diff options
| author | Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> | 2012-04-18 15:52:50 -0400 |
|---|---|---|
| committer | Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> | 2012-04-18 15:52:50 -0400 |
| commit | 681e4a5e13c1c8315694eb4f44e0cdd84c9082d2 (patch) | |
| tree | 699f14527c118859026e8ce0214e689d0b9c88cb /arch/x86 | |
| parent | b960d6c43a63ebd2d8518b328da3816b833ee8cc (diff) | |
| parent | c104f1fa1ecf4ee0fc06e31b1f77630b2551be81 (diff) | |
Merge commit 'c104f1fa1ecf4ee0fc06e31b1f77630b2551be81' into stable/for-linus-3.4
* commit 'c104f1fa1ecf4ee0fc06e31b1f77630b2551be81': (14566 commits)
cpufreq: OMAP: fix build errors: depends on ARCH_OMAP2PLUS
sparc64: Eliminate obsolete __handle_softirq() function
sparc64: Fix bootup crash on sun4v.
kconfig: delete last traces of __enabled_ from autoconf.h
Revert "kconfig: fix __enabled_ macros definition for invisible and un-selected symbols"
kconfig: fix IS_ENABLED to not require all options to be defined
irq_domain: fix type mismatch in debugfs output format
staging: android: fix mem leaks in __persistent_ram_init()
staging: vt6656: Don't leak memory in drivers/staging/vt6656/ioctl.c::private_ioctl()
staging: iio: hmc5843: Fix crash in probe function.
panic: fix stack dump print on direct call to panic()
drivers/rtc/rtc-pl031.c: enable clock on all ST variants
Revert "mm: vmscan: fix misused nr_reclaimed in shrink_mem_cgroup_zone()"
hugetlb: fix race condition in hugetlb_fault()
drivers/rtc/rtc-twl.c: use static register while reading time
drivers/rtc/rtc-s3c.c: add placeholder for driver private data
drivers/rtc/rtc-s3c.c: fix compilation error
MAINTAINERS: add PCDP console maintainer
memcg: do not open code accesses to res_counter members
drivers/rtc/rtc-efi.c: fix section mismatch warning
...
Diffstat (limited to 'arch/x86')
335 files changed, 14199 insertions, 7926 deletions
diff --git a/arch/x86/.gitignore b/arch/x86/.gitignore index 028079065af..7cab8c08e6d 100644 --- a/arch/x86/.gitignore +++ b/arch/x86/.gitignore @@ -1,3 +1,4 @@ boot/compressed/vmlinux tools/test_get_len +tools/insn_sanity diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 1a31254ceb8..1d14cc6b79a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -60,13 +60,15 @@ config X86 select PERF_EVENTS select HAVE_PERF_EVENTS_NMI select ANON_INODES + select HAVE_ALIGNED_STRUCT_PAGE if SLUB && !M386 + select HAVE_CMPXCHG_LOCAL if !M386 + select HAVE_CMPXCHG_DOUBLE select HAVE_ARCH_KMEMCHECK select HAVE_USER_RETURN_NOTIFIER select ARCH_BINFMT_ELF_RANDOMIZE_PIE select HAVE_ARCH_JUMP_LABEL select HAVE_TEXT_POKE_SMP select HAVE_GENERIC_HARDIRQS - select HAVE_SPARSE_IRQ select SPARSE_IRQ select GENERIC_FIND_FIRST_BIT select GENERIC_IRQ_PROBE @@ -79,6 +81,7 @@ config X86 select CLKEVT_I8253 select ARCH_HAVE_NMI_SAFE_CMPXCHG select GENERIC_IOMAP + select DCACHE_WORD_ACCESS if !DEBUG_PAGEALLOC config INSTRUCTION_DECODER def_bool (KPROBES || PERF_EVENTS) @@ -122,16 +125,6 @@ config HAVE_LATENCYTOP_SUPPORT config MMU def_bool y -config ZONE_DMA - bool "DMA memory allocation support" if EXPERT - default y - help - DMA memory allocation support allows devices with less than 32-bit - addressing to allocate within the first 16MB of address space. - Disable if no such devices will be used. - - If unsure, say Y. - config SBUS bool @@ -186,6 +179,9 @@ config ARCH_HAS_DEFAULT_IDLE config ARCH_HAS_CACHE_LINE_SIZE def_bool y +config ARCH_HAS_CPU_AUTOPROBE + def_bool y + config HAVE_SETUP_PER_CPU_AREA def_bool y @@ -252,6 +248,16 @@ source "kernel/Kconfig.freezer" menu "Processor type and features" +config ZONE_DMA + bool "DMA memory allocation support" if EXPERT + default y + help + DMA memory allocation support allows devices with less than 32-bit + addressing to allocate within the first 16MB of address space. + Disable if no such devices will be used. + + If unsure, say Y. + source "kernel/time/Kconfig" config SMP @@ -357,7 +363,6 @@ config X86_NUMACHIP depends on NUMA depends on SMP depends on X86_X2APIC - depends on !EDAC_AMD64 ---help--- Adds support for Numascale NumaChip large-SMP systems. Needed to enable more than ~168 cores. @@ -396,6 +401,7 @@ config X86_INTEL_CE select X86_REBOOTFIXUPS select OF select OF_EARLY_FLATTREE + select IRQ_DOMAIN ---help--- Select for the Intel CE media processor (CE4100) SOC. This option compiles in support for the CE4100 SOC for settop @@ -415,23 +421,25 @@ if X86_WANT_INTEL_MID config X86_INTEL_MID bool -config X86_MRST - bool "Moorestown MID platform" +config X86_MDFLD + bool "Medfield MID platform" depends on PCI depends on PCI_GOANY depends on X86_IO_APIC + select X86_INTEL_MID + select SFI + select DW_APB_TIMER select APB_TIMER select I2C select SPI select INTEL_SCU_IPC select X86_PLATFORM_DEVICES - select X86_INTEL_MID + select MFD_INTEL_MSIC ---help--- - Moorestown is Intel's Low Power Intel Architecture (LPIA) based Moblin - Internet Device(MID) platform. Moorestown consists of two chips: - Lincroft (CPU core, graphics, and memory controller) and Langwell IOH. - Unlike standard x86 PCs, Moorestown does not have many legacy devices - nor standard legacy replacement devices/features. e.g. Moorestown does + Medfield is Intel's Low Power Intel Architecture (LPIA) based Moblin + Internet Device(MID) platform. + Unlike standard x86 PCs, Medfield does not have many legacy devices + nor standard legacy replacement devices/features. e.g. Medfield does not contain i8259, i8254, HPET, legacy BIOS, most of the io ports. endif @@ -631,7 +639,7 @@ config X86_SUMMIT_NUMA config X86_CYCLONE_TIMER def_bool y - depends on X86_32_NON_STANDARD + depends on X86_SUMMIT source "arch/x86/Kconfig.cpu" @@ -659,9 +667,10 @@ config HPET_EMULATE_RTC depends on HPET_TIMER && (RTC=y || RTC=m || RTC_DRV_CMOS=m || RTC_DRV_CMOS=y) config APB_TIMER - def_bool y if MRST - prompt "Langwell APB Timer Support" if X86_MRST + def_bool y if X86_INTEL_MID + prompt "Intel MID APB Timer Support" if X86_INTEL_MID select DW_APB_TIMER + depends on X86_INTEL_MID && SFI help APB timer is the replacement for 8254, HPET on X86 MID platforms. The APBT provides a stable time base on SMP @@ -1489,6 +1498,13 @@ config EFI resultant kernel should continue to boot on existing non-EFI platforms. +config EFI_STUB + bool "EFI stub support" + depends on EFI + ---help--- + This kernel feature allows a bzImage to be loaded directly + by EFI firmware without the use of a bootloader. + config SECCOMP def_bool y prompt "Enable seccomp to safely compute untrusted bytecode" @@ -2044,6 +2060,7 @@ config OLPC select GPIOLIB select OF select OF_PROMTREE + select IRQ_DOMAIN ---help--- Add support for detecting the unique features of the OLPC XO hardware. @@ -2101,6 +2118,19 @@ config ALIX Note: You have to set alix.force=1 for boards with Award BIOS. +config NET5501 + bool "Soekris Engineering net5501 System Support (LEDS, GPIO, etc)" + select GPIOLIB + ---help--- + This option enables system support for the Soekris Engineering net5501. + +config GEOS + bool "Traverse Technologies GEOS System Support (LEDS, GPIO, etc)" + select GPIOLIB + depends on DMI + ---help--- + This option enables system support for the Traverse Technologies GEOS. + endif # X86_32 config AMD_NB @@ -2133,9 +2163,9 @@ config IA32_EMULATION depends on X86_64 select COMPAT_BINFMT_ELF ---help--- - Include code to run 32-bit programs under a 64-bit kernel. You should - likely turn this on, unless you're 100% sure that you don't have any - 32-bit programs left. + Include code to run legacy 32-bit programs under a + 64-bit kernel. You should likely turn this on, unless you're + 100% sure that you don't have any 32-bit programs left. config IA32_AOUT tristate "IA32 a.out support" @@ -2143,9 +2173,23 @@ config IA32_AOUT ---help--- Support old a.out binaries in the 32bit emulation. +config X86_X32 + bool "x32 ABI for 64-bit mode (EXPERIMENTAL)" + depends on X86_64 && IA32_EMULATION && EXPERIMENTAL + ---help--- + Include code to run binaries for the x32 native 32-bit ABI + for 64-bit processors. An x32 process gets access to the + full 64-bit register file and wide data path while leaving + pointers at 32 bits for smaller memory footprint. + + You will need a recent binutils (2.22 or later) with + elf32_x86_64 support enabled to compile a kernel with this + option set. + config COMPAT def_bool y - depends on IA32_EMULATION + depends on IA32_EMULATION || X86_X32 + select ARCH_WANT_OLD_COMPAT_IPC config COMPAT_FOR_U64_ALIGNMENT def_bool COMPAT diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index e3ca7e0d858..706e12e9984 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -303,18 +303,11 @@ config X86_GENERIC config X86_INTERNODE_CACHE_SHIFT int default "12" if X86_VSMP - default "7" if NUMA default X86_L1_CACHE_SHIFT config X86_CMPXCHG def_bool X86_64 || (X86_32 && !M386) -config CMPXCHG_LOCAL - def_bool X86_64 || (X86_32 && !M386) - -config CMPXCHG_DOUBLE - def_bool y - config X86_L1_CACHE_SHIFT int default "7" if MPENTIUM4 || MPSC @@ -447,7 +440,7 @@ config CPU_SUP_INTEL config CPU_SUP_CYRIX_32 default y bool "Support Cyrix processors" if PROCESSOR_SELECT - depends on !64BIT + depends on M386 || M486 || M586 || M586TSC || M586MMX || (EXPERT && !64BIT) ---help--- This enables detection, tunings and quirks for Cyrix processors @@ -501,7 +494,7 @@ config CPU_SUP_TRANSMETA_32 config CPU_SUP_UMC_32 default y bool "Support UMC processors" if PROCESSOR_SELECT - depends on !64BIT + depends on M386 || M486 || (EXPERT && !64BIT) ---help--- This enables detection, tunings and quirks for UMC processors diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index bf56e179327..e46c2147397 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -43,9 +43,9 @@ config EARLY_PRINTK with klogd/syslogd or the X server. You should normally N here, unless you want to debug such a crash. -config EARLY_PRINTK_MRST - bool "Early printk for MRST platform support" - depends on EARLY_PRINTK && X86_MRST +config EARLY_PRINTK_INTEL_MID + bool "Early printk for Intel MID platform support" + depends on EARLY_PRINTK && X86_INTEL_MID config EARLY_PRINTK_DBGP bool "Early printk via EHCI debug port" @@ -63,8 +63,11 @@ config DEBUG_STACKOVERFLOW bool "Check for stack overflows" depends on DEBUG_KERNEL ---help--- - This option will cause messages to be printed if free stack space - drops below a certain limit. + Say Y here if you want to check the overflows of kernel, IRQ + and exception stacks. This option will cause messages of the + stacks in detail when free stack space drops below a certain + limit. + If in doubt, say "N". config X86_PTDUMP bool "Export kernel pagetable layout to userspace via debugfs" @@ -284,4 +287,16 @@ config DEBUG_STRICT_USER_COPY_CHECKS If unsure, or if you run an older (pre 4.4) gcc, say N. +config DEBUG_NMI_SELFTEST + bool "NMI Selftest" + depends on DEBUG_KERNEL && X86_LOCAL_APIC + ---help--- + Enabling this option turns on a quick NMI selftest to verify + that the NMI behaves correctly. + + This might help diagnose strange hangs that rely on NMI to + function properly. + + If unsure, say N. + endmenu diff --git a/arch/x86/Makefile b/arch/x86/Makefile index b02e509072a..41a7237606a 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -82,6 +82,22 @@ ifdef CONFIG_CC_STACKPROTECTOR endif endif +ifdef CONFIG_X86_X32 + x32_ld_ok := $(call try-run,\ + /bin/echo -e '1: .quad 1b' | \ + $(CC) $(KBUILD_AFLAGS) -c -xassembler -o "$$TMP" - && \ + $(OBJCOPY) -O elf32-x86-64 "$$TMP" "$$TMPO" && \ + $(LD) -m elf32_x86_64 "$$TMPO" -o "$$TMP",y,n) + ifeq ($(x32_ld_ok),y) + CONFIG_X86_X32_ABI := y + KBUILD_AFLAGS += -DCONFIG_X86_X32_ABI + KBUILD_CFLAGS += -DCONFIG_X86_X32_ABI + else + $(warning CONFIG_X86_X32 enabled but no binutils support) + endif +endif +export CONFIG_X86_X32_ABI + # Don't unroll struct assignments with kmemcheck enabled ifeq ($(CONFIG_KMEMCHECK),y) KBUILD_CFLAGS += $(call cc-option,-fno-builtin-memcpy) @@ -113,11 +129,18 @@ KBUILD_CFLAGS += -Wno-sign-compare KBUILD_CFLAGS += -fno-asynchronous-unwind-tables # prevent gcc from generating any FP code by mistake KBUILD_CFLAGS += $(call cc-option,-mno-sse -mno-mmx -mno-sse2 -mno-3dnow,) +KBUILD_CFLAGS += $(call cc-option,-mno-avx,) KBUILD_CFLAGS += $(mflags-y) KBUILD_AFLAGS += $(mflags-y) ### +# Syscall table generation + +archheaders: + $(Q)$(MAKE) $(build)=arch/x86/syscalls all + +### # Kernel objects head-y := arch/x86/kernel/head_$(BITS).o diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um index 36ddec6a41c..36b62bc5263 100644 --- a/arch/x86/Makefile.um +++ b/arch/x86/Makefile.um @@ -8,15 +8,14 @@ ELF_ARCH := i386 ELF_FORMAT := elf32-i386 CHECKFLAGS += -D__i386__ -ifeq ("$(origin SUBARCH)", "command line") -ifneq ("$(shell uname -m | sed -e s/i.86/i386/)", "$(SUBARCH)") KBUILD_CFLAGS += $(call cc-option,-m32) KBUILD_AFLAGS += $(call cc-option,-m32) LINK-y += $(call cc-option,-m32) export LDFLAGS -endif -endif + +LDS_EXTRA := -Ui386 +export LDS_EXTRA # First of all, tune CFLAGS for the specific CPU. This actually sets cflags-y. include $(srctree)/arch/x86/Makefile_32.cpu diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 95365a82b6a..5a747dd884d 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -37,7 +37,8 @@ setup-y += video-bios.o targets += $(setup-y) hostprogs-y := mkcpustr tools/build -HOST_EXTRACFLAGS += $(LINUXINCLUDE) +HOST_EXTRACFLAGS += -I$(srctree)/tools/include $(LINUXINCLUDE) \ + -D__EXPORTED_HEADERS__ $(obj)/cpu.o: $(obj)/cpustr.h diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index c7093bd9f2d..18997e5a105 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -67,7 +67,7 @@ static inline void outl(u32 v, u16 port) { asm volatile("outl %0,%1" : : "a" (v), "dN" (port)); } -static inline u32 inl(u32 port) +static inline u32 inl(u16 port) { u32 v; asm volatile("inl %1,%0" : "=a" (v) : "dN" (port)); diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 09664efb9ce..fd55a2ff3ad 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -22,8 +22,17 @@ LDFLAGS := -m elf_$(UTS_MACHINE) LDFLAGS_vmlinux := -T hostprogs-y := mkpiggy +HOST_EXTRACFLAGS += -I$(srctree)/tools/include -$(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o $(obj)/string.o $(obj)/cmdline.o $(obj)/early_serial_console.o $(obj)/piggy.o FORCE +VMLINUX_OBJS = $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \ + $(obj)/string.o $(obj)/cmdline.o $(obj)/early_serial_console.o \ + $(obj)/piggy.o + +ifeq ($(CONFIG_EFI_STUB), y) + VMLINUX_OBJS += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o +endif + +$(obj)/vmlinux: $(VMLINUX_OBJS) FORCE $(call if_changed,ld) @: diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c new file mode 100644 index 00000000000..0cdfc0d2315 --- /dev/null +++ b/arch/x86/boot/compressed/eboot.c @@ -0,0 +1,1022 @@ +/* ----------------------------------------------------------------------- + * + * Copyright 2011 Intel Corporation; author Matt Fleming + * + * This file is part of the Linux kernel, and is made available under + * the terms of the GNU General Public License version 2. + * + * ----------------------------------------------------------------------- */ + +#include <linux/efi.h> +#include <asm/efi.h> +#include <asm/setup.h> +#include <asm/desc.h> + +#include "eboot.h" + +static efi_system_table_t *sys_table; + +static efi_status_t __get_map(efi_memory_desc_t **map, unsigned long *map_size, + unsigned long *desc_size) +{ + efi_memory_desc_t *m = NULL; + efi_status_t status; + unsigned long key; + u32 desc_version; + + *map_size = sizeof(*m) * 32; +again: + /* + * Add an additional efi_memory_desc_t because we're doing an + * allocation which may be in a new descriptor region. + */ + *map_size += sizeof(*m); + status = efi_call_phys3(sys_table->boottime->allocate_pool, + EFI_LOADER_DATA, *map_size, (void **)&m); + if (status != EFI_SUCCESS) + goto fail; + + status = efi_call_phys5(sys_table->boottime->get_memory_map, map_size, + m, &key, desc_size, &desc_version); + if (status == EFI_BUFFER_TOO_SMALL) { + efi_call_phys1(sys_table->boottime->free_pool, m); + goto again; + } + + if (status != EFI_SUCCESS) + efi_call_phys1(sys_table->boottime->free_pool, m); + +fail: + *map = m; + return status; +} + +/* + * Allocate at the highest possible address that is not above 'max'. + */ +static efi_status_t high_alloc(unsigned long size, unsigned long align, + unsigned long *addr, unsigned long max) +{ + unsigned long map_size, desc_size; + efi_memory_desc_t *map; + efi_status_t status; + unsigned long nr_pages; + u64 max_addr = 0; + int i; + + status = __get_map(&map, &map_size, &desc_size); + if (status != EFI_SUCCESS) + goto fail; + + nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE; +again: + for (i = 0; i < map_size / desc_size; i++) { + efi_memory_desc_t *desc; + unsigned long m = (unsigned long)map; + u64 start, end; + + desc = (efi_memory_desc_t *)(m + (i * desc_size)); + if (desc->type != EFI_CONVENTIONAL_MEMORY) + continue; + + if (desc->num_pages < nr_pages) + continue; + + start = desc->phys_addr; + end = start + desc->num_pages * (1UL << EFI_PAGE_SHIFT); + + if ((start + size) > end || (start + size) > max) + continue; + + if (end - size > max) + end = max; + + if (round_down(end - size, align) < start) + continue; + + start = round_down(end - size, align); + + /* + * Don't allocate at 0x0. It will confuse code that + * checks pointers against NULL. + */ + if (start == 0x0) + continue; + + if (start > max_addr) + max_addr = start; + } + + if (!max_addr) + status = EFI_NOT_FOUND; + else { + status = efi_call_phys4(sys_table->boottime->allocate_pages, + EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA, + nr_pages, &max_addr); + if (status != EFI_SUCCESS) { + max = max_addr; + max_addr = 0; + goto again; + } + + *addr = max_addr; + } + +free_pool: + efi_call_phys1(sys_table->boottime->free_pool, map); + +fail: + return status; +} + +/* + * Allocate at the lowest possible address. + */ +static efi_status_t low_alloc(unsigned long size, unsigned long align, + unsigned long *addr) +{ + unsigned long map_size, desc_size; + efi_memory_desc_t *map; + efi_status_t status; + unsigned long nr_pages; + int i; + + status = __get_map(&map, &map_size, &desc_size); + if (status != EFI_SUCCESS) + goto fail; + + nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE; + for (i = 0; i < map_size / desc_size; i++) { + efi_memory_desc_t *desc; + unsigned long m = (unsigned long)map; + u64 start, end; + + desc = (efi_memory_desc_t *)(m + (i * desc_size)); + + if (desc->type != EFI_CONVENTIONAL_MEMORY) + continue; + + if (desc->num_pages < nr_pages) + continue; + + start = desc->phys_addr; + end = start + desc->num_pages * (1UL << EFI_PAGE_SHIFT); + + /* + * Don't allocate at 0x0. It will confuse code that + * checks pointers against NULL. Skip the first 8 + * bytes so we start at a nice even number. + */ + if (start == 0x0) + start += 8; + + start = round_up(start, align); + if ((start + size) > end) + continue; + + status = efi_call_phys4(sys_table->boottime->allocate_pages, + EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA, + nr_pages, &start); + if (status == EFI_SUCCESS) { + *addr = start; + break; + } + } + + if (i == map_size / desc_size) + status = EFI_NOT_FOUND; + +free_pool: + efi_call_phys1(sys_table->boottime->free_pool, map); +fail: + return status; +} + +static void low_free(unsigned long size, unsigned long addr) +{ + unsigned long nr_pages; + + nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE; + efi_call_phys2(sys_table->boottime->free_pages, addr, size); +} + +static void find_bits(unsigned long mask, u8 *pos, u8 *size) +{ + u8 first, len; + + first = 0; + len = 0; + + if (mask) { + while (!(mask & 0x1)) { + mask = mask >> 1; + first++; + } + + while (mask & 0x1) { + mask = mask >> 1; + len++; + } + } + + *pos = first; + *size = len; +} + +/* + * See if we have Graphics Output Protocol + */ +static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto, + unsigned long size) +{ + struct efi_graphics_output_protocol *gop, *first_gop; + struct efi_pixel_bitmask pixel_info; + unsigned long nr_gops; + efi_status_t status; + void **gop_handle; + u16 width, height; + u32 fb_base, fb_size; + u32 pixels_per_scan_line; + int pixel_format; + int i; + + status = efi_call_phys3(sys_table->boottime->allocate_pool, + EFI_LOADER_DATA, size, &gop_handle); + if (status != EFI_SUCCESS) + return status; + + status = efi_call_phys5(sys_table->boottime->locate_handle, + EFI_LOCATE_BY_PROTOCOL, proto, + NULL, &size, gop_handle); + if (status != EFI_SUCCESS) + goto free_handle; + + first_gop = NULL; + + nr_gops = size / sizeof(void *); + for (i = 0; i < nr_gops; i++) { + struct efi_graphics_output_mode_info *info; + efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID; + void *pciio; + void *h = gop_handle[i]; + + status = efi_call_phys3(sys_table->boottime->handle_protocol, + h, proto, &gop); + if (status != EFI_SUCCESS) + continue; + + efi_call_phys3(sys_table->boottime->handle_protocol, + h, &pciio_proto, &pciio); + + status = efi_call_phys4(gop->query_mode, gop, + gop->mode->mode, &size, &info); + if (status == EFI_SUCCESS && (!first_gop || pciio)) { + /* + * Apple provide GOPs that are not backed by + * real hardware (they're used to handle + * multiple displays). The workaround is to + * search for a GOP implementing the PCIIO + * protocol, and if one isn't found, to just + * fallback to the first GOP. + */ + width = info->horizontal_resolution; + height = info->vertical_resolution; + fb_base = gop->mode->frame_buffer_base; + fb_size = gop->mode->frame_buffer_size; + pixel_format = info->pixel_format; + pixel_info = info->pixel_information; + pixels_per_scan_line = info->pixels_per_scan_line; + + /* + * Once we've found a GOP supporting PCIIO, + * don't bother looking any further. + */ + if (pciio) + break; + + first_gop = gop; + } + } + + /* Did we find any GOPs? */ + if (!first_gop) + goto free_handle; + + /* EFI framebuffer */ + si->orig_video_isVGA = VIDEO_TYPE_EFI; + + si->lfb_width = width; + si->lfb_height = height; + si->lfb_base = fb_base; + si->lfb_size = fb_size; + si->pages = 1; + + if (pixel_format == PIXEL_RGB_RESERVED_8BIT_PER_COLOR) { + si->lfb_depth = 32; + si->lfb_linelength = pixels_per_scan_line * 4; + si->red_size = 8; + si->red_pos = 0; + si->green_size = 8; + si->green_pos = 8; + si->blue_size = 8; + si->blue_pos = 16; + si->rsvd_size = 8; + si->rsvd_pos = 24; + } else if (pixel_format == PIXEL_BGR_RESERVED_8BIT_PER_COLOR) { + si->lfb_depth = 32; + si->lfb_linelength = pixels_per_scan_line * 4; + si->red_size = 8; + si->red_pos = 16; + si->green_size = 8; + si->green_pos = 8; + si->blue_size = 8; + si->blue_pos = 0; + si->rsvd_size = 8; + si->rsvd_pos = 24; + } else if (pixel_format == PIXEL_BIT_MASK) { + find_bits(pixel_info.red_mask, &si->red_pos, &si->red_size); + find_bits(pixel_info.green_mask, &si->green_pos, + &si->green_size); + find_bits(pixel_info.blue_mask, &si->blue_pos, &si->blue_size); + find_bits(pixel_info.reserved_mask, &si->rsvd_pos, + &si->rsvd_size); + si->lfb_depth = si->red_size + si->green_size + + si->blue_size + si->rsvd_size; + si->lfb_linelength = (pixels_per_scan_line * si->lfb_depth) / 8; + } else { + si->lfb_depth = 4; + si->lfb_linelength = si->lfb_width / 2; + si->red_size = 0; + si->red_pos = 0; + si->green_size = 0; + si->green_pos = 0; + si->blue_size = 0; + si->blue_pos = 0; + si->rsvd_size = 0; + si->rsvd_pos = 0; + } + +free_handle: + efi_call_phys1(sys_table->boottime->free_pool, gop_handle); + return status; +} + +/* + * See if we have Universal Graphics Adapter (UGA) protocol + */ +static efi_status_t setup_uga(struct screen_info *si, efi_guid_t *uga_proto, + unsigned long size) +{ + struct efi_uga_draw_protocol *uga, *first_uga; + unsigned long nr_ugas; + efi_status_t status; + u32 width, height; + void **uga_handle = NULL; + int i; + + status = efi_call_phys3(sys_table->boottime->allocate_pool, + EFI_LOADER_DATA, size, &uga_handle); + if (status != EFI_SUCCESS) + return status; + + status = efi_call_phys5(sys_table->boottime->locate_handle, + EFI_LOCATE_BY_PROTOCOL, uga_proto, + NULL, &size, uga_handle); + if (status != EFI_SUCCESS) + goto free_handle; + + first_uga = NULL; + + nr_ugas = size / sizeof(void *); + for (i = 0; i < nr_ugas; i++) { + efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID; + void *handle = uga_handle[i]; + u32 w, h, depth, refresh; + void *pciio; + + status = efi_call_phys3(sys_table->boottime->handle_protocol, + handle, uga_proto, &uga); + if (status != EFI_SUCCESS) + continue; + + efi_call_phys3(sys_table->boottime->handle_protocol, + handle, &pciio_proto, &pciio); + + status = efi_call_phys5(uga->get_mode, uga, &w, &h, + &depth, &refresh); + if (status == EFI_SUCCESS && (!first_uga || pciio)) { + width = w; + height = h; + + /* + * Once we've found a UGA supporting PCIIO, + * don't bother looking any further. + */ + if (pciio) + break; + + first_uga = uga; + } + } + + if (!first_uga) + goto free_handle; + + /* EFI framebuffer */ + si->orig_video_isVGA = VIDEO_TYPE_EFI; + + si->lfb_depth = 32; + si->lfb_width = width; + si->lfb_height = height; + + si->red_size = 8; + si->red_pos = 16; + si->green_size = 8; + si->green_pos = 8; + si->blue_size = 8; + si->blue_pos = 0; + si->rsvd_size = 8; + si->rsvd_pos = 24; + + +free_handle: + efi_call_phys1(sys_table->boottime->free_pool, uga_handle); + return status; +} + +void setup_graphics(struct boot_params *boot_params) +{ + efi_guid_t graphics_proto = EFI_GRAPHICS_OUTPUT_PROTOCOL_GUID; + struct screen_info *si; + efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID; + efi_status_t status; + unsigned long size; + void **gop_handle = NULL; + void **uga_handle = NULL; + + si = &boot_params->screen_info; + memset(si, 0, sizeof(*si)); + + size = 0; + status = efi_call_phys5(sys_table->boottime->locate_handle, + EFI_LOCATE_BY_PROTOCOL, &graphics_proto, + NULL, &size, gop_handle); + if (status == EFI_BUFFER_TOO_SMALL) + status = setup_gop(si, &graphics_proto, size); + + if (status != EFI_SUCCESS) { + size = 0; + status = efi_call_phys5(sys_table->boottime->locate_handle, + EFI_LOCATE_BY_PROTOCOL, &uga_proto, + NULL, &size, uga_handle); + if (status == EFI_BUFFER_TOO_SMALL) + setup_uga(si, &uga_proto, size); + } +} + +struct initrd { + efi_file_handle_t *handle; + u64 size; +}; + +/* + * Check the cmdline for a LILO-style initrd= arguments. + * + * We only support loading an initrd from the same filesystem as the + * kernel image. + */ +static efi_status_t handle_ramdisks(efi_loaded_image_t *image, + struct setup_header *hdr) +{ + struct initrd *initrds; + unsigned long initrd_addr; + efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID; + u64 initrd_total; + efi_file_io_interface_t *io; + efi_file_handle_t *fh; + efi_status_t status; + int nr_initrds; + char *str; + int i, j, k; + + initrd_addr = 0; + initrd_total = 0; + + str = (char *)(unsigned long)hdr->cmd_line_ptr; + + j = 0; /* See close_handles */ + + if (!str || !*str) + return EFI_SUCCESS; + + for (nr_initrds = 0; *str; nr_initrds++) { + str = strstr(str, "initrd="); + if (!str) + break; + + str += 7; + + /* Skip any leading slashes */ + while (*str == '/' || *str == '\\') + str++; + + while (*str && *str != ' ' && *str != '\n') + str++; + } + + if (!nr_initrds) + return EFI_SUCCESS; + + status = efi_call_phys3(sys_table->boottime->allocate_pool, + EFI_LOADER_DATA, + nr_initrds * sizeof(*initrds), + &initrds); + if (status != EFI_SUCCESS) + goto fail; + + str = (char *)(unsigned long)hdr->cmd_line_ptr; + for (i = 0; i < nr_initrds; i++) { + struct initrd *initrd; + efi_file_handle_t *h; + efi_file_info_t *info; + efi_char16_t filename_16[256]; + unsigned long info_sz; + efi_guid_t info_guid = EFI_FILE_INFO_ID; + efi_char16_t *p; + u64 file_sz; + + str = strstr(str, "initrd="); + if (!str) + break; + + str += 7; + + initrd = &initrds[i]; + p = filename_16; + + /* Skip any leading slashes */ + while (*str == '/' || *str == '\\') + str++; + + while (*str && *str != ' ' && *str != '\n') { + if ((u8 *)p >= (u8 *)filename_16 + sizeof(filename_16)) + break; + + *p++ = *str++; + } + + *p = '\0'; + + /* Only open the volume once. */ + if (!i) { + efi_boot_services_t *boottime; + + boottime = sys_table->boottime; + + status = efi_call_phys3(boottime->handle_protocol, + image->device_handle, &fs_proto, &io); + if (status != EFI_SUCCESS) + goto free_initrds; + + status = efi_call_phys2(io->open_volume, io, &fh); + if (status != EFI_SUCCESS) + goto free_initrds; + } + + status = efi_call_phys5(fh->open, fh, &h, filename_16, + EFI_FILE_MODE_READ, (u64)0); + if (status != EFI_SUCCESS) + goto close_handles; + + initrd->handle = h; + + info_sz = 0; + status = efi_call_phys4(h->get_info, h, &info_guid, + &info_sz, NULL); + if (status != EFI_BUFFER_TOO_SMALL) + goto close_handles; + +grow: + status = efi_call_phys3(sys_table->boottime->allocate_pool, + EFI_LOADER_DATA, info_sz, &info); + if (status != EFI_SUCCESS) + goto close_handles; + + status = efi_call_phys4(h->get_info, h, &info_guid, + &info_sz, info); + if (status == EFI_BUFFER_TOO_SMALL) { + efi_call_phys1(sys_table->boottime->free_pool, info); + goto grow; + } + + file_sz = info->file_size; + efi_call_phys1(sys_table->boottime->free_pool, info); + + if (status != EFI_SUCCESS) + goto close_handles; + + initrd->size = file_sz; + initrd_total += file_sz; + } + + if (initrd_total) { + unsigned long addr; + + /* + * Multiple initrd's need to be at consecutive + * addresses in memory, so allocate enough memory for + * all the initrd's. + */ + status = high_alloc(initrd_total, 0x1000, + &initrd_addr, hdr->initrd_addr_max); + if (status != EFI_SUCCESS) + goto close_handles; + + /* We've run out of free low memory. */ + if (initrd_addr > hdr->initrd_addr_max) { + status = EFI_INVALID_PARAMETER; + goto free_initrd_total; + } + + addr = initrd_addr; + for (j = 0; j < nr_initrds; j++) { + u64 size; + + size = initrds[j].size; + while (size) { + u64 chunksize; + if (size > EFI_READ_CHUNK_SIZE) + chunksize = EFI_READ_CHUNK_SIZE; + else + chunksize = size; + status = efi_call_phys3(fh->read, + initrds[j].handle, + &chunksize, addr); + if (status != EFI_SUCCESS) + goto free_initrd_total; + addr += chunksize; + size -= chunksize; + } + + efi_call_phys1(fh->close, initrds[j].handle); + } + + } + + efi_call_phys1(sys_table->boottime->free_pool, initrds); + + hdr->ramdisk_image = initrd_addr; + hdr->ramdisk_size = initrd_total; + + return status; + +free_initrd_total: + low_free(initrd_total, initrd_addr); + +close_handles: + for (k = j; k < nr_initrds; k++) + efi_call_phys1(fh->close, initrds[k].handle); +free_initrds: + efi_call_phys1(sys_table->boottime->free_pool, initrds); +fail: + hdr->ramdisk_image = 0; + hdr->ramdisk_size = 0; + + return status; +} + +/* + * Because the x86 boot code expects to be passed a boot_params we + * need to create one ourselves (usually the bootloader would create + * one for us). + */ +static efi_status_t make_boot_params(struct boot_params *boot_params, + efi_loaded_image_t *image, + void *handle) +{ + struct efi_info *efi = &boot_params->efi_info; + struct apm_bios_info *bi = &boot_params->apm_bios_info; + struct sys_desc_table *sdt = &boot_params->sys_desc_table; + struct e820entry *e820_map = &boot_params->e820_map[0]; + struct e820entry *prev = NULL; + struct setup_header *hdr = &boot_params->hdr; + unsigned long size, key, desc_size, _size; + efi_memory_desc_t *mem_map; + void *options = image->load_options; + u32 load_options_size = image->load_options_size / 2; /* ASCII */ + int options_size = 0; + efi_status_t status; + __u32 desc_version; + unsigned long cmdline; + u8 nr_entries; + u16 *s2; + u8 *s1; + int i; + + hdr->type_of_loader = 0x21; + + /* Convert unicode cmdline to ascii */ + cmdline = 0; + s2 = (u16 *)options; + + if (s2) { + while (*s2 && *s2 != '\n' && options_size < load_options_size) { + s2++; + options_size++; + } + + if (options_size) { + if (options_size > hdr->cmdline_size) + options_size = hdr->cmdline_size; + + options_size++; /* NUL termination */ + + status = low_alloc(options_size, 1, &cmdline); + if (status != EFI_SUCCESS) + goto fail; + + s1 = (u8 *)(unsigned long)cmdline; + s2 = (u16 *)options; + + for (i = 0; i < options_size - 1; i++) + *s1++ = *s2++; + + *s1 = '\0'; + } + } + + hdr->cmd_line_ptr = cmdline; + + hdr->ramdisk_image = 0; + hdr->ramdisk_size = 0; + + status = handle_ramdisks(image, hdr); + if (status != EFI_SUCCESS) + goto free_cmdline; + + setup_graphics(boot_params); + + /* Clear APM BIOS info */ + memset(bi, 0, sizeof(*bi)); + + memset(sdt, 0, sizeof(*sdt)); + + memcpy(&efi->efi_loader_signature, EFI_LOADER_SIGNATURE, sizeof(__u32)); + + size = sizeof(*mem_map) * 32; + +again: + size += sizeof(*mem_map); + _size = size; + status = low_alloc(size, 1, (unsigned long *)&mem_map); + if (status != EFI_SUCCESS) + goto free_cmdline; + + status = efi_call_phys5(sys_table->boottime->get_memory_map, &size, + mem_map, &key, &desc_size, &desc_version); + if (status == EFI_BUFFER_TOO_SMALL) { + low_free(_size, (unsigned long)mem_map); + goto again; + } + + if (status != EFI_SUCCESS) + goto free_mem_map; + + efi->efi_systab = (unsigned long)sys_table; + efi->efi_memdesc_size = desc_size; + efi->efi_memdesc_version = desc_version; + efi->efi_memmap = (unsigned long)mem_map; + efi->efi_memmap_size = size; + +#ifdef CONFIG_X86_64 + efi->efi_systab_hi = (unsigned long)sys_table >> 32; + efi->efi_memmap_hi = (unsigned long)mem_map >> 32; +#endif + + /* Might as well exit boot services now */ + status = efi_call_phys2(sys_table->boottime->exit_boot_services, + handle, key); + if (status != EFI_SUCCESS) + goto free_mem_map; + + /* Historic? */ + boot_params->alt_mem_k = 32 * 1024; + + /* + * Convert the EFI memory map to E820. + */ + nr_entries = 0; + for (i = 0; i < size / desc_size; i++) { + efi_memory_desc_t *d; + unsigned int e820_type = 0; + unsigned long m = (unsigned long)mem_map; + + d = (efi_memory_desc_t *)(m + (i * desc_size)); + switch (d->type) { + case EFI_RESERVED_TYPE: + case EFI_RUNTIME_SERVICES_CODE: + case EFI_RUNTIME_SERVICES_DATA: + case EFI_MEMORY_MAPPED_IO: + case EFI_MEMORY_MAPPED_IO_PORT_SPACE: + case EFI_PAL_CODE: + e820_type = E820_RESERVED; + break; + + case EFI_UNUSABLE_MEMORY: + e820_type = E820_UNUSABLE; + break; + + case EFI_ACPI_RECLAIM_MEMORY: + e820_type = E820_ACPI; + break; + + case EFI_LOADER_CODE: + case EFI_LOADER_DATA: + case EFI_BOOT_SERVICES_CODE: + case EFI_BOOT_SERVICES_DATA: + case EFI_CONVENTIONAL_MEMORY: + e820_type = E820_RAM; + break; + + case EFI_ACPI_MEMORY_NVS: + e820_type = E820_NVS; + break; + + default: + continue; + } + + /* Merge adjacent mappings */ + if (prev && prev->type == e820_type && + (prev->addr + prev->size) == d->phys_addr) + prev->size += d->num_pages << 12; + else { + e820_map->addr = d->phys_addr; + e820_map->size = d->num_pages << 12; + e820_map->type = e820_type; + prev = e820_map++; + nr_entries++; + } + } + + boot_params->e820_entries = nr_entries; + + return EFI_SUCCESS; + +free_mem_map: + low_free(_size, (unsigned long)mem_map); +free_cmdline: + if (options_size) + low_free(options_size, hdr->cmd_line_ptr); +fail: + return status; +} + +/* + * On success we return a pointer to a boot_params structure, and NULL + * on failure. + */ +struct boot_params *efi_main(void *handle, efi_system_table_t *_table) +{ + struct boot_params *boot_params; + unsigned long start, nr_pages; + struct desc_ptr *gdt, *idt; + efi_loaded_image_t *image; + struct setup_header *hdr; + efi_status_t status; + efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID; + struct desc_struct *desc; + + sys_table = _table; + + /* Check if we were booted by the EFI firmware */ + if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) + goto fail; + + status = efi_call_phys3(sys_table->boottime->handle_protocol, + handle, &proto, (void *)&image); + if (status != EFI_SUCCESS) + goto fail; + + status = low_alloc(0x4000, 1, (unsigned long *)&boot_params); + if (status != EFI_SUCCESS) + goto fail; + + memset(boot_params, 0x0, 0x4000); + + /* Copy first two sectors to boot_params */ + memcpy(boot_params, image->image_base, 1024); + + hdr = &boot_params->hdr; + + /* + * The EFI firmware loader could have placed the kernel image + * anywhere in memory, but the kernel has various restrictions + * on the max physical address it can run at. Attempt to move + * the kernel to boot_params.pref_address, or as low as + * possible. + */ + start = hdr->pref_address; + nr_pages = round_up(hdr->init_size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE; + + status = efi_call_phys4(sys_table->boottime->allocate_pages, + EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA, + nr_pages, &start); + if (status != EFI_SUCCESS) { + status = low_alloc(hdr->init_size, hdr->kernel_alignment, + &start); + if (status != EFI_SUCCESS) + goto fail; + } + + hdr->code32_start = (__u32)start; + hdr->pref_address = (__u64)(unsigned long)image->image_base; + + memcpy((void *)start, image->image_base, image->image_size); + + status = efi_call_phys3(sys_table->boottime->allocate_pool, + EFI_LOADER_DATA, sizeof(*gdt), + (void **)&gdt); + if (status != EFI_SUCCESS) + goto fail; + + gdt->size = 0x800; + status = low_alloc(gdt->size, 8, (unsigned long *)&gdt->address); + if (status != EFI_SUCCESS) + goto fail; + + status = efi_call_phys3(sys_table->boottime->allocate_pool, + EFI_LOADER_DATA, sizeof(*idt), + (void **)&idt); + if (status != EFI_SUCCESS) + goto fail; + + idt->size = 0; + idt->address = 0; + + status = make_boot_params(boot_params, image, handle); + if (status != EFI_SUCCESS) + goto fail; + + memset((char *)gdt->address, 0x0, gdt->size); + desc = (struct desc_struct *)gdt->address; + + /* The first GDT is a dummy and the second is unused. */ + desc += 2; + + desc->limit0 = 0xffff; + desc->base0 = 0x0000; + desc->base1 = 0x0000; + desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ; + desc->s = DESC_TYPE_CODE_DATA; + desc->dpl = 0; + desc->p = 1; + desc->limit = 0xf; + desc->avl = 0; + desc->l = 0; + desc->d = SEG_OP_SIZE_32BIT; + desc->g = SEG_GRANULARITY_4KB; + desc->base2 = 0x00; + + desc++; + desc->limit0 = 0xffff; + desc->base0 = 0x0000; + desc->base1 = 0x0000; + desc->type = SEG_TYPE_DATA | SEG_TYPE_READ_WRITE; + desc->s = DESC_TYPE_CODE_DATA; + desc->dpl = 0; + desc->p = 1; + desc->limit = 0xf; + desc->avl = 0; + desc->l = 0; + desc->d = SEG_OP_SIZE_32BIT; + desc->g = SEG_GRANULARITY_4KB; + desc->base2 = 0x00; + +#ifdef CONFIG_X86_64 + /* Task segment value */ + desc++; + desc->limit0 = 0x0000; + desc->base0 = 0x0000; + desc->base1 = 0x0000; + desc->type = SEG_TYPE_TSS; + desc->s = 0; + desc->dpl = 0; + desc->p = 1; + desc->limit = 0x0; + desc->avl = 0; + desc->l = 0; + desc->d = 0; + desc->g = SEG_GRANULARITY_4KB; + desc->base2 = 0x00; +#endif /* CONFIG_X86_64 */ + + asm volatile ("lidt %0" : : "m" (*idt)); + asm volatile ("lgdt %0" : : "m" (*gdt)); + + asm volatile("cli"); + + return boot_params; +fail: + return NULL; +} diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h new file mode 100644 index 00000000000..39251663e65 --- /dev/null +++ b/arch/x86/boot/compressed/eboot.h @@ -0,0 +1,61 @@ +#ifndef BOOT_COMPRESSED_EBOOT_H +#define BOOT_COMPRESSED_EBOOT_H + +#define SEG_TYPE_DATA (0 << 3) +#define SEG_TYPE_READ_WRITE (1 << 1) +#define SEG_TYPE_CODE (1 << 3) +#define SEG_TYPE_EXEC_READ (1 << 1) +#define SEG_TYPE_TSS ((1 << 3) | (1 << 0)) +#define SEG_OP_SIZE_32BIT (1 << 0) +#define SEG_GRANULARITY_4KB (1 << 0) + +#define DESC_TYPE_CODE_DATA (1 << 0) + +#define EFI_PAGE_SIZE (1UL << EFI_PAGE_SHIFT) +#define EFI_READ_CHUNK_SIZE (1024 * 1024) + +#define PIXEL_RGB_RESERVED_8BIT_PER_COLOR 0 +#define PIXEL_BGR_RESERVED_8BIT_PER_COLOR 1 +#define PIXEL_BIT_MASK 2 +#define PIXEL_BLT_ONLY 3 +#define PIXEL_FORMAT_MAX 4 + +struct efi_pixel_bitmask { + u32 red_mask; + u32 green_mask; + u32 blue_mask; + u32 reserved_mask; +}; + +struct efi_graphics_output_mode_info { + u32 version; + u32 horizontal_resolution; + u32 vertical_resolution; + int pixel_format; + struct efi_pixel_bitmask pixel_information; + u32 pixels_per_scan_line; +} __packed; + +struct efi_graphics_output_protocol_mode { + u32 max_mode; + u32 mode; + unsigned long info; + unsigned long size_of_info; + u64 frame_buffer_base; + unsigned long frame_buffer_size; +} __packed; + +struct efi_graphics_output_protocol { + void *query_mode; + unsigned long set_mode; + unsigned long blt; + struct efi_graphics_output_protocol_mode *mode; +}; + +struct efi_uga_draw_protocol { + void *get_mode; + void *set_mode; + void *blt; +}; + +#endif /* BOOT_COMPRESSED_EBOOT_H */ diff --git a/arch/x86/boot/compressed/efi_stub_32.S b/arch/x86/boot/compressed/efi_stub_32.S new file mode 100644 index 00000000000..a53440e81d5 --- /dev/null +++ b/arch/x86/boot/compressed/efi_stub_32.S @@ -0,0 +1,86 @@ +/* + * EFI call stub for IA32. + * + * This stub allows us to make EFI calls in physical mode with interrupts + * turned off. Note that this implementation is different from the one in + * arch/x86/platform/efi/efi_stub_32.S because we're _already_ in physical + * mode at this point. + */ + +#include <linux/linkage.h> +#include <asm/page_types.h> + +/* + * efi_call_phys(void *, ...) is a function with variable parameters. + * All the callers of this function assure that all the parameters are 4-bytes. + */ + +/* + * In gcc calling convention, EBX, ESP, EBP, ESI and EDI are all callee save. + * So we'd better save all of them at the beginning of this function and restore + * at the end no matter how many we use, because we can not assure EFI runtime + * service functions will comply with gcc calling convention, too. + */ + +.text +ENTRY(efi_call_phys) + /* + * 0. The function can only be called in Linux kernel. So CS has been + * set to 0x0010, DS and SS have been set to 0x0018. In EFI, I found + * the values of these registers are the same. And, the corresponding + * GDT entries are identical. So I will do nothing about segment reg + * and GDT, but change GDT base register in prelog and epilog. + */ + + /* + * 1. Because we haven't been relocated by this point we need to + * use relative addressing. + */ + call 1f +1: popl %edx + subl $1b, %edx + + /* + * 2. Now on the top of stack is the return + * address in the caller of efi_call_phys(), then parameter 1, + * parameter 2, ..., param n. To make things easy, we save the return + * address of efi_call_phys in a global variable. + */ + popl %ecx + movl %ecx, saved_return_addr(%edx) + /* get the function pointer into ECX*/ + popl %ecx + movl %ecx, efi_rt_function_ptr(%edx) + + /* + * 3. Call the physical function. + */ + call *%ecx + + /* + * 4. Balance the stack. And because EAX contain the return value, + * we'd better not clobber it. We need to calculate our address + * again because %ecx and %edx are not preserved across EFI function + * calls. + */ + call 1f +1: popl %edx + subl $1b, %edx + + movl efi_rt_function_ptr(%edx), %ecx + pushl %ecx + + /* + * 10. Push the saved return address onto the stack and return. + */ + movl saved_return_addr(%edx), %ecx + pushl %ecx + ret +ENDPROC(efi_call_phys) +.previous + +.data +saved_return_addr: + .long 0 +efi_rt_function_ptr: + .long 0 diff --git a/arch/x86/boot/compressed/efi_stub_64.S b/arch/x86/boot/compressed/efi_stub_64.S new file mode 100644 index 00000000000..cedc60de86e --- /dev/null +++ b/arch/x86/boot/compressed/efi_stub_64.S @@ -0,0 +1 @@ +#include "../../platform/efi/efi_stub_64.S" diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 67a655a39ce..a0559930a18 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -32,6 +32,28 @@ __HEAD ENTRY(startup_32) +#ifdef CONFIG_EFI_STUB + /* + * We don't need the return address, so set up the stack so + * efi_main() can find its arugments. + */ + add $0x4, %esp + + call efi_main + cmpl $0, %eax + je preferred_addr + movl %eax, %esi + call 1f +1: + popl %eax + subl $1b, %eax + subl BP_pref_address(%esi), %eax + add BP_code32_start(%esi), %eax + leal preferred_addr(%eax), %eax + jmp *%eax + +preferred_addr: +#endif cld /* * Test KEEP_SEGMENTS flag to see if the bootloader is asking diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 35af09d13dc..558d76ce23b 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -199,6 +199,26 @@ ENTRY(startup_64) * an identity mapped page table being provied that maps our * entire text+data+bss and hopefully all of memory. */ +#ifdef CONFIG_EFI_STUB + pushq %rsi + mov %rcx, %rdi + mov %rdx, %rsi + call efi_main + popq %rsi + cmpq $0,%rax + je preferred_addr + movq %rax,%rsi + call 1f +1: + popq %rax + subq $1b, %rax + subq BP_pref_address(%rsi), %rax + add BP_code32_start(%esi), %eax + leaq preferred_addr(%rax), %rax + jmp *%rax + +preferred_addr: +#endif /* Setup data segments. */ xorl %eax, %eax diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 3a19d04cebe..7116dcba0c9 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -321,6 +321,8 @@ static void parse_elf(void *output) default: /* Ignore other PT_* */ break; } } + + free(phdrs); } asmlinkage void decompress_kernel(void *rmode, memptr heap, diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c index 46a82388243..958a641483d 100644 --- a/arch/x86/boot/compressed/mkpiggy.c +++ b/arch/x86/boot/compressed/mkpiggy.c @@ -29,14 +29,7 @@ #include <stdio.h> #include <string.h> #include <inttypes.h> - -static uint32_t getle32(const void *p) -{ - const uint8_t *cp = p; - - return (uint32_t)cp[0] + ((uint32_t)cp[1] << 8) + - ((uint32_t)cp[2] << 16) + ((uint32_t)cp[3] << 24); -} +#include <tools/le_byteshift.h> int main(int argc, char *argv[]) { @@ -69,7 +62,7 @@ int main(int argc, char *argv[]) } ilen = ftell(f); - olen = getle32(&olen); + olen = get_unaligned_le32(&olen); fclose(f); /* diff --git a/arch/x86/boot/compressed/relocs.c b/arch/x86/boot/compressed/relocs.c index 89bbf4e4d05..d3c0b027766 100644 --- a/arch/x86/boot/compressed/relocs.c +++ b/arch/x86/boot/compressed/relocs.c @@ -10,6 +10,7 @@ #define USE_BSD #include <endian.h> #include <regex.h> +#include <tools/le_byteshift.h> static void die(char *fmt, ...); @@ -605,10 +606,7 @@ static void emit_relocs(int as_text) fwrite("\0\0\0\0", 4, 1, stdout); /* Now print each relocation */ for (i = 0; i < reloc_count; i++) { - buf[0] = (relocs[i] >> 0) & 0xff; - buf[1] = (relocs[i] >> 8) & 0xff; - buf[2] = (relocs[i] >> 16) & 0xff; - buf[3] = (relocs[i] >> 24) & 0xff; + put_unaligned_le32(relocs[i], buf); fwrite(buf, 4, 1, stdout); } } diff --git a/arch/x86/boot/compressed/string.c b/arch/x86/boot/compressed/string.c index 19b3e693cd7..ffb9c5c9d74 100644 --- a/arch/x86/boot/compressed/string.c +++ b/arch/x86/boot/compressed/string.c @@ -1,2 +1,11 @@ #include "misc.h" + +int memcmp(const void *s1, const void *s2, size_t len) +{ + u8 diff; + asm("repe; cmpsb; setnz %0" + : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len)); + return diff; +} + #include "../string.c" diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index bdb4d458ec8..f1bbeeb0914 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -45,6 +45,11 @@ SYSSEG = 0x1000 /* historical load address >> 4 */ .global bootsect_start bootsect_start: +#ifdef CONFIG_EFI_STUB + # "MZ", MS-DOS header + .byte 0x4d + .byte 0x5a +#endif # Normalize the start address ljmp $BOOTSEG, $start2 @@ -79,6 +84,14 @@ bs_die: # invoke the BIOS reset code... ljmp $0xf000,$0xfff0 +#ifdef CONFIG_EFI_STUB + .org 0x3c + # + # Offset to the PE header. + # + .long pe_header +#endif /* CONFIG_EFI_STUB */ + .section ".bsdata", "a" bugger_off_msg: .ascii "Direct booting from floppy is no longer supported.\r\n" @@ -87,6 +100,141 @@ bugger_off_msg: .ascii "Remove disk and press any key to reboot . . .\r\n" .byte 0 +#ifdef CONFIG_EFI_STUB +pe_header: + .ascii "PE" + .word 0 + +coff_header: +#ifdef CONFIG_X86_32 + .word 0x14c # i386 +#else + .word 0x8664 # x86-64 +#endif + .word 2 # nr_sections + .long 0 # TimeDateStamp + .long 0 # PointerToSymbolTable + .long 1 # NumberOfSymbols + .word section_table - optional_header # SizeOfOptionalHeader +#ifdef CONFIG_X86_32 + .word 0x306 # Characteristics. + # IMAGE_FILE_32BIT_MACHINE | + # IMAGE_FILE_DEBUG_STRIPPED | + # IMAGE_FILE_EXECUTABLE_IMAGE | + # IMAGE_FILE_LINE_NUMS_STRIPPED +#else + .word 0x206 # Characteristics + # IMAGE_FILE_DEBUG_STRIPPED | + # IMAGE_FILE_EXECUTABLE_IMAGE | + # IMAGE_FILE_LINE_NUMS_STRIPPED +#endif + +optional_header: +#ifdef CONFIG_X86_32 + .word 0x10b # PE32 format +#else + .word 0x20b # PE32+ format +#endif + .byte 0x02 # MajorLinkerVersion + .byte 0x14 # MinorLinkerVersion + + # Filled in by build.c + .long 0 # SizeOfCode + + .long 0 # SizeOfInitializedData + .long 0 # SizeOfUninitializedData + + # Filled in by build.c + .long 0x0000 # AddressOfEntryPoint + + .long 0x0000 # BaseOfCode +#ifdef CONFIG_X86_32 + .long 0 # data +#endif + +extra_header_fields: +#ifdef CONFIG_X86_32 + .long 0 # ImageBase +#else + .quad 0 # ImageBase +#endif + .long 0x1000 # SectionAlignment + .long 0x200 # FileAlignment + .word 0 # MajorOperatingSystemVersion + .word 0 # MinorOperatingSystemVersion + .word 0 # MajorImageVersion + .word 0 # MinorImageVersion + .word 0 # MajorSubsystemVersion + .word 0 # MinorSubsystemVersion + .long 0 # Win32VersionValue + + # + # The size of the bzImage is written in tools/build.c + # + .long 0 # SizeOfImage + + .long 0x200 # SizeOfHeaders + .long 0 # CheckSum + .word 0xa # Subsystem (EFI application) + .word 0 # DllCharacteristics +#ifdef CONFIG_X86_32 + .long 0 # SizeOfStackReserve + .long 0 # SizeOfStackCommit + .long 0 # SizeOfHeapReserve + .long 0 # SizeOfHeapCommit +#else + .quad 0 # SizeOfStackReserve + .quad 0 # SizeOfStackCommit + .quad 0 # SizeOfHeapReserve + .quad 0 # SizeOfHeapCommit +#endif + .long 0 # LoaderFlags + .long 0x1 # NumberOfRvaAndSizes + + .quad 0 # ExportTable + .quad 0 # ImportTable + .quad 0 # ResourceTable + .quad 0 # ExceptionTable + .quad 0 # CertificationTable + .quad 0 # BaseRelocationTable + + # Section table +section_table: + .ascii ".text" + .byte 0 + .byte 0 + .byte 0 + .long 0 + .long 0x0 # startup_{32,64} + .long 0 # Size of initialized data + # on disk + .long 0x0 # startup_{32,64} + .long 0 # PointerToRelocations + .long 0 # PointerToLineNumbers + .word 0 # NumberOfRelocations + .word 0 # NumberOfLineNumbers + .long 0x60500020 # Characteristics (section flags) + + # + # The EFI application loader requires a relocation section + # because EFI applications are relocatable and not having + # this section seems to confuse it. But since we don't need + # the loader to fixup any relocs for us just fill it with a + # single dummy reloc. + # + .ascii ".reloc" + .byte 0 + .byte 0 + .long reloc_end - reloc_start + .long reloc_start + .long reloc_end - reloc_start # SizeOfRawData + .long reloc_start # PointerToRawData + .long 0 # PointerToRelocations + .long 0 # PointerToLineNumbers + .word 0 # NumberOfRelocations + .word 0 # NumberOfLineNumbers + .long 0x42100040 # Characteristics (section flags) +#endif /* CONFIG_EFI_STUB */ # Kernel attributes; used by setup. This is part 1 of the # header, from the old boot sector. @@ -318,3 +466,13 @@ die: setup_corrupt: .byte 7 .string "No setup signature found...\n" + + .data +dummy: .long 0 + + .section .reloc +reloc_start: + .long dummy - reloc_start + .long 10 + .word 0 +reloc_end: diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index 3cbc4058dd2..574dedfe289 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -111,3 +111,38 @@ unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int bas return result; } + +/** + * strlen - Find the length of a string + * @s: The string to be sized + */ +size_t strlen(const char *s) +{ + const char *sc; + + for (sc = s; *sc != '\0'; ++sc) + /* nothing */; + return sc - s; +} + +/** + * strstr - Find the first substring in a %NUL terminated string + * @s1: The string to be searched + * @s2: The string to search for + */ +char *strstr(const char *s1, const char *s2) +{ + size_t l1, l2; + + l2 = strlen(s2); + if (!l2) + return (char *)s1; + l1 = strlen(s1); + while (l1 >= l2) { + l1--; + if (!memcmp(s1, s2, l2)) + return (char *)s1; + s1++; + } + return NULL; +} diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index fdc60a0b3c2..ed549767a23 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -29,18 +29,18 @@ #include <stdarg.h> #include <sys/types.h> #include <sys/stat.h> -#include <sys/sysmacros.h> #include <unistd.h> #include <fcntl.h> #include <sys/mman.h> -#include <asm/boot.h> +#include <tools/le_byteshift.h> typedef unsigned char u8; typedef unsigned short u16; -typedef unsigned long u32; +typedef unsigned int u32; #define DEFAULT_MAJOR_ROOT 0 #define DEFAULT_MINOR_ROOT 0 +#define DEFAULT_ROOT_DEV (DEFAULT_MAJOR_ROOT << 8 | DEFAULT_MINOR_ROOT) /* Minimal number of setup sectors */ #define SETUP_SECT_MIN 5 @@ -135,6 +135,9 @@ static void usage(void) int main(int argc, char ** argv) { +#ifdef CONFIG_EFI_STUB + unsigned int file_sz, pe_header; +#endif unsigned int i, sz, setup_sectors; int c; u32 sys_size; @@ -156,7 +159,7 @@ int main(int argc, char ** argv) die("read-error on `setup'"); if (c < 1024) die("The setup must be at least 1024 bytes"); - if (buf[510] != 0x55 || buf[511] != 0xaa) + if (get_unaligned_le16(&buf[510]) != 0xAA55) die("Boot block hasn't got boot flag (0xAA55)"); fclose(file); @@ -168,8 +171,7 @@ int main(int argc, char ** argv) memset(buf+c, 0, i-c); /* Set the default root device */ - buf[508] = DEFAULT_MINOR_ROOT; - buf[509] = DEFAULT_MAJOR_ROOT; + put_unaligned_le16(DEFAULT_ROOT_DEV, &buf[508]); fprintf(stderr, "Setup is %d bytes (padded to %d bytes).\n", c, i); @@ -189,10 +191,44 @@ int main(int argc, char ** argv) /* Patch the setup code with the appropriate size parameters */ buf[0x1f1] = setup_sectors-1; - buf[0x1f4] = sys_size; - buf[0x1f5] = sys_size >> 8; - buf[0x1f6] = sys_size >> 16; - buf[0x1f7] = sys_size >> 24; + put_unaligned_le32(sys_size, &buf[0x1f4]); + +#ifdef CONFIG_EFI_STUB + file_sz = sz + i + ((sys_size * 16) - sz); + + pe_header = get_unaligned_le32(&buf[0x3c]); + + /* Size of code */ + put_unaligned_le32(file_sz, &buf[pe_header + 0x1c]); + + /* Size of image */ + put_unaligned_le32(file_sz, &buf[pe_header + 0x50]); + +#ifdef CONFIG_X86_32 + /* Address of entry point */ + put_unaligned_le32(i, &buf[pe_header + 0x28]); + + /* .text size */ + put_unaligned_le32(file_sz, &buf[pe_header + 0xb0]); + + /* .text size of initialised data */ + put_unaligned_le32(file_sz, &buf[pe_header + 0xb8]); +#else + /* + * Address of entry point. startup_32 is at the beginning and + * the 64-bit entry point (startup_64) is always 512 bytes + * after. + */ + put_unaligned_le32(i + 512, &buf[pe_header + 0x28]); + + /* .text size */ + put_unaligned_le32(file_sz, &buf[pe_header + 0xc0]); + + /* .text size of initialised data */ + put_unaligned_le32(file_sz, &buf[pe_header + 0xc8]); + +#endif /* CONFIG_X86_32 */ +#endif /* CONFIG_EFI_STUB */ crc = partial_crc32(buf, i, crc); if (fwrite(buf, 1, i, stdout) != i) @@ -211,8 +247,9 @@ int main(int argc, char ** argv) } /* Write the CRC */ - fprintf(stderr, "CRC %lx\n", crc); - if (fwrite(&crc, 1, 4, stdout) != 4) + fprintf(stderr, "CRC %x\n", crc); + put_unaligned_le32(crc, buf); + if (fwrite(buf, 1, 4, stdout) != 4) die("Writing CRC failed"); close(fd); diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 2bf18059fbe..119db67dcb0 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -15,23 +15,28 @@ CONFIG_CPUSETS=y CONFIG_CGROUP_CPUACCT=y CONFIG_RESOURCE_COUNTERS=y CONFIG_CGROUP_SCHED=y -CONFIG_UTS_NS=y -CONFIG_IPC_NS=y -CONFIG_USER_NS=y -CONFIG_PID_NS=y -CONFIG_NET_NS=y CONFIG_BLK_DEV_INITRD=y -CONFIG_KALLSYMS_EXTRA_PASS=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y CONFIG_KPROBES=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y +CONFIG_PARTITION_ADVANCED=y +CONFIG_OSF_PARTITION=y +CONFIG_AMIGA_PARTITION=y +CONFIG_MAC_PARTITION=y +CONFIG_BSD_DISKLABEL=y +CONFIG_MINIX_SUBPARTITION=y +CONFIG_SOLARIS_X86_PARTITION=y +CONFIG_UNIXWARE_DISKLABEL=y +CONFIG_SGI_PARTITION=y +CONFIG_SUN_PARTITION=y +CONFIG_KARMA_PARTITION=y +CONFIG_EFI_PARTITION=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_SMP=y -CONFIG_SPARSE_IRQ=y CONFIG_X86_GENERIC=y CONFIG_HPET_TIMER=y CONFIG_SCHED_SMT=y @@ -51,14 +56,12 @@ CONFIG_HZ_1000=y CONFIG_KEXEC=y CONFIG_CRASH_DUMP=y # CONFIG_COMPAT_VDSO is not set -CONFIG_PM=y +CONFIG_HIBERNATION=y CONFIG_PM_DEBUG=y CONFIG_PM_TRACE_RTC=y -CONFIG_HIBERNATION=y CONFIG_ACPI_PROCFS=y CONFIG_ACPI_DOCK=y CONFIG_CPU_FREQ=y -CONFIG_CPU_FREQ_DEBUG=y # CONFIG_CPU_FREQ_STAT is not set CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_PERFORMANCE=y @@ -69,7 +72,6 @@ CONFIG_PCI_MSI=y CONFIG_PCCARD=y CONFIG_YENTA=y CONFIG_HOTPLUG_PCI=y -CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS=y CONFIG_BINFMT_MISC=y CONFIG_NET=y CONFIG_PACKET=y @@ -120,7 +122,6 @@ CONFIG_NF_CONNTRACK_IPV4=y CONFIG_IP_NF_IPTABLES=y CONFIG_IP_NF_FILTER=y CONFIG_IP_NF_TARGET_REJECT=y -CONFIG_IP_NF_TARGET_LOG=y CONFIG_IP_NF_TARGET_ULOG=y CONFIG_NF_NAT=y CONFIG_IP_NF_TARGET_MASQUERADE=y @@ -128,7 +129,6 @@ CONFIG_IP_NF_MANGLE=y CONFIG_NF_CONNTRACK_IPV6=y CONFIG_IP6_NF_IPTABLES=y CONFIG_IP6_NF_MATCH_IPV6HEADER=y -CONFIG_IP6_NF_TARGET_LOG=y CONFIG_IP6_NF_FILTER=y CONFIG_IP6_NF_TARGET_REJECT=y CONFIG_IP6_NF_MANGLE=y @@ -169,25 +169,20 @@ CONFIG_DM_ZERO=y CONFIG_MACINTOSH_DRIVERS=y CONFIG_MAC_EMUMOUSEBTN=y CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_NET_VENDOR_3COM=y +CONFIG_NETCONSOLE=y +CONFIG_BNX2=y +CONFIG_TIGON3=y CONFIG_NET_TULIP=y -CONFIG_NET_PCI=y -CONFIG_FORCEDETH=y CONFIG_E100=y +CONFIG_E1000=y +CONFIG_E1000E=y +CONFIG_SKY2=y CONFIG_NE2K_PCI=y +CONFIG_FORCEDETH=y CONFIG_8139TOO=y # CONFIG_8139TOO_PIO is not set -CONFIG_E1000=y -CONFIG_E1000E=y CONFIG_R8169=y -CONFIG_SKY2=y -CONFIG_TIGON3=y -CONFIG_BNX2=y -CONFIG_TR=y -CONFIG_NET_PCMCIA=y CONFIG_FDDI=y -CONFIG_NETCONSOLE=y CONFIG_INPUT_POLLDEV=y # CONFIG_INPUT_MOUSEDEV_PSAUX is not set CONFIG_INPUT_EVDEV=y @@ -196,6 +191,7 @@ CONFIG_INPUT_TABLET=y CONFIG_INPUT_TOUCHSCREEN=y CONFIG_INPUT_MISC=y CONFIG_VT_HW_CONSOLE_BINDING=y +# CONFIG_LEGACY_PTYS is not set CONFIG_SERIAL_NONSTANDARD=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y @@ -205,7 +201,6 @@ CONFIG_SERIAL_8250_MANY_PORTS=y CONFIG_SERIAL_8250_SHARE_IRQ=y CONFIG_SERIAL_8250_DETECT_IRQ=y CONFIG_SERIAL_8250_RSA=y -# CONFIG_LEGACY_PTYS is not set CONFIG_HW_RANDOM=y CONFIG_NVRAM=y CONFIG_HPET=y @@ -220,7 +215,6 @@ CONFIG_DRM_I915=y CONFIG_FB_MODE_HELPERS=y CONFIG_FB_TILEBLITTING=y CONFIG_FB_EFI=y -CONFIG_BACKLIGHT_LCD_SUPPORT=y # CONFIG_LCD_CLASS_DEVICE is not set CONFIG_VGACON_SOFT_SCROLLBACK=y CONFIG_LOGO=y @@ -283,7 +277,6 @@ CONFIG_ZISOFS=y CONFIG_MSDOS_FS=y CONFIG_VFAT_FS=y CONFIG_PROC_KCORE=y -CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_HUGETLBFS=y CONFIG_NFS_FS=y @@ -291,18 +284,6 @@ CONFIG_NFS_V3=y CONFIG_NFS_V3_ACL=y CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y -CONFIG_PARTITION_ADVANCED=y -CONFIG_OSF_PARTITION=y -CONFIG_AMIGA_PARTITION=y -CONFIG_MAC_PARTITION=y -CONFIG_BSD_DISKLABEL=y -CONFIG_MINIX_SUBPARTITION=y -CONFIG_SOLARIS_X86_PARTITION=y -CONFIG_UNIXWARE_DISKLABEL=y -CONFIG_SGI_PARTITION=y -CONFIG_SUN_PARTITION=y -CONFIG_KARMA_PARTITION=y -CONFIG_EFI_PARTITION=y CONFIG_NLS_DEFAULT="utf8" CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ASCII=y @@ -317,13 +298,12 @@ CONFIG_DEBUG_KERNEL=y # CONFIG_SCHED_DEBUG is not set CONFIG_SCHEDSTATS=y CONFIG_TIMER_STATS=y -# CONFIG_RCU_CPU_STALL_DETECTOR is not set +CONFIG_DEBUG_STACK_USAGE=y CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_PROVIDE_OHCI1394_DMA_INIT=y CONFIG_EARLY_PRINTK_DBGP=y CONFIG_DEBUG_STACKOVERFLOW=y -CONFIG_DEBUG_STACK_USAGE=y # CONFIG_DEBUG_RODATA_TEST is not set CONFIG_DEBUG_NX_TEST=m CONFIG_DEBUG_BOOT_PARAMS=y diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 058a35b8286..76eb2903809 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -1,4 +1,3 @@ -CONFIG_64BIT=y CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y @@ -16,26 +15,29 @@ CONFIG_CPUSETS=y CONFIG_CGROUP_CPUACCT=y CONFIG_RESOURCE_COUNTERS=y CONFIG_CGROUP_SCHED=y -CONFIG_UTS_NS=y -CONFIG_IPC_NS=y -CONFIG_USER_NS=y -CONFIG_PID_NS=y -CONFIG_NET_NS=y CONFIG_BLK_DEV_INITRD=y -CONFIG_KALLSYMS_EXTRA_PASS=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y CONFIG_KPROBES=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y +CONFIG_PARTITION_ADVANCED=y +CONFIG_OSF_PARTITION=y +CONFIG_AMIGA_PARTITION=y +CONFIG_MAC_PARTITION=y +CONFIG_BSD_DISKLABEL=y +CONFIG_MINIX_SUBPARTITION=y +CONFIG_SOLARIS_X86_PARTITION=y +CONFIG_UNIXWARE_DISKLABEL=y +CONFIG_SGI_PARTITION=y +CONFIG_SUN_PARTITION=y +CONFIG_KARMA_PARTITION=y +CONFIG_EFI_PARTITION=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_SMP=y -CONFIG_SPARSE_IRQ=y CONFIG_CALGARY_IOMMU=y -CONFIG_AMD_IOMMU=y -CONFIG_AMD_IOMMU_STATS=y CONFIG_NR_CPUS=64 CONFIG_SCHED_SMT=y CONFIG_PREEMPT_VOLUNTARY=y @@ -53,27 +55,22 @@ CONFIG_HZ_1000=y CONFIG_KEXEC=y CONFIG_CRASH_DUMP=y # CONFIG_COMPAT_VDSO is not set -CONFIG_PM=y +CONFIG_HIBERNATION=y CONFIG_PM_DEBUG=y CONFIG_PM_TRACE_RTC=y -CONFIG_HIBERNATION=y CONFIG_ACPI_PROCFS=y CONFIG_ACPI_DOCK=y CONFIG_CPU_FREQ=y -CONFIG_CPU_FREQ_DEBUG=y # CONFIG_CPU_FREQ_STAT is not set CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_PERFORMANCE=y CONFIG_CPU_FREQ_GOV_ONDEMAND=y CONFIG_X86_ACPI_CPUFREQ=y CONFIG_PCI_MMCONFIG=y -CONFIG_INTEL_IOMMU=y -# CONFIG_INTEL_IOMMU_DEFAULT_ON is not set CONFIG_PCIEPORTBUS=y CONFIG_PCCARD=y CONFIG_YENTA=y CONFIG_HOTPLUG_PCI=y -CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS=y CONFIG_BINFMT_MISC=y CONFIG_IA32_EMULATION=y CONFIG_NET=y @@ -125,7 +122,6 @@ CONFIG_NF_CONNTRACK_IPV4=y CONFIG_IP_NF_IPTABLES=y CONFIG_IP_NF_FILTER=y CONFIG_IP_NF_TARGET_REJECT=y -CONFIG_IP_NF_TARGET_LOG=y CONFIG_IP_NF_TARGET_ULOG=y CONFIG_NF_NAT=y CONFIG_IP_NF_TARGET_MASQUERADE=y @@ -133,7 +129,6 @@ CONFIG_IP_NF_MANGLE=y CONFIG_NF_CONNTRACK_IPV6=y CONFIG_IP6_NF_IPTABLES=y CONFIG_IP6_NF_MATCH_IPV6HEADER=y -CONFIG_IP6_NF_TARGET_LOG=y CONFIG_IP6_NF_FILTER=y CONFIG_IP6_NF_TARGET_REJECT=y CONFIG_IP6_NF_MANGLE=y @@ -172,20 +167,15 @@ CONFIG_DM_ZERO=y CONFIG_MACINTOSH_DRIVERS=y CONFIG_MAC_EMUMOUSEBTN=y CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_NET_VENDOR_3COM=y +CONFIG_NETCONSOLE=y +CONFIG_TIGON3=y CONFIG_NET_TULIP=y -CONFIG_NET_PCI=y -CONFIG_FORCEDETH=y CONFIG_E100=y -CONFIG_8139TOO=y CONFIG_E1000=y CONFIG_SKY2=y -CONFIG_TIGON3=y -CONFIG_TR=y -CONFIG_NET_PCMCIA=y +CONFIG_FORCEDETH=y +CONFIG_8139TOO=y CONFIG_FDDI=y -CONFIG_NETCONSOLE=y CONFIG_INPUT_POLLDEV=y # CONFIG_INPUT_MOUSEDEV_PSAUX is not set CONFIG_INPUT_EVDEV=y @@ -194,6 +184,7 @@ CONFIG_INPUT_TABLET=y CONFIG_INPUT_TOUCHSCREEN=y CONFIG_INPUT_MISC=y CONFIG_VT_HW_CONSOLE_BINDING=y +# CONFIG_LEGACY_PTYS is not set CONFIG_SERIAL_NONSTANDARD=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y @@ -203,7 +194,6 @@ CONFIG_SERIAL_8250_MANY_PORTS=y CONFIG_SERIAL_8250_SHARE_IRQ=y CONFIG_SERIAL_8250_DETECT_IRQ=y CONFIG_SERIAL_8250_RSA=y -# CONFIG_LEGACY_PTYS is not set CONFIG_HW_RANDOM=y # CONFIG_HW_RANDOM_INTEL is not set # CONFIG_HW_RANDOM_AMD is not set @@ -221,7 +211,6 @@ CONFIG_DRM_I915_KMS=y CONFIG_FB_MODE_HELPERS=y CONFIG_FB_TILEBLITTING=y CONFIG_FB_EFI=y -CONFIG_BACKLIGHT_LCD_SUPPORT=y # CONFIG_LCD_CLASS_DEVICE is not set CONFIG_VGACON_SOFT_SCROLLBACK=y CONFIG_LOGO=y @@ -268,6 +257,10 @@ CONFIG_RTC_CLASS=y # CONFIG_RTC_HCTOSYS is not set CONFIG_DMADEVICES=y CONFIG_EEEPC_LAPTOP=y +CONFIG_AMD_IOMMU=y +CONFIG_AMD_IOMMU_STATS=y +CONFIG_INTEL_IOMMU=y +# CONFIG_INTEL_IOMMU_DEFAULT_ON is not set CONFIG_EFI_VARS=y CONFIG_EXT3_FS=y # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set @@ -284,7 +277,6 @@ CONFIG_ZISOFS=y CONFIG_MSDOS_FS=y CONFIG_VFAT_FS=y CONFIG_PROC_KCORE=y -CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_HUGETLBFS=y CONFIG_NFS_FS=y @@ -292,18 +284,6 @@ CONFIG_NFS_V3=y CONFIG_NFS_V3_ACL=y CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y -CONFIG_PARTITION_ADVANCED=y -CONFIG_OSF_PARTITION=y -CONFIG_AMIGA_PARTITION=y -CONFIG_MAC_PARTITION=y -CONFIG_BSD_DISKLABEL=y -CONFIG_MINIX_SUBPARTITION=y -CONFIG_SOLARIS_X86_PARTITION=y -CONFIG_UNIXWARE_DISKLABEL=y -CONFIG_SGI_PARTITION=y -CONFIG_SUN_PARTITION=y -CONFIG_KARMA_PARTITION=y -CONFIG_EFI_PARTITION=y CONFIG_NLS_DEFAULT="utf8" CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ASCII=y @@ -317,13 +297,12 @@ CONFIG_DEBUG_KERNEL=y # CONFIG_SCHED_DEBUG is not set CONFIG_SCHEDSTATS=y CONFIG_TIMER_STATS=y -# CONFIG_RCU_CPU_STALL_DETECTOR is not set +CONFIG_DEBUG_STACK_USAGE=y CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_PROVIDE_OHCI1394_DMA_INIT=y CONFIG_EARLY_PRINTK_DBGP=y CONFIG_DEBUG_STACKOVERFLOW=y -CONFIG_DEBUG_STACK_USAGE=y # CONFIG_DEBUG_RODATA_TEST is not set CONFIG_DEBUG_NX_TEST=m CONFIG_DEBUG_BOOT_PARAMS=y diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index 2b0b9631474..e191ac048b5 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -8,6 +8,7 @@ obj-$(CONFIG_CRYPTO_SALSA20_586) += salsa20-i586.o obj-$(CONFIG_CRYPTO_SERPENT_SSE2_586) += serpent-sse2-i586.o obj-$(CONFIG_CRYPTO_AES_X86_64) += aes-x86_64.o +obj-$(CONFIG_CRYPTO_CAMELLIA_X86_64) += camellia-x86_64.o obj-$(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 @@ -25,6 +26,7 @@ salsa20-i586-y := salsa20-i586-asm_32.o salsa20_glue.o serpent-sse2-i586-y := serpent-sse2-i586-asm_32.o serpent_sse2_glue.o aes-x86_64-y := aes-x86_64-asm_64.o aes_glue.o +camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_glue.o 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 diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 545d0ce5981..c799352e24f 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -28,6 +28,7 @@ #include <crypto/aes.h> #include <crypto/cryptd.h> #include <crypto/ctr.h> +#include <asm/cpu_device_id.h> #include <asm/i387.h> #include <asm/aes.h> #include <crypto/scatterwalk.h> @@ -1107,12 +1108,12 @@ static int __driver_rfc4106_encrypt(struct aead_request *req) one_entry_in_sg = 1; scatterwalk_start(&src_sg_walk, req->src); scatterwalk_start(&assoc_sg_walk, req->assoc); - src = scatterwalk_map(&src_sg_walk, 0); - assoc = scatterwalk_map(&assoc_sg_walk, 0); + src = scatterwalk_map(&src_sg_walk); + assoc = scatterwalk_map(&assoc_sg_walk); dst = src; if (unlikely(req->src != req->dst)) { scatterwalk_start(&dst_sg_walk, req->dst); - dst = scatterwalk_map(&dst_sg_walk, 0); + dst = scatterwalk_map(&dst_sg_walk); } } else { @@ -1136,11 +1137,11 @@ static int __driver_rfc4106_encrypt(struct aead_request *req) * back to the packet. */ if (one_entry_in_sg) { if (unlikely(req->src != req->dst)) { - scatterwalk_unmap(dst, 0); + scatterwalk_unmap(dst); scatterwalk_done(&dst_sg_walk, 0, 0); } - scatterwalk_unmap(src, 0); - scatterwalk_unmap(assoc, 0); + scatterwalk_unmap(src); + scatterwalk_unmap(assoc); scatterwalk_done(&src_sg_walk, 0, 0); scatterwalk_done(&assoc_sg_walk, 0, 0); } else { @@ -1189,12 +1190,12 @@ static int __driver_rfc4106_decrypt(struct aead_request *req) one_entry_in_sg = 1; scatterwalk_start(&src_sg_walk, req->src); scatterwalk_start(&assoc_sg_walk, req->assoc); - src = scatterwalk_map(&src_sg_walk, 0); - assoc = scatterwalk_map(&assoc_sg_walk, 0); + src = scatterwalk_map(&src_sg_walk); + assoc = scatterwalk_map(&assoc_sg_walk); dst = src; if (unlikely(req->src != req->dst)) { scatterwalk_start(&dst_sg_walk, req->dst); - dst = scatterwalk_map(&dst_sg_walk, 0); + dst = scatterwalk_map(&dst_sg_walk); } } else { @@ -1219,11 +1220,11 @@ static int __driver_rfc4106_decrypt(struct aead_request *req) if (one_entry_in_sg) { if (unlikely(req->src != req->dst)) { - scatterwalk_unmap(dst, 0); + scatterwalk_unmap(dst); scatterwalk_done(&dst_sg_walk, 0, 0); } - scatterwalk_unmap(src, 0); - scatterwalk_unmap(assoc, 0); + scatterwalk_unmap(src); + scatterwalk_unmap(assoc); scatterwalk_done(&src_sg_walk, 0, 0); scatterwalk_done(&assoc_sg_walk, 0, 0); } else { @@ -1253,14 +1254,19 @@ static struct crypto_alg __rfc4106_alg = { }; #endif + +static const struct x86_cpu_id aesni_cpu_id[] = { + X86_FEATURE_MATCH(X86_FEATURE_AES), + {} +}; +MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id); + static int __init aesni_init(void) { int err; - if (!cpu_has_aes) { - printk(KERN_INFO "Intel AES-NI instructions are not detected.\n"); + if (!x86_match_cpu(aesni_cpu_id)) return -ENODEV; - } if ((err = crypto_fpu_init())) goto fpu_err; diff --git a/arch/x86/crypto/blowfish_glue.c b/arch/x86/crypto/blowfish_glue.c index b05aa163d55..7967474de8f 100644 --- a/arch/x86/crypto/blowfish_glue.c +++ b/arch/x86/crypto/blowfish_glue.c @@ -25,6 +25,7 @@ * */ +#include <asm/processor.h> #include <crypto/blowfish.h> #include <linux/crypto.h> #include <linux/init.h> @@ -76,27 +77,6 @@ static void blowfish_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) blowfish_dec_blk(crypto_tfm_ctx(tfm), dst, src); } -static struct crypto_alg bf_alg = { - .cra_name = "blowfish", - .cra_driver_name = "blowfish-asm", - .cra_priority = 200, - .cra_flags = CRYPTO_ALG_TYPE_CIPHER, - .cra_blocksize = BF_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct bf_ctx), - .cra_alignmask = 3, - .cra_module = THIS_MODULE, - .cra_list = LIST_HEAD_INIT(bf_alg.cra_list), - .cra_u = { - .cipher = { - .cia_min_keysize = BF_MIN_KEY_SIZE, - .cia_max_keysize = BF_MAX_KEY_SIZE, - .cia_setkey = blowfish_setkey, - .cia_encrypt = blowfish_encrypt, - .cia_decrypt = blowfish_decrypt, - } - } -}; - static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk, void (*fn)(struct bf_ctx *, u8 *, const u8 *), void (*fn_4way)(struct bf_ctx *, u8 *, const u8 *)) @@ -160,28 +140,6 @@ static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, return ecb_crypt(desc, &walk, blowfish_dec_blk, blowfish_dec_blk_4way); } -static struct crypto_alg blk_ecb_alg = { - .cra_name = "ecb(blowfish)", - .cra_driver_name = "ecb-blowfish-asm", - .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = BF_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct bf_ctx), - .cra_alignmask = 0, - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_list = LIST_HEAD_INIT(blk_ecb_alg.cra_list), - .cra_u = { - .blkcipher = { - .min_keysize = BF_MIN_KEY_SIZE, - .max_keysize = BF_MAX_KEY_SIZE, - .setkey = blowfish_setkey, - .encrypt = ecb_encrypt, - .decrypt = ecb_decrypt, - }, - }, -}; - static unsigned int __cbc_encrypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk) { @@ -307,29 +265,6 @@ static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, return err; } -static struct crypto_alg blk_cbc_alg = { - .cra_name = "cbc(blowfish)", - .cra_driver_name = "cbc-blowfish-asm", - .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = BF_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct bf_ctx), - .cra_alignmask = 0, - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_list = LIST_HEAD_INIT(blk_cbc_alg.cra_list), - .cra_u = { - .blkcipher = { - .min_keysize = BF_MIN_KEY_SIZE, - .max_keysize = BF_MAX_KEY_SIZE, - .ivsize = BF_BLOCK_SIZE, - .setkey = blowfish_setkey, - .encrypt = cbc_encrypt, - .decrypt = cbc_decrypt, - }, - }, -}; - static void ctr_crypt_final(struct bf_ctx *ctx, struct blkcipher_walk *walk) { u8 *ctrblk = walk->iv; @@ -423,7 +358,67 @@ static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst, return err; } -static struct crypto_alg blk_ctr_alg = { +static struct crypto_alg bf_algs[4] = { { + .cra_name = "blowfish", + .cra_driver_name = "blowfish-asm", + .cra_priority = 200, + .cra_flags = CRYPTO_ALG_TYPE_CIPHER, + .cra_blocksize = BF_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct bf_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(bf_algs[0].cra_list), + .cra_u = { + .cipher = { + .cia_min_keysize = BF_MIN_KEY_SIZE, + .cia_max_keysize = BF_MAX_KEY_SIZE, + .cia_setkey = blowfish_setkey, + .cia_encrypt = blowfish_encrypt, + .cia_decrypt = blowfish_decrypt, + } + } +}, { + .cra_name = "ecb(blowfish)", + .cra_driver_name = "ecb-blowfish-asm", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = BF_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct bf_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(bf_algs[1].cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = BF_MIN_KEY_SIZE, + .max_keysize = BF_MAX_KEY_SIZE, + .setkey = blowfish_setkey, + .encrypt = ecb_encrypt, + .decrypt = ecb_decrypt, + }, + }, +}, { + .cra_name = "cbc(blowfish)", + .cra_driver_name = "cbc-blowfish-asm", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = BF_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct bf_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(bf_algs[2].cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = BF_MIN_KEY_SIZE, + .max_keysize = BF_MAX_KEY_SIZE, + .ivsize = BF_BLOCK_SIZE, + .setkey = blowfish_setkey, + .encrypt = cbc_encrypt, + .decrypt = cbc_decrypt, + }, + }, +}, { .cra_name = "ctr(blowfish)", .cra_driver_name = "ctr-blowfish-asm", .cra_priority = 300, @@ -433,7 +428,7 @@ static struct crypto_alg blk_ctr_alg = { .cra_alignmask = 0, .cra_type = &crypto_blkcipher_type, .cra_module = THIS_MODULE, - .cra_list = LIST_HEAD_INIT(blk_ctr_alg.cra_list), + .cra_list = LIST_HEAD_INIT(bf_algs[3].cra_list), .cra_u = { .blkcipher = { .min_keysize = BF_MIN_KEY_SIZE, @@ -444,43 +439,45 @@ static struct crypto_alg blk_ctr_alg = { .decrypt = ctr_crypt, }, }, -}; +} }; + +static bool is_blacklisted_cpu(void) +{ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return false; + + if (boot_cpu_data.x86 == 0x0f) { + /* + * On Pentium 4, blowfish-x86_64 is slower than generic C + * implementation because use of 64bit rotates (which are really + * slow on P4). Therefore blacklist P4s. + */ + return true; + } + + return false; +} + +static int force; +module_param(force, int, 0); +MODULE_PARM_DESC(force, "Force module load, ignore CPU blacklist"); static int __init init(void) { - int err; + if (!force && is_blacklisted_cpu()) { + printk(KERN_INFO + "blowfish-x86_64: performance on this CPU " + "would be suboptimal: disabling " + "blowfish-x86_64.\n"); + return -ENODEV; + } - err = crypto_register_alg(&bf_alg); - if (err) - goto bf_err; - err = crypto_register_alg(&blk_ecb_alg); - if (err) - goto ecb_err; - err = crypto_register_alg(&blk_cbc_alg); - if (err) - goto cbc_err; - err = crypto_register_alg(&blk_ctr_alg); - if (err) - goto ctr_err; - - return 0; - -ctr_err: - crypto_unregister_alg(&blk_cbc_alg); -cbc_err: - crypto_unregister_alg(&blk_ecb_alg); -ecb_err: - crypto_unregister_alg(&bf_alg); -bf_err: - return err; + return crypto_register_algs(bf_algs, ARRAY_SIZE(bf_algs)); } static void __exit fini(void) { - crypto_unregister_alg(&blk_ctr_alg); - crypto_unregister_alg(&blk_cbc_alg); - crypto_unregister_alg(&blk_ecb_alg); - crypto_unregister_alg(&bf_alg); + crypto_unregister_algs(bf_algs, ARRAY_SIZE(bf_algs)); } module_init(init); diff --git a/arch/x86/crypto/camellia-x86_64-asm_64.S b/arch/x86/crypto/camellia-x86_64-asm_64.S new file mode 100644 index 00000000000..0b3374335fd --- /dev/null +++ b/arch/x86/crypto/camellia-x86_64-asm_64.S @@ -0,0 +1,520 @@ +/* + * Camellia Cipher Algorithm (x86_64) + * + * Copyright (C) 2012 Jussi Kivilinna <jussi.kivilinna@mbnet.fi> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 + * USA + * + */ + +.file "camellia-x86_64-asm_64.S" +.text + +.extern camellia_sp10011110; +.extern camellia_sp22000222; +.extern camellia_sp03303033; +.extern camellia_sp00444404; +.extern camellia_sp02220222; +.extern camellia_sp30333033; +.extern camellia_sp44044404; +.extern camellia_sp11101110; + +#define sp10011110 camellia_sp10011110 +#define sp22000222 camellia_sp22000222 +#define sp03303033 camellia_sp03303033 +#define sp00444404 camellia_sp00444404 +#define sp02220222 camellia_sp02220222 +#define sp30333033 camellia_sp30333033 +#define sp44044404 camellia_sp44044404 +#define sp11101110 camellia_sp11101110 + +#define CAMELLIA_TABLE_BYTE_LEN 272 + +/* struct camellia_ctx: */ +#define key_table 0 +#define key_length CAMELLIA_TABLE_BYTE_LEN + +/* register macros */ +#define CTX %rdi +#define RIO %rsi +#define RIOd %esi + +#define RAB0 %rax +#define RCD0 %rcx +#define RAB1 %rbx +#define RCD1 %rdx + +#define RAB0d %eax +#define RCD0d %ecx +#define RAB1d %ebx +#define RCD1d %edx + +#define RAB0bl %al +#define RCD0bl %cl +#define RAB1bl %bl +#define RCD1bl %dl + +#define RAB0bh %ah +#define RCD0bh %ch +#define RAB1bh %bh +#define RCD1bh %dh + +#define RT0 %rsi +#define RT1 %rbp +#define RT2 %r8 + +#define RT0d %esi +#define RT1d %ebp +#define RT2d %r8d + +#define RT2bl %r8b + +#define RXOR %r9 +#define RRBP %r10 +#define RDST %r11 + +#define RXORd %r9d +#define RXORbl %r9b + +#define xor2ror16(T0, T1, tmp1, tmp2, ab, dst) \ + movzbl ab ## bl, tmp2 ## d; \ + movzbl ab ## bh, tmp1 ## d; \ + rorq $16, ab; \ + xorq T0(, tmp2, 8), dst; \ + xorq T1(, tmp1, 8), dst; + +/********************************************************************** + 1-way camellia + **********************************************************************/ +#define roundsm(ab, subkey, cd) \ + movq (key_table + ((subkey) * 2) * 4)(CTX), RT2; \ + \ + xor2ror16(sp00444404, sp03303033, RT0, RT1, ab ## 0, cd ## 0); \ + xor2ror16(sp22000222, sp10011110, RT0, RT1, ab ## 0, RT2); \ + xor2ror16(sp11101110, sp44044404, RT0, RT1, ab ## 0, cd ## 0); \ + xor2ror16(sp30333033, sp02220222, RT0, RT1, ab ## 0, RT2); \ + \ + xorq RT2, cd ## 0; + +#define fls(l, r, kl, kr) \ + movl (key_table + ((kl) * 2) * 4)(CTX), RT0d; \ + andl l ## 0d, RT0d; \ + roll $1, RT0d; \ + shlq $32, RT0; \ + xorq RT0, l ## 0; \ + movq (key_table + ((kr) * 2) * 4)(CTX), RT1; \ + orq r ## 0, RT1; \ + shrq $32, RT1; \ + xorq RT1, r ## 0; \ + \ + movq (key_table + ((kl) * 2) * 4)(CTX), RT2; \ + orq l ## 0, RT2; \ + shrq $32, RT2; \ + xorq RT2, l ## 0; \ + movl (key_table + ((kr) * 2) * 4)(CTX), RT0d; \ + andl r ## 0d, RT0d; \ + roll $1, RT0d; \ + shlq $32, RT0; \ + xorq RT0, r ## 0; + +#define enc_rounds(i) \ + roundsm(RAB, i + 2, RCD); \ + roundsm(RCD, i + 3, RAB); \ + roundsm(RAB, i + 4, RCD); \ + roundsm(RCD, i + 5, RAB); \ + roundsm(RAB, i + 6, RCD); \ + roundsm(RCD, i + 7, RAB); + +#define enc_fls(i) \ + fls(RAB, RCD, i + 0, i + 1); + +#define enc_inpack() \ + movq (RIO), RAB0; \ + bswapq RAB0; \ + rolq $32, RAB0; \ + movq 4*2(RIO), RCD0; \ + bswapq RCD0; \ + rorq $32, RCD0; \ + xorq key_table(CTX), RAB0; + +#define enc_outunpack(op, max) \ + xorq key_table(CTX, max, 8), RCD0; \ + rorq $32, RCD0; \ + bswapq RCD0; \ + op ## q RCD0, (RIO); \ + rolq $32, RAB0; \ + bswapq RAB0; \ + op ## q RAB0, 4*2(RIO); + +#define dec_rounds(i) \ + roundsm(RAB, i + 7, RCD); \ + roundsm(RCD, i + 6, RAB); \ + roundsm(RAB, i + 5, RCD); \ + roundsm(RCD, i + 4, RAB); \ + roundsm(RAB, i + 3, RCD); \ + roundsm(RCD, i + 2, RAB); + +#define dec_fls(i) \ + fls(RAB, RCD, i + 1, i + 0); + +#define dec_inpack(max) \ + movq (RIO), RAB0; \ + bswapq RAB0; \ + rolq $32, RAB0; \ + movq 4*2(RIO), RCD0; \ + bswapq RCD0; \ + rorq $32, RCD0; \ + xorq key_table(CTX, max, 8), RAB0; + +#define dec_outunpack() \ + xorq key_table(CTX), RCD0; \ + rorq $32, RCD0; \ + bswapq RCD0; \ + movq RCD0, (RIO); \ + rolq $32, RAB0; \ + bswapq RAB0; \ + movq RAB0, 4*2(RIO); + +.global __camellia_enc_blk; +.type __camellia_enc_blk,@function; + +__camellia_enc_blk: + /* input: + * %rdi: ctx, CTX + * %rsi: dst + * %rdx: src + * %rcx: bool xor + */ + movq %rbp, RRBP; + + movq %rcx, RXOR; + movq %rsi, RDST; + movq %rdx, RIO; + + enc_inpack(); + + enc_rounds(0); + enc_fls(8); + enc_rounds(8); + enc_fls(16); + enc_rounds(16); + movl $24, RT1d; /* max */ + + cmpb $16, key_length(CTX); + je __enc_done; + + enc_fls(24); + enc_rounds(24); + movl $32, RT1d; /* max */ + +__enc_done: + testb RXORbl, RXORbl; + movq RDST, RIO; + + jnz __enc_xor; + + enc_outunpack(mov, RT1); + + movq RRBP, %rbp; + ret; + +__enc_xor: + enc_outunpack(xor, RT1); + + movq RRBP, %rbp; + ret; + +.global camellia_dec_blk; +.type camellia_dec_blk,@function; + +camellia_dec_blk: + /* input: + * %rdi: ctx, CTX + * %rsi: dst + * %rdx: src + */ + cmpl $16, key_length(CTX); + movl $32, RT2d; + movl $24, RXORd; + cmovel RXORd, RT2d; /* max */ + + movq %rbp, RRBP; + movq %rsi, RDST; + movq %rdx, RIO; + + dec_inpack(RT2); + + cmpb $24, RT2bl; + je __dec_rounds16; + + dec_rounds(24); + dec_fls(24); + +__dec_rounds16: + dec_rounds(16); + dec_fls(16); + dec_rounds(8); + dec_fls(8); + dec_rounds(0); + + movq RDST, RIO; + + dec_outunpack(); + + movq RRBP, %rbp; + ret; + +/********************************************************************** + 2-way camellia + **********************************************************************/ +#define roundsm2(ab, subkey, cd) \ + movq (key_table + ((subkey) * 2) * 4)(CTX), RT2; \ + xorq RT2, cd ## 1; \ + \ + xor2ror16(sp00444404, sp03303033, RT0, RT1, ab ## 0, cd ## 0); \ + xor2ror16(sp22000222, sp10011110, RT0, RT1, ab ## 0, RT2); \ + xor2ror16(sp11101110, sp44044404, RT0, RT1, ab ## 0, cd ## 0); \ + xor2ror16(sp30333033, sp02220222, RT0, RT1, ab ## 0, RT2); \ + \ + xor2ror16(sp00444404, sp03303033, RT0, RT1, ab ## 1, cd ## 1); \ + xorq RT2, cd ## 0; \ + xor2ror16(sp22000222, sp10011110, RT0, RT1, ab ## 1, cd ## 1); \ + xor2ror16(sp11101110, sp44044404, RT0, RT1, ab ## 1, cd ## 1); \ + xor2ror16(sp30333033, sp02220222, RT0, RT1, ab ## 1, cd ## 1); + +#define fls2(l, r, kl, kr) \ + movl (key_table + ((kl) * 2) * 4)(CTX), RT0d; \ + andl l ## 0d, RT0d; \ + roll $1, RT0d; \ + shlq $32, RT0; \ + xorq RT0, l ## 0; \ + movq (key_table + ((kr) * 2) * 4)(CTX), RT1; \ + orq r ## 0, RT1; \ + shrq $32, RT1; \ + xorq RT1, r ## 0; \ + \ + movl (key_table + ((kl) * 2) * 4)(CTX), RT2d; \ + andl l ## 1d, RT2d; \ + roll $1, RT2d; \ + shlq $32, RT2; \ + xorq RT2, l ## 1; \ + movq (key_table + ((kr) * 2) * 4)(CTX), RT0; \ + orq r ## 1, RT0; \ + shrq $32, RT0; \ + xorq RT0, r ## 1; \ + \ + movq (key_table + ((kl) * 2) * 4)(CTX), RT1; \ + orq l ## 0, RT1; \ + shrq $32, RT1; \ + xorq RT1, l ## 0; \ + movl (key_table + ((kr) * 2) * 4)(CTX), RT2d; \ + andl r ## 0d, RT2d; \ + roll $1, RT2d; \ + shlq $32, RT2; \ + xorq RT2, r ## 0; \ + \ + movq (key_table + ((kl) * 2) * 4)(CTX), RT0; \ + orq l ## 1, RT0; \ + shrq $32, RT0; \ + xorq RT0, l ## 1; \ + movl (key_table + ((kr) * 2) * 4)(CTX), RT1d; \ + andl r ## 1d, RT1d; \ + roll $1, RT1d; \ + shlq $32, RT1; \ + xorq RT1, r ## 1; + +#define enc_rounds2(i) \ + roundsm2(RAB, i + 2, RCD); \ + roundsm2(RCD, i + 3, RAB); \ + roundsm2(RAB, i + 4, RCD); \ + roundsm2(RCD, i + 5, RAB); \ + roundsm2(RAB, i + 6, RCD); \ + roundsm2(RCD, i + 7, RAB); + +#define enc_fls2(i) \ + fls2(RAB, RCD, i + 0, i + 1); + +#define enc_inpack2() \ + movq (RIO), RAB0; \ + bswapq RAB0; \ + rorq $32, RAB0; \ + movq 4*2(RIO), RCD0; \ + bswapq RCD0; \ + rolq $32, RCD0; \ + xorq key_table(CTX), RAB0; \ + \ + movq 8*2(RIO), RAB1; \ + bswapq RAB1; \ + rorq $32, RAB1; \ + movq 12*2(RIO), RCD1; \ + bswapq RCD1; \ + rolq $32, RCD1; \ + xorq key_table(CTX), RAB1; + +#define enc_outunpack2(op, max) \ + xorq key_table(CTX, max, 8), RCD0; \ + rolq $32, RCD0; \ + bswapq RCD0; \ + op ## q RCD0, (RIO); \ + rorq $32, RAB0; \ + bswapq RAB0; \ + op ## q RAB0, 4*2(RIO); \ + \ + xorq key_table(CTX, max, 8), RCD1; \ + rolq $32, RCD1; \ + bswapq RCD1; \ + op ## q RCD1, 8*2(RIO); \ + rorq $32, RAB1; \ + bswapq RAB1; \ + op ## q RAB1, 12*2(RIO); + +#define dec_rounds2(i) \ + roundsm2(RAB, i + 7, RCD); \ + roundsm2(RCD, i + 6, RAB); \ + roundsm2(RAB, i + 5, RCD); \ + roundsm2(RCD, i + 4, RAB); \ + roundsm2(RAB, i + 3, RCD); \ + roundsm2(RCD, i + 2, RAB); + +#define dec_fls2(i) \ + fls2(RAB, RCD, i + 1, i + 0); + +#define dec_inpack2(max) \ + movq (RIO), RAB0; \ + bswapq RAB0; \ + rorq $32, RAB0; \ + movq 4*2(RIO), RCD0; \ + bswapq RCD0; \ + rolq $32, RCD0; \ + xorq key_table(CTX, max, 8), RAB0; \ + \ + movq 8*2(RIO), RAB1; \ + bswapq RAB1; \ + rorq $32, RAB1; \ + movq 12*2(RIO), RCD1; \ + bswapq RCD1; \ + rolq $32, RCD1; \ + xorq key_table(CTX, max, 8), RAB1; + +#define dec_outunpack2() \ + xorq key_table(CTX), RCD0; \ + rolq $32, RCD0; \ + bswapq RCD0; \ + movq RCD0, (RIO); \ + rorq $32, RAB0; \ + bswapq RAB0; \ + movq RAB0, 4*2(RIO); \ + \ + xorq key_table(CTX), RCD1; \ + rolq $32, RCD1; \ + bswapq RCD1; \ + movq RCD1, 8*2(RIO); \ + rorq $32, RAB1; \ + bswapq RAB1; \ + movq RAB1, 12*2(RIO); + +.global __camellia_enc_blk_2way; +.type __camellia_enc_blk_2way,@function; + +__camellia_enc_blk_2way: + /* input: + * %rdi: ctx, CTX + * %rsi: dst + * %rdx: src + * %rcx: bool xor + */ + pushq %rbx; + + movq %rbp, RRBP; + movq %rcx, RXOR; + movq %rsi, RDST; + movq %rdx, RIO; + + enc_inpack2(); + + enc_rounds2(0); + enc_fls2(8); + enc_rounds2(8); + enc_fls2(16); + enc_rounds2(16); + movl $24, RT2d; /* max */ + + cmpb $16, key_length(CTX); + je __enc2_done; + + enc_fls2(24); + enc_rounds2(24); + movl $32, RT2d; /* max */ + +__enc2_done: + test RXORbl, RXORbl; + movq RDST, RIO; + jnz __enc2_xor; + + enc_outunpack2(mov, RT2); + + movq RRBP, %rbp; + popq %rbx; + ret; + +__enc2_xor: + enc_outunpack2(xor, RT2); + + movq RRBP, %rbp; + popq %rbx; + ret; + +.global camellia_dec_blk_2way; +.type camellia_dec_blk_2way,@function; + +camellia_dec_blk_2way: + /* input: + * %rdi: ctx, CTX + * %rsi: dst + * %rdx: src + */ + cmpl $16, key_length(CTX); + movl $32, RT2d; + movl $24, RXORd; + cmovel RXORd, RT2d; /* max */ + + movq %rbx, RXOR; + movq %rbp, RRBP; + movq %rsi, RDST; + movq %rdx, RIO; + + dec_inpack2(RT2); + + cmpb $24, RT2bl; + je __dec2_rounds16; + + dec_rounds2(24); + dec_fls2(24); + +__dec2_rounds16: + dec_rounds2(16); + dec_fls2(16); + dec_rounds2(8); + dec_fls2(8); + dec_rounds2(0); + + movq RDST, RIO; + + dec_outunpack2(); + + movq RRBP, %rbp; + movq RXOR, %rbx; + ret; diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c new file mode 100644 index 00000000000..3306dc0b139 --- /dev/null +++ b/arch/x86/crypto/camellia_glue.c @@ -0,0 +1,1952 @@ +/* + * Glue Code for assembler optimized version of Camellia + * + * Copyright (c) 2012 Jussi Kivilinna <jussi.kivilinna@mbnet.fi> + * + * Camellia parts based on code by: + * Copyright (C) 2006 NTT (Nippon Telegraph and Telephone Corporation) + * CBC & ECB parts based on code (crypto/cbc.c,ecb.c) by: + * Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au> + * CTR part based on code (crypto/ctr.c) by: + * (C) Copyright IBM Corp. 2007 - Joy Latten <latten@us.ibm.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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 + * USA + * + */ + +#include <asm/processor.h> +#include <asm/unaligned.h> +#include <linux/crypto.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/types.h> +#include <crypto/algapi.h> +#include <crypto/b128ops.h> +#include <crypto/lrw.h> +#include <crypto/xts.h> + +#define CAMELLIA_MIN_KEY_SIZE 16 +#define CAMELLIA_MAX_KEY_SIZE 32 +#define CAMELLIA_BLOCK_SIZE 16 +#define CAMELLIA_TABLE_BYTE_LEN 272 + +struct camellia_ctx { + u64 key_table[CAMELLIA_TABLE_BYTE_LEN / sizeof(u64)]; + u32 key_length; +}; + +/* regular block cipher functions */ +asmlinkage void __camellia_enc_blk(struct camellia_ctx *ctx, u8 *dst, + const u8 *src, bool xor); +asmlinkage void camellia_dec_blk(struct camellia_ctx *ctx, u8 *dst, + const u8 *src); + +/* 2-way parallel cipher functions */ +asmlinkage void __camellia_enc_blk_2way(struct camellia_ctx *ctx, u8 *dst, + const u8 *src, bool xor); +asmlinkage void camellia_dec_blk_2way(struct camellia_ctx *ctx, u8 *dst, + const u8 *src); + +static inline void camellia_enc_blk(struct camellia_ctx *ctx, u8 *dst, + const u8 *src) +{ + __camellia_enc_blk(ctx, dst, src, false); +} + +static inline void camellia_enc_blk_xor(struct camellia_ctx *ctx, u8 *dst, + const u8 *src) +{ + __camellia_enc_blk(ctx, dst, src, true); +} + +static inline void camellia_enc_blk_2way(struct camellia_ctx *ctx, u8 *dst, + const u8 *src) +{ + __camellia_enc_blk_2way(ctx, dst, src, false); +} + +static inline void camellia_enc_blk_xor_2way(struct camellia_ctx *ctx, u8 *dst, + const u8 *src) +{ + __camellia_enc_blk_2way(ctx, dst, src, true); +} + +static void camellia_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) +{ + camellia_enc_blk(crypto_tfm_ctx(tfm), dst, src); +} + +static void camellia_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) +{ + camellia_dec_blk(crypto_tfm_ctx(tfm), dst, src); +} + +/* camellia sboxes */ +const u64 camellia_sp10011110[256] = { + 0x7000007070707000, 0x8200008282828200, 0x2c00002c2c2c2c00, + 0xec0000ecececec00, 0xb30000b3b3b3b300, 0x2700002727272700, + 0xc00000c0c0c0c000, 0xe50000e5e5e5e500, 0xe40000e4e4e4e400, + 0x8500008585858500, 0x5700005757575700, 0x3500003535353500, + 0xea0000eaeaeaea00, 0x0c00000c0c0c0c00, 0xae0000aeaeaeae00, + 0x4100004141414100, 0x2300002323232300, 0xef0000efefefef00, + 0x6b00006b6b6b6b00, 0x9300009393939300, 0x4500004545454500, + 0x1900001919191900, 0xa50000a5a5a5a500, 0x2100002121212100, + 0xed0000edededed00, 0x0e00000e0e0e0e00, 0x4f00004f4f4f4f00, + 0x4e00004e4e4e4e00, 0x1d00001d1d1d1d00, 0x6500006565656500, + 0x9200009292929200, 0xbd0000bdbdbdbd00, 0x8600008686868600, + 0xb80000b8b8b8b800, 0xaf0000afafafaf00, 0x8f00008f8f8f8f00, + 0x7c00007c7c7c7c00, 0xeb0000ebebebeb00, 0x1f00001f1f1f1f00, + 0xce0000cececece00, 0x3e00003e3e3e3e00, 0x3000003030303000, + 0xdc0000dcdcdcdc00, 0x5f00005f5f5f5f00, 0x5e00005e5e5e5e00, + 0xc50000c5c5c5c500, 0x0b00000b0b0b0b00, 0x1a00001a1a1a1a00, + 0xa60000a6a6a6a600, 0xe10000e1e1e1e100, 0x3900003939393900, + 0xca0000cacacaca00, 0xd50000d5d5d5d500, 0x4700004747474700, + 0x5d00005d5d5d5d00, 0x3d00003d3d3d3d00, 0xd90000d9d9d9d900, + 0x0100000101010100, 0x5a00005a5a5a5a00, 0xd60000d6d6d6d600, + 0x5100005151515100, 0x5600005656565600, 0x6c00006c6c6c6c00, + 0x4d00004d4d4d4d00, 0x8b00008b8b8b8b00, 0x0d00000d0d0d0d00, + 0x9a00009a9a9a9a00, 0x6600006666666600, 0xfb0000fbfbfbfb00, + 0xcc0000cccccccc00, 0xb00000b0b0b0b000, 0x2d00002d2d2d2d00, + 0x7400007474747400, 0x1200001212121200, 0x2b00002b2b2b2b00, + 0x2000002020202000, 0xf00000f0f0f0f000, 0xb10000b1b1b1b100, + 0x8400008484848400, 0x9900009999999900, 0xdf0000dfdfdfdf00, + 0x4c00004c4c4c4c00, 0xcb0000cbcbcbcb00, 0xc20000c2c2c2c200, + 0x3400003434343400, 0x7e00007e7e7e7e00, 0x7600007676767600, + 0x0500000505050500, 0x6d00006d6d6d6d00, 0xb70000b7b7b7b700, + 0xa90000a9a9a9a900, 0x3100003131313100, 0xd10000d1d1d1d100, + 0x1700001717171700, 0x0400000404040400, 0xd70000d7d7d7d700, + 0x1400001414141400, 0x5800005858585800, 0x3a00003a3a3a3a00, + 0x6100006161616100, 0xde0000dededede00, 0x1b00001b1b1b1b00, + 0x1100001111111100, 0x1c00001c1c1c1c00, 0x3200003232323200, + 0x0f00000f0f0f0f00, 0x9c00009c9c9c9c00, 0x1600001616161600, + 0x5300005353535300, 0x1800001818181800, 0xf20000f2f2f2f200, + 0x2200002222222200, 0xfe0000fefefefe00, 0x4400004444444400, + 0xcf0000cfcfcfcf00, 0xb20000b2b2b2b200, 0xc30000c3c3c3c300, + 0xb50000b5b5b5b500, 0x7a00007a7a7a7a00, 0x9100009191919100, + 0x2400002424242400, 0x0800000808080800, 0xe80000e8e8e8e800, + 0xa80000a8a8a8a800, 0x6000006060606000, 0xfc0000fcfcfcfc00, + 0x6900006969696900, 0x5000005050505000, 0xaa0000aaaaaaaa00, + 0xd00000d0d0d0d000, 0xa00000a0a0a0a000, 0x7d00007d7d7d7d00, + 0xa10000a1a1a1a100, 0x8900008989898900, 0x6200006262626200, + 0x9700009797979700, 0x5400005454545400, 0x5b00005b5b5b5b00, + 0x1e00001e1e1e1e00, 0x9500009595959500, 0xe00000e0e0e0e000, + 0xff0000ffffffff00, 0x6400006464646400, 0xd20000d2d2d2d200, + 0x1000001010101000, 0xc40000c4c4c4c400, 0x0000000000000000, + 0x4800004848484800, 0xa30000a3a3a3a300, 0xf70000f7f7f7f700, + 0x7500007575757500, 0xdb0000dbdbdbdb00, 0x8a00008a8a8a8a00, + 0x0300000303030300, 0xe60000e6e6e6e600, 0xda0000dadadada00, + 0x0900000909090900, 0x3f00003f3f3f3f00, 0xdd0000dddddddd00, + 0x9400009494949400, 0x8700008787878700, 0x5c00005c5c5c5c00, + 0x8300008383838300, 0x0200000202020200, 0xcd0000cdcdcdcd00, + 0x4a00004a4a4a4a00, 0x9000009090909000, 0x3300003333333300, + 0x7300007373737300, 0x6700006767676700, 0xf60000f6f6f6f600, + 0xf30000f3f3f3f300, 0x9d00009d9d9d9d00, 0x7f00007f7f7f7f00, + 0xbf0000bfbfbfbf00, 0xe20000e2e2e2e200, 0x5200005252525200, + 0x9b00009b9b9b9b00, 0xd80000d8d8d8d800, 0x2600002626262600, + 0xc80000c8c8c8c800, 0x3700003737373700, 0xc60000c6c6c6c600, + 0x3b00003b3b3b3b00, 0x8100008181818100, 0x9600009696969600, + 0x6f00006f6f6f6f00, 0x4b00004b4b4b4b00, 0x1300001313131300, + 0xbe0000bebebebe00, 0x6300006363636300, 0x2e00002e2e2e2e00, + 0xe90000e9e9e9e900, 0x7900007979797900, 0xa70000a7a7a7a700, + 0x8c00008c8c8c8c00, 0x9f00009f9f9f9f00, 0x6e00006e6e6e6e00, + 0xbc0000bcbcbcbc00, 0x8e00008e8e8e8e00, 0x2900002929292900, + 0xf50000f5f5f5f500, 0xf90000f9f9f9f900, 0xb60000b6b6b6b600, + 0x2f00002f2f2f2f00, 0xfd0000fdfdfdfd00, 0xb40000b4b4b4b400, + 0x5900005959595900, 0x7800007878787800, 0x9800009898989800, + 0x0600000606060600, 0x6a00006a6a6a6a00, 0xe70000e7e7e7e700, + 0x4600004646464600, 0x7100007171717100, 0xba0000babababa00, + 0xd40000d4d4d4d400, 0x2500002525252500, 0xab0000abababab00, + 0x4200004242424200, 0x8800008888888800, 0xa20000a2a2a2a200, + 0x8d00008d8d8d8d00, 0xfa0000fafafafa00, 0x7200007272727200, + 0x0700000707070700, 0xb90000b9b9b9b900, 0x5500005555555500, + 0xf80000f8f8f8f800, 0xee0000eeeeeeee00, 0xac0000acacacac00, + 0x0a00000a0a0a0a00, 0x3600003636363600, 0x4900004949494900, + 0x2a00002a2a2a2a00, 0x6800006868686800, 0x3c00003c3c3c3c00, + 0x3800003838383800, 0xf10000f1f1f1f100, 0xa40000a4a4a4a400, + 0x4000004040404000, 0x2800002828282800, 0xd30000d3d3d3d300, + 0x7b00007b7b7b7b00, 0xbb0000bbbbbbbb00, 0xc90000c9c9c9c900, + 0x4300004343434300, 0xc10000c1c1c1c100, 0x1500001515151500, + 0xe30000e3e3e3e300, 0xad0000adadadad00, 0xf40000f4f4f4f400, + 0x7700007777777700, 0xc70000c7c7c7c700, 0x8000008080808000, + 0x9e00009e9e9e9e00, +}; + +const u64 camellia_sp22000222[256] = { + 0xe0e0000000e0e0e0, 0x0505000000050505, 0x5858000000585858, + 0xd9d9000000d9d9d9, 0x6767000000676767, 0x4e4e0000004e4e4e, + 0x8181000000818181, 0xcbcb000000cbcbcb, 0xc9c9000000c9c9c9, + 0x0b0b0000000b0b0b, 0xaeae000000aeaeae, 0x6a6a0000006a6a6a, + 0xd5d5000000d5d5d5, 0x1818000000181818, 0x5d5d0000005d5d5d, + 0x8282000000828282, 0x4646000000464646, 0xdfdf000000dfdfdf, + 0xd6d6000000d6d6d6, 0x2727000000272727, 0x8a8a0000008a8a8a, + 0x3232000000323232, 0x4b4b0000004b4b4b, 0x4242000000424242, + 0xdbdb000000dbdbdb, 0x1c1c0000001c1c1c, 0x9e9e0000009e9e9e, + 0x9c9c0000009c9c9c, 0x3a3a0000003a3a3a, 0xcaca000000cacaca, + 0x2525000000252525, 0x7b7b0000007b7b7b, 0x0d0d0000000d0d0d, + 0x7171000000717171, 0x5f5f0000005f5f5f, 0x1f1f0000001f1f1f, + 0xf8f8000000f8f8f8, 0xd7d7000000d7d7d7, 0x3e3e0000003e3e3e, + 0x9d9d0000009d9d9d, 0x7c7c0000007c7c7c, 0x6060000000606060, + 0xb9b9000000b9b9b9, 0xbebe000000bebebe, 0xbcbc000000bcbcbc, + 0x8b8b0000008b8b8b, 0x1616000000161616, 0x3434000000343434, + 0x4d4d0000004d4d4d, 0xc3c3000000c3c3c3, 0x7272000000727272, + 0x9595000000959595, 0xabab000000ababab, 0x8e8e0000008e8e8e, + 0xbaba000000bababa, 0x7a7a0000007a7a7a, 0xb3b3000000b3b3b3, + 0x0202000000020202, 0xb4b4000000b4b4b4, 0xadad000000adadad, + 0xa2a2000000a2a2a2, 0xacac000000acacac, 0xd8d8000000d8d8d8, + 0x9a9a0000009a9a9a, 0x1717000000171717, 0x1a1a0000001a1a1a, + 0x3535000000353535, 0xcccc000000cccccc, 0xf7f7000000f7f7f7, + 0x9999000000999999, 0x6161000000616161, 0x5a5a0000005a5a5a, + 0xe8e8000000e8e8e8, 0x2424000000242424, 0x5656000000565656, + 0x4040000000404040, 0xe1e1000000e1e1e1, 0x6363000000636363, + 0x0909000000090909, 0x3333000000333333, 0xbfbf000000bfbfbf, + 0x9898000000989898, 0x9797000000979797, 0x8585000000858585, + 0x6868000000686868, 0xfcfc000000fcfcfc, 0xecec000000ececec, + 0x0a0a0000000a0a0a, 0xdada000000dadada, 0x6f6f0000006f6f6f, + 0x5353000000535353, 0x6262000000626262, 0xa3a3000000a3a3a3, + 0x2e2e0000002e2e2e, 0x0808000000080808, 0xafaf000000afafaf, + 0x2828000000282828, 0xb0b0000000b0b0b0, 0x7474000000747474, + 0xc2c2000000c2c2c2, 0xbdbd000000bdbdbd, 0x3636000000363636, + 0x2222000000222222, 0x3838000000383838, 0x6464000000646464, + 0x1e1e0000001e1e1e, 0x3939000000393939, 0x2c2c0000002c2c2c, + 0xa6a6000000a6a6a6, 0x3030000000303030, 0xe5e5000000e5e5e5, + 0x4444000000444444, 0xfdfd000000fdfdfd, 0x8888000000888888, + 0x9f9f0000009f9f9f, 0x6565000000656565, 0x8787000000878787, + 0x6b6b0000006b6b6b, 0xf4f4000000f4f4f4, 0x2323000000232323, + 0x4848000000484848, 0x1010000000101010, 0xd1d1000000d1d1d1, + 0x5151000000515151, 0xc0c0000000c0c0c0, 0xf9f9000000f9f9f9, + 0xd2d2000000d2d2d2, 0xa0a0000000a0a0a0, 0x5555000000555555, + 0xa1a1000000a1a1a1, 0x4141000000414141, 0xfafa000000fafafa, + 0x4343000000434343, 0x1313000000131313, 0xc4c4000000c4c4c4, + 0x2f2f0000002f2f2f, 0xa8a8000000a8a8a8, 0xb6b6000000b6b6b6, + 0x3c3c0000003c3c3c, 0x2b2b0000002b2b2b, 0xc1c1000000c1c1c1, + 0xffff000000ffffff, 0xc8c8000000c8c8c8, 0xa5a5000000a5a5a5, + 0x2020000000202020, 0x8989000000898989, 0x0000000000000000, + 0x9090000000909090, 0x4747000000474747, 0xefef000000efefef, + 0xeaea000000eaeaea, 0xb7b7000000b7b7b7, 0x1515000000151515, + 0x0606000000060606, 0xcdcd000000cdcdcd, 0xb5b5000000b5b5b5, + 0x1212000000121212, 0x7e7e0000007e7e7e, 0xbbbb000000bbbbbb, + 0x2929000000292929, 0x0f0f0000000f0f0f, 0xb8b8000000b8b8b8, + 0x0707000000070707, 0x0404000000040404, 0x9b9b0000009b9b9b, + 0x9494000000949494, 0x2121000000212121, 0x6666000000666666, + 0xe6e6000000e6e6e6, 0xcece000000cecece, 0xeded000000ededed, + 0xe7e7000000e7e7e7, 0x3b3b0000003b3b3b, 0xfefe000000fefefe, + 0x7f7f0000007f7f7f, 0xc5c5000000c5c5c5, 0xa4a4000000a4a4a4, + 0x3737000000373737, 0xb1b1000000b1b1b1, 0x4c4c0000004c4c4c, + 0x9191000000919191, 0x6e6e0000006e6e6e, 0x8d8d0000008d8d8d, + 0x7676000000767676, 0x0303000000030303, 0x2d2d0000002d2d2d, + 0xdede000000dedede, 0x9696000000969696, 0x2626000000262626, + 0x7d7d0000007d7d7d, 0xc6c6000000c6c6c6, 0x5c5c0000005c5c5c, + 0xd3d3000000d3d3d3, 0xf2f2000000f2f2f2, 0x4f4f0000004f4f4f, + 0x1919000000191919, 0x3f3f0000003f3f3f, 0xdcdc000000dcdcdc, + 0x7979000000797979, 0x1d1d0000001d1d1d, 0x5252000000525252, + 0xebeb000000ebebeb, 0xf3f3000000f3f3f3, 0x6d6d0000006d6d6d, + 0x5e5e0000005e5e5e, 0xfbfb000000fbfbfb, 0x6969000000696969, + 0xb2b2000000b2b2b2, 0xf0f0000000f0f0f0, 0x3131000000313131, + 0x0c0c0000000c0c0c, 0xd4d4000000d4d4d4, 0xcfcf000000cfcfcf, + 0x8c8c0000008c8c8c, 0xe2e2000000e2e2e2, 0x7575000000757575, + 0xa9a9000000a9a9a9, 0x4a4a0000004a4a4a, 0x5757000000575757, + 0x8484000000848484, 0x1111000000111111, 0x4545000000454545, + 0x1b1b0000001b1b1b, 0xf5f5000000f5f5f5, 0xe4e4000000e4e4e4, + 0x0e0e0000000e0e0e, 0x7373000000737373, 0xaaaa000000aaaaaa, + 0xf1f1000000f1f1f1, 0xdddd000000dddddd, 0x5959000000595959, + 0x1414000000141414, 0x6c6c0000006c6c6c, 0x9292000000929292, + 0x5454000000545454, 0xd0d0000000d0d0d0, 0x7878000000787878, + 0x7070000000707070, 0xe3e3000000e3e3e3, 0x4949000000494949, + 0x8080000000808080, 0x5050000000505050, 0xa7a7000000a7a7a7, + 0xf6f6000000f6f6f6, 0x7777000000777777, 0x9393000000939393, + 0x8686000000868686, 0x8383000000838383, 0x2a2a0000002a2a2a, + 0xc7c7000000c7c7c7, 0x5b5b0000005b5b5b, 0xe9e9000000e9e9e9, + 0xeeee000000eeeeee, 0x8f8f0000008f8f8f, 0x0101000000010101, + 0x3d3d0000003d3d3d, +}; + +const u64 camellia_sp03303033[256] = { + 0x0038380038003838, 0x0041410041004141, 0x0016160016001616, + 0x0076760076007676, 0x00d9d900d900d9d9, 0x0093930093009393, + 0x0060600060006060, 0x00f2f200f200f2f2, 0x0072720072007272, + 0x00c2c200c200c2c2, 0x00abab00ab00abab, 0x009a9a009a009a9a, + 0x0075750075007575, 0x0006060006000606, 0x0057570057005757, + 0x00a0a000a000a0a0, 0x0091910091009191, 0x00f7f700f700f7f7, + 0x00b5b500b500b5b5, 0x00c9c900c900c9c9, 0x00a2a200a200a2a2, + 0x008c8c008c008c8c, 0x00d2d200d200d2d2, 0x0090900090009090, + 0x00f6f600f600f6f6, 0x0007070007000707, 0x00a7a700a700a7a7, + 0x0027270027002727, 0x008e8e008e008e8e, 0x00b2b200b200b2b2, + 0x0049490049004949, 0x00dede00de00dede, 0x0043430043004343, + 0x005c5c005c005c5c, 0x00d7d700d700d7d7, 0x00c7c700c700c7c7, + 0x003e3e003e003e3e, 0x00f5f500f500f5f5, 0x008f8f008f008f8f, + 0x0067670067006767, 0x001f1f001f001f1f, 0x0018180018001818, + 0x006e6e006e006e6e, 0x00afaf00af00afaf, 0x002f2f002f002f2f, + 0x00e2e200e200e2e2, 0x0085850085008585, 0x000d0d000d000d0d, + 0x0053530053005353, 0x00f0f000f000f0f0, 0x009c9c009c009c9c, + 0x0065650065006565, 0x00eaea00ea00eaea, 0x00a3a300a300a3a3, + 0x00aeae00ae00aeae, 0x009e9e009e009e9e, 0x00ecec00ec00ecec, + 0x0080800080008080, 0x002d2d002d002d2d, 0x006b6b006b006b6b, + 0x00a8a800a800a8a8, 0x002b2b002b002b2b, 0x0036360036003636, + 0x00a6a600a600a6a6, 0x00c5c500c500c5c5, 0x0086860086008686, + 0x004d4d004d004d4d, 0x0033330033003333, 0x00fdfd00fd00fdfd, + 0x0066660066006666, 0x0058580058005858, 0x0096960096009696, + 0x003a3a003a003a3a, 0x0009090009000909, 0x0095950095009595, + 0x0010100010001010, 0x0078780078007878, 0x00d8d800d800d8d8, + 0x0042420042004242, 0x00cccc00cc00cccc, 0x00efef00ef00efef, + 0x0026260026002626, 0x00e5e500e500e5e5, 0x0061610061006161, + 0x001a1a001a001a1a, 0x003f3f003f003f3f, 0x003b3b003b003b3b, + 0x0082820082008282, 0x00b6b600b600b6b6, 0x00dbdb00db00dbdb, + 0x00d4d400d400d4d4, 0x0098980098009898, 0x00e8e800e800e8e8, + 0x008b8b008b008b8b, 0x0002020002000202, 0x00ebeb00eb00ebeb, + 0x000a0a000a000a0a, 0x002c2c002c002c2c, 0x001d1d001d001d1d, + 0x00b0b000b000b0b0, 0x006f6f006f006f6f, 0x008d8d008d008d8d, + 0x0088880088008888, 0x000e0e000e000e0e, 0x0019190019001919, + 0x0087870087008787, 0x004e4e004e004e4e, 0x000b0b000b000b0b, + 0x00a9a900a900a9a9, 0x000c0c000c000c0c, 0x0079790079007979, + 0x0011110011001111, 0x007f7f007f007f7f, 0x0022220022002222, + 0x00e7e700e700e7e7, 0x0059590059005959, 0x00e1e100e100e1e1, + 0x00dada00da00dada, 0x003d3d003d003d3d, 0x00c8c800c800c8c8, + 0x0012120012001212, 0x0004040004000404, 0x0074740074007474, + 0x0054540054005454, 0x0030300030003030, 0x007e7e007e007e7e, + 0x00b4b400b400b4b4, 0x0028280028002828, 0x0055550055005555, + 0x0068680068006868, 0x0050500050005050, 0x00bebe00be00bebe, + 0x00d0d000d000d0d0, 0x00c4c400c400c4c4, 0x0031310031003131, + 0x00cbcb00cb00cbcb, 0x002a2a002a002a2a, 0x00adad00ad00adad, + 0x000f0f000f000f0f, 0x00caca00ca00caca, 0x0070700070007070, + 0x00ffff00ff00ffff, 0x0032320032003232, 0x0069690069006969, + 0x0008080008000808, 0x0062620062006262, 0x0000000000000000, + 0x0024240024002424, 0x00d1d100d100d1d1, 0x00fbfb00fb00fbfb, + 0x00baba00ba00baba, 0x00eded00ed00eded, 0x0045450045004545, + 0x0081810081008181, 0x0073730073007373, 0x006d6d006d006d6d, + 0x0084840084008484, 0x009f9f009f009f9f, 0x00eeee00ee00eeee, + 0x004a4a004a004a4a, 0x00c3c300c300c3c3, 0x002e2e002e002e2e, + 0x00c1c100c100c1c1, 0x0001010001000101, 0x00e6e600e600e6e6, + 0x0025250025002525, 0x0048480048004848, 0x0099990099009999, + 0x00b9b900b900b9b9, 0x00b3b300b300b3b3, 0x007b7b007b007b7b, + 0x00f9f900f900f9f9, 0x00cece00ce00cece, 0x00bfbf00bf00bfbf, + 0x00dfdf00df00dfdf, 0x0071710071007171, 0x0029290029002929, + 0x00cdcd00cd00cdcd, 0x006c6c006c006c6c, 0x0013130013001313, + 0x0064640064006464, 0x009b9b009b009b9b, 0x0063630063006363, + 0x009d9d009d009d9d, 0x00c0c000c000c0c0, 0x004b4b004b004b4b, + 0x00b7b700b700b7b7, 0x00a5a500a500a5a5, 0x0089890089008989, + 0x005f5f005f005f5f, 0x00b1b100b100b1b1, 0x0017170017001717, + 0x00f4f400f400f4f4, 0x00bcbc00bc00bcbc, 0x00d3d300d300d3d3, + 0x0046460046004646, 0x00cfcf00cf00cfcf, 0x0037370037003737, + 0x005e5e005e005e5e, 0x0047470047004747, 0x0094940094009494, + 0x00fafa00fa00fafa, 0x00fcfc00fc00fcfc, 0x005b5b005b005b5b, + 0x0097970097009797, 0x00fefe00fe00fefe, 0x005a5a005a005a5a, + 0x00acac00ac00acac, 0x003c3c003c003c3c, 0x004c4c004c004c4c, + 0x0003030003000303, 0x0035350035003535, 0x00f3f300f300f3f3, + 0x0023230023002323, 0x00b8b800b800b8b8, 0x005d5d005d005d5d, + 0x006a6a006a006a6a, 0x0092920092009292, 0x00d5d500d500d5d5, + 0x0021210021002121, 0x0044440044004444, 0x0051510051005151, + 0x00c6c600c600c6c6, 0x007d7d007d007d7d, 0x0039390039003939, + 0x0083830083008383, 0x00dcdc00dc00dcdc, 0x00aaaa00aa00aaaa, + 0x007c7c007c007c7c, 0x0077770077007777, 0x0056560056005656, + 0x0005050005000505, 0x001b1b001b001b1b, 0x00a4a400a400a4a4, + 0x0015150015001515, 0x0034340034003434, 0x001e1e001e001e1e, + 0x001c1c001c001c1c, 0x00f8f800f800f8f8, 0x0052520052005252, + 0x0020200020002020, 0x0014140014001414, 0x00e9e900e900e9e9, + 0x00bdbd00bd00bdbd, 0x00dddd00dd00dddd, 0x00e4e400e400e4e4, + 0x00a1a100a100a1a1, 0x00e0e000e000e0e0, 0x008a8a008a008a8a, + 0x00f1f100f100f1f1, 0x00d6d600d600d6d6, 0x007a7a007a007a7a, + 0x00bbbb00bb00bbbb, 0x00e3e300e300e3e3, 0x0040400040004040, + 0x004f4f004f004f4f, +}; + +const u64 camellia_sp00444404[256] = { + 0x0000707070700070, 0x00002c2c2c2c002c, 0x0000b3b3b3b300b3, + 0x0000c0c0c0c000c0, 0x0000e4e4e4e400e4, 0x0000575757570057, + 0x0000eaeaeaea00ea, 0x0000aeaeaeae00ae, 0x0000232323230023, + 0x00006b6b6b6b006b, 0x0000454545450045, 0x0000a5a5a5a500a5, + 0x0000edededed00ed, 0x00004f4f4f4f004f, 0x00001d1d1d1d001d, + 0x0000929292920092, 0x0000868686860086, 0x0000afafafaf00af, + 0x00007c7c7c7c007c, 0x00001f1f1f1f001f, 0x00003e3e3e3e003e, + 0x0000dcdcdcdc00dc, 0x00005e5e5e5e005e, 0x00000b0b0b0b000b, + 0x0000a6a6a6a600a6, 0x0000393939390039, 0x0000d5d5d5d500d5, + 0x00005d5d5d5d005d, 0x0000d9d9d9d900d9, 0x00005a5a5a5a005a, + 0x0000515151510051, 0x00006c6c6c6c006c, 0x00008b8b8b8b008b, + 0x00009a9a9a9a009a, 0x0000fbfbfbfb00fb, 0x0000b0b0b0b000b0, + 0x0000747474740074, 0x00002b2b2b2b002b, 0x0000f0f0f0f000f0, + 0x0000848484840084, 0x0000dfdfdfdf00df, 0x0000cbcbcbcb00cb, + 0x0000343434340034, 0x0000767676760076, 0x00006d6d6d6d006d, + 0x0000a9a9a9a900a9, 0x0000d1d1d1d100d1, 0x0000040404040004, + 0x0000141414140014, 0x00003a3a3a3a003a, 0x0000dededede00de, + 0x0000111111110011, 0x0000323232320032, 0x00009c9c9c9c009c, + 0x0000535353530053, 0x0000f2f2f2f200f2, 0x0000fefefefe00fe, + 0x0000cfcfcfcf00cf, 0x0000c3c3c3c300c3, 0x00007a7a7a7a007a, + 0x0000242424240024, 0x0000e8e8e8e800e8, 0x0000606060600060, + 0x0000696969690069, 0x0000aaaaaaaa00aa, 0x0000a0a0a0a000a0, + 0x0000a1a1a1a100a1, 0x0000626262620062, 0x0000545454540054, + 0x00001e1e1e1e001e, 0x0000e0e0e0e000e0, 0x0000646464640064, + 0x0000101010100010, 0x0000000000000000, 0x0000a3a3a3a300a3, + 0x0000757575750075, 0x00008a8a8a8a008a, 0x0000e6e6e6e600e6, + 0x0000090909090009, 0x0000dddddddd00dd, 0x0000878787870087, + 0x0000838383830083, 0x0000cdcdcdcd00cd, 0x0000909090900090, + 0x0000737373730073, 0x0000f6f6f6f600f6, 0x00009d9d9d9d009d, + 0x0000bfbfbfbf00bf, 0x0000525252520052, 0x0000d8d8d8d800d8, + 0x0000c8c8c8c800c8, 0x0000c6c6c6c600c6, 0x0000818181810081, + 0x00006f6f6f6f006f, 0x0000131313130013, 0x0000636363630063, + 0x0000e9e9e9e900e9, 0x0000a7a7a7a700a7, 0x00009f9f9f9f009f, + 0x0000bcbcbcbc00bc, 0x0000292929290029, 0x0000f9f9f9f900f9, + 0x00002f2f2f2f002f, 0x0000b4b4b4b400b4, 0x0000787878780078, + 0x0000060606060006, 0x0000e7e7e7e700e7, 0x0000717171710071, + 0x0000d4d4d4d400d4, 0x0000abababab00ab, 0x0000888888880088, + 0x00008d8d8d8d008d, 0x0000727272720072, 0x0000b9b9b9b900b9, + 0x0000f8f8f8f800f8, 0x0000acacacac00ac, 0x0000363636360036, + 0x00002a2a2a2a002a, 0x00003c3c3c3c003c, 0x0000f1f1f1f100f1, + 0x0000404040400040, 0x0000d3d3d3d300d3, 0x0000bbbbbbbb00bb, + 0x0000434343430043, 0x0000151515150015, 0x0000adadadad00ad, + 0x0000777777770077, 0x0000808080800080, 0x0000828282820082, + 0x0000ecececec00ec, 0x0000272727270027, 0x0000e5e5e5e500e5, + 0x0000858585850085, 0x0000353535350035, 0x00000c0c0c0c000c, + 0x0000414141410041, 0x0000efefefef00ef, 0x0000939393930093, + 0x0000191919190019, 0x0000212121210021, 0x00000e0e0e0e000e, + 0x00004e4e4e4e004e, 0x0000656565650065, 0x0000bdbdbdbd00bd, + 0x0000b8b8b8b800b8, 0x00008f8f8f8f008f, 0x0000ebebebeb00eb, + 0x0000cececece00ce, 0x0000303030300030, 0x00005f5f5f5f005f, + 0x0000c5c5c5c500c5, 0x00001a1a1a1a001a, 0x0000e1e1e1e100e1, + 0x0000cacacaca00ca, 0x0000474747470047, 0x00003d3d3d3d003d, + 0x0000010101010001, 0x0000d6d6d6d600d6, 0x0000565656560056, + 0x00004d4d4d4d004d, 0x00000d0d0d0d000d, 0x0000666666660066, + 0x0000cccccccc00cc, 0x00002d2d2d2d002d, 0x0000121212120012, + 0x0000202020200020, 0x0000b1b1b1b100b1, 0x0000999999990099, + 0x00004c4c4c4c004c, 0x0000c2c2c2c200c2, 0x00007e7e7e7e007e, + 0x0000050505050005, 0x0000b7b7b7b700b7, 0x0000313131310031, + 0x0000171717170017, 0x0000d7d7d7d700d7, 0x0000585858580058, + 0x0000616161610061, 0x00001b1b1b1b001b, 0x00001c1c1c1c001c, + 0x00000f0f0f0f000f, 0x0000161616160016, 0x0000181818180018, + 0x0000222222220022, 0x0000444444440044, 0x0000b2b2b2b200b2, + 0x0000b5b5b5b500b5, 0x0000919191910091, 0x0000080808080008, + 0x0000a8a8a8a800a8, 0x0000fcfcfcfc00fc, 0x0000505050500050, + 0x0000d0d0d0d000d0, 0x00007d7d7d7d007d, 0x0000898989890089, + 0x0000979797970097, 0x00005b5b5b5b005b, 0x0000959595950095, + 0x0000ffffffff00ff, 0x0000d2d2d2d200d2, 0x0000c4c4c4c400c4, + 0x0000484848480048, 0x0000f7f7f7f700f7, 0x0000dbdbdbdb00db, + 0x0000030303030003, 0x0000dadadada00da, 0x00003f3f3f3f003f, + 0x0000949494940094, 0x00005c5c5c5c005c, 0x0000020202020002, + 0x00004a4a4a4a004a, 0x0000333333330033, 0x0000676767670067, + 0x0000f3f3f3f300f3, 0x00007f7f7f7f007f, 0x0000e2e2e2e200e2, + 0x00009b9b9b9b009b, 0x0000262626260026, 0x0000373737370037, + 0x00003b3b3b3b003b, 0x0000969696960096, 0x00004b4b4b4b004b, + 0x0000bebebebe00be, 0x00002e2e2e2e002e, 0x0000797979790079, + 0x00008c8c8c8c008c, 0x00006e6e6e6e006e, 0x00008e8e8e8e008e, + 0x0000f5f5f5f500f5, 0x0000b6b6b6b600b6, 0x0000fdfdfdfd00fd, + 0x0000595959590059, 0x0000989898980098, 0x00006a6a6a6a006a, + 0x0000464646460046, 0x0000babababa00ba, 0x0000252525250025, + 0x0000424242420042, 0x0000a2a2a2a200a2, 0x0000fafafafa00fa, + 0x0000070707070007, 0x0000555555550055, 0x0000eeeeeeee00ee, + 0x00000a0a0a0a000a, 0x0000494949490049, 0x0000686868680068, + 0x0000383838380038, 0x0000a4a4a4a400a4, 0x0000282828280028, + 0x00007b7b7b7b007b, 0x0000c9c9c9c900c9, 0x0000c1c1c1c100c1, + 0x0000e3e3e3e300e3, 0x0000f4f4f4f400f4, 0x0000c7c7c7c700c7, + 0x00009e9e9e9e009e, +}; + +const u64 camellia_sp02220222[256] = { + 0x00e0e0e000e0e0e0, 0x0005050500050505, 0x0058585800585858, + 0x00d9d9d900d9d9d9, 0x0067676700676767, 0x004e4e4e004e4e4e, + 0x0081818100818181, 0x00cbcbcb00cbcbcb, 0x00c9c9c900c9c9c9, + 0x000b0b0b000b0b0b, 0x00aeaeae00aeaeae, 0x006a6a6a006a6a6a, + 0x00d5d5d500d5d5d5, 0x0018181800181818, 0x005d5d5d005d5d5d, + 0x0082828200828282, 0x0046464600464646, 0x00dfdfdf00dfdfdf, + 0x00d6d6d600d6d6d6, 0x0027272700272727, 0x008a8a8a008a8a8a, + 0x0032323200323232, 0x004b4b4b004b4b4b, 0x0042424200424242, + 0x00dbdbdb00dbdbdb, 0x001c1c1c001c1c1c, 0x009e9e9e009e9e9e, + 0x009c9c9c009c9c9c, 0x003a3a3a003a3a3a, 0x00cacaca00cacaca, + 0x0025252500252525, 0x007b7b7b007b7b7b, 0x000d0d0d000d0d0d, + 0x0071717100717171, 0x005f5f5f005f5f5f, 0x001f1f1f001f1f1f, + 0x00f8f8f800f8f8f8, 0x00d7d7d700d7d7d7, 0x003e3e3e003e3e3e, + 0x009d9d9d009d9d9d, 0x007c7c7c007c7c7c, 0x0060606000606060, + 0x00b9b9b900b9b9b9, 0x00bebebe00bebebe, 0x00bcbcbc00bcbcbc, + 0x008b8b8b008b8b8b, 0x0016161600161616, 0x0034343400343434, + 0x004d4d4d004d4d4d, 0x00c3c3c300c3c3c3, 0x0072727200727272, + 0x0095959500959595, 0x00ababab00ababab, 0x008e8e8e008e8e8e, + 0x00bababa00bababa, 0x007a7a7a007a7a7a, 0x00b3b3b300b3b3b3, + 0x0002020200020202, 0x00b4b4b400b4b4b4, 0x00adadad00adadad, + 0x00a2a2a200a2a2a2, 0x00acacac00acacac, 0x00d8d8d800d8d8d8, + 0x009a9a9a009a9a9a, 0x0017171700171717, 0x001a1a1a001a1a1a, + 0x0035353500353535, 0x00cccccc00cccccc, 0x00f7f7f700f7f7f7, + 0x0099999900999999, 0x0061616100616161, 0x005a5a5a005a5a5a, + 0x00e8e8e800e8e8e8, 0x0024242400242424, 0x0056565600565656, + 0x0040404000404040, 0x00e1e1e100e1e1e1, 0x0063636300636363, + 0x0009090900090909, 0x0033333300333333, 0x00bfbfbf00bfbfbf, + 0x0098989800989898, 0x0097979700979797, 0x0085858500858585, + 0x0068686800686868, 0x00fcfcfc00fcfcfc, 0x00ececec00ececec, + 0x000a0a0a000a0a0a, 0x00dadada00dadada, 0x006f6f6f006f6f6f, + 0x0053535300535353, 0x0062626200626262, 0x00a3a3a300a3a3a3, + 0x002e2e2e002e2e2e, 0x0008080800080808, 0x00afafaf00afafaf, + 0x0028282800282828, 0x00b0b0b000b0b0b0, 0x0074747400747474, + 0x00c2c2c200c2c2c2, 0x00bdbdbd00bdbdbd, 0x0036363600363636, + 0x0022222200222222, 0x0038383800383838, 0x0064646400646464, + 0x001e1e1e001e1e1e, 0x0039393900393939, 0x002c2c2c002c2c2c, + 0x00a6a6a600a6a6a6, 0x0030303000303030, 0x00e5e5e500e5e5e5, + 0x0044444400444444, 0x00fdfdfd00fdfdfd, 0x0088888800888888, + 0x009f9f9f009f9f9f, 0x0065656500656565, 0x0087878700878787, + 0x006b6b6b006b6b6b, 0x00f4f4f400f4f4f4, 0x0023232300232323, + 0x0048484800484848, 0x0010101000101010, 0x00d1d1d100d1d1d1, + 0x0051515100515151, 0x00c0c0c000c0c0c0, 0x00f9f9f900f9f9f9, + 0x00d2d2d200d2d2d2, 0x00a0a0a000a0a0a0, 0x0055555500555555, + 0x00a1a1a100a1a1a1, 0x0041414100414141, 0x00fafafa00fafafa, + 0x0043434300434343, 0x0013131300131313, 0x00c4c4c400c4c4c4, + 0x002f2f2f002f2f2f, 0x00a8a8a800a8a8a8, 0x00b6b6b600b6b6b6, + 0x003c3c3c003c3c3c, 0x002b2b2b002b2b2b, 0x00c1c1c100c1c1c1, + 0x00ffffff00ffffff, 0x00c8c8c800c8c8c8, 0x00a5a5a500a5a5a5, + 0x0020202000202020, 0x0089898900898989, 0x0000000000000000, + 0x0090909000909090, 0x0047474700474747, 0x00efefef00efefef, + 0x00eaeaea00eaeaea, 0x00b7b7b700b7b7b7, 0x0015151500151515, + 0x0006060600060606, 0x00cdcdcd00cdcdcd, 0x00b5b5b500b5b5b5, + 0x0012121200121212, 0x007e7e7e007e7e7e, 0x00bbbbbb00bbbbbb, + 0x0029292900292929, 0x000f0f0f000f0f0f, 0x00b8b8b800b8b8b8, + 0x0007070700070707, 0x0004040400040404, 0x009b9b9b009b9b9b, + 0x0094949400949494, 0x0021212100212121, 0x0066666600666666, + 0x00e6e6e600e6e6e6, 0x00cecece00cecece, 0x00ededed00ededed, + 0x00e7e7e700e7e7e7, 0x003b3b3b003b3b3b, 0x00fefefe00fefefe, + 0x007f7f7f007f7f7f, 0x00c5c5c500c5c5c5, 0x00a4a4a400a4a4a4, + 0x0037373700373737, 0x00b1b1b100b1b1b1, 0x004c4c4c004c4c4c, + 0x0091919100919191, 0x006e6e6e006e6e6e, 0x008d8d8d008d8d8d, + 0x0076767600767676, 0x0003030300030303, 0x002d2d2d002d2d2d, + 0x00dedede00dedede, 0x0096969600969696, 0x0026262600262626, + 0x007d7d7d007d7d7d, 0x00c6c6c600c6c6c6, 0x005c5c5c005c5c5c, + 0x00d3d3d300d3d3d3, 0x00f2f2f200f2f2f2, 0x004f4f4f004f4f4f, + 0x0019191900191919, 0x003f3f3f003f3f3f, 0x00dcdcdc00dcdcdc, + 0x0079797900797979, 0x001d1d1d001d1d1d, 0x0052525200525252, + 0x00ebebeb00ebebeb, 0x00f3f3f300f3f3f3, 0x006d6d6d006d6d6d, + 0x005e5e5e005e5e5e, 0x00fbfbfb00fbfbfb, 0x0069696900696969, + 0x00b2b2b200b2b2b2, 0x00f0f0f000f0f0f0, 0x0031313100313131, + 0x000c0c0c000c0c0c, 0x00d4d4d400d4d4d4, 0x00cfcfcf00cfcfcf, + 0x008c8c8c008c8c8c, 0x00e2e2e200e2e2e2, 0x0075757500757575, + 0x00a9a9a900a9a9a9, 0x004a4a4a004a4a4a, 0x0057575700575757, + 0x0084848400848484, 0x0011111100111111, 0x0045454500454545, + 0x001b1b1b001b1b1b, 0x00f5f5f500f5f5f5, 0x00e4e4e400e4e4e4, + 0x000e0e0e000e0e0e, 0x0073737300737373, 0x00aaaaaa00aaaaaa, + 0x00f1f1f100f1f1f1, 0x00dddddd00dddddd, 0x0059595900595959, + 0x0014141400141414, 0x006c6c6c006c6c6c, 0x0092929200929292, + 0x0054545400545454, 0x00d0d0d000d0d0d0, 0x0078787800787878, + 0x0070707000707070, 0x00e3e3e300e3e3e3, 0x0049494900494949, + 0x0080808000808080, 0x0050505000505050, 0x00a7a7a700a7a7a7, + 0x00f6f6f600f6f6f6, 0x0077777700777777, 0x0093939300939393, + 0x0086868600868686, 0x0083838300838383, 0x002a2a2a002a2a2a, + 0x00c7c7c700c7c7c7, 0x005b5b5b005b5b5b, 0x00e9e9e900e9e9e9, + 0x00eeeeee00eeeeee, 0x008f8f8f008f8f8f, 0x0001010100010101, + 0x003d3d3d003d3d3d, +}; + +const u64 camellia_sp30333033[256] = { + 0x3800383838003838, 0x4100414141004141, 0x1600161616001616, + 0x7600767676007676, 0xd900d9d9d900d9d9, 0x9300939393009393, + 0x6000606060006060, 0xf200f2f2f200f2f2, 0x7200727272007272, + 0xc200c2c2c200c2c2, 0xab00ababab00abab, 0x9a009a9a9a009a9a, + 0x7500757575007575, 0x0600060606000606, 0x5700575757005757, + 0xa000a0a0a000a0a0, 0x9100919191009191, 0xf700f7f7f700f7f7, + 0xb500b5b5b500b5b5, 0xc900c9c9c900c9c9, 0xa200a2a2a200a2a2, + 0x8c008c8c8c008c8c, 0xd200d2d2d200d2d2, 0x9000909090009090, + 0xf600f6f6f600f6f6, 0x0700070707000707, 0xa700a7a7a700a7a7, + 0x2700272727002727, 0x8e008e8e8e008e8e, 0xb200b2b2b200b2b2, + 0x4900494949004949, 0xde00dedede00dede, 0x4300434343004343, + 0x5c005c5c5c005c5c, 0xd700d7d7d700d7d7, 0xc700c7c7c700c7c7, + 0x3e003e3e3e003e3e, 0xf500f5f5f500f5f5, 0x8f008f8f8f008f8f, + 0x6700676767006767, 0x1f001f1f1f001f1f, 0x1800181818001818, + 0x6e006e6e6e006e6e, 0xaf00afafaf00afaf, 0x2f002f2f2f002f2f, + 0xe200e2e2e200e2e2, 0x8500858585008585, 0x0d000d0d0d000d0d, + 0x5300535353005353, 0xf000f0f0f000f0f0, 0x9c009c9c9c009c9c, + 0x6500656565006565, 0xea00eaeaea00eaea, 0xa300a3a3a300a3a3, + 0xae00aeaeae00aeae, 0x9e009e9e9e009e9e, 0xec00ececec00ecec, + 0x8000808080008080, 0x2d002d2d2d002d2d, 0x6b006b6b6b006b6b, + 0xa800a8a8a800a8a8, 0x2b002b2b2b002b2b, 0x3600363636003636, + 0xa600a6a6a600a6a6, 0xc500c5c5c500c5c5, 0x8600868686008686, + 0x4d004d4d4d004d4d, 0x3300333333003333, 0xfd00fdfdfd00fdfd, + 0x6600666666006666, 0x5800585858005858, 0x9600969696009696, + 0x3a003a3a3a003a3a, 0x0900090909000909, 0x9500959595009595, + 0x1000101010001010, 0x7800787878007878, 0xd800d8d8d800d8d8, + 0x4200424242004242, 0xcc00cccccc00cccc, 0xef00efefef00efef, + 0x2600262626002626, 0xe500e5e5e500e5e5, 0x6100616161006161, + 0x1a001a1a1a001a1a, 0x3f003f3f3f003f3f, 0x3b003b3b3b003b3b, + 0x8200828282008282, 0xb600b6b6b600b6b6, 0xdb00dbdbdb00dbdb, + 0xd400d4d4d400d4d4, 0x9800989898009898, 0xe800e8e8e800e8e8, + 0x8b008b8b8b008b8b, 0x0200020202000202, 0xeb00ebebeb00ebeb, + 0x0a000a0a0a000a0a, 0x2c002c2c2c002c2c, 0x1d001d1d1d001d1d, + 0xb000b0b0b000b0b0, 0x6f006f6f6f006f6f, 0x8d008d8d8d008d8d, + 0x8800888888008888, 0x0e000e0e0e000e0e, 0x1900191919001919, + 0x8700878787008787, 0x4e004e4e4e004e4e, 0x0b000b0b0b000b0b, + 0xa900a9a9a900a9a9, 0x0c000c0c0c000c0c, 0x7900797979007979, + 0x1100111111001111, 0x7f007f7f7f007f7f, 0x2200222222002222, + 0xe700e7e7e700e7e7, 0x5900595959005959, 0xe100e1e1e100e1e1, + 0xda00dadada00dada, 0x3d003d3d3d003d3d, 0xc800c8c8c800c8c8, + 0x1200121212001212, 0x0400040404000404, 0x7400747474007474, + 0x5400545454005454, 0x3000303030003030, 0x7e007e7e7e007e7e, + 0xb400b4b4b400b4b4, 0x2800282828002828, 0x5500555555005555, + 0x6800686868006868, 0x5000505050005050, 0xbe00bebebe00bebe, + 0xd000d0d0d000d0d0, 0xc400c4c4c400c4c4, 0x3100313131003131, + 0xcb00cbcbcb00cbcb, 0x2a002a2a2a002a2a, 0xad00adadad00adad, + 0x0f000f0f0f000f0f, 0xca00cacaca00caca, 0x7000707070007070, + 0xff00ffffff00ffff, 0x3200323232003232, 0x6900696969006969, + 0x0800080808000808, 0x6200626262006262, 0x0000000000000000, + 0x2400242424002424, 0xd100d1d1d100d1d1, 0xfb00fbfbfb00fbfb, + 0xba00bababa00baba, 0xed00ededed00eded, 0x4500454545004545, + 0x8100818181008181, 0x7300737373007373, 0x6d006d6d6d006d6d, + 0x8400848484008484, 0x9f009f9f9f009f9f, 0xee00eeeeee00eeee, + 0x4a004a4a4a004a4a, 0xc300c3c3c300c3c3, 0x2e002e2e2e002e2e, + 0xc100c1c1c100c1c1, 0x0100010101000101, 0xe600e6e6e600e6e6, + 0x2500252525002525, 0x4800484848004848, 0x9900999999009999, + 0xb900b9b9b900b9b9, 0xb300b3b3b300b3b3, 0x7b007b7b7b007b7b, + 0xf900f9f9f900f9f9, 0xce00cecece00cece, 0xbf00bfbfbf00bfbf, + 0xdf00dfdfdf00dfdf, 0x7100717171007171, 0x2900292929002929, + 0xcd00cdcdcd00cdcd, 0x6c006c6c6c006c6c, 0x1300131313001313, + 0x6400646464006464, 0x9b009b9b9b009b9b, 0x6300636363006363, + 0x9d009d9d9d009d9d, 0xc000c0c0c000c0c0, 0x4b004b4b4b004b4b, + 0xb700b7b7b700b7b7, 0xa500a5a5a500a5a5, 0x8900898989008989, + 0x5f005f5f5f005f5f, 0xb100b1b1b100b1b1, 0x1700171717001717, + 0xf400f4f4f400f4f4, 0xbc00bcbcbc00bcbc, 0xd300d3d3d300d3d3, + 0x4600464646004646, 0xcf00cfcfcf00cfcf, 0x3700373737003737, + 0x5e005e5e5e005e5e, 0x4700474747004747, 0x9400949494009494, + 0xfa00fafafa00fafa, 0xfc00fcfcfc00fcfc, 0x5b005b5b5b005b5b, + 0x9700979797009797, 0xfe00fefefe00fefe, 0x5a005a5a5a005a5a, + 0xac00acacac00acac, 0x3c003c3c3c003c3c, 0x4c004c4c4c004c4c, + 0x0300030303000303, 0x3500353535003535, 0xf300f3f3f300f3f3, + 0x2300232323002323, 0xb800b8b8b800b8b8, 0x5d005d5d5d005d5d, + 0x6a006a6a6a006a6a, 0x9200929292009292, 0xd500d5d5d500d5d5, + 0x2100212121002121, 0x4400444444004444, 0x5100515151005151, + 0xc600c6c6c600c6c6, 0x7d007d7d7d007d7d, 0x3900393939003939, + 0x8300838383008383, 0xdc00dcdcdc00dcdc, 0xaa00aaaaaa00aaaa, + 0x7c007c7c7c007c7c, 0x7700777777007777, 0x5600565656005656, + 0x0500050505000505, 0x1b001b1b1b001b1b, 0xa400a4a4a400a4a4, + 0x1500151515001515, 0x3400343434003434, 0x1e001e1e1e001e1e, + 0x1c001c1c1c001c1c, 0xf800f8f8f800f8f8, 0x5200525252005252, + 0x2000202020002020, 0x1400141414001414, 0xe900e9e9e900e9e9, + 0xbd00bdbdbd00bdbd, 0xdd00dddddd00dddd, 0xe400e4e4e400e4e4, + 0xa100a1a1a100a1a1, 0xe000e0e0e000e0e0, 0x8a008a8a8a008a8a, + 0xf100f1f1f100f1f1, 0xd600d6d6d600d6d6, 0x7a007a7a7a007a7a, + 0xbb00bbbbbb00bbbb, 0xe300e3e3e300e3e3, 0x4000404040004040, + 0x4f004f4f4f004f4f, +}; + +const u64 camellia_sp44044404[256] = { + 0x7070007070700070, 0x2c2c002c2c2c002c, 0xb3b300b3b3b300b3, + 0xc0c000c0c0c000c0, 0xe4e400e4e4e400e4, 0x5757005757570057, + 0xeaea00eaeaea00ea, 0xaeae00aeaeae00ae, 0x2323002323230023, + 0x6b6b006b6b6b006b, 0x4545004545450045, 0xa5a500a5a5a500a5, + 0xeded00ededed00ed, 0x4f4f004f4f4f004f, 0x1d1d001d1d1d001d, + 0x9292009292920092, 0x8686008686860086, 0xafaf00afafaf00af, + 0x7c7c007c7c7c007c, 0x1f1f001f1f1f001f, 0x3e3e003e3e3e003e, + 0xdcdc00dcdcdc00dc, 0x5e5e005e5e5e005e, 0x0b0b000b0b0b000b, + 0xa6a600a6a6a600a6, 0x3939003939390039, 0xd5d500d5d5d500d5, + 0x5d5d005d5d5d005d, 0xd9d900d9d9d900d9, 0x5a5a005a5a5a005a, + 0x5151005151510051, 0x6c6c006c6c6c006c, 0x8b8b008b8b8b008b, + 0x9a9a009a9a9a009a, 0xfbfb00fbfbfb00fb, 0xb0b000b0b0b000b0, + 0x7474007474740074, 0x2b2b002b2b2b002b, 0xf0f000f0f0f000f0, + 0x8484008484840084, 0xdfdf00dfdfdf00df, 0xcbcb00cbcbcb00cb, + 0x3434003434340034, 0x7676007676760076, 0x6d6d006d6d6d006d, + 0xa9a900a9a9a900a9, 0xd1d100d1d1d100d1, 0x0404000404040004, + 0x1414001414140014, 0x3a3a003a3a3a003a, 0xdede00dedede00de, + 0x1111001111110011, 0x3232003232320032, 0x9c9c009c9c9c009c, + 0x5353005353530053, 0xf2f200f2f2f200f2, 0xfefe00fefefe00fe, + 0xcfcf00cfcfcf00cf, 0xc3c300c3c3c300c3, 0x7a7a007a7a7a007a, + 0x2424002424240024, 0xe8e800e8e8e800e8, 0x6060006060600060, + 0x6969006969690069, 0xaaaa00aaaaaa00aa, 0xa0a000a0a0a000a0, + 0xa1a100a1a1a100a1, 0x6262006262620062, 0x5454005454540054, + 0x1e1e001e1e1e001e, 0xe0e000e0e0e000e0, 0x6464006464640064, + 0x1010001010100010, 0x0000000000000000, 0xa3a300a3a3a300a3, + 0x7575007575750075, 0x8a8a008a8a8a008a, 0xe6e600e6e6e600e6, + 0x0909000909090009, 0xdddd00dddddd00dd, 0x8787008787870087, + 0x8383008383830083, 0xcdcd00cdcdcd00cd, 0x9090009090900090, + 0x7373007373730073, 0xf6f600f6f6f600f6, 0x9d9d009d9d9d009d, + 0xbfbf00bfbfbf00bf, 0x5252005252520052, 0xd8d800d8d8d800d8, + 0xc8c800c8c8c800c8, 0xc6c600c6c6c600c6, 0x8181008181810081, + 0x6f6f006f6f6f006f, 0x1313001313130013, 0x6363006363630063, + 0xe9e900e9e9e900e9, 0xa7a700a7a7a700a7, 0x9f9f009f9f9f009f, + 0xbcbc00bcbcbc00bc, 0x2929002929290029, 0xf9f900f9f9f900f9, + 0x2f2f002f2f2f002f, 0xb4b400b4b4b400b4, 0x7878007878780078, + 0x0606000606060006, 0xe7e700e7e7e700e7, 0x7171007171710071, + 0xd4d400d4d4d400d4, 0xabab00ababab00ab, 0x8888008888880088, + 0x8d8d008d8d8d008d, 0x7272007272720072, 0xb9b900b9b9b900b9, + 0xf8f800f8f8f800f8, 0xacac00acacac00ac, 0x3636003636360036, + 0x2a2a002a2a2a002a, 0x3c3c003c3c3c003c, 0xf1f100f1f1f100f1, + 0x4040004040400040, 0xd3d300d3d3d300d3, 0xbbbb00bbbbbb00bb, + 0x4343004343430043, 0x1515001515150015, 0xadad00adadad00ad, + 0x7777007777770077, 0x8080008080800080, 0x8282008282820082, + 0xecec00ececec00ec, 0x2727002727270027, 0xe5e500e5e5e500e5, + 0x8585008585850085, 0x3535003535350035, 0x0c0c000c0c0c000c, + 0x4141004141410041, 0xefef00efefef00ef, 0x9393009393930093, + 0x1919001919190019, 0x2121002121210021, 0x0e0e000e0e0e000e, + 0x4e4e004e4e4e004e, 0x6565006565650065, 0xbdbd00bdbdbd00bd, + 0xb8b800b8b8b800b8, 0x8f8f008f8f8f008f, 0xebeb00ebebeb00eb, + 0xcece00cecece00ce, 0x3030003030300030, 0x5f5f005f5f5f005f, + 0xc5c500c5c5c500c5, 0x1a1a001a1a1a001a, 0xe1e100e1e1e100e1, + 0xcaca00cacaca00ca, 0x4747004747470047, 0x3d3d003d3d3d003d, + 0x0101000101010001, 0xd6d600d6d6d600d6, 0x5656005656560056, + 0x4d4d004d4d4d004d, 0x0d0d000d0d0d000d, 0x6666006666660066, + 0xcccc00cccccc00cc, 0x2d2d002d2d2d002d, 0x1212001212120012, + 0x2020002020200020, 0xb1b100b1b1b100b1, 0x9999009999990099, + 0x4c4c004c4c4c004c, 0xc2c200c2c2c200c2, 0x7e7e007e7e7e007e, + 0x0505000505050005, 0xb7b700b7b7b700b7, 0x3131003131310031, + 0x1717001717170017, 0xd7d700d7d7d700d7, 0x5858005858580058, + 0x6161006161610061, 0x1b1b001b1b1b001b, 0x1c1c001c1c1c001c, + 0x0f0f000f0f0f000f, 0x1616001616160016, 0x1818001818180018, + 0x2222002222220022, 0x4444004444440044, 0xb2b200b2b2b200b2, + 0xb5b500b5b5b500b5, 0x9191009191910091, 0x0808000808080008, + 0xa8a800a8a8a800a8, 0xfcfc00fcfcfc00fc, 0x5050005050500050, + 0xd0d000d0d0d000d0, 0x7d7d007d7d7d007d, 0x8989008989890089, + 0x9797009797970097, 0x5b5b005b5b5b005b, 0x9595009595950095, + 0xffff00ffffff00ff, 0xd2d200d2d2d200d2, 0xc4c400c4c4c400c4, + 0x4848004848480048, 0xf7f700f7f7f700f7, 0xdbdb00dbdbdb00db, + 0x0303000303030003, 0xdada00dadada00da, 0x3f3f003f3f3f003f, + 0x9494009494940094, 0x5c5c005c5c5c005c, 0x0202000202020002, + 0x4a4a004a4a4a004a, 0x3333003333330033, 0x6767006767670067, + 0xf3f300f3f3f300f3, 0x7f7f007f7f7f007f, 0xe2e200e2e2e200e2, + 0x9b9b009b9b9b009b, 0x2626002626260026, 0x3737003737370037, + 0x3b3b003b3b3b003b, 0x9696009696960096, 0x4b4b004b4b4b004b, + 0xbebe00bebebe00be, 0x2e2e002e2e2e002e, 0x7979007979790079, + 0x8c8c008c8c8c008c, 0x6e6e006e6e6e006e, 0x8e8e008e8e8e008e, + 0xf5f500f5f5f500f5, 0xb6b600b6b6b600b6, 0xfdfd00fdfdfd00fd, + 0x5959005959590059, 0x9898009898980098, 0x6a6a006a6a6a006a, + 0x4646004646460046, 0xbaba00bababa00ba, 0x2525002525250025, + 0x4242004242420042, 0xa2a200a2a2a200a2, 0xfafa00fafafa00fa, + 0x0707000707070007, 0x5555005555550055, 0xeeee00eeeeee00ee, + 0x0a0a000a0a0a000a, 0x4949004949490049, 0x6868006868680068, + 0x3838003838380038, 0xa4a400a4a4a400a4, 0x2828002828280028, + 0x7b7b007b7b7b007b, 0xc9c900c9c9c900c9, 0xc1c100c1c1c100c1, + 0xe3e300e3e3e300e3, 0xf4f400f4f4f400f4, 0xc7c700c7c7c700c7, + 0x9e9e009e9e9e009e, +}; + +const u64 camellia_sp11101110[256] = { + 0x7070700070707000, 0x8282820082828200, 0x2c2c2c002c2c2c00, + 0xececec00ececec00, 0xb3b3b300b3b3b300, 0x2727270027272700, + 0xc0c0c000c0c0c000, 0xe5e5e500e5e5e500, 0xe4e4e400e4e4e400, + 0x8585850085858500, 0x5757570057575700, 0x3535350035353500, + 0xeaeaea00eaeaea00, 0x0c0c0c000c0c0c00, 0xaeaeae00aeaeae00, + 0x4141410041414100, 0x2323230023232300, 0xefefef00efefef00, + 0x6b6b6b006b6b6b00, 0x9393930093939300, 0x4545450045454500, + 0x1919190019191900, 0xa5a5a500a5a5a500, 0x2121210021212100, + 0xededed00ededed00, 0x0e0e0e000e0e0e00, 0x4f4f4f004f4f4f00, + 0x4e4e4e004e4e4e00, 0x1d1d1d001d1d1d00, 0x6565650065656500, + 0x9292920092929200, 0xbdbdbd00bdbdbd00, 0x8686860086868600, + 0xb8b8b800b8b8b800, 0xafafaf00afafaf00, 0x8f8f8f008f8f8f00, + 0x7c7c7c007c7c7c00, 0xebebeb00ebebeb00, 0x1f1f1f001f1f1f00, + 0xcecece00cecece00, 0x3e3e3e003e3e3e00, 0x3030300030303000, + 0xdcdcdc00dcdcdc00, 0x5f5f5f005f5f5f00, 0x5e5e5e005e5e5e00, + 0xc5c5c500c5c5c500, 0x0b0b0b000b0b0b00, 0x1a1a1a001a1a1a00, + 0xa6a6a600a6a6a600, 0xe1e1e100e1e1e100, 0x3939390039393900, + 0xcacaca00cacaca00, 0xd5d5d500d5d5d500, 0x4747470047474700, + 0x5d5d5d005d5d5d00, 0x3d3d3d003d3d3d00, 0xd9d9d900d9d9d900, + 0x0101010001010100, 0x5a5a5a005a5a5a00, 0xd6d6d600d6d6d600, + 0x5151510051515100, 0x5656560056565600, 0x6c6c6c006c6c6c00, + 0x4d4d4d004d4d4d00, 0x8b8b8b008b8b8b00, 0x0d0d0d000d0d0d00, + 0x9a9a9a009a9a9a00, 0x6666660066666600, 0xfbfbfb00fbfbfb00, + 0xcccccc00cccccc00, 0xb0b0b000b0b0b000, 0x2d2d2d002d2d2d00, + 0x7474740074747400, 0x1212120012121200, 0x2b2b2b002b2b2b00, + 0x2020200020202000, 0xf0f0f000f0f0f000, 0xb1b1b100b1b1b100, + 0x8484840084848400, 0x9999990099999900, 0xdfdfdf00dfdfdf00, + 0x4c4c4c004c4c4c00, 0xcbcbcb00cbcbcb00, 0xc2c2c200c2c2c200, + 0x3434340034343400, 0x7e7e7e007e7e7e00, 0x7676760076767600, + 0x0505050005050500, 0x6d6d6d006d6d6d00, 0xb7b7b700b7b7b700, + 0xa9a9a900a9a9a900, 0x3131310031313100, 0xd1d1d100d1d1d100, + 0x1717170017171700, 0x0404040004040400, 0xd7d7d700d7d7d700, + 0x1414140014141400, 0x5858580058585800, 0x3a3a3a003a3a3a00, + 0x6161610061616100, 0xdedede00dedede00, 0x1b1b1b001b1b1b00, + 0x1111110011111100, 0x1c1c1c001c1c1c00, 0x3232320032323200, + 0x0f0f0f000f0f0f00, 0x9c9c9c009c9c9c00, 0x1616160016161600, + 0x5353530053535300, 0x1818180018181800, 0xf2f2f200f2f2f200, + 0x2222220022222200, 0xfefefe00fefefe00, 0x4444440044444400, + 0xcfcfcf00cfcfcf00, 0xb2b2b200b2b2b200, 0xc3c3c300c3c3c300, + 0xb5b5b500b5b5b500, 0x7a7a7a007a7a7a00, 0x9191910091919100, + 0x2424240024242400, 0x0808080008080800, 0xe8e8e800e8e8e800, + 0xa8a8a800a8a8a800, 0x6060600060606000, 0xfcfcfc00fcfcfc00, + 0x6969690069696900, 0x5050500050505000, 0xaaaaaa00aaaaaa00, + 0xd0d0d000d0d0d000, 0xa0a0a000a0a0a000, 0x7d7d7d007d7d7d00, + 0xa1a1a100a1a1a100, 0x8989890089898900, 0x6262620062626200, + 0x9797970097979700, 0x5454540054545400, 0x5b5b5b005b5b5b00, + 0x1e1e1e001e1e1e00, 0x9595950095959500, 0xe0e0e000e0e0e000, + 0xffffff00ffffff00, 0x6464640064646400, 0xd2d2d200d2d2d200, + 0x1010100010101000, 0xc4c4c400c4c4c400, 0x0000000000000000, + 0x4848480048484800, 0xa3a3a300a3a3a300, 0xf7f7f700f7f7f700, + 0x7575750075757500, 0xdbdbdb00dbdbdb00, 0x8a8a8a008a8a8a00, + 0x0303030003030300, 0xe6e6e600e6e6e600, 0xdadada00dadada00, + 0x0909090009090900, 0x3f3f3f003f3f3f00, 0xdddddd00dddddd00, + 0x9494940094949400, 0x8787870087878700, 0x5c5c5c005c5c5c00, + 0x8383830083838300, 0x0202020002020200, 0xcdcdcd00cdcdcd00, + 0x4a4a4a004a4a4a00, 0x9090900090909000, 0x3333330033333300, + 0x7373730073737300, 0x6767670067676700, 0xf6f6f600f6f6f600, + 0xf3f3f300f3f3f300, 0x9d9d9d009d9d9d00, 0x7f7f7f007f7f7f00, + 0xbfbfbf00bfbfbf00, 0xe2e2e200e2e2e200, 0x5252520052525200, + 0x9b9b9b009b9b9b00, 0xd8d8d800d8d8d800, 0x2626260026262600, + 0xc8c8c800c8c8c800, 0x3737370037373700, 0xc6c6c600c6c6c600, + 0x3b3b3b003b3b3b00, 0x8181810081818100, 0x9696960096969600, + 0x6f6f6f006f6f6f00, 0x4b4b4b004b4b4b00, 0x1313130013131300, + 0xbebebe00bebebe00, 0x6363630063636300, 0x2e2e2e002e2e2e00, + 0xe9e9e900e9e9e900, 0x7979790079797900, 0xa7a7a700a7a7a700, + 0x8c8c8c008c8c8c00, 0x9f9f9f009f9f9f00, 0x6e6e6e006e6e6e00, + 0xbcbcbc00bcbcbc00, 0x8e8e8e008e8e8e00, 0x2929290029292900, + 0xf5f5f500f5f5f500, 0xf9f9f900f9f9f900, 0xb6b6b600b6b6b600, + 0x2f2f2f002f2f2f00, 0xfdfdfd00fdfdfd00, 0xb4b4b400b4b4b400, + 0x5959590059595900, 0x7878780078787800, 0x9898980098989800, + 0x0606060006060600, 0x6a6a6a006a6a6a00, 0xe7e7e700e7e7e700, + 0x4646460046464600, 0x7171710071717100, 0xbababa00bababa00, + 0xd4d4d400d4d4d400, 0x2525250025252500, 0xababab00ababab00, + 0x4242420042424200, 0x8888880088888800, 0xa2a2a200a2a2a200, + 0x8d8d8d008d8d8d00, 0xfafafa00fafafa00, 0x7272720072727200, + 0x0707070007070700, 0xb9b9b900b9b9b900, 0x5555550055555500, + 0xf8f8f800f8f8f800, 0xeeeeee00eeeeee00, 0xacacac00acacac00, + 0x0a0a0a000a0a0a00, 0x3636360036363600, 0x4949490049494900, + 0x2a2a2a002a2a2a00, 0x6868680068686800, 0x3c3c3c003c3c3c00, + 0x3838380038383800, 0xf1f1f100f1f1f100, 0xa4a4a400a4a4a400, + 0x4040400040404000, 0x2828280028282800, 0xd3d3d300d3d3d300, + 0x7b7b7b007b7b7b00, 0xbbbbbb00bbbbbb00, 0xc9c9c900c9c9c900, + 0x4343430043434300, 0xc1c1c100c1c1c100, 0x1515150015151500, + 0xe3e3e300e3e3e300, 0xadadad00adadad00, 0xf4f4f400f4f4f400, + 0x7777770077777700, 0xc7c7c700c7c7c700, 0x8080800080808000, + 0x9e9e9e009e9e9e00, +}; + +/* key constants */ +#define CAMELLIA_SIGMA1L (0xA09E667FL) +#define CAMELLIA_SIGMA1R (0x3BCC908BL) +#define CAMELLIA_SIGMA2L (0xB67AE858L) +#define CAMELLIA_SIGMA2R (0x4CAA73B2L) +#define CAMELLIA_SIGMA3L (0xC6EF372FL) +#define CAMELLIA_SIGMA3R (0xE94F82BEL) +#define CAMELLIA_SIGMA4L (0x54FF53A5L) +#define CAMELLIA_SIGMA4R (0xF1D36F1CL) +#define CAMELLIA_SIGMA5L (0x10E527FAL) +#define CAMELLIA_SIGMA5R (0xDE682D1DL) +#define CAMELLIA_SIGMA6L (0xB05688C2L) +#define CAMELLIA_SIGMA6R (0xB3E6C1FDL) + +/* macros */ +#define ROLDQ(l, r, bits) ({ \ + u64 t = l; \ + l = (l << bits) | (r >> (64 - bits)); \ + r = (r << bits) | (t >> (64 - bits)); \ +}) + +#define CAMELLIA_F(x, kl, kr, y) ({ \ + u64 ii = x ^ (((u64)kl << 32) | kr); \ + y = camellia_sp11101110[(uint8_t)ii]; \ + y ^= camellia_sp44044404[(uint8_t)(ii >> 8)]; \ + ii >>= 16; \ + y ^= camellia_sp30333033[(uint8_t)ii]; \ + y ^= camellia_sp02220222[(uint8_t)(ii >> 8)]; \ + ii >>= 16; \ + y ^= camellia_sp00444404[(uint8_t)ii]; \ + y ^= camellia_sp03303033[(uint8_t)(ii >> 8)]; \ + ii >>= 16; \ + y ^= camellia_sp22000222[(uint8_t)ii]; \ + y ^= camellia_sp10011110[(uint8_t)(ii >> 8)]; \ + y = ror64(y, 32); \ +}) + +#define SET_SUBKEY_LR(INDEX, sRL) (subkey[(INDEX)] = ror64((sRL), 32)) + +static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max) +{ + u64 kw4, tt; + u32 dw, tl, tr; + + /* absorb kw2 to other subkeys */ + /* round 2 */ + subRL[3] ^= subRL[1]; + /* round 4 */ + subRL[5] ^= subRL[1]; + /* round 6 */ + subRL[7] ^= subRL[1]; + + subRL[1] ^= (subRL[1] & ~subRL[9]) << 32; + /* modified for FLinv(kl2) */ + dw = (subRL[1] & subRL[9]) >> 32, + subRL[1] ^= rol32(dw, 1); + + /* round 8 */ + subRL[11] ^= subRL[1]; + /* round 10 */ + subRL[13] ^= subRL[1]; + /* round 12 */ + subRL[15] ^= subRL[1]; + + subRL[1] ^= (subRL[1] & ~subRL[17]) << 32; + /* modified for FLinv(kl4) */ + dw = (subRL[1] & subRL[17]) >> 32, + subRL[1] ^= rol32(dw, 1); + + /* round 14 */ + subRL[19] ^= subRL[1]; + /* round 16 */ + subRL[21] ^= subRL[1]; + /* round 18 */ + subRL[23] ^= subRL[1]; + + if (max == 24) { + /* kw3 */ + subRL[24] ^= subRL[1]; + + /* absorb kw4 to other subkeys */ + kw4 = subRL[25]; + } else { + subRL[1] ^= (subRL[1] & ~subRL[25]) << 32; + /* modified for FLinv(kl6) */ + dw = (subRL[1] & subRL[25]) >> 32, + subRL[1] ^= rol32(dw, 1); + + /* round 20 */ + subRL[27] ^= subRL[1]; + /* round 22 */ + subRL[29] ^= subRL[1]; + /* round 24 */ + subRL[31] ^= subRL[1]; + /* kw3 */ + subRL[32] ^= subRL[1]; + + /* absorb kw4 to other subkeys */ + kw4 = subRL[33]; + /* round 23 */ + subRL[30] ^= kw4; + /* round 21 */ + subRL[28] ^= kw4; + /* round 19 */ + subRL[26] ^= kw4; + + kw4 ^= (kw4 & ~subRL[24]) << 32; + /* modified for FL(kl5) */ + dw = (kw4 & subRL[24]) >> 32, + kw4 ^= rol32(dw, 1); + } + + /* round 17 */ + subRL[22] ^= kw4; + /* round 15 */ + subRL[20] ^= kw4; + /* round 13 */ + subRL[18] ^= kw4; + + kw4 ^= (kw4 & ~subRL[16]) << 32; + /* modified for FL(kl3) */ + dw = (kw4 & subRL[16]) >> 32, + kw4 ^= rol32(dw, 1); + + /* round 11 */ + subRL[14] ^= kw4; + /* round 9 */ + subRL[12] ^= kw4; + /* round 7 */ + subRL[10] ^= kw4; + + kw4 ^= (kw4 & ~subRL[8]) << 32; + /* modified for FL(kl1) */ + dw = (kw4 & subRL[8]) >> 32, + kw4 ^= rol32(dw, 1); + + /* round 5 */ + subRL[6] ^= kw4; + /* round 3 */ + subRL[4] ^= kw4; + /* round 1 */ + subRL[2] ^= kw4; + /* kw1 */ + subRL[0] ^= kw4; + + /* key XOR is end of F-function */ + SET_SUBKEY_LR(0, subRL[0] ^ subRL[2]); /* kw1 */ + SET_SUBKEY_LR(2, subRL[3]); /* round 1 */ + SET_SUBKEY_LR(3, subRL[2] ^ subRL[4]); /* round 2 */ + SET_SUBKEY_LR(4, subRL[3] ^ subRL[5]); /* round 3 */ + SET_SUBKEY_LR(5, subRL[4] ^ subRL[6]); /* round 4 */ + SET_SUBKEY_LR(6, subRL[5] ^ subRL[7]); /* round 5 */ + + tl = (subRL[10] >> 32) ^ (subRL[10] & ~subRL[8]); + dw = tl & (subRL[8] >> 32), /* FL(kl1) */ + tr = subRL[10] ^ rol32(dw, 1); + tt = (tr | ((u64)tl << 32)); + + SET_SUBKEY_LR(7, subRL[6] ^ tt); /* round 6 */ + SET_SUBKEY_LR(8, subRL[8]); /* FL(kl1) */ + SET_SUBKEY_LR(9, subRL[9]); /* FLinv(kl2) */ + + tl = (subRL[7] >> 32) ^ (subRL[7] & ~subRL[9]); + dw = tl & (subRL[9] >> 32), /* FLinv(kl2) */ + tr = subRL[7] ^ rol32(dw, 1); + tt = (tr | ((u64)tl << 32)); + + SET_SUBKEY_LR(10, subRL[11] ^ tt); /* round 7 */ + SET_SUBKEY_LR(11, subRL[10] ^ subRL[12]); /* round 8 */ + SET_SUBKEY_LR(12, subRL[11] ^ subRL[13]); /* round 9 */ + SET_SUBKEY_LR(13, subRL[12] ^ subRL[14]); /* round 10 */ + SET_SUBKEY_LR(14, subRL[13] ^ subRL[15]); /* round 11 */ + + tl = (subRL[18] >> 32) ^ (subRL[18] & ~subRL[16]); + dw = tl & (subRL[16] >> 32), /* FL(kl3) */ + tr = subRL[18] ^ rol32(dw, 1); + tt = (tr | ((u64)tl << 32)); + + SET_SUBKEY_LR(15, subRL[14] ^ tt); /* round 12 */ + SET_SUBKEY_LR(16, subRL[16]); /* FL(kl3) */ + SET_SUBKEY_LR(17, subRL[17]); /* FLinv(kl4) */ + + tl = (subRL[15] >> 32) ^ (subRL[15] & ~subRL[17]); + dw = tl & (subRL[17] >> 32), /* FLinv(kl4) */ + tr = subRL[15] ^ rol32(dw, 1); + tt = (tr | ((u64)tl << 32)); + + SET_SUBKEY_LR(18, subRL[19] ^ tt); /* round 13 */ + SET_SUBKEY_LR(19, subRL[18] ^ subRL[20]); /* round 14 */ + SET_SUBKEY_LR(20, subRL[19] ^ subRL[21]); /* round 15 */ + SET_SUBKEY_LR(21, subRL[20] ^ subRL[22]); /* round 16 */ + SET_SUBKEY_LR(22, subRL[21] ^ subRL[23]); /* round 17 */ + + if (max == 24) { + SET_SUBKEY_LR(23, subRL[22]); /* round 18 */ + SET_SUBKEY_LR(24, subRL[24] ^ subRL[23]); /* kw3 */ + } else { + tl = (subRL[26] >> 32) ^ (subRL[26] & ~subRL[24]); + dw = tl & (subRL[24] >> 32), /* FL(kl5) */ + tr = subRL[26] ^ rol32(dw, 1); + tt = (tr | ((u64)tl << 32)); + + SET_SUBKEY_LR(23, subRL[22] ^ tt); /* round 18 */ + SET_SUBKEY_LR(24, subRL[24]); /* FL(kl5) */ + SET_SUBKEY_LR(25, subRL[25]); /* FLinv(kl6) */ + + tl = (subRL[23] >> 32) ^ (subRL[23] & ~subRL[25]); + dw = tl & (subRL[25] >> 32), /* FLinv(kl6) */ + tr = subRL[23] ^ rol32(dw, 1); + tt = (tr | ((u64)tl << 32)); + + SET_SUBKEY_LR(26, subRL[27] ^ tt); /* round 19 */ + SET_SUBKEY_LR(27, subRL[26] ^ subRL[28]); /* round 20 */ + SET_SUBKEY_LR(28, subRL[27] ^ subRL[29]); /* round 21 */ + SET_SUBKEY_LR(29, subRL[28] ^ subRL[30]); /* round 22 */ + SET_SUBKEY_LR(30, subRL[29] ^ subRL[31]); /* round 23 */ + SET_SUBKEY_LR(31, subRL[30]); /* round 24 */ + SET_SUBKEY_LR(32, subRL[32] ^ subRL[31]); /* kw3 */ + } +} + +static void camellia_setup128(const unsigned char *key, u64 *subkey) +{ + u64 kl, kr, ww; + u64 subRL[26]; + + /** + * k == kl || kr (|| is concatenation) + */ + kl = get_unaligned_be64(key); + kr = get_unaligned_be64(key + 8); + + /* generate KL dependent subkeys */ + /* kw1 */ + subRL[0] = kl; + /* kw2 */ + subRL[1] = kr; + + /* rotation left shift 15bit */ + ROLDQ(kl, kr, 15); + + /* k3 */ + subRL[4] = kl; + /* k4 */ + subRL[5] = kr; + + /* rotation left shift 15+30bit */ + ROLDQ(kl, kr, 30); + + /* k7 */ + subRL[10] = kl; + /* k8 */ + subRL[11] = kr; + + /* rotation left shift 15+30+15bit */ + ROLDQ(kl, kr, 15); + + /* k10 */ + subRL[13] = kr; + /* rotation left shift 15+30+15+17 bit */ + ROLDQ(kl, kr, 17); + + /* kl3 */ + subRL[16] = kl; + /* kl4 */ + subRL[17] = kr; + + /* rotation left shift 15+30+15+17+17 bit */ + ROLDQ(kl, kr, 17); + + /* k13 */ + subRL[18] = kl; + /* k14 */ + subRL[19] = kr; + + /* rotation left shift 15+30+15+17+17+17 bit */ + ROLDQ(kl, kr, 17); + + /* k17 */ + subRL[22] = kl; + /* k18 */ + subRL[23] = kr; + + /* generate KA */ + kl = subRL[0]; + kr = subRL[1]; + CAMELLIA_F(kl, CAMELLIA_SIGMA1L, CAMELLIA_SIGMA1R, ww); + kr ^= ww; + CAMELLIA_F(kr, CAMELLIA_SIGMA2L, CAMELLIA_SIGMA2R, kl); + + /* current status == (kll, klr, w0, w1) */ + CAMELLIA_F(kl, CAMELLIA_SIGMA3L, CAMELLIA_SIGMA3R, kr); + kr ^= ww; + CAMELLIA_F(kr, CAMELLIA_SIGMA4L, CAMELLIA_SIGMA4R, ww); + kl ^= ww; + + /* generate KA dependent subkeys */ + /* k1, k2 */ + subRL[2] = kl; + subRL[3] = kr; + ROLDQ(kl, kr, 15); + /* k5,k6 */ + subRL[6] = kl; + subRL[7] = kr; + ROLDQ(kl, kr, 15); + /* kl1, kl2 */ + subRL[8] = kl; + subRL[9] = kr; + ROLDQ(kl, kr, 15); + /* k9 */ + subRL[12] = kl; + ROLDQ(kl, kr, 15); + /* k11, k12 */ + subRL[14] = kl; + subRL[15] = kr; + ROLDQ(kl, kr, 34); + /* k15, k16 */ + subRL[20] = kl; + subRL[21] = kr; + ROLDQ(kl, kr, 17); + /* kw3, kw4 */ + subRL[24] = kl; + subRL[25] = kr; + + camellia_setup_tail(subkey, subRL, 24); +} + +static void camellia_setup256(const unsigned char *key, u64 *subkey) +{ + u64 kl, kr; /* left half of key */ + u64 krl, krr; /* right half of key */ + u64 ww; /* temporary variables */ + u64 subRL[34]; + + /** + * key = (kl || kr || krl || krr) (|| is concatenation) + */ + kl = get_unaligned_be64(key); + kr = get_unaligned_be64(key + 8); + krl = get_unaligned_be64(key + 16); + krr = get_unaligned_be64(key + 24); + + /* generate KL dependent subkeys */ + /* kw1 */ + subRL[0] = kl; + /* kw2 */ + subRL[1] = kr; + ROLDQ(kl, kr, 45); + /* k9 */ + subRL[12] = kl; + /* k10 */ + subRL[13] = kr; + ROLDQ(kl, kr, 15); + /* kl3 */ + subRL[16] = kl; + /* kl4 */ + subRL[17] = kr; + ROLDQ(kl, kr, 17); + /* k17 */ + subRL[22] = kl; + /* k18 */ + subRL[23] = kr; + ROLDQ(kl, kr, 34); + /* k23 */ + subRL[30] = kl; + /* k24 */ + subRL[31] = kr; + + /* generate KR dependent subkeys */ + ROLDQ(krl, krr, 15); + /* k3 */ + subRL[4] = krl; + /* k4 */ + subRL[5] = krr; + ROLDQ(krl, krr, 15); + /* kl1 */ + subRL[8] = krl; + /* kl2 */ + subRL[9] = krr; + ROLDQ(krl, krr, 30); + /* k13 */ + subRL[18] = krl; + /* k14 */ + subRL[19] = krr; + ROLDQ(krl, krr, 34); + /* k19 */ + subRL[26] = krl; + /* k20 */ + subRL[27] = krr; + ROLDQ(krl, krr, 34); + + /* generate KA */ + kl = subRL[0] ^ krl; + kr = subRL[1] ^ krr; + + CAMELLIA_F(kl, CAMELLIA_SIGMA1L, CAMELLIA_SIGMA1R, ww); + kr ^= ww; + CAMELLIA_F(kr, CAMELLIA_SIGMA2L, CAMELLIA_SIGMA2R, kl); + kl ^= krl; + CAMELLIA_F(kl, CAMELLIA_SIGMA3L, CAMELLIA_SIGMA3R, kr); + kr ^= ww ^ krr; + CAMELLIA_F(kr, CAMELLIA_SIGMA4L, CAMELLIA_SIGMA4R, ww); + kl ^= ww; + + /* generate KB */ + krl ^= kl; + krr ^= kr; + CAMELLIA_F(krl, CAMELLIA_SIGMA5L, CAMELLIA_SIGMA5R, ww); + krr ^= ww; + CAMELLIA_F(krr, CAMELLIA_SIGMA6L, CAMELLIA_SIGMA6R, ww); + krl ^= ww; + + /* generate KA dependent subkeys */ + ROLDQ(kl, kr, 15); + /* k5 */ + subRL[6] = kl; + /* k6 */ + subRL[7] = kr; + ROLDQ(kl, kr, 30); + /* k11 */ + subRL[14] = kl; + /* k12 */ + subRL[15] = kr; + /* rotation left shift 32bit */ + ROLDQ(kl, kr, 32); + /* kl5 */ + subRL[24] = kl; + /* kl6 */ + subRL[25] = kr; + /* rotation left shift 17 from k11,k12 -> k21,k22 */ + ROLDQ(kl, kr, 17); + /* k21 */ + subRL[28] = kl; + /* k22 */ + subRL[29] = kr; + + /* generate KB dependent subkeys */ + /* k1 */ + subRL[2] = krl; + /* k2 */ + subRL[3] = krr; + ROLDQ(krl, krr, 30); + /* k7 */ + subRL[10] = krl; + /* k8 */ + subRL[11] = krr; + ROLDQ(krl, krr, 30); + /* k15 */ + subRL[20] = krl; + /* k16 */ + subRL[21] = krr; + ROLDQ(krl, krr, 51); + /* kw3 */ + subRL[32] = krl; + /* kw4 */ + subRL[33] = krr; + + camellia_setup_tail(subkey, subRL, 32); +} + +static void camellia_setup192(const unsigned char *key, u64 *subkey) +{ + unsigned char kk[32]; + u64 krl, krr; + + memcpy(kk, key, 24); + memcpy((unsigned char *)&krl, key+16, 8); + krr = ~krl; + memcpy(kk+24, (unsigned char *)&krr, 8); + camellia_setup256(kk, subkey); +} + +static int __camellia_setkey(struct camellia_ctx *cctx, + const unsigned char *key, + unsigned int key_len, u32 *flags) +{ + if (key_len != 16 && key_len != 24 && key_len != 32) { + *flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; + return -EINVAL; + } + + cctx->key_length = key_len; + + switch (key_len) { + case 16: + camellia_setup128(key, cctx->key_table); + break; + case 24: + camellia_setup192(key, cctx->key_table); + break; + case 32: + camellia_setup256(key, cctx->key_table); + break; + } + + return 0; +} + +static int camellia_setkey(struct crypto_tfm *tfm, const u8 *in_key, + unsigned int key_len) +{ + return __camellia_setkey(crypto_tfm_ctx(tfm), in_key, key_len, + &tfm->crt_flags); +} + +static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk, + void (*fn)(struct camellia_ctx *, u8 *, const u8 *), + void (*fn_2way)(struct camellia_ctx *, u8 *, const u8 *)) +{ + struct camellia_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + unsigned int bsize = CAMELLIA_BLOCK_SIZE; + unsigned int nbytes; + int err; + + err = blkcipher_walk_virt(desc, walk); + + while ((nbytes = walk->nbytes)) { + u8 *wsrc = walk->src.virt.addr; + u8 *wdst = walk->dst.virt.addr; + + /* Process two block batch */ + if (nbytes >= bsize * 2) { + do { + fn_2way(ctx, wdst, wsrc); + + wsrc += bsize * 2; + wdst += bsize * 2; + nbytes -= bsize * 2; + } while (nbytes >= bsize * 2); + + if (nbytes < bsize) + goto done; + } + + /* Handle leftovers */ + do { + fn(ctx, wdst, wsrc); + + wsrc += bsize; + wdst += bsize; + nbytes -= bsize; + } while (nbytes >= bsize); + +done: + err = blkcipher_walk_done(desc, walk, nbytes); + } + + return err; +} + +static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct blkcipher_walk walk; + + blkcipher_walk_init(&walk, dst, src, nbytes); + return ecb_crypt(desc, &walk, camellia_enc_blk, camellia_enc_blk_2way); +} + +static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct blkcipher_walk walk; + + blkcipher_walk_init(&walk, dst, src, nbytes); + return ecb_crypt(desc, &walk, camellia_dec_blk, camellia_dec_blk_2way); +} + +static unsigned int __cbc_encrypt(struct blkcipher_desc *desc, + struct blkcipher_walk *walk) +{ + struct camellia_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + unsigned int bsize = CAMELLIA_BLOCK_SIZE; + unsigned int nbytes = walk->nbytes; + u128 *src = (u128 *)walk->src.virt.addr; + u128 *dst = (u128 *)walk->dst.virt.addr; + u128 *iv = (u128 *)walk->iv; + + do { + u128_xor(dst, src, iv); + camellia_enc_blk(ctx, (u8 *)dst, (u8 *)dst); + iv = dst; + + src += 1; + dst += 1; + nbytes -= bsize; + } while (nbytes >= bsize); + + u128_xor((u128 *)walk->iv, (u128 *)walk->iv, iv); + return nbytes; +} + +static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + while ((nbytes = walk.nbytes)) { + nbytes = __cbc_encrypt(desc, &walk); + err = blkcipher_walk_done(desc, &walk, nbytes); + } + + return err; +} + +static unsigned int __cbc_decrypt(struct blkcipher_desc *desc, + struct blkcipher_walk *walk) +{ + struct camellia_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + unsigned int bsize = CAMELLIA_BLOCK_SIZE; + unsigned int nbytes = walk->nbytes; + u128 *src = (u128 *)walk->src.virt.addr; + u128 *dst = (u128 *)walk->dst.virt.addr; + u128 ivs[2 - 1]; + u128 last_iv; + + /* Start of the last block. */ + src += nbytes / bsize - 1; + dst += nbytes / bsize - 1; + + last_iv = *src; + + /* Process two block batch */ + if (nbytes >= bsize * 2) { + do { + nbytes -= bsize * (2 - 1); + src -= 2 - 1; + dst -= 2 - 1; + + ivs[0] = src[0]; + + camellia_dec_blk_2way(ctx, (u8 *)dst, (u8 *)src); + + u128_xor(dst + 1, dst + 1, ivs + 0); + + nbytes -= bsize; + if (nbytes < bsize) + goto done; + + u128_xor(dst, dst, src - 1); + src -= 1; + dst -= 1; + } while (nbytes >= bsize * 2); + + if (nbytes < bsize) + goto done; + } + + /* Handle leftovers */ + for (;;) { + camellia_dec_blk(ctx, (u8 *)dst, (u8 *)src); + + nbytes -= bsize; + if (nbytes < bsize) + break; + + u128_xor(dst, dst, src - 1); + src -= 1; + dst -= 1; + } + +done: + u128_xor(dst, dst, (u128 *)walk->iv); + *(u128 *)walk->iv = last_iv; + + return nbytes; +} + +static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + while ((nbytes = walk.nbytes)) { + nbytes = __cbc_decrypt(desc, &walk); + err = blkcipher_walk_done(desc, &walk, nbytes); + } + + return err; +} + +static inline void u128_to_be128(be128 *dst, const u128 *src) +{ + dst->a = cpu_to_be64(src->a); + dst->b = cpu_to_be64(src->b); +} + +static inline void be128_to_u128(u128 *dst, const be128 *src) +{ + dst->a = be64_to_cpu(src->a); + dst->b = be64_to_cpu(src->b); +} + +static inline void u128_inc(u128 *i) +{ + i->b++; + if (!i->b) + i->a++; +} + +static void ctr_crypt_final(struct blkcipher_desc *desc, + struct blkcipher_walk *walk) +{ + struct camellia_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + u8 keystream[CAMELLIA_BLOCK_SIZE]; + u8 *src = walk->src.virt.addr; + u8 *dst = walk->dst.virt.addr; + unsigned int nbytes = walk->nbytes; + u128 ctrblk; + + memcpy(keystream, src, nbytes); + camellia_enc_blk_xor(ctx, keystream, walk->iv); + memcpy(dst, keystream, nbytes); + + be128_to_u128(&ctrblk, (be128 *)walk->iv); + u128_inc(&ctrblk); + u128_to_be128((be128 *)walk->iv, &ctrblk); +} + +static unsigned int __ctr_crypt(struct blkcipher_desc *desc, + struct blkcipher_walk *walk) +{ + struct camellia_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + unsigned int bsize = CAMELLIA_BLOCK_SIZE; + unsigned int nbytes = walk->nbytes; + u128 *src = (u128 *)walk->src.virt.addr; + u128 *dst = (u128 *)walk->dst.virt.addr; + u128 ctrblk; + be128 ctrblocks[2]; + + be128_to_u128(&ctrblk, (be128 *)walk->iv); + + /* Process two block batch */ + if (nbytes >= bsize * 2) { + do { + if (dst != src) { + dst[0] = src[0]; + dst[1] = src[1]; + } + + /* create ctrblks for parallel encrypt */ + u128_to_be128(&ctrblocks[0], &ctrblk); + u128_inc(&ctrblk); + u128_to_be128(&ctrblocks[1], &ctrblk); + u128_inc(&ctrblk); + + camellia_enc_blk_xor_2way(ctx, (u8 *)dst, + (u8 *)ctrblocks); + + src += 2; + dst += 2; + nbytes -= bsize * 2; + } while (nbytes >= bsize * 2); + + if (nbytes < bsize) + goto done; + } + + /* Handle leftovers */ + do { + if (dst != src) + *dst = *src; + + u128_to_be128(&ctrblocks[0], &ctrblk); + u128_inc(&ctrblk); + + camellia_enc_blk_xor(ctx, (u8 *)dst, (u8 *)ctrblocks); + + src += 1; + dst += 1; + nbytes -= bsize; + } while (nbytes >= bsize); + +done: + u128_to_be128((be128 *)walk->iv, &ctrblk); + return nbytes; +} + +static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt_block(desc, &walk, CAMELLIA_BLOCK_SIZE); + + while ((nbytes = walk.nbytes) >= CAMELLIA_BLOCK_SIZE) { + nbytes = __ctr_crypt(desc, &walk); + err = blkcipher_walk_done(desc, &walk, nbytes); + } + + if (walk.nbytes) { + ctr_crypt_final(desc, &walk); + err = blkcipher_walk_done(desc, &walk, 0); + } + + return err; +} + +static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes) +{ + const unsigned int bsize = CAMELLIA_BLOCK_SIZE; + struct camellia_ctx *ctx = priv; + int i; + + while (nbytes >= 2 * bsize) { + camellia_enc_blk_2way(ctx, srcdst, srcdst); + srcdst += bsize * 2; + nbytes -= bsize * 2; + } + + for (i = 0; i < nbytes / bsize; i++, srcdst += bsize) + camellia_enc_blk(ctx, srcdst, srcdst); +} + +static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes) +{ + const unsigned int bsize = CAMELLIA_BLOCK_SIZE; + struct camellia_ctx *ctx = priv; + int i; + + while (nbytes >= 2 * bsize) { + camellia_dec_blk_2way(ctx, srcdst, srcdst); + srcdst += bsize * 2; + nbytes -= bsize * 2; + } + + for (i = 0; i < nbytes / bsize; i++, srcdst += bsize) + camellia_dec_blk(ctx, srcdst, srcdst); +} + +struct camellia_lrw_ctx { + struct lrw_table_ctx lrw_table; + struct camellia_ctx camellia_ctx; +}; + +static int lrw_camellia_setkey(struct crypto_tfm *tfm, const u8 *key, + unsigned int keylen) +{ + struct camellia_lrw_ctx *ctx = crypto_tfm_ctx(tfm); + int err; + + err = __camellia_setkey(&ctx->camellia_ctx, key, + keylen - CAMELLIA_BLOCK_SIZE, + &tfm->crt_flags); + if (err) + return err; + + return lrw_init_table(&ctx->lrw_table, + key + keylen - CAMELLIA_BLOCK_SIZE); +} + +static int lrw_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct camellia_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + be128 buf[2 * 4]; + struct lrw_crypt_req req = { + .tbuf = buf, + .tbuflen = sizeof(buf), + + .table_ctx = &ctx->lrw_table, + .crypt_ctx = &ctx->camellia_ctx, + .crypt_fn = encrypt_callback, + }; + + return lrw_crypt(desc, dst, src, nbytes, &req); +} + +static int lrw_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct camellia_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + be128 buf[2 * 4]; + struct lrw_crypt_req req = { + .tbuf = buf, + .tbuflen = sizeof(buf), + + .table_ctx = &ctx->lrw_table, + .crypt_ctx = &ctx->camellia_ctx, + .crypt_fn = decrypt_callback, + }; + + return lrw_crypt(desc, dst, src, nbytes, &req); +} + +static void lrw_exit_tfm(struct crypto_tfm *tfm) +{ + struct camellia_lrw_ctx *ctx = crypto_tfm_ctx(tfm); + + lrw_free_table(&ctx->lrw_table); +} + +struct camellia_xts_ctx { + struct camellia_ctx tweak_ctx; + struct camellia_ctx crypt_ctx; +}; + +static int xts_camellia_setkey(struct crypto_tfm *tfm, const u8 *key, + unsigned int keylen) +{ + struct camellia_xts_ctx *ctx = crypto_tfm_ctx(tfm); + u32 *flags = &tfm->crt_flags; + int err; + + /* key consists of keys of equal size concatenated, therefore + * the length must be even + */ + if (keylen % 2) { + *flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; + return -EINVAL; + } + + /* first half of xts-key is for crypt */ + err = __camellia_setkey(&ctx->crypt_ctx, key, keylen / 2, flags); + if (err) + return err; + + /* second half of xts-key is for tweak */ + return __camellia_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2, + flags); +} + +static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct camellia_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + be128 buf[2 * 4]; + struct xts_crypt_req req = { + .tbuf = buf, + .tbuflen = sizeof(buf), + + .tweak_ctx = &ctx->tweak_ctx, + .tweak_fn = XTS_TWEAK_CAST(camellia_enc_blk), + .crypt_ctx = &ctx->crypt_ctx, + .crypt_fn = encrypt_callback, + }; + + return xts_crypt(desc, dst, src, nbytes, &req); +} + +static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct camellia_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + be128 buf[2 * 4]; + struct xts_crypt_req req = { + .tbuf = buf, + .tbuflen = sizeof(buf), + + .tweak_ctx = &ctx->tweak_ctx, + .tweak_fn = XTS_TWEAK_CAST(camellia_enc_blk), + .crypt_ctx = &ctx->crypt_ctx, + .crypt_fn = decrypt_callback, + }; + + return xts_crypt(desc, dst, src, nbytes, &req); +} + +static struct crypto_alg camellia_algs[6] = { { + .cra_name = "camellia", + .cra_driver_name = "camellia-asm", + .cra_priority = 200, + .cra_flags = CRYPTO_ALG_TYPE_CIPHER, + .cra_blocksize = CAMELLIA_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct camellia_ctx), + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(camellia_algs[0].cra_list), + .cra_u = { + .cipher = { + .cia_min_keysize = CAMELLIA_MIN_KEY_SIZE, + .cia_max_keysize = CAMELLIA_MAX_KEY_SIZE, + .cia_setkey = camellia_setkey, + .cia_encrypt = camellia_encrypt, + .cia_decrypt = camellia_decrypt + } + } +}, { + .cra_name = "ecb(camellia)", + .cra_driver_name = "ecb-camellia-asm", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = CAMELLIA_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct camellia_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(camellia_algs[1].cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = CAMELLIA_MIN_KEY_SIZE, + .max_keysize = CAMELLIA_MAX_KEY_SIZE, + .setkey = camellia_setkey, + .encrypt = ecb_encrypt, + .decrypt = ecb_decrypt, + }, + }, +}, { + .cra_name = "cbc(camellia)", + .cra_driver_name = "cbc-camellia-asm", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = CAMELLIA_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct camellia_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(camellia_algs[2].cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = CAMELLIA_MIN_KEY_SIZE, + .max_keysize = CAMELLIA_MAX_KEY_SIZE, + .ivsize = CAMELLIA_BLOCK_SIZE, + .setkey = camellia_setkey, + .encrypt = cbc_encrypt, + .decrypt = cbc_decrypt, + }, + }, +}, { + .cra_name = "ctr(camellia)", + .cra_driver_name = "ctr-camellia-asm", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct camellia_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(camellia_algs[3].cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = CAMELLIA_MIN_KEY_SIZE, + .max_keysize = CAMELLIA_MAX_KEY_SIZE, + .ivsize = CAMELLIA_BLOCK_SIZE, + .setkey = camellia_setkey, + .encrypt = ctr_crypt, + .decrypt = ctr_crypt, + }, + }, +}, { + .cra_name = "lrw(camellia)", + .cra_driver_name = "lrw-camellia-asm", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = CAMELLIA_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct camellia_lrw_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(camellia_algs[4].cra_list), + .cra_exit = lrw_exit_tfm, + .cra_u = { + .blkcipher = { + .min_keysize = CAMELLIA_MIN_KEY_SIZE + + CAMELLIA_BLOCK_SIZE, + .max_keysize = CAMELLIA_MAX_KEY_SIZE + + CAMELLIA_BLOCK_SIZE, + .ivsize = CAMELLIA_BLOCK_SIZE, + .setkey = lrw_camellia_setkey, + .encrypt = lrw_encrypt, + .decrypt = lrw_decrypt, + }, + }, +}, { + .cra_name = "xts(camellia)", + .cra_driver_name = "xts-camellia-asm", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = CAMELLIA_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct camellia_xts_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(camellia_algs[5].cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = CAMELLIA_MIN_KEY_SIZE * 2, + .max_keysize = CAMELLIA_MAX_KEY_SIZE * 2, + .ivsize = CAMELLIA_BLOCK_SIZE, + .setkey = xts_camellia_setkey, + .encrypt = xts_encrypt, + .decrypt = xts_decrypt, + }, + }, +} }; + +static bool is_blacklisted_cpu(void) +{ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return false; + + if (boot_cpu_data.x86 == 0x0f) { + /* + * On Pentium 4, camellia-asm is slower than original assembler + * implementation because excessive uses of 64bit rotate and + * left-shifts (which are really slow on P4) needed to store and + * handle 128bit block in two 64bit registers. + */ + return true; + } + + return false; +} + +static int force; +module_param(force, int, 0); +MODULE_PARM_DESC(force, "Force module load, ignore CPU blacklist"); + +static int __init init(void) +{ + if (!force && is_blacklisted_cpu()) { + printk(KERN_INFO + "camellia-x86_64: performance on this CPU " + "would be suboptimal: disabling " + "camellia-x86_64.\n"); + return -ENODEV; + } + + return crypto_register_algs(camellia_algs, ARRAY_SIZE(camellia_algs)); +} + +static void __exit fini(void) +{ + crypto_unregister_algs(camellia_algs, ARRAY_SIZE(camellia_algs)); +} + +module_init(init); +module_exit(fini); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Camellia Cipher Algorithm, asm optimized"); +MODULE_ALIAS("camellia"); +MODULE_ALIAS("camellia-asm"); diff --git a/arch/x86/crypto/crc32c-intel.c b/arch/x86/crypto/crc32c-intel.c index b9d00261703..493f959261f 100644 --- a/arch/x86/crypto/crc32c-intel.c +++ b/arch/x86/crypto/crc32c-intel.c @@ -31,6 +31,7 @@ #include <crypto/internal/hash.h> #include <asm/cpufeature.h> +#include <asm/cpu_device_id.h> #define CHKSUM_BLOCK_SIZE 1 #define CHKSUM_DIGEST_SIZE 4 @@ -173,13 +174,17 @@ static struct shash_alg alg = { } }; +static const struct x86_cpu_id crc32c_cpu_id[] = { + X86_FEATURE_MATCH(X86_FEATURE_XMM4_2), + {} +}; +MODULE_DEVICE_TABLE(x86cpu, crc32c_cpu_id); static int __init crc32c_intel_mod_init(void) { - if (cpu_has_xmm4_2) - return crypto_register_shash(&alg); - else + if (!x86_match_cpu(crc32c_cpu_id)) return -ENODEV; + return crypto_register_shash(&alg); } static void __exit crc32c_intel_mod_fini(void) diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index 976aa64d9a2..b4bf0a63b52 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -20,6 +20,7 @@ #include <crypto/gf128mul.h> #include <crypto/internal/hash.h> #include <asm/i387.h> +#include <asm/cpu_device_id.h> #define GHASH_BLOCK_SIZE 16 #define GHASH_DIGEST_SIZE 16 @@ -294,15 +295,18 @@ static struct ahash_alg ghash_async_alg = { }, }; +static const struct x86_cpu_id pcmul_cpu_id[] = { + X86_FEATURE_MATCH(X86_FEATURE_PCLMULQDQ), /* Pickle-Mickle-Duck */ + {} +}; +MODULE_DEVICE_TABLE(x86cpu, pcmul_cpu_id); + static int __init ghash_pclmulqdqni_mod_init(void) { int err; - if (!cpu_has_pclmulqdq) { - printk(KERN_INFO "Intel PCLMULQDQ-NI instructions are not" - " detected.\n"); + if (!x86_match_cpu(pcmul_cpu_id)) return -ENODEV; - } err = crypto_register_shash(&ghash_alg); if (err) diff --git a/arch/x86/crypto/serpent-sse2-i586-asm_32.S b/arch/x86/crypto/serpent-sse2-i586-asm_32.S index 4e37677ca85..c00053d42f9 100644 --- a/arch/x86/crypto/serpent-sse2-i586-asm_32.S +++ b/arch/x86/crypto/serpent-sse2-i586-asm_32.S @@ -463,23 +463,20 @@ pand x0, x4; \ pxor x2, x4; -#define transpose_4x4(x0, x1, x2, x3, t1, t2, t3) \ - movdqa x2, t3; \ - movdqa x0, t1; \ - unpcklps x3, t3; \ +#define transpose_4x4(x0, x1, x2, x3, t0, t1, t2) \ movdqa x0, t2; \ - unpcklps x1, t1; \ - unpckhps x1, t2; \ - movdqa t3, x1; \ - unpckhps x3, x2; \ - movdqa t1, x0; \ - movhlps t1, x1; \ - movdqa t2, t1; \ - movlhps t3, x0; \ - movlhps x2, t1; \ - movhlps t2, x2; \ - movdqa x2, x3; \ - movdqa t1, x2; + punpckldq x1, x0; \ + punpckhdq x1, t2; \ + movdqa x2, t1; \ + punpckhdq x3, x2; \ + punpckldq x3, t1; \ + movdqa x0, x1; \ + punpcklqdq t1, x0; \ + punpckhqdq t1, x1; \ + movdqa t2, x3; \ + punpcklqdq x2, t2; \ + punpckhqdq x2, x3; \ + movdqa t2, x2; #define read_blocks(in, x0, x1, x2, x3, t0, t1, t2) \ movdqu (0*4*4)(in), x0; \ diff --git a/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S b/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S index 7f24a154082..3ee1ff04d3e 100644 --- a/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S +++ b/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S @@ -585,23 +585,20 @@ get_key(i, 1, RK1); \ SBOX ## _2(x0 ## 2, x1 ## 2, x2 ## 2, x3 ## 2, x4 ## 2); \ -#define transpose_4x4(x0, x1, x2, x3, t1, t2, t3) \ - movdqa x2, t3; \ - movdqa x0, t1; \ - unpcklps x3, t3; \ +#define transpose_4x4(x0, x1, x2, x3, t0, t1, t2) \ movdqa x0, t2; \ - unpcklps x1, t1; \ - unpckhps x1, t2; \ - movdqa t3, x1; \ - unpckhps x3, x2; \ - movdqa t1, x0; \ - movhlps t1, x1; \ - movdqa t2, t1; \ - movlhps t3, x0; \ - movlhps x2, t1; \ - movhlps t2, x2; \ - movdqa x2, x3; \ - movdqa t1, x2; + punpckldq x1, x0; \ + punpckhdq x1, t2; \ + movdqa x2, t1; \ + punpckhdq x3, x2; \ + punpckldq x3, t1; \ + movdqa x0, x1; \ + punpcklqdq t1, x0; \ + punpckhqdq t1, x1; \ + movdqa t2, x3; \ + punpcklqdq x2, t2; \ + punpckhqdq x2, x3; \ + movdqa t2, x2; #define read_blocks(in, x0, x1, x2, x3, t0, t1, t2) \ movdqu (0*4*4)(in), x0; \ diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c index 7955a9b76b9..4b21be85e0a 100644 --- a/arch/x86/crypto/serpent_sse2_glue.c +++ b/arch/x86/crypto/serpent_sse2_glue.c @@ -145,28 +145,6 @@ static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, return ecb_crypt(desc, &walk, false); } -static struct crypto_alg blk_ecb_alg = { - .cra_name = "__ecb-serpent-sse2", - .cra_driver_name = "__driver-ecb-serpent-sse2", - .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = SERPENT_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct serpent_ctx), - .cra_alignmask = 0, - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_list = LIST_HEAD_INIT(blk_ecb_alg.cra_list), - .cra_u = { - .blkcipher = { - .min_keysize = SERPENT_MIN_KEY_SIZE, - .max_keysize = SERPENT_MAX_KEY_SIZE, - .setkey = serpent_setkey, - .encrypt = ecb_encrypt, - .decrypt = ecb_decrypt, - }, - }, -}; - static unsigned int __cbc_encrypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk) { @@ -295,28 +273,6 @@ static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, return err; } -static struct crypto_alg blk_cbc_alg = { - .cra_name = "__cbc-serpent-sse2", - .cra_driver_name = "__driver-cbc-serpent-sse2", - .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = SERPENT_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct serpent_ctx), - .cra_alignmask = 0, - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_list = LIST_HEAD_INIT(blk_cbc_alg.cra_list), - .cra_u = { - .blkcipher = { - .min_keysize = SERPENT_MIN_KEY_SIZE, - .max_keysize = SERPENT_MAX_KEY_SIZE, - .setkey = serpent_setkey, - .encrypt = cbc_encrypt, - .decrypt = cbc_decrypt, - }, - }, -}; - static inline void u128_to_be128(be128 *dst, const u128 *src) { dst->a = cpu_to_be64(src->a); @@ -439,29 +395,6 @@ static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst, return err; } -static struct crypto_alg blk_ctr_alg = { - .cra_name = "__ctr-serpent-sse2", - .cra_driver_name = "__driver-ctr-serpent-sse2", - .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = 1, - .cra_ctxsize = sizeof(struct serpent_ctx), - .cra_alignmask = 0, - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_list = LIST_HEAD_INIT(blk_ctr_alg.cra_list), - .cra_u = { - .blkcipher = { - .min_keysize = SERPENT_MIN_KEY_SIZE, - .max_keysize = SERPENT_MAX_KEY_SIZE, - .ivsize = SERPENT_BLOCK_SIZE, - .setkey = serpent_setkey, - .encrypt = ctr_crypt, - .decrypt = ctr_crypt, - }, - }, -}; - struct crypt_priv { struct serpent_ctx *ctx; bool fpu_enabled; @@ -580,32 +513,6 @@ static void lrw_exit_tfm(struct crypto_tfm *tfm) lrw_free_table(&ctx->lrw_table); } -static struct crypto_alg blk_lrw_alg = { - .cra_name = "__lrw-serpent-sse2", - .cra_driver_name = "__driver-lrw-serpent-sse2", - .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = SERPENT_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct serpent_lrw_ctx), - .cra_alignmask = 0, - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_list = LIST_HEAD_INIT(blk_lrw_alg.cra_list), - .cra_exit = lrw_exit_tfm, - .cra_u = { - .blkcipher = { - .min_keysize = SERPENT_MIN_KEY_SIZE + - SERPENT_BLOCK_SIZE, - .max_keysize = SERPENT_MAX_KEY_SIZE + - SERPENT_BLOCK_SIZE, - .ivsize = SERPENT_BLOCK_SIZE, - .setkey = lrw_serpent_setkey, - .encrypt = lrw_encrypt, - .decrypt = lrw_decrypt, - }, - }, -}; - struct serpent_xts_ctx { struct serpent_ctx tweak_ctx; struct serpent_ctx crypt_ctx; @@ -689,29 +596,6 @@ static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, return ret; } -static struct crypto_alg blk_xts_alg = { - .cra_name = "__xts-serpent-sse2", - .cra_driver_name = "__driver-xts-serpent-sse2", - .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = SERPENT_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct serpent_xts_ctx), - .cra_alignmask = 0, - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_list = LIST_HEAD_INIT(blk_xts_alg.cra_list), - .cra_u = { - .blkcipher = { - .min_keysize = SERPENT_MIN_KEY_SIZE * 2, - .max_keysize = SERPENT_MAX_KEY_SIZE * 2, - .ivsize = SERPENT_BLOCK_SIZE, - .setkey = xts_serpent_setkey, - .encrypt = xts_encrypt, - .decrypt = xts_decrypt, - }, - }, -}; - static int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key, unsigned int key_len) { @@ -792,28 +676,133 @@ static void ablk_exit(struct crypto_tfm *tfm) cryptd_free_ablkcipher(ctx->cryptd_tfm); } -static void ablk_init_common(struct crypto_tfm *tfm, - struct cryptd_ablkcipher *cryptd_tfm) +static int ablk_init(struct crypto_tfm *tfm) { struct async_serpent_ctx *ctx = crypto_tfm_ctx(tfm); + struct cryptd_ablkcipher *cryptd_tfm; + char drv_name[CRYPTO_MAX_ALG_NAME]; + + snprintf(drv_name, sizeof(drv_name), "__driver-%s", + crypto_tfm_alg_driver_name(tfm)); + + cryptd_tfm = cryptd_alloc_ablkcipher(drv_name, 0, 0); + if (IS_ERR(cryptd_tfm)) + return PTR_ERR(cryptd_tfm); ctx->cryptd_tfm = cryptd_tfm; tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request) + crypto_ablkcipher_reqsize(&cryptd_tfm->base); -} - -static int ablk_ecb_init(struct crypto_tfm *tfm) -{ - struct cryptd_ablkcipher *cryptd_tfm; - cryptd_tfm = cryptd_alloc_ablkcipher("__driver-ecb-serpent-sse2", 0, 0); - if (IS_ERR(cryptd_tfm)) - return PTR_ERR(cryptd_tfm); - ablk_init_common(tfm, cryptd_tfm); return 0; } -static struct crypto_alg ablk_ecb_alg = { +static struct crypto_alg serpent_algs[10] = { { + .cra_name = "__ecb-serpent-sse2", + .cra_driver_name = "__driver-ecb-serpent-sse2", + .cra_priority = 0, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = SERPENT_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct serpent_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(serpent_algs[0].cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = SERPENT_MIN_KEY_SIZE, + .max_keysize = SERPENT_MAX_KEY_SIZE, + .setkey = serpent_setkey, + .encrypt = ecb_encrypt, + .decrypt = ecb_decrypt, + }, + }, +}, { + .cra_name = "__cbc-serpent-sse2", + .cra_driver_name = "__driver-cbc-serpent-sse2", + .cra_priority = 0, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = SERPENT_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct serpent_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(serpent_algs[1].cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = SERPENT_MIN_KEY_SIZE, + .max_keysize = SERPENT_MAX_KEY_SIZE, + .setkey = serpent_setkey, + .encrypt = cbc_encrypt, + .decrypt = cbc_decrypt, + }, + }, +}, { + .cra_name = "__ctr-serpent-sse2", + .cra_driver_name = "__driver-ctr-serpent-sse2", + .cra_priority = 0, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct serpent_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(serpent_algs[2].cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = SERPENT_MIN_KEY_SIZE, + .max_keysize = SERPENT_MAX_KEY_SIZE, + .ivsize = SERPENT_BLOCK_SIZE, + .setkey = serpent_setkey, + .encrypt = ctr_crypt, + .decrypt = ctr_crypt, + }, + }, +}, { + .cra_name = "__lrw-serpent-sse2", + .cra_driver_name = "__driver-lrw-serpent-sse2", + .cra_priority = 0, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = SERPENT_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct serpent_lrw_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(serpent_algs[3].cra_list), + .cra_exit = lrw_exit_tfm, + .cra_u = { + .blkcipher = { + .min_keysize = SERPENT_MIN_KEY_SIZE + + SERPENT_BLOCK_SIZE, + .max_keysize = SERPENT_MAX_KEY_SIZE + + SERPENT_BLOCK_SIZE, + .ivsize = SERPENT_BLOCK_SIZE, + .setkey = lrw_serpent_setkey, + .encrypt = lrw_encrypt, + .decrypt = lrw_decrypt, + }, + }, +}, { + .cra_name = "__xts-serpent-sse2", + .cra_driver_name = "__driver-xts-serpent-sse2", + .cra_priority = 0, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = SERPENT_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct serpent_xts_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(serpent_algs[4].cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = SERPENT_MIN_KEY_SIZE * 2, + .max_keysize = SERPENT_MAX_KEY_SIZE * 2, + .ivsize = SERPENT_BLOCK_SIZE, + .setkey = xts_serpent_setkey, + .encrypt = xts_encrypt, + .decrypt = xts_decrypt, + }, + }, +}, { .cra_name = "ecb(serpent)", .cra_driver_name = "ecb-serpent-sse2", .cra_priority = 400, @@ -823,8 +812,8 @@ static struct crypto_alg ablk_ecb_alg = { .cra_alignmask = 0, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, - .cra_list = LIST_HEAD_INIT(ablk_ecb_alg.cra_list), - .cra_init = ablk_ecb_init, + .cra_list = LIST_HEAD_INIT(serpent_algs[5].cra_list), + .cra_init = ablk_init, .cra_exit = ablk_exit, .cra_u = { .ablkcipher = { @@ -835,20 +824,7 @@ static struct crypto_alg ablk_ecb_alg = { .decrypt = ablk_decrypt, }, }, -}; - -static int ablk_cbc_init(struct crypto_tfm *tfm) -{ - struct cryptd_ablkcipher *cryptd_tfm; - - cryptd_tfm = cryptd_alloc_ablkcipher("__driver-cbc-serpent-sse2", 0, 0); - if (IS_ERR(cryptd_tfm)) - return PTR_ERR(cryptd_tfm); - ablk_init_common(tfm, cryptd_tfm); - return 0; -} - -static struct crypto_alg ablk_cbc_alg = { +}, { .cra_name = "cbc(serpent)", .cra_driver_name = "cbc-serpent-sse2", .cra_priority = 400, @@ -858,8 +834,8 @@ static struct crypto_alg ablk_cbc_alg = { .cra_alignmask = 0, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, - .cra_list = LIST_HEAD_INIT(ablk_cbc_alg.cra_list), - .cra_init = ablk_cbc_init, + .cra_list = LIST_HEAD_INIT(serpent_algs[6].cra_list), + .cra_init = ablk_init, .cra_exit = ablk_exit, .cra_u = { .ablkcipher = { @@ -871,20 +847,7 @@ static struct crypto_alg ablk_cbc_alg = { .decrypt = ablk_decrypt, }, }, -}; - -static int ablk_ctr_init(struct crypto_tfm *tfm) -{ - struct cryptd_ablkcipher *cryptd_tfm; - - cryptd_tfm = cryptd_alloc_ablkcipher("__driver-ctr-serpent-sse2", 0, 0); - if (IS_ERR(cryptd_tfm)) - return PTR_ERR(cryptd_tfm); - ablk_init_common(tfm, cryptd_tfm); - return 0; -} - -static struct crypto_alg ablk_ctr_alg = { +}, { .cra_name = "ctr(serpent)", .cra_driver_name = "ctr-serpent-sse2", .cra_priority = 400, @@ -894,8 +857,8 @@ static struct crypto_alg ablk_ctr_alg = { .cra_alignmask = 0, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, - .cra_list = LIST_HEAD_INIT(ablk_ctr_alg.cra_list), - .cra_init = ablk_ctr_init, + .cra_list = LIST_HEAD_INIT(serpent_algs[7].cra_list), + .cra_init = ablk_init, .cra_exit = ablk_exit, .cra_u = { .ablkcipher = { @@ -908,20 +871,7 @@ static struct crypto_alg ablk_ctr_alg = { .geniv = "chainiv", }, }, -}; - -static int ablk_lrw_init(struct crypto_tfm *tfm) -{ - struct cryptd_ablkcipher *cryptd_tfm; - - cryptd_tfm = cryptd_alloc_ablkcipher("__driver-lrw-serpent-sse2", 0, 0); - if (IS_ERR(cryptd_tfm)) - return PTR_ERR(cryptd_tfm); - ablk_init_common(tfm, cryptd_tfm); - return 0; -} - -static struct crypto_alg ablk_lrw_alg = { +}, { .cra_name = "lrw(serpent)", .cra_driver_name = "lrw-serpent-sse2", .cra_priority = 400, @@ -931,8 +881,8 @@ static struct crypto_alg ablk_lrw_alg = { .cra_alignmask = 0, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, - .cra_list = LIST_HEAD_INIT(ablk_lrw_alg.cra_list), - .cra_init = ablk_lrw_init, + .cra_list = LIST_HEAD_INIT(serpent_algs[8].cra_list), + .cra_init = ablk_init, .cra_exit = ablk_exit, .cra_u = { .ablkcipher = { @@ -946,20 +896,7 @@ static struct crypto_alg ablk_lrw_alg = { .decrypt = ablk_decrypt, }, }, -}; - -static int ablk_xts_init(struct crypto_tfm *tfm) -{ - struct cryptd_ablkcipher *cryptd_tfm; - - cryptd_tfm = cryptd_alloc_ablkcipher("__driver-xts-serpent-sse2", 0, 0); - if (IS_ERR(cryptd_tfm)) - return PTR_ERR(cryptd_tfm); - ablk_init_common(tfm, cryptd_tfm); - return 0; -} - -static struct crypto_alg ablk_xts_alg = { +}, { .cra_name = "xts(serpent)", .cra_driver_name = "xts-serpent-sse2", .cra_priority = 400, @@ -969,8 +906,8 @@ static struct crypto_alg ablk_xts_alg = { .cra_alignmask = 0, .cra_type = &crypto_ablkcipher_type, .cra_module = THIS_MODULE, - .cra_list = LIST_HEAD_INIT(ablk_xts_alg.cra_list), - .cra_init = ablk_xts_init, + .cra_list = LIST_HEAD_INIT(serpent_algs[9].cra_list), + .cra_init = ablk_init, .cra_exit = ablk_exit, .cra_u = { .ablkcipher = { @@ -982,84 +919,21 @@ static struct crypto_alg ablk_xts_alg = { .decrypt = ablk_decrypt, }, }, -}; +} }; static int __init serpent_sse2_init(void) { - int err; - if (!cpu_has_xmm2) { printk(KERN_INFO "SSE2 instructions are not detected.\n"); return -ENODEV; } - err = crypto_register_alg(&blk_ecb_alg); - if (err) - goto blk_ecb_err; - err = crypto_register_alg(&blk_cbc_alg); - if (err) - goto blk_cbc_err; - err = crypto_register_alg(&blk_ctr_alg); - if (err) - goto blk_ctr_err; - err = crypto_register_alg(&ablk_ecb_alg); - if (err) - goto ablk_ecb_err; - err = crypto_register_alg(&ablk_cbc_alg); - if (err) - goto ablk_cbc_err; - err = crypto_register_alg(&ablk_ctr_alg); - if (err) - goto ablk_ctr_err; - err = crypto_register_alg(&blk_lrw_alg); - if (err) - goto blk_lrw_err; - err = crypto_register_alg(&ablk_lrw_alg); - if (err) - goto ablk_lrw_err; - err = crypto_register_alg(&blk_xts_alg); - if (err) - goto blk_xts_err; - err = crypto_register_alg(&ablk_xts_alg); - if (err) - goto ablk_xts_err; - return err; - - crypto_unregister_alg(&ablk_xts_alg); -ablk_xts_err: - crypto_unregister_alg(&blk_xts_alg); -blk_xts_err: - crypto_unregister_alg(&ablk_lrw_alg); -ablk_lrw_err: - crypto_unregister_alg(&blk_lrw_alg); -blk_lrw_err: - crypto_unregister_alg(&ablk_ctr_alg); -ablk_ctr_err: - crypto_unregister_alg(&ablk_cbc_alg); -ablk_cbc_err: - crypto_unregister_alg(&ablk_ecb_alg); -ablk_ecb_err: - crypto_unregister_alg(&blk_ctr_alg); -blk_ctr_err: - crypto_unregister_alg(&blk_cbc_alg); -blk_cbc_err: - crypto_unregister_alg(&blk_ecb_alg); -blk_ecb_err: - return err; + return crypto_register_algs(serpent_algs, ARRAY_SIZE(serpent_algs)); } static void __exit serpent_sse2_exit(void) { - crypto_unregister_alg(&ablk_xts_alg); - crypto_unregister_alg(&blk_xts_alg); - crypto_unregister_alg(&ablk_lrw_alg); - crypto_unregister_alg(&blk_lrw_alg); - crypto_unregister_alg(&ablk_ctr_alg); - crypto_unregister_alg(&ablk_cbc_alg); - crypto_unregister_alg(&ablk_ecb_alg); - crypto_unregister_alg(&blk_ctr_alg); - crypto_unregister_alg(&blk_cbc_alg); - crypto_unregister_alg(&blk_ecb_alg); + crypto_unregister_algs(serpent_algs, ARRAY_SIZE(serpent_algs)); } module_init(serpent_sse2_init); diff --git a/arch/x86/crypto/twofish_glue.c b/arch/x86/crypto/twofish_glue.c index dc6b3fb817f..359ae084275 100644 --- a/arch/x86/crypto/twofish_glue.c +++ b/arch/x86/crypto/twofish_glue.c @@ -68,7 +68,7 @@ static struct crypto_alg alg = { .cra_flags = CRYPTO_ALG_TYPE_CIPHER, .cra_blocksize = TF_BLOCK_SIZE, .cra_ctxsize = sizeof(struct twofish_ctx), - .cra_alignmask = 3, + .cra_alignmask = 0, .cra_module = THIS_MODULE, .cra_list = LIST_HEAD_INIT(alg.cra_list), .cra_u = { diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c index 7fee8c152f9..922ab24cce3 100644 --- a/arch/x86/crypto/twofish_glue_3way.c +++ b/arch/x86/crypto/twofish_glue_3way.c @@ -25,6 +25,7 @@ * */ +#include <asm/processor.h> #include <linux/crypto.h> #include <linux/init.h> #include <linux/module.h> @@ -122,28 +123,6 @@ static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, return ecb_crypt(desc, &walk, twofish_dec_blk, twofish_dec_blk_3way); } -static struct crypto_alg blk_ecb_alg = { - .cra_name = "ecb(twofish)", - .cra_driver_name = "ecb-twofish-3way", - .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = TF_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct twofish_ctx), - .cra_alignmask = 0, - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_list = LIST_HEAD_INIT(blk_ecb_alg.cra_list), - .cra_u = { - .blkcipher = { - .min_keysize = TF_MIN_KEY_SIZE, - .max_keysize = TF_MAX_KEY_SIZE, - .setkey = twofish_setkey, - .encrypt = ecb_encrypt, - .decrypt = ecb_decrypt, - }, - }, -}; - static unsigned int __cbc_encrypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk) { @@ -267,29 +246,6 @@ static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, return err; } -static struct crypto_alg blk_cbc_alg = { - .cra_name = "cbc(twofish)", - .cra_driver_name = "cbc-twofish-3way", - .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = TF_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct twofish_ctx), - .cra_alignmask = 0, - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_list = LIST_HEAD_INIT(blk_cbc_alg.cra_list), - .cra_u = { - .blkcipher = { - .min_keysize = TF_MIN_KEY_SIZE, - .max_keysize = TF_MAX_KEY_SIZE, - .ivsize = TF_BLOCK_SIZE, - .setkey = twofish_setkey, - .encrypt = cbc_encrypt, - .decrypt = cbc_decrypt, - }, - }, -}; - static inline void u128_to_be128(be128 *dst, const u128 *src) { dst->a = cpu_to_be64(src->a); @@ -411,29 +367,6 @@ static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst, return err; } -static struct crypto_alg blk_ctr_alg = { - .cra_name = "ctr(twofish)", - .cra_driver_name = "ctr-twofish-3way", - .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = 1, - .cra_ctxsize = sizeof(struct twofish_ctx), - .cra_alignmask = 0, - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_list = LIST_HEAD_INIT(blk_ctr_alg.cra_list), - .cra_u = { - .blkcipher = { - .min_keysize = TF_MIN_KEY_SIZE, - .max_keysize = TF_MAX_KEY_SIZE, - .ivsize = TF_BLOCK_SIZE, - .setkey = twofish_setkey, - .encrypt = ctr_crypt, - .decrypt = ctr_crypt, - }, - }, -}; - static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes) { const unsigned int bsize = TF_BLOCK_SIZE; @@ -524,30 +457,6 @@ static void lrw_exit_tfm(struct crypto_tfm *tfm) lrw_free_table(&ctx->lrw_table); } -static struct crypto_alg blk_lrw_alg = { - .cra_name = "lrw(twofish)", - .cra_driver_name = "lrw-twofish-3way", - .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = TF_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct twofish_lrw_ctx), - .cra_alignmask = 0, - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_list = LIST_HEAD_INIT(blk_lrw_alg.cra_list), - .cra_exit = lrw_exit_tfm, - .cra_u = { - .blkcipher = { - .min_keysize = TF_MIN_KEY_SIZE + TF_BLOCK_SIZE, - .max_keysize = TF_MAX_KEY_SIZE + TF_BLOCK_SIZE, - .ivsize = TF_BLOCK_SIZE, - .setkey = lrw_twofish_setkey, - .encrypt = lrw_encrypt, - .decrypt = lrw_decrypt, - }, - }, -}; - struct twofish_xts_ctx { struct twofish_ctx tweak_ctx; struct twofish_ctx crypt_ctx; @@ -614,7 +523,91 @@ static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, return xts_crypt(desc, dst, src, nbytes, &req); } -static struct crypto_alg blk_xts_alg = { +static struct crypto_alg tf_algs[5] = { { + .cra_name = "ecb(twofish)", + .cra_driver_name = "ecb-twofish-3way", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = TF_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct twofish_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(tf_algs[0].cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = TF_MIN_KEY_SIZE, + .max_keysize = TF_MAX_KEY_SIZE, + .setkey = twofish_setkey, + .encrypt = ecb_encrypt, + .decrypt = ecb_decrypt, + }, + }, +}, { + .cra_name = "cbc(twofish)", + .cra_driver_name = "cbc-twofish-3way", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = TF_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct twofish_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(tf_algs[1].cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = TF_MIN_KEY_SIZE, + .max_keysize = TF_MAX_KEY_SIZE, + .ivsize = TF_BLOCK_SIZE, + .setkey = twofish_setkey, + .encrypt = cbc_encrypt, + .decrypt = cbc_decrypt, + }, + }, +}, { + .cra_name = "ctr(twofish)", + .cra_driver_name = "ctr-twofish-3way", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct twofish_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(tf_algs[2].cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = TF_MIN_KEY_SIZE, + .max_keysize = TF_MAX_KEY_SIZE, + .ivsize = TF_BLOCK_SIZE, + .setkey = twofish_setkey, + .encrypt = ctr_crypt, + .decrypt = ctr_crypt, + }, + }, +}, { + .cra_name = "lrw(twofish)", + .cra_driver_name = "lrw-twofish-3way", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = TF_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct twofish_lrw_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(tf_algs[3].cra_list), + .cra_exit = lrw_exit_tfm, + .cra_u = { + .blkcipher = { + .min_keysize = TF_MIN_KEY_SIZE + TF_BLOCK_SIZE, + .max_keysize = TF_MAX_KEY_SIZE + TF_BLOCK_SIZE, + .ivsize = TF_BLOCK_SIZE, + .setkey = lrw_twofish_setkey, + .encrypt = lrw_encrypt, + .decrypt = lrw_decrypt, + }, + }, +}, { .cra_name = "xts(twofish)", .cra_driver_name = "xts-twofish-3way", .cra_priority = 300, @@ -624,7 +617,7 @@ static struct crypto_alg blk_xts_alg = { .cra_alignmask = 0, .cra_type = &crypto_blkcipher_type, .cra_module = THIS_MODULE, - .cra_list = LIST_HEAD_INIT(blk_xts_alg.cra_list), + .cra_list = LIST_HEAD_INIT(tf_algs[4].cra_list), .cra_u = { .blkcipher = { .min_keysize = TF_MIN_KEY_SIZE * 2, @@ -635,50 +628,62 @@ static struct crypto_alg blk_xts_alg = { .decrypt = xts_decrypt, }, }, -}; +} }; -int __init init(void) +static bool is_blacklisted_cpu(void) { - int err; + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return false; + + if (boot_cpu_data.x86 == 0x06 && + (boot_cpu_data.x86_model == 0x1c || + boot_cpu_data.x86_model == 0x26 || + boot_cpu_data.x86_model == 0x36)) { + /* + * On Atom, twofish-3way is slower than original assembler + * implementation. Twofish-3way trades off some performance in + * storing blocks in 64bit registers to allow three blocks to + * be processed parallel. Parallel operation then allows gaining + * more performance than was trade off, on out-of-order CPUs. + * However Atom does not benefit from this parallellism and + * should be blacklisted. + */ + return true; + } - err = crypto_register_alg(&blk_ecb_alg); - if (err) - goto ecb_err; - err = crypto_register_alg(&blk_cbc_alg); - if (err) - goto cbc_err; - err = crypto_register_alg(&blk_ctr_alg); - if (err) - goto ctr_err; - err = crypto_register_alg(&blk_lrw_alg); - if (err) - goto blk_lrw_err; - err = crypto_register_alg(&blk_xts_alg); - if (err) - goto blk_xts_err; - - return 0; - - crypto_unregister_alg(&blk_xts_alg); -blk_xts_err: - crypto_unregister_alg(&blk_lrw_alg); -blk_lrw_err: - crypto_unregister_alg(&blk_ctr_alg); -ctr_err: - crypto_unregister_alg(&blk_cbc_alg); -cbc_err: - crypto_unregister_alg(&blk_ecb_alg); -ecb_err: - return err; + if (boot_cpu_data.x86 == 0x0f) { + /* + * On Pentium 4, twofish-3way is slower than original assembler + * implementation because excessive uses of 64bit rotate and + * left-shifts (which are really slow on P4) needed to store and + * handle 128bit block in two 64bit registers. + */ + return true; + } + + return false; +} + +static int force; +module_param(force, int, 0); +MODULE_PARM_DESC(force, "Force module load, ignore CPU blacklist"); + +static int __init init(void) +{ + if (!force && is_blacklisted_cpu()) { + printk(KERN_INFO + "twofish-x86_64-3way: performance on this CPU " + "would be suboptimal: disabling " + "twofish-x86_64-3way.\n"); + return -ENODEV; + } + + return crypto_register_algs(tf_algs, ARRAY_SIZE(tf_algs)); } -void __exit fini(void) +static void __exit fini(void) { - crypto_unregister_alg(&blk_xts_alg); - crypto_unregister_alg(&blk_lrw_alg); - crypto_unregister_alg(&blk_ctr_alg); - crypto_unregister_alg(&blk_cbc_alg); - crypto_unregister_alg(&blk_ecb_alg); + crypto_unregister_algs(tf_algs, ARRAY_SIZE(tf_algs)); } module_init(init); diff --git a/arch/x86/ia32/Makefile b/arch/x86/ia32/Makefile index 52d0ccfcf6e..455646e0e53 100644 --- a/arch/x86/ia32/Makefile +++ b/arch/x86/ia32/Makefile @@ -3,6 +3,7 @@ # obj-$(CONFIG_IA32_EMULATION) := ia32entry.o sys_ia32.o ia32_signal.o +obj-$(CONFIG_IA32_EMULATION) += nosyscall.o syscall_ia32.o sysv-$(CONFIG_SYSVIPC) := ipc32.o obj-$(CONFIG_IA32_EMULATION) += $(sysv-y) diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index fd843877e84..d511d951a05 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -26,7 +26,6 @@ #include <linux/init.h> #include <linux/jiffies.h> -#include <asm/system.h> #include <asm/uaccess.h> #include <asm/pgalloc.h> #include <asm/cacheflush.h> @@ -315,8 +314,14 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs) current->mm->free_area_cache = TASK_UNMAPPED_BASE; current->mm->cached_hole_size = 0; + retval = setup_arg_pages(bprm, IA32_STACK_TOP, EXSTACK_DEFAULT); + if (retval < 0) { + /* Someone check-me: is this error path enough? */ + send_sig(SIGKILL, current, 0); + return retval; + } + install_exec_creds(bprm); - current->flags &= ~PF_FORKNOEXEC; if (N_MAGIC(ex) == OMAGIC) { unsigned long text_addr, map_size; @@ -410,13 +415,6 @@ beyond_if: set_brk(current->mm->start_brk, current->mm->brk); - retval = setup_arg_pages(bprm, IA32_STACK_TOP, EXSTACK_DEFAULT); - if (retval < 0) { - /* Someone check-me: is this error path enough? */ - send_sig(SIGKILL, current, 0); - return retval; - } - current->mm->start_stack = (unsigned long)create_aout_tables((char __user *)bprm->p, bprm); /* start thread */ @@ -519,7 +517,8 @@ out: static int __init init_aout_binfmt(void) { - return register_binfmt(&aout_format); + register_binfmt(&aout_format); + return 0; } static void __exit exit_aout_binfmt(void) diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 65577698cab..a69245ba27e 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -12,10 +12,8 @@ #include <linux/mm.h> #include <linux/smp.h> #include <linux/kernel.h> -#include <linux/signal.h> #include <linux/errno.h> #include <linux/wait.h> -#include <linux/ptrace.h> #include <linux/unistd.h> #include <linux/stddef.h> #include <linux/personality.h> @@ -24,6 +22,7 @@ #include <asm/ucontext.h> #include <asm/uaccess.h> #include <asm/i387.h> +#include <asm/fpu-internal.h> #include <asm/ptrace.h> #include <asm/ia32_unistd.h> #include <asm/user32.h> @@ -31,20 +30,15 @@ #include <asm/proto.h> #include <asm/vdso.h> #include <asm/sigframe.h> +#include <asm/sighandling.h> #include <asm/sys_ia32.h> -#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) - -#define FIX_EFLAGS (X86_EFLAGS_AC | X86_EFLAGS_OF | \ - X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \ - X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \ - X86_EFLAGS_CF) - -void signal_fault(struct pt_regs *regs, void __user *frame, char *where); +#define FIX_EFLAGS __FIX_EFLAGS int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) { int err = 0; + bool ia32 = is_ia32_task(); if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t))) return -EFAULT; @@ -74,8 +68,13 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) case __SI_FAULT >> 16: break; case __SI_CHLD >> 16: - put_user_ex(from->si_utime, &to->si_utime); - put_user_ex(from->si_stime, &to->si_stime); + 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: @@ -347,7 +346,7 @@ static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc, put_user_ex(regs->dx, &sc->dx); put_user_ex(regs->cx, &sc->cx); put_user_ex(regs->ax, &sc->ax); - put_user_ex(current->thread.trap_no, &sc->trapno); + put_user_ex(current->thread.trap_nr, &sc->trapno); put_user_ex(current->thread.error_code, &sc->err); put_user_ex(regs->ip, &sc->ip); put_user_ex(regs->cs, (unsigned int __user *)&sc->cs); diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 3e274564f6b..e3e734005e1 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -14,6 +14,7 @@ #include <asm/segment.h> #include <asm/irqflags.h> #include <linux/linkage.h> +#include <linux/err.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ #include <linux/elf-em.h> @@ -27,8 +28,6 @@ .section .entry.text, "ax" -#define IA32_NR_syscalls ((ia32_syscall_end - ia32_sys_call_table)/8) - .macro IA32_ARG_FIXUP noebp=0 movl %edi,%r8d .if \noebp @@ -191,7 +190,7 @@ sysexit_from_sys_call: movl %ebx,%edx /* 3rd arg: 1st syscall arg */ movl %eax,%esi /* 2nd arg: syscall number */ movl $AUDIT_ARCH_I386,%edi /* 1st arg: audit arch */ - call audit_syscall_entry + call __audit_syscall_entry movl RAX-ARGOFFSET(%rsp),%eax /* reload syscall number */ cmpq $(IA32_NR_syscalls-1),%rax ja ia32_badsys @@ -208,12 +207,13 @@ sysexit_from_sys_call: TRACE_IRQS_ON sti movl %eax,%esi /* second arg, syscall return value */ - cmpl $0,%eax /* is it < 0? */ - setl %al /* 1 if so, 0 if not */ + 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 */ - inc %edi /* first arg, 0->1(AUDITSC_SUCCESS), 1->2(AUDITSC_FAILURE) */ - call audit_syscall_exit - movl RAX-ARGOFFSET(%rsp),%eax /* reload syscall return value */ + call __audit_syscall_exit + movq RAX-ARGOFFSET(%rsp),%rax /* reload syscall return value */ movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi cli TRACE_IRQS_OFF @@ -447,9 +447,6 @@ ia32_badsys: movq $-ENOSYS,%rax jmp ia32_sysret -quiet_ni_syscall: - movq $-ENOSYS,%rax - ret CFI_ENDPROC .macro PTREGSCALL label, func, arg @@ -494,357 +491,3 @@ ia32_ptregs_common: jmp ia32_sysret /* misbalances the return cache */ CFI_ENDPROC END(ia32_ptregs_common) - - .section .rodata,"a" - .align 8 -ia32_sys_call_table: - .quad sys_restart_syscall - .quad sys_exit - .quad stub32_fork - .quad sys_read - .quad sys_write - .quad compat_sys_open /* 5 */ - .quad sys_close - .quad sys32_waitpid - .quad sys_creat - .quad sys_link - .quad sys_unlink /* 10 */ - .quad stub32_execve - .quad sys_chdir - .quad compat_sys_time - .quad sys_mknod - .quad sys_chmod /* 15 */ - .quad sys_lchown16 - .quad quiet_ni_syscall /* old break syscall holder */ - .quad sys_stat - .quad sys32_lseek - .quad sys_getpid /* 20 */ - .quad compat_sys_mount /* mount */ - .quad sys_oldumount /* old_umount */ - .quad sys_setuid16 - .quad sys_getuid16 - .quad compat_sys_stime /* stime */ /* 25 */ - .quad compat_sys_ptrace /* ptrace */ - .quad sys_alarm - .quad sys_fstat /* (old)fstat */ - .quad sys_pause - .quad compat_sys_utime /* 30 */ - .quad quiet_ni_syscall /* old stty syscall holder */ - .quad quiet_ni_syscall /* old gtty syscall holder */ - .quad sys_access - .quad sys_nice - .quad quiet_ni_syscall /* 35 */ /* old ftime syscall holder */ - .quad sys_sync - .quad sys32_kill - .quad sys_rename - .quad sys_mkdir - .quad sys_rmdir /* 40 */ - .quad sys_dup - .quad sys_pipe - .quad compat_sys_times - .quad quiet_ni_syscall /* old prof syscall holder */ - .quad sys_brk /* 45 */ - .quad sys_setgid16 - .quad sys_getgid16 - .quad sys_signal - .quad sys_geteuid16 - .quad sys_getegid16 /* 50 */ - .quad sys_acct - .quad sys_umount /* new_umount */ - .quad quiet_ni_syscall /* old lock syscall holder */ - .quad compat_sys_ioctl - .quad compat_sys_fcntl64 /* 55 */ - .quad quiet_ni_syscall /* old mpx syscall holder */ - .quad sys_setpgid - .quad quiet_ni_syscall /* old ulimit syscall holder */ - .quad sys_olduname - .quad sys_umask /* 60 */ - .quad sys_chroot - .quad compat_sys_ustat - .quad sys_dup2 - .quad sys_getppid - .quad sys_getpgrp /* 65 */ - .quad sys_setsid - .quad sys32_sigaction - .quad sys_sgetmask - .quad sys_ssetmask - .quad sys_setreuid16 /* 70 */ - .quad sys_setregid16 - .quad sys32_sigsuspend - .quad compat_sys_sigpending - .quad sys_sethostname - .quad compat_sys_setrlimit /* 75 */ - .quad compat_sys_old_getrlimit /* old_getrlimit */ - .quad compat_sys_getrusage - .quad compat_sys_gettimeofday - .quad compat_sys_settimeofday - .quad sys_getgroups16 /* 80 */ - .quad sys_setgroups16 - .quad compat_sys_old_select - .quad sys_symlink - .quad sys_lstat - .quad sys_readlink /* 85 */ - .quad sys_uselib - .quad sys_swapon - .quad sys_reboot - .quad compat_sys_old_readdir - .quad sys32_mmap /* 90 */ - .quad sys_munmap - .quad sys_truncate - .quad sys_ftruncate - .quad sys_fchmod - .quad sys_fchown16 /* 95 */ - .quad sys_getpriority - .quad sys_setpriority - .quad quiet_ni_syscall /* old profil syscall holder */ - .quad compat_sys_statfs - .quad compat_sys_fstatfs /* 100 */ - .quad sys_ioperm - .quad compat_sys_socketcall - .quad sys_syslog - .quad compat_sys_setitimer - .quad compat_sys_getitimer /* 105 */ - .quad compat_sys_newstat - .quad compat_sys_newlstat - .quad compat_sys_newfstat - .quad sys_uname - .quad stub32_iopl /* 110 */ - .quad sys_vhangup - .quad quiet_ni_syscall /* old "idle" system call */ - .quad sys32_vm86_warning /* vm86old */ - .quad compat_sys_wait4 - .quad sys_swapoff /* 115 */ - .quad compat_sys_sysinfo - .quad sys32_ipc - .quad sys_fsync - .quad stub32_sigreturn - .quad stub32_clone /* 120 */ - .quad sys_setdomainname - .quad sys_newuname - .quad sys_modify_ldt - .quad compat_sys_adjtimex - .quad sys32_mprotect /* 125 */ - .quad compat_sys_sigprocmask - .quad quiet_ni_syscall /* create_module */ - .quad sys_init_module - .quad sys_delete_module - .quad quiet_ni_syscall /* 130 get_kernel_syms */ - .quad sys32_quotactl - .quad sys_getpgid - .quad sys_fchdir - .quad quiet_ni_syscall /* bdflush */ - .quad sys_sysfs /* 135 */ - .quad sys_personality - .quad quiet_ni_syscall /* for afs_syscall */ - .quad sys_setfsuid16 - .quad sys_setfsgid16 - .quad sys_llseek /* 140 */ - .quad compat_sys_getdents - .quad compat_sys_select - .quad sys_flock - .quad sys_msync - .quad compat_sys_readv /* 145 */ - .quad compat_sys_writev - .quad sys_getsid - .quad sys_fdatasync - .quad compat_sys_sysctl /* sysctl */ - .quad sys_mlock /* 150 */ - .quad sys_munlock - .quad sys_mlockall - .quad sys_munlockall - .quad sys_sched_setparam - .quad sys_sched_getparam /* 155 */ - .quad sys_sched_setscheduler - .quad sys_sched_getscheduler - .quad sys_sched_yield - .quad sys_sched_get_priority_max - .quad sys_sched_get_priority_min /* 160 */ - .quad sys32_sched_rr_get_interval - .quad compat_sys_nanosleep - .quad sys_mremap - .quad sys_setresuid16 - .quad sys_getresuid16 /* 165 */ - .quad sys32_vm86_warning /* vm86 */ - .quad quiet_ni_syscall /* query_module */ - .quad sys_poll - .quad quiet_ni_syscall /* old nfsservctl */ - .quad sys_setresgid16 /* 170 */ - .quad sys_getresgid16 - .quad sys_prctl - .quad stub32_rt_sigreturn - .quad sys32_rt_sigaction - .quad sys32_rt_sigprocmask /* 175 */ - .quad sys32_rt_sigpending - .quad compat_sys_rt_sigtimedwait - .quad sys32_rt_sigqueueinfo - .quad sys_rt_sigsuspend - .quad sys32_pread /* 180 */ - .quad sys32_pwrite - .quad sys_chown16 - .quad sys_getcwd - .quad sys_capget - .quad sys_capset - .quad stub32_sigaltstack - .quad sys32_sendfile - .quad quiet_ni_syscall /* streams1 */ - .quad quiet_ni_syscall /* streams2 */ - .quad stub32_vfork /* 190 */ - .quad compat_sys_getrlimit - .quad sys_mmap_pgoff - .quad sys32_truncate64 - .quad sys32_ftruncate64 - .quad sys32_stat64 /* 195 */ - .quad sys32_lstat64 - .quad sys32_fstat64 - .quad sys_lchown - .quad sys_getuid - .quad sys_getgid /* 200 */ - .quad sys_geteuid - .quad sys_getegid - .quad sys_setreuid - .quad sys_setregid - .quad sys_getgroups /* 205 */ - .quad sys_setgroups - .quad sys_fchown - .quad sys_setresuid - .quad sys_getresuid - .quad sys_setresgid /* 210 */ - .quad sys_getresgid - .quad sys_chown - .quad sys_setuid - .quad sys_setgid - .quad sys_setfsuid /* 215 */ - .quad sys_setfsgid - .quad sys_pivot_root - .quad sys_mincore - .quad sys_madvise - .quad compat_sys_getdents64 /* 220 getdents64 */ - .quad compat_sys_fcntl64 - .quad quiet_ni_syscall /* tux */ - .quad quiet_ni_syscall /* security */ - .quad sys_gettid - .quad sys32_readahead /* 225 */ - .quad sys_setxattr - .quad sys_lsetxattr - .quad sys_fsetxattr - .quad sys_getxattr - .quad sys_lgetxattr /* 230 */ - .quad sys_fgetxattr - .quad sys_listxattr - .quad sys_llistxattr - .quad sys_flistxattr - .quad sys_removexattr /* 235 */ - .quad sys_lremovexattr - .quad sys_fremovexattr - .quad sys_tkill - .quad sys_sendfile64 - .quad compat_sys_futex /* 240 */ - .quad compat_sys_sched_setaffinity - .quad compat_sys_sched_getaffinity - .quad sys_set_thread_area - .quad sys_get_thread_area - .quad compat_sys_io_setup /* 245 */ - .quad sys_io_destroy - .quad compat_sys_io_getevents - .quad compat_sys_io_submit - .quad sys_io_cancel - .quad sys32_fadvise64 /* 250 */ - .quad quiet_ni_syscall /* free_huge_pages */ - .quad sys_exit_group - .quad sys32_lookup_dcookie - .quad sys_epoll_create - .quad sys_epoll_ctl /* 255 */ - .quad sys_epoll_wait - .quad sys_remap_file_pages - .quad sys_set_tid_address - .quad compat_sys_timer_create - .quad compat_sys_timer_settime /* 260 */ - .quad compat_sys_timer_gettime - .quad sys_timer_getoverrun - .quad sys_timer_delete - .quad compat_sys_clock_settime - .quad compat_sys_clock_gettime /* 265 */ - .quad compat_sys_clock_getres - .quad compat_sys_clock_nanosleep - .quad compat_sys_statfs64 - .quad compat_sys_fstatfs64 - .quad sys_tgkill /* 270 */ - .quad compat_sys_utimes - .quad sys32_fadvise64_64 - .quad quiet_ni_syscall /* sys_vserver */ - .quad sys_mbind - .quad compat_sys_get_mempolicy /* 275 */ - .quad sys_set_mempolicy - .quad compat_sys_mq_open - .quad sys_mq_unlink - .quad compat_sys_mq_timedsend - .quad compat_sys_mq_timedreceive /* 280 */ - .quad compat_sys_mq_notify - .quad compat_sys_mq_getsetattr - .quad compat_sys_kexec_load /* reserved for kexec */ - .quad compat_sys_waitid - .quad quiet_ni_syscall /* 285: sys_altroot */ - .quad sys_add_key - .quad sys_request_key - .quad sys_keyctl - .quad sys_ioprio_set - .quad sys_ioprio_get /* 290 */ - .quad sys_inotify_init - .quad sys_inotify_add_watch - .quad sys_inotify_rm_watch - .quad sys_migrate_pages - .quad compat_sys_openat /* 295 */ - .quad sys_mkdirat - .quad sys_mknodat - .quad sys_fchownat - .quad compat_sys_futimesat - .quad sys32_fstatat /* 300 */ - .quad sys_unlinkat - .quad sys_renameat - .quad sys_linkat - .quad sys_symlinkat - .quad sys_readlinkat /* 305 */ - .quad sys_fchmodat - .quad sys_faccessat - .quad compat_sys_pselect6 - .quad compat_sys_ppoll - .quad sys_unshare /* 310 */ - .quad compat_sys_set_robust_list - .quad compat_sys_get_robust_list - .quad sys_splice - .quad sys32_sync_file_range - .quad sys_tee /* 315 */ - .quad compat_sys_vmsplice - .quad compat_sys_move_pages - .quad sys_getcpu - .quad sys_epoll_pwait - .quad compat_sys_utimensat /* 320 */ - .quad compat_sys_signalfd - .quad sys_timerfd_create - .quad sys_eventfd - .quad sys32_fallocate - .quad compat_sys_timerfd_settime /* 325 */ - .quad compat_sys_timerfd_gettime - .quad compat_sys_signalfd4 - .quad sys_eventfd2 - .quad sys_epoll_create1 - .quad sys_dup3 /* 330 */ - .quad sys_pipe2 - .quad sys_inotify_init1 - .quad compat_sys_preadv - .quad compat_sys_pwritev - .quad compat_sys_rt_tgsigqueueinfo /* 335 */ - .quad sys_perf_event_open - .quad compat_sys_recvmmsg - .quad sys_fanotify_init - .quad sys32_fanotify_mark - .quad sys_prlimit64 /* 340 */ - .quad sys_name_to_handle_at - .quad compat_sys_open_by_handle_at - .quad compat_sys_clock_adjtime - .quad sys_syncfs - .quad compat_sys_sendmmsg /* 345 */ - .quad sys_setns - .quad compat_sys_process_vm_readv - .quad compat_sys_process_vm_writev -ia32_syscall_end: diff --git a/arch/x86/ia32/nosyscall.c b/arch/x86/ia32/nosyscall.c new file mode 100644 index 00000000000..51ecd5b4e78 --- /dev/null +++ b/arch/x86/ia32/nosyscall.c @@ -0,0 +1,7 @@ +#include <linux/kernel.h> +#include <linux/errno.h> + +long compat_ni_syscall(void) +{ + return -ENOSYS; +} diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index f6f5c53dc90..aec2202a596 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -287,46 +287,6 @@ asmlinkage long sys32_sigaction(int sig, struct old_sigaction32 __user *act, return ret; } -asmlinkage long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set, - compat_sigset_t __user *oset, - unsigned int sigsetsize) -{ - sigset_t s; - compat_sigset_t s32; - int ret; - mm_segment_t old_fs = get_fs(); - - if (set) { - if (copy_from_user(&s32, set, sizeof(compat_sigset_t))) - return -EFAULT; - switch (_NSIG_WORDS) { - case 4: s.sig[3] = s32.sig[6] | (((long)s32.sig[7]) << 32); - case 3: s.sig[2] = s32.sig[4] | (((long)s32.sig[5]) << 32); - case 2: s.sig[1] = s32.sig[2] | (((long)s32.sig[3]) << 32); - case 1: s.sig[0] = s32.sig[0] | (((long)s32.sig[1]) << 32); - } - } - set_fs(KERNEL_DS); - ret = sys_rt_sigprocmask(how, - set ? (sigset_t __user *)&s : NULL, - oset ? (sigset_t __user *)&s : NULL, - sigsetsize); - set_fs(old_fs); - if (ret) - return ret; - if (oset) { - switch (_NSIG_WORDS) { - case 4: s32.sig[7] = (s.sig[3] >> 32); s32.sig[6] = s.sig[3]; - case 3: s32.sig[5] = (s.sig[2] >> 32); s32.sig[4] = s.sig[2]; - case 2: s32.sig[3] = (s.sig[1] >> 32); s32.sig[2] = s.sig[1]; - case 1: s32.sig[1] = (s.sig[0] >> 32); s32.sig[0] = s.sig[0]; - } - if (copy_to_user(oset, &s32, sizeof(compat_sigset_t))) - return -EFAULT; - } - return 0; -} - asmlinkage long sys32_alarm(unsigned int seconds) { return alarm_setitimer(seconds); diff --git a/arch/x86/ia32/syscall_ia32.c b/arch/x86/ia32/syscall_ia32.c new file mode 100644 index 00000000000..4754ba0f5d9 --- /dev/null +++ b/arch/x86/ia32/syscall_ia32.c @@ -0,0 +1,25 @@ +/* System call table for ia32 emulation. */ + +#include <linux/linkage.h> +#include <linux/sys.h> +#include <linux/cache.h> +#include <asm/asm-offsets.h> + +#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void compat(void) ; +#include <asm/syscalls_32.h> +#undef __SYSCALL_I386 + +#define __SYSCALL_I386(nr, sym, compat) [nr] = compat, + +typedef void (*sys_call_ptr_t)(void); + +extern void compat_ni_syscall(void); + +const sys_call_ptr_t ia32_sys_call_table[__NR_ia32_syscall_max+1] = { + /* + * Smells like a compiler bug -- it doesn't work + * when the & below is removed. + */ + [0 ... __NR_ia32_syscall_max] = &compat_ni_syscall, +#include <asm/syscalls_32.h> +}; diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index 6fa90a845e4..f9c0d3ba9e8 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -14,12 +14,15 @@ header-y += msr.h header-y += mtrr.h header-y += posix_types_32.h header-y += posix_types_64.h +header-y += posix_types_x32.h header-y += prctl.h header-y += processor-flags.h header-y += ptrace-abi.h header-y += sigcontext32.h header-y += ucontext.h -header-y += unistd_32.h -header-y += unistd_64.h header-y += vm86.h header-y += vsyscall.h + +genhdr-y += unistd_32.h +genhdr-y += unistd_64.h +genhdr-y += unistd_x32.h diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 37ad100a221..49331bedc15 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -145,6 +145,12 @@ static inline int alternatives_text_reserved(void *start, void *end) */ #define ASM_OUTPUT2(a...) a +/* + * use this macro if you need clobbers but no inputs in + * alternative_{input,io,call}() + */ +#define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr + struct paravirt_patch_site; #ifdef CONFIG_PARAVIRT void apply_paravirt(struct paravirt_patch_site *start, diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 3ab9bdd87e7..d8541017126 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -11,7 +11,6 @@ #include <linux/atomic.h> #include <asm/fixmap.h> #include <asm/mpspec.h> -#include <asm/system.h> #include <asm/msr.h> #define ARCH_APICTIMER_STOPS_ON_C3 1 @@ -288,6 +287,7 @@ struct apic { int (*probe)(void); int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id); + int (*apic_id_valid)(int apicid); int (*apic_id_registered)(void); u32 irq_delivery_mode; @@ -532,6 +532,11 @@ static inline unsigned int read_apic_id(void) return apic->get_apic_id(reg); } +static inline int default_apic_id_valid(int apicid) +{ + return (apicid < 255); +} + extern void default_setup_apic_routing(void); extern struct apic apic_noop; diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index 24098aafce0..198119910da 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -14,13 +14,52 @@ typedef struct { #define ATOMIC64_INIT(val) { (val) } +#define __ATOMIC64_DECL(sym) void atomic64_##sym(atomic64_t *, ...) +#ifndef ATOMIC64_EXPORT +#define ATOMIC64_DECL_ONE __ATOMIC64_DECL +#else +#define ATOMIC64_DECL_ONE(sym) __ATOMIC64_DECL(sym); \ + ATOMIC64_EXPORT(atomic64_##sym) +#endif + #ifdef CONFIG_X86_CMPXCHG64 -#define ATOMIC64_ALTERNATIVE_(f, g) "call atomic64_" #g "_cx8" +#define __alternative_atomic64(f, g, out, in...) \ + asm volatile("call %P[func]" \ + : out : [func] "i" (atomic64_##g##_cx8), ## in) + +#define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8) #else -#define ATOMIC64_ALTERNATIVE_(f, g) ALTERNATIVE("call atomic64_" #f "_386", "call atomic64_" #g "_cx8", X86_FEATURE_CX8) +#define __alternative_atomic64(f, g, out, in...) \ + alternative_call(atomic64_##f##_386, atomic64_##g##_cx8, \ + X86_FEATURE_CX8, ASM_OUTPUT2(out), ## in) + +#define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8); \ + ATOMIC64_DECL_ONE(sym##_386) + +ATOMIC64_DECL_ONE(add_386); +ATOMIC64_DECL_ONE(sub_386); +ATOMIC64_DECL_ONE(inc_386); +ATOMIC64_DECL_ONE(dec_386); #endif -#define ATOMIC64_ALTERNATIVE(f) ATOMIC64_ALTERNATIVE_(f, f) +#define alternative_atomic64(f, out, in...) \ + __alternative_atomic64(f, f, ASM_OUTPUT2(out), ## in) + +ATOMIC64_DECL(read); +ATOMIC64_DECL(set); +ATOMIC64_DECL(xchg); +ATOMIC64_DECL(add_return); +ATOMIC64_DECL(sub_return); +ATOMIC64_DECL(inc_return); +ATOMIC64_DECL(dec_return); +ATOMIC64_DECL(dec_if_positive); +ATOMIC64_DECL(inc_not_zero); +ATOMIC64_DECL(add_unless); + +#undef ATOMIC64_DECL +#undef ATOMIC64_DECL_ONE +#undef __ATOMIC64_DECL +#undef ATOMIC64_EXPORT /** * atomic64_cmpxchg - cmpxchg atomic64 variable @@ -50,11 +89,9 @@ static inline long long atomic64_xchg(atomic64_t *v, long long n) long long o; unsigned high = (unsigned)(n >> 32); unsigned low = (unsigned)n; - asm volatile(ATOMIC64_ALTERNATIVE(xchg) - : "=A" (o), "+b" (low), "+c" (high) - : "S" (v) - : "memory" - ); + alternative_atomic64(xchg, "=&A" (o), + "S" (v), "b" (low), "c" (high) + : "memory"); return o; } @@ -69,11 +106,9 @@ static inline void atomic64_set(atomic64_t *v, long long i) { unsigned high = (unsigned)(i >> 32); unsigned low = (unsigned)i; - asm volatile(ATOMIC64_ALTERNATIVE(set) - : "+b" (low), "+c" (high) - : "S" (v) - : "eax", "edx", "memory" - ); + alternative_atomic64(set, /* no output */, + "S" (v), "b" (low), "c" (high) + : "eax", "edx", "memory"); } /** @@ -82,13 +117,10 @@ static inline void atomic64_set(atomic64_t *v, long long i) * * Atomically reads the value of @v and returns it. */ -static inline long long atomic64_read(atomic64_t *v) +static inline long long atomic64_read(const atomic64_t *v) { long long r; - asm volatile(ATOMIC64_ALTERNATIVE(read) - : "=A" (r), "+c" (v) - : : "memory" - ); + alternative_atomic64(read, "=&A" (r), "c" (v) : "memory"); return r; } @@ -101,10 +133,9 @@ static inline long long atomic64_read(atomic64_t *v) */ static inline long long atomic64_add_return(long long i, atomic64_t *v) { - asm volatile(ATOMIC64_ALTERNATIVE(add_return) - : "+A" (i), "+c" (v) - : : "memory" - ); + alternative_atomic64(add_return, + ASM_OUTPUT2("+A" (i), "+c" (v)), + ASM_NO_INPUT_CLOBBER("memory")); return i; } @@ -113,32 +144,25 @@ static inline long long atomic64_add_return(long long i, atomic64_t *v) */ static inline long long atomic64_sub_return(long long i, atomic64_t *v) { - asm volatile(ATOMIC64_ALTERNATIVE(sub_return) - : "+A" (i), "+c" (v) - : : "memory" - ); + alternative_atomic64(sub_return, + ASM_OUTPUT2("+A" (i), "+c" (v)), + ASM_NO_INPUT_CLOBBER("memory")); return i; } static inline long long atomic64_inc_return(atomic64_t *v) { long long a; - asm volatile(ATOMIC64_ALTERNATIVE(inc_return) - : "=A" (a) - : "S" (v) - : "memory", "ecx" - ); + alternative_atomic64(inc_return, "=&A" (a), + "S" (v) : "memory", "ecx"); return a; } static inline long long atomic64_dec_return(atomic64_t *v) { long long a; - asm volatile(ATOMIC64_ALTERNATIVE(dec_return) - : "=A" (a) - : "S" (v) - : "memory", "ecx" - ); + alternative_atomic64(dec_return, "=&A" (a), + "S" (v) : "memory", "ecx"); return a; } @@ -151,10 +175,9 @@ static inline long long atomic64_dec_return(atomic64_t *v) */ static inline long long atomic64_add(long long i, atomic64_t *v) { - asm volatile(ATOMIC64_ALTERNATIVE_(add, add_return) - : "+A" (i), "+c" (v) - : : "memory" - ); + __alternative_atomic64(add, add_return, + ASM_OUTPUT2("+A" (i), "+c" (v)), + ASM_NO_INPUT_CLOBBER("memory")); return i; } @@ -167,10 +190,9 @@ static inline long long atomic64_add(long long i, atomic64_t *v) */ static inline long long atomic64_sub(long long i, atomic64_t *v) { - asm volatile(ATOMIC64_ALTERNATIVE_(sub, sub_return) - : "+A" (i), "+c" (v) - : : "memory" - ); + __alternative_atomic64(sub, sub_return, + ASM_OUTPUT2("+A" (i), "+c" (v)), + ASM_NO_INPUT_CLOBBER("memory")); return i; } @@ -196,10 +218,8 @@ static inline int atomic64_sub_and_test(long long i, atomic64_t *v) */ static inline void atomic64_inc(atomic64_t *v) { - asm volatile(ATOMIC64_ALTERNATIVE_(inc, inc_return) - : : "S" (v) - : "memory", "eax", "ecx", "edx" - ); + __alternative_atomic64(inc, inc_return, /* no output */, + "S" (v) : "memory", "eax", "ecx", "edx"); } /** @@ -210,10 +230,8 @@ static inline void atomic64_inc(atomic64_t *v) */ static inline void atomic64_dec(atomic64_t *v) { - asm volatile(ATOMIC64_ALTERNATIVE_(dec, dec_return) - : : "S" (v) - : "memory", "eax", "ecx", "edx" - ); + __alternative_atomic64(dec, dec_return, /* no output */, + "S" (v) : "memory", "eax", "ecx", "edx"); } /** @@ -263,15 +281,15 @@ static inline int atomic64_add_negative(long long i, atomic64_t *v) * @u: ...unless v is equal to u. * * Atomically adds @a to @v, so long as it was not @u. - * Returns the old value of @v. + * Returns non-zero if the add was done, zero otherwise. */ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u) { unsigned low = (unsigned)u; unsigned high = (unsigned)(u >> 32); - asm volatile(ATOMIC64_ALTERNATIVE(add_unless) "\n\t" - : "+A" (a), "+c" (v), "+S" (low), "+D" (high) - : : "memory"); + alternative_atomic64(add_unless, + ASM_OUTPUT2("+A" (a), "+c" (low), "+D" (high)), + "S" (v) : "memory"); return (int)a; } @@ -279,26 +297,20 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u) static inline int atomic64_inc_not_zero(atomic64_t *v) { int r; - asm volatile(ATOMIC64_ALTERNATIVE(inc_not_zero) - : "=a" (r) - : "S" (v) - : "ecx", "edx", "memory" - ); + alternative_atomic64(inc_not_zero, "=&a" (r), + "S" (v) : "ecx", "edx", "memory"); return r; } static inline long long atomic64_dec_if_positive(atomic64_t *v) { long long r; - asm volatile(ATOMIC64_ALTERNATIVE(dec_if_positive) - : "=A" (r) - : "S" (v) - : "ecx", "memory" - ); + alternative_atomic64(dec_if_positive, "=&A" (r), + "S" (v) : "ecx", "memory"); return r; } -#undef ATOMIC64_ALTERNATIVE -#undef ATOMIC64_ALTERNATIVE_ +#undef alternative_atomic64 +#undef __alternative_atomic64 #endif /* _ASM_X86_ATOMIC64_32_H */ diff --git a/arch/x86/include/asm/auxvec.h b/arch/x86/include/asm/auxvec.h index 1316b4c3542..77203ac352d 100644 --- a/arch/x86/include/asm/auxvec.h +++ b/arch/x86/include/asm/auxvec.h @@ -9,4 +9,11 @@ #endif #define AT_SYSINFO_EHDR 33 +/* entries in ARCH_DLINFO: */ +#if defined(CONFIG_IA32_EMULATION) || !defined(CONFIG_X86_64) +# define AT_VECTOR_SIZE_ARCH 2 +#else /* else it's non-compat x86-64 */ +# define AT_VECTOR_SIZE_ARCH 1 +#endif + #endif /* _ASM_X86_AUXVEC_H */ diff --git a/arch/x86/um/asm/system.h b/arch/x86/include/asm/barrier.h index a459fd9b759..c6cd358a1ee 100644 --- a/arch/x86/um/asm/system.h +++ b/arch/x86/include/asm/barrier.h @@ -1,31 +1,15 @@ -#ifndef _ASM_X86_SYSTEM_H_ -#define _ASM_X86_SYSTEM_H_ +#ifndef _ASM_X86_BARRIER_H +#define _ASM_X86_BARRIER_H -#include <asm/asm.h> -#include <asm/segment.h> -#include <asm/cpufeature.h> -#include <asm/cmpxchg.h> +#include <asm/alternative.h> #include <asm/nops.h> -#include <linux/kernel.h> -#include <linux/irqflags.h> - -/* entries in ARCH_DLINFO: */ -#ifdef CONFIG_IA32_EMULATION -# define AT_VECTOR_SIZE_ARCH 2 -#else -# define AT_VECTOR_SIZE_ARCH 1 -#endif - -extern unsigned long arch_align_stack(unsigned long sp); - -void default_idle(void); - /* * Force strict CPU ordering. * And yes, this is required on UP too when we're talking * to devices. */ + #ifdef CONFIG_X86_32 /* * Some non-Intel clones support out of order store. wmb() ceases to be a @@ -123,13 +107,10 @@ void default_idle(void); * * (Could use an alternative three way for this if there was one.) */ -static inline void rdtsc_barrier(void) +static __always_inline void rdtsc_barrier(void) { alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC); alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC); } -extern void *_switch_to(void *prev, void *next, void *last); -#define switch_to(prev, next, last) prev = _switch_to(prev, next, last) - -#endif +#endif /* _ASM_X86_BARRIER_H */ diff --git a/arch/x86/include/asm/bootparam.h b/arch/x86/include/asm/bootparam.h index e020d88ec02..2f90c51cc49 100644 --- a/arch/x86/include/asm/bootparam.h +++ b/arch/x86/include/asm/bootparam.h @@ -64,6 +64,8 @@ struct setup_header { __u32 payload_offset; __u32 payload_length; __u64 setup_data; + __u64 pref_address; + __u32 init_size; } __attribute__((packed)); struct sys_desc_table { diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index f654d1bb17f..11e1152222d 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -36,4 +36,8 @@ do { \ #endif /* !CONFIG_BUG */ #include <asm-generic/bug.h> + + +extern void show_regs_common(void); + #endif /* _ASM_X86_BUG_H */ diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h index 4e12668711e..9863ee3747d 100644 --- a/arch/x86/include/asm/cacheflush.h +++ b/arch/x86/include/asm/cacheflush.h @@ -3,6 +3,7 @@ /* Caches aren't brain-dead on the intel. */ #include <asm-generic/cacheflush.h> +#include <asm/special_insns.h> #ifdef CONFIG_X86_PAT /* diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index 0c9fa2745f1..99480e55973 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -43,7 +43,7 @@ extern void __add_wrong_size(void) switch (sizeof(*(ptr))) { \ case __X86_CASE_B: \ asm volatile (lock #op "b %b0, %1\n" \ - : "+r" (__ret), "+m" (*(ptr)) \ + : "+q" (__ret), "+m" (*(ptr)) \ : : "memory", "cc"); \ break; \ case __X86_CASE_W: \ @@ -145,13 +145,13 @@ extern void __add_wrong_size(void) #ifdef __HAVE_ARCH_CMPXCHG #define cmpxchg(ptr, old, new) \ - __cmpxchg((ptr), (old), (new), sizeof(*ptr)) + __cmpxchg(ptr, old, new, sizeof(*(ptr))) #define sync_cmpxchg(ptr, old, new) \ - __sync_cmpxchg((ptr), (old), (new), sizeof(*ptr)) + __sync_cmpxchg(ptr, old, new, sizeof(*(ptr))) #define cmpxchg_local(ptr, old, new) \ - __cmpxchg_local((ptr), (old), (new), sizeof(*ptr)) + __cmpxchg_local(ptr, old, new, sizeof(*(ptr))) #endif /* @@ -173,7 +173,7 @@ extern void __add_wrong_size(void) switch (sizeof(*(ptr))) { \ case __X86_CASE_B: \ asm volatile (lock "addb %b1, %0\n" \ - : "+m" (*(ptr)) : "ri" (inc) \ + : "+m" (*(ptr)) : "qi" (inc) \ : "memory", "cc"); \ break; \ case __X86_CASE_W: \ diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index 30d737ef2a4..d6805798d6f 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -6,7 +6,9 @@ */ #include <linux/types.h> #include <linux/sched.h> +#include <asm/processor.h> #include <asm/user32.h> +#include <asm/unistd.h> #define COMPAT_USER_HZ 100 #define COMPAT_UTS_MACHINE "i686\0\0" @@ -186,7 +188,20 @@ struct compat_shmid64_ds { /* * The type of struct elf_prstatus.pr_reg in compatible core dumps. */ +#ifdef CONFIG_X86_X32_ABI +typedef struct user_regs_struct compat_elf_gregset_t; + +#define PR_REG_SIZE(S) (test_thread_flag(TIF_IA32) ? 68 : 216) +#define PRSTATUS_SIZE(S) (test_thread_flag(TIF_IA32) ? 144 : 296) +#define SET_PR_FPVALID(S,V) \ + do { *(int *) (((void *) &((S)->pr_reg)) + PR_REG_SIZE(0)) = (V); } \ + while (0) + +#define COMPAT_USE_64BIT_TIME \ + (!!(task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT)) +#else typedef struct user_regs_struct32 compat_elf_gregset_t; +#endif /* * A pointer passed in from user mode. This should not @@ -208,13 +223,30 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) static inline void __user *arch_compat_alloc_user_space(long len) { - struct pt_regs *regs = task_pt_regs(current); - return (void __user *)regs->sp - len; + compat_uptr_t sp; + + if (test_thread_flag(TIF_IA32)) { + sp = task_pt_regs(current)->sp; + } else { + /* -128 for the x32 ABI redzone */ + sp = percpu_read(old_rsp) - 128; + } + + return (void __user *)round_down(sp - len, 16); +} + +static inline bool is_x32_task(void) +{ +#ifdef CONFIG_X86_X32_ABI + if (task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT) + return true; +#endif + return false; } -static inline int is_compat_task(void) +static inline bool is_compat_task(void) { - return current_thread_info()->status & TS_COMPAT; + return is_ia32_task() || is_x32_task(); } #endif /* _ASM_X86_COMPAT_H */ diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h new file mode 100644 index 00000000000..ff501e511d9 --- /dev/null +++ b/arch/x86/include/asm/cpu_device_id.h @@ -0,0 +1,13 @@ +#ifndef _CPU_DEVICE_ID +#define _CPU_DEVICE_ID 1 + +/* + * Declare drivers belonging to specific x86 CPUs + * Similar in spirit to pci_device_id and related PCI functions + */ + +#include <linux/mod_devicetable.h> + +extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match); + +#endif diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 17c5d4bdee5..340ee49961a 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -159,6 +159,7 @@ #define X86_FEATURE_WDT (6*32+13) /* Watchdog timer */ #define X86_FEATURE_LWP (6*32+15) /* Light Weight Profiling */ #define X86_FEATURE_FMA4 (6*32+16) /* 4 operands MAC instructions */ +#define X86_FEATURE_TCE (6*32+17) /* translation cache extension */ #define X86_FEATURE_NODEID_MSR (6*32+19) /* NodeId MSR */ #define X86_FEATURE_TBM (6*32+21) /* trailing bit manipulations */ #define X86_FEATURE_TOPOEXT (6*32+22) /* topology extensions CPUID leafs */ @@ -176,6 +177,7 @@ #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_DTS (7*32+ 7) /* Digital Thermal Sensor */ +#define X86_FEATURE_HW_PSTATE (7*32+ 8) /* AMD HW-PState */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW (8*32+ 0) /* Intel TPR Shadow */ @@ -198,10 +200,13 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ #define X86_FEATURE_FSGSBASE (9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/ #define X86_FEATURE_BMI1 (9*32+ 3) /* 1st group bit manipulation extensions */ +#define X86_FEATURE_HLE (9*32+ 4) /* Hardware Lock Elision */ #define X86_FEATURE_AVX2 (9*32+ 5) /* AVX2 instructions */ #define X86_FEATURE_SMEP (9*32+ 7) /* Supervisor Mode Execution Protection */ #define X86_FEATURE_BMI2 (9*32+ 8) /* 2nd group bit manipulation extensions */ #define X86_FEATURE_ERMS (9*32+ 9) /* Enhanced REP MOVSB/STOSB */ +#define X86_FEATURE_INVPCID (9*32+10) /* Invalidate Processor Context ID */ +#define X86_FEATURE_RTM (9*32+11) /* Restricted Transactional Memory */ #if defined(__KERNEL__) && !defined(__ASSEMBLY__) diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index 078ad0caefc..2d91580bf22 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -78,8 +78,75 @@ */ #ifdef __KERNEL__ +#include <linux/bug.h> + DECLARE_PER_CPU(unsigned long, cpu_dr7); +#ifndef CONFIG_PARAVIRT +/* + * These special macros can be used to get or set a debugging register + */ +#define get_debugreg(var, register) \ + (var) = native_get_debugreg(register) +#define set_debugreg(value, register) \ + native_set_debugreg(register, value) +#endif + +static inline unsigned long native_get_debugreg(int regno) +{ + unsigned long val = 0; /* Damn you, gcc! */ + + switch (regno) { + case 0: + asm("mov %%db0, %0" :"=r" (val)); + break; + case 1: + asm("mov %%db1, %0" :"=r" (val)); + break; + case 2: + asm("mov %%db2, %0" :"=r" (val)); + break; + case 3: + asm("mov %%db3, %0" :"=r" (val)); + break; + case 6: + asm("mov %%db6, %0" :"=r" (val)); + break; + case 7: + asm("mov %%db7, %0" :"=r" (val)); + break; + default: + BUG(); + } + return val; +} + +static inline void native_set_debugreg(int regno, unsigned long value) +{ + switch (regno) { + case 0: + asm("mov %0, %%db0" ::"r" (value)); + break; + case 1: + asm("mov %0, %%db1" ::"r" (value)); + break; + case 2: + asm("mov %0, %%db2" ::"r" (value)); + break; + case 3: + asm("mov %0, %%db3" ::"r" (value)); + break; + case 6: + asm("mov %0, %%db6" ::"r" (value)); + break; + case 7: + asm("mov %0, %%db7" ::"r" (value)); + break; + default: + BUG(); + } +} + static inline void hw_breakpoint_disable(void) { /* Zero the control register for HW Breakpoint */ @@ -101,6 +168,28 @@ extern void aout_dump_debugregs(struct user *dump); extern void hw_breakpoint_restore(void); +#ifdef CONFIG_X86_64 +DECLARE_PER_CPU(int, debug_stack_usage); +static inline void debug_stack_usage_inc(void) +{ + __get_cpu_var(debug_stack_usage)++; +} +static inline void debug_stack_usage_dec(void) +{ + __get_cpu_var(debug_stack_usage)--; +} +int is_debug_stack(unsigned long addr); +void debug_stack_set_zero(void); +void debug_stack_reset(void); +#else /* !X86_64 */ +static inline int is_debug_stack(unsigned long addr) { return 0; } +static inline void debug_stack_set_zero(void) { } +static inline void debug_stack_reset(void) { } +static inline void debug_stack_usage_inc(void) { } +static inline void debug_stack_usage_dec(void) { } +#endif /* X86_64 */ + + #endif /* __KERNEL__ */ #endif /* _ASM_X86_DEBUGREG_H */ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 41935fadfdf..e95822d683f 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -35,6 +35,8 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in extern struct desc_ptr idt_descr; extern gate_desc idt_table[]; +extern struct desc_ptr nmi_idt_descr; +extern gate_desc nmi_idt_table[]; struct gdt_page { struct desc_struct gdt[GDT_ENTRIES]; @@ -307,6 +309,16 @@ static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit) desc->limit = (limit >> 16) & 0xf; } +#ifdef CONFIG_X86_64 +static inline void set_nmi_gate(int gate, void *addr) +{ + gate_desc s; + + pack_gate(&s, GATE_INTERRUPT, (unsigned long)addr, 0, 0, __KERNEL_CS); + write_idt_entry(nmi_idt_table, gate, &s); +} +#endif + static inline void _set_gate(int gate, unsigned type, void *addr, unsigned dpl, unsigned ist, unsigned seg) { diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index ed3065fd631..4b4331d7193 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -59,7 +59,8 @@ extern int dma_supported(struct device *hwdev, u64 mask); extern int dma_set_mask(struct device *dev, u64 mask); extern void *dma_generic_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_addr, gfp_t flag); + dma_addr_t *dma_addr, gfp_t flag, + struct dma_attrs *attrs); static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) { @@ -111,9 +112,11 @@ 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) + static inline void * -dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t gfp) +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; @@ -129,18 +132,21 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, if (!is_device_dma_capable(dev)) return NULL; - if (!ops->alloc_coherent) + if (!ops->alloc) return NULL; - memory = ops->alloc_coherent(dev, size, dma_handle, - dma_alloc_coherent_gfp_flags(dev, gfp)); + 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; } -static inline void dma_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t bus) +#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL) + +static inline void dma_free_attrs(struct device *dev, size_t size, + void *vaddr, dma_addr_t bus, + struct dma_attrs *attrs) { struct dma_map_ops *ops = get_dma_ops(dev); @@ -150,8 +156,8 @@ static inline void dma_free_coherent(struct device *dev, size_t size, return; debug_dma_free_coherent(dev, size, vaddr, bus); - if (ops->free_coherent) - ops->free_coherent(dev, size, vaddr, bus); + if (ops->free) + ops->free(dev, size, vaddr, bus, attrs); } #endif diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 7093e4a6a0b..c9dcc181d4d 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -3,6 +3,8 @@ #ifdef CONFIG_X86_32 +#define EFI_LOADER_SIGNATURE "EL32" + extern unsigned long asmlinkage efi_call_phys(void *, ...); #define efi_call_phys0(f) efi_call_phys(f) @@ -37,6 +39,8 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...); #else /* !CONFIG_X86_32 */ +#define EFI_LOADER_SIGNATURE "EL64" + extern u64 efi_call0(void *fp); extern u64 efi_call1(void *fp, u64 arg1); extern u64 efi_call2(void *fp, u64 arg1, u64 arg2); @@ -91,7 +95,7 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size, extern int add_efi_memmap; extern void efi_set_executable(efi_memory_desc_t *md, bool executable); -extern void efi_memblock_x86_reserve_range(void); +extern int efi_memblock_x86_reserve_range(void); extern void efi_call_phys_prelog(void); extern void efi_call_phys_epilog(void); diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 5f962df30d0..5939f44fe0c 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -84,7 +84,6 @@ extern unsigned int vdso_enabled; (((x)->e_machine == EM_386) || ((x)->e_machine == EM_486)) #include <asm/processor.h> -#include <asm/system.h> #ifdef CONFIG_X86_32 #include <asm/desc.h> @@ -156,7 +155,12 @@ do { \ #define elf_check_arch(x) \ ((x)->e_machine == EM_X86_64) -#define compat_elf_check_arch(x) elf_check_arch_ia32(x) +#define compat_elf_check_arch(x) \ + (elf_check_arch_ia32(x) || (x)->e_machine == EM_X86_64) + +#if __USER32_DS != __USER_DS +# error "The following code assumes __USER32_DS == __USER_DS" +#endif static inline void elf_common_init(struct thread_struct *t, struct pt_regs *regs, const u16 ds) @@ -179,8 +183,9 @@ static inline void elf_common_init(struct thread_struct *t, void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp); #define compat_start_thread start_thread_ia32 -void set_personality_ia32(void); -#define COMPAT_SET_PERSONALITY(ex) set_personality_ia32() +void set_personality_ia32(bool); +#define COMPAT_SET_PERSONALITY(ex) \ + set_personality_ia32((ex).e_machine == EM_X86_64) #define COMPAT_ELF_PLATFORM ("i686") @@ -287,7 +292,7 @@ do { \ #define VDSO_HIGH_BASE 0xffffe000U /* CONFIG_COMPAT_VDSO address */ /* 1GB for 64bit, 8MB for 32bit */ -#define STACK_RND_MASK (test_thread_flag(TIF_IA32) ? 0x7ff : 0x3fffff) +#define STACK_RND_MASK (test_thread_flag(TIF_ADDR32) ? 0x7ff : 0x3fffff) #define ARCH_DLINFO \ do { \ @@ -296,9 +301,20 @@ do { \ (unsigned long)current->mm->context.vdso); \ } while (0) +#define ARCH_DLINFO_X32 \ +do { \ + if (vdso_enabled) \ + NEW_AUX_ENT(AT_SYSINFO_EHDR, \ + (unsigned long)current->mm->context.vdso); \ +} while (0) + #define AT_SYSINFO 32 -#define COMPAT_ARCH_DLINFO ARCH_DLINFO_IA32(sysctl_vsyscall32) +#define COMPAT_ARCH_DLINFO \ +if (test_thread_flag(TIF_X32)) \ + ARCH_DLINFO_X32; \ +else \ + ARCH_DLINFO_IA32(sysctl_vsyscall32) #define COMPAT_ELF_ET_DYN_BASE (TASK_UNMAPPED_BASE + 0x1000000) @@ -314,6 +330,8 @@ struct linux_binprm; #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1 extern int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp); +extern int x32_setup_additional_pages(struct linux_binprm *bprm, + int uses_interp); extern int syscall32_setup_pages(struct linux_binprm *, int exstack); #define compat_arch_setup_additional_pages syscall32_setup_pages @@ -330,7 +348,7 @@ static inline int mmap_is_ia32(void) return 1; #endif #ifdef CONFIG_IA32_EMULATION - if (test_thread_flag(TIF_IA32)) + if (test_thread_flag(TIF_ADDR32)) return 1; #endif return 0; diff --git a/arch/x86/include/asm/exec.h b/arch/x86/include/asm/exec.h new file mode 100644 index 00000000000..54c2e1db274 --- /dev/null +++ b/arch/x86/include/asm/exec.h @@ -0,0 +1 @@ +/* define arch_align_stack() here */ diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 460c74e4852..4da3c0c4c97 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -117,7 +117,7 @@ enum fixed_addresses { #endif FIX_TEXT_POKE1, /* reserve 2 pages for text_poke() */ FIX_TEXT_POKE0, /* first page is last, because allocation is backward */ -#ifdef CONFIG_X86_MRST +#ifdef CONFIG_X86_INTEL_MID FIX_LNW_VRTC, #endif __end_of_permanent_fixed_addresses, diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h new file mode 100644 index 00000000000..4fa88154e4d --- /dev/null +++ b/arch/x86/include/asm/fpu-internal.h @@ -0,0 +1,520 @@ +/* + * Copyright (C) 1994 Linus Torvalds + * + * Pentium III FXSR, SSE support + * General FPU state handling cleanups + * Gareth Hughes <gareth@valinux.com>, May 2000 + * x86-64 work by Andi Kleen 2002 + */ + +#ifndef _FPU_INTERNAL_H +#define _FPU_INTERNAL_H + +#include <linux/kernel_stat.h> +#include <linux/regset.h> +#include <linux/slab.h> +#include <asm/asm.h> +#include <asm/cpufeature.h> +#include <asm/processor.h> +#include <asm/sigcontext.h> +#include <asm/user.h> +#include <asm/uaccess.h> +#include <asm/xsave.h> + +extern unsigned int sig_xstate_size; +extern void fpu_init(void); + +DECLARE_PER_CPU(struct task_struct *, fpu_owner_task); + +extern user_regset_active_fn fpregs_active, xfpregs_active; +extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get, + xstateregs_get; +extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set, + xstateregs_set; + + +/* + * xstateregs_active == fpregs_active. Please refer to the comment + * at the definition of fpregs_active. + */ +#define xstateregs_active fpregs_active + +extern struct _fpx_sw_bytes fx_sw_reserved; +#ifdef CONFIG_IA32_EMULATION +extern unsigned int sig_xstate_ia32_size; +extern struct _fpx_sw_bytes fx_sw_reserved_ia32; +struct _fpstate_ia32; +struct _xstate_ia32; +extern int save_i387_xstate_ia32(void __user *buf); +extern int restore_i387_xstate_ia32(void __user *buf); +#endif + +#ifdef CONFIG_MATH_EMULATION +extern void finit_soft_fpu(struct i387_soft_struct *soft); +#else +static inline void finit_soft_fpu(struct i387_soft_struct *soft) {} +#endif + +#define X87_FSW_ES (1 << 7) /* Exception Summary */ + +static __always_inline __pure bool use_xsaveopt(void) +{ + return static_cpu_has(X86_FEATURE_XSAVEOPT); +} + +static __always_inline __pure bool use_xsave(void) +{ + return static_cpu_has(X86_FEATURE_XSAVE); +} + +static __always_inline __pure bool use_fxsr(void) +{ + return static_cpu_has(X86_FEATURE_FXSR); +} + +extern void __sanitize_i387_state(struct task_struct *); + +static inline void sanitize_i387_state(struct task_struct *tsk) +{ + if (!use_xsaveopt()) + return; + __sanitize_i387_state(tsk); +} + +#ifdef CONFIG_X86_64 +static inline int fxrstor_checking(struct i387_fxsave_struct *fx) +{ + int err; + + /* See comment in fxsave() below. */ +#ifdef CONFIG_AS_FXSAVEQ + asm volatile("1: fxrstorq %[fx]\n\t" + "2:\n" + ".section .fixup,\"ax\"\n" + "3: movl $-1,%[err]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [err] "=r" (err) + : [fx] "m" (*fx), "0" (0)); +#else + asm volatile("1: rex64/fxrstor (%[fx])\n\t" + "2:\n" + ".section .fixup,\"ax\"\n" + "3: movl $-1,%[err]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [err] "=r" (err) + : [fx] "R" (fx), "m" (*fx), "0" (0)); +#endif + return err; +} + +static inline int fxsave_user(struct i387_fxsave_struct __user *fx) +{ + int err; + + /* + * Clear the bytes not touched by the fxsave and reserved + * for the SW usage. + */ + err = __clear_user(&fx->sw_reserved, + sizeof(struct _fpx_sw_bytes)); + if (unlikely(err)) + return -EFAULT; + + /* See comment in fxsave() below. */ +#ifdef CONFIG_AS_FXSAVEQ + asm volatile("1: fxsaveq %[fx]\n\t" + "2:\n" + ".section .fixup,\"ax\"\n" + "3: movl $-1,%[err]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [err] "=r" (err), [fx] "=m" (*fx) + : "0" (0)); +#else + asm volatile("1: rex64/fxsave (%[fx])\n\t" + "2:\n" + ".section .fixup,\"ax\"\n" + "3: movl $-1,%[err]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [err] "=r" (err), "=m" (*fx) + : [fx] "R" (fx), "0" (0)); +#endif + if (unlikely(err) && + __clear_user(fx, sizeof(struct i387_fxsave_struct))) + err = -EFAULT; + /* No need to clear here because the caller clears USED_MATH */ + return err; +} + +static inline void fpu_fxsave(struct fpu *fpu) +{ + /* Using "rex64; fxsave %0" is broken because, if the memory operand + uses any extended registers for addressing, a second REX prefix + will be generated (to the assembler, rex64 followed by semicolon + is a separate instruction), and hence the 64-bitness is lost. */ + +#ifdef CONFIG_AS_FXSAVEQ + /* Using "fxsaveq %0" would be the ideal choice, but is only supported + starting with gas 2.16. */ + __asm__ __volatile__("fxsaveq %0" + : "=m" (fpu->state->fxsave)); +#else + /* Using, as a workaround, the properly prefixed form below isn't + accepted by any binutils version so far released, complaining that + the same type of prefix is used twice if an extended register is + needed for addressing (fix submitted to mainline 2005-11-21). + asm volatile("rex64/fxsave %0" + : "=m" (fpu->state->fxsave)); + This, however, we can work around by forcing the compiler to select + an addressing mode that doesn't require extended registers. */ + asm volatile("rex64/fxsave (%[fx])" + : "=m" (fpu->state->fxsave) + : [fx] "R" (&fpu->state->fxsave)); +#endif +} + +#else /* CONFIG_X86_32 */ + +/* perform fxrstor iff the processor has extended states, otherwise frstor */ +static inline int fxrstor_checking(struct i387_fxsave_struct *fx) +{ + /* + * The "nop" is needed to make the instructions the same + * length. + */ + alternative_input( + "nop ; frstor %1", + "fxrstor %1", + X86_FEATURE_FXSR, + "m" (*fx)); + + return 0; +} + +static inline void fpu_fxsave(struct fpu *fpu) +{ + asm volatile("fxsave %[fx]" + : [fx] "=m" (fpu->state->fxsave)); +} + +#endif /* CONFIG_X86_64 */ + +/* + * These must be called with preempt disabled. Returns + * 'true' if the FPU state is still intact. + */ +static inline int fpu_save_init(struct fpu *fpu) +{ + if (use_xsave()) { + fpu_xsave(fpu); + + /* + * xsave header may indicate the init state of the FP. + */ + if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP)) + return 1; + } else if (use_fxsr()) { + fpu_fxsave(fpu); + } else { + asm volatile("fnsave %[fx]; fwait" + : [fx] "=m" (fpu->state->fsave)); + return 0; + } + + /* + * If exceptions are pending, we need to clear them so + * that we don't randomly get exceptions later. + * + * FIXME! Is this perhaps only true for the old-style + * irq13 case? Maybe we could leave the x87 state + * intact otherwise? + */ + if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) { + asm volatile("fnclex"); + return 0; + } + return 1; +} + +static inline int __save_init_fpu(struct task_struct *tsk) +{ + return fpu_save_init(&tsk->thread.fpu); +} + +static inline int fpu_fxrstor_checking(struct fpu *fpu) +{ + return fxrstor_checking(&fpu->state->fxsave); +} + +static inline int fpu_restore_checking(struct fpu *fpu) +{ + if (use_xsave()) + return fpu_xrstor_checking(fpu); + else + return fpu_fxrstor_checking(fpu); +} + +static inline int restore_fpu_checking(struct task_struct *tsk) +{ + /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception + is pending. Clear the x87 state here by setting it to fixed + values. "m" is a random variable that should be in L1 */ + alternative_input( + ASM_NOP8 ASM_NOP2, + "emms\n\t" /* clear stack tags */ + "fildl %P[addr]", /* set F?P to defined value */ + X86_FEATURE_FXSAVE_LEAK, + [addr] "m" (tsk->thread.fpu.has_fpu)); + + return fpu_restore_checking(&tsk->thread.fpu); +} + +/* + * Software FPU state helpers. Careful: these need to + * be preemption protection *and* they need to be + * properly paired with the CR0.TS changes! + */ +static inline int __thread_has_fpu(struct task_struct *tsk) +{ + return tsk->thread.fpu.has_fpu; +} + +/* Must be paired with an 'stts' after! */ +static inline void __thread_clear_has_fpu(struct task_struct *tsk) +{ + tsk->thread.fpu.has_fpu = 0; + percpu_write(fpu_owner_task, NULL); +} + +/* Must be paired with a 'clts' before! */ +static inline void __thread_set_has_fpu(struct task_struct *tsk) +{ + tsk->thread.fpu.has_fpu = 1; + percpu_write(fpu_owner_task, tsk); +} + +/* + * Encapsulate the CR0.TS handling together with the + * software flag. + * + * These generally need preemption protection to work, + * do try to avoid using these on their own. + */ +static inline void __thread_fpu_end(struct task_struct *tsk) +{ + __thread_clear_has_fpu(tsk); + stts(); +} + +static inline void __thread_fpu_begin(struct task_struct *tsk) +{ + clts(); + __thread_set_has_fpu(tsk); +} + +/* + * FPU state switching for scheduling. + * + * This is a two-stage process: + * + * - switch_fpu_prepare() saves the old state and + * sets the new state of the CR0.TS bit. This is + * done within the context of the old process. + * + * - switch_fpu_finish() restores the new state as + * necessary. + */ +typedef struct { int preload; } fpu_switch_t; + +/* + * FIXME! We could do a totally lazy restore, but we need to + * add a per-cpu "this was the task that last touched the FPU + * on this CPU" variable, and the task needs to have a "I last + * touched the FPU on this CPU" and check them. + * + * We don't do that yet, so "fpu_lazy_restore()" always returns + * false, but some day.. + */ +static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu) +{ + return new == percpu_read_stable(fpu_owner_task) && + cpu == new->thread.fpu.last_cpu; +} + +static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu) +{ + fpu_switch_t fpu; + + fpu.preload = tsk_used_math(new) && new->fpu_counter > 5; + if (__thread_has_fpu(old)) { + if (!__save_init_fpu(old)) + cpu = ~0; + old->thread.fpu.last_cpu = cpu; + old->thread.fpu.has_fpu = 0; /* But leave fpu_owner_task! */ + + /* Don't change CR0.TS if we just switch! */ + if (fpu.preload) { + new->fpu_counter++; + __thread_set_has_fpu(new); + prefetch(new->thread.fpu.state); + } else + stts(); + } else { + old->fpu_counter = 0; + old->thread.fpu.last_cpu = ~0; + if (fpu.preload) { + new->fpu_counter++; + if (fpu_lazy_restore(new, cpu)) + fpu.preload = 0; + else + prefetch(new->thread.fpu.state); + __thread_fpu_begin(new); + } + } + return fpu; +} + +/* + * By the time this gets called, we've already cleared CR0.TS and + * given the process the FPU if we are going to preload the FPU + * state - all we need to do is to conditionally restore the register + * state itself. + */ +static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu) +{ + if (fpu.preload) { + if (unlikely(restore_fpu_checking(new))) + __thread_fpu_end(new); + } +} + +/* + * Signal frame handlers... + */ +extern int save_i387_xstate(void __user *buf); +extern int restore_i387_xstate(void __user *buf); + +static inline void __clear_fpu(struct task_struct *tsk) +{ + if (__thread_has_fpu(tsk)) { + /* Ignore delayed exceptions from user space */ + asm volatile("1: fwait\n" + "2:\n" + _ASM_EXTABLE(1b, 2b)); + __thread_fpu_end(tsk); + } +} + +/* + * The actual user_fpu_begin/end() functions + * need to be preemption-safe. + * + * NOTE! user_fpu_end() must be used only after you + * have saved the FP state, and user_fpu_begin() must + * be used only immediately before restoring it. + * These functions do not do any save/restore on + * their own. + */ +static inline void user_fpu_end(void) +{ + preempt_disable(); + __thread_fpu_end(current); + preempt_enable(); +} + +static inline void user_fpu_begin(void) +{ + preempt_disable(); + if (!user_has_fpu()) + __thread_fpu_begin(current); + preempt_enable(); +} + +/* + * These disable preemption on their own and are safe + */ +static inline void save_init_fpu(struct task_struct *tsk) +{ + WARN_ON_ONCE(!__thread_has_fpu(tsk)); + preempt_disable(); + __save_init_fpu(tsk); + __thread_fpu_end(tsk); + preempt_enable(); +} + +static inline void clear_fpu(struct task_struct *tsk) +{ + preempt_disable(); + __clear_fpu(tsk); + preempt_enable(); +} + +/* + * i387 state interaction + */ +static inline unsigned short get_fpu_cwd(struct task_struct *tsk) +{ + if (cpu_has_fxsr) { + return tsk->thread.fpu.state->fxsave.cwd; + } else { + return (unsigned short)tsk->thread.fpu.state->fsave.cwd; + } +} + +static inline unsigned short get_fpu_swd(struct task_struct *tsk) +{ + if (cpu_has_fxsr) { + return tsk->thread.fpu.state->fxsave.swd; + } else { + return (unsigned short)tsk->thread.fpu.state->fsave.swd; + } +} + +static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk) +{ + if (cpu_has_xmm) { + return tsk->thread.fpu.state->fxsave.mxcsr; + } else { + return MXCSR_DEFAULT; + } +} + +static bool fpu_allocated(struct fpu *fpu) +{ + return fpu->state != NULL; +} + +static inline int fpu_alloc(struct fpu *fpu) +{ + if (fpu_allocated(fpu)) + return 0; + fpu->state = kmem_cache_alloc(task_xstate_cachep, GFP_KERNEL); + if (!fpu->state) + return -ENOMEM; + WARN_ON((unsigned long)fpu->state & 15); + return 0; +} + +static inline void fpu_free(struct fpu *fpu) +{ + if (fpu->state) { + kmem_cache_free(task_xstate_cachep, fpu->state); + fpu->state = NULL; + } +} + +static inline void fpu_copy(struct fpu *dst, struct fpu *src) +{ + memcpy(dst->state, src->state, xstate_size); +} + +extern void fpu_finit(struct fpu *fpu); + +#endif diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h index d09bb03653f..71ecbcba1a4 100644 --- a/arch/x86/include/asm/futex.h +++ b/arch/x86/include/asm/futex.h @@ -9,7 +9,6 @@ #include <asm/asm.h> #include <asm/errno.h> #include <asm/processor.h> -#include <asm/system.h> #define __futex_atomic_op1(insn, ret, oldval, uaddr, oparg) \ asm volatile("1:\t" insn "\n" \ diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index da0b3ca815b..382f75d735f 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -7,7 +7,6 @@ typedef struct { unsigned int __softirq_pending; unsigned int __nmi_count; /* arch dependent */ - unsigned int irq0_irqs; #ifdef CONFIG_X86_LOCAL_APIC unsigned int apic_timer_irqs; /* arch dependent */ unsigned int irq_spurious_count; diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h index 3bd04022fd0..302a323b3f6 100644 --- a/arch/x86/include/asm/highmem.h +++ b/arch/x86/include/asm/highmem.h @@ -61,7 +61,7 @@ void *kmap(struct page *page); void kunmap(struct page *page); void *kmap_atomic_prot(struct page *page, pgprot_t prot); -void *__kmap_atomic(struct page *page); +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); diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index 6919e936345..257d9cca214 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -13,323 +13,18 @@ #ifndef __ASSEMBLY__ #include <linux/sched.h> -#include <linux/kernel_stat.h> -#include <linux/regset.h> #include <linux/hardirq.h> -#include <linux/slab.h> -#include <asm/asm.h> -#include <asm/cpufeature.h> -#include <asm/processor.h> -#include <asm/sigcontext.h> -#include <asm/user.h> -#include <asm/uaccess.h> -#include <asm/xsave.h> -extern unsigned int sig_xstate_size; -extern void fpu_init(void); -extern void mxcsr_feature_mask_init(void); +struct pt_regs; +struct user_i387_struct; + extern int init_fpu(struct task_struct *child); -extern asmlinkage void math_state_restore(void); -extern void __math_state_restore(void); extern int dump_fpu(struct pt_regs *, struct user_i387_struct *); +extern void math_state_restore(void); -extern user_regset_active_fn fpregs_active, xfpregs_active; -extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get, - xstateregs_get; -extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set, - xstateregs_set; - -/* - * xstateregs_active == fpregs_active. Please refer to the comment - * at the definition of fpregs_active. - */ -#define xstateregs_active fpregs_active - -extern struct _fpx_sw_bytes fx_sw_reserved; -#ifdef CONFIG_IA32_EMULATION -extern unsigned int sig_xstate_ia32_size; -extern struct _fpx_sw_bytes fx_sw_reserved_ia32; -struct _fpstate_ia32; -struct _xstate_ia32; -extern int save_i387_xstate_ia32(void __user *buf); -extern int restore_i387_xstate_ia32(void __user *buf); -#endif - -#ifdef CONFIG_MATH_EMULATION -extern void finit_soft_fpu(struct i387_soft_struct *soft); -#else -static inline void finit_soft_fpu(struct i387_soft_struct *soft) {} -#endif - -#define X87_FSW_ES (1 << 7) /* Exception Summary */ - -static __always_inline __pure bool use_xsaveopt(void) -{ - return static_cpu_has(X86_FEATURE_XSAVEOPT); -} - -static __always_inline __pure bool use_xsave(void) -{ - return static_cpu_has(X86_FEATURE_XSAVE); -} - -static __always_inline __pure bool use_fxsr(void) -{ - return static_cpu_has(X86_FEATURE_FXSR); -} - -extern void __sanitize_i387_state(struct task_struct *); - -static inline void sanitize_i387_state(struct task_struct *tsk) -{ - if (!use_xsaveopt()) - return; - __sanitize_i387_state(tsk); -} - -#ifdef CONFIG_X86_64 -static inline int fxrstor_checking(struct i387_fxsave_struct *fx) -{ - int err; - - /* See comment in fxsave() below. */ -#ifdef CONFIG_AS_FXSAVEQ - asm volatile("1: fxrstorq %[fx]\n\t" - "2:\n" - ".section .fixup,\"ax\"\n" - "3: movl $-1,%[err]\n" - " jmp 2b\n" - ".previous\n" - _ASM_EXTABLE(1b, 3b) - : [err] "=r" (err) - : [fx] "m" (*fx), "0" (0)); -#else - asm volatile("1: rex64/fxrstor (%[fx])\n\t" - "2:\n" - ".section .fixup,\"ax\"\n" - "3: movl $-1,%[err]\n" - " jmp 2b\n" - ".previous\n" - _ASM_EXTABLE(1b, 3b) - : [err] "=r" (err) - : [fx] "R" (fx), "m" (*fx), "0" (0)); -#endif - return err; -} - -static inline int fxsave_user(struct i387_fxsave_struct __user *fx) -{ - int err; - - /* - * Clear the bytes not touched by the fxsave and reserved - * for the SW usage. - */ - err = __clear_user(&fx->sw_reserved, - sizeof(struct _fpx_sw_bytes)); - if (unlikely(err)) - return -EFAULT; - - /* See comment in fxsave() below. */ -#ifdef CONFIG_AS_FXSAVEQ - asm volatile("1: fxsaveq %[fx]\n\t" - "2:\n" - ".section .fixup,\"ax\"\n" - "3: movl $-1,%[err]\n" - " jmp 2b\n" - ".previous\n" - _ASM_EXTABLE(1b, 3b) - : [err] "=r" (err), [fx] "=m" (*fx) - : "0" (0)); -#else - asm volatile("1: rex64/fxsave (%[fx])\n\t" - "2:\n" - ".section .fixup,\"ax\"\n" - "3: movl $-1,%[err]\n" - " jmp 2b\n" - ".previous\n" - _ASM_EXTABLE(1b, 3b) - : [err] "=r" (err), "=m" (*fx) - : [fx] "R" (fx), "0" (0)); -#endif - if (unlikely(err) && - __clear_user(fx, sizeof(struct i387_fxsave_struct))) - err = -EFAULT; - /* No need to clear here because the caller clears USED_MATH */ - return err; -} - -static inline void fpu_fxsave(struct fpu *fpu) -{ - /* Using "rex64; fxsave %0" is broken because, if the memory operand - uses any extended registers for addressing, a second REX prefix - will be generated (to the assembler, rex64 followed by semicolon - is a separate instruction), and hence the 64-bitness is lost. */ - -#ifdef CONFIG_AS_FXSAVEQ - /* Using "fxsaveq %0" would be the ideal choice, but is only supported - starting with gas 2.16. */ - __asm__ __volatile__("fxsaveq %0" - : "=m" (fpu->state->fxsave)); -#else - /* Using, as a workaround, the properly prefixed form below isn't - accepted by any binutils version so far released, complaining that - the same type of prefix is used twice if an extended register is - needed for addressing (fix submitted to mainline 2005-11-21). - asm volatile("rex64/fxsave %0" - : "=m" (fpu->state->fxsave)); - This, however, we can work around by forcing the compiler to select - an addressing mode that doesn't require extended registers. */ - asm volatile("rex64/fxsave (%[fx])" - : "=m" (fpu->state->fxsave) - : [fx] "R" (&fpu->state->fxsave)); -#endif -} - -#else /* CONFIG_X86_32 */ - -/* perform fxrstor iff the processor has extended states, otherwise frstor */ -static inline int fxrstor_checking(struct i387_fxsave_struct *fx) -{ - /* - * The "nop" is needed to make the instructions the same - * length. - */ - alternative_input( - "nop ; frstor %1", - "fxrstor %1", - X86_FEATURE_FXSR, - "m" (*fx)); - - return 0; -} - -static inline void fpu_fxsave(struct fpu *fpu) -{ - asm volatile("fxsave %[fx]" - : [fx] "=m" (fpu->state->fxsave)); -} - -#endif /* CONFIG_X86_64 */ - -/* We need a safe address that is cheap to find and that is already - in L1 during context switch. The best choices are unfortunately - different for UP and SMP */ -#ifdef CONFIG_SMP -#define safe_address (__per_cpu_offset[0]) -#else -#define safe_address (__get_cpu_var(kernel_cpustat).cpustat[CPUTIME_USER]) -#endif - -/* - * These must be called with preempt disabled - */ -static inline void fpu_save_init(struct fpu *fpu) -{ - if (use_xsave()) { - fpu_xsave(fpu); - - /* - * xsave header may indicate the init state of the FP. - */ - if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP)) - return; - } else if (use_fxsr()) { - fpu_fxsave(fpu); - } else { - asm volatile("fnsave %[fx]; fwait" - : [fx] "=m" (fpu->state->fsave)); - return; - } - - if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) - asm volatile("fnclex"); - - /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception - is pending. Clear the x87 state here by setting it to fixed - values. safe_address is a random variable that should be in L1 */ - alternative_input( - ASM_NOP8 ASM_NOP2, - "emms\n\t" /* clear stack tags */ - "fildl %P[addr]", /* set F?P to defined value */ - X86_FEATURE_FXSAVE_LEAK, - [addr] "m" (safe_address)); -} - -static inline void __save_init_fpu(struct task_struct *tsk) -{ - fpu_save_init(&tsk->thread.fpu); - task_thread_info(tsk)->status &= ~TS_USEDFPU; -} - -static inline int fpu_fxrstor_checking(struct fpu *fpu) -{ - return fxrstor_checking(&fpu->state->fxsave); -} - -static inline int fpu_restore_checking(struct fpu *fpu) -{ - if (use_xsave()) - return fpu_xrstor_checking(fpu); - else - return fpu_fxrstor_checking(fpu); -} - -static inline int restore_fpu_checking(struct task_struct *tsk) -{ - return fpu_restore_checking(&tsk->thread.fpu); -} - -/* - * Signal frame handlers... - */ -extern int save_i387_xstate(void __user *buf); -extern int restore_i387_xstate(void __user *buf); - -static inline void __unlazy_fpu(struct task_struct *tsk) -{ - if (task_thread_info(tsk)->status & TS_USEDFPU) { - __save_init_fpu(tsk); - stts(); - } else - tsk->fpu_counter = 0; -} - -static inline void __clear_fpu(struct task_struct *tsk) -{ - if (task_thread_info(tsk)->status & TS_USEDFPU) { - /* Ignore delayed exceptions from user space */ - asm volatile("1: fwait\n" - "2:\n" - _ASM_EXTABLE(1b, 2b)); - task_thread_info(tsk)->status &= ~TS_USEDFPU; - stts(); - } -} - -static inline void kernel_fpu_begin(void) -{ - struct thread_info *me = current_thread_info(); - preempt_disable(); - if (me->status & TS_USEDFPU) - __save_init_fpu(me->task); - else - clts(); -} - -static inline void kernel_fpu_end(void) -{ - stts(); - preempt_enable(); -} - -static inline bool irq_fpu_usable(void) -{ - struct pt_regs *regs; - - return !in_interrupt() || !(regs = get_irq_regs()) || \ - user_mode(regs) || (read_cr0() & X86_CR0_TS); -} +extern bool irq_fpu_usable(void); +extern void kernel_fpu_begin(void); +extern void kernel_fpu_end(void); /* * Some instructions like VIA's padlock instructions generate a spurious @@ -363,90 +58,21 @@ static inline void irq_ts_restore(int TS_state) } /* - * These disable preemption on their own and are safe - */ -static inline void save_init_fpu(struct task_struct *tsk) -{ - preempt_disable(); - __save_init_fpu(tsk); - stts(); - preempt_enable(); -} - -static inline void unlazy_fpu(struct task_struct *tsk) -{ - preempt_disable(); - __unlazy_fpu(tsk); - preempt_enable(); -} - -static inline void clear_fpu(struct task_struct *tsk) -{ - preempt_disable(); - __clear_fpu(tsk); - preempt_enable(); -} - -/* - * i387 state interaction + * The question "does this thread have fpu access?" + * is slightly racy, since preemption could come in + * and revoke it immediately after the test. + * + * However, even in that very unlikely scenario, + * we can just assume we have FPU access - typically + * to save the FP state - we'll just take a #NM + * fault and get the FPU access back. */ -static inline unsigned short get_fpu_cwd(struct task_struct *tsk) -{ - if (cpu_has_fxsr) { - return tsk->thread.fpu.state->fxsave.cwd; - } else { - return (unsigned short)tsk->thread.fpu.state->fsave.cwd; - } -} - -static inline unsigned short get_fpu_swd(struct task_struct *tsk) -{ - if (cpu_has_fxsr) { - return tsk->thread.fpu.state->fxsave.swd; - } else { - return (unsigned short)tsk->thread.fpu.state->fsave.swd; - } -} - -static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk) -{ - if (cpu_has_xmm) { - return tsk->thread.fpu.state->fxsave.mxcsr; - } else { - return MXCSR_DEFAULT; - } -} - -static bool fpu_allocated(struct fpu *fpu) -{ - return fpu->state != NULL; -} - -static inline int fpu_alloc(struct fpu *fpu) -{ - if (fpu_allocated(fpu)) - return 0; - fpu->state = kmem_cache_alloc(task_xstate_cachep, GFP_KERNEL); - if (!fpu->state) - return -ENOMEM; - WARN_ON((unsigned long)fpu->state & 15); - return 0; -} - -static inline void fpu_free(struct fpu *fpu) -{ - if (fpu->state) { - kmem_cache_free(task_xstate_cachep, fpu->state); - fpu->state = NULL; - } -} - -static inline void fpu_copy(struct fpu *dst, struct fpu *src) +static inline int user_has_fpu(void) { - memcpy(dst->state, src->state, xstate_size); + return current->thread.fpu.has_fpu; } -extern void fpu_finit(struct fpu *fpu); +extern void unlazy_fpu(struct task_struct *tsk); #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h index 1f7e6251728..ee52760549f 100644 --- a/arch/x86/include/asm/ia32.h +++ b/arch/x86/include/asm/ia32.h @@ -43,6 +43,15 @@ struct ucontext_ia32 { compat_sigset_t uc_sigmask; /* mask last for extensibility */ }; +struct ucontext_x32 { + unsigned int uc_flags; + unsigned int uc_link; + stack_ia32_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 */ +}; + /* This matches struct stat64 in glibc2.2, hence the absolutely * insane amounts of padding around dev_t's. */ @@ -116,6 +125,15 @@ typedef struct compat_siginfo { compat_clock_t _stime; } _sigchld; + /* SIGCHLD (x32 version) */ + struct { + unsigned int _pid; /* which child */ + unsigned int _uid; /* sender's uid */ + int _status; /* exit code */ + compat_s64 _utime; + compat_s64 _stime; + } _sigchld_x32; + /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ struct { unsigned int _addr; /* faulting insn/memory ref. */ diff --git a/arch/x86/include/asm/ia32_unistd.h b/arch/x86/include/asm/ia32_unistd.h index 976f6ecd2ce..b0d5716ca1e 100644 --- a/arch/x86/include/asm/ia32_unistd.h +++ b/arch/x86/include/asm/ia32_unistd.h @@ -2,17 +2,10 @@ #define _ASM_X86_IA32_UNISTD_H /* - * This file contains the system call numbers of the ia32 port, + * This file contains the system call numbers of the ia32 compat ABI, * this is for the kernel only. - * Only add syscalls here where some part of the kernel needs to know - * the number. This should be otherwise in sync with asm-x86/unistd_32.h. -AK */ - -#define __NR_ia32_restart_syscall 0 -#define __NR_ia32_exit 1 -#define __NR_ia32_read 3 -#define __NR_ia32_write 4 -#define __NR_ia32_sigreturn 119 -#define __NR_ia32_rt_sigreturn 173 +#define __SYSCALL_ia32_NR(x) (x) +#include <asm/unistd_32_ia32.h> #endif /* _ASM_X86_IA32_UNISTD_H */ diff --git a/arch/x86/include/asm/idle.h b/arch/x86/include/asm/idle.h index f49253d7571..c5d1785373e 100644 --- a/arch/x86/include/asm/idle.h +++ b/arch/x86/include/asm/idle.h @@ -14,6 +14,7 @@ void exit_idle(void); #else /* !CONFIG_X86_64 */ static inline void enter_idle(void) { } static inline void exit_idle(void) { } +static inline void __exit_idle(void) { } #endif /* CONFIG_X86_64 */ void amd_e400_remove_cpu(int cpu); diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h index 205b063e3e3..74a2e312e8a 100644 --- a/arch/x86/include/asm/inat.h +++ b/arch/x86/include/asm/inat.h @@ -97,11 +97,12 @@ /* Attribute search APIs */ extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode); +extern int inat_get_last_prefix_id(insn_byte_t last_pfx); extern insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, - insn_byte_t last_pfx, + int lpfx_id, insn_attr_t esc_attr); extern insn_attr_t inat_get_group_attribute(insn_byte_t modrm, - insn_byte_t last_pfx, + int lpfx_id, insn_attr_t esc_attr); extern insn_attr_t inat_get_avx_attribute(insn_byte_t opcode, insn_byte_t vex_m, diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h index 8dbe353e41e..adcc0ae73d0 100644 --- a/arch/x86/include/asm/init.h +++ b/arch/x86/include/asm/init.h @@ -5,6 +5,8 @@ extern void __init early_ioremap_page_table_range_init(void); #endif +extern void __init zone_sizes_init(void); + extern unsigned long __init kernel_physical_mapping_init(unsigned long start, unsigned long end, diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h index 74df3f1eddf..48eb30a8606 100644 --- a/arch/x86/include/asm/insn.h +++ b/arch/x86/include/asm/insn.h @@ -96,12 +96,6 @@ struct insn { #define X86_VEX_P(vex) ((vex) & 0x03) /* VEX3 Byte2, VEX2 Byte1 */ #define X86_VEX_M_MAX 0x1f /* VEX3.M Maximum value */ -/* The last prefix is needed for two-byte and three-byte opcodes */ -static inline insn_byte_t insn_last_prefix(struct insn *insn) -{ - return insn->prefixes.bytes[3]; -} - extern void insn_init(struct insn *insn, const void *kaddr, int x86_64); extern void insn_get_prefixes(struct insn *insn); extern void insn_get_opcode(struct insn *insn); @@ -160,6 +154,18 @@ static inline insn_byte_t insn_vex_p_bits(struct insn *insn) return X86_VEX_P(insn->vex_prefix.bytes[2]); } +/* Get the last prefix id from last prefix or VEX prefix */ +static inline int insn_last_prefix_id(struct insn *insn) +{ + if (insn_is_avx(insn)) + return insn_vex_p_bits(insn); /* VEX_p is a SIMD prefix id */ + + if (insn->prefixes.bytes[3]) + return inat_get_last_prefix_id(insn->prefixes.bytes[3]); + + return 0; +} + /* Offset of each field from kaddr */ static inline int insn_offset_rex_prefix(struct insn *insn) { diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 690d1cc9a87..2c4943de515 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -21,6 +21,15 @@ #define IO_APIC_REDIR_LEVEL_TRIGGER (1 << 15) #define IO_APIC_REDIR_MASKED (1 << 16) +struct io_apic_ops { + void (*init) (void); + unsigned int (*read) (unsigned int apic, unsigned int reg); + void (*write) (unsigned int apic, unsigned int reg, unsigned int value); + void (*modify)(unsigned int apic, unsigned int reg, unsigned int value); +}; + +void __init set_io_apic_ops(const struct io_apic_ops *); + /* * The structure of the IO-APIC: */ diff --git a/arch/x86/include/asm/irq_controller.h b/arch/x86/include/asm/irq_controller.h deleted file mode 100644 index 423bbbddf36..00000000000 --- a/arch/x86/include/asm/irq_controller.h +++ /dev/null @@ -1,12 +0,0 @@ -#ifndef __IRQ_CONTROLLER__ -#define __IRQ_CONTROLLER__ - -struct irq_domain { - int (*xlate)(struct irq_domain *h, const u32 *intspec, u32 intsize, - u32 *out_hwirq, u32 *out_type); - void *priv; - struct device_node *controller; - struct list_head l; -}; - -#endif diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h index a32b18ce6ea..3a16c1483b4 100644 --- a/arch/x86/include/asm/jump_label.h +++ b/arch/x86/include/asm/jump_label.h @@ -9,12 +9,12 @@ #define JUMP_LABEL_NOP_SIZE 5 -#define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t" +#define STATIC_KEY_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t" -static __always_inline bool arch_static_branch(struct jump_label_key *key) +static __always_inline bool arch_static_branch(struct static_key *key) { asm goto("1:" - JUMP_LABEL_INITIAL_NOP + STATIC_KEY_INITIAL_NOP ".pushsection __jump_table, \"aw\" \n\t" _ASM_ALIGN "\n\t" _ASM_PTR "1b, %l[l_yes], %c0 \n\t" diff --git a/arch/x86/include/asm/kgdb.h b/arch/x86/include/asm/kgdb.h index 77e95f54570..332f98c9111 100644 --- a/arch/x86/include/asm/kgdb.h +++ b/arch/x86/include/asm/kgdb.h @@ -64,11 +64,15 @@ enum regnames { GDB_PS, /* 17 */ GDB_CS, /* 18 */ GDB_SS, /* 19 */ + GDB_DS, /* 20 */ + GDB_ES, /* 21 */ + GDB_FS, /* 22 */ + GDB_GS, /* 23 */ }; #define GDB_ORIG_AX 57 -#define DBG_MAX_REG_NUM 20 -/* 17 64 bit regs and 3 32 bit regs */ -#define NUMREGBYTES ((17 * 8) + (3 * 4)) +#define DBG_MAX_REG_NUM 24 +/* 17 64 bit regs and 5 32 bit regs */ +#define NUMREGBYTES ((17 * 8) + (5 * 4)) #endif /* ! CONFIG_X86_32 */ static inline void arch_kgdb_breakpoint(void) diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index 4d8dcbdfc12..e7d1c194d27 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -321,4 +321,8 @@ struct kvm_xcrs { __u64 padding[16]; }; +/* definition of registers in kvm_run */ +struct kvm_sync_regs { +}; + #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index ab4092e3214..c222e1a1b12 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -176,6 +176,7 @@ struct x86_emulate_ops { void (*set_idt)(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt); ulong (*get_cr)(struct x86_emulate_ctxt *ctxt, int cr); int (*set_cr)(struct x86_emulate_ctxt *ctxt, int cr, ulong val); + void (*set_rflags)(struct x86_emulate_ctxt *ctxt, ulong val); int (*cpl)(struct x86_emulate_ctxt *ctxt); int (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest); int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value); @@ -190,6 +191,9 @@ struct x86_emulate_ops { int (*intercept)(struct x86_emulate_ctxt *ctxt, struct x86_instruction_info *info, enum x86_intercept_stage stage); + + bool (*get_cpuid)(struct x86_emulate_ctxt *ctxt, + u32 *eax, u32 *ebx, u32 *ecx, u32 *edx); }; typedef u32 __attribute__((vector_size(16))) sse128_t; @@ -298,6 +302,19 @@ struct x86_emulate_ctxt { #define X86EMUL_MODE_PROT (X86EMUL_MODE_PROT16|X86EMUL_MODE_PROT32| \ X86EMUL_MODE_PROT64) +/* CPUID vendors */ +#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx 0x68747541 +#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx 0x444d4163 +#define X86EMUL_CPUID_VENDOR_AuthenticAMD_edx 0x69746e65 + +#define X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx 0x69444d41 +#define X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx 0x21726574 +#define X86EMUL_CPUID_VENDOR_AMDisbetterI_edx 0x74656273 + +#define X86EMUL_CPUID_VENDOR_GenuineIntel_ebx 0x756e6547 +#define X86EMUL_CPUID_VENDOR_GenuineIntel_ecx 0x6c65746e +#define X86EMUL_CPUID_VENDOR_GenuineIntel_edx 0x49656e69 + enum x86_intercept_stage { X86_ICTP_NONE = 0, /* Allow zero-init to not match anything */ X86_ICPT_PRE_EXCEPT, @@ -372,7 +389,7 @@ bool x86_page_table_writing_insn(struct x86_emulate_ctxt *ctxt); #define EMULATION_INTERCEPTED 2 int x86_emulate_insn(struct x86_emulate_ctxt *ctxt); int emulator_task_switch(struct x86_emulate_ctxt *ctxt, - u16 tss_selector, int reason, + u16 tss_selector, int idt_index, int reason, bool has_error_code, u32 error_code); int emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq); #endif /* _ASM_X86_KVM_X86_EMULATE_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 52d6640a5ca..e216ba066e7 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -29,7 +29,7 @@ #include <asm/msr-index.h> #define KVM_MAX_VCPUS 254 -#define KVM_SOFT_MAX_VCPUS 64 +#define KVM_SOFT_MAX_VCPUS 160 #define KVM_MEMORY_SLOTS 32 /* memory slots that does not exposed to userspace */ #define KVM_PRIVATE_MEM_SLOTS 4 @@ -181,13 +181,6 @@ struct kvm_mmu_memory_cache { void *objects[KVM_NR_MEM_OBJS]; }; -#define NR_PTE_CHAIN_ENTRIES 5 - -struct kvm_pte_chain { - u64 *parent_ptes[NR_PTE_CHAIN_ENTRIES]; - struct hlist_node link; -}; - /* * kvm_mmu_page_role, below, is defined as: * @@ -427,12 +420,16 @@ struct kvm_vcpu_arch { u64 last_guest_tsc; u64 last_kernel_ns; - u64 last_tsc_nsec; - u64 last_tsc_write; - u32 virtual_tsc_khz; + u64 last_host_tsc; + u64 tsc_offset_adjustment; + u64 this_tsc_nsec; + u64 this_tsc_write; + u8 this_tsc_generation; bool tsc_catchup; - u32 tsc_catchup_mult; - s8 tsc_catchup_shift; + bool tsc_always_catchup; + s8 virtual_tsc_shift; + u32 virtual_tsc_mult; + u32 virtual_tsc_khz; atomic_t nmi_queued; /* unprocessed asynchronous NMIs */ unsigned nmi_pending; /* NMI queued after currently running handler */ @@ -478,6 +475,21 @@ struct kvm_vcpu_arch { u32 id; bool send_user_only; } apf; + + /* OSVW MSRs (AMD only) */ + struct { + u64 length; + u64 status; + } osvw; +}; + +struct kvm_lpage_info { + unsigned long rmap_pde; + int write_count; +}; + +struct kvm_arch_memory_slot { + struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1]; }; struct kvm_arch { @@ -511,8 +523,12 @@ struct kvm_arch { s64 kvmclock_offset; raw_spinlock_t tsc_write_lock; u64 last_tsc_nsec; - u64 last_tsc_offset; u64 last_tsc_write; + u32 last_tsc_khz; + u64 cur_tsc_nsec; + u64 cur_tsc_write; + u64 cur_tsc_offset; + u8 cur_tsc_generation; struct kvm_xen_hvm_config xen_hvm_config; @@ -644,7 +660,7 @@ struct kvm_x86_ops { u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio); int (*get_lpage_level)(void); bool (*rdtscp_supported)(void); - void (*adjust_tsc_offset)(struct kvm_vcpu *vcpu, s64 adjustment); + void (*adjust_tsc_offset)(struct kvm_vcpu *vcpu, s64 adjustment, bool host); void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); @@ -652,7 +668,7 @@ struct kvm_x86_ops { bool (*has_wbinvd_exit)(void); - void (*set_tsc_khz)(struct kvm_vcpu *vcpu, u32 user_tsc_khz); + void (*set_tsc_khz)(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale); void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); u64 (*compute_tsc_offset)(struct kvm_vcpu *vcpu, u64 target_tsc); @@ -674,6 +690,17 @@ 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); @@ -741,8 +768,8 @@ int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu); void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg); -int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason, - bool has_error_code, u32 error_code); +int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, + int reason, bool has_error_code, u32 error_code); int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3); diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h index 9cdae5d47e8..c8bed0da434 100644 --- a/arch/x86/include/asm/local.h +++ b/arch/x86/include/asm/local.h @@ -3,7 +3,6 @@ #include <linux/percpu.h> -#include <asm/system.h> #include <linux/atomic.h> #include <asm/asm.h> diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h index 0e8e85bb7c5..d354fb781c5 100644 --- a/arch/x86/include/asm/mc146818rtc.h +++ b/arch/x86/include/asm/mc146818rtc.h @@ -5,7 +5,6 @@ #define _ASM_X86_MC146818RTC_H #include <asm/io.h> -#include <asm/system.h> #include <asm/processor.h> #include <linux/mc146818rtc.h> diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index f35ce43c1a7..441520e4174 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -151,7 +151,7 @@ static inline void enable_p5_mce(void) {} void mce_setup(struct mce *m); void mce_log(struct mce *m); -DECLARE_PER_CPU(struct device, mce_device); +DECLARE_PER_CPU(struct device *, mce_device); /* * Maximum banks number. diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h index 0a0a9546043..fc18bf3ce7c 100644 --- a/arch/x86/include/asm/mrst.h +++ b/arch/x86/include/asm/mrst.h @@ -26,8 +26,8 @@ extern struct sfi_rtc_table_entry sfi_mrtc_array[]; * identified via MSRs. */ enum mrst_cpu_type { - MRST_CPU_CHIP_LINCROFT = 1, - MRST_CPU_CHIP_PENWELL, + /* 1 was Moorestown */ + MRST_CPU_CHIP_PENWELL = 2, }; extern enum mrst_cpu_type __mrst_cpu_chip; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index a6962d9161a..ccb805966f6 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -56,6 +56,13 @@ #define MSR_OFFCORE_RSP_0 0x000001a6 #define MSR_OFFCORE_RSP_1 0x000001a7 +#define MSR_LBR_SELECT 0x000001c8 +#define MSR_LBR_TOS 0x000001c9 +#define MSR_LBR_NHM_FROM 0x00000680 +#define MSR_LBR_NHM_TO 0x000006c0 +#define MSR_LBR_CORE_FROM 0x00000040 +#define MSR_LBR_CORE_TO 0x00000060 + #define MSR_IA32_PEBS_ENABLE 0x000003f1 #define MSR_IA32_DS_AREA 0x00000600 #define MSR_IA32_PERF_CAPABILITIES 0x00000345 diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h index 4365ffdb461..7e3f17f92c6 100644 --- a/arch/x86/include/asm/mtrr.h +++ b/arch/x86/include/asm/mtrr.h @@ -29,18 +29,18 @@ #define MTRR_IOCTL_BASE 'M' -struct mtrr_sentry { - unsigned long base; /* Base address */ - unsigned int size; /* Size of region */ - unsigned int type; /* Type of region */ -}; - /* Warning: this structure has a different order from i386 on x86-64. The 32bit emulation code takes care of that. But you need to use this for 64bit, otherwise your X server will break. */ #ifdef __i386__ +struct mtrr_sentry { + unsigned long base; /* Base address */ + unsigned int size; /* Size of region */ + unsigned int type; /* Type of region */ +}; + struct mtrr_gentry { unsigned int regnum; /* Register number */ unsigned long base; /* Base address */ @@ -50,12 +50,20 @@ struct mtrr_gentry { #else /* __i386__ */ +struct mtrr_sentry { + __u64 base; /* Base address */ + __u32 size; /* Size of region */ + __u32 type; /* Type of region */ +}; + struct mtrr_gentry { - unsigned long base; /* Base address */ - unsigned int size; /* Size of region */ - unsigned int regnum; /* Register number */ - unsigned int type; /* Type of region */ + __u64 base; /* Base address */ + __u32 size; /* Size of region */ + __u32 regnum; /* Register number */ + __u32 type; /* Type of region */ + __u32 _pad; /* Unused */ }; + #endif /* !__i386__ */ struct mtrr_var_range { diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index bce688d54c1..e21fdd10479 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -55,7 +55,6 @@ extern unsigned long init_memory_mapping(unsigned long start, unsigned long end); extern void initmem_init(void); -extern void free_initmem(void); #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index a7d2db9a74f..aa0f9130836 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -10,6 +10,7 @@ #include <asm/paravirt_types.h> #ifndef __ASSEMBLY__ +#include <linux/bug.h> #include <linux/types.h> #include <linux/cpumask.h> @@ -230,9 +231,9 @@ static inline unsigned long long paravirt_sched_clock(void) return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock); } -struct jump_label_key; -extern struct jump_label_key paravirt_steal_enabled; -extern struct jump_label_key paravirt_steal_rq_enabled; +struct static_key; +extern struct static_key paravirt_steal_enabled; +extern struct static_key paravirt_steal_rq_enabled; static inline u64 paravirt_steal_clock(int cpu) { diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 096c975e099..2291895b183 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -23,6 +23,7 @@ #define ARCH_PERFMON_EVENTSEL_USR (1ULL << 16) #define ARCH_PERFMON_EVENTSEL_OS (1ULL << 17) #define ARCH_PERFMON_EVENTSEL_EDGE (1ULL << 18) +#define ARCH_PERFMON_EVENTSEL_PIN_CONTROL (1ULL << 19) #define ARCH_PERFMON_EVENTSEL_INT (1ULL << 20) #define ARCH_PERFMON_EVENTSEL_ANY (1ULL << 21) #define ARCH_PERFMON_EVENTSEL_ENABLE (1ULL << 22) @@ -188,8 +189,6 @@ extern u32 get_ibs_caps(void); #ifdef CONFIG_PERF_EVENTS extern void perf_events_lapic_init(void); -#define PERF_EVENT_INDEX_OFFSET 0 - /* * Abuse bit 3 of the cpu eflags register to indicate proper PEBS IP fixups. * This flag is otherwise unused and ABI specified to be 0, so nobody should @@ -242,4 +241,12 @@ static inline void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap) static inline void perf_events_lapic_init(void) { } #endif +#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD) + extern void amd_pmu_enable_virt(void); + extern void amd_pmu_disable_virt(void); +#else + static inline void amd_pmu_enable_virt(void) { } + static inline void amd_pmu_disable_virt(void) { } +#endif + #endif /* _ASM_X86_PERF_EVENT_H */ diff --git a/arch/x86/include/asm/posix_types.h b/arch/x86/include/asm/posix_types.h index bb7133dc155..3427b7798db 100644 --- a/arch/x86/include/asm/posix_types.h +++ b/arch/x86/include/asm/posix_types.h @@ -7,7 +7,9 @@ #else # ifdef __i386__ # include "posix_types_32.h" -# else +# elif defined(__LP64__) # include "posix_types_64.h" +# else +# include "posix_types_x32.h" # endif #endif diff --git a/arch/x86/include/asm/posix_types_32.h b/arch/x86/include/asm/posix_types_32.h index f7d9adf82e5..99f262e04b9 100644 --- a/arch/x86/include/asm/posix_types_32.h +++ b/arch/x86/include/asm/posix_types_32.h @@ -7,79 +7,22 @@ * assume GCC is being used. */ -typedef unsigned long __kernel_ino_t; typedef unsigned short __kernel_mode_t; +#define __kernel_mode_t __kernel_mode_t + typedef unsigned short __kernel_nlink_t; -typedef long __kernel_off_t; -typedef int __kernel_pid_t; +#define __kernel_nlink_t __kernel_nlink_t + typedef unsigned short __kernel_ipc_pid_t; +#define __kernel_ipc_pid_t __kernel_ipc_pid_t + typedef unsigned short __kernel_uid_t; typedef unsigned short __kernel_gid_t; -typedef unsigned int __kernel_size_t; -typedef int __kernel_ssize_t; -typedef int __kernel_ptrdiff_t; -typedef long __kernel_time_t; -typedef long __kernel_suseconds_t; -typedef long __kernel_clock_t; -typedef int __kernel_timer_t; -typedef int __kernel_clockid_t; -typedef int __kernel_daddr_t; -typedef char * __kernel_caddr_t; -typedef unsigned short __kernel_uid16_t; -typedef unsigned short __kernel_gid16_t; -typedef unsigned int __kernel_uid32_t; -typedef unsigned int __kernel_gid32_t; +#define __kernel_uid_t __kernel_uid_t -typedef unsigned short __kernel_old_uid_t; -typedef unsigned short __kernel_old_gid_t; typedef unsigned short __kernel_old_dev_t; +#define __kernel_old_dev_t __kernel_old_dev_t -#ifdef __GNUC__ -typedef long long __kernel_loff_t; -#endif - -typedef struct { - int val[2]; -} __kernel_fsid_t; - -#if defined(__KERNEL__) - -#undef __FD_SET -#define __FD_SET(fd,fdsetp) \ - asm volatile("btsl %1,%0": \ - "+m" (*(__kernel_fd_set *)(fdsetp)) \ - : "r" ((int)(fd))) - -#undef __FD_CLR -#define __FD_CLR(fd,fdsetp) \ - asm volatile("btrl %1,%0": \ - "+m" (*(__kernel_fd_set *)(fdsetp)) \ - : "r" ((int) (fd))) - -#undef __FD_ISSET -#define __FD_ISSET(fd,fdsetp) \ - (__extension__ \ - ({ \ - unsigned char __result; \ - asm volatile("btl %1,%2 ; setb %0" \ - : "=q" (__result) \ - : "r" ((int)(fd)), \ - "m" (*(__kernel_fd_set *)(fdsetp))); \ - __result; \ -})) - -#undef __FD_ZERO -#define __FD_ZERO(fdsetp) \ -do { \ - int __d0, __d1; \ - asm volatile("cld ; rep ; stosl" \ - : "=m" (*(__kernel_fd_set *)(fdsetp)), \ - "=&c" (__d0), "=&D" (__d1) \ - : "a" (0), "1" (__FDSET_LONGS), \ - "2" ((__kernel_fd_set *)(fdsetp)) \ - : "memory"); \ -} while (0) - -#endif /* defined(__KERNEL__) */ +#include <asm-generic/posix_types.h> #endif /* _ASM_X86_POSIX_TYPES_32_H */ diff --git a/arch/x86/include/asm/posix_types_64.h b/arch/x86/include/asm/posix_types_64.h index eb8d2d92b63..cba0c1ead16 100644 --- a/arch/x86/include/asm/posix_types_64.h +++ b/arch/x86/include/asm/posix_types_64.h @@ -7,113 +7,13 @@ * assume GCC is being used. */ -typedef unsigned long __kernel_ino_t; -typedef unsigned int __kernel_mode_t; -typedef unsigned long __kernel_nlink_t; -typedef long __kernel_off_t; -typedef int __kernel_pid_t; -typedef int __kernel_ipc_pid_t; -typedef unsigned int __kernel_uid_t; -typedef unsigned int __kernel_gid_t; -typedef unsigned long __kernel_size_t; -typedef long __kernel_ssize_t; -typedef long __kernel_ptrdiff_t; -typedef long __kernel_time_t; -typedef long __kernel_suseconds_t; -typedef long __kernel_clock_t; -typedef int __kernel_timer_t; -typedef int __kernel_clockid_t; -typedef int __kernel_daddr_t; -typedef char * __kernel_caddr_t; -typedef unsigned short __kernel_uid16_t; -typedef unsigned short __kernel_gid16_t; - -#ifdef __GNUC__ -typedef long long __kernel_loff_t; -#endif - -typedef struct { - int val[2]; -} __kernel_fsid_t; - typedef unsigned short __kernel_old_uid_t; typedef unsigned short __kernel_old_gid_t; -typedef __kernel_uid_t __kernel_uid32_t; -typedef __kernel_gid_t __kernel_gid32_t; +#define __kernel_old_uid_t __kernel_old_uid_t typedef unsigned long __kernel_old_dev_t; +#define __kernel_old_dev_t __kernel_old_dev_t -#ifdef __KERNEL__ - -#undef __FD_SET -static inline void __FD_SET(unsigned long fd, __kernel_fd_set *fdsetp) -{ - unsigned long _tmp = fd / __NFDBITS; - unsigned long _rem = fd % __NFDBITS; - fdsetp->fds_bits[_tmp] |= (1UL<<_rem); -} - -#undef __FD_CLR -static inline void __FD_CLR(unsigned long fd, __kernel_fd_set *fdsetp) -{ - unsigned long _tmp = fd / __NFDBITS; - unsigned long _rem = fd % __NFDBITS; - fdsetp->fds_bits[_tmp] &= ~(1UL<<_rem); -} - -#undef __FD_ISSET -static inline int __FD_ISSET(unsigned long fd, __const__ __kernel_fd_set *p) -{ - unsigned long _tmp = fd / __NFDBITS; - unsigned long _rem = fd % __NFDBITS; - return (p->fds_bits[_tmp] & (1UL<<_rem)) != 0; -} - -/* - * This will unroll the loop for the normal constant cases (8 or 32 longs, - * for 256 and 1024-bit fd_sets respectively) - */ -#undef __FD_ZERO -static inline void __FD_ZERO(__kernel_fd_set *p) -{ - unsigned long *tmp = p->fds_bits; - int i; - - if (__builtin_constant_p(__FDSET_LONGS)) { - switch (__FDSET_LONGS) { - case 32: - tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0; - tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0; - tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0; - tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0; - tmp[16] = 0; tmp[17] = 0; tmp[18] = 0; tmp[19] = 0; - tmp[20] = 0; tmp[21] = 0; tmp[22] = 0; tmp[23] = 0; - tmp[24] = 0; tmp[25] = 0; tmp[26] = 0; tmp[27] = 0; - tmp[28] = 0; tmp[29] = 0; tmp[30] = 0; tmp[31] = 0; - return; - case 16: - tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0; - tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0; - tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0; - tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0; - return; - case 8: - tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0; - tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0; - return; - case 4: - tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0; - return; - } - } - i = __FDSET_LONGS; - while (i) { - i--; - *tmp = 0; - tmp++; - } -} - -#endif /* defined(__KERNEL__) */ +#include <asm-generic/posix_types.h> #endif /* _ASM_X86_POSIX_TYPES_64_H */ diff --git a/arch/x86/include/asm/posix_types_x32.h b/arch/x86/include/asm/posix_types_x32.h new file mode 100644 index 00000000000..85f9bdafa93 --- /dev/null +++ b/arch/x86/include/asm/posix_types_x32.h @@ -0,0 +1,19 @@ +#ifndef _ASM_X86_POSIX_TYPES_X32_H +#define _ASM_X86_POSIX_TYPES_X32_H + +/* + * This file is only used by user-level software, so you need to + * be a little careful about namespace pollution etc. Also, we cannot + * assume GCC is being used. + * + * These types should generally match the ones used by the 64-bit kernel, + * + */ + +typedef long long __kernel_long_t; +typedef unsigned long long __kernel_ulong_t; +#define __kernel_long_t __kernel_long_t + +#include <asm/posix_types_64.h> + +#endif /* _ASM_X86_POSIX_TYPES_X32_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index aa9088c2693..4fa7dcceb6c 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -14,13 +14,13 @@ struct mm_struct; #include <asm/sigcontext.h> #include <asm/current.h> #include <asm/cpufeature.h> -#include <asm/system.h> #include <asm/page.h> #include <asm/pgtable_types.h> #include <asm/percpu.h> #include <asm/msr.h> #include <asm/desc_defs.h> #include <asm/nops.h> +#include <asm/special_insns.h> #include <linux/personality.h> #include <linux/cpumask.h> @@ -29,6 +29,15 @@ struct mm_struct; #include <linux/math64.h> #include <linux/init.h> #include <linux/err.h> +#include <linux/irqflags.h> + +/* + * We handle most unaligned accesses in hardware. On the other hand + * unaligned DMA can be quite expensive on some Nehalem processors. + * + * Based on this we disable the IP header alignment in network drivers. + */ +#define NET_IP_ALIGN 0 #define HBP_NUM 4 /* @@ -162,6 +171,7 @@ extern void early_cpu_init(void); extern void identify_boot_cpu(void); extern void identify_secondary_cpu(struct cpuinfo_x86 *); extern void print_cpu_info(struct cpuinfo_x86 *); +void print_cpu_msr(struct cpuinfo_x86 *); extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c); extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c); extern unsigned short num_cache_leaves; @@ -374,6 +384,8 @@ union thread_xstate { }; struct fpu { + unsigned int last_cpu; + unsigned int has_fpu; union thread_xstate *state; }; @@ -451,7 +463,7 @@ struct thread_struct { unsigned long ptrace_dr7; /* Fault info: */ unsigned long cr2; - unsigned long trap_no; + unsigned long trap_nr; unsigned long error_code; /* floating point and extended processor state */ struct fpu fpu; @@ -472,61 +484,6 @@ struct thread_struct { unsigned io_bitmap_max; }; -static inline unsigned long native_get_debugreg(int regno) -{ - unsigned long val = 0; /* Damn you, gcc! */ - - switch (regno) { - case 0: - asm("mov %%db0, %0" :"=r" (val)); - break; - case 1: - asm("mov %%db1, %0" :"=r" (val)); - break; - case 2: - asm("mov %%db2, %0" :"=r" (val)); - break; - case 3: - asm("mov %%db3, %0" :"=r" (val)); - break; - case 6: - asm("mov %%db6, %0" :"=r" (val)); - break; - case 7: - asm("mov %%db7, %0" :"=r" (val)); - break; - default: - BUG(); - } - return val; -} - -static inline void native_set_debugreg(int regno, unsigned long value) -{ - switch (regno) { - case 0: - asm("mov %0, %%db0" ::"r" (value)); - break; - case 1: - asm("mov %0, %%db1" ::"r" (value)); - break; - case 2: - asm("mov %0, %%db2" ::"r" (value)); - break; - case 3: - asm("mov %0, %%db3" ::"r" (value)); - break; - case 6: - asm("mov %0, %%db6" ::"r" (value)); - break; - case 7: - asm("mov %0, %%db7" ::"r" (value)); - break; - default: - BUG(); - } -} - /* * Set IOPL bits in EFLAGS from given mask */ @@ -572,14 +529,6 @@ static inline void native_swapgs(void) #define __cpuid native_cpuid #define paravirt_enabled() 0 -/* - * These special macros can be used to get or set a debugging register - */ -#define get_debugreg(var, register) \ - (var) = native_get_debugreg(register) -#define set_debugreg(value, register) \ - native_set_debugreg(register, value) - static inline void load_sp0(struct tss_struct *tss, struct thread_struct *thread) { @@ -924,9 +873,9 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk); #define IA32_PAGE_OFFSET ((current->personality & ADDR_LIMIT_3GB) ? \ 0xc0000000 : 0xFFFFe000) -#define TASK_SIZE (test_thread_flag(TIF_IA32) ? \ +#define TASK_SIZE (test_thread_flag(TIF_ADDR32) ? \ IA32_PAGE_OFFSET : TASK_SIZE_MAX) -#define TASK_SIZE_OF(child) ((test_tsk_thread_flag(child, TIF_IA32)) ? \ +#define TASK_SIZE_OF(child) ((test_tsk_thread_flag(child, TIF_ADDR32)) ? \ IA32_PAGE_OFFSET : TASK_SIZE_MAX) #define STACK_TOP TASK_SIZE @@ -948,6 +897,12 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk); #define task_pt_regs(tsk) ((struct pt_regs *)(tsk)->thread.sp0 - 1) extern unsigned long KSTK_ESP(struct task_struct *task); + +/* + * User space RSP while inside the SYSCALL fast path + */ +DECLARE_PER_CPU(unsigned long, old_rsp); + #endif /* CONFIG_X86_64 */ extern void start_thread(struct pt_regs *regs, unsigned long new_ip, @@ -1019,4 +974,14 @@ extern bool cpu_has_amd_erratum(const int *); #define cpu_has_amd_erratum(x) (false) #endif /* CONFIG_CPU_SUP_AMD */ +void cpu_idle_wait(void); + +extern unsigned long arch_align_stack(unsigned long sp); +extern void free_init_pages(char *what, unsigned long begin, unsigned long end); + +void default_idle(void); +bool set_pm_idle_to_default(void); + +void stop_this_cpu(void *dummy); + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h index 644dd885f05..60bef663609 100644 --- a/arch/x86/include/asm/prom.h +++ b/arch/x86/include/asm/prom.h @@ -21,7 +21,6 @@ #include <asm/irq.h> #include <linux/atomic.h> #include <asm/setup.h> -#include <asm/irq_controller.h> #ifdef CONFIG_OF extern int of_ioapic; @@ -43,15 +42,6 @@ extern char cmd_line[COMMAND_LINE_SIZE]; #define pci_address_to_pio pci_address_to_pio unsigned long pci_address_to_pio(phys_addr_t addr); -/** - * irq_dispose_mapping - Unmap an interrupt - * @virq: linux virq number of the interrupt to unmap - * - * FIXME: We really should implement proper virq handling like power, - * but that's going to be major surgery. - */ -static inline void irq_dispose_mapping(unsigned int virq) { } - #define HAVE_ARCH_DEVTREE_FIXUPS #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 35664547125..dcfde52979c 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -145,7 +145,6 @@ extern unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs); extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code, int si_code); -void signal_fault(struct pt_regs *regs, void __user *frame, char *where); extern long syscall_trace_enter(struct pt_regs *); extern void syscall_trace_leave(struct pt_regs *); diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 5e641715c3f..165466233ab 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -212,7 +212,61 @@ #ifdef __KERNEL__ #ifndef __ASSEMBLY__ extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][10]; -#endif -#endif + +/* + * Load a segment. Fall back on loading the zero + * segment if something goes wrong.. + */ +#define loadsegment(seg, value) \ +do { \ + unsigned short __val = (value); \ + \ + asm volatile(" \n" \ + "1: movl %k0,%%" #seg " \n" \ + \ + ".section .fixup,\"ax\" \n" \ + "2: xorl %k0,%k0 \n" \ + " jmp 1b \n" \ + ".previous \n" \ + \ + _ASM_EXTABLE(1b, 2b) \ + \ + : "+r" (__val) : : "memory"); \ +} while (0) + +/* + * Save a segment register away + */ +#define savesegment(seg, value) \ + asm("mov %%" #seg ",%0":"=r" (value) : : "memory") + +/* + * x86_32 user gs accessors. + */ +#ifdef CONFIG_X86_32 +#ifdef CONFIG_X86_32_LAZY_GS +#define get_user_gs(regs) (u16)({unsigned long v; savesegment(gs, v); v;}) +#define set_user_gs(regs, v) loadsegment(gs, (unsigned long)(v)) +#define task_user_gs(tsk) ((tsk)->thread.gs) +#define lazy_save_gs(v) savesegment(gs, (v)) +#define lazy_load_gs(v) loadsegment(gs, (v)) +#else /* X86_32_LAZY_GS */ +#define get_user_gs(regs) (u16)((regs)->gs) +#define set_user_gs(regs, v) do { (regs)->gs = (v); } while (0) +#define task_user_gs(tsk) (task_pt_regs(tsk)->gs) +#define lazy_save_gs(v) do { } while (0) +#define lazy_load_gs(v) do { } while (0) +#endif /* X86_32_LAZY_GS */ +#endif /* X86_32 */ + +static inline unsigned long get_limit(unsigned long segment) +{ + unsigned long __limit; + asm("lsll %1,%0" : "=r" (__limit) : "r" (segment)); + return __limit + 1; +} + +#endif /* !__ASSEMBLY__ */ +#endif /* __KERNEL__ */ #endif /* _ASM_X86_SEGMENT_H */ diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 9756551ec76..d0f19f9fb84 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -47,7 +47,7 @@ extern void reserve_standard_io_resources(void); extern void i386_reserve_resources(void); extern void setup_default_timer_irq(void); -#ifdef CONFIG_X86_MRST +#ifdef CONFIG_X86_INTEL_MID extern void x86_mrst_early_setup(void); #else static inline void x86_mrst_early_setup(void) { } diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h index 04459d25e66..4a085383af2 100644 --- a/arch/x86/include/asm/sigcontext.h +++ b/arch/x86/include/asm/sigcontext.h @@ -230,34 +230,37 @@ struct sigcontext { * User-space might still rely on the old definition: */ 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 rdi; - unsigned long rsi; - unsigned long rbp; - unsigned long rbx; - unsigned long rdx; - unsigned long rax; - unsigned long rcx; - unsigned long rsp; - unsigned long rip; - unsigned long eflags; /* RFLAGS */ - unsigned short cs; - unsigned short gs; - unsigned short fs; - unsigned short __pad0; - unsigned long err; - unsigned long trapno; - unsigned long oldmask; - unsigned long cr2; + __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 */ - unsigned long reserved1[8]; +#ifndef __LP64__ + __u32 __fpstate_pad; +#endif + __u64 reserved1[8]; }; #endif /* !__KERNEL__ */ diff --git a/arch/x86/include/asm/sigframe.h b/arch/x86/include/asm/sigframe.h index 4e0fe26d27d..7c7c27c97da 100644 --- a/arch/x86/include/asm/sigframe.h +++ b/arch/x86/include/asm/sigframe.h @@ -59,12 +59,25 @@ struct rt_sigframe_ia32 { #endif /* defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) */ #ifdef CONFIG_X86_64 + struct rt_sigframe { char __user *pretcode; struct ucontext uc; struct siginfo info; /* fp state follows here */ }; + +#ifdef CONFIG_X86_X32_ABI + +struct rt_sigframe_x32 { + u64 pretcode; + struct ucontext_x32 uc; + compat_siginfo_t info; + /* fp state follows here */ +}; + +#endif /* CONFIG_X86_X32_ABI */ + #endif /* CONFIG_X86_64 */ #endif /* _ASM_X86_SIGFRAME_H */ diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h new file mode 100644 index 00000000000..ada93b3b8c6 --- /dev/null +++ b/arch/x86/include/asm/sighandling.h @@ -0,0 +1,24 @@ +#ifndef _ASM_X86_SIGHANDLING_H +#define _ASM_X86_SIGHANDLING_H + +#include <linux/compiler.h> +#include <linux/ptrace.h> +#include <linux/signal.h> + +#include <asm/processor-flags.h> + +#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) + +#define __FIX_EFLAGS (X86_EFLAGS_AC | X86_EFLAGS_OF | \ + X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \ + X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \ + X86_EFLAGS_CF) + +void signal_fault(struct pt_regs *regs, void __user *frame, char *where); + +int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, + unsigned long *pax); +int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, + struct pt_regs *regs, unsigned long mask); + +#endif /* _ASM_X86_SIGHANDLING_H */ diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 73b11bc0ae6..0434c400287 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -225,5 +225,11 @@ extern int hard_smp_processor_id(void); #endif /* CONFIG_X86_LOCAL_APIC */ +#ifdef CONFIG_DEBUG_NMI_SELFTEST +extern void nmi_selftest(void); +#else +#define nmi_selftest() do { } while (0) +#endif + #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_SMP_H */ diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h new file mode 100644 index 00000000000..41fc93a2e22 --- /dev/null +++ b/arch/x86/include/asm/special_insns.h @@ -0,0 +1,199 @@ +#ifndef _ASM_X86_SPECIAL_INSNS_H +#define _ASM_X86_SPECIAL_INSNS_H + + +#ifdef __KERNEL__ + +static inline void native_clts(void) +{ + asm volatile("clts"); +} + +/* + * Volatile isn't enough to prevent the compiler from reordering the + * read/write functions for the control registers and messing everything up. + * A memory clobber would solve the problem, but would prevent reordering of + * all loads stores around it, which can hurt performance. Solution is to + * use a variable and mimic reads and writes to it to enforce serialization + */ +static unsigned long __force_order; + +static inline unsigned long native_read_cr0(void) +{ + unsigned long val; + asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order)); + return val; +} + +static inline void native_write_cr0(unsigned long val) +{ + asm volatile("mov %0,%%cr0": : "r" (val), "m" (__force_order)); +} + +static inline unsigned long native_read_cr2(void) +{ + unsigned long val; + asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order)); + return val; +} + +static inline void native_write_cr2(unsigned long val) +{ + asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order)); +} + +static inline unsigned long native_read_cr3(void) +{ + unsigned long val; + asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order)); + return val; +} + +static inline void native_write_cr3(unsigned long val) +{ + asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order)); +} + +static inline unsigned long native_read_cr4(void) +{ + unsigned long val; + asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order)); + return val; +} + +static inline unsigned long native_read_cr4_safe(void) +{ + unsigned long val; + /* This could fault if %cr4 does not exist. In x86_64, a cr4 always + * exists, so it will never fail. */ +#ifdef CONFIG_X86_32 + asm volatile("1: mov %%cr4, %0\n" + "2:\n" + _ASM_EXTABLE(1b, 2b) + : "=r" (val), "=m" (__force_order) : "0" (0)); +#else + val = native_read_cr4(); +#endif + return val; +} + +static inline void native_write_cr4(unsigned long val) +{ + asm volatile("mov %0,%%cr4": : "r" (val), "m" (__force_order)); +} + +#ifdef CONFIG_X86_64 +static inline unsigned long native_read_cr8(void) +{ + unsigned long cr8; + asm volatile("movq %%cr8,%0" : "=r" (cr8)); + return cr8; +} + +static inline void native_write_cr8(unsigned long val) +{ + asm volatile("movq %0,%%cr8" :: "r" (val) : "memory"); +} +#endif + +static inline void native_wbinvd(void) +{ + asm volatile("wbinvd": : :"memory"); +} + +extern void native_load_gs_index(unsigned); + +#ifdef CONFIG_PARAVIRT +#include <asm/paravirt.h> +#else + +static inline unsigned long read_cr0(void) +{ + return native_read_cr0(); +} + +static inline void write_cr0(unsigned long x) +{ + native_write_cr0(x); +} + +static inline unsigned long read_cr2(void) +{ + return native_read_cr2(); +} + +static inline void write_cr2(unsigned long x) +{ + native_write_cr2(x); +} + +static inline unsigned long read_cr3(void) +{ + return native_read_cr3(); +} + +static inline void write_cr3(unsigned long x) +{ + native_write_cr3(x); +} + +static inline unsigned long read_cr4(void) +{ + return native_read_cr4(); +} + +static inline unsigned long read_cr4_safe(void) +{ + return native_read_cr4_safe(); +} + +static inline void write_cr4(unsigned long x) +{ + native_write_cr4(x); +} + +static inline void wbinvd(void) +{ + native_wbinvd(); +} + +#ifdef CONFIG_X86_64 + +static inline unsigned long read_cr8(void) +{ + return native_read_cr8(); +} + +static inline void write_cr8(unsigned long x) +{ + native_write_cr8(x); +} + +static inline void load_gs_index(unsigned selector) +{ + native_load_gs_index(selector); +} + +#endif + +/* Clear the 'TS' bit */ +static inline void clts(void) +{ + native_clts(); +} + +#endif/* CONFIG_PARAVIRT */ + +#define stts() write_cr0(read_cr0() | X86_CR0_TS) + +static inline void clflush(volatile void *__p) +{ + asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p)); +} + +#define nop() asm volatile ("nop") + + +#endif /* __KERNEL__ */ + +#endif /* _ASM_X86_SPECIAL_INSNS_H */ diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index a82c2bf504b..76bfa2cf301 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -88,14 +88,14 @@ static inline int __ticket_spin_is_locked(arch_spinlock_t *lock) { struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets); - return !!(tmp.tail ^ tmp.head); + return tmp.tail != tmp.head; } static inline int __ticket_spin_is_contended(arch_spinlock_t *lock) { struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets); - return ((tmp.tail - tmp.head) & TICKET_MASK) > 1; + return (__ticket_t)(tmp.tail - tmp.head) > 1; } #ifndef CONFIG_PARAVIRT_SPINLOCKS diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h index 8ebd5df7451..ad0ad07fc00 100644 --- a/arch/x86/include/asm/spinlock_types.h +++ b/arch/x86/include/asm/spinlock_types.h @@ -16,7 +16,6 @@ typedef u32 __ticketpair_t; #endif #define TICKET_SHIFT (sizeof(__ticket_t) * 8) -#define TICKET_MASK ((__ticket_t)((1 << TICKET_SHIFT) - 1)) typedef struct arch_spinlock { union { diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index 15751776356..b5d9533d2c3 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -38,7 +38,6 @@ #include <asm/tsc.h> #include <asm/processor.h> #include <asm/percpu.h> -#include <asm/system.h> #include <asm/desc.h> #include <linux/random.h> diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h new file mode 100644 index 00000000000..4ec45b3abba --- /dev/null +++ b/arch/x86/include/asm/switch_to.h @@ -0,0 +1,129 @@ +#ifndef _ASM_X86_SWITCH_TO_H +#define _ASM_X86_SWITCH_TO_H + +struct task_struct; /* one of the stranger aspects of C forward declarations */ +struct task_struct *__switch_to(struct task_struct *prev, + struct task_struct *next); +struct tss_struct; +void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, + struct tss_struct *tss); + +#ifdef CONFIG_X86_32 + +#ifdef CONFIG_CC_STACKPROTECTOR +#define __switch_canary \ + "movl %P[task_canary](%[next]), %%ebx\n\t" \ + "movl %%ebx, "__percpu_arg([stack_canary])"\n\t" +#define __switch_canary_oparam \ + , [stack_canary] "=m" (stack_canary.canary) +#define __switch_canary_iparam \ + , [task_canary] "i" (offsetof(struct task_struct, stack_canary)) +#else /* CC_STACKPROTECTOR */ +#define __switch_canary +#define __switch_canary_oparam +#define __switch_canary_iparam +#endif /* CC_STACKPROTECTOR */ + +/* + * Saving eflags is important. It switches not only IOPL between tasks, + * it also protects other tasks from NT leaking through sysenter etc. + */ +#define switch_to(prev, next, last) \ +do { \ + /* \ + * Context-switching clobbers all registers, so we clobber \ + * them explicitly, via unused output variables. \ + * (EAX and EBP is not listed because EBP is saved/restored \ + * explicitly for wchan access and EAX is the return value of \ + * __switch_to()) \ + */ \ + unsigned long ebx, ecx, edx, esi, edi; \ + \ + asm volatile("pushfl\n\t" /* save flags */ \ + "pushl %%ebp\n\t" /* save EBP */ \ + "movl %%esp,%[prev_sp]\n\t" /* save ESP */ \ + "movl %[next_sp],%%esp\n\t" /* restore ESP */ \ + "movl $1f,%[prev_ip]\n\t" /* save EIP */ \ + "pushl %[next_ip]\n\t" /* restore EIP */ \ + __switch_canary \ + "jmp __switch_to\n" /* regparm call */ \ + "1:\t" \ + "popl %%ebp\n\t" /* restore EBP */ \ + "popfl\n" /* restore flags */ \ + \ + /* output parameters */ \ + : [prev_sp] "=m" (prev->thread.sp), \ + [prev_ip] "=m" (prev->thread.ip), \ + "=a" (last), \ + \ + /* clobbered output registers: */ \ + "=b" (ebx), "=c" (ecx), "=d" (edx), \ + "=S" (esi), "=D" (edi) \ + \ + __switch_canary_oparam \ + \ + /* input parameters: */ \ + : [next_sp] "m" (next->thread.sp), \ + [next_ip] "m" (next->thread.ip), \ + \ + /* regparm parameters for __switch_to(): */ \ + [prev] "a" (prev), \ + [next] "d" (next) \ + \ + __switch_canary_iparam \ + \ + : /* reloaded segment registers */ \ + "memory"); \ +} while (0) + +#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 __EXTRA_CLOBBER \ + , "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \ + "r12", "r13", "r14", "r15" + +#ifdef CONFIG_CC_STACKPROTECTOR +#define __switch_canary \ + "movq %P[task_canary](%%rsi),%%r8\n\t" \ + "movq %%r8,"__percpu_arg([gs_canary])"\n\t" +#define __switch_canary_oparam \ + , [gs_canary] "=m" (irq_stack_union.stack_canary) +#define __switch_canary_iparam \ + , [task_canary] "i" (offsetof(struct task_struct, stack_canary)) +#else /* CC_STACKPROTECTOR */ +#define __switch_canary +#define __switch_canary_oparam +#define __switch_canary_iparam +#endif /* CC_STACKPROTECTOR */ + +/* Save restore flags to clear handle leaking NT */ +#define switch_to(prev, next, last) \ + asm volatile(SAVE_CONTEXT \ + "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \ + "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */ \ + "call __switch_to\n\t" \ + "movq "__percpu_arg([current_task])",%%rsi\n\t" \ + __switch_canary \ + "movq %P[thread_info](%%rsi),%%r8\n\t" \ + "movq %%rax,%%rdi\n\t" \ + "testl %[_tif_fork],%P[ti_flags](%%r8)\n\t" \ + "jnz ret_from_fork\n\t" \ + RESTORE_CONTEXT \ + : "=a" (last) \ + __switch_canary_oparam \ + : [next] "S" (next), [prev] "D" (prev), \ + [threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \ + [ti_flags] "i" (offsetof(struct thread_info, flags)), \ + [_tif_fork] "i" (_TIF_FORK), \ + [thread_info] "i" (offsetof(struct task_struct, stack)), \ + [current_task] "m" (current_task) \ + __switch_canary_iparam \ + : "memory", "cc" __EXTRA_CLOBBER) + +#endif /* CONFIG_X86_32 */ + +#endif /* _ASM_X86_SWITCH_TO_H */ diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index cb238526a9f..3fda9db4881 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -10,6 +10,8 @@ #ifndef _ASM_X86_SYS_IA32_H #define _ASM_X86_SYS_IA32_H +#ifdef CONFIG_COMPAT + #include <linux/compiler.h> #include <linux/linkage.h> #include <linux/types.h> @@ -36,8 +38,6 @@ asmlinkage long sys32_rt_sigaction(int, struct sigaction32 __user *, struct sigaction32 __user *, unsigned int); asmlinkage long sys32_sigaction(int, struct old_sigaction32 __user *, struct old_sigaction32 __user *); -asmlinkage long sys32_rt_sigprocmask(int, compat_sigset_t __user *, - compat_sigset_t __user *, unsigned int); asmlinkage long sys32_alarm(unsigned int); asmlinkage long sys32_waitpid(compat_pid_t, unsigned int *, int); @@ -83,4 +83,7 @@ asmlinkage long sys32_ipc(u32, int, int, int, compat_uptr_t, u32); asmlinkage long sys32_fanotify_mark(int, unsigned int, u32, u32, int, const char __user *); + +#endif /* CONFIG_COMPAT */ + #endif /* _ASM_X86_SYS_IA32_H */ diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index c4a348f7bd4..386b78686c4 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -15,6 +15,8 @@ #include <linux/sched.h> #include <linux/err.h> +#include <asm/asm-offsets.h> /* For NR_syscalls */ +#include <asm/unistd.h> extern const unsigned long sys_call_table[]; @@ -25,13 +27,13 @@ extern const unsigned long sys_call_table[]; */ static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs) { - return regs->orig_ax; + return regs->orig_ax & __SYSCALL_MASK; } static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { - regs->ax = regs->orig_ax; + regs->ax = regs->orig_ax & __SYSCALL_MASK; } static inline long syscall_get_error(struct task_struct *task, diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h deleted file mode 100644 index 2d2f01ce6dc..00000000000 --- a/arch/x86/include/asm/system.h +++ /dev/null @@ -1,523 +0,0 @@ -#ifndef _ASM_X86_SYSTEM_H -#define _ASM_X86_SYSTEM_H - -#include <asm/asm.h> -#include <asm/segment.h> -#include <asm/cpufeature.h> -#include <asm/cmpxchg.h> -#include <asm/nops.h> - -#include <linux/kernel.h> -#include <linux/irqflags.h> - -/* entries in ARCH_DLINFO: */ -#if defined(CONFIG_IA32_EMULATION) || !defined(CONFIG_X86_64) -# define AT_VECTOR_SIZE_ARCH 2 -#else /* else it's non-compat x86-64 */ -# define AT_VECTOR_SIZE_ARCH 1 -#endif - -struct task_struct; /* one of the stranger aspects of C forward declarations */ -struct task_struct *__switch_to(struct task_struct *prev, - struct task_struct *next); -struct tss_struct; -void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, - struct tss_struct *tss); -extern void show_regs_common(void); - -#ifdef CONFIG_X86_32 - -#ifdef CONFIG_CC_STACKPROTECTOR -#define __switch_canary \ - "movl %P[task_canary](%[next]), %%ebx\n\t" \ - "movl %%ebx, "__percpu_arg([stack_canary])"\n\t" -#define __switch_canary_oparam \ - , [stack_canary] "=m" (stack_canary.canary) -#define __switch_canary_iparam \ - , [task_canary] "i" (offsetof(struct task_struct, stack_canary)) -#else /* CC_STACKPROTECTOR */ -#define __switch_canary -#define __switch_canary_oparam -#define __switch_canary_iparam -#endif /* CC_STACKPROTECTOR */ - -/* - * Saving eflags is important. It switches not only IOPL between tasks, - * it also protects other tasks from NT leaking through sysenter etc. - */ -#define switch_to(prev, next, last) \ -do { \ - /* \ - * Context-switching clobbers all registers, so we clobber \ - * them explicitly, via unused output variables. \ - * (EAX and EBP is not listed because EBP is saved/restored \ - * explicitly for wchan access and EAX is the return value of \ - * __switch_to()) \ - */ \ - unsigned long ebx, ecx, edx, esi, edi; \ - \ - asm volatile("pushfl\n\t" /* save flags */ \ - "pushl %%ebp\n\t" /* save EBP */ \ - "movl %%esp,%[prev_sp]\n\t" /* save ESP */ \ - "movl %[next_sp],%%esp\n\t" /* restore ESP */ \ - "movl $1f,%[prev_ip]\n\t" /* save EIP */ \ - "pushl %[next_ip]\n\t" /* restore EIP */ \ - __switch_canary \ - "jmp __switch_to\n" /* regparm call */ \ - "1:\t" \ - "popl %%ebp\n\t" /* restore EBP */ \ - "popfl\n" /* restore flags */ \ - \ - /* output parameters */ \ - : [prev_sp] "=m" (prev->thread.sp), \ - [prev_ip] "=m" (prev->thread.ip), \ - "=a" (last), \ - \ - /* clobbered output registers: */ \ - "=b" (ebx), "=c" (ecx), "=d" (edx), \ - "=S" (esi), "=D" (edi) \ - \ - __switch_canary_oparam \ - \ - /* input parameters: */ \ - : [next_sp] "m" (next->thread.sp), \ - [next_ip] "m" (next->thread.ip), \ - \ - /* regparm parameters for __switch_to(): */ \ - [prev] "a" (prev), \ - [next] "d" (next) \ - \ - __switch_canary_iparam \ - \ - : /* reloaded segment registers */ \ - "memory"); \ -} while (0) - -/* - * disable hlt during certain critical i/o operations - */ -#define HAVE_DISABLE_HLT -#else - -/* 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 __EXTRA_CLOBBER \ - , "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \ - "r12", "r13", "r14", "r15" - -#ifdef CONFIG_CC_STACKPROTECTOR -#define __switch_canary \ - "movq %P[task_canary](%%rsi),%%r8\n\t" \ - "movq %%r8,"__percpu_arg([gs_canary])"\n\t" -#define __switch_canary_oparam \ - , [gs_canary] "=m" (irq_stack_union.stack_canary) -#define __switch_canary_iparam \ - , [task_canary] "i" (offsetof(struct task_struct, stack_canary)) -#else /* CC_STACKPROTECTOR */ -#define __switch_canary -#define __switch_canary_oparam -#define __switch_canary_iparam -#endif /* CC_STACKPROTECTOR */ - -/* Save restore flags to clear handle leaking NT */ -#define switch_to(prev, next, last) \ - asm volatile(SAVE_CONTEXT \ - "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \ - "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */ \ - "call __switch_to\n\t" \ - "movq "__percpu_arg([current_task])",%%rsi\n\t" \ - __switch_canary \ - "movq %P[thread_info](%%rsi),%%r8\n\t" \ - "movq %%rax,%%rdi\n\t" \ - "testl %[_tif_fork],%P[ti_flags](%%r8)\n\t" \ - "jnz ret_from_fork\n\t" \ - RESTORE_CONTEXT \ - : "=a" (last) \ - __switch_canary_oparam \ - : [next] "S" (next), [prev] "D" (prev), \ - [threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \ - [ti_flags] "i" (offsetof(struct thread_info, flags)), \ - [_tif_fork] "i" (_TIF_FORK), \ - [thread_info] "i" (offsetof(struct task_struct, stack)), \ - [current_task] "m" (current_task) \ - __switch_canary_iparam \ - : "memory", "cc" __EXTRA_CLOBBER) -#endif - -#ifdef __KERNEL__ - -extern void native_load_gs_index(unsigned); - -/* - * Load a segment. Fall back on loading the zero - * segment if something goes wrong.. - */ -#define loadsegment(seg, value) \ -do { \ - unsigned short __val = (value); \ - \ - asm volatile(" \n" \ - "1: movl %k0,%%" #seg " \n" \ - \ - ".section .fixup,\"ax\" \n" \ - "2: xorl %k0,%k0 \n" \ - " jmp 1b \n" \ - ".previous \n" \ - \ - _ASM_EXTABLE(1b, 2b) \ - \ - : "+r" (__val) : : "memory"); \ -} while (0) - -/* - * Save a segment register away - */ -#define savesegment(seg, value) \ - asm("mov %%" #seg ",%0":"=r" (value) : : "memory") - -/* - * x86_32 user gs accessors. - */ -#ifdef CONFIG_X86_32 -#ifdef CONFIG_X86_32_LAZY_GS -#define get_user_gs(regs) (u16)({unsigned long v; savesegment(gs, v); v;}) -#define set_user_gs(regs, v) loadsegment(gs, (unsigned long)(v)) -#define task_user_gs(tsk) ((tsk)->thread.gs) -#define lazy_save_gs(v) savesegment(gs, (v)) -#define lazy_load_gs(v) loadsegment(gs, (v)) -#else /* X86_32_LAZY_GS */ -#define get_user_gs(regs) (u16)((regs)->gs) -#define set_user_gs(regs, v) do { (regs)->gs = (v); } while (0) -#define task_user_gs(tsk) (task_pt_regs(tsk)->gs) -#define lazy_save_gs(v) do { } while (0) -#define lazy_load_gs(v) do { } while (0) -#endif /* X86_32_LAZY_GS */ -#endif /* X86_32 */ - -static inline unsigned long get_limit(unsigned long segment) -{ - unsigned long __limit; - asm("lsll %1,%0" : "=r" (__limit) : "r" (segment)); - return __limit + 1; -} - -static inline void native_clts(void) -{ - asm volatile("clts"); -} - -/* - * Volatile isn't enough to prevent the compiler from reordering the - * read/write functions for the control registers and messing everything up. - * A memory clobber would solve the problem, but would prevent reordering of - * all loads stores around it, which can hurt performance. Solution is to - * use a variable and mimic reads and writes to it to enforce serialization - */ -static unsigned long __force_order; - -static inline unsigned long native_read_cr0(void) -{ - unsigned long val; - asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order)); - return val; -} - -static inline void native_write_cr0(unsigned long val) -{ - asm volatile("mov %0,%%cr0": : "r" (val), "m" (__force_order)); -} - -static inline unsigned long native_read_cr2(void) -{ - unsigned long val; - asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order)); - return val; -} - -static inline void native_write_cr2(unsigned long val) -{ - asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order)); -} - -static inline unsigned long native_read_cr3(void) -{ - unsigned long val; - asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order)); - return val; -} - -static inline void native_write_cr3(unsigned long val) -{ - asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order)); -} - -static inline unsigned long native_read_cr4(void) -{ - unsigned long val; - asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order)); - return val; -} - -static inline unsigned long native_read_cr4_safe(void) -{ - unsigned long val; - /* This could fault if %cr4 does not exist. In x86_64, a cr4 always - * exists, so it will never fail. */ -#ifdef CONFIG_X86_32 - asm volatile("1: mov %%cr4, %0\n" - "2:\n" - _ASM_EXTABLE(1b, 2b) - : "=r" (val), "=m" (__force_order) : "0" (0)); -#else - val = native_read_cr4(); -#endif - return val; -} - -static inline void native_write_cr4(unsigned long val) -{ - asm volatile("mov %0,%%cr4": : "r" (val), "m" (__force_order)); -} - -#ifdef CONFIG_X86_64 -static inline unsigned long native_read_cr8(void) -{ - unsigned long cr8; - asm volatile("movq %%cr8,%0" : "=r" (cr8)); - return cr8; -} - -static inline void native_write_cr8(unsigned long val) -{ - asm volatile("movq %0,%%cr8" :: "r" (val) : "memory"); -} -#endif - -static inline void native_wbinvd(void) -{ - asm volatile("wbinvd": : :"memory"); -} - -#ifdef CONFIG_PARAVIRT -#include <asm/paravirt.h> -#else - -static inline unsigned long read_cr0(void) -{ - return native_read_cr0(); -} - -static inline void write_cr0(unsigned long x) -{ - native_write_cr0(x); -} - -static inline unsigned long read_cr2(void) -{ - return native_read_cr2(); -} - -static inline void write_cr2(unsigned long x) -{ - native_write_cr2(x); -} - -static inline unsigned long read_cr3(void) -{ - return native_read_cr3(); -} - -static inline void write_cr3(unsigned long x) -{ - native_write_cr3(x); -} - -static inline unsigned long read_cr4(void) -{ - return native_read_cr4(); -} - -static inline unsigned long read_cr4_safe(void) -{ - return native_read_cr4_safe(); -} - -static inline void write_cr4(unsigned long x) -{ - native_write_cr4(x); -} - -static inline void wbinvd(void) -{ - native_wbinvd(); -} - -#ifdef CONFIG_X86_64 - -static inline unsigned long read_cr8(void) -{ - return native_read_cr8(); -} - -static inline void write_cr8(unsigned long x) -{ - native_write_cr8(x); -} - -static inline void load_gs_index(unsigned selector) -{ - native_load_gs_index(selector); -} - -#endif - -/* Clear the 'TS' bit */ -static inline void clts(void) -{ - native_clts(); -} - -#endif/* CONFIG_PARAVIRT */ - -#define stts() write_cr0(read_cr0() | X86_CR0_TS) - -#endif /* __KERNEL__ */ - -static inline void clflush(volatile void *__p) -{ - asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p)); -} - -#define nop() asm volatile ("nop") - -void disable_hlt(void); -void enable_hlt(void); - -void cpu_idle_wait(void); - -extern unsigned long arch_align_stack(unsigned long sp); -extern void free_init_pages(char *what, unsigned long begin, unsigned long end); - -void default_idle(void); -bool set_pm_idle_to_default(void); - -void stop_this_cpu(void *dummy); - -/* - * Force strict CPU ordering. - * And yes, this is required on UP too when we're talking - * to devices. - */ -#ifdef CONFIG_X86_32 -/* - * Some non-Intel clones support out of order store. wmb() ceases to be a - * nop for these. - */ -#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2) -#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2) -#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM) -#else -#define mb() asm volatile("mfence":::"memory") -#define rmb() asm volatile("lfence":::"memory") -#define wmb() asm volatile("sfence" ::: "memory") -#endif - -/** - * read_barrier_depends - Flush all pending reads that subsequents reads - * depend on. - * - * No data-dependent reads from memory-like regions are ever reordered - * over this barrier. All reads preceding this primitive are guaranteed - * to access memory (but not necessarily other CPUs' caches) before any - * reads following this primitive that depend on the data return by - * any of the preceding reads. This primitive is much lighter weight than - * rmb() on most CPUs, and is never heavier weight than is - * rmb(). - * - * These ordering constraints are respected by both the local CPU - * and the compiler. - * - * Ordering is not guaranteed by anything other than these primitives, - * not even by data dependencies. See the documentation for - * memory_barrier() for examples and URLs to more information. - * - * For example, the following code would force ordering (the initial - * value of "a" is zero, "b" is one, and "p" is "&a"): - * - * <programlisting> - * CPU 0 CPU 1 - * - * b = 2; - * memory_barrier(); - * p = &b; q = p; - * read_barrier_depends(); - * d = *q; - * </programlisting> - * - * because the read of "*q" depends on the read of "p" and these - * two reads are separated by a read_barrier_depends(). However, - * the following code, with the same initial values for "a" and "b": - * - * <programlisting> - * CPU 0 CPU 1 - * - * a = 2; - * memory_barrier(); - * b = 3; y = b; - * read_barrier_depends(); - * x = a; - * </programlisting> - * - * does not enforce ordering, since there is no data dependency between - * the read of "a" and the read of "b". Therefore, on some CPUs, such - * as Alpha, "y" could be set to 3 and "x" to 0. Use rmb() - * in cases like this where there are no data dependencies. - **/ - -#define read_barrier_depends() do { } while (0) - -#ifdef CONFIG_SMP -#define smp_mb() mb() -#ifdef CONFIG_X86_PPRO_FENCE -# define smp_rmb() rmb() -#else -# define smp_rmb() barrier() -#endif -#ifdef CONFIG_X86_OOSTORE -# define smp_wmb() wmb() -#else -# define smp_wmb() barrier() -#endif -#define smp_read_barrier_depends() read_barrier_depends() -#define set_mb(var, value) do { (void)xchg(&var, value); } while (0) -#else -#define smp_mb() barrier() -#define smp_rmb() barrier() -#define smp_wmb() barrier() -#define smp_read_barrier_depends() do { } while (0) -#define set_mb(var, value) do { var = value; barrier(); } while (0) -#endif - -/* - * 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 __always_inline void rdtsc_barrier(void) -{ - alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC); - alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC); -} - -/* - * We handle most unaligned accesses in hardware. On the other hand - * unaligned DMA can be quite expensive on some Nehalem processors. - * - * Based on this we disable the IP header alignment in network drivers. - */ -#define NET_IP_ALIGN 0 -#endif /* _ASM_X86_SYSTEM_H */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 74047159d0a..ad6df8ccd71 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -40,8 +40,8 @@ struct thread_info { */ __u8 supervisor_stack[0]; #endif - int sig_on_uaccess_error:1; - int uaccess_err:1; /* uaccess failed */ + unsigned int sig_on_uaccess_error:1; + unsigned int uaccess_err:1; /* uaccess failed */ }; #define INIT_THREAD_INFO(tsk) \ @@ -86,7 +86,7 @@ struct thread_info { #define TIF_MCE_NOTIFY 10 /* notify userspace of an MCE */ #define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ #define TIF_NOTSC 16 /* TSC is not accessible in userland */ -#define TIF_IA32 17 /* 32bit process */ +#define TIF_IA32 17 /* IA32 compatibility process */ #define TIF_FORK 18 /* ret_from_fork */ #define TIF_MEMDIE 20 /* is terminating due to OOM killer */ #define TIF_DEBUG 21 /* uses debug registers */ @@ -95,6 +95,8 @@ struct thread_info { #define TIF_BLOCKSTEP 25 /* set when we want DEBUGCTLMSR_BTF */ #define TIF_LAZY_MMU_UPDATES 27 /* task is updating the mmu lazily */ #define TIF_SYSCALL_TRACEPOINT 28 /* syscall tracepoint instrumentation */ +#define TIF_ADDR32 29 /* 32-bit address space on 64 bits */ +#define TIF_X32 30 /* 32-bit native x86-64 binary */ #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) @@ -116,6 +118,8 @@ struct thread_info { #define _TIF_BLOCKSTEP (1 << TIF_BLOCKSTEP) #define _TIF_LAZY_MMU_UPDATES (1 << TIF_LAZY_MMU_UPDATES) #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) +#define _TIF_ADDR32 (1 << TIF_ADDR32) +#define _TIF_X32 (1 << TIF_X32) /* work to do in syscall_trace_enter() */ #define _TIF_WORK_SYSCALL_ENTRY \ @@ -247,8 +251,6 @@ static inline struct thread_info *current_thread_info(void) * ever touches our thread-synchronous status, so we don't * have to worry about atomic accesses. */ -#define TS_USEDFPU 0x0001 /* FPU was used by this task - this quantum (SMP) */ #define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ #define TS_POLLING 0x0004 /* idle task polling need_resched, skip sending interrupt */ @@ -264,6 +266,18 @@ static inline void set_restore_sigmask(void) ti->status |= TS_RESTORE_SIGMASK; set_bit(TIF_SIGPENDING, (unsigned long *)&ti->flags); } + +static inline bool is_ia32_task(void) +{ +#ifdef CONFIG_X86_32 + return true; +#endif +#ifdef CONFIG_IA32_EMULATION + if (current_thread_info()->status & TS_COMPAT) + return true; +#endif + return false; +} #endif /* !__ASSEMBLY__ */ #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index 431793e5d48..34baa0eb5d0 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -57,14 +57,10 @@ DECLARE_PER_CPU(unsigned long long, cyc2ns_offset); static inline unsigned long long __cycles_2_ns(unsigned long long cyc) { - unsigned long long quot; - unsigned long long rem; int cpu = smp_processor_id(); unsigned long long ns = per_cpu(cyc2ns_offset, cpu); - quot = (cyc >> CYC2NS_SCALE_FACTOR); - rem = cyc & ((1ULL << CYC2NS_SCALE_FACTOR) - 1); - ns += quot * per_cpu(cyc2ns, cpu) + - ((rem * per_cpu(cyc2ns, cpu)) >> CYC2NS_SCALE_FACTOR); + ns += mult_frac(cyc, per_cpu(cyc2ns, cpu), + (1UL << CYC2NS_SCALE_FACTOR)); return ns; } diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 169be8938b9..c0e108e0807 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -5,7 +5,7 @@ #include <linux/sched.h> #include <asm/processor.h> -#include <asm/system.h> +#include <asm/special_insns.h> #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 0012d0902c5..88eae2aec61 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -89,4 +89,29 @@ asmlinkage void smp_thermal_interrupt(void); asmlinkage void mce_threshold_interrupt(void); #endif +/* Interrupts/Exceptions */ +enum { + X86_TRAP_DE = 0, /* 0, Divide-by-zero */ + X86_TRAP_DB, /* 1, Debug */ + X86_TRAP_NMI, /* 2, Non-maskable Interrupt */ + X86_TRAP_BP, /* 3, Breakpoint */ + X86_TRAP_OF, /* 4, Overflow */ + X86_TRAP_BR, /* 5, Bound Range Exceeded */ + X86_TRAP_UD, /* 6, Invalid Opcode */ + X86_TRAP_NM, /* 7, Device Not Available */ + X86_TRAP_DF, /* 8, Double Fault */ + X86_TRAP_OLD_MF, /* 9, Coprocessor Segment Overrun */ + X86_TRAP_TS, /* 10, Invalid TSS */ + X86_TRAP_NP, /* 11, Segment Not Present */ + X86_TRAP_SS, /* 12, Stack Segment Fault */ + X86_TRAP_GP, /* 13, General Protection Fault */ + X86_TRAP_PF, /* 14, Page Fault */ + X86_TRAP_SPURIOUS, /* 15, Spurious Interrupt */ + X86_TRAP_MF, /* 16, x87 Floating-Point Exception */ + X86_TRAP_AC, /* 17, Alignment Check */ + X86_TRAP_MC, /* 18, Machine Check */ + X86_TRAP_XF, /* 19, SIMD Floating-Point Exception */ + X86_TRAP_IRET = 32, /* 32, IRET Exception */ +}; + #endif /* _ASM_X86_TRAPS_H */ diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index 15d99153a96..c91e8b9d588 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -61,7 +61,7 @@ extern void check_tsc_sync_source(int cpu); extern void check_tsc_sync_target(void); extern int notsc_setup(char *); -extern void save_sched_clock_state(void); -extern void restore_sched_clock_state(void); +extern void tsc_save_sched_clock_state(void); +extern void tsc_restore_sched_clock_state(void); #endif /* _ASM_X86_TSC_H */ diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 8be5f54d936..e0544597cfe 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -557,6 +557,8 @@ struct __large_struct { unsigned long buf[100]; }; extern unsigned long copy_from_user_nmi(void *to, const void __user *from, unsigned long n); +extern __must_check long +strncpy_from_user(char *dst, const char __user *src, long count); /* * movsl can be slow when source and dest are not both 8-byte aligned diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index 566e803cc60..8084bc73b18 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -213,11 +213,6 @@ static inline unsigned long __must_check copy_from_user(void *to, return n; } -long __must_check strncpy_from_user(char *dst, const char __user *src, - long count); -long __must_check __strncpy_from_user(char *dst, - const char __user *src, long count); - /** * strlen_user: - Get the size of a string in user space. * @str: The string to measure. diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 1c66d30971a..fcd4b6f3ef0 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -208,10 +208,6 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size) } } -__must_check long -strncpy_from_user(char *dst, const char __user *src, long count); -__must_check long -__strncpy_from_user(char *dst, const char __user *src, long count); __must_check long strnlen_user(const char __user *str, long n); __must_check long __strnlen_user(const char __user *str, long n); __must_check long strlen_user(const char __user *str); diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h index 2a58ed3e51d..37cdc9d99bb 100644 --- a/arch/x86/include/asm/unistd.h +++ b/arch/x86/include/asm/unistd.h @@ -1,13 +1,73 @@ +#ifndef _ASM_X86_UNISTD_H +#define _ASM_X86_UNISTD_H 1 + +/* x32 syscall flag bit */ +#define __X32_SYSCALL_BIT 0x40000000 + #ifdef __KERNEL__ + +# ifdef CONFIG_X86_X32_ABI +# define __SYSCALL_MASK (~(__X32_SYSCALL_BIT)) +# else +# define __SYSCALL_MASK (~0) +# endif + # ifdef CONFIG_X86_32 -# include "unistd_32.h" + +# include <asm/unistd_32.h> +# define __ARCH_WANT_IPC_PARSE_VERSION +# define __ARCH_WANT_STAT64 +# define __ARCH_WANT_SYS_IPC +# define __ARCH_WANT_SYS_OLD_MMAP +# define __ARCH_WANT_SYS_OLD_SELECT + # else -# include "unistd_64.h" + +# include <asm/unistd_64.h> +# include <asm/unistd_64_x32.h> +# define __ARCH_WANT_COMPAT_SYS_TIME + # endif + +# define __ARCH_WANT_OLD_READDIR +# define __ARCH_WANT_OLD_STAT +# define __ARCH_WANT_SYS_ALARM +# define __ARCH_WANT_SYS_FADVISE64 +# define __ARCH_WANT_SYS_GETHOSTNAME +# define __ARCH_WANT_SYS_GETPGRP +# define __ARCH_WANT_SYS_LLSEEK +# define __ARCH_WANT_SYS_NICE +# define __ARCH_WANT_SYS_OLDUMOUNT +# define __ARCH_WANT_SYS_OLD_GETRLIMIT +# define __ARCH_WANT_SYS_OLD_UNAME +# define __ARCH_WANT_SYS_PAUSE +# define __ARCH_WANT_SYS_RT_SIGACTION +# define __ARCH_WANT_SYS_RT_SIGSUSPEND +# define __ARCH_WANT_SYS_SGETMASK +# define __ARCH_WANT_SYS_SIGNAL +# define __ARCH_WANT_SYS_SIGPENDING +# define __ARCH_WANT_SYS_SIGPROCMASK +# define __ARCH_WANT_SYS_SOCKETCALL +# define __ARCH_WANT_SYS_TIME +# define __ARCH_WANT_SYS_UTIME +# define __ARCH_WANT_SYS_WAITPID + +/* + * "Conditional" syscalls + * + * What we want is __attribute__((weak,alias("sys_ni_syscall"))), + * but it doesn't work on all toolchains, so we just do it by hand + */ +# define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall") + #else # ifdef __i386__ -# include "unistd_32.h" +# include <asm/unistd_32.h> +# elif defined(__LP64__) +# include <asm/unistd_64.h> # else -# include "unistd_64.h" +# include <asm/unistd_x32.h> # endif #endif + +#endif /* _ASM_X86_UNISTD_H */ diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h deleted file mode 100644 index 599c77d38f3..00000000000 --- a/arch/x86/include/asm/unistd_32.h +++ /dev/null @@ -1,401 +0,0 @@ -#ifndef _ASM_X86_UNISTD_32_H -#define _ASM_X86_UNISTD_32_H - -/* - * This file contains the system call numbers. - */ - -#define __NR_restart_syscall 0 -#define __NR_exit 1 -#define __NR_fork 2 -#define __NR_read 3 -#define __NR_write 4 -#define __NR_open 5 -#define __NR_close 6 -#define __NR_waitpid 7 -#define __NR_creat 8 -#define __NR_link 9 -#define __NR_unlink 10 -#define __NR_execve 11 -#define __NR_chdir 12 -#define __NR_time 13 -#define __NR_mknod 14 -#define __NR_chmod 15 -#define __NR_lchown 16 -#define __NR_break 17 -#define __NR_oldstat 18 -#define __NR_lseek 19 -#define __NR_getpid 20 -#define __NR_mount 21 -#define __NR_umount 22 -#define __NR_setuid 23 -#define __NR_getuid 24 -#define __NR_stime 25 -#define __NR_ptrace 26 -#define __NR_alarm 27 -#define __NR_oldfstat 28 -#define __NR_pause 29 -#define __NR_utime 30 -#define __NR_stty 31 -#define __NR_gtty 32 -#define __NR_access 33 -#define __NR_nice 34 -#define __NR_ftime 35 -#define __NR_sync 36 -#define __NR_kill 37 -#define __NR_rename 38 -#define __NR_mkdir 39 -#define __NR_rmdir 40 -#define __NR_dup 41 -#define __NR_pipe 42 -#define __NR_times 43 -#define __NR_prof 44 -#define __NR_brk 45 -#define __NR_setgid 46 -#define __NR_getgid 47 -#define __NR_signal 48 -#define __NR_geteuid 49 -#define __NR_getegid 50 -#define __NR_acct 51 -#define __NR_umount2 52 -#define __NR_lock 53 -#define __NR_ioctl 54 -#define __NR_fcntl 55 -#define __NR_mpx 56 -#define __NR_setpgid 57 -#define __NR_ulimit 58 -#define __NR_oldolduname 59 -#define __NR_umask 60 -#define __NR_chroot 61 -#define __NR_ustat 62 -#define __NR_dup2 63 -#define __NR_getppid 64 -#define __NR_getpgrp 65 -#define __NR_setsid 66 -#define __NR_sigaction 67 -#define __NR_sgetmask 68 -#define __NR_ssetmask 69 -#define __NR_setreuid 70 -#define __NR_setregid 71 -#define __NR_sigsuspend 72 -#define __NR_sigpending 73 -#define __NR_sethostname 74 -#define __NR_setrlimit 75 -#define __NR_getrlimit 76 /* Back compatible 2Gig limited rlimit */ -#define __NR_getrusage 77 -#define __NR_gettimeofday 78 -#define __NR_settimeofday 79 -#define __NR_getgroups 80 -#define __NR_setgroups 81 -#define __NR_select 82 -#define __NR_symlink 83 -#define __NR_oldlstat 84 -#define __NR_readlink 85 -#define __NR_uselib 86 -#define __NR_swapon 87 -#define __NR_reboot 88 -#define __NR_readdir 89 -#define __NR_mmap 90 -#define __NR_munmap 91 -#define __NR_truncate 92 -#define __NR_ftruncate 93 -#define __NR_fchmod 94 -#define __NR_fchown 95 -#define __NR_getpriority 96 -#define __NR_setpriority 97 -#define __NR_profil 98 -#define __NR_statfs 99 -#define __NR_fstatfs 100 -#define __NR_ioperm 101 -#define __NR_socketcall 102 -#define __NR_syslog 103 -#define __NR_setitimer 104 -#define __NR_getitimer 105 -#define __NR_stat 106 -#define __NR_lstat 107 -#define __NR_fstat 108 -#define __NR_olduname 109 -#define __NR_iopl 110 -#define __NR_vhangup 111 -#define __NR_idle 112 -#define __NR_vm86old 113 -#define __NR_wait4 114 -#define __NR_swapoff 115 -#define __NR_sysinfo 116 -#define __NR_ipc 117 -#define __NR_fsync 118 -#define __NR_sigreturn 119 -#define __NR_clone 120 -#define __NR_setdomainname 121 -#define __NR_uname 122 -#define __NR_modify_ldt 123 -#define __NR_adjtimex 124 -#define __NR_mprotect 125 -#define __NR_sigprocmask 126 -#define __NR_create_module 127 -#define __NR_init_module 128 -#define __NR_delete_module 129 -#define __NR_get_kernel_syms 130 -#define __NR_quotactl 131 -#define __NR_getpgid 132 -#define __NR_fchdir 133 -#define __NR_bdflush 134 -#define __NR_sysfs 135 -#define __NR_personality 136 -#define __NR_afs_syscall 137 /* Syscall for Andrew File System */ -#define __NR_setfsuid 138 -#define __NR_setfsgid 139 -#define __NR__llseek 140 -#define __NR_getdents 141 -#define __NR__newselect 142 -#define __NR_flock 143 -#define __NR_msync 144 -#define __NR_readv 145 -#define __NR_writev 146 -#define __NR_getsid 147 -#define __NR_fdatasync 148 -#define __NR__sysctl 149 -#define __NR_mlock 150 -#define __NR_munlock 151 -#define __NR_mlockall 152 -#define __NR_munlockall 153 -#define __NR_sched_setparam 154 -#define __NR_sched_getparam 155 -#define __NR_sched_setscheduler 156 -#define __NR_sched_getscheduler 157 -#define __NR_sched_yield 158 -#define __NR_sched_get_priority_max 159 -#define __NR_sched_get_priority_min 160 -#define __NR_sched_rr_get_interval 161 -#define __NR_nanosleep 162 -#define __NR_mremap 163 -#define __NR_setresuid 164 -#define __NR_getresuid 165 -#define __NR_vm86 166 -#define __NR_query_module 167 -#define __NR_poll 168 -#define __NR_nfsservctl 169 -#define __NR_setresgid 170 -#define __NR_getresgid 171 -#define __NR_prctl 172 -#define __NR_rt_sigreturn 173 -#define __NR_rt_sigaction 174 -#define __NR_rt_sigprocmask 175 -#define __NR_rt_sigpending 176 -#define __NR_rt_sigtimedwait 177 -#define __NR_rt_sigqueueinfo 178 -#define __NR_rt_sigsuspend 179 -#define __NR_pread64 180 -#define __NR_pwrite64 181 -#define __NR_chown 182 -#define __NR_getcwd 183 -#define __NR_capget 184 -#define __NR_capset 185 -#define __NR_sigaltstack 186 -#define __NR_sendfile 187 -#define __NR_getpmsg 188 /* some people actually want streams */ -#define __NR_putpmsg 189 /* some people actually want streams */ -#define __NR_vfork 190 -#define __NR_ugetrlimit 191 /* SuS compliant getrlimit */ -#define __NR_mmap2 192 -#define __NR_truncate64 193 -#define __NR_ftruncate64 194 -#define __NR_stat64 195 -#define __NR_lstat64 196 -#define __NR_fstat64 197 -#define __NR_lchown32 198 -#define __NR_getuid32 199 -#define __NR_getgid32 200 -#define __NR_geteuid32 201 -#define __NR_getegid32 202 -#define __NR_setreuid32 203 -#define __NR_setregid32 204 -#define __NR_getgroups32 205 -#define __NR_setgroups32 206 -#define __NR_fchown32 207 -#define __NR_setresuid32 208 -#define __NR_getresuid32 209 -#define __NR_setresgid32 210 -#define __NR_getresgid32 211 -#define __NR_chown32 212 -#define __NR_setuid32 213 -#define __NR_setgid32 214 -#define __NR_setfsuid32 215 -#define __NR_setfsgid32 216 -#define __NR_pivot_root 217 -#define __NR_mincore 218 -#define __NR_madvise 219 -#define __NR_madvise1 219 /* delete when C lib stub is removed */ -#define __NR_getdents64 220 -#define __NR_fcntl64 221 -/* 223 is unused */ -#define __NR_gettid 224 -#define __NR_readahead 225 -#define __NR_setxattr 226 -#define __NR_lsetxattr 227 -#define __NR_fsetxattr 228 -#define __NR_getxattr 229 -#define __NR_lgetxattr 230 -#define __NR_fgetxattr 231 -#define __NR_listxattr 232 -#define __NR_llistxattr 233 -#define __NR_flistxattr 234 -#define __NR_removexattr 235 -#define __NR_lremovexattr 236 -#define __NR_fremovexattr 237 -#define __NR_tkill 238 -#define __NR_sendfile64 239 -#define __NR_futex 240 -#define __NR_sched_setaffinity 241 -#define __NR_sched_getaffinity 242 -#define __NR_set_thread_area 243 -#define __NR_get_thread_area 244 -#define __NR_io_setup 245 -#define __NR_io_destroy 246 -#define __NR_io_getevents 247 -#define __NR_io_submit 248 -#define __NR_io_cancel 249 -#define __NR_fadvise64 250 -/* 251 is available for reuse (was briefly sys_set_zone_reclaim) */ -#define __NR_exit_group 252 -#define __NR_lookup_dcookie 253 -#define __NR_epoll_create 254 -#define __NR_epoll_ctl 255 -#define __NR_epoll_wait 256 -#define __NR_remap_file_pages 257 -#define __NR_set_tid_address 258 -#define __NR_timer_create 259 -#define __NR_timer_settime (__NR_timer_create+1) -#define __NR_timer_gettime (__NR_timer_create+2) -#define __NR_timer_getoverrun (__NR_timer_create+3) -#define __NR_timer_delete (__NR_timer_create+4) -#define __NR_clock_settime (__NR_timer_create+5) -#define __NR_clock_gettime (__NR_timer_create+6) -#define __NR_clock_getres (__NR_timer_create+7) -#define __NR_clock_nanosleep (__NR_timer_create+8) -#define __NR_statfs64 268 -#define __NR_fstatfs64 269 -#define __NR_tgkill 270 -#define __NR_utimes 271 -#define __NR_fadvise64_64 272 -#define __NR_vserver 273 -#define __NR_mbind 274 -#define __NR_get_mempolicy 275 -#define __NR_set_mempolicy 276 -#define __NR_mq_open 277 -#define __NR_mq_unlink (__NR_mq_open+1) -#define __NR_mq_timedsend (__NR_mq_open+2) -#define __NR_mq_timedreceive (__NR_mq_open+3) -#define __NR_mq_notify (__NR_mq_open+4) -#define __NR_mq_getsetattr (__NR_mq_open+5) -#define __NR_kexec_load 283 -#define __NR_waitid 284 -/* #define __NR_sys_setaltroot 285 */ -#define __NR_add_key 286 -#define __NR_request_key 287 -#define __NR_keyctl 288 -#define __NR_ioprio_set 289 -#define __NR_ioprio_get 290 -#define __NR_inotify_init 291 -#define __NR_inotify_add_watch 292 -#define __NR_inotify_rm_watch 293 -#define __NR_migrate_pages 294 -#define __NR_openat 295 -#define __NR_mkdirat 296 -#define __NR_mknodat 297 -#define __NR_fchownat 298 -#define __NR_futimesat 299 -#define __NR_fstatat64 300 -#define __NR_unlinkat 301 -#define __NR_renameat 302 -#define __NR_linkat 303 -#define __NR_symlinkat 304 -#define __NR_readlinkat 305 -#define __NR_fchmodat 306 -#define __NR_faccessat 307 -#define __NR_pselect6 308 -#define __NR_ppoll 309 -#define __NR_unshare 310 -#define __NR_set_robust_list 311 -#define __NR_get_robust_list 312 -#define __NR_splice 313 -#define __NR_sync_file_range 314 -#define __NR_tee 315 -#define __NR_vmsplice 316 -#define __NR_move_pages 317 -#define __NR_getcpu 318 -#define __NR_epoll_pwait 319 -#define __NR_utimensat 320 -#define __NR_signalfd 321 -#define __NR_timerfd_create 322 -#define __NR_eventfd 323 -#define __NR_fallocate 324 -#define __NR_timerfd_settime 325 -#define __NR_timerfd_gettime 326 -#define __NR_signalfd4 327 -#define __NR_eventfd2 328 -#define __NR_epoll_create1 329 -#define __NR_dup3 330 -#define __NR_pipe2 331 -#define __NR_inotify_init1 332 -#define __NR_preadv 333 -#define __NR_pwritev 334 -#define __NR_rt_tgsigqueueinfo 335 -#define __NR_perf_event_open 336 -#define __NR_recvmmsg 337 -#define __NR_fanotify_init 338 -#define __NR_fanotify_mark 339 -#define __NR_prlimit64 340 -#define __NR_name_to_handle_at 341 -#define __NR_open_by_handle_at 342 -#define __NR_clock_adjtime 343 -#define __NR_syncfs 344 -#define __NR_sendmmsg 345 -#define __NR_setns 346 -#define __NR_process_vm_readv 347 -#define __NR_process_vm_writev 348 - -#ifdef __KERNEL__ - -#define NR_syscalls 349 - -#define __ARCH_WANT_IPC_PARSE_VERSION -#define __ARCH_WANT_OLD_READDIR -#define __ARCH_WANT_OLD_STAT -#define __ARCH_WANT_STAT64 -#define __ARCH_WANT_SYS_ALARM -#define __ARCH_WANT_SYS_GETHOSTNAME -#define __ARCH_WANT_SYS_IPC -#define __ARCH_WANT_SYS_PAUSE -#define __ARCH_WANT_SYS_SGETMASK -#define __ARCH_WANT_SYS_SIGNAL -#define __ARCH_WANT_SYS_TIME -#define __ARCH_WANT_SYS_UTIME -#define __ARCH_WANT_SYS_WAITPID -#define __ARCH_WANT_SYS_SOCKETCALL -#define __ARCH_WANT_SYS_FADVISE64 -#define __ARCH_WANT_SYS_GETPGRP -#define __ARCH_WANT_SYS_LLSEEK -#define __ARCH_WANT_SYS_NICE -#define __ARCH_WANT_SYS_OLD_GETRLIMIT -#define __ARCH_WANT_SYS_OLD_UNAME -#define __ARCH_WANT_SYS_OLD_MMAP -#define __ARCH_WANT_SYS_OLD_SELECT -#define __ARCH_WANT_SYS_OLDUMOUNT -#define __ARCH_WANT_SYS_SIGPENDING -#define __ARCH_WANT_SYS_SIGPROCMASK -#define __ARCH_WANT_SYS_RT_SIGACTION -#define __ARCH_WANT_SYS_RT_SIGSUSPEND - -/* - * "Conditional" syscalls - * - * What we want is __attribute__((weak,alias("sys_ni_syscall"))), - * but it doesn't work on all toolchains, so we just do it by hand - */ -#ifndef cond_syscall -#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall") -#endif - -#endif /* __KERNEL__ */ -#endif /* _ASM_X86_UNISTD_32_H */ diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h deleted file mode 100644 index 0431f193c3f..00000000000 --- a/arch/x86/include/asm/unistd_64.h +++ /dev/null @@ -1,732 +0,0 @@ -#ifndef _ASM_X86_UNISTD_64_H -#define _ASM_X86_UNISTD_64_H - -#ifndef __SYSCALL -#define __SYSCALL(a, b) -#endif - -/* - * This file contains the system call numbers. - * - * Note: holes are not allowed. - */ - -/* at least 8 syscall per cacheline */ -#define __NR_read 0 -__SYSCALL(__NR_read, sys_read) -#define __NR_write 1 -__SYSCALL(__NR_write, sys_write) -#define __NR_open 2 -__SYSCALL(__NR_open, sys_open) -#define __NR_close 3 -__SYSCALL(__NR_close, sys_close) -#define __NR_stat 4 -__SYSCALL(__NR_stat, sys_newstat) -#define __NR_fstat 5 -__SYSCALL(__NR_fstat, sys_newfstat) -#define __NR_lstat 6 -__SYSCALL(__NR_lstat, sys_newlstat) -#define __NR_poll 7 -__SYSCALL(__NR_poll, sys_poll) - -#define __NR_lseek 8 -__SYSCALL(__NR_lseek, sys_lseek) -#define __NR_mmap 9 -__SYSCALL(__NR_mmap, sys_mmap) -#define __NR_mprotect 10 -__SYSCALL(__NR_mprotect, sys_mprotect) -#define __NR_munmap 11 -__SYSCALL(__NR_munmap, sys_munmap) -#define __NR_brk 12 -__SYSCALL(__NR_brk, sys_brk) -#define __NR_rt_sigaction 13 -__SYSCALL(__NR_rt_sigaction, sys_rt_sigaction) -#define __NR_rt_sigprocmask 14 -__SYSCALL(__NR_rt_sigprocmask, sys_rt_sigprocmask) -#define __NR_rt_sigreturn 15 -__SYSCALL(__NR_rt_sigreturn, stub_rt_sigreturn) - -#define __NR_ioctl 16 -__SYSCALL(__NR_ioctl, sys_ioctl) -#define __NR_pread64 17 -__SYSCALL(__NR_pread64, sys_pread64) -#define __NR_pwrite64 18 -__SYSCALL(__NR_pwrite64, sys_pwrite64) -#define __NR_readv 19 -__SYSCALL(__NR_readv, sys_readv) -#define __NR_writev 20 -__SYSCALL(__NR_writev, sys_writev) -#define __NR_access 21 -__SYSCALL(__NR_access, sys_access) -#define __NR_pipe 22 -__SYSCALL(__NR_pipe, sys_pipe) -#define __NR_select 23 -__SYSCALL(__NR_select, sys_select) - -#define __NR_sched_yield 24 -__SYSCALL(__NR_sched_yield, sys_sched_yield) -#define __NR_mremap 25 -__SYSCALL(__NR_mremap, sys_mremap) -#define __NR_msync 26 -__SYSCALL(__NR_msync, sys_msync) -#define __NR_mincore 27 -__SYSCALL(__NR_mincore, sys_mincore) -#define __NR_madvise 28 -__SYSCALL(__NR_madvise, sys_madvise) -#define __NR_shmget 29 -__SYSCALL(__NR_shmget, sys_shmget) -#define __NR_shmat 30 -__SYSCALL(__NR_shmat, sys_shmat) -#define __NR_shmctl 31 -__SYSCALL(__NR_shmctl, sys_shmctl) - -#define __NR_dup 32 -__SYSCALL(__NR_dup, sys_dup) -#define __NR_dup2 33 -__SYSCALL(__NR_dup2, sys_dup2) -#define __NR_pause 34 -__SYSCALL(__NR_pause, sys_pause) -#define __NR_nanosleep 35 -__SYSCALL(__NR_nanosleep, sys_nanosleep) -#define __NR_getitimer 36 -__SYSCALL(__NR_getitimer, sys_getitimer) -#define __NR_alarm 37 -__SYSCALL(__NR_alarm, sys_alarm) -#define __NR_setitimer 38 -__SYSCALL(__NR_setitimer, sys_setitimer) -#define __NR_getpid 39 -__SYSCALL(__NR_getpid, sys_getpid) - -#define __NR_sendfile 40 -__SYSCALL(__NR_sendfile, sys_sendfile64) -#define __NR_socket 41 -__SYSCALL(__NR_socket, sys_socket) -#define __NR_connect 42 -__SYSCALL(__NR_connect, sys_connect) -#define __NR_accept 43 -__SYSCALL(__NR_accept, sys_accept) -#define __NR_sendto 44 -__SYSCALL(__NR_sendto, sys_sendto) -#define __NR_recvfrom 45 -__SYSCALL(__NR_recvfrom, sys_recvfrom) -#define __NR_sendmsg 46 -__SYSCALL(__NR_sendmsg, sys_sendmsg) -#define __NR_recvmsg 47 -__SYSCALL(__NR_recvmsg, sys_recvmsg) - -#define __NR_shutdown 48 -__SYSCALL(__NR_shutdown, sys_shutdown) -#define __NR_bind 49 -__SYSCALL(__NR_bind, sys_bind) -#define __NR_listen 50 -__SYSCALL(__NR_listen, sys_listen) -#define __NR_getsockname 51 -__SYSCALL(__NR_getsockname, sys_getsockname) -#define __NR_getpeername 52 -__SYSCALL(__NR_getpeername, sys_getpeername) -#define __NR_socketpair 53 -__SYSCALL(__NR_socketpair, sys_socketpair) -#define __NR_setsockopt 54 -__SYSCALL(__NR_setsockopt, sys_setsockopt) -#define __NR_getsockopt 55 -__SYSCALL(__NR_getsockopt, sys_getsockopt) - -#define __NR_clone 56 -__SYSCALL(__NR_clone, stub_clone) -#define __NR_fork 57 -__SYSCALL(__NR_fork, stub_fork) -#define __NR_vfork 58 -__SYSCALL(__NR_vfork, stub_vfork) -#define __NR_execve 59 -__SYSCALL(__NR_execve, stub_execve) -#define __NR_exit 60 -__SYSCALL(__NR_exit, sys_exit) -#define __NR_wait4 61 -__SYSCALL(__NR_wait4, sys_wait4) -#define __NR_kill 62 -__SYSCALL(__NR_kill, sys_kill) -#define __NR_uname 63 -__SYSCALL(__NR_uname, sys_newuname) - -#define __NR_semget 64 -__SYSCALL(__NR_semget, sys_semget) -#define __NR_semop 65 -__SYSCALL(__NR_semop, sys_semop) -#define __NR_semctl 66 -__SYSCALL(__NR_semctl, sys_semctl) -#define __NR_shmdt 67 -__SYSCALL(__NR_shmdt, sys_shmdt) -#define __NR_msgget 68 -__SYSCALL(__NR_msgget, sys_msgget) -#define __NR_msgsnd 69 -__SYSCALL(__NR_msgsnd, sys_msgsnd) -#define __NR_msgrcv 70 -__SYSCALL(__NR_msgrcv, sys_msgrcv) -#define __NR_msgctl 71 -__SYSCALL(__NR_msgctl, sys_msgctl) - -#define __NR_fcntl 72 -__SYSCALL(__NR_fcntl, sys_fcntl) -#define __NR_flock 73 -__SYSCALL(__NR_flock, sys_flock) -#define __NR_fsync 74 -__SYSCALL(__NR_fsync, sys_fsync) -#define __NR_fdatasync 75 -__SYSCALL(__NR_fdatasync, sys_fdatasync) -#define __NR_truncate 76 -__SYSCALL(__NR_truncate, sys_truncate) -#define __NR_ftruncate 77 -__SYSCALL(__NR_ftruncate, sys_ftruncate) -#define __NR_getdents 78 -__SYSCALL(__NR_getdents, sys_getdents) -#define __NR_getcwd 79 -__SYSCALL(__NR_getcwd, sys_getcwd) - -#define __NR_chdir 80 -__SYSCALL(__NR_chdir, sys_chdir) -#define __NR_fchdir 81 -__SYSCALL(__NR_fchdir, sys_fchdir) -#define __NR_rename 82 -__SYSCALL(__NR_rename, sys_rename) -#define __NR_mkdir 83 -__SYSCALL(__NR_mkdir, sys_mkdir) -#define __NR_rmdir 84 -__SYSCALL(__NR_rmdir, sys_rmdir) -#define __NR_creat 85 -__SYSCALL(__NR_creat, sys_creat) -#define __NR_link 86 -__SYSCALL(__NR_link, sys_link) -#define __NR_unlink 87 -__SYSCALL(__NR_unlink, sys_unlink) - -#define __NR_symlink 88 -__SYSCALL(__NR_symlink, sys_symlink) -#define __NR_readlink 89 -__SYSCALL(__NR_readlink, sys_readlink) -#define __NR_chmod 90 -__SYSCALL(__NR_chmod, sys_chmod) -#define __NR_fchmod 91 -__SYSCALL(__NR_fchmod, sys_fchmod) -#define __NR_chown 92 -__SYSCALL(__NR_chown, sys_chown) -#define __NR_fchown 93 -__SYSCALL(__NR_fchown, sys_fchown) -#define __NR_lchown 94 -__SYSCALL(__NR_lchown, sys_lchown) -#define __NR_umask 95 -__SYSCALL(__NR_umask, sys_umask) - -#define __NR_gettimeofday 96 -__SYSCALL(__NR_gettimeofday, sys_gettimeofday) -#define __NR_getrlimit 97 -__SYSCALL(__NR_getrlimit, sys_getrlimit) -#define __NR_getrusage 98 -__SYSCALL(__NR_getrusage, sys_getrusage) -#define __NR_sysinfo 99 -__SYSCALL(__NR_sysinfo, sys_sysinfo) -#define __NR_times 100 -__SYSCALL(__NR_times, sys_times) -#define __NR_ptrace 101 -__SYSCALL(__NR_ptrace, sys_ptrace) -#define __NR_getuid 102 -__SYSCALL(__NR_getuid, sys_getuid) -#define __NR_syslog 103 -__SYSCALL(__NR_syslog, sys_syslog) - -/* at the very end the stuff that never runs during the benchmarks */ -#define __NR_getgid 104 -__SYSCALL(__NR_getgid, sys_getgid) -#define __NR_setuid 105 -__SYSCALL(__NR_setuid, sys_setuid) -#define __NR_setgid 106 -__SYSCALL(__NR_setgid, sys_setgid) -#define __NR_geteuid 107 -__SYSCALL(__NR_geteuid, sys_geteuid) -#define __NR_getegid 108 -__SYSCALL(__NR_getegid, sys_getegid) -#define __NR_setpgid 109 -__SYSCALL(__NR_setpgid, sys_setpgid) -#define __NR_getppid 110 -__SYSCALL(__NR_getppid, sys_getppid) -#define __NR_getpgrp 111 -__SYSCALL(__NR_getpgrp, sys_getpgrp) - -#define __NR_setsid 112 -__SYSCALL(__NR_setsid, sys_setsid) -#define __NR_setreuid 113 -__SYSCALL(__NR_setreuid, sys_setreuid) -#define __NR_setregid 114 -__SYSCALL(__NR_setregid, sys_setregid) -#define __NR_getgroups 115 -__SYSCALL(__NR_getgroups, sys_getgroups) -#define __NR_setgroups 116 -__SYSCALL(__NR_setgroups, sys_setgroups) -#define __NR_setresuid 117 -__SYSCALL(__NR_setresuid, sys_setresuid) -#define __NR_getresuid 118 -__SYSCALL(__NR_getresuid, sys_getresuid) -#define __NR_setresgid 119 -__SYSCALL(__NR_setresgid, sys_setresgid) - -#define __NR_getresgid 120 -__SYSCALL(__NR_getresgid, sys_getresgid) -#define __NR_getpgid 121 -__SYSCALL(__NR_getpgid, sys_getpgid) -#define __NR_setfsuid 122 -__SYSCALL(__NR_setfsuid, sys_setfsuid) -#define __NR_setfsgid 123 -__SYSCALL(__NR_setfsgid, sys_setfsgid) -#define __NR_getsid 124 -__SYSCALL(__NR_getsid, sys_getsid) -#define __NR_capget 125 -__SYSCALL(__NR_capget, sys_capget) -#define __NR_capset 126 -__SYSCALL(__NR_capset, sys_capset) - -#define __NR_rt_sigpending 127 -__SYSCALL(__NR_rt_sigpending, sys_rt_sigpending) -#define __NR_rt_sigtimedwait 128 -__SYSCALL(__NR_rt_sigtimedwait, sys_rt_sigtimedwait) -#define __NR_rt_sigqueueinfo 129 -__SYSCALL(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo) -#define __NR_rt_sigsuspend 130 -__SYSCALL(__NR_rt_sigsuspend, sys_rt_sigsuspend) -#define __NR_sigaltstack 131 -__SYSCALL(__NR_sigaltstack, stub_sigaltstack) -#define __NR_utime 132 -__SYSCALL(__NR_utime, sys_utime) -#define __NR_mknod 133 -__SYSCALL(__NR_mknod, sys_mknod) - -/* Only needed for a.out */ -#define __NR_uselib 134 -__SYSCALL(__NR_uselib, sys_ni_syscall) -#define __NR_personality 135 -__SYSCALL(__NR_personality, sys_personality) - -#define __NR_ustat 136 -__SYSCALL(__NR_ustat, sys_ustat) -#define __NR_statfs 137 -__SYSCALL(__NR_statfs, sys_statfs) -#define __NR_fstatfs 138 -__SYSCALL(__NR_fstatfs, sys_fstatfs) -#define __NR_sysfs 139 -__SYSCALL(__NR_sysfs, sys_sysfs) - -#define __NR_getpriority 140 -__SYSCALL(__NR_getpriority, sys_getpriority) -#define __NR_setpriority 141 -__SYSCALL(__NR_setpriority, sys_setpriority) -#define __NR_sched_setparam 142 -__SYSCALL(__NR_sched_setparam, sys_sched_setparam) -#define __NR_sched_getparam 143 -__SYSCALL(__NR_sched_getparam, sys_sched_getparam) -#define __NR_sched_setscheduler 144 -__SYSCALL(__NR_sched_setscheduler, sys_sched_setscheduler) -#define __NR_sched_getscheduler 145 -__SYSCALL(__NR_sched_getscheduler, sys_sched_getscheduler) -#define __NR_sched_get_priority_max 146 -__SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max) -#define __NR_sched_get_priority_min 147 -__SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min) -#define __NR_sched_rr_get_interval 148 -__SYSCALL(__NR_sched_rr_get_interval, sys_sched_rr_get_interval) - -#define __NR_mlock 149 -__SYSCALL(__NR_mlock, sys_mlock) -#define __NR_munlock 150 -__SYSCALL(__NR_munlock, sys_munlock) -#define __NR_mlockall 151 -__SYSCALL(__NR_mlockall, sys_mlockall) -#define __NR_munlockall 152 -__SYSCALL(__NR_munlockall, sys_munlockall) - -#define __NR_vhangup 153 -__SYSCALL(__NR_vhangup, sys_vhangup) - -#define __NR_modify_ldt 154 -__SYSCALL(__NR_modify_ldt, sys_modify_ldt) - -#define __NR_pivot_root 155 -__SYSCALL(__NR_pivot_root, sys_pivot_root) - -#define __NR__sysctl 156 -__SYSCALL(__NR__sysctl, sys_sysctl) - -#define __NR_prctl 157 -__SYSCALL(__NR_prctl, sys_prctl) -#define __NR_arch_prctl 158 -__SYSCALL(__NR_arch_prctl, sys_arch_prctl) - -#define __NR_adjtimex 159 -__SYSCALL(__NR_adjtimex, sys_adjtimex) - -#define __NR_setrlimit 160 -__SYSCALL(__NR_setrlimit, sys_setrlimit) - -#define __NR_chroot 161 -__SYSCALL(__NR_chroot, sys_chroot) - -#define __NR_sync 162 -__SYSCALL(__NR_sync, sys_sync) - -#define __NR_acct 163 -__SYSCALL(__NR_acct, sys_acct) - -#define __NR_settimeofday 164 -__SYSCALL(__NR_settimeofday, sys_settimeofday) - -#define __NR_mount 165 -__SYSCALL(__NR_mount, sys_mount) -#define __NR_umount2 166 -__SYSCALL(__NR_umount2, sys_umount) - -#define __NR_swapon 167 -__SYSCALL(__NR_swapon, sys_swapon) -#define __NR_swapoff 168 -__SYSCALL(__NR_swapoff, sys_swapoff) - -#define __NR_reboot 169 -__SYSCALL(__NR_reboot, sys_reboot) - -#define __NR_sethostname 170 -__SYSCALL(__NR_sethostname, sys_sethostname) -#define __NR_setdomainname 171 -__SYSCALL(__NR_setdomainname, sys_setdomainname) - -#define __NR_iopl 172 -__SYSCALL(__NR_iopl, stub_iopl) -#define __NR_ioperm 173 -__SYSCALL(__NR_ioperm, sys_ioperm) - -#define __NR_create_module 174 -__SYSCALL(__NR_create_module, sys_ni_syscall) -#define __NR_init_module 175 -__SYSCALL(__NR_init_module, sys_init_module) -#define __NR_delete_module 176 -__SYSCALL(__NR_delete_module, sys_delete_module) -#define __NR_get_kernel_syms 177 -__SYSCALL(__NR_get_kernel_syms, sys_ni_syscall) -#define __NR_query_module 178 -__SYSCALL(__NR_query_module, sys_ni_syscall) - -#define __NR_quotactl 179 -__SYSCALL(__NR_quotactl, sys_quotactl) - -#define __NR_nfsservctl 180 -__SYSCALL(__NR_nfsservctl, sys_ni_syscall) - -/* reserved for LiS/STREAMS */ -#define __NR_getpmsg 181 -__SYSCALL(__NR_getpmsg, sys_ni_syscall) -#define __NR_putpmsg 182 -__SYSCALL(__NR_putpmsg, sys_ni_syscall) - -/* reserved for AFS */ -#define __NR_afs_syscall 183 -__SYSCALL(__NR_afs_syscall, sys_ni_syscall) - -/* reserved for tux */ -#define __NR_tuxcall 184 -__SYSCALL(__NR_tuxcall, sys_ni_syscall) - -#define __NR_security 185 -__SYSCALL(__NR_security, sys_ni_syscall) - -#define __NR_gettid 186 -__SYSCALL(__NR_gettid, sys_gettid) - -#define __NR_readahead 187 -__SYSCALL(__NR_readahead, sys_readahead) -#define __NR_setxattr 188 -__SYSCALL(__NR_setxattr, sys_setxattr) -#define __NR_lsetxattr 189 -__SYSCALL(__NR_lsetxattr, sys_lsetxattr) -#define __NR_fsetxattr 190 -__SYSCALL(__NR_fsetxattr, sys_fsetxattr) -#define __NR_getxattr 191 -__SYSCALL(__NR_getxattr, sys_getxattr) -#define __NR_lgetxattr 192 -__SYSCALL(__NR_lgetxattr, sys_lgetxattr) -#define __NR_fgetxattr 193 -__SYSCALL(__NR_fgetxattr, sys_fgetxattr) -#define __NR_listxattr 194 -__SYSCALL(__NR_listxattr, sys_listxattr) -#define __NR_llistxattr 195 -__SYSCALL(__NR_llistxattr, sys_llistxattr) -#define __NR_flistxattr 196 -__SYSCALL(__NR_flistxattr, sys_flistxattr) -#define __NR_removexattr 197 -__SYSCALL(__NR_removexattr, sys_removexattr) -#define __NR_lremovexattr 198 -__SYSCALL(__NR_lremovexattr, sys_lremovexattr) -#define __NR_fremovexattr 199 -__SYSCALL(__NR_fremovexattr, sys_fremovexattr) -#define __NR_tkill 200 -__SYSCALL(__NR_tkill, sys_tkill) -#define __NR_time 201 -__SYSCALL(__NR_time, sys_time) -#define __NR_futex 202 -__SYSCALL(__NR_futex, sys_futex) -#define __NR_sched_setaffinity 203 -__SYSCALL(__NR_sched_setaffinity, sys_sched_setaffinity) -#define __NR_sched_getaffinity 204 -__SYSCALL(__NR_sched_getaffinity, sys_sched_getaffinity) -#define __NR_set_thread_area 205 -__SYSCALL(__NR_set_thread_area, sys_ni_syscall) /* use arch_prctl */ -#define __NR_io_setup 206 -__SYSCALL(__NR_io_setup, sys_io_setup) -#define __NR_io_destroy 207 -__SYSCALL(__NR_io_destroy, sys_io_destroy) -#define __NR_io_getevents 208 -__SYSCALL(__NR_io_getevents, sys_io_getevents) -#define __NR_io_submit 209 -__SYSCALL(__NR_io_submit, sys_io_submit) -#define __NR_io_cancel 210 -__SYSCALL(__NR_io_cancel, sys_io_cancel) -#define __NR_get_thread_area 211 -__SYSCALL(__NR_get_thread_area, sys_ni_syscall) /* use arch_prctl */ -#define __NR_lookup_dcookie 212 -__SYSCALL(__NR_lookup_dcookie, sys_lookup_dcookie) -#define __NR_epoll_create 213 -__SYSCALL(__NR_epoll_create, sys_epoll_create) -#define __NR_epoll_ctl_old 214 -__SYSCALL(__NR_epoll_ctl_old, sys_ni_syscall) -#define __NR_epoll_wait_old 215 -__SYSCALL(__NR_epoll_wait_old, sys_ni_syscall) -#define __NR_remap_file_pages 216 -__SYSCALL(__NR_remap_file_pages, sys_remap_file_pages) -#define __NR_getdents64 217 -__SYSCALL(__NR_getdents64, sys_getdents64) -#define __NR_set_tid_address 218 -__SYSCALL(__NR_set_tid_address, sys_set_tid_address) -#define __NR_restart_syscall 219 -__SYSCALL(__NR_restart_syscall, sys_restart_syscall) -#define __NR_semtimedop 220 -__SYSCALL(__NR_semtimedop, sys_semtimedop) -#define __NR_fadvise64 221 -__SYSCALL(__NR_fadvise64, sys_fadvise64) -#define __NR_timer_create 222 -__SYSCALL(__NR_timer_create, sys_timer_create) -#define __NR_timer_settime 223 -__SYSCALL(__NR_timer_settime, sys_timer_settime) -#define __NR_timer_gettime 224 -__SYSCALL(__NR_timer_gettime, sys_timer_gettime) -#define __NR_timer_getoverrun 225 -__SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun) -#define __NR_timer_delete 226 -__SYSCALL(__NR_timer_delete, sys_timer_delete) -#define __NR_clock_settime 227 -__SYSCALL(__NR_clock_settime, sys_clock_settime) -#define __NR_clock_gettime 228 -__SYSCALL(__NR_clock_gettime, sys_clock_gettime) -#define __NR_clock_getres 229 -__SYSCALL(__NR_clock_getres, sys_clock_getres) -#define __NR_clock_nanosleep 230 -__SYSCALL(__NR_clock_nanosleep, sys_clock_nanosleep) -#define __NR_exit_group 231 -__SYSCALL(__NR_exit_group, sys_exit_group) -#define __NR_epoll_wait 232 -__SYSCALL(__NR_epoll_wait, sys_epoll_wait) -#define __NR_epoll_ctl 233 -__SYSCALL(__NR_epoll_ctl, sys_epoll_ctl) -#define __NR_tgkill 234 -__SYSCALL(__NR_tgkill, sys_tgkill) -#define __NR_utimes 235 -__SYSCALL(__NR_utimes, sys_utimes) -#define __NR_vserver 236 -__SYSCALL(__NR_vserver, sys_ni_syscall) -#define __NR_mbind 237 -__SYSCALL(__NR_mbind, sys_mbind) -#define __NR_set_mempolicy 238 -__SYSCALL(__NR_set_mempolicy, sys_set_mempolicy) -#define __NR_get_mempolicy 239 -__SYSCALL(__NR_get_mempolicy, sys_get_mempolicy) -#define __NR_mq_open 240 -__SYSCALL(__NR_mq_open, sys_mq_open) -#define __NR_mq_unlink 241 -__SYSCALL(__NR_mq_unlink, sys_mq_unlink) -#define __NR_mq_timedsend 242 -__SYSCALL(__NR_mq_timedsend, sys_mq_timedsend) -#define __NR_mq_timedreceive 243 -__SYSCALL(__NR_mq_timedreceive, sys_mq_timedreceive) -#define __NR_mq_notify 244 -__SYSCALL(__NR_mq_notify, sys_mq_notify) -#define __NR_mq_getsetattr 245 -__SYSCALL(__NR_mq_getsetattr, sys_mq_getsetattr) -#define __NR_kexec_load 246 -__SYSCALL(__NR_kexec_load, sys_kexec_load) -#define __NR_waitid 247 -__SYSCALL(__NR_waitid, sys_waitid) -#define __NR_add_key 248 -__SYSCALL(__NR_add_key, sys_add_key) -#define __NR_request_key 249 -__SYSCALL(__NR_request_key, sys_request_key) -#define __NR_keyctl 250 -__SYSCALL(__NR_keyctl, sys_keyctl) -#define __NR_ioprio_set 251 -__SYSCALL(__NR_ioprio_set, sys_ioprio_set) -#define __NR_ioprio_get 252 -__SYSCALL(__NR_ioprio_get, sys_ioprio_get) -#define __NR_inotify_init 253 -__SYSCALL(__NR_inotify_init, sys_inotify_init) -#define __NR_inotify_add_watch 254 -__SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch) -#define __NR_inotify_rm_watch 255 -__SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch) -#define __NR_migrate_pages 256 -__SYSCALL(__NR_migrate_pages, sys_migrate_pages) -#define __NR_openat 257 -__SYSCALL(__NR_openat, sys_openat) -#define __NR_mkdirat 258 -__SYSCALL(__NR_mkdirat, sys_mkdirat) -#define __NR_mknodat 259 -__SYSCALL(__NR_mknodat, sys_mknodat) -#define __NR_fchownat 260 -__SYSCALL(__NR_fchownat, sys_fchownat) -#define __NR_futimesat 261 -__SYSCALL(__NR_futimesat, sys_futimesat) -#define __NR_newfstatat 262 -__SYSCALL(__NR_newfstatat, sys_newfstatat) -#define __NR_unlinkat 263 -__SYSCALL(__NR_unlinkat, sys_unlinkat) -#define __NR_renameat 264 -__SYSCALL(__NR_renameat, sys_renameat) -#define __NR_linkat 265 -__SYSCALL(__NR_linkat, sys_linkat) -#define __NR_symlinkat 266 -__SYSCALL(__NR_symlinkat, sys_symlinkat) -#define __NR_readlinkat 267 -__SYSCALL(__NR_readlinkat, sys_readlinkat) -#define __NR_fchmodat 268 -__SYSCALL(__NR_fchmodat, sys_fchmodat) -#define __NR_faccessat 269 -__SYSCALL(__NR_faccessat, sys_faccessat) -#define __NR_pselect6 270 -__SYSCALL(__NR_pselect6, sys_pselect6) -#define __NR_ppoll 271 -__SYSCALL(__NR_ppoll, sys_ppoll) -#define __NR_unshare 272 -__SYSCALL(__NR_unshare, sys_unshare) -#define __NR_set_robust_list 273 -__SYSCALL(__NR_set_robust_list, sys_set_robust_list) -#define __NR_get_robust_list 274 -__SYSCALL(__NR_get_robust_list, sys_get_robust_list) -#define __NR_splice 275 -__SYSCALL(__NR_splice, sys_splice) -#define __NR_tee 276 -__SYSCALL(__NR_tee, sys_tee) -#define __NR_sync_file_range 277 -__SYSCALL(__NR_sync_file_range, sys_sync_file_range) -#define __NR_vmsplice 278 -__SYSCALL(__NR_vmsplice, sys_vmsplice) -#define __NR_move_pages 279 -__SYSCALL(__NR_move_pages, sys_move_pages) -#define __NR_utimensat 280 -__SYSCALL(__NR_utimensat, sys_utimensat) -#define __NR_epoll_pwait 281 -__SYSCALL(__NR_epoll_pwait, sys_epoll_pwait) -#define __NR_signalfd 282 -__SYSCALL(__NR_signalfd, sys_signalfd) -#define __NR_timerfd_create 283 -__SYSCALL(__NR_timerfd_create, sys_timerfd_create) -#define __NR_eventfd 284 -__SYSCALL(__NR_eventfd, sys_eventfd) -#define __NR_fallocate 285 -__SYSCALL(__NR_fallocate, sys_fallocate) -#define __NR_timerfd_settime 286 -__SYSCALL(__NR_timerfd_settime, sys_timerfd_settime) -#define __NR_timerfd_gettime 287 -__SYSCALL(__NR_timerfd_gettime, sys_timerfd_gettime) -#define __NR_accept4 288 -__SYSCALL(__NR_accept4, sys_accept4) -#define __NR_signalfd4 289 -__SYSCALL(__NR_signalfd4, sys_signalfd4) -#define __NR_eventfd2 290 -__SYSCALL(__NR_eventfd2, sys_eventfd2) -#define __NR_epoll_create1 291 -__SYSCALL(__NR_epoll_create1, sys_epoll_create1) -#define __NR_dup3 292 -__SYSCALL(__NR_dup3, sys_dup3) -#define __NR_pipe2 293 -__SYSCALL(__NR_pipe2, sys_pipe2) -#define __NR_inotify_init1 294 -__SYSCALL(__NR_inotify_init1, sys_inotify_init1) -#define __NR_preadv 295 -__SYSCALL(__NR_preadv, sys_preadv) -#define __NR_pwritev 296 -__SYSCALL(__NR_pwritev, sys_pwritev) -#define __NR_rt_tgsigqueueinfo 297 -__SYSCALL(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo) -#define __NR_perf_event_open 298 -__SYSCALL(__NR_perf_event_open, sys_perf_event_open) -#define __NR_recvmmsg 299 -__SYSCALL(__NR_recvmmsg, sys_recvmmsg) -#define __NR_fanotify_init 300 -__SYSCALL(__NR_fanotify_init, sys_fanotify_init) -#define __NR_fanotify_mark 301 -__SYSCALL(__NR_fanotify_mark, sys_fanotify_mark) -#define __NR_prlimit64 302 -__SYSCALL(__NR_prlimit64, sys_prlimit64) -#define __NR_name_to_handle_at 303 -__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at) -#define __NR_open_by_handle_at 304 -__SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at) -#define __NR_clock_adjtime 305 -__SYSCALL(__NR_clock_adjtime, sys_clock_adjtime) -#define __NR_syncfs 306 -__SYSCALL(__NR_syncfs, sys_syncfs) -#define __NR_sendmmsg 307 -__SYSCALL(__NR_sendmmsg, sys_sendmmsg) -#define __NR_setns 308 -__SYSCALL(__NR_setns, sys_setns) -#define __NR_getcpu 309 -__SYSCALL(__NR_getcpu, sys_getcpu) -#define __NR_process_vm_readv 310 -__SYSCALL(__NR_process_vm_readv, sys_process_vm_readv) -#define __NR_process_vm_writev 311 -__SYSCALL(__NR_process_vm_writev, sys_process_vm_writev) - -#ifndef __NO_STUBS -#define __ARCH_WANT_OLD_READDIR -#define __ARCH_WANT_OLD_STAT -#define __ARCH_WANT_SYS_ALARM -#define __ARCH_WANT_SYS_GETHOSTNAME -#define __ARCH_WANT_SYS_PAUSE -#define __ARCH_WANT_SYS_SGETMASK -#define __ARCH_WANT_SYS_SIGNAL -#define __ARCH_WANT_SYS_UTIME -#define __ARCH_WANT_SYS_WAITPID -#define __ARCH_WANT_SYS_SOCKETCALL -#define __ARCH_WANT_SYS_FADVISE64 -#define __ARCH_WANT_SYS_GETPGRP -#define __ARCH_WANT_SYS_LLSEEK -#define __ARCH_WANT_SYS_NICE -#define __ARCH_WANT_SYS_OLD_GETRLIMIT -#define __ARCH_WANT_SYS_OLD_UNAME -#define __ARCH_WANT_SYS_OLDUMOUNT -#define __ARCH_WANT_SYS_SIGPENDING -#define __ARCH_WANT_SYS_SIGPROCMASK -#define __ARCH_WANT_SYS_RT_SIGACTION -#define __ARCH_WANT_SYS_RT_SIGSUSPEND -#define __ARCH_WANT_SYS_TIME -#define __ARCH_WANT_COMPAT_SYS_TIME -#endif /* __NO_STUBS */ - -#ifdef __KERNEL__ - -#ifndef COMPILE_OFFSETS -#include <asm/asm-offsets.h> -#define NR_syscalls (__NR_syscall_max + 1) -#endif - -/* - * "Conditional" syscalls - * - * What we want is __attribute__((weak,alias("sys_ni_syscall"))), - * but it doesn't work on all toolchains, so we just do it by hand - */ -#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall") -#endif /* __KERNEL__ */ - -#endif /* _ASM_X86_UNISTD_64_H */ diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h index 8e862aaf0d9..becf47b8173 100644 --- a/arch/x86/include/asm/uv/uv_bau.h +++ b/arch/x86/include/asm/uv/uv_bau.h @@ -65,7 +65,7 @@ * UV2: Bit 19 selects between * (0): 10 microsecond timebase and * (1): 80 microseconds - * we're using 655us, similar to UV1: 65 units of 10us + * we're using 560us, similar to UV1: 65 units of 10us */ #define UV1_INTD_SOFT_ACK_TIMEOUT_PERIOD (9UL) #define UV2_INTD_SOFT_ACK_TIMEOUT_PERIOD (15UL) @@ -167,6 +167,7 @@ #define FLUSH_RETRY_TIMEOUT 2 #define FLUSH_GIVEUP 3 #define FLUSH_COMPLETE 4 +#define FLUSH_RETRY_BUSYBUG 5 /* * tuning the action when the numalink network is extremely delayed @@ -235,10 +236,10 @@ struct bau_msg_payload { /* - * Message header: 16 bytes (128 bits) (bytes 0x30-0x3f of descriptor) + * UV1 Message header: 16 bytes (128 bits) (bytes 0x30-0x3f of descriptor) * see table 4.2.3.0.1 in broacast_assist spec. */ -struct bau_msg_header { +struct uv1_bau_msg_header { unsigned int dest_subnodeid:6; /* must be 0x10, for the LB */ /* bits 5:0 */ unsigned int base_dest_nasid:15; /* nasid of the first bit */ @@ -318,19 +319,87 @@ struct bau_msg_header { }; /* + * UV2 Message header: 16 bytes (128 bits) (bytes 0x30-0x3f of descriptor) + * see figure 9-2 of harp_sys.pdf + */ +struct uv2_bau_msg_header { + unsigned int base_dest_nasid:15; /* nasid of the first bit */ + /* bits 14:0 */ /* in uvhub map */ + unsigned int dest_subnodeid:5; /* must be 0x10, for the LB */ + /* bits 19:15 */ + unsigned int rsvd_1:1; /* must be zero */ + /* bit 20 */ + /* Address bits 59:21 */ + /* bits 25:2 of address (44:21) are payload */ + /* these next 24 bits become bytes 12-14 of msg */ + /* bits 28:21 land in byte 12 */ + unsigned int replied_to:1; /* sent as 0 by the source to + byte 12 */ + /* bit 21 */ + unsigned int msg_type:3; /* software type of the + message */ + /* bits 24:22 */ + unsigned int canceled:1; /* message canceled, resource + is to be freed*/ + /* bit 25 */ + unsigned int payload_1:3; /* not currently used */ + /* bits 28:26 */ + + /* bits 36:29 land in byte 13 */ + unsigned int payload_2a:3; /* not currently used */ + unsigned int payload_2b:5; /* not currently used */ + /* bits 36:29 */ + + /* bits 44:37 land in byte 14 */ + unsigned int payload_3:8; /* not currently used */ + /* bits 44:37 */ + + unsigned int rsvd_2:7; /* reserved */ + /* bits 51:45 */ + unsigned int swack_flag:1; /* software acknowledge flag */ + /* bit 52 */ + unsigned int rsvd_3a:3; /* must be zero */ + unsigned int rsvd_3b:8; /* must be zero */ + unsigned int rsvd_3c:8; /* must be zero */ + unsigned int rsvd_3d:3; /* must be zero */ + /* bits 74:53 */ + unsigned int fairness:3; /* usually zero */ + /* bits 77:75 */ + + unsigned int sequence:16; /* message sequence number */ + /* bits 93:78 Suppl_A */ + unsigned int chaining:1; /* next descriptor is part of + this activation*/ + /* bit 94 */ + unsigned int multilevel:1; /* multi-level multicast + format */ + /* bit 95 */ + unsigned int rsvd_4:24; /* ordered / source node / + source subnode / aging + must be zero */ + /* bits 119:96 */ + unsigned int command:8; /* message type */ + /* bits 127:120 */ +}; + +/* * The activation descriptor: * The format of the message to send, plus all accompanying control * Should be 64 bytes */ struct bau_desc { - struct pnmask distribution; + struct pnmask distribution; /* * message template, consisting of header and payload: */ - struct bau_msg_header header; - struct bau_msg_payload payload; + union bau_msg_header { + struct uv1_bau_msg_header uv1_hdr; + struct uv2_bau_msg_header uv2_hdr; + } header; + + struct bau_msg_payload payload; }; -/* +/* UV1: * -payload-- ---------header------ * bytes 0-11 bits 41-56 bits 58-81 * A B (2) C (3) @@ -340,6 +409,16 @@ struct bau_desc { * bytes 0-11 bytes 12-14 bytes 16-17 (byte 15 filled in by hw as vector) * ------------payload queue----------- */ +/* UV2: + * -payload-- ---------header------ + * bytes 0-11 bits 70-78 bits 21-44 + * A B (2) C (3) + * + * A/B/C are moved to: + * A C B + * bytes 0-11 bytes 12-14 bytes 16-17 (byte 15 filled in by hw as vector) + * ------------payload queue----------- + */ /* * The payload queue on the destination side is an array of these. @@ -385,7 +464,6 @@ struct bau_pq_entry { struct msg_desc { struct bau_pq_entry *msg; int msg_slot; - int swack_slot; struct bau_pq_entry *queue_first; struct bau_pq_entry *queue_last; }; @@ -405,6 +483,7 @@ struct ptc_stats { requests */ unsigned long s_stimeout; /* source side timeouts */ unsigned long s_dtimeout; /* destination side timeouts */ + unsigned long s_strongnacks; /* number of strong nack's */ unsigned long s_time; /* time spent in sending side */ unsigned long s_retriesok; /* successful retries */ unsigned long s_ntargcpu; /* total number of cpu's @@ -439,6 +518,9 @@ struct ptc_stats { unsigned long s_retry_messages; /* retry broadcasts */ unsigned long s_bau_reenabled; /* for bau enable/disable */ unsigned long s_bau_disabled; /* for bau enable/disable */ + unsigned long s_uv2_wars; /* uv2 workaround, perm. busy */ + unsigned long s_uv2_wars_hw; /* uv2 workaround, hiwater */ + unsigned long s_uv2_war_waits; /* uv2 workaround, long waits */ /* destination statistics */ unsigned long d_alltlb; /* times all tlb's on this cpu were flushed */ @@ -511,9 +593,12 @@ struct bau_control { short osnode; short uvhub_cpu; short uvhub; + short uvhub_version; short cpus_in_socket; short cpus_in_uvhub; short partition_base_pnode; + short using_desc; /* an index, like uvhub_cpu */ + unsigned int inuse_map; unsigned short message_number; unsigned short uvhub_quiesce; short socket_acknowledge_count[DEST_Q_SIZE]; @@ -531,6 +616,7 @@ struct bau_control { int cong_response_us; int cong_reps; int cong_period; + unsigned long clocks_per_100_usec; cycles_t period_time; long period_requests; struct hub_and_pnode *thp; @@ -591,6 +677,11 @@ static inline void write_mmr_sw_ack(unsigned long mr) uv_write_local_mmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, mr); } +static inline void write_gmmr_sw_ack(int pnode, unsigned long mr) +{ + write_gmmr(pnode, UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, mr); +} + static inline unsigned long read_mmr_sw_ack(void) { return read_lmmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE); diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index 54a13aaebc4..21f7385badb 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -318,13 +318,13 @@ uv_gpa_in_mmr_space(unsigned long gpa) /* UV global physical address --> socket phys RAM */ static inline unsigned long uv_gpa_to_soc_phys_ram(unsigned long gpa) { - unsigned long paddr = gpa & uv_hub_info->gpa_mask; + unsigned long paddr; unsigned long remap_base = uv_hub_info->lowmem_remap_base; unsigned long remap_top = uv_hub_info->lowmem_remap_top; gpa = ((gpa << uv_hub_info->m_shift) >> uv_hub_info->m_shift) | ((gpa >> uv_hub_info->n_lshift) << uv_hub_info->m_val); - gpa = gpa & uv_hub_info->gpa_mask; + paddr = gpa & uv_hub_info->gpa_mask; if (paddr >= remap_base && paddr < remap_base + remap_top) paddr -= remap_base; return paddr; diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h index 815285bcace..8b38be2de9e 100644 --- a/arch/x86/include/asm/vgtod.h +++ b/arch/x86/include/asm/vgtod.h @@ -5,13 +5,8 @@ #include <linux/clocksource.h> struct vsyscall_gtod_data { - seqlock_t lock; + seqcount_t seq; - /* open coded 'struct timespec' */ - time_t wall_time_sec; - u32 wall_time_nsec; - - struct timezone sys_tz; struct { /* extract of a clocksource struct */ int vclock_mode; cycle_t cycle_last; @@ -19,8 +14,16 @@ struct vsyscall_gtod_data { u32 mult; u32 shift; } clock; - struct timespec wall_to_monotonic; + + /* open coded 'struct timespec' */ + time_t wall_time_sec; + u32 wall_time_nsec; + u32 monotonic_time_nsec; + time_t monotonic_time_sec; + + struct timezone sys_tz; struct timespec wall_time_coarse; + struct timespec monotonic_time_coarse; }; extern struct vsyscall_gtod_data vsyscall_gtod_data; diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h index e0f9aa16358..5da71c27cc5 100644 --- a/arch/x86/include/asm/virtext.h +++ b/arch/x86/include/asm/virtext.h @@ -16,7 +16,6 @@ #define _ASM_X86_VIRTEX_H #include <asm/processor.h> -#include <asm/system.h> #include <asm/vmx.h> #include <asm/svm.h> diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h new file mode 100644 index 00000000000..6fe6767b712 --- /dev/null +++ b/arch/x86/include/asm/word-at-a-time.h @@ -0,0 +1,46 @@ +#ifndef _ASM_WORD_AT_A_TIME_H +#define _ASM_WORD_AT_A_TIME_H + +/* + * This is largely generic for little-endian machines, but the + * optimal byte mask counting is probably going to be something + * that is architecture-specific. If you have a reliably fast + * bit count instruction, that might be better than the multiply + * and shift, for example. + */ + +#ifdef CONFIG_64BIT + +/* + * Jan Achrenius on G+: microoptimized version of + * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56" + * that works for the bytemasks without having to + * mask them first. + */ +static inline long count_masked_bytes(unsigned long mask) +{ + return mask*0x0001020304050608ul >> 56; +} + +#else /* 32-bit case */ + +/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */ +static inline long count_masked_bytes(long mask) +{ + /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */ + long a = (0x0ff0001+mask) >> 23; + /* Fix the 1 for 00 case */ + return a & mask; +} + +#endif + +#define REPEAT_BYTE(x) ((~0ul / 0xff) * (x)) + +/* Return the high bit set in the first byte that is a zero */ +static inline unsigned long has_zero(unsigned long a) +{ + return ((a - REPEAT_BYTE(0x01)) & ~a) & REPEAT_BYTE(0x80); +} + +#endif /* _ASM_WORD_AT_A_TIME_H */ diff --git a/arch/x86/include/asm/x2apic.h b/arch/x86/include/asm/x2apic.h index 6bf5b8e478c..92e54abf89e 100644 --- a/arch/x86/include/asm/x2apic.h +++ b/arch/x86/include/asm/x2apic.h @@ -18,6 +18,11 @@ static const struct cpumask *x2apic_target_cpus(void) return cpu_online_mask; } +static int x2apic_apic_id_valid(int apicid) +{ + return 1; +} + static int x2apic_apic_id_registered(void) { return 1; diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 517d4767ffd..baaca8defec 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -145,9 +145,11 @@ struct x86_init_ops { /** * struct x86_cpuinit_ops - platform specific cpu hotplug setups * @setup_percpu_clockev: set up the per cpu clock event device + * @early_percpu_clock_init: early init of the per cpu clock event device */ struct x86_cpuinit_ops { void (*setup_percpu_clockev)(void); + void (*early_percpu_clock_init)(void); void (*fixup_cpu_id)(struct cpuinfo_x86 *c, int node); }; @@ -160,6 +162,8 @@ struct x86_cpuinit_ops { * @is_untracked_pat_range exclude from PAT logic * @nmi_init enable NMI on cpus * @i8042_detect pre-detect if i8042 controller exists + * @save_sched_clock_state: save state for sched_clock() on suspend + * @restore_sched_clock_state: restore state for sched_clock() on resume */ struct x86_platform_ops { unsigned long (*calibrate_tsc)(void); @@ -171,6 +175,8 @@ struct x86_platform_ops { void (*nmi_init)(void); unsigned char (*get_nmi_reason)(void); int (*i8042_detect)(void); + void (*save_sched_clock_state)(void); + void (*restore_sched_clock_state)(void); }; struct pci_dev; diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 8baca3c4871..532d2e090e6 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -25,7 +25,8 @@ obj-$(CONFIG_IRQ_WORK) += irq_work.o obj-y += probe_roms.o obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o -obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o +obj-y += syscall_$(BITS).o +obj-$(CONFIG_X86_64) += vsyscall_64.o obj-$(CONFIG_X86_64) += vsyscall_emu_64.o obj-y += bootflag.o e820.o obj-y += pci-dma.o quirks.o topology.o kdebugfs.o @@ -68,6 +69,7 @@ obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o obj-$(CONFIG_KPROBES) += kprobes.o +obj-$(CONFIG_OPTPROBES) += kprobes-opt.o obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_DOUBLEFAULT) += doublefault_32.o obj-$(CONFIG_KGDB) += kgdb.o @@ -80,6 +82,7 @@ obj-$(CONFIG_APB_TIMER) += apb_timer.o obj-$(CONFIG_AMD_NB) += amd_nb.o obj-$(CONFIG_DEBUG_RODATA_TEST) += test_rodata.o obj-$(CONFIG_DEBUG_NX_TEST) += test_nx.o +obj-$(CONFIG_DEBUG_NMI_SELFTEST) += nmi_selftest.o obj-$(CONFIG_KVM_GUEST) += kvm.o obj-$(CONFIG_KVM_CLOCK) += kvmclock.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index ce664f33ea8..a415b1f4436 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -239,7 +239,7 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end) * to not preallocating memory for all NR_CPUS * when we use CPU hotplug. */ - if (!cpu_has_x2apic && (apic_id >= 0xff) && enabled) + if (!apic->apic_id_valid(apic_id) && enabled) printk(KERN_WARNING PREFIX "x2apic entry ignored\n"); else acpi_register_lapic(apic_id, enabled); @@ -593,7 +593,7 @@ void __init acpi_set_irq_model_ioapic(void) #ifdef CONFIG_ACPI_HOTPLUG_CPU #include <acpi/processor.h> -static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) +static void __cpuinitdata acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) { #ifdef CONFIG_ACPI_NUMA int nid; @@ -642,6 +642,7 @@ static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu) kfree(buffer.pointer); buffer.length = ACPI_ALLOCATE_BUFFER; buffer.pointer = NULL; + lapic = NULL; if (!alloc_cpumask_var(&tmp_map, GFP_KERNEL)) goto out; @@ -650,7 +651,7 @@ static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu) goto free_tmp_map; cpumask_copy(tmp_map, cpu_present_mask); - acpi_register_lapic(physid, lapic->lapic_flags & ACPI_MADT_ENABLED); + acpi_register_lapic(physid, ACPI_MADT_ENABLED); /* * If mp_register_lapic successfully generates a new logical cpu diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index f50e7fb2a20..d2b7f27781b 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -14,6 +14,7 @@ #include <acpi/processor.h> #include <asm/acpi.h> #include <asm/mwait.h> +#include <asm/special_insns.h> /* * Initialize bm_flags based on the CPU cache properties diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index b1e7c7f7a0a..e66311200cb 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -477,7 +477,7 @@ error: /* allocate and map a coherent mapping */ static void * gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, - gfp_t flag) + gfp_t flag, struct dma_attrs *attrs) { dma_addr_t paddr; unsigned long align_mask; @@ -500,7 +500,8 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, } __free_pages(page, get_order(size)); } else - return dma_generic_alloc_coherent(dev, size, dma_addr, flag); + return dma_generic_alloc_coherent(dev, size, dma_addr, flag, + attrs); return NULL; } @@ -508,7 +509,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, /* free a coherent mapping */ static void gart_free_coherent(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_addr) + dma_addr_t dma_addr, struct dma_attrs *attrs) { gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, NULL); free_pages((unsigned long)vaddr, get_order(size)); @@ -700,8 +701,8 @@ static struct dma_map_ops gart_dma_ops = { .unmap_sg = gart_unmap_sg, .map_page = gart_map_page, .unmap_page = gart_unmap_page, - .alloc_coherent = gart_alloc_coherent, - .free_coherent = gart_free_coherent, + .alloc = gart_alloc_coherent, + .free = gart_free_coherent, .mapping_error = gart_mapping_error, }; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 2eec05b6d1b..11544d8f1e9 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -383,20 +383,25 @@ static inline int eilvt_entry_is_changeable(unsigned int old, unsigned int new) static unsigned int reserve_eilvt_offset(int offset, unsigned int new) { - unsigned int rsvd; /* 0: uninitialized */ + unsigned int rsvd, vector; if (offset >= APIC_EILVT_NR_MAX) return ~0; - rsvd = atomic_read(&eilvt_offsets[offset]) & ~APIC_EILVT_MASKED; + rsvd = atomic_read(&eilvt_offsets[offset]); do { - if (rsvd && - !eilvt_entry_is_changeable(rsvd, new)) + vector = rsvd & ~APIC_EILVT_MASKED; /* 0: unassigned */ + if (vector && !eilvt_entry_is_changeable(vector, new)) /* may not change if vectors are different */ return rsvd; rsvd = atomic_cmpxchg(&eilvt_offsets[offset], rsvd, new); } while (rsvd != new); + rsvd &= ~APIC_EILVT_MASKED; + if (rsvd && rsvd != vector) + pr_info("LVT offset %d assigned for vector 0x%02x\n", + offset, rsvd); + return new; } diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index 8c3cdded6f2..359b6899a36 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -180,6 +180,7 @@ static struct apic apic_flat = { .name = "flat", .probe = flat_probe, .acpi_madt_oem_check = flat_acpi_madt_oem_check, + .apic_id_valid = default_apic_id_valid, .apic_id_registered = flat_apic_id_registered, .irq_delivery_mode = dest_LowestPrio, @@ -337,6 +338,7 @@ static struct apic apic_physflat = { .name = "physical flat", .probe = physflat_probe, .acpi_madt_oem_check = physflat_acpi_madt_oem_check, + .apic_id_valid = default_apic_id_valid, .apic_id_registered = flat_apic_id_registered, .irq_delivery_mode = dest_Fixed, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 775b82bc655..634ae6cdd5c 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -124,6 +124,7 @@ struct apic apic_noop = { .probe = noop_probe, .acpi_madt_oem_check = NULL, + .apic_id_valid = default_apic_id_valid, .apic_id_registered = noop_apic_id_registered, .irq_delivery_mode = dest_LowestPrio, diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 09d3d8c1cd9..899803e0321 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -56,6 +56,12 @@ static unsigned int read_xapic_id(void) return get_apic_id(apic_read(APIC_ID)); } +static int numachip_apic_id_valid(int apicid) +{ + /* Trust what bootloader passes in MADT */ + return 1; +} + static int numachip_apic_id_registered(void) { return physid_isset(read_xapic_id(), phys_cpu_present_map); @@ -238,6 +244,7 @@ static struct apic apic_numachip __refconst = { .name = "NumaConnect system", .probe = numachip_probe, .acpi_madt_oem_check = numachip_acpi_madt_oem_check, + .apic_id_valid = numachip_apic_id_valid, .apic_id_registered = numachip_apic_id_registered, .irq_delivery_mode = dest_Fixed, diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 521bead0113..0cdec7065af 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -198,6 +198,7 @@ static struct apic apic_bigsmp = { .name = "bigsmp", .probe = probe_bigsmp, .acpi_madt_oem_check = NULL, + .apic_id_valid = default_apic_id_valid, .apic_id_registered = bigsmp_apic_id_registered, .irq_delivery_mode = dest_Fixed, diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c index 5d513bc47b6..e42d1d3b913 100644 --- a/arch/x86/kernel/apic/es7000_32.c +++ b/arch/x86/kernel/apic/es7000_32.c @@ -625,6 +625,7 @@ static struct apic __refdata apic_es7000_cluster = { .name = "es7000", .probe = probe_es7000, .acpi_madt_oem_check = es7000_acpi_madt_oem_check_cluster, + .apic_id_valid = default_apic_id_valid, .apic_id_registered = es7000_apic_id_registered, .irq_delivery_mode = dest_LowestPrio, @@ -690,6 +691,7 @@ static struct apic __refdata apic_es7000 = { .name = "es7000", .probe = probe_es7000, .acpi_madt_oem_check = es7000_acpi_madt_oem_check, + .apic_id_valid = default_apic_id_valid, .apic_id_registered = es7000_apic_id_registered, .irq_delivery_mode = dest_Fixed, diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index fb072754bc1..e88300d8e80 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -64,9 +64,28 @@ #include <asm/apic.h> #define __apicdebuginit(type) static type __init + #define for_each_irq_pin(entry, head) \ for (entry = head; entry; entry = entry->next) +static void __init __ioapic_init_mappings(void); + +static unsigned int __io_apic_read (unsigned int apic, unsigned int reg); +static void __io_apic_write (unsigned int apic, unsigned int reg, unsigned int val); +static void __io_apic_modify(unsigned int apic, unsigned int reg, unsigned int val); + +static struct io_apic_ops io_apic_ops = { + .init = __ioapic_init_mappings, + .read = __io_apic_read, + .write = __io_apic_write, + .modify = __io_apic_modify, +}; + +void __init set_io_apic_ops(const struct io_apic_ops *ops) +{ + io_apic_ops = *ops; +} + /* * Is the SiS APIC rmw bug present ? * -1 = don't know, 0 = no, 1 = yes @@ -294,6 +313,22 @@ static void free_irq_at(unsigned int at, struct irq_cfg *cfg) irq_free_desc(at); } +static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg) +{ + return io_apic_ops.read(apic, reg); +} + +static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value) +{ + io_apic_ops.write(apic, reg, value); +} + +static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value) +{ + io_apic_ops.modify(apic, reg, value); +} + + struct io_apic { unsigned int index; unsigned int unused[3]; @@ -314,16 +349,17 @@ static inline void io_apic_eoi(unsigned int apic, unsigned int vector) writel(vector, &io_apic->eoi); } -static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg) +static unsigned int __io_apic_read(unsigned int apic, unsigned int reg) { struct io_apic __iomem *io_apic = io_apic_base(apic); writel(reg, &io_apic->index); return readl(&io_apic->data); } -static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value) +static void __io_apic_write(unsigned int apic, unsigned int reg, unsigned int value) { struct io_apic __iomem *io_apic = io_apic_base(apic); + writel(reg, &io_apic->index); writel(value, &io_apic->data); } @@ -334,7 +370,7 @@ static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned i * * Older SiS APIC requires we rewrite the index register */ -static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value) +static void __io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value) { struct io_apic __iomem *io_apic = io_apic_base(apic); @@ -377,6 +413,7 @@ static struct IO_APIC_route_entry __ioapic_read_entry(int apic, int pin) eu.w1 = io_apic_read(apic, 0x10 + 2 * pin); eu.w2 = io_apic_read(apic, 0x11 + 2 * pin); + return eu.entry; } @@ -384,9 +421,11 @@ static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin) { union entry_union eu; unsigned long flags; + raw_spin_lock_irqsave(&ioapic_lock, flags); eu.entry = __ioapic_read_entry(apic, pin); raw_spin_unlock_irqrestore(&ioapic_lock, flags); + return eu.entry; } @@ -396,8 +435,7 @@ static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin) * the interrupt, and we need to make sure the entry is fully populated * before that happens. */ -static void -__ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e) +static void __ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e) { union entry_union eu = {{0, 0}}; @@ -409,6 +447,7 @@ __ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e) static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e) { unsigned long flags; + raw_spin_lock_irqsave(&ioapic_lock, flags); __ioapic_write_entry(apic, pin, e); raw_spin_unlock_irqrestore(&ioapic_lock, flags); @@ -435,8 +474,7 @@ static void ioapic_mask_entry(int apic, int pin) * shared ISA-space IRQs, so we have to support them. We are super * fast in the common case, and fast for shared ISA-space IRQs. */ -static int -__add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin) +static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin) { struct irq_pin_list **last, *entry; @@ -521,6 +559,7 @@ static void io_apic_sync(struct irq_pin_list *entry) * a dummy read from the IO-APIC */ struct io_apic __iomem *io_apic; + io_apic = io_apic_base(entry->apic); readl(&io_apic->data); } @@ -2512,21 +2551,73 @@ static void ack_apic_edge(struct irq_data *data) atomic_t irq_mis_count; -static void ack_apic_level(struct irq_data *data) -{ - struct irq_cfg *cfg = data->chip_data; - int i, do_unmask_irq = 0, irq = data->irq; - unsigned long v; - - irq_complete_move(cfg); #ifdef CONFIG_GENERIC_PENDING_IRQ +static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg) +{ /* If we are moving the irq we need to mask it */ if (unlikely(irqd_is_setaffinity_pending(data))) { - do_unmask_irq = 1; mask_ioapic(cfg); + return true; } + return false; +} + +static inline void ioapic_irqd_unmask(struct irq_data *data, + struct irq_cfg *cfg, bool masked) +{ + if (unlikely(masked)) { + /* Only migrate the irq if the ack has been received. + * + * On rare occasions the broadcast level triggered ack gets + * delayed going to ioapics, and if we reprogram the + * vector while Remote IRR is still set the irq will never + * fire again. + * + * To prevent this scenario we read the Remote IRR bit + * of the ioapic. This has two effects. + * - On any sane system the read of the ioapic will + * flush writes (and acks) going to the ioapic from + * this cpu. + * - We get to see if the ACK has actually been delivered. + * + * Based on failed experiments of reprogramming the + * ioapic entry from outside of irq context starting + * with masking the ioapic entry and then polling until + * Remote IRR was clear before reprogramming the + * ioapic I don't trust the Remote IRR bit to be + * completey accurate. + * + * However there appears to be no other way to plug + * this race, so if the Remote IRR bit is not + * accurate and is causing problems then it is a hardware bug + * and you can go talk to the chipset vendor about it. + */ + if (!io_apic_level_ack_pending(cfg)) + irq_move_masked_irq(data); + unmask_ioapic(cfg); + } +} +#else +static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg) +{ + return false; +} +static inline void ioapic_irqd_unmask(struct irq_data *data, + struct irq_cfg *cfg, bool masked) +{ +} #endif +static void ack_apic_level(struct irq_data *data) +{ + struct irq_cfg *cfg = data->chip_data; + int i, irq = data->irq; + unsigned long v; + bool masked; + + irq_complete_move(cfg); + masked = ioapic_irqd_mask(data, cfg); + /* * It appears there is an erratum which affects at least version 0x11 * of I/O APIC (that's the 82093AA and cores integrated into various @@ -2581,38 +2672,7 @@ static void ack_apic_level(struct irq_data *data) eoi_ioapic_irq(irq, cfg); } - /* Now we can move and renable the irq */ - if (unlikely(do_unmask_irq)) { - /* Only migrate the irq if the ack has been received. - * - * On rare occasions the broadcast level triggered ack gets - * delayed going to ioapics, and if we reprogram the - * vector while Remote IRR is still set the irq will never - * fire again. - * - * To prevent this scenario we read the Remote IRR bit - * of the ioapic. This has two effects. - * - On any sane system the read of the ioapic will - * flush writes (and acks) going to the ioapic from - * this cpu. - * - We get to see if the ACK has actually been delivered. - * - * Based on failed experiments of reprogramming the - * ioapic entry from outside of irq context starting - * with masking the ioapic entry and then polling until - * Remote IRR was clear before reprogramming the - * ioapic I don't trust the Remote IRR bit to be - * completey accurate. - * - * However there appears to be no other way to plug - * this race, so if the Remote IRR bit is not - * accurate and is causing problems then it is a hardware bug - * and you can go talk to the chipset vendor about it. - */ - if (!io_apic_level_ack_pending(cfg)) - irq_move_masked_irq(data); - unmask_ioapic(cfg); - } + ioapic_irqd_unmask(data, cfg, masked); } #ifdef CONFIG_IRQ_REMAP @@ -3873,6 +3933,11 @@ static struct resource * __init ioapic_setup_resources(int nr_ioapics) void __init ioapic_and_gsi_init(void) { + io_apic_ops.init(); +} + +static void __init __ioapic_init_mappings(void) +{ unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0; struct resource *ioapic_res; int i; @@ -3967,18 +4032,36 @@ int mp_find_ioapic_pin(int ioapic, u32 gsi) static __init int bad_ioapic(unsigned long address) { if (nr_ioapics >= MAX_IO_APICS) { - printk(KERN_WARNING "WARNING: Max # of I/O APICs (%d) exceeded " - "(found %d), skipping\n", MAX_IO_APICS, nr_ioapics); + pr_warn("WARNING: Max # of I/O APICs (%d) exceeded (found %d), skipping\n", + MAX_IO_APICS, nr_ioapics); return 1; } if (!address) { - printk(KERN_WARNING "WARNING: Bogus (zero) I/O APIC address" - " found in table, skipping!\n"); + pr_warn("WARNING: Bogus (zero) I/O APIC address found in table, skipping!\n"); return 1; } return 0; } +static __init int bad_ioapic_register(int idx) +{ + union IO_APIC_reg_00 reg_00; + union IO_APIC_reg_01 reg_01; + union IO_APIC_reg_02 reg_02; + + reg_00.raw = io_apic_read(idx, 0); + reg_01.raw = io_apic_read(idx, 1); + reg_02.raw = io_apic_read(idx, 2); + + if (reg_00.raw == -1 && reg_01.raw == -1 && reg_02.raw == -1) { + pr_warn("I/O APIC 0x%x registers return all ones, skipping!\n", + mpc_ioapic_addr(idx)); + return 1; + } + + return 0; +} + void __init mp_register_ioapic(int id, u32 address, u32 gsi_base) { int idx = 0; @@ -3995,6 +4078,12 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base) ioapics[idx].mp_config.apicaddr = address; set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address); + + if (bad_ioapic_register(idx)) { + clear_fixmap(FIX_IO_APIC_BASE_0 + idx); + return; + } + ioapics[idx].mp_config.apicid = io_apic_unique_id(id); ioapics[idx].mp_config.apicver = io_apic_get_version(idx); @@ -4015,10 +4104,10 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base) if (gsi_cfg->gsi_end >= gsi_top) gsi_top = gsi_cfg->gsi_end + 1; - printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%x, " - "GSI %d-%d\n", idx, mpc_ioapic_id(idx), - mpc_ioapic_ver(idx), mpc_ioapic_addr(idx), - gsi_cfg->gsi_base, gsi_cfg->gsi_end); + pr_info("IOAPIC[%d]: apic_id %d, version %d, address 0x%x, GSI %d-%d\n", + idx, mpc_ioapic_id(idx), + mpc_ioapic_ver(idx), mpc_ioapic_addr(idx), + gsi_cfg->gsi_base, gsi_cfg->gsi_end); nr_ioapics++; } diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index c4a61ca1349..00d2422ca7c 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -478,6 +478,7 @@ static struct apic __refdata apic_numaq = { .name = "NUMAQ", .probe = probe_numaq, .acpi_madt_oem_check = NULL, + .apic_id_valid = default_apic_id_valid, .apic_id_registered = numaq_apic_id_registered, .irq_delivery_mode = dest_LowestPrio, diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 0787bb3412f..ff2c1b9aac4 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -92,6 +92,7 @@ static struct apic apic_default = { .name = "default", .probe = probe_default, .acpi_madt_oem_check = NULL, + .apic_id_valid = default_apic_id_valid, .apic_id_registered = default_apic_id_registered, .irq_delivery_mode = dest_LowestPrio, diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c index 19114423c58..fea000b27f0 100644 --- a/arch/x86/kernel/apic/summit_32.c +++ b/arch/x86/kernel/apic/summit_32.c @@ -496,6 +496,7 @@ static struct apic apic_summit = { .name = "summit", .probe = probe_summit, .acpi_madt_oem_check = summit_acpi_madt_oem_check, + .apic_id_valid = default_apic_id_valid, .apic_id_registered = summit_apic_id_registered, .irq_delivery_mode = dest_LowestPrio, diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 50079587582..48f3103b3c9 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -213,6 +213,7 @@ static struct apic apic_x2apic_cluster = { .name = "cluster x2apic", .probe = x2apic_cluster_probe, .acpi_madt_oem_check = x2apic_acpi_madt_oem_check, + .apic_id_valid = x2apic_apic_id_valid, .apic_id_registered = x2apic_apic_id_registered, .irq_delivery_mode = dest_LowestPrio, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index f5373dfde21..8a778db45e3 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -119,6 +119,7 @@ static struct apic apic_x2apic_phys = { .name = "physical x2apic", .probe = x2apic_phys_probe, .acpi_madt_oem_check = x2apic_acpi_madt_oem_check, + .apic_id_valid = x2apic_apic_id_valid, .apic_id_registered = x2apic_apic_id_registered, .irq_delivery_mode = dest_Fixed, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 9d59bbacd4e..87bfa69e216 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -266,6 +266,11 @@ static void uv_send_IPI_all(int vector) uv_send_IPI_mask(cpu_online_mask, vector); } +static int uv_apic_id_valid(int apicid) +{ + return 1; +} + static int uv_apic_id_registered(void) { return 1; @@ -351,6 +356,7 @@ static struct apic __refdata apic_x2apic_uv_x = { .name = "UV large system", .probe = uv_probe, .acpi_madt_oem_check = uv_acpi_madt_oem_check, + .apic_id_valid = uv_apic_id_valid, .apic_id_registered = uv_apic_id_registered, .irq_delivery_mode = dest_Fixed, @@ -769,7 +775,12 @@ void __init uv_system_init(void) for(i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++) uv_possible_blades += hweight64(uv_read_local_mmr( UVH_NODE_PRESENT_TABLE + i * 8)); - printk(KERN_DEBUG "UV: Found %d blades\n", uv_num_possible_blades()); + + /* uv_num_possible_blades() is really the hub count */ + printk(KERN_INFO "UV: Found %d blades, %d hubs\n", + is_uv1_hub() ? uv_num_possible_blades() : + (uv_num_possible_blades() + 1) / 2, + uv_num_possible_blades()); bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades(); uv_blade_info = kzalloc(bytes, GFP_KERNEL); diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index a46bd383953..459e78cbf61 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -231,7 +231,6 @@ #include <linux/syscore_ops.h> #include <linux/i8253.h> -#include <asm/system.h> #include <asm/uaccess.h> #include <asm/desc.h> #include <asm/olpc.h> @@ -383,21 +382,21 @@ static int ignore_sys_suspend; static int ignore_normal_resume; static int bounce_interval __read_mostly = DEFAULT_BOUNCE_INTERVAL; -static int debug __read_mostly; -static int smp __read_mostly; +static bool debug __read_mostly; +static bool smp __read_mostly; static int apm_disabled = -1; #ifdef CONFIG_SMP -static int power_off; +static bool power_off; #else -static int power_off = 1; +static bool power_off = 1; #endif -static int realmode_power_off; +static bool realmode_power_off; #ifdef CONFIG_APM_ALLOW_INTS -static int allow_ints = 1; +static bool allow_ints = 1; #else -static int allow_ints; +static bool allow_ints; #endif -static int broken_psr; +static bool broken_psr; static DECLARE_WAIT_QUEUE_HEAD(apm_waitqueue); static DECLARE_WAIT_QUEUE_HEAD(apm_suspend_waitqueue); @@ -1234,8 +1233,7 @@ static int suspend(int vetoable) struct apm_user *as; dpm_suspend_start(PMSG_SUSPEND); - - dpm_suspend_noirq(PMSG_SUSPEND); + dpm_suspend_end(PMSG_SUSPEND); local_irq_disable(); syscore_suspend(); @@ -1259,9 +1257,9 @@ static int suspend(int vetoable) syscore_resume(); local_irq_enable(); - dpm_resume_noirq(PMSG_RESUME); - + dpm_resume_start(PMSG_RESUME); dpm_resume_end(PMSG_RESUME); + queue_event(APM_NORMAL_RESUME, NULL); spin_lock(&user_list_lock); for (as = user_list; as != NULL; as = as->next) { @@ -1277,7 +1275,7 @@ static void standby(void) { int err; - dpm_suspend_noirq(PMSG_SUSPEND); + dpm_suspend_end(PMSG_SUSPEND); local_irq_disable(); syscore_suspend(); @@ -1291,7 +1289,7 @@ static void standby(void) syscore_resume(); local_irq_enable(); - dpm_resume_noirq(PMSG_RESUME); + dpm_resume_start(PMSG_RESUME); } static apm_event_t get_event(void) diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 4f13fafc526..68de2dc962e 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -67,4 +67,6 @@ void common(void) { OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch); OFFSET(BP_version, boot_params, hdr.version); OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment); + OFFSET(BP_pref_address, boot_params, hdr.pref_address); + OFFSET(BP_code32_start, boot_params, hdr.code32_start); } diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index 395a10e6806..85d98ab15cd 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -3,6 +3,11 @@ #include <linux/lguest.h> #include "../../../drivers/lguest/lg.h" +#define __SYSCALL_I386(nr, sym, compat) [nr] = 1, +static char syscalls[] = { +#include <asm/syscalls_32.h> +}; + /* workaround for a warning with -Wmissing-prototypes */ void foo(void); @@ -76,4 +81,7 @@ void foo(void) OFFSET(LGUEST_PAGES_regs_errcode, lguest_pages, regs.errcode); OFFSET(LGUEST_PAGES_regs, lguest_pages, regs); #endif + BLANK(); + DEFINE(__NR_syscall_max, sizeof(syscalls) - 1); + DEFINE(NR_syscalls, sizeof(syscalls)); } diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index e72a1194af2..1b4754f82ba 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -1,11 +1,18 @@ #include <asm/ia32.h> -#define __NO_STUBS 1 -#undef __SYSCALL -#undef _ASM_X86_UNISTD_64_H -#define __SYSCALL(nr, sym) [nr] = 1, -static char syscalls[] = { -#include <asm/unistd.h> +#define __SYSCALL_64(nr, sym, compat) [nr] = 1, +#define __SYSCALL_COMMON(nr, sym, compat) [nr] = 1, +#ifdef CONFIG_X86_X32_ABI +# define __SYSCALL_X32(nr, sym, compat) [nr] = 1, +#else +# define __SYSCALL_X32(nr, sym, compat) /* nothing */ +#endif +static char syscalls_64[] = { +#include <asm/syscalls_64.h> +}; +#define __SYSCALL_I386(nr, sym, compat) [nr] = 1, +static char syscalls_ia32[] = { +#include <asm/syscalls_32.h> }; int main(void) @@ -72,7 +79,11 @@ int main(void) OFFSET(TSS_ist, tss_struct, x86_tss.ist); BLANK(); - DEFINE(__NR_syscall_max, sizeof(syscalls) - 1); + DEFINE(__NR_syscall_max, sizeof(syscalls_64) - 1); + DEFINE(NR_syscalls, sizeof(syscalls_64)); + + DEFINE(__NR_ia32_syscall_max, sizeof(syscalls_ia32) - 1); + DEFINE(IA32_NR_syscalls, sizeof(syscalls_ia32)); return 0; } diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 25f24dccdcf..6ab6aa2fdfd 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -16,6 +16,7 @@ obj-y := intel_cacheinfo.o scattered.o topology.o obj-y += proc.o capflags.o powerflags.o common.o obj-y += vmware.o hypervisor.o sched.o mshyperv.o obj-y += rdrand.o +obj-y += match.o obj-$(CONFIG_X86_32) += bugs.o obj-$(CONFIG_X86_64) += bugs_64.o diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index f4773f4aae3..0a44b90602b 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -5,6 +5,7 @@ #include <linux/mm.h> #include <linux/io.h> +#include <linux/sched.h> #include <asm/processor.h> #include <asm/apic.h> #include <asm/cpu.h> @@ -456,6 +457,8 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); + if (!check_tsc_unstable()) + sched_clock_stable = 1; } #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 850f2963a42..67e258362a3 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -18,6 +18,7 @@ #include <asm/archrandom.h> #include <asm/hypervisor.h> #include <asm/processor.h> +#include <asm/debugreg.h> #include <asm/sections.h> #include <linux/topology.h> #include <linux/cpumask.h> @@ -28,6 +29,7 @@ #include <asm/apic.h> #include <asm/desc.h> #include <asm/i387.h> +#include <asm/fpu-internal.h> #include <asm/mtrr.h> #include <linux/numa.h> #include <asm/asm.h> @@ -933,7 +935,7 @@ static const struct msr_range msr_range_array[] __cpuinitconst = { { 0xc0011000, 0xc001103b}, }; -static void __cpuinit print_cpu_msr(void) +static void __cpuinit __print_cpu_msr(void) { unsigned index_min, index_max; unsigned index; @@ -997,13 +999,13 @@ void __cpuinit print_cpu_info(struct cpuinfo_x86 *c) else printk(KERN_CONT "\n"); -#ifdef CONFIG_SMP + print_cpu_msr(c); +} + +void __cpuinit print_cpu_msr(struct cpuinfo_x86 *c) +{ if (c->cpu_index < show_msr) - print_cpu_msr(); -#else - if (show_msr) - print_cpu_msr(); -#endif + __print_cpu_msr(); } static __init int setup_disablecpuid(char *arg) @@ -1021,6 +1023,8 @@ __setup("clearcpuid=", setup_disablecpuid); #ifdef CONFIG_X86_64 struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table }; +struct desc_ptr nmi_idt_descr = { NR_VECTORS * 16 - 1, + (unsigned long) nmi_idt_table }; DEFINE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __aligned(PAGE_SIZE); @@ -1042,6 +1046,8 @@ DEFINE_PER_CPU(char *, irq_stack_ptr) = DEFINE_PER_CPU(unsigned int, irq_count) = -1; +DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); + /* * Special IST stacks which the CPU switches to when it calls * an IST-marked descriptor entry. Up to 7 stacks (hardware @@ -1085,10 +1091,31 @@ unsigned long kernel_eflags; */ DEFINE_PER_CPU(struct orig_ist, orig_ist); +static DEFINE_PER_CPU(unsigned long, debug_stack_addr); +DEFINE_PER_CPU(int, debug_stack_usage); + +int is_debug_stack(unsigned long addr) +{ + return __get_cpu_var(debug_stack_usage) || + (addr <= __get_cpu_var(debug_stack_addr) && + addr > (__get_cpu_var(debug_stack_addr) - DEBUG_STKSZ)); +} + +void debug_stack_set_zero(void) +{ + load_idt((const struct desc_ptr *)&nmi_idt_descr); +} + +void debug_stack_reset(void) +{ + load_idt((const struct desc_ptr *)&idt_descr); +} + #else /* CONFIG_X86_64 */ DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task; EXPORT_PER_CPU_SYMBOL(current_task); +DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); #ifdef CONFIG_CC_STACKPROTECTOR DEFINE_PER_CPU_ALIGNED(struct stack_canary, stack_canary); @@ -1212,6 +1239,8 @@ void __cpuinit cpu_init(void) estacks += exception_stack_sizes[v]; oist->ist[v] = t->x86_tss.ist[v] = (unsigned long)estacks; + if (v == DEBUG_STACK-1) + per_cpu(debug_stack_addr, cpu) = (unsigned long)estacks; } } diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 6b45e5e7a90..73d08ed98a6 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -326,8 +326,7 @@ static void __cpuinit amd_calc_l3_indices(struct amd_northbridge *nb) l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1; } -static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, - int index) +static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, int index) { int node; @@ -725,14 +724,16 @@ static DEFINE_PER_CPU(struct _cpuid4_info *, ici_cpuid4_info); #define CPUID4_INFO_IDX(x, y) (&((per_cpu(ici_cpuid4_info, x))[y])) #ifdef CONFIG_SMP -static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) + +static int __cpuinit cache_shared_amd_cpu_map_setup(unsigned int cpu, int index) { - struct _cpuid4_info *this_leaf, *sibling_leaf; - unsigned long num_threads_sharing; - int index_msb, i, sibling; + struct _cpuid4_info *this_leaf; + int ret, i, sibling; struct cpuinfo_x86 *c = &cpu_data(cpu); - if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) { + ret = 0; + if (index == 3) { + ret = 1; for_each_cpu(i, cpu_llc_shared_mask(cpu)) { if (!per_cpu(ici_cpuid4_info, i)) continue; @@ -743,8 +744,35 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) set_bit(sibling, this_leaf->shared_cpu_map); } } - return; + } else if ((c->x86 == 0x15) && ((index == 1) || (index == 2))) { + ret = 1; + for_each_cpu(i, cpu_sibling_mask(cpu)) { + if (!per_cpu(ici_cpuid4_info, i)) + continue; + this_leaf = CPUID4_INFO_IDX(i, index); + for_each_cpu(sibling, cpu_sibling_mask(cpu)) { + if (!cpu_online(sibling)) + continue; + set_bit(sibling, this_leaf->shared_cpu_map); + } + } } + + return ret; +} + +static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) +{ + struct _cpuid4_info *this_leaf, *sibling_leaf; + unsigned long num_threads_sharing; + int index_msb, i; + struct cpuinfo_x86 *c = &cpu_data(cpu); + + if (c->x86_vendor == X86_VENDOR_AMD) { + if (cache_shared_amd_cpu_map_setup(cpu, index)) + return; + } + this_leaf = CPUID4_INFO_IDX(cpu, index); num_threads_sharing = 1 + this_leaf->base.eax.split.num_threads_sharing; diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c new file mode 100644 index 00000000000..5502b289341 --- /dev/null +++ b/arch/x86/kernel/cpu/match.c @@ -0,0 +1,91 @@ +#include <asm/cpu_device_id.h> +#include <asm/processor.h> +#include <linux/cpu.h> +#include <linux/module.h> +#include <linux/slab.h> + +/** + * x86_match_cpu - match current CPU again an array of x86_cpu_ids + * @match: Pointer to array of x86_cpu_ids. Last entry terminated with + * {}. + * + * Return the entry if the current CPU matches the entries in the + * passed x86_cpu_id match table. Otherwise NULL. The match table + * contains vendor (X86_VENDOR_*), family, model and feature bits or + * respective wildcard entries. + * + * A typical table entry would be to match a specific CPU + * { X86_VENDOR_INTEL, 6, 0x12 } + * or to match a specific CPU feature + * { X86_FEATURE_MATCH(X86_FEATURE_FOOBAR) } + * + * Fields can be wildcarded with %X86_VENDOR_ANY, %X86_FAMILY_ANY, + * %X86_MODEL_ANY, %X86_FEATURE_ANY or 0 (except for vendor) + * + * Arrays used to match for this should also be declared using + * MODULE_DEVICE_TABLE(x86_cpu, ...) + * + * This always matches against the boot cpu, assuming models and features are + * consistent over all CPUs. + */ +const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match) +{ + const struct x86_cpu_id *m; + struct cpuinfo_x86 *c = &boot_cpu_data; + + for (m = match; m->vendor | m->family | m->model | m->feature; m++) { + if (m->vendor != X86_VENDOR_ANY && c->x86_vendor != m->vendor) + continue; + if (m->family != X86_FAMILY_ANY && c->x86 != m->family) + continue; + if (m->model != X86_MODEL_ANY && c->x86_model != m->model) + continue; + if (m->feature != X86_FEATURE_ANY && !cpu_has(c, m->feature)) + continue; + return m; + } + return NULL; +} +EXPORT_SYMBOL(x86_match_cpu); + +ssize_t arch_print_cpu_modalias(struct device *dev, + struct device_attribute *attr, + char *bufptr) +{ + int size = PAGE_SIZE; + int i, n; + char *buf = bufptr; + + n = snprintf(buf, size, "x86cpu:vendor:%04X:family:%04X:" + "model:%04X:feature:", + boot_cpu_data.x86_vendor, + boot_cpu_data.x86, + boot_cpu_data.x86_model); + size -= n; + buf += n; + size -= 1; + for (i = 0; i < NCAPINTS*32; i++) { + if (boot_cpu_has(i)) { + n = snprintf(buf, size, ",%04X", i); + if (n >= size) { + WARN(1, "x86 features overflow page\n"); + break; + } + size -= n; + buf += n; + } + } + *buf++ = '\n'; + return buf - bufptr; +} + +int arch_cpu_uevent(struct device *dev, struct kobj_uevent_env *env) +{ + char *buf = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (buf) { + arch_print_cpu_modalias(NULL, NULL, buf); + add_uevent_var(env, "MODALIAS=%s", buf); + kfree(buf); + } + return 0; +} diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 7395d5f4272..0c82091b165 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -54,7 +54,14 @@ static struct severity { #define MASK(x, y) .mask = x, .result = y #define MCI_UC_S (MCI_STATUS_UC|MCI_STATUS_S) #define MCI_UC_SAR (MCI_STATUS_UC|MCI_STATUS_S|MCI_STATUS_AR) +#define MCI_ADDR (MCI_STATUS_ADDRV|MCI_STATUS_MISCV) #define MCACOD 0xffff +/* Architecturally defined codes from SDM Vol. 3B Chapter 15 */ +#define MCACOD_SCRUB 0x00C0 /* 0xC0-0xCF Memory Scrubbing */ +#define MCACOD_SCRUBMSK 0xfff0 +#define MCACOD_L3WB 0x017A /* L3 Explicit Writeback */ +#define MCACOD_DATA 0x0134 /* Data Load */ +#define MCACOD_INSTR 0x0150 /* Instruction Fetch */ MCESEV( NO, "Invalid", @@ -102,11 +109,24 @@ static struct severity { SER, BITCLR(MCI_STATUS_S) ), - /* AR add known MCACODs here */ MCESEV( PANIC, "Action required with lost events", SER, BITSET(MCI_STATUS_OVER|MCI_UC_SAR) ), + + /* known AR MCACODs: */ +#ifdef CONFIG_MEMORY_FAILURE + MCESEV( + KEEP, "HT thread notices Action required: data load error", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA), + MCGMASK(MCG_STATUS_EIPV, 0) + ), + MCESEV( + AR, "Action required: data load error", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA), + USER + ), +#endif MCESEV( PANIC, "Action required: unknown MCACOD", SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_UC_SAR) @@ -115,11 +135,11 @@ static struct severity { /* known AO MCACODs: */ MCESEV( AO, "Action optional: memory scrubbing error", - SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|0xfff0, MCI_UC_S|0x00c0) + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCACOD_SCRUBMSK, MCI_UC_S|MCACOD_SCRUB) ), MCESEV( AO, "Action optional: last level cache writeback error", - SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCACOD, MCI_UC_S|0x017a) + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCACOD, MCI_UC_S|MCACOD_L3WB) ), MCESEV( SOME, "Action optional: unknown MCACOD", diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index f22a9f7f639..d086a09c087 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -191,7 +191,7 @@ static void drain_mcelog_buffer(void) { unsigned int next, i, prev = 0; - next = rcu_dereference_check_mce(mcelog.next); + next = ACCESS_ONCE(mcelog.next); do { struct mce *m; @@ -540,6 +540,27 @@ static void mce_report_event(struct pt_regs *regs) irq_work_queue(&__get_cpu_var(mce_irq_work)); } +/* + * Read ADDR and MISC registers. + */ +static void mce_read_aux(struct mce *m, int i) +{ + if (m->status & MCI_STATUS_MISCV) + m->misc = mce_rdmsrl(MSR_IA32_MCx_MISC(i)); + if (m->status & MCI_STATUS_ADDRV) { + m->addr = mce_rdmsrl(MSR_IA32_MCx_ADDR(i)); + + /* + * Mask the reported address by the reported granularity. + */ + if (mce_ser && (m->status & MCI_STATUS_MISCV)) { + u8 shift = MCI_MISC_ADDR_LSB(m->misc); + m->addr >>= shift; + m->addr <<= shift; + } + } +} + DEFINE_PER_CPU(unsigned, mce_poll_count); /* @@ -590,10 +611,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) (m.status & (mce_ser ? MCI_STATUS_S : MCI_STATUS_UC))) continue; - if (m.status & MCI_STATUS_MISCV) - m.misc = mce_rdmsrl(MSR_IA32_MCx_MISC(i)); - if (m.status & MCI_STATUS_ADDRV) - m.addr = mce_rdmsrl(MSR_IA32_MCx_ADDR(i)); + mce_read_aux(&m, i); if (!(flags & MCP_TIMESTAMP)) m.tsc = 0; @@ -917,6 +935,49 @@ static void mce_clear_state(unsigned long *toclear) } /* + * Need to save faulting physical address associated with a process + * in the machine check handler some place where we can grab it back + * later in mce_notify_process() + */ +#define MCE_INFO_MAX 16 + +struct mce_info { + atomic_t inuse; + struct task_struct *t; + __u64 paddr; +} mce_info[MCE_INFO_MAX]; + +static void mce_save_info(__u64 addr) +{ + struct mce_info *mi; + + for (mi = mce_info; mi < &mce_info[MCE_INFO_MAX]; mi++) { + if (atomic_cmpxchg(&mi->inuse, 0, 1) == 0) { + mi->t = current; + mi->paddr = addr; + return; + } + } + + mce_panic("Too many concurrent recoverable errors", NULL, NULL); +} + +static struct mce_info *mce_find_info(void) +{ + struct mce_info *mi; + + for (mi = mce_info; mi < &mce_info[MCE_INFO_MAX]; mi++) + if (atomic_read(&mi->inuse) && mi->t == current) + return mi; + return NULL; +} + +static void mce_clear_info(struct mce_info *mi) +{ + atomic_set(&mi->inuse, 0); +} + +/* * The actual machine check handler. This only handles real * exceptions when something got corrupted coming in through int 18. * @@ -969,7 +1030,9 @@ void do_machine_check(struct pt_regs *regs, long error_code) barrier(); /* - * When no restart IP must always kill or panic. + * When no restart IP might need to kill or panic. + * Assume the worst for now, but if we find the + * severity is MCE_AR_SEVERITY we have other options. */ if (!(m.mcgstatus & MCG_STATUS_RIPV)) kill_it = 1; @@ -1023,16 +1086,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) continue; } - /* - * Kill on action required. - */ - if (severity == MCE_AR_SEVERITY) - kill_it = 1; - - if (m.status & MCI_STATUS_MISCV) - m.misc = mce_rdmsrl(MSR_IA32_MCx_MISC(i)); - if (m.status & MCI_STATUS_ADDRV) - m.addr = mce_rdmsrl(MSR_IA32_MCx_ADDR(i)); + mce_read_aux(&m, i); /* * Action optional error. Queue address for later processing. @@ -1052,6 +1106,9 @@ void do_machine_check(struct pt_regs *regs, long error_code) } } + /* mce_clear_state will clear *final, save locally for use later */ + m = *final; + if (!no_way_out) mce_clear_state(toclear); @@ -1063,27 +1120,22 @@ void do_machine_check(struct pt_regs *regs, long error_code) no_way_out = worst >= MCE_PANIC_SEVERITY; /* - * If we have decided that we just CAN'T continue, and the user - * has not set tolerant to an insane level, give up and die. - * - * This is mainly used in the case when the system doesn't - * support MCE broadcasting or it has been disabled. + * At insane "tolerant" levels we take no action. Otherwise + * we only die if we have no other choice. For less serious + * issues we try to recover, or limit damage to the current + * process. */ - if (no_way_out && tolerant < 3) - mce_panic("Fatal machine check on current CPU", final, msg); - - /* - * If the error seems to be unrecoverable, something should be - * done. Try to kill as little as possible. If we can kill just - * one task, do that. If the user has set the tolerance very - * high, don't try to do anything at all. - */ - - if (kill_it && tolerant < 3) - force_sig(SIGBUS, current); - - /* notify userspace ASAP */ - set_thread_flag(TIF_MCE_NOTIFY); + if (tolerant < 3) { + if (no_way_out) + mce_panic("Fatal machine check on current CPU", &m, msg); + if (worst == MCE_AR_SEVERITY) { + /* schedule action before return to userland */ + mce_save_info(m.addr); + set_thread_flag(TIF_MCE_NOTIFY); + } else if (kill_it) { + force_sig(SIGBUS, current); + } + } if (worst > 0) mce_report_event(regs); @@ -1094,34 +1146,57 @@ out: } EXPORT_SYMBOL_GPL(do_machine_check); -/* dummy to break dependency. actual code is in mm/memory-failure.c */ -void __attribute__((weak)) memory_failure(unsigned long pfn, int vector) +#ifndef CONFIG_MEMORY_FAILURE +int memory_failure(unsigned long pfn, int vector, int flags) { - printk(KERN_ERR "Action optional memory failure at %lx ignored\n", pfn); + /* mce_severity() should not hand us an ACTION_REQUIRED error */ + BUG_ON(flags & MF_ACTION_REQUIRED); + printk(KERN_ERR "Uncorrected memory error in page 0x%lx ignored\n" + "Rebuild kernel with CONFIG_MEMORY_FAILURE=y for smarter handling\n", pfn); + + return 0; } +#endif /* - * Called after mce notification in process context. This code - * is allowed to sleep. Call the high level VM handler to process - * any corrupted pages. - * Assume that the work queue code only calls this one at a time - * per CPU. - * Note we don't disable preemption, so this code might run on the wrong - * CPU. In this case the event is picked up by the scheduled work queue. - * This is merely a fast path to expedite processing in some common - * cases. + * Called in process context that interrupted by MCE and marked with + * TIF_MCE_NOTIFY, just before returning to erroneous userland. + * This code is allowed to sleep. + * Attempt possible recovery such as calling the high level VM handler to + * process any corrupted pages, and kill/signal current process if required. + * Action required errors are handled here. */ void mce_notify_process(void) { unsigned long pfn; - mce_notify_irq(); - while (mce_ring_get(&pfn)) - memory_failure(pfn, MCE_VECTOR); + struct mce_info *mi = mce_find_info(); + + if (!mi) + mce_panic("Lost physical address for unconsumed uncorrectable error", NULL, NULL); + pfn = mi->paddr >> PAGE_SHIFT; + + clear_thread_flag(TIF_MCE_NOTIFY); + + pr_err("Uncorrected hardware memory error in user-access at %llx", + mi->paddr); + if (memory_failure(pfn, MCE_VECTOR, MF_ACTION_REQUIRED) < 0) { + pr_err("Memory error not recovered"); + force_sig(SIGBUS, current); + } + mce_clear_info(mi); } +/* + * Action optional processing happens here (picking up + * from the list of faulting pages that do_machine_check() + * placed into the "ring"). + */ static void mce_process_work(struct work_struct *dummy) { - mce_notify_process(); + unsigned long pfn; + + while (mce_ring_get(&pfn)) + memory_failure(pfn, MCE_VECTOR, 0); } #ifdef CONFIG_X86_MCE_INTEL @@ -1211,8 +1286,6 @@ int mce_notify_irq(void) /* Not more than two messages every minute */ static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); - clear_thread_flag(TIF_MCE_NOTIFY); - if (test_and_clear_bit(0, &mce_need_notify)) { /* wake processes polling /dev/mcelog */ wake_up_interruptible(&mce_chrdev_wait); @@ -1541,6 +1614,12 @@ static int __mce_read_apei(char __user **ubuf, size_t usize) /* Error or no more MCE record */ if (rc <= 0) { mce_apei_read_done = 1; + /* + * When ERST is disabled, mce_chrdev_read() should return + * "no record" instead of "no device." + */ + if (rc == -ENODEV) + return 0; return rc; } rc = -EFAULT; @@ -1859,7 +1938,7 @@ static struct bus_type mce_subsys = { .dev_name = "machinecheck", }; -DEFINE_PER_CPU(struct device, mce_device); +DEFINE_PER_CPU(struct device *, mce_device); __cpuinitdata void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu); @@ -2001,19 +2080,27 @@ static struct device_attribute *mce_device_attrs[] = { static cpumask_var_t mce_device_initialized; +static void mce_device_release(struct device *dev) +{ + kfree(dev); +} + /* Per cpu device init. All of the cpus still share the same ctrl bank: */ static __cpuinit int mce_device_create(unsigned int cpu) { - struct device *dev = &per_cpu(mce_device, cpu); + struct device *dev; int err; int i, j; if (!mce_available(&boot_cpu_data)) return -EIO; - memset(&dev->kobj, 0, sizeof(struct kobject)); + dev = kzalloc(sizeof *dev, GFP_KERNEL); + if (!dev) + return -ENOMEM; dev->id = cpu; dev->bus = &mce_subsys; + dev->release = &mce_device_release; err = device_register(dev); if (err) @@ -2030,6 +2117,7 @@ static __cpuinit int mce_device_create(unsigned int cpu) goto error2; } cpumask_set_cpu(cpu, mce_device_initialized); + per_cpu(mce_device, cpu) = dev; return 0; error2: @@ -2046,7 +2134,7 @@ error: static __cpuinit void mce_device_remove(unsigned int cpu) { - struct device *dev = &per_cpu(mce_device, cpu); + struct device *dev = per_cpu(mce_device, cpu); int i; if (!cpumask_test_cpu(cpu, mce_device_initialized)) @@ -2060,6 +2148,7 @@ static __cpuinit void mce_device_remove(unsigned int cpu) device_unregister(dev); cpumask_clear_cpu(cpu, mce_device_initialized); + per_cpu(mce_device, cpu) = NULL; } /* Make sure there are no machine checks on offlined CPUs. */ diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index ba0b94a7e20..99b57179f91 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -523,10 +523,12 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) { int i, err = 0; struct threshold_bank *b = NULL; + struct device *dev = per_cpu(mce_device, cpu); char name[32]; sprintf(name, "threshold_bank%i", bank); +#ifdef CONFIG_SMP if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) { /* symlink */ i = cpumask_first(cpu_llc_shared_mask(cpu)); @@ -543,8 +545,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) if (!b) goto out; - err = sysfs_create_link(&per_cpu(mce_device, cpu).kobj, - b->kobj, name); + err = sysfs_create_link(&dev->kobj, b->kobj, name); if (err) goto out; @@ -553,6 +554,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) goto out; } +#endif b = kzalloc(sizeof(struct threshold_bank), GFP_KERNEL); if (!b) { @@ -565,7 +567,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) goto out; } - b->kobj = kobject_create_and_add(name, &per_cpu(mce_device, cpu).kobj); + b->kobj = kobject_create_and_add(name, &dev->kobj); if (!b->kobj) goto out_free; @@ -585,8 +587,9 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) if (i == cpu) continue; - err = sysfs_create_link(&per_cpu(mce_device, i).kobj, - b->kobj, name); + dev = per_cpu(mce_device, i); + if (dev) + err = sysfs_create_link(&dev->kobj,b->kobj, name); if (err) goto out; @@ -649,6 +652,7 @@ static void deallocate_threshold_block(unsigned int cpu, static void threshold_remove_bank(unsigned int cpu, int bank) { struct threshold_bank *b; + struct device *dev; char name[32]; int i = 0; @@ -663,7 +667,8 @@ static void threshold_remove_bank(unsigned int cpu, int bank) #ifdef CONFIG_SMP /* sibling symlink */ if (shared_bank[bank] && b->blocks->cpu != cpu) { - sysfs_remove_link(&per_cpu(mce_device, cpu).kobj, name); + dev = per_cpu(mce_device, cpu); + sysfs_remove_link(&dev->kobj, name); per_cpu(threshold_banks, cpu)[bank] = NULL; return; @@ -675,7 +680,9 @@ static void threshold_remove_bank(unsigned int cpu, int bank) if (i == cpu) continue; - sysfs_remove_link(&per_cpu(mce_device, i).kobj, name); + dev = per_cpu(mce_device, i); + if (dev) + sysfs_remove_link(&dev->kobj, name); per_cpu(threshold_banks, i)[bank] = NULL; } diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c index 5c0e6533d9b..2d5454cd2c4 100644 --- a/arch/x86/kernel/cpu/mcheck/p5.c +++ b/arch/x86/kernel/cpu/mcheck/p5.c @@ -9,7 +9,6 @@ #include <linux/smp.h> #include <asm/processor.h> -#include <asm/system.h> #include <asm/mce.h> #include <asm/msr.h> diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 67bb17a37a0..47a1870279a 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -25,7 +25,6 @@ #include <linux/cpu.h> #include <asm/processor.h> -#include <asm/system.h> #include <asm/apic.h> #include <asm/idle.h> #include <asm/mce.h> diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c index 54060f56597..2d7998fb628 100644 --- a/arch/x86/kernel/cpu/mcheck/winchip.c +++ b/arch/x86/kernel/cpu/mcheck/winchip.c @@ -8,7 +8,6 @@ #include <linux/init.h> #include <asm/processor.h> -#include <asm/system.h> #include <asm/mce.h> #include <asm/msr.h> diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 97b26356e9e..75772ae6c65 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -12,7 +12,6 @@ #include <asm/processor-flags.h> #include <asm/cpufeature.h> #include <asm/tlbflush.h> -#include <asm/system.h> #include <asm/mtrr.h> #include <asm/msr.h> #include <asm/pat.h> diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c index 79289632cb2..a041e094b8b 100644 --- a/arch/x86/kernel/cpu/mtrr/if.c +++ b/arch/x86/kernel/cpu/mtrr/if.c @@ -167,6 +167,7 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) { int err = 0; mtrr_type type; + unsigned long base; unsigned long size; struct mtrr_sentry sentry; struct mtrr_gentry gentry; @@ -267,14 +268,14 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) #endif if (gentry.regnum >= num_var_ranges) return -EINVAL; - mtrr_if->get(gentry.regnum, &gentry.base, &size, &type); + mtrr_if->get(gentry.regnum, &base, &size, &type); /* Hide entries that go above 4GB */ - if (gentry.base + size - 1 >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT)) + if (base + size - 1 >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT)) || size >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT))) gentry.base = gentry.size = gentry.type = 0; else { - gentry.base <<= PAGE_SHIFT; + gentry.base = base << PAGE_SHIFT; gentry.size = size << PAGE_SHIFT; gentry.type = type; } @@ -321,11 +322,12 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) #endif if (gentry.regnum >= num_var_ranges) return -EINVAL; - mtrr_if->get(gentry.regnum, &gentry.base, &size, &type); + mtrr_if->get(gentry.regnum, &base, &size, &type); /* Hide entries that would overflow */ if (size != (__typeof__(gentry.size))size) gentry.base = gentry.size = gentry.type = 0; else { + gentry.base = base; gentry.size = size; gentry.type = type; } diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 5adce1040b1..bb8e03407e1 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -24,13 +24,14 @@ #include <linux/slab.h> #include <linux/cpu.h> #include <linux/bitops.h> +#include <linux/device.h> #include <asm/apic.h> #include <asm/stacktrace.h> #include <asm/nmi.h> -#include <asm/compat.h> #include <asm/smp.h> #include <asm/alternative.h> +#include <asm/timer.h> #include "perf_event.h" @@ -351,6 +352,36 @@ int x86_setup_perfctr(struct perf_event *event) return 0; } +/* + * check that branch_sample_type is compatible with + * settings needed for precise_ip > 1 which implies + * using the LBR to capture ALL taken branches at the + * priv levels of the measurement + */ +static inline int precise_br_compat(struct perf_event *event) +{ + u64 m = event->attr.branch_sample_type; + u64 b = 0; + + /* must capture all branches */ + if (!(m & PERF_SAMPLE_BRANCH_ANY)) + return 0; + + m &= PERF_SAMPLE_BRANCH_KERNEL | PERF_SAMPLE_BRANCH_USER; + + if (!event->attr.exclude_user) + b |= PERF_SAMPLE_BRANCH_USER; + + if (!event->attr.exclude_kernel) + b |= PERF_SAMPLE_BRANCH_KERNEL; + + /* + * ignore PERF_SAMPLE_BRANCH_HV, not supported on x86 + */ + + return m == b; +} + int x86_pmu_hw_config(struct perf_event *event) { if (event->attr.precise_ip) { @@ -367,6 +398,36 @@ int x86_pmu_hw_config(struct perf_event *event) if (event->attr.precise_ip > precise) return -EOPNOTSUPP; + /* + * check that PEBS LBR correction does not conflict with + * whatever the user is asking with attr->branch_sample_type + */ + if (event->attr.precise_ip > 1) { + u64 *br_type = &event->attr.branch_sample_type; + + if (has_branch_stack(event)) { + if (!precise_br_compat(event)) + return -EOPNOTSUPP; + + /* branch_sample_type is compatible */ + + } else { + /* + * user did not specify branch_sample_type + * + * For PEBS fixups, we capture all + * the branches at the priv level of the + * event. + */ + *br_type = PERF_SAMPLE_BRANCH_ANY; + + if (!event->attr.exclude_user) + *br_type |= PERF_SAMPLE_BRANCH_USER; + + if (!event->attr.exclude_kernel) + *br_type |= PERF_SAMPLE_BRANCH_KERNEL; + } + } } /* @@ -424,6 +485,10 @@ static int __x86_pmu_event_init(struct perf_event *event) /* mark unused */ event->hw.extra_reg.idx = EXTRA_REG_NONE; + /* mark not used */ + event->hw.extra_reg.idx = EXTRA_REG_NONE; + event->hw.branch_reg.idx = EXTRA_REG_NONE; + return x86_pmu.hw_config(event); } @@ -577,14 +642,14 @@ static bool __perf_sched_find_counter(struct perf_sched *sched) /* Prefer fixed purpose counters */ if (x86_pmu.num_counters_fixed) { idx = X86_PMC_IDX_FIXED; - for_each_set_bit_cont(idx, c->idxmsk, X86_PMC_IDX_MAX) { + for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_MAX) { if (!__test_and_set_bit(idx, sched->state.used)) goto done; } } /* Grab the first unused counter starting with idx */ idx = sched->state.counter; - for_each_set_bit_cont(idx, c->idxmsk, X86_PMC_IDX_FIXED) { + for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_FIXED) { if (!__test_and_set_bit(idx, sched->state.used)) goto done; } @@ -1210,6 +1275,8 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) break; case CPU_STARTING: + if (x86_pmu.attr_rdpmc) + set_in_cr4(X86_CR4_PCE); if (x86_pmu.cpu_starting) x86_pmu.cpu_starting(cpu); break; @@ -1246,6 +1313,11 @@ static void __init pmu_check_apic(void) pr_info("no hardware sampling interrupt available.\n"); } +static struct attribute_group x86_pmu_format_group = { + .name = "format", + .attrs = NULL, +}; + static int __init init_hw_perf_events(void) { struct x86_pmu_quirk *quirk; @@ -1319,6 +1391,9 @@ static int __init init_hw_perf_events(void) } } + x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */ + x86_pmu_format_group.attrs = x86_pmu.format_attrs; + pr_info("... version: %d\n", x86_pmu.version); pr_info("... bit width: %d\n", x86_pmu.cntval_bits); pr_info("... generic registers: %d\n", x86_pmu.num_counters); @@ -1542,23 +1617,115 @@ static int x86_pmu_event_init(struct perf_event *event) return err; } +static int x86_pmu_event_idx(struct perf_event *event) +{ + int idx = event->hw.idx; + + if (!x86_pmu.attr_rdpmc) + return 0; + + if (x86_pmu.num_counters_fixed && idx >= X86_PMC_IDX_FIXED) { + idx -= X86_PMC_IDX_FIXED; + idx |= 1 << 30; + } + + return idx + 1; +} + +static ssize_t get_attr_rdpmc(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, 40, "%d\n", x86_pmu.attr_rdpmc); +} + +static void change_rdpmc(void *info) +{ + bool enable = !!(unsigned long)info; + + if (enable) + set_in_cr4(X86_CR4_PCE); + else + clear_in_cr4(X86_CR4_PCE); +} + +static ssize_t set_attr_rdpmc(struct device *cdev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + unsigned long val = simple_strtoul(buf, NULL, 0); + + if (!!val != !!x86_pmu.attr_rdpmc) { + x86_pmu.attr_rdpmc = !!val; + smp_call_function(change_rdpmc, (void *)val, 1); + } + + return count; +} + +static DEVICE_ATTR(rdpmc, S_IRUSR | S_IWUSR, get_attr_rdpmc, set_attr_rdpmc); + +static struct attribute *x86_pmu_attrs[] = { + &dev_attr_rdpmc.attr, + NULL, +}; + +static struct attribute_group x86_pmu_attr_group = { + .attrs = x86_pmu_attrs, +}; + +static const struct attribute_group *x86_pmu_attr_groups[] = { + &x86_pmu_attr_group, + &x86_pmu_format_group, + NULL, +}; + +static void x86_pmu_flush_branch_stack(void) +{ + if (x86_pmu.flush_branch_stack) + x86_pmu.flush_branch_stack(); +} + static struct pmu pmu = { - .pmu_enable = x86_pmu_enable, - .pmu_disable = x86_pmu_disable, + .pmu_enable = x86_pmu_enable, + .pmu_disable = x86_pmu_disable, + + .attr_groups = x86_pmu_attr_groups, .event_init = x86_pmu_event_init, - .add = x86_pmu_add, - .del = x86_pmu_del, - .start = x86_pmu_start, - .stop = x86_pmu_stop, - .read = x86_pmu_read, + .add = x86_pmu_add, + .del = x86_pmu_del, + .start = x86_pmu_start, + .stop = x86_pmu_stop, + .read = x86_pmu_read, .start_txn = x86_pmu_start_txn, .cancel_txn = x86_pmu_cancel_txn, .commit_txn = x86_pmu_commit_txn, + + .event_idx = x86_pmu_event_idx, + .flush_branch_stack = x86_pmu_flush_branch_stack, }; +void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) +{ + userpg->cap_usr_time = 0; + userpg->cap_usr_rdpmc = x86_pmu.attr_rdpmc; + userpg->pmc_width = x86_pmu.cntval_bits; + + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) + return; + + if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) + return; + + userpg->cap_usr_time = 1; + userpg->time_mult = this_cpu_read(cyc2ns); + userpg->time_shift = CYC2NS_SCALE_FACTOR; + userpg->time_offset = this_cpu_read(cyc2ns_offset) - now; +} + /* * callchain support */ @@ -1595,6 +1762,9 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs) } #ifdef CONFIG_COMPAT + +#include <asm/compat.h> + static inline int perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) { diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 8944062f46e..6638aaf5449 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -33,6 +33,7 @@ enum extra_reg_type { EXTRA_REG_RSP_0 = 0, /* offcore_response_0 */ EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */ + EXTRA_REG_LBR = 2, /* lbr_select */ EXTRA_REG_MAX /* number of entries needed */ }; @@ -130,6 +131,8 @@ struct cpu_hw_events { void *lbr_context; struct perf_branch_stack lbr_stack; struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; + struct er_account *lbr_sel; + u64 br_sel; /* * Intel host/guest exclude bits @@ -147,7 +150,9 @@ struct cpu_hw_events { /* * AMD specific bits */ - struct amd_nb *amd_nb; + struct amd_nb *amd_nb; + /* Inverted mask of bits to clear in the perf_ctr ctrl registers */ + u64 perf_ctr_virt_mask; void *kfree_on_online; }; @@ -266,6 +271,29 @@ struct x86_pmu_quirk { void (*func)(void); }; +union x86_pmu_config { + struct { + u64 event:8, + umask:8, + usr:1, + os:1, + edge:1, + pc:1, + interrupt:1, + __reserved1:1, + en:1, + inv:1, + cmask:8, + event2:4, + __reserved2:4, + go:1, + ho:1; + } bits; + u64 value; +}; + +#define X86_CONFIG(args...) ((union x86_pmu_config){.bits = {args}}).value + /* * struct x86_pmu - generic x86 pmu */ @@ -307,10 +335,20 @@ struct x86_pmu { struct x86_pmu_quirk *quirks; int perfctr_second_write; + /* + * sysfs attrs + */ + int attr_rdpmc; + struct attribute **format_attrs; + + /* + * CPU Hotplug hooks + */ int (*cpu_prepare)(int cpu); void (*cpu_starting)(int cpu); void (*cpu_dying)(int cpu); void (*cpu_dead)(int cpu); + void (*flush_branch_stack)(void); /* * Intel Arch Perfmon v2+ @@ -332,6 +370,8 @@ struct x86_pmu { */ unsigned long lbr_tos, lbr_from, lbr_to; /* MSR base regs */ int lbr_nr; /* hardware stack size */ + u64 lbr_sel_mask; /* LBR_SELECT valid bits */ + const int *lbr_sel_map; /* lbr_select mappings */ /* * Extra registers for events @@ -417,9 +457,11 @@ void x86_pmu_disable_all(void); static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, u64 enable_mask) { + u64 disable_mask = __this_cpu_read(cpu_hw_events.perf_ctr_virt_mask); + if (hwc->extra_reg.reg) wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config); - wrmsrl(hwc->config_base, hwc->config | enable_mask); + wrmsrl(hwc->config_base, (hwc->config | enable_mask) & ~disable_mask); } void x86_pmu_enable_all(int added); @@ -443,6 +485,15 @@ extern struct event_constraint emptyconstraint; extern struct event_constraint unconstrained; +static inline bool kernel_ip(unsigned long ip) +{ +#ifdef CONFIG_X86_32 + return ip > PAGE_OFFSET; +#else + return (long)ip < 0; +#endif +} + #ifdef CONFIG_CPU_SUP_AMD int amd_pmu_init(void); @@ -523,6 +574,10 @@ void intel_pmu_lbr_init_nhm(void); void intel_pmu_lbr_init_atom(void); +void intel_pmu_lbr_init_snb(void); + +int intel_pmu_setup_lbr_filter(struct perf_event *event); + int p4_pmu_init(void); int p6_pmu_init(void); diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 0397b23be8e..95e7fe1c5f0 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -1,4 +1,5 @@ #include <linux/perf_event.h> +#include <linux/export.h> #include <linux/types.h> #include <linux/init.h> #include <linux/slab.h> @@ -138,6 +139,9 @@ static int amd_pmu_hw_config(struct perf_event *event) if (ret) return ret; + if (has_branch_stack(event)) + return -EOPNOTSUPP; + if (event->attr.exclude_host && event->attr.exclude_guest) /* * When HO == GO == 1 the hardware treats that as GO == HO == 0 @@ -357,7 +361,9 @@ static void amd_pmu_cpu_starting(int cpu) struct amd_nb *nb; int i, nb_id; - if (boot_cpu_data.x86_max_cores < 2) + cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY; + + if (boot_cpu_data.x86_max_cores < 2 || boot_cpu_data.x86 == 0x15) return; nb_id = amd_get_nb_id(cpu); @@ -398,6 +404,21 @@ static void amd_pmu_cpu_dead(int cpu) } } +PMU_FORMAT_ATTR(event, "config:0-7,32-35"); +PMU_FORMAT_ATTR(umask, "config:8-15" ); +PMU_FORMAT_ATTR(edge, "config:18" ); +PMU_FORMAT_ATTR(inv, "config:23" ); +PMU_FORMAT_ATTR(cmask, "config:24-31" ); + +static struct attribute *amd_format_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_cmask.attr, + NULL, +}; + static __initconst const struct x86_pmu amd_pmu = { .name = "AMD", .handle_irq = x86_pmu_handle_irq, @@ -420,6 +441,8 @@ static __initconst const struct x86_pmu amd_pmu = { .get_event_constraints = amd_get_event_constraints, .put_event_constraints = amd_put_event_constraints, + .format_attrs = amd_format_attr, + .cpu_prepare = amd_pmu_cpu_prepare, .cpu_starting = amd_pmu_cpu_starting, .cpu_dead = amd_pmu_cpu_dead, @@ -587,9 +610,10 @@ static __initconst const struct x86_pmu amd_pmu_f15h = { .put_event_constraints = amd_put_event_constraints, .cpu_prepare = amd_pmu_cpu_prepare, - .cpu_starting = amd_pmu_cpu_starting, .cpu_dead = amd_pmu_cpu_dead, #endif + .cpu_starting = amd_pmu_cpu_starting, + .format_attrs = amd_format_attr, }; __init int amd_pmu_init(void) @@ -621,3 +645,33 @@ __init int amd_pmu_init(void) return 0; } + +void amd_pmu_enable_virt(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + cpuc->perf_ctr_virt_mask = 0; + + /* Reload all events */ + x86_pmu_disable_all(); + x86_pmu_enable_all(0); +} +EXPORT_SYMBOL_GPL(amd_pmu_enable_virt); + +void amd_pmu_disable_virt(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + /* + * We only mask out the Host-only bit so that host-only counting works + * when SVM is disabled. If someone sets up a guest-only counter when + * SVM is disabled the Guest-only bits still gets set and the counter + * will not count anything. + */ + cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY; + + /* Reload all events */ + x86_pmu_disable_all(); + x86_pmu_enable_all(0); +} +EXPORT_SYMBOL_GPL(amd_pmu_disable_virt); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 3bd37bdf1b8..26b3e2fef10 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -385,14 +385,15 @@ static __initconst const u64 westmere_hw_cache_event_ids #define NHM_LOCAL_DRAM (1 << 14) #define NHM_NON_DRAM (1 << 15) -#define NHM_ALL_DRAM (NHM_REMOTE_DRAM|NHM_LOCAL_DRAM) +#define NHM_LOCAL (NHM_LOCAL_DRAM|NHM_REMOTE_CACHE_FWD) +#define NHM_REMOTE (NHM_REMOTE_DRAM) #define NHM_DMND_READ (NHM_DMND_DATA_RD) #define NHM_DMND_WRITE (NHM_DMND_RFO|NHM_DMND_WB) #define NHM_DMND_PREFETCH (NHM_PF_DATA_RD|NHM_PF_DATA_RFO) #define NHM_L3_HIT (NHM_UNCORE_HIT|NHM_OTHER_CORE_HIT_SNP|NHM_OTHER_CORE_HITM) -#define NHM_L3_MISS (NHM_NON_DRAM|NHM_ALL_DRAM|NHM_REMOTE_CACHE_FWD) +#define NHM_L3_MISS (NHM_NON_DRAM|NHM_LOCAL_DRAM|NHM_REMOTE_DRAM|NHM_REMOTE_CACHE_FWD) #define NHM_L3_ACCESS (NHM_L3_HIT|NHM_L3_MISS) static __initconst const u64 nehalem_hw_cache_extra_regs @@ -416,16 +417,16 @@ static __initconst const u64 nehalem_hw_cache_extra_regs }, [ C(NODE) ] = { [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = NHM_DMND_READ|NHM_ALL_DRAM, - [ C(RESULT_MISS) ] = NHM_DMND_READ|NHM_REMOTE_DRAM, + [ C(RESULT_ACCESS) ] = NHM_DMND_READ|NHM_LOCAL|NHM_REMOTE, + [ C(RESULT_MISS) ] = NHM_DMND_READ|NHM_REMOTE, }, [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = NHM_DMND_WRITE|NHM_ALL_DRAM, - [ C(RESULT_MISS) ] = NHM_DMND_WRITE|NHM_REMOTE_DRAM, + [ C(RESULT_ACCESS) ] = NHM_DMND_WRITE|NHM_LOCAL|NHM_REMOTE, + [ C(RESULT_MISS) ] = NHM_DMND_WRITE|NHM_REMOTE, }, [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = NHM_DMND_PREFETCH|NHM_ALL_DRAM, - [ C(RESULT_MISS) ] = NHM_DMND_PREFETCH|NHM_REMOTE_DRAM, + [ C(RESULT_ACCESS) ] = NHM_DMND_PREFETCH|NHM_LOCAL|NHM_REMOTE, + [ C(RESULT_MISS) ] = NHM_DMND_PREFETCH|NHM_REMOTE, }, }, }; @@ -727,6 +728,19 @@ static __initconst const u64 atom_hw_cache_event_ids }, }; +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) + return true; + + return false; +} + static void intel_pmu_disable_all(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -881,6 +895,13 @@ static void intel_pmu_disable_event(struct perf_event *event) cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx); cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx); + /* + * must disable before any actual event + * because any event may be combined with LBR + */ + if (intel_pmu_needs_lbr_smpl(event)) + intel_pmu_lbr_disable(event); + if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) { intel_pmu_disable_fixed(hwc); return; @@ -935,6 +956,12 @@ static void intel_pmu_enable_event(struct perf_event *event) intel_pmu_enable_bts(hwc->config); return; } + /* + * must enabled before any actual event + * because any event may be combined with LBR + */ + if (intel_pmu_needs_lbr_smpl(event)) + intel_pmu_lbr_enable(event); if (event->attr.exclude_host) cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx); @@ -1057,6 +1084,9 @@ again: data.period = event->hw.last_period; + if (has_branch_stack(event)) + data.br_stack = &cpuc->lbr_stack; + if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); } @@ -1123,17 +1153,17 @@ static bool intel_try_alt_er(struct perf_event *event, int orig_idx) */ static struct event_constraint * __intel_shared_reg_get_constraints(struct cpu_hw_events *cpuc, - struct perf_event *event) + struct perf_event *event, + struct hw_perf_event_extra *reg) { struct event_constraint *c = &emptyconstraint; - struct hw_perf_event_extra *reg = &event->hw.extra_reg; struct er_account *era; unsigned long flags; int orig_idx = reg->idx; /* already allocated shared msr */ if (reg->alloc) - return &unconstrained; + return NULL; /* call x86_get_event_constraint() */ again: era = &cpuc->shared_regs->regs[reg->idx]; @@ -1156,14 +1186,10 @@ again: reg->alloc = 1; /* - * All events using extra_reg are unconstrained. - * Avoids calling x86_get_event_constraints() - * - * Must revisit if extra_reg controlling events - * ever have constraints. Worst case we go through - * the regular event constraint table. + * need to call x86_get_event_constraint() + * to check if associated event has constraints */ - c = &unconstrained; + c = NULL; } else if (intel_try_alt_er(event, orig_idx)) { raw_spin_unlock_irqrestore(&era->lock, flags); goto again; @@ -1200,11 +1226,23 @@ static struct event_constraint * intel_shared_regs_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) { - struct event_constraint *c = NULL; - - if (event->hw.extra_reg.idx != EXTRA_REG_NONE) - c = __intel_shared_reg_get_constraints(cpuc, event); - + struct event_constraint *c = NULL, *d; + struct hw_perf_event_extra *xreg, *breg; + + xreg = &event->hw.extra_reg; + if (xreg->idx != EXTRA_REG_NONE) { + c = __intel_shared_reg_get_constraints(cpuc, event, xreg); + if (c == &emptyconstraint) + return c; + } + breg = &event->hw.branch_reg; + if (breg->idx != EXTRA_REG_NONE) { + d = __intel_shared_reg_get_constraints(cpuc, event, breg); + if (d == &emptyconstraint) { + __intel_shared_reg_put_constraints(cpuc, xreg); + c = d; + } + } return c; } @@ -1252,6 +1290,10 @@ intel_put_shared_regs_event_constraints(struct cpu_hw_events *cpuc, reg = &event->hw.extra_reg; if (reg->idx != EXTRA_REG_NONE) __intel_shared_reg_put_constraints(cpuc, reg); + + reg = &event->hw.branch_reg; + if (reg->idx != EXTRA_REG_NONE) + __intel_shared_reg_put_constraints(cpuc, reg); } static void intel_put_event_constraints(struct cpu_hw_events *cpuc, @@ -1287,12 +1329,19 @@ static int intel_pmu_hw_config(struct perf_event *event) * * Thereby we gain a PEBS capable cycle counter. */ - u64 alt_config = 0x108000c0; /* INST_RETIRED.TOTAL_CYCLES */ + u64 alt_config = X86_CONFIG(.event=0xc0, .inv=1, .cmask=16); + alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK); event->hw.config = alt_config; } + if (intel_pmu_needs_lbr_smpl(event)) { + ret = intel_pmu_setup_lbr_filter(event); + if (ret) + return ret; + } + if (event->attr.type != PERF_TYPE_RAW) return 0; @@ -1382,6 +1431,24 @@ static void core_pmu_enable_all(int added) } } +PMU_FORMAT_ATTR(event, "config:0-7" ); +PMU_FORMAT_ATTR(umask, "config:8-15" ); +PMU_FORMAT_ATTR(edge, "config:18" ); +PMU_FORMAT_ATTR(pc, "config:19" ); +PMU_FORMAT_ATTR(any, "config:21" ); /* v3 + */ +PMU_FORMAT_ATTR(inv, "config:23" ); +PMU_FORMAT_ATTR(cmask, "config:24-31" ); + +static struct attribute *intel_arch_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_pc.attr, + &format_attr_inv.attr, + &format_attr_cmask.attr, + NULL, +}; + static __initconst const struct x86_pmu core_pmu = { .name = "core", .handle_irq = x86_pmu_handle_irq, @@ -1406,6 +1473,7 @@ static __initconst const struct x86_pmu core_pmu = { .put_event_constraints = intel_put_event_constraints, .event_constraints = intel_core_event_constraints, .guest_get_msrs = core_guest_get_msrs, + .format_attrs = intel_arch_formats_attr, }; struct intel_shared_regs *allocate_shared_regs(int cpu) @@ -1431,7 +1499,7 @@ static int intel_pmu_cpu_prepare(int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); - if (!x86_pmu.extra_regs) + if (!(x86_pmu.extra_regs || x86_pmu.lbr_sel_map)) return NOTIFY_OK; cpuc->shared_regs = allocate_shared_regs(cpu); @@ -1453,22 +1521,28 @@ static void intel_pmu_cpu_starting(int cpu) */ intel_pmu_lbr_reset(); - if (!cpuc->shared_regs || (x86_pmu.er_flags & ERF_NO_HT_SHARING)) + cpuc->lbr_sel = NULL; + + if (!cpuc->shared_regs) return; - for_each_cpu(i, topology_thread_cpumask(cpu)) { - struct intel_shared_regs *pc; + if (!(x86_pmu.er_flags & ERF_NO_HT_SHARING)) { + for_each_cpu(i, topology_thread_cpumask(cpu)) { + struct intel_shared_regs *pc; - pc = per_cpu(cpu_hw_events, i).shared_regs; - if (pc && pc->core_id == core_id) { - cpuc->kfree_on_online = cpuc->shared_regs; - cpuc->shared_regs = pc; - break; + pc = per_cpu(cpu_hw_events, i).shared_regs; + if (pc && pc->core_id == core_id) { + cpuc->kfree_on_online = cpuc->shared_regs; + cpuc->shared_regs = pc; + break; + } } + cpuc->shared_regs->core_id = core_id; + cpuc->shared_regs->refcnt++; } - cpuc->shared_regs->core_id = core_id; - cpuc->shared_regs->refcnt++; + if (x86_pmu.lbr_sel_map) + cpuc->lbr_sel = &cpuc->shared_regs->regs[EXTRA_REG_LBR]; } static void intel_pmu_cpu_dying(int cpu) @@ -1486,6 +1560,33 @@ static void intel_pmu_cpu_dying(int cpu) fini_debug_store_on_cpu(cpu); } +static void intel_pmu_flush_branch_stack(void) +{ + /* + * Intel LBR does not tag entries with the + * PID of the current task, then we need to + * flush it on ctxsw + * For now, we simply reset it + */ + if (x86_pmu.lbr_nr) + intel_pmu_lbr_reset(); +} + +PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63"); + +static struct attribute *intel_arch3_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_pc.attr, + &format_attr_any.attr, + &format_attr_inv.attr, + &format_attr_cmask.attr, + + &format_attr_offcore_rsp.attr, /* XXX do NHM/WSM + SNB breakout */ + NULL, +}; + static __initconst const struct x86_pmu intel_pmu = { .name = "Intel", .handle_irq = intel_pmu_handle_irq, @@ -1509,10 +1610,13 @@ static __initconst const struct x86_pmu intel_pmu = { .get_event_constraints = intel_get_event_constraints, .put_event_constraints = intel_put_event_constraints, + .format_attrs = intel_arch3_formats_attr, + .cpu_prepare = intel_pmu_cpu_prepare, .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, .guest_get_msrs = intel_guest_get_msrs, + .flush_branch_stack = intel_pmu_flush_branch_stack, }; static __init void intel_clovertown_quirk(void) @@ -1689,9 +1793,11 @@ __init int intel_pmu_init(void) x86_pmu.extra_regs = intel_nehalem_extra_regs; /* UOPS_ISSUED.STALLED_CYCLES */ - intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e; + intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = + X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1); /* UOPS_EXECUTED.CORE_ACTIVE_CYCLES,c=1,i=1 */ - intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x1803fb1; + intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = + X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1); x86_add_quirk(intel_nehalem_quirk); @@ -1726,9 +1832,11 @@ __init int intel_pmu_init(void) x86_pmu.er_flags |= ERF_HAS_RSP_1; /* UOPS_ISSUED.STALLED_CYCLES */ - intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e; + intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = + X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1); /* UOPS_EXECUTED.CORE_ACTIVE_CYCLES,c=1,i=1 */ - intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x1803fb1; + intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = + X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1); pr_cont("Westmere events, "); break; @@ -1739,7 +1847,7 @@ __init int intel_pmu_init(void) memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); - intel_pmu_lbr_init_nhm(); + intel_pmu_lbr_init_snb(); x86_pmu.event_constraints = intel_snb_event_constraints; x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints; @@ -1749,9 +1857,11 @@ __init int intel_pmu_init(void) x86_pmu.er_flags |= ERF_NO_HT_SHARING; /* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */ - intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e; + intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = + X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1); /* UOPS_DISPATCHED.THREAD,c=1,i=1 to count stall cycles*/ - intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x18001b1; + intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = + X86_CONFIG(.event=0xb1, .umask=0x01, .inv=1, .cmask=1); pr_cont("SandyBridge events, "); break; diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 73da6b64f5b..7f64df19e7d 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -3,6 +3,7 @@ #include <linux/slab.h> #include <asm/perf_event.h> +#include <asm/insn.h> #include "perf_event.h" @@ -439,10 +440,6 @@ void intel_pmu_pebs_enable(struct perf_event *event) hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT; cpuc->pebs_enabled |= 1ULL << hwc->idx; - WARN_ON_ONCE(cpuc->enabled); - - if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1) - intel_pmu_lbr_enable(event); } void intel_pmu_pebs_disable(struct perf_event *event) @@ -455,9 +452,6 @@ void intel_pmu_pebs_disable(struct perf_event *event) wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); hwc->config |= ARCH_PERFMON_EVENTSEL_INT; - - if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1) - intel_pmu_lbr_disable(event); } void intel_pmu_pebs_enable_all(void) @@ -476,17 +470,6 @@ void intel_pmu_pebs_disable_all(void) wrmsrl(MSR_IA32_PEBS_ENABLE, 0); } -#include <asm/insn.h> - -static inline bool kernel_ip(unsigned long ip) -{ -#ifdef CONFIG_X86_32 - return ip > PAGE_OFFSET; -#else - return (long)ip < 0; -#endif -} - static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -573,6 +556,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event, * both formats and we don't use the other fields in this * routine. */ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct pebs_record_core *pebs = __pebs; struct perf_sample_data data; struct pt_regs regs; @@ -603,6 +587,9 @@ static void __intel_pmu_pebs_event(struct perf_event *event, else regs.flags &= ~PERF_EFLAGS_EXACT; + if (has_branch_stack(event)) + data.br_stack = &cpuc->lbr_stack; + if (perf_event_overflow(event, &data, ®s)) x86_pmu_stop(event, 0); } diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index 3fab3de3ce9..520b4265fcd 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -3,6 +3,7 @@ #include <asm/perf_event.h> #include <asm/msr.h> +#include <asm/insn.h> #include "perf_event.h" @@ -14,6 +15,100 @@ enum { }; /* + * Intel LBR_SELECT bits + * Intel Vol3a, April 2011, Section 16.7 Table 16-10 + * + * Hardware branch filter (not available on all CPUs) + */ +#define LBR_KERNEL_BIT 0 /* do not capture at ring0 */ +#define LBR_USER_BIT 1 /* do not capture at ring > 0 */ +#define LBR_JCC_BIT 2 /* do not capture conditional branches */ +#define LBR_REL_CALL_BIT 3 /* do not capture relative calls */ +#define LBR_IND_CALL_BIT 4 /* do not capture indirect calls */ +#define LBR_RETURN_BIT 5 /* do not capture near returns */ +#define LBR_IND_JMP_BIT 6 /* do not capture indirect jumps */ +#define LBR_REL_JMP_BIT 7 /* do not capture relative jumps */ +#define LBR_FAR_BIT 8 /* do not capture far branches */ + +#define LBR_KERNEL (1 << LBR_KERNEL_BIT) +#define LBR_USER (1 << LBR_USER_BIT) +#define LBR_JCC (1 << LBR_JCC_BIT) +#define LBR_REL_CALL (1 << LBR_REL_CALL_BIT) +#define LBR_IND_CALL (1 << LBR_IND_CALL_BIT) +#define LBR_RETURN (1 << LBR_RETURN_BIT) +#define LBR_REL_JMP (1 << LBR_REL_JMP_BIT) +#define LBR_IND_JMP (1 << LBR_IND_JMP_BIT) +#define LBR_FAR (1 << LBR_FAR_BIT) + +#define LBR_PLM (LBR_KERNEL | LBR_USER) + +#define LBR_SEL_MASK 0x1ff /* valid bits in LBR_SELECT */ +#define LBR_NOT_SUPP -1 /* LBR filter not supported */ +#define LBR_IGN 0 /* ignored */ + +#define LBR_ANY \ + (LBR_JCC |\ + LBR_REL_CALL |\ + LBR_IND_CALL |\ + LBR_RETURN |\ + LBR_REL_JMP |\ + LBR_IND_JMP |\ + LBR_FAR) + +#define LBR_FROM_FLAG_MISPRED (1ULL << 63) + +#define for_each_branch_sample_type(x) \ + for ((x) = PERF_SAMPLE_BRANCH_USER; \ + (x) < PERF_SAMPLE_BRANCH_MAX; (x) <<= 1) + +/* + * x86control flow change classification + * x86control flow changes include branches, interrupts, traps, faults + */ +enum { + X86_BR_NONE = 0, /* unknown */ + + X86_BR_USER = 1 << 0, /* branch target is user */ + X86_BR_KERNEL = 1 << 1, /* branch target is kernel */ + + X86_BR_CALL = 1 << 2, /* call */ + X86_BR_RET = 1 << 3, /* return */ + X86_BR_SYSCALL = 1 << 4, /* syscall */ + X86_BR_SYSRET = 1 << 5, /* syscall return */ + X86_BR_INT = 1 << 6, /* sw interrupt */ + X86_BR_IRET = 1 << 7, /* return from interrupt */ + X86_BR_JCC = 1 << 8, /* conditional */ + X86_BR_JMP = 1 << 9, /* jump */ + X86_BR_IRQ = 1 << 10,/* hw interrupt or trap or fault */ + X86_BR_IND_CALL = 1 << 11,/* indirect calls */ +}; + +#define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL) + +#define X86_BR_ANY \ + (X86_BR_CALL |\ + X86_BR_RET |\ + X86_BR_SYSCALL |\ + X86_BR_SYSRET |\ + X86_BR_INT |\ + X86_BR_IRET |\ + X86_BR_JCC |\ + X86_BR_JMP |\ + X86_BR_IRQ |\ + X86_BR_IND_CALL) + +#define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY) + +#define X86_BR_ANY_CALL \ + (X86_BR_CALL |\ + X86_BR_IND_CALL |\ + X86_BR_SYSCALL |\ + X86_BR_IRQ |\ + X86_BR_INT) + +static void intel_pmu_lbr_filter(struct cpu_hw_events *cpuc); + +/* * We only support LBR implementations that have FREEZE_LBRS_ON_PMI * otherwise it becomes near impossible to get a reliable stack. */ @@ -21,6 +116,10 @@ enum { static void __intel_pmu_lbr_enable(void) { u64 debugctl; + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + if (cpuc->lbr_sel) + wrmsrl(MSR_LBR_SELECT, cpuc->lbr_sel->config); rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); debugctl |= (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); @@ -72,17 +171,15 @@ void intel_pmu_lbr_enable(struct perf_event *event) if (!x86_pmu.lbr_nr) return; - WARN_ON_ONCE(cpuc->enabled); - /* * Reset the LBR stack if we changed task context to * avoid data leaks. */ - if (event->ctx->task && cpuc->lbr_context != event->ctx) { intel_pmu_lbr_reset(); cpuc->lbr_context = event->ctx; } + cpuc->br_sel = event->hw.branch_reg.reg; cpuc->lbr_users++; } @@ -97,8 +194,11 @@ void intel_pmu_lbr_disable(struct perf_event *event) cpuc->lbr_users--; WARN_ON_ONCE(cpuc->lbr_users < 0); - if (cpuc->enabled && !cpuc->lbr_users) + if (cpuc->enabled && !cpuc->lbr_users) { __intel_pmu_lbr_disable(); + /* avoid stale pointer */ + cpuc->lbr_context = NULL; + } } void intel_pmu_lbr_enable_all(void) @@ -117,6 +217,9 @@ void intel_pmu_lbr_disable_all(void) __intel_pmu_lbr_disable(); } +/* + * TOS = most recently recorded branch + */ static inline u64 intel_pmu_lbr_tos(void) { u64 tos; @@ -144,15 +247,15 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) rdmsrl(x86_pmu.lbr_from + lbr_idx, msr_lastbranch.lbr); - cpuc->lbr_entries[i].from = msr_lastbranch.from; - cpuc->lbr_entries[i].to = msr_lastbranch.to; - cpuc->lbr_entries[i].flags = 0; + cpuc->lbr_entries[i].from = msr_lastbranch.from; + cpuc->lbr_entries[i].to = msr_lastbranch.to; + cpuc->lbr_entries[i].mispred = 0; + cpuc->lbr_entries[i].predicted = 0; + cpuc->lbr_entries[i].reserved = 0; } cpuc->lbr_stack.nr = i; } -#define LBR_FROM_FLAG_MISPRED (1ULL << 63) - /* * Due to lack of segmentation in Linux the effective address (offset) * is the same as the linear address, allowing us to merge the LIP and EIP @@ -167,19 +270,22 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) for (i = 0; i < x86_pmu.lbr_nr; i++) { unsigned long lbr_idx = (tos - i) & mask; - u64 from, to, flags = 0; + u64 from, to, mis = 0, pred = 0; rdmsrl(x86_pmu.lbr_from + lbr_idx, from); rdmsrl(x86_pmu.lbr_to + lbr_idx, to); if (lbr_format == LBR_FORMAT_EIP_FLAGS) { - flags = !!(from & LBR_FROM_FLAG_MISPRED); + mis = !!(from & LBR_FROM_FLAG_MISPRED); + pred = !mis; from = (u64)((((s64)from) << 1) >> 1); } - cpuc->lbr_entries[i].from = from; - cpuc->lbr_entries[i].to = to; - cpuc->lbr_entries[i].flags = flags; + cpuc->lbr_entries[i].from = from; + cpuc->lbr_entries[i].to = to; + cpuc->lbr_entries[i].mispred = mis; + cpuc->lbr_entries[i].predicted = pred; + cpuc->lbr_entries[i].reserved = 0; } cpuc->lbr_stack.nr = i; } @@ -195,28 +301,404 @@ void intel_pmu_lbr_read(void) intel_pmu_lbr_read_32(cpuc); else intel_pmu_lbr_read_64(cpuc); + + intel_pmu_lbr_filter(cpuc); +} + +/* + * SW filter is used: + * - in case there is no HW filter + * - in case the HW filter has errata or limitations + */ +static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event) +{ + u64 br_type = event->attr.branch_sample_type; + int mask = 0; + + if (br_type & PERF_SAMPLE_BRANCH_USER) + mask |= X86_BR_USER; + + if (br_type & PERF_SAMPLE_BRANCH_KERNEL) + mask |= X86_BR_KERNEL; + + /* we ignore BRANCH_HV here */ + + if (br_type & PERF_SAMPLE_BRANCH_ANY) + mask |= X86_BR_ANY; + + if (br_type & PERF_SAMPLE_BRANCH_ANY_CALL) + mask |= X86_BR_ANY_CALL; + + if (br_type & PERF_SAMPLE_BRANCH_ANY_RETURN) + mask |= X86_BR_RET | X86_BR_IRET | X86_BR_SYSRET; + + if (br_type & PERF_SAMPLE_BRANCH_IND_CALL) + mask |= X86_BR_IND_CALL; + /* + * stash actual user request into reg, it may + * be used by fixup code for some CPU + */ + event->hw.branch_reg.reg = mask; +} + +/* + * setup the HW LBR filter + * Used only when available, may not be enough to disambiguate + * all branches, may need the help of the SW filter + */ +static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) +{ + struct hw_perf_event_extra *reg; + u64 br_type = event->attr.branch_sample_type; + u64 mask = 0, m; + u64 v; + + for_each_branch_sample_type(m) { + if (!(br_type & m)) + continue; + + v = x86_pmu.lbr_sel_map[m]; + if (v == LBR_NOT_SUPP) + return -EOPNOTSUPP; + + if (v != LBR_IGN) + mask |= v; + } + reg = &event->hw.branch_reg; + reg->idx = EXTRA_REG_LBR; + + /* LBR_SELECT operates in suppress mode so invert mask */ + reg->config = ~mask & x86_pmu.lbr_sel_mask; + + return 0; +} + +int intel_pmu_setup_lbr_filter(struct perf_event *event) +{ + int ret = 0; + + /* + * no LBR on this PMU + */ + if (!x86_pmu.lbr_nr) + return -EOPNOTSUPP; + + /* + * setup SW LBR filter + */ + intel_pmu_setup_sw_lbr_filter(event); + + /* + * setup HW LBR filter, if any + */ + if (x86_pmu.lbr_sel_map) + ret = intel_pmu_setup_hw_lbr_filter(event); + + return ret; +} + +/* + * return the type of control flow change at address "from" + * intruction is not necessarily a branch (in case of interrupt). + * + * The branch type returned also includes the priv level of the + * target of the control flow change (X86_BR_USER, X86_BR_KERNEL). + * + * If a branch type is unknown OR the instruction cannot be + * decoded (e.g., text page not present), then X86_BR_NONE is + * returned. + */ +static int branch_type(unsigned long from, unsigned long to) +{ + struct insn insn; + void *addr; + int bytes, size = MAX_INSN_SIZE; + int ret = X86_BR_NONE; + int ext, to_plm, from_plm; + u8 buf[MAX_INSN_SIZE]; + int is64 = 0; + + to_plm = kernel_ip(to) ? X86_BR_KERNEL : X86_BR_USER; + from_plm = kernel_ip(from) ? X86_BR_KERNEL : X86_BR_USER; + + /* + * maybe zero if lbr did not fill up after a reset by the time + * we get a PMU interrupt + */ + if (from == 0 || to == 0) + return X86_BR_NONE; + + if (from_plm == X86_BR_USER) { + /* + * can happen if measuring at the user level only + * and we interrupt in a kernel thread, e.g., idle. + */ + if (!current->mm) + return X86_BR_NONE; + + /* may fail if text not present */ + bytes = copy_from_user_nmi(buf, (void __user *)from, size); + if (bytes != size) + return X86_BR_NONE; + + addr = buf; + } else + addr = (void *)from; + + /* + * decoder needs to know the ABI especially + * on 64-bit systems running 32-bit apps + */ +#ifdef CONFIG_X86_64 + is64 = kernel_ip((unsigned long)addr) || !test_thread_flag(TIF_IA32); +#endif + insn_init(&insn, addr, is64); + insn_get_opcode(&insn); + + switch (insn.opcode.bytes[0]) { + case 0xf: + switch (insn.opcode.bytes[1]) { + case 0x05: /* syscall */ + case 0x34: /* sysenter */ + ret = X86_BR_SYSCALL; + break; + case 0x07: /* sysret */ + case 0x35: /* sysexit */ + ret = X86_BR_SYSRET; + break; + case 0x80 ... 0x8f: /* conditional */ + ret = X86_BR_JCC; + break; + default: + ret = X86_BR_NONE; + } + break; + case 0x70 ... 0x7f: /* conditional */ + ret = X86_BR_JCC; + break; + case 0xc2: /* near ret */ + case 0xc3: /* near ret */ + case 0xca: /* far ret */ + case 0xcb: /* far ret */ + ret = X86_BR_RET; + break; + case 0xcf: /* iret */ + ret = X86_BR_IRET; + break; + case 0xcc ... 0xce: /* int */ + ret = X86_BR_INT; + break; + case 0xe8: /* call near rel */ + case 0x9a: /* call far absolute */ + ret = X86_BR_CALL; + break; + case 0xe0 ... 0xe3: /* loop jmp */ + ret = X86_BR_JCC; + break; + case 0xe9 ... 0xeb: /* jmp */ + ret = X86_BR_JMP; + break; + case 0xff: /* call near absolute, call far absolute ind */ + insn_get_modrm(&insn); + ext = (insn.modrm.bytes[0] >> 3) & 0x7; + switch (ext) { + case 2: /* near ind call */ + case 3: /* far ind call */ + ret = X86_BR_IND_CALL; + break; + case 4: + case 5: + ret = X86_BR_JMP; + break; + } + break; + default: + ret = X86_BR_NONE; + } + /* + * interrupts, traps, faults (and thus ring transition) may + * occur on any instructions. Thus, to classify them correctly, + * we need to first look at the from and to priv levels. If they + * are different and to is in the kernel, then it indicates + * a ring transition. If the from instruction is not a ring + * transition instr (syscall, systenter, int), then it means + * it was a irq, trap or fault. + * + * we have no way of detecting kernel to kernel faults. + */ + if (from_plm == X86_BR_USER && to_plm == X86_BR_KERNEL + && ret != X86_BR_SYSCALL && ret != X86_BR_INT) + ret = X86_BR_IRQ; + + /* + * branch priv level determined by target as + * is done by HW when LBR_SELECT is implemented + */ + if (ret != X86_BR_NONE) + ret |= to_plm; + + return ret; +} + +/* + * implement actual branch filter based on user demand. + * Hardware may not exactly satisfy that request, thus + * we need to inspect opcodes. Mismatched branches are + * discarded. Therefore, the number of branches returned + * in PERF_SAMPLE_BRANCH_STACK sample may vary. + */ +static void +intel_pmu_lbr_filter(struct cpu_hw_events *cpuc) +{ + u64 from, to; + int br_sel = cpuc->br_sel; + int i, j, type; + bool compress = false; + + /* if sampling all branches, then nothing to filter */ + if ((br_sel & X86_BR_ALL) == X86_BR_ALL) + return; + + for (i = 0; i < cpuc->lbr_stack.nr; i++) { + + from = cpuc->lbr_entries[i].from; + to = cpuc->lbr_entries[i].to; + + type = branch_type(from, to); + + /* if type does not correspond, then discard */ + if (type == X86_BR_NONE || (br_sel & type) != type) { + cpuc->lbr_entries[i].from = 0; + compress = true; + } + } + + if (!compress) + return; + + /* remove all entries with from=0 */ + for (i = 0; i < cpuc->lbr_stack.nr; ) { + if (!cpuc->lbr_entries[i].from) { + j = i; + while (++j < cpuc->lbr_stack.nr) + cpuc->lbr_entries[j-1] = cpuc->lbr_entries[j]; + cpuc->lbr_stack.nr--; + if (!cpuc->lbr_entries[i].from) + continue; + } + i++; + } } +/* + * Map interface branch filters onto LBR filters + */ +static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = { + [PERF_SAMPLE_BRANCH_ANY] = LBR_ANY, + [PERF_SAMPLE_BRANCH_USER] = LBR_USER, + [PERF_SAMPLE_BRANCH_KERNEL] = LBR_KERNEL, + [PERF_SAMPLE_BRANCH_HV] = LBR_IGN, + [PERF_SAMPLE_BRANCH_ANY_RETURN] = LBR_RETURN | LBR_REL_JMP + | LBR_IND_JMP | LBR_FAR, + /* + * NHM/WSM erratum: must include REL_JMP+IND_JMP to get CALL branches + */ + [PERF_SAMPLE_BRANCH_ANY_CALL] = + LBR_REL_CALL | LBR_IND_CALL | LBR_REL_JMP | LBR_IND_JMP | LBR_FAR, + /* + * NHM/WSM erratum: must include IND_JMP to capture IND_CALL + */ + [PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL | LBR_IND_JMP, +}; + +static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = { + [PERF_SAMPLE_BRANCH_ANY] = LBR_ANY, + [PERF_SAMPLE_BRANCH_USER] = LBR_USER, + [PERF_SAMPLE_BRANCH_KERNEL] = LBR_KERNEL, + [PERF_SAMPLE_BRANCH_HV] = LBR_IGN, + [PERF_SAMPLE_BRANCH_ANY_RETURN] = LBR_RETURN | LBR_FAR, + [PERF_SAMPLE_BRANCH_ANY_CALL] = LBR_REL_CALL | LBR_IND_CALL + | LBR_FAR, + [PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL, +}; + +/* core */ void intel_pmu_lbr_init_core(void) { x86_pmu.lbr_nr = 4; - x86_pmu.lbr_tos = 0x01c9; - x86_pmu.lbr_from = 0x40; - x86_pmu.lbr_to = 0x60; + x86_pmu.lbr_tos = MSR_LBR_TOS; + x86_pmu.lbr_from = MSR_LBR_CORE_FROM; + x86_pmu.lbr_to = MSR_LBR_CORE_TO; + + /* + * SW branch filter usage: + * - compensate for lack of HW filter + */ + pr_cont("4-deep LBR, "); } +/* nehalem/westmere */ void intel_pmu_lbr_init_nhm(void) { x86_pmu.lbr_nr = 16; - x86_pmu.lbr_tos = 0x01c9; - x86_pmu.lbr_from = 0x680; - x86_pmu.lbr_to = 0x6c0; + 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 = nhm_lbr_sel_map; + + /* + * SW branch filter usage: + * - workaround LBR_SEL errata (see above) + * - support syscall, sysret capture. + * That requires LBR_FAR but that means far + * jmp need to be filtered out + */ + pr_cont("16-deep LBR, "); +} + +/* sandy bridge */ +void intel_pmu_lbr_init_snb(void) +{ + x86_pmu.lbr_nr = 16; + 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; + + /* + * SW branch filter usage: + * - support syscall, sysret capture. + * That requires LBR_FAR but that means far + * jmp need to be filtered out + */ + pr_cont("16-deep LBR, "); } +/* atom */ void intel_pmu_lbr_init_atom(void) { + /* + * only models starting at stepping 10 seems + * to have an operational LBR which can freeze + * on PMU interrupt + */ + if (boot_cpu_data.x86_mask < 10) { + pr_cont("LBR disabled due to erratum"); + return; + } + x86_pmu.lbr_nr = 8; - x86_pmu.lbr_tos = 0x01c9; - x86_pmu.lbr_from = 0x40; - x86_pmu.lbr_to = 0x60; + x86_pmu.lbr_tos = MSR_LBR_TOS; + x86_pmu.lbr_from = MSR_LBR_CORE_FROM; + x86_pmu.lbr_to = MSR_LBR_CORE_TO; + + /* + * SW branch filter usage: + * - compensate for lack of HW filter + */ + pr_cont("8-deep LBR, "); } diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index ef484d9d0a2..a2dfacfd710 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -1271,6 +1271,17 @@ done: return num ? -EINVAL : 0; } +PMU_FORMAT_ATTR(cccr, "config:0-31" ); +PMU_FORMAT_ATTR(escr, "config:32-62"); +PMU_FORMAT_ATTR(ht, "config:63" ); + +static struct attribute *intel_p4_formats_attr[] = { + &format_attr_cccr.attr, + &format_attr_escr.attr, + &format_attr_ht.attr, + NULL, +}; + static __initconst const struct x86_pmu p4_pmu = { .name = "Netburst P4/Xeon", .handle_irq = p4_pmu_handle_irq, @@ -1305,6 +1316,8 @@ static __initconst const struct x86_pmu p4_pmu = { * the former idea is taken from OProfile code */ .perfctr_second_write = 1, + + .format_attrs = intel_p4_formats_attr, }; __init int p4_pmu_init(void) diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index c7181befecd..32bcfc7dd23 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -87,6 +87,23 @@ static void p6_pmu_enable_event(struct perf_event *event) (void)checking_wrmsrl(hwc->config_base, val); } +PMU_FORMAT_ATTR(event, "config:0-7" ); +PMU_FORMAT_ATTR(umask, "config:8-15" ); +PMU_FORMAT_ATTR(edge, "config:18" ); +PMU_FORMAT_ATTR(pc, "config:19" ); +PMU_FORMAT_ATTR(inv, "config:23" ); +PMU_FORMAT_ATTR(cmask, "config:24-31" ); + +static struct attribute *intel_p6_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_pc.attr, + &format_attr_inv.attr, + &format_attr_cmask.attr, + NULL, +}; + static __initconst const struct x86_pmu p6_pmu = { .name = "p6", .handle_irq = x86_pmu_handle_irq, @@ -115,6 +132,8 @@ static __initconst const struct x86_pmu p6_pmu = { .cntval_mask = (1ULL << 32) - 1, .get_event_constraints = x86_get_event_constraints, .event_constraints = p6_event_constraints, + + .format_attrs = intel_p6_formats_attr, }; __init int p6_pmu_init(void) diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index c7f64e6f537..addf9e82a7f 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -40,6 +40,7 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c) { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_XSAVEOPT, CR_EAX, 0, 0x0000000d, 1 }, { X86_FEATURE_CPB, CR_EDX, 9, 0x80000007, 0 }, + { X86_FEATURE_HW_PSTATE, CR_EDX, 7, 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 }, diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index a524353d93f..39472dd2323 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -43,7 +43,6 @@ #include <asm/processor.h> #include <asm/msr.h> -#include <asm/system.h> static struct class *cpuid_class; diff --git a/arch/x86/kernel/crash_dump_32.c b/arch/x86/kernel/crash_dump_32.c index 642f75a68cd..11891ca7b71 100644 --- a/arch/x86/kernel/crash_dump_32.c +++ b/arch/x86/kernel/crash_dump_32.c @@ -62,16 +62,16 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, if (!userbuf) { memcpy(buf, (vaddr + offset), csize); - kunmap_atomic(vaddr, KM_PTE0); + kunmap_atomic(vaddr); } else { if (!kdump_buf_page) { printk(KERN_WARNING "Kdump: Kdump buffer page not" " allocated\n"); - kunmap_atomic(vaddr, KM_PTE0); + kunmap_atomic(vaddr); return -EFAULT; } copy_page(kdump_buf_page, vaddr); - kunmap_atomic(vaddr, KM_PTE0); + kunmap_atomic(vaddr); if (copy_to_user(buf, (kdump_buf_page + offset), csize)) return -EFAULT; } diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 52821799a70..3ae2ced4a87 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -4,6 +4,7 @@ #include <linux/bootmem.h> #include <linux/export.h> #include <linux/io.h> +#include <linux/irqdomain.h> #include <linux/interrupt.h> #include <linux/list.h> #include <linux/of.h> @@ -17,64 +18,14 @@ #include <linux/initrd.h> #include <asm/hpet.h> -#include <asm/irq_controller.h> #include <asm/apic.h> #include <asm/pci_x86.h> __initdata u64 initial_dtb; char __initdata cmd_line[COMMAND_LINE_SIZE]; -static LIST_HEAD(irq_domains); -static DEFINE_RAW_SPINLOCK(big_irq_lock); int __initdata of_ioapic; -#ifdef CONFIG_X86_IO_APIC -static void add_interrupt_host(struct irq_domain *ih) -{ - unsigned long flags; - - raw_spin_lock_irqsave(&big_irq_lock, flags); - list_add(&ih->l, &irq_domains); - raw_spin_unlock_irqrestore(&big_irq_lock, flags); -} -#endif - -static struct irq_domain *get_ih_from_node(struct device_node *controller) -{ - struct irq_domain *ih, *found = NULL; - unsigned long flags; - - raw_spin_lock_irqsave(&big_irq_lock, flags); - list_for_each_entry(ih, &irq_domains, l) { - if (ih->controller == controller) { - found = ih; - break; - } - } - raw_spin_unlock_irqrestore(&big_irq_lock, flags); - return found; -} - -unsigned int irq_create_of_mapping(struct device_node *controller, - const u32 *intspec, unsigned int intsize) -{ - struct irq_domain *ih; - u32 virq, type; - int ret; - - ih = get_ih_from_node(controller); - if (!ih) - return 0; - ret = ih->xlate(ih, intspec, intsize, &virq, &type); - if (ret) - return 0; - if (type == IRQ_TYPE_NONE) - return virq; - irq_set_irq_type(virq, type); - return virq; -} -EXPORT_SYMBOL_GPL(irq_create_of_mapping); - unsigned long pci_address_to_pio(phys_addr_t address) { /* @@ -354,36 +305,43 @@ static struct of_ioapic_type of_ioapic_type[] = }, }; -static int ioapic_xlate(struct irq_domain *id, const u32 *intspec, u32 intsize, - u32 *out_hwirq, u32 *out_type) +static int ioapic_xlate(struct irq_domain *domain, + struct device_node *controller, + const u32 *intspec, u32 intsize, + irq_hw_number_t *out_hwirq, u32 *out_type) { - struct mp_ioapic_gsi *gsi_cfg; struct io_apic_irq_attr attr; struct of_ioapic_type *it; - u32 line, idx, type; + u32 line, idx; + int rc; - if (intsize < 2) + if (WARN_ON(intsize < 2)) return -EINVAL; - line = *intspec; - idx = (u32) id->priv; - gsi_cfg = mp_ioapic_gsi_routing(idx); - *out_hwirq = line + gsi_cfg->gsi_base; - - intspec++; - type = *intspec; + line = intspec[0]; - if (type >= ARRAY_SIZE(of_ioapic_type)) + if (intspec[1] >= ARRAY_SIZE(of_ioapic_type)) return -EINVAL; - it = of_ioapic_type + type; - *out_type = it->out_type; + it = &of_ioapic_type[intspec[1]]; + idx = (u32) domain->host_data; set_io_apic_irq_attr(&attr, idx, line, it->trigger, it->polarity); - return io_apic_setup_irq_pin_once(*out_hwirq, cpu_to_node(0), &attr); + rc = io_apic_setup_irq_pin_once(irq_find_mapping(domain, line), + cpu_to_node(0), &attr); + if (rc) + return rc; + + *out_hwirq = line; + *out_type = it->out_type; + return 0; } +const struct irq_domain_ops ioapic_irq_domain_ops = { + .xlate = ioapic_xlate, +}; + static void __init ioapic_add_ofnode(struct device_node *np) { struct resource r; @@ -399,13 +357,14 @@ static void __init ioapic_add_ofnode(struct device_node *np) for (i = 0; i < nr_ioapics; i++) { if (r.start == mpc_ioapic_addr(i)) { struct irq_domain *id; + struct mp_ioapic_gsi *gsi_cfg; + + gsi_cfg = mp_ioapic_gsi_routing(i); - id = kzalloc(sizeof(*id), GFP_KERNEL); + id = irq_domain_add_legacy(np, 32, gsi_cfg->gsi_base, 0, + &ioapic_irq_domain_ops, + (void*)i); BUG_ON(!id); - id->controller = np; - id->xlate = ioapic_xlate; - id->priv = (void *)i; - add_interrupt_host(id); return; } } diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 1aae78f775f..1b81839b6c8 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -37,13 +37,16 @@ print_ftrace_graph_addr(unsigned long addr, void *data, const struct stacktrace_ops *ops, struct thread_info *tinfo, int *graph) { - struct task_struct *task = tinfo->task; + struct task_struct *task; unsigned long ret_addr; - int index = task->curr_ret_stack; + int index; if (addr != (unsigned long)return_to_handler) return; + task = tinfo->task; + index = task->curr_ret_stack; + if (!task->ret_stack || index < *graph) return; @@ -252,7 +255,8 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err) unsigned short ss; unsigned long sp; #endif - printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter); + printk(KERN_DEFAULT + "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter); #ifdef CONFIG_PREEMPT printk("PREEMPT "); #endif @@ -264,7 +268,7 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err) #endif printk("\n"); if (notify_die(DIE_OOPS, str, regs, err, - current->thread.trap_no, SIGSEGV) == NOTIFY_STOP) + current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP) return 1; show_registers(regs); diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index c99f9ed013d..88ec9129271 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -87,7 +87,7 @@ void show_registers(struct pt_regs *regs) int i; print_modules(); - __show_regs(regs, 0); + __show_regs(regs, !user_mode_vm(regs)); printk(KERN_EMERG "Process %.*s (pid: %d, ti=%p task=%p task.ti=%p)\n", TASK_COMM_LEN, current->comm, task_pid_nr(current), diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 6d728d9284b..17107bd6e1f 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -129,7 +129,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, if (!stack) { if (regs) stack = (unsigned long *)regs->sp; - else if (task && task != current) + else if (task != current) stack = (unsigned long *)task->thread.sp; else stack = &dummy; @@ -269,11 +269,11 @@ void show_registers(struct pt_regs *regs) unsigned char c; u8 *ip; - printk(KERN_EMERG "Stack:\n"); + printk(KERN_DEFAULT "Stack:\n"); show_stack_log_lvl(NULL, regs, (unsigned long *)sp, - 0, KERN_EMERG); + 0, KERN_DEFAULT); - printk(KERN_EMERG "Code: "); + printk(KERN_DEFAULT "Code: "); ip = (u8 *)regs->ip - code_prologue; if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) { diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 8071e2f3d6e..62d61e9976e 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -19,6 +19,7 @@ #include <linux/acpi.h> #include <linux/firmware-map.h> #include <linux/memblock.h> +#include <linux/sort.h> #include <asm/e820.h> #include <asm/proto.h> @@ -227,22 +228,38 @@ void __init e820_print_map(char *who) * ____________________33__ * ______________________4_ */ +struct change_member { + struct e820entry *pbios; /* pointer to original bios entry */ + unsigned long long addr; /* address for this change point */ +}; + +static int __init cpcompare(const void *a, const void *b) +{ + struct change_member * const *app = a, * const *bpp = b; + const struct change_member *ap = *app, *bp = *bpp; + + /* + * Inputs are pointers to two elements of change_point[]. If their + * addresses are unequal, their difference dominates. If the addresses + * are equal, then consider one that represents the end of its region + * to be greater than one that does not. + */ + if (ap->addr != bp->addr) + return ap->addr > bp->addr ? 1 : -1; + + return (ap->addr != ap->pbios->addr) - (bp->addr != bp->pbios->addr); +} int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, u32 *pnr_map) { - struct change_member { - struct e820entry *pbios; /* pointer to original bios entry */ - unsigned long long addr; /* address for this change point */ - }; static struct change_member change_point_list[2*E820_X_MAX] __initdata; static struct change_member *change_point[2*E820_X_MAX] __initdata; static struct e820entry *overlap_list[E820_X_MAX] __initdata; static struct e820entry new_bios[E820_X_MAX] __initdata; - struct change_member *change_tmp; unsigned long current_type, last_type; unsigned long long last_addr; - int chgidx, still_changing; + int chgidx; int overlap_entries; int new_bios_entry; int old_nr, new_nr, chg_nr; @@ -279,35 +296,7 @@ int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, chg_nr = chgidx; /* sort change-point list by memory addresses (low -> high) */ - still_changing = 1; - while (still_changing) { - still_changing = 0; - for (i = 1; i < chg_nr; i++) { - unsigned long long curaddr, lastaddr; - unsigned long long curpbaddr, lastpbaddr; - - curaddr = change_point[i]->addr; - lastaddr = change_point[i - 1]->addr; - curpbaddr = change_point[i]->pbios->addr; - lastpbaddr = change_point[i - 1]->pbios->addr; - - /* - * swap entries, when: - * - * curaddr > lastaddr or - * curaddr == lastaddr and curaddr == curpbaddr and - * lastaddr != lastpbaddr - */ - if (curaddr < lastaddr || - (curaddr == lastaddr && curaddr == curpbaddr && - lastaddr != lastpbaddr)) { - change_tmp = change_point[i]; - change_point[i] = change_point[i-1]; - change_point[i-1] = change_tmp; - still_changing = 1; - } - } - } + sort(change_point, chg_nr, sizeof *change_point, cpcompare, NULL); /* create a new bios memory map, removing overlaps */ overlap_entries = 0; /* number of entries in the overlap table */ @@ -714,7 +703,7 @@ void __init e820_mark_nosave_regions(unsigned long limit_pfn) } #endif -#ifdef CONFIG_HIBERNATION +#ifdef CONFIG_ACPI /** * Mark ACPI NVS memory region, so that we can save/restore it during * hibernation and the subsequent resume. @@ -727,7 +716,7 @@ static int __init e820_mark_nvs_memory(void) struct e820entry *ei = &e820.map[i]; if (ei->type == E820_NVS) - suspend_nvs_register(ei->addr, ei->size); + acpi_nvs_register(ei->addr, ei->size); } return 0; diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index 9d42a52d233..9b9f18b4991 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -240,7 +240,7 @@ static int __init setup_early_printk(char *buf) if (!strncmp(buf, "xen", 3)) early_console_register(&xenboot_console, keep); #endif -#ifdef CONFIG_EARLY_PRINTK_MRST +#ifdef CONFIG_EARLY_PRINTK_INTEL_MID if (!strncmp(buf, "mrst", 4)) { mrst_early_console_init(); early_console_register(&early_mrst_console, keep); diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 22d0e21b4dd..7b784f4ef1e 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -42,6 +42,7 @@ */ #include <linux/linkage.h> +#include <linux/err.h> #include <asm/thread_info.h> #include <asm/irqflags.h> #include <asm/errno.h> @@ -81,8 +82,6 @@ * enough to patch inline, increasing performance. */ -#define nr_syscalls ((syscall_table_size)/4) - #ifdef CONFIG_PREEMPT #define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF #else @@ -99,12 +98,6 @@ #endif .endm -#ifdef CONFIG_VM86 -#define resume_userspace_sig check_userspace -#else -#define resume_userspace_sig resume_userspace -#endif - /* * User gs save/restore * @@ -328,10 +321,19 @@ ret_from_exception: preempt_stop(CLBR_ANY) ret_from_intr: GET_THREAD_INFO(%ebp) -check_userspace: +resume_userspace_sig: +#ifdef CONFIG_VM86 movl PT_EFLAGS(%esp), %eax # mix EFLAGS and CS movb PT_CS(%esp), %al andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax +#else + /* + * We can be coming here from a syscall done in the kernel space, + * e.g. a failed kernel_execve(). + */ + movl PT_CS(%esp), %eax + andl $SEGMENT_RPL_MASK, %eax +#endif cmpl $USER_RPL, %eax jb resume_kernel # not returning to v8086 or userspace @@ -423,7 +425,7 @@ sysenter_past_esp: testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp) jnz sysenter_audit sysenter_do_call: - cmpl $(nr_syscalls), %eax + cmpl $(NR_syscalls), %eax jae syscall_badsys call *sys_call_table(,%eax,4) movl %eax,PT_EAX(%esp) @@ -455,7 +457,7 @@ sysenter_audit: movl %ebx,%ecx /* 3rd arg: 1st syscall arg */ movl %eax,%edx /* 2nd arg: syscall number */ movl $AUDIT_ARCH_I386,%eax /* 1st arg: audit arch */ - call audit_syscall_entry + call __audit_syscall_entry pushl_cfi %ebx movl PT_EAX(%esp),%eax /* reload syscall number */ jmp sysenter_do_call @@ -466,11 +468,10 @@ sysexit_audit: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_ANY) movl %eax,%edx /* second arg, syscall return value */ - cmpl $0,%eax /* is it < 0? */ - setl %al /* 1 if so, 0 if not */ + cmpl $-MAX_ERRNO,%eax /* is it an error ? */ + setbe %al /* 1 if so, 0 if not */ movzbl %al,%eax /* zero-extend that */ - inc %eax /* first arg, 0->1(AUDITSC_SUCCESS), 1->2(AUDITSC_FAILURE) */ - call audit_syscall_exit + call __audit_syscall_exit DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF movl TI_flags(%ebp), %ecx @@ -504,7 +505,7 @@ ENTRY(system_call) # system call tracing in operation / emulation testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp) jnz syscall_trace_entry - cmpl $(nr_syscalls), %eax + cmpl $(NR_syscalls), %eax jae syscall_badsys syscall_call: call *sys_call_table(,%eax,4) @@ -654,7 +655,7 @@ syscall_trace_entry: movl %esp, %eax call syscall_trace_enter /* What it returned is what we'll actually use. */ - cmpl $(nr_syscalls), %eax + cmpl $(NR_syscalls), %eax jnae syscall_call jmp syscall_exit END(syscall_trace_entry) @@ -694,29 +695,28 @@ END(syscall_badsys) * System calls that need a pt_regs pointer. */ #define PTREGSCALL0(name) \ - ALIGN; \ -ptregs_##name: \ +ENTRY(ptregs_##name) ; \ leal 4(%esp),%eax; \ - jmp sys_##name; + jmp sys_##name; \ +ENDPROC(ptregs_##name) #define PTREGSCALL1(name) \ - ALIGN; \ -ptregs_##name: \ +ENTRY(ptregs_##name) ; \ leal 4(%esp),%edx; \ movl (PT_EBX+4)(%esp),%eax; \ - jmp sys_##name; + jmp sys_##name; \ +ENDPROC(ptregs_##name) #define PTREGSCALL2(name) \ - ALIGN; \ -ptregs_##name: \ +ENTRY(ptregs_##name) ; \ leal 4(%esp),%ecx; \ movl (PT_ECX+4)(%esp),%edx; \ movl (PT_EBX+4)(%esp),%eax; \ - jmp sys_##name; + jmp sys_##name; \ +ENDPROC(ptregs_##name) #define PTREGSCALL3(name) \ - ALIGN; \ -ptregs_##name: \ +ENTRY(ptregs_##name) ; \ CFI_STARTPROC; \ leal 4(%esp),%eax; \ pushl_cfi %eax; \ @@ -741,8 +741,7 @@ PTREGSCALL2(vm86) PTREGSCALL1(vm86old) /* Clone is an oddball. The 4th arg is in %edi */ - ALIGN; -ptregs_clone: +ENTRY(ptregs_clone) CFI_STARTPROC leal 4(%esp),%eax pushl_cfi %eax @@ -1213,11 +1212,6 @@ return_to_handler: jmp *%ecx #endif -.section .rodata,"a" -#include "syscall_table_32.S" - -syscall_table_size=(.-sys_call_table) - /* * Some functions should be protected against kprobes */ diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index a20e1cb9dc8..cdc79b5cfcd 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -55,6 +55,7 @@ #include <asm/paravirt.h> #include <asm/ftrace.h> #include <asm/percpu.h> +#include <linux/err.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ #include <linux/elf-em.h> @@ -319,7 +320,7 @@ ENDPROC(native_usergs_sysret64) movq %rsp, %rsi leaq -RBP(%rsp),%rdi /* arg1 for handler */ - testl $3, CS(%rdi) + testl $3, CS-RBP(%rsi) je 1f SWAPGS /* @@ -329,11 +330,10 @@ ENDPROC(native_usergs_sysret64) * moving irq_enter into assembly, which would be too much work) */ 1: incl PER_CPU_VAR(irq_count) - jne 2f - mov PER_CPU_VAR(irq_stack_ptr),%rsp + cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp CFI_DEF_CFA_REGISTER rsi -2: /* Store previous stack value */ + /* Store previous stack value */ pushq %rsi CFI_ESCAPE 0x0f /* DW_CFA_def_cfa_expression */, 6, \ 0x77 /* DW_OP_breg7 */, 0, \ @@ -481,7 +481,12 @@ GLOBAL(system_call_after_swapgs) testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) jnz tracesys system_call_fastpath: +#if __SYSCALL_MASK == ~0 cmpq $__NR_syscall_max,%rax +#else + andl $__SYSCALL_MASK,%eax + cmpl $__NR_syscall_max,%eax +#endif ja badsys movq %r10,%rcx call *sys_call_table(,%rax,8) # XXX: rip relative @@ -548,7 +553,7 @@ badsys: #ifdef CONFIG_AUDITSYSCALL /* * Fast path for syscall audit without full syscall trace. - * We just call audit_syscall_entry() directly, and then + * We just call __audit_syscall_entry() directly, and then * jump back to the normal fast path. */ auditsys: @@ -558,22 +563,21 @@ auditsys: movq %rdi,%rdx /* 3rd arg: 1st syscall arg */ movq %rax,%rsi /* 2nd arg: syscall number */ movl $AUDIT_ARCH_X86_64,%edi /* 1st arg: audit arch */ - call audit_syscall_entry + call __audit_syscall_entry LOAD_ARGS 0 /* reload call-clobbered registers */ jmp system_call_fastpath /* - * Return fast path for syscall audit. Call audit_syscall_exit() + * Return fast path for syscall audit. Call __audit_syscall_exit() * directly and then jump back to the fast path with TIF_SYSCALL_AUDIT * masked off. */ sysret_audit: movq RAX-ARGOFFSET(%rsp),%rsi /* second arg, syscall return value */ - cmpq $0,%rsi /* is it < 0? */ - setl %al /* 1 if so, 0 if not */ + cmpq $-MAX_ERRNO,%rsi /* is it < -MAX_ERRNO? */ + setbe %al /* 1 if so, 0 if not */ movzbl %al,%edi /* zero-extend that into %edi */ - inc %edi /* first arg, 0->1(AUDITSC_SUCCESS), 1->2(AUDITSC_FAILURE) */ - call audit_syscall_exit + call __audit_syscall_exit movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi jmp sysret_check #endif /* CONFIG_AUDITSYSCALL */ @@ -596,7 +600,12 @@ tracesys: */ LOAD_ARGS ARGOFFSET, 1 RESTORE_REST +#if __SYSCALL_MASK == ~0 cmpq $__NR_syscall_max,%rax +#else + andl $__SYSCALL_MASK,%eax + cmpl $__NR_syscall_max,%eax +#endif ja int_ret_from_sys_call /* RAX(%rsp) set to -ENOSYS above */ movq %r10,%rcx /* fixup for C */ call *sys_call_table(,%rax,8) @@ -736,6 +745,40 @@ ENTRY(stub_rt_sigreturn) CFI_ENDPROC END(stub_rt_sigreturn) +#ifdef CONFIG_X86_X32_ABI + PTREGSCALL stub_x32_sigaltstack, sys32_sigaltstack, %rdx + +ENTRY(stub_x32_rt_sigreturn) + CFI_STARTPROC + addq $8, %rsp + PARTIAL_FRAME 0 + SAVE_REST + movq %rsp,%rdi + FIXUP_TOP_OF_STACK %r11 + call sys32_x32_rt_sigreturn + movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer + RESTORE_REST + jmp int_ret_from_sys_call + CFI_ENDPROC +END(stub_x32_rt_sigreturn) + +ENTRY(stub_x32_execve) + CFI_STARTPROC + addq $8, %rsp + PARTIAL_FRAME 0 + SAVE_REST + FIXUP_TOP_OF_STACK %r11 + movq %rsp, %rcx + call sys32_execve + RESTORE_TOP_OF_STACK %r11 + movq %rax,RAX(%rsp) + RESTORE_REST + jmp int_ret_from_sys_call + CFI_ENDPROC +END(stub_x32_execve) + +#endif + /* * Build the entry stubs and pointer table with some assembler magic. * We pack 7 stubs into a single 32-byte chunk, which will fit in a @@ -813,7 +856,7 @@ ret_from_intr: /* Restore saved previous stack */ popq %rsi - CFI_DEF_CFA_REGISTER rsi + CFI_DEF_CFA rsi,SS+8-RBP /* reg/off reset after def_cfa_expr */ leaq ARGOFFSET-RBP(%rsi), %rsp CFI_DEF_CFA_REGISTER rsp CFI_ADJUST_CFA_OFFSET RBP-ARGOFFSET @@ -1480,60 +1523,225 @@ ENTRY(error_exit) CFI_ENDPROC END(error_exit) +/* + * Test if a given stack is an NMI stack or not. + */ + .macro test_in_nmi reg stack nmi_ret normal_ret + cmpq %\reg, \stack + ja \normal_ret + subq $EXCEPTION_STKSZ, %\reg + cmpq %\reg, \stack + jb \normal_ret + jmp \nmi_ret + .endm /* runs on exception stack */ ENTRY(nmi) INTR_FRAME PARAVIRT_ADJUST_EXCEPTION_FRAME - pushq_cfi $-1 + /* + * We allow breakpoints in NMIs. If a breakpoint occurs, then + * the iretq it performs will take us out of NMI context. + * This means that we can have nested NMIs where the next + * NMI is using the top of the stack of the previous NMI. We + * can't let it execute because the nested NMI will corrupt the + * stack of the previous NMI. NMI handlers are not re-entrant + * anyway. + * + * To handle this case we do the following: + * Check the a special location on the stack that contains + * a variable that is set when NMIs are executing. + * The interrupted task's stack is also checked to see if it + * is an NMI stack. + * If the variable is not set and the stack is not the NMI + * stack then: + * o Set the special variable on the stack + * o Copy the interrupt frame into a "saved" location on the stack + * o Copy the interrupt frame into a "copy" location on the stack + * o Continue processing the NMI + * If the variable is set or the previous stack is the NMI stack: + * o Modify the "copy" location to jump to the repeate_nmi + * o return back to the first NMI + * + * Now on exit of the first NMI, we first clear the stack variable + * The NMI stack will tell any nested NMIs at that point that it is + * nested. Then we pop the stack normally with iret, and if there was + * a nested NMI that updated the copy interrupt stack frame, a + * jump will be made to the repeat_nmi code that will handle the second + * NMI. + */ + + /* Use %rdx as out temp variable throughout */ + pushq_cfi %rdx + CFI_REL_OFFSET rdx, 0 + + /* + * If %cs was not the kernel segment, then the NMI triggered in user + * space, which means it is definitely not nested. + */ + cmpl $__KERNEL_CS, 16(%rsp) + jne first_nmi + + /* + * Check the special variable on the stack to see if NMIs are + * executing. + */ + cmpl $1, -8(%rsp) + je nested_nmi + + /* + * Now test if the previous stack was an NMI stack. + * We need the double check. We check the NMI stack to satisfy the + * race when the first NMI clears the variable before returning. + * We check the variable because the first NMI could be in a + * breakpoint routine using a breakpoint stack. + */ + lea 6*8(%rsp), %rdx + test_in_nmi rdx, 4*8(%rsp), nested_nmi, first_nmi + CFI_REMEMBER_STATE + +nested_nmi: + /* + * Do nothing if we interrupted the fixup in repeat_nmi. + * It's about to repeat the NMI handler, so we are fine + * with ignoring this one. + */ + movq $repeat_nmi, %rdx + cmpq 8(%rsp), %rdx + ja 1f + movq $end_repeat_nmi, %rdx + cmpq 8(%rsp), %rdx + ja nested_nmi_out + +1: + /* Set up the interrupted NMIs stack to jump to repeat_nmi */ + leaq -6*8(%rsp), %rdx + movq %rdx, %rsp + CFI_ADJUST_CFA_OFFSET 6*8 + pushq_cfi $__KERNEL_DS + pushq_cfi %rdx + pushfq_cfi + pushq_cfi $__KERNEL_CS + pushq_cfi $repeat_nmi + + /* Put stack back */ + addq $(11*8), %rsp + CFI_ADJUST_CFA_OFFSET -11*8 + +nested_nmi_out: + popq_cfi %rdx + CFI_RESTORE rdx + + /* No need to check faults here */ + INTERRUPT_RETURN + + CFI_RESTORE_STATE +first_nmi: + /* + * Because nested NMIs will use the pushed location that we + * stored in rdx, we must keep that space available. + * Here's what our stack frame will look like: + * +-------------------------+ + * | original SS | + * | original Return RSP | + * | original RFLAGS | + * | original CS | + * | original RIP | + * +-------------------------+ + * | temp storage for rdx | + * +-------------------------+ + * | NMI executing variable | + * +-------------------------+ + * | Saved SS | + * | Saved Return RSP | + * | Saved RFLAGS | + * | Saved CS | + * | Saved RIP | + * +-------------------------+ + * | copied SS | + * | copied Return RSP | + * | copied RFLAGS | + * | copied CS | + * | copied RIP | + * +-------------------------+ + * | pt_regs | + * +-------------------------+ + * + * The saved stack frame is used to fix up the copied stack frame + * that a nested NMI may change to make the interrupted NMI iret jump + * to the repeat_nmi. The original stack frame and the temp storage + * is also used by nested NMIs and can not be trusted on exit. + */ + /* Do not pop rdx, nested NMIs will corrupt that part of the stack */ + movq (%rsp), %rdx + CFI_RESTORE rdx + + /* Set the NMI executing variable on the stack. */ + pushq_cfi $1 + + /* Copy the stack frame to the Saved frame */ + .rept 5 + pushq_cfi 6*8(%rsp) + .endr + CFI_DEF_CFA_OFFSET SS+8-RIP + + /* Everything up to here is safe from nested NMIs */ + + /* + * If there was a nested NMI, the first NMI's iret will return + * here. But NMIs are still enabled and we can take another + * nested NMI. The nested NMI checks the interrupted RIP to see + * if it is between repeat_nmi and end_repeat_nmi, and if so + * it will just return, as we are about to repeat an NMI anyway. + * This makes it safe to copy to the stack frame that a nested + * NMI will update. + */ +repeat_nmi: + /* + * Update the stack variable to say we are still in NMI (the update + * is benign for the non-repeat case, where 1 was pushed just above + * to this very stack slot). + */ + movq $1, 5*8(%rsp) + + /* Make another copy, this one may be modified by nested NMIs */ + .rept 5 + pushq_cfi 4*8(%rsp) + .endr + CFI_DEF_CFA_OFFSET SS+8-RIP +end_repeat_nmi: + + /* + * Everything below this point can be preempted by a nested + * NMI if the first NMI took an exception and reset our iret stack + * so that we repeat another NMI. + */ + pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ subq $ORIG_RAX-R15, %rsp CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 + /* + * Use save_paranoid to handle SWAPGS, but no need to use paranoid_exit + * as we should not be calling schedule in NMI context. + * Even with normal interrupts enabled. An NMI should not be + * setting NEED_RESCHED or anything that normal interrupts and + * exceptions might do. + */ call save_paranoid DEFAULT_FRAME 0 /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */ movq %rsp,%rdi movq $-1,%rsi call do_nmi -#ifdef CONFIG_TRACE_IRQFLAGS - /* paranoidexit; without TRACE_IRQS_OFF */ - /* ebx: no swapgs flag */ - DISABLE_INTERRUPTS(CLBR_NONE) testl %ebx,%ebx /* swapgs needed? */ jnz nmi_restore - testl $3,CS(%rsp) - jnz nmi_userspace nmi_swapgs: SWAPGS_UNSAFE_STACK nmi_restore: RESTORE_ALL 8 + /* Clear the NMI executing stack variable */ + movq $0, 10*8(%rsp) jmp irq_return -nmi_userspace: - GET_THREAD_INFO(%rcx) - movl TI_flags(%rcx),%ebx - andl $_TIF_WORK_MASK,%ebx - jz nmi_swapgs - movq %rsp,%rdi /* &pt_regs */ - call sync_regs - movq %rax,%rsp /* switch stack for scheduling */ - testl $_TIF_NEED_RESCHED,%ebx - jnz nmi_schedule - movl %ebx,%edx /* arg3: thread flags */ - ENABLE_INTERRUPTS(CLBR_NONE) - xorl %esi,%esi /* arg2: oldset */ - movq %rsp,%rdi /* arg1: &pt_regs */ - call do_notify_resume - DISABLE_INTERRUPTS(CLBR_NONE) - jmp nmi_userspace -nmi_schedule: - ENABLE_INTERRUPTS(CLBR_ANY) - call schedule - DISABLE_INTERRUPTS(CLBR_ANY) - jmp nmi_userspace CFI_ENDPROC -#else - jmp paranoid_exit - CFI_ENDPROC -#endif END(nmi) ENTRY(ignore_sysret) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index e11e39478a4..40f4eb3766d 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -417,6 +417,10 @@ ENTRY(phys_base) ENTRY(idt_table) .skip IDT_ENTRIES * 16 + .align L1_CACHE_BYTES +ENTRY(nmi_idt_table) + .skip IDT_ENTRIES * 16 + __PAGE_ALIGNED_BSS .align PAGE_SIZE ENTRY(empty_zero_page) diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 739d8598f78..7734bcbb5a3 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -16,6 +16,7 @@ #include <asm/uaccess.h> #include <asm/ptrace.h> #include <asm/i387.h> +#include <asm/fpu-internal.h> #include <asm/user.h> #ifdef CONFIG_X86_64 @@ -32,6 +33,86 @@ # define user32_fxsr_struct user_fxsr_struct #endif +/* + * Were we in an interrupt that interrupted kernel mode? + * + * We can do a kernel_fpu_begin/end() pair *ONLY* if that + * pair does nothing at all: the thread must not have fpu (so + * that we don't try to save the FPU state), and TS must + * be set (so that the clts/stts pair does nothing that is + * visible in the interrupted kernel thread). + */ +static inline bool interrupted_kernel_fpu_idle(void) +{ + return !__thread_has_fpu(current) && + (read_cr0() & X86_CR0_TS); +} + +/* + * Were we in user mode (or vm86 mode) when we were + * interrupted? + * + * Doing kernel_fpu_begin/end() is ok if we are running + * in an interrupt context from user mode - we'll just + * save the FPU state as required. + */ +static inline bool interrupted_user_mode(void) +{ + struct pt_regs *regs = get_irq_regs(); + return regs && user_mode_vm(regs); +} + +/* + * Can we use the FPU in kernel mode with the + * whole "kernel_fpu_begin/end()" sequence? + * + * It's always ok in process context (ie "not interrupt") + * but it is sometimes ok even from an irq. + */ +bool irq_fpu_usable(void) +{ + return !in_interrupt() || + interrupted_user_mode() || + interrupted_kernel_fpu_idle(); +} +EXPORT_SYMBOL(irq_fpu_usable); + +void kernel_fpu_begin(void) +{ + struct task_struct *me = current; + + WARN_ON_ONCE(!irq_fpu_usable()); + preempt_disable(); + if (__thread_has_fpu(me)) { + __save_init_fpu(me); + __thread_clear_has_fpu(me); + /* We do 'stts()' in kernel_fpu_end() */ + } else { + percpu_write(fpu_owner_task, NULL); + clts(); + } +} +EXPORT_SYMBOL(kernel_fpu_begin); + +void kernel_fpu_end(void) +{ + stts(); + preempt_enable(); +} +EXPORT_SYMBOL(kernel_fpu_end); + +void unlazy_fpu(struct task_struct *tsk) +{ + preempt_disable(); + if (__thread_has_fpu(tsk)) { + __save_init_fpu(tsk); + __thread_fpu_end(tsk); + } else + tsk->fpu_counter = 0; + preempt_enable(); +} +EXPORT_SYMBOL(unlazy_fpu); + #ifdef CONFIG_MATH_EMULATION # define HAVE_HWFP (boot_cpu_data.hard_math) #else @@ -44,7 +125,7 @@ EXPORT_SYMBOL_GPL(xstate_size); unsigned int sig_xstate_ia32_size = sizeof(struct _fpstate_ia32); static struct i387_fxsave_struct fx_scratch __cpuinitdata; -void __cpuinit mxcsr_feature_mask_init(void) +static void __cpuinit mxcsr_feature_mask_init(void) { unsigned long mask = 0; diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 610485223bd..36d1853e91a 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -15,7 +15,6 @@ #include <linux/delay.h> #include <linux/atomic.h> -#include <asm/system.h> #include <asm/timer.h> #include <asm/hw_irq.h> #include <asm/pgtable.h> diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 7943e0c21bd..3dafc6003b7 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -282,8 +282,13 @@ void fixup_irqs(void) else if (!(warned++)) set_affinity = 0; + /* + * We unmask if the irq was not marked masked by the + * core code. That respects the lazy irq disable + * behaviour. + */ if (!irqd_can_move_in_process_context(data) && - !irqd_irq_disabled(data) && chip->irq_unmask) + !irqd_irq_masked(data) && chip->irq_unmask) chip->irq_unmask(data); raw_spin_unlock(&desc->lock); diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 72090705a65..58b7f27cb3e 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -28,6 +28,9 @@ DEFINE_PER_CPU(struct pt_regs *, irq_regs); EXPORT_PER_CPU_SYMBOL(irq_regs); #ifdef CONFIG_DEBUG_STACKOVERFLOW + +int sysctl_panic_on_stackoverflow __read_mostly; + /* Debugging check for stack overflow: is there less than 1KB free? */ static int check_stack_overflow(void) { @@ -43,6 +46,8 @@ static void print_stack_overflow(void) { printk(KERN_WARNING "low stack detected by irq handler\n"); dump_stack(); + if (sysctl_panic_on_stackoverflow) + panic("low stack detected by irq handler - check messages\n"); } #else @@ -95,13 +100,8 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) irqctx->tinfo.task = curctx->tinfo.task; irqctx->tinfo.previous_esp = current_stack_pointer; - /* - * Copy the softirq bits in preempt_count so that the - * softirq checks work in the hardirq context. - */ - irqctx->tinfo.preempt_count = - (irqctx->tinfo.preempt_count & ~SOFTIRQ_MASK) | - (curctx->tinfo.preempt_count & SOFTIRQ_MASK); + /* Copy the preempt_count so that the [soft]irq checks work. */ + irqctx->tinfo.preempt_count = curctx->tinfo.preempt_count; if (unlikely(overflow)) call_on_stack(print_stack_overflow, isp); @@ -191,7 +191,7 @@ bool handle_irq(unsigned irq, struct pt_regs *regs) if (unlikely(!desc)) return false; - if (!execute_on_irq_stack(overflow, desc, irq)) { + if (user_mode_vm(regs) || !execute_on_irq_stack(overflow, desc, irq)) { if (unlikely(overflow)) print_stack_overflow(); desc->handle_irq(irq, desc); diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 69bca468c47..d04d3ecded6 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -26,6 +26,8 @@ EXPORT_PER_CPU_SYMBOL(irq_stat); DEFINE_PER_CPU(struct pt_regs *, irq_regs); EXPORT_PER_CPU_SYMBOL(irq_regs); +int sysctl_panic_on_stackoverflow; + /* * Probabilistic stack overflow check: * @@ -36,18 +38,39 @@ EXPORT_PER_CPU_SYMBOL(irq_regs); static inline void stack_overflow_check(struct pt_regs *regs) { #ifdef CONFIG_DEBUG_STACKOVERFLOW +#define STACK_TOP_MARGIN 128 + struct orig_ist *oist; + u64 irq_stack_top, irq_stack_bottom; + u64 estack_top, estack_bottom; u64 curbase = (u64)task_stack_page(current); if (user_mode_vm(regs)) return; - WARN_ONCE(regs->sp >= curbase && - regs->sp <= curbase + THREAD_SIZE && - regs->sp < curbase + sizeof(struct thread_info) + - sizeof(struct pt_regs) + 128, + if (regs->sp >= curbase + sizeof(struct thread_info) + + sizeof(struct pt_regs) + STACK_TOP_MARGIN && + regs->sp <= curbase + THREAD_SIZE) + return; + + irq_stack_top = (u64)__get_cpu_var(irq_stack_union.irq_stack) + + STACK_TOP_MARGIN; + irq_stack_bottom = (u64)__get_cpu_var(irq_stack_ptr); + if (regs->sp >= irq_stack_top && regs->sp <= irq_stack_bottom) + return; + + oist = &__get_cpu_var(orig_ist); + estack_top = (u64)oist->ist[0] - EXCEPTION_STKSZ + STACK_TOP_MARGIN; + estack_bottom = (u64)oist->ist[N_EXCEPTION_STACKS - 1]; + if (regs->sp >= estack_top && regs->sp <= estack_bottom) + return; + + WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx)\n", + current->comm, curbase, regs->sp, + irq_stack_top, irq_stack_bottom, + estack_top, estack_bottom); - "do_IRQ: %s near stack overflow (cur:%Lx,sp:%lx)\n", - current->comm, curbase, regs->sp); + if (sysctl_panic_on_stackoverflow) + panic("low stack detected by irq handler - check messages\n"); #endif } diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 313fb5cddbc..252981afd6c 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -16,7 +16,6 @@ #include <linux/delay.h> #include <linux/atomic.h> -#include <asm/system.h> #include <asm/timer.h> #include <asm/hw_irq.h> #include <asm/pgtable.h> @@ -61,7 +60,7 @@ static irqreturn_t math_error_irq(int cpl, void *dev_id) outb(0, 0xF0); if (ignore_fpu_irq || !boot_cpu_data.hard_math) return IRQ_NONE; - math_error(get_irq_regs(), 0, 16); + math_error(get_irq_regs(), 0, X86_TRAP_MF); return IRQ_HANDLED; } @@ -306,10 +305,10 @@ void __init native_init_IRQ(void) * us. (some of these will be overridden and become * 'special' SMP interrupts) */ - for (i = FIRST_EXTERNAL_VECTOR; i < NR_VECTORS; i++) { + i = FIRST_EXTERNAL_VECTOR; + for_each_clear_bit_from(i, used_vectors, NR_VECTORS) { /* IA32_SYSCALL_VECTOR could be used in trap_init already. */ - if (!test_bit(i, used_vectors)) - set_intr_gate(i, interrupt[i-FIRST_EXTERNAL_VECTOR]); + set_intr_gate(i, interrupt[i - FIRST_EXTERNAL_VECTOR]); } if (!acpi_ioapic && !of_ioapic) diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c index 90fcf62854b..1d5d31ea686 100644 --- a/arch/x86/kernel/kdebugfs.c +++ b/arch/x86/kernel/kdebugfs.c @@ -68,16 +68,9 @@ static ssize_t setup_data_read(struct file *file, char __user *user_buf, return count; } -static int setup_data_open(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - - return 0; -} - static const struct file_operations fops_setup_data = { .read = setup_data_read, - .open = setup_data_open, + .open = simple_open, .llseek = default_llseek, }; diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index faba5771aca..8bfb6146f75 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -43,10 +43,11 @@ #include <linux/smp.h> #include <linux/nmi.h> #include <linux/hw_breakpoint.h> +#include <linux/uaccess.h> +#include <linux/memory.h> #include <asm/debugreg.h> #include <asm/apicdef.h> -#include <asm/system.h> #include <asm/apic.h> #include <asm/nmi.h> @@ -67,8 +68,6 @@ struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = { "ss", 4, offsetof(struct pt_regs, ss) }, { "ds", 4, offsetof(struct pt_regs, ds) }, { "es", 4, offsetof(struct pt_regs, es) }, - { "fs", 4, -1 }, - { "gs", 4, -1 }, #else { "ax", 8, offsetof(struct pt_regs, ax) }, { "bx", 8, offsetof(struct pt_regs, bx) }, @@ -90,7 +89,11 @@ struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = { "flags", 4, offsetof(struct pt_regs, flags) }, { "cs", 4, offsetof(struct pt_regs, cs) }, { "ss", 4, offsetof(struct pt_regs, ss) }, + { "ds", 4, -1 }, + { "es", 4, -1 }, #endif + { "fs", 4, -1 }, + { "gs", 4, -1 }, }; int dbg_set_reg(int regno, void *mem, struct pt_regs *regs) @@ -740,6 +743,64 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip) regs->ip = ip; } +int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) +{ + int err; + char opc[BREAK_INSTR_SIZE]; + + bpt->type = BP_BREAKPOINT; + err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr, + BREAK_INSTR_SIZE); + if (err) + return err; + err = probe_kernel_write((char *)bpt->bpt_addr, + arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE); +#ifdef CONFIG_DEBUG_RODATA + if (!err) + return err; + /* + * It is safe to call text_poke() because normal kernel execution + * is stopped on all cores, so long as the text_mutex is not locked. + */ + if (mutex_is_locked(&text_mutex)) + return -EBUSY; + text_poke((void *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr, + BREAK_INSTR_SIZE); + err = probe_kernel_read(opc, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE); + if (err) + return err; + if (memcmp(opc, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE)) + return -EINVAL; + bpt->type = BP_POKE_BREAKPOINT; +#endif /* CONFIG_DEBUG_RODATA */ + return err; +} + +int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt) +{ +#ifdef CONFIG_DEBUG_RODATA + int err; + char opc[BREAK_INSTR_SIZE]; + + if (bpt->type != BP_POKE_BREAKPOINT) + goto knl_write; + /* + * It is safe to call text_poke() because normal kernel execution + * is stopped on all cores, so long as the text_mutex is not locked. + */ + if (mutex_is_locked(&text_mutex)) + goto knl_write; + text_poke((void *)bpt->bpt_addr, bpt->saved_instr, BREAK_INSTR_SIZE); + err = probe_kernel_read(opc, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE); + if (err || memcmp(opc, bpt->saved_instr, BREAK_INSTR_SIZE)) + goto knl_write; + return err; +knl_write: +#endif /* CONFIG_DEBUG_RODATA */ + return probe_kernel_write((char *)bpt->bpt_addr, + (char *)bpt->saved_instr, BREAK_INSTR_SIZE); +} + struct kgdb_arch arch_kgdb_ops = { /* Breakpoint instruction: */ .gdb_bpt_instr = { 0xcc }, diff --git a/arch/x86/kernel/kprobes-common.h b/arch/x86/kernel/kprobes-common.h new file mode 100644 index 00000000000..3230b68ef29 --- /dev/null +++ b/arch/x86/kernel/kprobes-common.h @@ -0,0 +1,102 @@ +#ifndef __X86_KERNEL_KPROBES_COMMON_H +#define __X86_KERNEL_KPROBES_COMMON_H + +/* Kprobes and Optprobes common header */ + +#ifdef CONFIG_X86_64 +#define SAVE_REGS_STRING \ + /* Skip cs, ip, orig_ax. */ \ + " subq $24, %rsp\n" \ + " pushq %rdi\n" \ + " pushq %rsi\n" \ + " pushq %rdx\n" \ + " pushq %rcx\n" \ + " pushq %rax\n" \ + " pushq %r8\n" \ + " pushq %r9\n" \ + " pushq %r10\n" \ + " pushq %r11\n" \ + " pushq %rbx\n" \ + " pushq %rbp\n" \ + " pushq %r12\n" \ + " pushq %r13\n" \ + " pushq %r14\n" \ + " pushq %r15\n" +#define RESTORE_REGS_STRING \ + " popq %r15\n" \ + " popq %r14\n" \ + " popq %r13\n" \ + " popq %r12\n" \ + " popq %rbp\n" \ + " popq %rbx\n" \ + " popq %r11\n" \ + " popq %r10\n" \ + " popq %r9\n" \ + " popq %r8\n" \ + " popq %rax\n" \ + " popq %rcx\n" \ + " popq %rdx\n" \ + " popq %rsi\n" \ + " popq %rdi\n" \ + /* Skip orig_ax, ip, cs */ \ + " addq $24, %rsp\n" +#else +#define SAVE_REGS_STRING \ + /* Skip cs, ip, orig_ax and gs. */ \ + " subl $16, %esp\n" \ + " pushl %fs\n" \ + " pushl %es\n" \ + " pushl %ds\n" \ + " pushl %eax\n" \ + " pushl %ebp\n" \ + " pushl %edi\n" \ + " pushl %esi\n" \ + " pushl %edx\n" \ + " pushl %ecx\n" \ + " pushl %ebx\n" +#define RESTORE_REGS_STRING \ + " popl %ebx\n" \ + " popl %ecx\n" \ + " popl %edx\n" \ + " popl %esi\n" \ + " popl %edi\n" \ + " popl %ebp\n" \ + " popl %eax\n" \ + /* Skip ds, es, fs, gs, orig_ax, and ip. Note: don't pop cs here*/\ + " addl $24, %esp\n" +#endif + +/* Ensure if the instruction can be boostable */ +extern int can_boost(kprobe_opcode_t *instruction); +/* Recover instruction if given address is probed */ +extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf, + unsigned long addr); +/* + * Copy an instruction and adjust the displacement if the instruction + * uses the %rip-relative addressing mode. + */ +extern int __copy_instruction(u8 *dest, u8 *src); + +/* Generate a relative-jump/call instruction */ +extern void synthesize_reljump(void *from, void *to); +extern void synthesize_relcall(void *from, void *to); + +#ifdef CONFIG_OPTPROBES +extern int arch_init_optprobes(void); +extern int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter); +extern unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr); +#else /* !CONFIG_OPTPROBES */ +static inline int arch_init_optprobes(void) +{ + return 0; +} +static inline int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) +{ + return 0; +} +static inline unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr) +{ + return addr; +} +#endif +#endif diff --git a/arch/x86/kernel/kprobes-opt.c b/arch/x86/kernel/kprobes-opt.c new file mode 100644 index 00000000000..c5e410eed40 --- /dev/null +++ b/arch/x86/kernel/kprobes-opt.c @@ -0,0 +1,512 @@ +/* + * Kernel Probes Jump Optimization (Optprobes) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2002, 2004 + * Copyright (C) Hitachi Ltd., 2012 + */ +#include <linux/kprobes.h> +#include <linux/ptrace.h> +#include <linux/string.h> +#include <linux/slab.h> +#include <linux/hardirq.h> +#include <linux/preempt.h> +#include <linux/module.h> +#include <linux/kdebug.h> +#include <linux/kallsyms.h> +#include <linux/ftrace.h> + +#include <asm/cacheflush.h> +#include <asm/desc.h> +#include <asm/pgtable.h> +#include <asm/uaccess.h> +#include <asm/alternative.h> +#include <asm/insn.h> +#include <asm/debugreg.h> + +#include "kprobes-common.h" + +unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr) +{ + struct optimized_kprobe *op; + struct kprobe *kp; + long offs; + int i; + + for (i = 0; i < RELATIVEJUMP_SIZE; i++) { + kp = get_kprobe((void *)addr - i); + /* This function only handles jump-optimized kprobe */ + if (kp && kprobe_optimized(kp)) { + op = container_of(kp, struct optimized_kprobe, kp); + /* If op->list is not empty, op is under optimizing */ + if (list_empty(&op->list)) + goto found; + } + } + + return addr; +found: + /* + * If the kprobe can be optimized, original bytes which can be + * overwritten by jump destination address. In this case, original + * bytes must be recovered from op->optinsn.copied_insn buffer. + */ + memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); + if (addr == (unsigned long)kp->addr) { + buf[0] = kp->opcode; + memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); + } else { + offs = addr - (unsigned long)kp->addr - 1; + memcpy(buf, op->optinsn.copied_insn + offs, RELATIVE_ADDR_SIZE - offs); + } + + return (unsigned long)buf; +} + +/* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */ +static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val) +{ +#ifdef CONFIG_X86_64 + *addr++ = 0x48; + *addr++ = 0xbf; +#else + *addr++ = 0xb8; +#endif + *(unsigned long *)addr = val; +} + +static void __used __kprobes kprobes_optinsn_template_holder(void) +{ + asm volatile ( + ".global optprobe_template_entry\n" + "optprobe_template_entry:\n" +#ifdef CONFIG_X86_64 + /* We don't bother saving the ss register */ + " pushq %rsp\n" + " pushfq\n" + SAVE_REGS_STRING + " movq %rsp, %rsi\n" + ".global optprobe_template_val\n" + "optprobe_template_val:\n" + ASM_NOP5 + ASM_NOP5 + ".global optprobe_template_call\n" + "optprobe_template_call:\n" + ASM_NOP5 + /* Move flags to rsp */ + " movq 144(%rsp), %rdx\n" + " movq %rdx, 152(%rsp)\n" + RESTORE_REGS_STRING + /* Skip flags entry */ + " addq $8, %rsp\n" + " popfq\n" +#else /* CONFIG_X86_32 */ + " pushf\n" + SAVE_REGS_STRING + " movl %esp, %edx\n" + ".global optprobe_template_val\n" + "optprobe_template_val:\n" + ASM_NOP5 + ".global optprobe_template_call\n" + "optprobe_template_call:\n" + ASM_NOP5 + RESTORE_REGS_STRING + " addl $4, %esp\n" /* skip cs */ + " popf\n" +#endif + ".global optprobe_template_end\n" + "optprobe_template_end:\n"); +} + +#define TMPL_MOVE_IDX \ + ((long)&optprobe_template_val - (long)&optprobe_template_entry) +#define TMPL_CALL_IDX \ + ((long)&optprobe_template_call - (long)&optprobe_template_entry) +#define TMPL_END_IDX \ + ((long)&optprobe_template_end - (long)&optprobe_template_entry) + +#define INT3_SIZE sizeof(kprobe_opcode_t) + +/* Optimized kprobe call back function: called from optinsn */ +static void __kprobes optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + unsigned long flags; + + /* This is possible if op is under delayed unoptimizing */ + if (kprobe_disabled(&op->kp)) + return; + + local_irq_save(flags); + if (kprobe_running()) { + kprobes_inc_nmissed_count(&op->kp); + } else { + /* Save skipped registers */ +#ifdef CONFIG_X86_64 + regs->cs = __KERNEL_CS; +#else + regs->cs = __KERNEL_CS | get_kernel_rpl(); + regs->gs = 0; +#endif + regs->ip = (unsigned long)op->kp.addr + INT3_SIZE; + regs->orig_ax = ~0UL; + + __this_cpu_write(current_kprobe, &op->kp); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + opt_pre_handler(&op->kp, regs); + __this_cpu_write(current_kprobe, NULL); + } + local_irq_restore(flags); +} + +static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src) +{ + int len = 0, ret; + + while (len < RELATIVEJUMP_SIZE) { + ret = __copy_instruction(dest + len, src + len); + if (!ret || !can_boost(dest + len)) + return -EINVAL; + len += ret; + } + /* Check whether the address range is reserved */ + if (ftrace_text_reserved(src, src + len - 1) || + alternatives_text_reserved(src, src + len - 1) || + jump_label_text_reserved(src, src + len - 1)) + return -EBUSY; + + return len; +} + +/* Check whether insn is indirect jump */ +static int __kprobes insn_is_indirect_jump(struct insn *insn) +{ + return ((insn->opcode.bytes[0] == 0xff && + (X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */ + insn->opcode.bytes[0] == 0xea); /* Segment based jump */ +} + +/* Check whether insn jumps into specified address range */ +static int insn_jump_into_range(struct insn *insn, unsigned long start, int len) +{ + unsigned long target = 0; + + switch (insn->opcode.bytes[0]) { + case 0xe0: /* loopne */ + case 0xe1: /* loope */ + case 0xe2: /* loop */ + case 0xe3: /* jcxz */ + case 0xe9: /* near relative jump */ + case 0xeb: /* short relative jump */ + break; + case 0x0f: + if ((insn->opcode.bytes[1] & 0xf0) == 0x80) /* jcc near */ + break; + return 0; + default: + if ((insn->opcode.bytes[0] & 0xf0) == 0x70) /* jcc short */ + break; + return 0; + } + target = (unsigned long)insn->next_byte + insn->immediate.value; + + return (start <= target && target <= start + len); +} + +/* Decode whole function to ensure any instructions don't jump into target */ +static int __kprobes can_optimize(unsigned long paddr) +{ + unsigned long addr, size = 0, offset = 0; + struct insn insn; + kprobe_opcode_t buf[MAX_INSN_SIZE]; + + /* Lookup symbol including addr */ + if (!kallsyms_lookup_size_offset(paddr, &size, &offset)) + return 0; + + /* + * Do not optimize in the entry code due to the unstable + * stack handling. + */ + if ((paddr >= (unsigned long)__entry_text_start) && + (paddr < (unsigned long)__entry_text_end)) + return 0; + + /* Check there is enough space for a relative jump. */ + if (size - offset < RELATIVEJUMP_SIZE) + return 0; + + /* Decode instructions */ + addr = paddr - offset; + while (addr < paddr - offset + size) { /* Decode until function end */ + if (search_exception_tables(addr)) + /* + * Since some fixup code will jumps into this function, + * we can't optimize kprobe in this function. + */ + return 0; + kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, addr)); + insn_get_length(&insn); + /* Another subsystem puts a breakpoint */ + if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) + return 0; + /* Recover address */ + insn.kaddr = (void *)addr; + insn.next_byte = (void *)(addr + insn.length); + /* Check any instructions don't jump into target */ + if (insn_is_indirect_jump(&insn) || + insn_jump_into_range(&insn, paddr + INT3_SIZE, + RELATIVE_ADDR_SIZE)) + return 0; + addr += insn.length; + } + + return 1; +} + +/* Check optimized_kprobe can actually be optimized. */ +int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op) +{ + int i; + struct kprobe *p; + + for (i = 1; i < op->optinsn.size; i++) { + p = get_kprobe(op->kp.addr + i); + if (p && !kprobe_disabled(p)) + return -EEXIST; + } + + return 0; +} + +/* Check the addr is within the optimized instructions. */ +int __kprobes +arch_within_optimized_kprobe(struct optimized_kprobe *op, unsigned long addr) +{ + return ((unsigned long)op->kp.addr <= addr && + (unsigned long)op->kp.addr + op->optinsn.size > addr); +} + +/* Free optimized instruction slot */ +static __kprobes +void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty) +{ + if (op->optinsn.insn) { + free_optinsn_slot(op->optinsn.insn, dirty); + op->optinsn.insn = NULL; + op->optinsn.size = 0; + } +} + +void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op) +{ + __arch_remove_optimized_kprobe(op, 1); +} + +/* + * Copy replacing target instructions + * Target instructions MUST be relocatable (checked inside) + * This is called when new aggr(opt)probe is allocated or reused. + */ +int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op) +{ + u8 *buf; + int ret; + long rel; + + if (!can_optimize((unsigned long)op->kp.addr)) + return -EILSEQ; + + op->optinsn.insn = get_optinsn_slot(); + if (!op->optinsn.insn) + return -ENOMEM; + + /* + * Verify if the address gap is in 2GB range, because this uses + * a relative jump. + */ + rel = (long)op->optinsn.insn - (long)op->kp.addr + RELATIVEJUMP_SIZE; + if (abs(rel) > 0x7fffffff) + return -ERANGE; + + buf = (u8 *)op->optinsn.insn; + + /* Copy instructions into the out-of-line buffer */ + ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr); + if (ret < 0) { + __arch_remove_optimized_kprobe(op, 0); + return ret; + } + op->optinsn.size = ret; + + /* Copy arch-dep-instance from template */ + memcpy(buf, &optprobe_template_entry, TMPL_END_IDX); + + /* Set probe information */ + synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op); + + /* Set probe function call */ + synthesize_relcall(buf + TMPL_CALL_IDX, optimized_callback); + + /* Set returning jmp instruction at the tail of out-of-line buffer */ + synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size, + (u8 *)op->kp.addr + op->optinsn.size); + + flush_icache_range((unsigned long) buf, + (unsigned long) buf + TMPL_END_IDX + + op->optinsn.size + RELATIVEJUMP_SIZE); + return 0; +} + +#define MAX_OPTIMIZE_PROBES 256 +static struct text_poke_param *jump_poke_params; +static struct jump_poke_buffer { + u8 buf[RELATIVEJUMP_SIZE]; +} *jump_poke_bufs; + +static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm, + u8 *insn_buf, + struct optimized_kprobe *op) +{ + s32 rel = (s32)((long)op->optinsn.insn - + ((long)op->kp.addr + RELATIVEJUMP_SIZE)); + + /* Backup instructions which will be replaced by jump address */ + memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE, + RELATIVE_ADDR_SIZE); + + insn_buf[0] = RELATIVEJUMP_OPCODE; + *(s32 *)(&insn_buf[1]) = rel; + + tprm->addr = op->kp.addr; + tprm->opcode = insn_buf; + tprm->len = RELATIVEJUMP_SIZE; +} + +/* + * Replace breakpoints (int3) with relative jumps. + * Caller must call with locking kprobe_mutex and text_mutex. + */ +void __kprobes arch_optimize_kprobes(struct list_head *oplist) +{ + struct optimized_kprobe *op, *tmp; + int c = 0; + + list_for_each_entry_safe(op, tmp, oplist, list) { + WARN_ON(kprobe_disabled(&op->kp)); + /* Setup param */ + setup_optimize_kprobe(&jump_poke_params[c], + jump_poke_bufs[c].buf, op); + list_del_init(&op->list); + if (++c >= MAX_OPTIMIZE_PROBES) + break; + } + + /* + * text_poke_smp doesn't support NMI/MCE code modifying. + * However, since kprobes itself also doesn't support NMI/MCE + * code probing, it's not a problem. + */ + text_poke_smp_batch(jump_poke_params, c); +} + +static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm, + u8 *insn_buf, + struct optimized_kprobe *op) +{ + /* Set int3 to first byte for kprobes */ + insn_buf[0] = BREAKPOINT_INSTRUCTION; + memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); + + tprm->addr = op->kp.addr; + tprm->opcode = insn_buf; + tprm->len = RELATIVEJUMP_SIZE; +} + +/* + * Recover original instructions and breakpoints from relative jumps. + * Caller must call with locking kprobe_mutex. + */ +extern void arch_unoptimize_kprobes(struct list_head *oplist, + struct list_head *done_list) +{ + struct optimized_kprobe *op, *tmp; + int c = 0; + + list_for_each_entry_safe(op, tmp, oplist, list) { + /* Setup param */ + setup_unoptimize_kprobe(&jump_poke_params[c], + jump_poke_bufs[c].buf, op); + list_move(&op->list, done_list); + if (++c >= MAX_OPTIMIZE_PROBES) + break; + } + + /* + * text_poke_smp doesn't support NMI/MCE code modifying. + * However, since kprobes itself also doesn't support NMI/MCE + * code probing, it's not a problem. + */ + text_poke_smp_batch(jump_poke_params, c); +} + +/* Replace a relative jump with a breakpoint (int3). */ +void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op) +{ + u8 buf[RELATIVEJUMP_SIZE]; + + /* Set int3 to first byte for kprobes */ + buf[0] = BREAKPOINT_INSTRUCTION; + memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); + text_poke_smp(op->kp.addr, buf, RELATIVEJUMP_SIZE); +} + +int __kprobes +setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) +{ + struct optimized_kprobe *op; + + if (p->flags & KPROBE_FLAG_OPTIMIZED) { + /* This kprobe is really able to run optimized path. */ + op = container_of(p, struct optimized_kprobe, kp); + /* Detour through copied instructions */ + regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX; + if (!reenter) + reset_current_kprobe(); + preempt_enable_no_resched(); + return 1; + } + return 0; +} + +int __kprobes arch_init_optprobes(void) +{ + /* Allocate code buffer and parameter array */ + jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) * + MAX_OPTIMIZE_PROBES, GFP_KERNEL); + if (!jump_poke_bufs) + return -ENOMEM; + + jump_poke_params = kmalloc(sizeof(struct text_poke_param) * + MAX_OPTIMIZE_PROBES, GFP_KERNEL); + if (!jump_poke_params) { + kfree(jump_poke_bufs); + jump_poke_bufs = NULL; + return -ENOMEM; + } + + return 0; +} diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 7da647d8b64..e213fc8408d 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -30,16 +30,15 @@ * <jkenisto@us.ibm.com> and Prasanna S Panchamukhi * <prasanna@in.ibm.com> added function-return probes. * 2005-May Rusty Lynch <rusty.lynch@intel.com> - * Added function return probes functionality + * Added function return probes functionality * 2006-Feb Masami Hiramatsu <hiramatu@sdl.hitachi.co.jp> added - * kprobe-booster and kretprobe-booster for i386. + * kprobe-booster and kretprobe-booster for i386. * 2007-Dec Masami Hiramatsu <mhiramat@redhat.com> added kprobe-booster - * and kretprobe-booster for x86-64 + * and kretprobe-booster for x86-64 * 2007-Dec Masami Hiramatsu <mhiramat@redhat.com>, Arjan van de Ven - * <arjan@infradead.org> and Jim Keniston <jkenisto@us.ibm.com> - * unified x86 kprobes code. + * <arjan@infradead.org> and Jim Keniston <jkenisto@us.ibm.com> + * unified x86 kprobes code. */ - #include <linux/kprobes.h> #include <linux/ptrace.h> #include <linux/string.h> @@ -59,6 +58,8 @@ #include <asm/insn.h> #include <asm/debugreg.h> +#include "kprobes-common.h" + void jprobe_return_end(void); DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; @@ -108,6 +109,7 @@ struct kretprobe_blackpoint kretprobe_blacklist[] = { doesn't switch kernel stack.*/ {NULL, NULL} /* Terminator */ }; + const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist); static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op) @@ -123,11 +125,17 @@ static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op) } /* Insert a jump instruction at address 'from', which jumps to address 'to'.*/ -static void __kprobes synthesize_reljump(void *from, void *to) +void __kprobes synthesize_reljump(void *from, void *to) { __synthesize_relative_insn(from, to, RELATIVEJUMP_OPCODE); } +/* Insert a call instruction at address 'from', which calls address 'to'.*/ +void __kprobes synthesize_relcall(void *from, void *to) +{ + __synthesize_relative_insn(from, to, RELATIVECALL_OPCODE); +} + /* * Skip the prefixes of the instruction. */ @@ -151,7 +159,7 @@ static kprobe_opcode_t *__kprobes skip_prefixes(kprobe_opcode_t *insn) * Returns non-zero if opcode is boostable. * RIP relative instructions are adjusted at copying time in 64 bits mode */ -static int __kprobes can_boost(kprobe_opcode_t *opcodes) +int __kprobes can_boost(kprobe_opcode_t *opcodes) { kprobe_opcode_t opcode; kprobe_opcode_t *orig_opcodes = opcodes; @@ -207,13 +215,15 @@ retry: } } -/* Recover the probed instruction at addr for further analysis. */ -static int recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr) +static unsigned long +__recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr) { struct kprobe *kp; + kp = get_kprobe((void *)addr); + /* There is no probe, return original address */ if (!kp) - return -EINVAL; + return addr; /* * Basically, kp->ainsn.insn has an original instruction. @@ -230,14 +240,29 @@ static int recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr) */ memcpy(buf, kp->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); buf[0] = kp->opcode; - return 0; + return (unsigned long)buf; +} + +/* + * Recover the probed instruction at addr for further analysis. + * Caller must lock kprobes by kprobe_mutex, or disable preemption + * for preventing to release referencing kprobes. + */ +unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr) +{ + unsigned long __addr; + + __addr = __recover_optprobed_insn(buf, addr); + if (__addr != addr) + return __addr; + + return __recover_probed_insn(buf, addr); } /* Check if paddr is at an instruction boundary */ static int __kprobes can_probe(unsigned long paddr) { - int ret; - unsigned long addr, offset = 0; + unsigned long addr, __addr, offset = 0; struct insn insn; kprobe_opcode_t buf[MAX_INSN_SIZE]; @@ -247,26 +272,24 @@ static int __kprobes can_probe(unsigned long paddr) /* Decode instructions */ addr = paddr - offset; while (addr < paddr) { - kernel_insn_init(&insn, (void *)addr); - insn_get_opcode(&insn); - /* * Check if the instruction has been modified by another * kprobe, in which case we replace the breakpoint by the * original instruction in our buffer. + * Also, jump optimization will change the breakpoint to + * relative-jump. Since the relative-jump itself is + * normally used, we just go through if there is no kprobe. */ - if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) { - ret = recover_probed_instruction(buf, addr); - if (ret) - /* - * Another debugging subsystem might insert - * this breakpoint. In that case, we can't - * recover it. - */ - return 0; - kernel_insn_init(&insn, buf); - } + __addr = recover_probed_instruction(buf, addr); + kernel_insn_init(&insn, (void *)__addr); insn_get_length(&insn); + + /* + * Another debugging subsystem might insert this breakpoint. + * In that case, we can't recover it. + */ + if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) + return 0; addr += insn.length; } @@ -299,24 +322,16 @@ static int __kprobes is_IF_modifier(kprobe_opcode_t *insn) * If not, return null. * Only applicable to 64-bit x86. */ -static int __kprobes __copy_instruction(u8 *dest, u8 *src, int recover) +int __kprobes __copy_instruction(u8 *dest, u8 *src) { struct insn insn; - int ret; kprobe_opcode_t buf[MAX_INSN_SIZE]; - kernel_insn_init(&insn, src); - if (recover) { - insn_get_opcode(&insn); - if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) { - ret = recover_probed_instruction(buf, - (unsigned long)src); - if (ret) - return 0; - kernel_insn_init(&insn, buf); - } - } + kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, (unsigned long)src)); insn_get_length(&insn); + /* Another subsystem puts a breakpoint, failed to recover */ + if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) + return 0; memcpy(dest, insn.kaddr, insn.length); #ifdef CONFIG_X86_64 @@ -337,8 +352,7 @@ static int __kprobes __copy_instruction(u8 *dest, u8 *src, int recover) * extension of the original signed 32-bit displacement would * have given. */ - newdisp = (u8 *) src + (s64) insn.displacement.value - - (u8 *) dest; + newdisp = (u8 *) src + (s64) insn.displacement.value - (u8 *) dest; BUG_ON((s64) (s32) newdisp != newdisp); /* Sanity check. */ disp = (u8 *) dest + insn_offset_displacement(&insn); *(s32 *) disp = (s32) newdisp; @@ -349,18 +363,20 @@ static int __kprobes __copy_instruction(u8 *dest, u8 *src, int recover) static void __kprobes arch_copy_kprobe(struct kprobe *p) { + /* Copy an instruction with recovering if other optprobe modifies it.*/ + __copy_instruction(p->ainsn.insn, p->addr); + /* - * Copy an instruction without recovering int3, because it will be - * put by another subsystem. + * __copy_instruction can modify the displacement of the instruction, + * but it doesn't affect boostable check. */ - __copy_instruction(p->ainsn.insn, p->addr, 0); - - if (can_boost(p->addr)) + if (can_boost(p->ainsn.insn)) p->ainsn.boostable = 0; else p->ainsn.boostable = -1; - p->opcode = *p->addr; + /* Also, displacement change doesn't affect the first byte */ + p->opcode = p->ainsn.insn[0]; } int __kprobes arch_prepare_kprobe(struct kprobe *p) @@ -442,8 +458,8 @@ static void __kprobes restore_btf(void) } } -void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, - struct pt_regs *regs) +void __kprobes +arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) { unsigned long *sara = stack_addr(regs); @@ -453,16 +469,8 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, *sara = (unsigned long) &kretprobe_trampoline; } -#ifdef CONFIG_OPTPROBES -static int __kprobes setup_detour_execution(struct kprobe *p, - struct pt_regs *regs, - int reenter); -#else -#define setup_detour_execution(p, regs, reenter) (0) -#endif - -static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb, int reenter) +static void __kprobes +setup_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb, int reenter) { if (setup_detour_execution(p, regs, reenter)) return; @@ -504,8 +512,8 @@ static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs, * within the handler. We save the original kprobes variables and just single * step on the instruction of the new probe without calling any user handlers. */ -static int __kprobes reenter_kprobe(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) +static int __kprobes +reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) { switch (kcb->kprobe_status) { case KPROBE_HIT_SSDONE: @@ -600,69 +608,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) return 0; } -#ifdef CONFIG_X86_64 -#define SAVE_REGS_STRING \ - /* Skip cs, ip, orig_ax. */ \ - " subq $24, %rsp\n" \ - " pushq %rdi\n" \ - " pushq %rsi\n" \ - " pushq %rdx\n" \ - " pushq %rcx\n" \ - " pushq %rax\n" \ - " pushq %r8\n" \ - " pushq %r9\n" \ - " pushq %r10\n" \ - " pushq %r11\n" \ - " pushq %rbx\n" \ - " pushq %rbp\n" \ - " pushq %r12\n" \ - " pushq %r13\n" \ - " pushq %r14\n" \ - " pushq %r15\n" -#define RESTORE_REGS_STRING \ - " popq %r15\n" \ - " popq %r14\n" \ - " popq %r13\n" \ - " popq %r12\n" \ - " popq %rbp\n" \ - " popq %rbx\n" \ - " popq %r11\n" \ - " popq %r10\n" \ - " popq %r9\n" \ - " popq %r8\n" \ - " popq %rax\n" \ - " popq %rcx\n" \ - " popq %rdx\n" \ - " popq %rsi\n" \ - " popq %rdi\n" \ - /* Skip orig_ax, ip, cs */ \ - " addq $24, %rsp\n" -#else -#define SAVE_REGS_STRING \ - /* Skip cs, ip, orig_ax and gs. */ \ - " subl $16, %esp\n" \ - " pushl %fs\n" \ - " pushl %es\n" \ - " pushl %ds\n" \ - " pushl %eax\n" \ - " pushl %ebp\n" \ - " pushl %edi\n" \ - " pushl %esi\n" \ - " pushl %edx\n" \ - " pushl %ecx\n" \ - " pushl %ebx\n" -#define RESTORE_REGS_STRING \ - " popl %ebx\n" \ - " popl %ecx\n" \ - " popl %edx\n" \ - " popl %esi\n" \ - " popl %edi\n" \ - " popl %ebp\n" \ - " popl %eax\n" \ - /* Skip ds, es, fs, gs, orig_ax, and ip. Note: don't pop cs here*/\ - " addl $24, %esp\n" -#endif - /* * When a retprobed function returns, this code saves registers and * calls trampoline_handler() runs, which calls the kretprobe's handler. @@ -816,8 +761,8 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) * jump instruction after the copied instruction, that jumps to the next * instruction after the probepoint. */ -static void __kprobes resume_execution(struct kprobe *p, - struct pt_regs *regs, struct kprobe_ctlblk *kcb) +static void __kprobes +resume_execution(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) { unsigned long *tos = stack_addr(regs); unsigned long copy_ip = (unsigned long)p->ainsn.insn; @@ -996,8 +941,8 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) /* * Wrapper routine for handling exceptions. */ -int __kprobes kprobe_exceptions_notify(struct notifier_block *self, - unsigned long val, void *data) +int __kprobes +kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data) { struct die_args *args = data; int ret = NOTIFY_DONE; @@ -1107,466 +1052,9 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) return 0; } - -#ifdef CONFIG_OPTPROBES - -/* Insert a call instruction at address 'from', which calls address 'to'.*/ -static void __kprobes synthesize_relcall(void *from, void *to) -{ - __synthesize_relative_insn(from, to, RELATIVECALL_OPCODE); -} - -/* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */ -static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr, - unsigned long val) -{ -#ifdef CONFIG_X86_64 - *addr++ = 0x48; - *addr++ = 0xbf; -#else - *addr++ = 0xb8; -#endif - *(unsigned long *)addr = val; -} - -static void __used __kprobes kprobes_optinsn_template_holder(void) -{ - asm volatile ( - ".global optprobe_template_entry\n" - "optprobe_template_entry: \n" -#ifdef CONFIG_X86_64 - /* We don't bother saving the ss register */ - " pushq %rsp\n" - " pushfq\n" - SAVE_REGS_STRING - " movq %rsp, %rsi\n" - ".global optprobe_template_val\n" - "optprobe_template_val: \n" - ASM_NOP5 - ASM_NOP5 - ".global optprobe_template_call\n" - "optprobe_template_call: \n" - ASM_NOP5 - /* Move flags to rsp */ - " movq 144(%rsp), %rdx\n" - " movq %rdx, 152(%rsp)\n" - RESTORE_REGS_STRING - /* Skip flags entry */ - " addq $8, %rsp\n" - " popfq\n" -#else /* CONFIG_X86_32 */ - " pushf\n" - SAVE_REGS_STRING - " movl %esp, %edx\n" - ".global optprobe_template_val\n" - "optprobe_template_val: \n" - ASM_NOP5 - ".global optprobe_template_call\n" - "optprobe_template_call: \n" - ASM_NOP5 - RESTORE_REGS_STRING - " addl $4, %esp\n" /* skip cs */ - " popf\n" -#endif - ".global optprobe_template_end\n" - "optprobe_template_end: \n"); -} - -#define TMPL_MOVE_IDX \ - ((long)&optprobe_template_val - (long)&optprobe_template_entry) -#define TMPL_CALL_IDX \ - ((long)&optprobe_template_call - (long)&optprobe_template_entry) -#define TMPL_END_IDX \ - ((long)&optprobe_template_end - (long)&optprobe_template_entry) - -#define INT3_SIZE sizeof(kprobe_opcode_t) - -/* Optimized kprobe call back function: called from optinsn */ -static void __kprobes optimized_callback(struct optimized_kprobe *op, - struct pt_regs *regs) -{ - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long flags; - - /* This is possible if op is under delayed unoptimizing */ - if (kprobe_disabled(&op->kp)) - return; - - local_irq_save(flags); - if (kprobe_running()) { - kprobes_inc_nmissed_count(&op->kp); - } else { - /* Save skipped registers */ -#ifdef CONFIG_X86_64 - regs->cs = __KERNEL_CS; -#else - regs->cs = __KERNEL_CS | get_kernel_rpl(); - regs->gs = 0; -#endif - regs->ip = (unsigned long)op->kp.addr + INT3_SIZE; - regs->orig_ax = ~0UL; - - __this_cpu_write(current_kprobe, &op->kp); - kcb->kprobe_status = KPROBE_HIT_ACTIVE; - opt_pre_handler(&op->kp, regs); - __this_cpu_write(current_kprobe, NULL); - } - local_irq_restore(flags); -} - -static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src) -{ - int len = 0, ret; - - while (len < RELATIVEJUMP_SIZE) { - ret = __copy_instruction(dest + len, src + len, 1); - if (!ret || !can_boost(dest + len)) - return -EINVAL; - len += ret; - } - /* Check whether the address range is reserved */ - if (ftrace_text_reserved(src, src + len - 1) || - alternatives_text_reserved(src, src + len - 1) || - jump_label_text_reserved(src, src + len - 1)) - return -EBUSY; - - return len; -} - -/* Check whether insn is indirect jump */ -static int __kprobes insn_is_indirect_jump(struct insn *insn) -{ - return ((insn->opcode.bytes[0] == 0xff && - (X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */ - insn->opcode.bytes[0] == 0xea); /* Segment based jump */ -} - -/* Check whether insn jumps into specified address range */ -static int insn_jump_into_range(struct insn *insn, unsigned long start, int len) -{ - unsigned long target = 0; - - switch (insn->opcode.bytes[0]) { - case 0xe0: /* loopne */ - case 0xe1: /* loope */ - case 0xe2: /* loop */ - case 0xe3: /* jcxz */ - case 0xe9: /* near relative jump */ - case 0xeb: /* short relative jump */ - break; - case 0x0f: - if ((insn->opcode.bytes[1] & 0xf0) == 0x80) /* jcc near */ - break; - return 0; - default: - if ((insn->opcode.bytes[0] & 0xf0) == 0x70) /* jcc short */ - break; - return 0; - } - target = (unsigned long)insn->next_byte + insn->immediate.value; - - return (start <= target && target <= start + len); -} - -/* Decode whole function to ensure any instructions don't jump into target */ -static int __kprobes can_optimize(unsigned long paddr) -{ - int ret; - unsigned long addr, size = 0, offset = 0; - struct insn insn; - kprobe_opcode_t buf[MAX_INSN_SIZE]; - - /* Lookup symbol including addr */ - if (!kallsyms_lookup_size_offset(paddr, &size, &offset)) - return 0; - - /* - * Do not optimize in the entry code due to the unstable - * stack handling. - */ - if ((paddr >= (unsigned long )__entry_text_start) && - (paddr < (unsigned long )__entry_text_end)) - return 0; - - /* Check there is enough space for a relative jump. */ - if (size - offset < RELATIVEJUMP_SIZE) - return 0; - - /* Decode instructions */ - addr = paddr - offset; - while (addr < paddr - offset + size) { /* Decode until function end */ - if (search_exception_tables(addr)) - /* - * Since some fixup code will jumps into this function, - * we can't optimize kprobe in this function. - */ - return 0; - kernel_insn_init(&insn, (void *)addr); - insn_get_opcode(&insn); - if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) { - ret = recover_probed_instruction(buf, addr); - if (ret) - return 0; - kernel_insn_init(&insn, buf); - } - insn_get_length(&insn); - /* Recover address */ - insn.kaddr = (void *)addr; - insn.next_byte = (void *)(addr + insn.length); - /* Check any instructions don't jump into target */ - if (insn_is_indirect_jump(&insn) || - insn_jump_into_range(&insn, paddr + INT3_SIZE, - RELATIVE_ADDR_SIZE)) - return 0; - addr += insn.length; - } - - return 1; -} - -/* Check optimized_kprobe can actually be optimized. */ -int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op) -{ - int i; - struct kprobe *p; - - for (i = 1; i < op->optinsn.size; i++) { - p = get_kprobe(op->kp.addr + i); - if (p && !kprobe_disabled(p)) - return -EEXIST; - } - - return 0; -} - -/* Check the addr is within the optimized instructions. */ -int __kprobes arch_within_optimized_kprobe(struct optimized_kprobe *op, - unsigned long addr) -{ - return ((unsigned long)op->kp.addr <= addr && - (unsigned long)op->kp.addr + op->optinsn.size > addr); -} - -/* Free optimized instruction slot */ -static __kprobes -void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty) -{ - if (op->optinsn.insn) { - free_optinsn_slot(op->optinsn.insn, dirty); - op->optinsn.insn = NULL; - op->optinsn.size = 0; - } -} - -void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op) -{ - __arch_remove_optimized_kprobe(op, 1); -} - -/* - * Copy replacing target instructions - * Target instructions MUST be relocatable (checked inside) - */ -int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op) -{ - u8 *buf; - int ret; - long rel; - - if (!can_optimize((unsigned long)op->kp.addr)) - return -EILSEQ; - - op->optinsn.insn = get_optinsn_slot(); - if (!op->optinsn.insn) - return -ENOMEM; - - /* - * Verify if the address gap is in 2GB range, because this uses - * a relative jump. - */ - rel = (long)op->optinsn.insn - (long)op->kp.addr + RELATIVEJUMP_SIZE; - if (abs(rel) > 0x7fffffff) - return -ERANGE; - - buf = (u8 *)op->optinsn.insn; - - /* Copy instructions into the out-of-line buffer */ - ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr); - if (ret < 0) { - __arch_remove_optimized_kprobe(op, 0); - return ret; - } - op->optinsn.size = ret; - - /* Copy arch-dep-instance from template */ - memcpy(buf, &optprobe_template_entry, TMPL_END_IDX); - - /* Set probe information */ - synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op); - - /* Set probe function call */ - synthesize_relcall(buf + TMPL_CALL_IDX, optimized_callback); - - /* Set returning jmp instruction at the tail of out-of-line buffer */ - synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size, - (u8 *)op->kp.addr + op->optinsn.size); - - flush_icache_range((unsigned long) buf, - (unsigned long) buf + TMPL_END_IDX + - op->optinsn.size + RELATIVEJUMP_SIZE); - return 0; -} - -#define MAX_OPTIMIZE_PROBES 256 -static struct text_poke_param *jump_poke_params; -static struct jump_poke_buffer { - u8 buf[RELATIVEJUMP_SIZE]; -} *jump_poke_bufs; - -static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm, - u8 *insn_buf, - struct optimized_kprobe *op) -{ - s32 rel = (s32)((long)op->optinsn.insn - - ((long)op->kp.addr + RELATIVEJUMP_SIZE)); - - /* Backup instructions which will be replaced by jump address */ - memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE, - RELATIVE_ADDR_SIZE); - - insn_buf[0] = RELATIVEJUMP_OPCODE; - *(s32 *)(&insn_buf[1]) = rel; - - tprm->addr = op->kp.addr; - tprm->opcode = insn_buf; - tprm->len = RELATIVEJUMP_SIZE; -} - -/* - * Replace breakpoints (int3) with relative jumps. - * Caller must call with locking kprobe_mutex and text_mutex. - */ -void __kprobes arch_optimize_kprobes(struct list_head *oplist) -{ - struct optimized_kprobe *op, *tmp; - int c = 0; - - list_for_each_entry_safe(op, tmp, oplist, list) { - WARN_ON(kprobe_disabled(&op->kp)); - /* Setup param */ - setup_optimize_kprobe(&jump_poke_params[c], - jump_poke_bufs[c].buf, op); - list_del_init(&op->list); - if (++c >= MAX_OPTIMIZE_PROBES) - break; - } - - /* - * text_poke_smp doesn't support NMI/MCE code modifying. - * However, since kprobes itself also doesn't support NMI/MCE - * code probing, it's not a problem. - */ - text_poke_smp_batch(jump_poke_params, c); -} - -static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm, - u8 *insn_buf, - struct optimized_kprobe *op) -{ - /* Set int3 to first byte for kprobes */ - insn_buf[0] = BREAKPOINT_INSTRUCTION; - memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); - - tprm->addr = op->kp.addr; - tprm->opcode = insn_buf; - tprm->len = RELATIVEJUMP_SIZE; -} - -/* - * Recover original instructions and breakpoints from relative jumps. - * Caller must call with locking kprobe_mutex. - */ -extern void arch_unoptimize_kprobes(struct list_head *oplist, - struct list_head *done_list) -{ - struct optimized_kprobe *op, *tmp; - int c = 0; - - list_for_each_entry_safe(op, tmp, oplist, list) { - /* Setup param */ - setup_unoptimize_kprobe(&jump_poke_params[c], - jump_poke_bufs[c].buf, op); - list_move(&op->list, done_list); - if (++c >= MAX_OPTIMIZE_PROBES) - break; - } - - /* - * text_poke_smp doesn't support NMI/MCE code modifying. - * However, since kprobes itself also doesn't support NMI/MCE - * code probing, it's not a problem. - */ - text_poke_smp_batch(jump_poke_params, c); -} - -/* Replace a relative jump with a breakpoint (int3). */ -void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op) -{ - u8 buf[RELATIVEJUMP_SIZE]; - - /* Set int3 to first byte for kprobes */ - buf[0] = BREAKPOINT_INSTRUCTION; - memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); - text_poke_smp(op->kp.addr, buf, RELATIVEJUMP_SIZE); -} - -static int __kprobes setup_detour_execution(struct kprobe *p, - struct pt_regs *regs, - int reenter) -{ - struct optimized_kprobe *op; - - if (p->flags & KPROBE_FLAG_OPTIMIZED) { - /* This kprobe is really able to run optimized path. */ - op = container_of(p, struct optimized_kprobe, kp); - /* Detour through copied instructions */ - regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX; - if (!reenter) - reset_current_kprobe(); - preempt_enable_no_resched(); - return 1; - } - return 0; -} - -static int __kprobes init_poke_params(void) -{ - /* Allocate code buffer and parameter array */ - jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) * - MAX_OPTIMIZE_PROBES, GFP_KERNEL); - if (!jump_poke_bufs) - return -ENOMEM; - - jump_poke_params = kmalloc(sizeof(struct text_poke_param) * - MAX_OPTIMIZE_PROBES, GFP_KERNEL); - if (!jump_poke_params) { - kfree(jump_poke_bufs); - jump_poke_bufs = NULL; - return -ENOMEM; - } - - return 0; -} -#else /* !CONFIG_OPTPROBES */ -static int __kprobes init_poke_params(void) -{ - return 0; -} -#endif - int __init arch_init_kprobes(void) { - return init_poke_params(); + return arch_init_optprobes(); } int __kprobes arch_trampoline_kprobe(struct kprobe *p) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index f0c6fd6f176..b8ba6e4a27e 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -38,6 +38,7 @@ #include <asm/traps.h> #include <asm/desc.h> #include <asm/tlbflush.h> +#include <asm/idle.h> static int kvmapf = 1; @@ -253,7 +254,10 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code) kvm_async_pf_task_wait((u32)read_cr2()); break; case KVM_PV_REASON_PAGE_READY: + rcu_irq_enter(); + exit_idle(); kvm_async_pf_task_wake((u32)read_cr2()); + rcu_irq_exit(); break; } } @@ -438,9 +442,9 @@ void __init kvm_guest_init(void) static __init int activate_jump_labels(void) { if (has_steal_clock) { - jump_label_inc(¶virt_steal_enabled); + static_key_slow_inc(¶virt_steal_enabled); if (steal_acc) - jump_label_inc(¶virt_steal_rq_enabled); + static_key_slow_inc(¶virt_steal_rq_enabled); } return 0; diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 44842d756b2..f8492da65bf 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -136,6 +136,15 @@ int kvm_register_clock(char *txt) return ret; } +static void kvm_save_sched_clock_state(void) +{ +} + +static void kvm_restore_sched_clock_state(void) +{ + kvm_register_clock("primary cpu clock, resume"); +} + #ifdef CONFIG_X86_LOCAL_APIC static void __cpuinit kvm_setup_secondary_clock(void) { @@ -144,8 +153,6 @@ static void __cpuinit kvm_setup_secondary_clock(void) * we shouldn't fail. */ WARN_ON(kvm_register_clock("secondary cpu clock")); - /* ok, done with our trickery, call native */ - setup_secondary_APIC_clock(); } #endif @@ -194,9 +201,11 @@ void __init kvmclock_init(void) x86_platform.get_wallclock = kvm_get_wallclock; x86_platform.set_wallclock = kvm_set_wallclock; #ifdef CONFIG_X86_LOCAL_APIC - x86_cpuinit.setup_percpu_clockev = + x86_cpuinit.early_percpu_clock_init = kvm_setup_secondary_clock; #endif + 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 machine_ops.crash_shutdown = kvm_crash_shutdown; diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index ea697263b37..ebc98739892 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -15,7 +15,6 @@ #include <linux/vmalloc.h> #include <linux/uaccess.h> -#include <asm/system.h> #include <asm/ldt.h> #include <asm/desc.h> #include <asm/mmu_context.h> diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index a3fa43ba5d3..5b19e4d78b0 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -23,7 +23,6 @@ #include <asm/apic.h> #include <asm/cpufeature.h> #include <asm/desc.h> -#include <asm/system.h> #include <asm/cacheflush.h> #include <asm/debugreg.h> diff --git a/arch/x86/kernel/mca_32.c b/arch/x86/kernel/mca_32.c index 177183cbb6a..7eb1e2b9782 100644 --- a/arch/x86/kernel/mca_32.c +++ b/arch/x86/kernel/mca_32.c @@ -43,7 +43,6 @@ #include <linux/mca.h> #include <linux/kprobes.h> #include <linux/slab.h> -#include <asm/system.h> #include <asm/io.h> #include <linux/proc_fs.h> #include <linux/mman.h> diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index fe86493f3ed..73465aab28f 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -311,13 +311,33 @@ out: return state; } +/* + * AMD microcode firmware naming convention, up to family 15h they are in + * the legacy file: + * + * amd-ucode/microcode_amd.bin + * + * This legacy file is always smaller than 2K in size. + * + * Starting at family 15h they are in family specific firmware files: + * + * amd-ucode/microcode_amd_fam15h.bin + * amd-ucode/microcode_amd_fam16h.bin + * ... + * + * These might be larger than 2K. + */ static enum ucode_state request_microcode_amd(int cpu, struct device *device) { - const char *fw_name = "amd-ucode/microcode_amd.bin"; + char fw_name[36] = "amd-ucode/microcode_amd.bin"; const struct firmware *fw; enum ucode_state ret = UCODE_NFOUND; + struct cpuinfo_x86 *c = &cpu_data(cpu); + + if (c->x86 >= 0x15) + snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86); - if (request_firmware(&fw, fw_name, device)) { + if (request_firmware(&fw, (const char *)fw_name, device)) { pr_err("failed to load file %s\n", fw_name); goto out; } @@ -340,7 +360,6 @@ out: static enum ucode_state request_microcode_user(int cpu, const void __user *buf, size_t size) { - pr_info("AMD microcode update via /dev/cpu/microcode not supported\n"); return UCODE_ERROR; } diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index fda91c30710..87a0f868830 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -86,6 +86,7 @@ #include <asm/microcode.h> #include <asm/processor.h> +#include <asm/cpu_device_id.h> MODULE_DESCRIPTION("Microcode Update Driver"); MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>"); @@ -504,6 +505,20 @@ static struct notifier_block __refdata mc_cpu_notifier = { .notifier_call = mc_cpu_callback, }; +#ifdef MODULE +/* Autoload on Intel and AMD systems */ +static const struct x86_cpu_id 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 int __init microcode_init(void) { struct cpuinfo_x86 *c = &cpu_data(0); diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 925179f871d..f21fd94ac89 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -26,7 +26,6 @@ #include <linux/gfp.h> #include <linux/jump_label.h> -#include <asm/system.h> #include <asm/page.h> #include <asm/pgtable.h> diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 96356762a51..eb113693f04 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -40,7 +40,6 @@ #include <asm/processor.h> #include <asm/msr.h> -#include <asm/system.h> static struct class *msr_class; diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index e88f37b58dd..47acaf31916 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -405,9 +405,108 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs) unknown_nmi_error(reason, regs); } +/* + * NMIs can hit breakpoints which will cause it to lose its + * NMI context with the CPU when the breakpoint does an iret. + */ +#ifdef CONFIG_X86_32 +/* + * For i386, NMIs use the same stack as the kernel, and we can + * add a workaround to the iret problem in C. Simply have 3 states + * the NMI can be in. + * + * 1) not running + * 2) executing + * 3) latched + * + * When no NMI is in progress, it is in the "not running" state. + * When an NMI comes in, it goes into the "executing" state. + * Normally, if another NMI is triggered, it does not interrupt + * the running NMI and the HW will simply latch it so that when + * the first NMI finishes, it will restart the second NMI. + * (Note, the latch is binary, thus multiple NMIs triggering, + * when one is running, are ignored. Only one NMI is restarted.) + * + * If an NMI hits a breakpoint that executes an iret, another + * NMI can preempt it. We do not want to allow this new NMI + * to run, but we want to execute it when the first one finishes. + * We set the state to "latched", and the first NMI will perform + * an cmpxchg on the state, and if it doesn't successfully + * reset the state to "not running" it will restart the next + * NMI. + */ +enum nmi_states { + NMI_NOT_RUNNING, + NMI_EXECUTING, + NMI_LATCHED, +}; +static DEFINE_PER_CPU(enum nmi_states, nmi_state); + +#define nmi_nesting_preprocess(regs) \ + do { \ + if (__get_cpu_var(nmi_state) != NMI_NOT_RUNNING) { \ + __get_cpu_var(nmi_state) = NMI_LATCHED; \ + return; \ + } \ + nmi_restart: \ + __get_cpu_var(nmi_state) = NMI_EXECUTING; \ + } while (0) + +#define nmi_nesting_postprocess() \ + do { \ + if (cmpxchg(&__get_cpu_var(nmi_state), \ + NMI_EXECUTING, NMI_NOT_RUNNING) != NMI_EXECUTING) \ + goto nmi_restart; \ + } while (0) +#else /* x86_64 */ +/* + * In x86_64 things are a bit more difficult. This has the same problem + * where an NMI hitting a breakpoint that calls iret will remove the + * NMI context, allowing a nested NMI to enter. What makes this more + * difficult is that both NMIs and breakpoints have their own stack. + * When a new NMI or breakpoint is executed, the stack is set to a fixed + * point. If an NMI is nested, it will have its stack set at that same + * fixed address that the first NMI had, and will start corrupting the + * stack. This is handled in entry_64.S, but the same problem exists with + * the breakpoint stack. + * + * If a breakpoint is being processed, and the debug stack is being used, + * if an NMI comes in and also hits a breakpoint, the stack pointer + * will be set to the same fixed address as the breakpoint that was + * interrupted, causing that stack to be corrupted. To handle this case, + * check if the stack that was interrupted is the debug stack, and if + * so, change the IDT so that new breakpoints will use the current stack + * and not switch to the fixed address. On return of the NMI, switch back + * to the original IDT. + */ +static DEFINE_PER_CPU(int, update_debug_stack); + +static inline void nmi_nesting_preprocess(struct pt_regs *regs) +{ + /* + * If we interrupted a breakpoint, it is possible that + * the nmi handler will have breakpoints too. We need to + * change the IDT such that breakpoints that happen here + * continue to use the NMI stack. + */ + if (unlikely(is_debug_stack(regs->sp))) { + debug_stack_set_zero(); + __get_cpu_var(update_debug_stack) = 1; + } +} + +static inline void nmi_nesting_postprocess(void) +{ + if (unlikely(__get_cpu_var(update_debug_stack))) + debug_stack_reset(); +} +#endif + dotraplinkage notrace __kprobes void do_nmi(struct pt_regs *regs, long error_code) { + nmi_nesting_preprocess(regs); + nmi_enter(); inc_irq_stat(__nmi_count); @@ -416,6 +515,9 @@ do_nmi(struct pt_regs *regs, long error_code) default_do_nmi(regs); nmi_exit(); + + /* On i386, may loop back to preprocess */ + nmi_nesting_postprocess(); } void stop_nmi(void) diff --git a/arch/x86/kernel/nmi_selftest.c b/arch/x86/kernel/nmi_selftest.c new file mode 100644 index 00000000000..2c39dcd510f --- /dev/null +++ b/arch/x86/kernel/nmi_selftest.c @@ -0,0 +1,181 @@ +/* + * arch/x86/kernel/nmi-selftest.c + * + * Testsuite for NMI: IPIs + * + * Started by Don Zickus: + * (using lib/locking-selftest.c as a guide) + * + * Copyright (C) 2011 Red Hat, Inc., Don Zickus <dzickus@redhat.com> + */ + +#include <linux/smp.h> +#include <linux/cpumask.h> +#include <linux/delay.h> +#include <linux/init.h> + +#include <asm/apic.h> +#include <asm/nmi.h> + +#define SUCCESS 0 +#define FAILURE 1 +#define TIMEOUT 2 + +static int __initdata nmi_fail; + +/* check to see if NMI IPIs work on this machine */ +static DECLARE_BITMAP(nmi_ipi_mask, NR_CPUS) __initdata; + +static int __initdata testcase_total; +static int __initdata testcase_successes; +static int __initdata expected_testcase_failures; +static int __initdata unexpected_testcase_failures; +static int __initdata unexpected_testcase_unknowns; + +static int __init nmi_unk_cb(unsigned int val, struct pt_regs *regs) +{ + unexpected_testcase_unknowns++; + return NMI_HANDLED; +} + +static void __init init_nmi_testsuite(void) +{ + /* trap all the unknown NMIs we may generate */ + register_nmi_handler(NMI_UNKNOWN, nmi_unk_cb, 0, "nmi_selftest_unk"); +} + +static void __init cleanup_nmi_testsuite(void) +{ + unregister_nmi_handler(NMI_UNKNOWN, "nmi_selftest_unk"); +} + +static int __init test_nmi_ipi_callback(unsigned int val, struct pt_regs *regs) +{ + int cpu = raw_smp_processor_id(); + + if (cpumask_test_and_clear_cpu(cpu, to_cpumask(nmi_ipi_mask))) + return NMI_HANDLED; + + return NMI_DONE; +} + +static void __init test_nmi_ipi(struct cpumask *mask) +{ + unsigned long timeout; + + if (register_nmi_handler(NMI_LOCAL, test_nmi_ipi_callback, + NMI_FLAG_FIRST, "nmi_selftest")) { + nmi_fail = FAILURE; + return; + } + + /* sync above data before sending NMI */ + wmb(); + + apic->send_IPI_mask(mask, NMI_VECTOR); + + /* Don't wait longer than a second */ + timeout = USEC_PER_SEC; + while (!cpumask_empty(mask) && timeout--) + udelay(1); + + /* What happens if we timeout, do we still unregister?? */ + unregister_nmi_handler(NMI_LOCAL, "nmi_selftest"); + + if (!timeout) + nmi_fail = TIMEOUT; + return; +} + +static void __init remote_ipi(void) +{ + cpumask_copy(to_cpumask(nmi_ipi_mask), cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), to_cpumask(nmi_ipi_mask)); + if (!cpumask_empty(to_cpumask(nmi_ipi_mask))) + test_nmi_ipi(to_cpumask(nmi_ipi_mask)); +} + +static void __init local_ipi(void) +{ + cpumask_clear(to_cpumask(nmi_ipi_mask)); + cpumask_set_cpu(smp_processor_id(), to_cpumask(nmi_ipi_mask)); + test_nmi_ipi(to_cpumask(nmi_ipi_mask)); +} + +static void __init reset_nmi(void) +{ + nmi_fail = 0; +} + +static void __init dotest(void (*testcase_fn)(void), int expected) +{ + testcase_fn(); + /* + * Filter out expected failures: + */ + if (nmi_fail != expected) { + unexpected_testcase_failures++; + + if (nmi_fail == FAILURE) + printk("FAILED |"); + else if (nmi_fail == TIMEOUT) + printk("TIMEOUT|"); + else + printk("ERROR |"); + dump_stack(); + } else { + testcase_successes++; + printk(" ok |"); + } + testcase_total++; + + reset_nmi(); +} + +static inline void __init print_testname(const char *testname) +{ + printk("%12s:", testname); +} + +void __init nmi_selftest(void) +{ + init_nmi_testsuite(); + + /* + * Run the testsuite: + */ + printk("----------------\n"); + printk("| NMI testsuite:\n"); + printk("--------------------\n"); + + print_testname("remote IPI"); + dotest(remote_ipi, SUCCESS); + printk("\n"); + print_testname("local IPI"); + dotest(local_ipi, SUCCESS); + printk("\n"); + + cleanup_nmi_testsuite(); + + if (unexpected_testcase_failures) { + printk("--------------------\n"); + printk("BUG: %3d unexpected failures (out of %3d) - debugging disabled! |\n", + unexpected_testcase_failures, testcase_total); + printk("-----------------------------------------------------------------\n"); + } else if (expected_testcase_failures && testcase_successes) { + printk("--------------------\n"); + printk("%3d out of %3d testcases failed, as expected. |\n", + expected_testcase_failures, testcase_total); + printk("----------------------------------------------------\n"); + } else if (expected_testcase_failures && !testcase_successes) { + printk("--------------------\n"); + printk("All %3d testcases failed, as expected. |\n", + expected_testcase_failures); + printk("----------------------------------------\n"); + } else { + printk("--------------------\n"); + printk("Good, all %3d testcases passed! |\n", + testcase_successes); + printk("---------------------------------\n"); + } +} diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index d90272e6bc4..ab137605e69 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -26,6 +26,7 @@ #include <asm/bug.h> #include <asm/paravirt.h> +#include <asm/debugreg.h> #include <asm/desc.h> #include <asm/setup.h> #include <asm/pgtable.h> @@ -37,6 +38,7 @@ #include <asm/apic.h> #include <asm/tlbflush.h> #include <asm/timer.h> +#include <asm/special_insns.h> /* nop stub */ void _paravirt_nop(void) @@ -202,8 +204,8 @@ static void native_flush_tlb_single(unsigned long addr) __native_flush_tlb_single(addr); } -struct jump_label_key paravirt_steal_enabled; -struct jump_label_key paravirt_steal_rq_enabled; +struct static_key paravirt_steal_enabled; +struct static_key paravirt_steal_rq_enabled; static u64 native_steal_clock(int cpu) { diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 726494b5834..d0b2fb9ccbb 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -42,7 +42,6 @@ #include <asm/calgary.h> #include <asm/tce.h> #include <asm/pci-direct.h> -#include <asm/system.h> #include <asm/dma.h> #include <asm/rio.h> #include <asm/bios_ebda.h> @@ -431,7 +430,7 @@ static void calgary_unmap_page(struct device *dev, dma_addr_t dma_addr, } static void* calgary_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag) + dma_addr_t *dma_handle, gfp_t flag, struct dma_attrs *attrs) { void *ret = NULL; dma_addr_t mapping; @@ -464,7 +463,8 @@ error: } static void calgary_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle) + void *vaddr, dma_addr_t dma_handle, + struct dma_attrs *attrs) { unsigned int npages; struct iommu_table *tbl = find_iommu_table(dev); @@ -477,8 +477,8 @@ static void calgary_free_coherent(struct device *dev, size_t size, } static struct dma_map_ops calgary_dma_ops = { - .alloc_coherent = calgary_alloc_coherent, - .free_coherent = calgary_free_coherent, + .alloc = calgary_alloc_coherent, + .free = calgary_free_coherent, .map_sg = calgary_map_sg, .unmap_sg = calgary_unmap_sg, .map_page = calgary_map_page, diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 1c4d769e21e..3003250ac51 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -96,7 +96,8 @@ void __init pci_iommu_alloc(void) } } void *dma_generic_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_addr, gfp_t flag) + dma_addr_t *dma_addr, gfp_t flag, + struct dma_attrs *attrs) { unsigned long dma_mask; struct page *page; @@ -262,10 +263,11 @@ rootfs_initcall(pci_iommu_init); static __devinit void via_no_dac(struct pci_dev *dev) { - if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && forbid_dac == 0) { + if (forbid_dac == 0) { dev_info(&dev->dev, "disabling DAC on VIA PCI bridge\n"); forbid_dac = 1; } } -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID, via_no_dac); +DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID, + PCI_CLASS_BRIDGE_PCI, 8, via_no_dac); #endif diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c index 3af4af810c0..f96050685b4 100644 --- a/arch/x86/kernel/pci-nommu.c +++ b/arch/x86/kernel/pci-nommu.c @@ -75,7 +75,7 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg, } static void nommu_free_coherent(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_addr) + dma_addr_t dma_addr, struct dma_attrs *attrs) { free_pages((unsigned long)vaddr, get_order(size)); } @@ -96,8 +96,8 @@ static void nommu_sync_sg_for_device(struct device *dev, } struct dma_map_ops nommu_dma_ops = { - .alloc_coherent = dma_generic_alloc_coherent, - .free_coherent = nommu_free_coherent, + .alloc = dma_generic_alloc_coherent, + .free = nommu_free_coherent, .map_sg = nommu_map_sg, .map_page = nommu_map_page, .sync_single_for_device = nommu_sync_single_for_device, diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 8f972cbddef..6c483ba98b9 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -15,21 +15,30 @@ int swiotlb __read_mostly; static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, - dma_addr_t *dma_handle, gfp_t flags) + dma_addr_t *dma_handle, gfp_t flags, + struct dma_attrs *attrs) { void *vaddr; - vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags); + vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags, + attrs); if (vaddr) return vaddr; return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags); } +static void x86_swiotlb_free_coherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_addr, + struct dma_attrs *attrs) +{ + swiotlb_free_coherent(dev, size, vaddr, dma_addr); +} + static struct dma_map_ops swiotlb_dma_ops = { .mapping_error = swiotlb_dma_mapping_error, - .alloc_coherent = x86_swiotlb_alloc_coherent, - .free_coherent = swiotlb_free_coherent, + .alloc = x86_swiotlb_alloc_coherent, + .free = x86_swiotlb_free_coherent, .sync_single_for_cpu = swiotlb_sync_single_for_cpu, .sync_single_for_device = swiotlb_sync_single_for_device, .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c index 34e06e84ce3..0bc72e2069e 100644 --- a/arch/x86/kernel/probe_roms.c +++ b/arch/x86/kernel/probe_roms.c @@ -12,6 +12,7 @@ #include <linux/pci.h> #include <linux/export.h> +#include <asm/probe_roms.h> #include <asm/pci-direct.h> #include <asm/e820.h> #include <asm/mmzone.h> diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 15763af7bfe..1d92a5ab6e8 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -12,16 +12,37 @@ #include <linux/user-return-notifier.h> #include <linux/dmi.h> #include <linux/utsname.h> +#include <linux/stackprotector.h> +#include <linux/tick.h> +#include <linux/cpuidle.h> #include <trace/events/power.h> #include <linux/hw_breakpoint.h> #include <asm/cpu.h> -#include <asm/system.h> #include <asm/apic.h> #include <asm/syscalls.h> #include <asm/idle.h> #include <asm/uaccess.h> #include <asm/i387.h> +#include <asm/fpu-internal.h> #include <asm/debugreg.h> +#include <asm/nmi.h> + +#ifdef CONFIG_X86_64 +static DEFINE_PER_CPU(unsigned char, is_idle); +static ATOMIC_NOTIFIER_HEAD(idle_notifier); + +void idle_notifier_register(struct notifier_block *n) +{ + atomic_notifier_chain_register(&idle_notifier, n); +} +EXPORT_SYMBOL_GPL(idle_notifier_register); + +void idle_notifier_unregister(struct notifier_block *n) +{ + atomic_notifier_chain_unregister(&idle_notifier, n); +} +EXPORT_SYMBOL_GPL(idle_notifier_unregister); +#endif struct kmem_cache *task_xstate_cachep; EXPORT_SYMBOL_GPL(task_xstate_cachep); @@ -341,44 +362,113 @@ void (*pm_idle)(void); EXPORT_SYMBOL(pm_idle); #endif -#ifdef CONFIG_X86_32 -/* - * This halt magic was a workaround for ancient floppy DMA - * wreckage. It should be safe to remove. - */ -static int hlt_counter; -void disable_hlt(void) +static inline int hlt_use_halt(void) { - hlt_counter++; + return 1; } -EXPORT_SYMBOL(disable_hlt); -void enable_hlt(void) +#ifndef CONFIG_SMP +static inline void play_dead(void) { - hlt_counter--; + BUG(); } -EXPORT_SYMBOL(enable_hlt); +#endif -static inline int hlt_use_halt(void) +#ifdef CONFIG_X86_64 +void enter_idle(void) { - return (!hlt_counter && boot_cpu_data.hlt_works_ok); + percpu_write(is_idle, 1); + atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL); } -#else -static inline int hlt_use_halt(void) + +static void __exit_idle(void) { - return 1; + if (x86_test_and_clear_bit_percpu(0, is_idle) == 0) + return; + atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL); +} + +/* Called from interrupts to signify idle end */ +void exit_idle(void) +{ + /* idle loop has pid 0 */ + if (current->pid) + return; + __exit_idle(); } #endif /* + * The idle thread. There's no useful work to be + * done, so just try to conserve power and have a + * low exit latency (ie sit in a loop waiting for + * somebody to say that they'd like to reschedule) + */ +void cpu_idle(void) +{ + /* + * If we're the non-boot CPU, nothing set the stack canary up + * for us. CPU0 already has it initialized but no harm in + * doing it again. This is a good place for updating it, as + * we wont ever return from this function (so the invalid + * canaries already on the stack wont ever trigger). + */ + boot_init_stack_canary(); + current_thread_info()->status |= TS_POLLING; + + while (1) { + tick_nohz_idle_enter(); + + while (!need_resched()) { + rmb(); + + if (cpu_is_offline(smp_processor_id())) + play_dead(); + + /* + * Idle routines should keep interrupts disabled + * from here on, until they go to idle. + * Otherwise, idle callbacks can misfire. + */ + local_touch_nmi(); + local_irq_disable(); + + enter_idle(); + + /* Don't trace irqs off for idle */ + stop_critical_timings(); + + /* enter_idle() needs rcu for notifiers */ + rcu_idle_enter(); + + if (cpuidle_idle_call()) + pm_idle(); + + rcu_idle_exit(); + start_critical_timings(); + + /* In many cases the interrupt that ended idle + has already called exit_idle. But some idle + loops can be woken up without interrupt. */ + __exit_idle(); + } + + tick_nohz_idle_exit(); + preempt_enable_no_resched(); + schedule(); + preempt_disable(); + } +} + +/* * We use this if we don't have any better * idle routine.. */ void default_idle(void) { if (hlt_use_halt()) { - trace_power_start(POWER_CSTATE, 1, smp_processor_id()); - trace_cpu_idle(1, smp_processor_id()); + trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id()); + trace_cpu_idle_rcuidle(1, smp_processor_id()); current_thread_info()->status &= ~TS_POLLING; /* * TS_POLLING-cleared state must be visible before we @@ -391,8 +481,8 @@ void default_idle(void) else local_irq_enable(); current_thread_info()->status |= TS_POLLING; - trace_power_end(smp_processor_id()); - trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); + trace_power_end_rcuidle(smp_processor_id()); + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } else { local_irq_enable(); /* loop is done by the caller */ @@ -450,8 +540,8 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait); static void mwait_idle(void) { if (!need_resched()) { - trace_power_start(POWER_CSTATE, 1, smp_processor_id()); - trace_cpu_idle(1, smp_processor_id()); + trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id()); + trace_cpu_idle_rcuidle(1, smp_processor_id()); if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR)) clflush((void *)¤t_thread_info()->flags); @@ -461,8 +551,8 @@ static void mwait_idle(void) __sti_mwait(0, 0); else local_irq_enable(); - trace_power_end(smp_processor_id()); - trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); + trace_power_end_rcuidle(smp_processor_id()); + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } else local_irq_enable(); } @@ -474,13 +564,13 @@ static void mwait_idle(void) */ static void poll_idle(void) { - trace_power_start(POWER_CSTATE, 0, smp_processor_id()); - trace_cpu_idle(0, smp_processor_id()); + trace_power_start_rcuidle(POWER_CSTATE, 0, smp_processor_id()); + trace_cpu_idle_rcuidle(0, smp_processor_id()); local_irq_enable(); while (!need_resched()) cpu_relax(); - trace_power_end(smp_processor_id()); - trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); + trace_power_end_rcuidle(smp_processor_id()); + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } /* diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 485204f58cd..ae6847303e2 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -9,7 +9,6 @@ * This file handles the architecture-dependent parts of process handling.. */ -#include <linux/stackprotector.h> #include <linux/cpu.h> #include <linux/errno.h> #include <linux/sched.h> @@ -31,20 +30,18 @@ #include <linux/kallsyms.h> #include <linux/ptrace.h> #include <linux/personality.h> -#include <linux/tick.h> #include <linux/percpu.h> #include <linux/prctl.h> #include <linux/ftrace.h> #include <linux/uaccess.h> #include <linux/io.h> #include <linux/kdebug.h> -#include <linux/cpuidle.h> #include <asm/pgtable.h> -#include <asm/system.h> #include <asm/ldt.h> #include <asm/processor.h> #include <asm/i387.h> +#include <asm/fpu-internal.h> #include <asm/desc.h> #ifdef CONFIG_MATH_EMULATION #include <asm/math_emu.h> @@ -57,7 +54,7 @@ #include <asm/idle.h> #include <asm/syscalls.h> #include <asm/debugreg.h> -#include <asm/nmi.h> +#include <asm/switch_to.h> asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); @@ -69,62 +66,6 @@ unsigned long thread_saved_pc(struct task_struct *tsk) return ((unsigned long *)tsk->thread.sp)[3]; } -#ifndef CONFIG_SMP -static inline void play_dead(void) -{ - BUG(); -} -#endif - -/* - * The idle thread. There's no useful work to be - * done, so just try to conserve power and have a - * low exit latency (ie sit in a loop waiting for - * somebody to say that they'd like to reschedule) - */ -void cpu_idle(void) -{ - int cpu = smp_processor_id(); - - /* - * If we're the non-boot CPU, nothing set the stack canary up - * for us. CPU0 already has it initialized but no harm in - * doing it again. This is a good place for updating it, as - * we wont ever return from this function (so the invalid - * canaries already on the stack wont ever trigger). - */ - boot_init_stack_canary(); - - current_thread_info()->status |= TS_POLLING; - - /* endless idle loop with no priority at all */ - while (1) { - tick_nohz_idle_enter(); - rcu_idle_enter(); - while (!need_resched()) { - - check_pgt_cache(); - rmb(); - - if (cpu_is_offline(cpu)) - play_dead(); - - local_touch_nmi(); - local_irq_disable(); - /* Don't trace irqs off for idle */ - stop_critical_timings(); - if (cpuidle_idle_call()) - pm_idle(); - start_critical_timings(); - } - rcu_idle_exit(); - tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); - } -} - void __show_regs(struct pt_regs *regs, int all) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L; @@ -214,6 +155,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, task_user_gs(p) = get_user_gs(regs); + p->fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; tsk = current; err = -ENOMEM; @@ -299,22 +241,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) *next = &next_p->thread; int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(init_tss, cpu); - bool preload_fpu; + fpu_switch_t fpu; /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ - /* - * If the task has used fpu the last 5 timeslices, just do a full - * restore of the math state immediately to avoid the trap; the - * chances of needing FPU soon are obviously high now - */ - preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5; - - __unlazy_fpu(prev_p); - - /* we're going to use this soon, after a few expensive things */ - if (preload_fpu) - prefetch(next->fpu.state); + fpu = switch_fpu_prepare(prev_p, next_p, cpu); /* * Reload esp0. @@ -354,11 +285,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT)) __switch_to_xtra(prev_p, next_p, tss); - /* If we're going to preload the fpu context, make sure clts - is run while we're batching the cpu state updates. */ - if (preload_fpu) - clts(); - /* * Leave lazy mode, flushing any hypercalls made here. * This must be done before restoring TLS segments so @@ -368,15 +294,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) */ arch_end_context_switch(next_p); - if (preload_fpu) - __math_state_restore(); - /* * Restore %gs if needed (which is common) */ if (prev->gs | next->gs) lazy_load_gs(next->gs); + switch_fpu_finish(next_p, fpu); + percpu_write(current_task, next_p); return prev_p; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 9b9fe4a85c8..733ca39f367 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -14,7 +14,6 @@ * This file handles the architecture-dependent parts of process handling.. */ -#include <linux/stackprotector.h> #include <linux/cpu.h> #include <linux/errno.h> #include <linux/sched.h> @@ -32,17 +31,15 @@ #include <linux/notifier.h> #include <linux/kprobes.h> #include <linux/kdebug.h> -#include <linux/tick.h> #include <linux/prctl.h> #include <linux/uaccess.h> #include <linux/io.h> #include <linux/ftrace.h> -#include <linux/cpuidle.h> #include <asm/pgtable.h> -#include <asm/system.h> #include <asm/processor.h> #include <asm/i387.h> +#include <asm/fpu-internal.h> #include <asm/mmu_context.h> #include <asm/prctl.h> #include <asm/desc.h> @@ -51,116 +48,11 @@ #include <asm/idle.h> #include <asm/syscalls.h> #include <asm/debugreg.h> -#include <asm/nmi.h> +#include <asm/switch_to.h> asmlinkage extern void ret_from_fork(void); DEFINE_PER_CPU(unsigned long, old_rsp); -static DEFINE_PER_CPU(unsigned char, is_idle); - -static ATOMIC_NOTIFIER_HEAD(idle_notifier); - -void idle_notifier_register(struct notifier_block *n) -{ - atomic_notifier_chain_register(&idle_notifier, n); -} -EXPORT_SYMBOL_GPL(idle_notifier_register); - -void idle_notifier_unregister(struct notifier_block *n) -{ - atomic_notifier_chain_unregister(&idle_notifier, n); -} -EXPORT_SYMBOL_GPL(idle_notifier_unregister); - -void enter_idle(void) -{ - percpu_write(is_idle, 1); - atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL); -} - -static void __exit_idle(void) -{ - if (x86_test_and_clear_bit_percpu(0, is_idle) == 0) - return; - atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL); -} - -/* Called from interrupts to signify idle end */ -void exit_idle(void) -{ - /* idle loop has pid 0 */ - if (current->pid) - return; - __exit_idle(); -} - -#ifndef CONFIG_SMP -static inline void play_dead(void) -{ - BUG(); -} -#endif - -/* - * The idle thread. There's no useful work to be - * done, so just try to conserve power and have a - * low exit latency (ie sit in a loop waiting for - * somebody to say that they'd like to reschedule) - */ -void cpu_idle(void) -{ - current_thread_info()->status |= TS_POLLING; - - /* - * If we're the non-boot CPU, nothing set the stack canary up - * for us. CPU0 already has it initialized but no harm in - * doing it again. This is a good place for updating it, as - * we wont ever return from this function (so the invalid - * canaries already on the stack wont ever trigger). - */ - boot_init_stack_canary(); - - /* endless idle loop with no priority at all */ - while (1) { - tick_nohz_idle_enter(); - while (!need_resched()) { - - rmb(); - - if (cpu_is_offline(smp_processor_id())) - play_dead(); - /* - * Idle routines should keep interrupts disabled - * from here on, until they go to idle. - * Otherwise, idle callbacks can misfire. - */ - local_touch_nmi(); - local_irq_disable(); - enter_idle(); - /* Don't trace irqs off for idle */ - stop_critical_timings(); - - /* enter_idle() needs rcu for notifiers */ - rcu_idle_enter(); - - if (cpuidle_idle_call()) - pm_idle(); - - rcu_idle_exit(); - start_critical_timings(); - - /* In many cases the interrupt that ended idle - has already called exit_idle. But some idle - loops can be woken up without interrupt. */ - __exit_idle(); - } - - tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); - } -} /* Prints also some state that isn't saved in the pt_regs */ void __show_regs(struct pt_regs *regs, int all) @@ -286,6 +178,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, set_tsk_thread_flag(p, TIF_FORK); + p->fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; savesegment(gs, p->thread.gsindex); @@ -341,6 +234,7 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip, loadsegment(es, _ds); loadsegment(ds, _ds); load_gs_index(0); + current->thread.usersp = new_sp; regs->ip = new_ip; regs->sp = new_sp; percpu_write(old_rsp, new_sp); @@ -364,7 +258,9 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp) { start_thread_common(regs, new_ip, new_sp, - __USER32_CS, __USER32_DS, __USER32_DS); + test_thread_flag(TIF_X32) + ? __USER_CS : __USER32_CS, + __USER_DS, __USER_DS); } #endif @@ -386,18 +282,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(init_tss, cpu); unsigned fsindex, gsindex; - bool preload_fpu; + fpu_switch_t fpu; - /* - * If the task has used fpu the last 5 timeslices, just do a full - * restore of the math state immediately to avoid the trap; the - * chances of needing FPU soon are obviously high now - */ - preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5; - - /* we're going to use this soon, after a few expensive things */ - if (preload_fpu) - prefetch(next->fpu.state); + fpu = switch_fpu_prepare(prev_p, next_p, cpu); /* * Reload esp0, LDT and the page table pointer: @@ -427,13 +314,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) load_TLS(next, cpu); - /* Must be after DS reload */ - __unlazy_fpu(prev_p); - - /* Make sure cpu is ready for new context */ - if (preload_fpu) - clts(); - /* * Leave lazy mode, flushing any hypercalls made here. * This must be done before restoring TLS segments so @@ -474,6 +354,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) wrmsrl(MSR_KERNEL_GS_BASE, next->gs); prev->gsindex = gsindex; + switch_fpu_finish(next_p, fpu); + /* * Switch the PDA and FPU contexts. */ @@ -492,13 +374,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV)) __switch_to_xtra(prev_p, next_p, tss); - /* - * Preload the FPU context, now that we've determined that the - * task is likely to be using it. - */ - if (preload_fpu) - __math_state_restore(); - return prev_p; } @@ -508,6 +383,8 @@ void set_personality_64bit(void) /* Make sure to be in 64bit mode */ clear_thread_flag(TIF_IA32); + clear_thread_flag(TIF_ADDR32); + clear_thread_flag(TIF_X32); /* Ensure the corresponding mm is not marked. */ if (current->mm) @@ -520,20 +397,31 @@ void set_personality_64bit(void) current->personality &= ~READ_IMPLIES_EXEC; } -void set_personality_ia32(void) +void set_personality_ia32(bool x32) { /* inherit personality from parent */ /* Make sure to be in 32bit mode */ - set_thread_flag(TIF_IA32); - current->personality |= force_personality32; + set_thread_flag(TIF_ADDR32); /* Mark the associated mm as containing 32-bit tasks. */ if (current->mm) current->mm->context.ia32_compat = 1; - /* Prepare the first "return" to user space */ - current_thread_info()->status |= TS_COMPAT; + if (x32) { + clear_thread_flag(TIF_IA32); + set_thread_flag(TIF_X32); + current->personality &= ~READ_IMPLIES_EXEC; + /* is_compat_task() uses the presence of the x32 + syscall bit flag to determine compat status */ + current_thread_info()->status &= ~TS_COMPAT; + } else { + set_thread_flag(TIF_IA32); + clear_thread_flag(TIF_X32); + current->personality |= force_personality32; + /* Prepare the first "return" to user space */ + current_thread_info()->status |= TS_COMPAT; + } } unsigned long get_wchan(struct task_struct *p) diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 89a04c7b5bb..685845cf16e 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -24,15 +24,16 @@ #include <asm/uaccess.h> #include <asm/pgtable.h> -#include <asm/system.h> #include <asm/processor.h> #include <asm/i387.h> +#include <asm/fpu-internal.h> #include <asm/debugreg.h> #include <asm/ldt.h> #include <asm/desc.h> #include <asm/prctl.h> #include <asm/proto.h> #include <asm/hw_breakpoint.h> +#include <asm/traps.h> #include "tls.h" @@ -1130,6 +1131,100 @@ static int genregs32_set(struct task_struct *target, return ret; } +#ifdef CONFIG_X86_X32_ABI +static long x32_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; + + switch (request) { + /* Read 32bits at location addr in the USER area. Only allow + to return the lower 32bits of segment and debug registers. */ + case PTRACE_PEEKUSR: { + u32 tmp; + + ret = -EIO; + if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user) || + addr < offsetof(struct user_regs_struct, cs)) + break; + + tmp = 0; /* Default return condition */ + if (addr < sizeof(struct user_regs_struct)) + tmp = getreg(child, addr); + else if (addr >= offsetof(struct user, u_debugreg[0]) && + addr <= offsetof(struct user, u_debugreg[7])) { + addr -= offsetof(struct user, u_debugreg[0]); + tmp = ptrace_get_debugreg(child, addr / sizeof(data)); + } + ret = put_user(tmp, (__u32 __user *)datap); + break; + } + + /* Write the word at location addr in the USER area. Only allow + to update segment and debug registers with the upper 32bits + zero-extended. */ + case PTRACE_POKEUSR: + ret = -EIO; + if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user) || + addr < offsetof(struct user_regs_struct, cs)) + break; + + if (addr < sizeof(struct user_regs_struct)) + ret = putreg(child, addr, data); + else if (addr >= offsetof(struct user, u_debugreg[0]) && + addr <= offsetof(struct user, u_debugreg[7])) { + addr -= offsetof(struct user, u_debugreg[0]); + ret = ptrace_set_debugreg(child, + addr / sizeof(data), data); + } + break; + + case PTRACE_GETREGS: /* Get all gp regs from the child. */ + return copy_regset_to_user(child, + task_user_regset_view(current), + REGSET_GENERAL, + 0, sizeof(struct user_regs_struct), + datap); + + case PTRACE_SETREGS: /* Set all gp regs in the child. */ + return copy_regset_from_user(child, + task_user_regset_view(current), + REGSET_GENERAL, + 0, sizeof(struct user_regs_struct), + datap); + + case PTRACE_GETFPREGS: /* Get the child FPU state. */ + return copy_regset_to_user(child, + task_user_regset_view(current), + REGSET_FP, + 0, sizeof(struct user_i387_struct), + datap); + + case PTRACE_SETFPREGS: /* Set the child FPU state. */ + return copy_regset_from_user(child, + task_user_regset_view(current), + REGSET_FP, + 0, sizeof(struct user_i387_struct), + datap); + + /* normal 64bit interface to access TLS data. + Works just like arch_prctl, except that the arguments + are reversed. */ + case PTRACE_ARCH_PRCTL: + return do_arch_prctl(child, data, addr); + + default: + return compat_ptrace_request(child, request, addr, data); + } + + return ret; +} +#endif + long compat_arch_ptrace(struct task_struct *child, compat_long_t request, compat_ulong_t caddr, compat_ulong_t cdata) { @@ -1139,6 +1234,11 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, 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); @@ -1326,7 +1426,7 @@ static void fill_sigtrap_info(struct task_struct *tsk, int error_code, int si_code, struct siginfo *info) { - tsk->thread.trap_no = 1; + tsk->thread.trap_nr = X86_TRAP_DB; tsk->thread.error_code = error_code; memset(info, 0, sizeof(*info)); @@ -1392,20 +1492,18 @@ long syscall_trace_enter(struct pt_regs *regs) if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_enter(regs, regs->orig_ax); - if (unlikely(current->audit_context)) { - if (IS_IA32) - audit_syscall_entry(AUDIT_ARCH_I386, - regs->orig_ax, - regs->bx, regs->cx, - regs->dx, regs->si); + if (IS_IA32) + audit_syscall_entry(AUDIT_ARCH_I386, + regs->orig_ax, + regs->bx, regs->cx, + regs->dx, regs->si); #ifdef CONFIG_X86_64 - else - audit_syscall_entry(AUDIT_ARCH_X86_64, - regs->orig_ax, - regs->di, regs->si, - regs->dx, regs->r10); + else + audit_syscall_entry(AUDIT_ARCH_X86_64, + regs->orig_ax, + regs->di, regs->si, + regs->dx, regs->r10); #endif - } return ret ?: regs->orig_ax; } @@ -1414,8 +1512,7 @@ void syscall_trace_leave(struct pt_regs *regs) { bool step; - if (unlikely(current->audit_context)) - audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax); + audit_syscall_exit(regs); if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_exit(regs, regs->ax); diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 37a458b521a..d840e69a853 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -39,6 +39,14 @@ static int reboot_mode; enum reboot_type reboot_type = BOOT_ACPI; int reboot_force; +/* This variable is used privately to keep track of whether or not + * reboot_type is still set to its default value (i.e., reboot= hasn't + * been set on the command line). This is needed so that we can + * suppress DMI scanning for reboot quirks. Without it, it's + * impossible to override a faulty reboot quirk without recompiling. + */ +static int reboot_default = 1; + #if defined(CONFIG_X86_32) && defined(CONFIG_SMP) static int reboot_cpu = -1; #endif @@ -67,6 +75,12 @@ bool port_cf9_safe = false; static int __init reboot_setup(char *str) { for (;;) { + /* Having anything passed on the command line via + * reboot= will cause us to disable DMI checking + * below. + */ + reboot_default = 0; + switch (*str) { case 'w': reboot_mode = 0x1234; @@ -295,14 +309,6 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "P4S800"), }, }, - { /* Handle problems with rebooting on VersaLogic Menlow boards */ - .callback = set_bios_reboot, - .ident = "VersaLogic Menlow based board", - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "VersaLogic Corporation"), - DMI_MATCH(DMI_BOARD_NAME, "VersaLogic Menlow board"), - }, - }, { /* Handle reboot issue on Acer Aspire one */ .callback = set_kbd_reboot, .ident = "Acer Aspire One A110", @@ -316,7 +322,12 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { static int __init reboot_init(void) { - dmi_check_system(reboot_dmi_table); + /* Only do the DMI check if reboot_type hasn't been overridden + * on the command line + */ + if (reboot_default) { + dmi_check_system(reboot_dmi_table); + } return 0; } core_initcall(reboot_init); @@ -465,7 +476,12 @@ static struct dmi_system_id __initdata pci_reboot_dmi_table[] = { static int __init pci_reboot_init(void) { - dmi_check_system(pci_reboot_dmi_table); + /* Only do the DMI check if reboot_type hasn't been overridden + * on the command line + */ + if (reboot_default) { + dmi_check_system(pci_reboot_dmi_table); + } return 0; } core_initcall(pci_reboot_init); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index d05444ac2ae..1a290156205 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -90,7 +90,6 @@ #include <asm/processor.h> #include <asm/bugs.h> -#include <asm/system.h> #include <asm/vsyscall.h> #include <asm/cpu.h> #include <asm/desc.h> @@ -509,15 +508,6 @@ static void __init memblock_x86_reserve_range_setup_data(void) #ifdef CONFIG_KEXEC -static inline unsigned long long get_total_mem(void) -{ - unsigned long long total; - - total = max_pfn - min_low_pfn; - - return total << PAGE_SHIFT; -} - /* * Keep the crash kernel below this limit. On 32 bits earlier kernels * would limit the kernel to the low 512 MiB due to mapping restrictions. @@ -536,7 +526,7 @@ static void __init reserve_crashkernel(void) unsigned long long crash_size, crash_base; int ret; - total_mem = get_total_mem(); + total_mem = memblock_phys_mem_size(); ret = parse_crashkernel(boot_command_line, total_mem, &crash_size, &crash_base); @@ -749,15 +739,16 @@ void __init setup_arch(char **cmdline_p) #endif #ifdef CONFIG_EFI if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, -#ifdef CONFIG_X86_32 - "EL32", -#else - "EL64", -#endif - 4)) { + "EL32", 4)) { + efi_enabled = 1; + efi_64bit = false; + } else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, + "EL64", 4)) { efi_enabled = 1; - efi_memblock_x86_reserve_range(); + efi_64bit = true; } + if (efi_enabled && efi_memblock_x86_reserve_range()) + efi_enabled = 0; #endif x86_init.oem.arch_setup(); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 46a01bdc27e..115eac43148 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -10,10 +10,8 @@ #include <linux/mm.h> #include <linux/smp.h> #include <linux/kernel.h> -#include <linux/signal.h> #include <linux/errno.h> #include <linux/wait.h> -#include <linux/ptrace.h> #include <linux/tracehook.h> #include <linux/unistd.h> #include <linux/stddef.h> @@ -24,12 +22,15 @@ #include <asm/processor.h> #include <asm/ucontext.h> #include <asm/i387.h> +#include <asm/fpu-internal.h> #include <asm/vdso.h> #include <asm/mce.h> +#include <asm/sighandling.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> @@ -37,13 +38,6 @@ #include <asm/sigframe.h> -#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) - -#define __FIX_EFLAGS (X86_EFLAGS_AC | X86_EFLAGS_OF | \ - X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \ - X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \ - X86_EFLAGS_CF) - #ifdef CONFIG_X86_32 # define FIX_EFLAGS (__FIX_EFLAGS | X86_EFLAGS_RF) #else @@ -68,9 +62,8 @@ regs->seg = GET_SEG(seg) | 3; \ } while (0) -static int -restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, - unsigned long *pax) +int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, + unsigned long *pax) { void __user *buf; unsigned int tmpflags; @@ -125,9 +118,8 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, return err; } -static int -setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, - struct pt_regs *regs, unsigned long mask) +int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, + struct pt_regs *regs, unsigned long mask) { int err = 0; @@ -159,7 +151,7 @@ setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, put_user_ex(regs->r15, &sc->r15); #endif /* CONFIG_X86_64 */ - put_user_ex(current->thread.trap_no, &sc->trapno); + put_user_ex(current->thread.trap_nr, &sc->trapno); put_user_ex(current->thread.error_code, &sc->err); put_user_ex(regs->ip, &sc->ip); #ifdef CONFIG_X86_32 @@ -642,6 +634,16 @@ static int signr_convert(int sig) #define is_ia32 0 #endif /* CONFIG_IA32_EMULATION */ +#ifdef CONFIG_X86_X32_ABI +#define is_x32 test_thread_flag(TIF_X32) + +static int x32_setup_rt_frame(int sig, struct k_sigaction *ka, + siginfo_t *info, compat_sigset_t *set, + struct pt_regs *regs); +#else /* !CONFIG_X86_X32_ABI */ +#define is_x32 0 +#endif /* CONFIG_X86_X32_ABI */ + int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *set, struct pt_regs *regs); int ia32_setup_frame(int sig, struct k_sigaction *ka, @@ -666,8 +668,14 @@ setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, ret = ia32_setup_rt_frame(usig, ka, info, set, regs); else ret = ia32_setup_frame(usig, ka, set, regs); - } else +#ifdef CONFIG_X86_X32_ABI + } else if (is_x32) { + ret = x32_setup_rt_frame(usig, ka, info, + (compat_sigset_t *)set, regs); +#endif + } else { ret = __setup_rt_frame(sig, ka, info, set, regs); + } if (ret) { force_sigsegv(sig, current); @@ -850,3 +858,102 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where) force_sig(SIGSEGV, me); } + +#ifdef CONFIG_X86_X32_ABI +static int x32_setup_rt_frame(int sig, struct k_sigaction *ka, + siginfo_t *info, compat_sigset_t *set, + struct pt_regs *regs) +{ + struct rt_sigframe_x32 __user *frame; + void __user *restorer; + int err = 0; + void __user *fpstate = NULL; + + frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate); + + if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) + return -EFAULT; + + if (ka->sa.sa_flags & SA_SIGINFO) { + if (copy_siginfo_to_user32(&frame->info, info)) + return -EFAULT; + } + + put_user_try { + /* Create the ucontext. */ + if (cpu_has_xsave) + put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); + else + put_user_ex(0, &frame->uc.uc_flags); + put_user_ex(0, &frame->uc.uc_link); + put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); + put_user_ex(sas_ss_flags(regs->sp), + &frame->uc.uc_stack.ss_flags); + put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size); + put_user_ex(0, &frame->uc.uc__pad0); + err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate, + regs, set->sig[0]); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + + if (ka->sa.sa_flags & SA_RESTORER) { + restorer = ka->sa.sa_restorer; + } else { + /* could use a vstub here */ + restorer = NULL; + err |= -EFAULT; + } + put_user_ex(restorer, &frame->pretcode); + } put_user_catch(err); + + if (err) + return -EFAULT; + + /* Set up registers for signal handler */ + regs->sp = (unsigned long) frame; + regs->ip = (unsigned long) ka->sa.sa_handler; + + /* We use the x32 calling convention here... */ + regs->di = sig; + regs->si = (unsigned long) &frame->info; + regs->dx = (unsigned long) &frame->uc; + + loadsegment(ds, __USER_DS); + loadsegment(es, __USER_DS); + + regs->cs = __USER_CS; + regs->ss = __USER_DS; + + return 0; +} + +asmlinkage long sys32_x32_rt_sigreturn(struct pt_regs *regs) +{ + struct rt_sigframe_x32 __user *frame; + sigset_t set; + unsigned long ax; + struct pt_regs tregs; + + frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8); + + if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) + goto badframe; + if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) + goto badframe; + + sigdelsetmask(&set, ~_BLOCKABLE); + set_current_blocked(&set); + + if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax)) + goto badframe; + + tregs = *regs; + if (sys32_sigaltstack(&frame->uc.uc_stack, NULL, &tregs) == -EFAULT) + goto badframe; + + return ax; + +badframe: + signal_fault(regs, frame, "x32 rt_sigreturn"); + return 0; +} +#endif diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 16204dc1548..66c74f481ca 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -29,6 +29,7 @@ #include <asm/mmu_context.h> #include <asm/proto.h> #include <asm/apic.h> +#include <asm/nmi.h> /* * Some notes on x86 processor bugs affecting SMP operation: * @@ -148,6 +149,60 @@ void native_send_call_func_ipi(const struct cpumask *mask) free_cpumask_var(allbutself); } +static atomic_t stopping_cpu = ATOMIC_INIT(-1); + +static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs) +{ + /* We are registered on stopping cpu too, avoid spurious NMI */ + if (raw_smp_processor_id() == atomic_read(&stopping_cpu)) + return NMI_HANDLED; + + stop_this_cpu(NULL); + + return NMI_HANDLED; +} + +static void native_nmi_stop_other_cpus(int wait) +{ + unsigned long flags; + unsigned long timeout; + + if (reboot_force) + return; + + /* + * Use an own vector here because smp_call_function + * does lots of things not suitable in a panic situation. + */ + if (num_online_cpus() > 1) { + /* did someone beat us here? */ + if (atomic_cmpxchg(&stopping_cpu, -1, safe_smp_processor_id()) != -1) + return; + + if (register_nmi_handler(NMI_LOCAL, smp_stop_nmi_callback, + NMI_FLAG_FIRST, "smp_stop")) + /* Note: we ignore failures here */ + return; + + /* sync above data before sending NMI */ + wmb(); + + apic->send_IPI_allbutself(NMI_VECTOR); + + /* + * Don't wait longer than a second if the caller + * didn't ask us to wait. + */ + timeout = USEC_PER_SEC; + while (num_online_cpus() > 1 && (wait || timeout--)) + udelay(1); + } + + local_irq_save(flags); + disable_local_APIC(); + local_irq_restore(flags); +} + /* * this function calls the 'stop' function on all other CPUs in the system. */ @@ -160,7 +215,7 @@ asmlinkage void smp_reboot_interrupt(void) irq_exit(); } -static void native_stop_other_cpus(int wait) +static void native_irq_stop_other_cpus(int wait) { unsigned long flags; unsigned long timeout; @@ -194,6 +249,11 @@ static void native_stop_other_cpus(int wait) local_irq_restore(flags); } +static void native_smp_disable_nmi_ipi(void) +{ + smp_ops.stop_other_cpus = native_irq_stop_other_cpus; +} + /* * Reschedule call back. */ @@ -225,12 +285,20 @@ void smp_call_function_single_interrupt(struct pt_regs *regs) irq_exit(); } +static int __init nonmi_ipi_setup(char *str) +{ + native_smp_disable_nmi_ipi(); + return 1; +} + +__setup("nonmi_ipi", nonmi_ipi_setup); + struct smp_ops smp_ops = { .smp_prepare_boot_cpu = native_smp_prepare_boot_cpu, .smp_prepare_cpus = native_smp_prepare_cpus, .smp_cpus_done = native_smp_cpus_done, - .stop_other_cpus = native_stop_other_cpus, + .stop_other_cpus = native_nmi_stop_other_cpus, .smp_send_reschedule = native_smp_send_reschedule, .cpu_up = native_cpu_up, diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index e38e21754ee..6e1e406038c 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -50,6 +50,7 @@ #include <linux/tboot.h> #include <linux/stackprotector.h> #include <linux/gfp.h> +#include <linux/cpuidle.h> #include <asm/acpi.h> #include <asm/desc.h> @@ -207,21 +208,22 @@ static void __cpuinit smp_callin(void) * Need to setup vector mappings before we enable interrupts. */ setup_vector_irq(smp_processor_id()); + /* - * Get our bogomips. - * - * Need to enable IRQs because it can take longer and then - * the NMI watchdog might kill us. + * Save our processor parameters. Note: this information + * is needed for clock calibration. */ - local_irq_enable(); - calibrate_delay(); - local_irq_disable(); - pr_debug("Stack at about %p\n", &cpuid); + smp_store_cpu_info(cpuid); /* - * Save our processor parameters + * Get our bogomips. + * Update loops_per_jiffy in cpu_data. Previous call to + * smp_store_cpu_info() stored a value that is close but not as + * accurate as the value just calculated. */ - smp_store_cpu_info(cpuid); + calibrate_delay(); + cpu_data(cpuid).loops_per_jiffy = loops_per_jiffy; + pr_debug("Stack at about %p\n", &cpuid); /* * This must be done before setting cpu_online_mask @@ -249,6 +251,7 @@ notrace static void __cpuinit start_secondary(void *unused) * most necessary things. */ cpu_init(); + x86_cpuinit.early_percpu_clock_init(); preempt_disable(); smp_callin(); @@ -285,19 +288,6 @@ notrace static void __cpuinit start_secondary(void *unused) per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; x86_platform.nmi_init(); - /* - * Wait until the cpu which brought this one up marked it - * online before enabling interrupts. If we don't do that then - * we can end up waking up the softirq thread before this cpu - * reached the active state, which makes the scheduler unhappy - * and schedule the softirq thread on the wrong cpu. This is - * only observable with forced threaded interrupts, but in - * theory it could also happen w/o them. It's just way harder - * to achieve. - */ - while (!cpumask_test_cpu(smp_processor_id(), cpu_active_mask)) - cpu_relax(); - /* enable local interrupts */ local_irq_enable(); @@ -734,8 +724,6 @@ do_rest: * the targeted processor. */ - printk(KERN_DEBUG "smpboot cpu %d: start_ip = %lx\n", cpu, start_ip); - atomic_set(&init_deasserted, 0); if (get_uv_system_type() != UV_NON_UNIQUE_APIC) { @@ -785,9 +773,10 @@ do_rest: schedule(); } - if (cpumask_test_cpu(cpu, cpu_callin_mask)) + if (cpumask_test_cpu(cpu, cpu_callin_mask)) { + print_cpu_msr(&cpu_data(cpu)); pr_debug("CPU%d: has booted.\n", cpu); - else { + } else { boot_error = 1; if (*(volatile u32 *)TRAMPOLINE_SYM(trampoline_status) == 0xA5A5A5A5) @@ -841,7 +830,7 @@ int __cpuinit native_cpu_up(unsigned int cpu) if (apicid == BAD_APICID || apicid == boot_cpu_physical_apicid || !physid_isset(apicid, phys_cpu_present_map) || - (!x2apic_mode && apicid >= 255)) { + !apic->apic_id_valid(apicid)) { printk(KERN_ERR "%s: bad cpu %d\n", __func__, cpu); return -EINVAL; } @@ -1143,6 +1132,7 @@ void __init native_smp_cpus_done(unsigned int max_cpus) { pr_debug("Boot done.\n"); + nmi_selftest(); impress_friends(); #ifdef CONFIG_X86_IO_APIC setup_ioapic_dest(); @@ -1415,7 +1405,8 @@ void native_play_dead(void) tboot_shutdown(TB_SHUTDOWN_WFS); mwait_play_dead(); /* Only returns on failure */ - hlt_play_dead(); + if (cpuidle_play_dead()) + hlt_play_dead(); } #else /* ... !CONFIG_HOTPLUG_CPU */ diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 051489082d5..b4d3c3927dd 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -98,7 +98,7 @@ out: static void find_start_end(unsigned long flags, unsigned long *begin, unsigned long *end) { - if (!test_thread_flag(TIF_IA32) && (flags & MAP_32BIT)) { + if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT)) { unsigned long new_begin; /* This is usually used needed to map code in small model, so it needs to be in the first 31bit. Limit @@ -144,7 +144,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, (!vma || addr + len <= vma->vm_start)) return addr; } - if (((flags & MAP_32BIT) || test_thread_flag(TIF_IA32)) + if (((flags & MAP_32BIT) || test_thread_flag(TIF_ADDR32)) && len <= mm->cached_hole_size) { mm->cached_hole_size = 0; mm->free_area_cache = begin; @@ -195,7 +195,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, { struct vm_area_struct *vma; struct mm_struct *mm = current->mm; - unsigned long addr = addr0; + unsigned long addr = addr0, start_addr; /* requested length too big for entire address space */ if (len > TASK_SIZE) @@ -205,7 +205,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, return addr; /* for MAP_32BIT mappings we force the legact mmap base */ - if (!test_thread_flag(TIF_IA32) && (flags & MAP_32BIT)) + if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT)) goto bottomup; /* requesting a specific address */ @@ -223,25 +223,14 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, mm->free_area_cache = mm->mmap_base; } +try_again: /* either no address requested or can't fit in requested address hole */ - addr = mm->free_area_cache; - - /* make sure it can fit in the remaining address space */ - if (addr > len) { - unsigned long tmp_addr = align_addr(addr - len, filp, - ALIGN_TOPDOWN); - - vma = find_vma(mm, tmp_addr); - if (!vma || tmp_addr + len <= vma->vm_start) - /* remember the address as a hint for next time */ - return mm->free_area_cache = tmp_addr; - } - - if (mm->mmap_base < len) - goto bottomup; + start_addr = addr = mm->free_area_cache; - addr = mm->mmap_base-len; + if (addr < len) + goto fail; + addr -= len; do { addr = align_addr(addr, filp, ALIGN_TOPDOWN); @@ -263,6 +252,17 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, addr = vma->vm_start-len; } while (len < vma->vm_start); +fail: + /* + * if hint left us with no space for the requested + * mapping then try again: + */ + if (start_addr != mm->mmap_base) { + mm->free_area_cache = mm->mmap_base; + mm->cached_hole_size = 0; + goto try_again; + } + bottomup: /* * A failed mmap() very likely causes application failure, diff --git a/arch/x86/kernel/syscall_32.c b/arch/x86/kernel/syscall_32.c new file mode 100644 index 00000000000..147fcd4941c --- /dev/null +++ b/arch/x86/kernel/syscall_32.c @@ -0,0 +1,25 @@ +/* System call table for i386. */ + +#include <linux/linkage.h> +#include <linux/sys.h> +#include <linux/cache.h> +#include <asm/asm-offsets.h> + +#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void sym(void) ; +#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); + +const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { + /* + * Smells like a compiler bug -- it doesn't work + * when the & below is removed. + */ + [0 ... __NR_syscall_max] = &sys_ni_syscall, +#include <asm/syscalls_32.h> +}; diff --git a/arch/x86/kernel/syscall_64.c b/arch/x86/kernel/syscall_64.c index de87d600829..5c7f8c20da7 100644 --- a/arch/x86/kernel/syscall_64.c +++ b/arch/x86/kernel/syscall_64.c @@ -5,15 +5,19 @@ #include <linux/cache.h> #include <asm/asm-offsets.h> -#define __NO_STUBS +#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat) -#define __SYSCALL(nr, sym) extern asmlinkage void sym(void) ; -#undef _ASM_X86_UNISTD_64_H -#include <asm/unistd_64.h> +#ifdef CONFIG_X86_X32_ABI +# define __SYSCALL_X32(nr, sym, compat) __SYSCALL_64(nr, sym, compat) +#else +# define __SYSCALL_X32(nr, sym, compat) /* nothing */ +#endif -#undef __SYSCALL -#define __SYSCALL(nr, sym) [nr] = sym, -#undef _ASM_X86_UNISTD_64_H +#define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ; +#include <asm/syscalls_64.h> +#undef __SYSCALL_64 + +#define __SYSCALL_64(nr, sym, compat) [nr] = sym, typedef void (*sys_call_ptr_t)(void); @@ -21,9 +25,9 @@ extern void sys_ni_syscall(void); const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { /* - *Smells like a like a compiler bug -- it doesn't work - *when the & below is removed. - */ + * Smells like a compiler bug -- it doesn't work + * when the & below is removed. + */ [0 ... __NR_syscall_max] = &sys_ni_syscall, -#include <asm/unistd_64.h> +#include <asm/syscalls_64.h> }; diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S deleted file mode 100644 index 9a0e3129392..00000000000 --- a/arch/x86/kernel/syscall_table_32.S +++ /dev/null @@ -1,350 +0,0 @@ -ENTRY(sys_call_table) - .long sys_restart_syscall /* 0 - old "setup()" system call, used for restarting */ - .long sys_exit - .long ptregs_fork - .long sys_read - .long sys_write - .long sys_open /* 5 */ - .long sys_close - .long sys_waitpid - .long sys_creat - .long sys_link - .long sys_unlink /* 10 */ - .long ptregs_execve - .long sys_chdir - .long sys_time - .long sys_mknod - .long sys_chmod /* 15 */ - .long sys_lchown16 - .long sys_ni_syscall /* old break syscall holder */ - .long sys_stat - .long sys_lseek - .long sys_getpid /* 20 */ - .long sys_mount - .long sys_oldumount - .long sys_setuid16 - .long sys_getuid16 - .long sys_stime /* 25 */ - .long sys_ptrace - .long sys_alarm - .long sys_fstat - .long sys_pause - .long sys_utime /* 30 */ - .long sys_ni_syscall /* old stty syscall holder */ - .long sys_ni_syscall /* old gtty syscall holder */ - .long sys_access - .long sys_nice - .long sys_ni_syscall /* 35 - old ftime syscall holder */ - .long sys_sync - .long sys_kill - .long sys_rename - .long sys_mkdir - .long sys_rmdir /* 40 */ - .long sys_dup - .long sys_pipe - .long sys_times - .long sys_ni_syscall /* old prof syscall holder */ - .long sys_brk /* 45 */ - .long sys_setgid16 - .long sys_getgid16 - .long sys_signal - .long sys_geteuid16 - .long sys_getegid16 /* 50 */ - .long sys_acct - .long sys_umount /* recycled never used phys() */ - .long sys_ni_syscall /* old lock syscall holder */ - .long sys_ioctl - .long sys_fcntl /* 55 */ - .long sys_ni_syscall /* old mpx syscall holder */ - .long sys_setpgid - .long sys_ni_syscall /* old ulimit syscall holder */ - .long sys_olduname - .long sys_umask /* 60 */ - .long sys_chroot - .long sys_ustat - .long sys_dup2 - .long sys_getppid - .long sys_getpgrp /* 65 */ - .long sys_setsid - .long sys_sigaction - .long sys_sgetmask - .long sys_ssetmask - .long sys_setreuid16 /* 70 */ - .long sys_setregid16 - .long sys_sigsuspend - .long sys_sigpending - .long sys_sethostname - .long sys_setrlimit /* 75 */ - .long sys_old_getrlimit - .long sys_getrusage - .long sys_gettimeofday - .long sys_settimeofday - .long sys_getgroups16 /* 80 */ - .long sys_setgroups16 - .long sys_old_select - .long sys_symlink - .long sys_lstat - .long sys_readlink /* 85 */ - .long sys_uselib - .long sys_swapon - .long sys_reboot - .long sys_old_readdir - .long sys_old_mmap /* 90 */ - .long sys_munmap - .long sys_truncate - .long sys_ftruncate - .long sys_fchmod - .long sys_fchown16 /* 95 */ - .long sys_getpriority - .long sys_setpriority - .long sys_ni_syscall /* old profil syscall holder */ - .long sys_statfs - .long sys_fstatfs /* 100 */ - .long sys_ioperm - .long sys_socketcall - .long sys_syslog - .long sys_setitimer - .long sys_getitimer /* 105 */ - .long sys_newstat - .long sys_newlstat - .long sys_newfstat - .long sys_uname - .long ptregs_iopl /* 110 */ - .long sys_vhangup - .long sys_ni_syscall /* old "idle" system call */ - .long ptregs_vm86old - .long sys_wait4 - .long sys_swapoff /* 115 */ - .long sys_sysinfo - .long sys_ipc - .long sys_fsync - .long ptregs_sigreturn - .long ptregs_clone /* 120 */ - .long sys_setdomainname - .long sys_newuname - .long sys_modify_ldt - .long sys_adjtimex - .long sys_mprotect /* 125 */ - .long sys_sigprocmask - .long sys_ni_syscall /* old "create_module" */ - .long sys_init_module - .long sys_delete_module - .long sys_ni_syscall /* 130: old "get_kernel_syms" */ - .long sys_quotactl - .long sys_getpgid - .long sys_fchdir - .long sys_bdflush - .long sys_sysfs /* 135 */ - .long sys_personality - .long sys_ni_syscall /* reserved for afs_syscall */ - .long sys_setfsuid16 - .long sys_setfsgid16 - .long sys_llseek /* 140 */ - .long sys_getdents - .long sys_select - .long sys_flock - .long sys_msync - .long sys_readv /* 145 */ - .long sys_writev - .long sys_getsid - .long sys_fdatasync - .long sys_sysctl - .long sys_mlock /* 150 */ - .long sys_munlock - .long sys_mlockall - .long sys_munlockall - .long sys_sched_setparam - .long sys_sched_getparam /* 155 */ - .long sys_sched_setscheduler - .long sys_sched_getscheduler - .long sys_sched_yield - .long sys_sched_get_priority_max - .long sys_sched_get_priority_min /* 160 */ - .long sys_sched_rr_get_interval - .long sys_nanosleep - .long sys_mremap - .long sys_setresuid16 - .long sys_getresuid16 /* 165 */ - .long ptregs_vm86 - .long sys_ni_syscall /* Old sys_query_module */ - .long sys_poll - .long sys_ni_syscall /* Old nfsservctl */ - .long sys_setresgid16 /* 170 */ - .long sys_getresgid16 - .long sys_prctl - .long ptregs_rt_sigreturn - .long sys_rt_sigaction - .long sys_rt_sigprocmask /* 175 */ - .long sys_rt_sigpending - .long sys_rt_sigtimedwait - .long sys_rt_sigqueueinfo - .long sys_rt_sigsuspend - .long sys_pread64 /* 180 */ - .long sys_pwrite64 - .long sys_chown16 - .long sys_getcwd - .long sys_capget - .long sys_capset /* 185 */ - .long ptregs_sigaltstack - .long sys_sendfile - .long sys_ni_syscall /* reserved for streams1 */ - .long sys_ni_syscall /* reserved for streams2 */ - .long ptregs_vfork /* 190 */ - .long sys_getrlimit - .long sys_mmap_pgoff - .long sys_truncate64 - .long sys_ftruncate64 - .long sys_stat64 /* 195 */ - .long sys_lstat64 - .long sys_fstat64 - .long sys_lchown - .long sys_getuid - .long sys_getgid /* 200 */ - .long sys_geteuid - .long sys_getegid - .long sys_setreuid - .long sys_setregid - .long sys_getgroups /* 205 */ - .long sys_setgroups - .long sys_fchown - .long sys_setresuid - .long sys_getresuid - .long sys_setresgid /* 210 */ - .long sys_getresgid - .long sys_chown - .long sys_setuid - .long sys_setgid - .long sys_setfsuid /* 215 */ - .long sys_setfsgid - .long sys_pivot_root - .long sys_mincore - .long sys_madvise - .long sys_getdents64 /* 220 */ - .long sys_fcntl64 - .long sys_ni_syscall /* reserved for TUX */ - .long sys_ni_syscall - .long sys_gettid - .long sys_readahead /* 225 */ - .long sys_setxattr - .long sys_lsetxattr - .long sys_fsetxattr - .long sys_getxattr - .long sys_lgetxattr /* 230 */ - .long sys_fgetxattr - .long sys_listxattr - .long sys_llistxattr - .long sys_flistxattr - .long sys_removexattr /* 235 */ - .long sys_lremovexattr - .long sys_fremovexattr - .long sys_tkill - .long sys_sendfile64 - .long sys_futex /* 240 */ - .long sys_sched_setaffinity - .long sys_sched_getaffinity - .long sys_set_thread_area - .long sys_get_thread_area - .long sys_io_setup /* 245 */ - .long sys_io_destroy - .long sys_io_getevents - .long sys_io_submit - .long sys_io_cancel - .long sys_fadvise64 /* 250 */ - .long sys_ni_syscall - .long sys_exit_group - .long sys_lookup_dcookie - .long sys_epoll_create - .long sys_epoll_ctl /* 255 */ - .long sys_epoll_wait - .long sys_remap_file_pages - .long sys_set_tid_address - .long sys_timer_create - .long sys_timer_settime /* 260 */ - .long sys_timer_gettime - .long sys_timer_getoverrun - .long sys_timer_delete - .long sys_clock_settime - .long sys_clock_gettime /* 265 */ - .long sys_clock_getres - .long sys_clock_nanosleep - .long sys_statfs64 - .long sys_fstatfs64 - .long sys_tgkill /* 270 */ - .long sys_utimes - .long sys_fadvise64_64 - .long sys_ni_syscall /* sys_vserver */ - .long sys_mbind - .long sys_get_mempolicy - .long sys_set_mempolicy - .long sys_mq_open - .long sys_mq_unlink - .long sys_mq_timedsend - .long sys_mq_timedreceive /* 280 */ - .long sys_mq_notify - .long sys_mq_getsetattr - .long sys_kexec_load - .long sys_waitid - .long sys_ni_syscall /* 285 */ /* available */ - .long sys_add_key - .long sys_request_key - .long sys_keyctl - .long sys_ioprio_set - .long sys_ioprio_get /* 290 */ - .long sys_inotify_init - .long sys_inotify_add_watch - .long sys_inotify_rm_watch - .long sys_migrate_pages - .long sys_openat /* 295 */ - .long sys_mkdirat - .long sys_mknodat - .long sys_fchownat - .long sys_futimesat - .long sys_fstatat64 /* 300 */ - .long sys_unlinkat - .long sys_renameat - .long sys_linkat - .long sys_symlinkat - .long sys_readlinkat /* 305 */ - .long sys_fchmodat - .long sys_faccessat - .long sys_pselect6 - .long sys_ppoll - .long sys_unshare /* 310 */ - .long sys_set_robust_list - .long sys_get_robust_list - .long sys_splice - .long sys_sync_file_range - .long sys_tee /* 315 */ - .long sys_vmsplice - .long sys_move_pages - .long sys_getcpu - .long sys_epoll_pwait - .long sys_utimensat /* 320 */ - .long sys_signalfd - .long sys_timerfd_create - .long sys_eventfd - .long sys_fallocate - .long sys_timerfd_settime /* 325 */ - .long sys_timerfd_gettime - .long sys_signalfd4 - .long sys_eventfd2 - .long sys_epoll_create1 - .long sys_dup3 /* 330 */ - .long sys_pipe2 - .long sys_inotify_init1 - .long sys_preadv - .long sys_pwritev - .long sys_rt_tgsigqueueinfo /* 335 */ - .long sys_perf_event_open - .long sys_recvmmsg - .long sys_fanotify_init - .long sys_fanotify_mark - .long sys_prlimit64 /* 340 */ - .long sys_name_to_handle_at - .long sys_open_by_handle_at - .long sys_clock_adjtime - .long sys_syncfs - .long sys_sendmmsg /* 345 */ - .long sys_setns - .long sys_process_vm_readv - .long sys_process_vm_writev diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index e2410e27f97..6410744ac5c 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -272,7 +272,7 @@ static void tboot_copy_fadt(const struct acpi_table_fadt *fadt) offsetof(struct acpi_table_facs, firmware_waking_vector); } -void tboot_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control) +static int tboot_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control) { static u32 acpi_shutdown_map[ACPI_S_STATE_COUNT] = { /* S0,1,2: */ -1, -1, -1, @@ -281,7 +281,7 @@ void tboot_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control) /* S5: */ TB_SHUTDOWN_S5 }; if (!tboot_enabled()) - return; + return 0; tboot_copy_fadt(&acpi_gbl_FADT); tboot->acpi_sinfo.pm1a_cnt_val = pm1a_control; @@ -292,10 +292,11 @@ void tboot_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control) if (sleep_state >= ACPI_S_STATE_COUNT || acpi_shutdown_map[sleep_state] == -1) { pr_warning("unsupported sleep state 0x%x\n", sleep_state); - return; + return -1; } tboot_shutdown(acpi_shutdown_map[sleep_state]); + return 0; } static atomic_t ap_wfs_count; @@ -345,6 +346,8 @@ static __init int tboot_late_init(void) atomic_set(&ap_wfs_count, 0); register_hotcpu_notifier(&tboot_cpu_notifier); + + acpi_os_set_prepare_sleep(&tboot_sleep); return 0; } diff --git a/arch/x86/kernel/tce_64.c b/arch/x86/kernel/tce_64.c index 9e540fee700..ab40954e113 100644 --- a/arch/x86/kernel/tce_64.c +++ b/arch/x86/kernel/tce_64.c @@ -34,6 +34,7 @@ #include <asm/tce.h> #include <asm/calgary.h> #include <asm/proto.h> +#include <asm/cacheflush.h> /* flush a tce at 'tceaddr' to main memory */ static inline void flush_tce(void* tceaddr) diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index dd5fbf4101f..c6eba2b4267 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -57,9 +57,6 @@ EXPORT_SYMBOL(profile_pc); */ static irqreturn_t timer_interrupt(int irq, void *dev_id) { - /* Keep nmi watchdog up to date */ - inc_irq_stat(irq0_irqs); - global_clock_event->event_handler(global_clock_event); /* MCA bus quirk: Acknowledge irq0 by setting bit 7 in port 0x61 */ diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index 6bb7b8579e7..9d9d2f9e77a 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -6,7 +6,6 @@ #include <asm/uaccess.h> #include <asm/desc.h> -#include <asm/system.h> #include <asm/ldt.h> #include <asm/processor.h> #include <asm/proto.h> @@ -163,7 +162,7 @@ int regset_tls_get(struct task_struct *target, const struct user_regset *regset, { const struct desc_struct *tls; - if (pos > GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) || + if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) || (pos % sizeof(struct user_desc)) != 0 || (count % sizeof(struct user_desc)) != 0) return -EINVAL; @@ -198,7 +197,7 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset, struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES]; const struct user_desc *info; - if (pos > GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) || + if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) || (pos % sizeof(struct user_desc)) != 0 || (count % sizeof(struct user_desc)) != 0) return -EINVAL; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index fa1191fb679..ff9281f1602 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -50,10 +50,10 @@ #include <asm/processor.h> #include <asm/debugreg.h> #include <linux/atomic.h> -#include <asm/system.h> #include <asm/traps.h> #include <asm/desc.h> #include <asm/i387.h> +#include <asm/fpu-internal.h> #include <asm/mce.h> #include <asm/mach_traps.h> @@ -119,7 +119,7 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, * traps 0, 1, 3, 4, and 5 should be forwarded to vm86. * On nmi (interrupt 2), do_trap should not be called. */ - if (trapnr < 6) + if (trapnr < X86_TRAP_UD) goto vm86_trap; goto trap_signal; } @@ -132,7 +132,7 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, trap_signal: #endif /* - * We want error_code and trap_no set for userspace faults and + * We want error_code and trap_nr set for userspace faults and * kernelspace faults which result in die(), but not * kernelspace faults which are fixed up. die() gives the * process no chance to handle the signal and notice the @@ -141,7 +141,7 @@ trap_signal: * delivered, faults. See also do_general_protection below. */ tsk->thread.error_code = error_code; - tsk->thread.trap_no = trapnr; + tsk->thread.trap_nr = trapnr; #ifdef CONFIG_X86_64 if (show_unhandled_signals && unhandled_signal(tsk, signr) && @@ -164,7 +164,7 @@ trap_signal: kernel_trap: if (!fixup_exception(regs)) { tsk->thread.error_code = error_code; - tsk->thread.trap_no = trapnr; + tsk->thread.trap_nr = trapnr; die(str, regs, error_code); } return; @@ -203,27 +203,31 @@ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ do_trap(trapnr, signr, str, regs, error_code, &info); \ } -DO_ERROR_INFO(0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->ip) -DO_ERROR(4, SIGSEGV, "overflow", overflow) -DO_ERROR(5, SIGSEGV, "bounds", bounds) -DO_ERROR_INFO(6, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, regs->ip) -DO_ERROR(9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun) -DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS) -DO_ERROR(11, SIGBUS, "segment not present", segment_not_present) +DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV, + regs->ip) +DO_ERROR(X86_TRAP_OF, SIGSEGV, "overflow", overflow) +DO_ERROR(X86_TRAP_BR, SIGSEGV, "bounds", bounds) +DO_ERROR_INFO(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, + regs->ip) +DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun", + coprocessor_segment_overrun) +DO_ERROR(X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS) +DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present) #ifdef CONFIG_X86_32 -DO_ERROR(12, SIGBUS, "stack segment", stack_segment) +DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment) #endif -DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0) +DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check, + BUS_ADRALN, 0) #ifdef CONFIG_X86_64 /* Runs on IST stack */ dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code) { if (notify_die(DIE_TRAP, "stack segment", regs, error_code, - 12, SIGBUS) == NOTIFY_STOP) + X86_TRAP_SS, SIGBUS) == NOTIFY_STOP) return; preempt_conditional_sti(regs); - do_trap(12, SIGBUS, "stack segment", regs, error_code, NULL); + do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL); preempt_conditional_cli(regs); } @@ -233,10 +237,10 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) struct task_struct *tsk = current; /* Return not checked because double check cannot be ignored */ - notify_die(DIE_TRAP, str, regs, error_code, 8, SIGSEGV); + notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV); tsk->thread.error_code = error_code; - tsk->thread.trap_no = 8; + tsk->thread.trap_nr = X86_TRAP_DF; /* * This is always a kernel trap and never fixable (and thus must @@ -264,7 +268,7 @@ do_general_protection(struct pt_regs *regs, long error_code) goto gp_in_kernel; tsk->thread.error_code = error_code; - tsk->thread.trap_no = 13; + tsk->thread.trap_nr = X86_TRAP_GP; if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) && printk_ratelimit()) { @@ -291,9 +295,9 @@ gp_in_kernel: return; tsk->thread.error_code = error_code; - tsk->thread.trap_no = 13; - if (notify_die(DIE_GPF, "general protection fault", regs, - error_code, 13, SIGSEGV) == NOTIFY_STOP) + tsk->thread.trap_nr = X86_TRAP_GP; + if (notify_die(DIE_GPF, "general protection fault", regs, error_code, + X86_TRAP_GP, SIGSEGV) == NOTIFY_STOP) return; die("general protection fault", regs, error_code); } @@ -302,18 +306,24 @@ gp_in_kernel: dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code) { #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP - if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) - == NOTIFY_STOP) + if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, + SIGTRAP) == NOTIFY_STOP) return; #endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */ - if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) - == NOTIFY_STOP) + if (notify_die(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, + SIGTRAP) == NOTIFY_STOP) return; + /* + * Let others (NMI) know that the debug stack is in use + * as we may switch to the interrupt stack. + */ + debug_stack_usage_inc(); preempt_conditional_sti(regs); - do_trap(3, SIGTRAP, "int3", regs, error_code, NULL); + do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL); preempt_conditional_cli(regs); + debug_stack_usage_dec(); } #ifdef CONFIG_X86_64 @@ -406,13 +416,20 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) SIGTRAP) == NOTIFY_STOP) return; + /* + * Let others (NMI) know that the debug stack is in use + * as we may switch to the interrupt stack. + */ + debug_stack_usage_inc(); + /* It's safe to allow irq's after DR6 has been saved */ preempt_conditional_sti(regs); if (regs->flags & X86_VM_MASK) { - handle_vm86_trap((struct kernel_vm86_regs *) regs, - error_code, 1); + handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, + X86_TRAP_DB); preempt_conditional_cli(regs); + debug_stack_usage_dec(); return; } @@ -432,6 +449,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp) send_sigtrap(tsk, regs, error_code, si_code); preempt_conditional_cli(regs); + debug_stack_usage_dec(); return; } @@ -446,7 +464,8 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr) struct task_struct *task = current; siginfo_t info; unsigned short err; - char *str = (trapnr == 16) ? "fpu exception" : "simd exception"; + char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" : + "simd exception"; if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, SIGFPE) == NOTIFY_STOP) return; @@ -456,7 +475,7 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr) { if (!fixup_exception(regs)) { task->thread.error_code = error_code; - task->thread.trap_no = trapnr; + task->thread.trap_nr = trapnr; die(str, regs, error_code); } return; @@ -466,12 +485,12 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr) * Save the info for the exception handler and clear the error. */ save_init_fpu(task); - task->thread.trap_no = trapnr; + task->thread.trap_nr = trapnr; task->thread.error_code = error_code; info.si_signo = SIGFPE; info.si_errno = 0; info.si_addr = (void __user *)regs->ip; - if (trapnr == 16) { + if (trapnr == X86_TRAP_MF) { unsigned short cwd, swd; /* * (~cwd & swd) will mask out exceptions that are not set to unmasked @@ -515,10 +534,11 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr) info.si_code = FPE_FLTRES; } else { /* - * If we're using IRQ 13, or supposedly even some trap 16 - * implementations, it's possible we get a spurious trap... + * If we're using IRQ 13, or supposedly even some trap + * X86_TRAP_MF implementations, it's possible + * we get a spurious trap, which is not an error. */ - return; /* Spurious trap, no error */ + return; } force_sig_info(SIGFPE, &info, task); } @@ -529,13 +549,13 @@ dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code) ignore_fpu_irq = 1; #endif - math_error(regs, error_code, 16); + math_error(regs, error_code, X86_TRAP_MF); } dotraplinkage void do_simd_coprocessor_error(struct pt_regs *regs, long error_code) { - math_error(regs, error_code, 19); + math_error(regs, error_code, X86_TRAP_XF); } dotraplinkage void @@ -557,41 +577,18 @@ asmlinkage void __attribute__((weak)) smp_threshold_interrupt(void) } /* - * __math_state_restore assumes that cr0.TS is already clear and the - * fpu state is all ready for use. Used during context switch. - */ -void __math_state_restore(void) -{ - struct thread_info *thread = current_thread_info(); - struct task_struct *tsk = thread->task; - - /* - * Paranoid restore. send a SIGSEGV if we fail to restore the state. - */ - if (unlikely(restore_fpu_checking(tsk))) { - stts(); - force_sig(SIGSEGV, tsk); - return; - } - - thread->status |= TS_USEDFPU; /* So we fnsave on switch_to() */ - tsk->fpu_counter++; -} - -/* * 'math_state_restore()' saves the current math information in the * old math state array, and gets the new ones from the current task * * Careful.. There are problems with IBM-designed IRQ13 behaviour. * Don't touch unless you *really* know how it works. * - * Must be called with kernel preemption disabled (in this case, - * local interrupts are disabled at the call-site in entry.S). + * Must be called with kernel preemption disabled (eg with local + * local interrupts as in the case of do_device_not_available). */ -asmlinkage void math_state_restore(void) +void math_state_restore(void) { - struct thread_info *thread = current_thread_info(); - struct task_struct *tsk = thread->task; + struct task_struct *tsk = current; if (!tsk_used_math(tsk)) { local_irq_enable(); @@ -608,9 +605,17 @@ asmlinkage void math_state_restore(void) local_irq_disable(); } - clts(); /* Allow maths ops (or we recurse) */ + __thread_fpu_begin(tsk); + /* + * Paranoid restore. send a SIGSEGV if we fail to restore the state. + */ + if (unlikely(restore_fpu_checking(tsk))) { + __thread_fpu_end(tsk); + force_sig(SIGSEGV, tsk); + return; + } - __math_state_restore(); + tsk->fpu_counter++; } EXPORT_SYMBOL_GPL(math_state_restore); @@ -644,20 +649,21 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) info.si_errno = 0; info.si_code = ILL_BADSTK; info.si_addr = NULL; - if (notify_die(DIE_TRAP, "iret exception", - regs, error_code, 32, SIGILL) == NOTIFY_STOP) + if (notify_die(DIE_TRAP, "iret exception", regs, error_code, + X86_TRAP_IRET, SIGILL) == NOTIFY_STOP) return; - do_trap(32, SIGILL, "iret exception", regs, error_code, &info); + do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code, + &info); } #endif /* Set of traps needed for early debugging. */ void __init early_trap_init(void) { - set_intr_gate_ist(1, &debug, DEBUG_STACK); + set_intr_gate_ist(X86_TRAP_DB, &debug, DEBUG_STACK); /* int3 can be called from all */ - set_system_intr_gate_ist(3, &int3, DEBUG_STACK); - set_intr_gate(14, &page_fault); + set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK); + set_intr_gate(X86_TRAP_PF, &page_fault); load_idt(&idt_descr); } @@ -673,30 +679,30 @@ void __init trap_init(void) early_iounmap(p, 4); #endif - set_intr_gate(0, ÷_error); - set_intr_gate_ist(2, &nmi, NMI_STACK); + set_intr_gate(X86_TRAP_DE, ÷_error); + set_intr_gate_ist(X86_TRAP_NMI, &nmi, NMI_STACK); /* int4 can be called from all */ - set_system_intr_gate(4, &overflow); - set_intr_gate(5, &bounds); - set_intr_gate(6, &invalid_op); - set_intr_gate(7, &device_not_available); + set_system_intr_gate(X86_TRAP_OF, &overflow); + set_intr_gate(X86_TRAP_BR, &bounds); + set_intr_gate(X86_TRAP_UD, &invalid_op); + set_intr_gate(X86_TRAP_NM, &device_not_available); #ifdef CONFIG_X86_32 - set_task_gate(8, GDT_ENTRY_DOUBLEFAULT_TSS); + set_task_gate(X86_TRAP_DF, GDT_ENTRY_DOUBLEFAULT_TSS); #else - set_intr_gate_ist(8, &double_fault, DOUBLEFAULT_STACK); + set_intr_gate_ist(X86_TRAP_DF, &double_fault, DOUBLEFAULT_STACK); #endif - set_intr_gate(9, &coprocessor_segment_overrun); - set_intr_gate(10, &invalid_TSS); - set_intr_gate(11, &segment_not_present); - set_intr_gate_ist(12, &stack_segment, STACKFAULT_STACK); - set_intr_gate(13, &general_protection); - set_intr_gate(15, &spurious_interrupt_bug); - set_intr_gate(16, &coprocessor_error); - set_intr_gate(17, &alignment_check); + set_intr_gate(X86_TRAP_OLD_MF, &coprocessor_segment_overrun); + set_intr_gate(X86_TRAP_TS, &invalid_TSS); + set_intr_gate(X86_TRAP_NP, &segment_not_present); + set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK); + set_intr_gate(X86_TRAP_GP, &general_protection); + set_intr_gate(X86_TRAP_SPURIOUS, &spurious_interrupt_bug); + set_intr_gate(X86_TRAP_MF, &coprocessor_error); + set_intr_gate(X86_TRAP_AC, &alignment_check); #ifdef CONFIG_X86_MCE - set_intr_gate_ist(18, &machine_check, MCE_STACK); + set_intr_gate_ist(X86_TRAP_MC, &machine_check, MCE_STACK); #endif - set_intr_gate(19, &simd_coprocessor_error); + set_intr_gate(X86_TRAP_XF, &simd_coprocessor_error); /* Reserve all the builtin and the syscall vector: */ for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++) @@ -718,4 +724,10 @@ void __init trap_init(void) cpu_init(); x86_init.irqs.trap_init(); + +#ifdef CONFIG_X86_64 + memcpy(&nmi_idt_table, &idt_table, IDT_ENTRIES * 16); + set_nmi_gate(X86_TRAP_DB, &debug); + set_nmi_gate(X86_TRAP_BP, &int3); +#endif } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 2c9cf0fd78f..fc0a147e372 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -290,14 +290,15 @@ static inline int pit_verify_msb(unsigned char val) static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *deltap) { int count; - u64 tsc = 0; + u64 tsc = 0, prev_tsc = 0; for (count = 0; count < 50000; count++) { if (!pit_verify_msb(val)) break; + prev_tsc = tsc; tsc = get_cycles(); } - *deltap = get_cycles() - tsc; + *deltap = get_cycles() - prev_tsc; *tscp = tsc; /* @@ -311,9 +312,9 @@ static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *de * How many MSB values do we want to see? We aim for * a maximum error rate of 500ppm (in practice the * real error is much smaller), but refuse to spend - * more than 25ms on it. + * more than 50ms on it. */ -#define MAX_QUICK_PIT_MS 25 +#define MAX_QUICK_PIT_MS 50 #define MAX_QUICK_PIT_ITERATIONS (MAX_QUICK_PIT_MS * PIT_TICK_RATE / 1000 / 256) static unsigned long quick_pit_calibrate(void) @@ -383,15 +384,12 @@ success: * * As a result, we can depend on there not being * any odd delays anywhere, and the TSC reads are - * reliable (within the error). We also adjust the - * delta to the middle of the error bars, just - * because it looks nicer. + * reliable (within the error). * * kHz = ticks / time-in-seconds / 1000; * kHz = (t2 - t1) / (I * 256 / PIT_TICK_RATE) / 1000 * kHz = ((t2 - t1) * PIT_TICK_RATE) / (I * 256 * 1000) */ - delta += (long)(d2 - d1)/2; delta *= PIT_TICK_RATE; do_div(delta, i*256*1000); printk("Fast TSC calibration using PIT\n"); @@ -622,7 +620,8 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) if (cpu_khz) { *scale = (NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR)/cpu_khz; - *offset = ns_now - (tsc_now * *scale >> CYC2NS_SCALE_FACTOR); + *offset = ns_now - mult_frac(tsc_now, *scale, + (1UL << CYC2NS_SCALE_FACTOR)); } sched_clock_idle_wakeup_event(0); @@ -631,7 +630,7 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) static unsigned long long cyc2ns_suspend; -void save_sched_clock_state(void) +void tsc_save_sched_clock_state(void) { if (!sched_clock_stable) return; @@ -647,7 +646,7 @@ void save_sched_clock_state(void) * that sched_clock() continues from the point where it was left off during * suspend. */ -void restore_sched_clock_state(void) +void tsc_restore_sched_clock_state(void) { unsigned long long offset; unsigned long flags; @@ -934,6 +933,16 @@ static int __init init_tsc_clocksource(void) clocksource_tsc.rating = 0; clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS; } + + /* + * Trust the results of the earlier calibration on systems + * exporting a reliable TSC. + */ + if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) { + clocksource_register_khz(&clocksource_tsc, tsc_khz); + return 0; + } + schedule_delayed_work(&tsc_irqwork, 0); return 0; } @@ -995,3 +1004,23 @@ void __init tsc_init(void) check_system_tsc_reliable(); } +#ifdef CONFIG_SMP +/* + * If we have a constant TSC and are using the TSC for the delay loop, + * we can skip clock calibration if another cpu in the same socket has already + * been calibrated. This assumes that CONSTANT_TSC applies to all + * cpus in the socket - this should be a safe assumption. + */ +unsigned long __cpuinit calibrate_delay_is_known(void) +{ + int i, cpu = smp_processor_id(); + + if (!tsc_disabled && !cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC)) + return 0; + + for_each_online_cpu(i) + if (cpu_data(i).phys_proc_id == cpu_data(cpu).phys_proc_id) + return cpu_data(i).loops_per_jiffy; + return 0; +} +#endif diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 9eba29b46cb..fc25e60a588 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -42,7 +42,7 @@ static __cpuinitdata int nr_warps; /* * TSC-warp measurement loop running on both CPUs: */ -static __cpuinit void check_tsc_warp(void) +static __cpuinit void check_tsc_warp(unsigned int timeout) { cycles_t start, now, prev, end; int i; @@ -51,9 +51,9 @@ static __cpuinit void check_tsc_warp(void) start = get_cycles(); rdtsc_barrier(); /* - * The measurement runs for 20 msecs: + * The measurement runs for 'timeout' msecs: */ - end = start + tsc_khz * 20ULL; + end = start + (cycles_t) tsc_khz * timeout; now = start; for (i = 0; ; i++) { @@ -99,6 +99,25 @@ static __cpuinit void check_tsc_warp(void) } /* + * If the target CPU coming online doesn't have any of its core-siblings + * online, a timeout of 20msec will be used for the TSC-warp measurement + * loop. Otherwise a smaller timeout of 2msec will be used, as we have some + * information about this socket already (and this information grows as we + * have more and more logical-siblings in that socket). + * + * Ideally we should be able to skip the TSC sync check on the other + * core-siblings, if the first logical CPU in a socket passed the sync test. + * But as the TSC is per-logical CPU and can potentially be modified wrongly + * by the bios, TSC sync test for smaller duration should be able + * to catch such errors. Also this will catch the condition where all the + * cores in the socket doesn't get reset at the same time. + */ +static inline unsigned int loop_timeout(int cpu) +{ + return (cpumask_weight(cpu_core_mask(cpu)) > 1) ? 2 : 20; +} + +/* * Source CPU calls into this - it waits for the freshly booted * target CPU to arrive and then starts the measurement: */ @@ -135,7 +154,7 @@ void __cpuinit check_tsc_sync_source(int cpu) */ atomic_inc(&start_count); - check_tsc_warp(); + check_tsc_warp(loop_timeout(cpu)); while (atomic_read(&stop_count) != cpus-1) cpu_relax(); @@ -183,7 +202,7 @@ void __cpuinit check_tsc_sync_target(void) while (atomic_read(&start_count) != cpus) cpu_relax(); - check_tsc_warp(); + check_tsc_warp(loop_timeout(smp_processor_id())); /* * Ok, we are done: diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 863f8753ab0..255f58ae71e 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -172,6 +172,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) spinlock_t *ptl; int i; + down_write(&mm->mmap_sem); pgd = pgd_offset(mm, 0xA0000); if (pgd_none_or_clear_bad(pgd)) goto out; @@ -190,6 +191,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) } pte_unmap_unlock(pte, ptl); out: + up_write(&mm->mmap_sem); flush_tlb(); } @@ -335,9 +337,11 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk if (info->flags & VM86_SCREEN_BITMAP) mark_screen_rdonly(tsk->mm); - /*call audit_syscall_exit since we do not exit via the normal paths */ + /*call __audit_syscall_exit since we do not exit via the normal paths */ +#ifdef CONFIG_AUDITSYSCALL if (unlikely(current->audit_context)) - audit_syscall_exit(AUDITSC_RESULT(0), 0); + __audit_syscall_exit(1, 0); +#endif __asm__ __volatile__( "movl %0,%%esp\n\t" @@ -565,7 +569,7 @@ int handle_vm86_trap(struct kernel_vm86_regs *regs, long error_code, int trapno) } if (trapno != 1) return 1; /* we let this handle by the calling routine */ - current->thread.trap_no = trapno; + current->thread.trap_nr = trapno; current->thread.error_code = error_code; force_sig(SIGTRAP, current); return 0; diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index b07ba939356..7515cf0e180 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -52,10 +52,7 @@ #include "vsyscall_trace.h" DEFINE_VVAR(int, vgetcpu_mode); -DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data) = -{ - .lock = __SEQLOCK_UNLOCKED(__vsyscall_gtod_data.lock), -}; +DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data); static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE; @@ -80,20 +77,15 @@ early_param("vsyscall", vsyscall_setup); void update_vsyscall_tz(void) { - unsigned long flags; - - write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags); - /* sys_tz has changed */ vsyscall_gtod_data.sys_tz = sys_tz; - write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags); } void update_vsyscall(struct timespec *wall_time, struct timespec *wtm, struct clocksource *clock, u32 mult) { - unsigned long flags; + struct timespec monotonic; - write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags); + write_seqcount_begin(&vsyscall_gtod_data.seq); /* copy vsyscall data */ vsyscall_gtod_data.clock.vclock_mode = clock->archdata.vclock_mode; @@ -101,12 +93,19 @@ void update_vsyscall(struct timespec *wall_time, struct timespec *wtm, vsyscall_gtod_data.clock.mask = clock->mask; vsyscall_gtod_data.clock.mult = mult; vsyscall_gtod_data.clock.shift = clock->shift; + vsyscall_gtod_data.wall_time_sec = wall_time->tv_sec; vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec; - vsyscall_gtod_data.wall_to_monotonic = *wtm; + + monotonic = timespec_add(*wall_time, *wtm); + vsyscall_gtod_data.monotonic_time_sec = monotonic.tv_sec; + vsyscall_gtod_data.monotonic_time_nsec = monotonic.tv_nsec; + vsyscall_gtod_data.wall_time_coarse = __current_kernel_time(); + vsyscall_gtod_data.monotonic_time_coarse = + timespec_add(vsyscall_gtod_data.wall_time_coarse, *wtm); - write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags); + write_seqcount_end(&vsyscall_gtod_data.seq); } static void warn_bad_vsyscall(const char *level, struct pt_regs *regs, @@ -153,7 +152,7 @@ static bool write_ok_or_segv(unsigned long ptr, size_t size) thread->error_code = 6; /* user fault, no page, write */ thread->cr2 = ptr; - thread->trap_no = 14; + thread->trap_nr = X86_TRAP_PF; memset(&info, 0, sizeof(info)); info.si_signo = SIGSEGV; @@ -217,9 +216,9 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) current_thread_info()->sig_on_uaccess_error = 1; /* - * 0 is a valid user pointer (in the access_ok sense) on 32-bit and + * NULL is a valid user pointer (in the access_ok sense) on 32-bit and * 64-bit, so we don't need to special-case it here. For all the - * vsyscalls, 0 means "don't write anything" not "write it at + * vsyscalls, NULL means "don't write anything" not "write it at * address 0". */ ret = -EFAULT; @@ -248,7 +247,7 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) ret = sys_getcpu((unsigned __user *)regs->di, (unsigned __user *)regs->si, - 0); + NULL); break; } diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 947a06ccc67..e9f265fd79a 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -91,6 +91,7 @@ struct x86_init_ops x86_init __initdata = { }; struct x86_cpuinit_ops x86_cpuinit __cpuinitdata = { + .early_percpu_clock_init = x86_init_noop, .setup_percpu_clockev = setup_secondary_APIC_clock, .fixup_cpu_id = x86_default_fixup_cpu_id, }; @@ -107,7 +108,9 @@ struct x86_platform_ops x86_platform = { .is_untracked_pat_range = is_ISA_range, .nmi_init = default_nmi_init, .get_nmi_reason = default_get_nmi_reason, - .i8042_detect = default_i8042_detect + .i8042_detect = default_i8042_detect, + .save_sched_clock_state = tsc_save_sched_clock_state, + .restore_sched_clock_state = tsc_restore_sched_clock_state, }; EXPORT_SYMBOL_GPL(x86_platform); diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index a3911343976..e62728e30b0 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -6,6 +6,7 @@ #include <linux/bootmem.h> #include <linux/compat.h> #include <asm/i387.h> +#include <asm/fpu-internal.h> #ifdef CONFIG_IA32_EMULATION #include <asm/sigcontext32.h> #endif @@ -47,7 +48,7 @@ void __sanitize_i387_state(struct task_struct *tsk) if (!fx) return; - BUG_ON(task_thread_info(tsk)->status & TS_USEDFPU); + BUG_ON(__thread_has_fpu(tsk)); xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv; @@ -168,7 +169,7 @@ int save_i387_xstate(void __user *buf) if (!used_math()) return 0; - if (task_thread_info(tsk)->status & TS_USEDFPU) { + if (user_has_fpu()) { if (use_xsave()) err = xsave_user(buf); else @@ -176,8 +177,7 @@ int save_i387_xstate(void __user *buf) if (err) return err; - task_thread_info(tsk)->status &= ~TS_USEDFPU; - stts(); + user_fpu_end(); } else { sanitize_i387_state(tsk); if (__copy_to_user(buf, &tsk->thread.fpu.state->fxsave, @@ -292,10 +292,7 @@ int restore_i387_xstate(void __user *buf) return err; } - if (!(task_thread_info(current)->status & TS_USEDFPU)) { - clts(); - task_thread_info(current)->status |= TS_USEDFPU; - } + user_fpu_begin(); if (use_xsave()) err = restore_user_xstate(buf); else diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 89b02bfaaca..9fed5bedaad 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -236,7 +236,7 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, const u32 kvm_supported_word6_x86_features = F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ | F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) | - F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(XOP) | + F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) | 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM); /* cpuid 0xC0000001.edx */ diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 5b97e1797a6..26d1fb437eb 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -43,4 +43,12 @@ static inline bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu) return best && (best->ebx & bit(X86_FEATURE_FSGSBASE)); } +static inline bool guest_cpuid_has_osvw(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); + return best && (best->ecx & bit(X86_FEATURE_OSVW)); +} + #endif diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 05a562b8502..83756223f8a 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -57,6 +57,7 @@ #define OpDS 23ull /* DS */ #define OpFS 24ull /* FS */ #define OpGS 25ull /* GS */ +#define OpMem8 26ull /* 8-bit zero extended memory operand */ #define OpBits 5 /* Width of operand field */ #define OpMask ((1ull << OpBits) - 1) @@ -101,6 +102,7 @@ #define SrcAcc (OpAcc << SrcShift) #define SrcImmU16 (OpImmU16 << SrcShift) #define SrcDX (OpDX << SrcShift) +#define SrcMem8 (OpMem8 << SrcShift) #define SrcMask (OpMask << SrcShift) #define BitOp (1<<11) #define MemAbs (1<<12) /* Memory operand is absolute displacement */ @@ -858,8 +860,7 @@ static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, } static void decode_register_operand(struct x86_emulate_ctxt *ctxt, - struct operand *op, - int inhibit_bytereg) + struct operand *op) { unsigned reg = ctxt->modrm_reg; int highbyte_regs = ctxt->rex_prefix == 0; @@ -876,7 +877,7 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt, } op->type = OP_REG; - if ((ctxt->d & ByteOp) && !inhibit_bytereg) { + if (ctxt->d & ByteOp) { op->addr.reg = decode_register(reg, ctxt->regs, highbyte_regs); op->bytes = 1; } else { @@ -1151,6 +1152,22 @@ static int pio_in_emulated(struct x86_emulate_ctxt *ctxt, return 1; } +static int read_interrupt_descriptor(struct x86_emulate_ctxt *ctxt, + u16 index, struct desc_struct *desc) +{ + struct desc_ptr dt; + ulong addr; + + ctxt->ops->get_idt(ctxt, &dt); + + if (dt.size < index * 8 + 7) + return emulate_gp(ctxt, index << 3 | 0x2); + + addr = dt.address + index * 8; + return ctxt->ops->read_std(ctxt, addr, desc, sizeof *desc, + &ctxt->exception); +} + static void get_descriptor_table_ptr(struct x86_emulate_ctxt *ctxt, u16 selector, struct desc_ptr *dt) { @@ -1227,6 +1244,8 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, seg_desc.type = 3; seg_desc.p = 1; seg_desc.s = 1; + if (ctxt->mode == X86EMUL_MODE_VM86) + seg_desc.dpl = 3; goto load; } @@ -1891,6 +1910,62 @@ setup_syscalls_segments(struct x86_emulate_ctxt *ctxt, ss->p = 1; } +static bool vendor_intel(struct x86_emulate_ctxt *ctxt) +{ + u32 eax, ebx, ecx, edx; + + eax = ecx = 0; + return ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx) + && ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx + && ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx + && edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx; +} + +static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt) +{ + struct x86_emulate_ops *ops = ctxt->ops; + u32 eax, ebx, ecx, edx; + + /* + * syscall should always be enabled in longmode - so only become + * vendor specific (cpuid) if other modes are active... + */ + if (ctxt->mode == X86EMUL_MODE_PROT64) + return true; + + eax = 0x00000000; + ecx = 0x00000000; + if (ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx)) { + /* + * Intel ("GenuineIntel") + * remark: Intel CPUs only support "syscall" in 64bit + * longmode. Also an 64bit guest with a + * 32bit compat-app running will #UD !! While this + * behaviour can be fixed (by emulating) into AMD + * response - CPUs of AMD can't behave like Intel. + */ + if (ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx && + ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx && + edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx) + return false; + + /* AMD ("AuthenticAMD") */ + if (ebx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx && + ecx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx && + edx == X86EMUL_CPUID_VENDOR_AuthenticAMD_edx) + return true; + + /* AMD ("AMDisbetter!") */ + if (ebx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx && + ecx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx && + edx == X86EMUL_CPUID_VENDOR_AMDisbetterI_edx) + return true; + } + + /* default: (not Intel, not AMD), apply Intel's stricter rules... */ + return false; +} + static int em_syscall(struct x86_emulate_ctxt *ctxt) { struct x86_emulate_ops *ops = ctxt->ops; @@ -1904,9 +1979,15 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt) ctxt->mode == X86EMUL_MODE_VM86) return emulate_ud(ctxt); + if (!(em_syscall_is_enabled(ctxt))) + return emulate_ud(ctxt); + ops->get_msr(ctxt, MSR_EFER, &efer); setup_syscalls_segments(ctxt, &cs, &ss); + if (!(efer & EFER_SCE)) + return emulate_ud(ctxt); + ops->get_msr(ctxt, MSR_STAR, &msr_data); msr_data >>= 32; cs_sel = (u16)(msr_data & 0xfffc); @@ -1956,6 +2037,14 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt) if (ctxt->mode == X86EMUL_MODE_REAL) return emulate_gp(ctxt, 0); + /* + * Not recognized on AMD in compat mode (but is recognized in legacy + * mode). + */ + if ((ctxt->mode == X86EMUL_MODE_PROT32) && (efer & EFER_LMA) + && !vendor_intel(ctxt)) + return emulate_ud(ctxt); + /* XXX sysenter/sysexit have not been tested in 64bit mode. * Therefore, we inject an #UD. */ @@ -2255,6 +2344,8 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, return emulate_gp(ctxt, 0); ctxt->_eip = tss->eip; ctxt->eflags = tss->eflags | 2; + + /* General purpose registers */ ctxt->regs[VCPU_REGS_RAX] = tss->eax; ctxt->regs[VCPU_REGS_RCX] = tss->ecx; ctxt->regs[VCPU_REGS_RDX] = tss->edx; @@ -2277,6 +2368,24 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, set_segment_selector(ctxt, tss->gs, VCPU_SREG_GS); /* + * If we're switching between Protected Mode and VM86, we need to make + * sure to update the mode before loading the segment descriptors so + * that the selectors are interpreted correctly. + * + * Need to get rflags to the vcpu struct immediately because it + * influences the CPL which is checked at least when loading the segment + * descriptors and when pushing an error code to the new kernel stack. + * + * TODO Introduce a separate ctxt->ops->set_cpl callback + */ + if (ctxt->eflags & X86_EFLAGS_VM) + ctxt->mode = X86EMUL_MODE_VM86; + else + ctxt->mode = X86EMUL_MODE_PROT32; + + ctxt->ops->set_rflags(ctxt, ctxt->eflags); + + /* * Now load segment descriptors. If fault happenes at this stage * it is handled in a context of new task */ @@ -2350,7 +2459,7 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt, } static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, - u16 tss_selector, int reason, + u16 tss_selector, int idt_index, int reason, bool has_error_code, u32 error_code) { struct x86_emulate_ops *ops = ctxt->ops; @@ -2372,12 +2481,35 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, /* FIXME: check that next_tss_desc is tss */ - if (reason != TASK_SWITCH_IRET) { - if ((tss_selector & 3) > next_tss_desc.dpl || - ops->cpl(ctxt) > next_tss_desc.dpl) - return emulate_gp(ctxt, 0); + /* + * Check privileges. The three cases are task switch caused by... + * + * 1. jmp/call/int to task gate: Check against DPL of the task gate + * 2. Exception/IRQ/iret: No check is performed + * 3. jmp/call to TSS: Check agains DPL of the TSS + */ + if (reason == TASK_SWITCH_GATE) { + if (idt_index != -1) { + /* Software interrupts */ + struct desc_struct task_gate_desc; + int dpl; + + ret = read_interrupt_descriptor(ctxt, idt_index, + &task_gate_desc); + if (ret != X86EMUL_CONTINUE) + return ret; + + dpl = task_gate_desc.dpl; + if ((tss_selector & 3) > dpl || ops->cpl(ctxt) > dpl) + return emulate_gp(ctxt, (idt_index << 3) | 0x2); + } + } else if (reason != TASK_SWITCH_IRET) { + int dpl = next_tss_desc.dpl; + if ((tss_selector & 3) > dpl || ops->cpl(ctxt) > dpl) + return emulate_gp(ctxt, tss_selector); } + desc_limit = desc_limit_scaled(&next_tss_desc); if (!next_tss_desc.p || ((desc_limit < 0x67 && (next_tss_desc.type & 8)) || @@ -2430,7 +2562,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, } int emulator_task_switch(struct x86_emulate_ctxt *ctxt, - u16 tss_selector, int reason, + u16 tss_selector, int idt_index, int reason, bool has_error_code, u32 error_code) { int rc; @@ -2438,7 +2570,7 @@ int emulator_task_switch(struct x86_emulate_ctxt *ctxt, ctxt->_eip = ctxt->eip; ctxt->dst.type = OP_NONE; - rc = emulator_do_task_switch(ctxt, tss_selector, reason, + rc = emulator_do_task_switch(ctxt, tss_selector, idt_index, reason, has_error_code, error_code); if (rc == X86EMUL_CONTINUE) @@ -3463,13 +3595,13 @@ static struct opcode twobyte_table[256] = { I(DstMem | SrcReg | ModRM | BitOp | Lock, em_btr), I(DstReg | SrcMemFAddr | ModRM | Src2FS, em_lseg), I(DstReg | SrcMemFAddr | ModRM | Src2GS, em_lseg), - D(ByteOp | DstReg | SrcMem | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), + D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xB8 - 0xBF */ N, N, G(BitOp, group8), I(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc), I(DstReg | SrcMem | ModRM, em_bsf), I(DstReg | SrcMem | ModRM, em_bsr), - D(ByteOp | DstReg | SrcMem | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), + D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xC0 - 0xCF */ D2bv(DstMem | SrcReg | ModRM | Lock), N, D(DstMem | SrcReg | ModRM | Mov), @@ -3551,9 +3683,7 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op, switch (d) { case OpReg: - decode_register_operand(ctxt, op, - op == &ctxt->dst && - ctxt->twobyte && (ctxt->b == 0xb6 || ctxt->b == 0xb7)); + decode_register_operand(ctxt, op); break; case OpImmUByte: rc = decode_imm(ctxt, op, 1, false); @@ -3605,6 +3735,9 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op, case OpImm: rc = decode_imm(ctxt, op, imm_size(ctxt), true); break; + case OpMem8: + ctxt->memop.bytes = 1; + goto mem_common; case OpMem16: ctxt->memop.bytes = 2; goto mem_common; diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index b6a73537e1e..81cf4fa4a2b 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -307,6 +307,7 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val) if (val & 0x10) { s->init4 = val & 1; s->last_irr = 0; + s->irr &= s->elcr; s->imr = 0; s->priority_add = 0; s->special_mask = 0; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index cfdc6e0ef00..858432287ab 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -433,7 +433,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, break; case APIC_DM_INIT: - if (level) { + if (!trig_mode || level) { result = 1; vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED; kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -731,7 +731,7 @@ static void start_apic_timer(struct kvm_lapic *apic) u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline; u64 ns = 0; struct kvm_vcpu *vcpu = apic->vcpu; - unsigned long this_tsc_khz = vcpu_tsc_khz(vcpu); + unsigned long this_tsc_khz = vcpu->arch.virtual_tsc_khz; unsigned long flags; if (unlikely(!tscdeadline || !this_tsc_khz)) @@ -1283,9 +1283,9 @@ void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu) if (!irqchip_in_kernel(vcpu->kvm) || !vcpu->arch.apic->vapic_addr) return; - vapic = kmap_atomic(vcpu->arch.apic->vapic_page, KM_USER0); + vapic = kmap_atomic(vcpu->arch.apic->vapic_page); data = *(u32 *)(vapic + offset_in_page(vcpu->arch.apic->vapic_addr)); - kunmap_atomic(vapic, KM_USER0); + kunmap_atomic(vapic); apic_set_tpr(vcpu->arch.apic, data & 0xff); } @@ -1310,9 +1310,9 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu) max_isr = 0; data = (tpr & 0xff) | ((max_isr & 0xf0) << 8) | (max_irr << 24); - vapic = kmap_atomic(vcpu->arch.apic->vapic_page, KM_USER0); + vapic = kmap_atomic(vcpu->arch.apic->vapic_page); *(u32 *)(vapic + offset_in_page(vcpu->arch.apic->vapic_addr)) = data; - kunmap_atomic(vapic, KM_USER0); + kunmap_atomic(vapic); } void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 2a2a9b40db1..4cb16426884 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -74,7 +74,7 @@ enum { #endif #ifdef MMU_DEBUG -static int dbg = 0; +static bool dbg = 0; module_param(dbg, bool, 0644); #endif @@ -688,9 +688,8 @@ static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn, { unsigned long idx; - idx = (gfn >> KVM_HPAGE_GFN_SHIFT(level)) - - (slot->base_gfn >> KVM_HPAGE_GFN_SHIFT(level)); - return &slot->lpage_info[level - 2][idx]; + idx = gfn_to_index(gfn, slot->base_gfn, level); + return &slot->arch.lpage_info[level - 2][idx]; } static void account_shadowed(struct kvm *kvm, gfn_t gfn) @@ -946,7 +945,7 @@ static void pte_list_walk(unsigned long *pte_list, pte_list_walk_fn fn) } } -static unsigned long *__gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level, +static unsigned long *__gfn_to_rmap(gfn_t gfn, int level, struct kvm_memory_slot *slot) { struct kvm_lpage_info *linfo; @@ -966,7 +965,7 @@ static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level) struct kvm_memory_slot *slot; slot = gfn_to_memslot(kvm, gfn); - return __gfn_to_rmap(kvm, gfn, level, slot); + return __gfn_to_rmap(gfn, level, slot); } static bool rmap_can_add(struct kvm_vcpu *vcpu) @@ -988,7 +987,7 @@ static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) return pte_list_add(vcpu, spte, rmapp); } -static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte) +static u64 *rmap_next(unsigned long *rmapp, u64 *spte) { return pte_list_next(rmapp, spte); } @@ -1018,8 +1017,8 @@ int kvm_mmu_rmap_write_protect(struct kvm *kvm, u64 gfn, u64 *spte; int i, write_protected = 0; - rmapp = __gfn_to_rmap(kvm, gfn, PT_PAGE_TABLE_LEVEL, slot); - spte = rmap_next(kvm, rmapp, NULL); + rmapp = __gfn_to_rmap(gfn, PT_PAGE_TABLE_LEVEL, slot); + spte = rmap_next(rmapp, NULL); while (spte) { BUG_ON(!(*spte & PT_PRESENT_MASK)); rmap_printk("rmap_write_protect: spte %p %llx\n", spte, *spte); @@ -1027,14 +1026,14 @@ int kvm_mmu_rmap_write_protect(struct kvm *kvm, u64 gfn, mmu_spte_update(spte, *spte & ~PT_WRITABLE_MASK); write_protected = 1; } - spte = rmap_next(kvm, rmapp, spte); + spte = rmap_next(rmapp, spte); } /* check for huge page mappings */ for (i = PT_DIRECTORY_LEVEL; i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { - rmapp = __gfn_to_rmap(kvm, gfn, i, slot); - spte = rmap_next(kvm, rmapp, NULL); + rmapp = __gfn_to_rmap(gfn, i, slot); + spte = rmap_next(rmapp, NULL); while (spte) { BUG_ON(!(*spte & PT_PRESENT_MASK)); BUG_ON(!is_large_pte(*spte)); @@ -1045,7 +1044,7 @@ int kvm_mmu_rmap_write_protect(struct kvm *kvm, u64 gfn, spte = NULL; write_protected = 1; } - spte = rmap_next(kvm, rmapp, spte); + spte = rmap_next(rmapp, spte); } } @@ -1066,7 +1065,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, u64 *spte; int need_tlb_flush = 0; - while ((spte = rmap_next(kvm, rmapp, NULL))) { + while ((spte = rmap_next(rmapp, NULL))) { BUG_ON(!(*spte & PT_PRESENT_MASK)); rmap_printk("kvm_rmap_unmap_hva: spte %p %llx\n", spte, *spte); drop_spte(kvm, spte); @@ -1085,14 +1084,14 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, WARN_ON(pte_huge(*ptep)); new_pfn = pte_pfn(*ptep); - spte = rmap_next(kvm, rmapp, NULL); + spte = rmap_next(rmapp, NULL); while (spte) { BUG_ON(!is_shadow_present_pte(*spte)); rmap_printk("kvm_set_pte_rmapp: spte %p %llx\n", spte, *spte); need_flush = 1; if (pte_write(*ptep)) { drop_spte(kvm, spte); - spte = rmap_next(kvm, rmapp, NULL); + spte = rmap_next(rmapp, NULL); } else { new_spte = *spte &~ (PT64_BASE_ADDR_MASK); new_spte |= (u64)new_pfn << PAGE_SHIFT; @@ -1102,7 +1101,7 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, new_spte &= ~shadow_accessed_mask; mmu_spte_clear_track_bits(spte); mmu_spte_set(spte, new_spte); - spte = rmap_next(kvm, rmapp, spte); + spte = rmap_next(rmapp, spte); } } if (need_flush) @@ -1176,7 +1175,7 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, if (!shadow_accessed_mask) return kvm_unmap_rmapp(kvm, rmapp, data); - spte = rmap_next(kvm, rmapp, NULL); + spte = rmap_next(rmapp, NULL); while (spte) { int _young; u64 _spte = *spte; @@ -1186,7 +1185,7 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, young = 1; clear_bit(PT_ACCESSED_SHIFT, (unsigned long *)spte); } - spte = rmap_next(kvm, rmapp, spte); + spte = rmap_next(rmapp, spte); } return young; } @@ -1205,7 +1204,7 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp, if (!shadow_accessed_mask) goto out; - spte = rmap_next(kvm, rmapp, NULL); + spte = rmap_next(rmapp, NULL); while (spte) { u64 _spte = *spte; BUG_ON(!(_spte & PT_PRESENT_MASK)); @@ -1214,7 +1213,7 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp, young = 1; break; } - spte = rmap_next(kvm, rmapp, spte); + spte = rmap_next(rmapp, spte); } out: return young; @@ -1391,11 +1390,6 @@ struct kvm_mmu_pages { unsigned int nr; }; -#define for_each_unsync_children(bitmap, idx) \ - for (idx = find_first_bit(bitmap, 512); \ - idx < 512; \ - idx = find_next_bit(bitmap, 512, idx+1)) - static int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp, int idx) { @@ -1417,7 +1411,7 @@ static int __mmu_unsync_walk(struct kvm_mmu_page *sp, { int i, ret, nr_unsync_leaf = 0; - for_each_unsync_children(sp->unsync_child_bitmap, i) { + for_each_set_bit(i, sp->unsync_child_bitmap, 512) { struct kvm_mmu_page *child; u64 ent = sp->spt[i]; @@ -1803,6 +1797,7 @@ static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep) { if (is_large_pte(*sptep)) { drop_spte(vcpu->kvm, sptep); + --vcpu->kvm->stat.lpages; kvm_flush_remote_tlbs(vcpu->kvm); } } @@ -3190,15 +3185,14 @@ static bool sync_mmio_spte(u64 *sptep, gfn_t gfn, unsigned access, #undef PTTYPE static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, - struct kvm_mmu *context, - int level) + struct kvm_mmu *context) { int maxphyaddr = cpuid_maxphyaddr(vcpu); u64 exb_bit_rsvd = 0; if (!context->nx) exb_bit_rsvd = rsvd_bits(63, 63); - switch (level) { + switch (context->root_level) { case PT32_ROOT_LEVEL: /* no rsvd bits for 2 level 4K page table entries */ context->rsvd_bits_mask[0][1] = 0; @@ -3256,8 +3250,9 @@ static int paging64_init_context_common(struct kvm_vcpu *vcpu, int level) { context->nx = is_nx(vcpu); + context->root_level = level; - reset_rsvds_bits_mask(vcpu, context, level); + reset_rsvds_bits_mask(vcpu, context); ASSERT(is_pae(vcpu)); context->new_cr3 = paging_new_cr3; @@ -3267,7 +3262,6 @@ static int paging64_init_context_common(struct kvm_vcpu *vcpu, context->invlpg = paging64_invlpg; context->update_pte = paging64_update_pte; context->free = paging_free; - context->root_level = level; context->shadow_root_level = level; context->root_hpa = INVALID_PAGE; context->direct_map = false; @@ -3284,8 +3278,9 @@ static int paging32_init_context(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { context->nx = false; + context->root_level = PT32_ROOT_LEVEL; - reset_rsvds_bits_mask(vcpu, context, PT32_ROOT_LEVEL); + reset_rsvds_bits_mask(vcpu, context); context->new_cr3 = paging_new_cr3; context->page_fault = paging32_page_fault; @@ -3294,7 +3289,6 @@ static int paging32_init_context(struct kvm_vcpu *vcpu, context->sync_page = paging32_sync_page; context->invlpg = paging32_invlpg; context->update_pte = paging32_update_pte; - context->root_level = PT32_ROOT_LEVEL; context->shadow_root_level = PT32E_ROOT_LEVEL; context->root_hpa = INVALID_PAGE; context->direct_map = false; @@ -3325,7 +3319,6 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) context->get_cr3 = get_cr3; context->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault; - context->nx = is_nx(vcpu); if (!is_paging(vcpu)) { context->nx = false; @@ -3333,19 +3326,19 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) context->root_level = 0; } else if (is_long_mode(vcpu)) { context->nx = is_nx(vcpu); - reset_rsvds_bits_mask(vcpu, context, PT64_ROOT_LEVEL); - context->gva_to_gpa = paging64_gva_to_gpa; context->root_level = PT64_ROOT_LEVEL; + reset_rsvds_bits_mask(vcpu, context); + context->gva_to_gpa = paging64_gva_to_gpa; } else if (is_pae(vcpu)) { context->nx = is_nx(vcpu); - reset_rsvds_bits_mask(vcpu, context, PT32E_ROOT_LEVEL); - context->gva_to_gpa = paging64_gva_to_gpa; context->root_level = PT32E_ROOT_LEVEL; + reset_rsvds_bits_mask(vcpu, context); + context->gva_to_gpa = paging64_gva_to_gpa; } else { context->nx = false; - reset_rsvds_bits_mask(vcpu, context, PT32_ROOT_LEVEL); - context->gva_to_gpa = paging32_gva_to_gpa; context->root_level = PT32_ROOT_LEVEL; + reset_rsvds_bits_mask(vcpu, context); + context->gva_to_gpa = paging32_gva_to_gpa; } return 0; @@ -3408,18 +3401,18 @@ static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu) g_context->gva_to_gpa = nonpaging_gva_to_gpa_nested; } else if (is_long_mode(vcpu)) { g_context->nx = is_nx(vcpu); - reset_rsvds_bits_mask(vcpu, g_context, PT64_ROOT_LEVEL); g_context->root_level = PT64_ROOT_LEVEL; + reset_rsvds_bits_mask(vcpu, g_context); g_context->gva_to_gpa = paging64_gva_to_gpa_nested; } else if (is_pae(vcpu)) { g_context->nx = is_nx(vcpu); - reset_rsvds_bits_mask(vcpu, g_context, PT32E_ROOT_LEVEL); g_context->root_level = PT32E_ROOT_LEVEL; + reset_rsvds_bits_mask(vcpu, g_context); g_context->gva_to_gpa = paging64_gva_to_gpa_nested; } else { g_context->nx = false; - reset_rsvds_bits_mask(vcpu, g_context, PT32_ROOT_LEVEL); g_context->root_level = PT32_ROOT_LEVEL; + reset_rsvds_bits_mask(vcpu, g_context); g_context->gva_to_gpa = paging32_gva_to_gpa_nested; } @@ -3555,7 +3548,7 @@ static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, * If we're seeing too many writes to a page, it may no longer be a page table, * or we may be forking, in which case it is better to unmap the page. */ -static bool detect_write_flooding(struct kvm_mmu_page *sp, u64 *spte) +static bool detect_write_flooding(struct kvm_mmu_page *sp) { /* * Skip write-flooding detected for the sp whose level is 1, because @@ -3664,10 +3657,8 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, mask.cr0_wp = mask.cr4_pae = mask.nxe = 1; for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn, node) { - spte = get_written_sptes(sp, gpa, &npte); - if (detect_write_misaligned(sp, gpa, bytes) || - detect_write_flooding(sp, spte)) { + detect_write_flooding(sp)) { zap_page |= !!kvm_mmu_prepare_zap_page(vcpu->kvm, sp, &invalid_list); ++vcpu->kvm->stat.mmu_flooded; diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c index fe15dcc07a6..715da5a19a5 100644 --- a/arch/x86/kvm/mmu_audit.c +++ b/arch/x86/kvm/mmu_audit.c @@ -200,13 +200,13 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp) slot = gfn_to_memslot(kvm, sp->gfn); rmapp = &slot->rmap[sp->gfn - slot->base_gfn]; - spte = rmap_next(kvm, rmapp, NULL); + spte = rmap_next(rmapp, NULL); while (spte) { if (is_writable_pte(*spte)) audit_printk(kvm, "shadow page has writable " "mappings: gfn %llx role %x\n", sp->gfn, sp->role.word); - spte = rmap_next(kvm, rmapp, spte); + spte = rmap_next(rmapp, spte); } } @@ -234,7 +234,7 @@ static void audit_vcpu_spte(struct kvm_vcpu *vcpu) } static bool mmu_audit; -static struct jump_label_key mmu_audit_key; +static struct static_key mmu_audit_key; static void __kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { @@ -250,7 +250,7 @@ static void __kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) static inline void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { - if (static_branch((&mmu_audit_key))) + if (static_key_false((&mmu_audit_key))) __kvm_mmu_audit(vcpu, point); } @@ -259,7 +259,7 @@ static void mmu_audit_enable(void) if (mmu_audit) return; - jump_label_inc(&mmu_audit_key); + static_key_slow_inc(&mmu_audit_key); mmu_audit = true; } @@ -268,7 +268,7 @@ static void mmu_audit_disable(void) if (!mmu_audit) return; - jump_label_dec(&mmu_audit_key); + static_key_slow_dec(&mmu_audit_key); mmu_audit = false; } diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 15610285ebb..df5a70311be 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -92,9 +92,9 @@ static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, if (unlikely(npages != 1)) return -EFAULT; - table = kmap_atomic(page, KM_USER0); + table = kmap_atomic(page); ret = CMPXCHG(&table[index], orig_pte, new_pte); - kunmap_atomic(table, KM_USER0); + kunmap_atomic(table); kvm_release_page_dirty(page); diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 7aad5446f39..173df38dbda 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -33,10 +33,11 @@ static struct kvm_arch_event_perf_mapping { [4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES }, [5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, [6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, + [7] = { 0x00, 0x30, PERF_COUNT_HW_REF_CPU_CYCLES }, }; /* mapping between fixed pmc index and arch_events array */ -int fixed_pmc_events[] = {1, 0, 2}; +int fixed_pmc_events[] = {1, 0, 7}; static bool pmc_is_gp(struct kvm_pmc *pmc) { @@ -210,6 +211,9 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) unsigned config, type = PERF_TYPE_RAW; u8 event_select, unit_mask; + if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL) + printk_once("kvm pmu: pin control bit is ignored\n"); + pmc->eventsel = eventsel; stop_counter(pmc); @@ -220,7 +224,7 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) event_select = eventsel & ARCH_PERFMON_EVENTSEL_EVENT; unit_mask = (eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; - if (!(event_select & (ARCH_PERFMON_EVENTSEL_EDGE | + if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE | ARCH_PERFMON_EVENTSEL_INV | ARCH_PERFMON_EVENTSEL_CMASK))) { config = find_arch_event(&pmc->vcpu->arch.pmu, event_select, @@ -365,7 +369,7 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data) case MSR_CORE_PERF_FIXED_CTR_CTRL: if (pmu->fixed_ctr_ctrl == data) return 0; - if (!(data & 0xfffffffffffff444)) { + if (!(data & 0xfffffffffffff444ull)) { reprogram_fixed_counters(pmu, data); return 0; } @@ -413,7 +417,7 @@ int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data) struct kvm_pmc *counters; u64 ctr; - pmc &= (3u << 30) - 1; + pmc &= ~(3u << 30); if (!fixed && pmc >= pmu->nr_arch_gp_counters) return 1; if (fixed && pmc >= pmu->nr_arch_fixed_counters) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 5fa553babe5..e334389e1c7 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -29,6 +29,7 @@ #include <linux/ftrace_event.h> #include <linux/slab.h> +#include <asm/perf_event.h> #include <asm/tlbflush.h> #include <asm/desc.h> #include <asm/kvm_para.h> @@ -110,6 +111,12 @@ struct nested_state { #define MSRPM_OFFSETS 16 static u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; +/* + * Set osvw_len to higher value when updated Revision Guides + * are published and we know what the new status bits are + */ +static uint64_t osvw_len = 4, osvw_status; + struct vcpu_svm { struct kvm_vcpu vcpu; struct vmcb *vmcb; @@ -176,11 +183,13 @@ static bool npt_enabled = true; #else static bool npt_enabled; #endif -static int npt = 1; +/* allow nested paging (virtualized MMU) for all guests */ +static int npt = true; module_param(npt, int, S_IRUGO); -static int nested = 1; +/* allow nested virtualization in KVM/SVM */ +static int nested = true; module_param(nested, int, S_IRUGO); static void svm_flush_tlb(struct kvm_vcpu *vcpu); @@ -556,6 +565,27 @@ static void svm_init_erratum_383(void) erratum_383_found = true; } +static void svm_init_osvw(struct kvm_vcpu *vcpu) +{ + /* + * Guests should see errata 400 and 415 as fixed (assuming that + * HLT and IO instructions are intercepted). + */ + vcpu->arch.osvw.length = (osvw_len >= 3) ? (osvw_len) : 3; + vcpu->arch.osvw.status = osvw_status & ~(6ULL); + + /* + * By increasing VCPU's osvw.length to 3 we are telling the guest that + * all osvw.status bits inside that length, including bit 0 (which is + * reserved for erratum 298), are valid. However, if host processor's + * osvw_len is 0 then osvw_status[0] carries no information. We need to + * be conservative here and therefore we tell the guest that erratum 298 + * is present (because we really don't know). + */ + if (osvw_len == 0 && boot_cpu_data.x86 == 0x10) + vcpu->arch.osvw.status |= 1; +} + static int has_svm(void) { const char *msg; @@ -575,6 +605,8 @@ static void svm_hardware_disable(void *garbage) wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT); cpu_svm_disable(); + + amd_pmu_disable_virt(); } static int svm_hardware_enable(void *garbage) @@ -620,8 +652,40 @@ static int svm_hardware_enable(void *garbage) __get_cpu_var(current_tsc_ratio) = TSC_RATIO_DEFAULT; } + + /* + * Get OSVW bits. + * + * Note that it is possible to have a system with mixed processor + * revisions and therefore different OSVW bits. If bits are not the same + * on different processors then choose the worst case (i.e. if erratum + * is present on one processor and not on another then assume that the + * erratum is present everywhere). + */ + if (cpu_has(&boot_cpu_data, X86_FEATURE_OSVW)) { + uint64_t len, status = 0; + int err; + + len = native_read_msr_safe(MSR_AMD64_OSVW_ID_LENGTH, &err); + if (!err) + status = native_read_msr_safe(MSR_AMD64_OSVW_STATUS, + &err); + + if (err) + osvw_status = osvw_len = 0; + else { + if (len < osvw_len) + osvw_len = len; + osvw_status |= status; + osvw_status &= (1ULL << osvw_len) - 1; + } + } else + osvw_status = osvw_len = 0; + svm_init_erratum_383(); + amd_pmu_enable_virt(); + return 0; } @@ -905,20 +969,25 @@ static u64 svm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc) return _tsc; } -static void svm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz) +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; - /* TSC scaling supported? */ - if (!boot_cpu_has(X86_FEATURE_TSCRATEMSR)) + /* Guest TSC same frequency as host TSC? */ + if (!scale) { + svm->tsc_ratio = TSC_RATIO_DEFAULT; return; + } - /* TSC-Scaling disabled or guest TSC same frequency as host TSC? */ - if (user_tsc_khz == 0) { - vcpu->arch.virtual_tsc_khz = 0; - svm->tsc_ratio = TSC_RATIO_DEFAULT; + /* 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; } @@ -933,7 +1002,6 @@ static void svm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz) user_tsc_khz); return; } - vcpu->arch.virtual_tsc_khz = user_tsc_khz; svm->tsc_ratio = ratio; } @@ -953,10 +1021,14 @@ 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) +static void svm_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool host) { struct vcpu_svm *svm = to_svm(vcpu); + WARN_ON(adjustment < 0); + if (host) + adjustment = svm_scale_tsc(vcpu, adjustment); + svm->vmcb->control.tsc_offset += adjustment; if (is_guest_mode(vcpu)) svm->nested.hsave->control.tsc_offset += adjustment; @@ -1186,6 +1258,8 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) if (kvm_vcpu_is_bsp(&svm->vcpu)) svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP; + svm_init_osvw(&svm->vcpu); + return &svm->vcpu; free_page4: @@ -1263,6 +1337,21 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu) wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); } +static void svm_update_cpl(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + int cpl; + + if (!is_protmode(vcpu)) + cpl = 0; + else if (svm->vmcb->save.rflags & X86_EFLAGS_VM) + cpl = 3; + else + cpl = svm->vmcb->save.cs.selector & 0x3; + + svm->vmcb->save.cpl = cpl; +} + static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) { return to_svm(vcpu)->vmcb->save.rflags; @@ -1270,7 +1359,11 @@ static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { + unsigned long old_rflags = to_svm(vcpu)->vmcb->save.rflags; + to_svm(vcpu)->vmcb->save.rflags = rflags; + if ((old_rflags ^ rflags) & X86_EFLAGS_VM) + svm_update_cpl(vcpu); } static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) @@ -1538,9 +1631,7 @@ static void svm_set_segment(struct kvm_vcpu *vcpu, s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT; } if (seg == VCPU_SREG_CS) - svm->vmcb->save.cpl - = (svm->vmcb->save.cs.attrib - >> SVM_SELECTOR_DPL_SHIFT) & 3; + svm_update_cpl(vcpu); mark_dirty(svm->vmcb, VMCB_SEG); } @@ -2730,7 +2821,10 @@ static int task_switch_interception(struct vcpu_svm *svm) (int_vec == OF_VECTOR || int_vec == BP_VECTOR))) skip_emulated_instruction(&svm->vcpu); - if (kvm_task_switch(&svm->vcpu, tss_selector, reason, + if (int_type != SVM_EXITINTINFO_TYPE_SOFT) + int_vec = -1; + + if (kvm_task_switch(&svm->vcpu, tss_selector, int_vec, reason, has_error_code, error_code) == EMULATE_FAIL) { svm->vcpu.run->exit_reason = KVM_EXIT_INTERNAL_ERROR; svm->vcpu.run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 906a7e84200..ad85adfef84 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -51,29 +51,26 @@ MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); -static int __read_mostly enable_vpid = 1; +static bool __read_mostly enable_vpid = 1; module_param_named(vpid, enable_vpid, bool, 0444); -static int __read_mostly flexpriority_enabled = 1; +static bool __read_mostly flexpriority_enabled = 1; module_param_named(flexpriority, flexpriority_enabled, bool, S_IRUGO); -static int __read_mostly enable_ept = 1; +static bool __read_mostly enable_ept = 1; module_param_named(ept, enable_ept, bool, S_IRUGO); -static int __read_mostly enable_unrestricted_guest = 1; +static bool __read_mostly enable_unrestricted_guest = 1; module_param_named(unrestricted_guest, enable_unrestricted_guest, bool, S_IRUGO); -static int __read_mostly emulate_invalid_guest_state = 0; +static bool __read_mostly emulate_invalid_guest_state = 0; module_param(emulate_invalid_guest_state, bool, S_IRUGO); -static int __read_mostly vmm_exclusive = 1; +static bool __read_mostly vmm_exclusive = 1; module_param(vmm_exclusive, bool, S_IRUGO); -static int __read_mostly yield_on_hlt = 1; -module_param(yield_on_hlt, bool, S_IRUGO); - -static int __read_mostly fasteoi = 1; +static bool __read_mostly fasteoi = 1; module_param(fasteoi, bool, S_IRUGO); /* @@ -81,7 +78,7 @@ module_param(fasteoi, bool, S_IRUGO); * VMX and be a hypervisor for its own guests. If nested=0, guests may not * use VMX instructions. */ -static int __read_mostly nested = 0; +static bool __read_mostly nested = 0; module_param(nested, bool, S_IRUGO); #define KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST \ @@ -1457,7 +1454,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) #ifdef CONFIG_X86_64 wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); #endif - if (current_thread_info()->status & TS_USEDFPU) + if (user_has_fpu()) clts(); load_gdt(&__get_cpu_var(host_gdt)); } @@ -1655,17 +1652,6 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) vmx_set_interrupt_shadow(vcpu, 0); } -static void vmx_clear_hlt(struct kvm_vcpu *vcpu) -{ - /* Ensure that we clear the HLT state in the VMCS. We don't need to - * explicitly skip the instruction because if the HLT state is set, then - * the instruction is already executing and RIP has already been - * advanced. */ - if (!yield_on_hlt && - vmcs_read32(GUEST_ACTIVITY_STATE) == GUEST_ACTIVITY_HLT) - vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); -} - /* * KVM wants to inject page-faults which it got to the guest. This function * checks whether in a nested guest, we need to inject them to L1 or L2. @@ -1678,7 +1664,7 @@ static int nested_pf_handled(struct kvm_vcpu *vcpu) struct vmcs12 *vmcs12 = get_vmcs12(vcpu); /* TODO: also check PFEC_MATCH/MASK, not just EB.PF. */ - if (!(vmcs12->exception_bitmap & PF_VECTOR)) + if (!(vmcs12->exception_bitmap & (1u << PF_VECTOR))) return 0; nested_vmx_vmexit(vcpu); @@ -1718,7 +1704,6 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, intr_info |= INTR_TYPE_HARD_EXCEPTION; vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info); - vmx_clear_hlt(vcpu); } static bool vmx_rdtscp_supported(void) @@ -1817,13 +1802,19 @@ u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu) } /* - * Empty call-back. Needs to be implemented when VMX enables the SET_TSC_KHZ - * ioctl. In this case the call-back should update internal vmx state to make - * the changes effective. + * 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) +static void vmx_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) { - /* Nothing to do here */ + 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"); } /* @@ -1850,7 +1841,7 @@ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) } } -static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment) +static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool host) { u64 offset = vmcs_read64(TSC_OFFSET); vmcs_write64(TSC_OFFSET, offset + adjustment); @@ -2219,6 +2210,9 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) msr = find_msr_entry(vmx, msr_index); if (msr) { msr->data = data; + if (msr - vmx->guest_msrs < vmx->save_nmsrs) + kvm_set_shared_msr(msr->index, msr->data, + msr->mask); break; } ret = kvm_set_msr_common(vcpu, msr_index, data); @@ -2399,7 +2393,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) &_pin_based_exec_control) < 0) return -EIO; - min = + min = CPU_BASED_HLT_EXITING | #ifdef CONFIG_X86_64 CPU_BASED_CR8_LOAD_EXITING | CPU_BASED_CR8_STORE_EXITING | @@ -2414,9 +2408,6 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) CPU_BASED_INVLPG_EXITING | CPU_BASED_RDPMC_EXITING; - if (yield_on_hlt) - min |= CPU_BASED_HLT_EXITING; - opt = CPU_BASED_TPR_SHADOW | CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; @@ -3915,7 +3906,9 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); vmx->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); vmx_set_cr0(&vmx->vcpu, kvm_read_cr0(vcpu)); /* enter rmode */ + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); vmx_set_cr4(&vmx->vcpu, 0); vmx_set_efer(&vmx->vcpu, 0); vmx_fpu_activate(&vmx->vcpu); @@ -4003,7 +3996,6 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu) } else intr |= INTR_TYPE_EXT_INTR; vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr); - vmx_clear_hlt(vcpu); } static void vmx_inject_nmi(struct kvm_vcpu *vcpu) @@ -4035,7 +4027,6 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu) } vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR); - vmx_clear_hlt(vcpu); } static int vmx_nmi_allowed(struct kvm_vcpu *vcpu) @@ -4672,9 +4663,10 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) bool has_error_code = false; u32 error_code = 0; u16 tss_selector; - int reason, type, idt_v; + int reason, type, idt_v, idt_index; idt_v = (vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK); + idt_index = (vmx->idt_vectoring_info & VECTORING_INFO_VECTOR_MASK); type = (vmx->idt_vectoring_info & VECTORING_INFO_TYPE_MASK); exit_qualification = vmcs_readl(EXIT_QUALIFICATION); @@ -4712,8 +4704,9 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) type != INTR_TYPE_NMI_INTR)) skip_emulated_instruction(vcpu); - if (kvm_task_switch(vcpu, tss_selector, reason, - has_error_code, error_code) == EMULATE_FAIL) { + if (kvm_task_switch(vcpu, tss_selector, + type == INTR_TYPE_SOFT_INTR ? idt_index : -1, reason, + has_error_code, error_code) == EMULATE_FAIL) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; vcpu->run->internal.ndata = 0; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1171def5f96..4044ce0bf7c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -57,6 +57,7 @@ #include <asm/mtrr.h> #include <asm/mce.h> #include <asm/i387.h> +#include <asm/fpu-internal.h> /* Ugh! */ #include <asm/xcr.h> #include <asm/pvclock.h> #include <asm/div64.h> @@ -88,14 +89,18 @@ static void process_nmi(struct kvm_vcpu *vcpu); struct kvm_x86_ops *kvm_x86_ops; EXPORT_SYMBOL_GPL(kvm_x86_ops); -int ignore_msrs = 0; -module_param_named(ignore_msrs, ignore_msrs, bool, S_IRUGO | S_IWUSR); +static bool ignore_msrs = 0; +module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR); bool kvm_has_tsc_control; EXPORT_SYMBOL_GPL(kvm_has_tsc_control); u32 kvm_max_guest_tsc_khz; EXPORT_SYMBOL_GPL(kvm_max_guest_tsc_khz); +/* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */ +static u32 tsc_tolerance_ppm = 250; +module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); + #define KVM_NR_SHARED_MSRS 16 struct kvm_shared_msrs_global { @@ -968,50 +973,51 @@ static inline u64 get_kernel_ns(void) static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz); unsigned long max_tsc_khz; -static inline int kvm_tsc_changes_freq(void) +static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) { - int cpu = get_cpu(); - int ret = !boot_cpu_has(X86_FEATURE_CONSTANT_TSC) && - cpufreq_quick_get(cpu) != 0; - put_cpu(); - return ret; + return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult, + vcpu->arch.virtual_tsc_shift); } -u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu) +static u32 adjust_tsc_khz(u32 khz, s32 ppm) { - if (vcpu->arch.virtual_tsc_khz) - return vcpu->arch.virtual_tsc_khz; - else - return __this_cpu_read(cpu_tsc_khz); + u64 v = (u64)khz * (1000000 + ppm); + do_div(v, 1000000); + return v; } -static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) +static void kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz) { - u64 ret; - - WARN_ON(preemptible()); - if (kvm_tsc_changes_freq()) - printk_once(KERN_WARNING - "kvm: unreliable cycle conversion on adjustable rate TSC\n"); - ret = nsec * vcpu_tsc_khz(vcpu); - do_div(ret, USEC_PER_SEC); - return ret; -} + u32 thresh_lo, thresh_hi; + int use_scaling = 0; -static void kvm_init_tsc_catchup(struct kvm_vcpu *vcpu, u32 this_tsc_khz) -{ /* Compute a scale to convert nanoseconds in TSC cycles */ kvm_get_time_scale(this_tsc_khz, NSEC_PER_SEC / 1000, - &vcpu->arch.tsc_catchup_shift, - &vcpu->arch.tsc_catchup_mult); + &vcpu->arch.virtual_tsc_shift, + &vcpu->arch.virtual_tsc_mult); + vcpu->arch.virtual_tsc_khz = this_tsc_khz; + + /* + * Compute the variation in TSC rate which is acceptable + * within the range of tolerance and decide if the + * rate being applied is within that bounds of the hardware + * rate. If so, no scaling or compensation need be done. + */ + thresh_lo = adjust_tsc_khz(tsc_khz, -tsc_tolerance_ppm); + thresh_hi = adjust_tsc_khz(tsc_khz, tsc_tolerance_ppm); + if (this_tsc_khz < thresh_lo || this_tsc_khz > thresh_hi) { + 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); } static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) { - u64 tsc = pvclock_scale_delta(kernel_ns-vcpu->arch.last_tsc_nsec, - vcpu->arch.tsc_catchup_mult, - vcpu->arch.tsc_catchup_shift); - tsc += vcpu->arch.last_tsc_write; + u64 tsc = pvclock_scale_delta(kernel_ns-vcpu->arch.this_tsc_nsec, + vcpu->arch.virtual_tsc_mult, + vcpu->arch.virtual_tsc_shift); + tsc += vcpu->arch.this_tsc_write; return tsc; } @@ -1020,48 +1026,88 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data) struct kvm *kvm = vcpu->kvm; u64 offset, ns, elapsed; unsigned long flags; - s64 sdiff; + s64 usdiff; raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); offset = kvm_x86_ops->compute_tsc_offset(vcpu, data); ns = get_kernel_ns(); elapsed = ns - kvm->arch.last_tsc_nsec; - sdiff = data - kvm->arch.last_tsc_write; - if (sdiff < 0) - sdiff = -sdiff; + + /* n.b - signed multiplication and division required */ + usdiff = data - kvm->arch.last_tsc_write; +#ifdef CONFIG_X86_64 + usdiff = (usdiff * 1000) / vcpu->arch.virtual_tsc_khz; +#else + /* do_div() only does unsigned */ + asm("idivl %2; xor %%edx, %%edx" + : "=A"(usdiff) + : "A"(usdiff * 1000), "rm"(vcpu->arch.virtual_tsc_khz)); +#endif + do_div(elapsed, 1000); + usdiff -= elapsed; + if (usdiff < 0) + usdiff = -usdiff; /* - * Special case: close write to TSC within 5 seconds of - * another CPU is interpreted as an attempt to synchronize - * The 5 seconds is to accommodate host load / swapping as - * well as any reset of TSC during the boot process. - * - * In that case, for a reliable TSC, we can match TSC offsets, - * or make a best guest using elapsed value. - */ - if (sdiff < nsec_to_cycles(vcpu, 5ULL * NSEC_PER_SEC) && - elapsed < 5ULL * NSEC_PER_SEC) { + * Special case: TSC write with a small delta (1 second) of virtual + * cycle time against real time is interpreted as an attempt to + * synchronize the CPU. + * + * For a reliable TSC, we can match TSC offsets, and for an unstable + * TSC, we add elapsed time in this computation. We could let the + * compensation code attempt to catch up if we fall behind, but + * it's better to try to match offsets from the beginning. + */ + if (usdiff < USEC_PER_SEC && + vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) { if (!check_tsc_unstable()) { - offset = kvm->arch.last_tsc_offset; + offset = kvm->arch.cur_tsc_offset; pr_debug("kvm: matched tsc offset for %llu\n", data); } else { u64 delta = nsec_to_cycles(vcpu, elapsed); - offset += delta; + data += delta; + offset = kvm_x86_ops->compute_tsc_offset(vcpu, data); pr_debug("kvm: adjusted tsc offset by %llu\n", delta); } - ns = kvm->arch.last_tsc_nsec; + } else { + /* + * We split periods of matched TSC writes into generations. + * For each generation, we track the original measured + * nanosecond time, offset, and write, so if TSCs are in + * sync, we can match exact offset, and if not, we can match + * exact software computaion in compute_guest_tsc() + * + * These values are tracked in kvm->arch.cur_xxx variables. + */ + kvm->arch.cur_tsc_generation++; + kvm->arch.cur_tsc_nsec = ns; + kvm->arch.cur_tsc_write = data; + kvm->arch.cur_tsc_offset = offset; + pr_debug("kvm: new tsc generation %u, clock %llu\n", + kvm->arch.cur_tsc_generation, data); } + + /* + * We also track th most recent recorded KHZ, write and time to + * allow the matching interval to be extended at each write. + */ kvm->arch.last_tsc_nsec = ns; kvm->arch.last_tsc_write = data; - kvm->arch.last_tsc_offset = offset; - kvm_x86_ops->write_tsc_offset(vcpu, offset); - raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); + kvm->arch.last_tsc_khz = vcpu->arch.virtual_tsc_khz; /* Reset of TSC must disable overshoot protection below */ vcpu->arch.hv_clock.tsc_timestamp = 0; - vcpu->arch.last_tsc_write = data; - vcpu->arch.last_tsc_nsec = ns; + vcpu->arch.last_guest_tsc = data; + + /* Keep track of which generation this VCPU has synchronized to */ + vcpu->arch.this_tsc_generation = kvm->arch.cur_tsc_generation; + vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec; + vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write; + + kvm_x86_ops->write_tsc_offset(vcpu, offset); + raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); } + EXPORT_SYMBOL_GPL(kvm_write_tsc); static int kvm_guest_time_update(struct kvm_vcpu *v) @@ -1077,7 +1123,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) local_irq_save(flags); tsc_timestamp = kvm_x86_ops->read_l1_tsc(v); kernel_ns = get_kernel_ns(); - this_tsc_khz = vcpu_tsc_khz(v); + this_tsc_khz = __get_cpu_var(cpu_tsc_khz); if (unlikely(this_tsc_khz == 0)) { local_irq_restore(flags); kvm_make_request(KVM_REQ_CLOCK_UPDATE, v); @@ -1097,7 +1143,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) if (vcpu->tsc_catchup) { u64 tsc = compute_guest_tsc(v, kernel_ns); if (tsc > tsc_timestamp) { - kvm_x86_ops->adjust_tsc_offset(v, tsc - tsc_timestamp); + adjust_tsc_offset_guest(v, tsc - tsc_timestamp); tsc_timestamp = tsc; } } @@ -1129,7 +1175,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) * observed by the guest and ensure the new system time is greater. */ max_kernel_ns = 0; - if (vcpu->hv_clock.tsc_timestamp && vcpu->last_guest_tsc) { + if (vcpu->hv_clock.tsc_timestamp) { max_kernel_ns = vcpu->last_guest_tsc - vcpu->hv_clock.tsc_timestamp; max_kernel_ns = pvclock_scale_delta(max_kernel_ns, @@ -1162,12 +1208,12 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) */ vcpu->hv_clock.version += 2; - shared_kaddr = kmap_atomic(vcpu->time_page, KM_USER0); + shared_kaddr = kmap_atomic(vcpu->time_page); memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock, sizeof(vcpu->hv_clock)); - kunmap_atomic(shared_kaddr, KM_USER0); + kunmap_atomic(shared_kaddr); mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT); return 0; @@ -1495,12 +1541,15 @@ static void record_steal_time(struct kvm_vcpu *vcpu) int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) { + bool pr = false; + switch (msr) { case MSR_EFER: return set_efer(vcpu, data); case MSR_K7_HWCR: data &= ~(u64)0x40; /* ignore flush filter disable */ data &= ~(u64)0x100; /* ignore ignne emulation enable */ + data &= ~(u64)0x8; /* ignore TLB cache disable */ if (data != 0) { pr_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n", data); @@ -1635,6 +1684,18 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) pr_unimpl(vcpu, "unimplemented perfctr wrmsr: " "0x%x data 0x%llx\n", msr, data); break; + case MSR_P6_PERFCTR0: + case MSR_P6_PERFCTR1: + pr = true; + case MSR_P6_EVNTSEL0: + case MSR_P6_EVNTSEL1: + if (kvm_pmu_msr(vcpu, msr)) + return kvm_pmu_set_msr(vcpu, msr, data); + + if (pr || data != 0) + pr_unimpl(vcpu, "disabled perfctr wrmsr: " + "0x%x data 0x%llx\n", msr, data); + break; case MSR_K7_CLK_CTL: /* * Ignore all writes to this no longer documented MSR. @@ -1661,6 +1722,16 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) */ pr_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", msr, data); break; + case MSR_AMD64_OSVW_ID_LENGTH: + if (!guest_cpuid_has_osvw(vcpu)) + return 1; + vcpu->arch.osvw.length = data; + break; + case MSR_AMD64_OSVW_STATUS: + if (!guest_cpuid_has_osvw(vcpu)) + return 1; + vcpu->arch.osvw.status = data; + break; default: if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr)) return xen_hvm_config(vcpu, data); @@ -1835,6 +1906,14 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_FAM10H_MMIO_CONF_BASE: data = 0; break; + case MSR_P6_PERFCTR0: + case MSR_P6_PERFCTR1: + case MSR_P6_EVNTSEL0: + case MSR_P6_EVNTSEL1: + if (kvm_pmu_msr(vcpu, msr)) + return kvm_pmu_get_msr(vcpu, msr, pdata); + data = 0; + break; case MSR_IA32_UCODE_REV: data = 0x100000000ULL; break; @@ -1937,6 +2016,16 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) */ data = 0xbe702111; break; + case MSR_AMD64_OSVW_ID_LENGTH: + if (!guest_cpuid_has_osvw(vcpu)) + return 1; + data = vcpu->arch.osvw.length; + break; + case MSR_AMD64_OSVW_STATUS: + if (!guest_cpuid_has_osvw(vcpu)) + return 1; + data = vcpu->arch.osvw.status; + break; default: if (kvm_pmu_msr(vcpu, msr)) return kvm_pmu_get_msr(vcpu, msr, pdata); @@ -2057,6 +2146,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_XSAVE: case KVM_CAP_ASYNC_PF: case KVM_CAP_GET_TSC_KHZ: + case KVM_CAP_PCI_2_3: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -2191,19 +2281,23 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) } kvm_x86_ops->vcpu_load(vcpu, cpu); - if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) { - /* Make sure TSC doesn't go backwards */ - s64 tsc_delta; - u64 tsc; - tsc = kvm_x86_ops->read_l1_tsc(vcpu); - tsc_delta = !vcpu->arch.last_guest_tsc ? 0 : - tsc - vcpu->arch.last_guest_tsc; + /* Apply any externally detected TSC adjustments (due to suspend) */ + if (unlikely(vcpu->arch.tsc_offset_adjustment)) { + adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment); + vcpu->arch.tsc_offset_adjustment = 0; + set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests); + } + 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; if (tsc_delta < 0) mark_tsc_unstable("KVM discovered backwards TSC"); if (check_tsc_unstable()) { - kvm_x86_ops->adjust_tsc_offset(vcpu, -tsc_delta); + u64 offset = kvm_x86_ops->compute_tsc_offset(vcpu, + vcpu->arch.last_guest_tsc); + kvm_x86_ops->write_tsc_offset(vcpu, offset); vcpu->arch.tsc_catchup = 1; } kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); @@ -2220,7 +2314,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { kvm_x86_ops->vcpu_put(vcpu); kvm_put_guest_fpu(vcpu); - vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu); + vcpu->arch.last_host_tsc = native_read_tsc(); } static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, @@ -2762,26 +2856,21 @@ long kvm_arch_vcpu_ioctl(struct file *filp, u32 user_tsc_khz; r = -EINVAL; - if (!kvm_has_tsc_control) - break; - user_tsc_khz = (u32)arg; if (user_tsc_khz >= kvm_max_guest_tsc_khz) goto out; - kvm_x86_ops->set_tsc_khz(vcpu, user_tsc_khz); + if (user_tsc_khz == 0) + user_tsc_khz = tsc_khz; + + kvm_set_tsc_khz(vcpu, user_tsc_khz); r = 0; goto out; } case KVM_GET_TSC_KHZ: { - r = -EIO; - if (check_tsc_unstable()) - goto out; - - r = vcpu_tsc_khz(vcpu); - + r = vcpu->arch.virtual_tsc_khz; goto out; } default: @@ -2792,6 +2881,11 @@ out: return r; } +int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) +{ + return VM_FAULT_SIGBUS; +} + static int kvm_vm_ioctl_set_tss_addr(struct kvm *kvm, unsigned long addr) { int ret; @@ -2975,6 +3069,8 @@ static void write_protect_slot(struct kvm *kvm, unsigned long *dirty_bitmap, unsigned long nr_dirty_pages) { + spin_lock(&kvm->mmu_lock); + /* Not many dirty pages compared to # of shadow pages. */ if (nr_dirty_pages < kvm->arch.n_used_mmu_pages) { unsigned long gfn_offset; @@ -2982,16 +3078,13 @@ static void write_protect_slot(struct kvm *kvm, for_each_set_bit(gfn_offset, dirty_bitmap, memslot->npages) { unsigned long gfn = memslot->base_gfn + gfn_offset; - spin_lock(&kvm->mmu_lock); kvm_mmu_rmap_write_protect(kvm, gfn, memslot); - spin_unlock(&kvm->mmu_lock); } kvm_flush_remote_tlbs(kvm); - } else { - spin_lock(&kvm->mmu_lock); + } else kvm_mmu_slot_remove_write_access(kvm, memslot->id); - spin_unlock(&kvm->mmu_lock); - } + + spin_unlock(&kvm->mmu_lock); } /* @@ -3110,6 +3203,9 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EEXIST; if (kvm->arch.vpic) goto create_irqchip_unlock; + r = -EINVAL; + if (atomic_read(&kvm->online_vcpus)) + goto create_irqchip_unlock; r = -ENOMEM; vpic = kvm_create_pic(kvm); if (vpic) { @@ -3826,7 +3922,7 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, goto emul_write; } - kaddr = kmap_atomic(page, KM_USER0); + kaddr = kmap_atomic(page); kaddr += offset_in_page(gpa); switch (bytes) { case 1: @@ -3844,7 +3940,7 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, default: BUG(); } - kunmap_atomic(kaddr, KM_USER0); + kunmap_atomic(kaddr); kvm_release_page_dirty(page); if (!exchanged) @@ -4040,6 +4136,11 @@ static int emulator_set_cr(struct x86_emulate_ctxt *ctxt, int cr, ulong val) return res; } +static void emulator_set_rflags(struct x86_emulate_ctxt *ctxt, ulong val) +{ + kvm_set_rflags(emul_to_vcpu(ctxt), val); +} + static int emulator_get_cpl(struct x86_emulate_ctxt *ctxt) { return kvm_x86_ops->get_cpl(emul_to_vcpu(ctxt)); @@ -4180,6 +4281,28 @@ static int emulator_intercept(struct x86_emulate_ctxt *ctxt, return kvm_x86_ops->check_intercept(emul_to_vcpu(ctxt), info, stage); } +static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt, + u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) +{ + struct kvm_cpuid_entry2 *cpuid = NULL; + + if (eax && ecx) + cpuid = kvm_find_cpuid_entry(emul_to_vcpu(ctxt), + *eax, *ecx); + + if (cpuid) { + *eax = cpuid->eax; + *ecx = cpuid->ecx; + if (ebx) + *ebx = cpuid->ebx; + if (edx) + *edx = cpuid->edx; + return true; + } + + return false; +} + static struct x86_emulate_ops emulate_ops = { .read_std = kvm_read_guest_virt_system, .write_std = kvm_write_guest_virt_system, @@ -4199,6 +4322,7 @@ static struct x86_emulate_ops emulate_ops = { .set_idt = emulator_set_idt, .get_cr = emulator_get_cr, .set_cr = emulator_set_cr, + .set_rflags = emulator_set_rflags, .cpl = emulator_get_cpl, .get_dr = emulator_get_dr, .set_dr = emulator_set_dr, @@ -4211,6 +4335,7 @@ static struct x86_emulate_ops emulate_ops = { .get_fpu = emulator_get_fpu, .put_fpu = emulator_put_fpu, .intercept = emulator_intercept, + .get_cpuid = emulator_get_cpuid, }; static void cache_all_regs(struct kvm_vcpu *vcpu) @@ -5242,6 +5367,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) profile_hit(KVM_PROFILING, (void *)rip); } + if (unlikely(vcpu->arch.tsc_always_catchup)) + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); kvm_lapic_sync_from_vapic(vcpu); @@ -5541,15 +5668,15 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, return 0; } -int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason, - bool has_error_code, u32 error_code) +int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, + int reason, bool has_error_code, u32 error_code) { struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; int ret; init_emulate_ctxt(vcpu); - ret = emulator_task_switch(ctxt, tss_selector, reason, + ret = emulator_task_switch(ctxt, tss_selector, idt_index, reason, has_error_code, error_code); if (ret) @@ -5882,13 +6009,88 @@ int kvm_arch_hardware_enable(void *garbage) struct kvm *kvm; struct kvm_vcpu *vcpu; int i; + int ret; + u64 local_tsc; + u64 max_tsc = 0; + bool stable, backwards_tsc = false; kvm_shared_msr_cpu_online(); - list_for_each_entry(kvm, &vm_list, vm_list) - kvm_for_each_vcpu(i, vcpu, kvm) - if (vcpu->cpu == smp_processor_id()) - kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); - return kvm_x86_ops->hardware_enable(garbage); + ret = kvm_x86_ops->hardware_enable(garbage); + if (ret != 0) + return ret; + + local_tsc = native_read_tsc(); + stable = !check_tsc_unstable(); + list_for_each_entry(kvm, &vm_list, vm_list) { + kvm_for_each_vcpu(i, vcpu, kvm) { + if (!stable && vcpu->cpu == smp_processor_id()) + set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests); + if (stable && vcpu->arch.last_host_tsc > local_tsc) { + backwards_tsc = true; + if (vcpu->arch.last_host_tsc > max_tsc) + max_tsc = vcpu->arch.last_host_tsc; + } + } + } + + /* + * Sometimes, even reliable TSCs go backwards. This happens on + * platforms that reset TSC during suspend or hibernate actions, but + * maintain synchronization. We must compensate. Fortunately, we can + * detect that condition here, which happens early in CPU bringup, + * before any KVM threads can be running. Unfortunately, we can't + * bring the TSCs fully up to date with real time, as we aren't yet far + * enough into CPU bringup that we know how much real time has actually + * elapsed; our helper function, get_kernel_ns() will be using boot + * variables that haven't been updated yet. + * + * So we simply find the maximum observed TSC above, then record the + * adjustment to TSC in each VCPU. When the VCPU later gets loaded, + * the adjustment will be applied. Note that we accumulate + * adjustments, in case multiple suspend cycles happen before some VCPU + * gets a chance to run again. In the event that no KVM threads get a + * chance to run, we will miss the entire elapsed period, as we'll have + * reset last_host_tsc, so VCPUs will not have the TSC adjusted and may + * loose cycle time. This isn't too big a deal, since the loss will be + * uniform across all VCPUs (not to mention the scenario is extremely + * unlikely). It is possible that a second hibernate recovery happens + * much faster than a first, causing the observed TSC here to be + * smaller; this would require additional padding adjustment, which is + * why we set last_host_tsc to the local tsc observed here. + * + * N.B. - this code below runs only on platforms with reliable TSC, + * as that is the only way backwards_tsc is set above. Also note + * that this runs for ALL vcpus, which is not a bug; all VCPUs should + * have the same delta_cyc adjustment applied if backwards_tsc + * is detected. Note further, this adjustment is only done once, + * as we reset last_host_tsc on all VCPUs to stop this from being + * called multiple times (one for each physical CPU bringup). + * + * Platforms with unnreliable TSCs don't have to deal with this, they + * will be compensated by the logic in vcpu_load, which sets the TSC to + * catchup mode. This will catchup all VCPUs to real time, but cannot + * guarantee that they stay in perfect synchronization. + */ + if (backwards_tsc) { + u64 delta_cyc = max_tsc - local_tsc; + list_for_each_entry(kvm, &vm_list, vm_list) { + kvm_for_each_vcpu(i, vcpu, kvm) { + vcpu->arch.tsc_offset_adjustment += delta_cyc; + vcpu->arch.last_host_tsc = local_tsc; + } + + /* + * We have to disable TSC offset matching.. if you were + * booting a VM while issuing an S4 host suspend.... + * you may have some problem. Solving this issue is + * left as an exercise to the reader. + */ + kvm->arch.last_tsc_nsec = 0; + kvm->arch.last_tsc_write = 0; + } + + } + return 0; } void kvm_arch_hardware_disable(void *garbage) @@ -5912,6 +6114,11 @@ void kvm_arch_check_processor_compat(void *rtn) kvm_x86_ops->check_processor_compatibility(rtn); } +bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) +{ + return irqchip_in_kernel(vcpu->kvm) == (vcpu->arch.apic != NULL); +} + int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) { struct page *page; @@ -5934,7 +6141,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) } vcpu->arch.pio_data = page_address(page); - kvm_init_tsc_catchup(vcpu, max_tsc_khz); + kvm_set_tsc_khz(vcpu, max_tsc_khz); r = kvm_mmu_create(vcpu); if (r < 0) @@ -5986,8 +6193,11 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) free_page((unsigned long)vcpu->arch.pio_data); } -int kvm_arch_init_vm(struct kvm *kvm) +int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { + if (type) + return -EINVAL; + INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); @@ -6047,6 +6257,65 @@ void kvm_arch_destroy_vm(struct kvm *kvm) put_page(kvm->arch.ept_identity_pagetable); } +void kvm_arch_free_memslot(struct kvm_memory_slot *free, + struct kvm_memory_slot *dont) +{ + int i; + + for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) { + if (!dont || free->arch.lpage_info[i] != dont->arch.lpage_info[i]) { + vfree(free->arch.lpage_info[i]); + free->arch.lpage_info[i] = NULL; + } + } +} + +int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) +{ + int i; + + for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) { + unsigned long ugfn; + int lpages; + int level = i + 2; + + lpages = gfn_to_index(slot->base_gfn + npages - 1, + slot->base_gfn, level) + 1; + + slot->arch.lpage_info[i] = + vzalloc(lpages * sizeof(*slot->arch.lpage_info[i])); + if (!slot->arch.lpage_info[i]) + goto out_free; + + if (slot->base_gfn & (KVM_PAGES_PER_HPAGE(level) - 1)) + slot->arch.lpage_info[i][0].write_count = 1; + if ((slot->base_gfn + npages) & (KVM_PAGES_PER_HPAGE(level) - 1)) + slot->arch.lpage_info[i][lpages - 1].write_count = 1; + ugfn = slot->userspace_addr >> PAGE_SHIFT; + /* + * If the gfn and userspace address are not aligned wrt each + * other, or if explicitly asked to, disable large page + * support for this slot + */ + if ((slot->base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE(level) - 1) || + !kvm_largepages_enabled()) { + unsigned long j; + + for (j = 0; j < lpages; ++j) + slot->arch.lpage_info[i][j].write_count = 1; + } + } + + return 0; + +out_free: + for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) { + vfree(slot->arch.lpage_info[i]); + slot->arch.lpage_info[i] = NULL; + } + return -ENOMEM; +} + int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_memory_slot old, diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index cf4603ba866..642d8805bc1 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -856,18 +856,23 @@ static void __init lguest_init_IRQ(void) } /* - * With CONFIG_SPARSE_IRQ, interrupt descriptors are allocated as-needed, so - * rather than set them in lguest_init_IRQ we are called here every time an - * lguest device needs an interrupt. - * - * FIXME: irq_alloc_desc_at() can fail due to lack of memory, we should - * pass that up! + * 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. */ -void lguest_setup_irq(unsigned int irq) +int lguest_setup_irq(unsigned int irq) { - irq_alloc_desc_at(irq, 0); + 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; } /* diff --git a/arch/x86/lib/atomic64_32.c b/arch/x86/lib/atomic64_32.c index 042f6826bf5..a0b4a350daa 100644 --- a/arch/x86/lib/atomic64_32.c +++ b/arch/x86/lib/atomic64_32.c @@ -1,59 +1,4 @@ -#include <linux/compiler.h> -#include <linux/module.h> -#include <linux/types.h> +#define ATOMIC64_EXPORT EXPORT_SYMBOL -#include <asm/processor.h> -#include <asm/cmpxchg.h> +#include <linux/export.h> #include <linux/atomic.h> - -long long atomic64_read_cx8(long long, const atomic64_t *v); -EXPORT_SYMBOL(atomic64_read_cx8); -long long atomic64_set_cx8(long long, const atomic64_t *v); -EXPORT_SYMBOL(atomic64_set_cx8); -long long atomic64_xchg_cx8(long long, unsigned high); -EXPORT_SYMBOL(atomic64_xchg_cx8); -long long atomic64_add_return_cx8(long long a, atomic64_t *v); -EXPORT_SYMBOL(atomic64_add_return_cx8); -long long atomic64_sub_return_cx8(long long a, atomic64_t *v); -EXPORT_SYMBOL(atomic64_sub_return_cx8); -long long atomic64_inc_return_cx8(long long a, atomic64_t *v); -EXPORT_SYMBOL(atomic64_inc_return_cx8); -long long atomic64_dec_return_cx8(long long a, atomic64_t *v); -EXPORT_SYMBOL(atomic64_dec_return_cx8); -long long atomic64_dec_if_positive_cx8(atomic64_t *v); -EXPORT_SYMBOL(atomic64_dec_if_positive_cx8); -int atomic64_inc_not_zero_cx8(atomic64_t *v); -EXPORT_SYMBOL(atomic64_inc_not_zero_cx8); -int atomic64_add_unless_cx8(atomic64_t *v, long long a, long long u); -EXPORT_SYMBOL(atomic64_add_unless_cx8); - -#ifndef CONFIG_X86_CMPXCHG64 -long long atomic64_read_386(long long, const atomic64_t *v); -EXPORT_SYMBOL(atomic64_read_386); -long long atomic64_set_386(long long, const atomic64_t *v); -EXPORT_SYMBOL(atomic64_set_386); -long long atomic64_xchg_386(long long, unsigned high); -EXPORT_SYMBOL(atomic64_xchg_386); -long long atomic64_add_return_386(long long a, atomic64_t *v); -EXPORT_SYMBOL(atomic64_add_return_386); -long long atomic64_sub_return_386(long long a, atomic64_t *v); -EXPORT_SYMBOL(atomic64_sub_return_386); -long long atomic64_inc_return_386(long long a, atomic64_t *v); -EXPORT_SYMBOL(atomic64_inc_return_386); -long long atomic64_dec_return_386(long long a, atomic64_t *v); -EXPORT_SYMBOL(atomic64_dec_return_386); -long long atomic64_add_386(long long a, atomic64_t *v); -EXPORT_SYMBOL(atomic64_add_386); -long long atomic64_sub_386(long long a, atomic64_t *v); -EXPORT_SYMBOL(atomic64_sub_386); -long long atomic64_inc_386(long long a, atomic64_t *v); -EXPORT_SYMBOL(atomic64_inc_386); -long long atomic64_dec_386(long long a, atomic64_t *v); -EXPORT_SYMBOL(atomic64_dec_386); -long long atomic64_dec_if_positive_386(atomic64_t *v); -EXPORT_SYMBOL(atomic64_dec_if_positive_386); -int atomic64_inc_not_zero_386(atomic64_t *v); -EXPORT_SYMBOL(atomic64_inc_not_zero_386); -int atomic64_add_unless_386(atomic64_t *v, long long a, long long u); -EXPORT_SYMBOL(atomic64_add_unless_386); -#endif diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S index e8e7e0d06f4..00933d5e992 100644 --- a/arch/x86/lib/atomic64_386_32.S +++ b/arch/x86/lib/atomic64_386_32.S @@ -137,13 +137,13 @@ BEGIN(dec_return) RET_ENDP #undef v -#define v %ecx +#define v %esi BEGIN(add_unless) - addl %eax, %esi + addl %eax, %ecx adcl %edx, %edi addl (v), %eax adcl 4(v), %edx - cmpl %eax, %esi + cmpl %eax, %ecx je 3f 1: movl %eax, (v) diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S index 391a083674b..f5cc9eb1d51 100644 --- a/arch/x86/lib/atomic64_cx8_32.S +++ b/arch/x86/lib/atomic64_cx8_32.S @@ -55,8 +55,6 @@ ENDPROC(atomic64_set_cx8) ENTRY(atomic64_xchg_cx8) CFI_STARTPROC - movl %ebx, %eax - movl %ecx, %edx 1: LOCK_PREFIX cmpxchg8b (%esi) @@ -78,7 +76,7 @@ ENTRY(atomic64_\func\()_return_cx8) movl %edx, %edi movl %ecx, %ebp - read64 %ebp + read64 %ecx 1: movl %eax, %ebx movl %edx, %ecx @@ -159,23 +157,22 @@ ENTRY(atomic64_add_unless_cx8) SAVE ebx /* these just push these two parameters on the stack */ SAVE edi - SAVE esi + SAVE ecx - movl %ecx, %ebp - movl %eax, %esi + movl %eax, %ebp movl %edx, %edi - read64 %ebp + read64 %esi 1: cmpl %eax, 0(%esp) je 4f 2: movl %eax, %ebx movl %edx, %ecx - addl %esi, %ebx + addl %ebp, %ebx adcl %edi, %ecx LOCK_PREFIX - cmpxchg8b (%ebp) + cmpxchg8b (%esi) jne 1b movl $1, %eax @@ -199,13 +196,13 @@ ENTRY(atomic64_inc_not_zero_cx8) read64 %esi 1: - testl %eax, %eax - je 4f -2: + movl %eax, %ecx + orl %edx, %ecx + jz 3f movl %eax, %ebx - movl %edx, %ecx + xorl %ecx, %ecx addl $1, %ebx - adcl $0, %ecx + adcl %edx, %ecx LOCK_PREFIX cmpxchg8b (%esi) jne 1b @@ -214,9 +211,5 @@ ENTRY(atomic64_inc_not_zero_cx8) 3: RESTORE ebx ret -4: - testl %edx, %edx - jne 2b - jmp 3b CFI_ENDPROC ENDPROC(atomic64_inc_not_zero_cx8) diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S index 01c805ba535..6b34d04d096 100644 --- a/arch/x86/lib/copy_page_64.S +++ b/arch/x86/lib/copy_page_64.S @@ -20,14 +20,12 @@ ENDPROC(copy_page_c) ENTRY(copy_page) CFI_STARTPROC - subq $3*8,%rsp - CFI_ADJUST_CFA_OFFSET 3*8 + subq $2*8,%rsp + CFI_ADJUST_CFA_OFFSET 2*8 movq %rbx,(%rsp) CFI_REL_OFFSET rbx, 0 movq %r12,1*8(%rsp) CFI_REL_OFFSET r12, 1*8 - movq %r13,2*8(%rsp) - CFI_REL_OFFSET r13, 2*8 movl $(4096/64)-5,%ecx .p2align 4 @@ -91,10 +89,8 @@ ENTRY(copy_page) CFI_RESTORE rbx movq 1*8(%rsp),%r12 CFI_RESTORE r12 - movq 2*8(%rsp),%r13 - CFI_RESTORE r13 - addq $3*8,%rsp - CFI_ADJUST_CFA_OFFSET -3*8 + addq $2*8,%rsp + CFI_ADJUST_CFA_OFFSET -2*8 ret .Lcopy_page_end: CFI_ENDPROC diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index fc45ba887d0..e395693abdb 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -48,9 +48,9 @@ static void delay_loop(unsigned long loops) } /* TSC based delay: */ -static void delay_tsc(unsigned long loops) +static void delay_tsc(unsigned long __loops) { - unsigned long bclock, now; + u32 bclock, now, loops = __loops; int cpu; preempt_disable(); diff --git a/arch/x86/lib/inat.c b/arch/x86/lib/inat.c index 88ad5fbda6e..c1f01a8e9f6 100644 --- a/arch/x86/lib/inat.c +++ b/arch/x86/lib/inat.c @@ -29,46 +29,46 @@ insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode) return inat_primary_table[opcode]; } -insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, insn_byte_t last_pfx, +int inat_get_last_prefix_id(insn_byte_t last_pfx) +{ + insn_attr_t lpfx_attr; + + lpfx_attr = inat_get_opcode_attribute(last_pfx); + return inat_last_prefix_id(lpfx_attr); +} + +insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, int lpfx_id, insn_attr_t esc_attr) { const insn_attr_t *table; - insn_attr_t lpfx_attr; - int n, m = 0; + int n; n = inat_escape_id(esc_attr); - if (last_pfx) { - lpfx_attr = inat_get_opcode_attribute(last_pfx); - m = inat_last_prefix_id(lpfx_attr); - } + table = inat_escape_tables[n][0]; if (!table) return 0; - if (inat_has_variant(table[opcode]) && m) { - table = inat_escape_tables[n][m]; + if (inat_has_variant(table[opcode]) && lpfx_id) { + table = inat_escape_tables[n][lpfx_id]; if (!table) return 0; } return table[opcode]; } -insn_attr_t inat_get_group_attribute(insn_byte_t modrm, insn_byte_t last_pfx, +insn_attr_t inat_get_group_attribute(insn_byte_t modrm, int lpfx_id, insn_attr_t grp_attr) { const insn_attr_t *table; - insn_attr_t lpfx_attr; - int n, m = 0; + int n; n = inat_group_id(grp_attr); - if (last_pfx) { - lpfx_attr = inat_get_opcode_attribute(last_pfx); - m = inat_last_prefix_id(lpfx_attr); - } + table = inat_group_tables[n][0]; if (!table) return inat_group_common_attribute(grp_attr); - if (inat_has_variant(table[X86_MODRM_REG(modrm)]) && m) { - table = inat_group_tables[n][m]; + if (inat_has_variant(table[X86_MODRM_REG(modrm)]) && lpfx_id) { + table = inat_group_tables[n][lpfx_id]; if (!table) return inat_group_common_attribute(grp_attr); } diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c index 5a1f9f3e3fb..25feb1ae71c 100644 --- a/arch/x86/lib/insn.c +++ b/arch/x86/lib/insn.c @@ -185,7 +185,8 @@ err_out: void insn_get_opcode(struct insn *insn) { struct insn_field *opcode = &insn->opcode; - insn_byte_t op, pfx; + insn_byte_t op; + int pfx_id; if (opcode->got) return; if (!insn->prefixes.got) @@ -212,8 +213,8 @@ void insn_get_opcode(struct insn *insn) /* Get escaped opcode */ op = get_next(insn_byte_t, insn); opcode->bytes[opcode->nbytes++] = op; - pfx = insn_last_prefix(insn); - insn->attr = inat_get_escape_attribute(op, pfx, insn->attr); + pfx_id = insn_last_prefix_id(insn); + insn->attr = inat_get_escape_attribute(op, pfx_id, insn->attr); } if (inat_must_vex(insn->attr)) insn->attr = 0; /* This instruction is bad */ @@ -235,7 +236,7 @@ err_out: void insn_get_modrm(struct insn *insn) { struct insn_field *modrm = &insn->modrm; - insn_byte_t pfx, mod; + insn_byte_t pfx_id, mod; if (modrm->got) return; if (!insn->opcode.got) @@ -246,8 +247,8 @@ void insn_get_modrm(struct insn *insn) modrm->value = mod; modrm->nbytes = 1; if (inat_is_group(insn->attr)) { - pfx = insn_last_prefix(insn); - insn->attr = inat_get_group_attribute(mod, pfx, + pfx_id = insn_last_prefix_id(insn); + insn->attr = inat_get_group_attribute(mod, pfx_id, insn->attr); if (insn_is_avx(insn) && !inat_accept_vex(insn->attr)) insn->attr = 0; /* This is bad */ diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index efbf2a0ecde..1c273be7c97 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -27,9 +27,8 @@ .section .altinstr_replacement, "ax", @progbits .Lmemcpy_c: movq %rdi, %rax - - movl %edx, %ecx - shrl $3, %ecx + movq %rdx, %rcx + shrq $3, %rcx andl $7, %edx rep movsq movl %edx, %ecx @@ -48,8 +47,7 @@ .section .altinstr_replacement, "ax", @progbits .Lmemcpy_c_e: movq %rdi, %rax - - movl %edx, %ecx + movq %rdx, %rcx rep movsb ret .Lmemcpy_e_e: @@ -60,10 +58,7 @@ ENTRY(memcpy) CFI_STARTPROC movq %rdi, %rax - /* - * Use 32bit CMP here to avoid long NOP padding. - */ - cmp $0x20, %edx + cmpq $0x20, %rdx jb .Lhandle_tail /* @@ -72,7 +67,7 @@ ENTRY(memcpy) */ cmp %dil, %sil jl .Lcopy_backward - subl $0x20, %edx + subq $0x20, %rdx .Lcopy_forward_loop: subq $0x20, %rdx @@ -91,7 +86,7 @@ ENTRY(memcpy) movq %r11, 3*8(%rdi) leaq 4*8(%rdi), %rdi jae .Lcopy_forward_loop - addq $0x20, %rdx + addl $0x20, %edx jmp .Lhandle_tail .Lcopy_backward: @@ -123,11 +118,11 @@ ENTRY(memcpy) /* * Calculate copy position to head. */ - addq $0x20, %rdx + addl $0x20, %edx subq %rdx, %rsi subq %rdx, %rdi .Lhandle_tail: - cmpq $16, %rdx + cmpl $16, %edx jb .Lless_16bytes /* @@ -144,7 +139,7 @@ ENTRY(memcpy) retq .p2align 4 .Lless_16bytes: - cmpq $8, %rdx + cmpl $8, %edx jb .Lless_8bytes /* * Move data from 8 bytes to 15 bytes. @@ -156,7 +151,7 @@ ENTRY(memcpy) retq .p2align 4 .Lless_8bytes: - cmpq $4, %rdx + cmpl $4, %edx jb .Lless_3bytes /* @@ -169,18 +164,19 @@ ENTRY(memcpy) retq .p2align 4 .Lless_3bytes: - cmpl $0, %edx - je .Lend + subl $1, %edx + jb .Lend /* * Move data from 1 bytes to 3 bytes. */ -.Lloop_1: - movb (%rsi), %r8b - movb %r8b, (%rdi) - incq %rdi - incq %rsi - decl %edx - jnz .Lloop_1 + movzbl (%rsi), %ecx + jz .Lstore_1byte + movzbq 1(%rsi), %r8 + movzbq (%rsi, %rdx), %r9 + movb %r8b, 1(%rdi) + movb %r9b, (%rdi, %rdx) +.Lstore_1byte: + movb %cl, (%rdi) .Lend: retq diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S index 79bd454b78a..2dcb3808cbd 100644 --- a/arch/x86/lib/memset_64.S +++ b/arch/x86/lib/memset_64.S @@ -19,16 +19,15 @@ .section .altinstr_replacement, "ax", @progbits .Lmemset_c: movq %rdi,%r9 - movl %edx,%r8d - andl $7,%r8d - movl %edx,%ecx - shrl $3,%ecx + movq %rdx,%rcx + andl $7,%edx + shrq $3,%rcx /* expand byte value */ movzbl %sil,%esi movabs $0x0101010101010101,%rax - mulq %rsi /* with rax, clobbers rdx */ + imulq %rsi,%rax rep stosq - movl %r8d,%ecx + movl %edx,%ecx rep stosb movq %r9,%rax ret @@ -50,7 +49,7 @@ .Lmemset_c_e: movq %rdi,%r9 movb %sil,%al - movl %edx,%ecx + movq %rdx,%rcx rep stosb movq %r9,%rax ret @@ -61,12 +60,11 @@ ENTRY(memset) ENTRY(__memset) CFI_STARTPROC movq %rdi,%r10 - movq %rdx,%r11 /* expand byte value */ movzbl %sil,%ecx movabs $0x0101010101010101,%rax - mul %rcx /* with rax, clobbers rdx */ + imulq %rcx,%rax /* align dst */ movl %edi,%r9d @@ -75,13 +73,13 @@ ENTRY(__memset) CFI_REMEMBER_STATE .Lafter_bad_alignment: - movl %r11d,%ecx - shrl $6,%ecx + movq %rdx,%rcx + shrq $6,%rcx jz .Lhandle_tail .p2align 4 .Lloop_64: - decl %ecx + decq %rcx movq %rax,(%rdi) movq %rax,8(%rdi) movq %rax,16(%rdi) @@ -97,7 +95,7 @@ ENTRY(__memset) to predict jump tables. */ .p2align 4 .Lhandle_tail: - movl %r11d,%ecx + movl %edx,%ecx andl $63&(~7),%ecx jz .Lhandle_7 shrl $3,%ecx @@ -109,12 +107,11 @@ ENTRY(__memset) jnz .Lloop_8 .Lhandle_7: - movl %r11d,%ecx - andl $7,%ecx + andl $7,%edx jz .Lende .p2align 4 .Lloop_1: - decl %ecx + decl %edx movb %al,(%rdi) leaq 1(%rdi),%rdi jnz .Lloop_1 @@ -125,13 +122,13 @@ ENTRY(__memset) CFI_RESTORE_STATE .Lbad_alignment: - cmpq $7,%r11 + cmpq $7,%rdx jbe .Lhandle_7 movq %rax,(%rdi) /* unaligned store */ movq $8,%r8 subq %r9,%r8 addq %r8,%rdi - subq %r8,%r11 + subq %r8,%rdx jmp .Lafter_bad_alignment .Lfinal: CFI_ENDPROC diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c index 97be9cb5448..57252c928f5 100644 --- a/arch/x86/lib/usercopy.c +++ b/arch/x86/lib/usercopy.c @@ -7,6 +7,8 @@ #include <linux/highmem.h> #include <linux/module.h> +#include <asm/word-at-a-time.h> + /* * best effort, GUP based copy_from_user() that is NMI-safe */ @@ -41,3 +43,104 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n) return len; } EXPORT_SYMBOL_GPL(copy_from_user_nmi); + +static inline unsigned long count_bytes(unsigned long mask) +{ + mask = (mask - 1) & ~mask; + mask >>= 7; + return count_masked_bytes(mask); +} + +/* + * Do a strncpy, return length of string without final '\0'. + * 'count' is the user-supplied count (return 'count' if we + * hit it), 'max' is the address space maximum (and we return + * -EFAULT if we hit it). + */ +static inline long do_strncpy_from_user(char *dst, const char __user *src, long count, long max) +{ + long res = 0; + + /* + * Truncate 'max' to the user-specified limit, so that + * we only have one limit we need to check in the loop + */ + if (max > count) + max = count; + + while (max >= sizeof(unsigned long)) { + unsigned long c; + + /* Fall back to byte-at-a-time if we get a page fault */ + if (unlikely(__get_user(c,(unsigned long __user *)(src+res)))) + break; + /* This can write a few bytes past the NUL character, but that's ok */ + *(unsigned long *)(dst+res) = c; + c = has_zero(c); + if (c) + return res + count_bytes(c); + res += sizeof(unsigned long); + max -= sizeof(unsigned long); + } + + while (max) { + char c; + + if (unlikely(__get_user(c,src+res))) + return -EFAULT; + dst[res] = c; + if (!c) + return res; + res++; + max--; + } + + /* + * Uhhuh. We hit 'max'. But was that the user-specified maximum + * too? If so, that's ok - we got as much as the user asked for. + */ + if (res >= count) + return count; + + /* + * Nope: we hit the address space limit, and we still had more + * characters the caller would have wanted. That's an EFAULT. + */ + return -EFAULT; +} + +/** + * strncpy_from_user: - Copy a NUL terminated string from userspace. + * @dst: Destination address, in kernel space. This buffer must be at + * least @count bytes long. + * @src: Source address, in user space. + * @count: Maximum number of bytes to copy, including the trailing NUL. + * + * Copies a NUL-terminated string from userspace to kernel space. + * + * On success, returns the length of the string (not including the trailing + * NUL). + * + * If access to userspace fails, returns -EFAULT (some data may have been + * copied). + * + * If @count is smaller than the length of the string, copies @count bytes + * and returns @count. + */ +long +strncpy_from_user(char *dst, const char __user *src, long count) +{ + unsigned long max_addr, src_addr; + + if (unlikely(count <= 0)) + return 0; + + max_addr = current_thread_info()->addr_limit.seg; + src_addr = (unsigned long)src; + if (likely(src_addr < max_addr)) { + unsigned long max = max_addr - src_addr; + return do_strncpy_from_user(dst, src, count, max); + } + return -EFAULT; +} +EXPORT_SYMBOL(strncpy_from_user); diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index e218d5df85f..ef2a6a5d78e 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -33,93 +33,6 @@ static inline int __movsl_is_ok(unsigned long a1, unsigned long a2, unsigned lon __movsl_is_ok((unsigned long)(a1), (unsigned long)(a2), (n)) /* - * Copy a null terminated string from userspace. - */ - -#define __do_strncpy_from_user(dst, src, count, res) \ -do { \ - int __d0, __d1, __d2; \ - might_fault(); \ - __asm__ __volatile__( \ - " testl %1,%1\n" \ - " jz 2f\n" \ - "0: lodsb\n" \ - " stosb\n" \ - " testb %%al,%%al\n" \ - " jz 1f\n" \ - " decl %1\n" \ - " jnz 0b\n" \ - "1: subl %1,%0\n" \ - "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: movl %5,%0\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(0b,3b) \ - : "=&d"(res), "=&c"(count), "=&a" (__d0), "=&S" (__d1), \ - "=&D" (__d2) \ - : "i"(-EFAULT), "0"(count), "1"(count), "3"(src), "4"(dst) \ - : "memory"); \ -} while (0) - -/** - * __strncpy_from_user: - Copy a NUL terminated string from userspace, with less checking. - * @dst: Destination address, in kernel space. This buffer must be at - * least @count bytes long. - * @src: Source address, in user space. - * @count: Maximum number of bytes to copy, including the trailing NUL. - * - * Copies a NUL-terminated string from userspace to kernel space. - * Caller must check the specified block with access_ok() before calling - * this function. - * - * On success, returns the length of the string (not including the trailing - * NUL). - * - * If access to userspace fails, returns -EFAULT (some data may have been - * copied). - * - * If @count is smaller than the length of the string, copies @count bytes - * and returns @count. - */ -long -__strncpy_from_user(char *dst, const char __user *src, long count) -{ - long res; - __do_strncpy_from_user(dst, src, count, res); - return res; -} -EXPORT_SYMBOL(__strncpy_from_user); - -/** - * strncpy_from_user: - Copy a NUL terminated string from userspace. - * @dst: Destination address, in kernel space. This buffer must be at - * least @count bytes long. - * @src: Source address, in user space. - * @count: Maximum number of bytes to copy, including the trailing NUL. - * - * Copies a NUL-terminated string from userspace to kernel space. - * - * On success, returns the length of the string (not including the trailing - * NUL). - * - * If access to userspace fails, returns -EFAULT (some data may have been - * copied). - * - * If @count is smaller than the length of the string, copies @count bytes - * and returns @count. - */ -long -strncpy_from_user(char *dst, const char __user *src, long count) -{ - long res = -EFAULT; - if (access_ok(VERIFY_READ, src, 1)) - __do_strncpy_from_user(dst, src, count, res); - return res; -} -EXPORT_SYMBOL(strncpy_from_user); - -/* * Zero Userspace */ @@ -760,9 +673,9 @@ survive: break; } - maddr = kmap_atomic(pg, KM_USER0); + maddr = kmap_atomic(pg); memcpy(maddr + offset, from, len); - kunmap_atomic(maddr, KM_USER0); + kunmap_atomic(maddr); set_page_dirty_lock(pg); put_page(pg); up_read(¤t->mm->mmap_sem); diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index b7c2849ffb6..0d0326f388c 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -9,55 +9,6 @@ #include <asm/uaccess.h> /* - * Copy a null terminated string from userspace. - */ - -#define __do_strncpy_from_user(dst,src,count,res) \ -do { \ - long __d0, __d1, __d2; \ - might_fault(); \ - __asm__ __volatile__( \ - " testq %1,%1\n" \ - " jz 2f\n" \ - "0: lodsb\n" \ - " stosb\n" \ - " testb %%al,%%al\n" \ - " jz 1f\n" \ - " decq %1\n" \ - " jnz 0b\n" \ - "1: subq %1,%0\n" \ - "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: movq %5,%0\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(0b,3b) \ - : "=&r"(res), "=&c"(count), "=&a" (__d0), "=&S" (__d1), \ - "=&D" (__d2) \ - : "i"(-EFAULT), "0"(count), "1"(count), "3"(src), "4"(dst) \ - : "memory"); \ -} while (0) - -long -__strncpy_from_user(char *dst, const char __user *src, long count) -{ - long res; - __do_strncpy_from_user(dst, src, count, res); - return res; -} -EXPORT_SYMBOL(__strncpy_from_user); - -long -strncpy_from_user(char *dst, const char __user *src, long count) -{ - long res = -EFAULT; - if (access_ok(VERIFY_READ, src, 1)) - return __strncpy_from_user(dst, src, count); - return res; -} -EXPORT_SYMBOL(strncpy_from_user); - -/* * Zero Userspace */ diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index 5b83c51c12e..81913790442 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -219,7 +219,9 @@ ab: STOS/W/D/Q Yv,rAX ac: LODS/B AL,Xb ad: LODS/W/D/Q rAX,Xv ae: SCAS/B AL,Yb -af: SCAS/W/D/Q rAX,Xv +# Note: The May 2011 Intel manual shows Xv for the second parameter of the +# next instruction but Yv is correct +af: SCAS/W/D/Q rAX,Yv # 0xb0 - 0xbf b0: MOV AL/R8L,Ib b1: MOV CL/R9L,Ib @@ -729,8 +731,8 @@ de: VAESDEC Vdq,Hdq,Wdq (66),(v1) df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1) f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) -f3: ANDN Gy,By,Ey (v) -f4: Grp17 (1A) +f2: ANDN Gy,By,Ey (v) +f3: Grp17 (1A) f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v) f6: MULX By,Gy,rDX,Ey (F2),(v) f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v) diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c index 7718541541d..9b868124128 100644 --- a/arch/x86/math-emu/fpu_entry.c +++ b/arch/x86/math-emu/fpu_entry.c @@ -28,6 +28,7 @@ #include <linux/regset.h> #include <asm/uaccess.h> +#include <asm/traps.h> #include <asm/desc.h> #include <asm/user.h> #include <asm/i387.h> @@ -269,7 +270,7 @@ void math_emulate(struct math_emu_info *info) FPU_EIP = FPU_ORIG_EIP; /* Point to current FPU instruction. */ RE_ENTRANT_CHECK_OFF; - current->thread.trap_no = 16; + current->thread.trap_nr = X86_TRAP_MF; current->thread.error_code = 0; send_sig(SIGFPE, current, 1); return; @@ -662,7 +663,7 @@ static int valid_prefix(u_char *Byte, u_char __user **fpu_eip, void math_abort(struct math_emu_info *info, unsigned int signal) { FPU_EIP = FPU_ORIG_EIP; - current->thread.trap_no = 16; + current->thread.trap_nr = X86_TRAP_MF; current->thread.error_code = 0; send_sig(signal, current, 1); RE_ENTRANT_CHECK_OFF; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 9d74824a708..3ecfd1aaf21 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -615,7 +615,7 @@ pgtable_bad(struct pt_regs *regs, unsigned long error_code, dump_pagetable(address); tsk->thread.cr2 = address; - tsk->thread.trap_no = 14; + tsk->thread.trap_nr = X86_TRAP_PF; tsk->thread.error_code = error_code; if (__die("Bad pagetable", regs, error_code)) @@ -636,7 +636,7 @@ no_context(struct pt_regs *regs, unsigned long error_code, /* Are we prepared to handle this kernel fault? */ if (fixup_exception(regs)) { if (current_thread_info()->sig_on_uaccess_error && signal) { - tsk->thread.trap_no = 14; + tsk->thread.trap_nr = X86_TRAP_PF; tsk->thread.error_code = error_code | PF_USER; tsk->thread.cr2 = address; @@ -673,10 +673,10 @@ no_context(struct pt_regs *regs, unsigned long error_code, stackend = end_of_stack(tsk); if (tsk != &init_task && *stackend != STACK_END_MAGIC) - printk(KERN_ALERT "Thread overran stack, or stack corrupted\n"); + printk(KERN_EMERG "Thread overran stack, or stack corrupted\n"); tsk->thread.cr2 = address; - tsk->thread.trap_no = 14; + tsk->thread.trap_nr = X86_TRAP_PF; tsk->thread.error_code = error_code; sig = SIGKILL; @@ -684,7 +684,7 @@ no_context(struct pt_regs *regs, unsigned long error_code, sig = 0; /* Executive summary in case the body of the oops scrolled away */ - printk(KERN_EMERG "CR2: %016lx\n", address); + printk(KERN_DEFAULT "CR2: %016lx\n", address); oops_end(flags, regs, sig); } @@ -754,7 +754,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, /* Kernel addresses are always protection faults: */ tsk->thread.cr2 = address; tsk->thread.error_code = error_code | (address >= TASK_SIZE); - tsk->thread.trap_no = 14; + tsk->thread.trap_nr = X86_TRAP_PF; force_sig_info_fault(SIGSEGV, si_code, address, tsk, 0); @@ -838,7 +838,7 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, tsk->thread.cr2 = address; tsk->thread.error_code = error_code; - tsk->thread.trap_no = 14; + tsk->thread.trap_nr = X86_TRAP_PF; #ifdef CONFIG_MEMORY_FAILURE if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) { diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index f4f29b19fac..6f31ee56c00 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -51,11 +51,11 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot) } EXPORT_SYMBOL(kmap_atomic_prot); -void *__kmap_atomic(struct page *page) +void *kmap_atomic(struct page *page) { return kmap_atomic_prot(page, kmap_prot); } -EXPORT_SYMBOL(__kmap_atomic); +EXPORT_SYMBOL(kmap_atomic); /* * This is the same as kmap_atomic() but can map memory that doesn't diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index f581a18c0d4..f6679a7fb8c 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -308,10 +308,11 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, { struct hstate *h = hstate_file(file); struct mm_struct *mm = current->mm; - struct vm_area_struct *vma, *prev_vma; - unsigned long base = mm->mmap_base, addr = addr0; + struct vm_area_struct *vma; + unsigned long base = mm->mmap_base; + unsigned long addr = addr0; unsigned long largest_hole = mm->cached_hole_size; - int first_time = 1; + unsigned long start_addr; /* don't allow allocations above current base */ if (mm->free_area_cache > base) @@ -322,6 +323,8 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, mm->free_area_cache = base; } try_again: + start_addr = mm->free_area_cache; + /* make sure it can fit in the remaining address space */ if (mm->free_area_cache < len) goto fail; @@ -333,24 +336,18 @@ try_again: * Lookup failure means no vma is above this address, * i.e. return with success: */ - if (!(vma = find_vma_prev(mm, addr, &prev_vma))) + vma = find_vma(mm, addr); + if (!vma) return addr; - /* - * new region fits between prev_vma->vm_end and - * vma->vm_start, use it: - */ - if (addr + len <= vma->vm_start && - (!prev_vma || (addr >= prev_vma->vm_end))) { + if (addr + len <= vma->vm_start) { /* remember the address as a hint for next time */ mm->cached_hole_size = largest_hole; return (mm->free_area_cache = addr); - } else { + } else if (mm->free_area_cache == vma->vm_end) { /* pull free_area_cache down to the first hole */ - if (mm->free_area_cache == vma->vm_end) { - mm->free_area_cache = vma->vm_start; - mm->cached_hole_size = largest_hole; - } + mm->free_area_cache = vma->vm_start; + mm->cached_hole_size = largest_hole; } /* remember the largest hole we saw so far */ @@ -366,10 +363,9 @@ fail: * if hint left us with no space for the requested * mapping then try again: */ - if (first_time) { + if (start_addr != base) { mm->free_area_cache = base; largest_hole = 0; - first_time = 0; goto try_again; } /* diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index a298914058f..4f0cec7e4ff 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -3,6 +3,7 @@ #include <linux/ioport.h> #include <linux/swap.h> #include <linux/memblock.h> +#include <linux/bootmem.h> /* for max_low_pfn */ #include <asm/cacheflush.h> #include <asm/e820.h> @@ -11,10 +12,10 @@ #include <asm/page_types.h> #include <asm/sections.h> #include <asm/setup.h> -#include <asm/system.h> #include <asm/tlbflush.h> #include <asm/tlb.h> #include <asm/proto.h> +#include <asm/dma.h> /* for MAX_DMA_PFN */ unsigned long __initdata pgt_buf_start; unsigned long __meminitdata pgt_buf_end; @@ -392,3 +393,24 @@ void free_initrd_mem(unsigned long start, unsigned long end) free_init_pages("initrd memory", start, PAGE_ALIGN(end)); } #endif + +void __init zone_sizes_init(void) +{ + unsigned long max_zone_pfns[MAX_NR_ZONES]; + + memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); + +#ifdef CONFIG_ZONE_DMA + max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN; +#endif +#ifdef CONFIG_ZONE_DMA32 + max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN; +#endif + max_zone_pfns[ZONE_NORMAL] = max_low_pfn; +#ifdef CONFIG_HIGHMEM + max_zone_pfns[ZONE_HIGHMEM] = max_pfn; +#endif + + free_area_init_nodes(max_zone_pfns); +} + diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 0c1da394a63..575d86f85ce 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -35,7 +35,6 @@ #include <asm/asm.h> #include <asm/bios_ebda.h> #include <asm/processor.h> -#include <asm/system.h> #include <asm/uaccess.h> #include <asm/pgtable.h> #include <asm/dma.h> @@ -668,22 +667,6 @@ void __init initmem_init(void) } #endif /* !CONFIG_NEED_MULTIPLE_NODES */ -static void __init zone_sizes_init(void) -{ - unsigned long max_zone_pfns[MAX_NR_ZONES]; - memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); -#ifdef CONFIG_ZONE_DMA - max_zone_pfns[ZONE_DMA] = - virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT; -#endif - max_zone_pfns[ZONE_NORMAL] = max_low_pfn; -#ifdef CONFIG_HIGHMEM - max_zone_pfns[ZONE_HIGHMEM] = highend_pfn; -#endif - - free_area_init_nodes(max_zone_pfns); -} - void __init setup_bootmem_allocator(void) { printk(KERN_INFO " mapped low ram: 0 - %08lx\n", @@ -754,6 +737,17 @@ void __init mem_init(void) #ifdef CONFIG_FLATMEM BUG_ON(!mem_map); #endif + /* + * With CONFIG_DEBUG_PAGEALLOC initialization of highmem pages has to + * be done before free_all_bootmem(). Memblock use free low memory for + * temporary data (see find_range_array()) and for this purpose can use + * pages that was already passed to the buddy allocator, hence marked as + * not accessible in the page tables when compiled with + * CONFIG_DEBUG_PAGEALLOC. Otherwise order of initialization is not + * important here. + */ + set_highmem_pages_init(); + /* this will put all low memory onto the freelists */ totalram_pages += free_all_bootmem(); @@ -765,8 +759,6 @@ void __init mem_init(void) if (page_is_ram(tmp) && PageReserved(pfn_to_page(tmp))) reservedpages++; - set_highmem_pages_init(); - codesize = (unsigned long) &_etext - (unsigned long) &_text; datasize = (unsigned long) &_edata - (unsigned long) &_etext; initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index a8a56ce3a96..fc18be0f6f2 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -35,7 +35,6 @@ #include <asm/processor.h> #include <asm/bios_ebda.h> -#include <asm/system.h> #include <asm/uaccess.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> @@ -614,15 +613,6 @@ void __init initmem_init(void) void __init paging_init(void) { - unsigned long max_zone_pfns[MAX_NR_ZONES]; - - memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); -#ifdef CONFIG_ZONE_DMA - max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN; -#endif - max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN; - max_zone_pfns[ZONE_NORMAL] = max_pfn; - sparse_memory_present_with_active_regions(MAX_NUMNODES); sparse_init(); @@ -634,7 +624,7 @@ void __init paging_init(void) */ node_clear_state(0, N_NORMAL_MEMORY); - free_area_init_nodes(max_zone_pfns); + zone_sizes_init(); } /* diff --git a/arch/x86/mm/kmemcheck/selftest.c b/arch/x86/mm/kmemcheck/selftest.c index 036efbea8b2..aef7140c006 100644 --- a/arch/x86/mm/kmemcheck/selftest.c +++ b/arch/x86/mm/kmemcheck/selftest.c @@ -1,3 +1,4 @@ +#include <linux/bug.h> #include <linux/kernel.h> #include "opcode.h" diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 4b5ba85eb5c..845df6835f9 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -75,9 +75,9 @@ static unsigned long mmap_rnd(void) */ if (current->flags & PF_RANDOMIZE) { if (mmap_is_ia32()) - rnd = (long)get_random_int() % (1<<8); + rnd = get_random_int() % (1<<8); else - rnd = (long)(get_random_int() % (1<<28)); + rnd = get_random_int() % (1<<28); } return rnd << PAGE_SHIFT; } diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index de54b9b278a..dc0b727742f 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -75,8 +75,8 @@ static LIST_HEAD(trace_list); /* struct remap_trace */ /* module parameters */ static unsigned long filter_offset; -static int nommiotrace; -static int trace_pc; +static bool nommiotrace; +static bool trace_pc; module_param(filter_offset, ulong, 0); module_param(nommiotrace, bool, 0); diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 496f494593b..19d3fa08b11 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -110,7 +110,7 @@ void __cpuinit numa_clear_node(int cpu) * Allocate node_to_cpumask_map based on number of available nodes * Requires node_possible_map to be valid. * - * Note: node_to_cpumask() is not valid until after this is done. + * Note: cpumask_of_node() is not valid until after this is done. * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.) */ void __init setup_node_to_cpumask_map(void) @@ -422,8 +422,9 @@ static int __init numa_alloc_distance(void) * calls are ignored until the distance table is reset with * numa_reset_distance(). * - * If @from or @to is higher than the highest known node at the time of - * table creation or @distance doesn't make sense, the call is ignored. + * If @from or @to is higher than the highest known node or lower than zero + * at the time of table creation or @distance doesn't make sense, the call + * is ignored. * This is to allow simplification of specific NUMA config implementations. */ void __init numa_set_distance(int from, int to, int distance) @@ -431,8 +432,9 @@ void __init numa_set_distance(int from, int to, int distance) if (!numa_distance && numa_alloc_distance() < 0) return; - if (from >= numa_distance_cnt || to >= numa_distance_cnt) { - printk_once(KERN_DEBUG "NUMA: Debug: distance out of bound, from=%d to=%d distance=%d\n", + if (from >= numa_distance_cnt || to >= numa_distance_cnt || + from < 0 || to < 0) { + pr_warn_once("NUMA: Warning: node ids are out of bound, from=%d to=%d distance=%d\n", from, to, distance); return; } diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index 46db56845f1..53489ff6bf8 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -28,7 +28,7 @@ static int __init emu_find_memblk_by_nid(int nid, const struct numa_meminfo *mi) return -ENOENT; } -static u64 mem_hole_size(u64 start, u64 end) +static u64 __init mem_hole_size(u64 start, u64 end) { unsigned long start_pfn = PFN_UP(start); unsigned long end_pfn = PFN_DOWN(end); @@ -60,7 +60,7 @@ static int __init emu_setup_memblk(struct numa_meminfo *ei, eb->nid = nid; if (emu_nid_to_phys[nid] == NUMA_NO_NODE) - emu_nid_to_phys[nid] = pb->nid; + emu_nid_to_phys[nid] = nid; pb->start += size; if (pb->start >= pb->end) { diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index eda2acbb6e8..e1ebde31521 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -1334,12 +1334,6 @@ void kernel_map_pages(struct page *page, int numpages, int enable) } /* - * If page allocator is not up yet then do not call c_p_a(): - */ - if (!debug_pagealloc_enabled) - return; - - /* * The return value is ignored as the calls cannot fail. * Large pages for identity mappings are not used at boot time * and hence no memory allocations during large page split. diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index cac71849925..a69bcb8c762 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -10,7 +10,6 @@ #include <linux/spinlock.h> #include <linux/module.h> -#include <asm/system.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/fixmap.h> diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index fd61b3fb734..efb5b4b9371 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -70,7 +70,7 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa) return; pxm = pa->proximity_domain; apic_id = pa->apic_id; - if (!cpu_has_x2apic && (apic_id >= 0xff)) { + if (!apic->apic_id_valid(apic_id)) { printk(KERN_INFO "SRAT: PXM %u -> X2APIC 0x%04x ignored\n", pxm, apic_id); return; @@ -109,6 +109,8 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) if ((pa->flags & ACPI_SRAT_CPU_ENABLED) == 0) return; pxm = pa->proximity_domain_lo; + if (acpi_srat_revision >= 2) + pxm |= *((unsigned int*)pa->proximity_domain_hi) << 8; node = setup_node(pxm); if (node < 0) { printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm); @@ -160,6 +162,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) start = ma->base_address; end = start + ma->length; pxm = ma->proximity_domain; + if (acpi_srat_revision <= 1) + pxm &= 0xff; node = setup_node(pxm); if (node < 0) { printk(KERN_ERR "SRAT: Too many proximity domains.\n"); diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S index 66870223f8c..877b9a1b215 100644 --- a/arch/x86/net/bpf_jit.S +++ b/arch/x86/net/bpf_jit.S @@ -18,17 +18,17 @@ * r9d : hlen = skb->len - skb->data_len */ #define SKBDATA %r8 - -sk_load_word_ind: - .globl sk_load_word_ind - - add %ebx,%esi /* offset += X */ -# test %esi,%esi /* if (offset < 0) goto bpf_error; */ - js bpf_error +#define SKF_MAX_NEG_OFF $(-0x200000) /* SKF_LL_OFF from filter.h */ sk_load_word: .globl sk_load_word + test %esi,%esi + js bpf_slow_path_word_neg + +sk_load_word_positive_offset: + .globl sk_load_word_positive_offset + mov %r9d,%eax # hlen sub %esi,%eax # hlen - offset cmp $3,%eax @@ -37,16 +37,15 @@ sk_load_word: bswap %eax /* ntohl() */ ret - -sk_load_half_ind: - .globl sk_load_half_ind - - add %ebx,%esi /* offset += X */ - js bpf_error - sk_load_half: .globl sk_load_half + test %esi,%esi + js bpf_slow_path_half_neg + +sk_load_half_positive_offset: + .globl sk_load_half_positive_offset + mov %r9d,%eax sub %esi,%eax # hlen - offset cmp $1,%eax @@ -55,14 +54,15 @@ sk_load_half: rol $8,%ax # ntohs() ret -sk_load_byte_ind: - .globl sk_load_byte_ind - add %ebx,%esi /* offset += X */ - js bpf_error - sk_load_byte: .globl sk_load_byte + test %esi,%esi + js bpf_slow_path_byte_neg + +sk_load_byte_positive_offset: + .globl sk_load_byte_positive_offset + cmp %esi,%r9d /* if (offset >= hlen) goto bpf_slow_path_byte */ jle bpf_slow_path_byte movzbl (SKBDATA,%rsi),%eax @@ -73,25 +73,21 @@ sk_load_byte: * * Implements BPF_S_LDX_B_MSH : ldxb 4*([offset]&0xf) * Must preserve A accumulator (%eax) - * Inputs : %esi is the offset value, already known positive + * Inputs : %esi is the offset value */ -ENTRY(sk_load_byte_msh) - CFI_STARTPROC +sk_load_byte_msh: + .globl sk_load_byte_msh + test %esi,%esi + js bpf_slow_path_byte_msh_neg + +sk_load_byte_msh_positive_offset: + .globl sk_load_byte_msh_positive_offset cmp %esi,%r9d /* if (offset >= hlen) goto bpf_slow_path_byte_msh */ jle bpf_slow_path_byte_msh movzbl (SKBDATA,%rsi),%ebx and $15,%bl shl $2,%bl ret - CFI_ENDPROC -ENDPROC(sk_load_byte_msh) - -bpf_error: -# force a return 0 from jit handler - xor %eax,%eax - mov -8(%rbp),%rbx - leaveq - ret /* rsi contains offset and can be scratched */ #define bpf_slow_path_common(LEN) \ @@ -138,3 +134,67 @@ bpf_slow_path_byte_msh: shl $2,%al xchg %eax,%ebx ret + +#define sk_negative_common(SIZE) \ + push %rdi; /* save skb */ \ + push %r9; \ + push SKBDATA; \ +/* rsi already has offset */ \ + mov $SIZE,%ecx; /* size */ \ + call bpf_internal_load_pointer_neg_helper; \ + test %rax,%rax; \ + pop SKBDATA; \ + pop %r9; \ + pop %rdi; \ + jz bpf_error + + +bpf_slow_path_word_neg: + cmp SKF_MAX_NEG_OFF, %esi /* test range */ + jl bpf_error /* offset lower -> error */ +sk_load_word_negative_offset: + .globl sk_load_word_negative_offset + sk_negative_common(4) + mov (%rax), %eax + bswap %eax + ret + +bpf_slow_path_half_neg: + cmp SKF_MAX_NEG_OFF, %esi + jl bpf_error +sk_load_half_negative_offset: + .globl sk_load_half_negative_offset + sk_negative_common(2) + mov (%rax),%ax + rol $8,%ax + movzwl %ax,%eax + ret + +bpf_slow_path_byte_neg: + cmp SKF_MAX_NEG_OFF, %esi + jl bpf_error +sk_load_byte_negative_offset: + .globl sk_load_byte_negative_offset + sk_negative_common(1) + movzbl (%rax), %eax + ret + +bpf_slow_path_byte_msh_neg: + cmp SKF_MAX_NEG_OFF, %esi + jl bpf_error +sk_load_byte_msh_negative_offset: + .globl sk_load_byte_msh_negative_offset + xchg %eax,%ebx /* dont lose A , X is about to be scratched */ + sk_negative_common(1) + movzbl (%rax),%eax + and $15,%al + shl $2,%al + xchg %eax,%ebx + ret + +bpf_error: +# force a return 0 from jit handler + xor %eax,%eax + mov -8(%rbp),%rbx + leaveq + ret diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 7b65f752c5f..0597f95b6da 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -30,7 +30,10 @@ int bpf_jit_enable __read_mostly; * assembly code in arch/x86/net/bpf_jit.S */ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[]; -extern u8 sk_load_word_ind[], sk_load_half_ind[], sk_load_byte_ind[]; +extern u8 sk_load_word_positive_offset[], sk_load_half_positive_offset[]; +extern u8 sk_load_byte_positive_offset[], sk_load_byte_msh_positive_offset[]; +extern u8 sk_load_word_negative_offset[], sk_load_half_negative_offset[]; +extern u8 sk_load_byte_negative_offset[], sk_load_byte_msh_negative_offset[]; static inline u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) { @@ -117,6 +120,8 @@ static inline void bpf_flush_icache(void *start, void *end) set_fs(old_fs); } +#define CHOOSE_LOAD_FUNC(K, func) \ + ((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset) void bpf_jit_compile(struct sk_filter *fp) { @@ -151,17 +156,18 @@ void bpf_jit_compile(struct sk_filter *fp) cleanup_addr = proglen; /* epilogue address */ for (pass = 0; pass < 10; pass++) { + u8 seen_or_pass0 = (pass == 0) ? (SEEN_XREG | SEEN_DATAREF | SEEN_MEM) : seen; /* no prologue/epilogue for trivial filters (RET something) */ proglen = 0; prog = temp; - if (seen) { + if (seen_or_pass0) { EMIT4(0x55, 0x48, 0x89, 0xe5); /* push %rbp; mov %rsp,%rbp */ EMIT4(0x48, 0x83, 0xec, 96); /* subq $96,%rsp */ /* note : must save %rbx in case bpf_error is hit */ - if (seen & (SEEN_XREG | SEEN_DATAREF)) + if (seen_or_pass0 & (SEEN_XREG | SEEN_DATAREF)) EMIT4(0x48, 0x89, 0x5d, 0xf8); /* mov %rbx, -8(%rbp) */ - if (seen & SEEN_XREG) + if (seen_or_pass0 & SEEN_XREG) CLEAR_X(); /* make sure we dont leek kernel memory */ /* @@ -170,7 +176,7 @@ void bpf_jit_compile(struct sk_filter *fp) * r9 = skb->len - skb->data_len * r8 = skb->data */ - if (seen & SEEN_DATAREF) { + if (seen_or_pass0 & SEEN_DATAREF) { if (offsetof(struct sk_buff, len) <= 127) /* mov off8(%rdi),%r9d */ EMIT4(0x44, 0x8b, 0x4f, offsetof(struct sk_buff, len)); @@ -260,9 +266,14 @@ void bpf_jit_compile(struct sk_filter *fp) case BPF_S_ALU_DIV_X: /* A /= X; */ seen |= SEEN_XREG; EMIT2(0x85, 0xdb); /* test %ebx,%ebx */ - if (pc_ret0 != -1) - EMIT_COND_JMP(X86_JE, addrs[pc_ret0] - (addrs[i] - 4)); - else { + if (pc_ret0 > 0) { + /* addrs[pc_ret0 - 1] is start address of target + * (addrs[i] - 4) is the address following this jmp + * ("xor %edx,%edx; div %ebx" being 4 bytes long) + */ + EMIT_COND_JMP(X86_JE, addrs[pc_ret0 - 1] - + (addrs[i] - 4)); + } else { EMIT_COND_JMP(X86_JNE, 2 + 5); CLEAR_A(); EMIT1_off32(0xe9, cleanup_addr - (addrs[i] - 4)); /* jmp .+off32 */ @@ -283,7 +294,7 @@ void bpf_jit_compile(struct sk_filter *fp) EMIT2(0x24, K & 0xFF); /* and imm8,%al */ } else if (K >= 0xFFFF0000) { EMIT2(0x66, 0x25); /* and imm16,%ax */ - EMIT2(K, 2); + EMIT(K, 2); } else { EMIT1_off32(0x25, K); /* and imm32,%eax */ } @@ -335,12 +346,12 @@ void bpf_jit_compile(struct sk_filter *fp) } /* fallinto */ case BPF_S_RET_A: - if (seen) { + if (seen_or_pass0) { if (i != flen - 1) { EMIT_JMP(cleanup_addr - addrs[i]); break; } - if (seen & SEEN_XREG) + if (seen_or_pass0 & SEEN_XREG) EMIT4(0x48, 0x8b, 0x5d, 0xf8); /* mov -8(%rbp),%rbx */ EMIT1(0xc9); /* leaveq */ } @@ -467,47 +478,46 @@ void bpf_jit_compile(struct sk_filter *fp) #endif break; case BPF_S_LD_W_ABS: - func = sk_load_word; + func = CHOOSE_LOAD_FUNC(K, sk_load_word); common_load: seen |= SEEN_DATAREF; - if ((int)K < 0) - goto out; t_offset = func - (image + addrs[i]); EMIT1_off32(0xbe, K); /* mov imm32,%esi */ EMIT1_off32(0xe8, t_offset); /* call */ break; case BPF_S_LD_H_ABS: - func = sk_load_half; + func = CHOOSE_LOAD_FUNC(K, sk_load_half); goto common_load; case BPF_S_LD_B_ABS: - func = sk_load_byte; + func = CHOOSE_LOAD_FUNC(K, sk_load_byte); goto common_load; case BPF_S_LDX_B_MSH: - if ((int)K < 0) { - if (pc_ret0 != -1) { - EMIT_JMP(addrs[pc_ret0] - addrs[i]); - break; - } - CLEAR_A(); - EMIT_JMP(cleanup_addr - addrs[i]); - break; - } + func = CHOOSE_LOAD_FUNC(K, sk_load_byte_msh); seen |= SEEN_DATAREF | SEEN_XREG; - t_offset = sk_load_byte_msh - (image + addrs[i]); + t_offset = func - (image + addrs[i]); EMIT1_off32(0xbe, K); /* mov imm32,%esi */ EMIT1_off32(0xe8, t_offset); /* call sk_load_byte_msh */ break; case BPF_S_LD_W_IND: - func = sk_load_word_ind; + func = sk_load_word; common_load_ind: seen |= SEEN_DATAREF | SEEN_XREG; t_offset = func - (image + addrs[i]); - EMIT1_off32(0xbe, K); /* mov imm32,%esi */ + if (K) { + if (is_imm8(K)) { + EMIT3(0x8d, 0x73, K); /* lea imm8(%rbx), %esi */ + } else { + EMIT2(0x8d, 0xb3); /* lea imm32(%rbx),%esi */ + EMIT(K, 4); + } + } else { + EMIT2(0x89,0xde); /* mov %ebx,%esi */ + } EMIT1_off32(0xe8, t_offset); /* call sk_load_xxx_ind */ break; case BPF_S_LD_H_IND: - func = sk_load_half_ind; + func = sk_load_half; goto common_load_ind; case BPF_S_LD_B_IND: - func = sk_load_byte_ind; + func = sk_load_byte; goto common_load_ind; case BPF_S_JMP_JA: t_offset = addrs[i + K] - addrs[i]; @@ -599,13 +609,14 @@ cond_branch: f_offset = addrs[i + filter[i].jf] - addrs[i]; * use it to give the cleanup instruction(s) addr */ cleanup_addr = proglen - 1; /* ret */ - if (seen) + if (seen_or_pass0) cleanup_addr -= 1; /* leaveq */ - if (seen & SEEN_XREG) + if (seen_or_pass0 & SEEN_XREG) cleanup_addr -= 4; /* mov -8(%rbp),%rbx */ if (image) { - WARN_ON(proglen != oldproglen); + if (proglen != oldproglen) + pr_err("bpb_jit_compile proglen=%u != oldproglen=%u\n", proglen, oldproglen); break; } if (proglen == oldproglen) { diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c index bff89dfe361..d6aa6e8315d 100644 --- a/arch/x86/oprofile/backtrace.c +++ b/arch/x86/oprofile/backtrace.c @@ -67,7 +67,7 @@ x86_backtrace_32(struct pt_regs * const regs, unsigned int depth) { struct stack_frame_ia32 *head; - /* User process is 32-bit */ + /* User process is IA32 */ if (!current || !test_thread_flag(TIF_IA32)) return 0; diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile index 6b8759f7634..e76e18c94a3 100644 --- a/arch/x86/pci/Makefile +++ b/arch/x86/pci/Makefile @@ -15,11 +15,12 @@ obj-$(CONFIG_X86_VISWS) += visws.o obj-$(CONFIG_X86_NUMAQ) += numaq_32.o -obj-$(CONFIG_X86_MRST) += mrst.o +obj-$(CONFIG_X86_INTEL_MID) += mrst.o obj-y += common.o early.o -obj-y += amd_bus.o bus_numa.o +obj-y += bus_numa.o +obj-$(CONFIG_AMD_NB) += amd_bus.o obj-$(CONFIG_PCI_CNB20LE_QUIRK) += broadcom_bus.o ifeq ($(CONFIG_PCI_DEBUG),y) diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index a312e76063a..ed2835e148b 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -60,6 +60,16 @@ static const struct dmi_system_id pci_use_crs_table[] __initconst = { DMI_MATCH(DMI_BIOS_VENDOR, "American Megatrends Inc."), }, }, + /* https://bugzilla.kernel.org/show_bug.cgi?id=42619 */ + { + .callback = set_use_crs, + .ident = "MSI MS-7253", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "MICRO-STAR INTERNATIONAL CO., LTD"), + DMI_MATCH(DMI_BOARD_NAME, "MS-7253"), + DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"), + }, + }, /* Now for the blacklist.. */ @@ -282,9 +292,6 @@ static void add_resources(struct pci_root_info *info) int i; struct resource *res, *root, *conflict; - if (!pci_use_crs) - return; - coalesce_windows(info, IORESOURCE_MEM); coalesce_windows(info, IORESOURCE_IO); @@ -336,8 +343,13 @@ get_current_resources(struct acpi_device *device, int busnum, acpi_walk_resources(device->handle, METHOD_NAME__CRS, setup_resource, &info); - add_resources(&info); - return; + if (pci_use_crs) { + add_resources(&info); + + return; + } + + kfree(info.name); name_alloc_fail: kfree(info.res); @@ -404,7 +416,12 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root) kfree(sd); } else { get_current_resources(device, busnum, domain, &resources); - if (list_empty(&resources)) + + /* + * _CRS with no apertures is normal, so only fall back to + * defaults or native bridge info if we're ignoring _CRS. + */ + if (!pci_use_crs) x86_pci_root_bus_resources(busnum, &resources); bus = pci_create_root_bus(NULL, busnum, &pci_root_ops, sd, &resources); diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 6dd89555fbf..d0e6e403b4f 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -164,11 +164,11 @@ DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8367_0, pci_fixup_ */ static void __devinit pci_fixup_transparent_bridge(struct pci_dev *dev) { - if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && - (dev->device & 0xff00) == 0x2400) + if ((dev->device & 0xff00) == 0x2400) dev->transparent = 1; } -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_fixup_transparent_bridge); +DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, + PCI_CLASS_BRIDGE_PCI, 8, pci_fixup_transparent_bridge); /* * Fixup for C1 Halt Disconnect problem on nForce2 systems. @@ -322,9 +322,6 @@ static void __devinit pci_fixup_video(struct pci_dev *pdev) struct pci_bus *bus; u16 config; - if ((pdev->class >> 8) != PCI_CLASS_DISPLAY_VGA) - return; - /* Is VGA routed to us? */ bus = pdev->bus; while (bus) { @@ -353,7 +350,8 @@ static void __devinit pci_fixup_video(struct pci_dev *pdev) dev_printk(KERN_DEBUG, &pdev->dev, "Boot video device\n"); } } -DECLARE_PCI_FIXUP_FINAL(PCI_ANY_ID, PCI_ANY_ID, pci_fixup_video); +DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_DISPLAY_VGA, 8, pci_fixup_video); static const struct dmi_system_id __devinitconst msi_k8t_dmi_table[] = { diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 91821a1a0c3..831971e731f 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -39,6 +39,87 @@ #include <asm/io_apic.h> +/* + * This list of dynamic mappings is for temporarily maintaining + * original BIOS BAR addresses for possible reinstatement. + */ +struct pcibios_fwaddrmap { + struct list_head list; + struct pci_dev *dev; + resource_size_t fw_addr[DEVICE_COUNT_RESOURCE]; +}; + +static LIST_HEAD(pcibios_fwaddrmappings); +static DEFINE_SPINLOCK(pcibios_fwaddrmap_lock); + +/* Must be called with 'pcibios_fwaddrmap_lock' lock held. */ +static struct pcibios_fwaddrmap *pcibios_fwaddrmap_lookup(struct pci_dev *dev) +{ + struct pcibios_fwaddrmap *map; + + WARN_ON(!spin_is_locked(&pcibios_fwaddrmap_lock)); + + list_for_each_entry(map, &pcibios_fwaddrmappings, list) + if (map->dev == dev) + return map; + + return NULL; +} + +static void +pcibios_save_fw_addr(struct pci_dev *dev, int idx, resource_size_t fw_addr) +{ + unsigned long flags; + struct pcibios_fwaddrmap *map; + + spin_lock_irqsave(&pcibios_fwaddrmap_lock, flags); + map = pcibios_fwaddrmap_lookup(dev); + if (!map) { + spin_unlock_irqrestore(&pcibios_fwaddrmap_lock, flags); + map = kzalloc(sizeof(*map), GFP_KERNEL); + if (!map) + return; + + map->dev = pci_dev_get(dev); + map->fw_addr[idx] = fw_addr; + INIT_LIST_HEAD(&map->list); + + spin_lock_irqsave(&pcibios_fwaddrmap_lock, flags); + list_add_tail(&map->list, &pcibios_fwaddrmappings); + } else + map->fw_addr[idx] = fw_addr; + spin_unlock_irqrestore(&pcibios_fwaddrmap_lock, flags); +} + +resource_size_t pcibios_retrieve_fw_addr(struct pci_dev *dev, int idx) +{ + unsigned long flags; + struct pcibios_fwaddrmap *map; + resource_size_t fw_addr = 0; + + spin_lock_irqsave(&pcibios_fwaddrmap_lock, flags); + map = pcibios_fwaddrmap_lookup(dev); + if (map) + fw_addr = map->fw_addr[idx]; + spin_unlock_irqrestore(&pcibios_fwaddrmap_lock, flags); + + return fw_addr; +} + +static void pcibios_fw_addr_list_del(void) +{ + unsigned long flags; + struct pcibios_fwaddrmap *entry, *next; + + spin_lock_irqsave(&pcibios_fwaddrmap_lock, flags); + list_for_each_entry_safe(entry, next, &pcibios_fwaddrmappings, list) { + list_del(&entry->list); + pci_dev_put(entry->dev); + kfree(entry); + } + spin_unlock_irqrestore(&pcibios_fwaddrmap_lock, flags); +} + static int skip_isa_ioresource_align(struct pci_dev *dev) { @@ -182,7 +263,8 @@ static void __init pcibios_allocate_resources(int pass) idx, r, disabled, pass); if (pci_claim_resource(dev, idx) < 0) { /* We'll assign a new address later */ - dev->fw_addr[idx] = r->start; + pcibios_save_fw_addr(dev, + idx, r->start); r->end -= r->start; r->start = 0; } @@ -228,6 +310,7 @@ static int __init pcibios_assign_resources(void) } pci_assign_unassigned_resources(); + pcibios_fw_addr_list_del(); return 0; } diff --git a/arch/x86/pci/mrst.c b/arch/x86/pci/mrst.c index cb29191cee5..140942f66b3 100644 --- a/arch/x86/pci/mrst.c +++ b/arch/x86/pci/mrst.c @@ -43,6 +43,8 @@ #define PCI_FIXED_BAR_4_SIZE 0x14 #define PCI_FIXED_BAR_5_SIZE 0x1c +static int pci_soc_mode = 0; + /** * fixed_bar_cap - return the offset of the fixed BAR cap if found * @bus: PCI bus @@ -148,7 +150,9 @@ static bool type1_access_ok(unsigned int bus, unsigned int devfn, int reg) */ if (reg >= 0x100 || reg == PCI_STATUS || reg == PCI_HEADER_TYPE) return 0; - if (bus == 0 && (devfn == PCI_DEVFN(2, 0) || devfn == PCI_DEVFN(0, 0))) + if (bus == 0 && (devfn == PCI_DEVFN(2, 0) + || devfn == PCI_DEVFN(0, 0) + || devfn == PCI_DEVFN(3, 0))) return 1; return 0; /* langwell on others */ } @@ -231,14 +235,43 @@ struct pci_ops pci_mrst_ops = { */ int __init pci_mrst_init(void) { - printk(KERN_INFO "Moorestown platform detected, using MRST PCI ops\n"); + printk(KERN_INFO "Intel MID platform detected, using MID PCI ops\n"); pci_mmcfg_late_init(); pcibios_enable_irq = mrst_pci_irq_enable; pci_root_ops = pci_mrst_ops; + pci_soc_mode = 1; /* Continue with standard init */ return 1; } +/* Langwell devices are not true pci devices, they are not subject to 10 ms + * d3 to d0 delay required by pci spec. + */ +static void __devinit pci_d3delay_fixup(struct pci_dev *dev) +{ + /* PCI fixups are effectively decided compile time. If we have a dual + SoC/non-SoC kernel we don't want to mangle d3 on non SoC devices */ + if (!pci_soc_mode) + return; + /* true pci devices in lincroft should allow type 1 access, the rest + * are langwell fake pci devices. + */ + if (type1_access_ok(dev->bus->number, dev->devfn, PCI_DEVICE_ID)) + return; + dev->d3_delay = 0; +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_d3delay_fixup); + +static void __devinit mrst_power_off_unused_dev(struct pci_dev *dev) +{ + pci_set_power_state(dev, PCI_D3cold); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0801, mrst_power_off_unused_dev); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0809, mrst_power_off_unused_dev); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x080C, mrst_power_off_unused_dev); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0812, mrst_power_off_unused_dev); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0815, mrst_power_off_unused_dev); + /* * Langwell devices reside at fixed offsets, don't try to move them. */ @@ -248,6 +281,9 @@ static void __devinit pci_fixed_bar_fixup(struct pci_dev *dev) u32 size; int i; + if (!pci_soc_mode) + return; + /* Must have extended configuration space */ if (dev->cfg_size < PCIE_CAP_OFFSET + 4) return; diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 249a5ae17d0..7415aa92791 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -400,7 +400,7 @@ int __init pci_xen_init(void) int __init pci_xen_hvm_init(void) { - if (!xen_feature(XENFEAT_hvm_pirqs)) + if (!xen_have_vector_callback || !xen_feature(XENFEAT_hvm_pirqs)) return 0; #ifdef CONFIG_ACPI diff --git a/arch/x86/platform/ce4100/falconfalls.dts b/arch/x86/platform/ce4100/falconfalls.dts index e70be38ce03..ce874f872cc 100644 --- a/arch/x86/platform/ce4100/falconfalls.dts +++ b/arch/x86/platform/ce4100/falconfalls.dts @@ -208,16 +208,19 @@ interrupts = <14 1>; }; - gpio@b,1 { + pcigpio: gpio@b,1 { + #gpio-cells = <2>; + #interrupt-cells = <2>; compatible = "pci8086,2e67.2", "pci8086,2e67", "pciclassff0000", "pciclassff00"; - #gpio-cells = <2>; reg = <0x15900 0x0 0x0 0x0 0x0>; interrupts = <15 1>; + interrupt-controller; gpio-controller; + intel,muxctl = <0>; }; i2c-controller@b,2 { diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 4cf9bd0a165..92660edaa1e 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -26,6 +26,8 @@ * Skip non-WB memory and ignore empty memory ranges. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kernel.h> #include <linux/init.h> #include <linux/efi.h> @@ -47,7 +49,6 @@ #include <asm/x86_init.h> #define EFI_DEBUG 1 -#define PFX "EFI: " int efi_enabled; EXPORT_SYMBOL(efi_enabled); @@ -67,6 +68,9 @@ EXPORT_SYMBOL(efi); struct efi_memory_map memmap; +bool efi_64bit; +static bool efi_native; + static struct efi efi_phys __initdata; static efi_system_table_t efi_systab __initdata; @@ -254,7 +258,7 @@ int efi_set_rtc_mmss(unsigned long nowtime) status = efi.get_time(&eft, &cap); if (status != EFI_SUCCESS) { - printk(KERN_ERR "Oops: efitime: can't read time!\n"); + pr_err("Oops: efitime: can't read time!\n"); return -1; } @@ -268,7 +272,7 @@ int efi_set_rtc_mmss(unsigned long nowtime) status = efi.set_time(&eft); if (status != EFI_SUCCESS) { - printk(KERN_ERR "Oops: efitime: can't write time!\n"); + pr_err("Oops: efitime: can't write time!\n"); return -1; } return 0; @@ -282,7 +286,7 @@ unsigned long efi_get_time(void) status = efi.get_time(&eft, &cap); if (status != EFI_SUCCESS) - printk(KERN_ERR "Oops: efitime: can't read time!\n"); + pr_err("Oops: efitime: can't read time!\n"); return mktime(eft.year, eft.month, eft.day, eft.hour, eft.minute, eft.second); @@ -338,11 +342,16 @@ static void __init do_add_efi_memmap(void) sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); } -void __init efi_memblock_x86_reserve_range(void) +int __init efi_memblock_x86_reserve_range(void) { unsigned long pmap; #ifdef CONFIG_X86_32 + /* Can't handle data above 4GB at this time */ + if (boot_params.efi_info.efi_memmap_hi) { + pr_err("Memory map is above 4GB, disabling EFI.\n"); + return -EINVAL; + } pmap = boot_params.efi_info.efi_memmap; #else pmap = (boot_params.efi_info.efi_memmap | @@ -354,6 +363,8 @@ void __init efi_memblock_x86_reserve_range(void) memmap.desc_version = boot_params.efi_info.efi_memdesc_version; memmap.desc_size = boot_params.efi_info.efi_memdesc_size; memblock_reserve(pmap, memmap.nr_map * memmap.desc_size); + + return 0; } #if EFI_DEBUG @@ -367,7 +378,7 @@ static void __init print_efi_memmap(void) p < memmap.map_end; p += memmap.desc_size, i++) { md = p; - printk(KERN_INFO PFX "mem%02u: type=%u, attr=0x%llx, " + pr_info("mem%02u: type=%u, attr=0x%llx, " "range=[0x%016llx-0x%016llx) (%lluMB)\n", i, md->type, md->attribute, md->phys_addr, md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT), @@ -400,7 +411,7 @@ void __init efi_reserve_boot_services(void) memblock_is_region_reserved(start, size)) { /* Could not reserve, skip it */ md->num_pages = 0; - memblock_dbg(PFX "Could not reserve boot range " + memblock_dbg("Could not reserve boot range " "[0x%010llx-0x%010llx]\n", start, start+size-1); } else @@ -429,103 +440,172 @@ static void __init efi_free_boot_services(void) } } -void __init efi_init(void) +static int __init efi_systab_init(void *phys) { - efi_config_table_t *config_tables; - efi_runtime_services_t *runtime; - efi_char16_t *c16; - char vendor[100] = "unknown"; - int i = 0; - void *tmp; + if (efi_64bit) { + efi_system_table_64_t *systab64; + u64 tmp = 0; + + systab64 = early_ioremap((unsigned long)phys, + sizeof(*systab64)); + if (systab64 == NULL) { + pr_err("Couldn't map the system table!\n"); + return -ENOMEM; + } + efi_systab.hdr = systab64->hdr; + efi_systab.fw_vendor = systab64->fw_vendor; + tmp |= systab64->fw_vendor; + efi_systab.fw_revision = systab64->fw_revision; + efi_systab.con_in_handle = systab64->con_in_handle; + tmp |= systab64->con_in_handle; + efi_systab.con_in = systab64->con_in; + tmp |= systab64->con_in; + efi_systab.con_out_handle = systab64->con_out_handle; + tmp |= systab64->con_out_handle; + efi_systab.con_out = systab64->con_out; + tmp |= systab64->con_out; + efi_systab.stderr_handle = systab64->stderr_handle; + tmp |= systab64->stderr_handle; + efi_systab.stderr = systab64->stderr; + tmp |= systab64->stderr; + efi_systab.runtime = (void *)(unsigned long)systab64->runtime; + tmp |= systab64->runtime; + efi_systab.boottime = (void *)(unsigned long)systab64->boottime; + tmp |= systab64->boottime; + efi_systab.nr_tables = systab64->nr_tables; + efi_systab.tables = systab64->tables; + tmp |= systab64->tables; + + early_iounmap(systab64, sizeof(*systab64)); #ifdef CONFIG_X86_32 - efi_phys.systab = (efi_system_table_t *)boot_params.efi_info.efi_systab; -#else - efi_phys.systab = (efi_system_table_t *) - (boot_params.efi_info.efi_systab | - ((__u64)boot_params.efi_info.efi_systab_hi<<32)); + if (tmp >> 32) { + pr_err("EFI data located above 4GB, disabling EFI.\n"); + return -EINVAL; + } #endif + } else { + efi_system_table_32_t *systab32; + + systab32 = early_ioremap((unsigned long)phys, + sizeof(*systab32)); + if (systab32 == NULL) { + pr_err("Couldn't map the system table!\n"); + return -ENOMEM; + } + + efi_systab.hdr = systab32->hdr; + efi_systab.fw_vendor = systab32->fw_vendor; + efi_systab.fw_revision = systab32->fw_revision; + efi_systab.con_in_handle = systab32->con_in_handle; + efi_systab.con_in = systab32->con_in; + efi_systab.con_out_handle = systab32->con_out_handle; + efi_systab.con_out = systab32->con_out; + efi_systab.stderr_handle = systab32->stderr_handle; + efi_systab.stderr = systab32->stderr; + efi_systab.runtime = (void *)(unsigned long)systab32->runtime; + efi_systab.boottime = (void *)(unsigned long)systab32->boottime; + efi_systab.nr_tables = systab32->nr_tables; + efi_systab.tables = systab32->tables; + + early_iounmap(systab32, sizeof(*systab32)); + } - efi.systab = early_ioremap((unsigned long)efi_phys.systab, - sizeof(efi_system_table_t)); - if (efi.systab == NULL) - printk(KERN_ERR "Couldn't map the EFI system table!\n"); - memcpy(&efi_systab, efi.systab, sizeof(efi_system_table_t)); - early_iounmap(efi.systab, sizeof(efi_system_table_t)); efi.systab = &efi_systab; /* * Verify the EFI Table */ - if (efi.systab->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) - printk(KERN_ERR "EFI system table signature incorrect!\n"); + if (efi.systab->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) { + pr_err("System table signature incorrect!\n"); + return -EINVAL; + } if ((efi.systab->hdr.revision >> 16) == 0) - printk(KERN_ERR "Warning: EFI system table version " + pr_err("Warning: System table version " "%d.%02d, expected 1.00 or greater!\n", efi.systab->hdr.revision >> 16, efi.systab->hdr.revision & 0xffff); - /* - * Show what we know for posterity - */ - c16 = tmp = early_ioremap(efi.systab->fw_vendor, 2); - if (c16) { - for (i = 0; i < sizeof(vendor) - 1 && *c16; ++i) - vendor[i] = *c16++; - vendor[i] = '\0'; - } else - printk(KERN_ERR PFX "Could not map the firmware vendor!\n"); - early_iounmap(tmp, 2); + return 0; +} - printk(KERN_INFO "EFI v%u.%.02u by %s\n", - efi.systab->hdr.revision >> 16, - efi.systab->hdr.revision & 0xffff, vendor); +static int __init efi_config_init(u64 tables, int nr_tables) +{ + void *config_tables, *tablep; + int i, sz; + + if (efi_64bit) + sz = sizeof(efi_config_table_64_t); + else + sz = sizeof(efi_config_table_32_t); /* * Let's see what config tables the firmware passed to us. */ - config_tables = early_ioremap( - efi.systab->tables, - efi.systab->nr_tables * sizeof(efi_config_table_t)); - if (config_tables == NULL) - printk(KERN_ERR "Could not map EFI Configuration Table!\n"); + config_tables = early_ioremap(tables, nr_tables * sz); + if (config_tables == NULL) { + pr_err("Could not map Configuration table!\n"); + return -ENOMEM; + } - printk(KERN_INFO); + tablep = config_tables; + pr_info(""); for (i = 0; i < efi.systab->nr_tables; i++) { - if (!efi_guidcmp(config_tables[i].guid, MPS_TABLE_GUID)) { - efi.mps = config_tables[i].table; - printk(" MPS=0x%lx ", config_tables[i].table); - } else if (!efi_guidcmp(config_tables[i].guid, - ACPI_20_TABLE_GUID)) { - efi.acpi20 = config_tables[i].table; - printk(" ACPI 2.0=0x%lx ", config_tables[i].table); - } else if (!efi_guidcmp(config_tables[i].guid, - ACPI_TABLE_GUID)) { - efi.acpi = config_tables[i].table; - printk(" ACPI=0x%lx ", config_tables[i].table); - } else if (!efi_guidcmp(config_tables[i].guid, - SMBIOS_TABLE_GUID)) { - efi.smbios = config_tables[i].table; - printk(" SMBIOS=0x%lx ", config_tables[i].table); + efi_guid_t guid; + unsigned long table; + + if (efi_64bit) { + u64 table64; + guid = ((efi_config_table_64_t *)tablep)->guid; + table64 = ((efi_config_table_64_t *)tablep)->table; + table = table64; +#ifdef CONFIG_X86_32 + if (table64 >> 32) { + pr_cont("\n"); + pr_err("Table located above 4GB, disabling EFI.\n"); + early_iounmap(config_tables, + efi.systab->nr_tables * sz); + return -EINVAL; + } +#endif + } else { + guid = ((efi_config_table_32_t *)tablep)->guid; + table = ((efi_config_table_32_t *)tablep)->table; + } + if (!efi_guidcmp(guid, MPS_TABLE_GUID)) { + efi.mps = table; + pr_cont(" MPS=0x%lx ", table); + } else if (!efi_guidcmp(guid, ACPI_20_TABLE_GUID)) { + efi.acpi20 = table; + pr_cont(" ACPI 2.0=0x%lx ", table); + } else if (!efi_guidcmp(guid, ACPI_TABLE_GUID)) { + efi.acpi = table; + pr_cont(" ACPI=0x%lx ", table); + } else if (!efi_guidcmp(guid, SMBIOS_TABLE_GUID)) { + efi.smbios = table; + pr_cont(" SMBIOS=0x%lx ", table); #ifdef CONFIG_X86_UV - } else if (!efi_guidcmp(config_tables[i].guid, - UV_SYSTEM_TABLE_GUID)) { - efi.uv_systab = config_tables[i].table; - printk(" UVsystab=0x%lx ", config_tables[i].table); + } else if (!efi_guidcmp(guid, UV_SYSTEM_TABLE_GUID)) { + efi.uv_systab = table; + pr_cont(" UVsystab=0x%lx ", table); #endif - } else if (!efi_guidcmp(config_tables[i].guid, - HCDP_TABLE_GUID)) { - efi.hcdp = config_tables[i].table; - printk(" HCDP=0x%lx ", config_tables[i].table); - } else if (!efi_guidcmp(config_tables[i].guid, - UGA_IO_PROTOCOL_GUID)) { - efi.uga = config_tables[i].table; - printk(" UGA=0x%lx ", config_tables[i].table); + } else if (!efi_guidcmp(guid, HCDP_TABLE_GUID)) { + efi.hcdp = table; + pr_cont(" HCDP=0x%lx ", table); + } else if (!efi_guidcmp(guid, UGA_IO_PROTOCOL_GUID)) { + efi.uga = table; + pr_cont(" UGA=0x%lx ", table); } + tablep += sz; } - printk("\n"); - early_iounmap(config_tables, - efi.systab->nr_tables * sizeof(efi_config_table_t)); + pr_cont("\n"); + early_iounmap(config_tables, efi.systab->nr_tables * sz); + return 0; +} + +static int __init efi_runtime_init(void) +{ + efi_runtime_services_t *runtime; /* * Check out the runtime services table. We need to map @@ -535,43 +615,116 @@ void __init efi_init(void) */ runtime = early_ioremap((unsigned long)efi.systab->runtime, sizeof(efi_runtime_services_t)); - if (runtime != NULL) { - /* - * We will only need *early* access to the following - * two EFI runtime services before set_virtual_address_map - * is invoked. - */ - efi_phys.get_time = (efi_get_time_t *)runtime->get_time; - efi_phys.set_virtual_address_map = - (efi_set_virtual_address_map_t *) - runtime->set_virtual_address_map; - /* - * Make efi_get_time can be called before entering - * virtual mode. - */ - efi.get_time = phys_efi_get_time; - } else - printk(KERN_ERR "Could not map the EFI runtime service " - "table!\n"); + if (!runtime) { + pr_err("Could not map the runtime service table!\n"); + return -ENOMEM; + } + /* + * We will only need *early* access to the following + * two EFI runtime services before set_virtual_address_map + * is invoked. + */ + efi_phys.get_time = (efi_get_time_t *)runtime->get_time; + efi_phys.set_virtual_address_map = + (efi_set_virtual_address_map_t *) + runtime->set_virtual_address_map; + /* + * Make efi_get_time can be called before entering + * virtual mode. + */ + efi.get_time = phys_efi_get_time; early_iounmap(runtime, sizeof(efi_runtime_services_t)); + return 0; +} + +static int __init efi_memmap_init(void) +{ /* Map the EFI memory map */ memmap.map = early_ioremap((unsigned long)memmap.phys_map, memmap.nr_map * memmap.desc_size); - if (memmap.map == NULL) - printk(KERN_ERR "Could not map the EFI memory map!\n"); + if (memmap.map == NULL) { + pr_err("Could not map the memory map!\n"); + return -ENOMEM; + } memmap.map_end = memmap.map + (memmap.nr_map * memmap.desc_size); - if (memmap.desc_size != sizeof(efi_memory_desc_t)) - printk(KERN_WARNING - "Kernel-defined memdesc doesn't match the one from EFI!\n"); - if (add_efi_memmap) do_add_efi_memmap(); + return 0; +} + +void __init efi_init(void) +{ + efi_char16_t *c16; + char vendor[100] = "unknown"; + int i = 0; + void *tmp; + +#ifdef CONFIG_X86_32 + if (boot_params.efi_info.efi_systab_hi || + boot_params.efi_info.efi_memmap_hi) { + pr_info("Table located above 4GB, disabling EFI.\n"); + efi_enabled = 0; + return; + } + efi_phys.systab = (efi_system_table_t *)boot_params.efi_info.efi_systab; + efi_native = !efi_64bit; +#else + efi_phys.systab = (efi_system_table_t *) + (boot_params.efi_info.efi_systab | + ((__u64)boot_params.efi_info.efi_systab_hi<<32)); + efi_native = efi_64bit; +#endif + + if (efi_systab_init(efi_phys.systab)) { + efi_enabled = 0; + return; + } + + /* + * Show what we know for posterity + */ + c16 = tmp = early_ioremap(efi.systab->fw_vendor, 2); + if (c16) { + for (i = 0; i < sizeof(vendor) - 1 && *c16; ++i) + vendor[i] = *c16++; + vendor[i] = '\0'; + } else + pr_err("Could not map the firmware vendor!\n"); + early_iounmap(tmp, 2); + + pr_info("EFI v%u.%.02u by %s\n", + efi.systab->hdr.revision >> 16, + efi.systab->hdr.revision & 0xffff, vendor); + + if (efi_config_init(efi.systab->tables, efi.systab->nr_tables)) { + efi_enabled = 0; + return; + } + + /* + * Note: We currently don't support runtime services on an EFI + * that doesn't match the kernel 32/64-bit mode. + */ + + if (!efi_native) + pr_info("No EFI runtime due to 32/64-bit mismatch with kernel\n"); + else if (efi_runtime_init()) { + efi_enabled = 0; + return; + } + + if (efi_memmap_init()) { + efi_enabled = 0; + return; + } #ifdef CONFIG_X86_32 - x86_platform.get_wallclock = efi_get_time; - x86_platform.set_wallclock = efi_set_rtc_mmss; + if (efi_native) { + x86_platform.get_wallclock = efi_get_time; + x86_platform.set_wallclock = efi_set_rtc_mmss; + } #endif #if EFI_DEBUG @@ -629,6 +782,14 @@ void __init efi_enter_virtual_mode(void) efi.systab = NULL; + /* + * We don't do virtual mode, since we don't do runtime services, on + * non-native EFI + */ + + if (!efi_native) + goto out; + /* Merge contiguous regions of the same type and attribute */ for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { u64 prev_size; @@ -677,7 +838,7 @@ void __init efi_enter_virtual_mode(void) md->virt_addr = (u64) (unsigned long) va; if (!va) { - printk(KERN_ERR PFX "ioremap of 0x%llX failed!\n", + pr_err("ioremap of 0x%llX failed!\n", (unsigned long long)md->phys_addr); continue; } @@ -711,8 +872,8 @@ void __init efi_enter_virtual_mode(void) (efi_memory_desc_t *)__pa(new_memmap)); if (status != EFI_SUCCESS) { - printk(KERN_ALERT "Unable to switch EFI into virtual mode " - "(status=%lx)!\n", status); + pr_alert("Unable to switch EFI into virtual mode " + "(status=%lx)!\n", status); panic("EFI call to SetVirtualAddressMap() failed!"); } @@ -744,6 +905,8 @@ void __init efi_enter_virtual_mode(void) efi.query_capsule_caps = virt_efi_query_capsule_caps; if (__supported_pte_mask & _PAGE_NX) runtime_code_page_mkexec(); + +out: early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size); memmap.map = NULL; kfree(new_memmap); diff --git a/arch/x86/platform/geode/Makefile b/arch/x86/platform/geode/Makefile index 07c9cd05021..5b51194f4c8 100644 --- a/arch/x86/platform/geode/Makefile +++ b/arch/x86/platform/geode/Makefile @@ -1 +1,3 @@ obj-$(CONFIG_ALIX) += alix.o +obj-$(CONFIG_NET5501) += net5501.o +obj-$(CONFIG_GEOS) += geos.o diff --git a/arch/x86/platform/geode/alix.c b/arch/x86/platform/geode/alix.c index ca1973699d3..90e23e7679a 100644 --- a/arch/x86/platform/geode/alix.c +++ b/arch/x86/platform/geode/alix.c @@ -6,6 +6,7 @@ * * Copyright (C) 2008 Constantin Baranov <const@mimas.ru> * Copyright (C) 2011 Ed Wildgoose <kernel@wildgooses.com> + * and Philip Prindeville <philipp@redfish-solutions.com> * * TODO: There are large similarities with leds-net5501.c * by Alessandro Zummo <a.zummo@towertech.it> @@ -24,14 +25,47 @@ #include <linux/leds.h> #include <linux/platform_device.h> #include <linux/gpio.h> +#include <linux/input.h> +#include <linux/gpio_keys.h> +#include <linux/dmi.h> #include <asm/geode.h> -static int force = 0; +#define BIOS_SIGNATURE_TINYBIOS 0xf0000 +#define BIOS_SIGNATURE_COREBOOT 0x500 +#define BIOS_REGION_SIZE 0x10000 + +static bool force = 0; module_param(force, bool, 0444); /* FIXME: Award bios is not automatically detected as Alix platform */ MODULE_PARM_DESC(force, "Force detection as ALIX.2/ALIX.3 platform"); +static struct gpio_keys_button alix_gpio_buttons[] = { + { + .code = KEY_RESTART, + .gpio = 24, + .active_low = 1, + .desc = "Reset button", + .type = EV_KEY, + .wakeup = 0, + .debounce_interval = 100, + .can_disable = 0, + } +}; +static struct gpio_keys_platform_data alix_buttons_data = { + .buttons = alix_gpio_buttons, + .nbuttons = ARRAY_SIZE(alix_gpio_buttons), + .poll_interval = 20, +}; + +static struct platform_device alix_buttons_dev = { + .name = "gpio-keys-polled", + .id = 1, + .dev = { + .platform_data = &alix_buttons_data, + } +}; + static struct gpio_led alix_leds[] = { { .name = "alix:1", @@ -64,17 +98,22 @@ static struct platform_device alix_leds_dev = { .dev.platform_data = &alix_leds_data, }; +static struct __initdata platform_device *alix_devs[] = { + &alix_buttons_dev, + &alix_leds_dev, +}; + static void __init register_alix(void) { /* Setup LED control through leds-gpio driver */ - platform_device_register(&alix_leds_dev); + platform_add_devices(alix_devs, ARRAY_SIZE(alix_devs)); } -static int __init alix_present(unsigned long bios_phys, +static bool __init alix_present(unsigned long bios_phys, const char *alix_sig, size_t alix_sig_len) { - const size_t bios_len = 0x00010000; + const size_t bios_len = BIOS_REGION_SIZE; const char *bios_virt; const char *scan_end; const char *p; @@ -84,7 +123,7 @@ static int __init alix_present(unsigned long bios_phys, printk(KERN_NOTICE "%s: forced to skip BIOS test, " "assume system is ALIX.2/ALIX.3\n", KBUILD_MODNAME); - return 1; + return true; } bios_virt = phys_to_virt(bios_phys); @@ -109,15 +148,33 @@ static int __init alix_present(unsigned long bios_phys, *a = '\0'; tail = p + alix_sig_len; - if ((tail[0] == '2' || tail[0] == '3')) { + if ((tail[0] == '2' || tail[0] == '3' || tail[0] == '6')) { printk(KERN_INFO "%s: system is recognized as \"%s\"\n", KBUILD_MODNAME, name); - return 1; + return true; } } - return 0; + return false; +} + +static bool __init alix_present_dmi(void) +{ + const char *vendor, *product; + + vendor = dmi_get_system_info(DMI_SYS_VENDOR); + if (!vendor || strcmp(vendor, "PC Engines")) + return false; + + product = dmi_get_system_info(DMI_PRODUCT_NAME); + if (!product || (strcmp(product, "ALIX.2D") && strcmp(product, "ALIX.6"))) + return false; + + printk(KERN_INFO "%s: system is recognized as \"%s %s\"\n", + KBUILD_MODNAME, vendor, product); + + return true; } static int __init alix_init(void) @@ -128,8 +185,9 @@ static int __init alix_init(void) if (!is_geode()) return 0; - if (alix_present(0xf0000, tinybios_sig, sizeof(tinybios_sig) - 1) || - alix_present(0x500, coreboot_sig, sizeof(coreboot_sig) - 1)) + if (alix_present(BIOS_SIGNATURE_TINYBIOS, tinybios_sig, sizeof(tinybios_sig) - 1) || + alix_present(BIOS_SIGNATURE_COREBOOT, coreboot_sig, sizeof(coreboot_sig) - 1) || + alix_present_dmi()) register_alix(); return 0; diff --git a/arch/x86/platform/geode/geos.c b/arch/x86/platform/geode/geos.c new file mode 100644 index 00000000000..c2e6d53558b --- /dev/null +++ b/arch/x86/platform/geode/geos.c @@ -0,0 +1,128 @@ +/* + * System Specific setup for Traverse Technologies GEOS. + * At the moment this means setup of GPIO control of LEDs. + * + * Copyright (C) 2008 Constantin Baranov <const@mimas.ru> + * Copyright (C) 2011 Ed Wildgoose <kernel@wildgooses.com> + * and Philip Prindeville <philipp@redfish-solutions.com> + * + * TODO: There are large similarities with leds-net5501.c + * by Alessandro Zummo <a.zummo@towertech.it> + * In the future leds-net5501.c should be migrated over to platform + * + * 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/kernel.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/string.h> +#include <linux/module.h> +#include <linux/leds.h> +#include <linux/platform_device.h> +#include <linux/gpio.h> +#include <linux/input.h> +#include <linux/gpio_keys.h> +#include <linux/dmi.h> + +#include <asm/geode.h> + +static struct gpio_keys_button geos_gpio_buttons[] = { + { + .code = KEY_RESTART, + .gpio = 3, + .active_low = 1, + .desc = "Reset button", + .type = EV_KEY, + .wakeup = 0, + .debounce_interval = 100, + .can_disable = 0, + } +}; +static struct gpio_keys_platform_data geos_buttons_data = { + .buttons = geos_gpio_buttons, + .nbuttons = ARRAY_SIZE(geos_gpio_buttons), + .poll_interval = 20, +}; + +static struct platform_device geos_buttons_dev = { + .name = "gpio-keys-polled", + .id = 1, + .dev = { + .platform_data = &geos_buttons_data, + } +}; + +static struct gpio_led geos_leds[] = { + { + .name = "geos:1", + .gpio = 6, + .default_trigger = "default-on", + .active_low = 1, + }, + { + .name = "geos:2", + .gpio = 25, + .default_trigger = "default-off", + .active_low = 1, + }, + { + .name = "geos:3", + .gpio = 27, + .default_trigger = "default-off", + .active_low = 1, + }, +}; + +static struct gpio_led_platform_data geos_leds_data = { + .num_leds = ARRAY_SIZE(geos_leds), + .leds = geos_leds, +}; + +static struct platform_device geos_leds_dev = { + .name = "leds-gpio", + .id = -1, + .dev.platform_data = &geos_leds_data, +}; + +static struct __initdata platform_device *geos_devs[] = { + &geos_buttons_dev, + &geos_leds_dev, +}; + +static void __init register_geos(void) +{ + /* Setup LED control through leds-gpio driver */ + platform_add_devices(geos_devs, ARRAY_SIZE(geos_devs)); +} + +static int __init geos_init(void) +{ + const char *vendor, *product; + + if (!is_geode()) + return 0; + + vendor = dmi_get_system_info(DMI_SYS_VENDOR); + if (!vendor || strcmp(vendor, "Traverse Technologies")) + return 0; + + product = dmi_get_system_info(DMI_PRODUCT_NAME); + if (!product || strcmp(product, "Geos")) + return 0; + + printk(KERN_INFO "%s: system is recognized as \"%s %s\"\n", + KBUILD_MODNAME, vendor, product); + + register_geos(); + + return 0; +} + +module_init(geos_init); + +MODULE_AUTHOR("Philip Prindeville <philipp@redfish-solutions.com>"); +MODULE_DESCRIPTION("Traverse Technologies Geos System Setup"); +MODULE_LICENSE("GPL"); diff --git a/arch/x86/platform/geode/net5501.c b/arch/x86/platform/geode/net5501.c new file mode 100644 index 00000000000..66d377e334f --- /dev/null +++ b/arch/x86/platform/geode/net5501.c @@ -0,0 +1,154 @@ +/* + * System Specific setup for Soekris net5501 + * At the moment this means setup of GPIO control of LEDs and buttons + * on net5501 boards. + * + * + * Copyright (C) 2008-2009 Tower Technologies + * Written by Alessandro Zummo <a.zummo@towertech.it> + * + * Copyright (C) 2008 Constantin Baranov <const@mimas.ru> + * Copyright (C) 2011 Ed Wildgoose <kernel@wildgooses.com> + * and Philip Prindeville <philipp@redfish-solutions.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/string.h> +#include <linux/module.h> +#include <linux/leds.h> +#include <linux/platform_device.h> +#include <linux/gpio.h> +#include <linux/input.h> +#include <linux/gpio_keys.h> + +#include <asm/geode.h> + +#define BIOS_REGION_BASE 0xffff0000 +#define BIOS_REGION_SIZE 0x00010000 + +static struct gpio_keys_button net5501_gpio_buttons[] = { + { + .code = KEY_RESTART, + .gpio = 24, + .active_low = 1, + .desc = "Reset button", + .type = EV_KEY, + .wakeup = 0, + .debounce_interval = 100, + .can_disable = 0, + } +}; +static struct gpio_keys_platform_data net5501_buttons_data = { + .buttons = net5501_gpio_buttons, + .nbuttons = ARRAY_SIZE(net5501_gpio_buttons), + .poll_interval = 20, +}; + +static struct platform_device net5501_buttons_dev = { + .name = "gpio-keys-polled", + .id = 1, + .dev = { + .platform_data = &net5501_buttons_data, + } +}; + +static struct gpio_led net5501_leds[] = { + { + .name = "net5501:1", + .gpio = 6, + .default_trigger = "default-on", + .active_low = 1, + }, +}; + +static struct gpio_led_platform_data net5501_leds_data = { + .num_leds = ARRAY_SIZE(net5501_leds), + .leds = net5501_leds, +}; + +static struct platform_device net5501_leds_dev = { + .name = "leds-gpio", + .id = -1, + .dev.platform_data = &net5501_leds_data, +}; + +static struct __initdata platform_device *net5501_devs[] = { + &net5501_buttons_dev, + &net5501_leds_dev, +}; + +static void __init register_net5501(void) +{ + /* Setup LED control through leds-gpio driver */ + platform_add_devices(net5501_devs, ARRAY_SIZE(net5501_devs)); +} + +struct net5501_board { + u16 offset; + u16 len; + char *sig; +}; + +static struct net5501_board __initdata boards[] = { + { 0xb7b, 7, "net5501" }, /* net5501 v1.33/1.33c */ + { 0xb1f, 7, "net5501" }, /* net5501 v1.32i */ +}; + +static bool __init net5501_present(void) +{ + int i; + unsigned char *rombase, *bios; + bool found = false; + + rombase = ioremap(BIOS_REGION_BASE, BIOS_REGION_SIZE - 1); + if (!rombase) { + printk(KERN_ERR "%s: failed to get rombase\n", KBUILD_MODNAME); + return found; + } + + bios = rombase + 0x20; /* null terminated */ + + if (memcmp(bios, "comBIOS", 7)) + goto unmap; + + for (i = 0; i < ARRAY_SIZE(boards); i++) { + unsigned char *model = rombase + boards[i].offset; + + if (!memcmp(model, boards[i].sig, boards[i].len)) { + printk(KERN_INFO "%s: system is recognized as \"%s\"\n", + KBUILD_MODNAME, model); + + found = true; + break; + } + } + +unmap: + iounmap(rombase); + return found; +} + +static int __init net5501_init(void) +{ + if (!is_geode()) + return 0; + + if (!net5501_present()) + return 0; + + register_net5501(); + + return 0; +} + +module_init(net5501_init); + +MODULE_AUTHOR("Philip Prindeville <philipp@redfish-solutions.com>"); +MODULE_DESCRIPTION("Soekris net5501 System Setup"); +MODULE_LICENSE("GPL"); diff --git a/arch/x86/platform/iris/iris.c b/arch/x86/platform/iris/iris.c index 1ba7f5ed8c9..5917eb56b31 100644 --- a/arch/x86/platform/iris/iris.c +++ b/arch/x86/platform/iris/iris.c @@ -42,7 +42,7 @@ MODULE_AUTHOR("Sébastien Hinderer <Sebastien.Hinderer@ens-lyon.org>"); MODULE_DESCRIPTION("A power_off handler for Iris devices from EuroBraille"); MODULE_SUPPORTED_DEVICE("Eurobraille/Iris"); -static int force; +static bool force; module_param(force, bool, 0); MODULE_PARM_DESC(force, "Set to one to force poweroff handler installation."); diff --git a/arch/x86/platform/mrst/Makefile b/arch/x86/platform/mrst/Makefile index 1ea38775a6d..af1da7e623f 100644 --- a/arch/x86/platform/mrst/Makefile +++ b/arch/x86/platform/mrst/Makefile @@ -1,4 +1,3 @@ -obj-$(CONFIG_X86_MRST) += mrst.o -obj-$(CONFIG_X86_MRST) += vrtc.o -obj-$(CONFIG_EARLY_PRINTK_MRST) += early_printk_mrst.o -obj-$(CONFIG_X86_MRST) += pmu.o +obj-$(CONFIG_X86_INTEL_MID) += mrst.o +obj-$(CONFIG_X86_INTEL_MID) += vrtc.o +obj-$(CONFIG_EARLY_PRINTK_INTEL_MID) += early_printk_mrst.o diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c index ad4ec1cb097..e0a37233c0a 100644 --- a/arch/x86/platform/mrst/mrst.c +++ b/arch/x86/platform/mrst/mrst.c @@ -28,6 +28,8 @@ #include <linux/module.h> #include <linux/notifier.h> #include <linux/mfd/intel_msic.h> +#include <linux/gpio.h> +#include <linux/i2c/tc35876x.h> #include <asm/setup.h> #include <asm/mpspec_def.h> @@ -78,16 +80,11 @@ int sfi_mrtc_num; static void mrst_power_off(void) { - if (__mrst_cpu_chip == MRST_CPU_CHIP_LINCROFT) - intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 1); } static void mrst_reboot(void) { - if (__mrst_cpu_chip == MRST_CPU_CHIP_LINCROFT) - intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 0); - else - intel_scu_ipc_simple_command(IPCMSG_COLD_BOOT, 0); + intel_scu_ipc_simple_command(IPCMSG_COLD_BOOT, 0); } /* parse all the mtimer info to a static mtimer array */ @@ -200,34 +197,28 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table) static unsigned long __init mrst_calibrate_tsc(void) { - unsigned long flags, fast_calibrate; - if (__mrst_cpu_chip == MRST_CPU_CHIP_PENWELL) { - u32 lo, hi, ratio, fsb; - - rdmsr(MSR_IA32_PERF_STATUS, lo, hi); - pr_debug("IA32 perf status is 0x%x, 0x%0x\n", lo, hi); - ratio = (hi >> 8) & 0x1f; - pr_debug("ratio is %d\n", ratio); - if (!ratio) { - pr_err("read a zero ratio, should be incorrect!\n"); - pr_err("force tsc ratio to 16 ...\n"); - ratio = 16; - } - rdmsr(MSR_FSB_FREQ, lo, hi); - if ((lo & 0x7) == 0x7) - fsb = PENWELL_FSB_FREQ_83SKU; - else - fsb = PENWELL_FSB_FREQ_100SKU; - fast_calibrate = ratio * fsb; - pr_debug("read penwell tsc %lu khz\n", fast_calibrate); - lapic_timer_frequency = fsb * 1000 / HZ; - /* mark tsc clocksource as reliable */ - set_cpu_cap(&boot_cpu_data, X86_FEATURE_TSC_RELIABLE); - } else { - local_irq_save(flags); - fast_calibrate = apbt_quick_calibrate(); - local_irq_restore(flags); + unsigned long fast_calibrate; + u32 lo, hi, ratio, fsb; + + rdmsr(MSR_IA32_PERF_STATUS, lo, hi); + pr_debug("IA32 perf status is 0x%x, 0x%0x\n", lo, hi); + ratio = (hi >> 8) & 0x1f; + pr_debug("ratio is %d\n", ratio); + if (!ratio) { + pr_err("read a zero ratio, should be incorrect!\n"); + pr_err("force tsc ratio to 16 ...\n"); + ratio = 16; } + rdmsr(MSR_FSB_FREQ, lo, hi); + if ((lo & 0x7) == 0x7) + fsb = PENWELL_FSB_FREQ_83SKU; + else + fsb = PENWELL_FSB_FREQ_100SKU; + fast_calibrate = ratio * fsb; + pr_debug("read penwell tsc %lu khz\n", fast_calibrate); + lapic_timer_frequency = fsb * 1000 / HZ; + /* mark tsc clocksource as reliable */ + set_cpu_cap(&boot_cpu_data, X86_FEATURE_TSC_RELIABLE); if (fast_calibrate) return fast_calibrate; @@ -261,16 +252,11 @@ static void __cpuinit mrst_arch_setup(void) { if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 0x27) __mrst_cpu_chip = MRST_CPU_CHIP_PENWELL; - else if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 0x26) - __mrst_cpu_chip = MRST_CPU_CHIP_LINCROFT; else { - pr_err("Unknown Moorestown CPU (%d:%d), default to Lincroft\n", + pr_err("Unknown Intel MID CPU (%d:%d), default to Penwell\n", boot_cpu_data.x86, boot_cpu_data.x86_model); - __mrst_cpu_chip = MRST_CPU_CHIP_LINCROFT; + __mrst_cpu_chip = MRST_CPU_CHIP_PENWELL; } - pr_debug("Moorestown CPU %s identified\n", - (__mrst_cpu_chip == MRST_CPU_CHIP_LINCROFT) ? - "Lincroft" : "Penwell"); } /* MID systems don't have i8042 controller */ @@ -686,6 +672,24 @@ static void *msic_ocd_platform_data(void *info) return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_OCD); } +static void *msic_thermal_platform_data(void *info) +{ + return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_THERMAL); +} + +/* tc35876x DSI-LVDS bridge chip and panel platform data */ +static void *tc35876x_platform_data(void *data) +{ + static struct tc35876x_platform_data pdata; + + /* gpio pins set to -1 will not be used by the driver */ + pdata.gpio_bridge_reset = get_gpio_by_name("LCMB_RXEN"); + pdata.gpio_panel_bl_en = get_gpio_by_name("6S6P_BL_EN"); + pdata.gpio_panel_vadd = get_gpio_by_name("EN_VREG_LCD_V3P3"); + + return &pdata; +} + static const struct devs_id __initconst device_ids[] = { {"bma023", SFI_DEV_TYPE_I2C, 1, &no_platform_data}, {"pmic_gpio", SFI_DEV_TYPE_SPI, 1, &pmic_gpio_platform_data}, @@ -698,6 +702,7 @@ static const struct devs_id __initconst device_ids[] = { {"i2c_accel", SFI_DEV_TYPE_I2C, 0, &lis331dl_platform_data}, {"pmic_audio", SFI_DEV_TYPE_IPC, 1, &no_platform_data}, {"mpu3050", SFI_DEV_TYPE_I2C, 1, &mpu3050_platform_data}, + {"i2c_disp_brig", SFI_DEV_TYPE_I2C, 0, &tc35876x_platform_data}, /* MSIC subdevices */ {"msic_battery", SFI_DEV_TYPE_IPC, 1, &msic_battery_platform_data}, @@ -705,6 +710,7 @@ static const struct devs_id __initconst device_ids[] = { {"msic_audio", SFI_DEV_TYPE_IPC, 1, &msic_audio_platform_data}, {"msic_power_btn", SFI_DEV_TYPE_IPC, 1, &msic_power_btn_platform_data}, {"msic_ocd", SFI_DEV_TYPE_IPC, 1, &msic_ocd_platform_data}, + {"msic_thermal", SFI_DEV_TYPE_IPC, 1, &msic_thermal_platform_data}, {}, }; @@ -848,8 +854,7 @@ static void __init sfi_handle_ipc_dev(struct sfi_device_table_entry *entry) if (mrst_has_msic()) return; - /* ID as IRQ is a hack that will go away */ - pdev = platform_device_alloc(entry->name, entry->irq); + pdev = platform_device_alloc(entry->name, 0); if (pdev == NULL) { pr_err("out of memory for SFI platform device '%s'.\n", entry->name); @@ -1030,6 +1035,7 @@ static int __init pb_keys_init(void) num = sizeof(gpio_button) / sizeof(struct gpio_keys_button); for (i = 0; i < num; i++) { gb[i].gpio = get_gpio_by_name(gb[i].desc); + pr_debug("info[%2d]: name = %s, gpio = %d\n", i, gb[i].desc, gb[i].gpio); if (gb[i].gpio == -1) continue; diff --git a/arch/x86/platform/mrst/pmu.c b/arch/x86/platform/mrst/pmu.c deleted file mode 100644 index c0ac06da57a..00000000000 --- a/arch/x86/platform/mrst/pmu.c +++ /dev/null @@ -1,817 +0,0 @@ -/* - * mrst/pmu.c - driver for MRST Power Management Unit - * - * Copyright (c) 2011, 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. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#include <linux/cpuidle.h> -#include <linux/debugfs.h> -#include <linux/delay.h> -#include <linux/interrupt.h> -#include <linux/module.h> -#include <linux/pci.h> -#include <linux/seq_file.h> -#include <linux/sfi.h> -#include <asm/intel_scu_ipc.h> -#include "pmu.h" - -#define IPCMSG_FW_REVISION 0xF4 - -struct mrst_device { - u16 pci_dev_num; /* DEBUG only */ - u16 lss; - u16 latest_request; - unsigned int pci_state_counts[PCI_D3cold + 1]; /* DEBUG only */ -}; - -/* - * comlete list of MRST PCI devices - */ -static struct mrst_device mrst_devs[] = { -/* 0 */ { 0x0800, LSS_SPI0 }, /* Moorestown SPI Ctrl 0 */ -/* 1 */ { 0x0801, LSS_SPI1 }, /* Moorestown SPI Ctrl 1 */ -/* 2 */ { 0x0802, LSS_I2C0 }, /* Moorestown I2C 0 */ -/* 3 */ { 0x0803, LSS_I2C1 }, /* Moorestown I2C 1 */ -/* 4 */ { 0x0804, LSS_I2C2 }, /* Moorestown I2C 2 */ -/* 5 */ { 0x0805, LSS_KBD }, /* Moorestown Keyboard Ctrl */ -/* 6 */ { 0x0806, LSS_USB_HC }, /* Moorestown USB Ctrl */ -/* 7 */ { 0x0807, LSS_SD_HC0 }, /* Moorestown SD Host Ctrl 0 */ -/* 8 */ { 0x0808, LSS_SD_HC1 }, /* Moorestown SD Host Ctrl 1 */ -/* 9 */ { 0x0809, LSS_NAND }, /* Moorestown NAND Ctrl */ -/* 10 */ { 0x080a, LSS_AUDIO }, /* Moorestown Audio Ctrl */ -/* 11 */ { 0x080b, LSS_IMAGING }, /* Moorestown ISP */ -/* 12 */ { 0x080c, LSS_SECURITY }, /* Moorestown Security Controller */ -/* 13 */ { 0x080d, LSS_DISPLAY }, /* Moorestown External Displays */ -/* 14 */ { 0x080e, 0 }, /* Moorestown SCU IPC */ -/* 15 */ { 0x080f, LSS_GPIO }, /* Moorestown GPIO Controller */ -/* 16 */ { 0x0810, 0 }, /* Moorestown Power Management Unit */ -/* 17 */ { 0x0811, LSS_USB_OTG }, /* Moorestown OTG Ctrl */ -/* 18 */ { 0x0812, LSS_SPI2 }, /* Moorestown SPI Ctrl 2 */ -/* 19 */ { 0x0813, 0 }, /* Moorestown SC DMA */ -/* 20 */ { 0x0814, LSS_AUDIO_LPE }, /* Moorestown LPE DMA */ -/* 21 */ { 0x0815, LSS_AUDIO_SSP }, /* Moorestown SSP0 */ - -/* 22 */ { 0x084F, LSS_SD_HC2 }, /* Moorestown SD Host Ctrl 2 */ - -/* 23 */ { 0x4102, 0 }, /* Lincroft */ -/* 24 */ { 0x4110, 0 }, /* Lincroft */ -}; - -/* n.b. We ignore PCI-id 0x815 in LSS9 b/c Linux has no driver for it */ -static u16 mrst_lss9_pci_ids[] = {0x080a, 0x0814, 0}; -static u16 mrst_lss10_pci_ids[] = {0x0800, 0x0801, 0x0802, 0x0803, - 0x0804, 0x0805, 0x080f, 0}; - -/* handle concurrent SMP invokations of pmu_pci_set_power_state() */ -static spinlock_t mrst_pmu_power_state_lock; - -static unsigned int wake_counters[MRST_NUM_LSS]; /* DEBUG only */ -static unsigned int pmu_irq_stats[INT_INVALID + 1]; /* DEBUG only */ - -static int graphics_is_off; -static int lss_s0i3_enabled; -static bool mrst_pmu_s0i3_enable; - -/* debug counters */ -static u32 pmu_wait_ready_calls; -static u32 pmu_wait_ready_udelays; -static u32 pmu_wait_ready_udelays_max; -static u32 pmu_wait_done_calls; -static u32 pmu_wait_done_udelays; -static u32 pmu_wait_done_udelays_max; -static u32 pmu_set_power_state_entry; -static u32 pmu_set_power_state_send_cmd; - -static struct mrst_device *pci_id_2_mrst_dev(u16 pci_dev_num) -{ - int index = 0; - - if ((pci_dev_num >= 0x0800) && (pci_dev_num <= 0x815)) - index = pci_dev_num - 0x800; - else if (pci_dev_num == 0x084F) - index = 22; - else if (pci_dev_num == 0x4102) - index = 23; - else if (pci_dev_num == 0x4110) - index = 24; - - if (pci_dev_num != mrst_devs[index].pci_dev_num) { - WARN_ONCE(1, FW_BUG "Unknown PCI device 0x%04X\n", pci_dev_num); - return 0; - } - - return &mrst_devs[index]; -} - -/** - * mrst_pmu_validate_cstates - * @dev: cpuidle_device - * - * Certain states are not appropriate for governor to pick in some cases. - * This function will be called as cpuidle_device's prepare callback and - * thus tells governor to ignore such states when selecting the next state - * to enter. - */ - -#define IDLE_STATE4_IS_C6 4 -#define IDLE_STATE5_IS_S0I3 5 - -int mrst_pmu_invalid_cstates(void) -{ - int cpu = smp_processor_id(); - - /* - * Demote to C4 if the PMU is busy. - * Since LSS changes leave the busy bit clear... - * busy means either the PMU is waiting for an ACK-C6 that - * isn't coming due to an MWAIT that returned immediately; - * or we returned from S0i3 successfully, and the PMU - * is not done sending us interrupts. - */ - if (pmu_read_busy_status()) - return 1 << IDLE_STATE4_IS_C6 | 1 << IDLE_STATE5_IS_S0I3; - - /* - * Disallow S0i3 if: PMU is not initialized, or CPU1 is active, - * or if device LSS is insufficient, or the GPU is active, - * or if it has been explicitly disabled. - */ - if (!pmu_reg || !cpumask_equal(cpu_online_mask, cpumask_of(cpu)) || - !lss_s0i3_enabled || !graphics_is_off || !mrst_pmu_s0i3_enable) - return 1 << IDLE_STATE5_IS_S0I3; - else - return 0; -} - -/* - * pmu_update_wake_counters(): read PM_WKS, update wake_counters[] - * DEBUG only. - */ -static void pmu_update_wake_counters(void) -{ - int lss; - u32 wake_status; - - wake_status = pmu_read_wks(); - - for (lss = 0; lss < MRST_NUM_LSS; ++lss) { - if (wake_status & (1 << lss)) - wake_counters[lss]++; - } -} - -int mrst_pmu_s0i3_entry(void) -{ - int status; - - /* Clear any possible error conditions */ - pmu_write_ics(0x300); - - /* set wake control to current D-states */ - pmu_write_wssc(S0I3_SSS_TARGET); - - status = mrst_s0i3_entry(PM_S0I3_COMMAND, &pmu_reg->pm_cmd); - pmu_update_wake_counters(); - return status; -} - -/* poll for maximum of 5ms for busy bit to clear */ -static int pmu_wait_ready(void) -{ - int udelays; - - pmu_wait_ready_calls++; - - for (udelays = 0; udelays < 500; ++udelays) { - if (udelays > pmu_wait_ready_udelays_max) - pmu_wait_ready_udelays_max = udelays; - - if (pmu_read_busy_status() == 0) - return 0; - - udelay(10); - pmu_wait_ready_udelays++; - } - - /* - * if this fires, observe - * /sys/kernel/debug/mrst_pmu_wait_ready_calls - * /sys/kernel/debug/mrst_pmu_wait_ready_udelays - */ - WARN_ONCE(1, "SCU not ready for 5ms"); - return -EBUSY; -} -/* poll for maximum of 50ms us for busy bit to clear */ -static int pmu_wait_done(void) -{ - int udelays; - - pmu_wait_done_calls++; - - for (udelays = 0; udelays < 500; ++udelays) { - if (udelays > pmu_wait_done_udelays_max) - pmu_wait_done_udelays_max = udelays; - - if (pmu_read_busy_status() == 0) - return 0; - - udelay(100); - pmu_wait_done_udelays++; - } - - /* - * if this fires, observe - * /sys/kernel/debug/mrst_pmu_wait_done_calls - * /sys/kernel/debug/mrst_pmu_wait_done_udelays - */ - WARN_ONCE(1, "SCU not done for 50ms"); - return -EBUSY; -} - -u32 mrst_pmu_msi_is_disabled(void) -{ - return pmu_msi_is_disabled(); -} - -void mrst_pmu_enable_msi(void) -{ - pmu_msi_enable(); -} - -/** - * pmu_irq - pmu driver interrupt handler - * Context: interrupt context - */ -static irqreturn_t pmu_irq(int irq, void *dummy) -{ - union pmu_pm_ics pmu_ics; - - pmu_ics.value = pmu_read_ics(); - - if (!pmu_ics.bits.pending) - return IRQ_NONE; - - switch (pmu_ics.bits.cause) { - case INT_SPURIOUS: - case INT_CMD_DONE: - case INT_CMD_ERR: - case INT_WAKE_RX: - case INT_SS_ERROR: - case INT_S0IX_MISS: - case INT_NO_ACKC6: - pmu_irq_stats[pmu_ics.bits.cause]++; - break; - default: - pmu_irq_stats[INT_INVALID]++; - } - - pmu_write_ics(pmu_ics.value); /* Clear pending interrupt */ - - return IRQ_HANDLED; -} - -/* - * Translate PCI power management to MRST LSS D-states - */ -static int pci_2_mrst_state(int lss, pci_power_t pci_state) -{ - switch (pci_state) { - case PCI_D0: - if (SSMSK(D0i1, lss) & D0I1_ACG_SSS_TARGET) - return D0i1; - else - return D0; - case PCI_D1: - return D0i1; - case PCI_D2: - return D0i2; - case PCI_D3hot: - case PCI_D3cold: - return D0i3; - default: - WARN(1, "pci_state %d\n", pci_state); - return 0; - } -} - -static int pmu_issue_command(u32 pm_ssc) -{ - union pmu_pm_set_cfg_cmd_t command; - - if (pmu_read_busy_status()) { - pr_debug("pmu is busy, Operation not permitted\n"); - return -1; - } - - /* - * enable interrupts in PMU so that interrupts are - * propagated when ioc bit for a particular set - * command is set - */ - - pmu_irq_enable(); - - /* Configure the sub systems for pmu2 */ - - pmu_write_ssc(pm_ssc); - - /* - * Send the set config command for pmu its configured - * for mode CM_IMMEDIATE & hence with No Trigger - */ - - command.pmu2_params.d_param.cfg_mode = CM_IMMEDIATE; - command.pmu2_params.d_param.cfg_delay = 0; - command.pmu2_params.d_param.rsvd = 0; - - /* construct the command to send SET_CFG to particular PMU */ - command.pmu2_params.d_param.cmd = SET_CFG_CMD; - command.pmu2_params.d_param.ioc = 0; - command.pmu2_params.d_param.mode_id = 0; - command.pmu2_params.d_param.sys_state = SYS_STATE_S0I0; - - /* write the value of PM_CMD into particular PMU */ - pr_debug("pmu command being written %x\n", - command.pmu_pm_set_cfg_cmd_value); - - pmu_write_cmd(command.pmu_pm_set_cfg_cmd_value); - - return 0; -} - -static u16 pmu_min_lss_pci_req(u16 *ids, u16 pci_state) -{ - u16 existing_request; - int i; - - for (i = 0; ids[i]; ++i) { - struct mrst_device *mrst_dev; - - mrst_dev = pci_id_2_mrst_dev(ids[i]); - if (unlikely(!mrst_dev)) - continue; - - existing_request = mrst_dev->latest_request; - if (existing_request < pci_state) - pci_state = existing_request; - } - return pci_state; -} - -/** - * pmu_pci_set_power_state - Callback function is used by all the PCI devices - * for a platform specific device power on/shutdown. - */ - -int pmu_pci_set_power_state(struct pci_dev *pdev, pci_power_t pci_state) -{ - u32 old_sss, new_sss; - int status = 0; - struct mrst_device *mrst_dev; - - pmu_set_power_state_entry++; - - BUG_ON(pdev->vendor != PCI_VENDOR_ID_INTEL); - BUG_ON(pci_state < PCI_D0 || pci_state > PCI_D3cold); - - mrst_dev = pci_id_2_mrst_dev(pdev->device); - if (unlikely(!mrst_dev)) - return -ENODEV; - - mrst_dev->pci_state_counts[pci_state]++; /* count invocations */ - - /* PMU driver calls self as part of PCI initialization, ignore */ - if (pdev->device == PCI_DEV_ID_MRST_PMU) - return 0; - - BUG_ON(!pmu_reg); /* SW bug if called before initialized */ - - spin_lock(&mrst_pmu_power_state_lock); - - if (pdev->d3_delay) { - dev_dbg(&pdev->dev, "d3_delay %d, should be 0\n", - pdev->d3_delay); - pdev->d3_delay = 0; - } - /* - * If Lincroft graphics, simply remember state - */ - if ((pdev->class >> 16) == PCI_BASE_CLASS_DISPLAY - && !((pdev->class & PCI_SUB_CLASS_MASK) >> 8)) { - if (pci_state == PCI_D0) - graphics_is_off = 0; - else - graphics_is_off = 1; - goto ret; - } - - if (!mrst_dev->lss) - goto ret; /* device with no LSS */ - - if (mrst_dev->latest_request == pci_state) - goto ret; /* no change */ - - mrst_dev->latest_request = pci_state; /* record latest request */ - - /* - * LSS9 and LSS10 contain multiple PCI devices. - * Use the lowest numbered (highest power) state in the LSS - */ - if (mrst_dev->lss == 9) - pci_state = pmu_min_lss_pci_req(mrst_lss9_pci_ids, pci_state); - else if (mrst_dev->lss == 10) - pci_state = pmu_min_lss_pci_req(mrst_lss10_pci_ids, pci_state); - - status = pmu_wait_ready(); - if (status) - goto ret; - - old_sss = pmu_read_sss(); - new_sss = old_sss & ~SSMSK(3, mrst_dev->lss); - new_sss |= SSMSK(pci_2_mrst_state(mrst_dev->lss, pci_state), - mrst_dev->lss); - - if (new_sss == old_sss) - goto ret; /* nothing to do */ - - pmu_set_power_state_send_cmd++; - - status = pmu_issue_command(new_sss); - - if (unlikely(status != 0)) { - dev_err(&pdev->dev, "Failed to Issue a PM command\n"); - goto ret; - } - - if (pmu_wait_done()) - goto ret; - - lss_s0i3_enabled = - ((pmu_read_sss() & S0I3_SSS_TARGET) == S0I3_SSS_TARGET); -ret: - spin_unlock(&mrst_pmu_power_state_lock); - return status; -} - -#ifdef CONFIG_DEBUG_FS -static char *d0ix_names[] = {"D0", "D0i1", "D0i2", "D0i3"}; - -static inline const char *d0ix_name(int state) -{ - return d0ix_names[(int) state]; -} - -static int debug_mrst_pmu_show(struct seq_file *s, void *unused) -{ - struct pci_dev *pdev = NULL; - u32 cur_pmsss; - int lss; - - seq_printf(s, "0x%08X D0I1_ACG_SSS_TARGET\n", D0I1_ACG_SSS_TARGET); - - cur_pmsss = pmu_read_sss(); - - seq_printf(s, "0x%08X S0I3_SSS_TARGET\n", S0I3_SSS_TARGET); - - seq_printf(s, "0x%08X Current SSS ", cur_pmsss); - seq_printf(s, lss_s0i3_enabled ? "\n" : "[BLOCKS s0i3]\n"); - - if (cpumask_equal(cpu_online_mask, cpumask_of(0))) - seq_printf(s, "cpu0 is only cpu online\n"); - else - seq_printf(s, "cpu0 is NOT only cpu online [BLOCKS S0i3]\n"); - - seq_printf(s, "GFX: %s\n", graphics_is_off ? "" : "[BLOCKS s0i3]"); - - - for_each_pci_dev(pdev) { - int pos; - u16 pmcsr; - struct mrst_device *mrst_dev; - int i; - - mrst_dev = pci_id_2_mrst_dev(pdev->device); - - seq_printf(s, "%s %04x/%04X %-16.16s ", - dev_name(&pdev->dev), - pdev->vendor, pdev->device, - dev_driver_string(&pdev->dev)); - - if (unlikely (!mrst_dev)) { - seq_printf(s, " UNKNOWN\n"); - continue; - } - - if (mrst_dev->lss) - seq_printf(s, "LSS %2d %-4s ", mrst_dev->lss, - d0ix_name(((cur_pmsss >> - (mrst_dev->lss * 2)) & 0x3))); - else - seq_printf(s, " "); - - /* PCI PM config space setting */ - pos = pci_find_capability(pdev, PCI_CAP_ID_PM); - if (pos != 0) { - pci_read_config_word(pdev, pos + PCI_PM_CTRL, &pmcsr); - seq_printf(s, "PCI-%-4s", - pci_power_name(pmcsr & PCI_PM_CTRL_STATE_MASK)); - } else { - seq_printf(s, " "); - } - - seq_printf(s, " %s ", pci_power_name(mrst_dev->latest_request)); - for (i = 0; i <= PCI_D3cold; ++i) - seq_printf(s, "%d ", mrst_dev->pci_state_counts[i]); - - if (mrst_dev->lss) { - unsigned int lssmask; - - lssmask = SSMSK(D0i3, mrst_dev->lss); - - if ((lssmask & S0I3_SSS_TARGET) && - ((lssmask & cur_pmsss) != - (lssmask & S0I3_SSS_TARGET))) - seq_printf(s , "[BLOCKS s0i3]"); - } - - seq_printf(s, "\n"); - } - seq_printf(s, "Wake Counters:\n"); - for (lss = 0; lss < MRST_NUM_LSS; ++lss) - seq_printf(s, "LSS%d %d\n", lss, wake_counters[lss]); - - seq_printf(s, "Interrupt Counters:\n"); - seq_printf(s, - "INT_SPURIOUS \t%8u\n" "INT_CMD_DONE \t%8u\n" - "INT_CMD_ERR \t%8u\n" "INT_WAKE_RX \t%8u\n" - "INT_SS_ERROR \t%8u\n" "INT_S0IX_MISS\t%8u\n" - "INT_NO_ACKC6 \t%8u\n" "INT_INVALID \t%8u\n", - pmu_irq_stats[INT_SPURIOUS], pmu_irq_stats[INT_CMD_DONE], - pmu_irq_stats[INT_CMD_ERR], pmu_irq_stats[INT_WAKE_RX], - pmu_irq_stats[INT_SS_ERROR], pmu_irq_stats[INT_S0IX_MISS], - pmu_irq_stats[INT_NO_ACKC6], pmu_irq_stats[INT_INVALID]); - - seq_printf(s, "mrst_pmu_wait_ready_calls %8d\n", - pmu_wait_ready_calls); - seq_printf(s, "mrst_pmu_wait_ready_udelays %8d\n", - pmu_wait_ready_udelays); - seq_printf(s, "mrst_pmu_wait_ready_udelays_max %8d\n", - pmu_wait_ready_udelays_max); - seq_printf(s, "mrst_pmu_wait_done_calls %8d\n", - pmu_wait_done_calls); - seq_printf(s, "mrst_pmu_wait_done_udelays %8d\n", - pmu_wait_done_udelays); - seq_printf(s, "mrst_pmu_wait_done_udelays_max %8d\n", - pmu_wait_done_udelays_max); - seq_printf(s, "mrst_pmu_set_power_state_entry %8d\n", - pmu_set_power_state_entry); - seq_printf(s, "mrst_pmu_set_power_state_send_cmd %8d\n", - pmu_set_power_state_send_cmd); - seq_printf(s, "SCU busy: %d\n", pmu_read_busy_status()); - - return 0; -} - -static int debug_mrst_pmu_open(struct inode *inode, struct file *file) -{ - return single_open(file, debug_mrst_pmu_show, NULL); -} - -static const struct file_operations devices_state_operations = { - .open = debug_mrst_pmu_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; -#endif /* DEBUG_FS */ - -/* - * Validate SCU PCI shim PCI vendor capability byte - * against LSS hard-coded in mrst_devs[] above. - * DEBUG only. - */ -static void pmu_scu_firmware_debug(void) -{ - struct pci_dev *pdev = NULL; - - for_each_pci_dev(pdev) { - struct mrst_device *mrst_dev; - u8 pci_config_lss; - int pos; - - mrst_dev = pci_id_2_mrst_dev(pdev->device); - if (unlikely(!mrst_dev)) { - printk(KERN_ERR FW_BUG "pmu: Unknown " - "PCI device 0x%04X\n", pdev->device); - continue; - } - - if (mrst_dev->lss == 0) - continue; /* no LSS in our table */ - - pos = pci_find_capability(pdev, PCI_CAP_ID_VNDR); - if (!pos != 0) { - printk(KERN_ERR FW_BUG "pmu: 0x%04X " - "missing PCI Vendor Capability\n", - pdev->device); - continue; - } - pci_read_config_byte(pdev, pos + 4, &pci_config_lss); - if (!(pci_config_lss & PCI_VENDOR_CAP_LOG_SS_MASK)) { - printk(KERN_ERR FW_BUG "pmu: 0x%04X " - "invalid PCI Vendor Capability 0x%x " - " expected LSS 0x%X\n", - pdev->device, pci_config_lss, mrst_dev->lss); - continue; - } - pci_config_lss &= PCI_VENDOR_CAP_LOG_ID_MASK; - - if (mrst_dev->lss == pci_config_lss) - continue; - - printk(KERN_ERR FW_BUG "pmu: 0x%04X LSS = %d, expected %d\n", - pdev->device, pci_config_lss, mrst_dev->lss); - } -} - -/** - * pmu_probe - */ -static int __devinit pmu_probe(struct pci_dev *pdev, - const struct pci_device_id *pci_id) -{ - int ret; - struct mrst_pmu_reg *pmu; - - /* Init the device */ - ret = pci_enable_device(pdev); - if (ret) { - dev_err(&pdev->dev, "Unable to Enable PCI device\n"); - return ret; - } - - ret = pci_request_regions(pdev, MRST_PMU_DRV_NAME); - if (ret < 0) { - dev_err(&pdev->dev, "Cannot obtain PCI resources, aborting\n"); - goto out_err1; - } - - /* Map the memory of PMU reg base */ - pmu = pci_iomap(pdev, 0, 0); - if (!pmu) { - dev_err(&pdev->dev, "Unable to map the PMU address space\n"); - ret = -ENOMEM; - goto out_err2; - } - -#ifdef CONFIG_DEBUG_FS - /* /sys/kernel/debug/mrst_pmu */ - (void) debugfs_create_file("mrst_pmu", S_IFREG | S_IRUGO, - NULL, NULL, &devices_state_operations); -#endif - pmu_reg = pmu; /* success */ - - if (request_irq(pdev->irq, pmu_irq, 0, MRST_PMU_DRV_NAME, NULL)) { - dev_err(&pdev->dev, "Registering isr has failed\n"); - ret = -1; - goto out_err3; - } - - pmu_scu_firmware_debug(); - - pmu_write_wkc(S0I3_WAKE_SOURCES); /* Enable S0i3 wakeup sources */ - - pmu_wait_ready(); - - pmu_write_ssc(D0I1_ACG_SSS_TARGET); /* Enable Auto-Clock_Gating */ - pmu_write_cmd(0x201); - - spin_lock_init(&mrst_pmu_power_state_lock); - - /* Enable the hardware interrupt */ - pmu_irq_enable(); - return 0; - -out_err3: - free_irq(pdev->irq, NULL); - pci_iounmap(pdev, pmu_reg); - pmu_reg = NULL; -out_err2: - pci_release_region(pdev, 0); -out_err1: - pci_disable_device(pdev); - return ret; -} - -static void __devexit pmu_remove(struct pci_dev *pdev) -{ - dev_err(&pdev->dev, "Mid PM pmu_remove called\n"); - - /* Freeing up the irq */ - free_irq(pdev->irq, NULL); - - pci_iounmap(pdev, pmu_reg); - pmu_reg = NULL; - - /* disable the current PCI device */ - pci_release_region(pdev, 0); - pci_disable_device(pdev); -} - -static DEFINE_PCI_DEVICE_TABLE(pmu_pci_ids) = { - { PCI_VDEVICE(INTEL, PCI_DEV_ID_MRST_PMU), 0 }, - { } -}; - -MODULE_DEVICE_TABLE(pci, pmu_pci_ids); - -static struct pci_driver driver = { - .name = MRST_PMU_DRV_NAME, - .id_table = pmu_pci_ids, - .probe = pmu_probe, - .remove = __devexit_p(pmu_remove), -}; - -/** - * pmu_pci_register - register the PMU driver as PCI device - */ -static int __init pmu_pci_register(void) -{ - return pci_register_driver(&driver); -} - -/* Register and probe via fs_initcall() to preceed device_initcall() */ -fs_initcall(pmu_pci_register); - -static void __exit mid_pci_cleanup(void) -{ - pci_unregister_driver(&driver); -} - -static int ia_major; -static int ia_minor; - -static int pmu_sfi_parse_oem(struct sfi_table_header *table) -{ - struct sfi_table_simple *sb; - - sb = (struct sfi_table_simple *)table; - ia_major = (sb->pentry[1] >> 0) & 0xFFFF; - ia_minor = (sb->pentry[1] >> 16) & 0xFFFF; - printk(KERN_INFO "mrst_pmu: IA FW version v%x.%x\n", - ia_major, ia_minor); - - return 0; -} - -static int __init scu_fw_check(void) -{ - int ret; - u32 fw_version; - - if (!pmu_reg) - return 0; /* this driver didn't probe-out */ - - sfi_table_parse("OEMB", NULL, NULL, pmu_sfi_parse_oem); - - if (ia_major < 0x6005 || ia_minor < 0x1525) { - WARN(1, "mrst_pmu: IA FW version too old\n"); - return -1; - } - - ret = intel_scu_ipc_command(IPCMSG_FW_REVISION, 0, NULL, 0, - &fw_version, 1); - - if (ret) { - WARN(1, "mrst_pmu: IPC FW version? %d\n", ret); - } else { - int scu_major = (fw_version >> 8) & 0xFF; - int scu_minor = (fw_version >> 0) & 0xFF; - - printk(KERN_INFO "mrst_pmu: firmware v%x\n", fw_version); - - if ((scu_major >= 0xC0) && (scu_minor >= 0x49)) { - printk(KERN_INFO "mrst_pmu: enabling S0i3\n"); - mrst_pmu_s0i3_enable = true; - } else { - WARN(1, "mrst_pmu: S0i3 disabled, old firmware %X.%X", - scu_major, scu_minor); - } - } - return 0; -} -late_initcall(scu_fw_check); -module_exit(mid_pci_cleanup); diff --git a/arch/x86/platform/mrst/pmu.h b/arch/x86/platform/mrst/pmu.h deleted file mode 100644 index bfbfe64b167..00000000000 --- a/arch/x86/platform/mrst/pmu.h +++ /dev/null @@ -1,234 +0,0 @@ -/* - * mrst/pmu.h - private definitions for MRST Power Management Unit mrst/pmu.c - * - * Copyright (c) 2011, 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. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#ifndef _MRST_PMU_H_ -#define _MRST_PMU_H_ - -#define PCI_DEV_ID_MRST_PMU 0x0810 -#define MRST_PMU_DRV_NAME "mrst_pmu" -#define PCI_SUB_CLASS_MASK 0xFF00 - -#define PCI_VENDOR_CAP_LOG_ID_MASK 0x7F -#define PCI_VENDOR_CAP_LOG_SS_MASK 0x80 - -#define SUB_SYS_ALL_D0I1 0x01155555 -#define S0I3_WAKE_SOURCES 0x00001FFF - -#define PM_S0I3_COMMAND \ - ((0 << 31) | /* Reserved */ \ - (0 << 30) | /* Core must be idle */ \ - (0xc2 << 22) | /* ACK C6 trigger */ \ - (3 << 19) | /* Trigger on DMI message */ \ - (3 << 16) | /* Enter S0i3 */ \ - (0 << 13) | /* Numeric mode ID (sw) */ \ - (3 << 9) | /* Trigger mode */ \ - (0 << 8) | /* Do not interrupt */ \ - (1 << 0)) /* Set configuration */ - -#define LSS_DMI 0 -#define LSS_SD_HC0 1 -#define LSS_SD_HC1 2 -#define LSS_NAND 3 -#define LSS_IMAGING 4 -#define LSS_SECURITY 5 -#define LSS_DISPLAY 6 -#define LSS_USB_HC 7 -#define LSS_USB_OTG 8 -#define LSS_AUDIO 9 -#define LSS_AUDIO_LPE 9 -#define LSS_AUDIO_SSP 9 -#define LSS_I2C0 10 -#define LSS_I2C1 10 -#define LSS_I2C2 10 -#define LSS_KBD 10 -#define LSS_SPI0 10 -#define LSS_SPI1 10 -#define LSS_SPI2 10 -#define LSS_GPIO 10 -#define LSS_SRAM 11 /* used by SCU, do not touch */ -#define LSS_SD_HC2 12 -/* LSS hardware bits 15,14,13 are hardwired to 0, thus unusable */ -#define MRST_NUM_LSS 13 - -#define MIN(a, b) (((a) < (b)) ? (a) : (b)) - -#define SSMSK(mask, lss) ((mask) << ((lss) * 2)) -#define D0 0 -#define D0i1 1 -#define D0i2 2 -#define D0i3 3 - -#define S0I3_SSS_TARGET ( \ - SSMSK(D0i1, LSS_DMI) | \ - SSMSK(D0i3, LSS_SD_HC0) | \ - SSMSK(D0i3, LSS_SD_HC1) | \ - SSMSK(D0i3, LSS_NAND) | \ - SSMSK(D0i3, LSS_SD_HC2) | \ - SSMSK(D0i3, LSS_IMAGING) | \ - SSMSK(D0i3, LSS_SECURITY) | \ - SSMSK(D0i3, LSS_DISPLAY) | \ - SSMSK(D0i3, LSS_USB_HC) | \ - SSMSK(D0i3, LSS_USB_OTG) | \ - SSMSK(D0i3, LSS_AUDIO) | \ - SSMSK(D0i1, LSS_I2C0)) - -/* - * D0i1 on Langwell is Autonomous Clock Gating (ACG). - * Enable ACG on every LSS except camera and audio - */ -#define D0I1_ACG_SSS_TARGET \ - (SUB_SYS_ALL_D0I1 & ~SSMSK(D0i1, LSS_IMAGING) & ~SSMSK(D0i1, LSS_AUDIO)) - -enum cm_mode { - CM_NOP, /* ignore the config mode value */ - CM_IMMEDIATE, - CM_DELAY, - CM_TRIGGER, - CM_INVALID -}; - -enum sys_state { - SYS_STATE_S0I0, - SYS_STATE_S0I1, - SYS_STATE_S0I2, - SYS_STATE_S0I3, - SYS_STATE_S3, - SYS_STATE_S5 -}; - -#define SET_CFG_CMD 1 - -enum int_status { - INT_SPURIOUS = 0, - INT_CMD_DONE = 1, - INT_CMD_ERR = 2, - INT_WAKE_RX = 3, - INT_SS_ERROR = 4, - INT_S0IX_MISS = 5, - INT_NO_ACKC6 = 6, - INT_INVALID = 7, -}; - -/* PMU register interface */ -static struct mrst_pmu_reg { - u32 pm_sts; /* 0x00 */ - u32 pm_cmd; /* 0x04 */ - u32 pm_ics; /* 0x08 */ - u32 _resv1; /* 0x0C */ - u32 pm_wkc[2]; /* 0x10 */ - u32 pm_wks[2]; /* 0x18 */ - u32 pm_ssc[4]; /* 0x20 */ - u32 pm_sss[4]; /* 0x30 */ - u32 pm_wssc[4]; /* 0x40 */ - u32 pm_c3c4; /* 0x50 */ - u32 pm_c5c6; /* 0x54 */ - u32 pm_msi_disable; /* 0x58 */ -} *pmu_reg; - -static inline u32 pmu_read_sts(void) { return readl(&pmu_reg->pm_sts); } -static inline u32 pmu_read_ics(void) { return readl(&pmu_reg->pm_ics); } -static inline u32 pmu_read_wks(void) { return readl(&pmu_reg->pm_wks[0]); } -static inline u32 pmu_read_sss(void) { return readl(&pmu_reg->pm_sss[0]); } - -static inline void pmu_write_cmd(u32 arg) { writel(arg, &pmu_reg->pm_cmd); } -static inline void pmu_write_ics(u32 arg) { writel(arg, &pmu_reg->pm_ics); } -static inline void pmu_write_wkc(u32 arg) { writel(arg, &pmu_reg->pm_wkc[0]); } -static inline void pmu_write_ssc(u32 arg) { writel(arg, &pmu_reg->pm_ssc[0]); } -static inline void pmu_write_wssc(u32 arg) - { writel(arg, &pmu_reg->pm_wssc[0]); } - -static inline void pmu_msi_enable(void) { writel(0, &pmu_reg->pm_msi_disable); } -static inline u32 pmu_msi_is_disabled(void) - { return readl(&pmu_reg->pm_msi_disable); } - -union pmu_pm_ics { - struct { - u32 cause:8; - u32 enable:1; - u32 pending:1; - u32 reserved:22; - } bits; - u32 value; -}; - -static inline void pmu_irq_enable(void) -{ - union pmu_pm_ics pmu_ics; - - pmu_ics.value = pmu_read_ics(); - pmu_ics.bits.enable = 1; - pmu_write_ics(pmu_ics.value); -} - -union pmu_pm_status { - struct { - u32 pmu_rev:8; - u32 pmu_busy:1; - u32 mode_id:4; - u32 Reserved:19; - } pmu_status_parts; - u32 pmu_status_value; -}; - -static inline int pmu_read_busy_status(void) -{ - union pmu_pm_status result; - - result.pmu_status_value = pmu_read_sts(); - - return result.pmu_status_parts.pmu_busy; -} - -/* pmu set config parameters */ -struct cfg_delay_param_t { - u32 cmd:8; - u32 ioc:1; - u32 cfg_mode:4; - u32 mode_id:3; - u32 sys_state:3; - u32 cfg_delay:8; - u32 rsvd:5; -}; - -struct cfg_trig_param_t { - u32 cmd:8; - u32 ioc:1; - u32 cfg_mode:4; - u32 mode_id:3; - u32 sys_state:3; - u32 cfg_trig_type:3; - u32 cfg_trig_val:8; - u32 cmbi:1; - u32 rsvd1:1; -}; - -union pmu_pm_set_cfg_cmd_t { - union { - struct cfg_delay_param_t d_param; - struct cfg_trig_param_t t_param; - } pmu2_params; - u32 pmu_pm_set_cfg_cmd_value; -}; - -#ifdef FUTURE_PATCH -extern int mrst_s0i3_entry(u32 regval, u32 *regaddr); -#else -static inline int mrst_s0i3_entry(u32 regval, u32 *regaddr) { return -1; } -#endif -#endif diff --git a/arch/x86/platform/olpc/olpc-xo15-sci.c b/arch/x86/platform/olpc/olpc-xo15-sci.c index 2b235b77d9a..23e5b9d7977 100644 --- a/arch/x86/platform/olpc/olpc-xo15-sci.c +++ b/arch/x86/platform/olpc/olpc-xo15-sci.c @@ -23,7 +23,66 @@ #define XO15_SCI_CLASS DRV_NAME #define XO15_SCI_DEVICE_NAME "OLPC XO-1.5 SCI" -static unsigned long xo15_sci_gpe; +static unsigned long xo15_sci_gpe; +static bool lid_wake_on_close; + +/* + * The normal ACPI LID wakeup behavior is wake-on-open, but not + * wake-on-close. This is implemented as standard by the XO-1.5 DSDT. + * + * We provide here a sysfs attribute that will additionally enable + * wake-on-close behavior. This is useful (e.g.) when we oportunistically + * suspend with the display running; if the lid is then closed, we want to + * wake up to turn the display off. + * + * This is controlled through a custom method in the XO-1.5 DSDT. + */ +static int set_lid_wake_behavior(bool wake_on_close) +{ + struct acpi_object_list arg_list; + union acpi_object arg; + acpi_status status; + + arg_list.count = 1; + arg_list.pointer = &arg; + arg.type = ACPI_TYPE_INTEGER; + arg.integer.value = wake_on_close; + + status = acpi_evaluate_object(NULL, "\\_SB.PCI0.LID.LIDW", &arg_list, NULL); + if (ACPI_FAILURE(status)) { + pr_warning(PFX "failed to set lid behavior\n"); + return 1; + } + + lid_wake_on_close = wake_on_close; + + return 0; +} + +static ssize_t +lid_wake_on_close_show(struct kobject *s, struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%u\n", lid_wake_on_close); +} + +static ssize_t lid_wake_on_close_store(struct kobject *s, + struct kobj_attribute *attr, + const char *buf, size_t n) +{ + unsigned int val; + + if (sscanf(buf, "%u", &val) != 1) + return -EINVAL; + + set_lid_wake_behavior(!!val); + + return n; +} + +static struct kobj_attribute lid_wake_on_close_attr = + __ATTR(lid_wake_on_close, 0644, + lid_wake_on_close_show, + lid_wake_on_close_store); static void battery_status_changed(void) { @@ -91,6 +150,7 @@ static int xo15_sci_add(struct acpi_device *device) { unsigned long long tmp; acpi_status status; + int r; if (!device) return -EINVAL; @@ -112,6 +172,10 @@ static int xo15_sci_add(struct acpi_device *device) dev_info(&device->dev, "Initialized, GPE = 0x%lx\n", xo15_sci_gpe); + r = sysfs_create_file(&device->dev.kobj, &lid_wake_on_close_attr.attr); + if (r) + goto err_sysfs; + /* Flush queue, and enable all SCI events */ process_sci_queue(); olpc_ec_mask_write(EC_SCI_SRC_ALL); @@ -123,6 +187,11 @@ static int xo15_sci_add(struct acpi_device *device) device_init_wakeup(&device->dev, true); return 0; + +err_sysfs: + acpi_remove_gpe_handler(NULL, xo15_sci_gpe, xo15_sci_gpe_handler); + cancel_work_sync(&sci_work); + return r; } static int xo15_sci_remove(struct acpi_device *device, int type) @@ -130,6 +199,7 @@ static int xo15_sci_remove(struct acpi_device *device, int type) acpi_disable_gpe(NULL, xo15_sci_gpe); acpi_remove_gpe_handler(NULL, xo15_sci_gpe, xo15_sci_gpe_handler); cancel_work_sync(&sci_work); + sysfs_remove_file(&device->dev.kobj, &lid_wake_on_close_attr.attr); return 0; } diff --git a/arch/x86/platform/olpc/olpc.c b/arch/x86/platform/olpc/olpc.c index 7cce722667b..a4bee53c2e5 100644 --- a/arch/x86/platform/olpc/olpc.c +++ b/arch/x86/platform/olpc/olpc.c @@ -20,6 +20,8 @@ #include <linux/platform_device.h> #include <linux/of.h> #include <linux/syscore_ops.h> +#include <linux/debugfs.h> +#include <linux/mutex.h> #include <asm/geode.h> #include <asm/setup.h> @@ -31,6 +33,15 @@ EXPORT_SYMBOL_GPL(olpc_platform_info); static DEFINE_SPINLOCK(ec_lock); +/* debugfs interface to EC commands */ +#define EC_MAX_CMD_ARGS (5 + 1) /* cmd byte + 5 args */ +#define EC_MAX_CMD_REPLY (8) + +static struct dentry *ec_debugfs_dir; +static DEFINE_MUTEX(ec_debugfs_cmd_lock); +static unsigned char ec_debugfs_resp[EC_MAX_CMD_REPLY]; +static unsigned int ec_debugfs_resp_bytes; + /* EC event mask to be applied during suspend (defining wakeup sources). */ static u16 ec_wakeup_mask; @@ -269,6 +280,91 @@ int olpc_ec_sci_query(u16 *sci_value) } EXPORT_SYMBOL_GPL(olpc_ec_sci_query); +static ssize_t ec_debugfs_cmd_write(struct file *file, const char __user *buf, + size_t size, loff_t *ppos) +{ + int i, m; + unsigned char ec_cmd[EC_MAX_CMD_ARGS]; + unsigned int ec_cmd_int[EC_MAX_CMD_ARGS]; + char cmdbuf[64]; + int ec_cmd_bytes; + + mutex_lock(&ec_debugfs_cmd_lock); + + size = simple_write_to_buffer(cmdbuf, sizeof(cmdbuf), ppos, buf, size); + + m = sscanf(cmdbuf, "%x:%u %x %x %x %x %x", &ec_cmd_int[0], + &ec_debugfs_resp_bytes, + &ec_cmd_int[1], &ec_cmd_int[2], &ec_cmd_int[3], + &ec_cmd_int[4], &ec_cmd_int[5]); + if (m < 2 || ec_debugfs_resp_bytes > EC_MAX_CMD_REPLY) { + /* reset to prevent overflow on read */ + ec_debugfs_resp_bytes = 0; + + printk(KERN_DEBUG "olpc-ec: bad ec cmd: " + "cmd:response-count [arg1 [arg2 ...]]\n"); + size = -EINVAL; + goto out; + } + + /* convert scanf'd ints to char */ + ec_cmd_bytes = m - 2; + for (i = 0; i <= ec_cmd_bytes; i++) + ec_cmd[i] = ec_cmd_int[i]; + + printk(KERN_DEBUG "olpc-ec: debugfs cmd 0x%02x with %d args " + "%02x %02x %02x %02x %02x, want %d returns\n", + ec_cmd[0], ec_cmd_bytes, ec_cmd[1], ec_cmd[2], ec_cmd[3], + ec_cmd[4], ec_cmd[5], ec_debugfs_resp_bytes); + + olpc_ec_cmd(ec_cmd[0], (ec_cmd_bytes == 0) ? NULL : &ec_cmd[1], + ec_cmd_bytes, ec_debugfs_resp, ec_debugfs_resp_bytes); + + printk(KERN_DEBUG "olpc-ec: response " + "%02x %02x %02x %02x %02x %02x %02x %02x (%d bytes expected)\n", + ec_debugfs_resp[0], ec_debugfs_resp[1], ec_debugfs_resp[2], + ec_debugfs_resp[3], ec_debugfs_resp[4], ec_debugfs_resp[5], + ec_debugfs_resp[6], ec_debugfs_resp[7], ec_debugfs_resp_bytes); + +out: + mutex_unlock(&ec_debugfs_cmd_lock); + return size; +} + +static ssize_t ec_debugfs_cmd_read(struct file *file, char __user *buf, + size_t size, loff_t *ppos) +{ + unsigned int i, r; + char *rp; + char respbuf[64]; + + mutex_lock(&ec_debugfs_cmd_lock); + rp = respbuf; + rp += sprintf(rp, "%02x", ec_debugfs_resp[0]); + for (i = 1; i < ec_debugfs_resp_bytes; i++) + rp += sprintf(rp, ", %02x", ec_debugfs_resp[i]); + mutex_unlock(&ec_debugfs_cmd_lock); + rp += sprintf(rp, "\n"); + + r = rp - respbuf; + return simple_read_from_buffer(buf, size, ppos, respbuf, r); +} + +static const struct file_operations ec_debugfs_genops = { + .write = ec_debugfs_cmd_write, + .read = ec_debugfs_cmd_read, +}; + +static void setup_debugfs(void) +{ + ec_debugfs_dir = debugfs_create_dir("olpc-ec", 0); + if (ec_debugfs_dir == ERR_PTR(-ENODEV)) + return; + + debugfs_create_file("cmd", 0600, ec_debugfs_dir, NULL, + &ec_debugfs_genops); +} + static int olpc_ec_suspend(void) { return olpc_ec_mask_write(ec_wakeup_mask); @@ -372,6 +468,7 @@ static int __init olpc_init(void) } register_syscore_ops(&olpc_syscore_ops); + setup_debugfs(); return 0; } diff --git a/arch/x86/platform/scx200/scx200_32.c b/arch/x86/platform/scx200/scx200_32.c index 7e004acbe52..7a9ad30d6c9 100644 --- a/arch/x86/platform/scx200/scx200_32.c +++ b/arch/x86/platform/scx200/scx200_32.c @@ -17,8 +17,6 @@ /* Verify that the configuration block really is there */ #define scx200_cb_probe(base) (inw((base) + SCx200_CBA) == (base)) -#define NAME "scx200" - MODULE_AUTHOR("Christer Weinigel <wingel@nano-system.com>"); MODULE_DESCRIPTION("NatSemi SCx200 Driver"); MODULE_LICENSE("GPL"); @@ -29,10 +27,10 @@ unsigned long scx200_gpio_shadow[2]; unsigned scx200_cb_base = 0; static struct pci_device_id scx200_tbl[] = { - { PCI_DEVICE(PCI_VENDOR_ID_NS, PCI_DEVICE_ID_NS_SCx200_BRIDGE) }, - { PCI_DEVICE(PCI_VENDOR_ID_NS, PCI_DEVICE_ID_NS_SC1100_BRIDGE) }, - { PCI_DEVICE(PCI_VENDOR_ID_NS, PCI_DEVICE_ID_NS_SCx200_XBUS) }, - { PCI_DEVICE(PCI_VENDOR_ID_NS, PCI_DEVICE_ID_NS_SC1100_XBUS) }, + { PCI_VDEVICE(NS, PCI_DEVICE_ID_NS_SCx200_BRIDGE) }, + { PCI_VDEVICE(NS, PCI_DEVICE_ID_NS_SC1100_BRIDGE) }, + { PCI_VDEVICE(NS, PCI_DEVICE_ID_NS_SCx200_XBUS) }, + { PCI_VDEVICE(NS, PCI_DEVICE_ID_NS_SC1100_XBUS) }, { }, }; MODULE_DEVICE_TABLE(pci,scx200_tbl); @@ -63,10 +61,11 @@ static int __devinit scx200_probe(struct pci_dev *pdev, const struct pci_device_ if (pdev->device == PCI_DEVICE_ID_NS_SCx200_BRIDGE || pdev->device == PCI_DEVICE_ID_NS_SC1100_BRIDGE) { base = pci_resource_start(pdev, 0); - printk(KERN_INFO NAME ": GPIO base 0x%x\n", base); + pr_info("GPIO base 0x%x\n", base); - if (!request_region(base, SCx200_GPIO_SIZE, "NatSemi SCx200 GPIO")) { - printk(KERN_ERR NAME ": can't allocate I/O for GPIOs\n"); + if (!request_region(base, SCx200_GPIO_SIZE, + "NatSemi SCx200 GPIO")) { + pr_err("can't allocate I/O for GPIOs\n"); return -EBUSY; } @@ -82,11 +81,11 @@ static int __devinit scx200_probe(struct pci_dev *pdev, const struct pci_device_ if (scx200_cb_probe(base)) { scx200_cb_base = base; } else { - printk(KERN_WARNING NAME ": Configuration Block not found\n"); + pr_warn("Configuration Block not found\n"); return -ENODEV; } } - printk(KERN_INFO NAME ": Configuration Block base 0x%x\n", scx200_cb_base); + pr_info("Configuration Block base 0x%x\n", scx200_cb_base); } return 0; @@ -111,8 +110,7 @@ u32 scx200_gpio_configure(unsigned index, u32 mask, u32 bits) static int __init scx200_init(void) { - printk(KERN_INFO NAME ": NatSemi SCx200 Driver\n"); - + pr_info("NatSemi SCx200 Driver\n"); return pci_register_driver(&scx200_pci_driver); } diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index 5b552198f77..3ae0e61abd2 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -157,13 +157,14 @@ static int __init uvhub_to_first_apicid(int uvhub) * clear of the Timeout bit (as well) will free the resource. No reply will * be sent (the hardware will only do one reply per message). */ -static void reply_to_message(struct msg_desc *mdp, struct bau_control *bcp) +static void reply_to_message(struct msg_desc *mdp, struct bau_control *bcp, + int do_acknowledge) { unsigned long dw; struct bau_pq_entry *msg; msg = mdp->msg; - if (!msg->canceled) { + if (!msg->canceled && do_acknowledge) { dw = (msg->swack_vec << UV_SW_ACK_NPENDING) | msg->swack_vec; write_mmr_sw_ack(dw); } @@ -212,8 +213,8 @@ static void bau_process_retry_msg(struct msg_desc *mdp, if (mmr & (msg_res << UV_SW_ACK_NPENDING)) { unsigned long mr; /* - * is the resource timed out? - * make everyone ignore the cancelled message. + * Is the resource timed out? + * Make everyone ignore the cancelled message. */ msg2->canceled = 1; stat->d_canceled++; @@ -231,8 +232,8 @@ static void bau_process_retry_msg(struct msg_desc *mdp, * Do all the things a cpu should do for a TLB shootdown message. * Other cpu's may come here at the same time for this message. */ -static void bau_process_message(struct msg_desc *mdp, - struct bau_control *bcp) +static void bau_process_message(struct msg_desc *mdp, struct bau_control *bcp, + int do_acknowledge) { short socket_ack_count = 0; short *sp; @@ -284,8 +285,9 @@ static void bau_process_message(struct msg_desc *mdp, if (msg_ack_count == bcp->cpus_in_uvhub) { /* * All cpus in uvhub saw it; reply + * (unless we are in the UV2 workaround) */ - reply_to_message(mdp, bcp); + reply_to_message(mdp, bcp, do_acknowledge); } } @@ -491,27 +493,138 @@ static int uv1_wait_completion(struct bau_desc *bau_desc, /* * UV2 has an extra bit of status in the ACTIVATION_STATUS_2 register. */ -static unsigned long uv2_read_status(unsigned long offset, int rshft, int cpu) +static unsigned long uv2_read_status(unsigned long offset, int rshft, int desc) { unsigned long descriptor_status; unsigned long descriptor_status2; descriptor_status = ((read_lmmr(offset) >> rshft) & UV_ACT_STATUS_MASK); - descriptor_status2 = (read_mmr_uv2_status() >> cpu) & 0x1UL; + descriptor_status2 = (read_mmr_uv2_status() >> desc) & 0x1UL; descriptor_status = (descriptor_status << 1) | descriptor_status2; return descriptor_status; } +/* + * Return whether the status of the descriptor that is normally used for this + * cpu (the one indexed by its hub-relative cpu number) is busy. + * The status of the original 32 descriptors is always reflected in the 64 + * bits of UVH_LB_BAU_SB_ACTIVATION_STATUS_0. + * The bit provided by the activation_status_2 register is irrelevant to + * the status if it is only being tested for busy or not busy. + */ +int normal_busy(struct bau_control *bcp) +{ + int cpu = bcp->uvhub_cpu; + int mmr_offset; + int right_shift; + + mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0; + right_shift = cpu * UV_ACT_STATUS_SIZE; + return (((((read_lmmr(mmr_offset) >> right_shift) & + UV_ACT_STATUS_MASK)) << 1) == UV2H_DESC_BUSY); +} + +/* + * Entered when a bau descriptor has gone into a permanent busy wait because + * of a hardware bug. + * Workaround the bug. + */ +int handle_uv2_busy(struct bau_control *bcp) +{ + int busy_one = bcp->using_desc; + int normal = bcp->uvhub_cpu; + int selected = -1; + int i; + unsigned long descriptor_status; + unsigned long status; + int mmr_offset; + struct bau_desc *bau_desc_old; + struct bau_desc *bau_desc_new; + struct bau_control *hmaster = bcp->uvhub_master; + struct ptc_stats *stat = bcp->statp; + cycles_t ttm; + + stat->s_uv2_wars++; + spin_lock(&hmaster->uvhub_lock); + /* try for the original first */ + if (busy_one != normal) { + if (!normal_busy(bcp)) + selected = normal; + } + if (selected < 0) { + /* can't use the normal, select an alternate */ + mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1; + descriptor_status = read_lmmr(mmr_offset); + + /* scan available descriptors 32-63 */ + for (i = 0; i < UV_CPUS_PER_AS; i++) { + if ((hmaster->inuse_map & (1 << i)) == 0) { + status = ((descriptor_status >> + (i * UV_ACT_STATUS_SIZE)) & + UV_ACT_STATUS_MASK) << 1; + if (status != UV2H_DESC_BUSY) { + selected = i + UV_CPUS_PER_AS; + break; + } + } + } + } + + if (busy_one != normal) + /* mark the busy alternate as not in-use */ + hmaster->inuse_map &= ~(1 << (busy_one - UV_CPUS_PER_AS)); + + if (selected >= 0) { + /* switch to the selected descriptor */ + if (selected != normal) { + /* set the selected alternate as in-use */ + hmaster->inuse_map |= + (1 << (selected - UV_CPUS_PER_AS)); + if (selected > stat->s_uv2_wars_hw) + stat->s_uv2_wars_hw = selected; + } + bau_desc_old = bcp->descriptor_base; + bau_desc_old += (ITEMS_PER_DESC * busy_one); + bcp->using_desc = selected; + bau_desc_new = bcp->descriptor_base; + bau_desc_new += (ITEMS_PER_DESC * selected); + *bau_desc_new = *bau_desc_old; + } else { + /* + * All are busy. Wait for the normal one for this cpu to + * free up. + */ + stat->s_uv2_war_waits++; + spin_unlock(&hmaster->uvhub_lock); + ttm = get_cycles(); + do { + cpu_relax(); + } while (normal_busy(bcp)); + spin_lock(&hmaster->uvhub_lock); + /* switch to the original descriptor */ + bcp->using_desc = normal; + bau_desc_old = bcp->descriptor_base; + bau_desc_old += (ITEMS_PER_DESC * bcp->using_desc); + bcp->using_desc = (ITEMS_PER_DESC * normal); + bau_desc_new = bcp->descriptor_base; + bau_desc_new += (ITEMS_PER_DESC * normal); + *bau_desc_new = *bau_desc_old; /* copy the entire descriptor */ + } + spin_unlock(&hmaster->uvhub_lock); + return FLUSH_RETRY_BUSYBUG; +} + static int uv2_wait_completion(struct bau_desc *bau_desc, unsigned long mmr_offset, int right_shift, struct bau_control *bcp, long try) { unsigned long descriptor_stat; cycles_t ttm; - int cpu = bcp->uvhub_cpu; + int desc = bcp->using_desc; + long busy_reps = 0; struct ptc_stats *stat = bcp->statp; - descriptor_stat = uv2_read_status(mmr_offset, right_shift, cpu); + descriptor_stat = uv2_read_status(mmr_offset, right_shift, desc); /* spin on the status MMR, waiting for it to go idle */ while (descriptor_stat != UV2H_DESC_IDLE) { @@ -522,32 +635,35 @@ static int uv2_wait_completion(struct bau_desc *bau_desc, * our message and its state will stay IDLE. */ if ((descriptor_stat == UV2H_DESC_SOURCE_TIMEOUT) || - (descriptor_stat == UV2H_DESC_DEST_STRONG_NACK) || (descriptor_stat == UV2H_DESC_DEST_PUT_ERR)) { stat->s_stimeout++; return FLUSH_GIVEUP; + } else if (descriptor_stat == UV2H_DESC_DEST_STRONG_NACK) { + stat->s_strongnacks++; + bcp->conseccompletes = 0; + return FLUSH_GIVEUP; } else if (descriptor_stat == UV2H_DESC_DEST_TIMEOUT) { stat->s_dtimeout++; - ttm = get_cycles(); - /* - * Our retries may be blocked by all destination - * swack resources being consumed, and a timeout - * pending. In that case hardware returns the - * ERROR that looks like a destination timeout. - */ - if (cycles_2_us(ttm - bcp->send_message) < timeout_us) { - bcp->conseccompletes = 0; - return FLUSH_RETRY_PLUGGED; - } bcp->conseccompletes = 0; return FLUSH_RETRY_TIMEOUT; } else { + busy_reps++; + if (busy_reps > 1000000) { + /* not to hammer on the clock */ + busy_reps = 0; + ttm = get_cycles(); + if ((ttm - bcp->send_message) > + (bcp->clocks_per_100_usec)) { + return handle_uv2_busy(bcp); + } + } /* * descriptor_stat is still BUSY */ cpu_relax(); } - descriptor_stat = uv2_read_status(mmr_offset, right_shift, cpu); + descriptor_stat = uv2_read_status(mmr_offset, right_shift, + desc); } bcp->conseccompletes++; return FLUSH_COMPLETE; @@ -563,17 +679,17 @@ static int wait_completion(struct bau_desc *bau_desc, { int right_shift; unsigned long mmr_offset; - int cpu = bcp->uvhub_cpu; + int desc = bcp->using_desc; - if (cpu < UV_CPUS_PER_AS) { + if (desc < UV_CPUS_PER_AS) { mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0; - right_shift = cpu * UV_ACT_STATUS_SIZE; + right_shift = desc * UV_ACT_STATUS_SIZE; } else { mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1; - right_shift = ((cpu - UV_CPUS_PER_AS) * UV_ACT_STATUS_SIZE); + right_shift = ((desc - UV_CPUS_PER_AS) * UV_ACT_STATUS_SIZE); } - if (is_uv1_hub()) + if (bcp->uvhub_version == 1) return uv1_wait_completion(bau_desc, mmr_offset, right_shift, bcp, try); else @@ -752,19 +868,22 @@ static void handle_cmplt(int completion_status, struct bau_desc *bau_desc, * Returns 1 if it gives up entirely and the original cpu mask is to be * returned to the kernel. */ -int uv_flush_send_and_wait(struct bau_desc *bau_desc, - struct cpumask *flush_mask, struct bau_control *bcp) +int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp) { int seq_number = 0; int completion_stat = 0; + int uv1 = 0; long try = 0; unsigned long index; cycles_t time1; cycles_t time2; struct ptc_stats *stat = bcp->statp; struct bau_control *hmaster = bcp->uvhub_master; + struct uv1_bau_msg_header *uv1_hdr = NULL; + struct uv2_bau_msg_header *uv2_hdr = NULL; + struct bau_desc *bau_desc; - if (is_uv1_hub()) + if (bcp->uvhub_version == 1) uv1_throttle(hmaster, stat); while (hmaster->uvhub_quiesce) @@ -772,22 +891,39 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc, time1 = get_cycles(); do { - if (try == 0) { - bau_desc->header.msg_type = MSG_REGULAR; + bau_desc = bcp->descriptor_base; + bau_desc += (ITEMS_PER_DESC * bcp->using_desc); + if (bcp->uvhub_version == 1) { + uv1 = 1; + uv1_hdr = &bau_desc->header.uv1_hdr; + } else + uv2_hdr = &bau_desc->header.uv2_hdr; + if ((try == 0) || (completion_stat == FLUSH_RETRY_BUSYBUG)) { + if (uv1) + uv1_hdr->msg_type = MSG_REGULAR; + else + uv2_hdr->msg_type = MSG_REGULAR; seq_number = bcp->message_number++; } else { - bau_desc->header.msg_type = MSG_RETRY; + if (uv1) + uv1_hdr->msg_type = MSG_RETRY; + else + uv2_hdr->msg_type = MSG_RETRY; stat->s_retry_messages++; } - bau_desc->header.sequence = seq_number; - index = (1UL << AS_PUSH_SHIFT) | bcp->uvhub_cpu; + if (uv1) + uv1_hdr->sequence = seq_number; + else + uv2_hdr->sequence = seq_number; + index = (1UL << AS_PUSH_SHIFT) | bcp->using_desc; bcp->send_message = get_cycles(); write_mmr_activation(index); try++; completion_stat = wait_completion(bau_desc, bcp, try); + /* UV2: wait_completion() may change the bcp->using_desc */ handle_cmplt(completion_stat, bau_desc, bcp, hmaster, stat); @@ -798,6 +934,7 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc, } cpu_relax(); } while ((completion_stat == FLUSH_RETRY_PLUGGED) || + (completion_stat == FLUSH_RETRY_BUSYBUG) || (completion_stat == FLUSH_RETRY_TIMEOUT)); time2 = get_cycles(); @@ -812,6 +949,7 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc, record_send_stats(time1, time2, bcp, stat, completion_stat, try); if (completion_stat == FLUSH_GIVEUP) + /* FLUSH_GIVEUP will fall back to using IPI's for tlb flush */ return 1; return 0; } @@ -967,7 +1105,7 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, stat->s_ntargself++; bau_desc = bcp->descriptor_base; - bau_desc += ITEMS_PER_DESC * bcp->uvhub_cpu; + bau_desc += (ITEMS_PER_DESC * bcp->using_desc); bau_uvhubs_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE); if (set_distrib_bits(flush_mask, bcp, bau_desc, &locals, &remotes)) return NULL; @@ -980,13 +1118,86 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, * uv_flush_send_and_wait returns 0 if all cpu's were messaged, * or 1 if it gave up and the original cpumask should be returned. */ - if (!uv_flush_send_and_wait(bau_desc, flush_mask, bcp)) + if (!uv_flush_send_and_wait(flush_mask, bcp)) return NULL; else return cpumask; } /* + * Search the message queue for any 'other' message with the same software + * acknowledge resource bit vector. + */ +struct bau_pq_entry *find_another_by_swack(struct bau_pq_entry *msg, + struct bau_control *bcp, unsigned char swack_vec) +{ + struct bau_pq_entry *msg_next = msg + 1; + + if (msg_next > bcp->queue_last) + msg_next = bcp->queue_first; + while ((msg_next->swack_vec != 0) && (msg_next != msg)) { + if (msg_next->swack_vec == swack_vec) + return msg_next; + msg_next++; + if (msg_next > bcp->queue_last) + msg_next = bcp->queue_first; + } + return NULL; +} + +/* + * UV2 needs to work around a bug in which an arriving message has not + * set a bit in the UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE register. + * Such a message must be ignored. + */ +void process_uv2_message(struct msg_desc *mdp, struct bau_control *bcp) +{ + unsigned long mmr_image; + unsigned char swack_vec; + struct bau_pq_entry *msg = mdp->msg; + struct bau_pq_entry *other_msg; + + mmr_image = read_mmr_sw_ack(); + swack_vec = msg->swack_vec; + + if ((swack_vec & mmr_image) == 0) { + /* + * This message was assigned a swack resource, but no + * reserved acknowlegment is pending. + * The bug has prevented this message from setting the MMR. + * And no other message has used the same sw_ack resource. + * Do the requested shootdown but do not reply to the msg. + * (the 0 means make no acknowledge) + */ + bau_process_message(mdp, bcp, 0); + return; + } + + /* + * Some message has set the MMR 'pending' bit; it might have been + * another message. Look for that message. + */ + other_msg = find_another_by_swack(msg, bcp, msg->swack_vec); + if (other_msg) { + /* There is another. Do not ack the current one. */ + bau_process_message(mdp, bcp, 0); + /* + * Let the natural processing of that message acknowledge + * it. Don't get the processing of sw_ack's out of order. + */ + return; + } + + /* + * There is no other message using this sw_ack, so it is safe to + * acknowledge it. + */ + bau_process_message(mdp, bcp, 1); + + return; +} + +/* * The BAU message interrupt comes here. (registered by set_intr_gate) * See entry_64.S * @@ -1009,6 +1220,7 @@ void uv_bau_message_interrupt(struct pt_regs *regs) struct ptc_stats *stat; struct msg_desc msgdesc; + ack_APIC_irq(); time_start = get_cycles(); bcp = &per_cpu(bau_control, smp_processor_id()); @@ -1022,9 +1234,11 @@ void uv_bau_message_interrupt(struct pt_regs *regs) count++; msgdesc.msg_slot = msg - msgdesc.queue_first; - msgdesc.swack_slot = ffs(msg->swack_vec) - 1; msgdesc.msg = msg; - bau_process_message(&msgdesc, bcp); + if (bcp->uvhub_version == 2) + process_uv2_message(&msgdesc, bcp); + else + bau_process_message(&msgdesc, bcp, 1); msg++; if (msg > msgdesc.queue_last) @@ -1036,8 +1250,6 @@ void uv_bau_message_interrupt(struct pt_regs *regs) stat->d_nomsg++; else if (count > 1) stat->d_multmsg++; - - ack_APIC_irq(); } /* @@ -1083,7 +1295,7 @@ static void __init enable_timeouts(void) */ mmr_image |= (1L << SOFTACK_MSHIFT); if (is_uv2_hub()) { - mmr_image |= (1L << UV2_LEG_SHFT); + mmr_image &= ~(1L << UV2_LEG_SHFT); mmr_image |= (1L << UV2_EXT_SHFT); } write_mmr_misc_control(pnode, mmr_image); @@ -1136,13 +1348,13 @@ static int ptc_seq_show(struct seq_file *file, void *data) seq_printf(file, "remotehub numuvhubs numuvhubs16 numuvhubs8 "); seq_printf(file, - "numuvhubs4 numuvhubs2 numuvhubs1 dto retries rok "); + "numuvhubs4 numuvhubs2 numuvhubs1 dto snacks retries rok "); seq_printf(file, "resetp resett giveup sto bz throt swack recv rtime "); seq_printf(file, "all one mult none retry canc nocan reset rcan "); seq_printf(file, - "disable enable\n"); + "disable enable wars warshw warwaits\n"); } if (cpu < num_possible_cpus() && cpu_online(cpu)) { stat = &per_cpu(ptcstats, cpu); @@ -1154,10 +1366,10 @@ static int ptc_seq_show(struct seq_file *file, void *data) stat->s_ntargremotes, stat->s_ntargcpu, stat->s_ntarglocaluvhub, stat->s_ntargremoteuvhub, stat->s_ntarguvhub, stat->s_ntarguvhub16); - seq_printf(file, "%ld %ld %ld %ld %ld ", + seq_printf(file, "%ld %ld %ld %ld %ld %ld ", stat->s_ntarguvhub8, stat->s_ntarguvhub4, stat->s_ntarguvhub2, stat->s_ntarguvhub1, - stat->s_dtimeout); + stat->s_dtimeout, stat->s_strongnacks); seq_printf(file, "%ld %ld %ld %ld %ld %ld %ld %ld ", stat->s_retry_messages, stat->s_retriesok, stat->s_resets_plug, stat->s_resets_timeout, @@ -1173,8 +1385,10 @@ static int ptc_seq_show(struct seq_file *file, void *data) stat->d_nomsg, stat->d_retries, stat->d_canceled, stat->d_nocanceled, stat->d_resets, stat->d_rcanceled); - seq_printf(file, "%ld %ld\n", - stat->s_bau_disabled, stat->s_bau_reenabled); + seq_printf(file, "%ld %ld %ld %ld %ld\n", + stat->s_bau_disabled, stat->s_bau_reenabled, + stat->s_uv2_wars, stat->s_uv2_wars_hw, + stat->s_uv2_war_waits); } return 0; } @@ -1432,12 +1646,15 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode) { int i; int cpu; + int uv1 = 0; unsigned long gpa; unsigned long m; unsigned long n; size_t dsize; struct bau_desc *bau_desc; struct bau_desc *bd2; + struct uv1_bau_msg_header *uv1_hdr; + struct uv2_bau_msg_header *uv2_hdr; struct bau_control *bcp; /* @@ -1451,6 +1668,8 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode) gpa = uv_gpa(bau_desc); n = uv_gpa_to_gnode(gpa); m = uv_gpa_to_offset(gpa); + if (is_uv1_hub()) + uv1 = 1; /* the 14-bit pnode */ write_mmr_descriptor_base(pnode, (n << UV_DESC_PSHIFT | m)); @@ -1461,21 +1680,33 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode) */ for (i = 0, bd2 = bau_desc; i < (ADP_SZ * ITEMS_PER_DESC); i++, bd2++) { memset(bd2, 0, sizeof(struct bau_desc)); - bd2->header.swack_flag = 1; - /* - * The base_dest_nasid set in the message header is the nasid - * of the first uvhub in the partition. The bit map will - * indicate destination pnode numbers relative to that base. - * They may not be consecutive if nasid striding is being used. - */ - bd2->header.base_dest_nasid = UV_PNODE_TO_NASID(base_pnode); - bd2->header.dest_subnodeid = UV_LB_SUBNODEID; - bd2->header.command = UV_NET_ENDPOINT_INTD; - bd2->header.int_both = 1; - /* - * all others need to be set to zero: - * fairness chaining multilevel count replied_to - */ + if (uv1) { + uv1_hdr = &bd2->header.uv1_hdr; + uv1_hdr->swack_flag = 1; + /* + * The base_dest_nasid set in the message header + * is the nasid of the first uvhub in the partition. + * The bit map will indicate destination pnode numbers + * relative to that base. They may not be consecutive + * if nasid striding is being used. + */ + uv1_hdr->base_dest_nasid = + UV_PNODE_TO_NASID(base_pnode); + uv1_hdr->dest_subnodeid = UV_LB_SUBNODEID; + uv1_hdr->command = UV_NET_ENDPOINT_INTD; + uv1_hdr->int_both = 1; + /* + * all others need to be set to zero: + * fairness chaining multilevel count replied_to + */ + } else { + uv2_hdr = &bd2->header.uv2_hdr; + uv2_hdr->swack_flag = 1; + uv2_hdr->base_dest_nasid = + UV_PNODE_TO_NASID(base_pnode); + uv2_hdr->dest_subnodeid = UV_LB_SUBNODEID; + uv2_hdr->command = UV_NET_ENDPOINT_INTD; + } } for_each_present_cpu(cpu) { if (pnode != uv_blade_to_pnode(uv_cpu_to_blade_id(cpu))) @@ -1531,6 +1762,7 @@ static void pq_init(int node, int pnode) write_mmr_payload_first(pnode, pn_first); write_mmr_payload_tail(pnode, first); write_mmr_payload_last(pnode, last); + write_gmmr_sw_ack(pnode, 0xffffUL); /* in effect, all msg_type's are set to MSG_NOOP */ memset(pqp, 0, sizeof(struct bau_pq_entry) * DEST_Q_SIZE); @@ -1584,14 +1816,14 @@ static int calculate_destination_timeout(void) ts_ns = base * mult1 * mult2; ret = ts_ns / 1000; } else { - /* 4 bits 0/1 for 10/80us, 3 bits of multiplier */ - mmr_image = uv_read_local_mmr(UVH_AGING_PRESCALE_SEL); + /* 4 bits 0/1 for 10/80us base, 3 bits of multiplier */ + mmr_image = uv_read_local_mmr(UVH_LB_BAU_MISC_CONTROL); mmr_image = (mmr_image & UV_SA_MASK) >> UV_SA_SHFT; if (mmr_image & (1L << UV2_ACK_UNITS_SHFT)) - mult1 = 80; + base = 80; else - mult1 = 10; - base = mmr_image & UV2_ACK_MASK; + base = 10; + mult1 = mmr_image & UV2_ACK_MASK; ret = mult1 * base; } return ret; @@ -1618,6 +1850,9 @@ static void __init init_per_cpu_tunables(void) bcp->cong_response_us = congested_respns_us; bcp->cong_reps = congested_reps; bcp->cong_period = congested_period; + bcp->clocks_per_100_usec = usec_2_cycles(100); + spin_lock_init(&bcp->queue_lock); + spin_lock_init(&bcp->uvhub_lock); } } @@ -1728,8 +1963,17 @@ static int scan_sock(struct socket_desc *sdp, struct uvhub_desc *bdp, bcp->cpus_in_socket = sdp->num_cpus; bcp->socket_master = *smasterp; bcp->uvhub = bdp->uvhub; + if (is_uv1_hub()) + bcp->uvhub_version = 1; + else if (is_uv2_hub()) + bcp->uvhub_version = 2; + else { + printk(KERN_EMERG "uvhub version not 1 or 2\n"); + return 1; + } bcp->uvhub_master = *hmasterp; bcp->uvhub_cpu = uv_cpu_hub_info(cpu)->blade_processor_id; + bcp->using_desc = bcp->uvhub_cpu; if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) { printk(KERN_EMERG "%d cpus per uvhub invalid\n", bcp->uvhub_cpu); @@ -1845,6 +2089,8 @@ static int __init uv_bau_init(void) uv_base_pnode = uv_blade_to_pnode(uvhub); } + enable_timeouts(); + if (init_per_cpu(nuvhubs, uv_base_pnode)) { nobau = 1; return 0; @@ -1855,7 +2101,6 @@ static int __init uv_bau_init(void) if (uv_blade_nr_possible_cpus(uvhub)) init_uvhub(uvhub, vector, uv_base_pnode); - enable_timeouts(); alloc_intr_gate(vector, uv_bau_message_intr1); for_each_possible_blade(uvhub) { @@ -1867,7 +2112,8 @@ static int __init uv_bau_init(void) val = 1L << 63; write_gmmr_activation(pnode, val); mmr = 1; /* should be 1 to broadcast to both sockets */ - write_mmr_data_broadcast(pnode, mmr); + if (!is_uv1_hub()) + write_mmr_data_broadcast(pnode, mmr); } } diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c index 374a05d8ad2..f25c2765a5c 100644 --- a/arch/x86/platform/uv/uv_irq.c +++ b/arch/x86/platform/uv/uv_irq.c @@ -25,7 +25,7 @@ struct uv_irq_2_mmr_pnode{ int irq; }; -static spinlock_t uv_irq_lock; +static DEFINE_SPINLOCK(uv_irq_lock); static struct rb_root uv_irq_root; static int uv_set_irq_affinity(struct irq_data *, const struct cpumask *, bool); diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c index 9f29a01ee1b..5032e0d19b8 100644 --- a/arch/x86/platform/uv/uv_time.c +++ b/arch/x86/platform/uv/uv_time.c @@ -37,7 +37,7 @@ static void uv_rtc_timer_setup(enum clock_event_mode, static struct clocksource clocksource_uv = { .name = RTC_NAME, - .rating = 400, + .rating = 299, .read = uv_read_rtc, .mask = (cycle_t)UVH_RTC_REAL_TIME_CLOCK_MASK, .flags = CLOCK_SOURCE_IS_CONTINUOUS, @@ -379,10 +379,6 @@ static __init int uv_rtc_setup_clock(void) if (!is_uv_system()) return -ENODEV; - /* If single blade, prefer tsc */ - if (uv_num_possible_blades() == 1) - clocksource_uv.rating = 250; - rc = clocksource_register_hz(&clocksource_uv, sn_rtc_cycles_per_second); if (rc) printk(KERN_INFO "UV RTC clocksource failed rc %d\n", rc); diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index f10c0afa1cb..218cdb16163 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -20,6 +20,7 @@ #include <asm/xcr.h> #include <asm/suspend.h> #include <asm/debugreg.h> +#include <asm/fpu-internal.h> /* pcntxt_mask */ #ifdef CONFIG_X86_32 static struct saved_context saved_context; @@ -114,7 +115,7 @@ static void __save_processor_state(struct saved_context *ctxt) void save_processor_state(void) { __save_processor_state(&saved_context); - save_sched_clock_state(); + x86_platform.save_sched_clock_state(); } #ifdef CONFIG_X86_32 EXPORT_SYMBOL(save_processor_state); @@ -224,6 +225,7 @@ static void __restore_processor_state(struct saved_context *ctxt) fix_processor_context(); do_fpu_end(); + x86_platform.restore_sched_clock_state(); mtrr_bp_restore(); } @@ -231,7 +233,6 @@ static void __restore_processor_state(struct saved_context *ctxt) void restore_processor_state(void) { __restore_processor_state(&saved_context); - restore_sched_clock_state(); } #ifdef CONFIG_X86_32 EXPORT_SYMBOL(restore_processor_state); diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c index 3769079874d..74202c1910c 100644 --- a/arch/x86/power/hibernate_32.c +++ b/arch/x86/power/hibernate_32.c @@ -10,7 +10,6 @@ #include <linux/suspend.h> #include <linux/bootmem.h> -#include <asm/system.h> #include <asm/page.h> #include <asm/pgtable.h> #include <asm/mmzone.h> diff --git a/arch/x86/syscalls/Makefile b/arch/x86/syscalls/Makefile new file mode 100644 index 00000000000..3236aebc828 --- /dev/null +++ b/arch/x86/syscalls/Makefile @@ -0,0 +1,55 @@ +out := $(obj)/../include/generated/asm + +# Create output directory if not already present +_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') + +syscall32 := $(srctree)/$(src)/syscall_32.tbl +syscall64 := $(srctree)/$(src)/syscall_64.tbl + +syshdr := $(srctree)/$(src)/syscallhdr.sh +systbl := $(srctree)/$(src)/syscalltbl.sh + +quiet_cmd_syshdr = SYSHDR $@ + cmd_syshdr = $(CONFIG_SHELL) '$(syshdr)' '$<' '$@' \ + '$(syshdr_abi_$(basetarget))' \ + '$(syshdr_pfx_$(basetarget))' \ + '$(syshdr_offset_$(basetarget))' +quiet_cmd_systbl = SYSTBL $@ + cmd_systbl = $(CONFIG_SHELL) '$(systbl)' $< $@ + +syshdr_abi_unistd_32 := i386 +$(out)/unistd_32.h: $(syscall32) $(syshdr) + $(call if_changed,syshdr) + +syshdr_abi_unistd_32_ia32 := i386 +syshdr_pfx_unistd_32_ia32 := ia32_ +$(out)/unistd_32_ia32.h: $(syscall32) $(syshdr) + $(call if_changed,syshdr) + +syshdr_abi_unistd_x32 := common,x32 +syshdr_offset_unistd_x32 := __X32_SYSCALL_BIT +$(out)/unistd_x32.h: $(syscall64) $(syshdr) + $(call if_changed,syshdr) + +syshdr_abi_unistd_64 := common,64 +$(out)/unistd_64.h: $(syscall64) $(syshdr) + $(call if_changed,syshdr) + +syshdr_abi_unistd_64_x32 := x32 +syshdr_pfx_unistd_64_x32 := x32_ +$(out)/unistd_64_x32.h: $(syscall64) $(syshdr) + $(call if_changed,syshdr) + +$(out)/syscalls_32.h: $(syscall32) $(systbl) + $(call if_changed,systbl) +$(out)/syscalls_64.h: $(syscall64) $(systbl) + $(call if_changed,systbl) + +syshdr-y += unistd_32.h unistd_64.h unistd_x32.h +syshdr-y += syscalls_32.h +syshdr-$(CONFIG_X86_64) += unistd_32_ia32.h unistd_64_x32.h +syshdr-$(CONFIG_X86_64) += syscalls_64.h + +targets += $(syshdr-y) + +all: $(addprefix $(out)/,$(targets)) diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl new file mode 100644 index 00000000000..29f9f0554f7 --- /dev/null +++ b/arch/x86/syscalls/syscall_32.tbl @@ -0,0 +1,357 @@ +# +# 32-bit system call numbers and entry vectors +# +# The format is: +# <number> <abi> <name> <entry point> <compat entry point> +# +# The abi is always "i386" for this file. +# +0 i386 restart_syscall sys_restart_syscall +1 i386 exit sys_exit +2 i386 fork ptregs_fork stub32_fork +3 i386 read sys_read +4 i386 write sys_write +5 i386 open sys_open compat_sys_open +6 i386 close sys_close +7 i386 waitpid sys_waitpid sys32_waitpid +8 i386 creat sys_creat +9 i386 link sys_link +10 i386 unlink sys_unlink +11 i386 execve ptregs_execve stub32_execve +12 i386 chdir sys_chdir +13 i386 time sys_time compat_sys_time +14 i386 mknod sys_mknod +15 i386 chmod sys_chmod +16 i386 lchown sys_lchown16 +17 i386 break +18 i386 oldstat sys_stat +19 i386 lseek sys_lseek sys32_lseek +20 i386 getpid sys_getpid +21 i386 mount sys_mount compat_sys_mount +22 i386 umount sys_oldumount +23 i386 setuid sys_setuid16 +24 i386 getuid sys_getuid16 +25 i386 stime sys_stime compat_sys_stime +26 i386 ptrace sys_ptrace compat_sys_ptrace +27 i386 alarm sys_alarm +28 i386 oldfstat sys_fstat +29 i386 pause sys_pause +30 i386 utime sys_utime compat_sys_utime +31 i386 stty +32 i386 gtty +33 i386 access sys_access +34 i386 nice sys_nice +35 i386 ftime +36 i386 sync sys_sync +37 i386 kill sys_kill sys32_kill +38 i386 rename sys_rename +39 i386 mkdir sys_mkdir +40 i386 rmdir sys_rmdir +41 i386 dup sys_dup +42 i386 pipe sys_pipe +43 i386 times sys_times compat_sys_times +44 i386 prof +45 i386 brk sys_brk +46 i386 setgid sys_setgid16 +47 i386 getgid sys_getgid16 +48 i386 signal sys_signal +49 i386 geteuid sys_geteuid16 +50 i386 getegid sys_getegid16 +51 i386 acct sys_acct +52 i386 umount2 sys_umount +53 i386 lock +54 i386 ioctl sys_ioctl compat_sys_ioctl +55 i386 fcntl sys_fcntl compat_sys_fcntl64 +56 i386 mpx +57 i386 setpgid sys_setpgid +58 i386 ulimit +59 i386 oldolduname sys_olduname +60 i386 umask sys_umask +61 i386 chroot sys_chroot +62 i386 ustat sys_ustat compat_sys_ustat +63 i386 dup2 sys_dup2 +64 i386 getppid sys_getppid +65 i386 getpgrp sys_getpgrp +66 i386 setsid sys_setsid +67 i386 sigaction sys_sigaction sys32_sigaction +68 i386 sgetmask sys_sgetmask +69 i386 ssetmask sys_ssetmask +70 i386 setreuid sys_setreuid16 +71 i386 setregid sys_setregid16 +72 i386 sigsuspend sys_sigsuspend sys32_sigsuspend +73 i386 sigpending sys_sigpending compat_sys_sigpending +74 i386 sethostname sys_sethostname +75 i386 setrlimit sys_setrlimit compat_sys_setrlimit +76 i386 getrlimit sys_old_getrlimit compat_sys_old_getrlimit +77 i386 getrusage sys_getrusage compat_sys_getrusage +78 i386 gettimeofday sys_gettimeofday compat_sys_gettimeofday +79 i386 settimeofday sys_settimeofday compat_sys_settimeofday +80 i386 getgroups sys_getgroups16 +81 i386 setgroups sys_setgroups16 +82 i386 select sys_old_select compat_sys_old_select +83 i386 symlink sys_symlink +84 i386 oldlstat sys_lstat +85 i386 readlink sys_readlink +86 i386 uselib sys_uselib +87 i386 swapon sys_swapon +88 i386 reboot sys_reboot +89 i386 readdir sys_old_readdir compat_sys_old_readdir +90 i386 mmap sys_old_mmap sys32_mmap +91 i386 munmap sys_munmap +92 i386 truncate sys_truncate +93 i386 ftruncate sys_ftruncate +94 i386 fchmod sys_fchmod +95 i386 fchown sys_fchown16 +96 i386 getpriority sys_getpriority +97 i386 setpriority sys_setpriority +98 i386 profil +99 i386 statfs sys_statfs compat_sys_statfs +100 i386 fstatfs sys_fstatfs compat_sys_fstatfs +101 i386 ioperm sys_ioperm +102 i386 socketcall sys_socketcall compat_sys_socketcall +103 i386 syslog sys_syslog +104 i386 setitimer sys_setitimer compat_sys_setitimer +105 i386 getitimer sys_getitimer compat_sys_getitimer +106 i386 stat sys_newstat compat_sys_newstat +107 i386 lstat sys_newlstat compat_sys_newlstat +108 i386 fstat sys_newfstat compat_sys_newfstat +109 i386 olduname sys_uname +110 i386 iopl ptregs_iopl stub32_iopl +111 i386 vhangup sys_vhangup +112 i386 idle +113 i386 vm86old ptregs_vm86old sys32_vm86_warning +114 i386 wait4 sys_wait4 compat_sys_wait4 +115 i386 swapoff sys_swapoff +116 i386 sysinfo sys_sysinfo compat_sys_sysinfo +117 i386 ipc sys_ipc sys32_ipc +118 i386 fsync sys_fsync +119 i386 sigreturn ptregs_sigreturn stub32_sigreturn +120 i386 clone ptregs_clone stub32_clone +121 i386 setdomainname sys_setdomainname +122 i386 uname sys_newuname +123 i386 modify_ldt sys_modify_ldt +124 i386 adjtimex sys_adjtimex compat_sys_adjtimex +125 i386 mprotect sys_mprotect sys32_mprotect +126 i386 sigprocmask sys_sigprocmask compat_sys_sigprocmask +127 i386 create_module +128 i386 init_module sys_init_module +129 i386 delete_module sys_delete_module +130 i386 get_kernel_syms +131 i386 quotactl sys_quotactl sys32_quotactl +132 i386 getpgid sys_getpgid +133 i386 fchdir sys_fchdir +134 i386 bdflush sys_bdflush +135 i386 sysfs sys_sysfs +136 i386 personality sys_personality +137 i386 afs_syscall +138 i386 setfsuid sys_setfsuid16 +139 i386 setfsgid sys_setfsgid16 +140 i386 _llseek sys_llseek +141 i386 getdents sys_getdents compat_sys_getdents +142 i386 _newselect sys_select compat_sys_select +143 i386 flock sys_flock +144 i386 msync sys_msync +145 i386 readv sys_readv compat_sys_readv +146 i386 writev sys_writev compat_sys_writev +147 i386 getsid sys_getsid +148 i386 fdatasync sys_fdatasync +149 i386 _sysctl sys_sysctl compat_sys_sysctl +150 i386 mlock sys_mlock +151 i386 munlock sys_munlock +152 i386 mlockall sys_mlockall +153 i386 munlockall sys_munlockall +154 i386 sched_setparam sys_sched_setparam +155 i386 sched_getparam sys_sched_getparam +156 i386 sched_setscheduler sys_sched_setscheduler +157 i386 sched_getscheduler sys_sched_getscheduler +158 i386 sched_yield sys_sched_yield +159 i386 sched_get_priority_max sys_sched_get_priority_max +160 i386 sched_get_priority_min sys_sched_get_priority_min +161 i386 sched_rr_get_interval sys_sched_rr_get_interval sys32_sched_rr_get_interval +162 i386 nanosleep sys_nanosleep compat_sys_nanosleep +163 i386 mremap sys_mremap +164 i386 setresuid sys_setresuid16 +165 i386 getresuid sys_getresuid16 +166 i386 vm86 ptregs_vm86 sys32_vm86_warning +167 i386 query_module +168 i386 poll sys_poll +169 i386 nfsservctl +170 i386 setresgid sys_setresgid16 +171 i386 getresgid sys_getresgid16 +172 i386 prctl sys_prctl +173 i386 rt_sigreturn ptregs_rt_sigreturn stub32_rt_sigreturn +174 i386 rt_sigaction sys_rt_sigaction sys32_rt_sigaction +175 i386 rt_sigprocmask sys_rt_sigprocmask +176 i386 rt_sigpending sys_rt_sigpending sys32_rt_sigpending +177 i386 rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait +178 i386 rt_sigqueueinfo sys_rt_sigqueueinfo sys32_rt_sigqueueinfo +179 i386 rt_sigsuspend sys_rt_sigsuspend +180 i386 pread64 sys_pread64 sys32_pread +181 i386 pwrite64 sys_pwrite64 sys32_pwrite +182 i386 chown sys_chown16 +183 i386 getcwd sys_getcwd +184 i386 capget sys_capget +185 i386 capset sys_capset +186 i386 sigaltstack ptregs_sigaltstack stub32_sigaltstack +187 i386 sendfile sys_sendfile sys32_sendfile +188 i386 getpmsg +189 i386 putpmsg +190 i386 vfork ptregs_vfork stub32_vfork +191 i386 ugetrlimit sys_getrlimit compat_sys_getrlimit +192 i386 mmap2 sys_mmap_pgoff +193 i386 truncate64 sys_truncate64 sys32_truncate64 +194 i386 ftruncate64 sys_ftruncate64 sys32_ftruncate64 +195 i386 stat64 sys_stat64 sys32_stat64 +196 i386 lstat64 sys_lstat64 sys32_lstat64 +197 i386 fstat64 sys_fstat64 sys32_fstat64 +198 i386 lchown32 sys_lchown +199 i386 getuid32 sys_getuid +200 i386 getgid32 sys_getgid +201 i386 geteuid32 sys_geteuid +202 i386 getegid32 sys_getegid +203 i386 setreuid32 sys_setreuid +204 i386 setregid32 sys_setregid +205 i386 getgroups32 sys_getgroups +206 i386 setgroups32 sys_setgroups +207 i386 fchown32 sys_fchown +208 i386 setresuid32 sys_setresuid +209 i386 getresuid32 sys_getresuid +210 i386 setresgid32 sys_setresgid +211 i386 getresgid32 sys_getresgid +212 i386 chown32 sys_chown +213 i386 setuid32 sys_setuid +214 i386 setgid32 sys_setgid +215 i386 setfsuid32 sys_setfsuid +216 i386 setfsgid32 sys_setfsgid +217 i386 pivot_root sys_pivot_root +218 i386 mincore sys_mincore +219 i386 madvise sys_madvise +220 i386 getdents64 sys_getdents64 compat_sys_getdents64 +221 i386 fcntl64 sys_fcntl64 compat_sys_fcntl64 +# 222 is unused +# 223 is unused +224 i386 gettid sys_gettid +225 i386 readahead sys_readahead sys32_readahead +226 i386 setxattr sys_setxattr +227 i386 lsetxattr sys_lsetxattr +228 i386 fsetxattr sys_fsetxattr +229 i386 getxattr sys_getxattr +230 i386 lgetxattr sys_lgetxattr +231 i386 fgetxattr sys_fgetxattr +232 i386 listxattr sys_listxattr +233 i386 llistxattr sys_llistxattr +234 i386 flistxattr sys_flistxattr +235 i386 removexattr sys_removexattr +236 i386 lremovexattr sys_lremovexattr +237 i386 fremovexattr sys_fremovexattr +238 i386 tkill sys_tkill +239 i386 sendfile64 sys_sendfile64 +240 i386 futex sys_futex compat_sys_futex +241 i386 sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity +242 i386 sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity +243 i386 set_thread_area sys_set_thread_area +244 i386 get_thread_area sys_get_thread_area +245 i386 io_setup sys_io_setup compat_sys_io_setup +246 i386 io_destroy sys_io_destroy +247 i386 io_getevents sys_io_getevents compat_sys_io_getevents +248 i386 io_submit sys_io_submit compat_sys_io_submit +249 i386 io_cancel sys_io_cancel +250 i386 fadvise64 sys_fadvise64 sys32_fadvise64 +# 251 is available for reuse (was briefly sys_set_zone_reclaim) +252 i386 exit_group sys_exit_group +253 i386 lookup_dcookie sys_lookup_dcookie sys32_lookup_dcookie +254 i386 epoll_create sys_epoll_create +255 i386 epoll_ctl sys_epoll_ctl +256 i386 epoll_wait sys_epoll_wait +257 i386 remap_file_pages sys_remap_file_pages +258 i386 set_tid_address sys_set_tid_address +259 i386 timer_create sys_timer_create compat_sys_timer_create +260 i386 timer_settime sys_timer_settime compat_sys_timer_settime +261 i386 timer_gettime sys_timer_gettime compat_sys_timer_gettime +262 i386 timer_getoverrun sys_timer_getoverrun +263 i386 timer_delete sys_timer_delete +264 i386 clock_settime sys_clock_settime compat_sys_clock_settime +265 i386 clock_gettime sys_clock_gettime compat_sys_clock_gettime +266 i386 clock_getres sys_clock_getres compat_sys_clock_getres +267 i386 clock_nanosleep sys_clock_nanosleep compat_sys_clock_nanosleep +268 i386 statfs64 sys_statfs64 compat_sys_statfs64 +269 i386 fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 +270 i386 tgkill sys_tgkill +271 i386 utimes sys_utimes compat_sys_utimes +272 i386 fadvise64_64 sys_fadvise64_64 sys32_fadvise64_64 +273 i386 vserver +274 i386 mbind sys_mbind +275 i386 get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy +276 i386 set_mempolicy sys_set_mempolicy +277 i386 mq_open sys_mq_open compat_sys_mq_open +278 i386 mq_unlink sys_mq_unlink +279 i386 mq_timedsend sys_mq_timedsend compat_sys_mq_timedsend +280 i386 mq_timedreceive sys_mq_timedreceive compat_sys_mq_timedreceive +281 i386 mq_notify sys_mq_notify compat_sys_mq_notify +282 i386 mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr +283 i386 kexec_load sys_kexec_load compat_sys_kexec_load +284 i386 waitid sys_waitid compat_sys_waitid +# 285 sys_setaltroot +286 i386 add_key sys_add_key +287 i386 request_key sys_request_key +288 i386 keyctl sys_keyctl +289 i386 ioprio_set sys_ioprio_set +290 i386 ioprio_get sys_ioprio_get +291 i386 inotify_init sys_inotify_init +292 i386 inotify_add_watch sys_inotify_add_watch +293 i386 inotify_rm_watch sys_inotify_rm_watch +294 i386 migrate_pages sys_migrate_pages +295 i386 openat sys_openat compat_sys_openat +296 i386 mkdirat sys_mkdirat +297 i386 mknodat sys_mknodat +298 i386 fchownat sys_fchownat +299 i386 futimesat sys_futimesat compat_sys_futimesat +300 i386 fstatat64 sys_fstatat64 sys32_fstatat +301 i386 unlinkat sys_unlinkat +302 i386 renameat sys_renameat +303 i386 linkat sys_linkat +304 i386 symlinkat sys_symlinkat +305 i386 readlinkat sys_readlinkat +306 i386 fchmodat sys_fchmodat +307 i386 faccessat sys_faccessat +308 i386 pselect6 sys_pselect6 compat_sys_pselect6 +309 i386 ppoll sys_ppoll compat_sys_ppoll +310 i386 unshare sys_unshare +311 i386 set_robust_list sys_set_robust_list compat_sys_set_robust_list +312 i386 get_robust_list sys_get_robust_list compat_sys_get_robust_list +313 i386 splice sys_splice +314 i386 sync_file_range sys_sync_file_range sys32_sync_file_range +315 i386 tee sys_tee +316 i386 vmsplice sys_vmsplice compat_sys_vmsplice +317 i386 move_pages sys_move_pages compat_sys_move_pages +318 i386 getcpu sys_getcpu +319 i386 epoll_pwait sys_epoll_pwait +320 i386 utimensat sys_utimensat compat_sys_utimensat +321 i386 signalfd sys_signalfd compat_sys_signalfd +322 i386 timerfd_create sys_timerfd_create +323 i386 eventfd sys_eventfd +324 i386 fallocate sys_fallocate sys32_fallocate +325 i386 timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime +326 i386 timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime +327 i386 signalfd4 sys_signalfd4 compat_sys_signalfd4 +328 i386 eventfd2 sys_eventfd2 +329 i386 epoll_create1 sys_epoll_create1 +330 i386 dup3 sys_dup3 +331 i386 pipe2 sys_pipe2 +332 i386 inotify_init1 sys_inotify_init1 +333 i386 preadv sys_preadv compat_sys_preadv +334 i386 pwritev sys_pwritev compat_sys_pwritev +335 i386 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo +336 i386 perf_event_open sys_perf_event_open +337 i386 recvmmsg sys_recvmmsg compat_sys_recvmmsg +338 i386 fanotify_init sys_fanotify_init +339 i386 fanotify_mark sys_fanotify_mark sys32_fanotify_mark +340 i386 prlimit64 sys_prlimit64 +341 i386 name_to_handle_at sys_name_to_handle_at +342 i386 open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at +343 i386 clock_adjtime sys_clock_adjtime compat_sys_clock_adjtime +344 i386 syncfs sys_syncfs +345 i386 sendmmsg sys_sendmmsg compat_sys_sendmmsg +346 i386 setns sys_setns +347 i386 process_vm_readv sys_process_vm_readv compat_sys_process_vm_readv +348 i386 process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl new file mode 100644 index 00000000000..dd29a9ea27c --- /dev/null +++ b/arch/x86/syscalls/syscall_64.tbl @@ -0,0 +1,353 @@ +# +# 64-bit system call numbers and entry vectors +# +# The format is: +# <number> <abi> <name> <entry point> +# +# The abi is "common", "64" or "x32" for this file. +# +0 common read sys_read +1 common write sys_write +2 common open sys_open +3 common close sys_close +4 common stat sys_newstat +5 common fstat sys_newfstat +6 common lstat sys_newlstat +7 common poll sys_poll +8 common lseek sys_lseek +9 common mmap sys_mmap +10 common mprotect sys_mprotect +11 common munmap sys_munmap +12 common brk sys_brk +13 64 rt_sigaction sys_rt_sigaction +14 common rt_sigprocmask sys_rt_sigprocmask +15 64 rt_sigreturn stub_rt_sigreturn +16 64 ioctl sys_ioctl +17 common pread64 sys_pread64 +18 common pwrite64 sys_pwrite64 +19 64 readv sys_readv +20 64 writev sys_writev +21 common access sys_access +22 common pipe sys_pipe +23 common select sys_select +24 common sched_yield sys_sched_yield +25 common mremap sys_mremap +26 common msync sys_msync +27 common mincore sys_mincore +28 common madvise sys_madvise +29 common shmget sys_shmget +30 common shmat sys_shmat +31 common shmctl sys_shmctl +32 common dup sys_dup +33 common dup2 sys_dup2 +34 common pause sys_pause +35 common nanosleep sys_nanosleep +36 common getitimer sys_getitimer +37 common alarm sys_alarm +38 common setitimer sys_setitimer +39 common getpid sys_getpid +40 common sendfile sys_sendfile64 +41 common socket sys_socket +42 common connect sys_connect +43 common accept sys_accept +44 common sendto sys_sendto +45 64 recvfrom sys_recvfrom +46 64 sendmsg sys_sendmsg +47 64 recvmsg sys_recvmsg +48 common shutdown sys_shutdown +49 common bind sys_bind +50 common listen sys_listen +51 common getsockname sys_getsockname +52 common getpeername sys_getpeername +53 common socketpair sys_socketpair +54 common setsockopt sys_setsockopt +55 common getsockopt sys_getsockopt +56 common clone stub_clone +57 common fork stub_fork +58 common vfork stub_vfork +59 64 execve stub_execve +60 common exit sys_exit +61 common wait4 sys_wait4 +62 common kill sys_kill +63 common uname sys_newuname +64 common semget sys_semget +65 common semop sys_semop +66 common semctl sys_semctl +67 common shmdt sys_shmdt +68 common msgget sys_msgget +69 common msgsnd sys_msgsnd +70 common msgrcv sys_msgrcv +71 common msgctl sys_msgctl +72 common fcntl sys_fcntl +73 common flock sys_flock +74 common fsync sys_fsync +75 common fdatasync sys_fdatasync +76 common truncate sys_truncate +77 common ftruncate sys_ftruncate +78 common getdents sys_getdents +79 common getcwd sys_getcwd +80 common chdir sys_chdir +81 common fchdir sys_fchdir +82 common rename sys_rename +83 common mkdir sys_mkdir +84 common rmdir sys_rmdir +85 common creat sys_creat +86 common link sys_link +87 common unlink sys_unlink +88 common symlink sys_symlink +89 common readlink sys_readlink +90 common chmod sys_chmod +91 common fchmod sys_fchmod +92 common chown sys_chown +93 common fchown sys_fchown +94 common lchown sys_lchown +95 common umask sys_umask +96 common gettimeofday sys_gettimeofday +97 common getrlimit sys_getrlimit +98 common getrusage sys_getrusage +99 common sysinfo sys_sysinfo +100 common times sys_times +101 64 ptrace sys_ptrace +102 common getuid sys_getuid +103 common syslog sys_syslog +104 common getgid sys_getgid +105 common setuid sys_setuid +106 common setgid sys_setgid +107 common geteuid sys_geteuid +108 common getegid sys_getegid +109 common setpgid sys_setpgid +110 common getppid sys_getppid +111 common getpgrp sys_getpgrp +112 common setsid sys_setsid +113 common setreuid sys_setreuid +114 common setregid sys_setregid +115 common getgroups sys_getgroups +116 common setgroups sys_setgroups +117 common setresuid sys_setresuid +118 common getresuid sys_getresuid +119 common setresgid sys_setresgid +120 common getresgid sys_getresgid +121 common getpgid sys_getpgid +122 common setfsuid sys_setfsuid +123 common setfsgid sys_setfsgid +124 common getsid sys_getsid +125 common capget sys_capget +126 common capset sys_capset +127 64 rt_sigpending sys_rt_sigpending +128 64 rt_sigtimedwait sys_rt_sigtimedwait +129 64 rt_sigqueueinfo sys_rt_sigqueueinfo +130 common rt_sigsuspend sys_rt_sigsuspend +131 64 sigaltstack stub_sigaltstack +132 common utime sys_utime +133 common mknod sys_mknod +134 64 uselib +135 common personality sys_personality +136 common ustat sys_ustat +137 common statfs sys_statfs +138 common fstatfs sys_fstatfs +139 common sysfs sys_sysfs +140 common getpriority sys_getpriority +141 common setpriority sys_setpriority +142 common sched_setparam sys_sched_setparam +143 common sched_getparam sys_sched_getparam +144 common sched_setscheduler sys_sched_setscheduler +145 common sched_getscheduler sys_sched_getscheduler +146 common sched_get_priority_max sys_sched_get_priority_max +147 common sched_get_priority_min sys_sched_get_priority_min +148 common sched_rr_get_interval sys_sched_rr_get_interval +149 common mlock sys_mlock +150 common munlock sys_munlock +151 common mlockall sys_mlockall +152 common munlockall sys_munlockall +153 common vhangup sys_vhangup +154 common modify_ldt sys_modify_ldt +155 common pivot_root sys_pivot_root +156 64 _sysctl sys_sysctl +157 common prctl sys_prctl +158 common arch_prctl sys_arch_prctl +159 common adjtimex sys_adjtimex +160 common setrlimit sys_setrlimit +161 common chroot sys_chroot +162 common sync sys_sync +163 common acct sys_acct +164 common settimeofday sys_settimeofday +165 common mount sys_mount +166 common umount2 sys_umount +167 common swapon sys_swapon +168 common swapoff sys_swapoff +169 common reboot sys_reboot +170 common sethostname sys_sethostname +171 common setdomainname sys_setdomainname +172 common iopl stub_iopl +173 common ioperm sys_ioperm +174 64 create_module +175 common init_module sys_init_module +176 common delete_module sys_delete_module +177 64 get_kernel_syms +178 64 query_module +179 common quotactl sys_quotactl +180 64 nfsservctl +181 common getpmsg +182 common putpmsg +183 common afs_syscall +184 common tuxcall +185 common security +186 common gettid sys_gettid +187 common readahead sys_readahead +188 common setxattr sys_setxattr +189 common lsetxattr sys_lsetxattr +190 common fsetxattr sys_fsetxattr +191 common getxattr sys_getxattr +192 common lgetxattr sys_lgetxattr +193 common fgetxattr sys_fgetxattr +194 common listxattr sys_listxattr +195 common llistxattr sys_llistxattr +196 common flistxattr sys_flistxattr +197 common removexattr sys_removexattr +198 common lremovexattr sys_lremovexattr +199 common fremovexattr sys_fremovexattr +200 common tkill sys_tkill +201 common time sys_time +202 common futex sys_futex +203 common sched_setaffinity sys_sched_setaffinity +204 common sched_getaffinity sys_sched_getaffinity +205 64 set_thread_area +206 common io_setup sys_io_setup +207 common io_destroy sys_io_destroy +208 common io_getevents sys_io_getevents +209 common io_submit sys_io_submit +210 common io_cancel sys_io_cancel +211 64 get_thread_area +212 common lookup_dcookie sys_lookup_dcookie +213 common epoll_create sys_epoll_create +214 64 epoll_ctl_old +215 64 epoll_wait_old +216 common remap_file_pages sys_remap_file_pages +217 common getdents64 sys_getdents64 +218 common set_tid_address sys_set_tid_address +219 common restart_syscall sys_restart_syscall +220 common semtimedop sys_semtimedop +221 common fadvise64 sys_fadvise64 +222 64 timer_create sys_timer_create +223 common timer_settime sys_timer_settime +224 common timer_gettime sys_timer_gettime +225 common timer_getoverrun sys_timer_getoverrun +226 common timer_delete sys_timer_delete +227 common clock_settime sys_clock_settime +228 common clock_gettime sys_clock_gettime +229 common clock_getres sys_clock_getres +230 common clock_nanosleep sys_clock_nanosleep +231 common exit_group sys_exit_group +232 common epoll_wait sys_epoll_wait +233 common epoll_ctl sys_epoll_ctl +234 common tgkill sys_tgkill +235 common utimes sys_utimes +236 64 vserver +237 common mbind sys_mbind +238 common set_mempolicy sys_set_mempolicy +239 common get_mempolicy sys_get_mempolicy +240 common mq_open sys_mq_open +241 common mq_unlink sys_mq_unlink +242 common mq_timedsend sys_mq_timedsend +243 common mq_timedreceive sys_mq_timedreceive +244 64 mq_notify sys_mq_notify +245 common mq_getsetattr sys_mq_getsetattr +246 64 kexec_load sys_kexec_load +247 64 waitid sys_waitid +248 common add_key sys_add_key +249 common request_key sys_request_key +250 common keyctl sys_keyctl +251 common ioprio_set sys_ioprio_set +252 common ioprio_get sys_ioprio_get +253 common inotify_init sys_inotify_init +254 common inotify_add_watch sys_inotify_add_watch +255 common inotify_rm_watch sys_inotify_rm_watch +256 common migrate_pages sys_migrate_pages +257 common openat sys_openat +258 common mkdirat sys_mkdirat +259 common mknodat sys_mknodat +260 common fchownat sys_fchownat +261 common futimesat sys_futimesat +262 common newfstatat sys_newfstatat +263 common unlinkat sys_unlinkat +264 common renameat sys_renameat +265 common linkat sys_linkat +266 common symlinkat sys_symlinkat +267 common readlinkat sys_readlinkat +268 common fchmodat sys_fchmodat +269 common faccessat sys_faccessat +270 common pselect6 sys_pselect6 +271 common ppoll sys_ppoll +272 common unshare sys_unshare +273 64 set_robust_list sys_set_robust_list +274 64 get_robust_list sys_get_robust_list +275 common splice sys_splice +276 common tee sys_tee +277 common sync_file_range sys_sync_file_range +278 64 vmsplice sys_vmsplice +279 64 move_pages sys_move_pages +280 common utimensat sys_utimensat +281 common epoll_pwait sys_epoll_pwait +282 common signalfd sys_signalfd +283 common timerfd_create sys_timerfd_create +284 common eventfd sys_eventfd +285 common fallocate sys_fallocate +286 common timerfd_settime sys_timerfd_settime +287 common timerfd_gettime sys_timerfd_gettime +288 common accept4 sys_accept4 +289 common signalfd4 sys_signalfd4 +290 common eventfd2 sys_eventfd2 +291 common epoll_create1 sys_epoll_create1 +292 common dup3 sys_dup3 +293 common pipe2 sys_pipe2 +294 common inotify_init1 sys_inotify_init1 +295 64 preadv sys_preadv +296 64 pwritev sys_pwritev +297 64 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo +298 common perf_event_open sys_perf_event_open +299 64 recvmmsg sys_recvmmsg +300 common fanotify_init sys_fanotify_init +301 common fanotify_mark sys_fanotify_mark +302 common prlimit64 sys_prlimit64 +303 common name_to_handle_at sys_name_to_handle_at +304 common open_by_handle_at sys_open_by_handle_at +305 common clock_adjtime sys_clock_adjtime +306 common syncfs sys_syncfs +307 64 sendmmsg sys_sendmmsg +308 common setns sys_setns +309 common getcpu sys_getcpu +310 64 process_vm_readv sys_process_vm_readv +311 64 process_vm_writev sys_process_vm_writev +# +# x32-specific system call numbers start at 512 to avoid cache impact +# for native 64-bit operation. +# +512 x32 rt_sigaction sys32_rt_sigaction +513 x32 rt_sigreturn stub_x32_rt_sigreturn +514 x32 ioctl compat_sys_ioctl +515 x32 readv compat_sys_readv +516 x32 writev compat_sys_writev +517 x32 recvfrom compat_sys_recvfrom +518 x32 sendmsg compat_sys_sendmsg +519 x32 recvmsg compat_sys_recvmsg +520 x32 execve stub_x32_execve +521 x32 ptrace compat_sys_ptrace +522 x32 rt_sigpending sys32_rt_sigpending +523 x32 rt_sigtimedwait compat_sys_rt_sigtimedwait +524 x32 rt_sigqueueinfo sys32_rt_sigqueueinfo +525 x32 sigaltstack stub_x32_sigaltstack +526 x32 timer_create compat_sys_timer_create +527 x32 mq_notify compat_sys_mq_notify +528 x32 kexec_load compat_sys_kexec_load +529 x32 waitid compat_sys_waitid +530 x32 set_robust_list compat_sys_set_robust_list +531 x32 get_robust_list compat_sys_get_robust_list +532 x32 vmsplice compat_sys_vmsplice +533 x32 move_pages compat_sys_move_pages +534 x32 preadv compat_sys_preadv64 +535 x32 pwritev compat_sys_pwritev64 +536 x32 rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo +537 x32 recvmmsg compat_sys_recvmmsg +538 x32 sendmmsg compat_sys_sendmmsg +539 x32 process_vm_readv compat_sys_process_vm_readv +540 x32 process_vm_writev compat_sys_process_vm_writev diff --git a/arch/x86/syscalls/syscallhdr.sh b/arch/x86/syscalls/syscallhdr.sh new file mode 100644 index 00000000000..31fd5f1f38f --- /dev/null +++ b/arch/x86/syscalls/syscallhdr.sh @@ -0,0 +1,27 @@ +#!/bin/sh + +in="$1" +out="$2" +my_abis=`echo "($3)" | tr ',' '|'` +prefix="$4" +offset="$5" + +fileguard=_ASM_X86_`basename "$out" | sed \ + -e 'y/abcdefghijklmnopqrstuvwxyz/ABCDEFGHIJKLMNOPQRSTUVWXYZ/' \ + -e 's/[^A-Z0-9_]/_/g' -e 's/__/_/g'` +grep -E "^[0-9A-Fa-fXx]+[[:space:]]+${my_abis}" "$in" | sort -n | ( + echo "#ifndef ${fileguard}" + echo "#define ${fileguard} 1" + echo "" + + while read nr abi name entry ; do + if [ -z "$offset" ]; then + echo "#define __NR_${prefix}${name} $nr" + else + echo "#define __NR_${prefix}${name} ($offset + $nr)" + fi + done + + echo "" + echo "#endif /* ${fileguard} */" +) > "$out" diff --git a/arch/x86/syscalls/syscalltbl.sh b/arch/x86/syscalls/syscalltbl.sh new file mode 100644 index 00000000000..0e7f8ec071e --- /dev/null +++ b/arch/x86/syscalls/syscalltbl.sh @@ -0,0 +1,15 @@ +#!/bin/sh + +in="$1" +out="$2" + +grep '^[0-9]' "$in" | sort -n | ( + while read nr abi name entry compat; do + abi=`echo "$abi" | tr '[a-z]' '[A-Z]'` + if [ -n "$compat" ]; then + echo "__SYSCALL_${abi}($nr, $entry, $compat)" + elif [ -n "$entry" ]; then + echo "__SYSCALL_${abi}($nr, $entry, $entry)" + fi + done +) > "$out" diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig index 1d97bd84b6f..9926e11a772 100644 --- a/arch/x86/um/Kconfig +++ b/arch/x86/um/Kconfig @@ -6,14 +6,6 @@ menu "UML-specific options" menu "Host processor type and features" -config CMPXCHG_LOCAL - bool - default n - -config CMPXCHG_DOUBLE - bool - default n - source "arch/x86/Kconfig.cpu" endmenu @@ -23,8 +15,8 @@ config UML_X86 select GENERIC_FIND_FIRST_BIT config 64BIT - bool - default SUBARCH = "x86_64" + bool "64-bit kernel" if SUBARCH = "x86" + default SUBARCH != "i386" config X86_32 def_bool !64BIT diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile index 8fb58400e41..5d065b2222d 100644 --- a/arch/x86/um/Makefile +++ b/arch/x86/um/Makefile @@ -37,7 +37,8 @@ subarch-$(CONFIG_MODULES) += ../kernel/module.o USER_OBJS := bugs_$(BITS).o ptrace_user.o fault.o extra-y += user-offsets.s -$(obj)/user-offsets.s: c_flags = -Wp,-MD,$(depfile) $(USER_CFLAGS) +$(obj)/user-offsets.s: c_flags = -Wp,-MD,$(depfile) $(USER_CFLAGS) \ + -Iarch/x86/include/generated UNPROFILE_OBJS := stub_segv.o CFLAGS_stub_segv.o := $(CFLAGS_NO_HARDENING) diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h new file mode 100644 index 00000000000..7d01b8c56c0 --- /dev/null +++ b/arch/x86/um/asm/barrier.h @@ -0,0 +1,75 @@ +#ifndef _ASM_UM_BARRIER_H_ +#define _ASM_UM_BARRIER_H_ + +#include <asm/asm.h> +#include <asm/segment.h> +#include <asm/cpufeature.h> +#include <asm/cmpxchg.h> +#include <asm/nops.h> + +#include <linux/kernel.h> +#include <linux/irqflags.h> + +/* + * Force strict CPU ordering. + * And yes, this is required on UP too when we're talking + * to devices. + */ +#ifdef CONFIG_X86_32 + +#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2) +#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2) +#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM) + +#else /* CONFIG_X86_32 */ + +#define mb() asm volatile("mfence" : : : "memory") +#define rmb() asm volatile("lfence" : : : "memory") +#define wmb() asm volatile("sfence" : : : "memory") + +#endif /* CONFIG_X86_32 */ + +#define read_barrier_depends() do { } while (0) + +#ifdef CONFIG_SMP + +#define smp_mb() mb() +#ifdef CONFIG_X86_PPRO_FENCE +#define smp_rmb() rmb() +#else /* CONFIG_X86_PPRO_FENCE */ +#define smp_rmb() barrier() +#endif /* CONFIG_X86_PPRO_FENCE */ + +#ifdef CONFIG_X86_OOSTORE +#define smp_wmb() wmb() +#else /* CONFIG_X86_OOSTORE */ +#define smp_wmb() barrier() +#endif /* CONFIG_X86_OOSTORE */ + +#define smp_read_barrier_depends() read_barrier_depends() +#define set_mb(var, value) do { (void)xchg(&var, value); } while (0) + +#else /* CONFIG_SMP */ + +#define smp_mb() barrier() +#define smp_rmb() barrier() +#define smp_wmb() barrier() +#define smp_read_barrier_depends() do { } while (0) +#define set_mb(var, value) do { var = value; barrier(); } while (0) + +#endif /* CONFIG_SMP */ + +/* + * 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(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC); + alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC); +} + +#endif diff --git a/arch/x86/um/asm/processor.h b/arch/x86/um/asm/processor.h index 2c32df6fe23..04f82e020f2 100644 --- a/arch/x86/um/asm/processor.h +++ b/arch/x86/um/asm/processor.h @@ -17,6 +17,16 @@ #define ARCH_IS_STACKGROW(address) \ (address + 65536 + 32 * sizeof(unsigned long) >= UPT_SP(¤t->thread.regs.regs)) +#include <asm/user.h> + +/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ +static inline void rep_nop(void) +{ + __asm__ __volatile__("rep;nop": : :"memory"); +} + +#define cpu_relax() rep_nop() + #include <asm/processor-generic.h> #endif diff --git a/arch/x86/um/asm/processor_32.h b/arch/x86/um/asm/processor_32.h index 018f732704d..6c6689e574c 100644 --- a/arch/x86/um/asm/processor_32.h +++ b/arch/x86/um/asm/processor_32.h @@ -45,16 +45,6 @@ static inline void arch_copy_thread(struct arch_thread *from, memcpy(&to->tls_array, &from->tls_array, sizeof(from->tls_array)); } -#include <asm/user.h> - -/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ -static inline void rep_nop(void) -{ - __asm__ __volatile__("rep;nop": : :"memory"); -} - -#define cpu_relax() rep_nop() - /* * Default implementation of macro that returns current * instruction pointer ("program counter"). Stolen diff --git a/arch/x86/um/asm/processor_64.h b/arch/x86/um/asm/processor_64.h index 61de92d916c..4b02a8455bd 100644 --- a/arch/x86/um/asm/processor_64.h +++ b/arch/x86/um/asm/processor_64.h @@ -14,14 +14,6 @@ struct arch_thread { struct faultinfo faultinfo; }; -/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ -static inline void rep_nop(void) -{ - __asm__ __volatile__("rep;nop": : :"memory"); -} - -#define cpu_relax() rep_nop() - #define INIT_ARCH_THREAD { .debugregs = { [ 0 ... 7 ] = 0 }, \ .debugregs_seq = 0, \ .fs = 0, \ @@ -37,8 +29,6 @@ static inline void arch_copy_thread(struct arch_thread *from, to->fs = from->fs; } -#include <asm/user.h> - #define current_text_addr() \ ({ void *pc; __asm__("movq $1f,%0\n1:":"=g" (pc)); pc; }) diff --git a/arch/x86/um/bugs_32.c b/arch/x86/um/bugs_32.c index a1fba5fb9db..17d88cf2c6c 100644 --- a/arch/x86/um/bugs_32.c +++ b/arch/x86/um/bugs_32.c @@ -13,8 +13,6 @@ static int host_has_cmov = 1; static jmp_buf cmov_test_return; -#define TASK_PID(task) *((int *) &(((char *) (task))[HOST_TASK_PID])) - static void cmov_sigill_test_handler(int sig) { host_has_cmov = 0; @@ -51,7 +49,7 @@ void arch_examine_signal(int sig, struct uml_pt_regs *regs) * This is testing for a cmov (0x0f 0x4x) instruction causing a * SIGILL in init. */ - if ((sig != SIGILL) || (TASK_PID(get_current()) != 1)) + if ((sig != SIGILL) || (get_current_pid() != 1)) return; if (copy_from_user_proc(tmp, (void *) UPT_IP(regs), 2)) { diff --git a/arch/x86/um/mem_32.c b/arch/x86/um/mem_32.c index 639900a6fde..f40281e5d6a 100644 --- a/arch/x86/um/mem_32.c +++ b/arch/x86/um/mem_32.c @@ -23,14 +23,6 @@ static int __init gate_vma_init(void) gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; gate_vma.vm_page_prot = __P101; - /* - * Make sure the vDSO gets into every core dump. - * Dumping its contents makes post-mortem fully interpretable later - * without matching up the same kernel and hardware config to see - * what PC values meant. - */ - gate_vma.vm_flags |= VM_ALWAYSDUMP; - return 0; } __initcall(gate_vma_init); diff --git a/arch/x86/um/shared/sysdep/ptrace.h b/arch/x86/um/shared/sysdep/ptrace.h index 711b1621747..2bbe1ec2d96 100644 --- a/arch/x86/um/shared/sysdep/ptrace.h +++ b/arch/x86/um/shared/sysdep/ptrace.h @@ -1,5 +1,15 @@ +#ifndef __SYSDEP_X86_PTRACE_H +#define __SYSDEP_X86_PTRACE_H + #ifdef __i386__ #include "ptrace_32.h" #else #include "ptrace_64.h" #endif + +static inline long regs_return_value(struct uml_pt_regs *regs) +{ + return UPT_SYSCALL_RET(regs); +} + +#endif /* __SYSDEP_X86_PTRACE_H */ diff --git a/arch/x86/um/sys_call_table_32.S b/arch/x86/um/sys_call_table_32.S deleted file mode 100644 index a7ca80d2dce..00000000000 --- a/arch/x86/um/sys_call_table_32.S +++ /dev/null @@ -1,26 +0,0 @@ -#include <linux/linkage.h> -/* Steal i386 syscall table for our purposes, but with some slight changes.*/ - -#define sys_iopl sys_ni_syscall -#define sys_ioperm sys_ni_syscall - -#define sys_vm86old sys_ni_syscall -#define sys_vm86 sys_ni_syscall - -#define old_mmap sys_old_mmap - -#define ptregs_fork sys_fork -#define ptregs_execve sys_execve -#define ptregs_iopl sys_iopl -#define ptregs_vm86old sys_vm86old -#define ptregs_clone sys_clone -#define ptregs_vm86 sys_vm86 -#define ptregs_sigaltstack sys_sigaltstack -#define ptregs_vfork sys_vfork - -.section .rodata,"a" - -#include "../kernel/syscall_table_32.S" - -ENTRY(syscall_table_size) -.long .-sys_call_table diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c new file mode 100644 index 00000000000..416bd40c0eb --- /dev/null +++ b/arch/x86/um/sys_call_table_32.c @@ -0,0 +1,55 @@ +/* + * System call table for UML/i386, copied from arch/x86/kernel/syscall_*.c + * with some changes for UML. + */ + +#include <linux/linkage.h> +#include <linux/sys.h> +#include <linux/cache.h> +#include <generated/user_constants.h> + +#define __NO_STUBS + +/* + * Below you can see, in terms of #define's, the differences between the x86-64 + * and the UML syscall table. + */ + +/* Not going to be implemented by UML, since we have no hardware. */ +#define sys_iopl sys_ni_syscall +#define sys_ioperm sys_ni_syscall + +#define sys_vm86old sys_ni_syscall +#define sys_vm86 sys_ni_syscall + +#define old_mmap sys_old_mmap + +#define ptregs_fork sys_fork +#define ptregs_execve sys_execve +#define ptregs_iopl sys_iopl +#define ptregs_vm86old sys_vm86old +#define ptregs_clone sys_clone +#define ptregs_vm86 sys_vm86 +#define ptregs_sigaltstack sys_sigaltstack +#define ptregs_vfork sys_vfork + +#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void sym(void) ; +#include <asm/syscalls_32.h> + +#undef __SYSCALL_I386 +#define __SYSCALL_I386(nr, sym, compat) [ nr ] = sym, + +typedef void (*sys_call_ptr_t)(void); + +extern void sys_ni_syscall(void); + +const sys_call_ptr_t sys_call_table[] __cacheline_aligned = { + /* + * Smells like a compiler bug -- it doesn't work + * when the & below is removed. + */ + [0 ... __NR_syscall_max] = &sys_ni_syscall, +#include <asm/syscalls_32.h> +}; + +int syscall_table_size = sizeof(sys_call_table); diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c index 99522f78b16..9924776f426 100644 --- a/arch/x86/um/sys_call_table_64.c +++ b/arch/x86/um/sys_call_table_64.c @@ -1,11 +1,12 @@ /* - * System call table for UML/x86-64, copied from arch/x86_64/kernel/syscall.c + * System call table for UML/x86-64, copied from arch/x86/kernel/syscall_*.c * with some changes for UML. */ #include <linux/linkage.h> #include <linux/sys.h> #include <linux/cache.h> +#include <generated/user_constants.h> #define __NO_STUBS @@ -34,31 +35,26 @@ #define stub_sigaltstack sys_sigaltstack #define stub_rt_sigreturn sys_rt_sigreturn -#define __SYSCALL(nr, sym) extern asmlinkage void sym(void) ; -#undef _ASM_X86_UNISTD_64_H -#include "../../x86/include/asm/unistd_64.h" +#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat) +#define __SYSCALL_X32(nr, sym, compat) /* Not supported */ -#undef __SYSCALL -#define __SYSCALL(nr, sym) [ nr ] = sym, -#undef _ASM_X86_UNISTD_64_H +#define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ; +#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); -/* - * We used to have a trick here which made sure that holes in the - * x86_64 table were filled in with sys_ni_syscall, but a comment in - * unistd_64.h says that holes aren't allowed, so the trick was - * removed. - * The trick looked like this - * [0 ... UM_NR_syscall_max] = &sys_ni_syscall - * before including unistd_64.h - the later initializations overwrote - * the sys_ni_syscall filler. - */ - -sys_call_ptr_t sys_call_table[] __cacheline_aligned = { -#include <asm/unistd_64.h> +const sys_call_ptr_t sys_call_table[] __cacheline_aligned = { + /* + * Smells like a compiler bug -- it doesn't work + * when the & below is removed. + */ + [0 ... __NR_syscall_max] = &sys_ni_syscall, +#include <asm/syscalls_64.h> }; int syscall_table_size = sizeof(sys_call_table); diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c index ca49be8ddd0..ce7e3607a87 100644 --- a/arch/x86/um/user-offsets.c +++ b/arch/x86/um/user-offsets.c @@ -8,6 +8,20 @@ #include <asm/ptrace.h> #include <asm/types.h> +#ifdef __i386__ +#define __SYSCALL_I386(nr, sym, compat) [nr] = 1, +static char syscalls[] = { +#include <asm/syscalls_32.h> +}; +#else +#define __SYSCALL_64(nr, sym, compat) [nr] = 1, +#define __SYSCALL_COMMON(nr, sym, compat) [nr] = 1, +#define __SYSCALL_X32(nr, sym, compat) /* Not supported */ +static char syscalls[] = { +#include <asm/syscalls_64.h> +}; +#endif + #define DEFINE(sym, val) \ asm volatile("\n->" #sym " %0 " #val : : "i" (val)) @@ -77,4 +91,7 @@ void foo(void) DEFINE(UM_PROT_READ, PROT_READ); DEFINE(UM_PROT_WRITE, PROT_WRITE); DEFINE(UM_PROT_EXEC, PROT_EXEC); + + DEFINE(__NR_syscall_max, sizeof(syscalls) - 1); + DEFINE(NR_syscalls, sizeof(syscalls)); } diff --git a/arch/x86/um/vdso/vma.c b/arch/x86/um/vdso/vma.c index 91f4ec9a0a5..af91901babb 100644 --- a/arch/x86/um/vdso/vma.c +++ b/arch/x86/um/vdso/vma.c @@ -64,8 +64,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) err = install_special_mapping(mm, um_vdso_addr, PAGE_SIZE, VM_READ|VM_EXEC| - VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC| - VM_ALWAYSDUMP, + VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, vdsop); up_write(&mm->mmap_sem); diff --git a/arch/x86/vdso/.gitignore b/arch/x86/vdso/.gitignore index 60274d5746e..3282874bc61 100644 --- a/arch/x86/vdso/.gitignore +++ b/arch/x86/vdso/.gitignore @@ -1,5 +1,7 @@ vdso.lds vdso-syms.lds +vdsox32.lds +vdsox32-syms.lds vdso32-syms.lds vdso32-syscall-syms.lds vdso32-sysenter-syms.lds diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index 5d179502a52..fd14be1d147 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -3,21 +3,29 @@ # VDSO64-$(CONFIG_X86_64) := y +VDSOX32-$(CONFIG_X86_X32_ABI) := y VDSO32-$(CONFIG_X86_32) := y VDSO32-$(CONFIG_COMPAT) := y vdso-install-$(VDSO64-y) += vdso.so +vdso-install-$(VDSOX32-y) += vdsox32.so vdso-install-$(VDSO32-y) += $(vdso32-images) # files to link into the vdso vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o +vobjs-$(VDSOX32-y) += $(vobjx32s-compat) + +# Filter out x32 objects. +vobj64s := $(filter-out $(vobjx32s-compat),$(vobjs-y)) + # files to link into kernel obj-$(VDSO64-y) += vma.o vdso.o +obj-$(VDSOX32-y) += vdsox32.o obj-$(VDSO32-y) += vdso32.o vdso32-setup.o -vobjs := $(foreach F,$(vobjs-y),$(obj)/$F) +vobjs := $(foreach F,$(vobj64s),$(obj)/$F) $(obj)/vdso.o: $(obj)/vdso.so @@ -73,6 +81,42 @@ $(obj)/%-syms.lds: $(obj)/%.so.dbg FORCE $(call if_changed,vdsosym) # +# X32 processes use x32 vDSO to access 64bit kernel data. +# +# Build x32 vDSO image: +# 1. Compile x32 vDSO as 64bit. +# 2. Convert object files to x32. +# 3. Build x32 VDSO image with x32 objects, which contains 64bit codes +# so that it can reach 64bit address space with 64bit pointers. +# + +targets += vdsox32-syms.lds +obj-$(VDSOX32-y) += vdsox32-syms.lds + +CPPFLAGS_vdsox32.lds = $(CPPFLAGS_vdso.lds) +VDSO_LDFLAGS_vdsox32.lds = -Wl,-m,elf32_x86_64 \ + -Wl,-soname=linux-vdso.so.1 \ + -Wl,-z,max-page-size=4096 \ + -Wl,-z,common-page-size=4096 + +vobjx32s-y := $(vobj64s:.o=-x32.o) +vobjx32s := $(foreach F,$(vobjx32s-y),$(obj)/$F) + +# Convert 64bit object file to x32 for x32 vDSO. +quiet_cmd_x32 = X32 $@ + cmd_x32 = $(OBJCOPY) -O elf32-x86-64 $< $@ + +$(obj)/%-x32.o: $(obj)/%.o FORCE + $(call if_changed,x32) + +targets += vdsox32.so vdsox32.so.dbg vdsox32.lds $(vobjx32s-y) + +$(obj)/vdsox32.o: $(src)/vdsox32.S $(obj)/vdsox32.so + +$(obj)/vdsox32.so.dbg: $(src)/vdsox32.lds $(vobjx32s) FORCE + $(call if_changed,vdso) + +# # Build multiple 32-bit vDSO images to choose from at boot time. # obj-$(VDSO32-y) += vdso32-syms.lds diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 6bc0e723b6e..885eff49d6a 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -70,100 +70,98 @@ notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) return ret; } +notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) +{ + long ret; + + asm("syscall" : "=a" (ret) : + "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory"); + return ret; +} + + notrace static inline long vgetns(void) { long v; cycles_t cycles; if (gtod->clock.vclock_mode == VCLOCK_TSC) cycles = vread_tsc(); - else + else if (gtod->clock.vclock_mode == VCLOCK_HPET) cycles = vread_hpet(); + else + return 0; v = (cycles - gtod->clock.cycle_last) & gtod->clock.mask; return (v * gtod->clock.mult) >> gtod->clock.shift; } -notrace static noinline int do_realtime(struct timespec *ts) +/* Code size doesn't matter (vdso is 4k anyway) and this is faster. */ +notrace static int __always_inline do_realtime(struct timespec *ts) { unsigned long seq, ns; + int mode; + do { - seq = read_seqbegin(>od->lock); + seq = read_seqcount_begin(>od->seq); + mode = gtod->clock.vclock_mode; ts->tv_sec = gtod->wall_time_sec; ts->tv_nsec = gtod->wall_time_nsec; ns = vgetns(); - } while (unlikely(read_seqretry(>od->lock, seq))); + } while (unlikely(read_seqcount_retry(>od->seq, seq))); + timespec_add_ns(ts, ns); - return 0; + return mode; } -notrace static noinline int do_monotonic(struct timespec *ts) +notrace static int do_monotonic(struct timespec *ts) { - unsigned long seq, ns, secs; + unsigned long seq, ns; + int mode; + do { - seq = read_seqbegin(>od->lock); - secs = gtod->wall_time_sec; - ns = gtod->wall_time_nsec + vgetns(); - secs += gtod->wall_to_monotonic.tv_sec; - ns += gtod->wall_to_monotonic.tv_nsec; - } while (unlikely(read_seqretry(>od->lock, seq))); - - /* wall_time_nsec, vgetns(), and wall_to_monotonic.tv_nsec - * are all guaranteed to be nonnegative. - */ - while (ns >= NSEC_PER_SEC) { - ns -= NSEC_PER_SEC; - ++secs; - } - ts->tv_sec = secs; - ts->tv_nsec = ns; + seq = read_seqcount_begin(>od->seq); + mode = gtod->clock.vclock_mode; + ts->tv_sec = gtod->monotonic_time_sec; + ts->tv_nsec = gtod->monotonic_time_nsec; + ns = vgetns(); + } while (unlikely(read_seqcount_retry(>od->seq, seq))); + timespec_add_ns(ts, ns); - return 0; + return mode; } -notrace static noinline int do_realtime_coarse(struct timespec *ts) +notrace static int do_realtime_coarse(struct timespec *ts) { unsigned long seq; do { - seq = read_seqbegin(>od->lock); + seq = read_seqcount_begin(>od->seq); ts->tv_sec = gtod->wall_time_coarse.tv_sec; ts->tv_nsec = gtod->wall_time_coarse.tv_nsec; - } while (unlikely(read_seqretry(>od->lock, seq))); + } while (unlikely(read_seqcount_retry(>od->seq, seq))); return 0; } -notrace static noinline int do_monotonic_coarse(struct timespec *ts) +notrace static int do_monotonic_coarse(struct timespec *ts) { - unsigned long seq, ns, secs; + unsigned long seq; do { - seq = read_seqbegin(>od->lock); - secs = gtod->wall_time_coarse.tv_sec; - ns = gtod->wall_time_coarse.tv_nsec; - secs += gtod->wall_to_monotonic.tv_sec; - ns += gtod->wall_to_monotonic.tv_nsec; - } while (unlikely(read_seqretry(>od->lock, seq))); - - /* wall_time_nsec and wall_to_monotonic.tv_nsec are - * guaranteed to be between 0 and NSEC_PER_SEC. - */ - if (ns >= NSEC_PER_SEC) { - ns -= NSEC_PER_SEC; - ++secs; - } - ts->tv_sec = secs; - ts->tv_nsec = ns; + seq = read_seqcount_begin(>od->seq); + ts->tv_sec = gtod->monotonic_time_coarse.tv_sec; + ts->tv_nsec = gtod->monotonic_time_coarse.tv_nsec; + } while (unlikely(read_seqcount_retry(>od->seq, seq))); return 0; } notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts) { + int ret = VCLOCK_NONE; + switch (clock) { case CLOCK_REALTIME: - if (likely(gtod->clock.vclock_mode != VCLOCK_NONE)) - return do_realtime(ts); + ret = do_realtime(ts); break; case CLOCK_MONOTONIC: - if (likely(gtod->clock.vclock_mode != VCLOCK_NONE)) - return do_monotonic(ts); + ret = do_monotonic(ts); break; case CLOCK_REALTIME_COARSE: return do_realtime_coarse(ts); @@ -171,32 +169,33 @@ notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts) return do_monotonic_coarse(ts); } - return vdso_fallback_gettime(clock, ts); + if (ret == VCLOCK_NONE) + return vdso_fallback_gettime(clock, ts); + return 0; } int clock_gettime(clockid_t, struct timespec *) __attribute__((weak, alias("__vdso_clock_gettime"))); notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) { - long ret; - if (likely(gtod->clock.vclock_mode != VCLOCK_NONE)) { - if (likely(tv != NULL)) { - BUILD_BUG_ON(offsetof(struct timeval, tv_usec) != - offsetof(struct timespec, tv_nsec) || - sizeof(*tv) != sizeof(struct timespec)); - do_realtime((struct timespec *)tv); - tv->tv_usec /= 1000; - } - if (unlikely(tz != NULL)) { - /* Avoid memcpy. Some old compilers fail to inline it */ - tz->tz_minuteswest = gtod->sys_tz.tz_minuteswest; - tz->tz_dsttime = gtod->sys_tz.tz_dsttime; - } - return 0; + long ret = VCLOCK_NONE; + + if (likely(tv != NULL)) { + BUILD_BUG_ON(offsetof(struct timeval, tv_usec) != + offsetof(struct timespec, tv_nsec) || + sizeof(*tv) != sizeof(struct timespec)); + ret = do_realtime((struct timespec *)tv); + tv->tv_usec /= 1000; } - asm("syscall" : "=a" (ret) : - "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory"); - return ret; + if (unlikely(tz != NULL)) { + /* Avoid memcpy. Some old compilers fail to inline it */ + tz->tz_minuteswest = gtod->sys_tz.tz_minuteswest; + tz->tz_dsttime = gtod->sys_tz.tz_dsttime; + } + + if (ret == VCLOCK_NONE) + return vdso_fallback_gtod(tv, tz); + return 0; } int gettimeofday(struct timeval *, struct timezone *) __attribute__((weak, alias("__vdso_gettimeofday"))); diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c index 468d591dde3..66e6d935982 100644 --- a/arch/x86/vdso/vdso32-setup.c +++ b/arch/x86/vdso/vdso32-setup.c @@ -250,13 +250,7 @@ static int __init gate_vma_init(void) gate_vma.vm_end = FIXADDR_USER_END; gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; gate_vma.vm_page_prot = __P101; - /* - * Make sure the vDSO gets into every core dump. - * Dumping its contents makes post-mortem fully interpretable later - * without matching up the same kernel and hardware config to see - * what PC values meant. - */ - gate_vma.vm_flags |= VM_ALWAYSDUMP; + return 0; } @@ -317,6 +311,11 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) int ret = 0; bool compat; +#ifdef CONFIG_X86_X32_ABI + if (test_thread_flag(TIF_X32)) + return x32_setup_additional_pages(bprm, uses_interp); +#endif + if (vdso_enabled == VDSO_DISABLED) return 0; @@ -343,17 +342,10 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) if (compat_uses_vma || !compat) { /* * MAYWRITE to allow gdb to COW and set breakpoints - * - * Make sure the vDSO gets into every core dump. - * Dumping its contents makes post-mortem fully - * interpretable later without matching up the same - * kernel and hardware config to see what PC values - * meant. */ ret = install_special_mapping(mm, addr, PAGE_SIZE, VM_READ|VM_EXEC| - VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC| - VM_ALWAYSDUMP, + VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, vdso32_pages); if (ret) diff --git a/arch/x86/vdso/vdsox32.S b/arch/x86/vdso/vdsox32.S new file mode 100644 index 00000000000..d6b9a7f42a8 --- /dev/null +++ b/arch/x86/vdso/vdsox32.S @@ -0,0 +1,22 @@ +#include <asm/page_types.h> +#include <linux/linkage.h> +#include <linux/init.h> + +__PAGE_ALIGNED_DATA + + .globl vdsox32_start, vdsox32_end + .align PAGE_SIZE +vdsox32_start: + .incbin "arch/x86/vdso/vdsox32.so" +vdsox32_end: + .align PAGE_SIZE /* extra data here leaks to userspace. */ + +.previous + + .globl vdsox32_pages + .bss + .align 8 + .type vdsox32_pages, @object +vdsox32_pages: + .zero (vdsox32_end - vdsox32_start + PAGE_SIZE - 1) / PAGE_SIZE * 8 + .size vdsox32_pages, .-vdsox32_pages diff --git a/arch/x86/vdso/vdsox32.lds.S b/arch/x86/vdso/vdsox32.lds.S new file mode 100644 index 00000000000..62272aa2ae0 --- /dev/null +++ b/arch/x86/vdso/vdsox32.lds.S @@ -0,0 +1,28 @@ +/* + * Linker script for x32 vDSO. + * We #include the file to define the layout details. + * Here we only choose the prelinked virtual address. + * + * This file defines the version script giving the user-exported symbols in + * the DSO. We can define local symbols here called VDSO* to make their + * values visible using the asm-x86/vdso.h macros from the kernel proper. + */ + +#define VDSO_PRELINK 0 +#include "vdso-layout.lds.S" + +/* + * This controls what userland symbols we export from the vDSO. + */ +VERSION { + LINUX_2.6 { + global: + __vdso_clock_gettime; + __vdso_gettimeofday; + __vdso_getcpu; + __vdso_time; + local: *; + }; +} + +VDSOX32_PRELINK = VDSO_PRELINK; diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c index 153407c35b7..00aaf047b39 100644 --- a/arch/x86/vdso/vma.c +++ b/arch/x86/vdso/vma.c @@ -24,7 +24,44 @@ extern unsigned short vdso_sync_cpuid; extern struct page *vdso_pages[]; static unsigned vdso_size; -static void __init patch_vdso(void *vdso, size_t len) +#ifdef CONFIG_X86_X32_ABI +extern char vdsox32_start[], vdsox32_end[]; +extern struct page *vdsox32_pages[]; +static unsigned vdsox32_size; + +static void __init patch_vdsox32(void *vdso, size_t len) +{ + Elf32_Ehdr *hdr = vdso; + Elf32_Shdr *sechdrs, *alt_sec = 0; + char *secstrings; + void *alt_data; + int i; + + BUG_ON(len < sizeof(Elf32_Ehdr)); + BUG_ON(memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0); + + sechdrs = (void *)hdr + hdr->e_shoff; + secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; + + for (i = 1; i < hdr->e_shnum; i++) { + Elf32_Shdr *shdr = &sechdrs[i]; + if (!strcmp(secstrings + shdr->sh_name, ".altinstructions")) { + alt_sec = shdr; + goto found; + } + } + + /* If we get here, it's probably a bug. */ + pr_warning("patch_vdsox32: .altinstructions not found\n"); + return; /* nothing to patch */ + +found: + alt_data = (void *)hdr + alt_sec->sh_offset; + apply_alternatives(alt_data, alt_data + alt_sec->sh_size); +} +#endif + +static void __init patch_vdso64(void *vdso, size_t len) { Elf64_Ehdr *hdr = vdso; Elf64_Shdr *sechdrs, *alt_sec = 0; @@ -47,7 +84,7 @@ static void __init patch_vdso(void *vdso, size_t len) } /* If we get here, it's probably a bug. */ - pr_warning("patch_vdso: .altinstructions not found\n"); + pr_warning("patch_vdso64: .altinstructions not found\n"); return; /* nothing to patch */ found: @@ -60,12 +97,20 @@ static int __init init_vdso(void) int npages = (vdso_end - vdso_start + PAGE_SIZE - 1) / PAGE_SIZE; int i; - patch_vdso(vdso_start, vdso_end - vdso_start); + patch_vdso64(vdso_start, vdso_end - vdso_start); vdso_size = npages << PAGE_SHIFT; for (i = 0; i < npages; i++) vdso_pages[i] = virt_to_page(vdso_start + i*PAGE_SIZE); +#ifdef CONFIG_X86_X32_ABI + patch_vdsox32(vdsox32_start, vdsox32_end - vdsox32_start); + npages = (vdsox32_end - vdsox32_start + PAGE_SIZE - 1) / PAGE_SIZE; + vdsox32_size = npages << PAGE_SHIFT; + for (i = 0; i < npages; i++) + vdsox32_pages[i] = virt_to_page(vdsox32_start + i*PAGE_SIZE); +#endif + return 0; } subsys_initcall(init_vdso); @@ -103,7 +148,10 @@ static unsigned long vdso_addr(unsigned long start, unsigned len) /* Setup a VMA at program startup for the vsyscall page. Not called for compat tasks */ -int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) +static int setup_additional_pages(struct linux_binprm *bprm, + int uses_interp, + struct page **pages, + unsigned size) { struct mm_struct *mm = current->mm; unsigned long addr; @@ -113,8 +161,8 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) return 0; down_write(&mm->mmap_sem); - addr = vdso_addr(mm->start_stack, vdso_size); - addr = get_unmapped_area(NULL, addr, vdso_size, 0, 0); + addr = vdso_addr(mm->start_stack, size); + addr = get_unmapped_area(NULL, addr, size, 0, 0); if (IS_ERR_VALUE(addr)) { ret = addr; goto up_fail; @@ -122,11 +170,10 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) current->mm->context.vdso = (void *)addr; - ret = install_special_mapping(mm, addr, vdso_size, + ret = install_special_mapping(mm, addr, size, VM_READ|VM_EXEC| - VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC| - VM_ALWAYSDUMP, - vdso_pages); + VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, + pages); if (ret) { current->mm->context.vdso = NULL; goto up_fail; @@ -137,6 +184,20 @@ up_fail: return ret; } +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) +{ + return setup_additional_pages(bprm, uses_interp, vdso_pages, + vdso_size); +} + +#ifdef CONFIG_X86_X32_ABI +int x32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) +{ + return setup_additional_pages(bprm, uses_interp, vdsox32_pages, + vdsox32_size); +} +#endif + static __init int vdso_setup(char *s) { vdso_enabled = simple_strtoul(s, NULL, 0); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index fe06bf4ef0e..4f51bebac02 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -967,7 +967,7 @@ void xen_setup_shared_info(void) xen_setup_mfn_list_list(); } -/* This is called once we have the cpu_possible_map */ +/* This is called once we have the cpu_possible_mask */ void xen_setup_vcpu_info_placement(void) { int cpu; @@ -1232,7 +1232,9 @@ asmlinkage void __init xen_start_kernel(void) /* Prevent unwanted bits from being set in PTEs. */ __supported_pte_mask &= ~_PAGE_GLOBAL; +#if 0 if (!xen_initial_domain()) +#endif __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD); __supported_pte_mask |= _PAGE_IOMAP; @@ -1295,10 +1297,6 @@ asmlinkage void __init xen_start_kernel(void) pgd = (pgd_t *)xen_start_info->pt_base; - if (!xen_initial_domain()) - __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD); - - __supported_pte_mask |= _PAGE_IOMAP; /* Don't do the full vcpu_info placement stuff until we have a possible map and a non-dummy shared_info. */ per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0]; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 91dc2871e33..b8e279479a6 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -415,13 +415,13 @@ static pteval_t iomap_pte(pteval_t val) static pteval_t xen_pte_val(pte_t pte) { pteval_t pteval = pte.pte; - +#if 0 /* If this is a WC pte, convert back from Xen WC to Linux WC */ if ((pteval & (_PAGE_PAT | _PAGE_PCD | _PAGE_PWT)) == _PAGE_PAT) { WARN_ON(!pat_enabled); pteval = (pteval & ~_PAGE_PAT) | _PAGE_PWT; } - +#endif if (xen_initial_domain() && (pteval & _PAGE_IOMAP)) return pteval; @@ -463,7 +463,7 @@ void xen_set_pat(u64 pat) static pte_t xen_make_pte(pteval_t pte) { phys_addr_t addr = (pte & PTE_PFN_MASK); - +#if 0 /* If Linux is trying to set a WC pte, then map to the Xen WC. * If _PAGE_PAT is set, then it probably means it is really * _PAGE_PSE, so avoid fiddling with the PAT mapping and hope @@ -476,7 +476,7 @@ static pte_t xen_make_pte(pteval_t pte) if ((pte & (_PAGE_PCD | _PAGE_PWT)) == _PAGE_PWT) pte = (pte & ~(_PAGE_PCD | _PAGE_PWT)) | _PAGE_PAT; } - +#endif /* * Unprivileged domains are allowed to do IOMAPpings for * PCI passthrough, but not map ISA space. The ISA diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c index b480d4207a4..967633ad98c 100644 --- a/arch/x86/xen/pci-swiotlb-xen.c +++ b/arch/x86/xen/pci-swiotlb-xen.c @@ -12,8 +12,8 @@ int xen_swiotlb __read_mostly; static struct dma_map_ops xen_swiotlb_dma_ops = { .mapping_error = xen_swiotlb_dma_mapping_error, - .alloc_coherent = xen_swiotlb_alloc_coherent, - .free_coherent = xen_swiotlb_free_coherent, + .alloc = xen_swiotlb_alloc_coherent, + .free = xen_swiotlb_free_coherent, .sync_single_for_cpu = xen_swiotlb_sync_single_for_cpu, .sync_single_for_device = xen_swiotlb_sync_single_for_device, .sync_sg_for_cpu = xen_swiotlb_sync_sg_for_cpu, diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index e845555ff48..5fac6919b95 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -415,6 +415,13 @@ static void __cpuinit xen_play_dead(void) /* used only with HOTPLUG_CPU */ play_dead_common(); HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL); cpu_bringup(); + /* + * Balance out the preempt calls - as we are running in cpu_idle + * loop which has been called at bootup from cpu_bringup_and_idle. + * The cpucpu_bringup_and_idle called cpu_bringup which made a + * preempt_disable() So this preempt_enable will balance it out. + */ + preempt_enable(); } #else /* !CONFIG_HOTPLUG_CPU */ diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index cc9b1e182fc..d69cc6c3f80 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -116,9 +116,26 @@ static inline void spin_time_accum_blocked(u64 start) } #endif /* CONFIG_XEN_DEBUG_FS */ +/* + * Size struct xen_spinlock so it's the same as arch_spinlock_t. + */ +#if NR_CPUS < 256 +typedef u8 xen_spinners_t; +# define inc_spinners(xl) \ + asm(LOCK_PREFIX " incb %0" : "+m" ((xl)->spinners) : : "memory"); +# define dec_spinners(xl) \ + asm(LOCK_PREFIX " decb %0" : "+m" ((xl)->spinners) : : "memory"); +#else +typedef u16 xen_spinners_t; +# define inc_spinners(xl) \ + asm(LOCK_PREFIX " incw %0" : "+m" ((xl)->spinners) : : "memory"); +# define dec_spinners(xl) \ + asm(LOCK_PREFIX " decw %0" : "+m" ((xl)->spinners) : : "memory"); +#endif + struct xen_spinlock { unsigned char lock; /* 0 -> free; 1 -> locked */ - unsigned short spinners; /* count of waiting cpus */ + xen_spinners_t spinners; /* count of waiting cpus */ }; static int xen_spin_is_locked(struct arch_spinlock *lock) @@ -164,8 +181,7 @@ static inline struct xen_spinlock *spinning_lock(struct xen_spinlock *xl) wmb(); /* set lock of interest before count */ - asm(LOCK_PREFIX " incw %0" - : "+m" (xl->spinners) : : "memory"); + inc_spinners(xl); return prev; } @@ -176,8 +192,7 @@ static inline struct xen_spinlock *spinning_lock(struct xen_spinlock *xl) */ static inline void unspinning_lock(struct xen_spinlock *xl, struct xen_spinlock *prev) { - asm(LOCK_PREFIX " decw %0" - : "+m" (xl->spinners) : : "memory"); + dec_spinners(xl); wmb(); /* decrement count before restoring lock */ __this_cpu_write(lock_spinners, prev); } @@ -373,6 +388,8 @@ void xen_uninit_lock_cpu(int cpu) void __init xen_init_spinlocks(void) { + BUILD_BUG_ON(sizeof(struct xen_spinlock) > sizeof(arch_spinlock_t)); + pv_lock_ops.spin_is_locked = xen_spin_is_locked; pv_lock_ops.spin_is_contended = xen_spin_is_contended; pv_lock_ops.spin_lock = xen_spin_lock; |