd moved from [mem %#010llx-%#010llx] to [mem %#010llx-%#010llx]\n", + start, start + size, new_area, new_area + size); + memblock_free(start, size); + boot_params.hdr.ramdisk_image = new_area; + boot_params.ext_ramdisk_image = new_area >> 32; + } + + /* + * Set identity map on non-RAM pages and prepare remapping the + * underlying RAM. + */ + xen_set_identity_and_remap(max_pfn); return "Xen"; } @@ -721,26 +932,30 @@ char * __init xen_memory_setup(void) */ char * __init xen_auto_xlated_memory_setup(void) { - static struct e820entry map[E820MAX] __initdata; - struct xen_memory_map memmap; int i; int rc; memmap.nr_entries = E820MAX; - set_xen_guest_handle(memmap.buffer, map); + set_xen_guest_handle(memmap.buffer, xen_e820_map); rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap); if (rc < 0) panic("No memory map (%d)\n", rc); - sanitize_e820_map(map, ARRAY_SIZE(map), &memmap.nr_entries); + xen_e820_map_entries = memmap.nr_entries; + + sanitize_e820_map(xen_e820_map, ARRAY_SIZE(xen_e820_map), + &xen_e820_map_entries); - for (i = 0; i < memmap.nr_entries; i++) - e820_add_region(map[i].addr, map[i].size, map[i].type); + for (i = 0; i < xen_e820_map_entries; i++) + e820_add_region(xen_e820_map[i].addr, xen_e820_map[i].size, + xen_e820_map[i].type); - memblock_reserve(__pa(xen_start_info->mfn_list), - xen_start_info->pt_base - xen_start_info->mfn_list); + /* Remove p2m info, it is not needed. */ + xen_start_info->mfn_list = 0; + xen_start_info->first_p2m_pfn = 0; + xen_start_info->nr_p2m_frames = 0; return "Xen"; } @@ -753,17 +968,8 @@ char * __init xen_auto_xlated_memory_setup(void) static void __init fiddle_vdso(void) { #ifdef CONFIG_X86_32 - /* - * This could be called before selected_vdso32 is initialized, so - * just fiddle with both possible images. vdso_image_32_syscall - * can't be selected, since it only exists on 64-bit systems. - */ - u32 *mask; - mask = vdso_image_32_int80.data + - vdso_image_32_int80.sym_VDSO32_NOTE_MASK; - *mask |= 1 << VDSO_NOTE_NONEGSEG_BIT; - mask = vdso_image_32_sysenter.data + - vdso_image_32_sysenter.sym_VDSO32_NOTE_MASK; + u32 *mask = vdso_image_32.data + + vdso_image_32.sym_VDSO32_NOTE_MASK; *mask |= 1 << VDSO_NOTE_NONEGSEG_BIT; #endif } diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 86484384492e..3f4ebf0261f2 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -26,6 +26,7 @@ #include <xen/interface/xen.h> #include <xen/interface/vcpu.h> +#include <xen/interface/xenpmu.h> #include <asm/xen/interface.h> #include <asm/xen/hypercall.h> @@ -38,6 +39,7 @@ #include "xen-ops.h" #include "mmu.h" #include "smp.h" +#include "pmu.h" cpumask_var_t xen_cpu_initialized_map; @@ -50,6 +52,7 @@ static DEFINE_PER_CPU(struct xen_common_irq, xen_callfunc_irq) = { .irq = -1 }; static DEFINE_PER_CPU(struct xen_common_irq, xen_callfuncsingle_irq) = { .irq = -1 }; static DEFINE_PER_CPU(struct xen_common_irq, xen_irq_work) = { .irq = -1 }; static DEFINE_PER_CPU(struct xen_common_irq, xen_debug_irq) = { .irq = -1 }; +static DEFINE_PER_CPU(struct xen_common_irq, xen_pmu_irq) = { .irq = -1 }; static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id); static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id); @@ -148,11 +151,18 @@ static void xen_smp_intr_free(unsigned int cpu) kfree(per_cpu(xen_irq_work, cpu).name); per_cpu(xen_irq_work, cpu).name = NULL; } + + if (per_cpu(xen_pmu_irq, cpu).irq >= 0) { + unbind_from_irqhandler(per_cpu(xen_pmu_irq, cpu).irq, NULL); + per_cpu(xen_pmu_irq, cpu).irq = -1; + kfree(per_cpu(xen_pmu_irq, cpu).name); + per_cpu(xen_pmu_irq, cpu).name = NULL; + } }; static int xen_smp_intr_init(unsigned int cpu) { int rc; - char *resched_name, *callfunc_name, *debug_name; + char *resched_name, *callfunc_name, *debug_name, *pmu_name; resched_name = kasprintf(GFP_KERNEL, "resched%d", cpu); rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR, @@ -218,6 +228,18 @@ static int xen_smp_intr_init(unsigned int cpu) per_cpu(xen_irq_work, cpu).irq = rc; per_cpu(xen_irq_work, cpu).name = callfunc_name; + if (is_xen_pmu(cpu)) { + pmu_name = kasprintf(GFP_KERNEL, "pmu%d", cpu); + rc = bind_virq_to_irqhandler(VIRQ_XENPMU, cpu, + xen_pmu_irq_handler, + IRQF_PERCPU|IRQF_NOBALANCING, + pmu_name, NULL); + if (rc < 0) + goto fail; + per_cpu(xen_pmu_irq, cpu).irq = rc; + per_cpu(xen_pmu_irq, cpu).name = pmu_name; + } + return 0; fail: @@ -335,6 +357,8 @@ static void __init xen_smp_prepare_cpus(unsigned int max_cpus) } set_cpu_sibling_map(0); + xen_pmu_init(0); + if (xen_smp_intr_init(0)) BUG(); @@ -429,7 +453,7 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) } #endif ctxt->user_regs.esp = idle->thread.sp0 - sizeof(struct pt_regs); - ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_mfn(swapper_pg_dir)); + ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_gfn(swapper_pg_dir)); if (HYPERVISOR_vcpu_op(VCPUOP_initialise, cpu, ctxt)) BUG(); @@ -462,6 +486,8 @@ static int xen_cpu_up(unsigned int cpu, struct task_struct *idle) if (rc) return rc; + xen_pmu_init(cpu); + rc = xen_smp_intr_init(cpu); if (rc) return rc; @@ -503,6 +529,7 @@ static void xen_cpu_die(unsigned int cpu) xen_smp_intr_free(cpu); xen_uninit_lock_cpu(cpu); xen_teardown_timer(cpu); + xen_pmu_finish(cpu); } } diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index 53b4c0811f4f..7f664c416faf 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -1,6 +1,7 @@ #include <linux/types.h> #include <linux/tick.h> +#include <xen/xen.h> #include <xen/interface/xen.h> #include <xen/grant_table.h> #include <xen/events.h> @@ -11,6 +12,7 @@ #include "xen-ops.h" #include "mmu.h" +#include "pmu.h" static void xen_pv_pre_suspend(void) { @@ -32,7 +34,8 @@ static void xen_hvm_post_suspend(int suspend_cancelled) { #ifdef CONFIG_XEN_PVHVM int cpu; - xen_hvm_init_shared_info(); + if (!suspend_cancelled) + xen_hvm_init_shared_info(); xen_callback_vector(); xen_unplug_emulated_devices(); if (xen_feature(XENFEAT_hvm_safe_pvclock)) { @@ -67,16 +70,16 @@ static void xen_pv_post_suspend(int suspend_cancelled) void xen_arch_pre_suspend(void) { - if (xen_pv_domain()) - xen_pv_pre_suspend(); + if (xen_pv_domain()) + xen_pv_pre_suspend(); } void xen_arch_post_suspend(int cancelled) { - if (xen_pv_domain()) - xen_pv_post_suspend(cancelled); - else - xen_hvm_post_suspend(cancelled); + if (xen_pv_domain()) + xen_pv_post_suspend(cancelled); + else + xen_hvm_post_suspend(cancelled); } static void xen_vcpu_notify_restore(void *data) @@ -95,10 +98,20 @@ static void xen_vcpu_notify_suspend(void *data) void xen_arch_resume(void) { + int cpu; + on_each_cpu(xen_vcpu_notify_restore, NULL, 1); + + for_each_online_cpu(cpu) + xen_pmu_init(cpu); } void xen_arch_suspend(void) { + int cpu; + + for_each_online_cpu(cpu) + xen_pmu_finish(cpu); + on_each_cpu(xen_vcpu_notify_suspend, NULL, 1); } diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 55da33b1d51c..a0a4e554c6f1 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -16,6 +16,7 @@ #include <linux/gfp.h> #include <linux/slab.h> #include <linux/pvclock_gtod.h> +#include <linux/timekeeper_internal.h> #include <asm/pvclock.h> #include <asm/xen/hypervisor.h> @@ -32,86 +33,12 @@ #define TIMER_SLOP 100000 #define NS_PER_TICK (1000000000LL / HZ) -/* runstate info updated by Xen */ -static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate); - /* snapshots of runstate info */ static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate_snapshot); /* unused ns of stolen time */ static DEFINE_PER_CPU(u64, xen_residual_stolen); -/* return an consistent snapshot of 64-bit time/counter value */ -static u64 get64(const u64 *p) -{ - u64 ret; - - if (BITS_PER_LONG < 64) { - u32 *p32 = (u32 *)p; - u32 h, l; - - /* - * Read high then low, and then make sure high is - * still the same; this will only loop if low wraps - * and carries into high. - * XXX some clean way to make this endian-proof? - */ - do { - h = p32[1]; - barrier(); - l = p32[0]; - barrier(); - } while (p32[1] != h); - - ret = (((u64)h) << 32) | l; - } else - ret = *p; - - return ret; -} - -/* - * Runstate accounting - */ -static void get_runstate_snapshot(struct vcpu_runstate_info *res) -{ - u64 state_time; - struct vcpu_runstate_info *state; - - BUG_ON(preemptible()); - - state = this_cpu_ptr(&xen_runstate); - - /* - * The runstate info is always updated by the hypervisor on - * the current CPU, so there's no need to use anything - * stronger than a compiler barrier when fetching it. - */ - do { - state_time = get64(&state->state_entry_time); - barrier(); - *res = *state; - barrier(); - } while (get64(&state->state_entry_time) != state_time); -} - -/* return true when a vcpu could run but has no real cpu to run on */ -bool xen_vcpu_stolen(int vcpu) -{ - return per_cpu(xen_runstate, vcpu).state == RUNSTATE_runnable; -} - -void xen_setup_runstate_info(int cpu) -{ - struct vcpu_register_runstate_memory_area area; - - area.addr.v = &per_cpu(xen_runstate, cpu); - - if (HYPERVISOR_vcpu_op(VCPUOP_register_runstate_memory_area, - cpu, &area)) - BUG(); -} - static void do_stolen_accounting(void) { struct vcpu_runstate_info state; @@ -119,7 +46,7 @@ static void do_stolen_accounting(void) s64 runnable, offline, stolen; cputime_t ticks; - get_runstate_snapshot(&state); + xen_get_runstate_snapshot(&state); WARN_ON(state.state != RUNSTATE_running); @@ -194,26 +121,46 @@ static int xen_pvclock_gtod_notify(struct notifier_block *nb, unsigned long was_set, void *priv) { /* Protected by the calling core code serialization */ - static struct timespec next_sync; + static struct timespec64 next_sync; struct xen_platform_op op; - struct timespec now; + struct timespec64 now; + struct timekeeper *tk = priv; + static bool settime64_supported = true; + int ret; - now = __current_kernel_time(); + now.tv_sec = tk->xtime_sec; + now.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); /* * We only take the expensive HV call when the clock was set * or when the 11 minutes RTC synchronization time elapsed. */ - if (!was_set && timespec_compare(&now, &next_sync) < 0) + if (!was_set && timespec64_compare(&now, &next_sync) < 0) return NOTIFY_OK; - op.cmd = XENPF_settime; - op.u.settime.secs = now.tv_sec; - op.u.settime.nsecs = now.tv_nsec; - op.u.settime.system_time = xen_clocksource_read(); +again: + if (settime64_supported) { + op.cmd = XENPF_settime64; + op.u.settime64.mbz = 0; + op.u.settime64.secs = now.tv_sec; + op.u.settime64.nsecs = now.tv_nsec; + op.u.settime64.system_time = xen_clocksource_read(); + } else { + op.cmd = XENPF_settime32; + op.u.settime32.secs = now.tv_sec; + op.u.settime32.nsecs = now.tv_nsec; + op.u.settime32.system_time = xen_clocksource_read(); + } + + ret = HYPERVISOR_platform_op(&op); - (void)HYPERVISOR_dom0_op(&op); + if (ret == -ENOSYS && settime64_supported) { + settime64_supported = false; + goto again; + } + if (ret < 0) + return NOTIFY_BAD; /* * Move the next drift compensation time 11 minutes @@ -274,30 +221,18 @@ static s64 get_abs_timeout(unsigned long delta) return xen_clocksource_read() + delta; } -static void xen_timerop_set_mode(enum clock_event_mode mode, - struct clock_event_device *evt) +static int xen_timerop_shutdown(struct clock_event_device *evt) { - switch (mode) { - case CLOCK_EVT_MODE_PERIODIC: - /* unsupported */ - WARN_ON(1); - break; - - case CLOCK_EVT_MODE_ONESHOT: - case CLOCK_EVT_MODE_RESUME: - break; - - case CLOCK_EVT_MODE_UNUSED: - case CLOCK_EVT_MODE_SHUTDOWN: - HYPERVISOR_set_timer_op(0); /* cancel timeout */ - break; - } + /* cancel timeout */ + HYPERVISOR_set_timer_op(0); + + return 0; } static int xen_timerop_set_next_event(unsigned long delta, struct clock_event_device *evt) { - WARN_ON(evt->mode != CLOCK_EVT_MODE_ONESHOT); + WARN_ON(!clockevent_state_oneshot(evt)); if (HYPERVISOR_set_timer_op(get_abs_timeout(delta)) < 0) BUG(); @@ -310,46 +245,39 @@ static int xen_timerop_set_next_event(unsigned long delta, } static const struct clock_event_device xen_timerop_clockevent = { - .name = "xen", - .features = CLOCK_EVT_FEAT_ONESHOT, + .name = "xen", + .features = CLOCK_EVT_FEAT_ONESHOT, - .max_delta_ns = 0xffffffff, - .min_delta_ns = TIMER_SLOP, + .max_delta_ns = 0xffffffff, + .min_delta_ns = TIMER_SLOP, - .mult = 1, - .shift = 0, - .rating = 500, + .mult = 1, + .shift = 0, + .rating = 500, - .set_mode = xen_timerop_set_mode, - .set_next_event = xen_timerop_set_next_event, + .set_state_shutdown = xen_timerop_shutdown, + .set_next_event = xen_timerop_set_next_event, }; +static int xen_vcpuop_shutdown(struct clock_event_device *evt) +{ + int cpu = smp_processor_id(); + if (HYPERVISOR_vcpu_op(VCPUOP_stop_singleshot_timer, cpu, NULL) || + HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL)) + BUG(); -static void xen_vcpuop_set_mode(enum clock_event_mode mode, - struct clock_event_device *evt) + return 0; +} + +static int xen_vcpuop_set_oneshot(struct clock_event_device *evt) { int cpu = smp_processor_id(); - switch (mode) { - case CLOCK_EVT_MODE_PERIODIC: - WARN_ON(1); /* unsupported */ - break; - - case CLOCK_EVT_MODE_ONESHOT: - if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL)) - BUG(); - break; + if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL)) + BUG(); - case CLOCK_EVT_MODE_UNUSED: - case CLOCK_EVT_MODE_SHUTDOWN: - if (HYPERVISOR_vcpu_op(VCPUOP_stop_singleshot_timer, cpu, NULL) || - HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL)) - BUG(); - break; - case CLOCK_EVT_MODE_RESUME: - break; - } + return 0; } static int xen_vcpuop_set_next_event(unsigned long delta, @@ -359,7 +287,7 @@ static int xen_vcpuop_set_next_event(unsigned long delta, struct vcpu_set_singleshot_timer single; int ret; - WARN_ON(evt->mode != CLOCK_EVT_MODE_ONESHOT); + WARN_ON(!clockevent_state_oneshot(evt)); single.timeout_abs_ns = get_abs_timeout(delta); single.flags = VCPU_SSHOTTMR_future; @@ -382,7 +310,8 @@ static const struct clock_event_device xen_vcpuop_clockevent = { .shift = 0, .rating = 500, - .set_mode = xen_vcpuop_set_mode, + .set_state_shutdown = xen_vcpuop_shutdown, + .set_state_oneshot = xen_vcpuop_set_oneshot, .set_next_event = xen_vcpuop_set_next_event, }; diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S index fd92a64d748e..feb6d40a0860 100644 --- a/arch/x86/xen/xen-asm_32.S +++ b/arch/x86/xen/xen-asm_32.S @@ -35,20 +35,6 @@ check_events: ret /* - * We can't use sysexit directly, because we're not running in ring0. - * But we can easily fake it up using iret. Assuming xen_sysexit is - * jumped to with a standard stack frame, we can just strip it back to - * a standard iret frame and use iret. - */ -ENTRY(xen_sysexit) - movl PT_EAX(%esp), %eax /* Shouldn't be necessary? */ - orl $X86_EFLAGS_IF, PT_EFLAGS(%esp) - lea PT_EIP(%esp), %esp - - jmp xen_iret -ENDPROC(xen_sysexit) - -/* * This is run where a normal iret would be run, with the same stack setup: * 8: eflags * 4: cs diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S index f22667abf7b9..cc8acc410ddb 100644 --- a/arch/x86/xen/xen-asm_64.S +++ b/arch/x86/xen/xen-asm_64.S @@ -68,25 +68,6 @@ ENTRY(xen_sysret64) ENDPATCH(xen_sysret64) RELOC(xen_sysret64, 1b+1) -ENTRY(xen_sysret32) - /* - * 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(cpu_current_top_of_stack), %rsp - - pushq $__USER32_DS - pushq PER_CPU_VAR(rsp_scratch) - pushq %r11 - pushq $__USER32_CS - pushq %rcx - - pushq $0 -1: jmp hypercall_iret -ENDPATCH(xen_sysret32) -RELOC(xen_sysret32, 1b+1) - /* * Xen handles syscall callbacks much like ordinary exceptions, which * means we have: diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 8afdfccf6086..b65f59a358a2 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -104,6 +104,8 @@ ENTRY(hypercall_page) ELFNOTE(Xen, XEN_ELFNOTE_VIRT_BASE, _ASM_PTR __PAGE_OFFSET) #else ELFNOTE(Xen, XEN_ELFNOTE_VIRT_BASE, _ASM_PTR __START_KERNEL_map) + /* Map the p2m table to a 512GB-aligned user address. */ + ELFNOTE(Xen, XEN_ELFNOTE_INIT_P2M, .quad PGDIR_SIZE) #endif ELFNOTE(Xen, XEN_ELFNOTE_ENTRY, _ASM_PTR startup_xen) ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, _ASM_PTR hypercall_page) diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 2292721b1d10..4140b070f2e9 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -35,13 +35,20 @@ void xen_build_mfn_list_list(void); void xen_setup_machphys_mapping(void); void xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn); void xen_reserve_top(void); +void __init xen_reserve_special_pages(void); +void __init xen_pt_check_e820(void); void xen_mm_pin_all(void); void xen_mm_unpin_all(void); +#ifdef CONFIG_X86_64 +void __init xen_relocate_p2m(void); +#endif +bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size); unsigned long __ref xen_chk_extra_mem(unsigned long pfn); void __init xen_inv_extra_mem(void); void __init xen_remap_memory(void); +phys_addr_t __init xen_find_free_area(phys_addr_t size); char * __init xen_memory_setup(void); char * xen_auto_xlated_memory_setup(void); void __init xen_arch_setup(void); @@ -132,9 +139,6 @@ 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); |